| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Framework and drivers for configuring and reading different PHYs * Based on code in sungem_phy.c and (long-removed) gianfar_phy.c * * Author: Andy Fleming * * Copyright (c) 2004 Freescale Semiconductor, Inc. */ #ifndef __PHY_H #define __PHY_H #include <linux/compiler.h> #include <linux/spinlock.h> #include <linux/ethtool.h> #include <linux/linkmode.h> #include <linux/mdio.h> #include <linux/mii.h> #include <linux/module.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/mod_devicetable.h> #include <linux/android_kabi.h> #include <linux/atomic.h> #define PHY_DEFAULT_FEATURES (SUPPORTED_Autoneg | \ SUPPORTED_TP | \ SUPPORTED_MII) #define PHY_10BT_FEATURES (SUPPORTED_10baseT_Half | \ SUPPORTED_10baseT_Full) #define PHY_100BT_FEATURES (SUPPORTED_100baseT_Half | \ SUPPORTED_100baseT_Full) #define PHY_1000BT_FEATURES (SUPPORTED_1000baseT_Half | \ SUPPORTED_1000baseT_Full) extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_t1_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_fibre_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_gbit_all_ports_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_fec_features) __ro_after_init; extern __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_10gbit_full_features) __ro_after_init; #define PHY_BASIC_FEATURES ((unsigned long *)&phy_basic_features) #define PHY_BASIC_T1_FEATURES ((unsigned long *)&phy_basic_t1_features) #define PHY_GBIT_FEATURES ((unsigned long *)&phy_gbit_features) #define PHY_GBIT_FIBRE_FEATURES ((unsigned long *)&phy_gbit_fibre_features) #define PHY_GBIT_ALL_PORTS_FEATURES ((unsigned long *)&phy_gbit_all_ports_features) #define PHY_10GBIT_FEATURES ((unsigned long *)&phy_10gbit_features) #define PHY_10GBIT_FEC_FEATURES ((unsigned long *)&phy_10gbit_fec_features) #define PHY_10GBIT_FULL_FEATURES ((unsigned long *)&phy_10gbit_full_features) extern const int phy_basic_ports_array[3]; extern const int phy_fibre_port_array[1]; extern const int phy_all_ports_features_array[7]; extern const int phy_10_100_features_array[4]; extern const int phy_basic_t1_features_array[2]; extern const int phy_gbit_features_array[2]; extern const int phy_10gbit_features_array[1]; /* * Set phydev->irq to PHY_POLL if interrupts are not supported, * or not desired for this PHY. Set to PHY_IGNORE_INTERRUPT if * the attached driver handles the interrupt */ #define PHY_POLL -1 #define PHY_IGNORE_INTERRUPT -2 #define PHY_IS_INTERNAL 0x00000001 #define PHY_RST_AFTER_CLK_EN 0x00000002 #define MDIO_DEVICE_IS_PHY 0x80000000 /* Interface Mode definitions */ typedef enum { PHY_INTERFACE_MODE_NA, PHY_INTERFACE_MODE_INTERNAL, PHY_INTERFACE_MODE_MII, PHY_INTERFACE_MODE_GMII, PHY_INTERFACE_MODE_SGMII, PHY_INTERFACE_MODE_TBI, PHY_INTERFACE_MODE_REVMII, PHY_INTERFACE_MODE_RMII, PHY_INTERFACE_MODE_RGMII, PHY_INTERFACE_MODE_RGMII_ID, PHY_INTERFACE_MODE_RGMII_RXID, PHY_INTERFACE_MODE_RGMII_TXID, PHY_INTERFACE_MODE_RTBI, PHY_INTERFACE_MODE_SMII, PHY_INTERFACE_MODE_XGMII, PHY_INTERFACE_MODE_MOCA, PHY_INTERFACE_MODE_QSGMII, PHY_INTERFACE_MODE_TRGMII, PHY_INTERFACE_MODE_1000BASEX, PHY_INTERFACE_MODE_2500BASEX, PHY_INTERFACE_MODE_RXAUI, PHY_INTERFACE_MODE_XAUI, /* 10GBASE-KR, XFI, SFI - single lane 10G Serdes */ PHY_INTERFACE_MODE_10GKR, PHY_INTERFACE_MODE_USXGMII, PHY_INTERFACE_MODE_MAX, } phy_interface_t; /** * phy_supported_speeds - return all speeds currently supported by a phy device * @phy: The phy device to return supported speeds of. * @speeds: buffer to store supported speeds in. * @size: size of speeds buffer. * * Description: Returns the number of supported speeds, and fills * the speeds buffer with the supported speeds. If speeds buffer is * too small to contain all currently supported speeds, will return as * many speeds as can fit. */ unsigned int phy_supported_speeds(struct phy_device *phy, unsigned int *speeds, unsigned int size); /** * phy_modes - map phy_interface_t enum to device tree binding of phy-mode * @interface: enum phy_interface_t value * * Description: maps 'enum phy_interface_t' defined in this file * into the device tree binding of 'phy-mode', so that Ethernet * device driver can get phy interface from device tree. */ static inline const char *phy_modes(phy_interface_t interface) { switch (interface) { case PHY_INTERFACE_MODE_NA: return ""; case PHY_INTERFACE_MODE_INTERNAL: return "internal"; case PHY_INTERFACE_MODE_MII: return "mii"; case PHY_INTERFACE_MODE_GMII: return "gmii"; case PHY_INTERFACE_MODE_SGMII: return "sgmii"; case PHY_INTERFACE_MODE_TBI: return "tbi"; case PHY_INTERFACE_MODE_REVMII: return "rev-mii"; case PHY_INTERFACE_MODE_RMII: return "rmii"; case PHY_INTERFACE_MODE_RGMII: return "rgmii"; case PHY_INTERFACE_MODE_RGMII_ID: return "rgmii-id"; case PHY_INTERFACE_MODE_RGMII_RXID: return "rgmii-rxid"; case PHY_INTERFACE_MODE_RGMII_TXID: return "rgmii-txid"; case PHY_INTERFACE_MODE_RTBI: return "rtbi"; case PHY_INTERFACE_MODE_SMII: return "smii"; case PHY_INTERFACE_MODE_XGMII: return "xgmii"; case PHY_INTERFACE_MODE_MOCA: return "moca"; case PHY_INTERFACE_MODE_QSGMII: return "qsgmii"; case PHY_INTERFACE_MODE_TRGMII: return "trgmii"; case PHY_INTERFACE_MODE_1000BASEX: return "1000base-x"; case PHY_INTERFACE_MODE_2500BASEX: return "2500base-x"; case PHY_INTERFACE_MODE_RXAUI: return "rxaui"; case PHY_INTERFACE_MODE_XAUI: return "xaui"; case PHY_INTERFACE_MODE_10GKR: return "10gbase-kr"; case PHY_INTERFACE_MODE_USXGMII: return "usxgmii"; default: return "unknown"; } } #define PHY_INIT_TIMEOUT 100000 #define PHY_FORCE_TIMEOUT 10 #define PHY_MAX_ADDR 32 /* Used when trying to connect to a specific phy (mii bus id:phy device id) */ #define PHY_ID_FMT "%s:%02x" #define MII_BUS_ID_SIZE 61 /* Or MII_ADDR_C45 into regnum for read/write on mii_bus to enable the 21 bit IEEE 802.3ae clause 45 addressing mode used by 10GIGE phy chips. */ #define MII_ADDR_C45 (1<<30) #define MII_DEVADDR_C45_SHIFT 16 #define MII_REGADDR_C45_MASK GENMASK(15, 0) struct device; struct phylink; struct sk_buff; /* * The Bus class for PHYs. Devices which provide access to * PHYs should register using this structure */ struct mii_bus { struct module *owner; const char *name; char id[MII_BUS_ID_SIZE]; void *priv; int (*read)(struct mii_bus *bus, int addr, int regnum); int (*write)(struct mii_bus *bus, int addr, int regnum, u16 val); int (*reset)(struct mii_bus *bus); /* * A lock to ensure that only one thing can read/write * the MDIO bus at a time */ struct mutex mdio_lock; struct device *parent; enum { MDIOBUS_ALLOCATED = 1, MDIOBUS_REGISTERED, MDIOBUS_UNREGISTERED, MDIOBUS_RELEASED, } state; struct device dev; /* list of all PHYs on bus */ struct mdio_device *mdio_map[PHY_MAX_ADDR]; /* PHY addresses to be ignored when probing */ u32 phy_mask; /* PHY addresses to ignore the TA/read failure */ u32 phy_ignore_ta_mask; /* * An array of interrupts, each PHY's interrupt at the index * matching its address */ int irq[PHY_MAX_ADDR]; /* GPIO reset pulse width in microseconds */ int reset_delay_us; /* RESET GPIO descriptor pointer */ struct gpio_desc *reset_gpiod; }; #define to_mii_bus(d) container_of(d, struct mii_bus, dev) struct mii_bus *mdiobus_alloc_size(size_t); static inline struct mii_bus *mdiobus_alloc(void) { return mdiobus_alloc_size(0); } int __mdiobus_register(struct mii_bus *bus, struct module *owner); #define mdiobus_register(bus) __mdiobus_register(bus, THIS_MODULE) void mdiobus_unregister(struct mii_bus *bus); void mdiobus_free(struct mii_bus *bus); struct mii_bus *devm_mdiobus_alloc_size(struct device *dev, int sizeof_priv); static inline struct mii_bus *devm_mdiobus_alloc(struct device *dev) { return devm_mdiobus_alloc_size(dev, 0); } void devm_mdiobus_free(struct device *dev, struct mii_bus *bus); struct phy_device *mdiobus_scan(struct mii_bus *bus, int addr); #define PHY_INTERRUPT_DISABLED false #define PHY_INTERRUPT_ENABLED true /* PHY state machine states: * * DOWN: PHY device and driver are not ready for anything. probe * should be called if and only if the PHY is in this state, * given that the PHY device exists. * - PHY driver probe function will set the state to READY * * READY: PHY is ready to send and receive packets, but the * controller is not. By default, PHYs which do not implement * probe will be set to this state by phy_probe(). * - start will set the state to UP * * UP: The PHY and attached device are ready to do work. * Interrupts should be started here. * - timer moves to NOLINK or RUNNING * * NOLINK: PHY is up, but not currently plugged in. * - irq or timer will set RUNNING if link comes back * - phy_stop moves to HALTED * * RUNNING: PHY is currently up, running, and possibly sending * and/or receiving packets * - irq or timer will set NOLINK if link goes down * - phy_stop moves to HALTED * * HALTED: PHY is up, but no polling or interrupts are done. Or * PHY is in an error state. * - phy_start moves to UP */ enum phy_state { PHY_DOWN = 0, PHY_READY, PHY_HALTED, PHY_UP, PHY_RUNNING, PHY_NOLINK, }; /** * struct phy_c45_device_ids - 802.3-c45 Device Identifiers * @devices_in_package: Bit vector of devices present. * @device_ids: The device identifer for each present device. */ struct phy_c45_device_ids { u32 devices_in_package; u32 device_ids[8]; }; /* phy_device: An instance of a PHY * * drv: Pointer to the driver for this PHY instance * phy_id: UID for this device found during discovery * c45_ids: 802.3-c45 Device Identifers if is_c45. * is_c45: Set to true if this phy uses clause 45 addressing. * is_internal: Set to true if this phy is internal to a MAC. * is_pseudo_fixed_link: Set to true if this phy is an Ethernet switch, etc. * is_gigabit_capable: Set to true if PHY supports 1000Mbps * has_fixups: Set to true if this phy has fixups/quirks. * suspended: Set to true if this phy has been suspended successfully. * suspended_by_mdio_bus: Set to true if this phy was suspended by MDIO bus. * sysfs_links: Internal boolean tracking sysfs symbolic links setup/removal. * loopback_enabled: Set true if this phy has been loopbacked successfully. * state: state of the PHY for management purposes * dev_flags: Device-specific flags used by the PHY driver. * irq: IRQ number of the PHY's interrupt (-1 if none) * phy_timer: The timer for handling the state machine * attached_dev: The attached enet driver's device instance ptr * adjust_link: Callback for the enet controller to respond to * changes in the link state. * * speed, duplex, pause, supported, advertising, lp_advertising, * and autoneg are used like in mii_if_info * * interrupts currently only supports enabled or disabled, * but could be changed in the future to support enabling * and disabling specific interrupts * * Contains some infrastructure for polling and interrupt * handling, as well as handling shifts in PHY hardware state */ struct phy_device { struct mdio_device mdio; /* Information about the PHY type */ /* And management functions */ struct phy_driver *drv; u32 phy_id; struct phy_c45_device_ids c45_ids; unsigned is_c45:1; unsigned is_internal:1; unsigned is_pseudo_fixed_link:1; unsigned is_gigabit_capable:1; unsigned has_fixups:1; unsigned suspended:1; unsigned suspended_by_mdio_bus:1; unsigned sysfs_links:1; unsigned loopback_enabled:1; unsigned autoneg:1; /* The most recently read link state */ unsigned link:1; unsigned autoneg_complete:1; /* Interrupts are enabled */ unsigned interrupts:1; enum phy_state state; u32 dev_flags; phy_interface_t interface; /* * forced speed & duplex (no autoneg) * partner speed & duplex & pause (autoneg) */ int speed; int duplex; int pause; int asym_pause; /* Union of PHY and Attached devices' supported link modes */ /* See ethtool.h for more info */ __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); /* used with phy_speed_down */ __ETHTOOL_DECLARE_LINK_MODE_MASK(adv_old); /* Energy efficient ethernet modes which should be prohibited */ u32 eee_broken_modes; #ifdef CONFIG_LED_TRIGGER_PHY struct phy_led_trigger *phy_led_triggers; unsigned int phy_num_led_triggers; struct phy_led_trigger *last_triggered; struct phy_led_trigger *led_link_trigger; #endif /* * Interrupt number for this PHY * -1 means no interrupt */ int irq; /* private data pointer */ /* For use by PHYs to maintain extra state */ void *priv; /* Interrupt and Polling infrastructure */ struct delayed_work state_queue; struct mutex lock; struct phylink *phylink; struct net_device *attached_dev; u8 mdix; u8 mdix_ctrl; void (*phy_link_change)(struct phy_device *, bool up, bool do_carrier); void (*adjust_link)(struct net_device *dev); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; #define to_phy_device(d) container_of(to_mdio_device(d), \ struct phy_device, mdio) /* struct phy_driver: Driver structure for a particular PHY type * * driver_data: static driver data * phy_id: The result of reading the UID registers of this PHY * type, and ANDing them with the phy_id_mask. This driver * only works for PHYs with IDs which match this field * name: The friendly name of this PHY type * phy_id_mask: Defines the important bits of the phy_id * features: A mandatory list of features (speed, duplex, etc) * supported by this PHY * flags: A bitfield defining certain other features this PHY * supports (like interrupts) * * All functions are optional. If config_aneg or read_status * are not implemented, the phy core uses the genphy versions. * Note that none of these functions should be called from * interrupt time. The goal is for the bus read/write functions * to be able to block when the bus transaction is happening, * and be freed up by an interrupt (The MPC85xx has this ability, * though it is not currently supported in the driver). */ struct phy_driver { struct mdio_driver_common mdiodrv; u32 phy_id; char *name; u32 phy_id_mask; const unsigned long * const features; u32 flags; const void *driver_data; /* * Called to issue a PHY software reset */ int (*soft_reset)(struct phy_device *phydev); /* * Called to initialize the PHY, * including after a reset */ int (*config_init)(struct phy_device *phydev); /* * Called during discovery. Used to set * up device-specific structures, if any */ int (*probe)(struct phy_device *phydev); /* * Probe the hardware to determine what abilities it has. * Should only set phydev->supported. */ int (*get_features)(struct phy_device *phydev); /* PHY Power Management */ int (*suspend)(struct phy_device *phydev); int (*resume)(struct phy_device *phydev); /* * Configures the advertisement and resets * autonegotiation if phydev->autoneg is on, * forces the speed to the current settings in phydev * if phydev->autoneg is off */ int (*config_aneg)(struct phy_device *phydev); /* Determines the auto negotiation result */ int (*aneg_done)(struct phy_device *phydev); /* Determines the negotiated speed and duplex */ int (*read_status)(struct phy_device *phydev); /* Clears any pending interrupts */ int (*ack_interrupt)(struct phy_device *phydev); /* Enables or disables interrupts */ int (*config_intr)(struct phy_device *phydev); /* * Checks if the PHY generated an interrupt. * For multi-PHY devices with shared PHY interrupt pin * Set interrupt bits have to be cleared. */ int (*did_interrupt)(struct phy_device *phydev); /* Override default interrupt handling */ int (*handle_interrupt)(struct phy_device *phydev); /* Clears up any memory if needed */ void (*remove)(struct phy_device *phydev); /* Returns true if this is a suitable driver for the given * phydev. If NULL, matching is based on phy_id and * phy_id_mask. */ int (*match_phy_device)(struct phy_device *phydev); /* Handles ethtool queries for hardware time stamping. */ int (*ts_info)(struct phy_device *phydev, struct ethtool_ts_info *ti); /* Handles SIOCSHWTSTAMP ioctl for hardware time stamping. */ int (*hwtstamp)(struct phy_device *phydev, struct ifreq *ifr); /* * Requests a Rx timestamp for 'skb'. If the skb is accepted, * the phy driver promises to deliver it using netif_rx() as * soon as a timestamp becomes available. One of the * PTP_CLASS_ values is passed in 'type'. The function must * return true if the skb is accepted for delivery. */ bool (*rxtstamp)(struct phy_device *dev, struct sk_buff *skb, int type); /* * Requests a Tx timestamp for 'skb'. The phy driver promises * to deliver it using skb_complete_tx_timestamp() as soon as a * timestamp becomes available. One of the PTP_CLASS_ values * is passed in 'type'. */ void (*txtstamp)(struct phy_device *dev, struct sk_buff *skb, int type); /* Some devices (e.g. qnap TS-119P II) require PHY register changes to * enable Wake on LAN, so set_wol is provided to be called in the * ethernet driver's set_wol function. */ int (*set_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /* See set_wol, but for checking whether Wake on LAN is enabled. */ void (*get_wol)(struct phy_device *dev, struct ethtool_wolinfo *wol); /* * Called to inform a PHY device driver when the core is about to * change the link state. This callback is supposed to be used as * fixup hook for drivers that need to take action when the link * state changes. Drivers are by no means allowed to mess with the * PHY device structure in their implementations. */ void (*link_change_notify)(struct phy_device *dev); /* * Phy specific driver override for reading a MMD register. * This function is optional for PHY specific drivers. When * not provided, the default MMD read function will be used * by phy_read_mmd(), which will use either a direct read for * Clause 45 PHYs or an indirect read for Clause 22 PHYs. * devnum is the MMD device number within the PHY device, * regnum is the register within the selected MMD device. */ int (*read_mmd)(struct phy_device *dev, int devnum, u16 regnum); /* * Phy specific driver override for writing a MMD register. * This function is optional for PHY specific drivers. When * not provided, the default MMD write function will be used * by phy_write_mmd(), which will use either a direct write for * Clause 45 PHYs, or an indirect write for Clause 22 PHYs. * devnum is the MMD device number within the PHY device, * regnum is the register within the selected MMD device. * val is the value to be written. */ int (*write_mmd)(struct phy_device *dev, int devnum, u16 regnum, u16 val); int (*read_page)(struct phy_device *dev); int (*write_page)(struct phy_device *dev, int page); /* Get the size and type of the eeprom contained within a plug-in * module */ int (*module_info)(struct phy_device *dev, struct ethtool_modinfo *modinfo); /* Get the eeprom information from the plug-in module */ int (*module_eeprom)(struct phy_device *dev, struct ethtool_eeprom *ee, u8 *data); /* Get statistics from the phy using ethtool */ int (*get_sset_count)(struct phy_device *dev); void (*get_strings)(struct phy_device *dev, u8 *data); void (*get_stats)(struct phy_device *dev, struct ethtool_stats *stats, u64 *data); /* Get and Set PHY tunables */ int (*get_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, void *data); int (*set_tunable)(struct phy_device *dev, struct ethtool_tunable *tuna, const void *data); int (*set_loopback)(struct phy_device *dev, bool enable); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; #define to_phy_driver(d) container_of(to_mdio_common_driver(d), \ struct phy_driver, mdiodrv) #define PHY_ANY_ID "MATCH ANY PHY" #define PHY_ANY_UID 0xffffffff #define PHY_ID_MATCH_EXACT(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 0) #define PHY_ID_MATCH_MODEL(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 4) #define PHY_ID_MATCH_VENDOR(id) .phy_id = (id), .phy_id_mask = GENMASK(31, 10) /* A Structure for boards to register fixups with the PHY Lib */ struct phy_fixup { struct list_head list; char bus_id[MII_BUS_ID_SIZE + 3]; u32 phy_uid; u32 phy_uid_mask; int (*run)(struct phy_device *phydev); }; const char *phy_speed_to_str(int speed); const char *phy_duplex_to_str(unsigned int duplex); /* A structure for mapping a particular speed and duplex * combination to a particular SUPPORTED and ADVERTISED value */ struct phy_setting { u32 speed; u8 duplex; u8 bit; }; const struct phy_setting * phy_lookup_setting(int speed, int duplex, const unsigned long *mask, bool exact); size_t phy_speeds(unsigned int *speeds, size_t size, unsigned long *mask); void of_set_phy_supported(struct phy_device *phydev); void of_set_phy_eee_broken(struct phy_device *phydev); int phy_speed_down_core(struct phy_device *phydev); /** * phy_is_started - Convenience function to check whether PHY is started * @phydev: The phy_device struct */ static inline bool phy_is_started(struct phy_device *phydev) { return phydev->state >= PHY_UP; } void phy_resolve_aneg_pause(struct phy_device *phydev); void phy_resolve_aneg_linkmode(struct phy_device *phydev); /** * phy_read - Convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_read(struct phy_device *phydev, u32 regnum) { return mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** * __phy_read - convenience function for reading a given PHY register * @phydev: the phy_device struct * @regnum: register number to read * * The caller must have taken the MDIO bus lock. */ static inline int __phy_read(struct phy_device *phydev, u32 regnum) { return __mdiobus_read(phydev->mdio.bus, phydev->mdio.addr, regnum); } /** * phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * NOTE: MUST NOT be called from interrupt context, * because the bus read/write functions may wait for an interrupt * to conclude the operation. */ static inline int phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * __phy_write - Convenience function for writing a given PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: value to write to @regnum * * The caller must have taken the MDIO bus lock. */ static inline int __phy_write(struct phy_device *phydev, u32 regnum, u16 val) { return __mdiobus_write(phydev->mdio.bus, phydev->mdio.addr, regnum, val); } /** * phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to read from * @regnum: The register on the MMD to read * * Same rules as for phy_read(); */ int phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * __phy_read_mmd - Convenience function for reading a register * from an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to read from * @regnum: The register on the MMD to read * * Same rules as for __phy_read(); */ int __phy_read_mmd(struct phy_device *phydev, int devad, u32 regnum); /** * phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to write to * @regnum: The register on the MMD to read * @val: value to write to @regnum * * Same rules as for phy_write(); */ int phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); /** * __phy_write_mmd - Convenience function for writing a register * on an MMD on a given PHY. * @phydev: The phy_device struct * @devad: The MMD to write to * @regnum: The register on the MMD to read * @val: value to write to @regnum * * Same rules as for __phy_write(); */ int __phy_write_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val); int __phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify_changed(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int phy_modify(struct phy_device *phydev, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd_changed(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int __phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); int phy_modify_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 mask, u16 set); /** * __phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, 0, val); } /** * __phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return __phy_modify(phydev, regnum, val, 0); } /** * phy_set_bits - Convenience function for setting bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to set */ static inline int phy_set_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, 0, val); } /** * phy_clear_bits - Convenience function for clearing bits in a PHY register * @phydev: the phy_device struct * @regnum: register number to write * @val: bits to clear */ static inline int phy_clear_bits(struct phy_device *phydev, u32 regnum, u16 val) { return phy_modify(phydev, regnum, val, 0); } /** * __phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set * * The caller must have taken the MDIO bus lock. */ static inline int __phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * __phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear * * The caller must have taken the MDIO bus lock. */ static inline int __phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return __phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_set_bits_mmd - Convenience function for setting bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to set */ static inline int phy_set_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, 0, val); } /** * phy_clear_bits_mmd - Convenience function for clearing bits in a register * on MMD * @phydev: the phy_device struct * @devad: the MMD containing register to modify * @regnum: register number to modify * @val: bits to clear */ static inline int phy_clear_bits_mmd(struct phy_device *phydev, int devad, u32 regnum, u16 val) { return phy_modify_mmd(phydev, devad, regnum, val, 0); } /** * phy_interrupt_is_valid - Convenience function for testing a given PHY irq * @phydev: the phy_device struct * * NOTE: must be kept in sync with addition/removal of PHY_POLL and * PHY_IGNORE_INTERRUPT */ static inline bool phy_interrupt_is_valid(struct phy_device *phydev) { return phydev->irq != PHY_POLL && phydev->irq != PHY_IGNORE_INTERRUPT; } /** * phy_polling_mode - Convenience function for testing whether polling is * used to detect PHY status changes * @phydev: the phy_device struct */ static inline bool phy_polling_mode(struct phy_device *phydev) { return phydev->irq == PHY_POLL; } /** * phy_is_internal - Convenience function for testing if a PHY is internal * @phydev: the phy_device struct */ static inline bool phy_is_internal(struct phy_device *phydev) { return phydev->is_internal; } /** * phy_interface_mode_is_rgmii - Convenience function for testing if a * PHY interface mode is RGMII (all variants) * @mode: the phy_interface_t enum */ static inline bool phy_interface_mode_is_rgmii(phy_interface_t mode) { return mode >= PHY_INTERFACE_MODE_RGMII && mode <= PHY_INTERFACE_MODE_RGMII_TXID; }; /** * phy_interface_mode_is_8023z() - does the phy interface mode use 802.3z * negotiation * @mode: one of &enum phy_interface_t * * Returns true if the phy interface mode uses the 16-bit negotiation * word as defined in 802.3z. (See 802.3-2015 37.2.1 Config_Reg encoding) */ static inline bool phy_interface_mode_is_8023z(phy_interface_t mode) { return mode == PHY_INTERFACE_MODE_1000BASEX || mode == PHY_INTERFACE_MODE_2500BASEX; } /** * phy_interface_is_rgmii - Convenience function for testing if a PHY interface * is RGMII (all variants) * @phydev: the phy_device struct */ static inline bool phy_interface_is_rgmii(struct phy_device *phydev) { return phy_interface_mode_is_rgmii(phydev->interface); }; /* * phy_is_pseudo_fixed_link - Convenience function for testing if this * PHY is the CPU port facing side of an Ethernet switch, or similar. * @phydev: the phy_device struct */ static inline bool phy_is_pseudo_fixed_link(struct phy_device *phydev) { return phydev->is_pseudo_fixed_link; } int phy_save_page(struct phy_device *phydev); int phy_select_page(struct phy_device *phydev, int page); int phy_restore_page(struct phy_device *phydev, int oldpage, int ret); int phy_read_paged(struct phy_device *phydev, int page, u32 regnum); int phy_write_paged(struct phy_device *phydev, int page, u32 regnum, u16 val); int phy_modify_paged_changed(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); int phy_modify_paged(struct phy_device *phydev, int page, u32 regnum, u16 mask, u16 set); struct phy_device *phy_device_create(struct mii_bus *bus, int addr, u32 phy_id, bool is_c45, struct phy_c45_device_ids *c45_ids); #if IS_ENABLED(CONFIG_PHYLIB) struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45); int phy_device_register(struct phy_device *phy); void phy_device_free(struct phy_device *phydev); #else static inline struct phy_device *get_phy_device(struct mii_bus *bus, int addr, bool is_c45) { return NULL; } static inline int phy_device_register(struct phy_device *phy) { return 0; } static inline void phy_device_free(struct phy_device *phydev) { } #endif /* CONFIG_PHYLIB */ void phy_device_remove(struct phy_device *phydev); int phy_init_hw(struct phy_device *phydev); int phy_suspend(struct phy_device *phydev); int phy_resume(struct phy_device *phydev); int __phy_resume(struct phy_device *phydev); int phy_loopback(struct phy_device *phydev, bool enable); struct phy_device *phy_attach(struct net_device *dev, const char *bus_id, phy_interface_t interface); struct phy_device *phy_find_first(struct mii_bus *bus); int phy_attach_direct(struct net_device *dev, struct phy_device *phydev, u32 flags, phy_interface_t interface); int phy_connect_direct(struct net_device *dev, struct phy_device *phydev, void (*handler)(struct net_device *), phy_interface_t interface); struct phy_device *phy_connect(struct net_device *dev, const char *bus_id, void (*handler)(struct net_device *), phy_interface_t interface); void phy_disconnect(struct phy_device *phydev); void phy_detach(struct phy_device *phydev); void phy_start(struct phy_device *phydev); void phy_stop(struct phy_device *phydev); int phy_start_aneg(struct phy_device *phydev); int phy_aneg_done(struct phy_device *phydev); int phy_speed_down(struct phy_device *phydev, bool sync); int phy_speed_up(struct phy_device *phydev); int phy_restart_aneg(struct phy_device *phydev); int phy_reset_after_clk_enable(struct phy_device *phydev); static inline void phy_device_reset(struct phy_device *phydev, int value) { mdio_device_reset(&phydev->mdio, value); } #define phydev_err(_phydev, format, args...) \ dev_err(&_phydev->mdio.dev, format, ##args) #define phydev_info(_phydev, format, args...) \ dev_info(&_phydev->mdio.dev, format, ##args) #define phydev_warn(_phydev, format, args...) \ dev_warn(&_phydev->mdio.dev, format, ##args) #define phydev_dbg(_phydev, format, args...) \ dev_dbg(&_phydev->mdio.dev, format, ##args) static inline const char *phydev_name(const struct phy_device *phydev) { return dev_name(&phydev->mdio.dev); } void phy_attached_print(struct phy_device *phydev, const char *fmt, ...) __printf(2, 3); void phy_attached_info(struct phy_device *phydev); /* Clause 22 PHY */ int genphy_read_abilities(struct phy_device *phydev); int genphy_setup_forced(struct phy_device *phydev); int genphy_restart_aneg(struct phy_device *phydev); int genphy_config_eee_advert(struct phy_device *phydev); int __genphy_config_aneg(struct phy_device *phydev, bool changed); int genphy_aneg_done(struct phy_device *phydev); int genphy_update_link(struct phy_device *phydev); int genphy_read_lpa(struct phy_device *phydev); int genphy_read_status(struct phy_device *phydev); int genphy_suspend(struct phy_device *phydev); int genphy_resume(struct phy_device *phydev); int genphy_loopback(struct phy_device *phydev, bool enable); int genphy_soft_reset(struct phy_device *phydev); static inline int genphy_config_aneg(struct phy_device *phydev) { return __genphy_config_aneg(phydev, false); } static inline int genphy_no_soft_reset(struct phy_device *phydev) { return 0; } static inline int genphy_no_ack_interrupt(struct phy_device *phydev) { return 0; } static inline int genphy_no_config_intr(struct phy_device *phydev) { return 0; } int genphy_read_mmd_unsupported(struct phy_device *phdev, int devad, u16 regnum); int genphy_write_mmd_unsupported(struct phy_device *phdev, int devnum, u16 regnum, u16 val); /* Clause 45 PHY */ int genphy_c45_restart_aneg(struct phy_device *phydev); int genphy_c45_check_and_restart_aneg(struct phy_device *phydev, bool restart); int genphy_c45_aneg_done(struct phy_device *phydev); int genphy_c45_read_link(struct phy_device *phydev); int genphy_c45_read_lpa(struct phy_device *phydev); int genphy_c45_read_pma(struct phy_device *phydev); int genphy_c45_pma_setup_forced(struct phy_device *phydev); int genphy_c45_an_config_aneg(struct phy_device *phydev); int genphy_c45_an_disable_aneg(struct phy_device *phydev); int genphy_c45_read_mdix(struct phy_device *phydev); int genphy_c45_pma_read_abilities(struct phy_device *phydev); int genphy_c45_read_status(struct phy_device *phydev); int genphy_c45_config_aneg(struct phy_device *phydev); /* The gen10g_* functions are the old Clause 45 stub */ int gen10g_config_aneg(struct phy_device *phydev); static inline int phy_read_status(struct phy_device *phydev) { if (!phydev->drv) return -EIO; if (phydev->drv->read_status) return phydev->drv->read_status(phydev); else return genphy_read_status(phydev); } void phy_driver_unregister(struct phy_driver *drv); void phy_drivers_unregister(struct phy_driver *drv, int n); int phy_driver_register(struct phy_driver *new_driver, struct module *owner); int phy_drivers_register(struct phy_driver *new_driver, int n, struct module *owner); void phy_state_machine(struct work_struct *work); void phy_queue_state_machine(struct phy_device *phydev, unsigned long jiffies); void phy_mac_interrupt(struct phy_device *phydev); void phy_start_machine(struct phy_device *phydev); void phy_stop_machine(struct phy_device *phydev); int phy_ethtool_sset(struct phy_device *phydev, struct ethtool_cmd *cmd); void phy_ethtool_ksettings_get(struct phy_device *phydev, struct ethtool_link_ksettings *cmd); int phy_ethtool_ksettings_set(struct phy_device *phydev, const struct ethtool_link_ksettings *cmd); int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); int phy_set_max_speed(struct phy_device *phydev, u32 max_speed); void phy_remove_link_mode(struct phy_device *phydev, u32 link_mode); void phy_advertise_supported(struct phy_device *phydev); void phy_support_sym_pause(struct phy_device *phydev); void phy_support_asym_pause(struct phy_device *phydev); void phy_set_sym_pause(struct phy_device *phydev, bool rx, bool tx, bool autoneg); void phy_set_asym_pause(struct phy_device *phydev, bool rx, bool tx); bool phy_validate_pause(struct phy_device *phydev, struct ethtool_pauseparam *pp); int phy_register_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_register_fixup_for_id(const char *bus_id, int (*run)(struct phy_device *)); int phy_register_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask, int (*run)(struct phy_device *)); int phy_unregister_fixup(const char *bus_id, u32 phy_uid, u32 phy_uid_mask); int phy_unregister_fixup_for_id(const char *bus_id); int phy_unregister_fixup_for_uid(u32 phy_uid, u32 phy_uid_mask); int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable); int phy_get_eee_err(struct phy_device *phydev); int phy_ethtool_set_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_get_eee(struct phy_device *phydev, struct ethtool_eee *data); int phy_ethtool_set_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); void phy_ethtool_get_wol(struct phy_device *phydev, struct ethtool_wolinfo *wol); int phy_ethtool_get_link_ksettings(struct net_device *ndev, struct ethtool_link_ksettings *cmd); int phy_ethtool_set_link_ksettings(struct net_device *ndev, const struct ethtool_link_ksettings *cmd); int phy_ethtool_nway_reset(struct net_device *ndev); #if IS_ENABLED(CONFIG_PHYLIB) int __init mdio_bus_init(void); void mdio_bus_exit(void); #endif /* Inline function for use within net/core/ethtool.c (built-in) */ static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) { if (!phydev->drv) return -EIO; mutex_lock(&phydev->lock); phydev->drv->get_strings(phydev, data); mutex_unlock(&phydev->lock); return 0; } static inline int phy_ethtool_get_sset_count(struct phy_device *phydev) { int ret; if (!phydev->drv) return -EIO; if (phydev->drv->get_sset_count && phydev->drv->get_strings && phydev->drv->get_stats) { mutex_lock(&phydev->lock); ret = phydev->drv->get_sset_count(phydev); mutex_unlock(&phydev->lock); return ret; } return -EOPNOTSUPP; } static inline int phy_ethtool_get_stats(struct phy_device *phydev, struct ethtool_stats *stats, u64 *data) { if (!phydev->drv) return -EIO; mutex_lock(&phydev->lock); phydev->drv->get_stats(phydev, stats, data); mutex_unlock(&phydev->lock); return 0; } extern struct bus_type mdio_bus_type; struct mdio_board_info { const char *bus_id; char modalias[MDIO_NAME_SIZE]; int mdio_addr; const void *platform_data; }; #if IS_ENABLED(CONFIG_MDIO_DEVICE) int mdiobus_register_board_info(const struct mdio_board_info *info, unsigned int n); #else static inline int mdiobus_register_board_info(const struct mdio_board_info *i, unsigned int n) { return 0; } #endif /** * module_phy_driver() - Helper macro for registering PHY drivers * @__phy_drivers: array of PHY drivers to register * * Helper macro for PHY drivers which do not do anything special in module * init/exit. Each module may only use this macro once, and calling it * replaces module_init() and module_exit(). */ #define phy_module_driver(__phy_drivers, __count) \ static int __init phy_module_init(void) \ { \ return phy_drivers_register(__phy_drivers, __count, THIS_MODULE); \ } \ module_init(phy_module_init); \ static void __exit phy_module_exit(void) \ { \ phy_drivers_unregister(__phy_drivers, __count); \ } \ module_exit(phy_module_exit) #define module_phy_driver(__phy_drivers) \ phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers)) bool phy_driver_is_genphy(struct phy_device *phydev); bool phy_driver_is_genphy_10g(struct phy_device *phydev); #endif /* __PHY_H */ |
| 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 | // SPDX-License-Identifier: GPL-2.0 #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/wext.h> #define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1) #define get_bucket(x) ((x) >> BUCKET_SPACE) #define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1)) #define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o)) extern struct list_head ptype_all __read_mostly; extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); struct net_device *dev; struct hlist_head *h; unsigned int count = 0, offset = get_offset(*pos); h = &net->dev_name_head[get_bucket(*pos)]; hlist_for_each_entry_rcu(dev, h, name_hlist) { if (++count == offset) return dev; } return NULL; } static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos) { struct net_device *dev; unsigned int bucket; do { dev = dev_from_same_bucket(seq, pos); if (dev) return dev; bucket = get_bucket(*pos) + 1; *pos = set_bucket_offset(bucket, 1); } while (bucket < NETDEV_HASHENTRIES); return NULL; } /* * This is invoked by the /proc filesystem handler to display a device * in detail. */ static void *dev_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); if (!*pos) return SEQ_START_TOKEN; if (get_bucket(*pos) >= NETDEV_HASHENTRIES) return NULL; return dev_from_bucket(seq, pos); } static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return dev_from_bucket(seq, pos); } static void dev_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, stats->rx_fifo_errors, stats->rx_length_errors + stats->rx_over_errors + stats->rx_crc_errors + stats->rx_frame_errors, stats->rx_compressed, stats->multicast, stats->tx_bytes, stats->tx_packets, stats->tx_errors, stats->tx_dropped, stats->tx_fifo_errors, stats->collisions, stats->tx_carrier_errors + stats->tx_aborted_errors + stats->tx_window_errors + stats->tx_heartbeat_errors, stats->tx_compressed); } /* * Called from the PROCfs module. This now uses the new arbitrary sized * /proc/net interface to create /proc/net/dev */ static int dev_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Inter-| Receive " " | Transmit\n" " face |bytes packets errs drop fifo frame " "compressed multicast|bytes packets errs " "drop fifo colls carrier compressed\n"); else dev_seq_printf_stats(seq, v); return 0; } static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; while (*pos < nr_cpu_ids) if (cpu_online(*pos)) { sd = &per_cpu(softnet_data, *pos); break; } else ++*pos; return sd; } static void *softnet_seq_start(struct seq_file *seq, loff_t *pos) { return softnet_get_online(pos); } static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return softnet_get_online(pos); } static void softnet_seq_stop(struct seq_file *seq, void *v) { } static int softnet_seq_show(struct seq_file *seq, void *v) { struct softnet_data *sd = v; unsigned int flow_limit_count = 0; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit *fl; rcu_read_lock(); fl = rcu_dereference(sd->flow_limit); if (fl) flow_limit_count = fl->count; rcu_read_unlock(); #endif seq_printf(seq, "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ sd->received_rps, flow_limit_count); return 0; } static const struct seq_operations dev_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_seq_show, }; static const struct seq_operations softnet_seq_ops = { .start = softnet_seq_start, .next = softnet_seq_next, .stop = softnet_seq_stop, .show = softnet_seq_show, }; static void *ptype_get_idx(struct seq_file *seq, loff_t pos) { struct list_head *ptype_list = NULL; struct packet_type *pt = NULL; struct net_device *dev; loff_t i = 0; int t; for_each_netdev_rcu(seq_file_net(seq), dev) { ptype_list = &dev->ptype_all; list_for_each_entry_rcu(pt, ptype_list, list) { if (i == pos) return pt; ++i; } } list_for_each_entry_rcu(pt, &ptype_all, list) { if (i == pos) return pt; ++i; } for (t = 0; t < PTYPE_HASH_SIZE; t++) { list_for_each_entry_rcu(pt, &ptype_base[t], list) { if (i == pos) return pt; ++i; } } return NULL; } static void *ptype_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { rcu_read_lock(); return *pos ? ptype_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct net_device *dev; struct packet_type *pt; struct list_head *nxt; int hash; ++*pos; if (v == SEQ_START_TOKEN) return ptype_get_idx(seq, 0); pt = v; nxt = pt->list.next; if (pt->dev) { if (nxt != &pt->dev->ptype_all) goto found; dev = pt->dev; for_each_netdev_continue_rcu(seq_file_net(seq), dev) { if (!list_empty(&dev->ptype_all)) { nxt = dev->ptype_all.next; goto found; } } nxt = ptype_all.next; goto ptype_all; } if (pt->type == htons(ETH_P_ALL)) { ptype_all: if (nxt != &ptype_all) goto found; hash = 0; nxt = ptype_base[0].next; } else hash = ntohs(pt->type) & PTYPE_HASH_MASK; while (nxt == &ptype_base[hash]) { if (++hash >= PTYPE_HASH_SIZE) return NULL; nxt = ptype_base[hash].next; } found: return list_entry(nxt, struct packet_type, list); } static void ptype_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock(); } static int ptype_seq_show(struct seq_file *seq, void *v) { struct packet_type *pt = v; if (v == SEQ_START_TOKEN) seq_puts(seq, "Type Device Function\n"); else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) { if (pt->type == htons(ETH_P_ALL)) seq_puts(seq, "ALL "); else seq_printf(seq, "%04x", ntohs(pt->type)); seq_printf(seq, " %-8s %ps\n", pt->dev ? pt->dev->name : "", pt->func); } return 0; } static const struct seq_operations ptype_seq_ops = { .start = ptype_seq_start, .next = ptype_seq_next, .stop = ptype_seq_stop, .show = ptype_seq_show, }; static int __net_init dev_proc_net_init(struct net *net) { int rc = -ENOMEM; if (!proc_create_net("dev", 0444, net->proc_net, &dev_seq_ops, sizeof(struct seq_net_private))) goto out; if (!proc_create_seq("softnet_stat", 0444, net->proc_net, &softnet_seq_ops)) goto out_dev; if (!proc_create_net("ptype", 0444, net->proc_net, &ptype_seq_ops, sizeof(struct seq_net_private))) goto out_softnet; if (wext_proc_init(net)) goto out_ptype; rc = 0; out: return rc; out_ptype: remove_proc_entry("ptype", net->proc_net); out_softnet: remove_proc_entry("softnet_stat", net->proc_net); out_dev: remove_proc_entry("dev", net->proc_net); goto out; } static void __net_exit dev_proc_net_exit(struct net *net) { wext_proc_exit(net); remove_proc_entry("ptype", net->proc_net); remove_proc_entry("softnet_stat", net->proc_net); remove_proc_entry("dev", net->proc_net); } static struct pernet_operations __net_initdata dev_proc_ops = { .init = dev_proc_net_init, .exit = dev_proc_net_exit, }; static int dev_mc_seq_show(struct seq_file *seq, void *v) { struct netdev_hw_addr *ha; struct net_device *dev = v; if (v == SEQ_START_TOKEN) return 0; netif_addr_lock_bh(dev); netdev_for_each_mc_addr(ha, dev) { seq_printf(seq, "%-4d %-15s %-5d %-5d %*phN\n", dev->ifindex, dev->name, ha->refcount, ha->global_use, (int)dev->addr_len, ha->addr); } netif_addr_unlock_bh(dev); return 0; } static const struct seq_operations dev_mc_seq_ops = { .start = dev_seq_start, .next = dev_seq_next, .stop = dev_seq_stop, .show = dev_mc_seq_show, }; static int __net_init dev_mc_net_init(struct net *net) { if (!proc_create_net("dev_mcast", 0, net->proc_net, &dev_mc_seq_ops, sizeof(struct seq_net_private))) return -ENOMEM; return 0; } static void __net_exit dev_mc_net_exit(struct net *net) { remove_proc_entry("dev_mcast", net->proc_net); } static struct pernet_operations __net_initdata dev_mc_net_ops = { .init = dev_mc_net_init, .exit = dev_mc_net_exit, }; int __init dev_proc_init(void) { int ret = register_pernet_subsys(&dev_proc_ops); if (!ret) return register_pernet_subsys(&dev_mc_net_ops); return ret; } |
| 25 25 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/gen_estimator.c Simple rate estimator. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * Eric Dumazet <edumazet@google.com> * * Changes: * Jamal Hadi Salim - moved it to net/core and reshulfed * names to make it usable in general net subsystem. */ #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/interrupt.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/seqlock.h> #include <net/sock.h> #include <net/gen_stats.h> /* This code is NOT intended to be used for statistics collection, * its purpose is to provide a base for statistical multiplexing * for controlled load service. * If you need only statistics, run a user level daemon which * periodically reads byte counters. */ struct net_rate_estimator { struct gnet_stats_basic_packed *bstats; spinlock_t *stats_lock; seqcount_t *running; struct gnet_stats_basic_cpu __percpu *cpu_bstats; u8 ewma_log; u8 intvl_log; /* period : (250ms << intvl_log) */ seqcount_t seq; u32 last_packets; u64 last_bytes; u64 avpps; u64 avbps; unsigned long next_jiffies; struct timer_list timer; struct rcu_head rcu; }; static void est_fetch_counters(struct net_rate_estimator *e, struct gnet_stats_basic_packed *b) { memset(b, 0, sizeof(*b)); if (e->stats_lock) spin_lock(e->stats_lock); __gnet_stats_copy_basic(e->running, b, e->cpu_bstats, e->bstats); if (e->stats_lock) spin_unlock(e->stats_lock); } static void est_timer(struct timer_list *t) { struct net_rate_estimator *est = from_timer(est, t, timer); struct gnet_stats_basic_packed b; u64 rate, brate; est_fetch_counters(est, &b); brate = (b.bytes - est->last_bytes) << (10 - est->intvl_log); brate = (brate >> est->ewma_log) - (est->avbps >> est->ewma_log); rate = (u64)(b.packets - est->last_packets) << (10 - est->intvl_log); rate = (rate >> est->ewma_log) - (est->avpps >> est->ewma_log); write_seqcount_begin(&est->seq); est->avbps += brate; est->avpps += rate; write_seqcount_end(&est->seq); est->last_bytes = b.bytes; est->last_packets = b.packets; est->next_jiffies += ((HZ/4) << est->intvl_log); if (unlikely(time_after_eq(jiffies, est->next_jiffies))) { /* Ouch... timer was delayed. */ est->next_jiffies = jiffies + 1; } mod_timer(&est->timer, est->next_jiffies); } /** * gen_new_estimator - create a new rate estimator * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: qdisc running seqcount * @opt: rate estimator configuration TLV * * Creates a new rate estimator with &bstats as source and &rate_est * as destination. A new timer with the interval specified in the * configuration TLV is created. Upon each interval, the latest statistics * will be read from &bstats and the estimated rate will be stored in * &rate_est with the statistics lock grabbed during this period. * * Returns 0 on success or a negative error code. * */ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, seqcount_t *running, struct nlattr *opt) { struct gnet_estimator *parm = nla_data(opt); struct net_rate_estimator *old, *est; struct gnet_stats_basic_packed b; int intvl_log; if (nla_len(opt) < sizeof(*parm)) return -EINVAL; /* allowed timer periods are : * -2 : 250ms, -1 : 500ms, 0 : 1 sec * 1 : 2 sec, 2 : 4 sec, 3 : 8 sec */ if (parm->interval < -2 || parm->interval > 3) return -EINVAL; if (parm->ewma_log == 0 || parm->ewma_log >= 31) return -EINVAL; est = kzalloc(sizeof(*est), GFP_KERNEL); if (!est) return -ENOBUFS; seqcount_init(&est->seq); intvl_log = parm->interval + 2; est->bstats = bstats; est->stats_lock = lock; est->running = running; est->ewma_log = parm->ewma_log; est->intvl_log = intvl_log; est->cpu_bstats = cpu_bstats; if (lock) local_bh_disable(); est_fetch_counters(est, &b); if (lock) local_bh_enable(); est->last_bytes = b.bytes; est->last_packets = b.packets; if (lock) spin_lock_bh(lock); old = rcu_dereference_protected(*rate_est, 1); if (old) { del_timer_sync(&old->timer); est->avbps = old->avbps; est->avpps = old->avpps; } est->next_jiffies = jiffies + ((HZ/4) << intvl_log); timer_setup(&est->timer, est_timer, 0); mod_timer(&est->timer, est->next_jiffies); rcu_assign_pointer(*rate_est, est); if (lock) spin_unlock_bh(lock); if (old) kfree_rcu(old, rcu); return 0; } EXPORT_SYMBOL(gen_new_estimator); /** * gen_kill_estimator - remove a rate estimator * @rate_est: rate estimator * * Removes the rate estimator. * */ void gen_kill_estimator(struct net_rate_estimator __rcu **rate_est) { struct net_rate_estimator *est; est = xchg((__force struct net_rate_estimator **)rate_est, NULL); if (est) { del_timer_sync(&est->timer); kfree_rcu(est, rcu); } } EXPORT_SYMBOL(gen_kill_estimator); /** * gen_replace_estimator - replace rate estimator configuration * @bstats: basic statistics * @cpu_bstats: bstats per cpu * @rate_est: rate estimator statistics * @lock: lock for statistics and control path * @running: qdisc running seqcount (might be NULL) * @opt: rate estimator configuration TLV * * Replaces the configuration of a rate estimator by calling * gen_kill_estimator() and gen_new_estimator(). * * Returns 0 on success or a negative error code. */ int gen_replace_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_basic_cpu __percpu *cpu_bstats, struct net_rate_estimator __rcu **rate_est, spinlock_t *lock, seqcount_t *running, struct nlattr *opt) { return gen_new_estimator(bstats, cpu_bstats, rate_est, lock, running, opt); } EXPORT_SYMBOL(gen_replace_estimator); /** * gen_estimator_active - test if estimator is currently in use * @rate_est: rate estimator * * Returns true if estimator is active, and false if not. */ bool gen_estimator_active(struct net_rate_estimator __rcu **rate_est) { return !!rcu_access_pointer(*rate_est); } EXPORT_SYMBOL(gen_estimator_active); bool gen_estimator_read(struct net_rate_estimator __rcu **rate_est, struct gnet_stats_rate_est64 *sample) { struct net_rate_estimator *est; unsigned seq; rcu_read_lock(); est = rcu_dereference(*rate_est); if (!est) { rcu_read_unlock(); return false; } do { seq = read_seqcount_begin(&est->seq); sample->bps = est->avbps >> 8; sample->pps = est->avpps >> 8; } while (read_seqcount_retry(&est->seq, seq)); rcu_read_unlock(); return true; } EXPORT_SYMBOL(gen_estimator_read); |
| 13 14 14 14 14 58 39 4 4 4 39 1 39 5 16 24 39 1 51 57 8 8 2 44 4 4 4 14 13 14 2 12 12 12 87 11 64 15 15 87 87 101 108 109 79 28 103 102 112 112 97 11 99 13 41 5 37 9 62 51 1 7 7 1 49 48 40 10 1 1 1 4 113 112 112 112 112 112 112 112 74 74 70 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 virtual tunneling interface * * Copyright (C) 2013 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> * * Based on: * net/ipv6/ip6_tunnel.c */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/etherdevice.h> #define IP6_VTI_HASH_SIZE_SHIFT 5 #define IP6_VTI_HASH_SIZE (1 << IP6_VTI_HASH_SIZE_SHIFT) static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); return hash_32(hash, IP6_VTI_HASH_SIZE_SHIFT); } static int vti6_dev_init(struct net_device *dev); static void vti6_dev_setup(struct net_device *dev); static struct rtnl_link_ops vti6_link_ops __read_mostly; static unsigned int vti6_net_id __read_mostly; struct vti6_net { /* the vti6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[IP6_VTI_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; }; #define for_each_vti6_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) /** * vti6_tnl_lookup - fetch tunnel matching the end-point addresses * @net: network namespace * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ static struct ip6_tnl * vti6_tnl_lookup(struct net *net, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); struct ip6_tnl *t; struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct in6_addr any; for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(local, &t->parms.laddr) && (t->dev->flags & IFF_UP)) return t; } hash = HASH(remote, &any); for_each_vti6_tunnel_rcu(ip6n->tnls_r_l[hash]) { if (ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * vti6_tnl_bucket - get head of list matching given tunnel parameters * @p: parameters containing tunnel end-points * * Description: * vti6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** vti6_tnl_bucket(struct vti6_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } static void vti6_tnl_link(struct vti6_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = vti6_tnl_bucket(ip6n, &t->parms); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } static void vti6_tnl_unlink(struct vti6_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; for (tp = vti6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void vti6_dev_free(struct net_device *dev) { free_percpu(dev->tstats); } static int vti6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; dev->rtnl_link_ops = &vti6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); vti6_tnl_link(ip6n, t); return 0; out: return err; } static struct ip6_tnl *vti6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err; if (p->name[0]) { if (!dev_valid_name(p->name)) goto failed; strlcpy(name, p->name, IFNAMSIZ); } else { sprintf(name, "ip6_vti%%d"); } dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, vti6_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = vti6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: free_netdev(dev); failed: return NULL; } /** * vti6_locate - find or create tunnel matching given parameters * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * vti6_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or NULL **/ static struct ip6_tnl *vti6_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct vti6_net *ip6n = net_generic(net, vti6_net_id); for (tp = vti6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr)) { if (create) return NULL; return t; } } if (!create) return NULL; return vti6_tnl_create(net, p); } /** * vti6_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * vti6_dev_uninit() removes tunnel from its list **/ static void vti6_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct vti6_net *ip6n = net_generic(t->net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else vti6_tnl_unlink(ip6n, t); dev_put(dev); } static int vti6_rcv(struct sk_buff *skb) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); rcu_read_lock(); t = vti6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr); if (t) { if (t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) { rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); goto discard; } ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) { t->dev->stats.rx_dropped++; rcu_read_unlock(); goto discard; } rcu_read_unlock(); return xfrm6_rcv_tnl(skb, t); } rcu_read_unlock(); return -EINVAL; discard: kfree_skb(skb); return 0; } static int vti6_rcv_cb(struct sk_buff *skb, int err) { unsigned short family; struct net_device *dev; struct pcpu_sw_netstats *tstats; struct xfrm_state *x; const struct xfrm_mode *inner_mode; struct ip6_tnl *t = XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6; u32 orig_mark = skb->mark; int ret; if (!t) return 1; dev = t->dev; if (err) { dev->stats.rx_errors++; dev->stats.rx_dropped++; return 0; } x = xfrm_input_state(skb); inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } family = inner_mode->family; skb->mark = be32_to_cpu(t->parms.i_key); ret = xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, family); skb->mark = orig_mark; if (!ret) return -EPERM; skb_scrub_packet(skb, !net_eq(t->net, dev_net(skb->dev))); skb->dev = dev; tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); return 0; } /** * vti6_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool vti6_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } static bool vti6_state_check(const struct xfrm_state *x, const struct in6_addr *dst, const struct in6_addr *src) { xfrm_address_t *daddr = (xfrm_address_t *)dst; xfrm_address_t *saddr = (xfrm_address_t *)src; /* if there is no transform then this tunnel is not functional. * Or if the xfrm is not mode tunnel. */ if (!x || x->props.mode != XFRM_MODE_TUNNEL || x->props.family != AF_INET6) return false; if (ipv6_addr_any(dst)) return xfrm_addr_equal(saddr, &x->props.saddr, AF_INET6); if (!xfrm_state_addr_check(x, daddr, saddr, AF_INET6)) return false; return true; } /** * vti6_xmit - send a packet * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @fl: the flow informations for the xfrm_lookup **/ static int vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; struct dst_entry *dst = skb_dst(skb); struct net_device *tdev; struct xfrm_state *x; int pkt_len = skb->len; int err = -1; int mtu; if (!dst) { switch (skb->protocol) { case htons(ETH_P_IP): { struct rtable *rt; fl->u.ip4.flowi4_oif = dev->ifindex; fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); if (IS_ERR(rt)) goto tx_err_link_failure; dst = &rt->dst; skb_dst_set(skb, dst); break; } case htons(ETH_P_IPV6): fl->u.ip6.flowi6_oif = dev->ifindex; fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); if (dst->error) { dst_release(dst); dst = NULL; goto tx_err_link_failure; } skb_dst_set(skb, dst); break; default: goto tx_err_link_failure; } } dst_hold(dst); dst = xfrm_lookup(t->net, dst, fl, NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } x = dst->xfrm; if (!vti6_state_check(x, &t->parms.raddr, &t->parms.laddr)) goto tx_err_link_failure; if (!ip6_tnl_xmit_ctl(t, (const struct in6_addr *)&x->props.saddr, (const struct in6_addr *)&x->id.daddr)) goto tx_err_link_failure; tdev = dst->dev; if (tdev == dev) { stats->collisions++; net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); } else { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } err = -EMSGSIZE; goto tx_err_dst_release; } skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = skb_dst(skb)->dev; err = dst_output(t->net, skb->sk, skb); if (net_xmit_eval(err) == 0) err = pkt_len; iptunnel_xmit_stats(dev, err); return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static netdev_tx_t vti6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net_device_stats *stats = &t->dev->stats; struct flowi fl; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): if ((t->parms.proto != IPPROTO_IPV6 && t->parms.proto != 0) || vti6_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(skb, &fl, AF_INET6); break; case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(skb, &fl, AF_INET); break; default: goto tx_err; } /* override mark with tunnel output key */ fl.flowi_mark = be32_to_cpu(t->parms.o_key); ret = vti6_xmit(skb, dev, &fl); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static int vti6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __be32 spi; __u32 mark; struct xfrm_state *x; struct ip6_tnl *t; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah; struct ip_comp_hdr *ipch; struct net *net = dev_net(skb->dev); const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; int protocol = iph->nexthdr; t = vti6_tnl_lookup(dev_net(skb->dev), &iph->daddr, &iph->saddr); if (!t) return -1; mark = be32_to_cpu(t->parms.o_key); switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data + offset); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data + offset); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static void vti6_link_config(struct ip6_tnl *t, bool keep_mtu) { struct net_device *dev = t->dev; struct __ip6_tnl_parm *p = &t->parms; struct net_device *tdev = NULL; int mtu; memcpy(dev->dev_addr, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); p->flags &= ~(IP6_TNL_F_CAP_XMIT | IP6_TNL_F_CAP_RCV | IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags & IP6_TNL_F_CAP_XMIT && p->flags & IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; if (keep_mtu && dev->mtu) { dev->mtu = clamp(dev->mtu, dev->min_mtu, dev->max_mtu); return; } if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (rt) tdev = rt->dst.dev; ip6_rt_put(rt); } if (!tdev && p->link) tdev = __dev_get_by_index(t->net, p->link); if (tdev) mtu = tdev->mtu - sizeof(struct ipv6hdr); else mtu = ETH_DATA_LEN - LL_MAX_HEADER - sizeof(struct ipv6hdr); dev->mtu = max_t(int, mtu, IPV4_MIN_MTU); } /** * vti6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * @keep_mtu: MTU was set from userspace, don't re-compute it * * Description: * vti6_tnl_change() updates the tunnel parameters **/ static int vti6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p, bool keep_mtu) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.link = p->link; t->parms.i_key = p->i_key; t->parms.o_key = p->o_key; t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); vti6_link_config(t, keep_mtu); return 0; } static int vti6_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, bool keep_mtu) { struct net *net = dev_net(t->dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); int err; vti6_tnl_unlink(ip6n, t); synchronize_net(); err = vti6_tnl_change(t, p, keep_mtu); vti6_tnl_link(ip6n, t); netdev_state_change(t->dev); return err; } static void vti6_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm2 *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->link = u->link; p->i_key = u->i_key; p->o_key = u->o_key; p->proto = u->proto; memcpy(p->name, u->name, sizeof(u->name)); } static void vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->link = p->link; u->i_key = p->i_key; u->o_key = p->o_key; if (u->i_key) u->i_flags |= GRE_KEY; if (u->o_key) u->o_flags |= GRE_KEY; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * vti6_ioctl - configure vti6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: parameters passed from userspace * @cmd: command to be performed * * Description: * vti6_ioctl() is used for managing vti6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6_vti0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int vti6_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { int err = 0; struct ip6_tnl_parm2 p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = NULL; struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { err = -EFAULT; break; } vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); } else { memset(&p, 0, sizeof(p)); } if (!t) t = netdev_priv(dev); vti6_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != 0) break; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, cmd == SIOCADDTUNNEL); if (dev != ip6n->fb_tnl_dev && cmd == SIOCCHGTUNNEL) { if (t) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); err = vti6_update(t, &p1, false); } if (t) { err = 0; vti6_parm_to_user(&p, &t->parms); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) err = -EFAULT; } else err = (cmd == SIOCADDTUNNEL ? -ENOBUFS : -ENOENT); break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) break; err = -ENOENT; vti6_parm_from_user(&p1, &p); t = vti6_locate(net, &p1, 0); if (!t) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } static const struct net_device_ops vti6_netdev_ops = { .ndo_init = vti6_dev_init, .ndo_uninit = vti6_dev_uninit, .ndo_start_xmit = vti6_tnl_xmit, .ndo_do_ioctl = vti6_ioctl, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip6_tnl_get_iflink, }; /** * vti6_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void vti6_dev_setup(struct net_device *dev) { dev->netdev_ops = &vti6_netdev_ops; dev->needs_free_netdev = true; dev->priv_destructor = vti6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->min_mtu = IPV4_MIN_MTU; dev->max_mtu = IP_MAX_MTU - sizeof(struct ipv6hdr); dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); netif_keep_dst(dev); /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * vti6_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int vti6_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); t->dev = dev; t->net = dev_net(dev); dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; dev_hold(dev); return 0; } /** * vti6_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int vti6_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = vti6_dev_init_gen(dev); if (err) return err; vti6_link_config(t, true); return 0; } /** * vti6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init vti6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int vti6_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void vti6_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_VTI_LINK]) parms->link = nla_get_u32(data[IFLA_VTI_LINK]); if (data[IFLA_VTI_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_VTI_LOCAL]); if (data[IFLA_VTI_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_VTI_REMOTE]); if (data[IFLA_VTI_IKEY]) parms->i_key = nla_get_be32(data[IFLA_VTI_IKEY]); if (data[IFLA_VTI_OKEY]) parms->o_key = nla_get_be32(data[IFLA_VTI_OKEY]); if (data[IFLA_VTI_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_VTI_FWMARK]); } static int vti6_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct ip6_tnl *nt; nt = netdev_priv(dev); vti6_netlink_parms(data, &nt->parms); nt->parms.proto = IPPROTO_IPV6; if (vti6_locate(net, &nt->parms, 0)) return -EEXIST; return vti6_tnl_create2(dev); } static void vti6_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static int vti6_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t; struct __ip6_tnl_parm p; struct net *net = dev_net(dev); struct vti6_net *ip6n = net_generic(net, vti6_net_id); if (dev == ip6n->fb_tnl_dev) return -EINVAL; vti6_netlink_parms(data, &p); t = vti6_locate(net, &p, 0); if (t) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); return vti6_update(t, &p, tb && tb[IFLA_MTU]); } static size_t vti6_get_size(const struct net_device *dev) { return /* IFLA_VTI_LINK */ nla_total_size(4) + /* IFLA_VTI_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VTI_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_VTI_IKEY */ nla_total_size(4) + /* IFLA_VTI_OKEY */ nla_total_size(4) + /* IFLA_VTI_FWMARK */ nla_total_size(4) + 0; } static int vti6_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_VTI_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_VTI_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_VTI_REMOTE, &parm->raddr) || nla_put_be32(skb, IFLA_VTI_IKEY, parm->i_key) || nla_put_be32(skb, IFLA_VTI_OKEY, parm->o_key) || nla_put_u32(skb, IFLA_VTI_FWMARK, parm->fwmark)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy vti6_policy[IFLA_VTI_MAX + 1] = { [IFLA_VTI_LINK] = { .type = NLA_U32 }, [IFLA_VTI_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_VTI_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_VTI_IKEY] = { .type = NLA_U32 }, [IFLA_VTI_OKEY] = { .type = NLA_U32 }, [IFLA_VTI_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops vti6_link_ops __read_mostly = { .kind = "vti6", .maxtype = IFLA_VTI_MAX, .policy = vti6_policy, .priv_size = sizeof(struct ip6_tnl), .setup = vti6_dev_setup, .validate = vti6_validate, .newlink = vti6_newlink, .dellink = vti6_dellink, .changelink = vti6_changelink, .get_size = vti6_get_size, .fill_info = vti6_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static void __net_exit vti6_destroy_tunnels(struct vti6_net *ip6n, struct list_head *list) { int h; struct ip6_tnl *t; for (h = 0; h < IP6_VTI_HASH_SIZE; h++) { t = rtnl_dereference(ip6n->tnls_r_l[h]); while (t) { unregister_netdevice_queue(t->dev, list); t = rtnl_dereference(t->next); } } t = rtnl_dereference(ip6n->tnls_wc[0]); if (t) unregister_netdevice_queue(t->dev, list); } static int __net_init vti6_init_net(struct net *net) { struct vti6_net *ip6n = net_generic(net, vti6_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; if (!net_has_fallback_tunnels(net)) return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6_vti0", NET_NAME_UNKNOWN, vti6_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &vti6_link_ops; err = vti6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static void __net_exit vti6_exit_batch_net(struct list_head *net_list) { struct vti6_net *ip6n; struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_list, exit_list) { ip6n = net_generic(net, vti6_net_id); vti6_destroy_tunnels(ip6n, &list); } unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations vti6_net_ops = { .init = vti6_init_net, .exit_batch = vti6_exit_batch_net, .id = &vti6_net_id, .size = sizeof(struct vti6_net), }; static struct xfrm6_protocol vti_esp6_protocol __read_mostly = { .handler = vti6_rcv, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; static struct xfrm6_protocol vti_ah6_protocol __read_mostly = { .handler = vti6_rcv, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; static struct xfrm6_protocol vti_ipcomp6_protocol __read_mostly = { .handler = vti6_rcv, .cb_handler = vti6_rcv_cb, .err_handler = vti6_err, .priority = 100, }; /** * vti6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init vti6_tunnel_init(void) { const char *msg; int err; msg = "tunnel device"; err = register_pernet_device(&vti6_net_ops); if (err < 0) goto pernet_dev_failed; msg = "tunnel protocols"; err = xfrm6_protocol_register(&vti_esp6_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&vti_ah6_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&vti_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; msg = "netlink interface"; err = rtnl_link_register(&vti6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm_proto_comp_failed: xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: unregister_pernet_device(&vti6_net_ops); pernet_dev_failed: pr_err("vti6 init: failed to register %s\n", msg); return err; } /** * vti6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit vti6_tunnel_cleanup(void) { rtnl_link_unregister(&vti6_link_ops); xfrm6_protocol_deregister(&vti_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&vti_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&vti_esp6_protocol, IPPROTO_ESP); unregister_pernet_device(&vti6_net_ops); } module_init(vti6_tunnel_init); module_exit(vti6_tunnel_cleanup); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("vti6"); MODULE_ALIAS_NETDEV("ip6_vti0"); MODULE_AUTHOR("Steffen Klassert"); MODULE_DESCRIPTION("IPv6 virtual tunnel interface"); |
| 74 74 3 308 90 103 104 104 105 3 3 120 3 29 85 76 75 119 120 120 113 111 112 76 74 67 66 67 45 42 214 74 75 75 75 72 44 238 76 75 9 67 9 9 164 169 72 6 6 4 232 12 3 125 78 125 38 27 75 67 67 236 205 7 27 98 267 69 3 93 24 2 96 86 30 64 4 1 5 7 7 5 82 3 10 8 152 41 3 22 13 19 59 246 166 39 7 139 173 74 74 74 73 73 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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. * * ROUTE - implementation of the IP router. * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Alan Cox, <gw4pts@gw4pts.ampr.org> * Linus Torvalds, <Linus.Torvalds@helsinki.fi> * Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> * * Fixes: * Alan Cox : Verify area fixes. * Alan Cox : cli() protects routing changes * Rui Oliveira : ICMP routing table updates * (rco@di.uminho.pt) Routing table insertion and update * Linus Torvalds : Rewrote bits to be sensible * Alan Cox : Added BSD route gw semantics * Alan Cox : Super /proc >4K * Alan Cox : MTU in route table * Alan Cox : MSS actually. Also added the window * clamper. * Sam Lantinga : Fixed route matching in rt_del() * Alan Cox : Routing cache support. * Alan Cox : Removed compatibility cruft. * Alan Cox : RTF_REJECT support. * Alan Cox : TCP irtt support. * Jonathan Naylor : Added Metric support. * Miquel van Smoorenburg : BSD API fixes. * Miquel van Smoorenburg : Metrics. * Alan Cox : Use __u32 properly * Alan Cox : Aligned routing errors more closely with BSD * our system is still very different. * Alan Cox : Faster /proc handling * Alexey Kuznetsov : Massive rework to support tree based routing, * routing caches and better behaviour. * * Olaf Erb : irtt wasn't being copied right. * Bjorn Ekwall : Kerneld route support. * Alan Cox : Multicast fixed (I hope) * Pavel Krauz : Limited broadcast fixed * Mike McLagan : Routing by source * Alexey Kuznetsov : End of old history. Split to fib.c and * route.c and rewritten from scratch. * Andi Kleen : Load-limit warning messages. * Vitaly E. Lavrov : Transparent proxy revived after year coma. * Vitaly E. Lavrov : Race condition in ip_route_input_slow. * Tobias Ringstrom : Uninitialized res.type in ip_route_output_slow. * Vladimir V. Ivanov : IP rule info (flowid) is really useful. * Marc Boucher : routing by fwmark * Robert Olsson : Added rt_cache statistics * Arnaldo C. Melo : Convert proc stuff to seq_file * Eric Dumazet : hashed spinlocks and rt_check_expire() fixes. * Ilia Sotnikov : Ignore TOS on PMTUD and Redirect * Ilia Sotnikov : Removed TOS from hash calculations */ #define pr_fmt(fmt) "IPv4: " fmt #include <linux/module.h> #include <linux/uaccess.h> #include <linux/bitops.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/errno.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/pkt_sched.h> #include <linux/mroute.h> #include <linux/netfilter_ipv4.h> #include <linux/random.h> #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> #include <net/route.h> #include <net/inetpeer.h> #include <net/sock.h> #include <net/ip_fib.h> #include <net/nexthop.h> #include <net/arp.h> #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> #include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif #include <net/secure_seq.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> #include "fib_lookup.h" #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) #define RT_GC_TIMEOUT (300*HZ) static int ip_rt_max_size; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; static int ip_rt_redirect_silence __read_mostly = ((HZ / 50) << (9 + 1)); static int ip_rt_error_cost __read_mostly = HZ; static int ip_rt_error_burst __read_mostly = 5 * HZ; static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static u32 ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; /* * Interface to generic destination cache. */ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); static u32 *ipv4_cow_metrics(struct dst_entry *dst, unsigned long old) { WARN_ON(1); return NULL; } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr); static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr); static struct dst_ops ipv4_dst_ops = { .family = AF_INET, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .negative_advice = (android_dst_ops_negative_advice_old_t)ipv4_negative_advice, .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .redirect = ip_do_redirect, .local_out = __ip_local_out, .neigh_lookup = ipv4_neigh_lookup, .confirm_neigh = ipv4_confirm_neigh, }; #define ECN_OR_COST(class) TC_PRIO_##class const __u8 ip_tos2prio[16] = { TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BESTEFFORT, ECN_OR_COST(BESTEFFORT), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_BULK, ECN_OR_COST(BULK), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE, ECN_OR_COST(INTERACTIVE), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK), TC_PRIO_INTERACTIVE_BULK, ECN_OR_COST(INTERACTIVE_BULK) }; EXPORT_SYMBOL(ip_tos2prio); static DEFINE_PER_CPU(struct rt_cache_stat, rt_cache_stat); #define RT_CACHE_STAT_INC(field) raw_cpu_inc(rt_cache_stat.field) #ifdef CONFIG_PROC_FS static void *rt_cache_seq_start(struct seq_file *seq, loff_t *pos) { if (*pos) return NULL; return SEQ_START_TOKEN; } static void *rt_cache_seq_next(struct seq_file *seq, void *v, loff_t *pos) { ++*pos; return NULL; } static void rt_cache_seq_stop(struct seq_file *seq, void *v) { } static int rt_cache_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_printf(seq, "%-127s\n", "Iface\tDestination\tGateway \tFlags\t\tRefCnt\tUse\t" "Metric\tSource\t\tMTU\tWindow\tIRTT\tTOS\tHHRef\t" "HHUptod\tSpecDst"); return 0; } static const struct seq_operations rt_cache_seq_ops = { .start = rt_cache_seq_start, .next = rt_cache_seq_next, .stop = rt_cache_seq_stop, .show = rt_cache_seq_show, }; static int rt_cache_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &rt_cache_seq_ops); } static const struct file_operations rt_cache_seq_fops = { .open = rt_cache_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) { int cpu; if (*pos == 0) return SEQ_START_TOKEN; for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } return NULL; } static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; return &per_cpu(rt_cache_stat, cpu); } (*pos)++; return NULL; } static void rt_cpu_seq_stop(struct seq_file *seq, void *v) { } static int rt_cpu_seq_show(struct seq_file *seq, void *v) { struct rt_cache_stat *st = v; if (v == SEQ_START_TOKEN) { seq_printf(seq, "entries in_hit in_slow_tot in_slow_mc in_no_route in_brd in_martian_dst in_martian_src out_hit out_slow_tot out_slow_mc gc_total gc_ignored gc_goal_miss gc_dst_overflow in_hlist_search out_hlist_search\n"); return 0; } seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x " " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n", dst_entries_get_slow(&ipv4_dst_ops), 0, /* st->in_hit */ st->in_slow_tot, st->in_slow_mc, st->in_no_route, st->in_brd, st->in_martian_dst, st->in_martian_src, 0, /* st->out_hit */ st->out_slow_tot, st->out_slow_mc, 0, /* st->gc_total */ 0, /* st->gc_ignored */ 0, /* st->gc_goal_miss */ 0, /* st->gc_dst_overflow */ 0, /* st->in_hlist_search */ 0 /* st->out_hlist_search */ ); return 0; } static const struct seq_operations rt_cpu_seq_ops = { .start = rt_cpu_seq_start, .next = rt_cpu_seq_next, .stop = rt_cpu_seq_stop, .show = rt_cpu_seq_show, }; static int rt_cpu_seq_open(struct inode *inode, struct file *file) { return seq_open(file, &rt_cpu_seq_ops); } static const struct file_operations rt_cpu_seq_fops = { .open = rt_cpu_seq_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, }; #ifdef CONFIG_IP_ROUTE_CLASSID static int rt_acct_proc_show(struct seq_file *m, void *v) { struct ip_rt_acct *dst, *src; unsigned int i, j; dst = kcalloc(256, sizeof(struct ip_rt_acct), GFP_KERNEL); if (!dst) return -ENOMEM; for_each_possible_cpu(i) { src = (struct ip_rt_acct *)per_cpu_ptr(ip_rt_acct, i); for (j = 0; j < 256; j++) { dst[j].o_bytes += src[j].o_bytes; dst[j].o_packets += src[j].o_packets; dst[j].i_bytes += src[j].i_bytes; dst[j].i_packets += src[j].i_packets; } } seq_write(m, dst, 256 * sizeof(struct ip_rt_acct)); kfree(dst); return 0; } #endif static int __net_init ip_rt_do_proc_init(struct net *net) { struct proc_dir_entry *pde; pde = proc_create("rt_cache", 0444, net->proc_net, &rt_cache_seq_fops); if (!pde) goto err1; pde = proc_create("rt_cache", 0444, net->proc_net_stat, &rt_cpu_seq_fops); if (!pde) goto err2; #ifdef CONFIG_IP_ROUTE_CLASSID pde = proc_create_single("rt_acct", 0, net->proc_net, rt_acct_proc_show); if (!pde) goto err3; #endif return 0; #ifdef CONFIG_IP_ROUTE_CLASSID err3: remove_proc_entry("rt_cache", net->proc_net_stat); #endif err2: remove_proc_entry("rt_cache", net->proc_net); err1: return -ENOMEM; } static void __net_exit ip_rt_do_proc_exit(struct net *net) { remove_proc_entry("rt_cache", net->proc_net_stat); remove_proc_entry("rt_cache", net->proc_net); #ifdef CONFIG_IP_ROUTE_CLASSID remove_proc_entry("rt_acct", net->proc_net); #endif } static struct pernet_operations ip_rt_proc_ops __net_initdata = { .init = ip_rt_do_proc_init, .exit = ip_rt_do_proc_exit, }; static int __init ip_rt_proc_init(void) { return register_pernet_subsys(&ip_rt_proc_ops); } #else static inline int ip_rt_proc_init(void) { return 0; } #endif /* CONFIG_PROC_FS */ static inline bool rt_is_expired(const struct rtable *rth) { bool res; rcu_read_lock(); res = rth->rt_genid != rt_genid_ipv4(dev_net_rcu(rth->dst.dev)); rcu_read_unlock(); return res; } void rt_cache_flush(struct net *net) { rt_genid_bump_ipv4(net); } static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; struct neighbour *n; rcu_read_lock_bh(); if (likely(rt->rt_gw_family == AF_INET)) { n = ip_neigh_gw4(dev, rt->rt_gw4); } else if (rt->rt_gw_family == AF_INET6) { n = ip_neigh_gw6(dev, &rt->rt_gw6); } else { __be32 pkey; pkey = skb ? ip_hdr(skb)->daddr : *((__be32 *) daddr); n = ip_neigh_gw4(dev, pkey); } if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); return n; } static void ipv4_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct rtable *rt = container_of(dst, struct rtable, dst); struct net_device *dev = dst->dev; const __be32 *pkey = daddr; if (rt->rt_gw_family == AF_INET) { pkey = (const __be32 *)&rt->rt_gw4; } else if (rt->rt_gw_family == AF_INET6) { return __ipv6_confirm_neigh_stub(dev, &rt->rt_gw6); } else if (!daddr || (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST | RTCF_LOCAL))) { return; } __ipv4_confirm_neigh(dev, *(__force u32 *)pkey); } /* Hash tables of size 2048..262144 depending on RAM size. * Each bucket uses 8 bytes. */ static u32 ip_idents_mask __read_mostly; static atomic_t *ip_idents __read_mostly; static u32 *ip_tstamps __read_mostly; /* In order to protect privacy, we add a perturbation to identifiers * if one generator is seldom used. This makes hard for an attacker * to infer how many packets were sent between two points in time. */ u32 ip_idents_reserve(u32 hash, int segs) { u32 bucket, old, now = (u32)jiffies; atomic_t *p_id; u32 *p_tstamp; u32 delta = 0; bucket = hash & ip_idents_mask; p_tstamp = ip_tstamps + bucket; p_id = ip_idents + bucket; old = READ_ONCE(*p_tstamp); if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); /* If UBSAN reports an error there, please make sure your compiler * supports -fno-strict-overflow before reporting it that was a bug * in UBSAN, and it has been fixed in GCC-8. */ return atomic_add_return(segs + delta, p_id) - segs; } EXPORT_SYMBOL(ip_idents_reserve); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs) { u32 hash, id; /* Note the following code is not safe, but this is okay. */ if (unlikely(siphash_key_is_zero(&net->ipv4.ip_id_key))) get_random_bytes(&net->ipv4.ip_id_key, sizeof(net->ipv4.ip_id_key)); hash = siphash_3u32((__force u32)iph->daddr, (__force u32)iph->saddr, iph->protocol, &net->ipv4.ip_id_key); id = ip_idents_reserve(hash, segs); iph->id = htons(id); } EXPORT_SYMBOL(__ip_select_ident); static void __build_flow_key(const struct net *net, struct flowi4 *fl4, const struct sock *sk, const struct iphdr *iph, int oif, u8 tos, u8 prot, u32 mark, int flow_flags) { if (sk) { const struct inet_sock *inet = inet_sk(sk); oif = sk->sk_bound_dev_if; mark = sk->sk_mark; tos = RT_CONN_FLAGS(sk); prot = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol; } flowi4_init_output(fl4, oif, mark, tos, RT_SCOPE_UNIVERSE, prot, flow_flags, iph->daddr, iph->saddr, 0, 0, sock_net_uid(net, sk)); } static void build_skb_flow_key(struct flowi4 *fl4, const struct sk_buff *skb, const struct sock *sk) { const struct net *net = dev_net(skb->dev); const struct iphdr *iph = ip_hdr(skb); int oif = skb->dev->ifindex; u8 tos = RT_TOS(iph->tos); u8 prot = iph->protocol; u32 mark = skb->mark; __build_flow_key(net, fl4, sk, iph, oif, tos, prot, mark, 0); } static void build_sk_flow_key(struct flowi4 *fl4, const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); const struct ip_options_rcu *inet_opt; __be32 daddr = inet->inet_daddr; rcu_read_lock(); inet_opt = rcu_dereference(inet->inet_opt); if (inet_opt && inet_opt->opt.srr) daddr = inet_opt->opt.faddr; flowi4_init_output(fl4, sk->sk_bound_dev_if, sk->sk_mark, RT_CONN_FLAGS(sk), RT_SCOPE_UNIVERSE, inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, inet_sk_flowi_flags(sk), daddr, inet->inet_saddr, 0, 0, sk->sk_uid); rcu_read_unlock(); } static void ip_rt_build_flow_key(struct flowi4 *fl4, const struct sock *sk, const struct sk_buff *skb) { if (skb) build_skb_flow_key(fl4, skb, sk); else build_sk_flow_key(fl4, sk); } static DEFINE_SPINLOCK(fnhe_lock); static void fnhe_flush_routes(struct fib_nh_exception *fnhe) { struct rtable *rt; rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_input, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) { RCU_INIT_POINTER(fnhe->fnhe_rth_output, NULL); dst_dev_put(&rt->dst); dst_release(&rt->dst); } } static void fnhe_remove_oldest(struct fnhe_hash_bucket *hash) { struct fib_nh_exception __rcu **fnhe_p, **oldest_p; struct fib_nh_exception *fnhe, *oldest = NULL; for (fnhe_p = &hash->chain; ; fnhe_p = &fnhe->fnhe_next) { fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); if (!fnhe) break; if (!oldest || time_before(fnhe->fnhe_stamp, oldest->fnhe_stamp)) { oldest = fnhe; oldest_p = fnhe_p; } } fnhe_flush_routes(oldest); *oldest_p = oldest->fnhe_next; kfree_rcu(oldest, rcu); } static u32 fnhe_hashfun(__be32 daddr) { static siphash_key_t fnhe_hash_key __read_mostly; u64 hval; net_get_random_once(&fnhe_hash_key, sizeof(fnhe_hash_key)); hval = siphash_1u32((__force u32)daddr, &fnhe_hash_key); return hash_64(hval, FNHE_HASH_SHIFT); } static void fill_route_from_fnhe(struct rtable *rt, struct fib_nh_exception *fnhe) { rt->rt_pmtu = fnhe->fnhe_pmtu; rt->rt_mtu_locked = fnhe->fnhe_mtu_locked; rt->dst.expires = fnhe->fnhe_expires; if (fnhe->fnhe_gw) { rt->rt_flags |= RTCF_REDIRECTED; rt->rt_uses_gateway = 1; rt->rt_gw_family = AF_INET; rt->rt_gw4 = fnhe->fnhe_gw; } } static void update_or_create_fnhe(struct fib_nh_common *nhc, __be32 daddr, __be32 gw, u32 pmtu, bool lock, unsigned long expires) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe; struct rtable *rt; u32 genid, hval; unsigned int i; int depth; genid = fnhe_genid(dev_net(nhc->nhc_dev)); hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference(nhc->nhc_exceptions); if (!hash) { hash = kcalloc(FNHE_HASH_SIZE, sizeof(*hash), GFP_ATOMIC); if (!hash) goto out_unlock; rcu_assign_pointer(nhc->nhc_exceptions, hash); } hash += hval; depth = 0; for (fnhe = rcu_dereference(hash->chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) break; depth++; } if (fnhe) { if (fnhe->fnhe_genid != genid) fnhe->fnhe_genid = genid; if (gw) fnhe->fnhe_gw = gw; if (pmtu) { fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; } fnhe->fnhe_expires = max(1UL, expires); /* Update all cached dsts too */ rt = rcu_dereference(fnhe->fnhe_rth_input); if (rt) fill_route_from_fnhe(rt, fnhe); rt = rcu_dereference(fnhe->fnhe_rth_output); if (rt) fill_route_from_fnhe(rt, fnhe); } else { /* Randomize max depth to avoid some side channels attacks. */ int max_depth = FNHE_RECLAIM_DEPTH + prandom_u32_max(FNHE_RECLAIM_DEPTH); while (depth > max_depth) { fnhe_remove_oldest(hash); depth--; } fnhe = kzalloc(sizeof(*fnhe), GFP_ATOMIC); if (!fnhe) goto out_unlock; fnhe->fnhe_next = hash->chain; fnhe->fnhe_genid = genid; fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; fnhe->fnhe_mtu_locked = lock; fnhe->fnhe_expires = max(1UL, expires); rcu_assign_pointer(hash->chain, fnhe); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception * applies to them. */ rt = rcu_dereference(nhc->nhc_rth_input); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; for_each_possible_cpu(i) { struct rtable __rcu **prt; prt = per_cpu_ptr(nhc->nhc_pcpu_rth_output, i); rt = rcu_dereference(*prt); if (rt) rt->dst.obsolete = DST_OBSOLETE_KILL; } } fnhe->fnhe_stamp = jiffies; out_unlock: spin_unlock_bh(&fnhe_lock); } static void __ip_do_redirect(struct rtable *rt, struct sk_buff *skb, struct flowi4 *fl4, bool kill_route) { __be32 new_gw = icmp_hdr(skb)->un.gateway; __be32 old_gw = ip_hdr(skb)->saddr; struct net_device *dev = skb->dev; struct in_device *in_dev; struct fib_result res; struct neighbour *n; struct net *net; switch (icmp_hdr(skb)->code & 7) { case ICMP_REDIR_NET: case ICMP_REDIR_NETTOS: case ICMP_REDIR_HOST: case ICMP_REDIR_HOSTTOS: break; default: return; } if (rt->rt_gw_family != AF_INET || rt->rt_gw4 != old_gw) return; in_dev = __in_dev_get_rcu(dev); if (!in_dev) return; net = dev_net(dev); if (new_gw == old_gw || !IN_DEV_RX_REDIRECTS(in_dev) || ipv4_is_multicast(new_gw) || ipv4_is_lbcast(new_gw) || ipv4_is_zeronet(new_gw)) goto reject_redirect; if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; if (IN_DEV_SEC_REDIRECTS(in_dev) && ip_fib_check_default(new_gw, dev)) goto reject_redirect; } else { if (inet_addr_type(net, new_gw) != RTN_UNICAST) goto reject_redirect; } n = __ipv4_neigh_lookup(rt->dst.dev, (__force u32)new_gw); if (!n) n = neigh_create(&arp_tbl, &new_gw, rt->dst.dev); if (!IS_ERR(n)) { if (!(n->nud_state & NUD_VALID)) { neigh_event_send(n, NULL); } else { if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, skb); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, new_gw, 0, false, jiffies + ip_rt_gc_timeout); } if (kill_route) rt->dst.obsolete = DST_OBSOLETE_KILL; call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); } neigh_release(n); } return; reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) { const struct iphdr *iph = (const struct iphdr *) skb->data; __be32 daddr = iph->daddr; __be32 saddr = iph->saddr; net_info_ratelimited("Redirect from %pI4 on %s about %pI4 ignored\n" " Advised path = %pI4 -> %pI4\n", &old_gw, dev->name, &new_gw, &saddr, &daddr); } #endif ; } static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct rtable *rt; struct flowi4 fl4; const struct iphdr *iph = (const struct iphdr *) skb->data; struct net *net = dev_net(skb->dev); int oif = skb->dev->ifindex; u8 tos = RT_TOS(iph->tos); u8 prot = iph->protocol; u32 mark = skb->mark; rt = (struct rtable *) dst; __build_flow_key(net, &fl4, sk, iph, oif, tos, prot, mark, 0); __ip_do_redirect(rt, skb, &fl4, true); } static void ipv4_negative_advice(struct sock *sk, struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; if ((dst->obsolete > 0) || (rt->rt_flags & RTCF_REDIRECTED) || rt->dst.expires) sk_dst_reset(sk); } /* * Algorithm: * 1. The first ip_rt_redirect_number redirects are sent * with exponential backoff, then we stop sending them at all, * assuming that the host ignores our redirects. * 2. If we did not see packets requiring redirects * during ip_rt_redirect_silence, we assume that the host * forgot redirected route and start to send redirects again. * * This algorithm is much cheaper and more intelligent than dumb load limiting * in icmp.c. * * NOTE. Do not forget to inhibit load limiting for redirects (redundant) * and "frag. need" (breaks PMTU discovery) in icmp.c. */ void ip_rt_send_redirect(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct in_device *in_dev; struct inet_peer *peer; struct net *net; int log_martians; int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); if (!in_dev || !IN_DEV_TX_REDIRECTS(in_dev)) { rcu_read_unlock(); return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); vif = l3mdev_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); return; } /* No redirected packets during ip_rt_redirect_silence; * reset the algorithm. */ if (time_after(jiffies, peer->rate_last + ip_rt_redirect_silence)) { peer->rate_tokens = 0; peer->n_redirects = 0; } /* Too many ignored redirects; do not send anything * set dst.rate_last to the last seen redirected packet. */ if (peer->n_redirects >= ip_rt_redirect_number) { peer->rate_last = jiffies; goto out_put_peer; } /* Check for load limit; set rate_last to the latest sent * redirect. */ if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { __be32 gw = rt_nexthop(rt, ip_hdr(skb)->daddr); icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); } out_put_peer: inet_putpeer(peer); } static int ip_error(struct sk_buff *skb) { struct rtable *rt = skb_rtable(skb); struct net_device *dev = skb->dev; struct in_device *in_dev; struct inet_peer *peer; unsigned long now; struct net *net; bool send; int code; if (netif_is_l3_master(skb->dev)) { dev = __dev_get_by_index(dev_net(skb->dev), IPCB(skb)->iif); if (!dev) goto out; } in_dev = __in_dev_get_rcu(dev); /* IP on this device is disabled. */ if (!in_dev) goto out; net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { case EHOSTUNREACH: __IP_INC_STATS(net, IPSTATS_MIB_INADDRERRORS); break; case ENETUNREACH: __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; } goto out; } switch (rt->dst.error) { case EINVAL: default: goto out; case EHOSTUNREACH: code = ICMP_HOST_UNREACH; break; case ENETUNREACH: code = ICMP_NET_UNREACH; __IP_INC_STATS(net, IPSTATS_MIB_INNOROUTES); break; case EACCES: code = ICMP_PKT_FILTERED; break; } peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, l3mdev_master_ifindex(skb->dev), 1); send = true; if (peer) { now = jiffies; peer->rate_tokens += now - peer->rate_last; if (peer->rate_tokens > ip_rt_error_burst) peer->rate_tokens = ip_rt_error_burst; peer->rate_last = now; if (peer->rate_tokens >= ip_rt_error_cost) peer->rate_tokens -= ip_rt_error_cost; else send = false; inet_putpeer(peer); } if (send) icmp_send(skb, ICMP_DEST_UNREACH, code, 0); out: kfree_skb(skb); return 0; } static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) { struct dst_entry *dst = &rt->dst; struct net *net = dev_net(dst->dev); u32 old_mtu = ipv4_mtu(dst); struct fib_result res; bool lock = false; if (ip_mtu_locked(dst)) return; if (old_mtu < mtu) return; if (mtu < ip_rt_min_pmtu) { lock = true; mtu = min(old_mtu, ip_rt_min_pmtu); } if (rt->rt_pmtu == mtu && !lock && time_before(jiffies, dst->expires - ip_rt_mtu_expires / 2)) return; rcu_read_lock(); if (fib_lookup(net, fl4, &res, 0) == 0) { struct fib_nh_common *nhc; fib_select_path(net, &res, fl4, NULL); nhc = FIB_RES_NHC(res); update_or_create_fnhe(nhc, fl4->daddr, 0, mtu, lock, jiffies + ip_rt_mtu_expires); } rcu_read_unlock(); } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; ip_rt_build_flow_key(&fl4, sk, skb); __ip_rt_update_pmtu(rt, &fl4, mtu); } void ipv4_update_pmtu(struct sk_buff *skb, struct net *net, u32 mtu, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; u32 mark = IP4_REPLY_MARK(net, skb->mark); __build_flow_key(net, &fl4, NULL, iph, oif, RT_TOS(iph->tos), protocol, mark, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_update_pmtu); static void __ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(sock_net(sk), &fl4, sk, iph, 0, 0, 0, 0, 0); if (!fl4.flowi4_mark) fl4.flowi4_mark = IP4_REPLY_MARK(sock_net(sk), skb->mark); rt = __ip_route_output_key(sock_net(sk), &fl4); if (!IS_ERR(rt)) { __ip_rt_update_pmtu(rt, &fl4, mtu); ip_rt_put(rt); } } void ipv4_sk_update_pmtu(struct sk_buff *skb, struct sock *sk, u32 mtu) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; struct dst_entry *odst = NULL; bool new = false; struct net *net = sock_net(sk); bh_lock_sock(sk); if (!ip_sk_accept_pmtu(sk)) goto out; odst = sk_dst_get(sk); if (sock_owned_by_user(sk) || !odst) { __ipv4_sk_update_pmtu(skb, sk, mtu); goto out; } __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = (struct rtable *)odst; if (odst->obsolete && !odst->ops->check(odst, 0)) { rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } __ip_rt_update_pmtu((struct rtable *) xfrm_dst_path(&rt->dst), &fl4, mtu); if (!dst_check(&rt->dst, 0)) { if (new) dst_release(&rt->dst); rt = ip_route_output_flow(sock_net(sk), &fl4, sk); if (IS_ERR(rt)) goto out; new = true; } if (new) sk_dst_set(sk, &rt->dst); out: bh_unlock_sock(sk); dst_release(odst); } EXPORT_SYMBOL_GPL(ipv4_sk_update_pmtu); void ipv4_redirect(struct sk_buff *skb, struct net *net, int oif, u8 protocol) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; __build_flow_key(net, &fl4, NULL, iph, oif, RT_TOS(iph->tos), protocol, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_redirect); void ipv4_sk_redirect(struct sk_buff *skb, struct sock *sk) { const struct iphdr *iph = (const struct iphdr *) skb->data; struct flowi4 fl4; struct rtable *rt; struct net *net = sock_net(sk); __build_flow_key(net, &fl4, sk, iph, 0, 0, 0, 0, 0); rt = __ip_route_output_key(net, &fl4); if (!IS_ERR(rt)) { __ip_do_redirect(rt, skb, &fl4, false); ip_rt_put(rt); } } EXPORT_SYMBOL_GPL(ipv4_sk_redirect); static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) { struct rtable *rt = (struct rtable *) dst; /* All IPV4 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. * * When a PMTU/redirect information update invalidates a route, * this is indicated by setting obsolete to DST_OBSOLETE_KILL or * DST_OBSOLETE_DEAD. */ if (dst->obsolete != DST_OBSOLETE_FORCE_CHK || rt_is_expired(rt)) return NULL; return dst; } static void ipv4_send_dest_unreach(struct sk_buff *skb) { struct net_device *dev; struct ip_options opt; int res; /* Recompile ip options since IPCB may not be valid anymore. * Also check we have a reasonable ipv4 header. */ if (!pskb_network_may_pull(skb, sizeof(struct iphdr)) || ip_hdr(skb)->version != 4 || ip_hdr(skb)->ihl < 5) return; memset(&opt, 0, sizeof(opt)); if (ip_hdr(skb)->ihl > 5) { if (!pskb_network_may_pull(skb, ip_hdr(skb)->ihl * 4)) return; opt.optlen = ip_hdr(skb)->ihl * 4 - sizeof(struct iphdr); rcu_read_lock(); dev = skb->dev ? skb->dev : skb_rtable(skb)->dst.dev; res = __ip_options_compile(dev_net(dev), &opt, skb, NULL); rcu_read_unlock(); if (res) return; } __icmp_send(skb, ICMP_DEST_UNREACH, ICMP_HOST_UNREACH, 0, &opt); } static void ipv4_link_failure(struct sk_buff *skb) { struct rtable *rt; ipv4_send_dest_unreach(skb); rt = skb_rtable(skb); if (rt) dst_set_expires(&rt->dst, 0); } static int ip_rt_bug(struct net *net, struct sock *sk, struct sk_buff *skb) { pr_debug("%s: %pI4 -> %pI4, %s\n", __func__, &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); WARN_ON(1); return 0; } /* We do not cache source address of outgoing interface, because it is used only by IP RR, TS and SRR options, so that it out of fast path. BTW remember: "addr" is allowed to be not aligned in IP options! */ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt) { __be32 src; if (rt_is_output_route(rt)) src = ip_hdr(skb)->saddr; else { struct fib_result res; struct iphdr *iph = ip_hdr(skb); struct flowi4 fl4 = { .daddr = iph->daddr, .saddr = iph->saddr, .flowi4_tos = iph->tos & IPTOS_RT_MASK, .flowi4_oif = rt->dst.dev->ifindex, .flowi4_iif = skb->dev->ifindex, .flowi4_mark = skb->mark, }; rcu_read_lock(); if (fib_lookup(dev_net(rt->dst.dev), &fl4, &res, 0) == 0) src = fib_result_prefsrc(dev_net(rt->dst.dev), &res); else src = inet_select_addr(rt->dst.dev, rt_nexthop(rt, iph->daddr), RT_SCOPE_UNIVERSE); rcu_read_unlock(); } memcpy(addr, &src, 4); } #ifdef CONFIG_IP_ROUTE_CLASSID static void set_class_tag(struct rtable *rt, u32 tag) { if (!(rt->dst.tclassid & 0xFFFF)) rt->dst.tclassid |= tag & 0xFFFF; if (!(rt->dst.tclassid & 0xFFFF0000)) rt->dst.tclassid |= tag & 0xFFFF0000; } #endif static unsigned int ipv4_default_advmss(const struct dst_entry *dst) { unsigned int header_size = sizeof(struct tcphdr) + sizeof(struct iphdr); unsigned int advmss = max_t(unsigned int, ipv4_mtu(dst) - header_size, ip_rt_min_advmss); return min(advmss, IPV4_MAX_PMTU - header_size); } static unsigned int ipv4_mtu(const struct dst_entry *dst) { const struct rtable *rt = (const struct rtable *) dst; unsigned int mtu = rt->rt_pmtu; if (!mtu || time_after_eq(jiffies, rt->dst.expires)) mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) goto out; mtu = READ_ONCE(dst->dev->mtu); if (unlikely(ip_mtu_locked(dst))) { if (rt->rt_uses_gateway && mtu > 576) mtu = 576; } out: mtu = min_t(unsigned int, mtu, IP_MAX_MTU); return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } static void ip_del_fnhe(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash; struct fib_nh_exception *fnhe, __rcu **fnhe_p; u32 hval = fnhe_hashfun(daddr); spin_lock_bh(&fnhe_lock); hash = rcu_dereference_protected(nhc->nhc_exceptions, lockdep_is_held(&fnhe_lock)); hash += hval; fnhe_p = &hash->chain; fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); while (fnhe) { if (fnhe->fnhe_daddr == daddr) { rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); /* set fnhe_daddr to 0 to ensure it won't bind with * new dsts in rt_bind_exception(). */ fnhe->fnhe_daddr = 0; fnhe_flush_routes(fnhe); kfree_rcu(fnhe, rcu); break; } fnhe_p = &fnhe->fnhe_next; fnhe = rcu_dereference_protected(fnhe->fnhe_next, lockdep_is_held(&fnhe_lock)); } spin_unlock_bh(&fnhe_lock); } static struct fib_nh_exception *find_exception(struct fib_nh_common *nhc, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nhc->nhc_exceptions); struct fib_nh_exception *fnhe; u32 hval; if (!hash) return NULL; hval = fnhe_hashfun(daddr); for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { if (fnhe->fnhe_daddr == daddr) { if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) { ip_del_fnhe(nhc, daddr); break; } return fnhe; } } return NULL; } /* MTU selection: * 1. mtu on route is locked - use it * 2. mtu from nexthop exception * 3. mtu from egress device */ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) { struct fib_nh_common *nhc = res->nhc; struct net_device *dev = nhc->nhc_dev; struct fib_info *fi = res->fi; u32 mtu = 0; if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; if (likely(!mtu)) { struct fib_nh_exception *fnhe; fnhe = find_exception(nhc, daddr); if (fnhe && !time_after_eq(jiffies, fnhe->fnhe_expires)) mtu = fnhe->fnhe_pmtu; } if (likely(!mtu)) mtu = min(READ_ONCE(dev->mtu), IP_MAX_MTU); return mtu - lwtunnel_headroom(nhc->nhc_lwtstate, mtu); } static bool rt_bind_exception(struct rtable *rt, struct fib_nh_exception *fnhe, __be32 daddr, const bool do_cache) { bool ret = false; spin_lock_bh(&fnhe_lock); if (daddr == fnhe->fnhe_daddr) { struct rtable __rcu **porig; struct rtable *orig; int genid = fnhe_genid(dev_net(rt->dst.dev)); if (rt_is_input_route(rt)) porig = &fnhe->fnhe_rth_input; else porig = &fnhe->fnhe_rth_output; orig = rcu_dereference(*porig); if (fnhe->fnhe_genid != genid) { fnhe->fnhe_genid = genid; fnhe->fnhe_gw = 0; fnhe->fnhe_pmtu = 0; fnhe->fnhe_expires = 0; fnhe->fnhe_mtu_locked = false; fnhe_flush_routes(fnhe); orig = NULL; } fill_route_from_fnhe(rt, fnhe); if (!rt->rt_gw4) { rt->rt_gw4 = daddr; rt->rt_gw_family = AF_INET; } if (do_cache) { dst_hold(&rt->dst); rcu_assign_pointer(*porig, rt); if (orig) { dst_dev_put(&orig->dst); dst_release(&orig->dst); } ret = true; } fnhe->fnhe_stamp = jiffies; } spin_unlock_bh(&fnhe_lock); return ret; } static bool rt_cache_route(struct fib_nh_common *nhc, struct rtable *rt) { struct rtable *orig, *prev, **p; bool ret = true; if (rt_is_input_route(rt)) { p = (struct rtable **)&nhc->nhc_rth_input; } else { p = (struct rtable **)raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } orig = *p; /* hold dst before doing cmpxchg() to avoid race condition * on this dst */ dst_hold(&rt->dst); prev = cmpxchg(p, orig, rt); if (prev == orig) { if (orig) { rt_add_uncached_list(orig); dst_release(&orig->dst); } } else { dst_release(&rt->dst); ret = false; } return ret; } struct uncached_list { spinlock_t lock; struct list_head head; }; static DEFINE_PER_CPU_ALIGNED(struct uncached_list, rt_uncached_list); void rt_add_uncached_list(struct rtable *rt) { struct uncached_list *ul = raw_cpu_ptr(&rt_uncached_list); rt->rt_uncached_list = ul; spin_lock_bh(&ul->lock); list_add_tail(&rt->rt_uncached, &ul->head); spin_unlock_bh(&ul->lock); } void rt_del_uncached_list(struct rtable *rt) { if (!list_empty(&rt->rt_uncached)) { struct uncached_list *ul = rt->rt_uncached_list; spin_lock_bh(&ul->lock); list_del(&rt->rt_uncached); spin_unlock_bh(&ul->lock); } } static void ipv4_dst_destroy(struct dst_entry *dst) { struct rtable *rt = (struct rtable *)dst; ip_dst_metrics_put(dst); rt_del_uncached_list(rt); } void rt_flush_dev(struct net_device *dev) { struct rtable *rt; int cpu; for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); spin_lock_bh(&ul->lock); list_for_each_entry(rt, &ul->head, rt_uncached) { if (rt->dst.dev != dev) continue; rt->dst.dev = blackhole_netdev; dev_hold(rt->dst.dev); dev_put(dev); } spin_unlock_bh(&ul->lock); } } static bool rt_cache_valid(const struct rtable *rt) { return rt && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && !rt_is_expired(rt); } static void rt_set_nexthop(struct rtable *rt, __be32 daddr, const struct fib_result *res, struct fib_nh_exception *fnhe, struct fib_info *fi, u16 type, u32 itag, const bool do_cache) { bool cached = false; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); if (nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK) { rt->rt_uses_gateway = 1; rt->rt_gw_family = nhc->nhc_gw_family; /* only INET and INET6 are supported */ if (likely(nhc->nhc_gw_family == AF_INET)) rt->rt_gw4 = nhc->nhc_gw.ipv4; else rt->rt_gw6 = nhc->nhc_gw.ipv6; } ip_dst_init_metrics(&rt->dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); rt->dst.tclassid = nh->nh_tclassid; } #endif rt->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr, do_cache); else if (do_cache) cached = rt_cache_route(nhc, rt); if (unlikely(!cached)) { /* Routes we intend to cache in nexthop exception or * FIB nexthop have the DST_NOCACHE bit clear. * However, if we are unsuccessful at storing this * route into the cache we really need to set it. */ if (!rt->rt_gw4) { rt->rt_gw_family = AF_INET; rt->rt_gw4 = daddr; } rt_add_uncached_list(rt); } } else rt_add_uncached_list(rt); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES set_class_tag(rt, res->tclassid); #endif set_class_tag(rt, itag); #endif } struct rtable *rt_dst_alloc(struct net_device *dev, unsigned int flags, u16 type, bool nopolicy, bool noxfrm, bool will_cache) { struct rtable *rt; rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, (will_cache ? 0 : DST_HOST) | (nopolicy ? DST_NOPOLICY : 0) | (noxfrm ? DST_NOXFRM : 0)); if (rt) { rt->rt_genid = rt_genid_ipv4(dev_net(dev)); rt->rt_flags = flags; rt->rt_type = type; rt->rt_is_input = 0; rt->rt_iif = 0; rt->rt_pmtu = 0; rt->rt_mtu_locked = 0; rt->rt_uses_gateway = 0; rt->rt_gw_family = 0; rt->rt_gw4 = 0; INIT_LIST_HEAD(&rt->rt_uncached); rt->dst.output = ip_output; if (flags & RTCF_LOCAL) rt->dst.input = ip_local_deliver; } return rt; } EXPORT_SYMBOL(rt_dst_alloc); struct rtable *rt_dst_clone(struct net_device *dev, struct rtable *rt) { struct rtable *new_rt; new_rt = dst_alloc(&ipv4_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, rt->dst.flags); if (new_rt) { new_rt->rt_genid = rt_genid_ipv4(dev_net(dev)); new_rt->rt_flags = rt->rt_flags; new_rt->rt_type = rt->rt_type; new_rt->rt_is_input = rt->rt_is_input; new_rt->rt_iif = rt->rt_iif; new_rt->rt_pmtu = rt->rt_pmtu; new_rt->rt_mtu_locked = rt->rt_mtu_locked; new_rt->rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) new_rt->rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) new_rt->rt_gw6 = rt->rt_gw6; INIT_LIST_HEAD(&new_rt->rt_uncached); new_rt->dst.flags |= DST_HOST; new_rt->dst.input = rt->dst.input; new_rt->dst.output = rt->dst.output; new_rt->dst.error = rt->dst.error; new_rt->dst.lastuse = jiffies; new_rt->dst.lwtstate = lwtstate_get(rt->dst.lwtstate); } return new_rt; } EXPORT_SYMBOL(rt_dst_clone); /* called in rcu_read_lock() section */ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct in_device *in_dev, u32 *itag) { int err; /* Primary sanity checks. */ if (!in_dev) return -EINVAL; if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr) || skb->protocol != htons(ETH_P_IP)) return -EINVAL; if (ipv4_is_loopback(saddr) && !IN_DEV_ROUTE_LOCALNET(in_dev)) return -EINVAL; if (ipv4_is_zeronet(saddr)) { if (!ipv4_is_local_multicast(daddr) && ip_hdr(skb)->protocol != IPPROTO_IGMP) return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, itag); if (err < 0) return err; } return 0; } /* called in rcu_read_lock() section */ static int ip_route_input_mc(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, int our) { struct in_device *in_dev = __in_dev_get_rcu(dev); unsigned int flags = RTCF_MULTICAST; struct rtable *rth; u32 itag = 0; int err; err = ip_mc_validate_source(skb, daddr, saddr, tos, dev, in_dev, &itag); if (err) return err; if (our) flags |= RTCF_LOCAL; rth = rt_dst_alloc(dev_net(dev)->loopback_dev, flags, RTN_MULTICAST, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, false); if (!rth) return -ENOBUFS; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->dst.output = ip_rt_bug; rth->rt_is_input= 1; #ifdef CONFIG_IP_MROUTE if (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) rth->dst.input = ip_mr_input; #endif RT_CACHE_STAT_INC(in_slow_mc); skb_dst_drop(skb); skb_dst_set(skb, &rth->dst); return 0; } static void ip_handle_martian_source(struct net_device *dev, struct in_device *in_dev, struct sk_buff *skb, __be32 daddr, __be32 saddr) { RT_CACHE_STAT_INC(in_martian_src); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) { /* * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ pr_warn("martian source %pI4 from %pI4, on dev %s\n", &daddr, &saddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { print_hex_dump(KERN_WARNING, "ll header: ", DUMP_PREFIX_OFFSET, 16, 1, skb_mac_header(skb), dev->hard_header_len, false); } } #endif } /* called in rcu_read_lock() section */ static int __mkroute_input(struct sk_buff *skb, const struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct net_device *dev = nhc->nhc_dev; struct fib_nh_exception *fnhe; struct rtable *rth; int err; struct in_device *out_dev; bool do_cache; u32 itag = 0; /* get a working reference to the output device */ out_dev = __in_dev_get_rcu(dev); if (!out_dev) { net_crit_ratelimited("Bug in ip_route_input_slow(). Please report.\n"); return -EINVAL; } err = fib_validate_source(skb, saddr, daddr, tos, FIB_RES_OIF(*res), in_dev->dev, in_dev, &itag); if (err < 0) { ip_handle_martian_source(in_dev->dev, in_dev, skb, daddr, saddr); goto cleanup; } do_cache = res->fi && !itag; if (out_dev == in_dev && err && IN_DEV_TX_REDIRECTS(out_dev) && skb->protocol == htons(ETH_P_IP)) { __be32 gw; gw = nhc->nhc_gw_family == AF_INET ? nhc->nhc_gw.ipv4 : 0; if (IN_DEV_SHARED_MEDIA(out_dev) || inet_addr_onlink(out_dev, saddr, gw)) IPCB(skb)->flags |= IPSKB_DOREDIRECT; } if (skb->protocol != htons(ETH_P_IP)) { /* Not IP (i.e. ARP). Do not create route, if it is * invalid for proxy arp. DNAT routes are always valid. * * Proxy arp feature have been extended to allow, ARP * replies back to the same interface, to support * Private VLAN switch technologies. See arp.c. */ if (out_dev == in_dev && IN_DEV_PROXY_ARP_PVLAN(in_dev) == 0) { err = -EINVAL; goto cleanup; } } fnhe = find_exception(nhc, daddr); if (do_cache) { if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); else rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; } } rth = rt_dst_alloc(out_dev->dev, 0, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(out_dev, NOXFRM), do_cache); if (!rth) { err = -ENOBUFS; goto cleanup; } rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); rth->dst.input = ip_forward; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag, do_cache); lwtunnel_set_redirect(&rth->dst); skb_dst_set(skb, &rth->dst); out: err = 0; cleanup: return err; } #ifdef CONFIG_IP_ROUTE_MULTIPATH /* To make ICMP packets follow the right flow, the multipath hash is * calculated from the inner IP addresses. */ static void ip_multipath_l3_keys(const struct sk_buff *skb, struct flow_keys *hash_keys) { const struct iphdr *outer_iph = ip_hdr(skb); const struct iphdr *key_iph = outer_iph; const struct iphdr *inner_iph; const struct icmphdr *icmph; struct iphdr _inner_iph; struct icmphdr _icmph; if (likely(outer_iph->protocol != IPPROTO_ICMP)) goto out; if (unlikely((outer_iph->frag_off & htons(IP_OFFSET)) != 0)) goto out; icmph = skb_header_pointer(skb, outer_iph->ihl * 4, sizeof(_icmph), &_icmph); if (!icmph) goto out; if (icmph->type != ICMP_DEST_UNREACH && icmph->type != ICMP_REDIRECT && icmph->type != ICMP_TIME_EXCEEDED && icmph->type != ICMP_PARAMETERPROB) goto out; inner_iph = skb_header_pointer(skb, outer_iph->ihl * 4 + sizeof(_icmph), sizeof(_inner_iph), &_inner_iph); if (!inner_iph) goto out; key_iph = inner_iph; out: hash_keys->addrs.v4addrs.src = key_iph->saddr; hash_keys->addrs.v4addrs.dst = key_iph->daddr; } /* if skb is set it will be used and fl4 can be NULL */ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys) { u32 multipath_hash = fl4 ? fl4->flowi4_multipath_hash : 0; struct flow_keys hash_keys; u32 mhash; switch (net->ipv4.sysctl_fib_multipath_hash_policy) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; if (skb) { ip_multipath_l3_keys(skb, &hash_keys); } else { hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } break; case 1: /* skb is currently provided only when forwarding */ if (skb) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; struct flow_keys keys; /* short-circuit if we already have L4 hash present */ if (skb->l4_hash) return skb_get_hash_raw(skb) >> 1; memset(&hash_keys, 0, sizeof(hash_keys)); if (!flkeys) { skb_flow_dissect_flow_keys(skb, &keys, flag); flkeys = &keys; } hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = flkeys->addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = flkeys->addrs.v4addrs.dst; hash_keys.ports.src = flkeys->ports.src; hash_keys.ports.dst = flkeys->ports.dst; hash_keys.basic.ip_proto = flkeys->basic.ip_proto; } else { memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; hash_keys.ports.src = fl4->fl4_sport; hash_keys.ports.dst = fl4->fl4_dport; hash_keys.basic.ip_proto = fl4->flowi4_proto; } break; case 2: memset(&hash_keys, 0, sizeof(hash_keys)); /* skb is currently provided only when forwarding */ if (skb) { struct flow_keys keys; skb_flow_dissect_flow_keys(skb, &keys, 0); /* Inner can be v4 or v6 */ if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV4_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = keys.addrs.v4addrs.src; hash_keys.addrs.v4addrs.dst = keys.addrs.v4addrs.dst; } else if (keys.control.addr_type == FLOW_DISSECTOR_KEY_IPV6_ADDRS) { hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; hash_keys.addrs.v6addrs.src = keys.addrs.v6addrs.src; hash_keys.addrs.v6addrs.dst = keys.addrs.v6addrs.dst; hash_keys.tags.flow_label = keys.tags.flow_label; hash_keys.basic.ip_proto = keys.basic.ip_proto; } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; ip_multipath_l3_keys(skb, &hash_keys); } } else { /* Same as case 0 */ hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; hash_keys.addrs.v4addrs.src = fl4->saddr; hash_keys.addrs.v4addrs.dst = fl4->daddr; } break; } mhash = flow_hash_from_keys(&hash_keys); if (multipath_hash) mhash = jhash_2words(mhash, multipath_hash, 0); return mhash >> 1; } #endif /* CONFIG_IP_ROUTE_MULTIPATH */ static int ip_mkroute_input(struct sk_buff *skb, struct fib_result *res, struct in_device *in_dev, __be32 daddr, __be32 saddr, u32 tos, struct flow_keys *hkeys) { #ifdef CONFIG_IP_ROUTE_MULTIPATH if (res->fi && fib_info_num_path(res->fi) > 1) { int h = fib_multipath_hash(res->fi->fib_net, NULL, skb, hkeys); fib_select_multipath(res, h); } #endif /* create a routing cache entry */ return __mkroute_input(skb, res, in_dev, daddr, saddr, tos); } /* * NOTE. We drop all the packets that has local source * addresses, because every properly looped back packet * must have correct destination already attached by output routine. * * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. * called with rcu_read_lock() */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { struct in_device *in_dev = __in_dev_get_rcu(dev); struct flow_keys *flkeys = NULL, _flkeys; struct net *net = dev_net(dev); struct ip_tunnel_info *tun_info; int err = -EINVAL; unsigned int flags = 0; u32 itag = 0; struct rtable *rth; struct flowi4 fl4; bool do_cache = true; /* IP on this device is disabled. */ if (!in_dev) goto out; /* Check for the most weird martians, which can be not detected by fib_lookup. */ tun_info = skb_tunnel_info(skb); if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; else fl4.flowi4_tun_key.tun_id = 0; skb_dst_drop(skb); if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; res->fi = NULL; res->table = NULL; if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; * I even do not know to fix it or not. Waiting for complains :-) */ if (ipv4_is_zeronet(saddr)) goto martian_source; if (ipv4_is_zeronet(daddr)) goto martian_destination; /* Following code try to avoid calling IN_DEV_NET_ROUTE_LOCALNET(), * and call it once if daddr or/and saddr are loopback addresses */ if (ipv4_is_loopback(daddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_destination; } else if (ipv4_is_loopback(saddr)) { if (!IN_DEV_NET_ROUTE_LOCALNET(in_dev, net)) goto martian_source; } /* * Now we are ready to route packet. */ fl4.flowi4_oif = 0; fl4.flowi4_iif = dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; fl4.flowi4_flags = 0; fl4.daddr = daddr; fl4.saddr = saddr; fl4.flowi4_uid = sock_net_uid(net, NULL); fl4.flowi4_multipath_hash = 0; if (fib4_rules_early_flow_dissect(net, skb, &fl4, &_flkeys)) { flkeys = &_flkeys; } else { fl4.flowi4_proto = 0; fl4.fl4_sport = 0; fl4.fl4_dport = 0; } err = fib_lookup(net, &fl4, res, 0); if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) err = -EHOSTUNREACH; goto no_route; } if (res->type == RTN_BROADCAST) { if (IN_DEV_BFORWARD(in_dev)) goto make_route; /* not do cache if bc_forwarding is enabled */ if (IPV4_DEVCONF_ALL(net, BC_FORWARDING)) do_cache = false; goto brd_input; } if (res->type == RTN_LOCAL) { err = fib_validate_source(skb, saddr, daddr, tos, 0, dev, in_dev, &itag); if (err < 0) goto martian_source; goto local_input; } if (!IN_DEV_FORWARD(in_dev)) { err = -EHOSTUNREACH; goto no_route; } if (res->type != RTN_UNICAST) goto martian_destination; make_route: err = ip_mkroute_input(skb, res, in_dev, daddr, saddr, tos, flkeys); out: return err; brd_input: if (skb->protocol != htons(ETH_P_IP)) goto e_inval; if (!ipv4_is_zeronet(saddr)) { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, in_dev, &itag); if (err < 0) goto martian_source; } flags |= RTCF_BROADCAST; res->type = RTN_BROADCAST; RT_CACHE_STAT_INC(in_brd); local_input: do_cache &= res->fi && !itag; if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth = rcu_dereference(nhc->nhc_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); err = 0; goto out; } } rth = rt_dst_alloc(l3mdev_master_dev_rcu(dev) ? : net->loopback_dev, flags | RTCF_LOCAL, res->type, IN_DEV_CONF_GET(in_dev, NOPOLICY), false, do_cache); if (!rth) goto e_nobufs; rth->dst.output= ip_rt_bug; #ifdef CONFIG_IP_ROUTE_CLASSID rth->dst.tclassid = itag; #endif rth->rt_is_input = 1; RT_CACHE_STAT_INC(in_slow_tot); if (res->type == RTN_UNREACHABLE) { rth->dst.input= ip_error; rth->dst.error= -err; rth->rt_flags &= ~RTCF_LOCAL; } if (do_cache) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); rth->dst.lwtstate = lwtstate_get(nhc->nhc_lwtstate); if (lwtunnel_input_redirect(rth->dst.lwtstate)) { WARN_ON(rth->dst.input == lwtunnel_input); rth->dst.lwtstate->orig_input = rth->dst.input; rth->dst.input = lwtunnel_input; } if (unlikely(!rt_cache_route(nhc, rth))) rt_add_uncached_list(rth); } skb_dst_set(skb, &rth->dst); err = 0; goto out; no_route: RT_CACHE_STAT_INC(in_no_route); res->type = RTN_UNREACHABLE; res->fi = NULL; res->table = NULL; goto local_input; /* * Do not cache martian addresses: they should be logged (RFC1812) */ martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev)) net_warn_ratelimited("martian destination %pI4 from %pI4, dev %s\n", &daddr, &saddr, dev->name); #endif e_inval: err = -EINVAL; goto out; e_nobufs: err = -ENOBUFS; goto out; martian_source: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); goto out; } int ip_route_input_noref(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev) { struct fib_result res; int err; tos &= IPTOS_RT_MASK; rcu_read_lock(); err = ip_route_input_rcu(skb, daddr, saddr, tos, dev, &res); rcu_read_unlock(); return err; } EXPORT_SYMBOL(ip_route_input_noref); /* called with rcu_read_lock held */ int ip_route_input_rcu(struct sk_buff *skb, __be32 daddr, __be32 saddr, u8 tos, struct net_device *dev, struct fib_result *res) { /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting network acquires a lot of useless route cache entries, sort of SDR messages from all the world. Now we try to get rid of them. Really, provided software IP multicast filter is organized reasonably (at least, hashed), it does not result in a slowdown comparing with route cache reject entries. Note, that multicast routers are not affected, because route cache entry is created eventually. */ if (ipv4_is_multicast(daddr)) { struct in_device *in_dev = __in_dev_get_rcu(dev); int our = 0; int err = -EINVAL; if (!in_dev) return err; our = ip_check_mc_rcu(in_dev, daddr, saddr, ip_hdr(skb)->protocol); /* check l3 master if no match yet */ if (!our && netif_is_l3_slave(dev)) { struct in_device *l3_in_dev; l3_in_dev = __in_dev_get_rcu(skb->dev); if (l3_in_dev) our = ip_check_mc_rcu(l3_in_dev, daddr, saddr, ip_hdr(skb)->protocol); } if (our #ifdef CONFIG_IP_MROUTE || (!ipv4_is_local_multicast(daddr) && IN_DEV_MFORWARD(in_dev)) #endif ) { err = ip_route_input_mc(skb, daddr, saddr, tos, dev, our); } return err; } return ip_route_input_slow(skb, daddr, saddr, tos, dev, res); } /* called with rcu_read_lock() */ static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, int orig_oif, struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; struct fib_nh_exception *fnhe; struct in_device *in_dev; u16 type = res->type; struct rtable *rth; bool do_cache; in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return ERR_PTR(-EINVAL); if (likely(!IN_DEV_ROUTE_LOCALNET(in_dev))) if (ipv4_is_loopback(fl4->saddr) && !(dev_out->flags & IFF_LOOPBACK) && !netif_is_l3_master(dev_out)) return ERR_PTR(-EINVAL); if (ipv4_is_lbcast(fl4->daddr)) type = RTN_BROADCAST; else if (ipv4_is_multicast(fl4->daddr)) type = RTN_MULTICAST; else if (ipv4_is_zeronet(fl4->daddr)) return ERR_PTR(-EINVAL); if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; do_cache = true; if (type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; fi = NULL; } else if (type == RTN_MULTICAST) { flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc_rcu(in_dev, fl4->daddr, fl4->saddr, fl4->flowi4_proto)) flags &= ~RTCF_LOCAL; else do_cache = false; /* If multicast route do not exist use * default one, but do not gateway in this case. * Yes, it is hack. */ if (fi && res->prefixlen < 4) fi = NULL; } else if ((type == RTN_LOCAL) && (orig_oif != 0) && (orig_oif != dev_out->ifindex)) { /* For local routes that require a particular output interface * we do not want to cache the result. Caching the result * causes incorrect behaviour when there are multiple source * addresses on the interface, the end result being that if the * intended recipient is waiting on that interface for the * packet he won't receive it because it will be delivered on * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; if (fi) { struct fib_nh_common *nhc = FIB_RES_NHC(*res); struct rtable __rcu **prth; fnhe = find_exception(nhc, fl4->daddr); if (!do_cache) goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; } else { if (unlikely(fl4->flowi4_flags & FLOWI_FLAG_KNOWN_NH && !(nhc->nhc_gw_family && nhc->nhc_scope == RT_SCOPE_LINK))) { do_cache = false; goto add; } prth = raw_cpu_ptr(nhc->nhc_pcpu_rth_output); } rth = rcu_dereference(*prth); if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } add: rth = rt_dst_alloc(dev_out, flags, type, IN_DEV_CONF_GET(in_dev, NOPOLICY), IN_DEV_CONF_GET(in_dev, NOXFRM), do_cache); if (!rth) return ERR_PTR(-ENOBUFS); rth->rt_iif = orig_oif; RT_CACHE_STAT_INC(out_slow_tot); if (flags & (RTCF_BROADCAST | RTCF_MULTICAST)) { if (flags & RTCF_LOCAL && !(dev_out->flags & IFF_LOOPBACK)) { rth->dst.output = ip_mc_output; RT_CACHE_STAT_INC(out_slow_mc); } #ifdef CONFIG_IP_MROUTE if (type == RTN_MULTICAST) { if (IN_DEV_MFORWARD(in_dev) && !ipv4_is_local_multicast(fl4->daddr)) { rth->dst.input = ip_mr_input; rth->dst.output = ip_mc_output; } } #endif } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0, do_cache); lwtunnel_set_redirect(&rth->dst); return rth; } /* * Major route resolver routine. */ struct rtable *ip_route_output_key_hash(struct net *net, struct flowi4 *fl4, const struct sk_buff *skb) { __u8 tos = RT_FL_TOS(fl4); struct fib_result res = { .type = RTN_UNSPEC, .fi = NULL, .table = NULL, .tclassid = 0, }; struct rtable *rth; fl4->flowi4_iif = LOOPBACK_IFINDEX; fl4->flowi4_tos = tos & IPTOS_RT_MASK; fl4->flowi4_scope = ((tos & RTO_ONLINK) ? RT_SCOPE_LINK : RT_SCOPE_UNIVERSE); rcu_read_lock(); rth = ip_route_output_key_hash_rcu(net, fl4, &res, skb); rcu_read_unlock(); return rth; } EXPORT_SYMBOL_GPL(ip_route_output_key_hash); struct rtable *ip_route_output_key_hash_rcu(struct net *net, struct flowi4 *fl4, struct fib_result *res, const struct sk_buff *skb) { struct net_device *dev_out = NULL; int orig_oif = fl4->flowi4_oif; unsigned int flags = 0; struct rtable *rth; int err; if (fl4->saddr) { if (ipv4_is_multicast(fl4->saddr) || ipv4_is_lbcast(fl4->saddr) || ipv4_is_zeronet(fl4->saddr)) { rth = ERR_PTR(-EINVAL); goto out; } rth = ERR_PTR(-ENETUNREACH); /* I removed check for oif == dev_out->oif here. It was wrong for two reasons: 1. ip_dev_find(net, saddr) can return wrong iface, if saddr is assigned to multiple interfaces. 2. Moreover, we are allowed to send packets with saddr of another iface. --ANK */ if (fl4->flowi4_oif == 0 && (ipv4_is_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ dev_out = __ip_dev_find(net, fl4->saddr, false); if (!dev_out) goto out; /* Special hack: user can direct multicasts and limited broadcast via necessary interface without fiddling with IP_MULTICAST_IF or IP_PKTINFO. This hack is not just for fun, it allows vic,vat and friends to work. They bind socket to loopback, set ttl to zero and expect that it will work. From the viewpoint of routing cache they are broken, because we are not allowed to build multicast path with loopback source addr (look, routing cache cannot know, that ttl is zero, so that packet will not leave this host and route is valid). Luckily, this hack is good workaround. */ fl4->flowi4_oif = dev_out->ifindex; goto make_route; } if (!(fl4->flowi4_flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ if (!__ip_dev_find(net, fl4->saddr, false)) goto out; } } if (fl4->flowi4_oif) { dev_out = dev_get_by_index_rcu(net, fl4->flowi4_oif); rth = ERR_PTR(-ENODEV); if (!dev_out) goto out; /* RACE: Check return value of inet_select_addr instead. */ if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { rth = ERR_PTR(-ENETUNREACH); goto out; } if (ipv4_is_local_multicast(fl4->daddr) || ipv4_is_lbcast(fl4->daddr) || fl4->flowi4_proto == IPPROTO_IGMP) { if (!fl4->saddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); goto make_route; } if (!fl4->saddr) { if (ipv4_is_multicast(fl4->daddr)) fl4->saddr = inet_select_addr(dev_out, 0, fl4->flowi4_scope); else if (!fl4->daddr) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } } if (!fl4->daddr) { fl4->daddr = fl4->saddr; if (!fl4->daddr) fl4->daddr = fl4->saddr = htonl(INADDR_LOOPBACK); dev_out = net->loopback_dev; fl4->flowi4_oif = LOOPBACK_IFINDEX; res->type = RTN_LOCAL; flags |= RTCF_LOCAL; goto make_route; } err = fib_lookup(net, fl4, res, 0); if (err) { res->fi = NULL; res->table = NULL; if (fl4->flowi4_oif && (ipv4_is_multicast(fl4->daddr) || !netif_index_is_l3_master(net, fl4->flowi4_oif))) { /* Apparently, routing tables are wrong. Assume, that the destination is on link. WHY? DW. Because we are allowed to send to iface even if it has NO routes and NO assigned addresses. When oif is specified, routing tables are looked up with only one purpose: to catch if destination is gatewayed, rather than direct. Moreover, if MSG_DONTROUTE is set, we send packet, ignoring both routing tables and ifaddr state. --ANK We could make it even if oif is unknown, likely IPv6, but we do not. */ if (fl4->saddr == 0) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); res->type = RTN_UNICAST; goto make_route; } rth = ERR_PTR(err); goto out; } if (res->type == RTN_LOCAL) { if (!fl4->saddr) { if (res->fi->fib_prefsrc) fl4->saddr = res->fi->fib_prefsrc; else fl4->saddr = fl4->daddr; } /* L3 master device is the loopback for that domain */ dev_out = l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) ? : net->loopback_dev; /* make sure orig_oif points to fib result device even * though packet rx/tx happens over loopback or l3mdev */ orig_oif = FIB_RES_OIF(*res); fl4->flowi4_oif = dev_out->ifindex; flags |= RTCF_LOCAL; goto make_route; } fib_select_path(net, res, fl4, skb); dev_out = FIB_RES_DEV(*res); make_route: rth = __mkroute_output(res, fl4, orig_oif, dev_out, flags); out: return rth; } static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) { return NULL; } static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { } static void ipv4_rt_blackhole_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { } static u32 *ipv4_rt_blackhole_cow_metrics(struct dst_entry *dst, unsigned long old) { return NULL; } static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .check = ipv4_blackhole_dst_check, .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .redirect = ipv4_rt_blackhole_redirect, .cow_metrics = ipv4_rt_blackhole_cow_metrics, .neigh_lookup = ipv4_neigh_lookup, }; struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_orig) { struct rtable *ort = (struct rtable *) dst_orig; struct rtable *rt; rt = dst_alloc(&ipv4_dst_blackhole_ops, NULL, 1, DST_OBSOLETE_DEAD, 0); if (rt) { struct dst_entry *new = &rt->dst; new->__use = 1; new->input = dst_discard; new->output = dst_discard_out; new->dev = net->loopback_dev; if (new->dev) dev_hold(new->dev); rt->rt_is_input = ort->rt_is_input; rt->rt_iif = ort->rt_iif; rt->rt_pmtu = ort->rt_pmtu; rt->rt_mtu_locked = ort->rt_mtu_locked; rt->rt_genid = rt_genid_ipv4(net); rt->rt_flags = ort->rt_flags; rt->rt_type = ort->rt_type; rt->rt_uses_gateway = ort->rt_uses_gateway; rt->rt_gw_family = ort->rt_gw_family; if (rt->rt_gw_family == AF_INET) rt->rt_gw4 = ort->rt_gw4; else if (rt->rt_gw_family == AF_INET6) rt->rt_gw6 = ort->rt_gw6; INIT_LIST_HEAD(&rt->rt_uncached); } dst_release(dst_orig); return rt ? &rt->dst : ERR_PTR(-ENOMEM); } struct rtable *ip_route_output_flow(struct net *net, struct flowi4 *flp4, const struct sock *sk) { struct rtable *rt = __ip_route_output_key(net, flp4); if (IS_ERR(rt)) return rt; if (flp4->flowi4_proto) { flp4->flowi4_oif = rt->dst.dev->ifindex; rt = (struct rtable *)xfrm_lookup_route(net, &rt->dst, flowi4_to_flowi(flp4), sk, 0); } return rt; } EXPORT_SYMBOL_GPL(ip_route_output_flow); /* called with rcu_read_lock held */ static int rt_fill_info(struct net *net, __be32 dst, __be32 src, struct rtable *rt, u32 table_id, struct flowi4 *fl4, struct sk_buff *skb, u32 portid, u32 seq, unsigned int flags) { struct rtmsg *r; struct nlmsghdr *nlh; unsigned long expires = 0; u32 error; u32 metrics[RTAX_MAX]; nlh = nlmsg_put(skb, portid, seq, RTM_NEWROUTE, sizeof(*r), flags); if (!nlh) return -EMSGSIZE; r = nlmsg_data(nlh); r->rtm_family = AF_INET; r->rtm_dst_len = 32; r->rtm_src_len = 0; r->rtm_tos = fl4 ? fl4->flowi4_tos : 0; r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, table_id)) goto nla_put_failure; r->rtm_type = rt->rt_type; r->rtm_scope = RT_SCOPE_UNIVERSE; r->rtm_protocol = RTPROT_UNSPEC; r->rtm_flags = (rt->rt_flags & ~0xFFFF) | RTM_F_CLONED; if (rt->rt_flags & RTCF_NOTIFY) r->rtm_flags |= RTM_F_NOTIFY; if (IPCB(skb)->flags & IPSKB_DOREDIRECT) r->rtm_flags |= RTCF_DOREDIRECT; if (nla_put_in_addr(skb, RTA_DST, dst)) goto nla_put_failure; if (src) { r->rtm_src_len = 32; if (nla_put_in_addr(skb, RTA_SRC, src)) goto nla_put_failure; } if (rt->dst.dev && nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) goto nla_put_failure; #ifdef CONFIG_IP_ROUTE_CLASSID if (rt->dst.tclassid && nla_put_u32(skb, RTA_FLOW, rt->dst.tclassid)) goto nla_put_failure; #endif if (fl4 && !rt_is_input_route(rt) && fl4->saddr != src) { if (nla_put_in_addr(skb, RTA_PREFSRC, fl4->saddr)) goto nla_put_failure; } if (rt->rt_uses_gateway) { if (rt->rt_gw_family == AF_INET && nla_put_in_addr(skb, RTA_GATEWAY, rt->rt_gw4)) { goto nla_put_failure; } else if (rt->rt_gw_family == AF_INET6) { int alen = sizeof(struct in6_addr); struct nlattr *nla; struct rtvia *via; nla = nla_reserve(skb, RTA_VIA, alen + 2); if (!nla) goto nla_put_failure; via = nla_data(nla); via->rtvia_family = AF_INET6; memcpy(via->rtvia_addr, &rt->rt_gw6, alen); } } expires = rt->dst.expires; if (expires) { unsigned long now = jiffies; if (time_before(now, expires)) expires -= now; else expires = 0; } memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); if (rt->rt_pmtu && expires) metrics[RTAX_MTU - 1] = rt->rt_pmtu; if (rt->rt_mtu_locked && expires) metrics[RTAX_LOCK - 1] |= BIT(RTAX_MTU); if (rtnetlink_put_metrics(skb, metrics) < 0) goto nla_put_failure; if (fl4) { if (fl4->flowi4_mark && nla_put_u32(skb, RTA_MARK, fl4->flowi4_mark)) goto nla_put_failure; if (!uid_eq(fl4->flowi4_uid, INVALID_UID) && nla_put_u32(skb, RTA_UID, from_kuid_munged(current_user_ns(), fl4->flowi4_uid))) goto nla_put_failure; if (rt_is_input_route(rt)) { #ifdef CONFIG_IP_MROUTE if (ipv4_is_multicast(dst) && !ipv4_is_local_multicast(dst) && IPV4_DEVCONF_ALL(net, MC_FORWARDING)) { int err = ipmr_get_route(net, skb, fl4->saddr, fl4->daddr, r, portid); if (err <= 0) { if (err == 0) return 0; goto nla_put_failure; } } else #endif if (nla_put_u32(skb, RTA_IIF, fl4->flowi4_iif)) goto nla_put_failure; } } error = rt->dst.error; if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, error) < 0) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fnhe_hash_bucket *bucket, int genid, int *fa_index, int fa_start, unsigned int flags) { int i; for (i = 0; i < FNHE_HASH_SIZE; i++) { struct fib_nh_exception *fnhe; for (fnhe = rcu_dereference(bucket[i].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { struct rtable *rt; int err; if (*fa_index < fa_start) goto next; if (fnhe->fnhe_genid != genid) goto next; if (fnhe->fnhe_expires && time_after(jiffies, fnhe->fnhe_expires)) goto next; rt = rcu_dereference(fnhe->fnhe_rth_input); if (!rt) rt = rcu_dereference(fnhe->fnhe_rth_output); if (!rt) goto next; err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt, table_id, NULL, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, flags); if (err) return err; next: (*fa_index)++; } } return 0; } int fib_dump_info_fnhe(struct sk_buff *skb, struct netlink_callback *cb, u32 table_id, struct fib_info *fi, int *fa_index, int fa_start, unsigned int flags) { struct net *net = sock_net(cb->skb->sk); int nhsel, genid = fnhe_genid(net); for (nhsel = 0; nhsel < fib_info_num_path(fi); nhsel++) { struct fib_nh_common *nhc = fib_info_nhc(fi, nhsel); struct fnhe_hash_bucket *bucket; int err; if (nhc->nhc_flags & RTNH_F_DEAD) continue; rcu_read_lock(); bucket = rcu_dereference(nhc->nhc_exceptions); err = 0; if (bucket) err = fnhe_dump_bucket(net, skb, cb, table_id, bucket, genid, fa_index, fa_start, flags); rcu_read_unlock(); if (err) return err; } return 0; } static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, u8 ip_proto, __be16 sport, __be16 dport) { struct sk_buff *skb; struct iphdr *iph; skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) return NULL; /* Reserve room for dummy headers, this skb can pass * through good chunk of routing engine. */ skb_reset_mac_header(skb); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); iph = skb_put(skb, sizeof(struct iphdr)); iph->protocol = ip_proto; iph->saddr = src; iph->daddr = dst; iph->version = 0x4; iph->frag_off = 0; iph->ihl = 0x5; skb_set_transport_header(skb, skb->len); switch (iph->protocol) { case IPPROTO_UDP: { struct udphdr *udph; udph = skb_put_zero(skb, sizeof(struct udphdr)); udph->source = sport; udph->dest = dport; udph->len = htons(sizeof(struct udphdr)); udph->check = 0; break; } case IPPROTO_TCP: { struct tcphdr *tcph; tcph = skb_put_zero(skb, sizeof(struct tcphdr)); tcph->source = sport; tcph->dest = dport; tcph->doff = sizeof(struct tcphdr) / 4; tcph->rst = 1; tcph->check = ~tcp_v4_check(sizeof(struct tcphdr), src, dst, 0); break; } case IPPROTO_ICMP: { struct icmphdr *icmph; icmph = skb_put_zero(skb, sizeof(struct icmphdr)); icmph->type = ICMP_ECHO; icmph->code = 0; } } return skb; } static int inet_rtm_valid_getroute_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { struct rtmsg *rtm; int i, err; if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { NL_SET_ERR_MSG(extack, "ipv4: Invalid header for route get request"); return -EINVAL; } if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); rtm = nlmsg_data(nlh); if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for route get request"); return -EINVAL; } if (rtm->rtm_flags & ~(RTM_F_NOTIFY | RTM_F_LOOKUP_TABLE | RTM_F_FIB_MATCH)) { NL_SET_ERR_MSG(extack, "ipv4: Unsupported rtm_flags for route get request"); return -EINVAL; } err = nlmsg_parse_deprecated_strict(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, extack); if (err) return err; if ((tb[RTA_SRC] && !rtm->rtm_src_len) || (tb[RTA_DST] && !rtm->rtm_dst_len)) { NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); return -EINVAL; } for (i = 0; i <= RTA_MAX; i++) { if (!tb[i]) continue; switch (i) { case RTA_IIF: case RTA_OIF: case RTA_SRC: case RTA_DST: case RTA_IP_PROTO: case RTA_SPORT: case RTA_DPORT: case RTA_MARK: case RTA_UID: break; default: NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in route get request"); return -EINVAL; } } return 0; } static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; u32 table_id = RT_TABLE_MAIN; __be16 sport = 0, dport = 0; struct fib_result res = {}; u8 ip_proto = IPPROTO_UDP; struct rtable *rt = NULL; struct sk_buff *skb; struct rtmsg *rtm; struct flowi4 fl4 = {}; __be32 dst = 0; __be32 src = 0; kuid_t uid; u32 iif; int err; int mark; err = inet_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; rtm = nlmsg_data(nlh); src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; dst = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; iif = tb[RTA_IIF] ? nla_get_u32(tb[RTA_IIF]) : 0; mark = tb[RTA_MARK] ? nla_get_u32(tb[RTA_MARK]) : 0; if (tb[RTA_UID]) uid = make_kuid(current_user_ns(), nla_get_u32(tb[RTA_UID])); else uid = (iif ? INVALID_UID : current_uid()); if (tb[RTA_IP_PROTO]) { err = rtm_getroute_parse_ip_proto(tb[RTA_IP_PROTO], &ip_proto, AF_INET, extack); if (err) return err; } if (tb[RTA_SPORT]) sport = nla_get_be16(tb[RTA_SPORT]); if (tb[RTA_DPORT]) dport = nla_get_be16(tb[RTA_DPORT]); skb = inet_rtm_getroute_build_skb(src, dst, ip_proto, sport, dport); if (!skb) return -ENOBUFS; fl4.daddr = dst; fl4.saddr = src; fl4.flowi4_tos = rtm->rtm_tos & IPTOS_RT_MASK; fl4.flowi4_oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0; fl4.flowi4_mark = mark; fl4.flowi4_uid = uid; if (sport) fl4.fl4_sport = sport; if (dport) fl4.fl4_dport = dport; fl4.flowi4_proto = ip_proto; rcu_read_lock(); if (iif) { struct net_device *dev; dev = dev_get_by_index_rcu(net, iif); if (!dev) { err = -ENODEV; goto errout_rcu; } fl4.flowi4_iif = iif; /* for rt_fill_info */ skb->dev = dev; skb->mark = mark; err = ip_route_input_rcu(skb, dst, src, rtm->rtm_tos & IPTOS_RT_MASK, dev, &res); rt = skb_rtable(skb); if (err == 0 && rt->dst.error) err = -rt->dst.error; } else { fl4.flowi4_iif = LOOPBACK_IFINDEX; skb->dev = net->loopback_dev; rt = ip_route_output_key_hash_rcu(net, &fl4, &res, skb); err = 0; if (IS_ERR(rt)) err = PTR_ERR(rt); else skb_dst_set(skb, &rt->dst); } if (err) goto errout_rcu; if (rtm->rtm_flags & RTM_F_NOTIFY) rt->rt_flags |= RTCF_NOTIFY; if (rtm->rtm_flags & RTM_F_LOOKUP_TABLE) table_id = res.table ? res.table->tb_id : 0; /* reset skb for netlink reply msg */ skb_trim(skb, 0); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, RTM_NEWROUTE, table_id, rt->rt_type, res.prefix, res.prefixlen, fl4.flowi4_tos, res.fi, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); } if (err < 0) goto errout_rcu; rcu_read_unlock(); err = rtnl_unicast(skb, net, NETLINK_CB(in_skb).portid); errout_free: return err; errout_rcu: rcu_read_unlock(); kfree_skb(skb); goto errout_free; } void ip_rt_multicast_event(struct in_device *in_dev) { rt_cache_flush(dev_net(in_dev->dev)); } #ifdef CONFIG_SYSCTL static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_gc_elasticity __read_mostly = 8; static int ip_min_valid_pmtu __read_mostly = IPV4_MIN_MTU; static int ipv4_sysctl_rtcache_flush(struct ctl_table *__ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { struct net *net = (struct net *)__ctl->extra1; if (write) { rt_cache_flush(net); fnhe_genid_bump(net); return 0; } return -EINVAL; } static struct ctl_table ipv4_route_table[] = { { .procname = "gc_thresh", .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "max_size", .data = &ip_rt_max_size, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { /* Deprecated. Use gc_min_interval_ms */ .procname = "gc_min_interval", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_min_interval_ms", .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_ms_jiffies, }, { .procname = "gc_timeout", .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "gc_interval", .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_number", .data = &ip_rt_redirect_number, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "redirect_silence", .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_cost", .data = &ip_rt_error_cost, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "error_burst", .data = &ip_rt_error_burst, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "gc_elasticity", .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { .procname = "mtu_expires", .data = &ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_jiffies, }, { .procname = "min_pmtu", .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = &ip_min_valid_pmtu, }, { .procname = "min_adv_mss", .data = &ip_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static const char ipv4_route_flush_procname[] = "flush"; static struct ctl_table ipv4_route_flush_table[] = { { .procname = ipv4_route_flush_procname, .maxlen = sizeof(int), .mode = 0200, .proc_handler = ipv4_sysctl_rtcache_flush, }, { }, }; static __net_init int sysctl_route_net_init(struct net *net) { struct ctl_table *tbl; tbl = ipv4_route_flush_table; if (!net_eq(net, &init_net)) { tbl = kmemdup(tbl, sizeof(ipv4_route_flush_table), GFP_KERNEL); if (!tbl) goto err_dup; /* Don't export non-whitelisted sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { if (tbl[0].procname != ipv4_route_flush_procname) tbl[0].procname = NULL; } } tbl[0].extra1 = net; net->ipv4.route_hdr = register_net_sysctl(net, "net/ipv4/route", tbl); if (!net->ipv4.route_hdr) goto err_reg; return 0; err_reg: if (tbl != ipv4_route_flush_table) kfree(tbl); err_dup: return -ENOMEM; } static __net_exit void sysctl_route_net_exit(struct net *net) { struct ctl_table *tbl; tbl = net->ipv4.route_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.route_hdr); BUG_ON(tbl == ipv4_route_flush_table); kfree(tbl); } static __net_initdata struct pernet_operations sysctl_route_ops = { .init = sysctl_route_net_init, .exit = sysctl_route_net_exit, }; #endif static __net_init int rt_genid_init(struct net *net) { atomic_set(&net->ipv4.rt_genid, 0); atomic_set(&net->fnhe_genid, 0); atomic_set(&net->ipv4.dev_addr_genid, get_random_int()); return 0; } static __net_initdata struct pernet_operations rt_genid_ops = { .init = rt_genid_init, }; static int __net_init ipv4_inetpeer_init(struct net *net) { struct inet_peer_base *bp = kmalloc(sizeof(*bp), GFP_KERNEL); if (!bp) return -ENOMEM; inet_peer_base_init(bp); net->ipv4.peers = bp; return 0; } static void __net_exit ipv4_inetpeer_exit(struct net *net) { struct inet_peer_base *bp = net->ipv4.peers; net->ipv4.peers = NULL; inetpeer_invalidate_tree(bp); kfree(bp); } static __net_initdata struct pernet_operations ipv4_inetpeer_ops = { .init = ipv4_inetpeer_init, .exit = ipv4_inetpeer_exit, }; #ifdef CONFIG_IP_ROUTE_CLASSID struct ip_rt_acct __percpu *ip_rt_acct __read_mostly; #endif /* CONFIG_IP_ROUTE_CLASSID */ int __init ip_rt_init(void) { void *idents_hash; int cpu; /* For modern hosts, this will use 2 MB of memory */ idents_hash = alloc_large_system_hash("IP idents", sizeof(*ip_idents) + sizeof(*ip_tstamps), 0, 16, /* one bucket per 64 KB */ HASH_ZERO, NULL, &ip_idents_mask, 2048, 256*1024); ip_idents = idents_hash; prandom_bytes(ip_idents, (ip_idents_mask + 1) * sizeof(*ip_idents)); ip_tstamps = idents_hash + (ip_idents_mask + 1) * sizeof(*ip_idents); for_each_possible_cpu(cpu) { struct uncached_list *ul = &per_cpu(rt_uncached_list, cpu); INIT_LIST_HEAD(&ul->head); spin_lock_init(&ul->lock); } #ifdef CONFIG_IP_ROUTE_CLASSID ip_rt_acct = __alloc_percpu(256 * sizeof(struct ip_rt_acct), __alignof__(struct ip_rt_acct)); if (!ip_rt_acct) panic("IP: failed to allocate ip_rt_acct\n"); #endif ipv4_dst_ops.kmem_cachep = kmem_cache_create("ip_dst_cache", sizeof(struct rtable), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; if (dst_entries_init(&ipv4_dst_ops) < 0) panic("IP: failed to allocate ipv4_dst_ops counter\n"); if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); ipv4_dst_ops.gc_thresh = ~0; ip_rt_max_size = INT_MAX; devinet_init(); ip_fib_init(); if (ip_rt_proc_init()) pr_err("Unable to create route proc files\n"); #ifdef CONFIG_XFRM xfrm_init(); xfrm4_init(); #endif rtnl_register(PF_INET, RTM_GETROUTE, inet_rtm_getroute, NULL, RTNL_FLAG_DOIT_UNLOCKED); #ifdef CONFIG_SYSCTL register_pernet_subsys(&sysctl_route_ops); #endif register_pernet_subsys(&rt_genid_ops); register_pernet_subsys(&ipv4_inetpeer_ops); return 0; } #ifdef CONFIG_SYSCTL /* * We really need to sanitize the damn ipv4 init order, then all * this nonsense will go away. */ void __init ip_static_sysctl_init(void) { register_net_sysctl(&init_net, "net/ipv4/route", ipv4_route_table); } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGE_MM_H #define _LINUX_HUGE_MM_H #include <linux/sched/coredump.h> #include <linux/mm_types.h> #include <linux/fs.h> /* only for vma_is_dax() */ extern vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf); extern int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr, struct vm_area_struct *vma); extern void huge_pmd_set_accessed(struct vm_fault *vmf, pmd_t orig_pmd); extern int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm, pud_t *dst_pud, pud_t *src_pud, unsigned long addr, struct vm_area_struct *vma); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD extern void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud); #else static inline void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { } #endif extern vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags); extern bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next); extern int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr); extern int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr); extern int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec); extern bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, pmd_t *old_pmd, pmd_t *new_pmd); extern int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, int prot_numa); vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write); vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write); enum transparent_hugepage_flag { TRANSPARENT_HUGEPAGE_FLAG, TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG, #ifdef CONFIG_DEBUG_VM TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG, #endif }; struct kobject; struct kobj_attribute; extern ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag); extern ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag); extern struct kobj_attribute shmem_enabled_attr; #define HPAGE_PMD_ORDER (HPAGE_PMD_SHIFT-PAGE_SHIFT) #define HPAGE_PMD_NR (1<<HPAGE_PMD_ORDER) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define HPAGE_PMD_SHIFT PMD_SHIFT #define HPAGE_PMD_SIZE ((1UL) << HPAGE_PMD_SHIFT) #define HPAGE_PMD_MASK (~(HPAGE_PMD_SIZE - 1)) #define HPAGE_PUD_SHIFT PUD_SHIFT #define HPAGE_PUD_SIZE ((1UL) << HPAGE_PUD_SHIFT) #define HPAGE_PUD_MASK (~(HPAGE_PUD_SIZE - 1)) extern bool is_vma_temporary_stack(struct vm_area_struct *vma); extern unsigned long transparent_hugepage_flags; /* * to be used on vmas which are known to support THP. * Use transparent_hugepage_enabled otherwise */ static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { if (vma->vm_flags & VM_NOHUGEPAGE) return false; if (is_vma_temporary_stack(vma)) return false; if (test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return false; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_FLAG)) return true; /* * For dax vmas, try to always use hugepage mappings. If the kernel does * not support hugepages, fsdax mappings will fallback to PAGE_SIZE * mappings, and device-dax namespaces, that try to guarantee a given * mapping size, will fail to enable */ if (vma_is_dax(vma)) return true; if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)) return !!(vma->vm_flags & VM_HUGEPAGE); return false; } bool transparent_hugepage_enabled(struct vm_area_struct *vma); #define HPAGE_CACHE_INDEX_MASK (HPAGE_PMD_NR - 1) static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { /* Don't have to check pgoff for anonymous vma */ if (!vma_is_anonymous(vma)) { if (((vma->vm_start >> PAGE_SHIFT) & HPAGE_CACHE_INDEX_MASK) != (vma->vm_pgoff & HPAGE_CACHE_INDEX_MASK)) return false; } if (haddr < vma->vm_start || haddr + HPAGE_PMD_SIZE > vma->vm_end) return false; return true; } #define transparent_hugepage_use_zero_page() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG)) #ifdef CONFIG_DEBUG_VM #define transparent_hugepage_debug_cow() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEBUG_COW_FLAG)) #else /* CONFIG_DEBUG_VM */ #define transparent_hugepage_debug_cow() 0 #endif /* CONFIG_DEBUG_VM */ extern unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); extern void prep_transhuge_page(struct page *page); extern void free_transhuge_page(struct page *page); bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); } void deferred_split_huge_page(struct page *page); void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page); #define split_huge_pmd(__vma, __pmd, __address) \ do { \ pmd_t *____pmd = (__pmd); \ if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd) \ || pmd_devmap(*____pmd)) \ __split_huge_pmd(__vma, __pmd, __address, \ false, NULL); \ } while (0) void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page); void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address); #define split_huge_pud(__vma, __pud, __address) \ do { \ pud_t *____pud = (__pud); \ if (pud_trans_huge(*____pud) \ || pud_devmap(*____pud)) \ __split_huge_pud(__vma, __pud, __address); \ } while (0) extern int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice); extern void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next); extern spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma); extern spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma); static inline int is_swap_pmd(pmd_t pmd) { return !pmd_none(pmd) && !pmd_present(pmd); } /* mmap_sem must be held on entry */ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) return __pmd_trans_huge_lock(pmd, vma); else return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { VM_BUG_ON_VMA(!rwsem_is_locked(&vma->vm_mm->mmap_sem), vma); if (pud_trans_huge(*pud) || pud_devmap(*pud)) return __pud_trans_huge_lock(pud, vma); else return NULL; } /** * thp_order - Order of a transparent huge page. * @page: Head page of a transparent huge page. */ static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); if (PageHead(page)) return HPAGE_PMD_ORDER; return 0; } static inline int hpage_nr_pages(struct page *page) { if (unlikely(PageTransHuge(page))) return HPAGE_PMD_NR; return 1; } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap); struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap); extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd); extern struct page *huge_zero_page; extern unsigned long huge_zero_pfn; static inline bool is_huge_zero_page(struct page *page) { return READ_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd) && pmd_present(pmd); } static inline bool is_huge_zero_pud(pud_t pud) { return false; } struct page *mm_get_huge_zero_page(struct mm_struct *mm); void mm_put_huge_zero_page(struct mm_struct *mm); #define mk_huge_pmd(page, prot) pmd_mkhuge(mk_pmd(page, prot)) static inline bool thp_migration_supported(void) { return IS_ENABLED(CONFIG_ARCH_ENABLE_THP_MIGRATION); } static inline struct list_head *page_deferred_list(struct page *page) { /* * Global or memcg deferred list in the second tail pages is * occupied by compound_head. */ return &page[2].deferred_list; } #else /* CONFIG_TRANSPARENT_HUGEPAGE */ #define HPAGE_PMD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PMD_SIZE ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SHIFT ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_MASK ({ BUILD_BUG(); 0; }) #define HPAGE_PUD_SIZE ({ BUILD_BUG(); 0; }) static inline unsigned int thp_order(struct page *page) { VM_BUG_ON_PGFLAGS(PageTail(page), page); return 0; } #define hpage_nr_pages(x) 1 static inline bool __transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; } static inline bool transparent_hugepage_enabled(struct vm_area_struct *vma) { return false; } static inline bool transhuge_vma_suitable(struct vm_area_struct *vma, unsigned long haddr) { return false; } static inline void prep_transhuge_page(struct page *page) {} #define transparent_hugepage_flags 0UL #define thp_get_unmapped_area NULL static inline bool can_split_huge_page(struct page *page, int *pextra_pins) { BUILD_BUG(); return false; } static inline int split_huge_page_to_list(struct page *page, struct list_head *list) { return 0; } static inline int split_huge_page(struct page *page) { return 0; } static inline void deferred_split_huge_page(struct page *page) {} #define split_huge_pmd(__vma, __pmd, __address) \ do { } while (0) static inline void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct page *page) {} static inline void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct page *page) {} #define split_huge_pud(__vma, __pmd, __address) \ do { } while (0) static inline int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { BUG(); return 0; } static inline void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { } static inline int is_swap_pmd(pmd_t pmd) { return 0; } static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { return NULL; } static inline spinlock_t *pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { return NULL; } static inline vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd) { return 0; } static inline bool is_huge_zero_page(struct page *page) { return false; } static inline bool is_huge_zero_pmd(pmd_t pmd) { return false; } static inline bool is_huge_zero_pud(pud_t pud) { return false; } static inline void mm_put_huge_zero_page(struct mm_struct *mm) { return; } static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap) { return NULL; } static inline bool thp_migration_supported(void) { return false; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #endif /* _LINUX_HUGE_MM_H */ |
| 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 | /* * Rusty Russell (C)2000 -- This code is GPL. * Patrick McHardy (c) 2006-2012 */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/protocol.h> #include <net/netfilter/nf_queue.h> #include <net/dst.h> #include "nf_internals.h" /* * Hook for nfnetlink_queue to register its queue handler. * We do this so that most of the NFQUEUE code can be modular. * * Once the queue is registered it must reinject all packets it * receives, no matter what. */ /* return EBUSY when somebody else is registered, return EEXIST if the * same handler is registered, return 0 in case of success. */ void nf_register_queue_handler(struct net *net, const struct nf_queue_handler *qh) { /* should never happen, we only have one queueing backend in kernel */ WARN_ON(rcu_access_pointer(net->nf.queue_handler)); rcu_assign_pointer(net->nf.queue_handler, qh); } EXPORT_SYMBOL(nf_register_queue_handler); /* The caller must flush their queue before this */ void nf_unregister_queue_handler(struct net *net) { RCU_INIT_POINTER(net->nf.queue_handler, NULL); } EXPORT_SYMBOL(nf_unregister_queue_handler); static void nf_queue_entry_release_br_nf_refs(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (nf_bridge) { struct net_device *physdev; physdev = nf_bridge_get_physindev(skb); if (physdev) dev_put(physdev); physdev = nf_bridge_get_physoutdev(skb); if (physdev) dev_put(physdev); } #endif } static void nf_queue_sock_put(struct sock *sk) { #ifdef CONFIG_INET sock_gen_put(sk); #else sock_put(sk); #endif } void nf_queue_entry_release_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; /* Release those devices we held, or Alexey will kill me. */ if (state->in) dev_put(state->in); if (state->out) dev_put(state->out); if (state->sk) nf_queue_sock_put(state->sk); nf_queue_entry_release_br_nf_refs(entry->skb); } EXPORT_SYMBOL_GPL(nf_queue_entry_release_refs); static void nf_queue_entry_get_br_nf_refs(struct sk_buff *skb) { #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb); if (nf_bridge) { struct net_device *physdev; physdev = nf_bridge_get_physindev(skb); if (physdev) dev_hold(physdev); physdev = nf_bridge_get_physoutdev(skb); if (physdev) dev_hold(physdev); } #endif } /* Bump dev refs so they don't vanish while packet is out */ bool nf_queue_entry_get_refs(struct nf_queue_entry *entry) { struct nf_hook_state *state = &entry->state; if (state->sk && !refcount_inc_not_zero(&state->sk->sk_refcnt)) return false; if (state->in) dev_hold(state->in); if (state->out) dev_hold(state->out); nf_queue_entry_get_br_nf_refs(entry->skb); return true; } EXPORT_SYMBOL_GPL(nf_queue_entry_get_refs); void nf_queue_nf_hook_drop(struct net *net) { const struct nf_queue_handler *qh; rcu_read_lock(); qh = rcu_dereference(net->nf.queue_handler); if (qh) qh->nf_hook_drop(net); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_queue_nf_hook_drop); static void nf_ip_saveroute(const struct sk_buff *skb, struct nf_queue_entry *entry) { struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct iphdr *iph = ip_hdr(skb); rt_info->tos = iph->tos; rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; rt_info->mark = skb->mark; } } static void nf_ip6_saveroute(const struct sk_buff *skb, struct nf_queue_entry *entry) { struct ip6_rt_info *rt_info = nf_queue_entry_reroute(entry); if (entry->state.hook == NF_INET_LOCAL_OUT) { const struct ipv6hdr *iph = ipv6_hdr(skb); rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; rt_info->mark = skb->mark; } } static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, unsigned int index, unsigned int queuenum) { int status = -ENOENT; struct nf_queue_entry *entry = NULL; const struct nf_queue_handler *qh; struct net *net = state->net; unsigned int route_key_size; /* QUEUE == DROP if no one is waiting, to be safe. */ qh = rcu_dereference(net->nf.queue_handler); if (!qh) { status = -ESRCH; goto err; } switch (state->pf) { case AF_INET: route_key_size = sizeof(struct ip_rt_info); break; case AF_INET6: route_key_size = sizeof(struct ip6_rt_info); break; default: route_key_size = 0; break; } entry = kmalloc(sizeof(*entry) + route_key_size, GFP_ATOMIC); if (!entry) { status = -ENOMEM; goto err; } if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } *entry = (struct nf_queue_entry) { .skb = skb, .state = *state, .hook_index = index, .size = sizeof(*entry) + route_key_size, }; if (!nf_queue_entry_get_refs(entry)) { kfree(entry); return -ENOTCONN; } switch (entry->state.pf) { case AF_INET: nf_ip_saveroute(skb, entry); break; case AF_INET6: nf_ip6_saveroute(skb, entry); break; } status = qh->outfn(entry, queuenum); if (status < 0) { nf_queue_entry_release_refs(entry); goto err; } return 0; err: kfree(entry); return status; } /* Packets leaving via this function must come back through nf_reinject(). */ int nf_queue(struct sk_buff *skb, struct nf_hook_state *state, unsigned int index, unsigned int verdict) { int ret; ret = __nf_queue(skb, state, index, verdict >> NF_VERDICT_QBITS); if (ret < 0) { if (ret == -ESRCH && (verdict & NF_VERDICT_FLAG_QUEUE_BYPASS)) return 1; kfree_skb(skb); } return 0; } EXPORT_SYMBOL_GPL(nf_queue); static unsigned int nf_iterate(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *hooks, unsigned int *index) { const struct nf_hook_entry *hook; unsigned int verdict, i = *index; while (i < hooks->num_hook_entries) { hook = &hooks->hooks[i]; repeat: verdict = nf_hook_entry_hookfn(hook, skb, state); if (verdict != NF_ACCEPT) { *index = i; if (verdict != NF_REPEAT) return verdict; goto repeat; } i++; } *index = i; return NF_ACCEPT; } static struct nf_hook_entries *nf_hook_entries_head(const struct net *net, u8 pf, u8 hooknum) { switch (pf) { #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: return rcu_dereference(net->nf.hooks_bridge[hooknum]); #endif case NFPROTO_IPV4: return rcu_dereference(net->nf.hooks_ipv4[hooknum]); case NFPROTO_IPV6: return rcu_dereference(net->nf.hooks_ipv6[hooknum]); default: WARN_ON_ONCE(1); return NULL; } return NULL; } /* Caller must hold rcu read-side lock */ void nf_reinject(struct nf_queue_entry *entry, unsigned int verdict) { const struct nf_hook_entry *hook_entry; const struct nf_hook_entries *hooks; struct sk_buff *skb = entry->skb; const struct net *net; unsigned int i; int err; u8 pf; net = entry->state.net; pf = entry->state.pf; hooks = nf_hook_entries_head(net, pf, entry->state.hook); nf_queue_entry_release_refs(entry); i = entry->hook_index; if (WARN_ON_ONCE(!hooks || i >= hooks->num_hook_entries)) { kfree_skb(skb); kfree(entry); return; } hook_entry = &hooks->hooks[i]; /* Continue traversal iff userspace said ok... */ if (verdict == NF_REPEAT) verdict = nf_hook_entry_hookfn(hook_entry, skb, &entry->state); if (verdict == NF_ACCEPT) { if (nf_reroute(skb, entry) < 0) verdict = NF_DROP; } if (verdict == NF_ACCEPT) { next_hook: ++i; verdict = nf_iterate(skb, &entry->state, hooks, &i); } switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: case NF_STOP: local_bh_disable(); entry->state.okfn(entry->state.net, entry->state.sk, skb); local_bh_enable(); break; case NF_QUEUE: err = nf_queue(skb, &entry->state, i, verdict); if (err == 1) goto next_hook; break; case NF_STOLEN: break; default: kfree_skb(skb); } kfree(entry); } EXPORT_SYMBOL(nf_reinject); |
| 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | // 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/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> 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); } /** * 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 PID: %d Comm: %.20s %s%s %s %.*s\n", log_lvl, raw_smp_processor_id(), current->pid, current->comm, kexec_crash_loaded() ? "Kdump: loaded " : "", print_tainted(), init_utsname()->release, (int)strcspn(init_utsname()->version, " "), init_utsname()->version); 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); } /** * 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(void) { dump_stack_print_info(KERN_DEFAULT); show_stack(NULL, NULL); } /** * dump_stack - dump the current task information and its stack trace * * Architectures can override this implementation by implementing its own. */ #ifdef CONFIG_SMP static atomic_t dump_lock = ATOMIC_INIT(-1); asmlinkage __visible void dump_stack(void) { unsigned long flags; int was_locked; int old; int cpu; /* * Permit this cpu to perform nested stack dumps while serialising * against other CPUs */ retry: local_irq_save(flags); cpu = smp_processor_id(); old = atomic_cmpxchg(&dump_lock, -1, cpu); if (old == -1) { was_locked = 0; } else if (old == cpu) { was_locked = 1; } else { local_irq_restore(flags); /* * Wait for the lock to release before jumping to * atomic_cmpxchg() in order to mitigate the thundering herd * problem. */ do { cpu_relax(); } while (atomic_read(&dump_lock) != -1); goto retry; } __dump_stack(); if (!was_locked) atomic_set(&dump_lock, -1); local_irq_restore(flags); } #else asmlinkage __visible void dump_stack(void) { __dump_stack(); } #endif EXPORT_SYMBOL(dump_stack); |
| 18 18 18 19 1 2 2 11 5 3 18 18 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 | // SPDX-License-Identifier: GPL-2.0 /* * XFRM virtual interface * * Copyright (C) 2018 secunet Security Networks AG * * Author: * Steffen Klassert <steffen.klassert@secunet.com> */ #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_link.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <linux/etherdevice.h> static int xfrmi_dev_init(struct net_device *dev); static void xfrmi_dev_setup(struct net_device *dev); static struct rtnl_link_ops xfrmi_link_ops __read_mostly; static unsigned int xfrmi_net_id __read_mostly; struct xfrmi_net { /* lists for storing interfaces in use */ struct xfrm_if __rcu *xfrmi[1]; }; #define for_each_xfrmi_rcu(start, xi) \ for (xi = rcu_dereference(start); xi; xi = rcu_dereference(xi->next)) static struct xfrm_if *xfrmi_lookup(struct net *net, struct xfrm_state *x) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if *xi; for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { if (x->if_id == xi->p.if_id && (xi->dev->flags & IFF_UP)) return xi; } return NULL; } static struct xfrm_if *xfrmi_decode_session(struct sk_buff *skb, unsigned short family) { struct xfrmi_net *xfrmn; struct xfrm_if *xi; int ifindex = 0; if (!secpath_exists(skb) || !skb->dev) return NULL; switch (family) { case AF_INET6: ifindex = inet6_sdif(skb); break; case AF_INET: ifindex = inet_sdif(skb); break; } if (!ifindex) ifindex = skb->dev->ifindex; xfrmn = net_generic(xs_net(xfrm_input_state(skb)), xfrmi_net_id); for_each_xfrmi_rcu(xfrmn->xfrmi[0], xi) { if (ifindex == xi->dev->ifindex && (xi->dev->flags & IFF_UP)) return xi; } return NULL; } static void xfrmi_link(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { struct xfrm_if __rcu **xip = &xfrmn->xfrmi[0]; rcu_assign_pointer(xi->next , rtnl_dereference(*xip)); rcu_assign_pointer(*xip, xi); } static void xfrmi_unlink(struct xfrmi_net *xfrmn, struct xfrm_if *xi) { struct xfrm_if __rcu **xip; struct xfrm_if *iter; for (xip = &xfrmn->xfrmi[0]; (iter = rtnl_dereference(*xip)) != NULL; xip = &iter->next) { if (xi == iter) { rcu_assign_pointer(*xip, xi->next); break; } } } static void xfrmi_dev_free(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); gro_cells_destroy(&xi->gro_cells); free_percpu(dev->tstats); } static int xfrmi_create(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = dev_net(dev); struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; dev->rtnl_link_ops = &xfrmi_link_ops; err = register_netdevice(dev); if (err < 0) goto out; dev_hold(dev); xfrmi_link(xfrmn, xi); return 0; out: return err; } static struct xfrm_if *xfrmi_locate(struct net *net, struct xfrm_if_parms *p) { struct xfrm_if __rcu **xip; struct xfrm_if *xi; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); for (xip = &xfrmn->xfrmi[0]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) if (xi->p.if_id == p->if_id) return xi; return NULL; } static void xfrmi_dev_uninit(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct xfrmi_net *xfrmn = net_generic(xi->net, xfrmi_net_id); xfrmi_unlink(xfrmn, xi); dev_put(dev); } static void xfrmi_scrub_packet(struct sk_buff *skb, bool xnet) { skb->tstamp = 0; skb->pkt_type = PACKET_HOST; skb->skb_iif = 0; skb->ignore_df = 0; skb_dst_drop(skb); nf_reset_ct(skb); nf_reset_trace(skb); if (!xnet) return; ipvs_reset(skb); secpath_reset(skb); skb_orphan(skb); skb->mark = 0; } static int xfrmi_rcv_cb(struct sk_buff *skb, int err) { const struct xfrm_mode *inner_mode; struct pcpu_sw_netstats *tstats; struct net_device *dev; struct xfrm_state *x; struct xfrm_if *xi; bool xnet; if (err && !secpath_exists(skb)) return 0; x = xfrm_input_state(skb); xi = xfrmi_lookup(xs_net(x), x); if (!xi) return 1; dev = xi->dev; skb->dev = dev; if (err) { dev->stats.rx_errors++; dev->stats.rx_dropped++; return 0; } xnet = !net_eq(xi->net, dev_net(skb->dev)); if (xnet) { inner_mode = &x->inner_mode; if (x->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(x, XFRM_MODE_SKB_CB(skb)->protocol); if (inner_mode == NULL) { XFRM_INC_STATS(dev_net(skb->dev), LINUX_MIB_XFRMINSTATEMODEERROR); return -EINVAL; } } if (!xfrm_policy_check(NULL, XFRM_POLICY_IN, skb, inner_mode->family)) return -EPERM; } xfrmi_scrub_packet(skb, xnet); tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->rx_packets++; tstats->rx_bytes += skb->len; u64_stats_update_end(&tstats->syncp); return 0; } static int xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); unsigned int length = skb->len; struct net_device *tdev; struct xfrm_state *x; int err = -1; int mtu; dst_hold(dst); dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } x = dst->xfrm; if (!x) goto tx_err_link_failure; if (x->if_id != xi->p.if_id) goto tx_err_link_failure; tdev = dst->dev; if (tdev == dev) { stats->collisions++; net_warn_ratelimited("%s: Local routing loop detected!\n", dev->name); goto tx_err_dst_release; } mtu = dst_mtu(dst); if (skb->len > mtu) { skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; if (skb->len > 1280) icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); else goto xmit; } else { if (!(ip_hdr(skb)->frag_off & htons(IP_DF))) goto xmit; icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); } dst_release(dst); return -EMSGSIZE; } xmit: xfrmi_scrub_packet(skb, !net_eq(xi->net, dev_net(dev))); skb_dst_set(skb, dst); skb->dev = tdev; err = dst_output(xi->net, skb->sk, skb); if (net_xmit_eval(err) == 0) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); tstats->tx_bytes += length; tstats->tx_packets++; u64_stats_update_end(&tstats->syncp); } else { stats->tx_errors++; stats->tx_aborted_errors++; } return 0; tx_err_link_failure: stats->tx_carrier_errors++; dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; memset(&fl, 0, sizeof(fl)); switch (skb->protocol) { case htons(ETH_P_IPV6): memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); xfrm_decode_session(skb, &fl, AF_INET6); if (!dst) { fl.u.ip6.flowi6_oif = dev->ifindex; fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); if (dst->error) { dst_release(dst); stats->tx_carrier_errors++; goto tx_err; } skb_dst_set(skb, dst); } break; case htons(ETH_P_IP): memset(IPCB(skb), 0, sizeof(*IPCB(skb))); xfrm_decode_session(skb, &fl, AF_INET); if (!dst) { struct rtable *rt; fl.u.ip4.flowi4_oif = dev->ifindex; fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); if (IS_ERR(rt)) { stats->tx_carrier_errors++; goto tx_err; } skb_dst_set(skb, &rt->dst); } break; default: goto tx_err; } fl.flowi_oif = xi->p.link; ret = xfrmi_xmit2(skb, dev, &fl); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: stats->tx_errors++; stats->tx_dropped++; kfree_skb(skb); return NETDEV_TX_OK; } static int xfrmi4_err(struct sk_buff *skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)skb->data; struct net *net = dev_net(skb->dev); int protocol = iph->protocol; struct ip_comp_hdr *ipch; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah ; struct xfrm_state *x; struct xfrm_if *xi; __be32 spi; switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data+(iph->ihl<<2)); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } switch (icmp_hdr(skb)->type) { case ICMP_DEST_UNREACH: if (icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return 0; case ICMP_REDIRECT: break; default: return 0; } x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET); if (!x) return 0; xi = xfrmi_lookup(net, x); if (!xi) { xfrm_state_put(x); return -1; } if (icmp_hdr(skb)->type == ICMP_DEST_UNREACH) ipv4_update_pmtu(skb, net, info, 0, protocol); else ipv4_redirect(skb, net, 0, protocol); xfrm_state_put(x); return 0; } static int xfrmi6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { const struct ipv6hdr *iph = (const struct ipv6hdr *)skb->data; struct net *net = dev_net(skb->dev); int protocol = iph->nexthdr; struct ip_comp_hdr *ipch; struct ip_esp_hdr *esph; struct ip_auth_hdr *ah; struct xfrm_state *x; struct xfrm_if *xi; __be32 spi; switch (protocol) { case IPPROTO_ESP: esph = (struct ip_esp_hdr *)(skb->data + offset); spi = esph->spi; break; case IPPROTO_AH: ah = (struct ip_auth_hdr *)(skb->data + offset); spi = ah->spi; break; case IPPROTO_COMP: ipch = (struct ip_comp_hdr *)(skb->data + offset); spi = htonl(ntohs(ipch->cpi)); break; default: return 0; } if (type != ICMPV6_PKT_TOOBIG && type != NDISC_REDIRECT) return 0; x = xfrm_state_lookup(net, skb->mark, (const xfrm_address_t *)&iph->daddr, spi, protocol, AF_INET6); if (!x) return 0; xi = xfrmi_lookup(net, x); if (!xi) { xfrm_state_put(x); return -1; } if (type == NDISC_REDIRECT) ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); else ip6_update_pmtu(skb, net, info, 0, 0, sock_net_uid(net, NULL)); xfrm_state_put(x); return 0; } static int xfrmi_change(struct xfrm_if *xi, const struct xfrm_if_parms *p) { if (xi->p.link != p->link) return -EINVAL; xi->p.if_id = p->if_id; return 0; } static int xfrmi_update(struct xfrm_if *xi, struct xfrm_if_parms *p) { struct net *net = xi->net; struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); int err; xfrmi_unlink(xfrmn, xi); synchronize_net(); err = xfrmi_change(xi, p); xfrmi_link(xfrmn, xi); netdev_state_change(xi->dev); return err; } static void xfrmi_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *s) { int cpu; for_each_possible_cpu(cpu) { struct pcpu_sw_netstats *stats; struct pcpu_sw_netstats tmp; int start; stats = per_cpu_ptr(dev->tstats, cpu); do { start = u64_stats_fetch_begin_irq(&stats->syncp); tmp.rx_packets = stats->rx_packets; tmp.rx_bytes = stats->rx_bytes; tmp.tx_packets = stats->tx_packets; tmp.tx_bytes = stats->tx_bytes; } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); s->rx_packets += tmp.rx_packets; s->rx_bytes += tmp.rx_bytes; s->tx_packets += tmp.tx_packets; s->tx_bytes += tmp.tx_bytes; } s->rx_dropped = dev->stats.rx_dropped; s->tx_dropped = dev->stats.tx_dropped; } static int xfrmi_get_iflink(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); return xi->p.link; } static const struct net_device_ops xfrmi_netdev_ops = { .ndo_init = xfrmi_dev_init, .ndo_uninit = xfrmi_dev_uninit, .ndo_start_xmit = xfrmi_xmit, .ndo_get_stats64 = xfrmi_get_stats64, .ndo_get_iflink = xfrmi_get_iflink, }; static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; dev->type = ARPHRD_NONE; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP_MAX_MTU; dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; netif_keep_dst(dev); eth_broadcast_addr(dev->broadcast); } static int xfrmi_dev_init(struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device *phydev = __dev_get_by_index(xi->net, xi->p.link); int err; dev->tstats = netdev_alloc_pcpu_stats(struct pcpu_sw_netstats); if (!dev->tstats) return -ENOMEM; err = gro_cells_init(&xi->gro_cells, dev); if (err) { free_percpu(dev->tstats); return err; } dev->features |= NETIF_F_LLTX; if (phydev) { dev->needed_headroom = phydev->needed_headroom; dev->needed_tailroom = phydev->needed_tailroom; if (is_zero_ether_addr(dev->dev_addr)) eth_hw_addr_inherit(dev, phydev); if (is_zero_ether_addr(dev->broadcast)) memcpy(dev->broadcast, phydev->broadcast, dev->addr_len); } else { eth_hw_addr_random(dev); eth_broadcast_addr(dev->broadcast); } return 0; } static int xfrmi_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { return 0; } static void xfrmi_netlink_parms(struct nlattr *data[], struct xfrm_if_parms *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_XFRM_LINK]) parms->link = nla_get_u32(data[IFLA_XFRM_LINK]); if (data[IFLA_XFRM_IF_ID]) parms->if_id = nla_get_u32(data[IFLA_XFRM_IF_ID]); } static int xfrmi_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net *net = dev_net(dev); struct xfrm_if_parms p = {}; struct xfrm_if *xi; int err; xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } xi = xfrmi_locate(net, &p); if (xi) return -EEXIST; xi = netdev_priv(dev); xi->p = p; xi->net = net; xi->dev = dev; err = xfrmi_create(dev); return err; } static void xfrmi_dellink(struct net_device *dev, struct list_head *head) { unregister_netdevice_queue(dev, head); } static int xfrmi_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct xfrm_if *xi = netdev_priv(dev); struct net *net = xi->net; struct xfrm_if_parms p = {}; xfrmi_netlink_parms(data, &p); if (!p.if_id) { NL_SET_ERR_MSG(extack, "if_id must be non zero"); return -EINVAL; } xi = xfrmi_locate(net, &p); if (!xi) { xi = netdev_priv(dev); } else { if (xi->dev != dev) return -EEXIST; } return xfrmi_update(xi, &p); } static size_t xfrmi_get_size(const struct net_device *dev) { return /* IFLA_XFRM_LINK */ nla_total_size(4) + /* IFLA_XFRM_IF_ID */ nla_total_size(4) + 0; } static int xfrmi_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct xfrm_if_parms *parm = &xi->p; if (nla_put_u32(skb, IFLA_XFRM_LINK, parm->link) || nla_put_u32(skb, IFLA_XFRM_IF_ID, parm->if_id)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static struct net *xfrmi_get_link_net(const struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); return xi->net; } static const struct nla_policy xfrmi_policy[IFLA_XFRM_MAX + 1] = { [IFLA_XFRM_LINK] = { .type = NLA_U32 }, [IFLA_XFRM_IF_ID] = { .type = NLA_U32 }, }; static struct rtnl_link_ops xfrmi_link_ops __read_mostly = { .kind = "xfrm", .maxtype = IFLA_XFRM_MAX, .policy = xfrmi_policy, .priv_size = sizeof(struct xfrm_if), .setup = xfrmi_dev_setup, .validate = xfrmi_validate, .newlink = xfrmi_newlink, .dellink = xfrmi_dellink, .changelink = xfrmi_changelink, .get_size = xfrmi_get_size, .fill_info = xfrmi_fill_info, .get_link_net = xfrmi_get_link_net, }; static void __net_exit xfrmi_destroy_interfaces(struct xfrmi_net *xfrmn) { struct xfrm_if *xi; LIST_HEAD(list); xi = rtnl_dereference(xfrmn->xfrmi[0]); if (!xi) return; unregister_netdevice_queue(xi->dev, &list); unregister_netdevice_many(&list); } static void __net_exit xfrmi_exit_net(struct net *net) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); rtnl_lock(); xfrmi_destroy_interfaces(xfrmn); rtnl_unlock(); } static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) { struct net *net; LIST_HEAD(list); rtnl_lock(); list_for_each_entry(net, net_exit_list, exit_list) { struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); struct xfrm_if __rcu **xip; struct xfrm_if *xi; for (xip = &xfrmn->xfrmi[0]; (xi = rtnl_dereference(*xip)) != NULL; xip = &xi->next) unregister_netdevice_queue(xi->dev, &list); } unregister_netdevice_many(&list); rtnl_unlock(); } static struct pernet_operations xfrmi_net_ops = { .exit_batch = xfrmi_exit_batch_net, .exit = xfrmi_exit_net, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; static struct xfrm6_protocol xfrmi_esp6_protocol __read_mostly = { .handler = xfrm6_rcv, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm6_protocol xfrmi_ah6_protocol __read_mostly = { .handler = xfrm6_rcv, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm6_protocol xfrmi_ipcomp6_protocol __read_mostly = { .handler = xfrm6_rcv, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi6_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_esp4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_ah4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static struct xfrm4_protocol xfrmi_ipcomp4_protocol __read_mostly = { .handler = xfrm4_rcv, .input_handler = xfrm_input, .cb_handler = xfrmi_rcv_cb, .err_handler = xfrmi4_err, .priority = 10, }; static int __init xfrmi4_init(void) { int err; err = xfrm4_protocol_register(&xfrmi_esp4_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm4_protocol_register(&xfrmi_ah4_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm4_protocol_register(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; return 0; xfrm_proto_comp_failed: xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: return err; } static void xfrmi4_fini(void) { xfrm4_protocol_deregister(&xfrmi_ipcomp4_protocol, IPPROTO_COMP); xfrm4_protocol_deregister(&xfrmi_ah4_protocol, IPPROTO_AH); xfrm4_protocol_deregister(&xfrmi_esp4_protocol, IPPROTO_ESP); } static int __init xfrmi6_init(void) { int err; err = xfrm6_protocol_register(&xfrmi_esp6_protocol, IPPROTO_ESP); if (err < 0) goto xfrm_proto_esp_failed; err = xfrm6_protocol_register(&xfrmi_ah6_protocol, IPPROTO_AH); if (err < 0) goto xfrm_proto_ah_failed; err = xfrm6_protocol_register(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); if (err < 0) goto xfrm_proto_comp_failed; return 0; xfrm_proto_comp_failed: xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm_proto_ah_failed: xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); xfrm_proto_esp_failed: return err; } static void xfrmi6_fini(void) { xfrm6_protocol_deregister(&xfrmi_ipcomp6_protocol, IPPROTO_COMP); xfrm6_protocol_deregister(&xfrmi_ah6_protocol, IPPROTO_AH); xfrm6_protocol_deregister(&xfrmi_esp6_protocol, IPPROTO_ESP); } static const struct xfrm_if_cb xfrm_if_cb = { .decode_session = xfrmi_decode_session, }; static int __init xfrmi_init(void) { const char *msg; int err; pr_info("IPsec XFRM device driver\n"); msg = "tunnel device"; err = register_pernet_device(&xfrmi_net_ops); if (err < 0) goto pernet_dev_failed; msg = "xfrm4 protocols"; err = xfrmi4_init(); if (err < 0) goto xfrmi4_failed; msg = "xfrm6 protocols"; err = xfrmi6_init(); if (err < 0) goto xfrmi6_failed; msg = "netlink interface"; err = rtnl_link_register(&xfrmi_link_ops); if (err < 0) goto rtnl_link_failed; xfrm_if_register_cb(&xfrm_if_cb); return err; rtnl_link_failed: xfrmi6_fini(); xfrmi6_failed: xfrmi4_fini(); xfrmi4_failed: unregister_pernet_device(&xfrmi_net_ops); pernet_dev_failed: pr_err("xfrmi init: failed to register %s\n", msg); return err; } static void __exit xfrmi_fini(void) { xfrm_if_unregister_cb(); rtnl_link_unregister(&xfrmi_link_ops); xfrmi4_fini(); xfrmi6_fini(); unregister_pernet_device(&xfrmi_net_ops); } module_init(xfrmi_init); module_exit(xfrmi_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("xfrm"); MODULE_ALIAS_NETDEV("xfrm0"); MODULE_AUTHOR("Steffen Klassert"); MODULE_DESCRIPTION("XFRM virtual interface"); |
| 821 823 719 164 446 449 439 11 450 449 438 11 11 11 11 323 321 12 12 155 12 65 2026 2023 448 359 420 31 17 447 451 448 451 450 448 70 381 447 448 449 448 120 116 3 13 688 690 689 17 688 687 731 729 731 251 251 116 116 120 13 13 116 116 116 52 52 31 449 450 449 615 187 450 451 245 69 246 69 177 244 180 69 178 68 246 69 243 243 245 245 200 195 47 176 74 3 37 10 74 28 63 62 21 46 46 46 73 75 75 74 73 69 112 112 26 26 168 534 536 529 535 217 204 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 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 | // SPDX-License-Identifier: GPL-2.0-only /* * (C) 1997 Linus Torvalds * (C) 1999 Andrea Arcangeli <andrea@suse.de> (dynamic inode allocation) */ #include <linux/export.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/backing-dev.h> #include <linux/hash.h> #include <linux/swap.h> #include <linux/security.h> #include <linux/cdev.h> #include <linux/memblock.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/mount.h> #include <linux/posix_acl.h> #include <linux/prefetch.h> #include <linux/buffer_head.h> /* for inode_has_buffers */ #include <linux/ratelimit.h> #include <linux/list_lru.h> #include <linux/iversion.h> #include <trace/events/writeback.h> #include "internal.h" /* * Inode locking rules: * * inode->i_lock protects: * inode->i_state, inode->i_hash, __iget() * Inode LRU list locks protect: * inode->i_sb->s_inode_lru, inode->i_lru * inode->i_sb->s_inode_list_lock protects: * inode->i_sb->s_inodes, inode->i_sb_list * bdi->wb.list_lock protects: * bdi->wb.b_{dirty,io,more_io,dirty_time}, inode->i_io_list * inode_hash_lock protects: * inode_hashtable, inode->i_hash * * Lock ordering: * * inode->i_sb->s_inode_list_lock * inode->i_lock * Inode LRU list locks * * bdi->wb.list_lock * inode->i_lock * * inode_hash_lock * inode->i_sb->s_inode_list_lock * inode->i_lock * * iunique_lock * inode_hash_lock */ static unsigned int i_hash_mask __read_mostly; static unsigned int i_hash_shift __read_mostly; static struct hlist_head *inode_hashtable __read_mostly; static __cacheline_aligned_in_smp DEFINE_SPINLOCK(inode_hash_lock); /* * Empty aops. Can be used for the cases where the user does not * define any of the address_space operations. */ const struct address_space_operations empty_aops = { }; EXPORT_SYMBOL(empty_aops); /* * Statistics gathering.. */ struct inodes_stat_t inodes_stat; static DEFINE_PER_CPU(unsigned long, nr_inodes); static DEFINE_PER_CPU(unsigned long, nr_unused); static struct kmem_cache *inode_cachep __read_mostly; static long get_nr_inodes(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_inodes, i); return sum < 0 ? 0 : sum; } static inline long get_nr_inodes_unused(void) { int i; long sum = 0; for_each_possible_cpu(i) sum += per_cpu(nr_unused, i); return sum < 0 ? 0 : sum; } long get_nr_dirty_inodes(void) { /* not actually dirty inodes, but a wild approximation */ long nr_dirty = get_nr_inodes() - get_nr_inodes_unused(); return nr_dirty > 0 ? nr_dirty : 0; } /* * Handle nr_inode sysctl */ #ifdef CONFIG_SYSCTL int proc_nr_inodes(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { inodes_stat.nr_inodes = get_nr_inodes(); inodes_stat.nr_unused = get_nr_inodes_unused(); return proc_doulongvec_minmax(table, write, buffer, lenp, ppos); } #endif static int no_open(struct inode *inode, struct file *file) { return -ENXIO; } /** * inode_init_always - perform inode structure initialisation * @sb: superblock inode belongs to * @inode: inode to initialise * * These are initializations that need to be done on every inode * allocation as the fields are not initialised by slab allocation. */ int inode_init_always(struct super_block *sb, struct inode *inode) { static const struct inode_operations empty_iops; static const struct file_operations no_open_fops = {.open = no_open}; struct address_space *const mapping = &inode->i_data; inode->i_sb = sb; inode->i_blkbits = sb->s_blocksize_bits; inode->i_flags = 0; atomic64_set(&inode->i_sequence, 0); atomic_set(&inode->i_count, 1); inode->i_op = &empty_iops; inode->i_fop = &no_open_fops; inode->__i_nlink = 1; inode->i_opflags = 0; if (sb->s_xattr) inode->i_opflags |= IOP_XATTR; i_uid_write(inode, 0); i_gid_write(inode, 0); atomic_set(&inode->i_writecount, 0); inode->i_size = 0; inode->i_write_hint = WRITE_LIFE_NOT_SET; inode->i_blocks = 0; inode->i_bytes = 0; inode->i_generation = 0; inode->i_pipe = NULL; inode->i_bdev = NULL; inode->i_cdev = NULL; inode->i_link = NULL; inode->i_dir_seq = 0; inode->i_rdev = 0; inode->dirtied_when = 0; #ifdef CONFIG_CGROUP_WRITEBACK inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; #endif spin_lock_init(&inode->i_lock); lockdep_set_class(&inode->i_lock, &sb->s_type->i_lock_key); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &sb->s_type->i_mutex_key); atomic_set(&inode->i_dio_count, 0); mapping->a_ops = &empty_aops; mapping->host = inode; mapping->flags = 0; mapping->wb_err = 0; atomic_set(&mapping->i_mmap_writable, 0); #ifdef CONFIG_READ_ONLY_THP_FOR_FS atomic_set(&mapping->nr_thps, 0); #endif mapping_set_gfp_mask(mapping, GFP_HIGHUSER_MOVABLE); mapping->private_data = NULL; mapping->writeback_index = 0; inode->i_private = NULL; inode->i_mapping = mapping; INIT_HLIST_HEAD(&inode->i_dentry); /* buggered by rcu freeing */ #ifdef CONFIG_FS_POSIX_ACL inode->i_acl = inode->i_default_acl = ACL_NOT_CACHED; #endif #ifdef CONFIG_FSNOTIFY inode->i_fsnotify_mask = 0; #endif inode->i_flctx = NULL; if (unlikely(security_inode_alloc(inode))) return -ENOMEM; this_cpu_inc(nr_inodes); return 0; } EXPORT_SYMBOL(inode_init_always); void free_inode_nonrcu(struct inode *inode) { kmem_cache_free(inode_cachep, inode); } EXPORT_SYMBOL(free_inode_nonrcu); static void i_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); if (inode->free_inode) inode->free_inode(inode); else free_inode_nonrcu(inode); } static struct inode *alloc_inode(struct super_block *sb) { const struct super_operations *ops = sb->s_op; struct inode *inode; if (ops->alloc_inode) inode = ops->alloc_inode(sb); else inode = kmem_cache_alloc(inode_cachep, GFP_KERNEL); if (!inode) return NULL; if (unlikely(inode_init_always(sb, inode))) { if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return NULL; } inode->free_inode = ops->free_inode; i_callback(&inode->i_rcu); return NULL; } return inode; } void __destroy_inode(struct inode *inode) { BUG_ON(inode_has_buffers(inode)); inode_detach_wb(inode); security_inode_free(inode); fsnotify_inode_delete(inode); locks_free_lock_context(inode); if (!inode->i_nlink) { WARN_ON(atomic_long_read(&inode->i_sb->s_remove_count) == 0); atomic_long_dec(&inode->i_sb->s_remove_count); } #ifdef CONFIG_FS_POSIX_ACL if (inode->i_acl && !is_uncached_acl(inode->i_acl)) posix_acl_release(inode->i_acl); if (inode->i_default_acl && !is_uncached_acl(inode->i_default_acl)) posix_acl_release(inode->i_default_acl); #endif this_cpu_dec(nr_inodes); } EXPORT_SYMBOL(__destroy_inode); static void destroy_inode(struct inode *inode) { const struct super_operations *ops = inode->i_sb->s_op; BUG_ON(!list_empty(&inode->i_lru)); __destroy_inode(inode); if (ops->destroy_inode) { ops->destroy_inode(inode); if (!ops->free_inode) return; } inode->free_inode = ops->free_inode; call_rcu(&inode->i_rcu, i_callback); } /** * drop_nlink - directly drop an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. In cases * where we are attempting to track writes to the * filesystem, a decrement to zero means an imminent * write when the file is truncated and actually unlinked * on the filesystem. */ void drop_nlink(struct inode *inode) { WARN_ON(inode->i_nlink == 0); inode->__i_nlink--; if (!inode->i_nlink) atomic_long_inc(&inode->i_sb->s_remove_count); } EXPORT_SYMBOL(drop_nlink); /** * clear_nlink - directly zero an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. See * drop_nlink() for why we care about i_nlink hitting zero. */ void clear_nlink(struct inode *inode) { if (inode->i_nlink) { inode->__i_nlink = 0; atomic_long_inc(&inode->i_sb->s_remove_count); } } EXPORT_SYMBOL(clear_nlink); /** * set_nlink - directly set an inode's link count * @inode: inode * @nlink: new nlink (should be non-zero) * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. */ void set_nlink(struct inode *inode, unsigned int nlink) { if (!nlink) { clear_nlink(inode); } else { /* Yes, some filesystems do change nlink from zero to one */ if (inode->i_nlink == 0) atomic_long_dec(&inode->i_sb->s_remove_count); inode->__i_nlink = nlink; } } EXPORT_SYMBOL(set_nlink); /** * inc_nlink - directly increment an inode's link count * @inode: inode * * This is a low-level filesystem helper to replace any * direct filesystem manipulation of i_nlink. Currently, * it is only here for parity with dec_nlink(). */ void inc_nlink(struct inode *inode) { if (unlikely(inode->i_nlink == 0)) { WARN_ON(!(inode->i_state & I_LINKABLE)); atomic_long_dec(&inode->i_sb->s_remove_count); } inode->__i_nlink++; } EXPORT_SYMBOL(inc_nlink); static void __address_space_init_once(struct address_space *mapping) { xa_init_flags(&mapping->i_pages, XA_FLAGS_LOCK_IRQ | XA_FLAGS_ACCOUNT); init_rwsem(&mapping->i_mmap_rwsem); INIT_LIST_HEAD(&mapping->private_list); spin_lock_init(&mapping->private_lock); mapping->i_mmap = RB_ROOT_CACHED; } void address_space_init_once(struct address_space *mapping) { memset(mapping, 0, sizeof(*mapping)); __address_space_init_once(mapping); } EXPORT_SYMBOL(address_space_init_once); /* * These are initializations that only need to be done * once, because the fields are idempotent across use * of the inode, so let the slab aware of that. */ void inode_init_once(struct inode *inode) { memset(inode, 0, sizeof(*inode)); INIT_HLIST_NODE(&inode->i_hash); INIT_LIST_HEAD(&inode->i_devices); INIT_LIST_HEAD(&inode->i_io_list); INIT_LIST_HEAD(&inode->i_wb_list); INIT_LIST_HEAD(&inode->i_lru); __address_space_init_once(&inode->i_data); i_size_ordered_init(inode); } EXPORT_SYMBOL(inode_init_once); static void init_once(void *foo) { struct inode *inode = (struct inode *) foo; inode_init_once(inode); } /* * inode->i_lock must be held */ void __iget(struct inode *inode) { atomic_inc(&inode->i_count); } /* * get additional reference to inode; caller must already hold one. */ void ihold(struct inode *inode) { WARN_ON(atomic_inc_return(&inode->i_count) < 2); } EXPORT_SYMBOL(ihold); static void inode_lru_list_add(struct inode *inode) { if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_inc(nr_unused); else inode->i_state |= I_REFERENCED; } /* * Add inode to LRU if needed (inode is unused and clean). * * Needs inode->i_lock held. */ void inode_add_lru(struct inode *inode) { if (!(inode->i_state & (I_DIRTY_ALL | I_SYNC | I_FREEING | I_WILL_FREE)) && !atomic_read(&inode->i_count) && inode->i_sb->s_flags & SB_ACTIVE) inode_lru_list_add(inode); } static void inode_lru_list_del(struct inode *inode) { if (list_lru_del(&inode->i_sb->s_inode_lru, &inode->i_lru)) this_cpu_dec(nr_unused); } static void inode_pin_lru_isolating(struct inode *inode) { lockdep_assert_held(&inode->i_lock); WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE)); inode->i_state |= I_LRU_ISOLATING; } static void inode_unpin_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_LRU_ISOLATING)); inode->i_state &= ~I_LRU_ISOLATING; smp_mb(); wake_up_bit(&inode->i_state, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); } static void inode_wait_for_lru_isolating(struct inode *inode) { spin_lock(&inode->i_lock); if (inode->i_state & I_LRU_ISOLATING) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING); spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_LRU_ISOLATING); } spin_unlock(&inode->i_lock); } /** * inode_sb_list_add - add inode to the superblock list of inodes * @inode: inode to add */ void inode_sb_list_add(struct inode *inode) { spin_lock(&inode->i_sb->s_inode_list_lock); list_add(&inode->i_sb_list, &inode->i_sb->s_inodes); spin_unlock(&inode->i_sb->s_inode_list_lock); } EXPORT_SYMBOL_GPL(inode_sb_list_add); static inline void inode_sb_list_del(struct inode *inode) { if (!list_empty(&inode->i_sb_list)) { spin_lock(&inode->i_sb->s_inode_list_lock); list_del_init(&inode->i_sb_list); spin_unlock(&inode->i_sb->s_inode_list_lock); } } static unsigned long hash(struct super_block *sb, unsigned long hashval) { unsigned long tmp; tmp = (hashval * (unsigned long)sb) ^ (GOLDEN_RATIO_PRIME + hashval) / L1_CACHE_BYTES; tmp = tmp ^ ((tmp ^ GOLDEN_RATIO_PRIME) >> i_hash_shift); return tmp & i_hash_mask; } /** * __insert_inode_hash - hash an inode * @inode: unhashed inode * @hashval: unsigned long value used to locate this object in the * inode_hashtable. * * Add an inode to the inode hash for this superblock. */ void __insert_inode_hash(struct inode *inode, unsigned long hashval) { struct hlist_head *b = inode_hashtable + hash(inode->i_sb, hashval); spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_add_head(&inode->i_hash, b); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__insert_inode_hash); /** * __remove_inode_hash - remove an inode from the hash * @inode: inode to unhash * * Remove an inode from the superblock. */ void __remove_inode_hash(struct inode *inode) { spin_lock(&inode_hash_lock); spin_lock(&inode->i_lock); hlist_del_init(&inode->i_hash); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); } EXPORT_SYMBOL(__remove_inode_hash); void clear_inode(struct inode *inode) { /* * We have to cycle the i_pages lock here because reclaim can be in the * process of removing the last page (in __delete_from_page_cache()) * and we must not free the mapping under it. */ xa_lock_irq(&inode->i_data.i_pages); BUG_ON(inode->i_data.nrpages); BUG_ON(inode->i_data.nrexceptional); xa_unlock_irq(&inode->i_data.i_pages); BUG_ON(!list_empty(&inode->i_data.private_list)); BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(inode->i_state & I_CLEAR); BUG_ON(!list_empty(&inode->i_wb_list)); /* don't need i_lock here, no concurrent mods to i_state */ inode->i_state = I_FREEING | I_CLEAR; } EXPORT_SYMBOL(clear_inode); /* * Free the inode passed in, removing it from the lists it is still connected * to. We remove any pages still attached to the inode and wait for any IO that * is still in progress before finally destroying the inode. * * An inode must already be marked I_FREEING so that we avoid the inode being * moved back onto lists if we race with other code that manipulates the lists * (e.g. writeback_single_inode). The caller is responsible for setting this. * * An inode must already be removed from the LRU list before being evicted from * the cache. This should occur atomically with setting the I_FREEING state * flag, so no inodes here should ever be on the LRU when being evicted. */ static void evict(struct inode *inode) { const struct super_operations *op = inode->i_sb->s_op; BUG_ON(!(inode->i_state & I_FREEING)); BUG_ON(!list_empty(&inode->i_lru)); if (!list_empty(&inode->i_io_list)) inode_io_list_del(inode); inode_sb_list_del(inode); inode_wait_for_lru_isolating(inode); /* * Wait for flusher thread to be done with the inode so that filesystem * does not start destroying it while writeback is still running. Since * the inode has I_FREEING set, flusher thread won't start new work on * the inode. We just have to wait for running writeback to finish. */ inode_wait_for_writeback(inode); if (op->evict_inode) { op->evict_inode(inode); } else { truncate_inode_pages_final(&inode->i_data); clear_inode(inode); } if (S_ISBLK(inode->i_mode) && inode->i_bdev) bd_forget(inode); if (S_ISCHR(inode->i_mode) && inode->i_cdev) cd_forget(inode); remove_inode_hash(inode); spin_lock(&inode->i_lock); wake_up_bit(&inode->i_state, __I_NEW); BUG_ON(inode->i_state != (I_FREEING | I_CLEAR)); spin_unlock(&inode->i_lock); destroy_inode(inode); } /* * dispose_list - dispose of the contents of a local list * @head: the head of the list to free * * Dispose-list gets a local list with local inodes in it, so it doesn't * need to worry about list corruption and SMP locks. */ static void dispose_list(struct list_head *head) { while (!list_empty(head)) { struct inode *inode; inode = list_first_entry(head, struct inode, i_lru); list_del_init(&inode->i_lru); evict(inode); cond_resched(); } } /** * evict_inodes - evict all evictable inodes for a superblock * @sb: superblock to operate on * * Make sure that no inodes with zero refcount are retained. This is * called by superblock shutdown after having SB_ACTIVE flag removed, * so any inode reaching zero refcount during or after that call will * be immediately evicted. */ void evict_inodes(struct super_block *sb) { struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { if (atomic_read(&inode->i_count)) continue; spin_lock(&inode->i_lock); if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); /* * We can have a ton of inodes to evict at unmount time given * enough memory, check to see if we need to go to sleep for a * bit so we don't livelock. */ if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); } EXPORT_SYMBOL_GPL(evict_inodes); /** * invalidate_inodes - attempt to free all inodes on a superblock * @sb: superblock to operate on * @kill_dirty: flag to guide handling of dirty inodes * * Attempts to free all inodes for a given superblock. If there were any * busy inodes return a non-zero value, else zero. * If @kill_dirty is set, discard dirty inodes too, otherwise treat * them as busy. */ int invalidate_inodes(struct super_block *sb, bool kill_dirty) { int busy = 0; struct inode *inode, *next; LIST_HEAD(dispose); again: spin_lock(&sb->s_inode_list_lock); list_for_each_entry_safe(inode, next, &sb->s_inodes, i_sb_list) { spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { spin_unlock(&inode->i_lock); continue; } if (inode->i_state & I_DIRTY_ALL && !kill_dirty) { spin_unlock(&inode->i_lock); busy = 1; continue; } if (atomic_read(&inode->i_count)) { spin_unlock(&inode->i_lock); busy = 1; continue; } inode->i_state |= I_FREEING; inode_lru_list_del(inode); spin_unlock(&inode->i_lock); list_add(&inode->i_lru, &dispose); if (need_resched()) { spin_unlock(&sb->s_inode_list_lock); cond_resched(); dispose_list(&dispose); goto again; } } spin_unlock(&sb->s_inode_list_lock); dispose_list(&dispose); return busy; } /* * Isolate the inode from the LRU in preparation for freeing it. * * Any inodes which are pinned purely because of attached pagecache have their * pagecache removed. If the inode has metadata buffers attached to * mapping->private_list then try to remove them. * * If the inode has the I_REFERENCED flag set, then it means that it has been * used recently - the flag is set in iput_final(). When we encounter such an * inode, clear the flag and move it to the back of the LRU so it gets another * pass through the LRU before it gets reclaimed. This is necessary because of * the fact we are doing lazy LRU updates to minimise lock contention so the * LRU does not have strict ordering. Hence we don't want to reclaim inodes * with this flag set because they are the inodes that are out of order. */ static enum lru_status inode_lru_isolate(struct list_head *item, struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { struct list_head *freeable = arg; struct inode *inode = container_of(item, struct inode, i_lru); /* * we are inverting the lru lock/inode->i_lock here, so use a trylock. * If we fail to get the lock, just skip it. */ if (!spin_trylock(&inode->i_lock)) return LRU_SKIP; /* * Referenced or dirty inodes are still in use. Give them another pass * through the LRU as we canot reclaim them now. */ if (atomic_read(&inode->i_count) || (inode->i_state & ~I_REFERENCED)) { list_lru_isolate(lru, &inode->i_lru); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* recently referenced inodes get one more pass */ if (inode->i_state & I_REFERENCED) { inode->i_state &= ~I_REFERENCED; spin_unlock(&inode->i_lock); return LRU_ROTATE; } if (inode_has_buffers(inode) || inode->i_data.nrpages) { inode_pin_lru_isolating(inode); spin_unlock(&inode->i_lock); spin_unlock(lru_lock); if (remove_inode_buffers(inode)) { unsigned long reap; reap = invalidate_mapping_pages(&inode->i_data, 0, -1); if (current_is_kswapd()) __count_vm_events(KSWAPD_INODESTEAL, reap); else __count_vm_events(PGINODESTEAL, reap); if (current->reclaim_state) current->reclaim_state->reclaimed_slab += reap; } inode_unpin_lru_isolating(inode); spin_lock(lru_lock); return LRU_RETRY; } WARN_ON(inode->i_state & I_NEW); inode->i_state |= I_FREEING; list_lru_isolate_move(lru, &inode->i_lru, freeable); spin_unlock(&inode->i_lock); this_cpu_dec(nr_unused); return LRU_REMOVED; } /* * Walk the superblock inode LRU for freeable inodes and attempt to free them. * This is called from the superblock shrinker function with a number of inodes * to trim from the LRU. Inodes to be freed are moved to a temporary list and * then are freed outside inode_lock by dispose_list(). */ long prune_icache_sb(struct super_block *sb, struct shrink_control *sc) { LIST_HEAD(freeable); long freed; freed = list_lru_shrink_walk(&sb->s_inode_lru, sc, inode_lru_isolate, &freeable); dispose_list(&freeable); return freed; } static void __wait_on_freeing_inode(struct inode *inode); /* * Called with the inode lock held. */ static struct inode *find_inode(struct super_block *sb, struct hlist_head *head, int (*test)(struct inode *, void *), void *data) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; if (!test(inode, data)) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * find_inode_fast is the fast path version of find_inode, see the comment at * iget_locked for details. */ static struct inode *find_inode_fast(struct super_block *sb, struct hlist_head *head, unsigned long ino) { struct inode *inode = NULL; repeat: hlist_for_each_entry(inode, head, i_hash) { if (inode->i_ino != ino) continue; if (inode->i_sb != sb) continue; spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE)) { __wait_on_freeing_inode(inode); goto repeat; } if (unlikely(inode->i_state & I_CREATING)) { spin_unlock(&inode->i_lock); return ERR_PTR(-ESTALE); } __iget(inode); spin_unlock(&inode->i_lock); return inode; } return NULL; } /* * Each cpu owns a range of LAST_INO_BATCH numbers. * 'shared_last_ino' is dirtied only once out of LAST_INO_BATCH allocations, * to renew the exhausted range. * * This does not significantly increase overflow rate because every CPU can * consume at most LAST_INO_BATCH-1 unused inode numbers. So there is * NR_CPUS*(LAST_INO_BATCH-1) wastage. At 4096 and 1024, this is ~0.1% of the * 2^32 range, and is a worst-case. Even a 50% wastage would only increase * overflow rate by 2x, which does not seem too significant. * * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ #define LAST_INO_BATCH 1024 static DEFINE_PER_CPU(unsigned int, last_ino); unsigned int get_next_ino(void) { unsigned int *p = &get_cpu_var(last_ino); unsigned int res = *p; #ifdef CONFIG_SMP if (unlikely((res & (LAST_INO_BATCH-1)) == 0)) { static atomic_t shared_last_ino; int next = atomic_add_return(LAST_INO_BATCH, &shared_last_ino); res = next - LAST_INO_BATCH; } #endif res++; /* get_next_ino should not provide a 0 inode number */ if (unlikely(!res)) res++; *p = res; put_cpu_var(last_ino); return res; } EXPORT_SYMBOL(get_next_ino); /** * new_inode_pseudo - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. * Inode wont be chained in superblock s_inodes list * This means : * - fs can't be unmount * - quotas, fsnotify, writeback can't work */ struct inode *new_inode_pseudo(struct super_block *sb) { struct inode *inode = alloc_inode(sb); if (inode) { spin_lock(&inode->i_lock); inode->i_state = 0; spin_unlock(&inode->i_lock); INIT_LIST_HEAD(&inode->i_sb_list); } return inode; } /** * new_inode - obtain an inode * @sb: superblock * * Allocates a new inode for given superblock. The default gfp_mask * for allocations related to inode->i_mapping is GFP_HIGHUSER_MOVABLE. * If HIGHMEM pages are unsuitable or it is known that pages allocated * for the page cache are not reclaimable or migratable, * mapping_set_gfp_mask() must be called with suitable flags on the * newly created inode's mapping * */ struct inode *new_inode(struct super_block *sb) { struct inode *inode; spin_lock_prefetch(&sb->s_inode_list_lock); inode = new_inode_pseudo(sb); if (inode) inode_sb_list_add(inode); return inode; } EXPORT_SYMBOL(new_inode); #ifdef CONFIG_DEBUG_LOCK_ALLOC void lockdep_annotate_inode_mutex_key(struct inode *inode) { if (S_ISDIR(inode->i_mode)) { struct file_system_type *type = inode->i_sb->s_type; /* Set new key only if filesystem hasn't already changed it */ if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) { /* * ensure nobody is actually holding i_mutex */ // mutex_destroy(&inode->i_mutex); init_rwsem(&inode->i_rwsem); lockdep_set_class(&inode->i_rwsem, &type->i_mutex_dir_key); } } } EXPORT_SYMBOL(lockdep_annotate_inode_mutex_key); #endif /** * unlock_new_inode - clear the I_NEW state and wake up any waiters * @inode: new inode to unlock * * Called when the inode is fully initialised to clear the new state of the * inode and wake up anyone waiting for the inode to finish initialisation. */ void unlock_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW & ~I_CREATING; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(unlock_new_inode); void discard_new_inode(struct inode *inode) { lockdep_annotate_inode_mutex_key(inode); spin_lock(&inode->i_lock); WARN_ON(!(inode->i_state & I_NEW)); inode->i_state &= ~I_NEW; smp_mb(); wake_up_bit(&inode->i_state, __I_NEW); spin_unlock(&inode->i_lock); iput(inode); } EXPORT_SYMBOL(discard_new_inode); /** * lock_two_inodes - lock two inodes (may be regular files but also dirs) * * Lock any non-NULL argument. The caller must make sure that if he is passing * in two directories, one is not ancestor of the other. Zero, one or two * objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock * @subclass1: inode lock subclass for the first lock obtained * @subclass2: inode lock subclass for the second lock obtained */ void lock_two_inodes(struct inode *inode1, struct inode *inode2, unsigned subclass1, unsigned subclass2) { if (!inode1 || !inode2) { /* * Make sure @subclass1 will be used for the acquired lock. * This is not strictly necessary (no current caller cares) but * let's keep things consistent. */ if (!inode1) swap(inode1, inode2); goto lock; } /* * If one object is directory and the other is not, we must make sure * to lock directory first as the other object may be its child. */ if (S_ISDIR(inode2->i_mode) == S_ISDIR(inode1->i_mode)) { if (inode1 > inode2) swap(inode1, inode2); } else if (!S_ISDIR(inode1->i_mode)) swap(inode1, inode2); lock: if (inode1) inode_lock_nested(inode1, subclass1); if (inode2 && inode2 != inode1) inode_lock_nested(inode2, subclass2); } /** * lock_two_nondirectories - take two i_mutexes on non-directory objects * * Lock any non-NULL argument that is not a directory. * Zero, one or two objects may be locked by this function. * * @inode1: first inode to lock * @inode2: second inode to lock */ void lock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1 > inode2) swap(inode1, inode2); if (inode1 && !S_ISDIR(inode1->i_mode)) inode_lock(inode1); if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) inode_lock_nested(inode2, I_MUTEX_NONDIR2); } EXPORT_SYMBOL(lock_two_nondirectories); /** * unlock_two_nondirectories - release locks from lock_two_nondirectories() * @inode1: first inode to unlock * @inode2: second inode to unlock */ void unlock_two_nondirectories(struct inode *inode1, struct inode *inode2) { if (inode1 && !S_ISDIR(inode1->i_mode)) inode_unlock(inode1); if (inode2 && !S_ISDIR(inode2->i_mode) && inode2 != inode1) inode_unlock(inode2); } EXPORT_SYMBOL(unlock_two_nondirectories); /** * inode_insert5 - obtain an inode from a mounted file system * @inode: pre-allocated inode to use for insert to cache * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a variant of iget5_locked() for callers that don't want to fail on memory * allocation of inode. * * If the inode is not in cache, insert the pre-allocated inode to cache and * return it locked, hashed, and with the I_NEW flag set. The file system gets * to fill it in before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *inode_insert5(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(inode->i_sb, hashval); struct inode *old; bool creating = inode->i_state & I_CREATING; again: spin_lock(&inode_hash_lock); old = find_inode(inode->i_sb, head, test, data); if (unlikely(old)) { /* * Uhhuh, somebody else created the same inode under us. * Use the old inode instead of the preallocated one. */ spin_unlock(&inode_hash_lock); if (IS_ERR(old)) return NULL; wait_on_inode(old); if (unlikely(inode_unhashed(old))) { iput(old); goto again; } return old; } if (set && unlikely(set(inode, data))) { inode = NULL; goto unlock; } /* * Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ spin_lock(&inode->i_lock); inode->i_state |= I_NEW; hlist_add_head(&inode->i_hash, head); spin_unlock(&inode->i_lock); if (!creating) inode_sb_list_add(inode); unlock: spin_unlock(&inode_hash_lock); return inode; } EXPORT_SYMBOL(inode_insert5); /** * iget5_locked - obtain an inode from a mounted file system * @sb: super block of file system * @hashval: hash value (usually inode number) to get * @test: callback used for comparisons between inodes * @set: callback used to initialize a new struct inode * @data: opaque data pointer to pass to @test and @set * * Search for the inode specified by @hashval and @data in the inode cache, * and if present it is return it with an increased reference count. This is * a generalized version of iget_locked() for file systems where the inode * number is not sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). * * Note both @test and @set are called with the inode_hash_lock held, so can't * sleep. */ struct inode *iget5_locked(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), int (*set)(struct inode *, void *), void *data) { struct inode *inode = ilookup5(sb, hashval, test, data); if (!inode) { struct inode *new = alloc_inode(sb); if (new) { new->i_state = 0; inode = inode_insert5(new, hashval, test, set, data); if (unlikely(inode != new)) destroy_inode(new); } } return inode; } EXPORT_SYMBOL(iget5_locked); /** * iget_locked - obtain an inode from a mounted file system * @sb: super block of file system * @ino: inode number to get * * Search for the inode specified by @ino in the inode cache and if present * return it with an increased reference count. This is for file systems * where the inode number is sufficient for unique identification of an inode. * * If the inode is not in cache, allocate a new inode and return it locked, * hashed, and with the I_NEW flag set. The file system gets to fill it in * before unlocking it via unlock_new_inode(). */ struct inode *iget_locked(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } return inode; } inode = alloc_inode(sb); if (inode) { struct inode *old; spin_lock(&inode_hash_lock); /* We released the lock, so.. */ old = find_inode_fast(sb, head, ino); if (!old) { inode->i_ino = ino; spin_lock(&inode->i_lock); inode->i_state = I_NEW; hlist_add_head(&inode->i_hash, head); spin_unlock(&inode->i_lock); inode_sb_list_add(inode); spin_unlock(&inode_hash_lock); /* Return the locked inode with I_NEW set, the * caller is responsible for filling in the contents */ return inode; } /* * Uhhuh, somebody else created the same inode under * us. Use the old inode instead of the one we just * allocated. */ spin_unlock(&inode_hash_lock); destroy_inode(inode); if (IS_ERR(old)) return NULL; inode = old; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(iget_locked); /* * search the inode cache for a matching inode number. * If we find one, then the inode number we are trying to * allocate is not unique and so we should not use it. * * Returns 1 if the inode number is unique, 0 if it is not. */ static int test_inode_iunique(struct super_block *sb, unsigned long ino) { struct hlist_head *b = inode_hashtable + hash(sb, ino); struct inode *inode; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, b, i_hash) { if (inode->i_ino == ino && inode->i_sb == sb) { spin_unlock(&inode_hash_lock); return 0; } } spin_unlock(&inode_hash_lock); return 1; } /** * iunique - get a unique inode number * @sb: superblock * @max_reserved: highest reserved inode number * * Obtain an inode number that is unique on the system for a given * superblock. This is used by file systems that have no natural * permanent inode numbering system. An inode number is returned that * is higher than the reserved limit but unique. * * BUGS: * With a large number of inodes live on the file system this function * currently becomes quite slow. */ ino_t iunique(struct super_block *sb, ino_t max_reserved) { /* * On a 32bit, non LFS stat() call, glibc will generate an EOVERFLOW * error if st_ino won't fit in target struct field. Use 32bit counter * here to attempt to avoid that. */ static DEFINE_SPINLOCK(iunique_lock); static unsigned int counter; ino_t res; spin_lock(&iunique_lock); do { if (counter <= max_reserved) counter = max_reserved + 1; res = counter++; } while (!test_inode_iunique(sb, res)); spin_unlock(&iunique_lock); return res; } EXPORT_SYMBOL(iunique); struct inode *igrab(struct inode *inode) { spin_lock(&inode->i_lock); if (!(inode->i_state & (I_FREEING|I_WILL_FREE))) { __iget(inode); spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); /* * Handle the case where s_op->clear_inode is not been * called yet, and somebody is calling igrab * while the inode is getting freed. */ inode = NULL; } return inode; } EXPORT_SYMBOL(igrab); /** * ilookup5_nowait - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache. * If the inode is in the cache, the inode is returned with an incremented * reference count. * * Note: I_NEW is not waited upon so you have to be very careful what you do * with the returned inode. You probably should be using ilookup5() instead. * * Note2: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5_nowait(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode; spin_lock(&inode_hash_lock); inode = find_inode(sb, head, test, data); spin_unlock(&inode_hash_lock); return IS_ERR(inode) ? NULL : inode; } EXPORT_SYMBOL(ilookup5_nowait); /** * ilookup5 - search for an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @test: callback used for comparisons between inodes * @data: opaque data pointer to pass to @test * * Search for the inode specified by @hashval and @data in the inode cache, * and if the inode is in the cache, return the inode with an incremented * reference count. Waits on I_NEW before returning the inode. * returned with an incremented reference count. * * This is a generalized version of ilookup() for file systems where the * inode number is not sufficient for unique identification of an inode. * * Note: @test is called with the inode_hash_lock held, so can't sleep. */ struct inode *ilookup5(struct super_block *sb, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *inode; again: inode = ilookup5_nowait(sb, hashval, test, data); if (inode) { wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup5); /** * ilookup - search for an inode in the inode cache * @sb: super block of file system to search * @ino: inode number to search for * * Search for the inode @ino in the inode cache, and if the inode is in the * cache, the inode is returned with an incremented reference count. */ struct inode *ilookup(struct super_block *sb, unsigned long ino) { struct hlist_head *head = inode_hashtable + hash(sb, ino); struct inode *inode; again: spin_lock(&inode_hash_lock); inode = find_inode_fast(sb, head, ino); spin_unlock(&inode_hash_lock); if (inode) { if (IS_ERR(inode)) return NULL; wait_on_inode(inode); if (unlikely(inode_unhashed(inode))) { iput(inode); goto again; } } return inode; } EXPORT_SYMBOL(ilookup); /** * find_inode_nowait - find an inode in the inode cache * @sb: super block of file system to search * @hashval: hash value (usually inode number) to search for * @match: callback used for comparisons between inodes * @data: opaque data pointer to pass to @match * * Search for the inode specified by @hashval and @data in the inode * cache, where the helper function @match will return 0 if the inode * does not match, 1 if the inode does match, and -1 if the search * should be stopped. The @match function must be responsible for * taking the i_lock spin_lock and checking i_state for an inode being * freed or being initialized, and incrementing the reference count * before returning 1. It also must not sleep, since it is called with * the inode_hash_lock spinlock held. * * This is a even more generalized version of ilookup5() when the * function must never block --- find_inode() can block in * __wait_on_freeing_inode() --- or when the caller can not increment * the reference count because the resulting iput() might cause an * inode eviction. The tradeoff is that the @match funtion must be * very carefully implemented. */ struct inode *find_inode_nowait(struct super_block *sb, unsigned long hashval, int (*match)(struct inode *, unsigned long, void *), void *data) { struct hlist_head *head = inode_hashtable + hash(sb, hashval); struct inode *inode, *ret_inode = NULL; int mval; spin_lock(&inode_hash_lock); hlist_for_each_entry(inode, head, i_hash) { if (inode->i_sb != sb) continue; mval = match(inode, hashval, data); if (mval == 0) continue; if (mval == 1) ret_inode = inode; goto out; } out: spin_unlock(&inode_hash_lock); return ret_inode; } EXPORT_SYMBOL(find_inode_nowait); int insert_inode_locked(struct inode *inode) { struct super_block *sb = inode->i_sb; ino_t ino = inode->i_ino; struct hlist_head *head = inode_hashtable + hash(sb, ino); while (1) { struct inode *old = NULL; spin_lock(&inode_hash_lock); hlist_for_each_entry(old, head, i_hash) { if (old->i_ino != ino) continue; if (old->i_sb != sb) continue; spin_lock(&old->i_lock); if (old->i_state & (I_FREEING|I_WILL_FREE)) { spin_unlock(&old->i_lock); continue; } break; } if (likely(!old)) { spin_lock(&inode->i_lock); inode->i_state |= I_NEW | I_CREATING; hlist_add_head(&inode->i_hash, head); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); return 0; } if (unlikely(old->i_state & I_CREATING)) { spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); return -EBUSY; } __iget(old); spin_unlock(&old->i_lock); spin_unlock(&inode_hash_lock); wait_on_inode(old); if (unlikely(!inode_unhashed(old))) { iput(old); return -EBUSY; } iput(old); } } EXPORT_SYMBOL(insert_inode_locked); int insert_inode_locked4(struct inode *inode, unsigned long hashval, int (*test)(struct inode *, void *), void *data) { struct inode *old; inode->i_state |= I_CREATING; old = inode_insert5(inode, hashval, test, NULL, data); if (old != inode) { iput(old); return -EBUSY; } return 0; } EXPORT_SYMBOL(insert_inode_locked4); int generic_delete_inode(struct inode *inode) { return 1; } EXPORT_SYMBOL(generic_delete_inode); /* * Called when we're dropping the last reference * to an inode. * * Call the FS "drop_inode()" function, defaulting to * the legacy UNIX filesystem behaviour. If it tells * us to evict inode, do so. Otherwise, retain inode * in cache if fs is alive, sync and evict if fs is * shutting down. */ static void iput_final(struct inode *inode) { struct super_block *sb = inode->i_sb; const struct super_operations *op = inode->i_sb->s_op; int drop; WARN_ON(inode->i_state & I_NEW); if (op->drop_inode) drop = op->drop_inode(inode); else drop = generic_drop_inode(inode); if (!drop && (sb->s_flags & SB_ACTIVE)) { inode_add_lru(inode); spin_unlock(&inode->i_lock); return; } if (!drop) { inode->i_state |= I_WILL_FREE; spin_unlock(&inode->i_lock); write_inode_now(inode, 1); spin_lock(&inode->i_lock); WARN_ON(inode->i_state & I_NEW); inode->i_state &= ~I_WILL_FREE; } inode->i_state |= I_FREEING; if (!list_empty(&inode->i_lru)) inode_lru_list_del(inode); spin_unlock(&inode->i_lock); evict(inode); } /** * iput - put an inode * @inode: inode to put * * Puts an inode, dropping its usage count. If the inode use count hits * zero, the inode is then freed and may also be destroyed. * * Consequently, iput() can sleep. */ void iput(struct inode *inode) { if (!inode) return; BUG_ON(inode->i_state & I_CLEAR); retry: if (atomic_dec_and_lock(&inode->i_count, &inode->i_lock)) { if (inode->i_nlink && (inode->i_state & I_DIRTY_TIME)) { atomic_inc(&inode->i_count); spin_unlock(&inode->i_lock); trace_writeback_lazytime_iput(inode); mark_inode_dirty_sync(inode); goto retry; } iput_final(inode); } } EXPORT_SYMBOL(iput); #ifdef CONFIG_BLOCK /** * bmap - find a block number in a file * @inode: inode owning the block number being requested * @block: pointer containing the block to find * * Replaces the value in *block with the block number on the device holding * corresponding to the requested block number in the file. * That is, asked for block 4 of inode 1 the function will replace the * 4 in *block, with disk block relative to the disk start that holds that * block of the file. * * Returns -EINVAL in case of error, 0 otherwise. If mapping falls into a * hole, returns 0 and *block is also set to 0. */ int bmap(struct inode *inode, sector_t *block) { if (!inode->i_mapping->a_ops->bmap) return -EINVAL; *block = inode->i_mapping->a_ops->bmap(inode->i_mapping, *block); return 0; } EXPORT_SYMBOL(bmap); #endif /* * With relative atime, only update atime if the previous atime is * earlier than either the ctime or mtime or if at least a day has * passed since the last atime update. */ static int relatime_need_update(struct vfsmount *mnt, struct inode *inode, struct timespec64 now) { if (!(mnt->mnt_flags & MNT_RELATIME)) return 1; /* * Is mtime younger than atime? If yes, update atime: */ if (timespec64_compare(&inode->i_mtime, &inode->i_atime) >= 0) return 1; /* * Is ctime younger than atime? If yes, update atime: */ if (timespec64_compare(&inode->i_ctime, &inode->i_atime) >= 0) return 1; /* * Is the previous atime value older than a day? If yes, * update atime: */ if ((long)(now.tv_sec - inode->i_atime.tv_sec) >= 24*60*60) return 1; /* * Good, we can skip the atime update: */ return 0; } int generic_update_time(struct inode *inode, struct timespec64 *time, int flags) { int iflags = I_DIRTY_TIME; bool dirty = false; if (flags & S_ATIME) inode->i_atime = *time; if (flags & S_VERSION) dirty = inode_maybe_inc_iversion(inode, false); if (flags & S_CTIME) inode->i_ctime = *time; if (flags & S_MTIME) inode->i_mtime = *time; if ((flags & (S_ATIME | S_CTIME | S_MTIME)) && !(inode->i_sb->s_flags & SB_LAZYTIME)) dirty = true; if (dirty) iflags |= I_DIRTY_SYNC; __mark_inode_dirty(inode, iflags); return 0; } EXPORT_SYMBOL(generic_update_time); /* * This does the actual work of updating an inodes time or version. Must have * had called mnt_want_write() before calling this. */ static int update_time(struct inode *inode, struct timespec64 *time, int flags) { int (*update_time)(struct inode *, struct timespec64 *, int); update_time = inode->i_op->update_time ? inode->i_op->update_time : generic_update_time; return update_time(inode, time, flags); } /** * touch_atime - update the access time * @path: the &struct path to update * @inode: inode to update * * Update the accessed time on an inode and mark it for writeback. * This function automatically handles read only file systems and media, * as well as the "noatime" flag and inode specific "noatime" markers. */ bool atime_needs_update(const struct path *path, struct inode *inode) { struct vfsmount *mnt = path->mnt; struct timespec64 now; if (inode->i_flags & S_NOATIME) return false; /* Atime updates will likely cause i_uid and i_gid to be written * back improprely if their true value is unknown to the vfs. */ if (HAS_UNMAPPED_ID(inode)) return false; if (IS_NOATIME(inode)) return false; if ((inode->i_sb->s_flags & SB_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; if (mnt->mnt_flags & MNT_NOATIME) return false; if ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)) return false; now = current_time(inode); if (!relatime_need_update(mnt, inode, now)) return false; if (timespec64_equal(&inode->i_atime, &now)) return false; return true; } void touch_atime(const struct path *path) { struct vfsmount *mnt = path->mnt; struct inode *inode = d_inode(path->dentry); struct timespec64 now; if (!atime_needs_update(path, inode)) return; if (!sb_start_write_trylock(inode->i_sb)) return; if (__mnt_want_write(mnt) != 0) goto skip_update; /* * File systems can error out when updating inodes if they need to * allocate new space to modify an inode (such is the case for * Btrfs), but since we touch atime while walking down the path we * really don't care if we failed to update the atime of the file, * so just ignore the return value. * We may also fail on filesystems that have the ability to make parts * of the fs read only, e.g. subvolumes in Btrfs. */ now = current_time(inode); update_time(inode, &now, S_ATIME); __mnt_drop_write(mnt); skip_update: sb_end_write(inode->i_sb); } EXPORT_SYMBOL(touch_atime); /* * The logic we want is * * if suid or (sgid and xgrp) * remove privs */ int should_remove_suid(struct dentry *dentry) { umode_t mode = d_inode(dentry)->i_mode; int kill = 0; /* suid always must be killed */ if (unlikely(mode & S_ISUID)) kill = ATTR_KILL_SUID; /* * sgid without any exec bits is just a mandatory locking mark; leave * it alone. If some exec bits are set, it's a real sgid; kill it. */ if (unlikely((mode & S_ISGID) && (mode & S_IXGRP))) kill |= ATTR_KILL_SGID; if (unlikely(kill && !capable(CAP_FSETID) && S_ISREG(mode))) return kill; return 0; } EXPORT_SYMBOL(should_remove_suid); /* * Return mask of changes for notify_change() that need to be done as a * response to write or truncate. Return 0 if nothing has to be changed. * Negative value on error (change should be denied). */ int dentry_needs_remove_privs(struct dentry *dentry) { struct inode *inode = d_inode(dentry); int mask = 0; int ret; if (IS_NOSEC(inode)) return 0; mask = should_remove_suid(dentry); ret = security_inode_need_killpriv(dentry); if (ret < 0) return ret; if (ret) mask |= ATTR_KILL_PRIV; return mask; } static int __remove_privs(struct dentry *dentry, int kill) { struct iattr newattrs; newattrs.ia_valid = ATTR_FORCE | kill; /* * Note we call this on write, so notify_change will not * encounter any conflicting delegations: */ return notify_change(dentry, &newattrs, NULL); } /* * Remove special file priviledges (suid, capabilities) when file is written * to or truncated. */ int file_remove_privs(struct file *file) { struct dentry *dentry = file_dentry(file); struct inode *inode = file_inode(file); int kill; int error = 0; /* * Fast path for nothing security related. * As well for non-regular files, e.g. blkdev inodes. * For example, blkdev_write_iter() might get here * trying to remove privs which it is not allowed to. */ if (IS_NOSEC(inode) || !S_ISREG(inode->i_mode)) return 0; kill = dentry_needs_remove_privs(dentry); if (kill < 0) return kill; if (kill) error = __remove_privs(dentry, kill); if (!error) inode_has_no_xattr(inode); return error; } EXPORT_SYMBOL(file_remove_privs); /** * file_update_time - update mtime and ctime time * @file: file accessed * * Update the mtime and ctime members of an inode and mark the inode * for writeback. Note that this function is meant exclusively for * usage in the file write path of filesystems, and filesystems may * choose to explicitly ignore update via this function with the * S_NOCMTIME inode flag, e.g. for network filesystem where these * timestamps are handled by the server. This can return an error for * file systems who need to allocate space in order to update an inode. */ int file_update_time(struct file *file) { struct inode *inode = file_inode(file); struct timespec64 now; int sync_it = 0; int ret; /* First try to exhaust all avenues to not sync */ if (IS_NOCMTIME(inode)) return 0; now = current_time(inode); if (!timespec64_equal(&inode->i_mtime, &now)) sync_it = S_MTIME; if (!timespec64_equal(&inode->i_ctime, &now)) sync_it |= S_CTIME; if (IS_I_VERSION(inode) && inode_iversion_need_inc(inode)) sync_it |= S_VERSION; if (!sync_it) return 0; /* Finally allowed to write? Takes lock. */ if (__mnt_want_write_file(file)) return 0; ret = update_time(inode, &now, sync_it); __mnt_drop_write_file(file); return ret; } EXPORT_SYMBOL(file_update_time); /* Caller must hold the file's inode lock */ int file_modified(struct file *file) { int err; /* * Clear the security bits if the process is not being run by root. * This keeps people from modifying setuid and setgid binaries. */ err = file_remove_privs(file); if (err) return err; if (unlikely(file->f_mode & FMODE_NOCMTIME)) return 0; return file_update_time(file); } EXPORT_SYMBOL(file_modified); int inode_needs_sync(struct inode *inode) { if (IS_SYNC(inode)) return 1; if (S_ISDIR(inode->i_mode) && IS_DIRSYNC(inode)) return 1; return 0; } EXPORT_SYMBOL(inode_needs_sync); /* * If we try to find an inode in the inode hash while it is being * deleted, we have to wait until the filesystem completes its * deletion before reporting that it isn't found. This function waits * until the deletion _might_ have completed. Callers are responsible * to recheck inode state. * * It doesn't matter if I_NEW is not set initially, a call to * wake_up_bit(&inode->i_state, __I_NEW) after removing from the hash list * will DTRT. */ static void __wait_on_freeing_inode(struct inode *inode) { wait_queue_head_t *wq; DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW); wq = bit_waitqueue(&inode->i_state, __I_NEW); prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE); spin_unlock(&inode->i_lock); spin_unlock(&inode_hash_lock); schedule(); finish_wait(wq, &wait.wq_entry); spin_lock(&inode_hash_lock); } static __initdata unsigned long ihash_entries; static int __init set_ihash_entries(char *str) { if (!str) return 0; ihash_entries = simple_strtoul(str, &str, 0); return 1; } __setup("ihash_entries=", set_ihash_entries); /* * Initialize the waitqueues and inode hash table. */ void __init inode_init_early(void) { /* If hashes are distributed across NUMA nodes, defer * hash allocation until vmalloc space is available. */ if (hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_EARLY | HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void __init inode_init(void) { /* inode slab cache */ inode_cachep = kmem_cache_create("inode_cache", sizeof(struct inode), 0, (SLAB_RECLAIM_ACCOUNT|SLAB_PANIC| SLAB_MEM_SPREAD|SLAB_ACCOUNT), init_once); /* Hash may have been set up in inode_init_early */ if (!hashdist) return; inode_hashtable = alloc_large_system_hash("Inode-cache", sizeof(struct hlist_head), ihash_entries, 14, HASH_ZERO, &i_hash_shift, &i_hash_mask, 0, 0); } void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev) { inode->i_mode = mode; if (S_ISCHR(mode)) { inode->i_fop = &def_chr_fops; inode->i_rdev = rdev; } else if (S_ISBLK(mode)) { inode->i_fop = &def_blk_fops; inode->i_rdev = rdev; } else if (S_ISFIFO(mode)) inode->i_fop = &pipefifo_fops; else if (S_ISSOCK(mode)) ; /* leave it no_open_fops */ else printk(KERN_DEBUG "init_special_inode: bogus i_mode (%o) for" " inode %s:%lu\n", mode, inode->i_sb->s_id, inode->i_ino); } EXPORT_SYMBOL(init_special_inode); /** * inode_init_owner - Init uid,gid,mode for new inode according to posix standards * @inode: New inode * @dir: Directory inode * @mode: mode of the new inode */ void inode_init_owner(struct inode *inode, const struct inode *dir, umode_t mode) { inode->i_uid = current_fsuid(); if (dir && dir->i_mode & S_ISGID) { inode->i_gid = dir->i_gid; /* Directories are special, and always inherit S_ISGID */ if (S_ISDIR(mode)) mode |= S_ISGID; } else inode->i_gid = current_fsgid(); inode->i_mode = mode; } EXPORT_SYMBOL(inode_init_owner); /** * inode_owner_or_capable - check current task permissions to inode * @inode: inode being checked * * Return true if current either has CAP_FOWNER in a namespace with the * inode owner uid mapped, or owns the file. */ bool inode_owner_or_capable(const struct inode *inode) { struct user_namespace *ns; if (uid_eq(current_fsuid(), inode->i_uid)) return true; ns = current_user_ns(); if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER)) return true; return false; } EXPORT_SYMBOL(inode_owner_or_capable); /* * Direct i/o helper functions */ static void __inode_dio_wait(struct inode *inode) { wait_queue_head_t *wq = bit_waitqueue(&inode->i_state, __I_DIO_WAKEUP); DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP); do { prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE); if (atomic_read(&inode->i_dio_count)) schedule(); } while (atomic_read(&inode->i_dio_count)); finish_wait(wq, &q.wq_entry); } /** * inode_dio_wait - wait for outstanding DIO requests to finish * @inode: inode to wait for * * Waits for all pending direct I/O requests to finish so that we can * proceed with a truncate or equivalent operation. * * Must be called under a lock that serializes taking new references * to i_dio_count, usually by inode->i_mutex. */ void inode_dio_wait(struct inode *inode) { if (atomic_read(&inode->i_dio_count)) __inode_dio_wait(inode); } EXPORT_SYMBOL(inode_dio_wait); /* * inode_set_flags - atomically set some inode flags * * Note: the caller should be holding i_mutex, or else be sure that * they have exclusive access to the inode structure (i.e., while the * inode is being instantiated). The reason for the cmpxchg() loop * --- which wouldn't be necessary if all code paths which modify * i_flags actually followed this rule, is that there is at least one * code path which doesn't today so we use cmpxchg() out of an abundance * of caution. * * In the long run, i_mutex is overkill, and we should probably look * at using the i_lock spinlock to protect i_flags, and then make sure * it is so documented in include/linux/fs.h and that all code follows * the locking convention!! */ void inode_set_flags(struct inode *inode, unsigned int flags, unsigned int mask) { WARN_ON_ONCE(flags & ~mask); set_mask_bits(&inode->i_flags, mask, flags); } EXPORT_SYMBOL(inode_set_flags); void inode_nohighmem(struct inode *inode) { mapping_set_gfp_mask(inode->i_mapping, GFP_USER); } EXPORT_SYMBOL(inode_nohighmem); /** * timespec64_trunc - Truncate timespec64 to a granularity * @t: Timespec64 * @gran: Granularity in ns. * * Truncate a timespec64 to a granularity. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timespec64_trunc(struct timespec64 t, unsigned gran) { /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) { /* nothing */ } else if (gran == NSEC_PER_SEC) { t.tv_nsec = 0; } else if (gran > 1 && gran < NSEC_PER_SEC) { t.tv_nsec -= t.tv_nsec % gran; } else { WARN(1, "illegal file time granularity: %u", gran); } return t; } EXPORT_SYMBOL(timespec64_trunc); /** * timestamp_truncate - Truncate timespec to a granularity * @t: Timespec * @inode: inode being updated * * Truncate a timespec to the granularity supported by the fs * containing the inode. Always rounds down. gran must * not be 0 nor greater than a second (NSEC_PER_SEC, or 10^9 ns). */ struct timespec64 timestamp_truncate(struct timespec64 t, struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned int gran = sb->s_time_gran; t.tv_sec = clamp(t.tv_sec, sb->s_time_min, sb->s_time_max); if (unlikely(t.tv_sec == sb->s_time_max || t.tv_sec == sb->s_time_min)) t.tv_nsec = 0; /* Avoid division in the common cases 1 ns and 1 s. */ if (gran == 1) ; /* nothing */ else if (gran == NSEC_PER_SEC) t.tv_nsec = 0; else if (gran > 1 && gran < NSEC_PER_SEC) t.tv_nsec -= t.tv_nsec % gran; else WARN(1, "invalid file time granularity: %u", gran); return t; } EXPORT_SYMBOL(timestamp_truncate); /** * current_time - Return FS time * @inode: inode. * * Return the current time truncated to the time granularity supported by * the fs. * * Note that inode and inode->sb cannot be NULL. * Otherwise, the function warns and returns time without truncation. */ struct timespec64 current_time(struct inode *inode) { struct timespec64 now; ktime_get_coarse_real_ts64(&now); if (unlikely(!inode->i_sb)) { WARN(1, "current_time() called with uninitialized super_block in the inode"); return now; } return timestamp_truncate(now, inode); } EXPORT_SYMBOL(current_time); /* * Generic function to check FS_IOC_SETFLAGS values and reject any invalid * configurations. * * Note: the caller should be holding i_mutex, or else be sure that they have * exclusive access to the inode structure. */ int vfs_ioc_setflags_prepare(struct inode *inode, unsigned int oldflags, unsigned int flags) { /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. * * This test looks nicer. Thanks to Pauline Middelink */ if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; return fscrypt_prepare_setflags(inode, oldflags, flags); } EXPORT_SYMBOL(vfs_ioc_setflags_prepare); /* * Generic function to check FS_IOC_FSSETXATTR values and reject any invalid * configurations. * * Note: the caller should be holding i_mutex, or else be sure that they have * exclusive access to the inode structure. */ int vfs_ioc_fssetxattr_check(struct inode *inode, const struct fsxattr *old_fa, struct fsxattr *fa) { /* * Can't modify an immutable/append-only file unless we have * appropriate permission. */ if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & (FS_XFLAG_IMMUTABLE | FS_XFLAG_APPEND) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; /* * Project Quota ID state is only allowed to change from within the init * namespace. Enforce that restriction only if we are trying to change * the quota ID state. Everything else is allowed in user namespaces. */ if (current_user_ns() != &init_user_ns) { if (old_fa->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_fa->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } /* Check extent size hints. */ if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) && !S_ISDIR(inode->i_mode)) return -EINVAL; if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) && !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode)) return -EINVAL; /* * It is only valid to set the DAX flag on regular files and * directories on filesystems. */ if ((fa->fsx_xflags & FS_XFLAG_DAX) && !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode))) return -EINVAL; /* Extent size hints of zero turn off the flags. */ if (fa->fsx_extsize == 0) fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT); if (fa->fsx_cowextsize == 0) fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE; return 0; } EXPORT_SYMBOL(vfs_ioc_fssetxattr_check); /** * mode_strip_sgid - handle the sgid bit for non-directories * @dir: parent directory inode * @mode: mode of the file to be created in @dir * * If the @mode of the new file has both the S_ISGID and S_IXGRP bit * raised and @dir has the S_ISGID bit raised ensure that the caller is * either in the group of the parent directory or they have CAP_FSETID * in their user namespace and are privileged over the parent directory. * In all other cases, strip the S_ISGID bit from @mode. * * Return: the new mode to use for the file */ umode_t mode_strip_sgid(const struct inode *dir, umode_t mode) { if ((mode & (S_ISGID | S_IXGRP)) != (S_ISGID | S_IXGRP)) return mode; if (S_ISDIR(mode) || !dir || !(dir->i_mode & S_ISGID)) return mode; if (in_group_p(dir->i_gid)) return mode; if (capable_wrt_inode_uidgid(dir, CAP_FSETID)) return mode; return mode & ~S_ISGID; } EXPORT_SYMBOL(mode_strip_sgid); |
| 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH trace/hooks #if !defined(_TRACE_HOOK_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_HOOK_CGROUP_H #include <linux/tracepoint.h> #include <trace/hooks/vendor_hooks.h> struct task_struct; DECLARE_HOOK(android_vh_cgroup_set_task, TP_PROTO(int ret, struct task_struct *task), TP_ARGS(ret, task)); #endif #include <trace/define_trace.h> |
| 80 80 80 2 79 1050 3 1047 2031 1636 1770 1522 1232 686 755 2031 336 337 335 338 2029 2021 328 19 2152 1907 61 556 1652 2127 121 1902 926 928 2036 1040 2143 212 2144 585 2126 121 121 2148 326 2153 2156 459 2157 2150 196 2219 2219 196 2205 2221 30 2203 2221 2225 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 1 1 1 1 5 5 5 5 5 5 5 23 31 8 2 23 2 2659 2 2668 2612 576 121 1047 1048 2622 2621 3 2 2633 450 1585 2121 592 2221 33 60 960 1583 449 2 20 2122 2 2657 2666 484 2615 2 594 594 594 2221 32 33 60 1584 449 2 20 1654 1795 485 2649 12 1378 1388 975 11 11 1414 172 92 171 167 87 87 87 87 3 87 87 79 80 80 172 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/lib/vsprintf.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */ /* * Wirzenius wrote this portably, Torvalds fucked it up :-) */ /* * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com> * - changed to provide snprintf and vsnprintf functions * So Feb 1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de> * - scnprintf and vscnprintf */ #include <stdarg.h> #include <linux/build_bug.h> #include <linux/clk.h> #include <linux/clk-provider.h> #include <linux/module.h> /* for KSYM_SYMBOL_LEN */ #include <linux/types.h> #include <linux/string.h> #include <linux/ctype.h> #include <linux/kernel.h> #include <linux/kallsyms.h> #include <linux/math64.h> #include <linux/uaccess.h> #include <linux/ioport.h> #include <linux/dcache.h> #include <linux/cred.h> #include <linux/rtc.h> #include <linux/uuid.h> #include <linux/of.h> #include <net/addrconf.h> #include <linux/siphash.h> #include <linux/compiler.h> #ifdef CONFIG_BLOCK #include <linux/blkdev.h> #endif #include "../mm/internal.h" /* For the trace_print_flags arrays */ #include <asm/page.h> /* for PAGE_SIZE */ #include <asm/byteorder.h> /* cpu_to_le16 */ #include <linux/string_helpers.h> #include "kstrtox.h" /* Disable pointer hashing if requested */ bool no_hash_pointers __ro_after_init; EXPORT_SYMBOL_GPL(no_hash_pointers); static unsigned long long simple_strntoull(const char *startp, size_t max_chars, char **endp, unsigned int base) { const char *cp; unsigned long long result = 0ULL; size_t prefix_chars; unsigned int rv; cp = _parse_integer_fixup_radix(startp, &base); prefix_chars = cp - startp; if (prefix_chars < max_chars) { rv = _parse_integer_limit(cp, base, &result, max_chars - prefix_chars); /* FIXME */ cp += (rv & ~KSTRTOX_OVERFLOW); } else { /* Field too short for prefix + digit, skip over without converting */ cp = startp + max_chars; } if (endp) *endp = (char *)cp; return result; } /** * simple_strtoull - convert a string to an unsigned long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function is obsolete. Please use kstrtoull instead. */ unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base) { return simple_strntoull(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoull); /** * simple_strtoul - convert a string to an unsigned long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function is obsolete. Please use kstrtoul instead. */ unsigned long simple_strtoul(const char *cp, char **endp, unsigned int base) { return simple_strtoull(cp, endp, base); } EXPORT_SYMBOL(simple_strtoul); /** * simple_strtol - convert a string to a signed long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function is obsolete. Please use kstrtol instead. */ long simple_strtol(const char *cp, char **endp, unsigned int base) { if (*cp == '-') return -simple_strtoul(cp + 1, endp, base); return simple_strtoul(cp, endp, base); } EXPORT_SYMBOL(simple_strtol); static long long simple_strntoll(const char *cp, size_t max_chars, char **endp, unsigned int base) { /* * simple_strntoull() safely handles receiving max_chars==0 in the * case cp[0] == '-' && max_chars == 1. * If max_chars == 0 we can drop through and pass it to simple_strntoull() * and the content of *cp is irrelevant. */ if (*cp == '-' && max_chars > 0) return -simple_strntoull(cp + 1, max_chars - 1, endp, base); return simple_strntoull(cp, max_chars, endp, base); } /** * simple_strtoll - convert a string to a signed long long * @cp: The start of the string * @endp: A pointer to the end of the parsed string will be placed here * @base: The number base to use * * This function is obsolete. Please use kstrtoll instead. */ long long simple_strtoll(const char *cp, char **endp, unsigned int base) { return simple_strntoll(cp, INT_MAX, endp, base); } EXPORT_SYMBOL(simple_strtoll); static noinline_for_stack int skip_atoi(const char **s) { int i = 0; do { i = i*10 + *((*s)++) - '0'; } while (isdigit(**s)); return i; } /* * Decimal conversion is by far the most typical, and is used for * /proc and /sys data. This directly impacts e.g. top performance * with many processes running. We optimize it for speed by emitting * two characters at a time, using a 200 byte lookup table. This * roughly halves the number of multiplications compared to computing * the digits one at a time. Implementation strongly inspired by the * previous version, which in turn used ideas described at * <http://www.cs.uiowa.edu/~jones/bcd/divide.html> (with permission * from the author, Douglas W. Jones). * * It turns out there is precisely one 26 bit fixed-point * approximation a of 64/100 for which x/100 == (x * (u64)a) >> 32 * holds for all x in [0, 10^8-1], namely a = 0x28f5c29. The actual * range happens to be somewhat larger (x <= 1073741898), but that's * irrelevant for our purpose. * * For dividing a number in the range [10^4, 10^6-1] by 100, we still * need a 32x32->64 bit multiply, so we simply use the same constant. * * For dividing a number in the range [100, 10^4-1] by 100, there are * several options. The simplest is (x * 0x147b) >> 19, which is valid * for all x <= 43698. */ static const u16 decpair[100] = { #define _(x) (__force u16) cpu_to_le16(((x % 10) | ((x / 10) << 8)) + 0x3030) _( 0), _( 1), _( 2), _( 3), _( 4), _( 5), _( 6), _( 7), _( 8), _( 9), _(10), _(11), _(12), _(13), _(14), _(15), _(16), _(17), _(18), _(19), _(20), _(21), _(22), _(23), _(24), _(25), _(26), _(27), _(28), _(29), _(30), _(31), _(32), _(33), _(34), _(35), _(36), _(37), _(38), _(39), _(40), _(41), _(42), _(43), _(44), _(45), _(46), _(47), _(48), _(49), _(50), _(51), _(52), _(53), _(54), _(55), _(56), _(57), _(58), _(59), _(60), _(61), _(62), _(63), _(64), _(65), _(66), _(67), _(68), _(69), _(70), _(71), _(72), _(73), _(74), _(75), _(76), _(77), _(78), _(79), _(80), _(81), _(82), _(83), _(84), _(85), _(86), _(87), _(88), _(89), _(90), _(91), _(92), _(93), _(94), _(95), _(96), _(97), _(98), _(99), #undef _ }; /* * This will print a single '0' even if r == 0, since we would * immediately jump to out_r where two 0s would be written but only * one of them accounted for in buf. This is needed by ip4_string * below. All other callers pass a non-zero value of r. */ static noinline_for_stack char *put_dec_trunc8(char *buf, unsigned r) { unsigned q; /* 1 <= r < 10^8 */ if (r < 100) goto out_r; /* 100 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 1 <= q < 10^6 */ if (q < 100) goto out_q; /* 100 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 1 <= r < 10^4 */ if (r < 100) goto out_r; /* 100 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; out_q: /* 1 <= q < 100 */ r = q; out_r: /* 1 <= r < 100 */ *((u16 *)buf) = decpair[r]; buf += r < 10 ? 1 : 2; return buf; } #if BITS_PER_LONG == 64 && BITS_PER_LONG_LONG == 64 static noinline_for_stack char *put_dec_full8(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^8 */ q = (r * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 10^6 */ r = (q * (u64)0x28f5c29) >> 32; *((u16 *)buf) = decpair[q - 100*r]; buf += 2; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; buf += 2; return buf; } static noinline_for_stack char *put_dec(char *buf, unsigned long long n) { if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n <= 1.6e11 */ if (n >= 100*1000*1000) buf = put_dec_full8(buf, do_div(n, 100*1000*1000)); /* 1 <= n < 1e8 */ return put_dec_trunc8(buf, n); } #elif BITS_PER_LONG == 32 && BITS_PER_LONG_LONG == 64 static void put_dec_full4(char *buf, unsigned r) { unsigned q; /* 0 <= r < 10^4 */ q = (r * 0x147b) >> 19; *((u16 *)buf) = decpair[r - 100*q]; buf += 2; /* 0 <= q < 100 */ *((u16 *)buf) = decpair[q]; } /* * Call put_dec_full4 on x % 10000, return x / 10000. * The approximation x/10000 == (x * 0x346DC5D7) >> 43 * holds for all x < 1,128,869,999. The largest value this * helper will ever be asked to convert is 1,125,520,955. * (second call in the put_dec code, assuming n is all-ones). */ static noinline_for_stack unsigned put_dec_helper4(char *buf, unsigned x) { uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43; put_dec_full4(buf, x - q * 10000); return q; } /* Based on code by Douglas W. Jones found at * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour> * (with permission from the author). * Performs no 64-bit division and hence should be fast on 32-bit machines. */ static char *put_dec(char *buf, unsigned long long n) { uint32_t d3, d2, d1, q, h; if (n < 100*1000*1000) return put_dec_trunc8(buf, n); d1 = ((uint32_t)n >> 16); /* implicit "& 0xffff" */ h = (n >> 32); d2 = (h ) & 0xffff; d3 = (h >> 16); /* implicit "& 0xffff" */ /* n = 2^48 d3 + 2^32 d2 + 2^16 d1 + d0 = 281_4749_7671_0656 d3 + 42_9496_7296 d2 + 6_5536 d1 + d0 */ q = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff); q = put_dec_helper4(buf, q); q += 7671 * d3 + 9496 * d2 + 6 * d1; q = put_dec_helper4(buf+4, q); q += 4749 * d3 + 42 * d2; q = put_dec_helper4(buf+8, q); q += 281 * d3; buf += 12; if (q) buf = put_dec_trunc8(buf, q); else while (buf[-1] == '0') --buf; return buf; } #endif /* * Convert passed number to decimal string. * Returns the length of string. On buffer overflow, returns 0. * * If speed is not important, use snprintf(). It's easy to read the code. */ int num_to_str(char *buf, int size, unsigned long long num, unsigned int width) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[sizeof(num) * 3] __aligned(2); int idx, len; /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */ if (num <= 9) { tmp[0] = '0' + num; len = 1; } else { len = put_dec(tmp, num) - tmp; } if (len > size || width > size) return 0; if (width > len) { width = width - len; for (idx = 0; idx < width; idx++) buf[idx] = ' '; } else { width = 0; } for (idx = 0; idx < len; ++idx) buf[idx + width] = tmp[len - idx - 1]; return len + width; } #define SIGN 1 /* unsigned/signed, must be 1 */ #define LEFT 2 /* left justified */ #define PLUS 4 /* show plus */ #define SPACE 8 /* space if plus */ #define ZEROPAD 16 /* pad with zero, must be 16 == '0' - ' ' */ #define SMALL 32 /* use lowercase in hex (must be 32 == 0x20) */ #define SPECIAL 64 /* prefix hex with "0x", octal with "0" */ enum format_type { FORMAT_TYPE_NONE, /* Just a string part */ FORMAT_TYPE_WIDTH, FORMAT_TYPE_PRECISION, FORMAT_TYPE_CHAR, FORMAT_TYPE_STR, FORMAT_TYPE_PTR, FORMAT_TYPE_PERCENT_CHAR, FORMAT_TYPE_INVALID, FORMAT_TYPE_LONG_LONG, FORMAT_TYPE_ULONG, FORMAT_TYPE_LONG, FORMAT_TYPE_UBYTE, FORMAT_TYPE_BYTE, FORMAT_TYPE_USHORT, FORMAT_TYPE_SHORT, FORMAT_TYPE_UINT, FORMAT_TYPE_INT, FORMAT_TYPE_SIZE_T, FORMAT_TYPE_PTRDIFF }; struct printf_spec { unsigned int type:8; /* format_type enum */ signed int field_width:24; /* width of output field */ unsigned int flags:8; /* flags to number() */ unsigned int base:8; /* number base, 8, 10 or 16 only */ signed int precision:16; /* # of digits/chars */ } __packed; static_assert(sizeof(struct printf_spec) == 8); #define FIELD_WIDTH_MAX ((1 << 23) - 1) #define PRECISION_MAX ((1 << 15) - 1) static noinline_for_stack char *number(char *buf, char *end, unsigned long long num, struct printf_spec spec) { /* put_dec requires 2-byte alignment of the buffer. */ char tmp[3 * sizeof(num)] __aligned(2); char sign; char locase; int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10); int i; bool is_zero = num == 0LL; int field_width = spec.field_width; int precision = spec.precision; /* locase = 0 or 0x20. ORing digits or letters with 'locase' * produces same digits or (maybe lowercased) letters */ locase = (spec.flags & SMALL); if (spec.flags & LEFT) spec.flags &= ~ZEROPAD; sign = 0; if (spec.flags & SIGN) { if ((signed long long)num < 0) { sign = '-'; num = -(signed long long)num; field_width--; } else if (spec.flags & PLUS) { sign = '+'; field_width--; } else if (spec.flags & SPACE) { sign = ' '; field_width--; } } if (need_pfx) { if (spec.base == 16) field_width -= 2; else if (!is_zero) field_width--; } /* generate full string in tmp[], in reverse order */ i = 0; if (num < spec.base) tmp[i++] = hex_asc_upper[num] | locase; else if (spec.base != 10) { /* 8 or 16 */ int mask = spec.base - 1; int shift = 3; if (spec.base == 16) shift = 4; do { tmp[i++] = (hex_asc_upper[((unsigned char)num) & mask] | locase); num >>= shift; } while (num); } else { /* base 10 */ i = put_dec(tmp, num) - tmp; } /* printing 100 using %2d gives "100", not "00" */ if (i > precision) precision = i; /* leading space padding */ field_width -= precision; if (!(spec.flags & (ZEROPAD | LEFT))) { while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } } /* sign */ if (sign) { if (buf < end) *buf = sign; ++buf; } /* "0x" / "0" prefix */ if (need_pfx) { if (spec.base == 16 || !is_zero) { if (buf < end) *buf = '0'; ++buf; } if (spec.base == 16) { if (buf < end) *buf = ('X' | locase); ++buf; } } /* zero or space padding */ if (!(spec.flags & LEFT)) { char c = ' ' + (spec.flags & ZEROPAD); BUILD_BUG_ON(' ' + ZEROPAD != '0'); while (--field_width >= 0) { if (buf < end) *buf = c; ++buf; } } /* hmm even more zero padding? */ while (i <= --precision) { if (buf < end) *buf = '0'; ++buf; } /* actual digits of result */ while (--i >= 0) { if (buf < end) *buf = tmp[i]; ++buf; } /* trailing space padding */ while (--field_width >= 0) { if (buf < end) *buf = ' '; ++buf; } return buf; } static noinline_for_stack char *special_hex_number(char *buf, char *end, unsigned long long num, int size) { struct printf_spec spec; spec.type = FORMAT_TYPE_PTR; spec.field_width = 2 + 2 * size; /* 0x + hex */ spec.flags = SPECIAL | SMALL | ZEROPAD; spec.base = 16; spec.precision = -1; return number(buf, end, num, spec); } static void move_right(char *buf, char *end, unsigned len, unsigned spaces) { size_t size; if (buf >= end) /* nowhere to put anything */ return; size = end - buf; if (size <= spaces) { memset(buf, ' ', size); return; } if (len) { if (len > size - spaces) len = size - spaces; memmove(buf + spaces, buf, len); } memset(buf, ' ', spaces); } /* * Handle field width padding for a string. * @buf: current buffer position * @n: length of string * @end: end of output buffer * @spec: for field width and flags * Returns: new buffer position after padding. */ static noinline_for_stack char *widen_string(char *buf, int n, char *end, struct printf_spec spec) { unsigned spaces; if (likely(n >= spec.field_width)) return buf; /* we want to pad the sucker */ spaces = spec.field_width - n; if (!(spec.flags & LEFT)) { move_right(buf - n, end, n, spaces); return buf + spaces; } while (spaces--) { if (buf < end) *buf = ' '; ++buf; } return buf; } /* Handle string from a well known address. */ static char *string_nocheck(char *buf, char *end, const char *s, struct printf_spec spec) { int len = 0; int lim = spec.precision; while (lim--) { char c = *s++; if (!c) break; if (buf < end) *buf = c; ++buf; ++len; } return widen_string(buf, len, end, spec); } /* Be careful: error messages must fit into the given buffer. */ static char *error_string(char *buf, char *end, const char *s, struct printf_spec spec) { /* * Hard limit to avoid a completely insane messages. It actually * works pretty well because most error messages are in * the many pointer format modifiers. */ if (spec.precision == -1) spec.precision = 2 * sizeof(void *); return string_nocheck(buf, end, s, spec); } /* * Do not call any complex external code here. Nested printk()/vsprintf() * might cause infinite loops. Failures might break printk() and would * be hard to debug. */ static const char *check_pointer_msg(const void *ptr) { if (!ptr) return "(null)"; if ((unsigned long)ptr < PAGE_SIZE || IS_ERR_VALUE(ptr)) return "(efault)"; return NULL; } static int check_pointer(char **buf, char *end, const void *ptr, struct printf_spec spec) { const char *err_msg; err_msg = check_pointer_msg(ptr); if (err_msg) { *buf = error_string(*buf, end, err_msg, spec); return -EFAULT; } return 0; } static noinline_for_stack char *string(char *buf, char *end, const char *s, struct printf_spec spec) { if (check_pointer(&buf, end, s, spec)) return buf; return string_nocheck(buf, end, s, spec); } static char *pointer_string(char *buf, char *end, const void *ptr, struct printf_spec spec) { spec.base = 16; spec.flags |= SMALL; if (spec.field_width == -1) { spec.field_width = 2 * sizeof(ptr); spec.flags |= ZEROPAD; } return number(buf, end, (unsigned long int)ptr, spec); } /* Make pointers available for printing early in the boot sequence. */ static int debug_boot_weak_hash __ro_after_init; static int __init debug_boot_weak_hash_enable(char *str) { debug_boot_weak_hash = 1; pr_info("debug_boot_weak_hash enabled\n"); return 0; } early_param("debug_boot_weak_hash", debug_boot_weak_hash_enable); static DEFINE_STATIC_KEY_TRUE(not_filled_random_ptr_key); static siphash_key_t ptr_key __read_mostly; static void enable_ptr_key_workfn(struct work_struct *work) { get_random_bytes(&ptr_key, sizeof(ptr_key)); /* Needs to run from preemptible context */ static_branch_disable(¬_filled_random_ptr_key); } static DECLARE_WORK(enable_ptr_key_work, enable_ptr_key_workfn); static int fill_random_ptr_key(struct notifier_block *nb, unsigned long action, void *data) { /* This may be in an interrupt handler. */ queue_work(system_unbound_wq, &enable_ptr_key_work); return 0; } static struct notifier_block random_ready = { .notifier_call = fill_random_ptr_key }; static int __init initialize_ptr_random(void) { int key_size = sizeof(ptr_key); int ret; /* Use hw RNG if available. */ if (get_random_bytes_arch(&ptr_key, key_size) == key_size) { static_branch_disable(¬_filled_random_ptr_key); return 0; } ret = register_random_ready_notifier(&random_ready); if (!ret) { return 0; } else if (ret == -EALREADY) { /* This is in preemptible context */ enable_ptr_key_workfn(&enable_ptr_key_work); return 0; } return ret; } early_initcall(initialize_ptr_random); static inline int __ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { unsigned long hashval; if (static_branch_unlikely(¬_filled_random_ptr_key)) return -EAGAIN; #ifdef CONFIG_64BIT hashval = (unsigned long)siphash_1u64((u64)ptr, &ptr_key); /* * Mask off the first 32 bits, this makes explicit that we have * modified the address (and 32 bits is plenty for a unique ID). */ hashval = hashval & 0xffffffff; #else hashval = (unsigned long)siphash_1u32((u32)ptr, &ptr_key); #endif *hashval_out = hashval; return 0; } int ptr_to_hashval(const void *ptr, unsigned long *hashval_out) { return __ptr_to_hashval(ptr, hashval_out); } /* Maps a pointer to a 32 bit unique identifier. */ static char *ptr_to_id(char *buf, char *end, const void *ptr, struct printf_spec spec) { const char *str = sizeof(ptr) == 8 ? "(____ptrval____)" : "(ptrval)"; unsigned long hashval; int ret; /* * Print the real pointer value for NULL and error pointers, * as they are not actual addresses. */ if (IS_ERR_OR_NULL(ptr)) return pointer_string(buf, end, ptr, spec); /* When debugging early boot use non-cryptographically secure hash. */ if (unlikely(debug_boot_weak_hash)) { hashval = hash_long((unsigned long)ptr, 32); return pointer_string(buf, end, (const void *)hashval, spec); } ret = __ptr_to_hashval(ptr, &hashval); if (ret) { spec.field_width = 2 * sizeof(ptr); /* string length must be less than default_width */ return error_string(buf, end, str, spec); } return pointer_string(buf, end, (const void *)hashval, spec); } static char *default_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { /* * default is to _not_ leak addresses, so hash before printing, * unless no_hash_pointers is specified on the command line. */ if (unlikely(no_hash_pointers)) return pointer_string(buf, end, ptr, spec); return ptr_to_id(buf, end, ptr, spec); } int kptr_restrict __read_mostly; static noinline_for_stack char *restricted_pointer(char *buf, char *end, const void *ptr, struct printf_spec spec) { switch (kptr_restrict) { case 0: /* Handle as %p, hash and do _not_ leak addresses. */ return default_pointer(buf, end, ptr, spec); case 1: { const struct cred *cred; /* * kptr_restrict==1 cannot be used in IRQ context * because its test for CAP_SYSLOG would be meaningless. */ if (in_irq() || in_serving_softirq() || in_nmi()) { if (spec.field_width == -1) spec.field_width = 2 * sizeof(ptr); return error_string(buf, end, "pK-error", spec); } /* * Only print the real pointer value if the current * process has CAP_SYSLOG and is running with the * same credentials it started with. This is because * access to files is checked at open() time, but %pK * checks permission at read() time. We don't want to * leak pointer values if a binary opens a file using * %pK and then elevates privileges before reading it. */ cred = current_cred(); if (!has_capability_noaudit(current, CAP_SYSLOG) || !uid_eq(cred->euid, cred->uid) || !gid_eq(cred->egid, cred->gid)) ptr = NULL; break; } case 2: default: /* Always print 0's for %pK */ ptr = NULL; break; } return pointer_string(buf, end, ptr, spec); } static noinline_for_stack char *dentry_name(char *buf, char *end, const struct dentry *d, struct printf_spec spec, const char *fmt) { const char *array[4], *s; const struct dentry *p; int depth; int i, n; switch (fmt[1]) { case '2': case '3': case '4': depth = fmt[1] - '0'; break; default: depth = 1; } rcu_read_lock(); for (i = 0; i < depth; i++, d = p) { if (check_pointer(&buf, end, d, spec)) { rcu_read_unlock(); return buf; } p = READ_ONCE(d->d_parent); array[i] = READ_ONCE(d->d_name.name); if (p == d) { if (i) array[i] = ""; i++; break; } } s = array[--i]; for (n = 0; n != spec.precision; n++, buf++) { char c = *s++; if (!c) { if (!i) break; c = '/'; s = array[--i]; } if (buf < end) *buf = c; } rcu_read_unlock(); return widen_string(buf, n, end, spec); } static noinline_for_stack char *file_dentry_name(char *buf, char *end, const struct file *f, struct printf_spec spec, const char *fmt) { if (check_pointer(&buf, end, f, spec)) return buf; return dentry_name(buf, end, f->f_path.dentry, spec, fmt); } #ifdef CONFIG_BLOCK static noinline_for_stack char *bdev_name(char *buf, char *end, struct block_device *bdev, struct printf_spec spec, const char *fmt) { struct gendisk *hd; if (check_pointer(&buf, end, bdev, spec)) return buf; hd = bdev->bd_disk; buf = string(buf, end, hd->disk_name, spec); if (bdev->bd_part->partno) { if (isdigit(hd->disk_name[strlen(hd->disk_name)-1])) { if (buf < end) *buf = 'p'; buf++; } buf = number(buf, end, bdev->bd_part->partno, spec); } return buf; } #endif static noinline_for_stack char *symbol_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { unsigned long value; #ifdef CONFIG_KALLSYMS char sym[KSYM_SYMBOL_LEN]; #endif if (fmt[1] == 'R') ptr = __builtin_extract_return_addr(ptr); value = (unsigned long)ptr; #ifdef CONFIG_KALLSYMS if (*fmt == 'B') sprint_backtrace(sym, value); else if (*fmt != 'f' && *fmt != 's') sprint_symbol(sym, value); else sprint_symbol_no_offset(sym, value); return string_nocheck(buf, end, sym, spec); #else return special_hex_number(buf, end, value, sizeof(void *)); #endif } static const struct printf_spec default_str_spec = { .field_width = -1, .precision = -1, }; static const struct printf_spec default_flag_spec = { .base = 16, .precision = -1, .flags = SPECIAL | SMALL, }; static const struct printf_spec default_dec_spec = { .base = 10, .precision = -1, }; static const struct printf_spec default_dec02_spec = { .base = 10, .field_width = 2, .precision = -1, .flags = ZEROPAD, }; static const struct printf_spec default_dec04_spec = { .base = 10, .field_width = 4, .precision = -1, .flags = ZEROPAD, }; static noinline_for_stack char *resource_string(char *buf, char *end, struct resource *res, struct printf_spec spec, const char *fmt) { #ifndef IO_RSRC_PRINTK_SIZE #define IO_RSRC_PRINTK_SIZE 6 #endif #ifndef MEM_RSRC_PRINTK_SIZE #define MEM_RSRC_PRINTK_SIZE 10 #endif static const struct printf_spec io_spec = { .base = 16, .field_width = IO_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec mem_spec = { .base = 16, .field_width = MEM_RSRC_PRINTK_SIZE, .precision = -1, .flags = SPECIAL | SMALL | ZEROPAD, }; static const struct printf_spec bus_spec = { .base = 16, .field_width = 2, .precision = -1, .flags = SMALL | ZEROPAD, }; static const struct printf_spec str_spec = { .field_width = -1, .precision = 10, .flags = LEFT, }; /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8) * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */ #define RSRC_BUF_SIZE ((2 * sizeof(resource_size_t)) + 4) #define FLAG_BUF_SIZE (2 * sizeof(res->flags)) #define DECODED_BUF_SIZE sizeof("[mem - 64bit pref window disabled]") #define RAW_BUF_SIZE sizeof("[mem - flags 0x]") char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE, 2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)]; char *p = sym, *pend = sym + sizeof(sym); int decode = (fmt[0] == 'R') ? 1 : 0; const struct printf_spec *specp; if (check_pointer(&buf, end, res, spec)) return buf; *p++ = '['; if (res->flags & IORESOURCE_IO) { p = string_nocheck(p, pend, "io ", str_spec); specp = &io_spec; } else if (res->flags & IORESOURCE_MEM) { p = string_nocheck(p, pend, "mem ", str_spec); specp = &mem_spec; } else if (res->flags & IORESOURCE_IRQ) { p = string_nocheck(p, pend, "irq ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_DMA) { p = string_nocheck(p, pend, "dma ", str_spec); specp = &default_dec_spec; } else if (res->flags & IORESOURCE_BUS) { p = string_nocheck(p, pend, "bus ", str_spec); specp = &bus_spec; } else { p = string_nocheck(p, pend, "??? ", str_spec); specp = &mem_spec; decode = 0; } if (decode && res->flags & IORESOURCE_UNSET) { p = string_nocheck(p, pend, "size ", str_spec); p = number(p, pend, resource_size(res), *specp); } else { p = number(p, pend, res->start, *specp); if (res->start != res->end) { *p++ = '-'; p = number(p, pend, res->end, *specp); } } if (decode) { if (res->flags & IORESOURCE_MEM_64) p = string_nocheck(p, pend, " 64bit", str_spec); if (res->flags & IORESOURCE_PREFETCH) p = string_nocheck(p, pend, " pref", str_spec); if (res->flags & IORESOURCE_WINDOW) p = string_nocheck(p, pend, " window", str_spec); if (res->flags & IORESOURCE_DISABLED) p = string_nocheck(p, pend, " disabled", str_spec); } else { p = string_nocheck(p, pend, " flags ", str_spec); p = number(p, pend, res->flags, default_flag_spec); } *p++ = ']'; *p = '\0'; return string_nocheck(buf, end, sym, spec); } static noinline_for_stack char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { int i, len = 1; /* if we pass '%ph[CDN]', field width remains negative value, fallback to the default */ char separator; if (spec.field_width == 0) /* nothing to print */ return buf; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'C': separator = ':'; break; case 'D': separator = '-'; break; case 'N': separator = 0; break; default: separator = ' '; break; } if (spec.field_width > 0) len = min_t(int, spec.field_width, 64); for (i = 0; i < len; ++i) { if (buf < end) *buf = hex_asc_hi(addr[i]); ++buf; if (buf < end) *buf = hex_asc_lo(addr[i]); ++buf; if (separator && i != len - 1) { if (buf < end) *buf = separator; ++buf; } } return buf; } static noinline_for_stack char *bitmap_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { const int CHUNKSZ = 32; int nr_bits = max_t(int, spec.field_width, 0); int i, chunksz; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; /* reused to print numbers */ spec = (struct printf_spec){ .flags = SMALL | ZEROPAD, .base = 16 }; chunksz = nr_bits & (CHUNKSZ - 1); if (chunksz == 0) chunksz = CHUNKSZ; i = ALIGN(nr_bits, CHUNKSZ) - CHUNKSZ; for (; i >= 0; i -= CHUNKSZ) { u32 chunkmask, val; int word, bit; chunkmask = ((1ULL << chunksz) - 1); word = i / BITS_PER_LONG; bit = i % BITS_PER_LONG; val = (bitmap[word] >> bit) & chunkmask; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; spec.field_width = DIV_ROUND_UP(chunksz, 4); buf = number(buf, end, val, spec); chunksz = CHUNKSZ; } return buf; } static noinline_for_stack char *bitmap_list_string(char *buf, char *end, unsigned long *bitmap, struct printf_spec spec, const char *fmt) { int nr_bits = max_t(int, spec.field_width, 0); /* current bit is 'cur', most recently seen range is [rbot, rtop] */ int cur, rbot, rtop; bool first = true; if (check_pointer(&buf, end, bitmap, spec)) return buf; rbot = cur = find_first_bit(bitmap, nr_bits); while (cur < nr_bits) { rtop = cur; cur = find_next_bit(bitmap, nr_bits, cur + 1); if (cur < nr_bits && cur <= rtop + 1) continue; if (!first) { if (buf < end) *buf = ','; buf++; } first = false; buf = number(buf, end, rbot, default_dec_spec); if (rbot < rtop) { if (buf < end) *buf = '-'; buf++; buf = number(buf, end, rtop, default_dec_spec); } rbot = cur; } return buf; } static noinline_for_stack char *mac_address_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { char mac_addr[sizeof("xx:xx:xx:xx:xx:xx")]; char *p = mac_addr; int i; char separator; bool reversed = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': separator = '-'; break; case 'R': reversed = true; /* fall through */ default: separator = ':'; break; } for (i = 0; i < 6; i++) { if (reversed) p = hex_byte_pack(p, addr[5 - i]); else p = hex_byte_pack(p, addr[i]); if (fmt[0] == 'M' && i != 5) *p++ = separator; } *p = '\0'; return string_nocheck(buf, end, mac_addr, spec); } static noinline_for_stack char *ip4_string(char *p, const u8 *addr, const char *fmt) { int i; bool leading_zeros = (fmt[0] == 'i'); int index; int step; switch (fmt[2]) { case 'h': #ifdef __BIG_ENDIAN index = 0; step = 1; #else index = 3; step = -1; #endif break; case 'l': index = 3; step = -1; break; case 'n': case 'b': default: index = 0; step = 1; break; } for (i = 0; i < 4; i++) { char temp[4] __aligned(2); /* hold each IP quad in reverse order */ int digits = put_dec_trunc8(temp, addr[index]) - temp; if (leading_zeros) { if (digits < 3) *p++ = '0'; if (digits < 2) *p++ = '0'; } /* reverse the digits in the quad */ while (digits--) *p++ = temp[digits]; if (i < 3) *p++ = '.'; index += step; } *p = '\0'; return p; } static noinline_for_stack char *ip6_compressed_string(char *p, const char *addr) { int i, j, range; unsigned char zerolength[8]; int longest = 1; int colonpos = -1; u16 word; u8 hi, lo; bool needcolon = false; bool useIPv4; struct in6_addr in6; memcpy(&in6, addr, sizeof(struct in6_addr)); useIPv4 = ipv6_addr_v4mapped(&in6) || ipv6_addr_is_isatap(&in6); memset(zerolength, 0, sizeof(zerolength)); if (useIPv4) range = 6; else range = 8; /* find position of longest 0 run */ for (i = 0; i < range; i++) { for (j = i; j < range; j++) { if (in6.s6_addr16[j] != 0) break; zerolength[i]++; } } for (i = 0; i < range; i++) { if (zerolength[i] > longest) { longest = zerolength[i]; colonpos = i; } } if (longest == 1) /* don't compress a single 0 */ colonpos = -1; /* emit address */ for (i = 0; i < range; i++) { if (i == colonpos) { if (needcolon || i == 0) *p++ = ':'; *p++ = ':'; needcolon = false; i += longest - 1; continue; } if (needcolon) { *p++ = ':'; needcolon = false; } /* hex u16 without leading 0s */ word = ntohs(in6.s6_addr16[i]); hi = word >> 8; lo = word & 0xff; if (hi) { if (hi > 0x0f) p = hex_byte_pack(p, hi); else *p++ = hex_asc_lo(hi); p = hex_byte_pack(p, lo); } else if (lo > 0x0f) p = hex_byte_pack(p, lo); else *p++ = hex_asc_lo(lo); needcolon = true; } if (useIPv4) { if (needcolon) *p++ = ':'; p = ip4_string(p, &in6.s6_addr[12], "I4"); } *p = '\0'; return p; } static noinline_for_stack char *ip6_string(char *p, const char *addr, const char *fmt) { int i; for (i = 0; i < 8; i++) { p = hex_byte_pack(p, *addr++); p = hex_byte_pack(p, *addr++); if (fmt[0] == 'I' && i != 7) *p++ = ':'; } *p = '\0'; return p; } static noinline_for_stack char *ip6_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip6_addr[sizeof("xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255")]; if (fmt[0] == 'I' && fmt[2] == 'c') ip6_compressed_string(ip6_addr, addr); else ip6_string(ip6_addr, addr, fmt); return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char ip4_addr[sizeof("255.255.255.255")]; ip4_string(ip4_addr, addr, fmt); return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip6_addr_string_sa(char *buf, char *end, const struct sockaddr_in6 *sa, struct printf_spec spec, const char *fmt) { bool have_p = false, have_s = false, have_f = false, have_c = false; char ip6_addr[sizeof("[xxxx:xxxx:xxxx:xxxx:xxxx:xxxx:255.255.255.255]") + sizeof(":12345") + sizeof("/123456789") + sizeof("%1234567890")]; char *p = ip6_addr, *pend = ip6_addr + sizeof(ip6_addr); const u8 *addr = (const u8 *) &sa->sin6_addr; char fmt6[2] = { fmt[0], '6' }; u8 off = 0; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'f': have_f = true; break; case 's': have_s = true; break; case 'c': have_c = true; break; } } if (have_p || have_s || have_f) { *p = '['; off = 1; } if (fmt6[0] == 'I' && have_c) p = ip6_compressed_string(ip6_addr + off, addr); else p = ip6_string(ip6_addr + off, addr, fmt6); if (have_p || have_s || have_f) *p++ = ']'; if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin6_port), spec); } if (have_f) { *p++ = '/'; p = number(p, pend, ntohl(sa->sin6_flowinfo & IPV6_FLOWINFO_MASK), spec); } if (have_s) { *p++ = '%'; p = number(p, pend, sa->sin6_scope_id, spec); } *p = '\0'; return string_nocheck(buf, end, ip6_addr, spec); } static noinline_for_stack char *ip4_addr_string_sa(char *buf, char *end, const struct sockaddr_in *sa, struct printf_spec spec, const char *fmt) { bool have_p = false; char *p, ip4_addr[sizeof("255.255.255.255") + sizeof(":12345")]; char *pend = ip4_addr + sizeof(ip4_addr); const u8 *addr = (const u8 *) &sa->sin_addr.s_addr; char fmt4[3] = { fmt[0], '4', 0 }; fmt++; while (isalpha(*++fmt)) { switch (*fmt) { case 'p': have_p = true; break; case 'h': case 'l': case 'n': case 'b': fmt4[2] = *fmt; break; } } p = ip4_string(ip4_addr, addr, fmt4); if (have_p) { *p++ = ':'; p = number(p, pend, ntohs(sa->sin_port), spec); } *p = '\0'; return string_nocheck(buf, end, ip4_addr, spec); } static noinline_for_stack char *ip_addr_string(char *buf, char *end, const void *ptr, struct printf_spec spec, const char *fmt) { char *err_fmt_msg; if (check_pointer(&buf, end, ptr, spec)) return buf; switch (fmt[1]) { case '6': return ip6_addr_string(buf, end, ptr, spec, fmt); case '4': return ip4_addr_string(buf, end, ptr, spec, fmt); case 'S': { const union { struct sockaddr raw; struct sockaddr_in v4; struct sockaddr_in6 v6; } *sa = ptr; switch (sa->raw.sa_family) { case AF_INET: return ip4_addr_string_sa(buf, end, &sa->v4, spec, fmt); case AF_INET6: return ip6_addr_string_sa(buf, end, &sa->v6, spec, fmt); default: return error_string(buf, end, "(einval)", spec); }} } err_fmt_msg = fmt[0] == 'i' ? "(%pi?)" : "(%pI?)"; return error_string(buf, end, err_fmt_msg, spec); } static noinline_for_stack char *escaped_string(char *buf, char *end, u8 *addr, struct printf_spec spec, const char *fmt) { bool found = true; int count = 1; unsigned int flags = 0; int len; if (spec.field_width == 0) return buf; /* nothing to print */ if (check_pointer(&buf, end, addr, spec)) return buf; do { switch (fmt[count++]) { case 'a': flags |= ESCAPE_ANY; break; case 'c': flags |= ESCAPE_SPECIAL; break; case 'h': flags |= ESCAPE_HEX; break; case 'n': flags |= ESCAPE_NULL; break; case 'o': flags |= ESCAPE_OCTAL; break; case 'p': flags |= ESCAPE_NP; break; case 's': flags |= ESCAPE_SPACE; break; default: found = false; break; } } while (found); if (!flags) flags = ESCAPE_ANY_NP; len = spec.field_width < 0 ? 1 : spec.field_width; /* * string_escape_mem() writes as many characters as it can to * the given buffer, and returns the total size of the output * had the buffer been big enough. */ buf += string_escape_mem(addr, len, buf, buf < end ? end - buf : 0, flags, NULL); return buf; } static char *va_format(char *buf, char *end, struct va_format *va_fmt, struct printf_spec spec, const char *fmt) { va_list va; if (check_pointer(&buf, end, va_fmt, spec)) return buf; va_copy(va, *va_fmt->va); buf += vsnprintf(buf, end > buf ? end - buf : 0, va_fmt->fmt, va); va_end(va); return buf; } static noinline_for_stack char *uuid_string(char *buf, char *end, const u8 *addr, struct printf_spec spec, const char *fmt) { char uuid[UUID_STRING_LEN + 1]; char *p = uuid; int i; const u8 *index = uuid_index; bool uc = false; if (check_pointer(&buf, end, addr, spec)) return buf; switch (*(++fmt)) { case 'L': uc = true; /* fall-through */ case 'l': index = guid_index; break; case 'B': uc = true; break; } for (i = 0; i < 16; i++) { if (uc) p = hex_byte_pack_upper(p, addr[index[i]]); else p = hex_byte_pack(p, addr[index[i]]); switch (i) { case 3: case 5: case 7: case 9: *p++ = '-'; break; } } *p = 0; return string_nocheck(buf, end, uuid, spec); } static noinline_for_stack char *netdev_bits(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'F': num = *(const netdev_features_t *)addr; size = sizeof(netdev_features_t); break; default: return error_string(buf, end, "(%pN?)", spec); } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *address_val(char *buf, char *end, const void *addr, struct printf_spec spec, const char *fmt) { unsigned long long num; int size; if (check_pointer(&buf, end, addr, spec)) return buf; switch (fmt[1]) { case 'd': num = *(const dma_addr_t *)addr; size = sizeof(dma_addr_t); break; case 'p': default: num = *(const phys_addr_t *)addr; size = sizeof(phys_addr_t); break; } return special_hex_number(buf, end, num, size); } static noinline_for_stack char *date_str(char *buf, char *end, const struct rtc_time *tm, bool r) { int year = tm->tm_year + (r ? 0 : 1900); int mon = tm->tm_mon + (r ? 0 : 1); buf = number(buf, end, year, default_dec04_spec); if (buf < end) *buf = '-'; buf++; buf = number(buf, end, mon, default_dec02_spec); if (buf < end) *buf = '-'; buf++; return number(buf, end, tm->tm_mday, default_dec02_spec); } static noinline_for_stack char *time_str(char *buf, char *end, const struct rtc_time *tm, bool r) { buf = number(buf, end, tm->tm_hour, default_dec02_spec); if (buf < end) *buf = ':'; buf++; buf = number(buf, end, tm->tm_min, default_dec02_spec); if (buf < end) *buf = ':'; buf++; return number(buf, end, tm->tm_sec, default_dec02_spec); } static noinline_for_stack char *rtc_str(char *buf, char *end, const struct rtc_time *tm, struct printf_spec spec, const char *fmt) { bool have_t = true, have_d = true; bool raw = false; int count = 2; if (check_pointer(&buf, end, tm, spec)) return buf; switch (fmt[count]) { case 'd': have_t = false; count++; break; case 't': have_d = false; count++; break; } raw = fmt[count] == 'r'; if (have_d) buf = date_str(buf, end, tm, raw); if (have_d && have_t) { /* Respect ISO 8601 */ if (buf < end) *buf = 'T'; buf++; } if (have_t) buf = time_str(buf, end, tm, raw); return buf; } static noinline_for_stack char *time_and_date(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'R': return rtc_str(buf, end, (const struct rtc_time *)ptr, spec, fmt); default: return error_string(buf, end, "(%ptR?)", spec); } } static noinline_for_stack char *clock(char *buf, char *end, struct clk *clk, struct printf_spec spec, const char *fmt) { if (!IS_ENABLED(CONFIG_HAVE_CLK)) return error_string(buf, end, "(%pC?)", spec); if (check_pointer(&buf, end, clk, spec)) return buf; switch (fmt[1]) { case 'n': default: #ifdef CONFIG_COMMON_CLK return string(buf, end, __clk_get_name(clk), spec); #else return ptr_to_id(buf, end, clk, spec); #endif } } static char *format_flags(char *buf, char *end, unsigned long flags, const struct trace_print_flags *names) { unsigned long mask; for ( ; flags && names->name; names++) { mask = names->mask; if ((flags & mask) != mask) continue; buf = string(buf, end, names->name, default_str_spec); flags &= ~mask; if (flags) { if (buf < end) *buf = '|'; buf++; } } if (flags) buf = number(buf, end, flags, default_flag_spec); return buf; } static noinline_for_stack char *flags_string(char *buf, char *end, void *flags_ptr, struct printf_spec spec, const char *fmt) { unsigned long flags; const struct trace_print_flags *names; if (check_pointer(&buf, end, flags_ptr, spec)) return buf; switch (fmt[1]) { case 'p': flags = *(unsigned long *)flags_ptr; /* Remove zone id */ flags &= (1UL << NR_PAGEFLAGS) - 1; names = pageflag_names; break; case 'v': flags = *(unsigned long *)flags_ptr; names = vmaflag_names; break; case 'g': flags = *(gfp_t *)flags_ptr; names = gfpflag_names; break; default: return error_string(buf, end, "(%pG?)", spec); } return format_flags(buf, end, flags, names); } static const char *device_node_name_for_depth(const struct device_node *np, int depth) { for ( ; np && depth; depth--) np = np->parent; return kbasename(np->full_name); } static noinline_for_stack char *device_node_gen_full_name(const struct device_node *np, char *buf, char *end) { int depth; const struct device_node *parent = np->parent; /* special case for root node */ if (!parent) return string_nocheck(buf, end, "/", default_str_spec); for (depth = 0; parent->parent; depth++) parent = parent->parent; for ( ; depth >= 0; depth--) { buf = string_nocheck(buf, end, "/", default_str_spec); buf = string(buf, end, device_node_name_for_depth(np, depth), default_str_spec); } return buf; } static noinline_for_stack char *device_node_string(char *buf, char *end, struct device_node *dn, struct printf_spec spec, const char *fmt) { char tbuf[sizeof("xxxx") + 1]; const char *p; int ret; char *buf_start = buf; struct property *prop; bool has_mult, pass; static const struct printf_spec num_spec = { .flags = SMALL, .field_width = -1, .precision = -1, .base = 10, }; struct printf_spec str_spec = spec; str_spec.field_width = -1; if (!IS_ENABLED(CONFIG_OF)) return error_string(buf, end, "(%pOF?)", spec); if (check_pointer(&buf, end, dn, spec)) return buf; /* simple case without anything any more format specifiers */ fmt++; if (fmt[0] == '\0' || strcspn(fmt,"fnpPFcC") > 0) fmt = "f"; for (pass = false; strspn(fmt,"fnpPFcC"); fmt++, pass = true) { int precision; if (pass) { if (buf < end) *buf = ':'; buf++; } switch (*fmt) { case 'f': /* full_name */ buf = device_node_gen_full_name(dn, buf, end); break; case 'n': /* name */ p = kbasename(of_node_full_name(dn)); precision = str_spec.precision; str_spec.precision = strchrnul(p, '@') - p; buf = string(buf, end, p, str_spec); str_spec.precision = precision; break; case 'p': /* phandle */ buf = number(buf, end, (unsigned int)dn->phandle, num_spec); break; case 'P': /* path-spec */ p = kbasename(of_node_full_name(dn)); if (!p[1]) p = "/"; buf = string(buf, end, p, str_spec); break; case 'F': /* flags */ tbuf[0] = of_node_check_flag(dn, OF_DYNAMIC) ? 'D' : '-'; tbuf[1] = of_node_check_flag(dn, OF_DETACHED) ? 'd' : '-'; tbuf[2] = of_node_check_flag(dn, OF_POPULATED) ? 'P' : '-'; tbuf[3] = of_node_check_flag(dn, OF_POPULATED_BUS) ? 'B' : '-'; tbuf[4] = 0; buf = string_nocheck(buf, end, tbuf, str_spec); break; case 'c': /* major compatible string */ ret = of_property_read_string(dn, "compatible", &p); if (!ret) buf = string(buf, end, p, str_spec); break; case 'C': /* full compatible string */ has_mult = false; of_property_for_each_string(dn, "compatible", prop, p) { if (has_mult) buf = string_nocheck(buf, end, ",", str_spec); buf = string_nocheck(buf, end, "\"", str_spec); buf = string(buf, end, p, str_spec); buf = string_nocheck(buf, end, "\"", str_spec); has_mult = true; } break; default: break; } } return widen_string(buf, buf - buf_start, end, spec); } static char *kobject_string(char *buf, char *end, void *ptr, struct printf_spec spec, const char *fmt) { switch (fmt[1]) { case 'F': return device_node_string(buf, end, ptr, spec, fmt + 1); } return error_string(buf, end, "(%pO?)", spec); } static int __init no_hash_pointers_enable(char *str) { no_hash_pointers = true; pr_warn("**********************************************************\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("** **\n"); pr_warn("** This system shows unhashed kernel memory addresses **\n"); pr_warn("** via the console, logs, and other interfaces. This **\n"); pr_warn("** might reduce the security of your system. **\n"); pr_warn("** **\n"); pr_warn("** If you see this message and you are not debugging **\n"); pr_warn("** the kernel, report this immediately to your system **\n"); pr_warn("** administrator! **\n"); pr_warn("** **\n"); pr_warn("** NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE **\n"); pr_warn("**********************************************************\n"); return 0; } early_param("no_hash_pointers", no_hash_pointers_enable); /* * Show a '%p' thing. A kernel extension is that the '%p' is followed * by an extra set of alphanumeric characters that are extended format * specifiers. * * Please update scripts/checkpatch.pl when adding/removing conversion * characters. (Search for "check for vsprintf extension"). * * Right now we handle: * * - 'S' For symbolic direct pointers (or function descriptors) with offset * - 's' For symbolic direct pointers (or function descriptors) without offset * - 'F' Same as 'S' * - 'f' Same as 's' * - '[FfSs]R' as above with __builtin_extract_return_addr() translation * - 'B' For backtraced symbolic direct pointers with offset * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref] * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201] * - 'b[l]' For a bitmap, the number of bits is determined by the field * width which must be explicitly specified either as part of the * format string '%32b[l]' or through '%*b[l]', [l] selects * range-list format instead of hex format * - 'M' For a 6-byte MAC address, it prints the address in the * usual colon-separated hex notation * - 'm' For a 6-byte MAC address, it prints the hex address without colons * - 'MF' For a 6-byte MAC FDDI address, it prints the address * with a dash-separated hex notation * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth) * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way * IPv4 uses dot-separated decimal without leading 0's (1.2.3.4) * IPv6 uses colon separated network-order 16 bit hex with leading 0's * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - 'i' [46] for 'raw' IPv4/IPv6 addresses * IPv6 omits the colons (01020304...0f) * IPv4 uses dot-separated decimal with leading 0's (010.123.045.006) * [S][pfs] * Generic IPv4/IPv6 address (struct sockaddr *) that falls back to * [4] or [6] and is able to print port [p], flowinfo [f], scope [s] * - '[Ii][4S][hnbl]' IPv4 addresses in host, network, big or little endian order * - 'I[6S]c' for IPv6 addresses printed as specified by * http://tools.ietf.org/html/rfc5952 * - 'E[achnops]' For an escaped buffer, where rules are defined by combination * of the following flags (see string_escape_mem() for the * details): * a - ESCAPE_ANY * c - ESCAPE_SPECIAL * h - ESCAPE_HEX * n - ESCAPE_NULL * o - ESCAPE_OCTAL * p - ESCAPE_NP * s - ESCAPE_SPACE * By default ESCAPE_ANY_NP is used. * - 'U' For a 16 byte UUID/GUID, it prints the UUID/GUID in the form * "xxxxxxxx-xxxx-xxxx-xxxx-xxxxxxxxxxxx" * Options for %pU are: * b big endian lower case hex (default) * B big endian UPPER case hex * l little endian lower case hex * L little endian UPPER case hex * big endian output byte order is: * [0][1][2][3]-[4][5]-[6][7]-[8][9]-[10][11][12][13][14][15] * little endian output byte order is: * [3][2][1][0]-[5][4]-[7][6]-[8][9]-[10][11][12][13][14][15] * - 'V' For a struct va_format which contains a format string * and va_list *, * call vsnprintf(->format, *->va_list). * Implements a "recursive vsnprintf". * Do not use this feature without some mechanism to verify the * correctness of the format string and va_list arguments. * - 'K' For a kernel pointer that should be hidden from unprivileged users * - 'NF' For a netdev_features_t * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with * a certain separator (' ' by default): * C colon * D dash * N no separator * The maximum supported length is 64 bytes of the input. Consider * to use print_hex_dump() for the larger input. * - 'a[pd]' For address types [p] phys_addr_t, [d] dma_addr_t and derivatives * (default assumed to be phys_addr_t, passed by reference) * - 'd[234]' For a dentry name (optionally 2-4 last components) * - 'D[234]' Same as 'd' but for a struct file * - 'g' For block_device name (gendisk + partition number) * - 't[R][dt][r]' For time and date as represented: * R struct rtc_time * - 'C' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'Cn' For a clock, it prints the name (Common Clock Framework) or address * (legacy clock framework) of the clock * - 'G' For flags to be printed as a collection of symbolic strings that would * construct the specific value. Supported flags given by option: * p page flags (see struct page) given as pointer to unsigned long * g gfp flags (GFP_* and __GFP_*) given as pointer to gfp_t * v vma flags (VM_*) given as pointer to unsigned long * - 'OF[fnpPcCF]' For a device tree object * Without any optional arguments prints the full_name * f device node full_name * n device node name * p device node phandle * P device node path spec (name + @unit) * F device node flags * c major compatible string * C full compatible string * - 'x' For printing the address. Equivalent to "%lx". * * ** When making changes please also update: * Documentation/core-api/printk-formats.rst * * Note: The default behaviour (unadorned %p) is to hash the address, * rendering it useful as a unique identifier. */ static noinline_for_stack char *pointer(const char *fmt, char *buf, char *end, void *ptr, struct printf_spec spec) { switch (*fmt) { case 'F': case 'f': case 'S': case 's': ptr = dereference_symbol_descriptor(ptr); /* Fallthrough */ case 'B': return symbol_string(buf, end, ptr, spec, fmt); case 'R': case 'r': return resource_string(buf, end, ptr, spec, fmt); case 'h': return hex_string(buf, end, ptr, spec, fmt); case 'b': switch (fmt[1]) { case 'l': return bitmap_list_string(buf, end, ptr, spec, fmt); default: return bitmap_string(buf, end, ptr, spec, fmt); } case 'M': /* Colon separated: 00:01:02:03:04:05 */ case 'm': /* Contiguous: 000102030405 */ /* [mM]F (FDDI) */ /* [mM]R (Reverse order; Bluetooth) */ return mac_address_string(buf, end, ptr, spec, fmt); case 'I': /* Formatted IP supported * 4: 1.2.3.4 * 6: 0001:0203:...:0708 * 6c: 1::708 or 1::1.2.3.4 */ case 'i': /* Contiguous: * 4: 001.002.003.004 * 6: 000102...0f */ return ip_addr_string(buf, end, ptr, spec, fmt); case 'E': return escaped_string(buf, end, ptr, spec, fmt); case 'U': return uuid_string(buf, end, ptr, spec, fmt); case 'V': return va_format(buf, end, ptr, spec, fmt); case 'K': return restricted_pointer(buf, end, ptr, spec); case 'N': return netdev_bits(buf, end, ptr, spec, fmt); case 'a': return address_val(buf, end, ptr, spec, fmt); case 'd': return dentry_name(buf, end, ptr, spec, fmt); case 't': return time_and_date(buf, end, ptr, spec, fmt); case 'C': return clock(buf, end, ptr, spec, fmt); case 'D': return file_dentry_name(buf, end, ptr, spec, fmt); #ifdef CONFIG_BLOCK case 'g': return bdev_name(buf, end, ptr, spec, fmt); #endif case 'G': return flags_string(buf, end, ptr, spec, fmt); case 'O': return kobject_string(buf, end, ptr, spec, fmt); case 'x': return pointer_string(buf, end, ptr, spec); default: return default_pointer(buf, end, ptr, spec); } } /* * Helper function to decode printf style format. * Each call decode a token from the format and return the * number of characters read (or likely the delta where it wants * to go on the next call). * The decoded token is returned through the parameters * * 'h', 'l', or 'L' for integer fields * 'z' support added 23/7/1999 S.H. * 'z' changed to 'Z' --davidm 1/25/99 * 'Z' changed to 'z' --adobriyan 2017-01-25 * 't' added for ptrdiff_t * * @fmt: the format string * @type of the token returned * @flags: various flags such as +, -, # tokens.. * @field_width: overwritten width * @base: base of the number (octal, hex, ...) * @precision: precision of a number * @qualifier: qualifier of a number (long, size_t, ...) */ static noinline_for_stack int format_decode(const char *fmt, struct printf_spec *spec) { const char *start = fmt; char qualifier; /* we finished early by reading the field width */ if (spec->type == FORMAT_TYPE_WIDTH) { if (spec->field_width < 0) { spec->field_width = -spec->field_width; spec->flags |= LEFT; } spec->type = FORMAT_TYPE_NONE; goto precision; } /* we finished early by reading the precision */ if (spec->type == FORMAT_TYPE_PRECISION) { if (spec->precision < 0) spec->precision = 0; spec->type = FORMAT_TYPE_NONE; goto qualifier; } /* By default */ spec->type = FORMAT_TYPE_NONE; for (; *fmt ; ++fmt) { if (*fmt == '%') break; } /* Return the current non-format string */ if (fmt != start || !*fmt) return fmt - start; /* Process flags */ spec->flags = 0; while (1) { /* this also skips first '%' */ bool found = true; ++fmt; switch (*fmt) { case '-': spec->flags |= LEFT; break; case '+': spec->flags |= PLUS; break; case ' ': spec->flags |= SPACE; break; case '#': spec->flags |= SPECIAL; break; case '0': spec->flags |= ZEROPAD; break; default: found = false; } if (!found) break; } /* get field width */ spec->field_width = -1; if (isdigit(*fmt)) spec->field_width = skip_atoi(&fmt); else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_WIDTH; return ++fmt - start; } precision: /* get the precision */ spec->precision = -1; if (*fmt == '.') { ++fmt; if (isdigit(*fmt)) { spec->precision = skip_atoi(&fmt); if (spec->precision < 0) spec->precision = 0; } else if (*fmt == '*') { /* it's the next argument */ spec->type = FORMAT_TYPE_PRECISION; return ++fmt - start; } } qualifier: /* get the conversion qualifier */ qualifier = 0; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z' || *fmt == 't') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'l') { qualifier = 'L'; ++fmt; } else if (qualifier == 'h') { qualifier = 'H'; ++fmt; } } } /* default base */ spec->base = 10; switch (*fmt) { case 'c': spec->type = FORMAT_TYPE_CHAR; return ++fmt - start; case 's': spec->type = FORMAT_TYPE_STR; return ++fmt - start; case 'p': spec->type = FORMAT_TYPE_PTR; return ++fmt - start; case '%': spec->type = FORMAT_TYPE_PERCENT_CHAR; return ++fmt - start; /* integer number formats - set up the flags and "break" */ case 'o': spec->base = 8; break; case 'x': spec->flags |= SMALL; /* fall through */ case 'X': spec->base = 16; break; case 'd': case 'i': spec->flags |= SIGN; case 'u': break; case 'n': /* * Since %n poses a greater security risk than * utility, treat it as any other invalid or * unsupported format specifier. */ /* Fall-through */ default: WARN_ONCE(1, "Please remove unsupported %%%c in format string\n", *fmt); spec->type = FORMAT_TYPE_INVALID; return fmt - start; } if (qualifier == 'L') spec->type = FORMAT_TYPE_LONG_LONG; else if (qualifier == 'l') { BUILD_BUG_ON(FORMAT_TYPE_ULONG + SIGN != FORMAT_TYPE_LONG); spec->type = FORMAT_TYPE_ULONG + (spec->flags & SIGN); } else if (qualifier == 'z') { spec->type = FORMAT_TYPE_SIZE_T; } else if (qualifier == 't') { spec->type = FORMAT_TYPE_PTRDIFF; } else if (qualifier == 'H') { BUILD_BUG_ON(FORMAT_TYPE_UBYTE + SIGN != FORMAT_TYPE_BYTE); spec->type = FORMAT_TYPE_UBYTE + (spec->flags & SIGN); } else if (qualifier == 'h') { BUILD_BUG_ON(FORMAT_TYPE_USHORT + SIGN != FORMAT_TYPE_SHORT); spec->type = FORMAT_TYPE_USHORT + (spec->flags & SIGN); } else { BUILD_BUG_ON(FORMAT_TYPE_UINT + SIGN != FORMAT_TYPE_INT); spec->type = FORMAT_TYPE_UINT + (spec->flags & SIGN); } return ++fmt - start; } static void set_field_width(struct printf_spec *spec, int width) { spec->field_width = width; if (WARN_ONCE(spec->field_width != width, "field width %d too large", width)) { spec->field_width = clamp(width, -FIELD_WIDTH_MAX, FIELD_WIDTH_MAX); } } static void set_precision(struct printf_spec *spec, int prec) { spec->precision = prec; if (WARN_ONCE(spec->precision != prec, "precision %d too large", prec)) { spec->precision = clamp(prec, 0, PRECISION_MAX); } } /** * vsnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * This function generally follows C99 vsnprintf, but has some * extensions and a few limitations: * * - ``%n`` is unsupported * - ``%p*`` is handled by pointer() * * See pointer() or Documentation/core-api/printk-formats.rst for more * extensive description. * * **Please update the documentation in both places when making changes** * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. * * If you're not already dealing with a va_list consider using snprintf(). */ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args) { unsigned long long num; char *str, *end; struct printf_spec spec = {0}; /* Reject out-of-range values early. Large positive sizes are used for unknown buffer sizes. */ if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, va_arg(args, int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, va_arg(args, int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) va_arg(args, int); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: str = string(str, end, va_arg(args, char *), spec); break; case FORMAT_TYPE_PTR: str = pointer(fmt, str, end, va_arg(args, void *), spec); while (isalnum(*fmt)) fmt++; break; case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: /* * Presumably the arguments passed gcc's type * checking, but there is no safe or sane way * for us to continue parsing the format and * fetching from the va_list; the remaining * specifiers and arguments would be out of * sync. */ goto out; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = va_arg(args, long long); break; case FORMAT_TYPE_ULONG: num = va_arg(args, unsigned long); break; case FORMAT_TYPE_LONG: num = va_arg(args, long); break; case FORMAT_TYPE_SIZE_T: if (spec.flags & SIGN) num = va_arg(args, ssize_t); else num = va_arg(args, size_t); break; case FORMAT_TYPE_PTRDIFF: num = va_arg(args, ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = (unsigned char) va_arg(args, int); break; case FORMAT_TYPE_BYTE: num = (signed char) va_arg(args, int); break; case FORMAT_TYPE_USHORT: num = (unsigned short) va_arg(args, int); break; case FORMAT_TYPE_SHORT: num = (short) va_arg(args, int); break; case FORMAT_TYPE_INT: num = (int) va_arg(args, int); break; default: num = va_arg(args, unsigned int); } str = number(str, end, num, spec); } } out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } /* the trailing null byte doesn't count towards the total */ return str-buf; } EXPORT_SYMBOL(vsnprintf); /** * vscnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @args: Arguments for the format string * * The return value is the number of characters which have been written into * the @buf not including the trailing '\0'. If @size is == 0 the function * returns 0. * * If you're not already dealing with a va_list consider using scnprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vscnprintf(char *buf, size_t size, const char *fmt, va_list args) { int i; i = vsnprintf(buf, size, fmt, args); if (likely(i < size)) return i; if (size != 0) return size - 1; return 0; } EXPORT_SYMBOL(vscnprintf); /** * snprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters which would be * generated for the given input, excluding the trailing null, * as per ISO C99. If the return is greater than or equal to * @size, the resulting string is truncated. * * See the vsnprintf() documentation for format string extensions over C99. */ int snprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(snprintf); /** * scnprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @...: Arguments for the format string * * The return value is the number of characters written into @buf not including * the trailing '\0'. If @size is == 0 the function returns 0. */ int scnprintf(char *buf, size_t size, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vscnprintf(buf, size, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(scnprintf); /** * vsprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @args: Arguments for the format string * * The function returns the number of characters written * into @buf. Use vsnprintf() or vscnprintf() in order to avoid * buffer overflows. * * If you're not already dealing with a va_list consider using sprintf(). * * See the vsnprintf() documentation for format string extensions over C99. */ int vsprintf(char *buf, const char *fmt, va_list args) { return vsnprintf(buf, INT_MAX, fmt, args); } EXPORT_SYMBOL(vsprintf); /** * sprintf - Format a string and place it in a buffer * @buf: The buffer to place the result into * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of characters written * into @buf. Use snprintf() or scnprintf() in order to avoid * buffer overflows. * * See the vsnprintf() documentation for format string extensions over C99. */ int sprintf(char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsnprintf(buf, INT_MAX, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sprintf); #ifdef CONFIG_BINARY_PRINTF /* * bprintf service: * vbin_printf() - VA arguments to binary data * bstr_printf() - Binary data to text string */ /** * vbin_printf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @args: Arguments for the format string * * The format follows C99 vsnprintf, except %n is ignored, and its argument * is skipped. * * The return value is the number of words(32bits) which would be generated for * the given input. * * NOTE: * If the return value is greater than @size, the resulting bin_buf is NOT * valid for bstr_printf(). */ int vbin_printf(u32 *bin_buf, size_t size, const char *fmt, va_list args) { struct printf_spec spec = {0}; char *str, *end; int width; str = (char *)bin_buf; end = (char *)(bin_buf + size); #define save_arg(type) \ ({ \ unsigned long long value; \ if (sizeof(type) == 8) { \ unsigned long long val8; \ str = PTR_ALIGN(str, sizeof(u32)); \ val8 = va_arg(args, unsigned long long); \ if (str + sizeof(type) <= end) { \ *(u32 *)str = *(u32 *)&val8; \ *(u32 *)(str + 4) = *((u32 *)&val8 + 1); \ } \ value = val8; \ } else { \ unsigned int val4; \ str = PTR_ALIGN(str, sizeof(type)); \ val4 = va_arg(args, int); \ if (str + sizeof(type) <= end) \ *(typeof(type) *)str = (type)(long)val4; \ value = (unsigned long long)val4; \ } \ str += sizeof(type); \ value; \ }) while (*fmt) { int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: case FORMAT_TYPE_PERCENT_CHAR: break; case FORMAT_TYPE_INVALID: goto out; case FORMAT_TYPE_WIDTH: case FORMAT_TYPE_PRECISION: width = (int)save_arg(int); /* Pointers may require the width */ if (*fmt == 'p') set_field_width(&spec, width); break; case FORMAT_TYPE_CHAR: save_arg(char); break; case FORMAT_TYPE_STR: { const char *save_str = va_arg(args, char *); const char *err_msg; size_t len; err_msg = check_pointer_msg(save_str); if (err_msg) save_str = err_msg; len = strlen(save_str) + 1; if (str + len < end) memcpy(str, save_str, len); str += len; break; } case FORMAT_TYPE_PTR: /* Dereferenced pointers must be done now */ switch (*fmt) { /* Dereference of functions is still OK */ case 'S': case 's': case 'F': case 'f': case 'x': case 'K': save_arg(void *); break; default: if (!isalnum(*fmt)) { save_arg(void *); break; } str = pointer(fmt, str, end, va_arg(args, void *), spec); if (str + 1 < end) *str++ = '\0'; else end[-1] = '\0'; /* Must be nul terminated */ } /* skip all alphanumeric pointer suffixes */ while (isalnum(*fmt)) fmt++; break; default: switch (spec.type) { case FORMAT_TYPE_LONG_LONG: save_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: save_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: save_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: save_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: case FORMAT_TYPE_BYTE: save_arg(char); break; case FORMAT_TYPE_USHORT: case FORMAT_TYPE_SHORT: save_arg(short); break; default: save_arg(int); } } } out: return (u32 *)(PTR_ALIGN(str, sizeof(u32))) - bin_buf; #undef save_arg } EXPORT_SYMBOL_GPL(vbin_printf); /** * bstr_printf - Format a string from binary arguments and place it in a buffer * @buf: The buffer to place the result into * @size: The size of the buffer, including the trailing null space * @fmt: The format string to use * @bin_buf: Binary arguments for the format string * * This function like C99 vsnprintf, but the difference is that vsnprintf gets * arguments from stack, and bstr_printf gets arguments from @bin_buf which is * a binary buffer that generated by vbin_printf. * * The format follows C99 vsnprintf, but has some extensions: * see vsnprintf comment for details. * * The return value is the number of characters which would * be generated for the given input, excluding the trailing * '\0', as per ISO C99. If you want to have the exact * number of characters written into @buf as return value * (not including the trailing '\0'), use vscnprintf(). If the * return is greater than or equal to @size, the resulting * string is truncated. */ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf) { struct printf_spec spec = {0}; char *str, *end; const char *args = (const char *)bin_buf; if (WARN_ON_ONCE(size > INT_MAX)) return 0; str = buf; end = buf + size; #define get_arg(type) \ ({ \ typeof(type) value; \ if (sizeof(type) == 8) { \ args = PTR_ALIGN(args, sizeof(u32)); \ *(u32 *)&value = *(u32 *)args; \ *((u32 *)&value + 1) = *(u32 *)(args + 4); \ } else { \ args = PTR_ALIGN(args, sizeof(type)); \ value = *(typeof(type) *)args; \ } \ args += sizeof(type); \ value; \ }) /* Make sure end is always >= buf */ if (end < buf) { end = ((void *)-1); size = end - buf; } while (*fmt) { const char *old_fmt = fmt; int read = format_decode(fmt, &spec); fmt += read; switch (spec.type) { case FORMAT_TYPE_NONE: { int copy = read; if (str < end) { if (copy > end - str) copy = end - str; memcpy(str, old_fmt, copy); } str += read; break; } case FORMAT_TYPE_WIDTH: set_field_width(&spec, get_arg(int)); break; case FORMAT_TYPE_PRECISION: set_precision(&spec, get_arg(int)); break; case FORMAT_TYPE_CHAR: { char c; if (!(spec.flags & LEFT)) { while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } } c = (unsigned char) get_arg(char); if (str < end) *str = c; ++str; while (--spec.field_width > 0) { if (str < end) *str = ' '; ++str; } break; } case FORMAT_TYPE_STR: { const char *str_arg = args; args += strlen(str_arg) + 1; str = string(str, end, (char *)str_arg, spec); break; } case FORMAT_TYPE_PTR: { bool process = false; int copy, len; /* Non function dereferences were already done */ switch (*fmt) { case 'S': case 's': case 'F': case 'f': case 'x': case 'K': process = true; break; default: if (!isalnum(*fmt)) { process = true; break; } /* Pointer dereference was already processed */ if (str < end) { len = copy = strlen(args); if (copy > end - str) copy = end - str; memcpy(str, args, copy); str += len; args += len + 1; } } if (process) str = pointer(fmt, str, end, get_arg(void *), spec); while (isalnum(*fmt)) fmt++; break; } case FORMAT_TYPE_PERCENT_CHAR: if (str < end) *str = '%'; ++str; break; case FORMAT_TYPE_INVALID: goto out; default: { unsigned long long num; switch (spec.type) { case FORMAT_TYPE_LONG_LONG: num = get_arg(long long); break; case FORMAT_TYPE_ULONG: case FORMAT_TYPE_LONG: num = get_arg(unsigned long); break; case FORMAT_TYPE_SIZE_T: num = get_arg(size_t); break; case FORMAT_TYPE_PTRDIFF: num = get_arg(ptrdiff_t); break; case FORMAT_TYPE_UBYTE: num = get_arg(unsigned char); break; case FORMAT_TYPE_BYTE: num = get_arg(signed char); break; case FORMAT_TYPE_USHORT: num = get_arg(unsigned short); break; case FORMAT_TYPE_SHORT: num = get_arg(short); break; case FORMAT_TYPE_UINT: num = get_arg(unsigned int); break; default: num = get_arg(int); } str = number(str, end, num, spec); } /* default: */ } /* switch(spec.type) */ } /* while(*fmt) */ out: if (size > 0) { if (str < end) *str = '\0'; else end[-1] = '\0'; } #undef get_arg /* the trailing null byte doesn't count towards the total */ return str - buf; } EXPORT_SYMBOL_GPL(bstr_printf); /** * bprintf - Parse a format string and place args' binary value in a buffer * @bin_buf: The buffer to place args' binary value * @size: The size of the buffer(by words(32bits), not characters) * @fmt: The format string to use * @...: Arguments for the format string * * The function returns the number of words(u32) written * into @bin_buf. */ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = vbin_printf(bin_buf, size, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL_GPL(bprintf); #endif /* CONFIG_BINARY_PRINTF */ /** * vsscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: format of buffer * @args: arguments */ int vsscanf(const char *buf, const char *fmt, va_list args) { const char *str = buf; char *next; char digit; int num = 0; u8 qualifier; unsigned int base; union { long long s; unsigned long long u; } val; s16 field_width; bool is_sign; while (*fmt) { /* skip any white space in format */ /* white space in format matchs any amount of * white space, including none, in the input. */ if (isspace(*fmt)) { fmt = skip_spaces(++fmt); str = skip_spaces(str); } /* anything that is not a conversion must match exactly */ if (*fmt != '%' && *fmt) { if (*fmt++ != *str++) break; continue; } if (!*fmt) break; ++fmt; /* skip this conversion. * advance both strings to next white space */ if (*fmt == '*') { if (!*str) break; while (!isspace(*fmt) && *fmt != '%' && *fmt) { /* '%*[' not yet supported, invalid format */ if (*fmt == '[') return num; fmt++; } while (!isspace(*str) && *str) str++; continue; } /* get field width */ field_width = -1; if (isdigit(*fmt)) { field_width = skip_atoi(&fmt); if (field_width <= 0) break; } /* get conversion qualifier */ qualifier = -1; if (*fmt == 'h' || _tolower(*fmt) == 'l' || *fmt == 'z') { qualifier = *fmt++; if (unlikely(qualifier == *fmt)) { if (qualifier == 'h') { qualifier = 'H'; fmt++; } else if (qualifier == 'l') { qualifier = 'L'; fmt++; } } } if (!*fmt) break; if (*fmt == 'n') { /* return number of characters read so far */ *va_arg(args, int *) = str - buf; ++fmt; continue; } if (!*str) break; base = 10; is_sign = false; switch (*fmt++) { case 'c': { char *s = (char *)va_arg(args, char*); if (field_width == -1) field_width = 1; do { *s++ = *str++; } while (--field_width > 0 && *str); num++; } continue; case 's': { char *s = (char *)va_arg(args, char *); if (field_width == -1) field_width = SHRT_MAX; /* first, skip leading white space in buffer */ str = skip_spaces(str); /* now copy until next white space */ while (*str && !isspace(*str) && field_width--) *s++ = *str++; *s = '\0'; num++; } continue; /* * Warning: This implementation of the '[' conversion specifier * deviates from its glibc counterpart in the following ways: * (1) It does NOT support ranges i.e. '-' is NOT a special * character * (2) It cannot match the closing bracket ']' itself * (3) A field width is required * (4) '%*[' (discard matching input) is currently not supported * * Example usage: * ret = sscanf("00:0a:95","%2[^:]:%2[^:]:%2[^:]", * buf1, buf2, buf3); * if (ret < 3) * // etc.. */ case '[': { char *s = (char *)va_arg(args, char *); DECLARE_BITMAP(set, 256) = {0}; unsigned int len = 0; bool negate = (*fmt == '^'); /* field width is required */ if (field_width == -1) return num; if (negate) ++fmt; for ( ; *fmt && *fmt != ']'; ++fmt, ++len) set_bit((u8)*fmt, set); /* no ']' or no character set found */ if (!*fmt || !len) return num; ++fmt; if (negate) { bitmap_complement(set, set, 256); /* exclude null '\0' byte */ clear_bit(0, set); } /* match must be non-empty */ if (!test_bit((u8)*str, set)) return num; while (test_bit((u8)*str, set) && field_width--) *s++ = *str++; *s = '\0'; ++num; } continue; case 'o': base = 8; break; case 'x': case 'X': base = 16; break; case 'i': base = 0; /* fall through */ case 'd': is_sign = true; /* fall through */ case 'u': break; case '%': /* looking for '%' in str */ if (*str++ != '%') return num; continue; default: /* invalid format; stop here */ return num; } /* have some sort of integer conversion. * first, skip white space in buffer. */ str = skip_spaces(str); digit = *str; if (is_sign && digit == '-') digit = *(str + 1); if (!digit || (base == 16 && !isxdigit(digit)) || (base == 10 && !isdigit(digit)) || (base == 8 && (!isdigit(digit) || digit > '7')) || (base == 0 && !isdigit(digit))) break; if (is_sign) val.s = simple_strntoll(str, field_width >= 0 ? field_width : INT_MAX, &next, base); else val.u = simple_strntoull(str, field_width >= 0 ? field_width : INT_MAX, &next, base); switch (qualifier) { case 'H': /* that's 'hh' in format */ if (is_sign) *va_arg(args, signed char *) = val.s; else *va_arg(args, unsigned char *) = val.u; break; case 'h': if (is_sign) *va_arg(args, short *) = val.s; else *va_arg(args, unsigned short *) = val.u; break; case 'l': if (is_sign) *va_arg(args, long *) = val.s; else *va_arg(args, unsigned long *) = val.u; break; case 'L': if (is_sign) *va_arg(args, long long *) = val.s; else *va_arg(args, unsigned long long *) = val.u; break; case 'z': *va_arg(args, size_t *) = val.u; break; default: if (is_sign) *va_arg(args, int *) = val.s; else *va_arg(args, unsigned int *) = val.u; break; } num++; if (!next) break; str = next; } return num; } EXPORT_SYMBOL(vsscanf); /** * sscanf - Unformat a buffer into a list of arguments * @buf: input buffer * @fmt: formatting of buffer * @...: resulting arguments */ int sscanf(const char *buf, const char *fmt, ...) { va_list args; int i; va_start(args, fmt); i = vsscanf(buf, fmt, args); va_end(args); return i; } EXPORT_SYMBOL(sscanf); |
| 27 14 80 82 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Spanning tree protocol; timer-related code * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/kernel.h> #include <linux/times.h> #include "br_private.h" #include "br_private_stp.h" /* called under bridge lock */ static int br_is_designated_for_some_port(const struct net_bridge *br) { struct net_bridge_port *p; list_for_each_entry(p, &br->port_list, list) { if (p->state != BR_STATE_DISABLED && !memcmp(&p->designated_bridge, &br->bridge_id, 8)) return 1; } return 0; } static void br_hello_timer_expired(struct timer_list *t) { struct net_bridge *br = from_timer(br, t, hello_timer); br_debug(br, "hello timer expired\n"); spin_lock(&br->lock); if (br->dev->flags & IFF_UP) { br_config_bpdu_generation(br); if (br->stp_enabled == BR_KERNEL_STP) mod_timer(&br->hello_timer, round_jiffies(jiffies + br->hello_time)); } spin_unlock(&br->lock); } static void br_message_age_timer_expired(struct timer_list *t) { struct net_bridge_port *p = from_timer(p, t, message_age_timer); struct net_bridge *br = p->br; const bridge_id *id = &p->designated_bridge; int was_root; if (p->state == BR_STATE_DISABLED) return; br_info(br, "port %u(%s) neighbor %.2x%.2x.%pM lost\n", (unsigned int) p->port_no, p->dev->name, id->prio[0], id->prio[1], &id->addr); /* * According to the spec, the message age timer cannot be * running when we are the root bridge. So.. this was_root * check is redundant. I'm leaving it in for now, though. */ spin_lock(&br->lock); if (p->state == BR_STATE_DISABLED) goto unlock; was_root = br_is_root_bridge(br); br_become_designated_port(p); br_configuration_update(br); br_port_state_selection(br); if (br_is_root_bridge(br) && !was_root) br_become_root_bridge(br); unlock: spin_unlock(&br->lock); } static void br_forward_delay_timer_expired(struct timer_list *t) { struct net_bridge_port *p = from_timer(p, t, forward_delay_timer); struct net_bridge *br = p->br; br_debug(br, "port %u(%s) forward delay timer\n", (unsigned int) p->port_no, p->dev->name); spin_lock(&br->lock); if (p->state == BR_STATE_LISTENING) { br_set_state(p, BR_STATE_LEARNING); mod_timer(&p->forward_delay_timer, jiffies + br->forward_delay); } else if (p->state == BR_STATE_LEARNING) { br_set_state(p, BR_STATE_FORWARDING); if (br_is_designated_for_some_port(br)) br_topology_change_detection(br); netif_carrier_on(br->dev); } rcu_read_lock(); br_ifinfo_notify(RTM_NEWLINK, NULL, p); rcu_read_unlock(); spin_unlock(&br->lock); } static void br_tcn_timer_expired(struct timer_list *t) { struct net_bridge *br = from_timer(br, t, tcn_timer); br_debug(br, "tcn timer expired\n"); spin_lock(&br->lock); if (!br_is_root_bridge(br) && (br->dev->flags & IFF_UP)) { br_transmit_tcn(br); mod_timer(&br->tcn_timer, jiffies + br->bridge_hello_time); } spin_unlock(&br->lock); } static void br_topology_change_timer_expired(struct timer_list *t) { struct net_bridge *br = from_timer(br, t, topology_change_timer); br_debug(br, "topo change timer expired\n"); spin_lock(&br->lock); br->topology_change_detected = 0; __br_set_topology_change(br, 0); spin_unlock(&br->lock); } static void br_hold_timer_expired(struct timer_list *t) { struct net_bridge_port *p = from_timer(p, t, hold_timer); br_debug(p->br, "port %u(%s) hold timer expired\n", (unsigned int) p->port_no, p->dev->name); spin_lock(&p->br->lock); if (p->config_pending) br_transmit_config(p); spin_unlock(&p->br->lock); } void br_stp_timer_init(struct net_bridge *br) { timer_setup(&br->hello_timer, br_hello_timer_expired, 0); timer_setup(&br->tcn_timer, br_tcn_timer_expired, 0); timer_setup(&br->topology_change_timer, br_topology_change_timer_expired, 0); } void br_stp_port_timer_init(struct net_bridge_port *p) { timer_setup(&p->message_age_timer, br_message_age_timer_expired, 0); timer_setup(&p->forward_delay_timer, br_forward_delay_timer_expired, 0); timer_setup(&p->hold_timer, br_hold_timer_expired, 0); } /* Report ticks left (in USER_HZ) used for API */ unsigned long br_timer_value(const struct timer_list *timer) { return timer_pending(timer) ? jiffies_delta_to_clock_t(timer->expires - jiffies) : 0; } |
| 74 74 74 74 74 74 74 74 74 74 74 74 74 74 74 74 74 74 315 318 317 62 62 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 | /* netfilter.c: look after the filters for various protocols. * Heavily influenced by the old firewall.c by David Bonn and Alan Cox. * * Thanks to Rob `CmdrTaco' Malda for not influencing this code in any * way. * * This code is GPL. */ #include <linux/kernel.h> #include <linux/netfilter.h> #include <net/protocol.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/wait.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/if.h> #include <linux/netdevice.h> #include <linux/netfilter_ipv6.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/mutex.h> #include <linux/mm.h> #include <linux/rcupdate.h> #include <net/net_namespace.h> #include <net/netfilter/nf_queue.h> #include <net/sock.h> #include "nf_internals.h" const struct nf_ipv6_ops __rcu *nf_ipv6_ops __read_mostly; EXPORT_SYMBOL_GPL(nf_ipv6_ops); DEFINE_PER_CPU(bool, nf_skb_duplicated); EXPORT_SYMBOL_GPL(nf_skb_duplicated); #ifdef CONFIG_JUMP_LABEL struct static_key nf_hooks_needed[NFPROTO_NUMPROTO][NF_MAX_HOOKS]; EXPORT_SYMBOL(nf_hooks_needed); #endif static DEFINE_MUTEX(nf_hook_mutex); /* max hooks per family/hooknum */ #define MAX_HOOK_COUNT 1024 #define nf_entry_dereference(e) \ rcu_dereference_protected(e, lockdep_is_held(&nf_hook_mutex)) static struct nf_hook_entries *allocate_hook_entries_size(u16 num) { struct nf_hook_entries *e; size_t alloc = sizeof(*e) + sizeof(struct nf_hook_entry) * num + sizeof(struct nf_hook_ops *) * num + sizeof(struct nf_hook_entries_rcu_head); if (num == 0) return NULL; e = kvzalloc(alloc, GFP_KERNEL); if (e) e->num_hook_entries = num; return e; } static void __nf_hook_entries_free(struct rcu_head *h) { struct nf_hook_entries_rcu_head *head; head = container_of(h, struct nf_hook_entries_rcu_head, head); kvfree(head->allocation); } static void nf_hook_entries_free(struct nf_hook_entries *e) { struct nf_hook_entries_rcu_head *head; struct nf_hook_ops **ops; unsigned int num; if (!e) return; num = e->num_hook_entries; ops = nf_hook_entries_get_hook_ops(e); head = (void *)&ops[num]; head->allocation = e; call_rcu(&head->head, __nf_hook_entries_free); } static unsigned int accept_all(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return NF_ACCEPT; /* ACCEPT makes nf_hook_slow call next hook */ } static const struct nf_hook_ops dummy_ops = { .hook = accept_all, .priority = INT_MIN, }; static struct nf_hook_entries * nf_hook_entries_grow(const struct nf_hook_entries *old, const struct nf_hook_ops *reg) { unsigned int i, alloc_entries, nhooks, old_entries; struct nf_hook_ops **orig_ops = NULL; struct nf_hook_ops **new_ops; struct nf_hook_entries *new; bool inserted = false; alloc_entries = 1; old_entries = old ? old->num_hook_entries : 0; if (old) { orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old_entries; i++) { if (orig_ops[i] != &dummy_ops) alloc_entries++; } } if (alloc_entries > MAX_HOOK_COUNT) return ERR_PTR(-E2BIG); new = allocate_hook_entries_size(alloc_entries); if (!new) return ERR_PTR(-ENOMEM); new_ops = nf_hook_entries_get_hook_ops(new); i = 0; nhooks = 0; while (i < old_entries) { if (orig_ops[i] == &dummy_ops) { ++i; continue; } if (inserted || reg->priority > orig_ops[i]->priority) { new_ops[nhooks] = (void *)orig_ops[i]; new->hooks[nhooks] = old->hooks[i]; i++; } else { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; inserted = true; } nhooks++; } if (!inserted) { new_ops[nhooks] = (void *)reg; new->hooks[nhooks].hook = reg->hook; new->hooks[nhooks].priv = reg->priv; } return new; } static void hooks_validate(const struct nf_hook_entries *hooks) { #ifdef CONFIG_DEBUG_MISC struct nf_hook_ops **orig_ops; int prio = INT_MIN; size_t i = 0; orig_ops = nf_hook_entries_get_hook_ops(hooks); for (i = 0; i < hooks->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; WARN_ON(orig_ops[i]->priority < prio); if (orig_ops[i]->priority > prio) prio = orig_ops[i]->priority; } #endif } int nf_hook_entries_insert_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *new_hooks; struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } EXPORT_SYMBOL_GPL(nf_hook_entries_insert_raw); /* * __nf_hook_entries_try_shrink - try to shrink hook array * * @old -- current hook blob at @pp * @pp -- location of hook blob * * Hook unregistration must always succeed, so to-be-removed hooks * are replaced by a dummy one that will just move to next hook. * * This counts the current dummy hooks, attempts to allocate new blob, * copies the live hooks, then replaces and discards old one. * * return values: * * Returns address to free, or NULL. */ static void *__nf_hook_entries_try_shrink(struct nf_hook_entries *old, struct nf_hook_entries __rcu **pp) { unsigned int i, j, skip = 0, hook_entries; struct nf_hook_entries *new = NULL; struct nf_hook_ops **orig_ops; struct nf_hook_ops **new_ops; if (WARN_ON_ONCE(!old)) return NULL; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) skip++; } /* if skip == hook_entries all hooks have been removed */ hook_entries = old->num_hook_entries; if (skip == hook_entries) goto out_assign; if (skip == 0) return NULL; hook_entries -= skip; new = allocate_hook_entries_size(hook_entries); if (!new) return NULL; new_ops = nf_hook_entries_get_hook_ops(new); for (i = 0, j = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] == &dummy_ops) continue; new->hooks[j] = old->hooks[i]; new_ops[j] = (void *)orig_ops[i]; j++; } hooks_validate(new); out_assign: rcu_assign_pointer(*pp, new); return old; } static struct nf_hook_entries __rcu ** nf_hook_entry_head(struct net *net, int pf, unsigned int hooknum, struct net_device *dev) { switch (pf) { case NFPROTO_NETDEV: break; #ifdef CONFIG_NETFILTER_FAMILY_ARP case NFPROTO_ARP: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_arp) <= hooknum)) return NULL; return net->nf.hooks_arp + hooknum; #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE case NFPROTO_BRIDGE: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_bridge) <= hooknum)) return NULL; return net->nf.hooks_bridge + hooknum; #endif case NFPROTO_IPV4: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv4) <= hooknum)) return NULL; return net->nf.hooks_ipv4 + hooknum; case NFPROTO_IPV6: if (WARN_ON_ONCE(ARRAY_SIZE(net->nf.hooks_ipv6) <= hooknum)) return NULL; return net->nf.hooks_ipv6 + hooknum; default: WARN_ON_ONCE(1); return NULL; } #ifdef CONFIG_NETFILTER_INGRESS if (hooknum == NF_NETDEV_INGRESS) { if (dev && dev_net(dev) == net) return &dev->nf_hooks_ingress; } #endif WARN_ON_ONCE(1); return NULL; } static int __nf_register_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries *p, *new_hooks; struct nf_hook_entries __rcu **pp; if (pf == NFPROTO_NETDEV) { #ifndef CONFIG_NETFILTER_INGRESS if (reg->hooknum == NF_NETDEV_INGRESS) return -EOPNOTSUPP; #endif if (reg->hooknum != NF_NETDEV_INGRESS || !reg->dev || dev_net(reg->dev) != net) return -EINVAL; } pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return -EINVAL; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); new_hooks = nf_hook_entries_grow(p, reg); if (!IS_ERR(new_hooks)) { hooks_validate(new_hooks); rcu_assign_pointer(*pp, new_hooks); } mutex_unlock(&nf_hook_mutex); if (IS_ERR(new_hooks)) return PTR_ERR(new_hooks); #ifdef CONFIG_NETFILTER_INGRESS if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) net_inc_ingress_queue(); #endif #ifdef CONFIG_JUMP_LABEL static_key_slow_inc(&nf_hooks_needed[pf][reg->hooknum]); #endif BUG_ON(p == new_hooks); nf_hook_entries_free(p); return 0; } /* * nf_remove_net_hook - remove a hook from blob * * @oldp: current address of hook blob * @unreg: hook to unregister * * This cannot fail, hook unregistration must always succeed. * Therefore replace the to-be-removed hook with a dummy hook. */ static bool nf_remove_net_hook(struct nf_hook_entries *old, const struct nf_hook_ops *unreg) { struct nf_hook_ops **orig_ops; unsigned int i; orig_ops = nf_hook_entries_get_hook_ops(old); for (i = 0; i < old->num_hook_entries; i++) { if (orig_ops[i] != unreg) continue; WRITE_ONCE(old->hooks[i].hook, accept_all); WRITE_ONCE(orig_ops[i], &dummy_ops); return true; } return false; } static void __nf_unregister_net_hook(struct net *net, int pf, const struct nf_hook_ops *reg) { struct nf_hook_entries __rcu **pp; struct nf_hook_entries *p; pp = nf_hook_entry_head(net, pf, reg->hooknum, reg->dev); if (!pp) return; mutex_lock(&nf_hook_mutex); p = nf_entry_dereference(*pp); if (WARN_ON_ONCE(!p)) { mutex_unlock(&nf_hook_mutex); return; } if (nf_remove_net_hook(p, reg)) { #ifdef CONFIG_NETFILTER_INGRESS if (pf == NFPROTO_NETDEV && reg->hooknum == NF_NETDEV_INGRESS) net_dec_ingress_queue(); #endif #ifdef CONFIG_JUMP_LABEL static_key_slow_dec(&nf_hooks_needed[pf][reg->hooknum]); #endif } else { WARN_ONCE(1, "hook not found, pf %d num %d", pf, reg->hooknum); } p = __nf_hook_entries_try_shrink(p, pp); mutex_unlock(&nf_hook_mutex); if (!p) return; nf_queue_nf_hook_drop(net); nf_hook_entries_free(p); } void nf_unregister_net_hook(struct net *net, const struct nf_hook_ops *reg) { if (reg->pf == NFPROTO_INET) { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); __nf_unregister_net_hook(net, NFPROTO_IPV6, reg); } else { __nf_unregister_net_hook(net, reg->pf, reg); } } EXPORT_SYMBOL(nf_unregister_net_hook); void nf_hook_entries_delete_raw(struct nf_hook_entries __rcu **pp, const struct nf_hook_ops *reg) { struct nf_hook_entries *p; p = rcu_dereference_raw(*pp); if (nf_remove_net_hook(p, reg)) { p = __nf_hook_entries_try_shrink(p, pp); nf_hook_entries_free(p); } } EXPORT_SYMBOL_GPL(nf_hook_entries_delete_raw); int nf_register_net_hook(struct net *net, const struct nf_hook_ops *reg) { int err; if (reg->pf == NFPROTO_INET) { err = __nf_register_net_hook(net, NFPROTO_IPV4, reg); if (err < 0) return err; err = __nf_register_net_hook(net, NFPROTO_IPV6, reg); if (err < 0) { __nf_unregister_net_hook(net, NFPROTO_IPV4, reg); return err; } } else { err = __nf_register_net_hook(net, reg->pf, reg); if (err < 0) return err; } return 0; } EXPORT_SYMBOL(nf_register_net_hook); int nf_register_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int n) { unsigned int i; int err = 0; for (i = 0; i < n; i++) { err = nf_register_net_hook(net, ®[i]); if (err) goto err; } return err; err: if (i > 0) nf_unregister_net_hooks(net, reg, i); return err; } EXPORT_SYMBOL(nf_register_net_hooks); void nf_unregister_net_hooks(struct net *net, const struct nf_hook_ops *reg, unsigned int hookcount) { unsigned int i; for (i = 0; i < hookcount; i++) nf_unregister_net_hook(net, ®[i]); } EXPORT_SYMBOL(nf_unregister_net_hooks); /* Returns 1 if okfn() needs to be executed by the caller, * -EPERM for NF_DROP, 0 otherwise. Caller must hold rcu_read_lock. */ int nf_hook_slow(struct sk_buff *skb, struct nf_hook_state *state, const struct nf_hook_entries *e, unsigned int s) { unsigned int verdict; int ret; for (; s < e->num_hook_entries; s++) { verdict = nf_hook_entry_hookfn(&e->hooks[s], skb, state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: break; case NF_DROP: kfree_skb(skb); ret = NF_DROP_GETERR(verdict); if (ret == 0) ret = -EPERM; return ret; case NF_QUEUE: ret = nf_queue(skb, state, s, verdict); if (ret == 1) continue; return ret; default: /* Implicit handling for NF_STOLEN, as well as any other * non conventional verdicts. */ return 0; } } return 1; } EXPORT_SYMBOL(nf_hook_slow); /* This needs to be compiled in any case to avoid dependencies between the * nfnetlink_queue code and nf_conntrack. */ struct nfnl_ct_hook __rcu *nfnl_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nfnl_ct_hook); struct nf_ct_hook __rcu *nf_ct_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_ct_hook); #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* This does not belong here, but locally generated errors need it if connection tracking in use: without this, connection may not be in hash table, and hence manufactured ICMP or RST packets will not be associated with it. */ void (*ip_ct_attach)(struct sk_buff *, const struct sk_buff *) __rcu __read_mostly; EXPORT_SYMBOL(ip_ct_attach); struct nf_nat_hook __rcu *nf_nat_hook __read_mostly; EXPORT_SYMBOL_GPL(nf_nat_hook); void nf_ct_attach(struct sk_buff *new, const struct sk_buff *skb) { void (*attach)(struct sk_buff *, const struct sk_buff *); if (skb->_nfct) { rcu_read_lock(); attach = rcu_dereference(ip_ct_attach); if (attach) attach(new, skb); rcu_read_unlock(); } } EXPORT_SYMBOL(nf_ct_attach); void nf_conntrack_destroy(struct nf_conntrack *nfct) { struct nf_ct_hook *ct_hook; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ct_hook->destroy(nfct); rcu_read_unlock(); WARN_ON(!ct_hook); } EXPORT_SYMBOL(nf_conntrack_destroy); bool nf_ct_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { struct nf_ct_hook *ct_hook; bool ret = false; rcu_read_lock(); ct_hook = rcu_dereference(nf_ct_hook); if (ct_hook) ret = ct_hook->get_tuple_skb(dst_tuple, skb); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(nf_ct_get_tuple_skb); /* Built-in default zone used e.g. by modules. */ const struct nf_conntrack_zone nf_ct_zone_dflt = { .id = NF_CT_DEFAULT_ZONE_ID, .dir = NF_CT_DEFAULT_ZONE_DIR, }; EXPORT_SYMBOL_GPL(nf_ct_zone_dflt); #endif /* CONFIG_NF_CONNTRACK */ static void __net_init __netfilter_net_init(struct nf_hook_entries __rcu **e, int max) { int h; for (h = 0; h < max; h++) RCU_INIT_POINTER(e[h], NULL); } static int __net_init netfilter_net_init(struct net *net) { __netfilter_net_init(net->nf.hooks_ipv4, ARRAY_SIZE(net->nf.hooks_ipv4)); __netfilter_net_init(net->nf.hooks_ipv6, ARRAY_SIZE(net->nf.hooks_ipv6)); #ifdef CONFIG_NETFILTER_FAMILY_ARP __netfilter_net_init(net->nf.hooks_arp, ARRAY_SIZE(net->nf.hooks_arp)); #endif #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE __netfilter_net_init(net->nf.hooks_bridge, ARRAY_SIZE(net->nf.hooks_bridge)); #endif #ifdef CONFIG_PROC_FS net->nf.proc_netfilter = proc_net_mkdir(net, "netfilter", net->proc_net); if (!net->nf.proc_netfilter) { if (!net_eq(net, &init_net)) pr_err("cannot create netfilter proc entry"); return -ENOMEM; } #endif return 0; } static void __net_exit netfilter_net_exit(struct net *net) { remove_proc_entry("netfilter", net->proc_net); } static struct pernet_operations netfilter_net_ops = { .init = netfilter_net_init, .exit = netfilter_net_exit, }; int __init netfilter_init(void) { int ret; ret = register_pernet_subsys(&netfilter_net_ops); if (ret < 0) goto err; ret = netfilter_log_init(); if (ret < 0) goto err_pernet; return 0; err_pernet: unregister_pernet_subsys(&netfilter_net_ops); err: return ret; } |
| 24 2 1 2 2 2 1 2 2 2 3 3 1 2 2 3 4 2 2 6 4 2 3 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | // SPDX-License-Identifier: GPL-2.0 // bpf-lirc.c - handles bpf // // Copyright (C) 2018 Sean Young <sean@mess.org> #include <linux/bpf.h> #include <linux/filter.h> #include <linux/bpf_lirc.h> #include "rc-core-priv.h" #define lirc_rcu_dereference(p) \ rcu_dereference_protected(p, lockdep_is_held(&ir_raw_handler_lock)) /* * BPF interface for raw IR */ const struct bpf_prog_ops lirc_mode2_prog_ops = { }; BPF_CALL_1(bpf_rc_repeat, u32*, sample) { struct ir_raw_event_ctrl *ctrl; ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample); rc_repeat(ctrl->dev); return 0; } static const struct bpf_func_proto rc_repeat_proto = { .func = bpf_rc_repeat, .gpl_only = true, /* rc_repeat is EXPORT_SYMBOL_GPL */ .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; /* * Currently rc-core does not support 64-bit scancodes, but there are many * known protocols with more than 32 bits. So, define the interface as u64 * as a future-proof. */ BPF_CALL_4(bpf_rc_keydown, u32*, sample, u32, protocol, u64, scancode, u32, toggle) { struct ir_raw_event_ctrl *ctrl; ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample); rc_keydown(ctrl->dev, protocol, scancode, toggle != 0); return 0; } static const struct bpf_func_proto rc_keydown_proto = { .func = bpf_rc_keydown, .gpl_only = true, /* rc_keydown is EXPORT_SYMBOL_GPL */ .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_ANYTHING, }; BPF_CALL_3(bpf_rc_pointer_rel, u32*, sample, s32, rel_x, s32, rel_y) { struct ir_raw_event_ctrl *ctrl; ctrl = container_of(sample, struct ir_raw_event_ctrl, bpf_sample); input_report_rel(ctrl->dev->input_dev, REL_X, rel_x); input_report_rel(ctrl->dev->input_dev, REL_Y, rel_y); input_sync(ctrl->dev->input_dev); return 0; } static const struct bpf_func_proto rc_pointer_rel_proto = { .func = bpf_rc_pointer_rel, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; static const struct bpf_func_proto * lirc_mode2_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { switch (func_id) { case BPF_FUNC_rc_repeat: return &rc_repeat_proto; case BPF_FUNC_rc_keydown: return &rc_keydown_proto; case BPF_FUNC_rc_pointer_rel: return &rc_pointer_rel_proto; case BPF_FUNC_map_lookup_elem: return &bpf_map_lookup_elem_proto; case BPF_FUNC_map_update_elem: return &bpf_map_update_elem_proto; case BPF_FUNC_map_delete_elem: return &bpf_map_delete_elem_proto; case BPF_FUNC_map_push_elem: return &bpf_map_push_elem_proto; case BPF_FUNC_map_pop_elem: return &bpf_map_pop_elem_proto; case BPF_FUNC_map_peek_elem: return &bpf_map_peek_elem_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; case BPF_FUNC_ktime_get_boot_ns: return &bpf_ktime_get_boot_ns_proto; case BPF_FUNC_tail_call: return &bpf_tail_call_proto; case BPF_FUNC_get_prandom_u32: return &bpf_get_prandom_u32_proto; case BPF_FUNC_trace_printk: if (capable(CAP_SYS_ADMIN)) return bpf_get_trace_printk_proto(); /* fall through */ default: return NULL; } } static bool lirc_mode2_is_valid_access(int off, int size, enum bpf_access_type type, const struct bpf_prog *prog, struct bpf_insn_access_aux *info) { /* We have one field of u32 */ return type == BPF_READ && off == 0 && size == sizeof(u32); } const struct bpf_verifier_ops lirc_mode2_verifier_ops = { .get_func_proto = lirc_mode2_func_proto, .is_valid_access = lirc_mode2_is_valid_access }; #define BPF_MAX_PROGS 64 static int lirc_bpf_attach(struct rc_dev *rcdev, struct bpf_prog *prog) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; struct ir_raw_event_ctrl *raw; int ret; if (rcdev->driver_type != RC_DRIVER_IR_RAW) return -EINVAL; ret = mutex_lock_interruptible(&ir_raw_handler_lock); if (ret) return ret; raw = rcdev->raw; if (!raw) { ret = -ENODEV; goto unlock; } old_array = lirc_rcu_dereference(raw->progs); if (old_array && bpf_prog_array_length(old_array) >= BPF_MAX_PROGS) { ret = -E2BIG; goto unlock; } ret = bpf_prog_array_copy(old_array, NULL, prog, &new_array); if (ret < 0) goto unlock; rcu_assign_pointer(raw->progs, new_array); bpf_prog_array_free(old_array); unlock: mutex_unlock(&ir_raw_handler_lock); return ret; } static int lirc_bpf_detach(struct rc_dev *rcdev, struct bpf_prog *prog) { struct bpf_prog_array *old_array; struct bpf_prog_array *new_array; struct ir_raw_event_ctrl *raw; int ret; if (rcdev->driver_type != RC_DRIVER_IR_RAW) return -EINVAL; ret = mutex_lock_interruptible(&ir_raw_handler_lock); if (ret) return ret; raw = rcdev->raw; if (!raw) { ret = -ENODEV; goto unlock; } old_array = lirc_rcu_dereference(raw->progs); ret = bpf_prog_array_copy(old_array, prog, NULL, &new_array); /* * Do not use bpf_prog_array_delete_safe() as we would end up * with a dummy entry in the array, and the we would free the * dummy in lirc_bpf_free() */ if (ret) goto unlock; rcu_assign_pointer(raw->progs, new_array); bpf_prog_array_free(old_array); bpf_prog_put(prog); unlock: mutex_unlock(&ir_raw_handler_lock); return ret; } void lirc_bpf_run(struct rc_dev *rcdev, u32 sample) { struct ir_raw_event_ctrl *raw = rcdev->raw; raw->bpf_sample = sample; if (raw->progs) BPF_PROG_RUN_ARRAY(raw->progs, &raw->bpf_sample, BPF_PROG_RUN); } /* * This should be called once the rc thread has been stopped, so there can be * no concurrent bpf execution. * * Should be called with the ir_raw_handler_lock held. */ void lirc_bpf_free(struct rc_dev *rcdev) { struct bpf_prog_array_item *item; struct bpf_prog_array *array; array = lirc_rcu_dereference(rcdev->raw->progs); if (!array) return; for (item = array->items; item->prog; item++) bpf_prog_put(item->prog); bpf_prog_array_free(array); } int lirc_prog_attach(const union bpf_attr *attr, struct bpf_prog *prog) { struct rc_dev *rcdev; int ret; if (attr->attach_flags) return -EINVAL; rcdev = rc_dev_get_from_fd(attr->target_fd); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); ret = lirc_bpf_attach(rcdev, prog); put_device(&rcdev->dev); return ret; } int lirc_prog_detach(const union bpf_attr *attr) { struct bpf_prog *prog; struct rc_dev *rcdev; int ret; if (attr->attach_flags) return -EINVAL; prog = bpf_prog_get_type(attr->attach_bpf_fd, BPF_PROG_TYPE_LIRC_MODE2); if (IS_ERR(prog)) return PTR_ERR(prog); rcdev = rc_dev_get_from_fd(attr->target_fd); if (IS_ERR(rcdev)) { bpf_prog_put(prog); return PTR_ERR(rcdev); } ret = lirc_bpf_detach(rcdev, prog); bpf_prog_put(prog); put_device(&rcdev->dev); return ret; } int lirc_prog_query(const union bpf_attr *attr, union bpf_attr __user *uattr) { __u32 __user *prog_ids = u64_to_user_ptr(attr->query.prog_ids); struct bpf_prog_array *progs; struct rc_dev *rcdev; u32 cnt, flags = 0; int ret; if (attr->query.query_flags) return -EINVAL; rcdev = rc_dev_get_from_fd(attr->query.target_fd); if (IS_ERR(rcdev)) return PTR_ERR(rcdev); if (rcdev->driver_type != RC_DRIVER_IR_RAW) { ret = -EINVAL; goto put; } ret = mutex_lock_interruptible(&ir_raw_handler_lock); if (ret) goto put; progs = lirc_rcu_dereference(rcdev->raw->progs); cnt = progs ? bpf_prog_array_length(progs) : 0; if (copy_to_user(&uattr->query.prog_cnt, &cnt, sizeof(cnt))) { ret = -EFAULT; goto unlock; } if (copy_to_user(&uattr->query.attach_flags, &flags, sizeof(flags))) { ret = -EFAULT; goto unlock; } if (attr->query.prog_cnt != 0 && prog_ids && cnt) ret = bpf_prog_array_copy_to_user(progs, prog_ids, attr->query.prog_cnt); unlock: mutex_unlock(&ir_raw_handler_lock); put: put_device(&rcdev->dev); return ret; } |
| 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 | // 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. * * Generic INET6 transport hashtables * * Authors: Lotsa people, from code originally in tcp, generalised here * by Arnaldo Carvalho de Melo <acme@mandriva.com> */ #include <linux/module.h> #include <linux/random.h> #include <net/addrconf.h> #include <net/inet_connection_sock.h> #include <net/inet_hashtables.h> #include <net/inet6_hashtables.h> #include <net/secure_seq.h> #include <net/ip.h> #include <net/sock_reuseport.h> u32 inet6_ehashfn(const struct net *net, const struct in6_addr *laddr, const u16 lport, const struct in6_addr *faddr, const __be16 fport) { static u32 inet6_ehash_secret __read_mostly; static u32 ipv6_hash_secret __read_mostly; u32 lhash, fhash; net_get_random_once(&inet6_ehash_secret, sizeof(inet6_ehash_secret)); net_get_random_once(&ipv6_hash_secret, sizeof(ipv6_hash_secret)); lhash = (__force u32)laddr->s6_addr32[3]; fhash = __ipv6_addr_jhash(faddr, ipv6_hash_secret); return __inet6_ehashfn(lhash, lport, fhash, fport, inet6_ehash_secret + net_hash_mix(net)); } /* * Sockets in TCP_CLOSE state are _always_ taken out of the hash, so * we need not check it for TCP lookups anymore, thanks Alexey. -DaveM * * The sockhash lock must be held as a reader here. */ struct sock *__inet6_lookup_established(struct net *net, struct inet_hashinfo *hashinfo, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 hnum, const int dif, const int sdif) { struct sock *sk; const struct hlist_nulls_node *node; const __portpair ports = INET_COMBINED_PORTS(sport, hnum); /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; begin: sk_nulls_for_each_rcu(sk, node, &head->chain) { if (sk->sk_hash != hash) continue; if (!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif)) continue; if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) goto out; if (unlikely(!INET6_MATCH(sk, net, saddr, daddr, ports, dif, sdif))) { sock_gen_put(sk); goto begin; } goto found; } if (get_nulls_value(node) != slot) goto begin; out: sk = NULL; found: return sk; } EXPORT_SYMBOL(__inet6_lookup_established); static inline int compute_score(struct sock *sk, struct net *net, const unsigned short hnum, const struct in6_addr *daddr, const int dif, const int sdif, bool exact_dif) { int score = -1; if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { if (!ipv6_addr_equal(&sk->sk_v6_rcv_saddr, daddr)) return -1; if (!inet_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) return -1; score = sk->sk_bound_dev_if ? 2 : 1; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; } /* called with rcu_read_lock() */ static struct sock *inet6_lhash2_lookup(struct net *net, struct inet_listen_hashbucket *ilb2, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { bool exact_dif = inet6_exact_dif_match(net, skb); struct inet_connection_sock *icsk; struct sock *sk, *result = NULL; int score, hiscore = 0; u32 phash = 0; inet_lhash2_for_each_icsk_rcu(icsk, &ilb2->head) { sk = (struct sock *)icsk; score = compute_score(sk, net, hnum, daddr, dif, sdif, exact_dif); if (score > hiscore) { if (sk->sk_reuseport) { phash = inet6_ehashfn(net, daddr, hnum, saddr, sport); result = reuseport_select_sock(sk, phash, skb, doff); if (result) return result; } result = sk; hiscore = score; } } return result; } struct sock *inet6_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const unsigned short hnum, const int dif, const int sdif) { struct inet_listen_hashbucket *ilb2; struct sock *result = NULL; unsigned int hash2; hash2 = ipv6_portaddr_hash(net, daddr, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, daddr, hnum, dif, sdif); if (result) goto done; /* Lookup lhash2 with in6addr_any */ hash2 = ipv6_portaddr_hash(net, &in6addr_any, hnum); ilb2 = inet_lhash2_bucket(hashinfo, hash2); result = inet6_lhash2_lookup(net, ilb2, skb, doff, saddr, sport, &in6addr_any, hnum, dif, sdif); done: if (IS_ERR(result)) return NULL; return result; } EXPORT_SYMBOL_GPL(inet6_lookup_listener); struct sock *inet6_lookup(struct net *net, struct inet_hashinfo *hashinfo, struct sk_buff *skb, int doff, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const __be16 dport, const int dif) { struct sock *sk; bool refcounted; sk = __inet6_lookup(net, hashinfo, skb, doff, saddr, sport, daddr, ntohs(dport), dif, 0, &refcounted); if (sk && !refcounted && !refcount_inc_not_zero(&sk->sk_refcnt)) sk = NULL; return sk; } EXPORT_SYMBOL_GPL(inet6_lookup); static int __inet6_check_established(struct inet_timewait_death_row *death_row, struct sock *sk, const __u16 lport, struct inet_timewait_sock **twp) { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_sock *inet = inet_sk(sk); const struct in6_addr *daddr = &sk->sk_v6_rcv_saddr; const struct in6_addr *saddr = &sk->sk_v6_daddr; const int dif = sk->sk_bound_dev_if; struct net *net = sock_net(sk); const int sdif = l3mdev_master_ifindex_by_index(net, dif); const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; spin_lock(lock); sk_nulls_for_each(sk2, node, &head->chain) { if (sk2->sk_hash != hash) continue; if (likely(INET6_MATCH(sk2, net, saddr, daddr, ports, dif, sdif))) { if (sk2->sk_state == TCP_TIME_WAIT) { tw = inet_twsk(sk2); if (twsk_unique(sk, sk2, twp)) break; } goto not_unique; } } /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ inet->inet_num = lport; inet->inet_sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { sk_nulls_del_node_init_rcu((struct sock *)tw); __NET_INC_STATS(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule_put(tw); } return 0; not_unique: spin_unlock(lock); return -EADDRNOTAVAIL; } static u64 inet6_sk_port_offset(const struct sock *sk) { const struct inet_sock *inet = inet_sk(sk); return secure_ipv6_port_ephemeral(sk->sk_v6_rcv_saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32, inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk) { u64 port_offset = 0; if (!inet_sk(sk)->inet_num) port_offset = inet6_sk_port_offset(sk); return __inet_hash_connect(death_row, sk, port_offset, __inet6_check_established); } EXPORT_SYMBOL_GPL(inet6_hash_connect); int inet6_hash(struct sock *sk) { int err = 0; if (sk->sk_state != TCP_CLOSE) { local_bh_disable(); err = __inet_hash(sk, NULL); local_bh_enable(); } return err; } EXPORT_SYMBOL_GPL(inet6_hash); |
| 1483 3349 115 2 25 3404 3 3359 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/kasan-checks.h> #include <linux/thread_info.h> #include <linux/uaccess.h> #include <linux/kernel.h> #include <linux/errno.h> #include <linux/mm.h> #include <asm/byteorder.h> #include <asm/word-at-a-time.h> #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS #define IS_UNALIGNED(src, dst) 0 #else #define IS_UNALIGNED(src, dst) \ (((long) dst | (long) src) & (sizeof(long) - 1)) #endif /* * Do a strncpy, return length of string without final '\0'. * 'count' is the user-supplied count (return 'count' if we * hit it), 'max' is the address space maximum (and we return * -EFAULT if we hit it). */ static inline long do_strncpy_from_user(char *dst, const char __user *src, unsigned long count, unsigned long max) { const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS; unsigned long res = 0; if (IS_UNALIGNED(src, dst)) goto byte_at_a_time; while (max >= sizeof(unsigned long)) { unsigned long c, data; /* Fall back to byte-at-a-time if we get a page fault */ unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time); *(unsigned long *)(dst+res) = c; if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); return res + find_zero(data); } res += sizeof(unsigned long); max -= sizeof(unsigned long); } byte_at_a_time: while (max) { char c; unsafe_get_user(c,src+res, efault); dst[res] = c; if (!c) return res; res++; max--; } /* * Uhhuh. We hit 'max'. But was that the user-specified maximum * too? If so, that's ok - we got as much as the user asked for. */ if (res >= count) return res; /* * Nope: we hit the address space limit, and we still had more * characters the caller would have wanted. That's an EFAULT. */ efault: return -EFAULT; } /** * strncpy_from_user: - Copy a NUL terminated string from userspace. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @src: Source address, in user space. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from userspace to kernel space. * * On success, returns the length of the string (not including the trailing * NUL). * * If access to userspace fails, returns -EFAULT (some data may have been * copied). * * If @count is smaller than the length of the string, copies @count bytes * and returns @count. */ long strncpy_from_user(char *dst, const char __user *src, long count) { unsigned long max_addr, src_addr; if (unlikely(count <= 0)) return 0; max_addr = user_addr_max(); src_addr = (unsigned long)untagged_addr(src); if (likely(src_addr < max_addr)) { unsigned long max = max_addr - src_addr; long retval; /* * Truncate 'max' to the user-specified limit, so that * we only have one limit we need to check in the loop */ if (max > count) max = count; kasan_check_write(dst, count); check_object_size(dst, count, false); if (user_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 438 438 439 439 439 439 439 438 73 490 439 73 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | // SPDX-License-Identifier: GPL-2.0-only /* * Link physical devices with ACPI devices support * * Copyright (c) 2005 David Shaohua Li <shaohua.li@intel.com> * Copyright (c) 2005 Intel Corp. */ #include <linux/acpi_iort.h> #include <linux/export.h> #include <linux/init.h> #include <linux/list.h> #include <linux/device.h> #include <linux/slab.h> #include <linux/rwsem.h> #include <linux/acpi.h> #include <linux/dma-mapping.h> #include <linux/platform_device.h> #include "internal.h" #define ACPI_GLUE_DEBUG 0 #if ACPI_GLUE_DEBUG #define DBG(fmt, ...) \ printk(KERN_DEBUG PREFIX fmt, ##__VA_ARGS__) #else #define DBG(fmt, ...) \ do { \ if (0) \ printk(KERN_DEBUG PREFIX fmt, ##__VA_ARGS__); \ } while (0) #endif static LIST_HEAD(bus_type_list); static DECLARE_RWSEM(bus_type_sem); #define PHYSICAL_NODE_STRING "physical_node" #define PHYSICAL_NODE_NAME_SIZE (sizeof(PHYSICAL_NODE_STRING) + 10) int register_acpi_bus_type(struct acpi_bus_type *type) { if (acpi_disabled) return -ENODEV; if (type && type->match && type->find_companion) { down_write(&bus_type_sem); list_add_tail(&type->list, &bus_type_list); up_write(&bus_type_sem); printk(KERN_INFO PREFIX "bus type %s registered\n", type->name); return 0; } return -ENODEV; } EXPORT_SYMBOL_GPL(register_acpi_bus_type); int unregister_acpi_bus_type(struct acpi_bus_type *type) { if (acpi_disabled) return 0; if (type) { down_write(&bus_type_sem); list_del_init(&type->list); up_write(&bus_type_sem); printk(KERN_INFO PREFIX "bus type %s unregistered\n", type->name); return 0; } return -ENODEV; } EXPORT_SYMBOL_GPL(unregister_acpi_bus_type); static struct acpi_bus_type *acpi_get_bus_type(struct device *dev) { struct acpi_bus_type *tmp, *ret = NULL; down_read(&bus_type_sem); list_for_each_entry(tmp, &bus_type_list, list) { if (tmp->match(dev)) { ret = tmp; break; } } up_read(&bus_type_sem); return ret; } #define FIND_CHILD_MIN_SCORE 1 #define FIND_CHILD_MAX_SCORE 2 static int find_child_checks(struct acpi_device *adev, bool check_children) { bool sta_present = true; unsigned long long sta; acpi_status status; status = acpi_evaluate_integer(adev->handle, "_STA", NULL, &sta); if (status == AE_NOT_FOUND) sta_present = false; else if (ACPI_FAILURE(status) || !(sta & ACPI_STA_DEVICE_ENABLED)) return -ENODEV; if (check_children && list_empty(&adev->children)) return -ENODEV; /* * If the device has a _HID returning a valid ACPI/PNP device ID, it is * better to make it look less attractive here, so that the other device * with the same _ADR value (that may not have a valid device ID) can be * matched going forward. [This means a second spec violation in a row, * so whatever we do here is best effort anyway.] */ return sta_present && !adev->pnp.type.platform_id ? FIND_CHILD_MAX_SCORE : FIND_CHILD_MIN_SCORE; } struct acpi_device *acpi_find_child_device(struct acpi_device *parent, u64 address, bool check_children) { struct acpi_device *adev, *ret = NULL; int ret_score = 0; if (!parent) return NULL; list_for_each_entry(adev, &parent->children, node) { unsigned long long addr; acpi_status status; int score; status = acpi_evaluate_integer(adev->handle, METHOD_NAME__ADR, NULL, &addr); if (ACPI_FAILURE(status) || addr != address) continue; if (!ret) { /* This is the first matching object. Save it. */ ret = adev; continue; } /* * There is more than one matching device object with the same * _ADR value. That really is unexpected, so we are kind of * beyond the scope of the spec here. We have to choose which * one to return, though. * * First, check if the previously found object is good enough * and return it if so. Second, do the same for the object that * we've just found. */ if (!ret_score) { ret_score = find_child_checks(ret, check_children); if (ret_score == FIND_CHILD_MAX_SCORE) return ret; } score = find_child_checks(adev, check_children); if (score == FIND_CHILD_MAX_SCORE) { return adev; } else if (score > ret_score) { ret = adev; ret_score = score; } } return ret; } EXPORT_SYMBOL_GPL(acpi_find_child_device); static void acpi_physnode_link_name(char *buf, unsigned int node_id) { if (node_id > 0) snprintf(buf, PHYSICAL_NODE_NAME_SIZE, PHYSICAL_NODE_STRING "%u", node_id); else strcpy(buf, PHYSICAL_NODE_STRING); } int acpi_bind_one(struct device *dev, struct acpi_device *acpi_dev) { struct acpi_device_physical_node *physical_node, *pn; char physical_node_name[PHYSICAL_NODE_NAME_SIZE]; struct list_head *physnode_list; unsigned int node_id; int retval = -EINVAL; if (has_acpi_companion(dev)) { if (acpi_dev) { dev_warn(dev, "ACPI companion already set\n"); return -EINVAL; } else { acpi_dev = ACPI_COMPANION(dev); } } if (!acpi_dev) return -EINVAL; get_device(&acpi_dev->dev); get_device(dev); physical_node = kzalloc(sizeof(*physical_node), GFP_KERNEL); if (!physical_node) { retval = -ENOMEM; goto err; } mutex_lock(&acpi_dev->physical_node_lock); /* * Keep the list sorted by node_id so that the IDs of removed nodes can * be recycled easily. */ physnode_list = &acpi_dev->physical_node_list; node_id = 0; list_for_each_entry(pn, &acpi_dev->physical_node_list, node) { /* Sanity check. */ if (pn->dev == dev) { mutex_unlock(&acpi_dev->physical_node_lock); dev_warn(dev, "Already associated with ACPI node\n"); kfree(physical_node); if (ACPI_COMPANION(dev) != acpi_dev) goto err; put_device(dev); put_device(&acpi_dev->dev); return 0; } if (pn->node_id == node_id) { physnode_list = &pn->node; node_id++; } } physical_node->node_id = node_id; physical_node->dev = dev; list_add(&physical_node->node, physnode_list); acpi_dev->physical_node_count++; if (!has_acpi_companion(dev)) ACPI_COMPANION_SET(dev, acpi_dev); acpi_physnode_link_name(physical_node_name, node_id); retval = sysfs_create_link(&acpi_dev->dev.kobj, &dev->kobj, physical_node_name); if (retval) dev_err(&acpi_dev->dev, "Failed to create link %s (%d)\n", physical_node_name, retval); retval = sysfs_create_link(&dev->kobj, &acpi_dev->dev.kobj, "firmware_node"); if (retval) dev_err(dev, "Failed to create link firmware_node (%d)\n", retval); mutex_unlock(&acpi_dev->physical_node_lock); if (acpi_dev->wakeup.flags.valid) device_set_wakeup_capable(dev, true); return 0; err: ACPI_COMPANION_SET(dev, NULL); put_device(dev); put_device(&acpi_dev->dev); return retval; } EXPORT_SYMBOL_GPL(acpi_bind_one); int acpi_unbind_one(struct device *dev) { struct acpi_device *acpi_dev = ACPI_COMPANION(dev); struct acpi_device_physical_node *entry; if (!acpi_dev) return 0; mutex_lock(&acpi_dev->physical_node_lock); list_for_each_entry(entry, &acpi_dev->physical_node_list, node) if (entry->dev == dev) { char physnode_name[PHYSICAL_NODE_NAME_SIZE]; list_del(&entry->node); acpi_dev->physical_node_count--; acpi_physnode_link_name(physnode_name, entry->node_id); sysfs_remove_link(&acpi_dev->dev.kobj, physnode_name); sysfs_remove_link(&dev->kobj, "firmware_node"); ACPI_COMPANION_SET(dev, NULL); /* Drop references taken by acpi_bind_one(). */ put_device(dev); put_device(&acpi_dev->dev); kfree(entry); break; } mutex_unlock(&acpi_dev->physical_node_lock); return 0; } EXPORT_SYMBOL_GPL(acpi_unbind_one); static int acpi_device_notify(struct device *dev) { struct acpi_bus_type *type = acpi_get_bus_type(dev); struct acpi_device *adev; int ret; ret = acpi_bind_one(dev, NULL); if (ret && type) { struct acpi_device *adev; adev = type->find_companion(dev); if (!adev) { DBG("Unable to get handle for %s\n", dev_name(dev)); ret = -ENODEV; goto out; } ret = acpi_bind_one(dev, adev); if (ret) goto out; } adev = ACPI_COMPANION(dev); if (!adev) goto out; if (dev_is_platform(dev)) acpi_configure_pmsi_domain(dev); if (type && type->setup) type->setup(dev); else if (adev->handler && adev->handler->bind) adev->handler->bind(dev); out: #if ACPI_GLUE_DEBUG if (!ret) { struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; acpi_get_name(ACPI_HANDLE(dev), ACPI_FULL_PATHNAME, &buffer); DBG("Device %s -> %s\n", dev_name(dev), (char *)buffer.pointer); kfree(buffer.pointer); } else DBG("Device %s -> No ACPI support\n", dev_name(dev)); #endif return ret; } static int acpi_device_notify_remove(struct device *dev) { struct acpi_device *adev = ACPI_COMPANION(dev); struct acpi_bus_type *type; if (!adev) return 0; type = acpi_get_bus_type(dev); if (type && type->cleanup) type->cleanup(dev); else if (adev->handler && adev->handler->unbind) adev->handler->unbind(dev); acpi_unbind_one(dev); return 0; } int acpi_platform_notify(struct device *dev, enum kobject_action action) { switch (action) { case KOBJ_ADD: acpi_device_notify(dev); break; case KOBJ_REMOVE: acpi_device_notify_remove(dev); break; default: break; } return 0; } |
| 14 14 14 14 14 20 3 19 3 1 17 11 18 18 17 3 17 16 16 6 8 13 14 12 3 12 5 3 2 2 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 /* * linux/fs/pipe.c * * Copyright (C) 1991, 1992, 1999 Linus Torvalds */ #include <linux/mm.h> #include <linux/file.h> #include <linux/poll.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/init.h> #include <linux/fs.h> #include <linux/log2.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/magic.h> #include <linux/pipe_fs_i.h> #include <linux/uio.h> #include <linux/highmem.h> #include <linux/pagemap.h> #include <linux/audit.h> #include <linux/syscalls.h> #include <linux/fcntl.h> #include <linux/memcontrol.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include "internal.h" /* * New pipe buffers will be restricted to this size while the user is exceeding * their pipe buffer quota. The general pipe use case needs at least two * buffers: one for data yet to be read, and one for new data. If this is less * than two, then a write to a non-empty pipe may block even if the pipe is not * full. This can occur with GNU make jobserver or similar uses of pipes as * semaphores: multiple processes may be waiting to write tokens back to the * pipe before reading tokens: https://lore.kernel.org/lkml/1628086770.5rn8p04n6j.none@localhost/. * * Users can reduce their pipe buffers with F_SETPIPE_SZ below this at their * own risk, namely: pipe writes to non-full pipes may block until the pipe is * emptied. */ #define PIPE_MIN_DEF_BUFFERS 2 /* * The max size that a non-root user is allowed to grow the pipe. Can * be set by root in /proc/sys/fs/pipe-max-size */ unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ unsigned long pipe_user_pages_hard; unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use a start+len construction, which provides full use of the * allocated memory. * -- Florian Coosmann (FGC) * * Reads with count = 0 should always return 0. * -- Julian Bradfield 1999-06-07. * * FIFOs and Pipes now generate SIGIO for both readers and writers. * -- Jeremy Elson <jelson@circlemud.org> 2001-08-16 * * pipe_read & write cleanup * -- Manfred Spraul <manfred@colorfullife.com> 2002-05-09 */ static void pipe_lock_nested(struct pipe_inode_info *pipe, int subclass) { if (pipe->files) mutex_lock_nested(&pipe->mutex, subclass); } void pipe_lock(struct pipe_inode_info *pipe) { /* * pipe_lock() nests non-pipe inode locks (for writing to a file) */ pipe_lock_nested(pipe, I_MUTEX_PARENT); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); static inline void __pipe_lock(struct pipe_inode_info *pipe) { mutex_lock_nested(&pipe->mutex, I_MUTEX_PARENT); } static inline void __pipe_unlock(struct pipe_inode_info *pipe) { mutex_unlock(&pipe->mutex); } void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 < pipe2) { pipe_lock_nested(pipe1, I_MUTEX_PARENT); pipe_lock_nested(pipe2, I_MUTEX_CHILD); } else { pipe_lock_nested(pipe2, I_MUTEX_PARENT); pipe_lock_nested(pipe1, I_MUTEX_CHILD); } } /* Drop the inode semaphore and wait for a pipe event, atomically */ void pipe_wait(struct pipe_inode_info *pipe) { DEFINE_WAIT(wait); /* * Pipes are system-local resources, so sleeping on them * is considered a noninteractive wait: */ prepare_to_wait(&pipe->wait, &wait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->wait, &wait); pipe_lock(pipe); } static void anon_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * If nobody else uses this page, and we don't already have a * temporary page, let's keep track of it as a one-deep * allocation cache. (Otherwise just release our reference to it) */ if (page_count(page) == 1 && !pipe->tmp_page) pipe->tmp_page = page; else put_page(page); } static int anon_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) == 1) { memcg_kmem_uncharge(page, 0); __SetPageLocked(page); return 0; } return 1; } /** * generic_pipe_buf_steal - attempt to take ownership of a &pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to attempt to steal * * Description: * This function attempts to steal the &struct page attached to * @buf. If successful, this function returns 0 and returns with * the page locked. The caller may then reuse the page for whatever * he wishes; the typical use is insertion into a different file * page cache. */ int generic_pipe_buf_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; /* * A reference of one is golden, that means that the owner of this * page is the only one holding a reference to it. lock the page * and return OK. */ if (page_count(page) == 1) { lock_page(page); return 0; } return 1; } EXPORT_SYMBOL(generic_pipe_buf_steal); /** * generic_pipe_buf_get - get a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to get a reference to * * Description: * This function grabs an extra reference to @buf. It's used in * in the tee() system call, when we duplicate the buffers in one * pipe into another. */ bool generic_pipe_buf_get(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { return try_get_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_get); /** * generic_pipe_buf_confirm - verify contents of the pipe buffer * @info: the pipe that the buffer belongs to * @buf: the buffer to confirm * * Description: * This function does nothing, because the generic pipe code uses * pages that are always good when inserted into the pipe. */ int generic_pipe_buf_confirm(struct pipe_inode_info *info, struct pipe_buffer *buf) { return 0; } EXPORT_SYMBOL(generic_pipe_buf_confirm); /** * generic_pipe_buf_release - put a reference to a &struct pipe_buffer * @pipe: the pipe that the buffer belongs to * @buf: the buffer to put a reference to * * Description: * This function releases a reference to @buf. */ void generic_pipe_buf_release(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { put_page(buf->page); } EXPORT_SYMBOL(generic_pipe_buf_release); /* New data written to a pipe may be appended to a buffer with this type. */ static const struct pipe_buf_operations anon_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = anon_pipe_buf_steal, .get = generic_pipe_buf_get, }; static const struct pipe_buf_operations anon_pipe_buf_nomerge_ops = { .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = anon_pipe_buf_steal, .get = generic_pipe_buf_get, }; static const struct pipe_buf_operations packet_pipe_buf_ops = { .confirm = generic_pipe_buf_confirm, .release = anon_pipe_buf_release, .steal = anon_pipe_buf_steal, .get = generic_pipe_buf_get, }; /** * pipe_buf_mark_unmergeable - mark a &struct pipe_buffer as unmergeable * @buf: the buffer to mark * * Description: * This function ensures that no future writes will be merged into the * given &struct pipe_buffer. This is necessary when multiple pipe buffers * share the same backing page. */ void pipe_buf_mark_unmergeable(struct pipe_buffer *buf) { if (buf->ops == &anon_pipe_buf_ops) buf->ops = &anon_pipe_buf_nomerge_ops; } static bool pipe_buf_can_merge(struct pipe_buffer *buf) { return buf->ops == &anon_pipe_buf_ops; } static ssize_t pipe_read(struct kiocb *iocb, struct iov_iter *to) { size_t total_len = iov_iter_count(to); struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; int do_wakeup; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; do_wakeup = 0; ret = 0; __pipe_lock(pipe); for (;;) { int bufs = pipe->nrbufs; if (bufs) { int curbuf = pipe->curbuf; struct pipe_buffer *buf = pipe->bufs + curbuf; size_t chars = buf->len; size_t written; int error; if (chars > total_len) chars = total_len; error = pipe_buf_confirm(pipe, buf); if (error) { if (!ret) ret = error; break; } written = copy_page_to_iter(buf->page, buf->offset, chars, to); if (unlikely(written < chars)) { if (!ret) ret = -EFAULT; break; } ret += chars; buf->offset += chars; buf->len -= chars; /* Was it a packet buffer? Clean up and exit */ if (buf->flags & PIPE_BUF_FLAG_PACKET) { total_len = chars; buf->len = 0; } if (!buf->len) { pipe_buf_release(pipe, buf); curbuf = (curbuf + 1) & (pipe->buffers - 1); pipe->curbuf = curbuf; pipe->nrbufs = --bufs; do_wakeup = 1; } total_len -= chars; if (!total_len) break; /* common path: read succeeded */ } if (bufs) /* More to do? */ continue; if (!pipe->writers) break; if (!pipe->waiting_writers) { /* syscall merging: Usually we must not sleep * if O_NONBLOCK is set, or if we got some data. * But if a writer sleeps in kernel space, then * we can wait for that data without violating POSIX. */ if (ret) break; if (filp->f_flags & O_NONBLOCK) { ret = -EAGAIN; break; } } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } if (do_wakeup) { wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } pipe_wait(pipe); } __pipe_unlock(pipe); /* Signal writers asynchronously that there is more room. */ if (do_wakeup) { wake_up_interruptible_sync_poll(&pipe->wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } if (ret > 0) file_accessed(filp); return ret; } static inline int is_packetized(struct file *file) { return (file->f_flags & O_DIRECT) != 0; } static ssize_t pipe_write(struct kiocb *iocb, struct iov_iter *from) { struct file *filp = iocb->ki_filp; struct pipe_inode_info *pipe = filp->private_data; ssize_t ret = 0; int do_wakeup = 0; size_t total_len = iov_iter_count(from); ssize_t chars; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; __pipe_lock(pipe); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* We try to merge small writes */ chars = total_len & (PAGE_SIZE-1); /* size of the last buffer */ if (pipe->nrbufs && chars != 0) { int lastbuf = (pipe->curbuf + pipe->nrbufs - 1) & (pipe->buffers - 1); struct pipe_buffer *buf = pipe->bufs + lastbuf; int offset = buf->offset + buf->len; if (pipe_buf_can_merge(buf) && offset + chars <= PAGE_SIZE) { ret = pipe_buf_confirm(pipe, buf); if (ret) goto out; ret = copy_page_from_iter(buf->page, offset, chars, from); if (unlikely(ret < chars)) { ret = -EFAULT; goto out; } do_wakeup = 1; buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { int bufs; if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } bufs = pipe->nrbufs; if (bufs < pipe->buffers) { int newbuf = (pipe->curbuf + bufs) & (pipe->buffers-1); struct pipe_buffer *buf = pipe->bufs + newbuf; struct page *page = pipe->tmp_page; int copied; if (!page) { page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT); if (unlikely(!page)) { ret = ret ? : -ENOMEM; break; } pipe->tmp_page = page; } /* Always wake up, even if the copy fails. Otherwise * we lock up (O_NONBLOCK-)readers that sleep due to * syscall merging. * FIXME! Is this really true? */ do_wakeup = 1; copied = copy_page_from_iter(page, 0, PAGE_SIZE, from); if (unlikely(copied < PAGE_SIZE && iov_iter_count(from))) { if (!ret) ret = -EFAULT; break; } ret += copied; /* Insert it into the buffer array */ buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = copied; buf->flags = 0; if (is_packetized(filp)) { buf->ops = &packet_pipe_buf_ops; buf->flags = PIPE_BUF_FLAG_PACKET; } pipe->nrbufs = ++bufs; pipe->tmp_page = NULL; if (!iov_iter_count(from)) break; } if (bufs < pipe->buffers) continue; if (filp->f_flags & O_NONBLOCK) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } if (do_wakeup) { wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); do_wakeup = 0; } pipe->waiting_writers++; pipe_wait(pipe); pipe->waiting_writers--; } out: __pipe_unlock(pipe); if (do_wakeup) { wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); } if (ret > 0 && sb_start_write_trylock(file_inode(filp)->i_sb)) { int err = file_update_time(filp); if (err) ret = err; sb_end_write(file_inode(filp)->i_sb); } return ret; } static long pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe = filp->private_data; int count, buf, nrbufs; switch (cmd) { case FIONREAD: __pipe_lock(pipe); count = 0; buf = pipe->curbuf; nrbufs = pipe->nrbufs; while (--nrbufs >= 0) { count += pipe->bufs[buf].len; buf = (buf+1) & (pipe->buffers - 1); } __pipe_unlock(pipe); return put_user(count, (int __user *)arg); default: return -ENOIOCTLCMD; } } /* No kernel lock held - fine */ static __poll_t pipe_poll(struct file *filp, poll_table *wait) { __poll_t mask; struct pipe_inode_info *pipe = filp->private_data; int nrbufs; poll_wait(filp, &pipe->wait, wait); /* Reading only -- no need for acquiring the semaphore. */ nrbufs = pipe->nrbufs; mask = 0; if (filp->f_mode & FMODE_READ) { mask = (nrbufs > 0) ? EPOLLIN | EPOLLRDNORM : 0; if (!pipe->writers && filp->f_version != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { mask |= (nrbufs < pipe->buffers) ? EPOLLOUT | EPOLLWRNORM : 0; /* * Most Unices do not set EPOLLERR for FIFOs but on Linux they * behave exactly like pipes for poll(). */ if (!pipe->readers) mask |= EPOLLERR; } return mask; } static void put_pipe_info(struct inode *inode, struct pipe_inode_info *pipe) { int kill = 0; spin_lock(&inode->i_lock); if (!--pipe->files) { inode->i_pipe = NULL; kill = 1; } spin_unlock(&inode->i_lock); if (kill) free_pipe_info(pipe); } static int pipe_release(struct inode *inode, struct file *file) { struct pipe_inode_info *pipe = file->private_data; __pipe_lock(pipe); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; if (pipe->readers || pipe->writers) { wake_up_interruptible_sync_poll(&pipe->wait, EPOLLIN | EPOLLOUT | EPOLLRDNORM | EPOLLWRNORM | EPOLLERR | EPOLLHUP); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } __pipe_unlock(pipe); put_pipe_info(inode, pipe); return 0; } static int pipe_fasync(int fd, struct file *filp, int on) { struct pipe_inode_info *pipe = filp->private_data; int retval = 0; __pipe_lock(pipe); if (filp->f_mode & FMODE_READ) retval = fasync_helper(fd, filp, on, &pipe->fasync_readers); if ((filp->f_mode & FMODE_WRITE) && retval >= 0) { retval = fasync_helper(fd, filp, on, &pipe->fasync_writers); if (retval < 0 && (filp->f_mode & FMODE_READ)) /* this can happen only if on == T */ fasync_helper(-1, filp, 0, &pipe->fasync_readers); } __pipe_unlock(pipe); return retval; } static unsigned long account_pipe_buffers(struct user_struct *user, unsigned long old, unsigned long new) { return atomic_long_add_return(new - old, &user->pipe_bufs); } static bool too_many_pipe_buffers_soft(unsigned long user_bufs) { unsigned long soft_limit = READ_ONCE(pipe_user_pages_soft); return soft_limit && user_bufs > soft_limit; } static bool too_many_pipe_buffers_hard(unsigned long user_bufs) { unsigned long hard_limit = READ_ONCE(pipe_user_pages_hard); return hard_limit && user_bufs > hard_limit; } static bool is_unprivileged_user(void) { return !capable(CAP_SYS_RESOURCE) && !capable(CAP_SYS_ADMIN); } struct pipe_inode_info *alloc_pipe_info(void) { struct pipe_inode_info *pipe; unsigned long pipe_bufs = PIPE_DEF_BUFFERS; struct user_struct *user = get_current_user(); unsigned long user_bufs; unsigned int max_size = READ_ONCE(pipe_max_size); pipe = kzalloc(sizeof(struct pipe_inode_info), GFP_KERNEL_ACCOUNT); if (pipe == NULL) goto out_free_uid; if (pipe_bufs * PAGE_SIZE > max_size && !capable(CAP_SYS_RESOURCE)) pipe_bufs = max_size >> PAGE_SHIFT; user_bufs = account_pipe_buffers(user, 0, pipe_bufs); if (too_many_pipe_buffers_soft(user_bufs) && is_unprivileged_user()) { user_bufs = account_pipe_buffers(user, pipe_bufs, PIPE_MIN_DEF_BUFFERS); pipe_bufs = PIPE_MIN_DEF_BUFFERS; } if (too_many_pipe_buffers_hard(user_bufs) && is_unprivileged_user()) goto out_revert_acct; pipe->bufs = kcalloc(pipe_bufs, sizeof(struct pipe_buffer), GFP_KERNEL_ACCOUNT); if (pipe->bufs) { init_waitqueue_head(&pipe->wait); pipe->r_counter = pipe->w_counter = 1; pipe->buffers = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); return pipe; } out_revert_acct: (void) account_pipe_buffers(user, pipe_bufs, 0); kfree(pipe); out_free_uid: free_uid(user); return NULL; } void free_pipe_info(struct pipe_inode_info *pipe) { int i; (void) account_pipe_buffers(pipe->user, pipe->buffers, 0); free_uid(pipe->user); for (i = 0; i < pipe->buffers; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __read_mostly; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "pipe:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations pipefs_dentry_operations = { .d_dname = pipefs_dname, }; static struct inode * get_pipe_inode(void) { struct inode *inode = new_inode_pseudo(pipe_mnt->mnt_sb); struct pipe_inode_info *pipe; if (!inode) goto fail_inode; inode->i_ino = get_next_ino(); pipe = alloc_pipe_info(); if (!pipe) goto fail_iput; inode->i_pipe = pipe; pipe->files = 2; pipe->readers = pipe->writers = 1; inode->i_fop = &pipefifo_fops; /* * Mark the inode dirty from the very beginning, * that way it will never be moved to the dirty * list because "mark_inode_dirty()" will think * that it already _is_ on the dirty list. */ inode->i_state = I_DIRTY; inode->i_mode = S_IFIFO | S_IRUSR | S_IWUSR; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode); return inode; fail_iput: iput(inode); fail_inode: return NULL; } int create_pipe_files(struct file **res, int flags) { struct inode *inode = get_pipe_inode(); struct file *f; if (!inode) return -ENFILE; f = alloc_file_pseudo(inode, pipe_mnt, "", O_WRONLY | (flags & (O_NONBLOCK | O_DIRECT)), &pipefifo_fops); if (IS_ERR(f)) { free_pipe_info(inode->i_pipe); iput(inode); return PTR_ERR(f); } f->private_data = inode->i_pipe; res[0] = alloc_file_clone(f, O_RDONLY | (flags & O_NONBLOCK), &pipefifo_fops); if (IS_ERR(res[0])) { put_pipe_info(inode, inode->i_pipe); fput(f); return PTR_ERR(res[0]); } res[0]->private_data = inode->i_pipe; res[1] = f; return 0; } static int __do_pipe_flags(int *fd, struct file **files, int flags) { int error; int fdw, fdr; if (flags & ~(O_CLOEXEC | O_NONBLOCK | O_DIRECT)) return -EINVAL; error = create_pipe_files(files, flags); if (error) return error; error = get_unused_fd_flags(flags); if (error < 0) goto err_read_pipe; fdr = error; error = get_unused_fd_flags(flags); if (error < 0) goto err_fdr; fdw = error; audit_fd_pair(fdr, fdw); fd[0] = fdr; fd[1] = fdw; return 0; err_fdr: put_unused_fd(fdr); err_read_pipe: fput(files[0]); fput(files[1]); return error; } int do_pipe_flags(int *fd, int flags) { struct file *files[2]; int error = __do_pipe_flags(fd, files, flags); if (!error) { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } return error; } /* * sys_pipe() is the normal C calling standard for creating * a pipe. It's not the way Unix traditionally does this, though. */ static int do_pipe2(int __user *fildes, int flags) { struct file *files[2]; int fd[2]; int error; error = __do_pipe_flags(fd, files, flags); if (!error) { if (unlikely(copy_to_user(fildes, fd, sizeof(fd)))) { fput(files[0]); fput(files[1]); put_unused_fd(fd[0]); put_unused_fd(fd[1]); error = -EFAULT; } else { fd_install(fd[0], files[0]); fd_install(fd[1], files[1]); } } return error; } SYSCALL_DEFINE2(pipe2, int __user *, fildes, int, flags) { return do_pipe2(fildes, flags); } SYSCALL_DEFINE1(pipe, int __user *, fildes) { return do_pipe2(fildes, 0); } static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { int cur = *cnt; while (cur == *cnt) { pipe_wait(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible(&pipe->wait); } static int fifo_open(struct inode *inode, struct file *filp) { struct pipe_inode_info *pipe; bool is_pipe = inode->i_sb->s_magic == PIPEFS_MAGIC; int ret; filp->f_version = 0; spin_lock(&inode->i_lock); if (inode->i_pipe) { pipe = inode->i_pipe; pipe->files++; spin_unlock(&inode->i_lock); } else { spin_unlock(&inode->i_lock); pipe = alloc_pipe_info(); if (!pipe) return -ENOMEM; pipe->files = 1; spin_lock(&inode->i_lock); if (unlikely(inode->i_pipe)) { inode->i_pipe->files++; spin_unlock(&inode->i_lock); free_pipe_info(pipe); pipe = inode->i_pipe; } else { inode->i_pipe = pipe; spin_unlock(&inode->i_lock); } } filp->private_data = pipe; /* OK, we have a pipe and it's pinned down */ __pipe_lock(pipe); /* We can only do regular read/write on fifos */ filp->f_mode &= (FMODE_READ | FMODE_WRITE); switch (filp->f_mode) { case FMODE_READ: /* * O_RDONLY * POSIX.1 says that O_NONBLOCK means return with the FIFO * opened, even when there is no process writing the FIFO. */ pipe->r_counter++; if (pipe->readers++ == 0) wake_up_partner(pipe); if (!is_pipe && !pipe->writers) { if ((filp->f_flags & O_NONBLOCK)) { /* suppress EPOLLHUP until we have * seen a writer */ filp->f_version = pipe->w_counter; } else { if (wait_for_partner(pipe, &pipe->w_counter)) goto err_rd; } } break; case FMODE_WRITE: /* * O_WRONLY * POSIX.1 says that O_NONBLOCK means return -1 with * errno=ENXIO when there is no process reading the FIFO. */ ret = -ENXIO; if (!is_pipe && (filp->f_flags & O_NONBLOCK) && !pipe->readers) goto err; pipe->w_counter++; if (!pipe->writers++) wake_up_partner(pipe); if (!is_pipe && !pipe->readers) { if (wait_for_partner(pipe, &pipe->r_counter)) goto err_wr; } break; case FMODE_READ | FMODE_WRITE: /* * O_RDWR * POSIX.1 leaves this case "undefined" when O_NONBLOCK is set. * This implementation will NEVER block on a O_RDWR open, since * the process can at least talk to itself. */ pipe->readers++; pipe->writers++; pipe->r_counter++; pipe->w_counter++; if (pipe->readers == 1 || pipe->writers == 1) wake_up_partner(pipe); break; default: ret = -EINVAL; goto err; } /* Ok! */ __pipe_unlock(pipe); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible(&pipe->wait); ret = -ERESTARTSYS; goto err; err: __pipe_unlock(pipe); put_pipe_info(inode, pipe); return ret; } const struct file_operations pipefifo_fops = { .open = fifo_open, .llseek = no_llseek, .read_iter = pipe_read, .write_iter = pipe_write, .poll = pipe_poll, .unlocked_ioctl = pipe_ioctl, .release = pipe_release, .fasync = pipe_fasync, }; /* * Currently we rely on the pipe array holding a power-of-2 number * of pages. Returns 0 on error. */ unsigned int round_pipe_size(unsigned long size) { if (size > (1U << 31)) return 0; /* Minimum pipe size, as required by POSIX */ if (size < PAGE_SIZE) return PAGE_SIZE; return roundup_pow_of_two(size); } /* * Allocate a new array of pipe buffers and copy the info over. Returns the * pipe size if successful, or return -ERROR on error. */ static long pipe_set_size(struct pipe_inode_info *pipe, unsigned long arg) { struct pipe_buffer *bufs; unsigned int size, nr_pages; unsigned long user_bufs; long ret = 0; size = round_pipe_size(arg); nr_pages = size >> PAGE_SHIFT; if (!nr_pages) return -EINVAL; /* * If trying to increase the pipe capacity, check that an * unprivileged user is not trying to exceed various limits * (soft limit check here, hard limit check just below). * Decreasing the pipe capacity is always permitted, even * if the user is currently over a limit. */ if (nr_pages > pipe->buffers && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->buffers, nr_pages); if (nr_pages > pipe->buffers && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } /* * We can shrink the pipe, if arg >= pipe->nrbufs. Since we don't * expect a lot of shrink+grow operations, just free and allocate * again like we would do for growing. If the pipe currently * contains more buffers than arg, then return busy. */ if (nr_pages < pipe->nrbufs) { ret = -EBUSY; goto out_revert_acct; } bufs = kcalloc(nr_pages, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) { ret = -ENOMEM; goto out_revert_acct; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indexes. */ if (pipe->nrbufs) { unsigned int tail; unsigned int head; tail = pipe->curbuf + pipe->nrbufs; if (tail < pipe->buffers) tail = 0; else tail &= (pipe->buffers - 1); head = pipe->nrbufs - tail; if (head) memcpy(bufs, pipe->bufs + pipe->curbuf, head * sizeof(struct pipe_buffer)); if (tail) memcpy(bufs + head, pipe->bufs, tail * sizeof(struct pipe_buffer)); } pipe->curbuf = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->buffers = nr_pages; return nr_pages * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_pages, pipe->buffers); return ret; } /* * After the inode slimming patch, i_pipe/i_bdev/i_cdev share the same * location, so checking ->i_pipe is not enough to verify that this is a * pipe. */ struct pipe_inode_info *get_pipe_info(struct file *file) { return file->f_op == &pipefifo_fops ? file->private_data : NULL; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned long arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file); if (!pipe) return -EBADF; __pipe_lock(pipe); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->buffers * PAGE_SIZE; break; default: ret = -EINVAL; break; } __pipe_unlock(pipe); return ret; } static const struct super_operations pipefs_ops = { .destroy_inode = free_inode_nonrcu, .statfs = simple_statfs, }; /* * pipefs should _never_ be mounted by userland - too much of security hassle, * no real gain from having the whole whorehouse mounted. So we don't need * any operations on the root directory. However, we need a non-trivial * d_name - pipe: will go nicely and kill the special-casing in procfs. */ static int pipefs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, PIPEFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &pipefs_ops; ctx->dops = &pipefs_dentry_operations; return 0; } static struct file_system_type pipe_fs_type = { .name = "pipefs", .init_fs_context = pipefs_init_fs_context, .kill_sb = kill_anon_super, }; static int __init init_pipe_fs(void) { int err = register_filesystem(&pipe_fs_type); if (!err) { pipe_mnt = kern_mount(&pipe_fs_type); if (IS_ERR(pipe_mnt)) { err = PTR_ERR(pipe_mnt); unregister_filesystem(&pipe_fs_type); } } return err; } fs_initcall(init_pipe_fs); |
| 350 1753 63 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_SIGNAL_H #define _LINUX_SCHED_SIGNAL_H #include <linux/rculist.h> #include <linux/signal.h> #include <linux/sched.h> #include <linux/sched/jobctl.h> #include <linux/sched/task.h> #include <linux/cred.h> #include <linux/refcount.h> #include <linux/posix-timers.h> #include <linux/android_kabi.h> #include <linux/mm_types.h> #include <asm/ptrace.h> /* * Types defining task->signal and task->sighand and APIs using them: */ struct sighand_struct { spinlock_t siglock; refcount_t count; wait_queue_head_t signalfd_wqh; struct k_sigaction action[_NSIG]; }; /* * Per-process accounting stats: */ struct pacct_struct { int ac_flag; long ac_exitcode; unsigned long ac_mem; u64 ac_utime, ac_stime; unsigned long ac_minflt, ac_majflt; }; struct cpu_itimer { u64 expires; u64 incr; }; /* * This is the atomic variant of task_cputime, which can be used for * storing and updating task_cputime statistics without locking. */ struct task_cputime_atomic { atomic64_t utime; atomic64_t stime; atomic64_t sum_exec_runtime; }; #define INIT_CPUTIME_ATOMIC \ (struct task_cputime_atomic) { \ .utime = ATOMIC64_INIT(0), \ .stime = ATOMIC64_INIT(0), \ .sum_exec_runtime = ATOMIC64_INIT(0), \ } /** * struct thread_group_cputimer - thread group interval timer counts * @cputime_atomic: atomic thread group interval timers. * * This structure contains the version of task_cputime, above, that is * used for thread group CPU timer calculations. */ struct thread_group_cputimer { struct task_cputime_atomic cputime_atomic; }; struct multiprocess_signals { sigset_t signal; struct hlist_node node; }; /* * NOTE! "signal_struct" does not have its own * locking, because a shared signal_struct always * implies a shared sighand_struct, so locking * sighand_struct is always a proper superset of * the locking of signal_struct. */ struct signal_struct { refcount_t sigcnt; atomic_t live; int nr_threads; struct list_head thread_head; wait_queue_head_t wait_chldexit; /* for wait4() */ /* current thread group signal load-balancing target: */ struct task_struct *curr_target; /* shared signal handling: */ struct sigpending shared_pending; /* For collecting multiprocess signals during fork */ struct hlist_head multiprocess; /* thread group exit support */ int group_exit_code; /* overloaded: * - notify group_exit_task when ->count is equal to notify_count * - everyone except group_exit_task is stopped during signal delivery * of fatal signals, group_exit_task processes the signal. */ int notify_count; struct task_struct *group_exit_task; /* thread group stop support, overloads group_exit_code too */ int group_stop_count; unsigned int flags; /* see SIGNAL_* flags below */ /* * PR_SET_CHILD_SUBREAPER marks a process, like a service * manager, to re-parent orphan (double-forking) child processes * to this process instead of 'init'. The service manager is * able to receive SIGCHLD signals and is able to investigate * the process until it calls wait(). All children of this * process will inherit a flag if they should look for a * child_subreaper process at exit. */ unsigned int is_child_subreaper:1; unsigned int has_child_subreaper:1; #ifdef CONFIG_POSIX_TIMERS /* POSIX.1b Interval Timers */ int posix_timer_id; struct list_head posix_timers; /* ITIMER_REAL timer for the process */ struct hrtimer real_timer; ktime_t it_real_incr; /* * ITIMER_PROF and ITIMER_VIRTUAL timers for the process, we use * CPUCLOCK_PROF and CPUCLOCK_VIRT for indexing array as these * values are defined to 0 and 1 respectively */ struct cpu_itimer it[2]; /* * Thread group totals for process CPU timers. * See thread_group_cputimer(), et al, for details. */ struct thread_group_cputimer cputimer; #endif /* Empty if CONFIG_POSIX_TIMERS=n */ struct posix_cputimers posix_cputimers; /* PID/PID hash table linkage. */ struct pid *pids[PIDTYPE_MAX]; #ifdef CONFIG_NO_HZ_FULL atomic_t tick_dep_mask; #endif struct pid *tty_old_pgrp; /* boolean value for session group leader */ int leader; struct tty_struct *tty; /* NULL if no tty */ #ifdef CONFIG_SCHED_AUTOGROUP struct autogroup *autogroup; #endif /* * Cumulative resource counters for dead threads in the group, * and for reaped dead child processes forked by this group. * Live threads maintain their own counters and add to these * in __exit_signal, except for the group leader. */ seqlock_t stats_lock; u64 utime, stime, cutime, cstime; u64 gtime; u64 cgtime; struct prev_cputime prev_cputime; unsigned long nvcsw, nivcsw, cnvcsw, cnivcsw; unsigned long min_flt, maj_flt, cmin_flt, cmaj_flt; unsigned long inblock, oublock, cinblock, coublock; unsigned long maxrss, cmaxrss; struct task_io_accounting ioac; /* * Cumulative ns of schedule CPU time fo dead threads in the * group, not including a zombie group leader, (This only differs * from jiffies_to_ns(utime + stime) if sched_clock uses something * other than jiffies.) */ unsigned long long sum_sched_runtime; /* * We don't bother to synchronize most readers of this at all, * because there is no reader checking a limit that actually needs * to get both rlim_cur and rlim_max atomically, and either one * alone is a single word that can safely be read normally. * getrlimit/setrlimit use task_lock(current->group_leader) to * protect this instead of the siglock, because they really * have no need to disable irqs. */ struct rlimit rlim[RLIM_NLIMITS]; #ifdef CONFIG_BSD_PROCESS_ACCT struct pacct_struct pacct; /* per-process accounting information */ #endif #ifdef CONFIG_TASKSTATS struct taskstats *stats; #endif #ifdef CONFIG_AUDIT unsigned audit_tty; struct tty_audit_buf *tty_audit_buf; #endif /* * Thread is the potential origin of an oom condition; kill first on * oom */ bool oom_flag_origin; short oom_score_adj; /* OOM kill score adjustment */ short oom_score_adj_min; /* OOM kill score adjustment min value. * Only settable by CAP_SYS_RESOURCE. */ struct mm_struct *oom_mm; /* recorded mm when the thread group got * killed by the oom killer */ struct mutex cred_guard_mutex; /* guard against foreign influences on * credential calculations * (notably. ptrace) * Deprecated do not use in new code. * Use exec_update_lock instead. */ struct rw_semaphore exec_update_lock; /* Held while task_struct is * being updated during exec, * and may have inconsistent * permissions. */ ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); } __randomize_layout; /* * Bits in flags field of signal_struct. */ #define SIGNAL_STOP_STOPPED 0x00000001 /* job control stop in effect */ #define SIGNAL_STOP_CONTINUED 0x00000002 /* SIGCONT since WCONTINUED reap */ #define SIGNAL_GROUP_EXIT 0x00000004 /* group exit in progress */ #define SIGNAL_GROUP_COREDUMP 0x00000008 /* coredump in progress */ /* * Pending notifications to parent. */ #define SIGNAL_CLD_STOPPED 0x00000010 #define SIGNAL_CLD_CONTINUED 0x00000020 #define SIGNAL_CLD_MASK (SIGNAL_CLD_STOPPED|SIGNAL_CLD_CONTINUED) #define SIGNAL_UNKILLABLE 0x00000040 /* for init: ignore fatal signals */ #define SIGNAL_STOP_MASK (SIGNAL_CLD_MASK | SIGNAL_STOP_STOPPED | \ SIGNAL_STOP_CONTINUED) static inline void signal_set_stop_flags(struct signal_struct *sig, unsigned int flags) { WARN_ON(sig->flags & (SIGNAL_GROUP_EXIT|SIGNAL_GROUP_COREDUMP)); sig->flags = (sig->flags & ~SIGNAL_STOP_MASK) | flags; } /* If true, all threads except ->group_exit_task have pending SIGKILL */ static inline int signal_group_exit(const struct signal_struct *sig) { return (sig->flags & SIGNAL_GROUP_EXIT) || (sig->group_exit_task != NULL); } extern void flush_signals(struct task_struct *); extern void ignore_signals(struct task_struct *); extern void flush_signal_handlers(struct task_struct *, int force_default); extern int dequeue_signal(struct task_struct *task, sigset_t *mask, kernel_siginfo_t *info); static inline int kernel_dequeue_signal(void) { struct task_struct *task = current; kernel_siginfo_t __info; int ret; spin_lock_irq(&task->sighand->siglock); ret = dequeue_signal(task, &task->blocked, &__info); spin_unlock_irq(&task->sighand->siglock); return ret; } static inline void kernel_signal_stop(void) { spin_lock_irq(¤t->sighand->siglock); if (current->jobctl & JOBCTL_STOP_DEQUEUED) set_special_state(TASK_STOPPED); spin_unlock_irq(¤t->sighand->siglock); schedule(); } #ifdef __ARCH_SI_TRAPNO # define ___ARCH_SI_TRAPNO(_a1) , _a1 #else # define ___ARCH_SI_TRAPNO(_a1) #endif #ifdef __ia64__ # define ___ARCH_SI_IA64(_a1, _a2, _a3) , _a1, _a2, _a3 #else # define ___ARCH_SI_IA64(_a1, _a2, _a3) #endif int force_sig_fault_to_task(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr)); int send_sig_fault(int sig, int code, void __user *addr ___ARCH_SI_TRAPNO(int trapno) ___ARCH_SI_IA64(int imm, unsigned int flags, unsigned long isr) , struct task_struct *t); int force_sig_mceerr(int code, void __user *, short); int send_sig_mceerr(int code, void __user *, short, struct task_struct *); int force_sig_bnderr(void __user *addr, void __user *lower, void __user *upper); int force_sig_pkuerr(void __user *addr, u32 pkey); int force_sig_ptrace_errno_trap(int errno, void __user *addr); extern int send_sig_info(int, struct kernel_siginfo *, struct task_struct *); extern void force_sigsegv(int sig); extern int force_sig_info(struct kernel_siginfo *); extern int __kill_pgrp_info(int sig, struct kernel_siginfo *info, struct pid *pgrp); extern int kill_pid_info(int sig, struct kernel_siginfo *info, struct pid *pid); extern int kill_pid_usb_asyncio(int sig, int errno, sigval_t addr, struct pid *, const struct cred *); extern int kill_pgrp(struct pid *pid, int sig, int priv); extern int kill_pid(struct pid *pid, int sig, int priv); extern __must_check bool do_notify_parent(struct task_struct *, int); extern void __wake_up_parent(struct task_struct *p, struct task_struct *parent); extern void force_sig(int); extern int send_sig(int, struct task_struct *, int); extern int zap_other_threads(struct task_struct *p); extern struct sigqueue *sigqueue_alloc(void); extern void sigqueue_free(struct sigqueue *); extern int send_sigqueue(struct sigqueue *, struct pid *, enum pid_type); extern int do_sigaction(int, struct k_sigaction *, struct k_sigaction *); static inline int restart_syscall(void) { set_tsk_thread_flag(current, TIF_SIGPENDING); return -ERESTARTNOINTR; } static inline int signal_pending(struct task_struct *p) { return unlikely(test_tsk_thread_flag(p,TIF_SIGPENDING)); } static inline int __fatal_signal_pending(struct task_struct *p) { return unlikely(sigismember(&p->pending.signal, SIGKILL)); } static inline int fatal_signal_pending(struct task_struct *p) { return signal_pending(p) && __fatal_signal_pending(p); } static inline int signal_pending_state(long state, struct task_struct *p) { if (!(state & (TASK_INTERRUPTIBLE | TASK_WAKEKILL))) return 0; if (!signal_pending(p)) return 0; return (state & TASK_INTERRUPTIBLE) || __fatal_signal_pending(p); } /* * This should only be used in fault handlers to decide whether we * should stop the current fault routine to handle the signals * instead, especially with the case where we've got interrupted with * a VM_FAULT_RETRY. */ static inline bool fault_signal_pending(vm_fault_t fault_flags, struct pt_regs *regs) { return unlikely((fault_flags & VM_FAULT_RETRY) && (fatal_signal_pending(current) || (user_mode(regs) && signal_pending(current)))); } /* * Reevaluate whether the task has signals pending delivery. * Wake the task if so. * This is required every time the blocked sigset_t changes. * callers must hold sighand->siglock. */ extern void recalc_sigpending_and_wake(struct task_struct *t); extern void recalc_sigpending(void); extern void calculate_sigpending(void); extern void signal_wake_up_state(struct task_struct *t, unsigned int state); static inline void signal_wake_up(struct task_struct *t, bool resume) { signal_wake_up_state(t, resume ? TASK_WAKEKILL : 0); } static inline void ptrace_signal_wake_up(struct task_struct *t, bool resume) { signal_wake_up_state(t, resume ? __TASK_TRACED : 0); } void task_join_group_stop(struct task_struct *task); #ifdef TIF_RESTORE_SIGMASK /* * Legacy restore_sigmask accessors. These are inefficient on * SMP architectures because they require atomic operations. */ /** * set_restore_sigmask() - make sure saved_sigmask processing gets done * * This sets TIF_RESTORE_SIGMASK and ensures that the arch signal code * will run before returning to user mode, to process the flag. For * all callers, TIF_SIGPENDING is already set or it's no harm to set * it. TIF_RESTORE_SIGMASK need not be in the set of bits that the * arch code will notice on return to user mode, in case those bits * are scarce. We set TIF_SIGPENDING here to ensure that the arch * signal code always gets run when TIF_RESTORE_SIGMASK is set. */ static inline void set_restore_sigmask(void) { set_thread_flag(TIF_RESTORE_SIGMASK); } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { clear_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline void clear_restore_sigmask(void) { clear_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return test_tsk_thread_flag(task, TIF_RESTORE_SIGMASK); } static inline bool test_restore_sigmask(void) { return test_thread_flag(TIF_RESTORE_SIGMASK); } static inline bool test_and_clear_restore_sigmask(void) { return test_and_clear_thread_flag(TIF_RESTORE_SIGMASK); } #else /* TIF_RESTORE_SIGMASK */ /* Higher-quality implementation, used if TIF_RESTORE_SIGMASK doesn't exist. */ static inline void set_restore_sigmask(void) { current->restore_sigmask = true; } static inline void clear_tsk_restore_sigmask(struct task_struct *task) { task->restore_sigmask = false; } static inline void clear_restore_sigmask(void) { current->restore_sigmask = false; } static inline bool test_restore_sigmask(void) { return current->restore_sigmask; } static inline bool test_tsk_restore_sigmask(struct task_struct *task) { return task->restore_sigmask; } static inline bool test_and_clear_restore_sigmask(void) { if (!current->restore_sigmask) return false; current->restore_sigmask = false; return true; } #endif static inline void restore_saved_sigmask(void) { if (test_and_clear_restore_sigmask()) __set_current_blocked(¤t->saved_sigmask); } extern int set_user_sigmask(const sigset_t __user *umask, size_t sigsetsize); static inline void restore_saved_sigmask_unless(bool interrupted) { if (interrupted) WARN_ON(!test_thread_flag(TIF_SIGPENDING)); else restore_saved_sigmask(); } static inline sigset_t *sigmask_to_save(void) { sigset_t *res = ¤t->blocked; if (unlikely(test_restore_sigmask())) res = ¤t->saved_sigmask; return res; } static inline int kill_cad_pid(int sig, int priv) { return kill_pid(cad_pid, sig, priv); } /* These can be the second arg to send_sig_info/send_group_sig_info. */ #define SEND_SIG_NOINFO ((struct kernel_siginfo *) 0) #define SEND_SIG_PRIV ((struct kernel_siginfo *) 1) static inline int __on_sig_stack(unsigned long sp) { #ifdef CONFIG_STACK_GROWSUP return sp >= current->sas_ss_sp && sp - current->sas_ss_sp < current->sas_ss_size; #else return sp > current->sas_ss_sp && sp - current->sas_ss_sp <= current->sas_ss_size; #endif } /* * True if we are on the alternate signal stack. */ static inline int on_sig_stack(unsigned long sp) { /* * If the signal stack is SS_AUTODISARM then, by construction, we * can't be on the signal stack unless user code deliberately set * SS_AUTODISARM when we were already on it. * * This improves reliability: if user state gets corrupted such that * the stack pointer points very close to the end of the signal stack, * then this check will enable the signal to be handled anyway. */ if (current->sas_ss_flags & SS_AUTODISARM) return 0; return __on_sig_stack(sp); } static inline int sas_ss_flags(unsigned long sp) { if (!current->sas_ss_size) return SS_DISABLE; return on_sig_stack(sp) ? SS_ONSTACK : 0; } static inline void sas_ss_reset(struct task_struct *p) { p->sas_ss_sp = 0; p->sas_ss_size = 0; p->sas_ss_flags = SS_DISABLE; } static inline unsigned long sigsp(unsigned long sp, struct ksignal *ksig) { if (unlikely((ksig->ka.sa.sa_flags & SA_ONSTACK)) && ! sas_ss_flags(sp)) #ifdef CONFIG_STACK_GROWSUP return current->sas_ss_sp; #else return current->sas_ss_sp + current->sas_ss_size; #endif return sp; } extern void __cleanup_sighand(struct sighand_struct *); extern void flush_itimer_signals(void); #define tasklist_empty() \ list_empty(&init_task.tasks) #define next_task(p) \ list_entry_rcu((p)->tasks.next, struct task_struct, tasks) #define for_each_process(p) \ for (p = &init_task ; (p = next_task(p)) != &init_task ; ) extern bool current_is_single_threaded(void); /* * Careful: do_each_thread/while_each_thread is a double loop so * 'break' will not work as expected - use goto instead. */ #define do_each_thread(g, t) \ for (g = t = &init_task ; (g = t = next_task(g)) != &init_task ; ) do #define while_each_thread(g, t) \ while ((t = next_thread(t)) != g) #define __for_each_thread(signal, t) \ list_for_each_entry_rcu(t, &(signal)->thread_head, thread_node) #define for_each_thread(p, t) \ __for_each_thread((p)->signal, t) /* Careful: this is a double loop, 'break' won't work as expected. */ #define for_each_process_thread(p, t) \ for_each_process(p) for_each_thread(p, t) typedef int (*proc_visitor)(struct task_struct *p, void *data); void walk_process_tree(struct task_struct *top, proc_visitor, void *); static inline struct pid *task_pid_type(struct task_struct *task, enum pid_type type) { struct pid *pid; if (type == PIDTYPE_PID) pid = task_pid(task); else pid = task->signal->pids[type]; return pid; } static inline struct pid *task_tgid(struct task_struct *task) { return task->signal->pids[PIDTYPE_TGID]; } /* * Without tasklist or RCU lock it is not safe to dereference * the result of task_pgrp/task_session even if task == current, * we can race with another thread doing sys_setsid/sys_setpgid. */ static inline struct pid *task_pgrp(struct task_struct *task) { return task->signal->pids[PIDTYPE_PGID]; } static inline struct pid *task_session(struct task_struct *task) { return task->signal->pids[PIDTYPE_SID]; } static inline int get_nr_threads(struct task_struct *task) { return task->signal->nr_threads; } static inline bool thread_group_leader(struct task_struct *p) { return p->exit_signal >= 0; } /* Do to the insanities of de_thread it is possible for a process * to have the pid of the thread group leader without actually being * the thread group leader. For iteration through the pids in proc * all we care about is that we have a task with the appropriate * pid, we don't actually care if we have the right task. */ static inline bool has_group_leader_pid(struct task_struct *p) { return task_pid(p) == task_tgid(p); } static inline bool same_thread_group(struct task_struct *p1, struct task_struct *p2) { return p1->signal == p2->signal; } static inline struct task_struct *next_thread(const struct task_struct *p) { return list_entry_rcu(p->thread_group.next, struct task_struct, thread_group); } static inline int thread_group_empty(struct task_struct *p) { return list_empty(&p->thread_group); } #define delay_group_leader(p) \ (thread_group_leader(p) && !thread_group_empty(p)) extern struct sighand_struct *__lock_task_sighand(struct task_struct *task, unsigned long *flags); static inline struct sighand_struct *lock_task_sighand(struct task_struct *task, unsigned long *flags) { struct sighand_struct *ret; ret = __lock_task_sighand(task, flags); (void)__cond_lock(&task->sighand->siglock, ret); return ret; } static inline void unlock_task_sighand(struct task_struct *task, unsigned long *flags) { spin_unlock_irqrestore(&task->sighand->siglock, *flags); } static inline unsigned long task_rlimit(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_cur); } static inline unsigned long task_rlimit_max(const struct task_struct *task, unsigned int limit) { return READ_ONCE(task->signal->rlim[limit].rlim_max); } static inline unsigned long rlimit(unsigned int limit) { return task_rlimit(current, limit); } static inline unsigned long rlimit_max(unsigned int limit) { return task_rlimit_max(current, limit); } #endif /* _LINUX_SCHED_SIGNAL_H */ |
| 1169 1173 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/swapfile.c * * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds * Swap reorganised 29.12.95, Stephen Tweedie */ #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/hugetlb.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/kernel_stat.h> #include <linux/swap.h> #include <linux/vmalloc.h> #include <linux/pagemap.h> #include <linux/namei.h> #include <linux/shmem_fs.h> #include <linux/blkdev.h> #include <linux/random.h> #include <linux/writeback.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/init.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/backing-dev.h> #include <linux/mutex.h> #include <linux/capability.h> #include <linux/syscalls.h> #include <linux/memcontrol.h> #include <linux/poll.h> #include <linux/oom.h> #include <linux/frontswap.h> #include <linux/swapfile.h> #include <linux/export.h> #include <linux/swap_slots.h> #include <linux/sort.h> #include <asm/pgtable.h> #include <asm/tlbflush.h> #include <linux/swapops.h> #include <linux/swap_cgroup.h> static bool swap_count_continued(struct swap_info_struct *, pgoff_t, unsigned char); static void free_swap_count_continuations(struct swap_info_struct *); static sector_t map_swap_entry(swp_entry_t, struct block_device**); DEFINE_SPINLOCK(swap_lock); static unsigned int nr_swapfiles; atomic_long_t nr_swap_pages; /* * Some modules use swappable objects and may try to swap them out under * memory pressure (via the shrinker). Before doing so, they may wish to * check to see if any swap space is available. */ EXPORT_SYMBOL_GPL(nr_swap_pages); /* protected with swap_lock. reading in vm_swap_full() doesn't need lock */ long total_swap_pages; static int least_priority = -1; static const char Bad_file[] = "Bad swap file entry "; static const char Unused_file[] = "Unused swap file entry "; static const char Bad_offset[] = "Bad swap offset entry "; static const char Unused_offset[] = "Unused swap offset entry "; /* * all active swap_info_structs * protected with swap_lock, and ordered by priority. */ PLIST_HEAD(swap_active_head); /* * all available (active, not full) swap_info_structs * protected with swap_avail_lock, ordered by priority. * This is used by get_swap_page() instead of swap_active_head * because swap_active_head includes all swap_info_structs, * but get_swap_page() doesn't need to look at full ones. * This uses its own lock instead of swap_lock because when a * swap_info_struct changes between not-full/full, it needs to * add/remove itself to/from this list, but the swap_info_struct->lock * is held and the locking order requires swap_lock to be taken * before any swap_info_struct->lock. */ static struct plist_head *swap_avail_heads; static DEFINE_SPINLOCK(swap_avail_lock); struct swap_info_struct *swap_info[MAX_SWAPFILES]; static DEFINE_MUTEX(swapon_mutex); static DECLARE_WAIT_QUEUE_HEAD(proc_poll_wait); /* Activity counter to indicate that a swapon or swapoff has occurred */ static atomic_t proc_poll_event = ATOMIC_INIT(0); atomic_t nr_rotate_swap = ATOMIC_INIT(0); static struct swap_info_struct *swap_type_to_swap_info(int type) { if (type >= READ_ONCE(nr_swapfiles)) return NULL; smp_rmb(); /* Pairs with smp_wmb in alloc_swap_info. */ return READ_ONCE(swap_info[type]); } static inline unsigned char swap_count(unsigned char ent) { return ent & ~SWAP_HAS_CACHE; /* may include COUNT_CONTINUED flag */ } /* Reclaim the swap entry anyway if possible */ #define TTRS_ANYWAY 0x1 /* * Reclaim the swap entry if there are no more mappings of the * corresponding page */ #define TTRS_UNMAPPED 0x2 /* Reclaim the swap entry if swap is getting full*/ #define TTRS_FULL 0x4 /* returns 1 if swap entry is freed */ static int __try_to_reclaim_swap(struct swap_info_struct *si, unsigned long offset, unsigned long flags) { swp_entry_t entry = swp_entry(si->type, offset); struct page *page; int ret = 0; page = find_get_page(swap_address_space(entry), offset); if (!page) return 0; /* * When this function is called from scan_swap_map_slots() and it's * called by vmscan.c at reclaiming pages. So, we hold a lock on a page, * here. We have to use trylock for avoiding deadlock. This is a special * case and you should use try_to_free_swap() with explicit lock_page() * in usual operations. */ if (trylock_page(page)) { if ((flags & TTRS_ANYWAY) || ((flags & TTRS_UNMAPPED) && !page_mapped(page)) || ((flags & TTRS_FULL) && mem_cgroup_swap_full(page))) ret = try_to_free_swap(page); unlock_page(page); } put_page(page); return ret; } static inline struct swap_extent *first_se(struct swap_info_struct *sis) { struct rb_node *rb = rb_first(&sis->swap_extent_root); return rb_entry(rb, struct swap_extent, rb_node); } static inline struct swap_extent *next_se(struct swap_extent *se) { struct rb_node *rb = rb_next(&se->rb_node); return rb ? rb_entry(rb, struct swap_extent, rb_node) : NULL; } /* * swapon tell device that all the old swap contents can be discarded, * to allow the swap device to optimize its wear-levelling. */ static int discard_swap(struct swap_info_struct *si) { struct swap_extent *se; sector_t start_block; sector_t nr_blocks; int err = 0; /* Do not discard the swap header page! */ se = first_se(si); start_block = (se->start_block + 1) << (PAGE_SHIFT - 9); nr_blocks = ((sector_t)se->nr_pages - 1) << (PAGE_SHIFT - 9); if (nr_blocks) { err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) return err; cond_resched(); } for (se = next_se(se); se; se = next_se(se)) { start_block = se->start_block << (PAGE_SHIFT - 9); nr_blocks = (sector_t)se->nr_pages << (PAGE_SHIFT - 9); err = blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_KERNEL, 0); if (err) break; cond_resched(); } return err; /* That will often be -EOPNOTSUPP */ } static struct swap_extent * offset_to_swap_extent(struct swap_info_struct *sis, unsigned long offset) { struct swap_extent *se; struct rb_node *rb; rb = sis->swap_extent_root.rb_node; while (rb) { se = rb_entry(rb, struct swap_extent, rb_node); if (offset < se->start_page) rb = rb->rb_left; else if (offset >= se->start_page + se->nr_pages) rb = rb->rb_right; else return se; } /* It *must* be present */ BUG(); } sector_t swap_page_sector(struct page *page) { struct swap_info_struct *sis = page_swap_info(page); struct swap_extent *se; sector_t sector; pgoff_t offset; offset = __page_file_index(page); se = offset_to_swap_extent(sis, offset); sector = se->start_block + (offset - se->start_page); return sector << (PAGE_SHIFT - 9); } /* * swap allocation tell device that a cluster of swap can now be discarded, * to allow the swap device to optimize its wear-levelling. */ static void discard_swap_cluster(struct swap_info_struct *si, pgoff_t start_page, pgoff_t nr_pages) { struct swap_extent *se = offset_to_swap_extent(si, start_page); while (nr_pages) { pgoff_t offset = start_page - se->start_page; sector_t start_block = se->start_block + offset; sector_t nr_blocks = se->nr_pages - offset; if (nr_blocks > nr_pages) nr_blocks = nr_pages; start_page += nr_blocks; nr_pages -= nr_blocks; start_block <<= PAGE_SHIFT - 9; nr_blocks <<= PAGE_SHIFT - 9; if (blkdev_issue_discard(si->bdev, start_block, nr_blocks, GFP_NOIO, 0)) break; se = next_se(se); } } #ifdef CONFIG_THP_SWAP #define SWAPFILE_CLUSTER HPAGE_PMD_NR #define swap_entry_size(size) (size) #else #define SWAPFILE_CLUSTER 256 /* * Define swap_entry_size() as constant to let compiler to optimize * out some code if !CONFIG_THP_SWAP */ #define swap_entry_size(size) 1 #endif #define LATENCY_LIMIT 256 static inline void cluster_set_flag(struct swap_cluster_info *info, unsigned int flag) { info->flags = flag; } static inline unsigned int cluster_count(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_count(struct swap_cluster_info *info, unsigned int c) { info->data = c; } static inline void cluster_set_count_flag(struct swap_cluster_info *info, unsigned int c, unsigned int f) { info->flags = f; info->data = c; } static inline unsigned int cluster_next(struct swap_cluster_info *info) { return info->data; } static inline void cluster_set_next(struct swap_cluster_info *info, unsigned int n) { info->data = n; } static inline void cluster_set_next_flag(struct swap_cluster_info *info, unsigned int n, unsigned int f) { info->flags = f; info->data = n; } static inline bool cluster_is_free(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_FREE; } static inline bool cluster_is_null(struct swap_cluster_info *info) { return info->flags & CLUSTER_FLAG_NEXT_NULL; } static inline void cluster_set_null(struct swap_cluster_info *info) { info->flags = CLUSTER_FLAG_NEXT_NULL; info->data = 0; } static inline bool cluster_is_huge(struct swap_cluster_info *info) { if (IS_ENABLED(CONFIG_THP_SWAP)) return info->flags & CLUSTER_FLAG_HUGE; return false; } static inline void cluster_clear_huge(struct swap_cluster_info *info) { info->flags &= ~CLUSTER_FLAG_HUGE; } static inline struct swap_cluster_info *lock_cluster(struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; ci = si->cluster_info; if (ci) { ci += offset / SWAPFILE_CLUSTER; spin_lock(&ci->lock); } return ci; } static inline void unlock_cluster(struct swap_cluster_info *ci) { if (ci) spin_unlock(&ci->lock); } /* * Determine the locking method in use for this device. Return * swap_cluster_info if SSD-style cluster-based locking is in place. */ static inline struct swap_cluster_info *lock_cluster_or_swap_info( struct swap_info_struct *si, unsigned long offset) { struct swap_cluster_info *ci; /* Try to use fine-grained SSD-style locking if available: */ ci = lock_cluster(si, offset); /* Otherwise, fall back to traditional, coarse locking: */ if (!ci) spin_lock(&si->lock); return ci; } static inline void unlock_cluster_or_swap_info(struct swap_info_struct *si, struct swap_cluster_info *ci) { if (ci) unlock_cluster(ci); else spin_unlock(&si->lock); } static inline bool cluster_list_empty(struct swap_cluster_list *list) { return cluster_is_null(&list->head); } static inline unsigned int cluster_list_first(struct swap_cluster_list *list) { return cluster_next(&list->head); } static void cluster_list_init(struct swap_cluster_list *list) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } static void cluster_list_add_tail(struct swap_cluster_list *list, struct swap_cluster_info *ci, unsigned int idx) { if (cluster_list_empty(list)) { cluster_set_next_flag(&list->head, idx, 0); cluster_set_next_flag(&list->tail, idx, 0); } else { struct swap_cluster_info *ci_tail; unsigned int tail = cluster_next(&list->tail); /* * Nested cluster lock, but both cluster locks are * only acquired when we held swap_info_struct->lock */ ci_tail = ci + tail; spin_lock_nested(&ci_tail->lock, SINGLE_DEPTH_NESTING); cluster_set_next(ci_tail, idx); spin_unlock(&ci_tail->lock); cluster_set_next_flag(&list->tail, idx, 0); } } static unsigned int cluster_list_del_first(struct swap_cluster_list *list, struct swap_cluster_info *ci) { unsigned int idx; idx = cluster_next(&list->head); if (cluster_next(&list->tail) == idx) { cluster_set_null(&list->head); cluster_set_null(&list->tail); } else cluster_set_next_flag(&list->head, cluster_next(&ci[idx]), 0); return idx; } /* Add a cluster to discard list and schedule it to do discard */ static void swap_cluster_schedule_discard(struct swap_info_struct *si, unsigned int idx) { /* * If scan_swap_map() can't find a free cluster, it will check * si->swap_map directly. To make sure the discarding cluster isn't * taken by scan_swap_map(), mark the swap entries bad (occupied). It * will be cleared after discard */ memset(si->swap_map + idx * SWAPFILE_CLUSTER, SWAP_MAP_BAD, SWAPFILE_CLUSTER); cluster_list_add_tail(&si->discard_clusters, si->cluster_info, idx); schedule_work(&si->discard_work); } static void __free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; cluster_set_flag(ci + idx, CLUSTER_FLAG_FREE); cluster_list_add_tail(&si->free_clusters, ci, idx); } /* * Doing discard actually. After a cluster discard is finished, the cluster * will be added to free cluster list. caller should hold si->lock. */ static void swap_do_scheduled_discard(struct swap_info_struct *si) { struct swap_cluster_info *info, *ci; unsigned int idx; info = si->cluster_info; while (!cluster_list_empty(&si->discard_clusters)) { idx = cluster_list_del_first(&si->discard_clusters, info); spin_unlock(&si->lock); discard_swap_cluster(si, idx * SWAPFILE_CLUSTER, SWAPFILE_CLUSTER); spin_lock(&si->lock); ci = lock_cluster(si, idx * SWAPFILE_CLUSTER); __free_cluster(si, idx); memset(si->swap_map + idx * SWAPFILE_CLUSTER, 0, SWAPFILE_CLUSTER); unlock_cluster(ci); } } static void swap_discard_work(struct work_struct *work) { struct swap_info_struct *si; si = container_of(work, struct swap_info_struct, discard_work); spin_lock(&si->lock); swap_do_scheduled_discard(si); spin_unlock(&si->lock); } static void alloc_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info; VM_BUG_ON(cluster_list_first(&si->free_clusters) != idx); cluster_list_del_first(&si->free_clusters, ci); cluster_set_count_flag(ci + idx, 0, 0); } static void free_cluster(struct swap_info_struct *si, unsigned long idx) { struct swap_cluster_info *ci = si->cluster_info + idx; VM_BUG_ON(cluster_count(ci) != 0); /* * If the swap is discardable, prepare discard the cluster * instead of free it immediately. The cluster will be freed * after discard. */ if ((si->flags & (SWP_WRITEOK | SWP_PAGE_DISCARD)) == (SWP_WRITEOK | SWP_PAGE_DISCARD)) { swap_cluster_schedule_discard(si, idx); return; } __free_cluster(si, idx); } /* * The cluster corresponding to page_nr will be used. The cluster will be * removed from free cluster list and its usage counter will be increased. */ static void inc_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; if (cluster_is_free(&cluster_info[idx])) alloc_cluster(p, idx); VM_BUG_ON(cluster_count(&cluster_info[idx]) >= SWAPFILE_CLUSTER); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) + 1); } /* * The cluster corresponding to page_nr decreases one usage. If the usage * counter becomes 0, which means no page in the cluster is in using, we can * optionally discard the cluster and add it to free cluster list. */ static void dec_cluster_info_page(struct swap_info_struct *p, struct swap_cluster_info *cluster_info, unsigned long page_nr) { unsigned long idx = page_nr / SWAPFILE_CLUSTER; if (!cluster_info) return; VM_BUG_ON(cluster_count(&cluster_info[idx]) == 0); cluster_set_count(&cluster_info[idx], cluster_count(&cluster_info[idx]) - 1); if (cluster_count(&cluster_info[idx]) == 0) free_cluster(p, idx); } /* * It's possible scan_swap_map() uses a free cluster in the middle of free * cluster list. Avoiding such abuse to avoid list corruption. */ static bool scan_swap_map_ssd_cluster_conflict(struct swap_info_struct *si, unsigned long offset) { struct percpu_cluster *percpu_cluster; bool conflict; offset /= SWAPFILE_CLUSTER; conflict = !cluster_list_empty(&si->free_clusters) && offset != cluster_list_first(&si->free_clusters) && cluster_is_free(&si->cluster_info[offset]); if (!conflict) return false; percpu_cluster = this_cpu_ptr(si->percpu_cluster); cluster_set_null(&percpu_cluster->index); return true; } /* * Try to get a swap entry from current cpu's swap entry pool (a cluster). This * might involve allocating a new cluster for current CPU too. */ static bool scan_swap_map_try_ssd_cluster(struct swap_info_struct *si, unsigned long *offset, unsigned long *scan_base) { struct percpu_cluster *cluster; struct swap_cluster_info *ci; bool found_free; unsigned long tmp, max; new_cluster: cluster = this_cpu_ptr(si->percpu_cluster); if (cluster_is_null(&cluster->index)) { if (!cluster_list_empty(&si->free_clusters)) { cluster->index = si->free_clusters.head; cluster->next = cluster_next(&cluster->index) * SWAPFILE_CLUSTER; } else if (!cluster_list_empty(&si->discard_clusters)) { /* * we don't have free cluster but have some clusters in * discarding, do discard now and reclaim them */ swap_do_scheduled_discard(si); *scan_base = *offset = si->cluster_next; goto new_cluster; } else return false; } found_free = false; /* * Other CPUs can use our cluster if they can't find a free cluster, * check if there is still free entry in the cluster */ tmp = cluster->next; max = min_t(unsigned long, si->max, (cluster_next(&cluster->index) + 1) * SWAPFILE_CLUSTER); if (tmp >= max) { cluster_set_null(&cluster->index); goto new_cluster; } ci = lock_cluster(si, tmp); while (tmp < max) { if (!si->swap_map[tmp]) { found_free = true; break; } tmp++; } unlock_cluster(ci); if (!found_free) { cluster_set_null(&cluster->index); goto new_cluster; } cluster->next = tmp + 1; *offset = tmp; *scan_base = tmp; return found_free; } static void __del_from_avail_list(struct swap_info_struct *p) { int nid; assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } static void del_from_avail_list(struct swap_info_struct *p) { spin_lock(&swap_avail_lock); __del_from_avail_list(p); spin_unlock(&swap_avail_lock); } static void swap_range_alloc(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned int end = offset + nr_entries - 1; if (offset == si->lowest_bit) si->lowest_bit += nr_entries; if (end == si->highest_bit) si->highest_bit -= nr_entries; si->inuse_pages += nr_entries; if (si->inuse_pages == si->pages) { si->lowest_bit = si->max; si->highest_bit = 0; del_from_avail_list(si); } } static void add_to_avail_list(struct swap_info_struct *p) { int nid; spin_lock(&swap_avail_lock); for_each_node(nid) { WARN_ON(!plist_node_empty(&p->avail_lists[nid])); plist_add(&p->avail_lists[nid], &swap_avail_heads[nid]); } spin_unlock(&swap_avail_lock); } static void swap_range_free(struct swap_info_struct *si, unsigned long offset, unsigned int nr_entries) { unsigned long end = offset + nr_entries - 1; void (*swap_slot_free_notify)(struct block_device *, unsigned long); if (offset < si->lowest_bit) si->lowest_bit = offset; if (end > si->highest_bit) { bool was_full = !si->highest_bit; si->highest_bit = end; if (was_full && (si->flags & SWP_WRITEOK)) add_to_avail_list(si); } atomic_long_add(nr_entries, &nr_swap_pages); si->inuse_pages -= nr_entries; if (si->flags & SWP_BLKDEV) swap_slot_free_notify = si->bdev->bd_disk->fops->swap_slot_free_notify; else swap_slot_free_notify = NULL; while (offset <= end) { frontswap_invalidate_page(si->type, offset); if (swap_slot_free_notify) swap_slot_free_notify(si->bdev, offset); offset++; } } static int scan_swap_map_slots(struct swap_info_struct *si, unsigned char usage, int nr, swp_entry_t slots[]) { struct swap_cluster_info *ci; unsigned long offset; unsigned long scan_base; unsigned long last_in_cluster = 0; int latency_ration = LATENCY_LIMIT; int n_ret = 0; if (nr > SWAP_BATCH) nr = SWAP_BATCH; /* * We try to cluster swap pages by allocating them sequentially * in swap. Once we've allocated SWAPFILE_CLUSTER pages this * way, however, we resort to first-free allocation, starting * a new cluster. This prevents us from scattering swap pages * all over the entire swap partition, so that we reduce * overall disk seek times between swap pages. -- sct * But we do now try to find an empty cluster. -Andrea * And we let swap pages go all over an SSD partition. Hugh */ si->flags += SWP_SCANNING; scan_base = offset = si->cluster_next; /* SSD algorithm */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; else goto scan; } if (unlikely(!si->cluster_nr--)) { if (si->pages - si->inuse_pages < SWAPFILE_CLUSTER) { si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } spin_unlock(&si->lock); /* * If seek is expensive, start searching for new cluster from * start of partition, to minimize the span of allocated swap. * If seek is cheap, that is the SWP_SOLIDSTATE si->cluster_info * case, just handled by scan_swap_map_try_ssd_cluster() above. */ scan_base = offset = si->lowest_bit; last_in_cluster = offset + SWAPFILE_CLUSTER - 1; /* Locate the first empty (unaligned) cluster */ for (; last_in_cluster <= si->highest_bit; offset++) { if (si->swap_map[offset]) last_in_cluster = offset + SWAPFILE_CLUSTER; else if (offset == last_in_cluster) { spin_lock(&si->lock); offset -= SWAPFILE_CLUSTER - 1; si->cluster_next = offset; si->cluster_nr = SWAPFILE_CLUSTER - 1; goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = scan_base; spin_lock(&si->lock); si->cluster_nr = SWAPFILE_CLUSTER - 1; } checks: if (si->cluster_info) { while (scan_swap_map_ssd_cluster_conflict(si, offset)) { /* take a break if we already got some slots */ if (n_ret) goto done; if (!scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto scan; } } if (!(si->flags & SWP_WRITEOK)) goto no_page; if (!si->highest_bit) goto no_page; if (offset > si->highest_bit) scan_base = offset = si->lowest_bit; ci = lock_cluster(si, offset); /* reuse swap entry of cache-only swap if not busy. */ if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { int swap_was_freed; unlock_cluster(ci); spin_unlock(&si->lock); swap_was_freed = __try_to_reclaim_swap(si, offset, TTRS_ANYWAY); spin_lock(&si->lock); /* entry was freed successfully, try to use this again */ if (swap_was_freed) goto checks; goto scan; /* check next one */ } if (si->swap_map[offset]) { unlock_cluster(ci); if (!n_ret) goto scan; else goto done; } si->swap_map[offset] = usage; inc_cluster_info_page(si, si->cluster_info, offset); unlock_cluster(ci); swap_range_alloc(si, offset, 1); si->cluster_next = offset + 1; slots[n_ret++] = swp_entry(si->type, offset); /* got enough slots or reach max slots? */ if ((n_ret == nr) || (offset >= si->highest_bit)) goto done; /* search for next available slot */ /* time to take a break? */ if (unlikely(--latency_ration < 0)) { if (n_ret) goto done; spin_unlock(&si->lock); cond_resched(); spin_lock(&si->lock); latency_ration = LATENCY_LIMIT; } /* try to get more slots in cluster */ if (si->cluster_info) { if (scan_swap_map_try_ssd_cluster(si, &offset, &scan_base)) goto checks; else goto done; } /* non-ssd case */ ++offset; /* non-ssd case, still more slots in cluster? */ if (si->cluster_nr && !si->swap_map[offset]) { --si->cluster_nr; goto checks; } done: si->flags -= SWP_SCANNING; return n_ret; scan: spin_unlock(&si->lock); while (++offset <= si->highest_bit) { if (!si->swap_map[offset]) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } } offset = si->lowest_bit; while (offset < scan_base) { if (!si->swap_map[offset]) { spin_lock(&si->lock); goto checks; } if (vm_swap_full() && si->swap_map[offset] == SWAP_HAS_CACHE) { spin_lock(&si->lock); goto checks; } if (unlikely(--latency_ration < 0)) { cond_resched(); latency_ration = LATENCY_LIMIT; } offset++; } spin_lock(&si->lock); no_page: si->flags -= SWP_SCANNING; return n_ret; } static int swap_alloc_cluster(struct swap_info_struct *si, swp_entry_t *slot) { unsigned long idx; struct swap_cluster_info *ci; unsigned long offset, i; unsigned char *map; /* * Should not even be attempting cluster allocations when huge * page swap is disabled. Warn and fail the allocation. */ if (!IS_ENABLED(CONFIG_THP_SWAP)) { VM_WARN_ON_ONCE(1); return 0; } if (cluster_list_empty(&si->free_clusters)) return 0; idx = cluster_list_first(&si->free_clusters); offset = idx * SWAPFILE_CLUSTER; ci = lock_cluster(si, offset); alloc_cluster(si, idx); cluster_set_count_flag(ci, SWAPFILE_CLUSTER, CLUSTER_FLAG_HUGE); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) map[i] = SWAP_HAS_CACHE; unlock_cluster(ci); swap_range_alloc(si, offset, SWAPFILE_CLUSTER); *slot = swp_entry(si->type, offset); return 1; } static void swap_free_cluster(struct swap_info_struct *si, unsigned long idx) { unsigned long offset = idx * SWAPFILE_CLUSTER; struct swap_cluster_info *ci; ci = lock_cluster(si, offset); memset(si->swap_map + offset, 0, SWAPFILE_CLUSTER); cluster_set_count_flag(ci, 0, 0); free_cluster(si, idx); unlock_cluster(ci); swap_range_free(si, offset, SWAPFILE_CLUSTER); } static unsigned long scan_swap_map(struct swap_info_struct *si, unsigned char usage) { swp_entry_t entry; int n_ret; n_ret = scan_swap_map_slots(si, usage, 1, &entry); if (n_ret) return swp_offset(entry); else return 0; } int get_swap_pages(int n_goal, swp_entry_t swp_entries[], int entry_size) { unsigned long size = swap_entry_size(entry_size); struct swap_info_struct *si, *next; long avail_pgs; int n_ret = 0; int node; /* Only single cluster request supported */ WARN_ON_ONCE(n_goal > 1 && size == SWAPFILE_CLUSTER); avail_pgs = atomic_long_read(&nr_swap_pages) / size; if (avail_pgs <= 0) goto noswap; if (n_goal > SWAP_BATCH) n_goal = SWAP_BATCH; if (n_goal > avail_pgs) n_goal = avail_pgs; atomic_long_sub(n_goal * size, &nr_swap_pages); spin_lock(&swap_avail_lock); start_over: node = numa_node_id(); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { /* requeue si to after same-priority siblings */ plist_requeue(&si->avail_lists[node], &swap_avail_heads[node]); spin_unlock(&swap_avail_lock); spin_lock(&si->lock); if (!si->highest_bit || !(si->flags & SWP_WRITEOK)) { spin_lock(&swap_avail_lock); if (plist_node_empty(&si->avail_lists[node])) { spin_unlock(&si->lock); goto nextsi; } WARN(!si->highest_bit, "swap_info %d in list but !highest_bit\n", si->type); WARN(!(si->flags & SWP_WRITEOK), "swap_info %d in list but !SWP_WRITEOK\n", si->type); __del_from_avail_list(si); spin_unlock(&si->lock); goto nextsi; } if (size == SWAPFILE_CLUSTER) { if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, n_goal, swp_entries); spin_unlock(&si->lock); if (n_ret || size == SWAPFILE_CLUSTER) goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); cond_resched(); spin_lock(&swap_avail_lock); nextsi: /* * if we got here, it's likely that si was almost full before, * and since scan_swap_map() can drop the si->lock, multiple * callers probably all tried to get a page from the same si * and it filled up before we could get one; or, the si filled * up between us dropping swap_avail_lock and taking si->lock. * Since we dropped the swap_avail_lock, the swap_avail_head * list may have been modified; so if next is still in the * swap_avail_head list then try it, otherwise start over * if we have not gotten any slots. */ if (plist_node_empty(&next->avail_lists[node])) goto start_over; } spin_unlock(&swap_avail_lock); check_out: if (n_ret < n_goal) atomic_long_add((long)(n_goal - n_ret) * size, &nr_swap_pages); noswap: return n_ret; } /* The only caller of this function is now suspend routine */ swp_entry_t get_swap_page_of_type(int type) { struct swap_info_struct *si = swap_type_to_swap_info(type); pgoff_t offset; if (!si) goto fail; spin_lock(&si->lock); if (si->flags & SWP_WRITEOK) { atomic_long_dec(&nr_swap_pages); /* This is called for allocating swap entry, not cache */ offset = scan_swap_map(si, 1); if (offset) { spin_unlock(&si->lock); return swp_entry(type, offset); } atomic_long_inc(&nr_swap_pages); } spin_unlock(&si->lock); fail: return (swp_entry_t) {0}; } static struct swap_info_struct *__swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; unsigned long offset; if (!entry.val) goto out; p = swp_swap_info(entry); if (!p) goto bad_nofile; if (!(p->flags & SWP_USED)) goto bad_device; offset = swp_offset(entry); if (offset >= p->max) goto bad_offset; return p; bad_offset: pr_err("swap_info_get: %s%08lx\n", Bad_offset, entry.val); goto out; bad_device: pr_err("swap_info_get: %s%08lx\n", Unused_file, entry.val); goto out; bad_nofile: pr_err("swap_info_get: %s%08lx\n", Bad_file, entry.val); out: return NULL; } static struct swap_info_struct *_swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = __swap_info_get(entry); if (!p) goto out; if (!p->swap_map[swp_offset(entry)]) goto bad_free; return p; bad_free: pr_err("swap_info_get: %s%08lx\n", Unused_offset, entry.val); goto out; out: return NULL; } static struct swap_info_struct *swap_info_get(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) spin_lock(&p->lock); return p; } static struct swap_info_struct *swap_info_get_cont(swp_entry_t entry, struct swap_info_struct *q) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p != q) { if (q != NULL) spin_unlock(&q->lock); if (p != NULL) spin_lock(&p->lock); } return p; } static unsigned char __swap_entry_free_locked(struct swap_info_struct *p, unsigned long offset, unsigned char usage) { unsigned char count; unsigned char has_cache; count = p->swap_map[offset]; has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; if (usage == SWAP_HAS_CACHE) { VM_BUG_ON(!has_cache); has_cache = 0; } else if (count == SWAP_MAP_SHMEM) { /* * Or we could insist on shmem.c using a special * swap_shmem_free() and free_shmem_swap_and_cache()... */ count = 0; } else if ((count & ~COUNT_CONTINUED) <= SWAP_MAP_MAX) { if (count == COUNT_CONTINUED) { if (swap_count_continued(p, offset, count)) count = SWAP_MAP_MAX | COUNT_CONTINUED; else count = SWAP_MAP_MAX; } else count--; } usage = count | has_cache; p->swap_map[offset] = usage ? : SWAP_HAS_CACHE; return usage; } /* * Check whether swap entry is valid in the swap device. If so, * return pointer to swap_info_struct, and keep the swap entry valid * via preventing the swap device from being swapoff, until * put_swap_device() is called. Otherwise return NULL. * * The entirety of the RCU read critical section must come before the * return from or after the call to synchronize_rcu() in * enable_swap_info() or swapoff(). So if "si->flags & SWP_VALID" is * true, the si->map, si->cluster_info, etc. must be valid in the * critical section. * * Notice that swapoff or swapoff+swapon can still happen before the * rcu_read_lock() in get_swap_device() or after the rcu_read_unlock() * in put_swap_device() if there isn't any other way to prevent * swapoff, such as page lock, page table lock, etc. The caller must * be prepared for that. For example, the following situation is * possible. * * CPU1 CPU2 * do_swap_page() * ... swapoff+swapon * __read_swap_cache_async() * swapcache_prepare() * __swap_duplicate() * // check swap_map * // verify PTE not changed * * In __swap_duplicate(), the swap_map need to be checked before * changing partly because the specified swap entry may be for another * swap device which has been swapoff. And in do_swap_page(), after * the page is read from the swap device, the PTE is verified not * changed with the page table locked to check whether the swap device * has been swapoff or swapoff+swapon. */ struct swap_info_struct *get_swap_device(swp_entry_t entry) { struct swap_info_struct *si; unsigned long offset; if (!entry.val) goto out; si = swp_swap_info(entry); if (!si) goto bad_nofile; rcu_read_lock(); if (!(si->flags & SWP_VALID)) goto unlock_out; offset = swp_offset(entry); if (offset >= si->max) goto unlock_out; return si; bad_nofile: pr_err("%s: %s%08lx\n", __func__, Bad_file, entry.val); out: return NULL; unlock_out: rcu_read_unlock(); return NULL; } static unsigned char __swap_entry_free(struct swap_info_struct *p, swp_entry_t entry, unsigned char usage) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); usage = __swap_entry_free_locked(p, offset, usage); unlock_cluster_or_swap_info(p, ci); if (!usage) free_swap_slot(entry); return usage; } static void swap_entry_free(struct swap_info_struct *p, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); unsigned char count; ci = lock_cluster(p, offset); count = p->swap_map[offset]; VM_BUG_ON(count != SWAP_HAS_CACHE); p->swap_map[offset] = 0; dec_cluster_info_page(p, p->cluster_info, offset); unlock_cluster(ci); mem_cgroup_uncharge_swap(entry, 1); swap_range_free(p, offset, 1); } /* * Caller has made sure that the swap device corresponding to entry * is still around or has not been recycled. */ void swap_free(swp_entry_t entry) { struct swap_info_struct *p; p = _swap_info_get(entry); if (p) __swap_entry_free(p, entry, 1); } /* * Called after dropping swapcache to decrease refcnt to swap entries. */ void put_swap_page(struct page *page, swp_entry_t entry) { unsigned long offset = swp_offset(entry); unsigned long idx = offset / SWAPFILE_CLUSTER; struct swap_cluster_info *ci; struct swap_info_struct *si; unsigned char *map; unsigned int i, free_entries = 0; unsigned char val; int size = swap_entry_size(hpage_nr_pages(page)); si = _swap_info_get(entry); if (!si) return; ci = lock_cluster_or_swap_info(si, offset); if (size == SWAPFILE_CLUSTER) { VM_BUG_ON(!cluster_is_huge(ci)); map = si->swap_map + offset; for (i = 0; i < SWAPFILE_CLUSTER; i++) { val = map[i]; VM_BUG_ON(!(val & SWAP_HAS_CACHE)); if (val == SWAP_HAS_CACHE) free_entries++; } cluster_clear_huge(ci); if (free_entries == SWAPFILE_CLUSTER) { unlock_cluster_or_swap_info(si, ci); spin_lock(&si->lock); mem_cgroup_uncharge_swap(entry, SWAPFILE_CLUSTER); swap_free_cluster(si, idx); spin_unlock(&si->lock); return; } } for (i = 0; i < size; i++, entry.val++) { if (!__swap_entry_free_locked(si, offset + i, SWAP_HAS_CACHE)) { unlock_cluster_or_swap_info(si, ci); free_swap_slot(entry); if (i == size - 1) return; lock_cluster_or_swap_info(si, offset); } } unlock_cluster_or_swap_info(si, ci); } #ifdef CONFIG_THP_SWAP int split_swap_cluster(swp_entry_t entry) { struct swap_info_struct *si; struct swap_cluster_info *ci; unsigned long offset = swp_offset(entry); si = _swap_info_get(entry); if (!si) return -EBUSY; ci = lock_cluster(si, offset); cluster_clear_huge(ci); unlock_cluster(ci); return 0; } #endif static int swp_entry_cmp(const void *ent1, const void *ent2) { const swp_entry_t *e1 = ent1, *e2 = ent2; return (int)swp_type(*e1) - (int)swp_type(*e2); } void swapcache_free_entries(swp_entry_t *entries, int n) { struct swap_info_struct *p, *prev; int i; if (n <= 0) return; prev = NULL; p = NULL; /* * Sort swap entries by swap device, so each lock is only taken once. * nr_swapfiles isn't absolutely correct, but the overhead of sort() is * so low that it isn't necessary to optimize further. */ if (nr_swapfiles > 1) sort(entries, n, sizeof(entries[0]), swp_entry_cmp, NULL); for (i = 0; i < n; ++i) { p = swap_info_get_cont(entries[i], prev); if (p) swap_entry_free(p, entries[i]); prev = p; } if (p) spin_unlock(&p->lock); } /* * How many references to page are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int page_swapcount(struct page *page) { int count = 0; struct swap_info_struct *p; struct swap_cluster_info *ci; swp_entry_t entry; unsigned long offset; entry.val = page_private(page); p = _swap_info_get(entry); if (p) { offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); unlock_cluster_or_swap_info(p, ci); } return count; } int __swap_count(swp_entry_t entry) { struct swap_info_struct *si; pgoff_t offset = swp_offset(entry); int count = 0; si = get_swap_device(entry); if (si) { count = swap_count(si->swap_map[offset]); put_swap_device(si); } return count; } static int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { int count = 0; pgoff_t offset = swp_offset(entry); struct swap_cluster_info *ci; ci = lock_cluster_or_swap_info(si, offset); count = swap_count(si->swap_map[offset]); unlock_cluster_or_swap_info(si, ci); return count; } /* * How many references to @entry are currently swapped out? * This does not give an exact answer when swap count is continued, * but does include the high COUNT_CONTINUED flag to allow for that. */ int __swp_swapcount(swp_entry_t entry) { int count = 0; struct swap_info_struct *si; si = get_swap_device(entry); if (si) { count = swap_swapcount(si, entry); put_swap_device(si); } return count; } /* * How many references to @entry are currently swapped out? * This considers COUNT_CONTINUED so it returns exact answer. */ int swp_swapcount(swp_entry_t entry) { int count, tmp_count, n; struct swap_info_struct *p; struct swap_cluster_info *ci; struct page *page; pgoff_t offset; unsigned char *map; p = _swap_info_get(entry); if (!p) return 0; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = swap_count(p->swap_map[offset]); if (!(count & COUNT_CONTINUED)) goto out; count &= ~COUNT_CONTINUED; n = SWAP_MAP_MAX + 1; page = vmalloc_to_page(p->swap_map + offset); offset &= ~PAGE_MASK; VM_BUG_ON(page_private(page) != SWP_CONTINUED); do { page = list_next_entry(page, lru); map = kmap_atomic(page); tmp_count = map[offset]; kunmap_atomic(map); count += (tmp_count & ~COUNT_CONTINUED) * n; n *= (SWAP_CONT_MAX + 1); } while (tmp_count & COUNT_CONTINUED); out: unlock_cluster_or_swap_info(p, ci); return count; } static bool swap_page_trans_huge_swapped(struct swap_info_struct *si, swp_entry_t entry) { struct swap_cluster_info *ci; unsigned char *map = si->swap_map; unsigned long roffset = swp_offset(entry); unsigned long offset = round_down(roffset, SWAPFILE_CLUSTER); int i; bool ret = false; ci = lock_cluster_or_swap_info(si, offset); if (!ci || !cluster_is_huge(ci)) { if (swap_count(map[roffset])) ret = true; goto unlock_out; } for (i = 0; i < SWAPFILE_CLUSTER; i++) { if (swap_count(map[offset + i])) { ret = true; break; } } unlock_out: unlock_cluster_or_swap_info(si, ci); return ret; } static bool page_swapped(struct page *page) { swp_entry_t entry; struct swap_info_struct *si; if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) return page_swapcount(page) != 0; page = compound_head(page); entry.val = page_private(page); si = _swap_info_get(entry); if (si) return swap_page_trans_huge_swapped(si, entry); return false; } static int page_trans_huge_map_swapcount(struct page *page, int *total_mapcount, int *total_swapcount) { int i, map_swapcount, _total_mapcount, _total_swapcount; unsigned long offset = 0; struct swap_info_struct *si; struct swap_cluster_info *ci = NULL; unsigned char *map = NULL; int mapcount, swapcount = 0; /* hugetlbfs shouldn't call it */ VM_BUG_ON_PAGE(PageHuge(page), page); if (!IS_ENABLED(CONFIG_THP_SWAP) || likely(!PageTransCompound(page))) { mapcount = page_trans_huge_mapcount(page, total_mapcount); if (PageSwapCache(page)) swapcount = page_swapcount(page); if (total_swapcount) *total_swapcount = swapcount; return mapcount + swapcount; } page = compound_head(page); _total_mapcount = _total_swapcount = map_swapcount = 0; if (PageSwapCache(page)) { swp_entry_t entry; entry.val = page_private(page); si = _swap_info_get(entry); if (si) { map = si->swap_map; offset = swp_offset(entry); } } if (map) ci = lock_cluster(si, offset); for (i = 0; i < HPAGE_PMD_NR; i++) { mapcount = atomic_read(&page[i]._mapcount) + 1; _total_mapcount += mapcount; if (map) { swapcount = swap_count(map[offset + i]); _total_swapcount += swapcount; } map_swapcount = max(map_swapcount, mapcount + swapcount); } unlock_cluster(ci); if (PageDoubleMap(page)) { map_swapcount -= 1; _total_mapcount -= HPAGE_PMD_NR; } mapcount = compound_mapcount(page); map_swapcount += mapcount; _total_mapcount += mapcount; if (total_mapcount) *total_mapcount = _total_mapcount; if (total_swapcount) *total_swapcount = _total_swapcount; return map_swapcount; } /* * We can write to an anon page without COW if there are no other references * to it. And as a side-effect, free up its swap: because the old content * on disk will never be read, and seeking back there to write new content * later would only waste time away from clustering. * * NOTE: total_map_swapcount should not be relied upon by the caller if * reuse_swap_page() returns false, but it may be always overwritten * (see the other implementation for CONFIG_SWAP=n). */ bool reuse_swap_page(struct page *page, int *total_map_swapcount) { int count, total_mapcount, total_swapcount; VM_BUG_ON_PAGE(!PageLocked(page), page); if (unlikely(PageKsm(page))) return false; count = page_trans_huge_map_swapcount(page, &total_mapcount, &total_swapcount); if (total_map_swapcount) *total_map_swapcount = total_mapcount + total_swapcount; if (count == 1 && PageSwapCache(page) && (likely(!PageTransCompound(page)) || /* The remaining swap count will be freed soon */ total_swapcount == page_swapcount(page))) { if (!PageWriteback(page)) { page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); } else { swp_entry_t entry; struct swap_info_struct *p; entry.val = page_private(page); p = swap_info_get(entry); if (p->flags & SWP_STABLE_WRITES) { spin_unlock(&p->lock); return false; } spin_unlock(&p->lock); } } return count <= 1; } /* * If swap is getting full, or if there are no more mappings of this page, * then try_to_free_swap is called to free its swap space. */ int try_to_free_swap(struct page *page) { VM_BUG_ON_PAGE(!PageLocked(page), page); if (!PageSwapCache(page)) return 0; if (PageWriteback(page)) return 0; if (page_swapped(page)) return 0; /* * Once hibernation has begun to create its image of memory, * there's a danger that one of the calls to try_to_free_swap() * - most probably a call from __try_to_reclaim_swap() while * hibernation is allocating its own swap pages for the image, * but conceivably even a call from memory reclaim - will free * the swap from a page which has already been recorded in the * image as a clean swapcache page, and then reuse its swap for * another page of the image. On waking from hibernation, the * original page might be freed under memory pressure, then * later read back in from swap, now with the wrong data. * * Hibernation suspends storage while it is writing the image * to disk so check that here. */ if (pm_suspended_storage()) return 0; page = compound_head(page); delete_from_swap_cache(page); SetPageDirty(page); return 1; } /* * Free the swap entry like above, but also try to * free the page cache entry if it is the last user. */ int free_swap_and_cache(swp_entry_t entry) { struct swap_info_struct *p; unsigned char count; if (non_swap_entry(entry)) return 1; p = _swap_info_get(entry); if (p) { count = __swap_entry_free(p, entry, 1); if (count == SWAP_HAS_CACHE && !swap_page_trans_huge_swapped(p, entry)) __try_to_reclaim_swap(p, swp_offset(entry), TTRS_UNMAPPED | TTRS_FULL); } return p != NULL; } #ifdef CONFIG_HIBERNATION /* * Find the swap type that corresponds to given device (if any). * * @offset - number of the PAGE_SIZE-sized block of the device, starting * from 0, in which the swap header is expected to be located. * * This is needed for the suspend to disk (aka swsusp). */ int swap_type_of(dev_t device, sector_t offset, struct block_device **bdev_p) { struct block_device *bdev = NULL; int type; if (device) bdev = bdget(device); spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *sis = swap_info[type]; if (!(sis->flags & SWP_WRITEOK)) continue; if (!bdev) { if (bdev_p) *bdev_p = bdgrab(sis->bdev); spin_unlock(&swap_lock); return type; } if (bdev == sis->bdev) { struct swap_extent *se = first_se(sis); if (se->start_block == offset) { if (bdev_p) *bdev_p = bdgrab(sis->bdev); spin_unlock(&swap_lock); bdput(bdev); return type; } } } spin_unlock(&swap_lock); if (bdev) bdput(bdev); return -ENODEV; } /* * Get the (PAGE_SIZE) block corresponding to given offset on the swapdev * corresponding to given index in swap_info (swap type). */ sector_t swapdev_block(int type, pgoff_t offset) { struct block_device *bdev; struct swap_info_struct *si = swap_type_to_swap_info(type); if (!si || !(si->flags & SWP_WRITEOK)) return 0; return map_swap_entry(swp_entry(type, offset), &bdev); } /* * Return either the total number of swap pages of given type, or the number * of free pages of that type (depending on @free) * * This is needed for software suspend */ unsigned int count_swap_pages(int type, int free) { unsigned int n = 0; spin_lock(&swap_lock); if ((unsigned int)type < nr_swapfiles) { struct swap_info_struct *sis = swap_info[type]; spin_lock(&sis->lock); if (sis->flags & SWP_WRITEOK) { n = sis->pages; if (free) n -= sis->inuse_pages; } spin_unlock(&sis->lock); } spin_unlock(&swap_lock); return n; } #endif /* CONFIG_HIBERNATION */ static inline int pte_same_as_swp(pte_t pte, pte_t swp_pte) { return pte_same(pte_swp_clear_soft_dirty(pte), swp_pte); } /* * No need to decide whether this PTE shares the swap entry with others, * just let do_wp_page work it out if a write is requested later - to * force COW, vm_page_prot omits write permission from any private vma. */ static int unuse_pte(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, swp_entry_t entry, struct page *page) { struct page *swapcache; struct mem_cgroup *memcg; spinlock_t *ptl; pte_t *pte; int ret = 1; swapcache = page; page = ksm_might_need_to_copy(page, vma, addr); if (unlikely(!page)) return -ENOMEM; if (mem_cgroup_try_charge(page, vma->vm_mm, GFP_KERNEL, &memcg, false)) { ret = -ENOMEM; goto out_nolock; } pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); if (unlikely(!pte_same_as_swp(*pte, swp_entry_to_pte(entry)))) { mem_cgroup_cancel_charge(page, memcg, false); ret = 0; goto out; } dec_mm_counter(vma->vm_mm, MM_SWAPENTS); inc_mm_counter(vma->vm_mm, MM_ANONPAGES); get_page(page); set_pte_at(vma->vm_mm, addr, pte, pte_mkold(mk_pte(page, vma->vm_page_prot))); if (page == swapcache) { page_add_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, true, false); } else { /* ksm created a completely new copy */ page_add_new_anon_rmap(page, vma, addr, false); mem_cgroup_commit_charge(page, memcg, false, false); lru_cache_add_active_or_unevictable(page, vma); } swap_free(entry); /* * Move the page to the active list so it is not * immediately swapped out again after swapon. */ activate_page(page); out: pte_unmap_unlock(pte, ptl); out_nolock: if (page != swapcache) { unlock_page(page); put_page(page); } return ret; } static int unuse_pte_range(struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct page *page; swp_entry_t entry; pte_t *pte; struct swap_info_struct *si; unsigned long offset; int ret = 0; volatile unsigned char *swap_map; si = swap_info[type]; pte = pte_offset_map(pmd, addr); do { struct vm_fault vmf; if (!is_swap_pte(*pte)) continue; entry = pte_to_swp_entry(*pte); if (swp_type(entry) != type) continue; offset = swp_offset(entry); if (frontswap && !frontswap_test(si, offset)) continue; pte_unmap(pte); swap_map = &si->swap_map[offset]; page = lookup_swap_cache(entry, vma, addr); if (!page) { vmf.vma = vma; vmf.address = addr; vmf.pmd = pmd; page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, &vmf); } if (!page) { if (*swap_map == 0 || *swap_map == SWAP_MAP_BAD) goto try_next; return -ENOMEM; } lock_page(page); wait_on_page_writeback(page); ret = unuse_pte(vma, pmd, addr, entry, page); if (ret < 0) { unlock_page(page); put_page(page); goto out; } try_to_free_swap(page); unlock_page(page); put_page(page); if (*fs_pages_to_unuse && !--(*fs_pages_to_unuse)) { ret = FRONTSWAP_PAGES_UNUSED; goto out; } try_next: pte = pte_offset_map(pmd, addr); } while (pte++, addr += PAGE_SIZE, addr != end); pte_unmap(pte - 1); ret = 0; out: return ret; } static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pmd_t *pmd; unsigned long next; int ret; pmd = pmd_offset(pud, addr); do { cond_resched(); next = pmd_addr_end(addr, end); if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pmd++, addr = next, addr != end); return 0; } static inline int unuse_pud_range(struct vm_area_struct *vma, p4d_t *p4d, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pud_t *pud; unsigned long next; int ret; pud = pud_offset(p4d, addr); do { next = pud_addr_end(addr, end); if (pud_none_or_clear_bad(pud)) continue; ret = unuse_pmd_range(vma, pud, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pud++, addr = next, addr != end); return 0; } static inline int unuse_p4d_range(struct vm_area_struct *vma, pgd_t *pgd, unsigned long addr, unsigned long end, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { p4d_t *p4d; unsigned long next; int ret; p4d = p4d_offset(pgd, addr); do { next = p4d_addr_end(addr, end); if (p4d_none_or_clear_bad(p4d)) continue; ret = unuse_pud_range(vma, p4d, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (p4d++, addr = next, addr != end); return 0; } static int unuse_vma(struct vm_area_struct *vma, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { pgd_t *pgd; unsigned long addr, end, next; int ret; addr = vma->vm_start; end = vma->vm_end; pgd = pgd_offset(vma->vm_mm, addr); do { next = pgd_addr_end(addr, end); if (pgd_none_or_clear_bad(pgd)) continue; ret = unuse_p4d_range(vma, pgd, addr, next, type, frontswap, fs_pages_to_unuse); if (ret) return ret; } while (pgd++, addr = next, addr != end); return 0; } static int unuse_mm(struct mm_struct *mm, unsigned int type, bool frontswap, unsigned long *fs_pages_to_unuse) { struct vm_area_struct *vma; int ret = 0; down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { if (vma->anon_vma && !is_vm_hugetlb_page(vma)) { ret = unuse_vma(vma, type, frontswap, fs_pages_to_unuse); if (ret) break; } cond_resched(); } up_read(&mm->mmap_sem); return ret; } /* * Scan swap_map (or frontswap_map if frontswap parameter is true) * from current position to next entry still in use. Return 0 * if there are no inuse entries after prev till end of the map. */ static unsigned int find_next_to_unuse(struct swap_info_struct *si, unsigned int prev, bool frontswap) { unsigned int i; unsigned char count; /* * No need for swap_lock here: we're just looking * for whether an entry is in use, not modifying it; false * hits are okay, and sys_swapoff() has already prevented new * allocations from this area (while holding swap_lock). */ for (i = prev + 1; i < si->max; i++) { count = READ_ONCE(si->swap_map[i]); if (count && swap_count(count) != SWAP_MAP_BAD) if (!frontswap || frontswap_test(si, i)) break; if ((i % LATENCY_LIMIT) == 0) cond_resched(); } if (i == si->max) i = 0; return i; } /* * If the boolean frontswap is true, only unuse pages_to_unuse pages; * pages_to_unuse==0 means all pages; ignored if frontswap is false */ int try_to_unuse(unsigned int type, bool frontswap, unsigned long pages_to_unuse) { struct mm_struct *prev_mm; struct mm_struct *mm; struct list_head *p; int retval = 0; struct swap_info_struct *si = swap_info[type]; struct page *page; swp_entry_t entry; unsigned int i; if (!READ_ONCE(si->inuse_pages)) return 0; if (!frontswap) pages_to_unuse = 0; retry: retval = shmem_unuse(type, frontswap, &pages_to_unuse); if (retval) goto out; prev_mm = &init_mm; mmget(prev_mm); spin_lock(&mmlist_lock); p = &init_mm.mmlist; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { mm = list_entry(p, struct mm_struct, mmlist); if (!mmget_not_zero(mm)) continue; spin_unlock(&mmlist_lock); mmput(prev_mm); prev_mm = mm; retval = unuse_mm(mm, type, frontswap, &pages_to_unuse); if (retval) { mmput(prev_mm); goto out; } /* * Make sure that we aren't completely killing * interactive performance. */ cond_resched(); spin_lock(&mmlist_lock); } spin_unlock(&mmlist_lock); mmput(prev_mm); i = 0; while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i, frontswap)) != 0) { entry = swp_entry(type, i); page = find_get_page(swap_address_space(entry), i); if (!page) continue; /* * It is conceivable that a racing task removed this page from * swap cache just before we acquired the page lock. The page * might even be back in swap cache on another swap area. But * that is okay, try_to_free_swap() only removes stale pages. */ lock_page(page); wait_on_page_writeback(page); try_to_free_swap(page); unlock_page(page); put_page(page); /* * For frontswap, we just need to unuse pages_to_unuse, if * it was specified. Need not check frontswap again here as * we already zeroed out pages_to_unuse if not frontswap. */ if (pages_to_unuse && --pages_to_unuse == 0) goto out; } /* * Lets check again to see if there are still swap entries in the map. * If yes, we would need to do retry the unuse logic again. * Under global memory pressure, swap entries can be reinserted back * into process space after the mmlist loop above passes over them. * * Limit the number of retries? No: when mmget_not_zero() above fails, * that mm is likely to be freeing swap from exit_mmap(), which proceeds * at its own independent pace; and even shmem_writepage() could have * been preempted after get_swap_page(), temporarily hiding that swap. * It's easy and robust (though cpu-intensive) just to keep retrying. */ if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; retval = -EINTR; } out: return (retval == FRONTSWAP_PAGES_UNUSED) ? 0 : retval; } /* * After a successful try_to_unuse, if no swap is now in use, we know * we can empty the mmlist. swap_lock must be held on entry and exit. * Note that mmlist_lock nests inside swap_lock, and an mm must be * added to the mmlist just after page_duplicate - before would be racy. */ static void drain_mmlist(void) { struct list_head *p, *next; unsigned int type; for (type = 0; type < nr_swapfiles; type++) if (swap_info[type]->inuse_pages) return; spin_lock(&mmlist_lock); list_for_each_safe(p, next, &init_mm.mmlist) list_del_init(p); spin_unlock(&mmlist_lock); } /* * Use this swapdev's extent info to locate the (PAGE_SIZE) block which * corresponds to page offset for the specified swap entry. * Note that the type of this function is sector_t, but it returns page offset * into the bdev, not sector offset. */ static sector_t map_swap_entry(swp_entry_t entry, struct block_device **bdev) { struct swap_info_struct *sis; struct swap_extent *se; pgoff_t offset; sis = swp_swap_info(entry); *bdev = sis->bdev; offset = swp_offset(entry); se = offset_to_swap_extent(sis, offset); return se->start_block + (offset - se->start_page); } /* * Returns the page offset into bdev for the specified page's swap entry. */ sector_t map_swap_page(struct page *page, struct block_device **bdev) { swp_entry_t entry; entry.val = page_private(page); return map_swap_entry(entry, bdev); } /* * Free all of a swapdev's extent information */ static void destroy_swap_extents(struct swap_info_struct *sis) { while (!RB_EMPTY_ROOT(&sis->swap_extent_root)) { struct rb_node *rb = sis->swap_extent_root.rb_node; struct swap_extent *se = rb_entry(rb, struct swap_extent, rb_node); rb_erase(rb, &sis->swap_extent_root); kfree(se); } if (sis->flags & SWP_ACTIVATED) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; sis->flags &= ~SWP_ACTIVATED; if (mapping->a_ops->swap_deactivate) mapping->a_ops->swap_deactivate(swap_file); } } /* * Add a block range (and the corresponding page range) into this swapdev's * extent tree. * * This function rather assumes that it is called in ascending page order. */ int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { struct rb_node **link = &sis->swap_extent_root.rb_node, *parent = NULL; struct swap_extent *se; struct swap_extent *new_se; /* * place the new node at the right most since the * function is called in ascending page order. */ while (*link) { parent = *link; link = &parent->rb_right; } if (parent) { se = rb_entry(parent, struct swap_extent, rb_node); BUG_ON(se->start_page + se->nr_pages != start_page); if (se->start_block + se->nr_pages == start_block) { /* Merge it */ se->nr_pages += nr_pages; return 0; } } /* No merge, insert a new extent. */ new_se = kmalloc(sizeof(*se), GFP_KERNEL); if (new_se == NULL) return -ENOMEM; new_se->start_page = start_page; new_se->nr_pages = nr_pages; new_se->start_block = start_block; rb_link_node(&new_se->rb_node, parent, link); rb_insert_color(&new_se->rb_node, &sis->swap_extent_root); return 1; } EXPORT_SYMBOL_GPL(add_swap_extent); /* * A `swap extent' is a simple thing which maps a contiguous range of pages * onto a contiguous range of disk blocks. An ordered list of swap extents * is built at swapon time and is then used at swap_writepage/swap_readpage * time for locating where on disk a page belongs. * * If the swapfile is an S_ISBLK block device, a single extent is installed. * This is done so that the main operating code can treat S_ISBLK and S_ISREG * swap files identically. * * Whether the swapdev is an S_ISREG file or an S_ISBLK blockdev, the swap * extent list operates in PAGE_SIZE disk blocks. Both S_ISREG and S_ISBLK * swapfiles are handled *identically* after swapon time. * * For S_ISREG swapfiles, setup_swap_extents() will walk all the file's blocks * and will parse them into an ordered extent list, in PAGE_SIZE chunks. If * some stray blocks are found which do not fall within the PAGE_SIZE alignment * requirements, they are simply tossed out - we will never use those blocks * for swapping. * * For all swap devices we set S_SWAPFILE across the life of the swapon. This * prevents users from writing to the swap device, which will corrupt memory. * * The amount of disk space which a single swap extent represents varies. * Typically it is in the 1-4 megabyte range. So we can have hundreds of * extents in the list. To avoid much list walking, we cache the previous * search location in `curr_swap_extent', and start new searches from there. * This is extremely effective. The average number of iterations in * map_swap_page() has been measured at about 0.3 per page. - akpm. */ static int setup_swap_extents(struct swap_info_struct *sis, sector_t *span) { struct file *swap_file = sis->swap_file; struct address_space *mapping = swap_file->f_mapping; struct inode *inode = mapping->host; int ret; if (S_ISBLK(inode->i_mode)) { ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; return ret; } if (mapping->a_ops->swap_activate) { ret = mapping->a_ops->swap_activate(sis, swap_file, span); if (ret >= 0) sis->flags |= SWP_ACTIVATED; if (!ret) { sis->flags |= SWP_FS; ret = add_swap_extent(sis, 0, sis->max, 0); *span = sis->pages; } return ret; } return generic_swapfile_activate(sis, swap_file, span); } static int swap_node(struct swap_info_struct *p) { struct block_device *bdev; if (p->bdev) bdev = p->bdev; else bdev = p->swap_file->f_inode->i_sb->s_bdev; return bdev ? bdev->bd_disk->node_id : NUMA_NO_NODE; } static void setup_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info) { int i; if (prio >= 0) p->prio = prio; else p->prio = --least_priority; /* * the plist prio is negated because plist ordering is * low-to-high, while swap ordering is high-to-low */ p->list.prio = -p->prio; for_each_node(i) { if (p->prio >= 0) p->avail_lists[i].prio = -p->prio; else { if (swap_node(p) == i) p->avail_lists[i].prio = 1; else p->avail_lists[i].prio = -p->prio; } } p->swap_map = swap_map; p->cluster_info = cluster_info; } static void _enable_swap_info(struct swap_info_struct *p) { p->flags |= SWP_WRITEOK | SWP_VALID; atomic_long_add(p->pages, &nr_swap_pages); total_swap_pages += p->pages; assert_spin_locked(&swap_lock); /* * both lists are plists, and thus priority ordered. * swap_active_head needs to be priority ordered for swapoff(), * which on removal of any swap_info_struct with an auto-assigned * (i.e. negative) priority increments the auto-assigned priority * of any lower-priority swap_info_structs. * swap_avail_head needs to be priority ordered for get_swap_page(), * which allocates swap pages from the highest available priority * swap_info_struct. */ plist_add(&p->list, &swap_active_head); add_to_avail_list(p); } static void enable_swap_info(struct swap_info_struct *p, int prio, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long *frontswap_map) { frontswap_init(p->type, frontswap_map); spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, prio, swap_map, cluster_info); spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * Guarantee swap_map, cluster_info, etc. fields are valid * between get/put_swap_device() if SWP_VALID bit is set */ synchronize_rcu(); spin_lock(&swap_lock); spin_lock(&p->lock); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } static void reinsert_swap_info(struct swap_info_struct *p) { spin_lock(&swap_lock); spin_lock(&p->lock); setup_swap_info(p, p->prio, p->swap_map, p->cluster_info); _enable_swap_info(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); } bool has_usable_swap(void) { bool ret = true; spin_lock(&swap_lock); if (plist_head_empty(&swap_active_head)) ret = false; spin_unlock(&swap_lock); return ret; } SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) { struct swap_info_struct *p = NULL; unsigned char *swap_map; struct swap_cluster_info *cluster_info; unsigned long *frontswap_map; struct file *swap_file, *victim; struct address_space *mapping; struct inode *inode; struct filename *pathname; int err, found = 0; unsigned int old_block_size; if (!capable(CAP_SYS_ADMIN)) return -EPERM; BUG_ON(!current->mm); pathname = getname(specialfile); if (IS_ERR(pathname)) return PTR_ERR(pathname); victim = file_open_name(pathname, O_RDWR|O_LARGEFILE, 0); err = PTR_ERR(victim); if (IS_ERR(victim)) goto out; mapping = victim->f_mapping; spin_lock(&swap_lock); plist_for_each_entry(p, &swap_active_head, list) { if (p->flags & SWP_WRITEOK) { if (p->swap_file->f_mapping == mapping) { found = 1; break; } } } if (!found) { err = -EINVAL; spin_unlock(&swap_lock); goto out_dput; } if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; spin_unlock(&swap_lock); goto out_dput; } spin_lock(&p->lock); del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; plist_for_each_entry_continue(si, &swap_active_head, list) { si->prio++; si->list.prio--; for_each_node(nid) { if (si->avail_lists[nid].prio != 1) si->avail_lists[nid].prio--; } } least_priority++; } plist_del(&p->list, &swap_active_head); atomic_long_sub(p->pages, &nr_swap_pages); total_swap_pages -= p->pages; p->flags &= ~SWP_WRITEOK; spin_unlock(&p->lock); spin_unlock(&swap_lock); disable_swap_slots_cache_lock(); set_current_oom_origin(); err = try_to_unuse(p->type, false, 0); /* force unuse all pages */ clear_current_oom_origin(); if (err) { /* re-insert swap space back into swap_list */ reinsert_swap_info(p); reenable_swap_slots_cache_unlock(); goto out_dput; } reenable_swap_slots_cache_unlock(); spin_lock(&swap_lock); spin_lock(&p->lock); p->flags &= ~SWP_VALID; /* mark swap device as invalid */ spin_unlock(&p->lock); spin_unlock(&swap_lock); /* * wait for swap operations protected by get/put_swap_device() * to complete */ synchronize_rcu(); flush_work(&p->discard_work); destroy_swap_extents(p); if (p->flags & SWP_CONTINUED) free_swap_count_continuations(p); if (!p->bdev || !blk_queue_nonrot(bdev_get_queue(p->bdev))) atomic_dec(&nr_rotate_swap); mutex_lock(&swapon_mutex); spin_lock(&swap_lock); spin_lock(&p->lock); drain_mmlist(); /* wait for anyone still in scan_swap_map */ p->highest_bit = 0; /* cuts scans short */ while (p->flags >= SWP_SCANNING) { spin_unlock(&p->lock); spin_unlock(&swap_lock); schedule_timeout_uninterruptible(1); spin_lock(&swap_lock); spin_lock(&p->lock); } swap_file = p->swap_file; old_block_size = p->old_block_size; p->swap_file = NULL; p->max = 0; swap_map = p->swap_map; p->swap_map = NULL; cluster_info = p->cluster_info; p->cluster_info = NULL; frontswap_map = frontswap_map_get(p); spin_unlock(&p->lock); spin_unlock(&swap_lock); frontswap_invalidate_area(p->type); frontswap_map_set(p, NULL); mutex_unlock(&swapon_mutex); free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); /* Destroy swap account information */ swap_cgroup_swapoff(p->type); exit_swap_address_space(p->type); inode = mapping->host; if (S_ISBLK(inode->i_mode)) { struct block_device *bdev = I_BDEV(inode); set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; inode_unlock(inode); filp_close(swap_file, NULL); /* * Clear the SWP_USED flag after all resources are freed so that swapon * can reuse this swap_info in alloc_swap_info() safely. It is ok to * not hold p->lock after we cleared its SWP_WRITEOK. */ spin_lock(&swap_lock); p->flags = 0; spin_unlock(&swap_lock); err = 0; atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); out_dput: filp_close(victim, NULL); out: putname(pathname); return err; } #ifdef CONFIG_PROC_FS static __poll_t swaps_poll(struct file *file, poll_table *wait) { struct seq_file *seq = file->private_data; poll_wait(file, &proc_poll_wait, wait); if (seq->poll_event != atomic_read(&proc_poll_event)) { seq->poll_event = atomic_read(&proc_poll_event); return EPOLLIN | EPOLLRDNORM | EPOLLERR | EPOLLPRI; } return EPOLLIN | EPOLLRDNORM; } /* iterator */ static void *swap_start(struct seq_file *swap, loff_t *pos) { struct swap_info_struct *si; int type; loff_t l = *pos; mutex_lock(&swapon_mutex); if (!l) return SEQ_START_TOKEN; for (type = 0; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; if (!--l) return si; } return NULL; } static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) { struct swap_info_struct *si = v; int type; if (v == SEQ_START_TOKEN) type = 0; else type = si->type + 1; ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; return si; } return NULL; } static void swap_stop(struct seq_file *swap, void *v) { mutex_unlock(&swapon_mutex); } static int swap_show(struct seq_file *swap, void *v) { struct swap_info_struct *si = v; struct file *file; int len; if (si == SEQ_START_TOKEN) { seq_puts(swap,"Filename\t\t\t\tType\t\tSize\tUsed\tPriority\n"); return 0; } file = si->swap_file; len = seq_file_path(swap, file, " \t\n\\"); seq_printf(swap, "%*s%s\t%u\t%u\t%d\n", len < 40 ? 40 - len : 1, " ", S_ISBLK(file_inode(file)->i_mode) ? "partition" : "file\t", si->pages << (PAGE_SHIFT - 10), si->inuse_pages << (PAGE_SHIFT - 10), si->prio); return 0; } static const struct seq_operations swaps_op = { .start = swap_start, .next = swap_next, .stop = swap_stop, .show = swap_show }; static int swaps_open(struct inode *inode, struct file *file) { struct seq_file *seq; int ret; ret = seq_open(file, &swaps_op); if (ret) return ret; seq = file->private_data; seq->poll_event = atomic_read(&proc_poll_event); return 0; } static const struct file_operations proc_swaps_operations = { .open = swaps_open, .read = seq_read, .llseek = seq_lseek, .release = seq_release, .poll = swaps_poll, }; static int __init procswaps_init(void) { proc_create("swaps", 0, NULL, &proc_swaps_operations); return 0; } __initcall(procswaps_init); #endif /* CONFIG_PROC_FS */ #ifdef MAX_SWAPFILES_CHECK static int __init max_swapfiles_check(void) { MAX_SWAPFILES_CHECK(); return 0; } late_initcall(max_swapfiles_check); #endif static struct swap_info_struct *alloc_swap_info(void) { struct swap_info_struct *p; struct swap_info_struct *defer = NULL; unsigned int type; int i; p = kvzalloc(struct_size(p, avail_lists, nr_node_ids), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { if (!(swap_info[type]->flags & SWP_USED)) break; } if (type >= MAX_SWAPFILES) { spin_unlock(&swap_lock); kvfree(p); return ERR_PTR(-EPERM); } if (type >= nr_swapfiles) { p->type = type; WRITE_ONCE(swap_info[type], p); /* * Write swap_info[type] before nr_swapfiles, in case a * racing procfs swap_start() or swap_next() is reading them. * (We never shrink nr_swapfiles, we never free this entry.) */ smp_wmb(); WRITE_ONCE(nr_swapfiles, nr_swapfiles + 1); } else { defer = p; p = swap_info[type]; /* * Do not memset this entry: a racing procfs swap_next() * would be relying on p->type to remain valid. */ } p->swap_extent_root = RB_ROOT; plist_node_init(&p->list, 0); for_each_node(i) plist_node_init(&p->avail_lists[i], 0); p->flags = SWP_USED; spin_unlock(&swap_lock); kvfree(defer); spin_lock_init(&p->lock); spin_lock_init(&p->cont_lock); return p; } static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) { int error; if (S_ISBLK(inode->i_mode)) { p->bdev = bdgrab(I_BDEV(inode)); error = blkdev_get(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL, p); if (error < 0) { p->bdev = NULL; return error; } p->old_block_size = block_size(p->bdev); error = set_blocksize(p->bdev, PAGE_SIZE); if (error < 0) return error; p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; } return 0; } /* * Find out how many pages are allowed for a single swap device. There * are two limiting factors: * 1) the number of bits for the swap offset in the swp_entry_t type, and * 2) the number of bits in the swap pte, as defined by the different * architectures. * * In order to find the largest possible bit mask, a swap entry with * swap type 0 and swap offset ~0UL is created, encoded to a swap pte, * decoded to a swp_entry_t again, and finally the swap offset is * extracted. * * This will mask all the bits from the initial ~0UL mask that can't * be encoded in either the swp_entry_t or the architecture definition * of a swap pte. */ unsigned long generic_max_swapfile_size(void) { return swp_offset(pte_to_swp_entry( swp_entry_to_pte(swp_entry(0, ~0UL)))) + 1; } /* Can be overridden by an architecture for additional checks. */ __weak unsigned long max_swapfile_size(void) { return generic_max_swapfile_size(); } static unsigned long read_swap_header(struct swap_info_struct *p, union swap_header *swap_header, struct inode *inode) { int i; unsigned long maxpages; unsigned long swapfilepages; unsigned long last_page; if (memcmp("SWAPSPACE2", swap_header->magic.magic, 10)) { pr_err("Unable to find swap-space signature\n"); return 0; } /* swap partition endianess hack... */ if (swab32(swap_header->info.version) == 1) { swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } /* Check the swap header's sub-version */ if (swap_header->info.version != 1) { pr_warn("Unable to handle swap header version %d\n", swap_header->info.version); return 0; } p->lowest_bit = 1; p->cluster_next = 1; p->cluster_nr = 0; maxpages = max_swapfile_size(); last_page = swap_header->info.last_page; if (!last_page) { pr_warn("Empty swap-file\n"); return 0; } if (last_page > maxpages) { pr_warn("Truncating oversized swap area, only using %luk out of %luk\n", maxpages << (PAGE_SHIFT - 10), last_page << (PAGE_SHIFT - 10)); } if (maxpages > last_page) { maxpages = last_page + 1; /* p->max is an unsigned int: don't overflow it */ if ((unsigned int)maxpages == 0) maxpages = UINT_MAX; } p->highest_bit = maxpages - 1; if (!maxpages) return 0; swapfilepages = i_size_read(inode) >> PAGE_SHIFT; if (swapfilepages && maxpages > swapfilepages) { pr_warn("Swap area shorter than signature indicates\n"); return 0; } if (swap_header->info.nr_badpages && S_ISREG(inode->i_mode)) return 0; if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) return 0; return maxpages; } #define SWAP_CLUSTER_INFO_COLS \ DIV_ROUND_UP(L1_CACHE_BYTES, sizeof(struct swap_cluster_info)) #define SWAP_CLUSTER_SPACE_COLS \ DIV_ROUND_UP(SWAP_ADDRESS_SPACE_PAGES, SWAPFILE_CLUSTER) #define SWAP_CLUSTER_COLS \ max_t(unsigned int, SWAP_CLUSTER_INFO_COLS, SWAP_CLUSTER_SPACE_COLS) static int setup_swap_map_and_extents(struct swap_info_struct *p, union swap_header *swap_header, unsigned char *swap_map, struct swap_cluster_info *cluster_info, unsigned long maxpages, sector_t *span) { unsigned int j, k; unsigned int nr_good_pages; int nr_extents; unsigned long nr_clusters = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); unsigned long col = p->cluster_next / SWAPFILE_CLUSTER % SWAP_CLUSTER_COLS; unsigned long i, idx; nr_good_pages = maxpages - 1; /* omit header page */ cluster_list_init(&p->free_clusters); cluster_list_init(&p->discard_clusters); for (i = 0; i < swap_header->info.nr_badpages; i++) { unsigned int page_nr = swap_header->info.badpages[i]; if (page_nr == 0 || page_nr > swap_header->info.last_page) return -EINVAL; if (page_nr < maxpages) { swap_map[page_nr] = SWAP_MAP_BAD; nr_good_pages--; /* * Haven't marked the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, page_nr); } } /* Haven't marked the cluster free yet, no list operation involved */ for (i = maxpages; i < round_up(maxpages, SWAPFILE_CLUSTER); i++) inc_cluster_info_page(p, cluster_info, i); if (nr_good_pages) { swap_map[0] = SWAP_MAP_BAD; /* * Not mark the cluster free yet, no list * operation involved */ inc_cluster_info_page(p, cluster_info, 0); p->max = maxpages; p->pages = nr_good_pages; nr_extents = setup_swap_extents(p, span); if (nr_extents < 0) return nr_extents; nr_good_pages = p->pages; } if (!nr_good_pages) { pr_warn("Empty swap-file\n"); return -EINVAL; } if (!cluster_info) return nr_extents; /* * Reduce false cache line sharing between cluster_info and * sharing same address space. */ for (k = 0; k < SWAP_CLUSTER_COLS; k++) { j = (k + col) % SWAP_CLUSTER_COLS; for (i = 0; i < DIV_ROUND_UP(nr_clusters, SWAP_CLUSTER_COLS); i++) { idx = i * SWAP_CLUSTER_COLS + j; if (idx >= nr_clusters) continue; if (cluster_count(&cluster_info[idx])) continue; cluster_set_flag(&cluster_info[idx], CLUSTER_FLAG_FREE); cluster_list_add_tail(&p->free_clusters, cluster_info, idx); } } return nr_extents; } /* * Helper to sys_swapon determining if a given swap * backing device queue supports DISCARD operations. */ static bool swap_discardable(struct swap_info_struct *si) { struct request_queue *q = bdev_get_queue(si->bdev); if (!q || !blk_queue_discard(q)) return false; return true; } SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) { struct swap_info_struct *p; struct filename *name; struct file *swap_file = NULL; struct address_space *mapping; int prio; int error; union swap_header *swap_header; int nr_extents; sector_t span; unsigned long maxpages; unsigned char *swap_map = NULL; struct swap_cluster_info *cluster_info = NULL; unsigned long *frontswap_map = NULL; struct page *page = NULL; struct inode *inode = NULL; bool inced_nr_rotate_swap = false; if (swap_flags & ~SWAP_FLAGS_VALID) return -EINVAL; if (!capable(CAP_SYS_ADMIN)) return -EPERM; if (!swap_avail_heads) return -ENOMEM; p = alloc_swap_info(); if (IS_ERR(p)) return PTR_ERR(p); INIT_WORK(&p->discard_work, swap_discard_work); name = getname(specialfile); if (IS_ERR(name)) { error = PTR_ERR(name); name = NULL; goto bad_swap; } swap_file = file_open_name(name, O_RDWR|O_LARGEFILE, 0); if (IS_ERR(swap_file)) { error = PTR_ERR(swap_file); swap_file = NULL; goto bad_swap; } p->swap_file = swap_file; mapping = swap_file->f_mapping; inode = mapping->host; error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; inode_lock(inode); if (IS_SWAPFILE(inode)) { error = -EBUSY; goto bad_swap_unlock_inode; } /* * Read the swap header. */ if (!mapping->a_ops->readpage) { error = -EINVAL; goto bad_swap_unlock_inode; } page = read_mapping_page(mapping, 0, swap_file); if (IS_ERR(page)) { error = PTR_ERR(page); goto bad_swap_unlock_inode; } swap_header = kmap(page); maxpages = read_swap_header(p, swap_header, inode); if (unlikely(!maxpages)) { error = -EINVAL; goto bad_swap_unlock_inode; } /* OK, set up the swap map and apply the bad block list */ swap_map = vzalloc(maxpages); if (!swap_map) { error = -ENOMEM; goto bad_swap_unlock_inode; } if (bdi_cap_stable_pages_required(inode_to_bdi(inode))) p->flags |= SWP_STABLE_WRITES; if (bdi_cap_synchronous_io(inode_to_bdi(inode))) p->flags |= SWP_SYNCHRONOUS_IO; if (p->bdev && blk_queue_nonrot(bdev_get_queue(p->bdev))) { int cpu; unsigned long ci, nr_cluster; p->flags |= SWP_SOLIDSTATE; /* * select a random position to start with to help wear leveling * SSD */ p->cluster_next = 1 + (prandom_u32() % p->highest_bit); nr_cluster = DIV_ROUND_UP(maxpages, SWAPFILE_CLUSTER); cluster_info = kvcalloc(nr_cluster, sizeof(*cluster_info), GFP_KERNEL); if (!cluster_info) { error = -ENOMEM; goto bad_swap_unlock_inode; } for (ci = 0; ci < nr_cluster; ci++) spin_lock_init(&((cluster_info + ci)->lock)); p->percpu_cluster = alloc_percpu(struct percpu_cluster); if (!p->percpu_cluster) { error = -ENOMEM; goto bad_swap_unlock_inode; } for_each_possible_cpu(cpu) { struct percpu_cluster *cluster; cluster = per_cpu_ptr(p->percpu_cluster, cpu); cluster_set_null(&cluster->index); } } else { atomic_inc(&nr_rotate_swap); inced_nr_rotate_swap = true; } error = swap_cgroup_swapon(p->type, maxpages); if (error) goto bad_swap_unlock_inode; nr_extents = setup_swap_map_and_extents(p, swap_header, swap_map, cluster_info, maxpages, &span); if (unlikely(nr_extents < 0)) { error = nr_extents; goto bad_swap_unlock_inode; } /* frontswap enabled? set up bit-per-page map for frontswap */ if (IS_ENABLED(CONFIG_FRONTSWAP)) frontswap_map = kvcalloc(BITS_TO_LONGS(maxpages), sizeof(long), GFP_KERNEL); if (p->bdev &&(swap_flags & SWAP_FLAG_DISCARD) && swap_discardable(p)) { /* * When discard is enabled for swap with no particular * policy flagged, we set all swap discard flags here in * order to sustain backward compatibility with older * swapon(8) releases. */ p->flags |= (SWP_DISCARDABLE | SWP_AREA_DISCARD | SWP_PAGE_DISCARD); /* * By flagging sys_swapon, a sysadmin can tell us to * either do single-time area discards only, or to just * perform discards for released swap page-clusters. * Now it's time to adjust the p->flags accordingly. */ if (swap_flags & SWAP_FLAG_DISCARD_ONCE) p->flags &= ~SWP_PAGE_DISCARD; else if (swap_flags & SWAP_FLAG_DISCARD_PAGES) p->flags &= ~SWP_AREA_DISCARD; /* issue a swapon-time discard if it's still required */ if (p->flags & SWP_AREA_DISCARD) { int err = discard_swap(p); if (unlikely(err)) pr_err("swapon: discard_swap(%p): %d\n", p, err); } } error = init_swap_address_space(p->type, maxpages); if (error) goto bad_swap_unlock_inode; /* * Flush any pending IO and dirty mappings before we start using this * swap device. */ inode->i_flags |= S_SWAPFILE; error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; goto free_swap_address_space; } mutex_lock(&swapon_mutex); prio = -1; if (swap_flags & SWAP_FLAG_PREFER) prio = (swap_flags & SWAP_FLAG_PRIO_MASK) >> SWAP_FLAG_PRIO_SHIFT; enable_swap_info(p, prio, swap_map, cluster_info, frontswap_map); pr_info("Adding %uk swap on %s. Priority:%d extents:%d across:%lluk %s%s%s%s%s\n", p->pages<<(PAGE_SHIFT-10), name->name, p->prio, nr_extents, (unsigned long long)span<<(PAGE_SHIFT-10), (p->flags & SWP_SOLIDSTATE) ? "SS" : "", (p->flags & SWP_DISCARDABLE) ? "D" : "", (p->flags & SWP_AREA_DISCARD) ? "s" : "", (p->flags & SWP_PAGE_DISCARD) ? "c" : "", (frontswap_map) ? "FS" : ""); mutex_unlock(&swapon_mutex); atomic_inc(&proc_poll_event); wake_up_interruptible(&proc_poll_wait); error = 0; goto out; free_swap_address_space: exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: free_percpu(p->percpu_cluster); p->percpu_cluster = NULL; if (inode && S_ISBLK(inode->i_mode) && p->bdev) { set_blocksize(p->bdev, p->old_block_size); blkdev_put(p->bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } inode = NULL; destroy_swap_extents(p); swap_cgroup_swapoff(p->type); spin_lock(&swap_lock); p->swap_file = NULL; p->flags = 0; spin_unlock(&swap_lock); vfree(swap_map); kvfree(cluster_info); kvfree(frontswap_map); if (inced_nr_rotate_swap) atomic_dec(&nr_rotate_swap); if (swap_file) filp_close(swap_file, NULL); out: if (page && !IS_ERR(page)) { kunmap(page); put_page(page); } if (name) putname(name); if (inode) inode_unlock(inode); if (!error) enable_swap_slots_cache(); return error; } void si_swapinfo(struct sysinfo *val) { unsigned int type; unsigned long nr_to_be_unused = 0; spin_lock(&swap_lock); for (type = 0; type < nr_swapfiles; type++) { struct swap_info_struct *si = swap_info[type]; if ((si->flags & SWP_USED) && !(si->flags & SWP_WRITEOK)) nr_to_be_unused += si->inuse_pages; } val->freeswap = atomic_long_read(&nr_swap_pages) + nr_to_be_unused; val->totalswap = total_swap_pages + nr_to_be_unused; spin_unlock(&swap_lock); } /* * Verify that a swap entry is valid and increment its swap map count. * * Returns error code in following case. * - success -> 0 * - swp_entry is invalid -> EINVAL * - swp_entry is migration entry -> EINVAL * - swap-cache reference is requested but there is already one. -> EEXIST * - swap-cache reference is requested but the entry is not used. -> ENOENT * - swap-mapped reference requested but needs continued swap count. -> ENOMEM */ static int __swap_duplicate(swp_entry_t entry, unsigned char usage) { struct swap_info_struct *p; struct swap_cluster_info *ci; unsigned long offset; unsigned char count; unsigned char has_cache; int err = -EINVAL; p = get_swap_device(entry); if (!p) goto out; offset = swp_offset(entry); ci = lock_cluster_or_swap_info(p, offset); count = p->swap_map[offset]; /* * swapin_readahead() doesn't check if a swap entry is valid, so the * swap entry could be SWAP_MAP_BAD. Check here with lock held. */ if (unlikely(swap_count(count) == SWAP_MAP_BAD)) { err = -ENOENT; goto unlock_out; } has_cache = count & SWAP_HAS_CACHE; count &= ~SWAP_HAS_CACHE; err = 0; if (usage == SWAP_HAS_CACHE) { /* set SWAP_HAS_CACHE if there is no cache and entry is used */ if (!has_cache && count) has_cache = SWAP_HAS_CACHE; else if (has_cache) /* someone else added cache */ err = -EEXIST; else /* no users remaining */ err = -ENOENT; } else if (count || has_cache) { if ((count & ~COUNT_CONTINUED) < SWAP_MAP_MAX) count += usage; else if ((count & ~COUNT_CONTINUED) > SWAP_MAP_MAX) err = -EINVAL; else if (swap_count_continued(p, offset, count)) count = COUNT_CONTINUED; else err = -ENOMEM; } else err = -ENOENT; /* unused swap entry */ p->swap_map[offset] = count | has_cache; unlock_out: unlock_cluster_or_swap_info(p, ci); out: if (p) put_swap_device(p); return err; } /* * Help swapoff by noting that swap entry belongs to shmem/tmpfs * (in which case its reference count is never incremented). */ void swap_shmem_alloc(swp_entry_t entry) { __swap_duplicate(entry, SWAP_MAP_SHMEM); } /* * Increase reference count of swap entry by 1. * Returns 0 for success, or -ENOMEM if a swap_count_continuation is required * but could not be atomically allocated. Returns 0, just as if it succeeded, * if __swap_duplicate() fails for another reason (-EINVAL or -ENOENT), which * might occur if a page table entry has got corrupted. */ int swap_duplicate(swp_entry_t entry) { int err = 0; while (!err && __swap_duplicate(entry, 1) == -ENOMEM) err = add_swap_count_continuation(entry, GFP_ATOMIC); return err; } /* * @entry: swap entry for which we allocate swap cache. * * Called when allocating swap cache for existing swap entry, * This can return error codes. Returns 0 at success. * -EBUSY means there is a swap cache. * Note: return code is different from swap_duplicate(). */ int swapcache_prepare(swp_entry_t entry) { return __swap_duplicate(entry, SWAP_HAS_CACHE); } struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return swap_type_to_swap_info(swp_type(entry)); } struct swap_info_struct *page_swap_info(struct page *page) { swp_entry_t entry = { .val = page_private(page) }; return swp_swap_info(entry); } /* * out-of-line __page_file_ methods to avoid include hell. */ struct address_space *__page_file_mapping(struct page *page) { return page_swap_info(page)->swap_file->f_mapping; } EXPORT_SYMBOL_GPL(__page_file_mapping); pgoff_t __page_file_index(struct page *page) { swp_entry_t swap = { .val = page_private(page) }; return swp_offset(swap); } EXPORT_SYMBOL_GPL(__page_file_index); /* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count * (for that entry and for its neighbouring PAGE_SIZE swap entries). Called * again when count is duplicated beyond SWAP_MAP_MAX * SWAP_CONT_MAX, etc. * * These continuation pages are seldom referenced: the common paths all work * on the original swap_map, only referring to a continuation page when the * low "digit" of a count is incremented or decremented through SWAP_MAP_MAX. * * add_swap_count_continuation(, GFP_ATOMIC) can be called while holding * page table locks; if it fails, add_swap_count_continuation(, GFP_KERNEL) * can be called after dropping locks. */ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) { struct swap_info_struct *si; struct swap_cluster_info *ci; struct page *head; struct page *page; struct page *list_page; pgoff_t offset; unsigned char count; int ret = 0; /* * When debugging, it's easier to use __GFP_ZERO here; but it's better * for latency not to zero a page while GFP_ATOMIC and holding locks. */ page = alloc_page(gfp_mask | __GFP_HIGHMEM); si = get_swap_device(entry); if (!si) { /* * An acceptable race has occurred since the failing * __swap_duplicate(): the swap device may be swapoff */ goto outer; } spin_lock(&si->lock); offset = swp_offset(entry); ci = lock_cluster(si, offset); count = si->swap_map[offset] & ~SWAP_HAS_CACHE; if ((count & ~COUNT_CONTINUED) != SWAP_MAP_MAX) { /* * The higher the swap count, the more likely it is that tasks * will race to add swap count continuation: we need to avoid * over-provisioning. */ goto out; } if (!page) { ret = -ENOMEM; goto out; } /* * We are fortunate that although vmalloc_to_page uses pte_offset_map, * no architecture is using highmem pages for kernel page tables: so it * will not corrupt the GFP_ATOMIC caller's atomic page table kmaps. */ head = vmalloc_to_page(si->swap_map + offset); offset &= ~PAGE_MASK; spin_lock(&si->cont_lock); /* * Page allocation does not initialize the page's lru field, * but it does always reset its private field. */ if (!page_private(head)) { BUG_ON(count & COUNT_CONTINUED); INIT_LIST_HEAD(&head->lru); set_page_private(head, SWP_CONTINUED); si->flags |= SWP_CONTINUED; } list_for_each_entry(list_page, &head->lru, lru) { unsigned char *map; /* * If the previous map said no continuation, but we've found * a continuation page, free our allocation and use this one. */ if (!(count & COUNT_CONTINUED)) goto out_unlock_cont; map = kmap_atomic(list_page) + offset; count = *map; kunmap_atomic(map); /* * If this continuation count now has some space in it, * free our allocation and use this one. */ if ((count & ~COUNT_CONTINUED) != SWAP_CONT_MAX) goto out_unlock_cont; } list_add_tail(&page->lru, &head->lru); page = NULL; /* now it's attached, don't free it */ out_unlock_cont: spin_unlock(&si->cont_lock); out: unlock_cluster(ci); spin_unlock(&si->lock); put_swap_device(si); outer: if (page) __free_page(page); return ret; } /* * swap_count_continued - when the original swap_map count is incremented * from SWAP_MAP_MAX, check if there is already a continuation page to carry * into, carry if so, or else fail until a new continuation page is allocated; * when the original swap_map count is decremented from 0 with continuation, * borrow from the continuation and report whether it still holds more. * Called while __swap_duplicate() or swap_entry_free() holds swap or cluster * lock. */ static bool swap_count_continued(struct swap_info_struct *si, pgoff_t offset, unsigned char count) { struct page *head; struct page *page; unsigned char *map; bool ret; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head) != SWP_CONTINUED) { BUG_ON(count & COUNT_CONTINUED); return false; /* need to add count continuation */ } spin_lock(&si->cont_lock); offset &= ~PAGE_MASK; page = list_entry(head->lru.next, struct page, lru); map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ if (count == (SWAP_MAP_MAX | COUNT_CONTINUED)) { /* incrementing */ /* * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); if (page == head) { ret = false; /* add count continuation */ goto out; } map = kmap_atomic(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); while (page != head) { map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); } ret = true; /* incremented */ } else { /* decrementing */ /* * Think of how you subtract 1 from 1000 */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); BUG_ON(page == head); map = kmap_atomic(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); while (page != head) { map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); } ret = count == COUNT_CONTINUED; } out: spin_unlock(&si->cont_lock); return ret; } /* * free_swap_count_continuations - swapoff free all the continuation pages * appended to the swap_map, after swap_map is quiesced, before vfree'ing it. */ static void free_swap_count_continuations(struct swap_info_struct *si) { pgoff_t offset; for (offset = 0; offset < si->max; offset += PAGE_SIZE) { struct page *head; head = vmalloc_to_page(si->swap_map + offset); if (page_private(head)) { struct page *page, *next; list_for_each_entry_safe(page, next, &head->lru, lru) { list_del(&page->lru); __free_page(page); } } } } #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void mem_cgroup_throttle_swaprate(struct mem_cgroup *memcg, int node, gfp_t gfp_mask) { struct swap_info_struct *si, *next; if (!(gfp_mask & __GFP_IO) || !memcg) return; if (!blk_cgroup_congested()) return; /* * We've already scheduled a throttle, avoid taking the global swap * lock. */ if (current->throttle_queue) return; spin_lock(&swap_avail_lock); plist_for_each_entry_safe(si, next, &swap_avail_heads[node], avail_lists[node]) { if (si->bdev) { blkcg_schedule_throttle(bdev_get_queue(si->bdev), true); break; } } spin_unlock(&swap_avail_lock); } #endif static int __init swapfile_init(void) { int nid; swap_avail_heads = kmalloc_array(nr_node_ids, sizeof(struct plist_head), GFP_KERNEL); if (!swap_avail_heads) { pr_emerg("Not enough memory for swap heads, swap is disabled\n"); return -ENOMEM; } for_each_node(nid) plist_head_init(&swap_avail_heads[nid]); return 0; } subsys_initcall(swapfile_init); |
| 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 | // SPDX-License-Identifier: GPL-2.0 /* * To speed up listener socket lookup, create an array to store all sockets * listening on the same port. This allows a decision to be made after finding * the first socket. An optional BPF program can also be configured for * selecting the socket index from the array of available sockets. */ #include <net/sock_reuseport.h> #include <linux/bpf.h> #include <linux/idr.h> #include <linux/filter.h> #include <linux/rcupdate.h> #define INIT_SOCKS 128 DEFINE_SPINLOCK(reuseport_lock); #define REUSEPORT_MIN_ID 1 static DEFINE_IDA(reuseport_ida); int reuseport_get_id(struct sock_reuseport *reuse) { int id; if (reuse->reuseport_id) return reuse->reuseport_id; id = ida_simple_get(&reuseport_ida, REUSEPORT_MIN_ID, 0, /* Called under reuseport_lock */ GFP_ATOMIC); if (id < 0) return id; reuse->reuseport_id = id; return reuse->reuseport_id; } static struct sock_reuseport *__reuseport_alloc(unsigned int max_socks) { unsigned int size = sizeof(struct sock_reuseport) + sizeof(struct sock *) * max_socks; struct sock_reuseport *reuse = kzalloc(size, GFP_ATOMIC); if (!reuse) return NULL; reuse->max_socks = max_socks; RCU_INIT_POINTER(reuse->prog, NULL); return reuse; } int reuseport_alloc(struct sock *sk, bool bind_inany) { struct sock_reuseport *reuse; /* bh lock used since this function call may precede hlist lock in * soft irq of receive path or setsockopt from process context */ spin_lock_bh(&reuseport_lock); /* Allocation attempts can occur concurrently via the setsockopt path * and the bind/hash path. Nothing to do when we lose the race. */ reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (reuse) { /* Only set reuse->bind_inany if the bind_inany is true. * Otherwise, it will overwrite the reuse->bind_inany * which was set by the bind/hash path. */ if (bind_inany) reuse->bind_inany = bind_inany; goto out; } reuse = __reuseport_alloc(INIT_SOCKS); if (!reuse) { spin_unlock_bh(&reuseport_lock); return -ENOMEM; } reuse->socks[0] = sk; reuse->num_socks = 1; reuse->bind_inany = bind_inany; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); out: spin_unlock_bh(&reuseport_lock); return 0; } EXPORT_SYMBOL(reuseport_alloc); static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) { struct sock_reuseport *more_reuse; u32 more_socks_size, i; more_socks_size = reuse->max_socks * 2U; if (more_socks_size > U16_MAX) return NULL; more_reuse = __reuseport_alloc(more_socks_size); if (!more_reuse) return NULL; more_reuse->max_socks = more_socks_size; more_reuse->num_socks = reuse->num_socks; more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; more_reuse->has_conns = reuse->has_conns; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); more_reuse->synq_overflow_ts = READ_ONCE(reuse->synq_overflow_ts); for (i = 0; i < reuse->num_socks; ++i) rcu_assign_pointer(reuse->socks[i]->sk_reuseport_cb, more_reuse); /* Note: we use kfree_rcu here instead of reuseport_free_rcu so * that reuse and more_reuse can temporarily share a reference * to prog. */ kfree_rcu(reuse, rcu); return more_reuse; } static void reuseport_free_rcu(struct rcu_head *head) { struct sock_reuseport *reuse; reuse = container_of(head, struct sock_reuseport, rcu); sk_reuseport_prog_free(rcu_dereference_protected(reuse->prog, 1)); if (reuse->reuseport_id) ida_simple_remove(&reuseport_ida, reuse->reuseport_id); kfree(reuse); } /** * reuseport_add_sock - Add a socket to the reuseport group of another. * @sk: New socket to add to the group. * @sk2: Socket belonging to the existing reuseport group. * @bind_inany: Whether or not the group is bound to a local INANY address. * * May return ENOMEM and not add socket to group under memory pressure. */ int reuseport_add_sock(struct sock *sk, struct sock *sk2, bool bind_inany) { struct sock_reuseport *old_reuse, *reuse; if (!rcu_access_pointer(sk2->sk_reuseport_cb)) { int err = reuseport_alloc(sk2, bind_inany); if (err) return err; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk2->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); if (old_reuse && old_reuse->num_socks != 1) { spin_unlock_bh(&reuseport_lock); return -EBUSY; } if (reuse->num_socks == reuse->max_socks) { reuse = reuseport_grow(reuse); if (!reuse) { spin_unlock_bh(&reuseport_lock); return -ENOMEM; } } reuse->socks[reuse->num_socks] = sk; /* paired with smp_rmb() in reuseport_select_sock() */ smp_wmb(); reuse->num_socks++; rcu_assign_pointer(sk->sk_reuseport_cb, reuse); spin_unlock_bh(&reuseport_lock); if (old_reuse) call_rcu(&old_reuse->rcu, reuseport_free_rcu); return 0; } EXPORT_SYMBOL(reuseport_add_sock); void reuseport_detach_sock(struct sock *sk) { struct sock_reuseport *reuse; int i; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); /* At least one of the sk in this reuseport group is added to * a bpf map. Notify the bpf side. The bpf map logic will * remove the sk if it is indeed added to a bpf map. */ if (reuse->reuseport_id) bpf_sk_reuseport_detach(sk); rcu_assign_pointer(sk->sk_reuseport_cb, NULL); for (i = 0; i < reuse->num_socks; i++) { if (reuse->socks[i] == sk) { reuse->socks[i] = reuse->socks[reuse->num_socks - 1]; reuse->num_socks--; if (reuse->num_socks == 0) call_rcu(&reuse->rcu, reuseport_free_rcu); break; } } spin_unlock_bh(&reuseport_lock); } EXPORT_SYMBOL(reuseport_detach_sock); static struct sock *run_bpf_filter(struct sock_reuseport *reuse, u16 socks, struct bpf_prog *prog, struct sk_buff *skb, int hdr_len) { struct sk_buff *nskb = NULL; u32 index; if (skb_shared(skb)) { nskb = skb_clone(skb, GFP_ATOMIC); if (!nskb) return NULL; skb = nskb; } /* temporarily advance data past protocol header */ if (!pskb_pull(skb, hdr_len)) { kfree_skb(nskb); return NULL; } index = bpf_prog_run_save_cb(prog, skb); __skb_push(skb, hdr_len); consume_skb(nskb); if (index >= socks) return NULL; return reuse->socks[index]; } /** * reuseport_select_sock - Select a socket from an SO_REUSEPORT group. * @sk: First socket in the group. * @hash: When no BPF filter is available, use this hash to select. * @skb: skb to run through BPF filter. * @hdr_len: BPF filter expects skb data pointer at payload data. If * the skb does not yet point at the payload, this parameter represents * how far the pointer needs to advance to reach the payload. * Returns a socket that should receive the packet (or NULL on error). */ struct sock *reuseport_select_sock(struct sock *sk, u32 hash, struct sk_buff *skb, int hdr_len) { struct sock_reuseport *reuse; struct bpf_prog *prog; struct sock *sk2 = NULL; u16 socks; rcu_read_lock(); reuse = rcu_dereference(sk->sk_reuseport_cb); /* if memory allocation failed or add call is not yet complete */ if (!reuse) goto out; prog = rcu_dereference(reuse->prog); socks = READ_ONCE(reuse->num_socks); if (likely(socks)) { /* paired with smp_wmb() in reuseport_add_sock() */ smp_rmb(); if (!prog || !skb) goto select_by_hash; if (prog->type == BPF_PROG_TYPE_SK_REUSEPORT) sk2 = bpf_run_sk_reuseport(reuse, sk, prog, skb, hash); else sk2 = run_bpf_filter(reuse, socks, prog, skb, hdr_len); select_by_hash: /* no bpf or invalid bpf result: fall back to hash usage */ if (!sk2) { int i, j; i = j = reciprocal_scale(hash, socks); while (reuse->socks[i]->sk_state == TCP_ESTABLISHED) { i++; if (i >= socks) i = 0; if (i == j) goto out; } sk2 = reuse->socks[i]; } } out: rcu_read_unlock(); return sk2; } EXPORT_SYMBOL(reuseport_select_sock); int reuseport_attach_prog(struct sock *sk, struct bpf_prog *prog) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; if (sk_unhashed(sk) && sk->sk_reuseport) { int err = reuseport_alloc(sk, false); if (err) return err; } else if (!rcu_access_pointer(sk->sk_reuseport_cb)) { /* The socket wasn't bound with SO_REUSEPORT */ return -EINVAL; } spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); old_prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); rcu_assign_pointer(reuse->prog, prog); spin_unlock_bh(&reuseport_lock); sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_attach_prog); int reuseport_detach_prog(struct sock *sk) { struct sock_reuseport *reuse; struct bpf_prog *old_prog; if (!rcu_access_pointer(sk->sk_reuseport_cb)) return sk->sk_reuseport ? -ENOENT : -EINVAL; old_prog = NULL; spin_lock_bh(&reuseport_lock); reuse = rcu_dereference_protected(sk->sk_reuseport_cb, lockdep_is_held(&reuseport_lock)); rcu_swap_protected(reuse->prog, old_prog, lockdep_is_held(&reuseport_lock)); spin_unlock_bh(&reuseport_lock); if (!old_prog) return -ENOENT; sk_reuseport_prog_free(old_prog); return 0; } EXPORT_SYMBOL(reuseport_detach_prog); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_HWEIGHT_H #define _ASM_X86_HWEIGHT_H #include <asm/cpufeatures.h> #ifdef CONFIG_64BIT #define REG_IN "D" #define REG_OUT "a" #else #define REG_IN "a" #define REG_OUT "a" #endif static __always_inline unsigned int __arch_hweight32(unsigned int w) { unsigned int res; asm (ALTERNATIVE("call __sw_hweight32", "popcntl %1, %0", X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); return res; } static inline unsigned int __arch_hweight16(unsigned int w) { return __arch_hweight32(w & 0xffff); } static inline unsigned int __arch_hweight8(unsigned int w) { return __arch_hweight32(w & 0xff); } #ifdef CONFIG_X86_32 static inline unsigned long __arch_hweight64(__u64 w) { return __arch_hweight32((u32)w) + __arch_hweight32((u32)(w >> 32)); } #else static __always_inline unsigned long __arch_hweight64(__u64 w) { unsigned long res; asm (ALTERNATIVE("call __sw_hweight64", "popcntq %1, %0", X86_FEATURE_POPCNT) : "="REG_OUT (res) : REG_IN (w)); return res; } #endif /* CONFIG_X86_32 */ #endif |
| 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * This is a module which is used for logging packets to userspace via * nfetlink. * * (C) 2005 by Harald Welte <laforge@netfilter.org> * (C) 2006-2012 Patrick McHardy <kaber@trash.net> * * Based on the old ipv4-only ipt_ULOG.c: * (C) 2000-2004 by Harald Welte <laforge@netfilter.org> */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/skbuff.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/ip.h> #include <linux/ipv6.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/netfilter_bridge.h> #include <net/netlink.h> #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_log.h> #include <linux/netfilter/nf_conntrack_common.h> #include <linux/spinlock.h> #include <linux/sysctl.h> #include <linux/proc_fs.h> #include <linux/security.h> #include <linux/list.h> #include <linux/slab.h> #include <net/sock.h> #include <net/netfilter/nf_log.h> #include <net/netns/generic.h> #include <linux/atomic.h> #include <linux/refcount.h> #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) #include "../bridge/br_private.h" #endif #define NFULNL_COPY_DISABLED 0xff #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ /* max packet size is limited by 16-bit struct nfattr nfa_len field */ #define NFULNL_COPY_RANGE_MAX (0xFFFF - NLA_HDRLEN) #define PRINTR(x, args...) do { if (net_ratelimit()) \ printk(x, ## args); } while (0); struct nfulnl_instance { struct hlist_node hlist; /* global list of instances */ spinlock_t lock; refcount_t use; /* use count */ unsigned int qlen; /* number of nlmsgs in skb */ struct sk_buff *skb; /* pre-allocatd skb */ struct timer_list timer; struct net *net; struct user_namespace *peer_user_ns; /* User namespace of the peer process */ u32 peer_portid; /* PORTID of the peer process */ /* configurable parameters */ unsigned int flushtimeout; /* timeout until queue flush */ unsigned int nlbufsiz; /* netlink buffer allocation size */ unsigned int qthreshold; /* threshold of the queue */ u_int32_t copy_range; u_int32_t seq; /* instance-local sequential counter */ u_int16_t group_num; /* number of this queue */ u_int16_t flags; u_int8_t copy_mode; struct rcu_head rcu; }; #define INSTANCE_BUCKETS 16 static unsigned int nfnl_log_net_id __read_mostly; struct nfnl_log_net { spinlock_t instances_lock; struct hlist_head instance_table[INSTANCE_BUCKETS]; atomic_t global_seq; }; static struct nfnl_log_net *nfnl_log_pernet(struct net *net) { return net_generic(net, nfnl_log_net_id); } static inline u_int8_t instance_hashfn(u_int16_t group_num) { return ((group_num & 0xff) % INSTANCE_BUCKETS); } static struct nfulnl_instance * __instance_lookup(struct nfnl_log_net *log, u_int16_t group_num) { struct hlist_head *head; struct nfulnl_instance *inst; head = &log->instance_table[instance_hashfn(group_num)]; hlist_for_each_entry_rcu(inst, head, hlist) { if (inst->group_num == group_num) return inst; } return NULL; } static inline void instance_get(struct nfulnl_instance *inst) { refcount_inc(&inst->use); } static struct nfulnl_instance * instance_lookup_get(struct nfnl_log_net *log, u_int16_t group_num) { struct nfulnl_instance *inst; rcu_read_lock_bh(); inst = __instance_lookup(log, group_num); if (inst && !refcount_inc_not_zero(&inst->use)) inst = NULL; rcu_read_unlock_bh(); return inst; } static void nfulnl_instance_free_rcu(struct rcu_head *head) { struct nfulnl_instance *inst = container_of(head, struct nfulnl_instance, rcu); put_net(inst->net); kfree(inst); module_put(THIS_MODULE); } static void instance_put(struct nfulnl_instance *inst) { if (inst && refcount_dec_and_test(&inst->use)) call_rcu(&inst->rcu, nfulnl_instance_free_rcu); } static void nfulnl_timer(struct timer_list *t); static struct nfulnl_instance * instance_create(struct net *net, u_int16_t group_num, u32 portid, struct user_namespace *user_ns) { struct nfulnl_instance *inst; struct nfnl_log_net *log = nfnl_log_pernet(net); int err; spin_lock_bh(&log->instances_lock); if (__instance_lookup(log, group_num)) { err = -EEXIST; goto out_unlock; } inst = kzalloc(sizeof(*inst), GFP_ATOMIC); if (!inst) { err = -ENOMEM; goto out_unlock; } if (!try_module_get(THIS_MODULE)) { kfree(inst); err = -EAGAIN; goto out_unlock; } INIT_HLIST_NODE(&inst->hlist); spin_lock_init(&inst->lock); /* needs to be two, since we _put() after creation */ refcount_set(&inst->use, 2); timer_setup(&inst->timer, nfulnl_timer, 0); inst->net = get_net(net); inst->peer_user_ns = user_ns; inst->peer_portid = portid; inst->group_num = group_num; inst->qthreshold = NFULNL_QTHRESH_DEFAULT; inst->flushtimeout = NFULNL_TIMEOUT_DEFAULT; inst->nlbufsiz = NFULNL_NLBUFSIZ_DEFAULT; inst->copy_mode = NFULNL_COPY_PACKET; inst->copy_range = NFULNL_COPY_RANGE_MAX; hlist_add_head_rcu(&inst->hlist, &log->instance_table[instance_hashfn(group_num)]); spin_unlock_bh(&log->instances_lock); return inst; out_unlock: spin_unlock_bh(&log->instances_lock); return ERR_PTR(err); } static void __nfulnl_flush(struct nfulnl_instance *inst); /* called with BH disabled */ static void __instance_destroy(struct nfulnl_instance *inst) { /* first pull it out of the global list */ hlist_del_rcu(&inst->hlist); /* then flush all pending packets from skb */ spin_lock(&inst->lock); /* lockless readers wont be able to use us */ inst->copy_mode = NFULNL_COPY_DISABLED; if (inst->skb) __nfulnl_flush(inst); spin_unlock(&inst->lock); /* and finally put the refcount */ instance_put(inst); } static inline void instance_destroy(struct nfnl_log_net *log, struct nfulnl_instance *inst) { spin_lock_bh(&log->instances_lock); __instance_destroy(inst); spin_unlock_bh(&log->instances_lock); } static int nfulnl_set_mode(struct nfulnl_instance *inst, u_int8_t mode, unsigned int range) { int status = 0; spin_lock_bh(&inst->lock); switch (mode) { case NFULNL_COPY_NONE: case NFULNL_COPY_META: inst->copy_mode = mode; inst->copy_range = 0; break; case NFULNL_COPY_PACKET: inst->copy_mode = mode; if (range == 0) range = NFULNL_COPY_RANGE_MAX; inst->copy_range = min_t(unsigned int, range, NFULNL_COPY_RANGE_MAX); break; default: status = -EINVAL; break; } spin_unlock_bh(&inst->lock); return status; } static int nfulnl_set_nlbufsiz(struct nfulnl_instance *inst, u_int32_t nlbufsiz) { int status; spin_lock_bh(&inst->lock); if (nlbufsiz < NFULNL_NLBUFSIZ_DEFAULT) status = -ERANGE; else if (nlbufsiz > 131072) status = -ERANGE; else { inst->nlbufsiz = nlbufsiz; status = 0; } spin_unlock_bh(&inst->lock); return status; } static void nfulnl_set_timeout(struct nfulnl_instance *inst, u_int32_t timeout) { spin_lock_bh(&inst->lock); inst->flushtimeout = timeout; spin_unlock_bh(&inst->lock); } static void nfulnl_set_qthresh(struct nfulnl_instance *inst, u_int32_t qthresh) { spin_lock_bh(&inst->lock); inst->qthreshold = qthresh; spin_unlock_bh(&inst->lock); } static int nfulnl_set_flags(struct nfulnl_instance *inst, u_int16_t flags) { spin_lock_bh(&inst->lock); inst->flags = flags; spin_unlock_bh(&inst->lock); return 0; } static struct sk_buff * nfulnl_alloc_skb(struct net *net, u32 peer_portid, unsigned int inst_size, unsigned int pkt_size) { struct sk_buff *skb; unsigned int n; /* alloc skb which should be big enough for a whole multipart * message. WARNING: has to be <= 128k due to slab restrictions */ n = max(inst_size, pkt_size); skb = alloc_skb(n, GFP_ATOMIC | __GFP_NOWARN); if (!skb) { if (n > pkt_size) { /* try to allocate only as much as we need for current * packet */ skb = alloc_skb(pkt_size, GFP_ATOMIC); } } return skb; } static void __nfulnl_send(struct nfulnl_instance *inst) { if (inst->qlen > 1) { struct nlmsghdr *nlh = nlmsg_put(inst->skb, 0, 0, NLMSG_DONE, sizeof(struct nfgenmsg), 0); if (WARN_ONCE(!nlh, "bad nlskb size: %u, tailroom %d\n", inst->skb->len, skb_tailroom(inst->skb))) { kfree_skb(inst->skb); goto out; } } nfnetlink_unicast(inst->skb, inst->net, inst->peer_portid); out: inst->qlen = 0; inst->skb = NULL; } static void __nfulnl_flush(struct nfulnl_instance *inst) { /* timer holds a reference */ if (del_timer(&inst->timer)) instance_put(inst); if (inst->skb) __nfulnl_send(inst); } static void nfulnl_timer(struct timer_list *t) { struct nfulnl_instance *inst = from_timer(inst, t, timer); spin_lock_bh(&inst->lock); if (inst->skb) __nfulnl_send(inst); spin_unlock_bh(&inst->lock); instance_put(inst); } static u32 nfulnl_get_bridge_size(const struct sk_buff *skb) { u32 size = 0; if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_present(skb)) { size += nla_total_size(0); /* nested */ size += nla_total_size(sizeof(u16)); /* id */ size += nla_total_size(sizeof(u16)); /* tag */ } if (skb->network_header > skb->mac_header) size += nla_total_size(skb->network_header - skb->mac_header); return size; } static int nfulnl_put_bridge(struct nfulnl_instance *inst, const struct sk_buff *skb) { if (!skb_mac_header_was_set(skb)) return 0; if (skb_vlan_tag_present(skb)) { struct nlattr *nest; nest = nla_nest_start(inst->skb, NFULA_VLAN); if (!nest) goto nla_put_failure; if (nla_put_be16(inst->skb, NFULA_VLAN_TCI, htons(skb->vlan_tci)) || nla_put_be16(inst->skb, NFULA_VLAN_PROTO, skb->vlan_proto)) goto nla_put_failure; nla_nest_end(inst->skb, nest); } if (skb->mac_header < skb->network_header) { int len = (int)(skb->network_header - skb->mac_header); if (nla_put(inst->skb, NFULA_L2HDR, len, skb_mac_header(skb))) goto nla_put_failure; } return 0; nla_put_failure: return -1; } /* This is an inline function, we don't really care about a long * list of arguments */ static inline int __build_packet_message(struct nfnl_log_net *log, struct nfulnl_instance *inst, const struct sk_buff *skb, unsigned int data_len, u_int8_t pf, unsigned int hooknum, const struct net_device *indev, const struct net_device *outdev, const char *prefix, unsigned int plen, const struct nfnl_ct_hook *nfnl_ct, struct nf_conn *ct, enum ip_conntrack_info ctinfo) { struct nfulnl_msg_packet_hdr pmsg; struct nlmsghdr *nlh; sk_buff_data_t old_tail = inst->skb->tail; struct sock *sk; const unsigned char *hwhdrp; nlh = nfnl_msg_put(inst->skb, 0, 0, nfnl_msg_type(NFNL_SUBSYS_ULOG, NFULNL_MSG_PACKET), 0, pf, NFNETLINK_V0, htons(inst->group_num)); if (!nlh) return -1; memset(&pmsg, 0, sizeof(pmsg)); pmsg.hw_protocol = skb->protocol; pmsg.hook = hooknum; if (nla_put(inst->skb, NFULA_PACKET_HDR, sizeof(pmsg), &pmsg)) goto nla_put_failure; if (prefix && nla_put(inst->skb, NFULA_PREFIX, plen, prefix)) goto nla_put_failure; if (indev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical input device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(indev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(br_port_get_rcu(indev)->br->dev->ifindex))) goto nla_put_failure; } else { struct net_device *physindev; /* Case 2: indev is bridge group, we need to look for * physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_INDEV, htonl(indev->ifindex))) goto nla_put_failure; physindev = nf_bridge_get_physindev(skb); if (physindev && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSINDEV, htonl(physindev->ifindex))) goto nla_put_failure; } #endif } if (outdev) { #if !IS_ENABLED(CONFIG_BRIDGE_NETFILTER) if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; #else if (pf == PF_BRIDGE) { /* Case 1: outdev is physical output device, we need to * look for bridge group (when called from * netfilter_bridge) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(outdev->ifindex)) || /* this is the bridge group "brX" */ /* rcu_read_lock()ed by nf_hook_thresh or * nf_log_packet. */ nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(br_port_get_rcu(outdev)->br->dev->ifindex))) goto nla_put_failure; } else { struct net_device *physoutdev; /* Case 2: indev is a bridge group, we need to look * for physical device (when called from ipv4) */ if (nla_put_be32(inst->skb, NFULA_IFINDEX_OUTDEV, htonl(outdev->ifindex))) goto nla_put_failure; physoutdev = nf_bridge_get_physoutdev(skb); if (physoutdev && nla_put_be32(inst->skb, NFULA_IFINDEX_PHYSOUTDEV, htonl(physoutdev->ifindex))) goto nla_put_failure; } #endif } if (skb->mark && nla_put_be32(inst->skb, NFULA_MARK, htonl(skb->mark))) goto nla_put_failure; if (indev && skb->dev && skb_mac_header_was_set(skb) && skb_mac_header_len(skb) != 0) { struct nfulnl_msg_packet_hw phw; int len; memset(&phw, 0, sizeof(phw)); len = dev_parse_header(skb, phw.hw_addr); if (len > 0) { phw.hw_addrlen = htons(len); if (nla_put(inst->skb, NFULA_HWADDR, sizeof(phw), &phw)) goto nla_put_failure; } } if (indev && skb_mac_header_was_set(skb)) { if (nla_put_be16(inst->skb, NFULA_HWTYPE, htons(skb->dev->type)) || nla_put_be16(inst->skb, NFULA_HWLEN, htons(skb->dev->hard_header_len))) goto nla_put_failure; hwhdrp = skb_mac_header(skb); if (skb->dev->type == ARPHRD_SIT) hwhdrp -= ETH_HLEN; if (hwhdrp >= skb->head && nla_put(inst->skb, NFULA_HWHEADER, skb->dev->hard_header_len, hwhdrp)) goto nla_put_failure; } if (hooknum <= NF_INET_FORWARD && skb->tstamp) { struct nfulnl_msg_packet_timestamp ts; struct timespec64 kts = ktime_to_timespec64(skb->tstamp); ts.sec = cpu_to_be64(kts.tv_sec); ts.usec = cpu_to_be64(kts.tv_nsec / NSEC_PER_USEC); if (nla_put(inst->skb, NFULA_TIMESTAMP, sizeof(ts), &ts)) goto nla_put_failure; } /* UID */ sk = skb->sk; if (sk && sk_fullsock(sk)) { read_lock_bh(&sk->sk_callback_lock); if (sk->sk_socket && sk->sk_socket->file) { struct file *file = sk->sk_socket->file; const struct cred *cred = file->f_cred; struct user_namespace *user_ns = inst->peer_user_ns; __be32 uid = htonl(from_kuid_munged(user_ns, cred->fsuid)); __be32 gid = htonl(from_kgid_munged(user_ns, cred->fsgid)); read_unlock_bh(&sk->sk_callback_lock); if (nla_put_be32(inst->skb, NFULA_UID, uid) || nla_put_be32(inst->skb, NFULA_GID, gid)) goto nla_put_failure; } else read_unlock_bh(&sk->sk_callback_lock); } /* local sequence number */ if ((inst->flags & NFULNL_CFG_F_SEQ) && nla_put_be32(inst->skb, NFULA_SEQ, htonl(inst->seq++))) goto nla_put_failure; /* global sequence number */ if ((inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) && nla_put_be32(inst->skb, NFULA_SEQ_GLOBAL, htonl(atomic_inc_return(&log->global_seq)))) goto nla_put_failure; if (ct && nfnl_ct->build(inst->skb, ct, ctinfo, NFULA_CT, NFULA_CT_INFO) < 0) goto nla_put_failure; if ((pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) && nfulnl_put_bridge(inst, skb) < 0) goto nla_put_failure; if (data_len) { struct nlattr *nla; int size = nla_attr_size(data_len); if (skb_tailroom(inst->skb) < nla_total_size(data_len)) goto nla_put_failure; nla = skb_put(inst->skb, nla_total_size(data_len)); nla->nla_type = NFULA_PAYLOAD; nla->nla_len = size; if (skb_copy_bits(skb, 0, nla_data(nla), data_len)) BUG(); } nlh->nlmsg_len = inst->skb->tail - old_tail; return 0; nla_put_failure: PRINTR(KERN_ERR "nfnetlink_log: error creating log nlmsg\n"); return -1; } static const struct nf_loginfo default_loginfo = { .type = NF_LOG_TYPE_ULOG, .u = { .ulog = { .copy_len = 0xffff, .group = 0, .qthreshold = 1, }, }, }; /* log handler for internal netfilter logging api */ static void nfulnl_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *li_user, const char *prefix) { size_t size; unsigned int data_len; struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; enum ip_conntrack_info ctinfo = 0; struct nf_conn *ct = NULL; if (li_user && li_user->type == NF_LOG_TYPE_ULOG) li = li_user; else li = &default_loginfo; inst = instance_lookup_get(log, li->u.ulog.group); if (!inst) return; if (prefix) plen = strlen(prefix) + 1; /* FIXME: do we want to make the size calculation conditional based on * what is actually present? way more branches and checks, but more * memory efficient... */ size = nlmsg_total_size(sizeof(struct nfgenmsg)) + nla_total_size(sizeof(struct nfulnl_msg_packet_hdr)) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) + nla_total_size(sizeof(u_int32_t)) /* ifindex */ + nla_total_size(sizeof(u_int32_t)) /* ifindex */ #endif + nla_total_size(sizeof(u_int32_t)) /* mark */ + nla_total_size(sizeof(u_int32_t)) /* uid */ + nla_total_size(sizeof(u_int32_t)) /* gid */ + nla_total_size(plen) /* prefix */ + nla_total_size(sizeof(struct nfulnl_msg_packet_hw)) + nla_total_size(sizeof(struct nfulnl_msg_packet_timestamp)) + nla_total_size(sizeof(struct nfgenmsg)); /* NLMSG_DONE */ if (in && skb_mac_header_was_set(skb)) { size += nla_total_size(skb->dev->hard_header_len) + nla_total_size(sizeof(u_int16_t)) /* hwtype */ + nla_total_size(sizeof(u_int16_t)); /* hwlen */ } spin_lock_bh(&inst->lock); if (inst->flags & NFULNL_CFG_F_SEQ) size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_SEQ_GLOBAL) size += nla_total_size(sizeof(u_int32_t)); if (inst->flags & NFULNL_CFG_F_CONNTRACK) { nfnl_ct = rcu_dereference(nfnl_ct_hook); if (nfnl_ct != NULL) { ct = nfnl_ct->get_ct(skb, &ctinfo); if (ct != NULL) size += nfnl_ct->build_size(ct); } } if (pf == NFPROTO_NETDEV || pf == NFPROTO_BRIDGE) size += nfulnl_get_bridge_size(skb); qthreshold = inst->qthreshold; /* per-rule qthreshold overrides per-instance */ if (li->u.ulog.qthreshold) if (qthreshold > li->u.ulog.qthreshold) qthreshold = li->u.ulog.qthreshold; switch (inst->copy_mode) { case NFULNL_COPY_META: case NFULNL_COPY_NONE: data_len = 0; break; case NFULNL_COPY_PACKET: data_len = inst->copy_range; if ((li->u.ulog.flags & NF_LOG_F_COPY_LEN) && (li->u.ulog.copy_len < data_len)) data_len = li->u.ulog.copy_len; if (data_len > skb->len) data_len = skb->len; size += nla_total_size(data_len); break; case NFULNL_COPY_DISABLED: default: goto unlock_and_release; } if (inst->skb && size > skb_tailroom(inst->skb)) { /* either the queue len is too high or we don't have * enough room in the skb left. flush to userspace. */ __nfulnl_flush(inst); } if (!inst->skb) { inst->skb = nfulnl_alloc_skb(net, inst->peer_portid, inst->nlbufsiz, size); if (!inst->skb) goto alloc_failure; } inst->qlen++; __build_packet_message(log, inst, skb, data_len, pf, hooknum, in, out, prefix, plen, nfnl_ct, ct, ctinfo); if (inst->qlen >= qthreshold) __nfulnl_flush(inst); /* timer_pending always called within inst->lock, so there * is no chance of a race here */ else if (!timer_pending(&inst->timer)) { instance_get(inst); inst->timer.expires = jiffies + (inst->flushtimeout*HZ/100); add_timer(&inst->timer); } unlock_and_release: spin_unlock_bh(&inst->lock); instance_put(inst); return; alloc_failure: /* FIXME: statistics */ goto unlock_and_release; } static int nfulnl_rcv_nl_event(struct notifier_block *this, unsigned long event, void *ptr) { struct netlink_notify *n = ptr; struct nfnl_log_net *log = nfnl_log_pernet(n->net); if (event == NETLINK_URELEASE && n->protocol == NETLINK_NETFILTER) { int i; /* destroy all instances for this portid */ spin_lock_bh(&log->instances_lock); for (i = 0; i < INSTANCE_BUCKETS; i++) { struct hlist_node *t2; struct nfulnl_instance *inst; struct hlist_head *head = &log->instance_table[i]; hlist_for_each_entry_safe(inst, t2, head, hlist) { if (n->portid == inst->peer_portid) __instance_destroy(inst); } } spin_unlock_bh(&log->instances_lock); } return NOTIFY_DONE; } static struct notifier_block nfulnl_rtnl_notifier = { .notifier_call = nfulnl_rcv_nl_event, }; static int nfulnl_recv_unsupp(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nfqa[], struct netlink_ext_ack *extack) { return -ENOTSUPP; } static struct nf_logger nfulnl_logger __read_mostly = { .name = "nfnetlink_log", .type = NF_LOG_TYPE_ULOG, .logfn = nfulnl_log_packet, .me = THIS_MODULE, }; static const struct nla_policy nfula_cfg_policy[NFULA_CFG_MAX+1] = { [NFULA_CFG_CMD] = { .len = sizeof(struct nfulnl_msg_config_cmd) }, [NFULA_CFG_MODE] = { .len = sizeof(struct nfulnl_msg_config_mode) }, [NFULA_CFG_TIMEOUT] = { .type = NLA_U32 }, [NFULA_CFG_QTHRESH] = { .type = NLA_U32 }, [NFULA_CFG_NLBUFSIZ] = { .type = NLA_U32 }, [NFULA_CFG_FLAGS] = { .type = NLA_U16 }, }; static int nfulnl_recv_config(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nfula[], struct netlink_ext_ack *extack) { struct nfgenmsg *nfmsg = nlmsg_data(nlh); u_int16_t group_num = ntohs(nfmsg->res_id); struct nfulnl_instance *inst; struct nfulnl_msg_config_cmd *cmd = NULL; struct nfnl_log_net *log = nfnl_log_pernet(net); int ret = 0; u16 flags = 0; if (nfula[NFULA_CFG_CMD]) { u_int8_t pf = nfmsg->nfgen_family; cmd = nla_data(nfula[NFULA_CFG_CMD]); /* Commands without queue context */ switch (cmd->command) { case NFULNL_CFG_CMD_PF_BIND: return nf_log_bind_pf(net, pf, &nfulnl_logger); case NFULNL_CFG_CMD_PF_UNBIND: nf_log_unbind_pf(net, pf); return 0; } } inst = instance_lookup_get(log, group_num); if (inst && inst->peer_portid != NETLINK_CB(skb).portid) { ret = -EPERM; goto out_put; } /* Check if we support these flags in first place, dependencies should * be there too not to break atomicity. */ if (nfula[NFULA_CFG_FLAGS]) { flags = ntohs(nla_get_be16(nfula[NFULA_CFG_FLAGS])); if ((flags & NFULNL_CFG_F_CONNTRACK) && !rcu_access_pointer(nfnl_ct_hook)) { #ifdef CONFIG_MODULES nfnl_unlock(NFNL_SUBSYS_ULOG); request_module("ip_conntrack_netlink"); nfnl_lock(NFNL_SUBSYS_ULOG); if (rcu_access_pointer(nfnl_ct_hook)) { ret = -EAGAIN; goto out_put; } #endif ret = -EOPNOTSUPP; goto out_put; } } if (cmd != NULL) { switch (cmd->command) { case NFULNL_CFG_CMD_BIND: if (inst) { ret = -EBUSY; goto out_put; } inst = instance_create(net, group_num, NETLINK_CB(skb).portid, sk_user_ns(NETLINK_CB(skb).sk)); if (IS_ERR(inst)) { ret = PTR_ERR(inst); goto out; } break; case NFULNL_CFG_CMD_UNBIND: if (!inst) { ret = -ENODEV; goto out; } instance_destroy(log, inst); goto out_put; default: ret = -ENOTSUPP; goto out_put; } } else if (!inst) { ret = -ENODEV; goto out; } if (nfula[NFULA_CFG_MODE]) { struct nfulnl_msg_config_mode *params = nla_data(nfula[NFULA_CFG_MODE]); nfulnl_set_mode(inst, params->copy_mode, ntohl(params->copy_range)); } if (nfula[NFULA_CFG_TIMEOUT]) { __be32 timeout = nla_get_be32(nfula[NFULA_CFG_TIMEOUT]); nfulnl_set_timeout(inst, ntohl(timeout)); } if (nfula[NFULA_CFG_NLBUFSIZ]) { __be32 nlbufsiz = nla_get_be32(nfula[NFULA_CFG_NLBUFSIZ]); nfulnl_set_nlbufsiz(inst, ntohl(nlbufsiz)); } if (nfula[NFULA_CFG_QTHRESH]) { __be32 qthresh = nla_get_be32(nfula[NFULA_CFG_QTHRESH]); nfulnl_set_qthresh(inst, ntohl(qthresh)); } if (nfula[NFULA_CFG_FLAGS]) nfulnl_set_flags(inst, flags); out_put: instance_put(inst); out: return ret; } static const struct nfnl_callback nfulnl_cb[NFULNL_MSG_MAX] = { [NFULNL_MSG_PACKET] = { .call = nfulnl_recv_unsupp, .attr_count = NFULA_MAX, }, [NFULNL_MSG_CONFIG] = { .call = nfulnl_recv_config, .attr_count = NFULA_CFG_MAX, .policy = nfula_cfg_policy }, }; static const struct nfnetlink_subsystem nfulnl_subsys = { .name = "log", .subsys_id = NFNL_SUBSYS_ULOG, .cb_count = NFULNL_MSG_MAX, .cb = nfulnl_cb, }; #ifdef CONFIG_PROC_FS struct iter_state { struct seq_net_private p; unsigned int bucket; }; static struct hlist_node *get_first(struct net *net, struct iter_state *st) { struct nfnl_log_net *log; if (!st) return NULL; log = nfnl_log_pernet(net); for (st->bucket = 0; st->bucket < INSTANCE_BUCKETS; st->bucket++) { struct hlist_head *head = &log->instance_table[st->bucket]; if (!hlist_empty(head)) return rcu_dereference_bh(hlist_first_rcu(head)); } return NULL; } static struct hlist_node *get_next(struct net *net, struct iter_state *st, struct hlist_node *h) { h = rcu_dereference_bh(hlist_next_rcu(h)); while (!h) { struct nfnl_log_net *log; struct hlist_head *head; if (++st->bucket >= INSTANCE_BUCKETS) return NULL; log = nfnl_log_pernet(net); head = &log->instance_table[st->bucket]; h = rcu_dereference_bh(hlist_first_rcu(head)); } return h; } static struct hlist_node *get_idx(struct net *net, struct iter_state *st, loff_t pos) { struct hlist_node *head; head = get_first(net, st); if (head) while (pos && (head = get_next(net, st, head))) pos--; return pos ? NULL : head; } static void *seq_start(struct seq_file *s, loff_t *pos) __acquires(rcu_bh) { rcu_read_lock_bh(); return get_idx(seq_file_net(s), s->private, *pos); } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { (*pos)++; return get_next(seq_file_net(s), s->private, v); } static void seq_stop(struct seq_file *s, void *v) __releases(rcu_bh) { rcu_read_unlock_bh(); } static int seq_show(struct seq_file *s, void *v) { const struct nfulnl_instance *inst = v; seq_printf(s, "%5u %6u %5u %1u %5u %6u %2u\n", inst->group_num, inst->peer_portid, inst->qlen, inst->copy_mode, inst->copy_range, inst->flushtimeout, refcount_read(&inst->use)); return 0; } static const struct seq_operations nful_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ static int __net_init nfnl_log_net_init(struct net *net) { unsigned int i; struct nfnl_log_net *log = nfnl_log_pernet(net); #ifdef CONFIG_PROC_FS struct proc_dir_entry *proc; kuid_t root_uid; kgid_t root_gid; #endif for (i = 0; i < INSTANCE_BUCKETS; i++) INIT_HLIST_HEAD(&log->instance_table[i]); spin_lock_init(&log->instances_lock); #ifdef CONFIG_PROC_FS proc = proc_create_net("nfnetlink_log", 0440, net->nf.proc_netfilter, &nful_seq_ops, sizeof(struct iter_state)); if (!proc) return -ENOMEM; root_uid = make_kuid(net->user_ns, 0); root_gid = make_kgid(net->user_ns, 0); if (uid_valid(root_uid) && gid_valid(root_gid)) proc_set_user(proc, root_uid, root_gid); #endif return 0; } static void __net_exit nfnl_log_net_exit(struct net *net) { struct nfnl_log_net *log = nfnl_log_pernet(net); unsigned int i; #ifdef CONFIG_PROC_FS remove_proc_entry("nfnetlink_log", net->nf.proc_netfilter); #endif nf_log_unset(net, &nfulnl_logger); for (i = 0; i < INSTANCE_BUCKETS; i++) WARN_ON_ONCE(!hlist_empty(&log->instance_table[i])); } static struct pernet_operations nfnl_log_net_ops = { .init = nfnl_log_net_init, .exit = nfnl_log_net_exit, .id = &nfnl_log_net_id, .size = sizeof(struct nfnl_log_net), }; static int __init nfnetlink_log_init(void) { int status; status = register_pernet_subsys(&nfnl_log_net_ops); if (status < 0) { pr_err("failed to register pernet ops\n"); goto out; } netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); if (status < 0) { pr_err("failed to create netlink socket\n"); goto cleanup_netlink_notifier; } status = nf_log_register(NFPROTO_UNSPEC, &nfulnl_logger); if (status < 0) { pr_err("failed to register logger\n"); goto cleanup_subsys; } return status; cleanup_subsys: nfnetlink_subsys_unregister(&nfulnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_log_net_ops); out: return status; } static void __exit nfnetlink_log_fini(void) { nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); } MODULE_DESCRIPTION("netfilter userspace logging"); MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); MODULE_LICENSE("GPL"); MODULE_ALIAS_NFNL_SUBSYS(NFNL_SUBSYS_ULOG); MODULE_ALIAS_NF_LOGGER(AF_INET, 1); MODULE_ALIAS_NF_LOGGER(AF_INET6, 1); MODULE_ALIAS_NF_LOGGER(AF_BRIDGE, 1); MODULE_ALIAS_NF_LOGGER(3, 1); /* NFPROTO_ARP */ MODULE_ALIAS_NF_LOGGER(5, 1); /* NFPROTO_NETDEV */ module_init(nfnetlink_log_init); module_exit(nfnetlink_log_fini); |
| 988 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Sleepable Read-Copy Update mechanism for mutual exclusion * * Copyright (C) IBM Corporation, 2006 * Copyright (C) Fujitsu, 2012 * * Author: Paul McKenney <paulmck@linux.ibm.com> * Lai Jiangshan <laijs@cn.fujitsu.com> * * For detailed explanation of Read-Copy Update mechanism see - * Documentation/RCU/ *.txt * */ #ifndef _LINUX_SRCU_H #define _LINUX_SRCU_H #include <linux/mutex.h> #include <linux/rcupdate.h> #include <linux/workqueue.h> #include <linux/rcu_segcblist.h> struct srcu_struct; #ifdef CONFIG_DEBUG_LOCK_ALLOC int __init_srcu_struct(struct srcu_struct *ssp, const char *name, struct lock_class_key *key); #define init_srcu_struct(ssp) \ ({ \ static struct lock_class_key __srcu_key; \ \ __init_srcu_struct((ssp), #ssp, &__srcu_key); \ }) #define __SRCU_DEP_MAP_INIT(srcu_name) .dep_map = { .name = #srcu_name }, #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ int init_srcu_struct(struct srcu_struct *ssp); #define __SRCU_DEP_MAP_INIT(srcu_name) #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_TINY_SRCU #include <linux/srcutiny.h> #elif defined(CONFIG_TREE_SRCU) #include <linux/srcutree.h> #elif defined(CONFIG_SRCU) #error "Unknown SRCU implementation specified to kernel configuration" #else /* Dummy definition for things like notifiers. Actual use gets link error. */ struct srcu_struct { }; #endif void call_srcu(struct srcu_struct *ssp, struct rcu_head *head, void (*func)(struct rcu_head *head)); void cleanup_srcu_struct(struct srcu_struct *ssp); int __srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp); void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp); void synchronize_srcu(struct srcu_struct *ssp); #ifdef CONFIG_DEBUG_LOCK_ALLOC /** * srcu_read_lock_held - might we be in SRCU read-side critical section? * @ssp: The srcu_struct structure to check * * If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU * read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC, * this assumes we are in an SRCU read-side critical section unless it can * prove otherwise. * * Checks debug_lockdep_rcu_enabled() to prevent false positives during boot * and while lockdep is disabled. * * Note that SRCU is based on its own statemachine and it doesn't * relies on normal RCU, it can be called from the CPU which * is in the idle loop from an RCU point of view or offline. */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { if (!debug_lockdep_rcu_enabled()) return 1; return lock_is_held(&ssp->dep_map); } #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ static inline int srcu_read_lock_held(const struct srcu_struct *ssp) { return 1; } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ /** * srcu_dereference_check - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * @c: condition to check for update-side use * * If PROVE_RCU is enabled, invoking this outside of an RCU read-side * critical section will result in an RCU-lockdep splat, unless @c evaluates * to 1. The @c argument will normally be a logical expression containing * lockdep_is_held() calls. */ #define srcu_dereference_check(p, ssp, c) \ __rcu_dereference_check((p), (c) || srcu_read_lock_held(ssp), __rcu) /** * srcu_dereference - fetch SRCU-protected pointer for later dereferencing * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. * * Makes rcu_dereference_check() do the dirty work. If PROVE_RCU * is enabled, invoking this outside of an RCU read-side critical * section will result in an RCU-lockdep splat. */ #define srcu_dereference(p, ssp) srcu_dereference_check((p), (ssp), 0) /** * srcu_dereference_notrace - no tracing and no lockdep calls from here * @p: the pointer to fetch and protect for later dereferencing * @ssp: pointer to the srcu_struct, which is used to check that we * really are in an SRCU read-side critical section. */ #define srcu_dereference_notrace(p, ssp) srcu_dereference_check((p), (ssp), 1) /** * srcu_read_lock - register a new reader for an SRCU-protected structure. * @ssp: srcu_struct in which to register the new reader. * * Enter an SRCU read-side critical section. Note that SRCU read-side * critical sections may be nested. However, it is illegal to * call anything that waits on an SRCU grace period for the same * srcu_struct, whether directly or indirectly. Please note that * one way to indirectly wait on an SRCU grace period is to acquire * a mutex that is held elsewhere while calling synchronize_srcu() or * synchronize_srcu_expedited(). * * Note that srcu_read_lock() and the matching srcu_read_unlock() must * occur in the same context, for example, it is illegal to invoke * srcu_read_unlock() in an irq handler if the matching srcu_read_lock() * was invoked in process context. */ static inline int srcu_read_lock(struct srcu_struct *ssp) __acquires(ssp) { int retval; retval = __srcu_read_lock(ssp); rcu_lock_acquire(&(ssp)->dep_map); return retval; } /* Used by tracing, cannot be traced and cannot invoke lockdep. */ static inline notrace int srcu_read_lock_notrace(struct srcu_struct *ssp) __acquires(ssp) { int retval; retval = __srcu_read_lock(ssp); return retval; } /** * srcu_read_unlock - unregister a old reader from an SRCU-protected structure. * @ssp: srcu_struct in which to unregister the old reader. * @idx: return value from corresponding srcu_read_lock(). * * Exit an SRCU read-side critical section. */ static inline void srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp) { WARN_ON_ONCE(idx & ~0x1); rcu_lock_release(&(ssp)->dep_map); __srcu_read_unlock(ssp, idx); } /* Used by tracing, cannot be traced and cannot call lockdep. */ static inline notrace void srcu_read_unlock_notrace(struct srcu_struct *ssp, int idx) __releases(ssp) { __srcu_read_unlock(ssp, idx); } /** * smp_mb__after_srcu_read_unlock - ensure full ordering after srcu_read_unlock * * Converts the preceding srcu_read_unlock into a two-way memory barrier. * * Call this after srcu_read_unlock, to guarantee that all memory operations * that occur after smp_mb__after_srcu_read_unlock will appear to happen after * the preceding srcu_read_unlock. */ static inline void smp_mb__after_srcu_read_unlock(void) { /* __srcu_read_unlock has smp_mb() internally so nothing to do here. */ } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_UACCESS_H #define _ASM_X86_UACCESS_H /* * User space memory access functions */ #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/string.h> #include <asm/asm.h> #include <asm/page.h> #include <asm/smap.h> #include <asm/extable.h> /* * The fs value determines whether argument validity checking should be * performed or not. If get_fs() == USER_DS, checking is performed, with * get_fs() == KERNEL_DS, checking is bypassed. * * For historical reasons, these macros are grossly misnamed. */ #define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) #define KERNEL_DS MAKE_MM_SEG(-1UL) #define USER_DS MAKE_MM_SEG(TASK_SIZE_MAX) #define get_fs() (current->thread.addr_limit) static inline void set_fs(mm_segment_t fs) { current->thread.addr_limit = fs; /* On user-mode return, check fs is correct */ set_thread_flag(TIF_FSCHECK); } #define segment_eq(a, b) ((a).seg == (b).seg) #define user_addr_max() (current->thread.addr_limit.seg) /* * Test whether a block of memory is a valid user space address. * Returns 0 if the range is valid, nonzero otherwise. */ static inline bool __chk_range_not_ok(unsigned long addr, unsigned long size, unsigned long limit) { /* * If we have used "sizeof()" for the size, * we know it won't overflow the limit (but * it might overflow the 'addr', so it's * important to subtract the size from the * limit, not add it to the address). */ if (__builtin_constant_p(size)) return unlikely(addr > limit - size); /* Arbitrary sizes? Be careful about overflow */ addr += size; if (unlikely(addr < size)) return true; return unlikely(addr > limit); } #define __range_not_ok(addr, size, limit) \ ({ \ __chk_user_ptr(addr); \ __chk_range_not_ok((unsigned long __force)(addr), size, limit); \ }) #ifdef CONFIG_DEBUG_ATOMIC_SLEEP static inline bool pagefault_disabled(void); # define WARN_ON_IN_IRQ() \ WARN_ON_ONCE(!in_task() && !pagefault_disabled()) #else # define WARN_ON_IN_IRQ() #endif /** * access_ok - Checks if a user space pointer is valid * @addr: User space pointer to start of block to check * @size: Size of block to check * * Context: User context only. This function may sleep if pagefaults are * enabled. * * Checks if a pointer to a block of memory in user space is valid. * * Note that, depending on architecture, this function probably just * checks that the pointer is in the user space range - after calling * this function, memory access functions may still return -EFAULT. * * Return: true (nonzero) if the memory block may be valid, false (zero) * if it is definitely invalid. */ #define access_ok(addr, size) \ ({ \ WARN_ON_IN_IRQ(); \ likely(!__range_not_ok(addr, size, user_addr_max())); \ }) /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. * * This gets kind of ugly. We want to return _two_ values in "get_user()" * and yet we don't want to do any pointers, because that is too much * of a performance impact. Thus we have a few rather ugly macros here, * and hide all the ugliness from the user. * * The "__xxx" versions of the user access functions are versions that * do not verify the address space, that must have been done previously * with a separate "access_ok()" call (this is used when we do multiple * accesses to the same area of user memory). */ extern int __get_user_1(void); extern int __get_user_2(void); extern int __get_user_4(void); extern int __get_user_8(void); extern int __get_user_bad(void); #define __uaccess_begin() stac() #define __uaccess_end() clac() #define __uaccess_begin_nospec() \ ({ \ stac(); \ barrier_nospec(); \ }) /* * This is a type: either unsigned long, if the argument fits into * that type, or otherwise unsigned long long. */ #define __inttype(x) \ __typeof__(__builtin_choose_expr(sizeof(x) > sizeof(0UL), 0ULL, 0UL)) /** * get_user - Get a simple variable from user space. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ /* * Careful: we have to cast the result to the type of the pointer * for sign reasons. * * The use of _ASM_DX as the register specifier is a bit of a * simplification, as gcc only cares about it as the starting point * and not size: for a 64-bit value it will use %ecx:%edx on 32 bits * (%ecx being the next register in gcc's x86 register sequence), and * %rdx on 64 bits. * * Clang/LLVM cares about the size of the register, but still wants * the base register for something that ends up being a pair. */ #define get_user(x, ptr) \ ({ \ int __ret_gu; \ register __inttype(*(ptr)) __val_gu asm("%"_ASM_DX); \ __chk_user_ptr(ptr); \ might_fault(); \ asm volatile("call __get_user_%P4" \ : "=a" (__ret_gu), "=r" (__val_gu), \ ASM_CALL_CONSTRAINT \ : "0" (ptr), "i" (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr))) __val_gu; \ __builtin_expect(__ret_gu, 0); \ }) #define __put_user_x(size, x, ptr, __ret_pu) \ asm volatile("call __put_user_" #size : "=a" (__ret_pu) \ : "0" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #ifdef CONFIG_X86_32 #define __put_user_goto_u64(x, addr, label) \ asm_volatile_goto("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ _ASM_EXTABLE_UA(1b, %l2) \ _ASM_EXTABLE_UA(2b, %l2) \ : : "A" (x), "r" (addr) \ : : label) #define __put_user_asm_ex_u64(x, addr) \ asm volatile("\n" \ "1: movl %%eax,0(%1)\n" \ "2: movl %%edx,4(%1)\n" \ "3:" \ _ASM_EXTABLE_EX(1b, 2b) \ _ASM_EXTABLE_EX(2b, 3b) \ : : "A" (x), "r" (addr)) #define __put_user_x8(x, ptr, __ret_pu) \ asm volatile("call __put_user_8" : "=a" (__ret_pu) \ : "A" ((typeof(*(ptr)))(x)), "c" (ptr) : "ebx") #else #define __put_user_goto_u64(x, ptr, label) \ __put_user_goto(x, ptr, "q", "", "er", label) #define __put_user_asm_ex_u64(x, addr) \ __put_user_asm_ex(x, addr, "q", "", "er") #define __put_user_x8(x, ptr, __ret_pu) __put_user_x(8, x, ptr, __ret_pu) #endif extern void __put_user_bad(void); /* * Strange magic calling convention: pointer in %ecx, * value in %eax(:%edx), return value in %eax. clobbers %rbx */ extern void __put_user_1(void); extern void __put_user_2(void); extern void __put_user_4(void); extern void __put_user_8(void); /** * put_user - Write a simple value into user space. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Return: zero on success, or -EFAULT on error. */ #define put_user(x, ptr) \ ({ \ int __ret_pu; \ __typeof__(*(ptr)) __pu_val; \ __chk_user_ptr(ptr); \ might_fault(); \ __pu_val = x; \ switch (sizeof(*(ptr))) { \ case 1: \ __put_user_x(1, __pu_val, ptr, __ret_pu); \ break; \ case 2: \ __put_user_x(2, __pu_val, ptr, __ret_pu); \ break; \ case 4: \ __put_user_x(4, __pu_val, ptr, __ret_pu); \ break; \ case 8: \ __put_user_x8(__pu_val, ptr, __ret_pu); \ break; \ default: \ __put_user_x(X, __pu_val, ptr, __ret_pu); \ break; \ } \ __builtin_expect(__ret_pu, 0); \ }) #define __put_user_size(x, ptr, size, label) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __put_user_goto(x, ptr, "b", "b", "iq", label); \ break; \ case 2: \ __put_user_goto(x, ptr, "w", "w", "ir", label); \ break; \ case 4: \ __put_user_goto(x, ptr, "l", "k", "ir", label); \ break; \ case 8: \ __put_user_goto_u64(x, ptr, label); \ break; \ default: \ __put_user_bad(); \ } \ } while (0) /* * This doesn't do __uaccess_begin/end - the exception handling * around it must do that. */ #define __put_user_size_ex(x, ptr, size) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __put_user_asm_ex(x, ptr, "b", "b", "iq"); \ break; \ case 2: \ __put_user_asm_ex(x, ptr, "w", "w", "ir"); \ break; \ case 4: \ __put_user_asm_ex(x, ptr, "l", "k", "ir"); \ break; \ case 8: \ __put_user_asm_ex_u64((__typeof__(*ptr))(x), ptr); \ break; \ default: \ __put_user_bad(); \ } \ } while (0) #ifdef CONFIG_X86_32 #define __get_user_asm_u64(x, ptr, retval, errret) \ ({ \ __typeof__(ptr) __ptr = (ptr); \ asm volatile("\n" \ "1: movl %2,%%eax\n" \ "2: movl %3,%%edx\n" \ "3:\n" \ ".section .fixup,\"ax\"\n" \ "4: mov %4,%0\n" \ " xorl %%eax,%%eax\n" \ " xorl %%edx,%%edx\n" \ " jmp 3b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 4b) \ _ASM_EXTABLE_UA(2b, 4b) \ : "=r" (retval), "=&A"(x) \ : "m" (__m(__ptr)), "m" __m(((u32 __user *)(__ptr)) + 1), \ "i" (errret), "0" (retval)); \ }) #define __get_user_asm_ex_u64(x, ptr) (x) = __get_user_bad() #else #define __get_user_asm_u64(x, ptr, retval, errret) \ __get_user_asm(x, ptr, retval, "q", "", "=r", errret) #define __get_user_asm_ex_u64(x, ptr) \ __get_user_asm_ex(x, ptr, "q", "", "=r") #endif #define __get_user_size(x, ptr, size, retval, errret) \ do { \ unsigned char x_u8__; \ \ retval = 0; \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __get_user_asm(x_u8__, ptr, retval, "b", "b", "=q", errret); \ (x) = x_u8__; \ break; \ case 2: \ __get_user_asm(x, ptr, retval, "w", "w", "=r", errret); \ break; \ case 4: \ __get_user_asm(x, ptr, retval, "l", "k", "=r", errret); \ break; \ case 8: \ __get_user_asm_u64(x, ptr, retval, errret); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm(x, addr, err, itype, rtype, ltype, errret) \ asm volatile("\n" \ "1: mov"itype" %2,%"rtype"1\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3: mov %3,%0\n" \ " xor"itype" %"rtype"1,%"rtype"1\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "=r" (err), ltype(x) \ : "m" (__m(addr)), "i" (errret), "0" (err)) /* * This doesn't do __uaccess_begin/end - the exception handling * around it must do that. */ #define __get_user_size_ex(x, ptr, size) \ do { \ __chk_user_ptr(ptr); \ switch (size) { \ case 1: \ __get_user_asm_ex(x, ptr, "b", "b", "=q"); \ break; \ case 2: \ __get_user_asm_ex(x, ptr, "w", "w", "=r"); \ break; \ case 4: \ __get_user_asm_ex(x, ptr, "l", "k", "=r"); \ break; \ case 8: \ __get_user_asm_ex_u64(x, ptr); \ break; \ default: \ (x) = __get_user_bad(); \ } \ } while (0) #define __get_user_asm_ex(x, addr, itype, rtype, ltype) \ asm volatile("1: mov"itype" %1,%"rtype"0\n" \ "2:\n" \ ".section .fixup,\"ax\"\n" \ "3:xor"itype" %"rtype"0,%"rtype"0\n" \ " jmp 2b\n" \ ".previous\n" \ _ASM_EXTABLE_EX(1b, 3b) \ : ltype(x) : "m" (__m(addr))) #define __put_user_nocheck(x, ptr, size) \ ({ \ __label__ __pu_label; \ int __pu_err = -EFAULT; \ __typeof__(*(ptr)) __pu_val = (x); \ __typeof__(ptr) __pu_ptr = (ptr); \ __typeof__(size) __pu_size = (size); \ __uaccess_begin(); \ __put_user_size(__pu_val, __pu_ptr, __pu_size, __pu_label); \ __pu_err = 0; \ __pu_label: \ __uaccess_end(); \ __builtin_expect(__pu_err, 0); \ }) #define __get_user_nocheck(x, ptr, size) \ ({ \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ __typeof__(ptr) __gu_ptr = (ptr); \ __typeof__(size) __gu_size = (size); \ __uaccess_begin_nospec(); \ __get_user_size(__gu_val, __gu_ptr, __gu_size, __gu_err, -EFAULT); \ __uaccess_end(); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ __builtin_expect(__gu_err, 0); \ }) #ifdef CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm_volatile_goto("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ _ASM_EXTABLE_UA(1b, %l[label]) \ : CC_OUT(z) (success), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory" \ : label); \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #endif // CONFIG_X86_32 #else // !CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT #define __try_cmpxchg_user_asm(itype, ltype, _ptr, _pold, _new, label) ({ \ int __err = 0; \ bool success; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg"itype" %[new], %[ptr]\n"\ CC_SET(z) \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, \ %[errout]) \ : CC_OUT(z) (success), \ [errout] "+r" (__err), \ [ptr] "+m" (*_ptr), \ [old] "+a" (__old) \ : [new] ltype (__new) \ : "memory"); \ if (unlikely(__err)) \ goto label; \ if (unlikely(!success)) \ *_old = __old; \ likely(success); }) #ifdef CONFIG_X86_32 /* * Unlike the normal CMPXCHG, hardcode ECX for both success/fail and error. * There are only six GPRs available and four (EAX, EBX, ECX, and EDX) are * hardcoded by CMPXCHG8B, leaving only ESI and EDI. If the compiler uses * both ESI and EDI for the memory operand, compilation will fail if the error * is an input+output as there will be no register available for input. */ #define __try_cmpxchg64_user_asm(_ptr, _pold, _new, label) ({ \ int __result; \ __typeof__(_ptr) _old = (__typeof__(_ptr))(_pold); \ __typeof__(*(_ptr)) __old = *_old; \ __typeof__(*(_ptr)) __new = (_new); \ asm volatile("\n" \ "1: " LOCK_PREFIX "cmpxchg8b %[ptr]\n" \ "mov $0, %%ecx\n\t" \ "setz %%cl\n" \ "2:\n" \ _ASM_EXTABLE_TYPE_REG(1b, 2b, EX_TYPE_EFAULT_REG, %%ecx) \ : [result]"=c" (__result), \ "+A" (__old), \ [ptr] "+m" (*_ptr) \ : "b" ((u32)__new), \ "c" ((u32)((u64)__new >> 32)) \ : "memory", "cc"); \ if (unlikely(__result < 0)) \ goto label; \ if (unlikely(!__result)) \ *_old = __old; \ likely(__result); }) #endif // CONFIG_X86_32 #endif // CONFIG_CC_HAS_ASM_GOTO_TIED_OUTPUT /* FIXME: this hack is definitely wrong -AK */ struct __large_struct { unsigned long buf[100]; }; #define __m(x) (*(struct __large_struct __user *)(x)) /* * Tell gcc we read from memory instead of writing: this is because * we do not write to any memory gcc knows about, so there are no * aliasing issues. */ #define __put_user_goto(x, addr, itype, rtype, ltype, label) \ asm_volatile_goto("\n" \ "1: mov"itype" %"rtype"0,%1\n" \ _ASM_EXTABLE_UA(1b, %l2) \ : : ltype(x), "m" (__m(addr)) \ : : label) #define __put_user_failed(x, addr, itype, rtype, ltype, errret) \ ({ __label__ __puflab; \ int __pufret = errret; \ __put_user_goto(x,addr,itype,rtype,ltype,__puflab); \ __pufret = 0; \ __puflab: __pufret; }) #define __put_user_asm(x, addr, retval, itype, rtype, ltype, errret) do { \ retval = __put_user_failed(x, addr, itype, rtype, ltype, errret); \ } while (0) #define __put_user_asm_ex(x, addr, itype, rtype, ltype) \ asm volatile("1: mov"itype" %"rtype"0,%1\n" \ "2:\n" \ _ASM_EXTABLE_EX(1b, 2b) \ : : ltype(x), "m" (__m(addr))) /* * uaccess_try and catch */ #define uaccess_try do { \ current->thread.uaccess_err = 0; \ __uaccess_begin(); \ barrier(); #define uaccess_try_nospec do { \ current->thread.uaccess_err = 0; \ __uaccess_begin_nospec(); \ #define uaccess_catch(err) \ __uaccess_end(); \ (err) |= (current->thread.uaccess_err ? -EFAULT : 0); \ } while (0) /** * __get_user - Get a simple variable from user space, with less checking. * @x: Variable to store result. * @ptr: Source address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple variable from user space to kernel * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and the result of * dereferencing @ptr must be assignable to @x without a cast. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. * On error, the variable @x is set to zero. */ #define __get_user(x, ptr) \ __get_user_nocheck((x), (ptr), sizeof(*(ptr))) /** * __put_user - Write a simple value into user space, with less checking. * @x: Value to copy to user space. * @ptr: Destination address, in user space. * * Context: User context only. This function may sleep if pagefaults are * enabled. * * This macro copies a single simple value from kernel space to user * space. It supports simple types like char and int, but not larger * data types like structures or arrays. * * @ptr must have pointer-to-simple-variable type, and @x must be assignable * to the result of dereferencing @ptr. * * Caller must check the pointer with access_ok() before calling this * function. * * Return: zero on success, or -EFAULT on error. */ #define __put_user(x, ptr) \ __put_user_nocheck((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) /* * {get|put}_user_try and catch * * get_user_try { * get_user_ex(...); * } get_user_catch(err) */ #define get_user_try uaccess_try_nospec #define get_user_catch(err) uaccess_catch(err) #define get_user_ex(x, ptr) do { \ unsigned long __gue_val; \ __get_user_size_ex((__gue_val), (ptr), (sizeof(*(ptr)))); \ (x) = (__force __typeof__(*(ptr)))__gue_val; \ } while (0) #define put_user_try uaccess_try #define put_user_catch(err) uaccess_catch(err) #define put_user_ex(x, ptr) \ __put_user_size_ex((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr))) extern unsigned long copy_from_user_nmi(void *to, const void __user *from, unsigned long n); extern __must_check long strncpy_from_user(char *dst, const char __user *src, long count); extern __must_check long strnlen_user(const char __user *str, long n); unsigned long __must_check clear_user(void __user *mem, unsigned long len); unsigned long __must_check __clear_user(void __user *mem, unsigned long len); extern void __cmpxchg_wrong_size(void) __compiletime_error("Bad argument size for cmpxchg"); #define __user_atomic_cmpxchg_inatomic(uval, ptr, old, new, size) \ ({ \ int __ret = 0; \ __typeof__(*(ptr)) __old = (old); \ __typeof__(*(ptr)) __new = (new); \ __uaccess_begin_nospec(); \ switch (size) { \ case 1: \ { \ asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgb %4, %2\n" \ "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "q" (__new), "1" (__old) \ : "memory" \ ); \ break; \ } \ case 2: \ { \ asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgw %4, %2\n" \ "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "r" (__new), "1" (__old) \ : "memory" \ ); \ break; \ } \ case 4: \ { \ asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgl %4, %2\n" \ "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "r" (__new), "1" (__old) \ : "memory" \ ); \ break; \ } \ case 8: \ { \ if (!IS_ENABLED(CONFIG_X86_64)) \ __cmpxchg_wrong_size(); \ \ asm volatile("\n" \ "1:\t" LOCK_PREFIX "cmpxchgq %4, %2\n" \ "2:\n" \ "\t.section .fixup, \"ax\"\n" \ "3:\tmov %3, %0\n" \ "\tjmp 2b\n" \ "\t.previous\n" \ _ASM_EXTABLE_UA(1b, 3b) \ : "+r" (__ret), "=a" (__old), "+m" (*(ptr)) \ : "i" (-EFAULT), "r" (__new), "1" (__old) \ : "memory" \ ); \ break; \ } \ default: \ __cmpxchg_wrong_size(); \ } \ __uaccess_end(); \ *(uval) = __old; \ __ret; \ }) #define user_atomic_cmpxchg_inatomic(uval, ptr, old, new) \ ({ \ access_ok((ptr), sizeof(*(ptr))) ? \ __user_atomic_cmpxchg_inatomic((uval), (ptr), \ (old), (new), sizeof(*(ptr))) : \ -EFAULT; \ }) /* * movsl can be slow when source and dest are not both 8-byte aligned */ #ifdef CONFIG_X86_INTEL_USERCOPY extern struct movsl_mask { int mask; } ____cacheline_aligned_in_smp movsl_mask; #endif #define ARCH_HAS_NOCACHE_UACCESS 1 #ifdef CONFIG_X86_32 # include <asm/uaccess_32.h> #else # include <asm/uaccess_64.h> #endif /* * We rely on the nested NMI work to allow atomic faults from the NMI path; the * nested NMI paths are careful to preserve CR2. * * Caller must use pagefault_enable/disable, or run in interrupt context, * and also do a uaccess_ok() check */ #define __copy_from_user_nmi __copy_from_user_inatomic /* * The "unsafe" user accesses aren't really "unsafe", but the naming * is a big fat warning: you have to not only do the access_ok() * checking before using them, but you have to surround them with the * user_access_begin/end() pair. */ static __must_check __always_inline bool user_access_begin(const void __user *ptr, size_t len) { if (unlikely(!access_ok(ptr,len))) return 0; __uaccess_begin_nospec(); return 1; } #define user_access_begin(a,b) user_access_begin(a,b) #define user_access_end() __uaccess_end() #define user_access_save() smap_save() #define user_access_restore(x) smap_restore(x) #define unsafe_put_user(x, ptr, label) \ __put_user_size((__typeof__(*(ptr)))(x), (ptr), sizeof(*(ptr)), label) #define unsafe_get_user(x, ptr, err_label) \ do { \ int __gu_err; \ __inttype(*(ptr)) __gu_val; \ __get_user_size(__gu_val, (ptr), sizeof(*(ptr)), __gu_err, -EFAULT); \ (x) = (__force __typeof__(*(ptr)))__gu_val; \ if (unlikely(__gu_err)) goto err_label; \ } while (0) extern void __try_cmpxchg_user_wrong_size(void); #ifndef CONFIG_X86_32 #define __try_cmpxchg64_user_asm(_ptr, _oldp, _nval, _label) \ __try_cmpxchg_user_asm("q", "r", (_ptr), (_oldp), (_nval), _label) #endif /* * Force the pointer to u<size> to match the size expected by the asm helper. * clang/LLVM compiles all cases and only discards the unused paths after * processing errors, which breaks i386 if the pointer is an 8-byte value. */ #define unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ bool __ret; \ __chk_user_ptr(_ptr); \ switch (sizeof(*(_ptr))) { \ case 1: __ret = __try_cmpxchg_user_asm("b", "q", \ (__force u8 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 2: __ret = __try_cmpxchg_user_asm("w", "r", \ (__force u16 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 4: __ret = __try_cmpxchg_user_asm("l", "r", \ (__force u32 *)(_ptr), (_oldp), \ (_nval), _label); \ break; \ case 8: __ret = __try_cmpxchg64_user_asm((__force u64 *)(_ptr), (_oldp),\ (_nval), _label); \ break; \ default: __try_cmpxchg_user_wrong_size(); \ } \ __ret; }) /* "Returns" 0 on success, 1 on failure, -EFAULT if the access faults. */ #define __try_cmpxchg_user(_ptr, _oldp, _nval, _label) ({ \ int __ret = -EFAULT; \ __uaccess_begin_nospec(); \ __ret = !unsafe_try_cmpxchg_user(_ptr, _oldp, _nval, _label); \ _label: \ __uaccess_end(); \ __ret; \ }) /* * We want the unsafe accessors to always be inlined and use * the error labels - thus the macro games. */ #define unsafe_copy_loop(dst, src, len, type, label) \ while (len >= sizeof(type)) { \ unsafe_put_user(*(type *)src,(type __user *)dst,label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } #define unsafe_copy_to_user(_dst,_src,_len,label) \ do { \ char __user *__ucu_dst = (_dst); \ const char *__ucu_src = (_src); \ size_t __ucu_len = (_len); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u64, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u32, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u16, label); \ unsafe_copy_loop(__ucu_dst, __ucu_src, __ucu_len, u8, label); \ } while (0) #endif /* _ASM_X86_UACCESS_H */ |
| 2152 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * include/linux/idr.h * * 2002-10-18 written by Jim Houston jim.houston@ccur.com * Copyright (C) 2002 by Concurrent Computer Corporation * * Small id to pointer translation service avoiding fixed sized * tables. */ #ifndef __IDR_H__ #define __IDR_H__ #include <linux/radix-tree.h> #include <linux/gfp.h> #include <linux/percpu.h> struct idr { struct radix_tree_root idr_rt; unsigned int idr_base; unsigned int idr_next; }; /* * The IDR API does not expose the tagging functionality of the radix tree * to users. Use tag 0 to track whether a node has free space below it. */ #define IDR_FREE 0 /* Set the IDR flag and the IDR_FREE tag */ #define IDR_RT_MARKER (ROOT_IS_IDR | (__force gfp_t) \ (1 << (ROOT_TAG_SHIFT + IDR_FREE))) #define IDR_INIT_BASE(name, base) { \ .idr_rt = RADIX_TREE_INIT(name, IDR_RT_MARKER), \ .idr_base = (base), \ .idr_next = 0, \ } /** * IDR_INIT() - Initialise an IDR. * @name: Name of IDR. * * A freshly-initialised IDR contains no IDs. */ #define IDR_INIT(name) IDR_INIT_BASE(name, 0) /** * DEFINE_IDR() - Define a statically-allocated IDR. * @name: Name of IDR. * * An IDR defined using this macro is ready for use with no additional * initialisation required. It contains no IDs. */ #define DEFINE_IDR(name) struct idr name = IDR_INIT(name) /** * idr_get_cursor - Return the current position of the cyclic allocator * @idr: idr handle * * The value returned is the value that will be next returned from * idr_alloc_cyclic() if it is free (otherwise the search will start from * this position). */ static inline unsigned int idr_get_cursor(const struct idr *idr) { return READ_ONCE(idr->idr_next); } /** * idr_set_cursor - Set the current position of the cyclic allocator * @idr: idr handle * @val: new position * * The next call to idr_alloc_cyclic() will return @val if it is free * (otherwise the search will start from this position). */ static inline void idr_set_cursor(struct idr *idr, unsigned int val) { WRITE_ONCE(idr->idr_next, val); } /** * DOC: idr sync * idr synchronization (stolen from radix-tree.h) * * idr_find() is able to be called locklessly, using RCU. The caller must * ensure calls to this function are made within rcu_read_lock() regions. * Other readers (lock-free or otherwise) and modifications may be running * concurrently. * * It is still required that the caller manage the synchronization and * lifetimes of the items. So if RCU lock-free lookups are used, typically * this would mean that the items have their own locks, or are amenable to * lock-free access; and that the items are freed by RCU (or only freed after * having been deleted from the idr tree *and* a synchronize_rcu() grace * period). */ #define idr_lock(idr) xa_lock(&(idr)->idr_rt) #define idr_unlock(idr) xa_unlock(&(idr)->idr_rt) #define idr_lock_bh(idr) xa_lock_bh(&(idr)->idr_rt) #define idr_unlock_bh(idr) xa_unlock_bh(&(idr)->idr_rt) #define idr_lock_irq(idr) xa_lock_irq(&(idr)->idr_rt) #define idr_unlock_irq(idr) xa_unlock_irq(&(idr)->idr_rt) #define idr_lock_irqsave(idr, flags) \ xa_lock_irqsave(&(idr)->idr_rt, flags) #define idr_unlock_irqrestore(idr, flags) \ xa_unlock_irqrestore(&(idr)->idr_rt, flags) void idr_preload(gfp_t gfp_mask); int idr_alloc(struct idr *, void *ptr, int start, int end, gfp_t); int __must_check idr_alloc_u32(struct idr *, void *ptr, u32 *id, unsigned long max, gfp_t); int idr_alloc_cyclic(struct idr *, void *ptr, int start, int end, gfp_t); void *idr_remove(struct idr *, unsigned long id); void *idr_find(const struct idr *, unsigned long id); int idr_for_each(const struct idr *, int (*fn)(int id, void *p, void *data), void *data); void *idr_get_next(struct idr *, int *nextid); void *idr_get_next_ul(struct idr *, unsigned long *nextid); void *idr_replace(struct idr *, void *, unsigned long id); void idr_destroy(struct idr *); /** * idr_init_base() - Initialise an IDR. * @idr: IDR handle. * @base: The base value for the IDR. * * This variation of idr_init() creates an IDR which will allocate IDs * starting at %base. */ static inline void idr_init_base(struct idr *idr, int base) { INIT_RADIX_TREE(&idr->idr_rt, IDR_RT_MARKER); idr->idr_base = base; idr->idr_next = 0; } /** * idr_init() - Initialise an IDR. * @idr: IDR handle. * * Initialise a dynamically allocated IDR. To initialise a * statically allocated IDR, use DEFINE_IDR(). */ static inline void idr_init(struct idr *idr) { idr_init_base(idr, 0); } /** * idr_is_empty() - Are there any IDs allocated? * @idr: IDR handle. * * Return: %true if any IDs have been allocated from this IDR. */ static inline bool idr_is_empty(const struct idr *idr) { return radix_tree_empty(&idr->idr_rt) && radix_tree_tagged(&idr->idr_rt, IDR_FREE); } /** * idr_preload_end - end preload section started with idr_preload() * * Each idr_preload() should be matched with an invocation of this * function. See idr_preload() for details. */ static inline void idr_preload_end(void) { preempt_enable(); } /** * idr_for_each_entry() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry(idr, entry, id) \ for (id = 0; ((entry) = idr_get_next(idr, &(id))) != NULL; id += 1U) /** * idr_for_each_entry_ul() - Iterate over an IDR's elements of a given type. * @idr: IDR handle. * @entry: The type * to use as cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * @entry and @id do not need to be initialized before the loop, and * after normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_ul(idr, entry, tmp, id) \ for (tmp = 0, id = 0; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /** * idr_for_each_entry_continue() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. */ #define idr_for_each_entry_continue(idr, entry, id) \ for ((entry) = idr_get_next((idr), &(id)); \ entry; \ ++id, (entry) = idr_get_next((idr), &(id))) /** * idr_for_each_entry_continue_ul() - Continue iteration over an IDR's elements of a given type * @idr: IDR handle. * @entry: The type * to use as a cursor. * @tmp: A temporary placeholder for ID. * @id: Entry ID. * * Continue to iterate over entries, continuing after the current position. * After normal termination @entry is left with the value NULL. This * is convenient for a "not found" value. */ #define idr_for_each_entry_continue_ul(idr, entry, tmp, id) \ for (tmp = id; \ ((entry) = tmp <= id ? idr_get_next_ul(idr, &(id)) : NULL) != NULL; \ tmp = id, ++id) /* * IDA - ID Allocator, use when translation from id to pointer isn't necessary. */ #define IDA_CHUNK_SIZE 128 /* 128 bytes per chunk */ #define IDA_BITMAP_LONGS (IDA_CHUNK_SIZE / sizeof(long)) #define IDA_BITMAP_BITS (IDA_BITMAP_LONGS * sizeof(long) * 8) struct ida_bitmap { unsigned long bitmap[IDA_BITMAP_LONGS]; }; struct ida { struct xarray xa; }; #define IDA_INIT_FLAGS (XA_FLAGS_LOCK_IRQ | XA_FLAGS_ALLOC) #define IDA_INIT(name) { \ .xa = XARRAY_INIT(name, IDA_INIT_FLAGS) \ } #define DEFINE_IDA(name) struct ida name = IDA_INIT(name) int ida_alloc_range(struct ida *, unsigned int min, unsigned int max, gfp_t); void ida_free(struct ida *, unsigned int id); void ida_destroy(struct ida *ida); /** * ida_alloc() - Allocate an unused ID. * @ida: IDA handle. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and %INT_MAX, inclusive. * * Context: Any context. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc(struct ida *ida, gfp_t gfp) { return ida_alloc_range(ida, 0, ~0, gfp); } /** * ida_alloc_min() - Allocate an unused ID. * @ida: IDA handle. * @min: Lowest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between @min and %INT_MAX, inclusive. * * Context: Any context. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_min(struct ida *ida, unsigned int min, gfp_t gfp) { return ida_alloc_range(ida, min, ~0, gfp); } /** * ida_alloc_max() - Allocate an unused ID. * @ida: IDA handle. * @max: Highest ID to allocate. * @gfp: Memory allocation flags. * * Allocate an ID between 0 and @max, inclusive. * * Context: Any context. * Return: The allocated ID, or %-ENOMEM if memory could not be allocated, * or %-ENOSPC if there are no free IDs. */ static inline int ida_alloc_max(struct ida *ida, unsigned int max, gfp_t gfp) { return ida_alloc_range(ida, 0, max, gfp); } static inline void ida_init(struct ida *ida) { xa_init_flags(&ida->xa, IDA_INIT_FLAGS); } #define ida_simple_get(ida, start, end, gfp) \ ida_alloc_range(ida, start, (end) - 1, gfp) #define ida_simple_remove(ida, id) ida_free(ida, id) static inline bool ida_is_empty(const struct ida *ida) { return xa_empty(&ida->xa); } #endif /* __IDR_H__ */ |
| 74 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/skbuff.h> #include <linux/netfilter.h> #include <linux/seq_file.h> #include <net/protocol.h> #include <net/netfilter/nf_log.h> #include "nf_internals.h" /* Internal logging interface, which relies on the real LOG target modules */ #define NFLOGGER_NAME_LEN 64 int sysctl_nf_log_all_netns __read_mostly; EXPORT_SYMBOL(sysctl_nf_log_all_netns); static struct nf_logger __rcu *loggers[NFPROTO_NUMPROTO][NF_LOG_TYPE_MAX] __read_mostly; static DEFINE_MUTEX(nf_log_mutex); #define nft_log_dereference(logger) \ rcu_dereference_protected(logger, lockdep_is_held(&nf_log_mutex)) static struct nf_logger *__find_logger(int pf, const char *str_logger) { struct nf_logger *log; int i; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[pf][i] == NULL) continue; log = nft_log_dereference(loggers[pf][i]); if (!strncasecmp(str_logger, log->name, strlen(log->name))) return log; } return NULL; } int nf_log_set(struct net *net, u_int8_t pf, const struct nf_logger *logger) { const struct nf_logger *log; if (pf == NFPROTO_UNSPEC || pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EOPNOTSUPP; mutex_lock(&nf_log_mutex); log = nft_log_dereference(net->nf.nf_loggers[pf]); if (log == NULL) rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_set); void nf_log_unset(struct net *net, const struct nf_logger *logger) { int i; const struct nf_logger *log; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(net->nf.nf_loggers[i]); if (log == logger) RCU_INIT_POINTER(net->nf.nf_loggers[i], NULL); } mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unset); /* return EEXIST if the same logger is registered, 0 on success. */ int nf_log_register(u_int8_t pf, struct nf_logger *logger) { int i; int ret = 0; if (pf >= ARRAY_SIZE(init_net.nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (pf == NFPROTO_UNSPEC) { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { if (rcu_access_pointer(loggers[i][logger->type])) { ret = -EEXIST; goto unlock; } } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) rcu_assign_pointer(loggers[i][logger->type], logger); } else { if (rcu_access_pointer(loggers[pf][logger->type])) { ret = -EEXIST; goto unlock; } rcu_assign_pointer(loggers[pf][logger->type], logger); } unlock: mutex_unlock(&nf_log_mutex); return ret; } EXPORT_SYMBOL(nf_log_register); void nf_log_unregister(struct nf_logger *logger) { const struct nf_logger *log; int i; mutex_lock(&nf_log_mutex); for (i = 0; i < NFPROTO_NUMPROTO; i++) { log = nft_log_dereference(loggers[i][logger->type]); if (log == logger) RCU_INIT_POINTER(loggers[i][logger->type], NULL); } mutex_unlock(&nf_log_mutex); synchronize_rcu(); } EXPORT_SYMBOL(nf_log_unregister); int nf_log_bind_pf(struct net *net, u_int8_t pf, const struct nf_logger *logger) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return -EINVAL; mutex_lock(&nf_log_mutex); if (__find_logger(pf, logger->name) == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[pf], logger); mutex_unlock(&nf_log_mutex); return 0; } EXPORT_SYMBOL(nf_log_bind_pf); void nf_log_unbind_pf(struct net *net, u_int8_t pf) { if (pf >= ARRAY_SIZE(net->nf.nf_loggers)) return; mutex_lock(&nf_log_mutex); RCU_INIT_POINTER(net->nf.nf_loggers[pf], NULL); mutex_unlock(&nf_log_mutex); } EXPORT_SYMBOL(nf_log_unbind_pf); void nf_logger_request_module(int pf, enum nf_log_type type) { if (loggers[pf][type] == NULL) request_module("nf-logger-%u-%u", pf, type); } EXPORT_SYMBOL_GPL(nf_logger_request_module); int nf_logger_find_get(int pf, enum nf_log_type type) { struct nf_logger *logger; int ret = -ENOENT; if (pf == NFPROTO_INET) { ret = nf_logger_find_get(NFPROTO_IPV4, type); if (ret < 0) return ret; ret = nf_logger_find_get(NFPROTO_IPV6, type); if (ret < 0) { nf_logger_put(NFPROTO_IPV4, type); return ret; } return 0; } if (rcu_access_pointer(loggers[pf][type]) == NULL) request_module("nf-logger-%u-%u", pf, type); rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (logger == NULL) goto out; if (try_module_get(logger->me)) ret = 0; out: rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(nf_logger_find_get); void nf_logger_put(int pf, enum nf_log_type type) { struct nf_logger *logger; if (pf == NFPROTO_INET) { nf_logger_put(NFPROTO_IPV4, type); nf_logger_put(NFPROTO_IPV6, type); return; } rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); if (!logger) WARN_ON_ONCE(1); else module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); void nf_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); if (loginfo != NULL) logger = rcu_dereference(loggers[pf][loginfo->type]); else logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_packet); void nf_log_trace(struct net *net, u_int8_t pf, unsigned int hooknum, const struct sk_buff *skb, const struct net_device *in, const struct net_device *out, const struct nf_loginfo *loginfo, const char *fmt, ...) { va_list args; char prefix[NF_LOG_PREFIXLEN]; const struct nf_logger *logger; rcu_read_lock(); logger = rcu_dereference(net->nf.nf_loggers[pf]); if (logger) { va_start(args, fmt); vsnprintf(prefix, sizeof(prefix), fmt, args); va_end(args); logger->logfn(net, pf, hooknum, skb, in, out, loginfo, prefix); } rcu_read_unlock(); } EXPORT_SYMBOL(nf_log_trace); #define S_SIZE (1024 - (sizeof(unsigned int) + 1)) struct nf_log_buf { unsigned int count; char buf[S_SIZE + 1]; }; static struct nf_log_buf emergency, *emergency_ptr = &emergency; __printf(2, 3) int nf_log_buf_add(struct nf_log_buf *m, const char *f, ...) { va_list args; int len; if (likely(m->count < S_SIZE)) { va_start(args, f); len = vsnprintf(m->buf + m->count, S_SIZE - m->count, f, args); va_end(args); if (likely(m->count + len < S_SIZE)) { m->count += len; return 0; } } m->count = S_SIZE; printk_once(KERN_ERR KBUILD_MODNAME " please increase S_SIZE\n"); return -1; } EXPORT_SYMBOL_GPL(nf_log_buf_add); struct nf_log_buf *nf_log_buf_open(void) { struct nf_log_buf *m = kmalloc(sizeof(*m), GFP_ATOMIC); if (unlikely(!m)) { local_bh_disable(); do { m = xchg(&emergency_ptr, NULL); } while (!m); } m->count = 0; return m; } EXPORT_SYMBOL_GPL(nf_log_buf_open); void nf_log_buf_close(struct nf_log_buf *m) { m->buf[m->count] = 0; printk("%s\n", m->buf); if (likely(m != &emergency)) kfree(m); else { emergency_ptr = m; local_bh_enable(); } } EXPORT_SYMBOL_GPL(nf_log_buf_close); #ifdef CONFIG_PROC_FS static void *seq_start(struct seq_file *seq, loff_t *pos) { struct net *net = seq_file_net(seq); mutex_lock(&nf_log_mutex); if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void *seq_next(struct seq_file *s, void *v, loff_t *pos) { struct net *net = seq_file_net(s); (*pos)++; if (*pos >= ARRAY_SIZE(net->nf.nf_loggers)) return NULL; return pos; } static void seq_stop(struct seq_file *s, void *v) { mutex_unlock(&nf_log_mutex); } static int seq_show(struct seq_file *s, void *v) { loff_t *pos = v; const struct nf_logger *logger; int i; struct net *net = seq_file_net(s); logger = nft_log_dereference(net->nf.nf_loggers[*pos]); if (!logger) seq_printf(s, "%2lld NONE (", *pos); else seq_printf(s, "%2lld %s (", *pos, logger->name); if (seq_has_overflowed(s)) return -ENOSPC; for (i = 0; i < NF_LOG_TYPE_MAX; i++) { if (loggers[*pos][i] == NULL) continue; logger = nft_log_dereference(loggers[*pos][i]); seq_puts(s, logger->name); if (i == 0 && loggers[*pos][i + 1] != NULL) seq_puts(s, ","); if (seq_has_overflowed(s)) return -ENOSPC; } seq_puts(s, ")\n"); if (seq_has_overflowed(s)) return -ENOSPC; return 0; } static const struct seq_operations nflog_seq_ops = { .start = seq_start, .next = seq_next, .stop = seq_stop, .show = seq_show, }; #endif /* PROC_FS */ #ifdef CONFIG_SYSCTL static char nf_log_sysctl_fnames[NFPROTO_NUMPROTO-NFPROTO_UNSPEC][3]; static struct ctl_table nf_log_sysctl_table[NFPROTO_NUMPROTO+1]; static struct ctl_table_header *nf_log_sysctl_fhdr; static struct ctl_table nf_log_sysctl_ftable[] = { { .procname = "nf_log_all_netns", .data = &sysctl_nf_log_all_netns, .maxlen = sizeof(sysctl_nf_log_all_netns), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static int nf_log_proc_dostring(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { const struct nf_logger *logger; char buf[NFLOGGER_NAME_LEN]; int r = 0; int tindex = (unsigned long)table->extra1; struct net *net = table->extra2; if (write) { struct ctl_table tmp = *table; /* proc_dostring() can append to existing strings, so we need to * initialize it as an empty string. */ buf[0] = '\0'; tmp.data = buf; r = proc_dostring(&tmp, write, buffer, lenp, ppos); if (r) return r; if (!strcmp(buf, "NONE")) { nf_log_unbind_pf(net, tindex); return 0; } mutex_lock(&nf_log_mutex); logger = __find_logger(tindex, buf); if (logger == NULL) { mutex_unlock(&nf_log_mutex); return -ENOENT; } rcu_assign_pointer(net->nf.nf_loggers[tindex], logger); mutex_unlock(&nf_log_mutex); } else { struct ctl_table tmp = *table; tmp.data = buf; mutex_lock(&nf_log_mutex); logger = nft_log_dereference(net->nf.nf_loggers[tindex]); if (!logger) strlcpy(buf, "NONE", sizeof(buf)); else strlcpy(buf, logger->name, sizeof(buf)); mutex_unlock(&nf_log_mutex); r = proc_dostring(&tmp, write, buffer, lenp, ppos); } return r; } static int netfilter_log_sysctl_init(struct net *net) { int i; struct ctl_table *table; table = nf_log_sysctl_table; if (!net_eq(net, &init_net)) { table = kmemdup(nf_log_sysctl_table, sizeof(nf_log_sysctl_table), GFP_KERNEL); if (!table) goto err_alloc; } else { for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) { snprintf(nf_log_sysctl_fnames[i], 3, "%d", i); nf_log_sysctl_table[i].procname = nf_log_sysctl_fnames[i]; nf_log_sysctl_table[i].maxlen = NFLOGGER_NAME_LEN; nf_log_sysctl_table[i].mode = 0644; nf_log_sysctl_table[i].proc_handler = nf_log_proc_dostring; nf_log_sysctl_table[i].extra1 = (void *)(unsigned long) i; } nf_log_sysctl_fhdr = register_net_sysctl(net, "net/netfilter", nf_log_sysctl_ftable); if (!nf_log_sysctl_fhdr) goto err_freg; } for (i = NFPROTO_UNSPEC; i < NFPROTO_NUMPROTO; i++) table[i].extra2 = net; net->nf.nf_log_dir_header = register_net_sysctl(net, "net/netfilter/nf_log", table); if (!net->nf.nf_log_dir_header) goto err_reg; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); err_freg: err_alloc: return -ENOMEM; } static void netfilter_log_sysctl_exit(struct net *net) { struct ctl_table *table; table = net->nf.nf_log_dir_header->ctl_table_arg; unregister_net_sysctl_table(net->nf.nf_log_dir_header); if (!net_eq(net, &init_net)) kfree(table); else unregister_net_sysctl_table(nf_log_sysctl_fhdr); } #else static int netfilter_log_sysctl_init(struct net *net) { return 0; } static void netfilter_log_sysctl_exit(struct net *net) { } #endif /* CONFIG_SYSCTL */ static int __net_init nf_log_net_init(struct net *net) { int ret = -ENOMEM; #ifdef CONFIG_PROC_FS if (!proc_create_net("nf_log", 0444, net->nf.proc_netfilter, &nflog_seq_ops, sizeof(struct seq_net_private))) return ret; #endif ret = netfilter_log_sysctl_init(net); if (ret < 0) goto out_sysctl; return 0; out_sysctl: #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif return ret; } static void __net_exit nf_log_net_exit(struct net *net) { netfilter_log_sysctl_exit(net); #ifdef CONFIG_PROC_FS remove_proc_entry("nf_log", net->nf.proc_netfilter); #endif } static struct pernet_operations nf_log_net_ops = { .init = nf_log_net_init, .exit = nf_log_net_exit, }; int __init netfilter_log_init(void) { return register_pernet_subsys(&nf_log_net_ops); } |
| 360 360 13 13 13 13 13 13 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/readahead.c - address_space-level file readahead. * * Copyright (C) 2002, Linus Torvalds * * 09Apr2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/export.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/task_io_accounting_ops.h> #include <linux/pagevec.h> #include <linux/pagemap.h> #include <linux/syscalls.h> #include <linux/file.h> #include <linux/mm_inline.h> #include <linux/blk-cgroup.h> #include <linux/fadvise.h> #include "internal.h" /* * Initialise a struct file's readahead state. Assumes that the caller has * memset *ra to zero. */ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); /* * see if a page needs releasing upon read_cache_pages() failure * - the caller of read_cache_pages() may have set PG_private or PG_fscache * before calling, such as the NFS fs marking pages that are cached locally * on disk, thus we need to give the fs a chance to clean up in the event of * an error */ static void read_cache_pages_invalidate_page(struct address_space *mapping, struct page *page) { if (page_has_private(page)) { if (!trylock_page(page)) BUG(); page->mapping = mapping; do_invalidatepage(page, 0, PAGE_SIZE); page->mapping = NULL; unlock_page(page); } put_page(page); } /* * release a list of pages, invalidating them first if need be */ static void read_cache_pages_invalidate_pages(struct address_space *mapping, struct list_head *pages) { struct page *victim; while (!list_empty(pages)) { victim = lru_to_page(pages); list_del(&victim->lru); read_cache_pages_invalidate_page(mapping, victim); } } /** * read_cache_pages - populate an address space with some pages & start reads against them * @mapping: the address_space * @pages: The address of a list_head which contains the target pages. These * pages have their ->index populated and are otherwise uninitialised. * @filler: callback routine for filling a single page. * @data: private data for the callback routine. * * Hides the details of the LRU cache etc from the filesystems. * * Returns: %0 on success, error return by @filler otherwise */ int read_cache_pages(struct address_space *mapping, struct list_head *pages, int (*filler)(void *, struct page *), void *data) { struct page *page; int ret = 0; while (!list_empty(pages)) { page = lru_to_page(pages); list_del(&page->lru); if (add_to_page_cache_lru(page, mapping, page->index, readahead_gfp_mask(mapping))) { read_cache_pages_invalidate_page(mapping, page); continue; } put_page(page); ret = filler(data, page); if (unlikely(ret)) { read_cache_pages_invalidate_pages(mapping, pages); break; } task_io_account_read(PAGE_SIZE); } return ret; } EXPORT_SYMBOL(read_cache_pages); static int read_pages(struct address_space *mapping, struct file *filp, struct list_head *pages, unsigned int nr_pages, gfp_t gfp) { struct blk_plug plug; unsigned page_idx; int ret; blk_start_plug(&plug); if (mapping->a_ops->readpages) { ret = mapping->a_ops->readpages(filp, mapping, pages, nr_pages); /* Clean up the remaining pages */ put_pages_list(pages); goto out; } for (page_idx = 0; page_idx < nr_pages; page_idx++) { struct page *page = lru_to_page(pages); list_del(&page->lru); if (!add_to_page_cache_lru(page, mapping, page->index, gfp)) mapping->a_ops->readpage(filp, page); put_page(page); } ret = 0; out: blk_finish_plug(&plug); return ret; } /* * __do_page_cache_readahead() actually reads a chunk of disk. It allocates * the pages first, then submits them for I/O. This avoids the very bad * behaviour which would occur if page allocations are causing VM writeback. * We really don't want to intermingle reads and writes like that. * * Returns the number of pages requested, or the maximum amount of I/O allowed. */ unsigned int __do_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read, unsigned long lookahead_size) { struct inode *inode = mapping->host; struct page *page; unsigned long end_index; /* The last page we want to read */ LIST_HEAD(page_pool); int page_idx; unsigned int nr_pages = 0; loff_t isize = i_size_read(inode); gfp_t gfp_mask = readahead_gfp_mask(mapping); if (isize == 0) goto out; end_index = ((isize - 1) >> PAGE_SHIFT); /* * Preallocate as many pages as we will need. */ for (page_idx = 0; page_idx < nr_to_read; page_idx++) { pgoff_t page_offset = offset + page_idx; if (page_offset > end_index) break; page = xa_load(&mapping->i_pages, page_offset); if (page && !xa_is_value(page)) { /* * Page already present? Kick off the current batch of * contiguous pages before continuing with the next * batch. */ if (nr_pages) read_pages(mapping, filp, &page_pool, nr_pages, gfp_mask); nr_pages = 0; continue; } page = __page_cache_alloc(gfp_mask); if (!page) break; page->index = page_offset; list_add(&page->lru, &page_pool); if (page_idx == nr_to_read - lookahead_size) SetPageReadahead(page); nr_pages++; } /* * Now start the IO. We ignore I/O errors - if the page is not * uptodate then the caller will launch readpage again, and * will then handle the error. */ if (nr_pages) read_pages(mapping, filp, &page_pool, nr_pages, gfp_mask); BUG_ON(!list_empty(&page_pool)); out: return nr_pages; } /* * Chunk the readahead into 2 megabyte units, so that we don't pin too much * memory at once. */ int force_page_cache_readahead(struct address_space *mapping, struct file *filp, pgoff_t offset, unsigned long nr_to_read) { struct backing_dev_info *bdi = inode_to_bdi(mapping->host); struct file_ra_state *ra = &filp->f_ra; unsigned long max_pages; if (unlikely(!mapping->a_ops->readpage && !mapping->a_ops->readpages)) return -EINVAL; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ max_pages = max_t(unsigned long, bdi->io_pages, ra->ra_pages); nr_to_read = min(nr_to_read, max_pages); while (nr_to_read) { unsigned long this_chunk = (2 * 1024 * 1024) / PAGE_SIZE; if (this_chunk > nr_to_read) this_chunk = nr_to_read; __do_page_cache_readahead(mapping, filp, offset, this_chunk, 0); offset += this_chunk; nr_to_read -= this_chunk; } return 0; } /* * Set the initial window size, round to next power of 2 and square * for small size, x 4 for medium, and x 2 for large * for 128k (32 page) max ra * 1-8 page = 32k initial, > 8 page = 128k initial */ static unsigned long get_init_ra_size(unsigned long size, unsigned long max) { unsigned long newsize = roundup_pow_of_two(size); if (newsize <= max / 32) newsize = newsize * 4; else if (newsize <= max / 4) newsize = newsize * 2; else newsize = max; return newsize; } /* * Get the previous window size, ramp it up, and * return it as the new window size. */ static unsigned long get_next_ra_size(struct file_ra_state *ra, unsigned long max) { unsigned long cur = ra->size; if (cur < max / 16) return 4 * cur; if (cur <= max / 2) return 2 * cur; return max; } /* * On-demand readahead design. * * The fields in struct file_ra_state represent the most-recently-executed * readahead attempt: * * |<----- async_size ---------| * |------------------- size -------------------->| * |==================#===========================| * ^start ^page marked with PG_readahead * * To overlap application thinking time and disk I/O time, we do * `readahead pipelining': Do not wait until the application consumed all * readahead pages and stalled on the missing page at readahead_index; * Instead, submit an asynchronous readahead I/O as soon as there are * only async_size pages left in the readahead window. Normally async_size * will be equal to size, for maximum pipelining. * * In interleaved sequential reads, concurrent streams on the same fd can * be invalidating each other's readahead state. So we flag the new readahead * page at (start+size-async_size) with PG_readahead, and use it as readahead * indicator. The flag won't be set on already cached pages, to avoid the * readahead-for-nothing fuss, saving pointless page cache lookups. * * prev_pos tracks the last visited byte in the _previous_ read request. * It should be maintained by the caller, and will be used for detecting * small random reads. Note that the readahead algorithm checks loosely * for sequential patterns. Hence interleaved reads might be served as * sequential ones. * * There is a special-case: if the first page which the application tries to * read happens to be the first page of the file, it is assumed that a linear * read is about to happen and the window is immediately set to the initial size * based on I/O request size and the max_readahead. * * The code ramps up the readahead size aggressively at first, but slow down as * it approaches max_readhead. */ /* * Count contiguously cached pages from @offset-1 to @offset-@max, * this count is a conservative estimation of * - length of the sequential read sequence, or * - thrashing threshold in memory tight systems */ static pgoff_t count_history_pages(struct address_space *mapping, pgoff_t offset, unsigned long max) { pgoff_t head; rcu_read_lock(); head = page_cache_prev_miss(mapping, offset - 1, max); rcu_read_unlock(); return offset - 1 - head; } /* * page cache context based read-ahead */ static int try_context_readahead(struct address_space *mapping, struct file_ra_state *ra, pgoff_t offset, unsigned long req_size, unsigned long max) { pgoff_t size; size = count_history_pages(mapping, offset, max); /* * not enough history pages: * it could be a random read */ if (size <= req_size) return 0; /* * starts from beginning of file: * it is a strong indication of long-run stream (or whole-file-read) */ if (size >= offset) size *= 2; ra->start = offset; ra->size = min(size + req_size, max); ra->async_size = 1; return 1; } /* * A minimal readahead algorithm for trivial sequential/random reads. */ static unsigned long ondemand_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *filp, bool hit_readahead_marker, pgoff_t offset, unsigned long req_size) { struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long max_pages = ra->ra_pages; unsigned long add_pages; pgoff_t prev_offset; /* * If the request exceeds the readahead window, allow the read to * be up to the optimal hardware IO size */ if (req_size > max_pages && bdi->io_pages > max_pages) max_pages = min(req_size, bdi->io_pages); /* * start of file */ if (!offset) goto initial_readahead; /* * It's the expected callback offset, assume sequential access. * Ramp up sizes, and push forward the readahead window. */ if ((offset == (ra->start + ra->size - ra->async_size) || offset == (ra->start + ra->size))) { ra->start += ra->size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * Hit a marked page without valid readahead state. * E.g. interleaved reads. * Query the pagecache for async_size, which normally equals to * readahead size. Ramp it up and use it as the new readahead size. */ if (hit_readahead_marker) { pgoff_t start; rcu_read_lock(); start = page_cache_next_miss(mapping, offset + 1, max_pages); rcu_read_unlock(); if (!start || start - offset > max_pages) return 0; ra->start = start; ra->size = start - offset; /* old async_size */ ra->size += req_size; ra->size = get_next_ra_size(ra, max_pages); ra->async_size = ra->size; goto readit; } /* * oversize read */ if (req_size > max_pages) goto initial_readahead; /* * sequential cache miss * trivial case: (offset - prev_offset) == 1 * unaligned reads: (offset - prev_offset) == 0 */ prev_offset = (unsigned long long)ra->prev_pos >> PAGE_SHIFT; if (offset - prev_offset <= 1UL) goto initial_readahead; /* * Query the page cache and look for the traces(cached history pages) * that a sequential stream would leave behind. */ if (try_context_readahead(mapping, ra, offset, req_size, max_pages)) goto readit; /* * standalone, small random read * Read as is, and do not pollute the readahead state. */ return __do_page_cache_readahead(mapping, filp, offset, req_size, 0); initial_readahead: ra->start = offset; ra->size = get_init_ra_size(req_size, max_pages); ra->async_size = ra->size > req_size ? ra->size - req_size : ra->size; readit: /* * Will this read hit the readahead marker made by itself? * If so, trigger the readahead marker hit now, and merge * the resulted next readahead window into the current one. * Take care of maximum IO pages as above. */ if (offset == ra->start && ra->size == ra->async_size) { add_pages = get_next_ra_size(ra, max_pages); if (ra->size + add_pages <= max_pages) { ra->async_size = add_pages; ra->size += add_pages; } else { ra->size = max_pages; ra->async_size = max_pages >> 1; } } return ra_submit(ra, mapping, filp); } /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @filp: passed on to ->readpage() and ->readpages() * @offset: start offset into @mapping, in pagecache page-sized units * @req_size: hint: total size of the read which the caller is performing in * pagecache pages * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *filp, pgoff_t offset, unsigned long req_size) { /* no read-ahead */ if (!ra->ra_pages) return; if (blk_cgroup_congested()) return; /* be dumb */ if (filp && (filp->f_mode & FMODE_RANDOM)) { force_page_cache_readahead(mapping, filp, offset, req_size); return; } /* do read-ahead */ ondemand_readahead(mapping, ra, filp, false, offset, req_size); } EXPORT_SYMBOL_GPL(page_cache_sync_readahead); /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @filp: passed on to ->readpage() and ->readpages() * @page: the page at @offset which has the PG_readahead flag set * @offset: start offset into @mapping, in pagecache page-sized units * @req_size: hint: total size of the read which the caller is performing in * pagecache pages * * page_cache_async_readahead() should be called when a page is used which * has the PG_readahead flag; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *filp, struct page *page, pgoff_t offset, unsigned long req_size) { /* no read-ahead */ if (!ra->ra_pages) return; /* * Same bit is used for PG_readahead and PG_reclaim. */ if (PageWriteback(page)) return; ClearPageReadahead(page); /* * Defer asynchronous read-ahead on IO congestion. */ if (inode_read_congested(mapping->host)) return; if (blk_cgroup_congested()) return; /* do read-ahead */ ondemand_readahead(mapping, ra, filp, true, offset, req_size); } EXPORT_SYMBOL_GPL(page_cache_async_readahead); ssize_t ksys_readahead(int fd, loff_t offset, size_t count) { ssize_t ret; struct fd f; ret = -EBADF; f = fdget(fd); if (!f.file || !(f.file->f_mode & FMODE_READ)) goto out; /* * The readahead() syscall is intended to run only on files * that can execute readahead. If readahead is not possible * on this file, then we must return -EINVAL. */ ret = -EINVAL; if (!f.file->f_mapping || !f.file->f_mapping->a_ops || (!S_ISREG(file_inode(f.file)->i_mode) && !S_ISBLK(file_inode(f.file)->i_mode))) goto out; ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); out: fdput(f); return ret; } SYSCALL_DEFINE3(readahead, int, fd, loff_t, offset, size_t, count) { return ksys_readahead(fd, offset, count); } |
| 212 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 | // SPDX-License-Identifier: GPL-2.0 /* * Detect hard and soft lockups on a system * * started by Don Zickus, Copyright (C) 2010 Red Hat, Inc. * * Note: Most of this code is borrowed heavily from the original softlockup * detector, so thanks to Ingo for the initial implementation. * Some chunks also taken from the old x86-specific nmi watchdog code, thanks * to those contributors as well. */ #define pr_fmt(fmt) "watchdog: " fmt #include <linux/mm.h> #include <linux/cpu.h> #include <linux/nmi.h> #include <linux/init.h> #include <linux/module.h> #include <linux/sysctl.h> #include <linux/tick.h> #include <linux/sched/clock.h> #include <linux/sched/debug.h> #include <linux/sched/isolation.h> #include <linux/stop_machine.h> #include <asm/irq_regs.h> #include <linux/kvm_para.h> static DEFINE_MUTEX(watchdog_mutex); #if defined(CONFIG_HARDLOCKUP_DETECTOR) || defined(CONFIG_HAVE_NMI_WATCHDOG) # define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED | NMI_WATCHDOG_ENABLED) # define NMI_WATCHDOG_DEFAULT 1 #else # define WATCHDOG_DEFAULT (SOFT_WATCHDOG_ENABLED) # define NMI_WATCHDOG_DEFAULT 0 #endif unsigned long __read_mostly watchdog_enabled; int __read_mostly watchdog_user_enabled = 1; int __read_mostly nmi_watchdog_user_enabled = NMI_WATCHDOG_DEFAULT; int __read_mostly soft_watchdog_user_enabled = 1; int __read_mostly watchdog_thresh = 10; static int __read_mostly nmi_watchdog_available; static struct cpumask watchdog_allowed_mask __read_mostly; struct cpumask watchdog_cpumask __read_mostly; unsigned long *watchdog_cpumask_bits = cpumask_bits(&watchdog_cpumask); #ifdef CONFIG_HARDLOCKUP_DETECTOR /* * Should we panic when a soft-lockup or hard-lockup occurs: */ unsigned int __read_mostly hardlockup_panic = CONFIG_BOOTPARAM_HARDLOCKUP_PANIC_VALUE; /* * We may not want to enable hard lockup detection by default in all cases, * for example when running the kernel as a guest on a hypervisor. In these * cases this function can be called to disable hard lockup detection. This * function should only be executed once by the boot processor before the * kernel command line parameters are parsed, because otherwise it is not * possible to override this in hardlockup_panic_setup(). */ void __init hardlockup_detector_disable(void) { nmi_watchdog_user_enabled = 0; } static int __init hardlockup_panic_setup(char *str) { if (!strncmp(str, "panic", 5)) hardlockup_panic = 1; else if (!strncmp(str, "nopanic", 7)) hardlockup_panic = 0; else if (!strncmp(str, "0", 1)) nmi_watchdog_user_enabled = 0; else if (!strncmp(str, "1", 1)) nmi_watchdog_user_enabled = 1; return 1; } __setup("nmi_watchdog=", hardlockup_panic_setup); # ifdef CONFIG_SMP int __read_mostly sysctl_hardlockup_all_cpu_backtrace; static int __init hardlockup_all_cpu_backtrace_setup(char *str) { sysctl_hardlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("hardlockup_all_cpu_backtrace=", hardlockup_all_cpu_backtrace_setup); # endif /* CONFIG_SMP */ #endif /* CONFIG_HARDLOCKUP_DETECTOR */ /* * These functions can be overridden if an architecture implements its * own hardlockup detector. * * watchdog_nmi_enable/disable can be implemented to start and stop when * softlockup watchdog threads start and stop. The arch must select the * SOFTLOCKUP_DETECTOR Kconfig. */ int __weak watchdog_nmi_enable(unsigned int cpu) { hardlockup_detector_perf_enable(); return 0; } void __weak watchdog_nmi_disable(unsigned int cpu) { hardlockup_detector_perf_disable(); } /* Return 0, if a NMI watchdog is available. Error code otherwise */ int __weak __init watchdog_nmi_probe(void) { return hardlockup_detector_perf_init(); } /** * watchdog_nmi_stop - Stop the watchdog for reconfiguration * * The reconfiguration steps are: * watchdog_nmi_stop(); * update_variables(); * watchdog_nmi_start(); */ void __weak watchdog_nmi_stop(void) { } /** * watchdog_nmi_start - Start the watchdog after reconfiguration * * Counterpart to watchdog_nmi_stop(). * * The following variables have been updated in update_variables() and * contain the currently valid configuration: * - watchdog_enabled * - watchdog_thresh * - watchdog_cpumask */ void __weak watchdog_nmi_start(void) { } /** * lockup_detector_update_enable - Update the sysctl enable bit * * Caller needs to make sure that the NMI/perf watchdogs are off, so this * can't race with watchdog_nmi_disable(). */ static void lockup_detector_update_enable(void) { watchdog_enabled = 0; if (!watchdog_user_enabled) return; if (nmi_watchdog_available && nmi_watchdog_user_enabled) watchdog_enabled |= NMI_WATCHDOG_ENABLED; if (soft_watchdog_user_enabled) watchdog_enabled |= SOFT_WATCHDOG_ENABLED; } #ifdef CONFIG_SOFTLOCKUP_DETECTOR #define SOFTLOCKUP_RESET ULONG_MAX /* Global variables, exported for sysctl */ unsigned int __read_mostly softlockup_panic = CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE; static bool softlockup_initialized __read_mostly; static u64 __read_mostly sample_period; static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts); static DEFINE_PER_CPU(struct hrtimer, watchdog_hrtimer); static DEFINE_PER_CPU(bool, softlockup_touch_sync); static DEFINE_PER_CPU(bool, soft_watchdog_warn); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts); static DEFINE_PER_CPU(unsigned long, soft_lockup_hrtimer_cnt); static DEFINE_PER_CPU(struct task_struct *, softlockup_task_ptr_saved); static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved); static unsigned long soft_lockup_nmi_warn; static int __init softlockup_panic_setup(char *str) { softlockup_panic = simple_strtoul(str, NULL, 0); return 1; } __setup("softlockup_panic=", softlockup_panic_setup); static int __init nowatchdog_setup(char *str) { watchdog_user_enabled = 0; return 1; } __setup("nowatchdog", nowatchdog_setup); static int __init nosoftlockup_setup(char *str) { soft_watchdog_user_enabled = 0; return 1; } __setup("nosoftlockup", nosoftlockup_setup); static int __init watchdog_thresh_setup(char *str) { get_option(&str, &watchdog_thresh); return 1; } __setup("watchdog_thresh=", watchdog_thresh_setup); #ifdef CONFIG_SMP int __read_mostly sysctl_softlockup_all_cpu_backtrace; static int __init softlockup_all_cpu_backtrace_setup(char *str) { sysctl_softlockup_all_cpu_backtrace = !!simple_strtol(str, NULL, 0); return 1; } __setup("softlockup_all_cpu_backtrace=", softlockup_all_cpu_backtrace_setup); #endif static void __lockup_detector_cleanup(void); /* * Hard-lockup warnings should be triggered after just a few seconds. Soft- * lockups can have false positives under extreme conditions. So we generally * want a higher threshold for soft lockups than for hard lockups. So we couple * the thresholds with a factor: we make the soft threshold twice the amount of * time the hard threshold is. */ static int get_softlockup_thresh(void) { return watchdog_thresh * 2; } /* * Returns seconds, approximately. We don't need nanosecond * resolution, and we don't need to waste time with a big divide when * 2^30ns == 1.074s. */ static unsigned long get_timestamp(void) { return running_clock() >> 30LL; /* 2^30 ~= 10^9 */ } static void set_sample_period(void) { /* * convert watchdog_thresh from seconds to ns * the divide by 5 is to give hrtimer several chances (two * or three with the current relation between the soft * and hard thresholds) to increment before the * hardlockup detector generates a warning */ sample_period = get_softlockup_thresh() * ((u64)NSEC_PER_SEC / 5); watchdog_update_hrtimer_threshold(sample_period); } /* Commands for resetting the watchdog */ static void __touch_watchdog(void) { __this_cpu_write(watchdog_touch_ts, get_timestamp()); } /** * touch_softlockup_watchdog_sched - touch watchdog on scheduler stalls * * Call when the scheduler may have stalled for legitimate reasons * preventing the watchdog task from executing - e.g. the scheduler * entering idle state. This should only be used for scheduler events. * Use touch_softlockup_watchdog() for everything else. */ notrace void touch_softlockup_watchdog_sched(void) { /* * Preemption can be enabled. It doesn't matter which CPU's timestamp * gets zeroed here, so use the raw_ operation. */ raw_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } notrace void touch_softlockup_watchdog(void) { touch_softlockup_watchdog_sched(); wq_watchdog_touch(raw_smp_processor_id()); } EXPORT_SYMBOL(touch_softlockup_watchdog); void touch_all_softlockup_watchdogs(void) { int cpu; /* * watchdog_mutex cannpt be taken here, as this might be called * from (soft)interrupt context, so the access to * watchdog_allowed_cpumask might race with a concurrent update. * * The watchdog time stamp can race against a concurrent real * update as well, the only side effect might be a cycle delay for * the softlockup check. */ for_each_cpu(cpu, &watchdog_allowed_mask) per_cpu(watchdog_touch_ts, cpu) = SOFTLOCKUP_RESET; wq_watchdog_touch(-1); } void touch_softlockup_watchdog_sync(void) { __this_cpu_write(softlockup_touch_sync, true); __this_cpu_write(watchdog_touch_ts, SOFTLOCKUP_RESET); } static int is_softlockup(unsigned long touch_ts) { unsigned long now = get_timestamp(); if ((watchdog_enabled & SOFT_WATCHDOG_ENABLED) && watchdog_thresh){ /* Warn about unreasonable delays. */ if (time_after(now, touch_ts + get_softlockup_thresh())) return now - touch_ts; } return 0; } /* watchdog detector functions */ bool is_hardlockup(void) { unsigned long hrint = __this_cpu_read(hrtimer_interrupts); if (__this_cpu_read(hrtimer_interrupts_saved) == hrint) return true; __this_cpu_write(hrtimer_interrupts_saved, hrint); return false; } static void watchdog_interrupt_count(void) { __this_cpu_inc(hrtimer_interrupts); } static DEFINE_PER_CPU(struct completion, softlockup_completion); static DEFINE_PER_CPU(struct cpu_stop_work, softlockup_stop_work); /* * The watchdog thread function - touches the timestamp. * * It only runs once every sample_period seconds (4 seconds by * default) to reset the softlockup timestamp. If this gets delayed * for more than 2*watchdog_thresh seconds then the debug-printout * triggers in watchdog_timer_fn(). */ static int softlockup_fn(void *data) { __this_cpu_write(soft_lockup_hrtimer_cnt, __this_cpu_read(hrtimer_interrupts)); __touch_watchdog(); complete(this_cpu_ptr(&softlockup_completion)); return 0; } /* watchdog kicker functions */ static enum hrtimer_restart watchdog_timer_fn(struct hrtimer *hrtimer) { unsigned long touch_ts = __this_cpu_read(watchdog_touch_ts); struct pt_regs *regs = get_irq_regs(); int duration; int softlockup_all_cpu_backtrace = sysctl_softlockup_all_cpu_backtrace; if (!watchdog_enabled) return HRTIMER_NORESTART; /* kick the hardlockup detector */ watchdog_interrupt_count(); /* kick the softlockup detector */ if (completion_done(this_cpu_ptr(&softlockup_completion))) { reinit_completion(this_cpu_ptr(&softlockup_completion)); stop_one_cpu_nowait(smp_processor_id(), softlockup_fn, NULL, this_cpu_ptr(&softlockup_stop_work)); } /* .. and repeat */ hrtimer_forward_now(hrtimer, ns_to_ktime(sample_period)); if (touch_ts == SOFTLOCKUP_RESET) { if (unlikely(__this_cpu_read(softlockup_touch_sync))) { /* * If the time stamp was touched atomically * make sure the scheduler tick is up to date. */ __this_cpu_write(softlockup_touch_sync, false); sched_clock_tick(); } /* Clear the guest paused flag on watchdog reset */ kvm_check_and_clear_guest_paused(); __touch_watchdog(); return HRTIMER_RESTART; } /* check for a softlockup * This is done by making sure a high priority task is * being scheduled. The task touches the watchdog to * indicate it is getting cpu time. If it hasn't then * this is a good indication some task is hogging the cpu */ duration = is_softlockup(touch_ts); if (unlikely(duration)) { /* * If a virtual machine is stopped by the host it can look to * the watchdog like a soft lockup, check to see if the host * stopped the vm before we issue the warning */ if (kvm_check_and_clear_guest_paused()) return HRTIMER_RESTART; /* only warn once */ if (__this_cpu_read(soft_watchdog_warn) == true) { /* * When multiple processes are causing softlockups the * softlockup detector only warns on the first one * because the code relies on a full quiet cycle to * re-arm. The second process prevents the quiet cycle * and never gets reported. Use task pointers to detect * this. */ if (__this_cpu_read(softlockup_task_ptr_saved) != current) { __this_cpu_write(soft_watchdog_warn, false); __touch_watchdog(); } return HRTIMER_RESTART; } if (softlockup_all_cpu_backtrace) { /* Prevent multiple soft-lockup reports if one cpu is already * engaged in dumping cpu back traces */ if (test_and_set_bit(0, &soft_lockup_nmi_warn)) { /* Someone else will report us. Let's give up */ __this_cpu_write(soft_watchdog_warn, true); return HRTIMER_RESTART; } } pr_emerg("BUG: soft lockup - CPU#%d stuck for %us! [%s:%d]\n", smp_processor_id(), duration, current->comm, task_pid_nr(current)); __this_cpu_write(softlockup_task_ptr_saved, current); print_modules(); print_irqtrace_events(current); if (regs) show_regs(regs); else dump_stack(); if (softlockup_all_cpu_backtrace) { /* Avoid generating two back traces for current * given that one is already made above */ trigger_allbutself_cpu_backtrace(); clear_bit(0, &soft_lockup_nmi_warn); /* Barrier to sync with other cpus */ smp_mb__after_atomic(); } add_taint(TAINT_SOFTLOCKUP, LOCKDEP_STILL_OK); if (softlockup_panic) panic("softlockup: hung tasks"); __this_cpu_write(soft_watchdog_warn, true); } else __this_cpu_write(soft_watchdog_warn, false); return HRTIMER_RESTART; } static void watchdog_enable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); struct completion *done = this_cpu_ptr(&softlockup_completion); WARN_ON_ONCE(cpu != smp_processor_id()); init_completion(done); complete(done); /* * Start the timer first to prevent the NMI watchdog triggering * before the timer has a chance to fire. */ hrtimer_init(hrtimer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD); hrtimer->function = watchdog_timer_fn; hrtimer_start(hrtimer, ns_to_ktime(sample_period), HRTIMER_MODE_REL_PINNED_HARD); /* Initialize timestamp */ __touch_watchdog(); /* Enable the perf event */ if (watchdog_enabled & NMI_WATCHDOG_ENABLED) watchdog_nmi_enable(cpu); } static void watchdog_disable(unsigned int cpu) { struct hrtimer *hrtimer = this_cpu_ptr(&watchdog_hrtimer); WARN_ON_ONCE(cpu != smp_processor_id()); /* * Disable the perf event first. That prevents that a large delay * between disabling the timer and disabling the perf event causes * the perf NMI to detect a false positive. */ watchdog_nmi_disable(cpu); hrtimer_cancel(hrtimer); wait_for_completion(this_cpu_ptr(&softlockup_completion)); } static int softlockup_stop_fn(void *data) { watchdog_disable(smp_processor_id()); return 0; } static void softlockup_stop_all(void) { int cpu; if (!softlockup_initialized) return; for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_stop_fn, NULL, false); cpumask_clear(&watchdog_allowed_mask); } static int softlockup_start_fn(void *data) { watchdog_enable(smp_processor_id()); return 0; } static void softlockup_start_all(void) { int cpu; cpumask_copy(&watchdog_allowed_mask, &watchdog_cpumask); for_each_cpu(cpu, &watchdog_allowed_mask) smp_call_on_cpu(cpu, softlockup_start_fn, NULL, false); } int lockup_detector_online_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_enable(cpu); return 0; } int lockup_detector_offline_cpu(unsigned int cpu) { if (cpumask_test_cpu(cpu, &watchdog_allowed_mask)) watchdog_disable(cpu); return 0; } static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); softlockup_stop_all(); set_sample_period(); lockup_detector_update_enable(); if (watchdog_enabled && watchdog_thresh) softlockup_start_all(); watchdog_nmi_start(); cpus_read_unlock(); /* * Must be called outside the cpus locked section to prevent * recursive locking in the perf code. */ __lockup_detector_cleanup(); } void lockup_detector_reconfigure(void) { mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(); mutex_unlock(&watchdog_mutex); } /* * Create the watchdog thread infrastructure and configure the detector(s). * * The threads are not unparked as watchdog_allowed_mask is empty. When * the threads are successfully initialized, take the proper locks and * unpark the threads in the watchdog_cpumask if the watchdog is enabled. */ static __init void lockup_detector_setup(void) { /* * If sysctl is off and watchdog got disabled on the command line, * nothing to do here. */ lockup_detector_update_enable(); if (!IS_ENABLED(CONFIG_SYSCTL) && !(watchdog_enabled && watchdog_thresh)) return; mutex_lock(&watchdog_mutex); __lockup_detector_reconfigure(); softlockup_initialized = true; mutex_unlock(&watchdog_mutex); } #else /* CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_reconfigure(void) { cpus_read_lock(); watchdog_nmi_stop(); lockup_detector_update_enable(); watchdog_nmi_start(); cpus_read_unlock(); } void lockup_detector_reconfigure(void) { __lockup_detector_reconfigure(); } static inline void lockup_detector_setup(void) { __lockup_detector_reconfigure(); } #endif /* !CONFIG_SOFTLOCKUP_DETECTOR */ static void __lockup_detector_cleanup(void) { lockdep_assert_held(&watchdog_mutex); hardlockup_detector_perf_cleanup(); } /** * lockup_detector_cleanup - Cleanup after cpu hotplug or sysctl changes * * Caller must not hold the cpu hotplug rwsem. */ void lockup_detector_cleanup(void) { mutex_lock(&watchdog_mutex); __lockup_detector_cleanup(); mutex_unlock(&watchdog_mutex); } /** * lockup_detector_soft_poweroff - Interface to stop lockup detector(s) * * Special interface for parisc. It prevents lockup detector warnings from * the default pm_poweroff() function which busy loops forever. */ void lockup_detector_soft_poweroff(void) { watchdog_enabled = 0; } #ifdef CONFIG_SYSCTL /* Propagate any changes to the watchdog threads */ static void proc_watchdog_update(void) { /* Remove impossible cpus to keep sysctl output clean. */ cpumask_and(&watchdog_cpumask, &watchdog_cpumask, cpu_possible_mask); __lockup_detector_reconfigure(); } /* * common function for watchdog, nmi_watchdog and soft_watchdog parameter * * caller | table->data points to | 'which' * -------------------|----------------------------|-------------------------- * proc_watchdog | watchdog_user_enabled | NMI_WATCHDOG_ENABLED | * | | SOFT_WATCHDOG_ENABLED * -------------------|----------------------------|-------------------------- * proc_nmi_watchdog | nmi_watchdog_user_enabled | NMI_WATCHDOG_ENABLED * -------------------|----------------------------|-------------------------- * proc_soft_watchdog | soft_watchdog_user_enabled | SOFT_WATCHDOG_ENABLED */ static int proc_watchdog_common(int which, struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int err, old, *param = table->data; mutex_lock(&watchdog_mutex); if (!write) { /* * On read synchronize the userspace interface. This is a * racy snapshot. */ *param = (watchdog_enabled & which) != 0; err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } else { old = READ_ONCE(*param); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && old != READ_ONCE(*param)) proc_watchdog_update(); } mutex_unlock(&watchdog_mutex); return err; } /* * /proc/sys/kernel/watchdog */ int proc_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(NMI_WATCHDOG_ENABLED|SOFT_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/nmi_watchdog */ int proc_nmi_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { if (!nmi_watchdog_available && write) return -ENOTSUPP; return proc_watchdog_common(NMI_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/soft_watchdog */ int proc_soft_watchdog(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { return proc_watchdog_common(SOFT_WATCHDOG_ENABLED, table, write, buffer, lenp, ppos); } /* * /proc/sys/kernel/watchdog_thresh */ int proc_watchdog_thresh(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int err, old; mutex_lock(&watchdog_mutex); old = READ_ONCE(watchdog_thresh); err = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!err && write && old != READ_ONCE(watchdog_thresh)) proc_watchdog_update(); mutex_unlock(&watchdog_mutex); return err; } /* * The cpumask is the mask of possible cpus that the watchdog can run * on, not the mask of cpus it is actually running on. This allows the * user to specify a mask that will include cpus that have not yet * been brought online, if desired. */ int proc_watchdog_cpumask(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int err; mutex_lock(&watchdog_mutex); err = proc_do_large_bitmap(table, write, buffer, lenp, ppos); if (!err && write) proc_watchdog_update(); mutex_unlock(&watchdog_mutex); return err; } #endif /* CONFIG_SYSCTL */ void __init lockup_detector_init(void) { if (tick_nohz_full_enabled()) pr_info("Disabling watchdog on nohz_full cores by default\n"); cpumask_copy(&watchdog_cpumask, housekeeping_cpumask(HK_FLAG_TIMER)); if (!watchdog_nmi_probe()) nmi_watchdog_available = true; lockup_detector_setup(); } |
| 508 73 73 463 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | // SPDX-License-Identifier: GPL-2.0 /* * 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/kobject.txt 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/spinlock.h> #include <linux/kref.h> #include <linux/kobject_ns.h> #include <linux/kernel.h> #include <linux/wait.h> #include <linux/atomic.h> #include <linux/workqueue.h> #include <linux/uidgid.h> #include <linux/android_kabi.h> #define UEVENT_HELPER_PATH_LEN 256 #define UEVENT_NUM_ENVP 32 /* 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 u64 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, KOBJ_MAX }; struct kobject { const char *name; struct list_head entry; struct kobject *parent; struct kset *kset; struct kobj_type *ktype; struct kernfs_node *sd; /* sysfs directory entry */ struct kref kref; #ifdef CONFIG_DEBUG_KOBJECT_RELEASE struct delayed_work release; #endif 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; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; extern __printf(2, 3) int kobject_set_name(struct kobject *kobj, const char *name, ...); extern __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; } extern void kobject_init(struct kobject *kobj, struct kobj_type *ktype); extern __printf(3, 4) __must_check int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...); extern __printf(4, 5) __must_check int kobject_init_and_add(struct kobject *kobj, struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...); extern void kobject_del(struct kobject *kobj); extern struct kobject * __must_check kobject_create(void); extern struct kobject * __must_check kobject_create_and_add(const char *name, struct kobject *parent); extern int __must_check kobject_rename(struct kobject *, const char *new_name); extern int __must_check kobject_move(struct kobject *, struct kobject *); extern struct kobject *kobject_get(struct kobject *kobj); extern struct kobject * __must_check kobject_get_unless_zero( struct kobject *kobj); extern void kobject_put(struct kobject *kobj); extern const void *kobject_namespace(struct kobject *kobj); extern void kobject_get_ownership(struct kobject *kobj, kuid_t *uid, kgid_t *gid); extern char *kobject_get_path(struct kobject *kobj, gfp_t flag); /** * kobject_has_children - Returns whether a kobject has children. * @kobj: the object to test * * This will return whether a kobject has other kobjects as children. * * It does NOT account for the presence of attribute files, only sub * directories. It also assumes there is no concurrent addition or * removal of such children, and thus relies on external locking. */ static inline bool kobject_has_children(struct kobject *kobj) { WARN_ON_ONCE(kref_read(&kobj->kref) == 0); return kobj->sd && kobj->sd->dir.subdirs; } struct kobj_type { void (*release)(struct kobject *kobj); const struct sysfs_ops *sysfs_ops; struct attribute **default_attrs; /* use default_groups instead */ const struct attribute_group **default_groups; const struct kobj_ns_type_operations *(*child_ns_type)(struct kobject *kobj); const void *(*namespace)(struct kobject *kobj); void (*get_ownership)(struct kobject *kobj, kuid_t *uid, kgid_t *gid); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; 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)(struct kset *kset, struct kobject *kobj); const char *(* const name)(struct kset *kset, struct kobject *kobj); int (* const uevent)(struct kset *kset, 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; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); } __randomize_layout; extern void kset_init(struct kset *kset); extern int __must_check kset_register(struct kset *kset); extern void kset_unregister(struct kset *kset); extern 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 struct kobj_type *get_ktype(struct kobject *kobj) { return kobj->ktype; } extern 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_ */ |
| 283 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGE_REF_H #define _LINUX_PAGE_REF_H #include <linux/atomic.h> #include <linux/mm_types.h> #include <linux/page-flags.h> #include <linux/tracepoint-defs.h> extern struct tracepoint __tracepoint_page_ref_set; extern struct tracepoint __tracepoint_page_ref_mod; extern struct tracepoint __tracepoint_page_ref_mod_and_test; extern struct tracepoint __tracepoint_page_ref_mod_and_return; extern struct tracepoint __tracepoint_page_ref_mod_unless; extern struct tracepoint __tracepoint_page_ref_freeze; extern struct tracepoint __tracepoint_page_ref_unfreeze; #ifdef CONFIG_DEBUG_PAGE_REF /* * Ideally we would want to use the trace_<tracepoint>_enabled() helper * functions. But due to include header file issues, that is not * feasible. Instead we have to open code the static key functions. * * See trace_##name##_enabled(void) in include/linux/tracepoint.h */ #define page_ref_tracepoint_active(t) static_key_false(&(t).key) extern void __page_ref_set(struct page *page, int v); extern void __page_ref_mod(struct page *page, int v); extern void __page_ref_mod_and_test(struct page *page, int v, int ret); extern void __page_ref_mod_and_return(struct page *page, int v, int ret); extern void __page_ref_mod_unless(struct page *page, int v, int u); extern void __page_ref_freeze(struct page *page, int v, int ret); extern void __page_ref_unfreeze(struct page *page, int v); #else #define page_ref_tracepoint_active(t) false static inline void __page_ref_set(struct page *page, int v) { } static inline void __page_ref_mod(struct page *page, int v) { } static inline void __page_ref_mod_and_test(struct page *page, int v, int ret) { } static inline void __page_ref_mod_and_return(struct page *page, int v, int ret) { } static inline void __page_ref_mod_unless(struct page *page, int v, int u) { } static inline void __page_ref_freeze(struct page *page, int v, int ret) { } static inline void __page_ref_unfreeze(struct page *page, int v) { } #endif static inline int page_ref_count(struct page *page) { return atomic_read(&page->_refcount); } static inline int page_count(struct page *page) { return atomic_read(&compound_head(page)->_refcount); } static inline void set_page_count(struct page *page, int v) { atomic_set(&page->_refcount, v); if (page_ref_tracepoint_active(__tracepoint_page_ref_set)) __page_ref_set(page, v); } /* * Setup the page count before being freed into the page allocator for * the first time (boot or memory hotplug) */ static inline void init_page_count(struct page *page) { set_page_count(page, 1); } static inline void page_ref_add(struct page *page, int nr) { atomic_add(nr, &page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) __page_ref_mod(page, nr); } static inline void page_ref_sub(struct page *page, int nr) { atomic_sub(nr, &page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) __page_ref_mod(page, -nr); } static inline void page_ref_inc(struct page *page) { atomic_inc(&page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) __page_ref_mod(page, 1); } static inline void page_ref_dec(struct page *page) { atomic_dec(&page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod)) __page_ref_mod(page, -1); } static inline int page_ref_sub_and_test(struct page *page, int nr) { int ret = atomic_sub_and_test(nr, &page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) __page_ref_mod_and_test(page, -nr, ret); return ret; } static inline int page_ref_inc_return(struct page *page) { int ret = atomic_inc_return(&page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) __page_ref_mod_and_return(page, 1, ret); return ret; } static inline int page_ref_dec_and_test(struct page *page) { int ret = atomic_dec_and_test(&page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_test)) __page_ref_mod_and_test(page, -1, ret); return ret; } static inline int page_ref_dec_return(struct page *page) { int ret = atomic_dec_return(&page->_refcount); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_and_return)) __page_ref_mod_and_return(page, -1, ret); return ret; } static inline int page_ref_add_unless(struct page *page, int nr, int u) { int ret = atomic_add_unless(&page->_refcount, nr, u); if (page_ref_tracepoint_active(__tracepoint_page_ref_mod_unless)) __page_ref_mod_unless(page, nr, ret); return ret; } static inline int page_ref_freeze(struct page *page, int count) { int ret = likely(atomic_cmpxchg(&page->_refcount, count, 0) == count); if (page_ref_tracepoint_active(__tracepoint_page_ref_freeze)) __page_ref_freeze(page, count, ret); return ret; } static inline void page_ref_unfreeze(struct page *page, int count) { VM_BUG_ON_PAGE(page_count(page) != 0, page); VM_BUG_ON(count == 0); atomic_set_release(&page->_refcount, count); if (page_ref_tracepoint_active(__tracepoint_page_ref_unfreeze)) __page_ref_unfreeze(page, count); } #endif |
| 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 | // SPDX-License-Identifier: GPL-2.0 /* * xfrm4_policy.c * * Changes: * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki @USAGI * Split up af-specific portion * */ #include <linux/err.h> #include <linux/kernel.h> #include <linux/inetdevice.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/l3mdev.h> static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct rtable *rt; memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; fl4->flowi4_oif = l3mdev_master_ifindex_by_index(net, oif); fl4->flowi4_mark = mark; if (saddr) fl4->saddr = saddr->a4; fl4->flowi4_flags = FLOWI_FLAG_SKIP_NH_OIF; rt = __ip_route_output_key(net, fl4); if (!IS_ERR(rt)) return &rt->dst; return ERR_CAST(rt); } static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr, u32 mark) { struct flowi4 fl4; return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr, mark); } static int xfrm4_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr, u32 mark) { struct dst_entry *dst; struct flowi4 fl4; dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr, mark); if (IS_ERR(dst)) return -EHOSTUNREACH; saddr->a4 = fl4.saddr; dst_release(dst); return 0; } static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { struct rtable *rt = (struct rtable *)xdst->route; const struct flowi4 *fl4 = &fl->u.ip4; xdst->u.rt.rt_iif = fl4->flowi4_iif; xdst->u.dst.dev = dev; dev_hold(dev); /* Sheit... I remember I did this right. Apparently, * it was magically lost, so this code needs audit */ xdst->u.rt.rt_is_input = rt->rt_is_input; xdst->u.rt.rt_flags = rt->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST | RTCF_LOCAL); xdst->u.rt.rt_type = rt->rt_type; xdst->u.rt.rt_uses_gateway = rt->rt_uses_gateway; xdst->u.rt.rt_gw_family = rt->rt_gw_family; if (rt->rt_gw_family == AF_INET) xdst->u.rt.rt_gw4 = rt->rt_gw4; else if (rt->rt_gw_family == AF_INET6) xdst->u.rt.rt_gw6 = rt->rt_gw6; xdst->u.rt.rt_pmtu = rt->rt_pmtu; xdst->u.rt.rt_mtu_locked = rt->rt_mtu_locked; INIT_LIST_HEAD(&xdst->u.rt.rt_uncached); rt_add_uncached_list(&xdst->u.rt); return 0; } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu, bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; path->ops->redirect(path, sk, skb); } static void xfrm4_dst_destroy(struct dst_entry *dst) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; dst_destroy_metrics_generic(dst); if (xdst->u.rt.rt_uncached_list) rt_del_uncached_list(&xdst->u.rt); xfrm_dst_destroy(xdst); } static void xfrm4_dst_ifdown(struct dst_entry *dst, struct net_device *dev, int unregister) { if (!unregister) return; xfrm_dst_ifdown(dst, dev); } static struct dst_ops xfrm4_dst_ops_template = { .family = AF_INET, .update_pmtu = xfrm4_update_pmtu, .redirect = xfrm4_redirect, .cow_metrics = dst_cow_metrics_generic, .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 32768, }; static const struct xfrm_policy_afinfo xfrm4_policy_afinfo = { .dst_ops = &xfrm4_dst_ops_template, .dst_lookup = xfrm4_dst_lookup, .get_saddr = xfrm4_get_saddr, .fill_dst = xfrm4_fill_dst, .blackhole_route = ipv4_blackhole_route, }; #ifdef CONFIG_SYSCTL static struct ctl_table xfrm4_policy_table[] = { { .procname = "xfrm4_gc_thresh", .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, }, { } }; static __net_init int xfrm4_net_sysctl_init(struct net *net) { struct ctl_table *table; struct ctl_table_header *hdr; table = xfrm4_policy_table; if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(xfrm4_policy_table), GFP_KERNEL); if (!table) goto err_alloc; table[0].data = &net->xfrm.xfrm4_dst_ops.gc_thresh; } hdr = register_net_sysctl(net, "net/ipv4", table); if (!hdr) goto err_reg; net->ipv4.xfrm4_hdr = hdr; return 0; err_reg: if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; } static __net_exit void xfrm4_net_sysctl_exit(struct net *net) { struct ctl_table *table; if (!net->ipv4.xfrm4_hdr) return; table = net->ipv4.xfrm4_hdr->ctl_table_arg; unregister_net_sysctl_table(net->ipv4.xfrm4_hdr); if (!net_eq(net, &init_net)) kfree(table); } #else /* CONFIG_SYSCTL */ static inline int xfrm4_net_sysctl_init(struct net *net) { return 0; } static inline void xfrm4_net_sysctl_exit(struct net *net) { } #endif static int __net_init xfrm4_net_init(struct net *net) { int ret; memcpy(&net->xfrm.xfrm4_dst_ops, &xfrm4_dst_ops_template, sizeof(xfrm4_dst_ops_template)); ret = dst_entries_init(&net->xfrm.xfrm4_dst_ops); if (ret) return ret; ret = xfrm4_net_sysctl_init(net); if (ret) dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); return ret; } static void __net_exit xfrm4_net_exit(struct net *net) { xfrm4_net_sysctl_exit(net); dst_entries_destroy(&net->xfrm.xfrm4_dst_ops); } static struct pernet_operations __net_initdata xfrm4_net_ops = { .init = xfrm4_net_init, .exit = xfrm4_net_exit, }; static void __init xfrm4_policy_init(void) { xfrm_policy_register_afinfo(&xfrm4_policy_afinfo, AF_INET); } void __init xfrm4_init(void) { xfrm4_state_init(); xfrm4_policy_init(); xfrm4_protocol_init(); register_pernet_subsys(&xfrm4_net_ops); } |
| 131 50 578 67 575 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Tracing hooks * * Copyright (C) 2008-2009 Red Hat, Inc. All rights reserved. * * This file defines hook entry points called by core code where * user tracing/debugging support might need to do something. These * entry points are called tracehook_*(). Each hook declared below * has a detailed kerneldoc comment giving the context (locking et * al) from which it is called, and the meaning of its return value. * * Each function here typically has only one call site, so it is ok * to have some nontrivial tracehook_*() inlines. In all cases, the * fast path when no tracing is enabled should be very short. * * The purpose of this file and the tracehook_* layer is to consolidate * the interface that the kernel core and arch code uses to enable any * user debugging or tracing facility (such as ptrace). The interfaces * here are carefully documented so that maintainers of core and arch * code do not need to think about the implementation details of the * tracing facilities. Likewise, maintainers of the tracing code do not * need to understand all the calling core or arch code in detail, just * documented circumstances of each call, such as locking conditions. * * If the calling core code changes so that locking is different, then * it is ok to change the interface documented here. The maintainer of * core code changing should notify the maintainers of the tracing code * that they need to work out the change. * * Some tracehook_*() inlines take arguments that the current tracing * implementations might not necessarily use. These function signatures * are chosen to pass in all the information that is on hand in the * caller and might conceivably be relevant to a tracer, so that the * core code won't have to be updated when tracing adds more features. * If a call site changes so that some of those parameters are no longer * already on hand without extra work, then the tracehook_* interface * can change so there is no make-work burden on the core code. The * maintainer of core code changing should notify the maintainers of the * tracing code that they need to work out the change. */ #ifndef _LINUX_TRACEHOOK_H #define _LINUX_TRACEHOOK_H 1 #include <linux/sched.h> #include <linux/ptrace.h> #include <linux/security.h> #include <linux/task_work.h> #include <linux/memcontrol.h> #include <linux/blk-cgroup.h> struct linux_binprm; /* * ptrace report for syscall entry and exit looks identical. */ static inline int ptrace_report_syscall(struct pt_regs *regs, unsigned long message) { int ptrace = current->ptrace; if (!(ptrace & PT_PTRACED)) return 0; current->ptrace_message = message; ptrace_notify(SIGTRAP | ((ptrace & PT_TRACESYSGOOD) ? 0x80 : 0)); /* * this isn't the same as continuing with a signal, but it will do * for normal use. strace only continues with a signal if the * stopping signal is not SIGTRAP. -brl */ if (current->exit_code) { send_sig(current->exit_code, current, 1); current->exit_code = 0; } current->ptrace_message = 0; return fatal_signal_pending(current); } /** * tracehook_report_syscall_entry - task is about to attempt a system call * @regs: user register state of current task * * This will be called if %TIF_SYSCALL_TRACE or %TIF_SYSCALL_EMU have been set, * when the current task has just entered the kernel for a system call. * Full user register state is available here. Changing the values * in @regs can affect the system call number and arguments to be tried. * It is safe to block here, preventing the system call from beginning. * * Returns zero normally, or nonzero if the calling arch code should abort * the system call. That must prevent normal entry so no system call is * made. If @task ever returns to user mode after this, its register state * is unspecified, but should be something harmless like an %ENOSYS error * return. It should preserve enough information so that syscall_rollback() * can work (see asm-generic/syscall.h). * * Called without locks, just after entering kernel mode. */ static inline __must_check int tracehook_report_syscall_entry( struct pt_regs *regs) { return ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_ENTRY); } /** * tracehook_report_syscall_exit - task has just finished a system call * @regs: user register state of current task * @step: nonzero if simulating single-step or block-step * * This will be called if %TIF_SYSCALL_TRACE has been set, when the * current task has just finished an attempted system call. Full * user register state is available here. It is safe to block here, * preventing signals from being processed. * * If @step is nonzero, this report is also in lieu of the normal * trap that would follow the system call instruction because * user_enable_block_step() or user_enable_single_step() was used. * In this case, %TIF_SYSCALL_TRACE might not be set. * * Called without locks, just before checking for pending signals. */ static inline void tracehook_report_syscall_exit(struct pt_regs *regs, int step) { if (step) user_single_step_report(regs); else ptrace_report_syscall(regs, PTRACE_EVENTMSG_SYSCALL_EXIT); } /** * tracehook_signal_handler - signal handler setup is complete * @stepping: nonzero if debugger single-step or block-step in use * * Called by the arch code after a signal handler has been set up. * Register and stack state reflects the user handler about to run. * Signal mask changes have already been made. * * Called without locks, shortly before returning to user mode * (or handling more signals). */ static inline void tracehook_signal_handler(int stepping) { if (stepping) ptrace_notify(SIGTRAP); } /** * set_notify_resume - cause tracehook_notify_resume() to be called * @task: task that will call tracehook_notify_resume() * * Calling this arranges that @task will call tracehook_notify_resume() * before returning to user mode. If it's already running in user mode, * it will enter the kernel and call tracehook_notify_resume() soon. * If it's blocked, it will not be woken. */ static inline void set_notify_resume(struct task_struct *task) { #ifdef TIF_NOTIFY_RESUME if (!test_and_set_tsk_thread_flag(task, TIF_NOTIFY_RESUME)) kick_process(task); #endif } /** * tracehook_notify_resume - report when about to return 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 tracehook_notify_resume(struct pt_regs *regs) { /* * The caller just cleared 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(current->task_works)) 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(); blkcg_maybe_throttle_current(); } #endif /* <linux/tracehook.h> */ |
| 212 212 213 212 212 213 212 211 211 213 211 213 213 213 212 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Base port operations for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * Split from 8250_core.c, Copyright (C) 2001 Russell King. * * A note about mapbase / membase * * mapbase is the physical address of the IO port. * membase is an 'ioremapped' cookie. */ #if defined(CONFIG_SERIAL_8250_CONSOLE) && defined(CONFIG_MAGIC_SYSRQ) #define SUPPORT_SYSRQ #endif #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/console.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/ktime.h> #include <asm/io.h> #include <asm/irq.h> #include "8250.h" /* Nuvoton NPCM timeout register */ #define UART_NPCM_TOR 7 #define UART_NPCM_TOIE BIT(7) /* Timeout Interrupt Enable */ /* * Debugging. */ #if 0 #define DEBUG_AUTOCONF(fmt...) printk(fmt) #else #define DEBUG_AUTOCONF(fmt...) do { } while (0) #endif #define BOTH_EMPTY (UART_LSR_TEMT | UART_LSR_THRE) /* * Here we define the default xmit fifo size used for each type of UART. */ static const struct serial8250_config uart_config[] = { [PORT_UNKNOWN] = { .name = "unknown", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_8250] = { .name = "8250", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16450] = { .name = "16450", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550] = { .name = "16550", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16550A] = { .name = "16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_CIRRUS] = { .name = "Cirrus", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16650] = { .name = "ST16650", .fifo_size = 1, .tx_loadsz = 1, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16650V2] = { .name = "ST16650V2", .fifo_size = 32, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_00, .rxtrig_bytes = {8, 16, 24, 28}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16750] = { .name = "TI16750", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .rxtrig_bytes = {1, 16, 32, 56}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP | UART_CAP_AFE, }, [PORT_STARTECH] = { .name = "Startech", .fifo_size = 1, .tx_loadsz = 1, }, [PORT_16C950] = { .name = "16C950/954", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01, .rxtrig_bytes = {16, 32, 112, 120}, /* UART_CAP_EFR breaks billionon CF bluetooth card. */ .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, [PORT_16654] = { .name = "ST16654", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_10, .rxtrig_bytes = {8, 16, 56, 60}, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_16850] = { .name = "XR16850", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_RSA] = { .name = "RSA", .fifo_size = 2048, .tx_loadsz = 2048, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11, .flags = UART_CAP_FIFO, }, [PORT_NS16550A] = { .name = "NS16550A", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_NATSEMI, }, [PORT_XSCALE] = { .name = "XScale", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_UUE | UART_CAP_RTOIE, }, [PORT_OCTEON] = { .name = "OCTEON", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO, }, [PORT_AR7] = { .name = "AR7", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00, .flags = UART_CAP_FIFO /* | UART_CAP_AFE */, }, [PORT_U6_16550A] = { .name = "U6_16550A", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_TEGRA] = { .name = "Tegra", .fifo_size = 32, .tx_loadsz = 8, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_01 | UART_FCR_T_TRIG_01, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_RTOIE, }, [PORT_XR17D15X] = { .name = "XR17D15X", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_XR17V35X] = { .name = "XR17V35X", .fifo_size = 256, .tx_loadsz = 256, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_11 | UART_FCR_T_TRIG_11, .flags = UART_CAP_FIFO | UART_CAP_AFE | UART_CAP_EFR | UART_CAP_SLEEP, }, [PORT_LPC3220] = { .name = "LPC3220", .fifo_size = 64, .tx_loadsz = 32, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_00 | UART_FCR_T_TRIG_00, .flags = UART_CAP_FIFO, }, [PORT_BRCM_TRUMANAGE] = { .name = "TruManage", .fifo_size = 1, .tx_loadsz = 1024, .flags = UART_CAP_HFIFO, }, [PORT_8250_CIR] = { .name = "CIR port" }, [PORT_ALTR_16550_F32] = { .name = "Altera 16550 FIFO32", .fifo_size = 32, .tx_loadsz = 32, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 8, 16, 30}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F64] = { .name = "Altera 16550 FIFO64", .fifo_size = 64, .tx_loadsz = 64, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 16, 32, 62}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_ALTR_16550_F128] = { .name = "Altera 16550 FIFO128", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 126}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, /* * tx_loadsz is set to 63-bytes instead of 64-bytes to implement * workaround of errata A-008006 which states that tx_loadsz should * be configured less than Maximum supported fifo bytes. */ [PORT_16550A_FSL64] = { .name = "16550A_FSL64", .fifo_size = 64, .tx_loadsz = 63, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR7_64BYTE, .flags = UART_CAP_FIFO, }, [PORT_RT2880] = { .name = "Palmchip BK-3103", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_DA830] = { .name = "TI DA8xx/66AK2x", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_DMA_SELECT | UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO | UART_CAP_AFE, }, [PORT_MTK_BTIF] = { .name = "MediaTek BTIF", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .flags = UART_CAP_FIFO, }, [PORT_NPCM] = { .name = "Nuvoton 16550", .fifo_size = 16, .tx_loadsz = 16, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10 | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT, .rxtrig_bytes = {1, 4, 8, 14}, .flags = UART_CAP_FIFO, }, [PORT_SUNIX] = { .name = "Sunix", .fifo_size = 128, .tx_loadsz = 128, .fcr = UART_FCR_ENABLE_FIFO | UART_FCR_R_TRIG_10, .rxtrig_bytes = {1, 32, 64, 112}, .flags = UART_CAP_FIFO | UART_CAP_SLEEP, }, }; /* Uart divisor latch read */ static int default_serial_dl_read(struct uart_8250_port *up) { /* Assign these in pieces to truncate any bits above 7. */ unsigned char dll = serial_in(up, UART_DLL); unsigned char dlm = serial_in(up, UART_DLM); return dll | dlm << 8; } /* Uart divisor latch write */ static void default_serial_dl_write(struct uart_8250_port *up, int value) { serial_out(up, UART_DLL, value & 0xff); serial_out(up, UART_DLM, value >> 8 & 0xff); } #ifdef CONFIG_SERIAL_8250_RT288X /* Au1x00/RT288x UART hardware has a weird register layout */ static const s8 au_io_in_map[8] = { 0, /* UART_RX */ 2, /* UART_IER */ 3, /* UART_IIR */ 5, /* UART_LCR */ 6, /* UART_MCR */ 7, /* UART_LSR */ 8, /* UART_MSR */ -1, /* UART_SCR (unmapped) */ }; static const s8 au_io_out_map[8] = { 1, /* UART_TX */ 2, /* UART_IER */ 4, /* UART_FCR */ 5, /* UART_LCR */ 6, /* UART_MCR */ -1, /* UART_LSR (unmapped) */ -1, /* UART_MSR (unmapped) */ -1, /* UART_SCR (unmapped) */ }; unsigned int au_serial_in(struct uart_port *p, int offset) { if (offset >= ARRAY_SIZE(au_io_in_map)) return UINT_MAX; offset = au_io_in_map[offset]; if (offset < 0) return UINT_MAX; return __raw_readl(p->membase + (offset << p->regshift)); } void au_serial_out(struct uart_port *p, int offset, int value) { if (offset >= ARRAY_SIZE(au_io_out_map)) return; offset = au_io_out_map[offset]; if (offset < 0) return; __raw_writel(value, p->membase + (offset << p->regshift)); } /* Au1x00 haven't got a standard divisor latch */ static int au_serial_dl_read(struct uart_8250_port *up) { return __raw_readl(up->port.membase + 0x28); } static void au_serial_dl_write(struct uart_8250_port *up, int value) { __raw_writel(value, up->port.membase + 0x28); } #endif static unsigned int hub6_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); return inb(p->iobase + 1); } static void hub6_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; outb(p->hub6 - 1 + offset, p->iobase); outb(value, p->iobase + 1); } static unsigned int mem_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readb(p->membase + offset); } static void mem_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writeb(value, p->membase + offset); } static void mem16_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writew(value, p->membase + offset); } static unsigned int mem16_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readw(p->membase + offset); } static void mem32_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; writel(value, p->membase + offset); } static unsigned int mem32_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return readl(p->membase + offset); } static void mem32be_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; iowrite32be(value, p->membase + offset); } static unsigned int mem32be_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return ioread32be(p->membase + offset); } static unsigned int io_serial_in(struct uart_port *p, int offset) { offset = offset << p->regshift; return inb(p->iobase + offset); } static void io_serial_out(struct uart_port *p, int offset, int value) { offset = offset << p->regshift; outb(value, p->iobase + offset); } static int serial8250_default_handle_irq(struct uart_port *port); static void set_io_from_upio(struct uart_port *p) { struct uart_8250_port *up = up_to_u8250p(p); up->dl_read = default_serial_dl_read; up->dl_write = default_serial_dl_write; switch (p->iotype) { case UPIO_HUB6: p->serial_in = hub6_serial_in; p->serial_out = hub6_serial_out; break; case UPIO_MEM: p->serial_in = mem_serial_in; p->serial_out = mem_serial_out; break; case UPIO_MEM16: p->serial_in = mem16_serial_in; p->serial_out = mem16_serial_out; break; case UPIO_MEM32: p->serial_in = mem32_serial_in; p->serial_out = mem32_serial_out; break; case UPIO_MEM32BE: p->serial_in = mem32be_serial_in; p->serial_out = mem32be_serial_out; break; #ifdef CONFIG_SERIAL_8250_RT288X case UPIO_AU: p->serial_in = au_serial_in; p->serial_out = au_serial_out; up->dl_read = au_serial_dl_read; up->dl_write = au_serial_dl_write; break; #endif default: p->serial_in = io_serial_in; p->serial_out = io_serial_out; break; } /* Remember loaded iotype */ up->cur_iotype = p->iotype; p->handle_irq = serial8250_default_handle_irq; } static void serial_port_out_sync(struct uart_port *p, int offset, int value) { switch (p->iotype) { case UPIO_MEM: case UPIO_MEM16: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_AU: p->serial_out(p, offset, value); p->serial_in(p, UART_LCR); /* safe, no side-effects */ break; default: p->serial_out(p, offset, value); } } /* * For the 16C950 */ static void serial_icr_write(struct uart_8250_port *up, int offset, int value) { serial_out(up, UART_SCR, offset); serial_out(up, UART_ICR, value); } static unsigned int serial_icr_read(struct uart_8250_port *up, int offset) { unsigned int value; serial_icr_write(up, UART_ACR, up->acr | UART_ACR_ICRRD); serial_out(up, UART_SCR, offset); value = serial_in(up, UART_ICR); serial_icr_write(up, UART_ACR, up->acr); return value; } /* * FIFO support. */ static void serial8250_clear_fifos(struct uart_8250_port *p) { if (p->capabilities & UART_CAP_FIFO) { serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(p, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial_out(p, UART_FCR, 0); } } static inline void serial8250_em485_rts_after_send(struct uart_8250_port *p) { unsigned char mcr = serial8250_in_MCR(p); if (p->port.rs485.flags & SER_RS485_RTS_AFTER_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(p, mcr); } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t); static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t); void serial8250_clear_and_reinit_fifos(struct uart_8250_port *p) { serial8250_clear_fifos(p); serial_out(p, UART_FCR, p->fcr); } EXPORT_SYMBOL_GPL(serial8250_clear_and_reinit_fifos); void serial8250_rpm_get(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get); void serial8250_rpm_put(struct uart_8250_port *p) { if (!(p->capabilities & UART_CAP_RPM)) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put); /** * serial8250_em485_init() - put uart_8250_port into rs485 emulating * @p: uart_8250_port port instance * * The function is used to start rs485 software emulating on the * &struct uart_8250_port* @p. Namely, RTS is switched before/after * transmission. The function is idempotent, so it is safe to call it * multiple times. * * The caller MUST enable interrupt on empty shift register before * calling serial8250_em485_init(). This interrupt is not a part of * 8250 standard, but implementation defined. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_destroy() * * Return 0 - success, -errno - otherwise */ int serial8250_em485_init(struct uart_8250_port *p) { if (p->em485) return 0; p->em485 = kmalloc(sizeof(struct uart_8250_em485), GFP_ATOMIC); if (!p->em485) return -ENOMEM; hrtimer_init(&p->em485->stop_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); hrtimer_init(&p->em485->start_tx_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL); p->em485->stop_tx_timer.function = &serial8250_em485_handle_stop_tx; p->em485->start_tx_timer.function = &serial8250_em485_handle_start_tx; p->em485->port = p; p->em485->active_timer = NULL; serial8250_em485_rts_after_send(p); return 0; } EXPORT_SYMBOL_GPL(serial8250_em485_init); /** * serial8250_em485_destroy() - put uart_8250_port into normal state * @p: uart_8250_port port instance * * The function is used to stop rs485 software emulating on the * &struct uart_8250_port* @p. The function is idempotent, so it is safe to * call it multiple times. * * The function is supposed to be called from .rs485_config callback * or from any other callback protected with p->port.lock spinlock. * * See also serial8250_em485_init() */ void serial8250_em485_destroy(struct uart_8250_port *p) { if (!p->em485) return; hrtimer_cancel(&p->em485->start_tx_timer); hrtimer_cancel(&p->em485->stop_tx_timer); kfree(p->em485); p->em485 = NULL; } EXPORT_SYMBOL_GPL(serial8250_em485_destroy); /* * These two wrappers ensure that enable_runtime_pm_tx() can be called more than * once and disable_runtime_pm_tx() will still disable RPM because the fifo is * empty and the HW can idle again. */ void serial8250_rpm_get_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 1); if (rpm_active) return; pm_runtime_get_sync(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_get_tx); void serial8250_rpm_put_tx(struct uart_8250_port *p) { unsigned char rpm_active; if (!(p->capabilities & UART_CAP_RPM)) return; rpm_active = xchg(&p->rpm_tx_active, 0); if (!rpm_active) return; pm_runtime_mark_last_busy(p->port.dev); pm_runtime_put_autosuspend(p->port.dev); } EXPORT_SYMBOL_GPL(serial8250_rpm_put_tx); /* * IER sleep support. UARTs which have EFRs need the "extended * capability" bit enabled. Note that on XR16C850s, we need to * reset LCR to write to IER. */ static void serial8250_set_sleep(struct uart_8250_port *p, int sleep) { unsigned char lcr = 0, efr = 0; serial8250_rpm_get(p); if (p->capabilities & UART_CAP_SLEEP) { if (p->capabilities & UART_CAP_EFR) { lcr = serial_in(p, UART_LCR); efr = serial_in(p, UART_EFR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, UART_EFR_ECB); serial_out(p, UART_LCR, 0); } serial_out(p, UART_IER, sleep ? UART_IERX_SLEEP : 0); if (p->capabilities & UART_CAP_EFR) { serial_out(p, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(p, UART_EFR, efr); serial_out(p, UART_LCR, lcr); } } serial8250_rpm_put(p); } #ifdef CONFIG_SERIAL_8250_RSA /* * Attempts to turn on the RSA FIFO. Returns zero on failure. * We set the port uart clock rate if we succeed. */ static int __enable_rsa(struct uart_8250_port *up) { unsigned char mode; int result; mode = serial_in(up, UART_RSA_MSR); result = mode & UART_RSA_MSR_FIFO; if (!result) { serial_out(up, UART_RSA_MSR, mode | UART_RSA_MSR_FIFO); mode = serial_in(up, UART_RSA_MSR); result = mode & UART_RSA_MSR_FIFO; } if (result) up->port.uartclk = SERIAL_RSA_BAUD_BASE * 16; return result; } static void enable_rsa(struct uart_8250_port *up) { if (up->port.type == PORT_RSA) { if (up->port.uartclk != SERIAL_RSA_BAUD_BASE * 16) { spin_lock_irq(&up->port.lock); __enable_rsa(up); spin_unlock_irq(&up->port.lock); } if (up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) serial_out(up, UART_RSA_FRR, 0); } } /* * Attempts to turn off the RSA FIFO. Returns zero on failure. * It is unknown why interrupts were disabled in here. However, * the caller is expected to preserve this behaviour by grabbing * the spinlock before calling this function. */ static void disable_rsa(struct uart_8250_port *up) { unsigned char mode; int result; if (up->port.type == PORT_RSA && up->port.uartclk == SERIAL_RSA_BAUD_BASE * 16) { spin_lock_irq(&up->port.lock); mode = serial_in(up, UART_RSA_MSR); result = !(mode & UART_RSA_MSR_FIFO); if (!result) { serial_out(up, UART_RSA_MSR, mode & ~UART_RSA_MSR_FIFO); mode = serial_in(up, UART_RSA_MSR); result = !(mode & UART_RSA_MSR_FIFO); } if (result) up->port.uartclk = SERIAL_RSA_BAUD_BASE_LO * 16; spin_unlock_irq(&up->port.lock); } } #endif /* CONFIG_SERIAL_8250_RSA */ /* * This is a quickie test to see how big the FIFO is. * It doesn't work at all the time, more's the pity. */ static int size_fifo(struct uart_8250_port *up) { unsigned char old_fcr, old_mcr, old_lcr; unsigned short old_dl; int count; old_lcr = serial_in(up, UART_LCR); serial_out(up, UART_LCR, 0); old_fcr = serial_in(up, UART_FCR); old_mcr = serial8250_in_MCR(up); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT); serial8250_out_MCR(up, UART_MCR_LOOP); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(up); serial_dl_write(up, 0x0001); serial_out(up, UART_LCR, 0x03); for (count = 0; count < 256; count++) serial_out(up, UART_TX, count); mdelay(20);/* FIXME - schedule_timeout */ for (count = 0; (serial_in(up, UART_LSR) & UART_LSR_DR) && (count < 256); count++) serial_in(up, UART_RX); serial_out(up, UART_FCR, old_fcr); serial8250_out_MCR(up, old_mcr); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_dl_write(up, old_dl); serial_out(up, UART_LCR, old_lcr); return count; } /* * Read UART ID using the divisor method - set DLL and DLM to zero * and the revision will be in DLL and device type in DLM. We * preserve the device state across this. */ static unsigned int autoconfig_read_divisor_id(struct uart_8250_port *p) { unsigned char old_lcr; unsigned int id, old_dl; old_lcr = serial_in(p, UART_LCR); serial_out(p, UART_LCR, UART_LCR_CONF_MODE_A); old_dl = serial_dl_read(p); serial_dl_write(p, 0); id = serial_dl_read(p); serial_dl_write(p, old_dl); serial_out(p, UART_LCR, old_lcr); return id; } /* * This is a helper routine to autodetect StarTech/Exar/Oxsemi UART's. * When this function is called we know it is at least a StarTech * 16650 V2, but it might be one of several StarTech UARTs, or one of * its clones. (We treat the broken original StarTech 16650 V1 as a * 16550, and why not? Startech doesn't seem to even acknowledge its * existence.) * * What evil have men's minds wrought... */ static void autoconfig_has_efr(struct uart_8250_port *up) { unsigned int id1, id2, id3, rev; /* * Everything with an EFR has SLEEP */ up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; /* * First we check to see if it's an Oxford Semiconductor UART. * * If we have to do this here because some non-National * Semiconductor clone chips lock up if you try writing to the * LSR register (which serial_icr_read does) */ /* * Check for Oxford Semiconductor 16C950. * * EFR [4] must be set else this test fails. * * This shouldn't be necessary, but Mike Hudson (Exoray@isys.ca) * claims that it's needed for 952 dual UART's (which are not * recommended for new designs). */ up->acr = 0; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, UART_EFR_ECB); serial_out(up, UART_LCR, 0x00); id1 = serial_icr_read(up, UART_ID1); id2 = serial_icr_read(up, UART_ID2); id3 = serial_icr_read(up, UART_ID3); rev = serial_icr_read(up, UART_REV); DEBUG_AUTOCONF("950id=%02x:%02x:%02x:%02x ", id1, id2, id3, rev); if (id1 == 0x16 && id2 == 0xC9 && (id3 == 0x50 || id3 == 0x52 || id3 == 0x54)) { up->port.type = PORT_16C950; /* * Enable work around for the Oxford Semiconductor 952 rev B * chip which causes it to seriously miscalculate baud rates * when DLL is 0. */ if (id3 == 0x52 && rev == 0x01) up->bugs |= UART_BUG_QUOT; return; } /* * We check for a XR16C850 by setting DLL and DLM to 0, and then * reading back DLL and DLM. The chip type depends on the DLM * value read back: * 0x10 - XR16C850 and the DLL contains the chip revision. * 0x12 - XR16C2850. * 0x14 - XR16C854. */ id1 = autoconfig_read_divisor_id(up); DEBUG_AUTOCONF("850id=%04x ", id1); id2 = id1 >> 8; if (id2 == 0x10 || id2 == 0x12 || id2 == 0x14) { up->port.type = PORT_16850; return; } /* * It wasn't an XR16C850. * * We distinguish between the '654 and the '650 by counting * how many bytes are in the FIFO. I'm using this for now, * since that's the technique that was sent to me in the * serial driver update, but I'm not convinced this works. * I've had problems doing this in the past. -TYT */ if (size_fifo(up) == 64) up->port.type = PORT_16654; else up->port.type = PORT_16650V2; } /* * We detected a chip without a FIFO. Only two fall into * this category - the original 8250 and the 16450. The * 16450 has a scratch register (accessible with LCR=0) */ static void autoconfig_8250(struct uart_8250_port *up) { unsigned char scratch, status1, status2; up->port.type = PORT_8250; scratch = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0xa5); status1 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, 0x5a); status2 = serial_in(up, UART_SCR); serial_out(up, UART_SCR, scratch); if (status1 == 0xa5 && status2 == 0x5a) up->port.type = PORT_16450; } static int broken_efr(struct uart_8250_port *up) { /* * Exar ST16C2550 "A2" devices incorrectly detect as * having an EFR, and report an ID of 0x0201. See * http://linux.derkeiler.com/Mailing-Lists/Kernel/2004-11/4812.html */ if (autoconfig_read_divisor_id(up) == 0x0201 && size_fifo(up) == 16) return 1; return 0; } /* * We know that the chip has FIFOs. Does it have an EFR? The * EFR is located in the same register position as the IIR and * we know the top two bits of the IIR are currently set. The * EFR should contain zero. Try to read the EFR. */ static void autoconfig_16550a(struct uart_8250_port *up) { unsigned char status1, status2; unsigned int iersave; up->port.type = PORT_16550A; up->capabilities |= UART_CAP_FIFO; /* * Check for presence of the EFR when DLAB is set. * Only ST16C650V1 UARTs pass this test. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); if (serial_in(up, UART_EFR) == 0) { serial_out(up, UART_EFR, 0xA8); if (serial_in(up, UART_EFR) != 0) { DEBUG_AUTOCONF("EFRv1 "); up->port.type = PORT_16650; up->capabilities |= UART_CAP_EFR | UART_CAP_SLEEP; } else { serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) >> 5; serial_out(up, UART_FCR, 0); serial_out(up, UART_LCR, 0); if (status1 == 7) up->port.type = PORT_16550A_FSL64; else DEBUG_AUTOCONF("Motorola 8xxx DUART "); } serial_out(up, UART_EFR, 0); return; } /* * Maybe it requires 0xbf to be written to the LCR. * (other ST16C650V2 UARTs, TI16C752A, etc) */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); if (serial_in(up, UART_EFR) == 0 && !broken_efr(up)) { DEBUG_AUTOCONF("EFRv2 "); autoconfig_has_efr(up); return; } /* * Check for a National Semiconductor SuperIO chip. * Attempt to switch to bank 2, read the value of the LOOP bit * from EXCR1. Switch back to bank 0, change it in MCR. Then * switch back to bank 2, read it from EXCR1 again and check * it's changed. If so, set baud_base in EXCR2 to 921600. -- dwmw2 */ serial_out(up, UART_LCR, 0); status1 = serial8250_in_MCR(up); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ if (!((status2 ^ status1) & UART_MCR_LOOP)) { serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1 ^ UART_MCR_LOOP); serial_out(up, UART_LCR, 0xE0); status2 = serial_in(up, 0x02); /* EXCR1 */ serial_out(up, UART_LCR, 0); serial8250_out_MCR(up, status1); if ((status2 ^ status1) & UART_MCR_LOOP) { unsigned short quot; serial_out(up, UART_LCR, 0xE0); quot = serial_dl_read(up); quot <<= 3; if (ns16550a_goto_highspeed(up)) serial_dl_write(up, quot); serial_out(up, UART_LCR, 0); up->port.uartclk = 921600*16; up->port.type = PORT_NS16550A; up->capabilities |= UART_NATSEMI; return; } } /* * No EFR. Try to detect a TI16750, which only sets bit 5 of * the IIR when 64 byte FIFO mode is enabled when DLAB is set. * Try setting it with and without DLAB set. Cheap clones * set bit 5 without DLAB set. */ serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status1 = serial_in(up, UART_IIR) >> 5; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, UART_LCR_CONF_MODE_A); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO | UART_FCR7_64BYTE); status2 = serial_in(up, UART_IIR) >> 5; serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); serial_out(up, UART_LCR, 0); DEBUG_AUTOCONF("iir1=%d iir2=%d ", status1, status2); if (status1 == 6 && status2 == 7) { up->port.type = PORT_16750; up->capabilities |= UART_CAP_AFE | UART_CAP_SLEEP; return; } /* * Try writing and reading the UART_IER_UUE bit (b6). * If it works, this is probably one of the Xscale platform's * internal UARTs. * We're going to explicitly set the UUE bit to 0 before * trying to write and read a 1 just to make sure it's not * already a 1 and maybe locked there before we even start start. */ iersave = serial_in(up, UART_IER); serial_out(up, UART_IER, iersave & ~UART_IER_UUE); if (!(serial_in(up, UART_IER) & UART_IER_UUE)) { /* * OK it's in a known zero state, try writing and reading * without disturbing the current state of the other bits. */ serial_out(up, UART_IER, iersave | UART_IER_UUE); if (serial_in(up, UART_IER) & UART_IER_UUE) { /* * It's an Xscale. * We'll leave the UART_IER_UUE bit set to 1 (enabled). */ DEBUG_AUTOCONF("Xscale "); up->port.type = PORT_XSCALE; up->capabilities |= UART_CAP_UUE | UART_CAP_RTOIE; return; } } else { /* * If we got here we couldn't force the IER_UUE bit to 0. * Log it and continue. */ DEBUG_AUTOCONF("Couldn't force IER_UUE to 0 "); } serial_out(up, UART_IER, iersave); /* * We distinguish between 16550A and U6 16550A by counting * how many bytes are in the FIFO. */ if (up->port.type == PORT_16550A && size_fifo(up) == 64) { up->port.type = PORT_U6_16550A; up->capabilities |= UART_CAP_AFE; } } /* * This routine is called by rs_init() to initialize a specific serial * port. It determines what type of UART chip this serial port is * using: 8250, 16450, 16550, 16550A. The important question is * whether or not this UART is a 16550A or not, since this will * determine whether or not we can use its FIFO features or not. */ static void autoconfig(struct uart_8250_port *up) { unsigned char status1, scratch, scratch2, scratch3; unsigned char save_lcr, save_mcr; struct uart_port *port = &up->port; unsigned long flags; unsigned int old_capabilities; if (!port->iobase && !port->mapbase && !port->membase) return; DEBUG_AUTOCONF("%s: autoconf (0x%04lx, 0x%p): ", port->name, port->iobase, port->membase); /* * We really do need global IRQs disabled here - we're going to * be frobbing the chips IRQ enable register to see if it exists. */ spin_lock_irqsave(&port->lock, flags); up->capabilities = 0; up->bugs = 0; if (!(port->flags & UPF_BUGGY_UART)) { /* * Do a simple existence test first; if we fail this, * there's no point trying anything else. * * 0x80 is used as a nonsense port to prevent against * false positives due to ISA bus float. The * assumption is that 0x80 is a non-existent port; * which should be safe since include/asm/io.h also * makes this assumption. * * Note: this is safe as long as MCR bit 4 is clear * and the device is in "PC" mode. */ scratch = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); #ifdef __i386__ outb(0xff, 0x080); #endif /* * Mask out IER[7:4] bits for test as some UARTs (e.g. TL * 16C754B) allow only to modify them if an EFR bit is set. */ scratch2 = serial_in(up, UART_IER) & 0x0f; serial_out(up, UART_IER, 0x0F); #ifdef __i386__ outb(0, 0x080); #endif scratch3 = serial_in(up, UART_IER) & 0x0f; serial_out(up, UART_IER, scratch); if (scratch2 != 0 || scratch3 != 0x0F) { /* * We failed; there's nothing here */ spin_unlock_irqrestore(&port->lock, flags); DEBUG_AUTOCONF("IER test failed (%02x, %02x) ", scratch2, scratch3); goto out; } } save_mcr = serial8250_in_MCR(up); save_lcr = serial_in(up, UART_LCR); /* * Check to see if a UART is really there. Certain broken * internal modems based on the Rockwell chipset fail this * test, because they apparently don't implement the loopback * test mode. So this test is skipped on the COM 1 through * COM 4 ports. This *should* be safe, since no board * manufacturer would be stupid enough to design a board * that conflicts with COM 1-4 --- we hope! */ if (!(port->flags & UPF_SKIP_TEST)) { serial8250_out_MCR(up, UART_MCR_LOOP | 0x0A); status1 = serial_in(up, UART_MSR) & 0xF0; serial8250_out_MCR(up, save_mcr); if (status1 != 0x90) { spin_unlock_irqrestore(&port->lock, flags); DEBUG_AUTOCONF("LOOP test failed (%02x) ", status1); goto out; } } /* * We're pretty sure there's a port here. Lets find out what * type of port it is. The IIR top two bits allows us to find * out if it's 8250 or 16450, 16550, 16550A or later. This * determines what we test for next. * * We also initialise the EFR (if any) to zero for later. The * EFR occupies the same register location as the FCR and IIR. */ serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); serial_out(up, UART_EFR, 0); serial_out(up, UART_LCR, 0); serial_out(up, UART_FCR, UART_FCR_ENABLE_FIFO); /* Assign this as it is to truncate any bits above 7. */ scratch = serial_in(up, UART_IIR); switch (scratch >> 6) { case 0: autoconfig_8250(up); break; case 1: port->type = PORT_UNKNOWN; break; case 2: port->type = PORT_16550; break; case 3: autoconfig_16550a(up); break; } #ifdef CONFIG_SERIAL_8250_RSA /* * Only probe for RSA ports if we got the region. */ if (port->type == PORT_16550A && up->probe & UART_PROBE_RSA && __enable_rsa(up)) port->type = PORT_RSA; #endif serial_out(up, UART_LCR, save_lcr); port->fifosize = uart_config[up->port.type].fifo_size; old_capabilities = up->capabilities; up->capabilities = uart_config[port->type].flags; up->tx_loadsz = uart_config[port->type].tx_loadsz; if (port->type == PORT_UNKNOWN) goto out_lock; /* * Reset the UART. */ #ifdef CONFIG_SERIAL_8250_RSA if (port->type == PORT_RSA) serial_out(up, UART_RSA_FRR, 0); #endif serial8250_out_MCR(up, save_mcr); serial8250_clear_fifos(up); serial_in(up, UART_RX); if (up->capabilities & UART_CAP_UUE) serial_out(up, UART_IER, UART_IER_UUE); else serial_out(up, UART_IER, 0); out_lock: spin_unlock_irqrestore(&port->lock, flags); /* * Check if the device is a Fintek F81216A */ if (port->type == PORT_16550A && port->iotype == UPIO_PORT) fintek_8250_probe(up); if (up->capabilities != old_capabilities) { pr_warn("%s: detected caps %08x should be %08x\n", port->name, old_capabilities, up->capabilities); } out: DEBUG_AUTOCONF("iir=%d ", scratch); DEBUG_AUTOCONF("type=%s\n", uart_config[port->type].name); } static void autoconfig_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned char save_mcr, save_ier; unsigned char save_ICP = 0; unsigned int ICP = 0; unsigned long irqs; int irq; if (port->flags & UPF_FOURPORT) { ICP = (port->iobase & 0xfe0) | 0x1f; save_ICP = inb_p(ICP); outb_p(0x80, ICP); inb_p(ICP); } if (uart_console(port)) console_lock(); /* forget possible initially masked and pending IRQ */ probe_irq_off(probe_irq_on()); save_mcr = serial8250_in_MCR(up); save_ier = serial_in(up, UART_IER); serial8250_out_MCR(up, UART_MCR_OUT1 | UART_MCR_OUT2); irqs = probe_irq_on(); serial8250_out_MCR(up, 0); udelay(10); if (port->flags & UPF_FOURPORT) { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS); } else { serial8250_out_MCR(up, UART_MCR_DTR | UART_MCR_RTS | UART_MCR_OUT2); } serial_out(up, UART_IER, 0x0f); /* enable all intrs */ serial_in(up, UART_LSR); serial_in(up, UART_RX); serial_in(up, UART_IIR); serial_in(up, UART_MSR); serial_out(up, UART_TX, 0xFF); udelay(20); irq = probe_irq_off(irqs); serial8250_out_MCR(up, save_mcr); serial_out(up, UART_IER, save_ier); if (port->flags & UPF_FOURPORT) outb_p(save_ICP, ICP); if (uart_console(port)) console_unlock(); port->irq = (irq > 0) ? irq : 0; } static void serial8250_stop_rx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); up->ier &= ~(UART_IER_RLSI | UART_IER_RDI); up->port.read_status_mask &= ~UART_LSR_DR; serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); } static void __do_stop_tx_rs485(struct uart_8250_port *p) { serial8250_em485_rts_after_send(p); /* * Empty the RX FIFO, we are not interested in anything * received during the half-duplex transmission. * Enable previously disabled RX interrupts. */ if (!(p->port.rs485.flags & SER_RS485_RX_DURING_TX)) { serial8250_clear_and_reinit_fifos(p); p->ier |= UART_IER_RLSI | UART_IER_RDI; serial_port_out(&p->port, UART_IER, p->ier); } } static enum hrtimer_restart serial8250_em485_handle_stop_tx(struct hrtimer *t) { struct uart_8250_em485 *em485; struct uart_8250_port *p; unsigned long flags; em485 = container_of(t, struct uart_8250_em485, stop_tx_timer); p = em485->port; serial8250_rpm_get(p); spin_lock_irqsave(&p->port.lock, flags); if (em485->active_timer == &em485->stop_tx_timer) { __do_stop_tx_rs485(p); em485->active_timer = NULL; } spin_unlock_irqrestore(&p->port.lock, flags); serial8250_rpm_put(p); return HRTIMER_NORESTART; } static void start_hrtimer_ms(struct hrtimer *hrt, unsigned long msec) { long sec = msec / 1000; long nsec = (msec % 1000) * 1000000; ktime_t t = ktime_set(sec, nsec); hrtimer_start(hrt, t, HRTIMER_MODE_REL); } static void __stop_tx_rs485(struct uart_8250_port *p) { struct uart_8250_em485 *em485 = p->em485; /* * __do_stop_tx_rs485 is going to set RTS according to config * AND flush RX FIFO if required. */ if (p->port.rs485.delay_rts_after_send > 0) { em485->active_timer = &em485->stop_tx_timer; start_hrtimer_ms(&em485->stop_tx_timer, p->port.rs485.delay_rts_after_send); } else { __do_stop_tx_rs485(p); } } static inline void __do_stop_tx(struct uart_8250_port *p) { if (serial8250_clear_THRI(p)) serial8250_rpm_put_tx(p); } static inline void __stop_tx(struct uart_8250_port *p) { struct uart_8250_em485 *em485 = p->em485; if (em485) { unsigned char lsr = serial_in(p, UART_LSR); p->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; /* * To provide required timeing and allow FIFO transfer, * __stop_tx_rs485() must be called only when both FIFO and * shift register are empty. It is for device driver to enable * interrupt on TEMT. */ if ((lsr & BOTH_EMPTY) != BOTH_EMPTY) return; em485->active_timer = NULL; __stop_tx_rs485(p); } __do_stop_tx(p); } static void serial8250_stop_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); __stop_tx(up); /* * We really want to stop the transmitter from sending. */ if (port->type == PORT_16C950) { up->acr |= UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } serial8250_rpm_put(up); } static inline void __start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma && !up->dma->tx_dma(up)) return; if (serial8250_set_THRI(up)) { if (up->bugs & UART_BUG_TXEN) { unsigned char lsr; lsr = serial_in(up, UART_LSR); up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; if (lsr & UART_LSR_THRE) serial8250_tx_chars(up); } } /* * Re-enable the transmitter if we disabled it. */ if (port->type == PORT_16C950 && up->acr & UART_ACR_TXDIS) { up->acr &= ~UART_ACR_TXDIS; serial_icr_write(up, UART_ACR, up->acr); } } static inline void start_tx_rs485(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; unsigned char mcr; if (!(up->port.rs485.flags & SER_RS485_RX_DURING_TX)) serial8250_stop_rx(&up->port); /* * While serial8250_em485_handle_stop_tx() is a noop if * em485->active_timer != &em485->stop_tx_timer, it might happen that * the timer is still armed and triggers only after the current bunch of * chars is send and em485->active_timer == &em485->stop_tx_timer again. * So cancel the timer. There is still a theoretical race condition if * the timer is already running and only comes around to check for * em485->active_timer when &em485->stop_tx_timer is armed again. */ if (em485->active_timer == &em485->stop_tx_timer) hrtimer_try_to_cancel(&em485->stop_tx_timer); em485->active_timer = NULL; mcr = serial8250_in_MCR(up); if (!!(up->port.rs485.flags & SER_RS485_RTS_ON_SEND) != !!(mcr & UART_MCR_RTS)) { if (up->port.rs485.flags & SER_RS485_RTS_ON_SEND) mcr |= UART_MCR_RTS; else mcr &= ~UART_MCR_RTS; serial8250_out_MCR(up, mcr); if (up->port.rs485.delay_rts_before_send > 0) { em485->active_timer = &em485->start_tx_timer; start_hrtimer_ms(&em485->start_tx_timer, up->port.rs485.delay_rts_before_send); return; } } __start_tx(port); } static enum hrtimer_restart serial8250_em485_handle_start_tx(struct hrtimer *t) { struct uart_8250_em485 *em485; struct uart_8250_port *p; unsigned long flags; em485 = container_of(t, struct uart_8250_em485, start_tx_timer); p = em485->port; spin_lock_irqsave(&p->port.lock, flags); if (em485->active_timer == &em485->start_tx_timer) { __start_tx(&p->port); em485->active_timer = NULL; } spin_unlock_irqrestore(&p->port.lock, flags); return HRTIMER_NORESTART; } static void serial8250_start_tx(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); struct uart_8250_em485 *em485 = up->em485; serial8250_rpm_get_tx(up); if (em485 && em485->active_timer == &em485->start_tx_timer) return; if (em485) start_tx_rs485(port); else __start_tx(port); } static void serial8250_throttle(struct uart_port *port) { port->throttle(port); } static void serial8250_unthrottle(struct uart_port *port) { port->unthrottle(port); } static void serial8250_disable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_disable_ms(up->gpios); up->ier &= ~UART_IER_MSI; serial_port_out(port, UART_IER, up->ier); } static void serial8250_enable_ms(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); /* no MSR capabilities */ if (up->bugs & UART_BUG_NOMSR) return; mctrl_gpio_enable_ms(up->gpios); up->ier |= UART_IER_MSI; serial8250_rpm_get(up); serial_port_out(port, UART_IER, up->ier); serial8250_rpm_put(up); } void serial8250_read_char(struct uart_8250_port *up, unsigned char lsr) { struct uart_port *port = &up->port; unsigned char ch; char flag = TTY_NORMAL; if (likely(lsr & UART_LSR_DR)) ch = serial_in(up, UART_RX); else /* * Intel 82571 has a Serial Over Lan device that will * set UART_LSR_BI without setting UART_LSR_DR when * it receives a break. To avoid reading from the * receive buffer without UART_LSR_DR bit set, we * just force the read character to be 0 */ ch = 0; port->icount.rx++; lsr |= up->lsr_saved_flags; up->lsr_saved_flags = 0; if (unlikely(lsr & UART_LSR_BRK_ERROR_BITS)) { if (lsr & UART_LSR_BI) { lsr &= ~(UART_LSR_FE | UART_LSR_PE); port->icount.brk++; /* * We do the SysRQ and SAK checking * here because otherwise the break * may get masked by ignore_status_mask * or read_status_mask. */ if (uart_handle_break(port)) return; } else if (lsr & UART_LSR_PE) port->icount.parity++; else if (lsr & UART_LSR_FE) port->icount.frame++; if (lsr & UART_LSR_OE) port->icount.overrun++; /* * Mask off conditions which should be ignored. */ lsr &= port->read_status_mask; if (lsr & UART_LSR_BI) { pr_debug("%s: handling break\n", __func__); flag = TTY_BREAK; } else if (lsr & UART_LSR_PE) flag = TTY_PARITY; else if (lsr & UART_LSR_FE) flag = TTY_FRAME; } if (uart_prepare_sysrq_char(port, ch)) return; uart_insert_char(port, lsr, UART_LSR_OE, ch, flag); } EXPORT_SYMBOL_GPL(serial8250_read_char); /* * serial8250_rx_chars: processes according to the passed in LSR * value, and returns the remaining LSR bits not handled * by this Rx routine. */ unsigned char serial8250_rx_chars(struct uart_8250_port *up, unsigned char lsr) { struct uart_port *port = &up->port; int max_count = 256; do { serial8250_read_char(up, lsr); if (--max_count == 0) break; lsr = serial_in(up, UART_LSR); } while (lsr & (UART_LSR_DR | UART_LSR_BI)); tty_flip_buffer_push(&port->state->port); return lsr; } EXPORT_SYMBOL_GPL(serial8250_rx_chars); void serial8250_tx_chars(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct circ_buf *xmit = &port->state->xmit; int count; if (port->x_char) { serial_out(up, UART_TX, port->x_char); port->icount.tx++; port->x_char = 0; return; } if (uart_tx_stopped(port)) { serial8250_stop_tx(port); return; } if (uart_circ_empty(xmit)) { __stop_tx(up); return; } count = up->tx_loadsz; do { serial_out(up, UART_TX, xmit->buf[xmit->tail]); xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1); port->icount.tx++; if (uart_circ_empty(xmit)) break; if ((up->capabilities & UART_CAP_HFIFO) && (serial_in(up, UART_LSR) & BOTH_EMPTY) != BOTH_EMPTY) break; /* The BCM2835 MINI UART THRE bit is really a not-full bit. */ if ((up->capabilities & UART_CAP_MINI) && !(serial_in(up, UART_LSR) & UART_LSR_THRE)) break; } while (--count > 0); if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS) uart_write_wakeup(port); /* * With RPM enabled, we have to wait until the FIFO is empty before the * HW can go idle. So we get here once again with empty FIFO and disable * the interrupt and RPM in __stop_tx() */ if (uart_circ_empty(xmit) && !(up->capabilities & UART_CAP_RPM)) __stop_tx(up); } EXPORT_SYMBOL_GPL(serial8250_tx_chars); /* Caller holds uart port lock */ unsigned int serial8250_modem_status(struct uart_8250_port *up) { struct uart_port *port = &up->port; unsigned int status = serial_in(up, UART_MSR); status |= up->msr_saved_flags; up->msr_saved_flags = 0; if (status & UART_MSR_ANY_DELTA && up->ier & UART_IER_MSI && port->state != NULL) { if (status & UART_MSR_TERI) port->icount.rng++; if (status & UART_MSR_DDSR) port->icount.dsr++; if (status & UART_MSR_DDCD) uart_handle_dcd_change(port, status & UART_MSR_DCD); if (status & UART_MSR_DCTS) uart_handle_cts_change(port, status & UART_MSR_CTS); wake_up_interruptible(&port->state->port.delta_msr_wait); } return status; } EXPORT_SYMBOL_GPL(serial8250_modem_status); static bool handle_rx_dma(struct uart_8250_port *up, unsigned int iir) { switch (iir & 0x3f) { case UART_IIR_RDI: if (!up->dma->rx_running) break; fallthrough; case UART_IIR_RLSI: case UART_IIR_RX_TIMEOUT: serial8250_rx_dma_flush(up); return true; } return up->dma->rx_dma(up); } /* * This handles the interrupt from one port. */ int serial8250_handle_irq(struct uart_port *port, unsigned int iir) { unsigned char status; unsigned long flags; struct uart_8250_port *up = up_to_u8250p(port); struct tty_port *tport = &port->state->port; bool skip_rx = false; if (iir & UART_IIR_NO_INT) return 0; spin_lock_irqsave(&port->lock, flags); status = serial_port_in(port, UART_LSR); /* * If port is stopped and there are no error conditions in the * FIFO, then don't drain the FIFO, as this may lead to TTY buffer * overflow. Not servicing, RX FIFO would trigger auto HW flow * control when FIFO occupancy reaches preset threshold, thus * halting RX. This only works when auto HW flow control is * available. */ if (!(status & (UART_LSR_FIFOE | UART_LSR_BRK_ERROR_BITS)) && (port->status & (UPSTAT_AUTOCTS | UPSTAT_AUTORTS)) && !(port->read_status_mask & UART_LSR_DR)) skip_rx = true; if (status & (UART_LSR_DR | UART_LSR_BI) && !skip_rx) { struct irq_data *d; d = irq_get_irq_data(port->irq); if (d && irqd_is_wakeup_set(d)) pm_wakeup_event(tport->tty->dev, 0); if (!up->dma || handle_rx_dma(up, iir)) status = serial8250_rx_chars(up, status); } serial8250_modem_status(up); if ((!up->dma || up->dma->tx_err) && (status & UART_LSR_THRE) && (up->ier & UART_IER_THRI)) serial8250_tx_chars(up); uart_unlock_and_check_sysrq(port, flags); return 1; } EXPORT_SYMBOL_GPL(serial8250_handle_irq); static int serial8250_default_handle_irq(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int iir; int ret; serial8250_rpm_get(up); iir = serial_port_in(port, UART_IIR); ret = serial8250_handle_irq(port, iir); serial8250_rpm_put(up); return ret; } /* * Newer 16550 compatible parts such as the SC16C650 & Altera 16550 Soft IP * have a programmable TX threshold that triggers the THRE interrupt in * the IIR register. In this case, the THRE interrupt indicates the FIFO * has space available. Load it up with tx_loadsz bytes. */ static int serial8250_tx_threshold_handle_irq(struct uart_port *port) { unsigned long flags; unsigned int iir = serial_port_in(port, UART_IIR); /* TX Threshold IRQ triggered so load up FIFO */ if ((iir & UART_IIR_ID) == UART_IIR_THRI) { struct uart_8250_port *up = up_to_u8250p(port); spin_lock_irqsave(&port->lock, flags); serial8250_tx_chars(up); spin_unlock_irqrestore(&port->lock, flags); } iir = serial_port_in(port, UART_IIR); return serial8250_handle_irq(port, iir); } static unsigned int serial8250_tx_empty(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int result = 0; unsigned long flags; unsigned int lsr; serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); if (!serial8250_tx_dma_running(up)) { lsr = serial_port_in(port, UART_LSR); up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; if ((lsr & BOTH_EMPTY) == BOTH_EMPTY) result = TIOCSER_TEMT; } spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); return result; } unsigned int serial8250_do_get_mctrl(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int status; unsigned int val; serial8250_rpm_get(up); status = serial8250_modem_status(up); serial8250_rpm_put(up); val = serial8250_MSR_to_TIOCM(status); if (up->gpios) return mctrl_gpio_get(up->gpios, &val); return val; } EXPORT_SYMBOL_GPL(serial8250_do_get_mctrl); static unsigned int serial8250_get_mctrl(struct uart_port *port) { if (port->get_mctrl) return port->get_mctrl(port); return serial8250_do_get_mctrl(port); } void serial8250_do_set_mctrl(struct uart_port *port, unsigned int mctrl) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char mcr; mcr = serial8250_TIOCM_to_MCR(mctrl); mcr = (mcr & up->mcr_mask) | up->mcr_force | up->mcr; serial8250_out_MCR(up, mcr); } EXPORT_SYMBOL_GPL(serial8250_do_set_mctrl); static void serial8250_set_mctrl(struct uart_port *port, unsigned int mctrl) { if (port->set_mctrl) port->set_mctrl(port, mctrl); else serial8250_do_set_mctrl(port, mctrl); } static void serial8250_break_ctl(struct uart_port *port, int break_state) { struct uart_8250_port *up = up_to_u8250p(port); unsigned long flags; serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); if (break_state == -1) up->lcr |= UART_LCR_SBC; else up->lcr &= ~UART_LCR_SBC; serial_port_out(port, UART_LCR, up->lcr); spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); } /* * Wait for transmitter & holding register to empty */ static void wait_for_xmitr(struct uart_8250_port *up, int bits) { unsigned int status, tmout = 10000; /* Wait up to 10ms for the character(s) to be sent. */ for (;;) { status = serial_in(up, UART_LSR); up->lsr_saved_flags |= status & LSR_SAVE_FLAGS; if ((status & bits) == bits) break; if (--tmout == 0) break; udelay(1); touch_nmi_watchdog(); } /* Wait up to 1s for flow control if necessary */ if (up->port.flags & UPF_CONS_FLOW) { for (tmout = 1000000; tmout; tmout--) { unsigned int msr = serial_in(up, UART_MSR); up->msr_saved_flags |= msr & MSR_SAVE_FLAGS; if (msr & UART_MSR_CTS) break; udelay(1); touch_nmi_watchdog(); } } } #ifdef CONFIG_CONSOLE_POLL /* * Console polling routines for writing and reading from the uart while * in an interrupt or debug context. */ static int serial8250_get_poll_char(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char lsr; int status; serial8250_rpm_get(up); lsr = serial_port_in(port, UART_LSR); if (!(lsr & UART_LSR_DR)) { status = NO_POLL_CHAR; goto out; } status = serial_port_in(port, UART_RX); out: serial8250_rpm_put(up); return status; } static void serial8250_put_poll_char(struct uart_port *port, unsigned char c) { unsigned int ier; struct uart_8250_port *up = up_to_u8250p(port); serial8250_rpm_get(up); /* * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); if (up->capabilities & UART_CAP_UUE) serial_port_out(port, UART_IER, UART_IER_UUE); else serial_port_out(port, UART_IER, 0); wait_for_xmitr(up, BOTH_EMPTY); /* * Send the character out. */ serial_port_out(port, UART_TX, c); /* * Finally, wait for transmitter to become empty * and restore the IER */ wait_for_xmitr(up, BOTH_EMPTY); serial_port_out(port, UART_IER, ier); serial8250_rpm_put(up); } #endif /* CONFIG_CONSOLE_POLL */ int serial8250_do_startup(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned long flags; unsigned char lsr, iir; int retval; if (!port->fifosize) port->fifosize = uart_config[port->type].fifo_size; if (!up->tx_loadsz) up->tx_loadsz = uart_config[port->type].tx_loadsz; if (!up->capabilities) up->capabilities = uart_config[port->type].flags; up->mcr = 0; if (port->iotype != up->cur_iotype) set_io_from_upio(port); serial8250_rpm_get(up); if (port->type == PORT_16C950) { /* Wake up and initialize UART */ up->acr = 0; serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, UART_EFR, UART_EFR_ECB); serial_port_out(port, UART_IER, 0); serial_port_out(port, UART_LCR, 0); serial_icr_write(up, UART_CSR, 0); /* Reset the UART */ serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); serial_port_out(port, UART_EFR, UART_EFR_ECB); serial_port_out(port, UART_LCR, 0); } if (port->type == PORT_DA830) { /* Reset the port */ serial_port_out(port, UART_IER, 0); serial_port_out(port, UART_DA830_PWREMU_MGMT, 0); mdelay(10); /* Enable Tx, Rx and free run mode */ serial_port_out(port, UART_DA830_PWREMU_MGMT, UART_DA830_PWREMU_MGMT_UTRST | UART_DA830_PWREMU_MGMT_URRST | UART_DA830_PWREMU_MGMT_FREE); } if (port->type == PORT_NPCM) { /* * Nuvoton calls the scratch register 'UART_TOR' (timeout * register). Enable it, and set TIOC (timeout interrupt * comparator) to be 0x20 for correct operation. */ serial_port_out(port, UART_NPCM_TOR, UART_NPCM_TOIE | 0x20); } #ifdef CONFIG_SERIAL_8250_RSA /* * If this is an RSA port, see if we can kick it up to the * higher speed clock. */ enable_rsa(up); #endif if (port->type == PORT_XR17V35X) { /* * First enable access to IER [7:5], ISR [5:4], FCR [5:4], * MCR [7:5] and MSR [7:0] */ serial_port_out(port, UART_XR_EFR, UART_EFR_ECB); /* * Make sure all interrups are masked until initialization is * complete and the FIFOs are cleared */ serial_port_out(port, UART_IER, 0); } /* * Clear the FIFO buffers and disable them. * (they will be reenabled in set_termios()) */ serial8250_clear_fifos(up); /* * Clear the interrupt registers. */ serial_port_in(port, UART_LSR); serial_port_in(port, UART_RX); serial_port_in(port, UART_IIR); serial_port_in(port, UART_MSR); /* * At this point, there's no way the LSR could still be 0xff; * if it is, then bail out, because there's likely no UART * here. */ if (!(port->flags & UPF_BUGGY_UART) && (serial_port_in(port, UART_LSR) == 0xff)) { pr_info_ratelimited("%s: LSR safety check engaged!\n", port->name); retval = -ENODEV; goto out; } /* * For a XR16C850, we need to set the trigger levels */ if (port->type == PORT_16850) { unsigned char fctr; serial_out(up, UART_LCR, UART_LCR_CONF_MODE_B); fctr = serial_in(up, UART_FCTR) & ~(UART_FCTR_RX|UART_FCTR_TX); serial_port_out(port, UART_FCTR, fctr | UART_FCTR_TRGD | UART_FCTR_RX); serial_port_out(port, UART_TRG, UART_TRG_96); serial_port_out(port, UART_FCTR, fctr | UART_FCTR_TRGD | UART_FCTR_TX); serial_port_out(port, UART_TRG, UART_TRG_96); serial_port_out(port, UART_LCR, 0); } /* * For the Altera 16550 variants, set TX threshold trigger level. */ if (((port->type == PORT_ALTR_16550_F32) || (port->type == PORT_ALTR_16550_F64) || (port->type == PORT_ALTR_16550_F128)) && (port->fifosize > 1)) { /* Bounds checking of TX threshold (valid 0 to fifosize-2) */ if ((up->tx_loadsz < 2) || (up->tx_loadsz > port->fifosize)) { pr_err("%s TX FIFO Threshold errors, skipping\n", port->name); } else { serial_port_out(port, UART_ALTR_AFR, UART_ALTR_EN_TXFIFO_LW); serial_port_out(port, UART_ALTR_TX_LOW, port->fifosize - up->tx_loadsz); port->handle_irq = serial8250_tx_threshold_handle_irq; } } /* Check if we need to have shared IRQs */ if (port->irq && (up->port.flags & UPF_SHARE_IRQ)) up->port.irqflags |= IRQF_SHARED; if (port->irq && !(up->port.flags & UPF_NO_THRE_TEST)) { unsigned char iir1; if (port->irqflags & IRQF_SHARED) disable_irq_nosync(port->irq); /* * Test for UARTs that do not reassert THRE when the * transmitter is idle and the interrupt has already * been cleared. Real 16550s should always reassert * this interrupt whenever the transmitter is idle and * the interrupt is enabled. Delays are necessary to * allow register changes to become visible. */ spin_lock_irqsave(&port->lock, flags); wait_for_xmitr(up, UART_LSR_THRE); serial_port_out_sync(port, UART_IER, UART_IER_THRI); udelay(1); /* allow THRE to set */ iir1 = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); serial_port_out_sync(port, UART_IER, UART_IER_THRI); udelay(1); /* allow a working UART time to re-assert THRE */ iir = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); spin_unlock_irqrestore(&port->lock, flags); if (port->irqflags & IRQF_SHARED) enable_irq(port->irq); /* * If the interrupt is not reasserted, or we otherwise * don't trust the iir, setup a timer to kick the UART * on a regular basis. */ if ((!(iir1 & UART_IIR_NO_INT) && (iir & UART_IIR_NO_INT)) || up->port.flags & UPF_BUG_THRE) { up->bugs |= UART_BUG_THRE; } } retval = up->ops->setup_irq(up); if (retval) goto out; /* * Now, initialize the UART */ serial_port_out(port, UART_LCR, UART_LCR_WLEN8); spin_lock_irqsave(&port->lock, flags); if (up->port.flags & UPF_FOURPORT) { if (!up->port.irq) up->port.mctrl |= TIOCM_OUT1; } else /* * Most PC uarts need OUT2 raised to enable interrupts. */ if (port->irq) up->port.mctrl |= TIOCM_OUT2; serial8250_set_mctrl(port, port->mctrl); /* * Serial over Lan (SoL) hack: * Intel 8257x Gigabit ethernet chips have a 16550 emulation, to be * used for Serial Over Lan. Those chips take a longer time than a * normal serial device to signalize that a transmission data was * queued. Due to that, the above test generally fails. One solution * would be to delay the reading of iir. However, this is not * reliable, since the timeout is variable. So, let's just don't * test if we receive TX irq. This way, we'll never enable * UART_BUG_TXEN. */ if (up->port.quirks & UPQ_NO_TXEN_TEST) goto dont_test_tx_en; /* * Do a quick test to see if we receive an interrupt when we enable * the TX irq. */ serial_port_out(port, UART_IER, UART_IER_THRI); lsr = serial_port_in(port, UART_LSR); iir = serial_port_in(port, UART_IIR); serial_port_out(port, UART_IER, 0); if (lsr & UART_LSR_TEMT && iir & UART_IIR_NO_INT) { if (!(up->bugs & UART_BUG_TXEN)) { up->bugs |= UART_BUG_TXEN; pr_debug("%s - enabling bad tx status workarounds\n", port->name); } } else { up->bugs &= ~UART_BUG_TXEN; } dont_test_tx_en: spin_unlock_irqrestore(&port->lock, flags); /* * Clear the interrupt registers again for luck, and clear the * saved flags to avoid getting false values from polling * routines or the previous session. */ serial_port_in(port, UART_LSR); serial_port_in(port, UART_RX); serial_port_in(port, UART_IIR); serial_port_in(port, UART_MSR); up->lsr_saved_flags = 0; up->msr_saved_flags = 0; /* * Request DMA channels for both RX and TX. */ if (up->dma) { retval = serial8250_request_dma(up); if (retval) { pr_warn_ratelimited("%s - failed to request DMA\n", port->name); up->dma = NULL; } } /* * Set the IER shadow for rx interrupts but defer actual interrupt * enable until after the FIFOs are enabled; otherwise, an already- * active sender can swamp the interrupt handler with "too much work". */ up->ier = UART_IER_RLSI | UART_IER_RDI; if (port->flags & UPF_FOURPORT) { unsigned int icp; /* * Enable interrupts on the AST Fourport board */ icp = (port->iobase & 0xfe0) | 0x01f; outb_p(0x80, icp); inb_p(icp); } retval = 0; out: serial8250_rpm_put(up); return retval; } EXPORT_SYMBOL_GPL(serial8250_do_startup); static int serial8250_startup(struct uart_port *port) { if (port->startup) return port->startup(port); return serial8250_do_startup(port); } void serial8250_do_shutdown(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); unsigned long flags; serial8250_rpm_get(up); /* * Disable interrupts from this port */ spin_lock_irqsave(&port->lock, flags); up->ier = 0; serial_port_out(port, UART_IER, 0); spin_unlock_irqrestore(&port->lock, flags); synchronize_irq(port->irq); if (up->dma) serial8250_release_dma(up); spin_lock_irqsave(&port->lock, flags); if (port->flags & UPF_FOURPORT) { /* reset interrupts on the AST Fourport board */ inb((port->iobase & 0xfe0) | 0x1f); port->mctrl |= TIOCM_OUT1; } else port->mctrl &= ~TIOCM_OUT2; serial8250_set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); /* * Disable break condition and FIFOs */ serial_port_out(port, UART_LCR, serial_port_in(port, UART_LCR) & ~UART_LCR_SBC); serial8250_clear_fifos(up); #ifdef CONFIG_SERIAL_8250_RSA /* * Reset the RSA board back to 115kbps compat mode. */ disable_rsa(up); #endif /* * Read data port to reset things, and then unlink from * the IRQ chain. */ serial_port_in(port, UART_RX); serial8250_rpm_put(up); up->ops->release_irq(up); } EXPORT_SYMBOL_GPL(serial8250_do_shutdown); static void serial8250_shutdown(struct uart_port *port) { if (port->shutdown) port->shutdown(port); else serial8250_do_shutdown(port); } /* Nuvoton NPCM UARTs have a custom divisor calculation */ static unsigned int npcm_get_divisor(struct uart_8250_port *up, unsigned int baud) { struct uart_port *port = &up->port; return DIV_ROUND_CLOSEST(port->uartclk, 16 * baud + 2) - 2; } static void serial8250_flush_buffer(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (up->dma) serial8250_tx_dma_flush(up); } static unsigned int serial8250_do_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) { struct uart_8250_port *up = up_to_u8250p(port); unsigned int quot; /* * Handle magic divisors for baud rates above baud_base on * SMSC SuperIO chips. * */ if ((port->flags & UPF_MAGIC_MULTIPLIER) && baud == (port->uartclk/4)) quot = 0x8001; else if ((port->flags & UPF_MAGIC_MULTIPLIER) && baud == (port->uartclk/8)) quot = 0x8002; else if (up->port.type == PORT_NPCM) quot = npcm_get_divisor(up, baud); else quot = uart_get_divisor(port, baud); /* * Oxford Semi 952 rev B workaround */ if (up->bugs & UART_BUG_QUOT && (quot & 0xff) == 0) quot++; return quot; } static unsigned int serial8250_get_divisor(struct uart_port *port, unsigned int baud, unsigned int *frac) { if (port->get_divisor) return port->get_divisor(port, baud, frac); return serial8250_do_get_divisor(port, baud, frac); } static unsigned char serial8250_compute_lcr(struct uart_8250_port *up, tcflag_t c_cflag) { unsigned char cval; switch (c_cflag & CSIZE) { case CS5: cval = UART_LCR_WLEN5; break; case CS6: cval = UART_LCR_WLEN6; break; case CS7: cval = UART_LCR_WLEN7; break; default: case CS8: cval = UART_LCR_WLEN8; break; } if (c_cflag & CSTOPB) cval |= UART_LCR_STOP; if (c_cflag & PARENB) { cval |= UART_LCR_PARITY; if (up->bugs & UART_BUG_PARITY) up->fifo_bug = true; } if (!(c_cflag & PARODD)) cval |= UART_LCR_EPAR; #ifdef CMSPAR if (c_cflag & CMSPAR) cval |= UART_LCR_SPAR; #endif return cval; } void serial8250_do_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot, unsigned int quot_frac) { struct uart_8250_port *up = up_to_u8250p(port); /* Workaround to enable 115200 baud on OMAP1510 internal ports */ if (is_omap1510_8250(up)) { if (baud == 115200) { quot = 1; serial_port_out(port, UART_OMAP_OSC_12M_SEL, 1); } else serial_port_out(port, UART_OMAP_OSC_12M_SEL, 0); } /* * For NatSemi, switch to bank 2 not bank 1, to avoid resetting EXCR2, * otherwise just set DLAB */ if (up->capabilities & UART_NATSEMI) serial_port_out(port, UART_LCR, 0xe0); else serial_port_out(port, UART_LCR, up->lcr | UART_LCR_DLAB); serial_dl_write(up, quot); } EXPORT_SYMBOL_GPL(serial8250_do_set_divisor); static void serial8250_set_divisor(struct uart_port *port, unsigned int baud, unsigned int quot, unsigned int quot_frac) { if (port->set_divisor) port->set_divisor(port, baud, quot, quot_frac); else serial8250_do_set_divisor(port, baud, quot, quot_frac); } static unsigned int serial8250_get_baud_rate(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { unsigned int tolerance = port->uartclk / 100; unsigned int min; unsigned int max; /* * Handle magic divisors for baud rates above baud_base on SMSC * Super I/O chips. Enable custom rates of clk/4 and clk/8, but * disable divisor values beyond 32767, which are unavailable. */ if (port->flags & UPF_MAGIC_MULTIPLIER) { min = port->uartclk / 16 / UART_DIV_MAX >> 1; max = (port->uartclk + tolerance) / 4; } else { min = port->uartclk / 16 / UART_DIV_MAX; max = (port->uartclk + tolerance) / 16; } /* * Ask the core to calculate the divisor for us. * Allow 1% tolerance at the upper limit so uart clks marginally * slower than nominal still match standard baud rates without * causing transmission errors. */ return uart_get_baud_rate(port, termios, old, min, max); } void serial8250_do_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { struct uart_8250_port *up = up_to_u8250p(port); unsigned char cval; unsigned long flags; unsigned int baud, quot, frac = 0; if (up->capabilities & UART_CAP_MINI) { termios->c_cflag &= ~(CSTOPB | PARENB | PARODD | CMSPAR); if ((termios->c_cflag & CSIZE) == CS5 || (termios->c_cflag & CSIZE) == CS6) termios->c_cflag = (termios->c_cflag & ~CSIZE) | CS7; } cval = serial8250_compute_lcr(up, termios->c_cflag); baud = serial8250_get_baud_rate(port, termios, old); quot = serial8250_get_divisor(port, baud, &frac); /* * Ok, we're now changing the port state. Do it with * interrupts disabled. */ serial8250_rpm_get(up); spin_lock_irqsave(&port->lock, flags); up->lcr = cval; /* Save computed LCR */ if (up->capabilities & UART_CAP_FIFO && port->fifosize > 1) { /* NOTE: If fifo_bug is not set, a user can set RX_trigger. */ if ((baud < 2400 && !up->dma) || up->fifo_bug) { up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= UART_FCR_TRIGGER_1; } } /* * MCR-based auto flow control. When AFE is enabled, RTS will be * deasserted when the receive FIFO contains more characters than * the trigger, or the MCR RTS bit is cleared. */ if (up->capabilities & UART_CAP_AFE) { up->mcr &= ~UART_MCR_AFE; if (termios->c_cflag & CRTSCTS) up->mcr |= UART_MCR_AFE; } /* * Update the per-port timeout. */ uart_update_timeout(port, termios->c_cflag, baud); port->read_status_mask = UART_LSR_OE | UART_LSR_THRE | UART_LSR_DR; if (termios->c_iflag & INPCK) port->read_status_mask |= UART_LSR_FE | UART_LSR_PE; if (termios->c_iflag & (IGNBRK | BRKINT | PARMRK)) port->read_status_mask |= UART_LSR_BI; /* * Characteres to ignore */ port->ignore_status_mask = 0; if (termios->c_iflag & IGNPAR) port->ignore_status_mask |= UART_LSR_PE | UART_LSR_FE; if (termios->c_iflag & IGNBRK) { port->ignore_status_mask |= UART_LSR_BI; /* * If we're ignoring parity and break indicators, * ignore overruns too (for real raw support). */ if (termios->c_iflag & IGNPAR) port->ignore_status_mask |= UART_LSR_OE; } /* * ignore all characters if CREAD is not set */ if ((termios->c_cflag & CREAD) == 0) port->ignore_status_mask |= UART_LSR_DR; /* * CTS flow control flag and modem status interrupts */ up->ier &= ~UART_IER_MSI; if (!(up->bugs & UART_BUG_NOMSR) && UART_ENABLE_MS(&up->port, termios->c_cflag)) up->ier |= UART_IER_MSI; if (up->capabilities & UART_CAP_UUE) up->ier |= UART_IER_UUE; if (up->capabilities & UART_CAP_RTOIE) up->ier |= UART_IER_RTOIE; serial_port_out(port, UART_IER, up->ier); if (up->capabilities & UART_CAP_EFR) { unsigned char efr = 0; /* * TI16C752/Startech hardware flow control. FIXME: * - TI16C752 requires control thresholds to be set. * - UART_MCR_RTS is ineffective if auto-RTS mode is enabled. */ if (termios->c_cflag & CRTSCTS) efr |= UART_EFR_CTS; serial_port_out(port, UART_LCR, UART_LCR_CONF_MODE_B); if (port->flags & UPF_EXAR_EFR) serial_port_out(port, UART_XR_EFR, efr); else serial_port_out(port, UART_EFR, efr); } serial8250_set_divisor(port, baud, quot, frac); /* * LCR DLAB must be set to enable 64-byte FIFO mode. If the FCR * is written without DLAB set, this mode will be disabled. */ if (port->type == PORT_16750) serial_port_out(port, UART_FCR, up->fcr); serial_port_out(port, UART_LCR, up->lcr); /* reset DLAB */ if (port->type != PORT_16750) { /* emulated UARTs (Lucent Venus 167x) need two steps */ if (up->fcr & UART_FCR_ENABLE_FIFO) serial_port_out(port, UART_FCR, UART_FCR_ENABLE_FIFO); serial_port_out(port, UART_FCR, up->fcr); /* set fcr */ } serial8250_set_mctrl(port, port->mctrl); spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); /* Don't rewrite B0 */ if (tty_termios_baud_rate(termios)) tty_termios_encode_baud_rate(termios, baud, baud); } EXPORT_SYMBOL(serial8250_do_set_termios); static void serial8250_set_termios(struct uart_port *port, struct ktermios *termios, struct ktermios *old) { if (port->set_termios) port->set_termios(port, termios, old); else serial8250_do_set_termios(port, termios, old); } void serial8250_do_set_ldisc(struct uart_port *port, struct ktermios *termios) { if (termios->c_line == N_PPS) { port->flags |= UPF_HARDPPS_CD; spin_lock_irq(&port->lock); serial8250_enable_ms(port); spin_unlock_irq(&port->lock); } else { port->flags &= ~UPF_HARDPPS_CD; if (!UART_ENABLE_MS(port, termios->c_cflag)) { spin_lock_irq(&port->lock); serial8250_disable_ms(port); spin_unlock_irq(&port->lock); } } } EXPORT_SYMBOL_GPL(serial8250_do_set_ldisc); static void serial8250_set_ldisc(struct uart_port *port, struct ktermios *termios) { if (port->set_ldisc) port->set_ldisc(port, termios); else serial8250_do_set_ldisc(port, termios); } void serial8250_do_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) { struct uart_8250_port *p = up_to_u8250p(port); serial8250_set_sleep(p, state != 0); } EXPORT_SYMBOL(serial8250_do_pm); static void serial8250_pm(struct uart_port *port, unsigned int state, unsigned int oldstate) { if (port->pm) port->pm(port, state, oldstate); else serial8250_do_pm(port, state, oldstate); } static unsigned int serial8250_port_size(struct uart_8250_port *pt) { if (pt->port.mapsize) return pt->port.mapsize; if (pt->port.iotype == UPIO_AU) { if (pt->port.type == PORT_RT2880) return 0x100; return 0x1000; } if (is_omap1_8250(pt)) return 0x16 << pt->port.regshift; return 8 << pt->port.regshift; } /* * Resource handling. */ static int serial8250_request_std_resource(struct uart_8250_port *up) { unsigned int size = serial8250_port_size(up); struct uart_port *port = &up->port; int ret = 0; switch (port->iotype) { case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) { ret = -EINVAL; break; } if (!request_mem_region(port->mapbase, size, "serial")) { ret = -EBUSY; break; } if (port->flags & UPF_IOREMAP) { port->membase = ioremap_nocache(port->mapbase, size); if (!port->membase) { release_mem_region(port->mapbase, size); ret = -ENOMEM; } } break; case UPIO_HUB6: case UPIO_PORT: if (!request_region(port->iobase, size, "serial")) ret = -EBUSY; break; } return ret; } static void serial8250_release_std_resource(struct uart_8250_port *up) { unsigned int size = serial8250_port_size(up); struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_AU: case UPIO_TSI: case UPIO_MEM32: case UPIO_MEM32BE: case UPIO_MEM16: case UPIO_MEM: if (!port->mapbase) break; if (port->flags & UPF_IOREMAP) { iounmap(port->membase); port->membase = NULL; } release_mem_region(port->mapbase, size); break; case UPIO_HUB6: case UPIO_PORT: release_region(port->iobase, size); break; } } static void serial8250_release_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); serial8250_release_std_resource(up); } static int serial8250_request_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); return serial8250_request_std_resource(up); } static int fcr_get_rxtrig_bytes(struct uart_8250_port *up) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; unsigned char bytes; bytes = conf_type->rxtrig_bytes[UART_FCR_R_TRIG_BITS(up->fcr)]; return bytes ? bytes : -EOPNOTSUPP; } static int bytes_to_fcr_rxtrig(struct uart_8250_port *up, unsigned char bytes) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; int i; if (!conf_type->rxtrig_bytes[UART_FCR_R_TRIG_BITS(UART_FCR_R_TRIG_00)]) return -EOPNOTSUPP; for (i = 1; i < UART_FCR_R_TRIG_MAX_STATE; i++) { if (bytes < conf_type->rxtrig_bytes[i]) /* Use the nearest lower value */ return (--i) << UART_FCR_R_TRIG_SHIFT; } return UART_FCR_R_TRIG_11; } static int do_get_rxtrig(struct tty_port *port) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = state->uart_port; struct uart_8250_port *up = up_to_u8250p(uport); if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1) return -EINVAL; return fcr_get_rxtrig_bytes(up); } static int do_serial8250_get_rxtrig(struct tty_port *port) { int rxtrig_bytes; mutex_lock(&port->mutex); rxtrig_bytes = do_get_rxtrig(port); mutex_unlock(&port->mutex); return rxtrig_bytes; } static ssize_t serial8250_get_attr_rx_trig_bytes(struct device *dev, struct device_attribute *attr, char *buf) { struct tty_port *port = dev_get_drvdata(dev); int rxtrig_bytes; rxtrig_bytes = do_serial8250_get_rxtrig(port); if (rxtrig_bytes < 0) return rxtrig_bytes; return snprintf(buf, PAGE_SIZE, "%d\n", rxtrig_bytes); } static int do_set_rxtrig(struct tty_port *port, unsigned char bytes) { struct uart_state *state = container_of(port, struct uart_state, port); struct uart_port *uport = state->uart_port; struct uart_8250_port *up = up_to_u8250p(uport); int rxtrig; if (!(up->capabilities & UART_CAP_FIFO) || uport->fifosize <= 1 || up->fifo_bug) return -EINVAL; rxtrig = bytes_to_fcr_rxtrig(up, bytes); if (rxtrig < 0) return rxtrig; serial8250_clear_fifos(up); up->fcr &= ~UART_FCR_TRIGGER_MASK; up->fcr |= (unsigned char)rxtrig; serial_out(up, UART_FCR, up->fcr); return 0; } static int do_serial8250_set_rxtrig(struct tty_port *port, unsigned char bytes) { int ret; mutex_lock(&port->mutex); ret = do_set_rxtrig(port, bytes); mutex_unlock(&port->mutex); return ret; } static ssize_t serial8250_set_attr_rx_trig_bytes(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct tty_port *port = dev_get_drvdata(dev); unsigned char bytes; int ret; if (!count) return -EINVAL; ret = kstrtou8(buf, 10, &bytes); if (ret < 0) return ret; ret = do_serial8250_set_rxtrig(port, bytes); if (ret < 0) return ret; return count; } static DEVICE_ATTR(rx_trig_bytes, S_IRUSR | S_IWUSR | S_IRGRP, serial8250_get_attr_rx_trig_bytes, serial8250_set_attr_rx_trig_bytes); static struct attribute *serial8250_dev_attrs[] = { &dev_attr_rx_trig_bytes.attr, NULL, }; static struct attribute_group serial8250_dev_attr_group = { .attrs = serial8250_dev_attrs, }; static void register_dev_spec_attr_grp(struct uart_8250_port *up) { const struct serial8250_config *conf_type = &uart_config[up->port.type]; if (conf_type->rxtrig_bytes[0]) up->port.attr_group = &serial8250_dev_attr_group; } static void serial8250_config_port(struct uart_port *port, int flags) { struct uart_8250_port *up = up_to_u8250p(port); int ret; /* * Find the region that we can probe for. This in turn * tells us whether we can probe for the type of port. */ ret = serial8250_request_std_resource(up); if (ret < 0) return; if (port->iotype != up->cur_iotype) set_io_from_upio(port); if (flags & UART_CONFIG_TYPE) autoconfig(up); /* if access method is AU, it is a 16550 with a quirk */ if (port->type == PORT_16550A && port->iotype == UPIO_AU) up->bugs |= UART_BUG_NOMSR; /* HW bugs may trigger IRQ while IIR == NO_INT */ if (port->type == PORT_TEGRA) up->bugs |= UART_BUG_NOMSR; if (port->type != PORT_UNKNOWN && flags & UART_CONFIG_IRQ) autoconfig_irq(up); if (port->type == PORT_UNKNOWN) serial8250_release_std_resource(up); register_dev_spec_attr_grp(up); up->fcr = uart_config[up->port.type].fcr; } static int serial8250_verify_port(struct uart_port *port, struct serial_struct *ser) { if (ser->irq >= nr_irqs || ser->irq < 0 || ser->baud_base < 9600 || ser->type < PORT_UNKNOWN || ser->type >= ARRAY_SIZE(uart_config) || ser->type == PORT_CIRRUS || ser->type == PORT_STARTECH) return -EINVAL; return 0; } static const char *serial8250_type(struct uart_port *port) { int type = port->type; if (type >= ARRAY_SIZE(uart_config)) type = 0; return uart_config[type].name; } static const struct uart_ops serial8250_pops = { .tx_empty = serial8250_tx_empty, .set_mctrl = serial8250_set_mctrl, .get_mctrl = serial8250_get_mctrl, .stop_tx = serial8250_stop_tx, .start_tx = serial8250_start_tx, .throttle = serial8250_throttle, .unthrottle = serial8250_unthrottle, .stop_rx = serial8250_stop_rx, .enable_ms = serial8250_enable_ms, .break_ctl = serial8250_break_ctl, .startup = serial8250_startup, .shutdown = serial8250_shutdown, .flush_buffer = serial8250_flush_buffer, .set_termios = serial8250_set_termios, .set_ldisc = serial8250_set_ldisc, .pm = serial8250_pm, .type = serial8250_type, .release_port = serial8250_release_port, .request_port = serial8250_request_port, .config_port = serial8250_config_port, .verify_port = serial8250_verify_port, #ifdef CONFIG_CONSOLE_POLL .poll_get_char = serial8250_get_poll_char, .poll_put_char = serial8250_put_poll_char, #endif }; void serial8250_init_port(struct uart_8250_port *up) { struct uart_port *port = &up->port; spin_lock_init(&port->lock); port->pm = NULL; port->ops = &serial8250_pops; up->cur_iotype = 0xFF; } EXPORT_SYMBOL_GPL(serial8250_init_port); void serial8250_set_defaults(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (up->port.flags & UPF_FIXED_TYPE) { unsigned int type = up->port.type; if (!up->port.fifosize) up->port.fifosize = uart_config[type].fifo_size; if (!up->tx_loadsz) up->tx_loadsz = uart_config[type].tx_loadsz; if (!up->capabilities) up->capabilities = uart_config[type].flags; } set_io_from_upio(port); /* default dma handlers */ if (up->dma) { if (!up->dma->tx_dma) up->dma->tx_dma = serial8250_tx_dma; if (!up->dma->rx_dma) up->dma->rx_dma = serial8250_rx_dma; } } EXPORT_SYMBOL_GPL(serial8250_set_defaults); #ifdef CONFIG_SERIAL_8250_CONSOLE static void serial8250_console_putchar(struct uart_port *port, int ch) { struct uart_8250_port *up = up_to_u8250p(port); wait_for_xmitr(up, UART_LSR_THRE); serial_port_out(port, UART_TX, ch); } /* * Restore serial console when h/w power-off detected */ static void serial8250_console_restore(struct uart_8250_port *up) { struct uart_port *port = &up->port; struct ktermios termios; unsigned int baud, quot, frac = 0; termios.c_cflag = port->cons->cflag; if (port->state->port.tty && termios.c_cflag == 0) termios.c_cflag = port->state->port.tty->termios.c_cflag; baud = serial8250_get_baud_rate(port, &termios, NULL); quot = serial8250_get_divisor(port, baud, &frac); serial8250_set_divisor(port, baud, quot, frac); serial_port_out(port, UART_LCR, up->lcr); serial8250_out_MCR(up, up->mcr | UART_MCR_DTR | UART_MCR_RTS); } /* * Print a string to the serial port trying not to disturb * any possible real use of the port... * * The console_lock must be held when we get here. */ void serial8250_console_write(struct uart_8250_port *up, const char *s, unsigned int count) { struct uart_port *port = &up->port; unsigned long flags; unsigned int ier; int locked = 1; touch_nmi_watchdog(); serial8250_rpm_get(up); if (oops_in_progress) locked = spin_trylock_irqsave(&port->lock, flags); else spin_lock_irqsave(&port->lock, flags); /* * First save the IER then disable the interrupts */ ier = serial_port_in(port, UART_IER); if (up->capabilities & UART_CAP_UUE) serial_port_out(port, UART_IER, UART_IER_UUE); else serial_port_out(port, UART_IER, 0); /* check scratch reg to see if port powered off during system sleep */ if (up->canary && (up->canary != serial_port_in(port, UART_SCR))) { serial8250_console_restore(up); up->canary = 0; } uart_console_write(port, s, count, serial8250_console_putchar); /* * Finally, wait for transmitter to become empty * and restore the IER */ wait_for_xmitr(up, BOTH_EMPTY); serial_port_out(port, UART_IER, ier); /* * The receive handling will happen properly because the * receive ready bit will still be set; it is not cleared * on read. However, modem control will not, we must * call it if we have saved something in the saved flags * while processing with interrupts off. */ if (up->msr_saved_flags) serial8250_modem_status(up); if (locked) spin_unlock_irqrestore(&port->lock, flags); serial8250_rpm_put(up); } static unsigned int probe_baud(struct uart_port *port) { unsigned char lcr, dll, dlm; unsigned int quot; lcr = serial_port_in(port, UART_LCR); serial_port_out(port, UART_LCR, lcr | UART_LCR_DLAB); dll = serial_port_in(port, UART_DLL); dlm = serial_port_in(port, UART_DLM); serial_port_out(port, UART_LCR, lcr); quot = (dlm << 8) | dll; return (port->uartclk / 16) / quot; } int serial8250_console_setup(struct uart_port *port, char *options, bool probe) { int baud = 9600; int bits = 8; int parity = 'n'; int flow = 'n'; if (!port->iobase && !port->membase) return -ENODEV; if (options) uart_parse_options(options, &baud, &parity, &bits, &flow); else if (probe) baud = probe_baud(port); return uart_set_options(port, port->cons, baud, parity, bits, flow); } #endif /* CONFIG_SERIAL_8250_CONSOLE */ MODULE_LICENSE("GPL"); |
| 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ /* linux/net/inet/arp.h */ #ifndef _ARP_H #define _ARP_H #include <linux/if_arp.h> #include <linux/hash.h> #include <net/neighbour.h> extern struct neigh_table arp_tbl; static inline u32 arp_hashfn(const void *pkey, const struct net_device *dev, u32 *hash_rnd) { u32 key = *(const u32 *)pkey; u32 val = key ^ hash32_ptr(dev); return val * hash_rnd[0]; } #ifdef CONFIG_INET static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) key = INADDR_ANY; return ___neigh_lookup_noref(&arp_tbl, neigh_key_eq32, arp_hashfn, &key, dev); } #else static inline struct neighbour *__ipv4_neigh_lookup_noref(struct net_device *dev, u32 key) { return NULL; } #endif static inline struct neighbour *__ipv4_neigh_lookup(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); return n; } static inline void __ipv4_confirm_neigh(struct net_device *dev, u32 key) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv4_neigh_lookup_noref(dev, key); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } void arp_init(void); int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg); void arp_send(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *th); int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir); void arp_ifdown(struct net_device *dev); int arp_invalidate(struct net_device *dev, __be32 ip, bool force); struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct net_device *dev, __be32 src_ip, const unsigned char *dest_hw, const unsigned char *src_hw, const unsigned char *target_hw); void arp_xmit(struct sk_buff *skb); #endif /* _ARP_H */ |
| 74 74 74 74 74 74 15 74 74 67 74 152 82 74 67 466 465 466 16 12 16 3 3 9 6 2 3 74 11 11 11 11 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 | // SPDX-License-Identifier: GPL-2.0-only #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/workqueue.h> #include <linux/rtnetlink.h> #include <linux/cache.h> #include <linux/slab.h> #include <linux/list.h> #include <linux/delay.h> #include <linux/sched.h> #include <linux/idr.h> #include <linux/rculist.h> #include <linux/nsproxy.h> #include <linux/fs.h> #include <linux/proc_ns.h> #include <linux/file.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> /* * Our network namespace constructor/destructor lists */ static LIST_HEAD(pernet_list); static struct list_head *first_device = &pernet_list; LIST_HEAD(net_namespace_list); EXPORT_SYMBOL_GPL(net_namespace_list); /* Protects net_namespace_list. Nests iside rtnl_lock() */ DECLARE_RWSEM(net_rwsem); EXPORT_SYMBOL_GPL(net_rwsem); #ifdef CONFIG_KEYS static struct key_tag init_net_key_domain = { .usage = REFCOUNT_INIT(1) }; #endif struct net init_net = { .count = REFCOUNT_INIT(1), .dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head), #ifdef CONFIG_KEYS .key_domain = &init_net_key_domain, #endif }; EXPORT_SYMBOL(init_net); static bool init_net_initialized; /* * pernet_ops_rwsem: protects: pernet_list, net_generic_ids, * init_net_initialized and first_device pointer. * This is internal net namespace object. Please, don't use it * outside. */ DECLARE_RWSEM(pernet_ops_rwsem); EXPORT_SYMBOL_GPL(pernet_ops_rwsem); #define MIN_PERNET_OPS_ID \ ((sizeof(struct net_generic) + sizeof(void *) - 1) / sizeof(void *)) #define INITIAL_NET_GEN_PTRS 13 /* +1 for len +2 for rcu_head */ static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; static struct net_generic *net_alloc_generic(void) { unsigned int gen_ptrs = READ_ONCE(max_gen_ptrs); unsigned int generic_size; struct net_generic *ng; generic_size = offsetof(struct net_generic, ptr[gen_ptrs]); ng = kzalloc(generic_size, GFP_KERNEL); if (ng) ng->s.len = gen_ptrs; return ng; } static int net_assign_generic(struct net *net, unsigned int id, void *data) { struct net_generic *ng, *old_ng; BUG_ON(id < MIN_PERNET_OPS_ID); old_ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); if (old_ng->s.len > id) { old_ng->ptr[id] = data; return 0; } ng = net_alloc_generic(); if (ng == NULL) return -ENOMEM; /* * Some synchronisation notes: * * The net_generic explores the net->gen array inside rcu * read section. Besides once set the net->gen->ptr[x] * pointer never changes (see rules in netns/generic.h). * * That said, we simply duplicate this array and schedule * the old copy for kfree after a grace period. */ memcpy(&ng->ptr[MIN_PERNET_OPS_ID], &old_ng->ptr[MIN_PERNET_OPS_ID], (old_ng->s.len - MIN_PERNET_OPS_ID) * sizeof(void *)); ng->ptr[id] = data; rcu_assign_pointer(net->gen, ng); kfree_rcu(old_ng, s.rcu); return 0; } static int ops_init(const struct pernet_operations *ops, struct net *net) { struct net_generic *ng; int err = -ENOMEM; void *data = NULL; if (ops->id && ops->size) { data = kzalloc(ops->size, GFP_KERNEL); if (!data) goto out; err = net_assign_generic(net, *ops->id, data); if (err) goto cleanup; } err = 0; if (ops->init) err = ops->init(net); if (!err) return 0; if (ops->id && ops->size) { ng = rcu_dereference_protected(net->gen, lockdep_is_held(&pernet_ops_rwsem)); ng->ptr[*ops->id] = NULL; } cleanup: kfree(data); out: return err; } static void ops_free(const struct pernet_operations *ops, struct net *net) { if (ops->id && ops->size) { kfree(net_generic(net, *ops->id)); } } static void ops_pre_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->pre_exit) { list_for_each_entry(net, net_exit_list, exit_list) ops->pre_exit(net); } } static void ops_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->exit) { list_for_each_entry(net, net_exit_list, exit_list) { ops->exit(net); cond_resched(); } } if (ops->exit_batch) ops->exit_batch(net_exit_list); } static void ops_free_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { struct net *net; if (ops->size && ops->id) { list_for_each_entry(net, net_exit_list, exit_list) ops_free(ops, net); } } /* should be called with nsid_lock held */ static int alloc_netid(struct net *net, struct net *peer, int reqid) { int min = 0, max = 0; if (reqid >= 0) { min = reqid; max = reqid + 1; } return idr_alloc(&net->netns_ids, peer, min, max, GFP_ATOMIC); } /* This function is used by idr_for_each(). If net is equal to peer, the * function returns the id so that idr_for_each() stops. Because we cannot * returns the id 0 (idr_for_each() will not stop), we return the magic value * NET_ID_ZERO (-1) for it. */ #define NET_ID_ZERO -1 static int net_eq_idr(int id, void *net, void *peer) { if (net_eq(net, peer)) return id ? : NET_ID_ZERO; return 0; } /* Must be called from RCU-critical section or with nsid_lock held. If * a new id is assigned, the bool alloc is set to true, thus the * caller knows that the new id must be notified via rtnl. */ static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); bool alloc_it = *alloc; *alloc = false; /* Magic value for id 0. */ if (id == NET_ID_ZERO) return 0; if (id > 0) return id; if (alloc_it) { id = alloc_netid(net, peer, -1); *alloc = true; return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED; } return NETNSA_NSID_NOT_ASSIGNED; } /* Must be called from RCU-critical section or with nsid_lock held */ static int __peernet2id(struct net *net, struct net *peer) { bool no = false; return __peernet2id_alloc(net, peer, &no); } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { bool alloc = false, alive = false; int id; if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED; spin_lock_bh(&net->nsid_lock); /* * When peer is obtained from RCU lists, we may race with * its cleanup. Check whether it's alive, and this guarantees * we never hash a peer back to net->netns_ids, after it has * just been idr_remove()'d from there in cleanup_net(). */ if (maybe_get_net(peer)) alive = alloc = true; id = __peernet2id_alloc(net, peer, &alloc); spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); if (alive) put_net(peer); return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(struct net *net, struct net *peer) { int id; rcu_read_lock(); id = __peernet2id(net, peer); rcu_read_unlock(); return id; } EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. */ bool peernet_has_id(struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } struct net *get_net_ns_by_id(struct net *net, int id) { struct net *peer; if (id < 0) return NULL; rcu_read_lock(); peer = idr_find(&net->netns_ids, id); if (peer) peer = maybe_get_net(peer); rcu_read_unlock(); return peer; } /* * setup_net runs the initializers for the network namespace object. */ static __net_init int setup_net(struct net *net, struct user_namespace *user_ns) { /* Must be called with pernet_ops_rwsem held */ const struct pernet_operations *ops, *saved_ops; int error = 0; LIST_HEAD(net_exit_list); refcount_set(&net->count, 1); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); net->dev_base_seq = 1; net->user_ns = user_ns; idr_init(&net->netns_ids); spin_lock_init(&net->nsid_lock); mutex_init(&net->ipv4.ra_mutex); list_for_each_entry(ops, &pernet_list, list) { error = ops_init(ops, net); if (error < 0) goto out_undo; } down_write(&net_rwsem); list_add_tail_rcu(&net->list, &net_namespace_list); up_write(&net_rwsem); out: return error; out_undo: /* Walk through the list backwards calling the exit functions * for the pernet modules whose init functions did not fail. */ list_add(&net->exit_list, &net_exit_list); saved_ops = ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); ops = saved_ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); rcu_barrier(); goto out; } static int __net_init net_defaults_init_net(struct net *net) { net->core.sysctl_somaxconn = SOMAXCONN; return 0; } static struct pernet_operations net_defaults_ops = { .init = net_defaults_init_net, }; static __init int net_defaults_init(void) { if (register_pernet_subsys(&net_defaults_ops)) panic("Cannot initialize net default settings"); return 0; } core_initcall(net_defaults_init); #ifdef CONFIG_NET_NS static struct ucounts *inc_net_namespaces(struct user_namespace *ns) { return inc_ucount(ns, current_euid(), UCOUNT_NET_NAMESPACES); } static void dec_net_namespaces(struct ucounts *ucounts) { dec_ucount(ucounts, UCOUNT_NET_NAMESPACES); } static struct kmem_cache *net_cachep __ro_after_init; static struct workqueue_struct *netns_wq; static struct net *net_alloc(void) { struct net *net = NULL; struct net_generic *ng; ng = net_alloc_generic(); if (!ng) goto out; net = kmem_cache_zalloc(net_cachep, GFP_KERNEL); if (!net) goto out_free; #ifdef CONFIG_KEYS net->key_domain = kzalloc(sizeof(struct key_tag), GFP_KERNEL); if (!net->key_domain) goto out_free_2; refcount_set(&net->key_domain->usage, 1); #endif rcu_assign_pointer(net->gen, ng); out: return net; #ifdef CONFIG_KEYS out_free_2: kmem_cache_free(net_cachep, net); net = NULL; #endif out_free: kfree(ng); goto out; } static void net_free(struct net *net) { kfree(rcu_access_pointer(net->gen)); kmem_cache_free(net_cachep, net); } void net_drop_ns(void *p) { struct net *ns = p; if (ns && refcount_dec_and_test(&ns->passive)) net_free(ns); } struct net *copy_net_ns(unsigned long flags, struct user_namespace *user_ns, struct net *old_net) { struct ucounts *ucounts; struct net *net; int rv; if (!(flags & CLONE_NEWNET)) return get_net(old_net); ucounts = inc_net_namespaces(user_ns); if (!ucounts) return ERR_PTR(-ENOSPC); net = net_alloc(); if (!net) { rv = -ENOMEM; goto dec_ucounts; } refcount_set(&net->passive, 1); net->ucounts = ucounts; get_user_ns(user_ns); rv = down_read_killable(&pernet_ops_rwsem); if (rv < 0) goto put_userns; rv = setup_net(net, user_ns); up_read(&pernet_ops_rwsem); if (rv < 0) { put_userns: #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(user_ns); net_drop_ns(net); dec_ucounts: dec_net_namespaces(ucounts); return ERR_PTR(rv); } return net; } /** * net_ns_get_ownership - get sysfs ownership data for @net * @net: network namespace in question (can be NULL) * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns the uid/gid pair of root in the user namespace associated with the * given network namespace. */ void net_ns_get_ownership(const struct net *net, kuid_t *uid, kgid_t *gid) { if (net) { kuid_t ns_root_uid = make_kuid(net->user_ns, 0); kgid_t ns_root_gid = make_kgid(net->user_ns, 0); if (uid_valid(ns_root_uid)) *uid = ns_root_uid; if (gid_valid(ns_root_gid)) *gid = ns_root_gid; } else { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; } } EXPORT_SYMBOL_GPL(net_ns_get_ownership); static void unhash_nsid(struct net *net, struct net *last) { struct net *tmp; /* This function is only called from cleanup_net() work, * and this work is the only process, that may delete * a net from net_namespace_list. So, when the below * is executing, the list may only grow. Thus, we do not * use for_each_net_rcu() or net_rwsem. */ for_each_net(tmp) { int id; spin_lock_bh(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } spin_lock_bh(&net->nsid_lock); idr_destroy(&net->netns_ids); spin_unlock_bh(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); static void cleanup_net(struct work_struct *work) { const struct pernet_operations *ops; struct net *net, *tmp, *last; struct llist_node *net_kill_list; LIST_HEAD(net_exit_list); /* Atomically snapshot the list of namespaces to cleanup */ net_kill_list = llist_del_all(&cleanup_list); down_read(&pernet_ops_rwsem); /* Don't let anyone else find us. */ down_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) list_del_rcu(&net->list); /* Cache last net. After we unlock rtnl, no one new net * added to net_namespace_list can assign nsid pointer * to a net from net_kill_list (see peernet2id_alloc()). * So, we skip them in unhash_nsid(). * * Note, that unhash_nsid() does not delete nsid links * between net_kill_list's nets, as they've already * deleted from net_namespace_list. But, this would be * useless anyway, as netns_ids are destroyed there. */ last = list_last_entry(&net_namespace_list, struct net, list); up_write(&net_rwsem); llist_for_each_entry(net, net_kill_list, cleanup_list) { unhash_nsid(net, last); list_add_tail(&net->exit_list, &net_exit_list); } /* Run all of the network namespace pre_exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_pre_exit_list(ops, &net_exit_list); /* * Another CPU might be rcu-iterating the list, wait for it. * This needs to be before calling the exit() notifiers, so * the rcu_barrier() below isn't sufficient alone. * Also the pre_exit() and exit() methods need this barrier. */ synchronize_rcu(); /* Run all of the network namespace exit methods */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); /* Free the net generic variables */ list_for_each_entry_reverse(ops, &pernet_list, list) ops_free_list(ops, &net_exit_list); up_read(&pernet_ops_rwsem); /* Ensure there are no outstanding rcu callbacks using this * network namespace. */ rcu_barrier(); /* Finally it is safe to free my network namespace structure */ list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); dec_net_namespaces(net->ucounts); #ifdef CONFIG_KEYS key_remove_domain(net->key_domain); #endif put_user_ns(net->user_ns); net_drop_ns(net); } } /** * net_ns_barrier - wait until concurrent net_cleanup_work is done * * cleanup_net runs from work queue and will first remove namespaces * from the global list, then run net exit functions. * * Call this in module exit path to make sure that all netns * ->exit ops have been invoked before the function is removed. */ void net_ns_barrier(void) { down_write(&pernet_ops_rwsem); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL(net_ns_barrier); static DECLARE_WORK(net_cleanup_work, cleanup_net); void __put_net(struct net *net) { /* Cleanup the network namespace in process context */ if (llist_add(&net->cleanup_list, &cleanup_list)) queue_work(netns_wq, &net_cleanup_work); } EXPORT_SYMBOL_GPL(__put_net); /** * get_net_ns - increment the refcount of the network namespace * @ns: common namespace (net) * * Returns the net's common namespace or ERR_PTR() if ref is zero. */ struct ns_common *get_net_ns(struct ns_common *ns) { struct net *net; net = maybe_get_net(container_of(ns, struct net, ns)); if (net) return &net->ns; return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(get_net_ns); struct net *get_net_ns_by_fd(int fd) { struct file *file; struct ns_common *ns; struct net *net; file = proc_ns_fget(fd); if (IS_ERR(file)) return ERR_CAST(file); ns = get_proc_ns(file_inode(file)); if (ns->ops == &netns_operations) net = get_net(container_of(ns, struct net, ns)); else net = ERR_PTR(-EINVAL); fput(file); return net; } #else struct net *get_net_ns_by_fd(int fd) { return ERR_PTR(-EINVAL); } #endif EXPORT_SYMBOL_GPL(get_net_ns_by_fd); struct net *get_net_ns_by_pid(pid_t pid) { struct task_struct *tsk; struct net *net; /* Lookup the network namespace */ net = ERR_PTR(-ESRCH); rcu_read_lock(); tsk = find_task_by_vpid(pid); if (tsk) { struct nsproxy *nsproxy; task_lock(tsk); nsproxy = tsk->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(tsk); } rcu_read_unlock(); return net; } EXPORT_SYMBOL_GPL(get_net_ns_by_pid); static __net_init int net_ns_net_init(struct net *net) { #ifdef CONFIG_NET_NS net->ns.ops = &netns_operations; #endif return ns_alloc_inum(&net->ns); } static __net_exit void net_ns_net_exit(struct net *net) { ns_free_inum(&net->ns); } static struct pernet_operations __net_initdata net_ns_ops = { .init = net_ns_net_init, .exit = net_ns_net_exit, }; static const struct nla_policy rtnl_net_policy[NETNSA_MAX + 1] = { [NETNSA_NONE] = { .type = NLA_UNSPEC }, [NETNSA_NSID] = { .type = NLA_S32 }, [NETNSA_PID] = { .type = NLA_U32 }, [NETNSA_FD] = { .type = NLA_U32 }, [NETNSA_TARGET_NSID] = { .type = NLA_S32 }, }; static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct nlattr *nla; struct net *peer; int nsid, err; err = nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; if (!tb[NETNSA_NSID]) { NL_SET_ERR_MSG(extack, "nsid is missing"); return -EINVAL; } nsid = nla_get_s32(tb[NETNSA_NSID]); if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } spin_lock_bh(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { spin_unlock_bh(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns already has a nsid assigned"); goto out; } err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; NL_SET_BAD_ATTR(extack, tb[NETNSA_NSID]); NL_SET_ERR_MSG(extack, "The specified nsid is already used"); } out: put_net(peer); return err; } static int rtnl_net_get_size(void) { return NLMSG_ALIGN(sizeof(struct rtgenmsg)) + nla_total_size(sizeof(s32)) /* NETNSA_NSID */ + nla_total_size(sizeof(s32)) /* NETNSA_CURRENT_NSID */ ; } struct net_fill_args { u32 portid; u32 seq; int flags; int cmd; int nsid; bool add_ref; int ref_nsid; }; static int rtnl_net_fill(struct sk_buff *skb, struct net_fill_args *args) { struct nlmsghdr *nlh; struct rtgenmsg *rth; nlh = nlmsg_put(skb, args->portid, args->seq, args->cmd, sizeof(*rth), args->flags); if (!nlh) return -EMSGSIZE; rth = nlmsg_data(nlh); rth->rtgen_family = AF_UNSPEC; if (nla_put_s32(skb, NETNSA_NSID, args->nsid)) goto nla_put_failure; if (args->add_ref && nla_put_s32(skb, NETNSA_CURRENT_NSID, args->ref_nsid)) goto nla_put_failure; nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } static int rtnl_net_valid_getid_req(struct sk_buff *skb, const struct nlmsghdr *nlh, struct nlattr **tb, struct netlink_ext_ack *extack) { int i, err; if (!netlink_strict_get_check(skb)) return nlmsg_parse_deprecated(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; switch (i) { case NETNSA_PID: case NETNSA_FD: case NETNSA_NSID: case NETNSA_TARGET_NSID: break; default: NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request"); return -EINVAL; } } return 0; } static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct nlattr *tb[NETNSA_MAX + 1]; struct net_fill_args fillargs = { .portid = NETLINK_CB(skb).portid, .seq = nlh->nlmsg_seq, .cmd = RTM_NEWNSID, }; struct net *peer, *target = net; struct nlattr *nla; struct sk_buff *msg; int err; err = rtnl_net_valid_getid_req(skb, nlh, tb, extack); if (err < 0) return err; if (tb[NETNSA_PID]) { peer = get_net_ns_by_pid(nla_get_u32(tb[NETNSA_PID])); nla = tb[NETNSA_PID]; } else if (tb[NETNSA_FD]) { peer = get_net_ns_by_fd(nla_get_u32(tb[NETNSA_FD])); nla = tb[NETNSA_FD]; } else if (tb[NETNSA_NSID]) { peer = get_net_ns_by_id(net, nla_get_s32(tb[NETNSA_NSID])); if (!peer) peer = ERR_PTR(-ENOENT); nla = tb[NETNSA_NSID]; } else { NL_SET_ERR_MSG(extack, "Peer netns reference is missing"); return -EINVAL; } if (IS_ERR(peer)) { NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, "Peer netns reference is invalid"); return PTR_ERR(peer); } if (tb[NETNSA_TARGET_NSID]) { int id = nla_get_s32(tb[NETNSA_TARGET_NSID]); target = rtnl_get_net_ns_capable(NETLINK_CB(skb).sk, id); if (IS_ERR(target)) { NL_SET_BAD_ATTR(extack, tb[NETNSA_TARGET_NSID]); NL_SET_ERR_MSG(extack, "Target netns reference is invalid"); err = PTR_ERR(target); goto out; } fillargs.add_ref = true; fillargs.ref_nsid = peernet2id(net, peer); } msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); if (!msg) { err = -ENOMEM; goto out; } fillargs.nsid = peernet2id(target, peer); err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; err = rtnl_unicast(msg, net, NETLINK_CB(skb).portid); goto out; err_out: nlmsg_free(msg); out: if (fillargs.add_ref) put_net(target); put_net(peer); return err; } struct rtnl_net_dump_cb { struct net *tgt_net; struct net *ref_net; struct sk_buff *skb; struct net_fill_args fillargs; int idx; int s_idx; }; /* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; int ret; if (net_cb->idx < net_cb->s_idx) goto cont; net_cb->fillargs.nsid = id; if (net_cb->fillargs.add_ref) net_cb->fillargs.ref_nsid = __peernet2id(net_cb->ref_net, peer); ret = rtnl_net_fill(net_cb->skb, &net_cb->fillargs); if (ret < 0) return ret; cont: net_cb->idx++; return 0; } static int rtnl_valid_dump_net_req(const struct nlmsghdr *nlh, struct sock *sk, struct rtnl_net_dump_cb *net_cb, struct netlink_callback *cb) { struct netlink_ext_ack *extack = cb->extack; struct nlattr *tb[NETNSA_MAX + 1]; int err, i; err = nlmsg_parse_deprecated_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, rtnl_net_policy, extack); if (err < 0) return err; for (i = 0; i <= NETNSA_MAX; i++) { if (!tb[i]) continue; if (i == NETNSA_TARGET_NSID) { struct net *net; net = rtnl_get_net_ns_capable(sk, nla_get_s32(tb[i])); if (IS_ERR(net)) { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Invalid target network namespace id"); return PTR_ERR(net); } net_cb->fillargs.add_ref = true; net_cb->ref_net = net_cb->tgt_net; net_cb->tgt_net = net; } else { NL_SET_BAD_ATTR(extack, tb[i]); NL_SET_ERR_MSG(extack, "Unsupported attribute in dump request"); return -EINVAL; } } return 0; } static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) { struct rtnl_net_dump_cb net_cb = { .tgt_net = sock_net(skb->sk), .skb = skb, .fillargs = { .portid = NETLINK_CB(cb->skb).portid, .seq = cb->nlh->nlmsg_seq, .flags = NLM_F_MULTI, .cmd = RTM_NEWNSID, }, .idx = 0, .s_idx = cb->args[0], }; int err = 0; if (cb->strict_check) { err = rtnl_valid_dump_net_req(cb->nlh, skb->sk, &net_cb, cb); if (err < 0) goto end; } rcu_read_lock(); idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); rcu_read_unlock(); cb->args[0] = net_cb.idx; end: if (net_cb.fillargs.add_ref) put_net(net_cb.tgt_net); return err < 0 ? err : skb->len; } static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp) { struct net_fill_args fillargs = { .portid = portid, .seq = nlh ? nlh->nlmsg_seq : 0, .cmd = cmd, .nsid = id, }; struct sk_buff *msg; int err = -ENOMEM; msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; err = rtnl_net_fill(msg, &fillargs); if (err < 0) goto err_out; rtnl_notify(msg, net, portid, RTNLGRP_NSID, nlh, gfp); return; err_out: nlmsg_free(msg); out: rtnl_set_sk_err(net, RTNLGRP_NSID, err); } static int __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS net_cachep = kmem_cache_create("net_namespace", sizeof(struct net), SMP_CACHE_BYTES, SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Create workqueue for cleanup */ netns_wq = create_singlethread_workqueue("netns"); if (!netns_wq) panic("Could not create netns workq"); #endif ng = net_alloc_generic(); if (!ng) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) panic("Could not setup the initial network namespace"); init_net_initialized = true; up_write(&pernet_ops_rwsem); if (register_pernet_subsys(&net_ns_ops)) panic("Could not register network namespace subsystems"); rtnl_register(PF_UNSPEC, RTM_NEWNSID, rtnl_net_newid, NULL, RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETNSID, rtnl_net_getid, rtnl_net_dumpid, RTNL_FLAG_DOIT_UNLOCKED); return 0; } pure_initcall(net_ns_init); #ifdef CONFIG_NET_NS static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { struct net *net; int error; LIST_HEAD(net_exit_list); list_add_tail(&ops->list, list); if (ops->init || (ops->id && ops->size)) { /* We held write locked pernet_ops_rwsem, and parallel * setup_net() and cleanup_net() are not possible. */ for_each_net(net) { error = ops_init(ops, net); if (error) goto out_undo; list_add_tail(&net->exit_list, &net_exit_list); } } return 0; out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops_exit_list(ops, &net_exit_list); ops_free_list(ops, &net_exit_list); return error; } static void __unregister_pernet_operations(struct pernet_operations *ops) { struct net *net; LIST_HEAD(net_exit_list); list_del(&ops->list); /* See comment in __register_pernet_operations() */ for_each_net(net) list_add_tail(&net->exit_list, &net_exit_list); ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops_exit_list(ops, &net_exit_list); ops_free_list(ops, &net_exit_list); } #else static int __register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { if (!init_net_initialized) { list_add_tail(&ops->list, list); return 0; } return ops_init(ops, &init_net); } static void __unregister_pernet_operations(struct pernet_operations *ops) { if (!init_net_initialized) { list_del(&ops->list); } else { LIST_HEAD(net_exit_list); list_add(&init_net.exit_list, &net_exit_list); ops_pre_exit_list(ops, &net_exit_list); synchronize_rcu(); ops_exit_list(ops, &net_exit_list); ops_free_list(ops, &net_exit_list); } } #endif /* CONFIG_NET_NS */ static DEFINE_IDA(net_generic_ids); static int register_pernet_operations(struct list_head *list, struct pernet_operations *ops) { int error; if (ops->id) { error = ida_alloc_min(&net_generic_ids, MIN_PERNET_OPS_ID, GFP_KERNEL); if (error < 0) return error; *ops->id = error; /* This does not require READ_ONCE as writers already hold * pernet_ops_rwsem. But WRITE_ONCE is needed to protect * net_alloc_generic. */ WRITE_ONCE(max_gen_ptrs, max(max_gen_ptrs, *ops->id + 1)); } error = __register_pernet_operations(list, ops); if (error) { rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } return error; } static void unregister_pernet_operations(struct pernet_operations *ops) { __unregister_pernet_operations(ops); rcu_barrier(); if (ops->id) ida_free(&net_generic_ids, *ops->id); } /** * register_pernet_subsys - register a network namespace subsystem * @ops: pernet operations structure for the subsystem * * Register a subsystem which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_subsys(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(first_device, ops); up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_subsys); /** * unregister_pernet_subsys - unregister a network namespace subsystem * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_subsys(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_subsys); /** * register_pernet_device - register a network namespace device * @ops: pernet operations structure for the subsystem * * Register a device which has init and exit functions * that are called when network namespaces are created and * destroyed respectively. * * When registered all network namespace init functions are * called for every existing network namespace. Allowing kernel * modules to have a race free view of the set of network namespaces. * * When a new network namespace is created all of the init * methods are called in the order in which they were registered. * * When a network namespace is destroyed all of the exit methods * are called in the reverse of the order with which they were * registered. */ int register_pernet_device(struct pernet_operations *ops) { int error; down_write(&pernet_ops_rwsem); error = register_pernet_operations(&pernet_list, ops); if (!error && (first_device == &pernet_list)) first_device = &ops->list; up_write(&pernet_ops_rwsem); return error; } EXPORT_SYMBOL_GPL(register_pernet_device); /** * unregister_pernet_device - unregister a network namespace netdevice * @ops: pernet operations structure to manipulate * * Remove the pernet operations structure from the list to be * used when network namespaces are created or destroyed. In * addition run the exit method for all existing network * namespaces. */ void unregister_pernet_device(struct pernet_operations *ops) { down_write(&pernet_ops_rwsem); if (&ops->list == first_device) first_device = first_device->next; unregister_pernet_operations(ops); up_write(&pernet_ops_rwsem); } EXPORT_SYMBOL_GPL(unregister_pernet_device); #ifdef CONFIG_NET_NS static struct ns_common *netns_get(struct task_struct *task) { struct net *net = NULL; struct nsproxy *nsproxy; task_lock(task); nsproxy = task->nsproxy; if (nsproxy) net = get_net(nsproxy->net_ns); task_unlock(task); return net ? &net->ns : NULL; } static inline struct net *to_net_ns(struct ns_common *ns) { return container_of(ns, struct net, ns); } static void netns_put(struct ns_common *ns) { put_net(to_net_ns(ns)); } static int netns_install(struct nsproxy *nsproxy, struct ns_common *ns) { struct net *net = to_net_ns(ns); if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || !ns_capable(current_user_ns(), CAP_SYS_ADMIN)) return -EPERM; put_net(nsproxy->net_ns); nsproxy->net_ns = get_net(net); return 0; } static struct user_namespace *netns_owner(struct ns_common *ns) { return to_net_ns(ns)->user_ns; } const struct proc_ns_operations netns_operations = { .name = "net", .type = CLONE_NEWNET, .get = netns_get, .put = netns_put, .install = netns_install, .owner = netns_owner, }; #endif |
| 229 229 231 229 447 450 447 245 242 246 244 243 27 230 231 230 231 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/fs-writeback.c * * Copyright (C) 2002, Linus Torvalds. * * Contains all the functions related to writing back and waiting * upon dirty inodes against superblocks, and writing back dirty * pages against inodes. ie: data writeback. Writeout of the * inode itself is not handled here. * * 10Apr2002 Andrew Morton * Split out of fs/inode.c * Additions for address_space-based writeback */ #include <linux/kernel.h> #include <linux/export.h> #include <linux/spinlock.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/kthread.h> #include <linux/writeback.h> #include <linux/blkdev.h> #include <linux/backing-dev.h> #include <linux/tracepoint.h> #include <linux/device.h> #include <linux/memcontrol.h> #include "internal.h" /* * 4MB minimal write chunk size */ #define MIN_WRITEBACK_PAGES (4096UL >> (PAGE_SHIFT - 10)) /* * Passed into wb_writeback(), essentially a subset of writeback_control */ struct wb_writeback_work { long nr_pages; struct super_block *sb; enum writeback_sync_modes sync_mode; unsigned int tagged_writepages:1; unsigned int for_kupdate:1; unsigned int range_cyclic:1; unsigned int for_background:1; unsigned int for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned int auto_free:1; /* free on completion */ enum wb_reason reason; /* why was writeback initiated? */ struct list_head list; /* pending work list */ struct wb_completion *done; /* set if the caller waits */ }; /* * If an inode is constantly having its pages dirtied, but then the * updates stop dirtytime_expire_interval seconds in the past, it's * possible for the worst case time between when an inode has its * timestamps updated and when they finally get written out to be two * dirtytime_expire_intervals. We set the default to 12 hours (in * seconds), which means most of the time inodes will have their * timestamps written to disk after 12 hours, but in the worst case a * few inodes might not their timestamps updated for 24 hours. */ unsigned int dirtytime_expire_interval = 12 * 60 * 60; static inline struct inode *wb_inode(struct list_head *head) { return list_entry(head, struct inode, i_io_list); } /* * Include the creation of the trace points after defining the * wb_writeback_work structure and inline functions so that the definition * remains local to this file. */ #define CREATE_TRACE_POINTS #include <trace/events/writeback.h> EXPORT_TRACEPOINT_SYMBOL_GPL(wbc_writepage); static bool wb_io_lists_populated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb)) { return false; } else { set_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(!wb->avg_write_bandwidth); atomic_long_add(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth); return true; } } static void wb_io_lists_depopulated(struct bdi_writeback *wb) { if (wb_has_dirty_io(wb) && list_empty(&wb->b_dirty) && list_empty(&wb->b_io) && list_empty(&wb->b_more_io)) { clear_bit(WB_has_dirty_io, &wb->state); WARN_ON_ONCE(atomic_long_sub_return(wb->avg_write_bandwidth, &wb->bdi->tot_write_bandwidth) < 0); } } /** * inode_io_list_move_locked - move an inode onto a bdi_writeback IO list * @inode: inode to be moved * @wb: target bdi_writeback * @head: one of @wb->b_{dirty|io|more_io|dirty_time} * * Move @inode->i_io_list to @list of @wb and set %WB_has_dirty_io. * Returns %true if @inode is the first occupant of the !dirty_time IO * lists; otherwise, %false. */ static bool inode_io_list_move_locked(struct inode *inode, struct bdi_writeback *wb, struct list_head *head) { assert_spin_locked(&wb->list_lock); list_move(&inode->i_io_list, head); /* dirty_time doesn't count as dirty_io until expiration */ if (head != &wb->b_dirty_time) return wb_io_lists_populated(wb); wb_io_lists_depopulated(wb); return false; } /** * inode_io_list_del_locked - remove an inode from its bdi_writeback IO list * @inode: inode to be removed * @wb: bdi_writeback @inode is being removed from * * Remove @inode which may be on one of @wb->b_{dirty|io|more_io} lists and * clear %WB_has_dirty_io if all are empty afterwards. */ static void inode_io_list_del_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&wb->list_lock); assert_spin_locked(&inode->i_lock); inode->i_state &= ~I_SYNC_QUEUED; list_del_init(&inode->i_io_list); wb_io_lists_depopulated(wb); } static void wb_wakeup(struct bdi_writeback *wb) { spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) mod_delayed_work(bdi_wq, &wb->dwork, 0); spin_unlock_bh(&wb->work_lock); } static void finish_writeback_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { struct wb_completion *done = work->done; if (work->auto_free) kfree(work); if (done) { wait_queue_head_t *waitq = done->waitq; /* @done can't be accessed after the following dec */ if (atomic_dec_and_test(&done->cnt)) wake_up_all(waitq); } } static void wb_queue_work(struct bdi_writeback *wb, struct wb_writeback_work *work) { trace_writeback_queue(wb, work); if (work->done) atomic_inc(&work->done->cnt); spin_lock_bh(&wb->work_lock); if (test_bit(WB_registered, &wb->state)) { list_add_tail(&work->list, &wb->work_list); mod_delayed_work(bdi_wq, &wb->dwork, 0); } else finish_writeback_work(wb, work); spin_unlock_bh(&wb->work_lock); } /** * wb_wait_for_completion - wait for completion of bdi_writeback_works * @done: target wb_completion * * Wait for one or more work items issued to @bdi with their ->done field * set to @done, which should have been initialized with * DEFINE_WB_COMPLETION(). This function returns after all such work items * are completed. Work items which are waited upon aren't freed * automatically on completion. */ void wb_wait_for_completion(struct wb_completion *done) { atomic_dec(&done->cnt); /* put down the initial count */ wait_event(*done->waitq, !atomic_read(&done->cnt)); } #ifdef CONFIG_CGROUP_WRITEBACK /* * Parameters for foreign inode detection, see wbc_detach_inode() to see * how they're used. * * These paramters are inherently heuristical as the detection target * itself is fuzzy. All we want to do is detaching an inode from the * current owner if it's being written to by some other cgroups too much. * * The current cgroup writeback is built on the assumption that multiple * cgroups writing to the same inode concurrently is very rare and a mode * of operation which isn't well supported. As such, the goal is not * taking too long when a different cgroup takes over an inode while * avoiding too aggressive flip-flops from occasional foreign writes. * * We record, very roughly, 2s worth of IO time history and if more than * half of that is foreign, trigger the switch. The recording is quantized * to 16 slots. To avoid tiny writes from swinging the decision too much, * writes smaller than 1/8 of avg size are ignored. */ #define WB_FRN_TIME_SHIFT 13 /* 1s = 2^13, upto 8 secs w/ 16bit */ #define WB_FRN_TIME_AVG_SHIFT 3 /* avg = avg * 7/8 + new * 1/8 */ #define WB_FRN_TIME_CUT_DIV 8 /* ignore rounds < avg / 8 */ #define WB_FRN_TIME_PERIOD (2 * (1 << WB_FRN_TIME_SHIFT)) /* 2s */ #define WB_FRN_HIST_SLOTS 16 /* inode->i_wb_frn_history is 16bit */ #define WB_FRN_HIST_UNIT (WB_FRN_TIME_PERIOD / WB_FRN_HIST_SLOTS) /* each slot's duration is 2s / 16 */ #define WB_FRN_HIST_THR_SLOTS (WB_FRN_HIST_SLOTS / 2) /* if foreign slots >= 8, switch */ #define WB_FRN_HIST_MAX_SLOTS (WB_FRN_HIST_THR_SLOTS / 2 + 1) /* one round can affect upto 5 slots */ #define WB_FRN_MAX_IN_FLIGHT 1024 /* don't queue too many concurrently */ static atomic_t isw_nr_in_flight = ATOMIC_INIT(0); static struct workqueue_struct *isw_wq; void __inode_attach_wb(struct inode *inode, struct page *page) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct bdi_writeback *wb = NULL; if (inode_cgwb_enabled(inode)) { struct cgroup_subsys_state *memcg_css; if (page) { memcg_css = mem_cgroup_css_from_page(page); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); } else { /* must pin memcg_css, see wb_get_create() */ memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); } } if (!wb) wb = &bdi->wb; /* * There may be multiple instances of this function racing to * update the same inode. Use cmpxchg() to tell the winner. */ if (unlikely(cmpxchg(&inode->i_wb, NULL, wb))) wb_put(wb); } EXPORT_SYMBOL_GPL(__inode_attach_wb); /** * locked_inode_to_wb_and_lock_list - determine a locked inode's wb and lock it * @inode: inode of interest with i_lock held * * Returns @inode's wb with its list_lock held. @inode->i_lock must be * held on entry and is released on return. The returned wb is guaranteed * to stay @inode's associated wb until its list_lock is released. */ static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { while (true) { struct bdi_writeback *wb = inode_to_wb(inode); /* * inode_to_wb() association is protected by both * @inode->i_lock and @wb->list_lock but list_lock nests * outside i_lock. Drop i_lock and verify that the * association hasn't changed after acquiring list_lock. */ wb_get(wb); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); /* i_wb may have changed inbetween, can't use inode_to_wb() */ if (likely(wb == inode->i_wb)) { wb_put(wb); /* @inode already has ref */ return wb; } spin_unlock(&wb->list_lock); wb_put(wb); cpu_relax(); spin_lock(&inode->i_lock); } } /** * inode_to_wb_and_lock_list - determine an inode's wb and lock it * @inode: inode of interest * * Same as locked_inode_to_wb_and_lock_list() but @inode->i_lock isn't held * on entry. */ static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { spin_lock(&inode->i_lock); return locked_inode_to_wb_and_lock_list(inode); } struct inode_switch_wbs_context { struct inode *inode; struct bdi_writeback *new_wb; struct rcu_head rcu_head; struct work_struct work; }; static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { down_write(&bdi->wb_switch_rwsem); } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { up_write(&bdi->wb_switch_rwsem); } static void inode_switch_wbs_work_fn(struct work_struct *work) { struct inode_switch_wbs_context *isw = container_of(work, struct inode_switch_wbs_context, work); struct inode *inode = isw->inode; struct backing_dev_info *bdi = inode_to_bdi(inode); struct address_space *mapping = inode->i_mapping; struct bdi_writeback *old_wb = inode->i_wb; struct bdi_writeback *new_wb = isw->new_wb; XA_STATE(xas, &mapping->i_pages, 0); struct page *page; bool switched = false; /* * If @inode switches cgwb membership while sync_inodes_sb() is * being issued, sync_inodes_sb() might miss it. Synchronize. */ down_read(&bdi->wb_switch_rwsem); /* * By the time control reaches here, RCU grace period has passed * since I_WB_SWITCH assertion and all wb stat update transactions * between unlocked_inode_to_wb_begin/end() are guaranteed to be * synchronizing against the i_pages lock. * * Grabbing old_wb->list_lock, inode->i_lock and the i_pages lock * gives us exclusion against all wb related operations on @inode * including IO list manipulations and stat updates. */ if (old_wb < new_wb) { spin_lock(&old_wb->list_lock); spin_lock_nested(&new_wb->list_lock, SINGLE_DEPTH_NESTING); } else { spin_lock(&new_wb->list_lock); spin_lock_nested(&old_wb->list_lock, SINGLE_DEPTH_NESTING); } spin_lock(&inode->i_lock); xa_lock_irq(&mapping->i_pages); /* * Once I_FREEING is visible under i_lock, the eviction path owns * the inode and we shouldn't modify ->i_io_list. */ if (unlikely(inode->i_state & I_FREEING)) goto skip_switch; trace_inode_switch_wbs(inode, old_wb, new_wb); /* * Count and transfer stats. Note that PAGECACHE_TAG_DIRTY points * to possibly dirty pages while PAGECACHE_TAG_WRITEBACK points to * pages actually under writeback. */ xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_DIRTY) { if (PageDirty(page)) { dec_wb_stat(old_wb, WB_RECLAIMABLE); inc_wb_stat(new_wb, WB_RECLAIMABLE); } } xas_set(&xas, 0); xas_for_each_marked(&xas, page, ULONG_MAX, PAGECACHE_TAG_WRITEBACK) { WARN_ON_ONCE(!PageWriteback(page)); dec_wb_stat(old_wb, WB_WRITEBACK); inc_wb_stat(new_wb, WB_WRITEBACK); } wb_get(new_wb); /* * Transfer to @new_wb's IO list if necessary. The specific list * @inode was on is ignored and the inode is put on ->b_dirty which * is always correct including from ->b_dirty_time. The transfer * preserves @inode->dirtied_when ordering. */ if (!list_empty(&inode->i_io_list)) { struct inode *pos; inode_io_list_del_locked(inode, old_wb); inode->i_wb = new_wb; list_for_each_entry(pos, &new_wb->b_dirty, i_io_list) if (time_after_eq(inode->dirtied_when, pos->dirtied_when)) break; inode_io_list_move_locked(inode, new_wb, pos->i_io_list.prev); } else { inode->i_wb = new_wb; } /* ->i_wb_frn updates may race wbc_detach_inode() but doesn't matter */ inode->i_wb_frn_winner = 0; inode->i_wb_frn_avg_time = 0; inode->i_wb_frn_history = 0; switched = true; skip_switch: /* * Paired with load_acquire in unlocked_inode_to_wb_begin() and * ensures that the new wb is visible if they see !I_WB_SWITCH. */ smp_store_release(&inode->i_state, inode->i_state & ~I_WB_SWITCH); xa_unlock_irq(&mapping->i_pages); spin_unlock(&inode->i_lock); spin_unlock(&new_wb->list_lock); spin_unlock(&old_wb->list_lock); up_read(&bdi->wb_switch_rwsem); if (switched) { wb_wakeup(new_wb); wb_put(old_wb); } wb_put(new_wb); iput(inode); kfree(isw); atomic_dec(&isw_nr_in_flight); } static void inode_switch_wbs_rcu_fn(struct rcu_head *rcu_head) { struct inode_switch_wbs_context *isw = container_of(rcu_head, struct inode_switch_wbs_context, rcu_head); /* needs to grab bh-unsafe locks, bounce to work item */ INIT_WORK(&isw->work, inode_switch_wbs_work_fn); queue_work(isw_wq, &isw->work); } /** * inode_switch_wbs - change the wb association of an inode * @inode: target inode * @new_wb_id: ID of the new wb * * Switch @inode's wb association to the wb identified by @new_wb_id. The * switching is performed asynchronously and may fail silently. */ static void inode_switch_wbs(struct inode *inode, int new_wb_id) { struct backing_dev_info *bdi = inode_to_bdi(inode); struct cgroup_subsys_state *memcg_css; struct inode_switch_wbs_context *isw; /* noop if seems to be already in progress */ if (inode->i_state & I_WB_SWITCH) return; /* avoid queueing a new switch if too many are already in flight */ if (atomic_read(&isw_nr_in_flight) > WB_FRN_MAX_IN_FLIGHT) return; isw = kzalloc(sizeof(*isw), GFP_ATOMIC); if (!isw) return; atomic_inc(&isw_nr_in_flight); /* find and pin the new wb */ rcu_read_lock(); memcg_css = css_from_id(new_wb_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) goto out_free; isw->new_wb = wb_get_create(bdi, memcg_css, GFP_ATOMIC); css_put(memcg_css); if (!isw->new_wb) goto out_free; /* while holding I_WB_SWITCH, no one else can update the association */ spin_lock(&inode->i_lock); if (!(inode->i_sb->s_flags & SB_ACTIVE) || inode->i_state & (I_WB_SWITCH | I_FREEING) || inode_to_wb(inode) == isw->new_wb) { spin_unlock(&inode->i_lock); goto out_free; } inode->i_state |= I_WB_SWITCH; __iget(inode); spin_unlock(&inode->i_lock); isw->inode = inode; /* * In addition to synchronizing among switchers, I_WB_SWITCH tells * the RCU protected stat update paths to grab the i_page * lock so that stat transfer can synchronize against them. * Let's continue after I_WB_SWITCH is guaranteed to be visible. */ call_rcu(&isw->rcu_head, inode_switch_wbs_rcu_fn); return; out_free: atomic_dec(&isw_nr_in_flight); if (isw->new_wb) wb_put(isw->new_wb); kfree(isw); } /** * wbc_attach_and_unlock_inode - associate wbc with target inode and unlock it * @wbc: writeback_control of interest * @inode: target inode * * @inode is locked and about to be written back under the control of @wbc. * Record @inode's writeback context into @wbc and unlock the i_lock. On * writeback completion, wbc_detach_inode() should be called. This is used * to track the cgroup writeback context. */ void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) { if (!inode_cgwb_enabled(inode)) { spin_unlock(&inode->i_lock); return; } wbc->wb = inode_to_wb(inode); wbc->inode = inode; wbc->wb_id = wbc->wb->memcg_css->id; wbc->wb_lcand_id = inode->i_wb_frn_winner; wbc->wb_tcand_id = 0; wbc->wb_bytes = 0; wbc->wb_lcand_bytes = 0; wbc->wb_tcand_bytes = 0; wb_get(wbc->wb); spin_unlock(&inode->i_lock); /* * A dying wb indicates that either the blkcg associated with the * memcg changed or the associated memcg is dying. In the first * case, a replacement wb should already be available and we should * refresh the wb immediately. In the second case, trying to * refresh will keep failing. */ if (unlikely(wb_dying(wbc->wb) && !css_is_dying(wbc->wb->memcg_css))) inode_switch_wbs(inode, wbc->wb_id); } EXPORT_SYMBOL_GPL(wbc_attach_and_unlock_inode); /** * wbc_detach_inode - disassociate wbc from inode and perform foreign detection * @wbc: writeback_control of the just finished writeback * * To be called after a writeback attempt of an inode finishes and undoes * wbc_attach_and_unlock_inode(). Can be called under any context. * * As concurrent write sharing of an inode is expected to be very rare and * memcg only tracks page ownership on first-use basis severely confining * the usefulness of such sharing, cgroup writeback tracks ownership * per-inode. While the support for concurrent write sharing of an inode * is deemed unnecessary, an inode being written to by different cgroups at * different points in time is a lot more common, and, more importantly, * charging only by first-use can too readily lead to grossly incorrect * behaviors (single foreign page can lead to gigabytes of writeback to be * incorrectly attributed). * * To resolve this issue, cgroup writeback detects the majority dirtier of * an inode and transfers the ownership to it. To avoid unnnecessary * oscillation, the detection mechanism keeps track of history and gives * out the switch verdict only if the foreign usage pattern is stable over * a certain amount of time and/or writeback attempts. * * On each writeback attempt, @wbc tries to detect the majority writer * using Boyer-Moore majority vote algorithm. In addition to the byte * count from the majority voting, it also counts the bytes written for the * current wb and the last round's winner wb (max of last round's current * wb, the winner from two rounds ago, and the last round's majority * candidate). Keeping track of the historical winner helps the algorithm * to semi-reliably detect the most active writer even when it's not the * absolute majority. * * Once the winner of the round is determined, whether the winner is * foreign or not and how much IO time the round consumed is recorded in * inode->i_wb_frn_history. If the amount of recorded foreign IO time is * over a certain threshold, the switch verdict is given. */ void wbc_detach_inode(struct writeback_control *wbc) { struct bdi_writeback *wb = wbc->wb; struct inode *inode = wbc->inode; unsigned long avg_time, max_bytes, max_time; u16 history; int max_id; if (!wb) return; history = inode->i_wb_frn_history; avg_time = inode->i_wb_frn_avg_time; /* pick the winner of this round */ if (wbc->wb_bytes >= wbc->wb_lcand_bytes && wbc->wb_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_id; max_bytes = wbc->wb_bytes; } else if (wbc->wb_lcand_bytes >= wbc->wb_tcand_bytes) { max_id = wbc->wb_lcand_id; max_bytes = wbc->wb_lcand_bytes; } else { max_id = wbc->wb_tcand_id; max_bytes = wbc->wb_tcand_bytes; } /* * Calculate the amount of IO time the winner consumed and fold it * into the running average kept per inode. If the consumed IO * time is lower than avag / WB_FRN_TIME_CUT_DIV, ignore it for * deciding whether to switch or not. This is to prevent one-off * small dirtiers from skewing the verdict. */ max_time = DIV_ROUND_UP((max_bytes >> PAGE_SHIFT) << WB_FRN_TIME_SHIFT, wb->avg_write_bandwidth); if (avg_time) avg_time += (max_time >> WB_FRN_TIME_AVG_SHIFT) - (avg_time >> WB_FRN_TIME_AVG_SHIFT); else avg_time = max_time; /* immediate catch up on first run */ if (max_time >= avg_time / WB_FRN_TIME_CUT_DIV) { int slots; /* * The switch verdict is reached if foreign wb's consume * more than a certain proportion of IO time in a * WB_FRN_TIME_PERIOD. This is loosely tracked by 16 slot * history mask where each bit represents one sixteenth of * the period. Determine the number of slots to shift into * history from @max_time. */ slots = min(DIV_ROUND_UP(max_time, WB_FRN_HIST_UNIT), (unsigned long)WB_FRN_HIST_MAX_SLOTS); history <<= slots; if (wbc->wb_id != max_id) history |= (1U << slots) - 1; if (history) trace_inode_foreign_history(inode, wbc, history); /* * Switch if the current wb isn't the consistent winner. * If there are multiple closely competing dirtiers, the * inode may switch across them repeatedly over time, which * is okay. The main goal is avoiding keeping an inode on * the wrong wb for an extended period of time. */ if (hweight16(history) > WB_FRN_HIST_THR_SLOTS) inode_switch_wbs(inode, max_id); } /* * Multiple instances of this function may race to update the * following fields but we don't mind occassional inaccuracies. */ inode->i_wb_frn_winner = max_id; inode->i_wb_frn_avg_time = min(avg_time, (unsigned long)U16_MAX); inode->i_wb_frn_history = history; wb_put(wbc->wb); wbc->wb = NULL; } EXPORT_SYMBOL_GPL(wbc_detach_inode); /** * wbc_account_cgroup_owner - account writeback to update inode cgroup ownership * @wbc: writeback_control of the writeback in progress * @page: page being written out * @bytes: number of bytes being written out * * @bytes from @page are about to written out during the writeback * controlled by @wbc. Keep the book for foreign inode detection. See * wbc_detach_inode(). */ void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { struct cgroup_subsys_state *css; int id; /* * pageout() path doesn't attach @wbc to the inode being written * out. This is intentional as we don't want the function to block * behind a slow cgroup. Ultimately, we want pageout() to kick off * regular writeback instead of writing things out itself. */ if (!wbc->wb || wbc->no_cgroup_owner) return; css = mem_cgroup_css_from_page(page); /* dead cgroups shouldn't contribute to inode ownership arbitration */ if (!(css->flags & CSS_ONLINE)) return; id = css->id; if (id == wbc->wb_id) { wbc->wb_bytes += bytes; return; } if (id == wbc->wb_lcand_id) wbc->wb_lcand_bytes += bytes; /* Boyer-Moore majority vote algorithm */ if (!wbc->wb_tcand_bytes) wbc->wb_tcand_id = id; if (id == wbc->wb_tcand_id) wbc->wb_tcand_bytes += bytes; else wbc->wb_tcand_bytes -= min(bytes, wbc->wb_tcand_bytes); } EXPORT_SYMBOL_GPL(wbc_account_cgroup_owner); /** * inode_congested - test whether an inode is congested * @inode: inode to test for congestion (may be NULL) * @cong_bits: mask of WB_[a]sync_congested bits to test * * Tests whether @inode is congested. @cong_bits is the mask of congestion * bits to test and the return value is the mask of set bits. * * If cgroup writeback is enabled for @inode, the congestion state is * determined by whether the cgwb (cgroup bdi_writeback) for the blkcg * associated with @inode is congested; otherwise, the root wb's congestion * state is used. * * @inode is allowed to be NULL as this function is often called on * mapping->host which is NULL for the swapper space. */ int inode_congested(struct inode *inode, int cong_bits) { /* * Once set, ->i_wb never becomes NULL while the inode is alive. * Start transaction iff ->i_wb is visible. */ if (inode && inode_to_wb_is_valid(inode)) { struct bdi_writeback *wb; struct wb_lock_cookie lock_cookie = {}; bool congested; wb = unlocked_inode_to_wb_begin(inode, &lock_cookie); congested = wb_congested(wb, cong_bits); unlocked_inode_to_wb_end(inode, &lock_cookie); return congested; } return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } EXPORT_SYMBOL_GPL(inode_congested); /** * wb_split_bdi_pages - split nr_pages to write according to bandwidth * @wb: target bdi_writeback to split @nr_pages to * @nr_pages: number of pages to write for the whole bdi * * Split @wb's portion of @nr_pages according to @wb's write bandwidth in * relation to the total write bandwidth of all wb's w/ dirty inodes on * @wb->bdi. */ static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { unsigned long this_bw = wb->avg_write_bandwidth; unsigned long tot_bw = atomic_long_read(&wb->bdi->tot_write_bandwidth); if (nr_pages == LONG_MAX) return LONG_MAX; /* * This may be called on clean wb's and proportional distribution * may not make sense, just use the original @nr_pages in those * cases. In general, we wanna err on the side of writing more. */ if (!tot_bw || this_bw >= tot_bw) return nr_pages; else return DIV_ROUND_UP_ULL((u64)nr_pages * this_bw, tot_bw); } /** * bdi_split_work_to_wbs - split a wb_writeback_work to all wb's of a bdi * @bdi: target backing_dev_info * @base_work: wb_writeback_work to issue * @skip_if_busy: skip wb's which already have writeback in progress * * Split and issue @base_work to all wb's (bdi_writeback's) of @bdi which * have dirty inodes. If @base_work->nr_page isn't %LONG_MAX, it's * distributed to the busy wbs according to each wb's proportion in the * total active write bandwidth of @bdi. */ static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { struct bdi_writeback *last_wb = NULL; struct bdi_writeback *wb = list_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); might_sleep(); restart: rcu_read_lock(); list_for_each_entry_continue_rcu(wb, &bdi->wb_list, bdi_node) { DEFINE_WB_COMPLETION(fallback_work_done, bdi); struct wb_writeback_work fallback_work; struct wb_writeback_work *work; long nr_pages; if (last_wb) { wb_put(last_wb); last_wb = NULL; } /* SYNC_ALL writes out I_DIRTY_TIME too */ if (!wb_has_dirty_io(wb) && (base_work->sync_mode == WB_SYNC_NONE || list_empty(&wb->b_dirty_time))) continue; if (skip_if_busy && writeback_in_progress(wb)) continue; nr_pages = wb_split_bdi_pages(wb, base_work->nr_pages); work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 1; wb_queue_work(wb, work); continue; } /* alloc failed, execute synchronously using on-stack fallback */ work = &fallback_work; *work = *base_work; work->nr_pages = nr_pages; work->auto_free = 0; work->done = &fallback_work_done; wb_queue_work(wb, work); /* * Pin @wb so that it stays on @bdi->wb_list. This allows * continuing iteration from @wb after dropping and * regrabbing rcu read lock. */ wb_get(wb); last_wb = wb; rcu_read_unlock(); wb_wait_for_completion(&fallback_work_done); goto restart; } rcu_read_unlock(); if (last_wb) wb_put(last_wb); } /** * cgroup_writeback_by_id - initiate cgroup writeback from bdi and memcg IDs * @bdi_id: target bdi id * @memcg_id: target memcg css id * @nr: number of pages to write, 0 for best-effort dirty flushing * @reason: reason why some writeback work initiated * @done: target wb_completion * * Initiate flush of the bdi_writeback identified by @bdi_id and @memcg_id * with the specified parameters. */ int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, unsigned long nr, enum wb_reason reason, struct wb_completion *done) { struct backing_dev_info *bdi; struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; struct wb_writeback_work *work; int ret; /* lookup bdi and memcg */ bdi = bdi_get_by_id(bdi_id); if (!bdi) return -ENOENT; rcu_read_lock(); memcg_css = css_from_id(memcg_id, &memory_cgrp_subsys); if (memcg_css && !css_tryget(memcg_css)) memcg_css = NULL; rcu_read_unlock(); if (!memcg_css) { ret = -ENOENT; goto out_bdi_put; } /* * And find the associated wb. If the wb isn't there already * there's nothing to flush, don't create one. */ wb = wb_get_lookup(bdi, memcg_css); if (!wb) { ret = -ENOENT; goto out_css_put; } /* * If @nr is zero, the caller is attempting to write out most of * the currently dirty pages. Let's take the current dirty page * count and inflate it by 25% which should be large enough to * flush out most dirty pages while avoiding getting livelocked by * concurrent dirtiers. */ if (!nr) { unsigned long filepages, headroom, dirty, writeback; mem_cgroup_wb_stats(wb, &filepages, &headroom, &dirty, &writeback); nr = dirty * 10 / 8; } /* issue the writeback work */ work = kzalloc(sizeof(*work), GFP_NOWAIT | __GFP_NOWARN); if (work) { work->nr_pages = nr; work->sync_mode = WB_SYNC_NONE; work->range_cyclic = 1; work->reason = reason; work->done = done; work->auto_free = 1; wb_queue_work(wb, work); ret = 0; } else { ret = -ENOMEM; } wb_put(wb); out_css_put: css_put(memcg_css); out_bdi_put: bdi_put(bdi); return ret; } /** * cgroup_writeback_umount - flush inode wb switches for umount * * This function is called when a super_block is about to be destroyed and * flushes in-flight inode wb switches. An inode wb switch goes through * RCU and then workqueue, so the two need to be flushed in order to ensure * that all previously scheduled switches are finished. As wb switches are * rare occurrences and synchronize_rcu() can take a while, perform * flushing iff wb switches are in flight. */ void cgroup_writeback_umount(void) { if (atomic_read(&isw_nr_in_flight)) { /* * Use rcu_barrier() to wait for all pending callbacks to * ensure that all in-flight wb switches are in the workqueue. */ rcu_barrier(); flush_workqueue(isw_wq); } } static int __init cgroup_writeback_init(void) { isw_wq = alloc_workqueue("inode_switch_wbs", 0, 0); if (!isw_wq) return -ENOMEM; return 0; } fs_initcall(cgroup_writeback_init); #else /* CONFIG_CGROUP_WRITEBACK */ static void bdi_down_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static void bdi_up_write_wb_switch_rwsem(struct backing_dev_info *bdi) { } static struct bdi_writeback * locked_inode_to_wb_and_lock_list(struct inode *inode) __releases(&inode->i_lock) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_unlock(&inode->i_lock); spin_lock(&wb->list_lock); return wb; } static struct bdi_writeback *inode_to_wb_and_lock_list(struct inode *inode) __acquires(&wb->list_lock) { struct bdi_writeback *wb = inode_to_wb(inode); spin_lock(&wb->list_lock); return wb; } static long wb_split_bdi_pages(struct bdi_writeback *wb, long nr_pages) { return nr_pages; } static void bdi_split_work_to_wbs(struct backing_dev_info *bdi, struct wb_writeback_work *base_work, bool skip_if_busy) { might_sleep(); if (!skip_if_busy || !writeback_in_progress(&bdi->wb)) { base_work->auto_free = 0; wb_queue_work(&bdi->wb, base_work); } } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * Add in the number of potentially dirty inodes, because each inode * write can dirty pagecache in the underlying blockdev. */ static unsigned long get_nr_dirty_pages(void) { return global_node_page_state(NR_FILE_DIRTY) + global_node_page_state(NR_UNSTABLE_NFS) + get_nr_dirty_inodes(); } static void wb_start_writeback(struct bdi_writeback *wb, enum wb_reason reason) { if (!wb_has_dirty_io(wb)) return; /* * All callers of this function want to start writeback of all * dirty pages. Places like vmscan can call this at a very * high frequency, causing pointless allocations of tons of * work items and keeping the flusher threads busy retrieving * that work. Ensure that we only allow one of them pending and * inflight at the time. */ if (test_bit(WB_start_all, &wb->state) || test_and_set_bit(WB_start_all, &wb->state)) return; wb->start_all_reason = reason; wb_wakeup(wb); } /** * wb_start_background_writeback - start background writeback * @wb: bdi_writback to write from * * Description: * This makes sure WB_SYNC_NONE background writeback happens. When * this function returns, it is only guaranteed that for given wb * some IO is happening if we are over background dirty threshold. * Caller need not hold sb s_umount semaphore. */ void wb_start_background_writeback(struct bdi_writeback *wb) { /* * We just wake up the flusher thread. It will perform background * writeback as soon as there is no other work to do. */ trace_writeback_wake_background(wb); wb_wakeup(wb); } /* * Remove the inode from the writeback list it is on. */ void inode_io_list_del(struct inode *inode) { struct bdi_writeback *wb; wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); inode_io_list_del_locked(inode, wb); spin_unlock(&inode->i_lock); spin_unlock(&wb->list_lock); } /* * mark an inode as under writeback on the sb */ void sb_mark_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (list_empty(&inode->i_wb_list)) { list_add_tail(&inode->i_wb_list, &sb->s_inodes_wb); trace_sb_mark_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * clear an inode as under writeback on the sb */ void sb_clear_inode_writeback(struct inode *inode) { struct super_block *sb = inode->i_sb; unsigned long flags; if (!list_empty(&inode->i_wb_list)) { spin_lock_irqsave(&sb->s_inode_wblist_lock, flags); if (!list_empty(&inode->i_wb_list)) { list_del_init(&inode->i_wb_list); trace_sb_clear_inode_writeback(inode); } spin_unlock_irqrestore(&sb->s_inode_wblist_lock, flags); } } /* * Redirty an inode: set its when-it-was dirtied timestamp and move it to the * furthest end of its superblock's dirty-inode list. * * Before stamping the inode's ->dirtied_when, we check to see whether it is * already the most-recently-dirtied inode on the b_dirty list. If that is * the case then the inode must have been redirtied while it was being written * out and we don't reset its dirtied_when. */ static void redirty_tail_locked(struct inode *inode, struct bdi_writeback *wb) { assert_spin_locked(&inode->i_lock); if (!list_empty(&wb->b_dirty)) { struct inode *tail; tail = wb_inode(wb->b_dirty.next); if (time_before(inode->dirtied_when, tail->dirtied_when)) inode->dirtied_when = jiffies; } inode_io_list_move_locked(inode, wb, &wb->b_dirty); inode->i_state &= ~I_SYNC_QUEUED; } static void redirty_tail(struct inode *inode, struct bdi_writeback *wb) { spin_lock(&inode->i_lock); redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); } /* * requeue inode for re-scanning after bdi->b_io list is exhausted. */ static void requeue_io(struct inode *inode, struct bdi_writeback *wb) { inode_io_list_move_locked(inode, wb, &wb->b_more_io); } static void inode_sync_complete(struct inode *inode) { inode->i_state &= ~I_SYNC; /* If inode is clean an unused, put it into LRU now... */ inode_add_lru(inode); /* Waiters must see I_SYNC cleared before being woken up */ smp_mb(); wake_up_bit(&inode->i_state, __I_SYNC); } static bool inode_dirtied_after(struct inode *inode, unsigned long t) { bool ret = time_after(inode->dirtied_when, t); #ifndef CONFIG_64BIT /* * For inodes being constantly redirtied, dirtied_when can get stuck. * It _appears_ to be in the future, but is actually in distant past. * This test is necessary to prevent such wrapped-around relative times * from permanently stopping the whole bdi writeback. */ ret = ret && time_before_eq(inode->dirtied_when, jiffies); #endif return ret; } #define EXPIRE_DIRTY_ATIME 0x0001 /* * Move expired (dirtied before dirtied_before) dirty inodes from * @delaying_queue to @dispatch_queue. */ static int move_expired_inodes(struct list_head *delaying_queue, struct list_head *dispatch_queue, unsigned long dirtied_before) { LIST_HEAD(tmp); struct list_head *pos, *node; struct super_block *sb = NULL; struct inode *inode; int do_sb_sort = 0; int moved = 0; while (!list_empty(delaying_queue)) { inode = wb_inode(delaying_queue->prev); if (inode_dirtied_after(inode, dirtied_before)) break; list_move(&inode->i_io_list, &tmp); moved++; spin_lock(&inode->i_lock); inode->i_state |= I_SYNC_QUEUED; spin_unlock(&inode->i_lock); if (sb_is_blkdev_sb(inode->i_sb)) continue; if (sb && sb != inode->i_sb) do_sb_sort = 1; sb = inode->i_sb; } /* just one sb in list, splice to dispatch_queue and we're done */ if (!do_sb_sort) { list_splice(&tmp, dispatch_queue); goto out; } /* Move inodes from one superblock together */ while (!list_empty(&tmp)) { sb = wb_inode(tmp.prev)->i_sb; list_for_each_prev_safe(pos, node, &tmp) { inode = wb_inode(pos); if (inode->i_sb == sb) list_move(&inode->i_io_list, dispatch_queue); } } out: return moved; } /* * Queue all expired dirty inodes for io, eldest first. * Before * newly dirtied b_dirty b_io b_more_io * =============> gf edc BA * After * newly dirtied b_dirty b_io b_more_io * =============> g fBAedc * | * +--> dequeue for IO */ static void queue_io(struct bdi_writeback *wb, struct wb_writeback_work *work, unsigned long dirtied_before) { int moved; unsigned long time_expire_jif = dirtied_before; assert_spin_locked(&wb->list_lock); list_splice_init(&wb->b_more_io, &wb->b_io); moved = move_expired_inodes(&wb->b_dirty, &wb->b_io, dirtied_before); if (!work->for_sync) time_expire_jif = jiffies - dirtytime_expire_interval * HZ; moved += move_expired_inodes(&wb->b_dirty_time, &wb->b_io, time_expire_jif); if (moved) wb_io_lists_populated(wb); trace_writeback_queue_io(wb, work, dirtied_before, moved); } static int write_inode(struct inode *inode, struct writeback_control *wbc) { int ret; if (inode->i_sb->s_op->write_inode && !is_bad_inode(inode)) { trace_writeback_write_inode_start(inode, wbc); ret = inode->i_sb->s_op->write_inode(inode, wbc); trace_writeback_write_inode(inode, wbc); return ret; } return 0; } /* * Wait for writeback on an inode to complete. Called with i_lock held. * Caller must make sure inode cannot go away when we drop i_lock. */ static void __inode_wait_for_writeback(struct inode *inode) __releases(inode->i_lock) __acquires(inode->i_lock) { DEFINE_WAIT_BIT(wq, &inode->i_state, __I_SYNC); wait_queue_head_t *wqh; wqh = bit_waitqueue(&inode->i_state, __I_SYNC); while (inode->i_state & I_SYNC) { spin_unlock(&inode->i_lock); __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE); spin_lock(&inode->i_lock); } } /* * Wait for writeback on an inode to complete. Caller must have inode pinned. */ void inode_wait_for_writeback(struct inode *inode) { spin_lock(&inode->i_lock); __inode_wait_for_writeback(inode); spin_unlock(&inode->i_lock); } /* * Sleep until I_SYNC is cleared. This function must be called with i_lock * held and drops it. It is aimed for callers not holding any inode reference * so once i_lock is dropped, inode can go away. */ static void inode_sleep_on_writeback(struct inode *inode) __releases(inode->i_lock) { DEFINE_WAIT(wait); wait_queue_head_t *wqh = bit_waitqueue(&inode->i_state, __I_SYNC); int sleep; prepare_to_wait(wqh, &wait, TASK_UNINTERRUPTIBLE); sleep = inode->i_state & I_SYNC; spin_unlock(&inode->i_lock); if (sleep) schedule(); finish_wait(wqh, &wait); } /* * Find proper writeback list for the inode depending on its current state and * possibly also change of its state while we were doing writeback. Here we * handle things such as livelock prevention or fairness of writeback among * inodes. This function can be called only by flusher thread - noone else * processes all inodes in writeback lists and requeueing inodes behind flusher * thread's back can have unexpected consequences. */ static void requeue_inode(struct inode *inode, struct bdi_writeback *wb, struct writeback_control *wbc) { if (inode->i_state & I_FREEING) return; /* * Sync livelock prevention. Each inode is tagged and synced in one * shot. If still dirty, it will be redirty_tail()'ed below. Update * the dirty time to prevent enqueue and sync it again. */ if ((inode->i_state & I_DIRTY) && (wbc->sync_mode == WB_SYNC_ALL || wbc->tagged_writepages)) inode->dirtied_when = jiffies; if (wbc->pages_skipped) { /* * writeback is not making progress due to locked * buffers. Skip this inode for now. */ redirty_tail_locked(inode, wb); return; } if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_DIRTY)) { /* * We didn't write back all the pages. nfs_writepages() * sometimes bales out without doing anything. */ if (wbc->nr_to_write <= 0) { /* Slice used up. Queue for next turn. */ requeue_io(inode, wb); } else { /* * Writeback blocked by something other than * congestion. Delay the inode for some time to * avoid spinning on the CPU (100% iowait) * retrying writeback of the dirty page/inode * that cannot be performed immediately. */ redirty_tail_locked(inode, wb); } } else if (inode->i_state & I_DIRTY) { /* * Filesystems can dirty the inode during writeback operations, * such as delayed allocation during submission or metadata * updates after data IO completion. */ redirty_tail_locked(inode, wb); } else if (inode->i_state & I_DIRTY_TIME) { inode->dirtied_when = jiffies; inode_io_list_move_locked(inode, wb, &wb->b_dirty_time); inode->i_state &= ~I_SYNC_QUEUED; } else { /* The inode is clean. Remove from writeback lists. */ inode_io_list_del_locked(inode, wb); } } /* * Write out an inode and its dirty pages. Do not update the writeback list * linkage. That is left to the caller. The caller is also responsible for * setting I_SYNC flag and calling inode_sync_complete() to clear it. */ static int __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct address_space *mapping = inode->i_mapping; long nr_to_write = wbc->nr_to_write; unsigned dirty; int ret; WARN_ON(!(inode->i_state & I_SYNC)); trace_writeback_single_inode_start(inode, wbc, nr_to_write); ret = do_writepages(mapping, wbc); /* * Make sure to wait on the data before writing out the metadata. * This is important for filesystems that modify metadata on data * I/O completion. We don't do it for sync(2) writeback because it has a * separate, external IO completion path and ->sync_fs for guaranteeing * inode metadata is written back correctly. */ if (wbc->sync_mode == WB_SYNC_ALL && !wbc->for_sync) { int err = filemap_fdatawait(mapping); if (ret == 0) ret = err; } /* * If the inode has dirty timestamps and we need to write them, call * mark_inode_dirty_sync() to notify the filesystem about it and to * change I_DIRTY_TIME into I_DIRTY_SYNC. */ if ((inode->i_state & I_DIRTY_TIME) && (wbc->sync_mode == WB_SYNC_ALL || wbc->for_sync || time_after(jiffies, inode->dirtied_time_when + dirtytime_expire_interval * HZ))) { trace_writeback_lazytime(inode); mark_inode_dirty_sync(inode); } /* * Some filesystems may redirty the inode during the writeback * due to delalloc, clear dirty metadata flags right before * write_inode() */ spin_lock(&inode->i_lock); dirty = inode->i_state & I_DIRTY; inode->i_state &= ~dirty; /* * Paired with smp_mb() in __mark_inode_dirty(). This allows * __mark_inode_dirty() to test i_state without grabbing i_lock - * either they see the I_DIRTY bits cleared or we see the dirtied * inode. * * I_DIRTY_PAGES is always cleared together above even if @mapping * still has dirty pages. The flag is reinstated after smp_mb() if * necessary. This guarantees that either __mark_inode_dirty() * sees clear I_DIRTY_PAGES or we see PAGECACHE_TAG_DIRTY. */ smp_mb(); if (mapping_tagged(mapping, PAGECACHE_TAG_DIRTY)) inode->i_state |= I_DIRTY_PAGES; spin_unlock(&inode->i_lock); /* Don't write the inode if only I_DIRTY_PAGES was set */ if (dirty & ~I_DIRTY_PAGES) { int err = write_inode(inode, wbc); if (ret == 0) ret = err; } trace_writeback_single_inode(inode, wbc, nr_to_write); return ret; } /* * Write out an inode's dirty pages. Either the caller has an active reference * on the inode or the inode has I_WILL_FREE set. * * This function is designed to be called for writing back one inode which * we go e.g. from filesystem. Flusher thread uses __writeback_single_inode() * and does more profound writeback list handling in writeback_sb_inodes(). */ static int writeback_single_inode(struct inode *inode, struct writeback_control *wbc) { struct bdi_writeback *wb; int ret = 0; spin_lock(&inode->i_lock); if (!atomic_read(&inode->i_count)) WARN_ON(!(inode->i_state & (I_WILL_FREE|I_FREEING))); else WARN_ON(inode->i_state & I_WILL_FREE); if (inode->i_state & I_SYNC) { if (wbc->sync_mode != WB_SYNC_ALL) goto out; /* * It's a data-integrity sync. We must wait. Since callers hold * inode reference or inode has I_WILL_FREE set, it cannot go * away under us. */ __inode_wait_for_writeback(inode); } WARN_ON(inode->i_state & I_SYNC); /* * Skip inode if it is clean and we have no outstanding writeback in * WB_SYNC_ALL mode. We don't want to mess with writeback lists in this * function since flusher thread may be doing for example sync in * parallel and if we move the inode, it could get skipped. So here we * make sure inode is on some writeback list and leave it there unless * we have completely cleaned the inode. */ if (!(inode->i_state & I_DIRTY_ALL) && (wbc->sync_mode != WB_SYNC_ALL || !mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))) goto out; inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(wbc, inode); ret = __writeback_single_inode(inode, wbc); wbc_detach_inode(wbc); wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); /* * If inode is clean, remove it from writeback lists. Otherwise don't * touch it. See comment above for explanation. */ if (!(inode->i_state & I_DIRTY_ALL)) inode_io_list_del_locked(inode, wb); spin_unlock(&wb->list_lock); inode_sync_complete(inode); out: spin_unlock(&inode->i_lock); return ret; } static long writeback_chunk_size(struct bdi_writeback *wb, struct wb_writeback_work *work) { long pages; /* * WB_SYNC_ALL mode does livelock avoidance by syncing dirty * inodes/pages in one big loop. Setting wbc.nr_to_write=LONG_MAX * here avoids calling into writeback_inodes_wb() more than once. * * The intended call sequence for WB_SYNC_ALL writeback is: * * wb_writeback() * writeback_sb_inodes() <== called only once * write_cache_pages() <== called once for each inode * (quickly) tag currently dirty pages * (maybe slowly) sync all tagged pages */ if (work->sync_mode == WB_SYNC_ALL || work->tagged_writepages) pages = LONG_MAX; else { pages = min(wb->avg_write_bandwidth / 2, global_wb_domain.dirty_limit / DIRTY_SCOPE); pages = min(pages, work->nr_pages); pages = round_down(pages + MIN_WRITEBACK_PAGES, MIN_WRITEBACK_PAGES); } return pages; } /* * Write a portion of b_io inodes which belong to @sb. * * Return the number of pages and/or inodes written. * * NOTE! This is called with wb->list_lock held, and will * unlock and relock that for each inode it ends up doing * IO for. */ static long writeback_sb_inodes(struct super_block *sb, struct bdi_writeback *wb, struct wb_writeback_work *work) { struct writeback_control wbc = { .sync_mode = work->sync_mode, .tagged_writepages = work->tagged_writepages, .for_kupdate = work->for_kupdate, .for_background = work->for_background, .for_sync = work->for_sync, .range_cyclic = work->range_cyclic, .range_start = 0, .range_end = LLONG_MAX, }; unsigned long start_time = jiffies; long write_chunk; long total_wrote = 0; /* count both pages and inodes */ while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct bdi_writeback *tmp_wb; long wrote; if (inode->i_sb != sb) { if (work->sb) { /* * We only want to write back data for this * superblock, move all inodes not belonging * to it back onto the dirty list. */ redirty_tail(inode, wb); continue; } /* * The inode belongs to a different superblock. * Bounce back to the caller to unpin this and * pin the next superblock. */ break; } /* * Don't bother with new inodes or inodes being freed, first * kind does not need periodic writeout yet, and for the latter * kind writeout is handled by the freer. */ spin_lock(&inode->i_lock); if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) { redirty_tail_locked(inode, wb); spin_unlock(&inode->i_lock); continue; } if ((inode->i_state & I_SYNC) && wbc.sync_mode != WB_SYNC_ALL) { /* * If this inode is locked for writeback and we are not * doing writeback-for-data-integrity, move it to * b_more_io so that writeback can proceed with the * other inodes on s_io. * * We'll have another go at writing back this inode * when we completed a full scan of b_io. */ spin_unlock(&inode->i_lock); requeue_io(inode, wb); trace_writeback_sb_inodes_requeue(inode); continue; } spin_unlock(&wb->list_lock); /* * We already requeued the inode if it had I_SYNC set and we * are doing WB_SYNC_NONE writeback. So this catches only the * WB_SYNC_ALL case. */ if (inode->i_state & I_SYNC) { /* Wait for I_SYNC. This function drops i_lock... */ inode_sleep_on_writeback(inode); /* Inode may be gone, start again */ spin_lock(&wb->list_lock); continue; } inode->i_state |= I_SYNC; wbc_attach_and_unlock_inode(&wbc, inode); write_chunk = writeback_chunk_size(wb, work); wbc.nr_to_write = write_chunk; wbc.pages_skipped = 0; /* * We use I_SYNC to pin the inode in memory. While it is set * evict_inode() will wait so the inode cannot be freed. */ __writeback_single_inode(inode, &wbc); wbc_detach_inode(&wbc); work->nr_pages -= write_chunk - wbc.nr_to_write; wrote = write_chunk - wbc.nr_to_write - wbc.pages_skipped; wrote = wrote < 0 ? 0 : wrote; total_wrote += wrote; if (need_resched()) { /* * We're trying to balance between building up a nice * long list of IOs to improve our merge rate, and * getting those IOs out quickly for anyone throttling * in balance_dirty_pages(). cond_resched() doesn't * unplug, so get our IOs out the door before we * give up the CPU. */ blk_flush_plug(current); cond_resched(); } /* * Requeue @inode if still dirty. Be careful as @inode may * have been switched to another wb in the meantime. */ tmp_wb = inode_to_wb_and_lock_list(inode); spin_lock(&inode->i_lock); if (!(inode->i_state & I_DIRTY_ALL)) total_wrote++; requeue_inode(inode, tmp_wb, &wbc); inode_sync_complete(inode); spin_unlock(&inode->i_lock); if (unlikely(tmp_wb != wb)) { spin_unlock(&tmp_wb->list_lock); spin_lock(&wb->list_lock); } /* * bail out to wb_writeback() often enough to check * background threshold and other termination conditions. */ if (total_wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } return total_wrote; } static long __writeback_inodes_wb(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long start_time = jiffies; long wrote = 0; while (!list_empty(&wb->b_io)) { struct inode *inode = wb_inode(wb->b_io.prev); struct super_block *sb = inode->i_sb; if (!trylock_super(sb)) { /* * trylock_super() may fail consistently due to * s_umount being grabbed by someone else. Don't use * requeue_io() to avoid busy retrying the inode/sb. */ redirty_tail(inode, wb); continue; } wrote += writeback_sb_inodes(sb, wb, work); up_read(&sb->s_umount); /* refer to the same tests at the end of writeback_sb_inodes */ if (wrote) { if (time_is_before_jiffies(start_time + HZ / 10UL)) break; if (work->nr_pages <= 0) break; } } /* Leave any unwritten inodes on b_io */ return wrote; } static long writeback_inodes_wb(struct bdi_writeback *wb, long nr_pages, enum wb_reason reason) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = reason, }; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); if (list_empty(&wb->b_io)) queue_io(wb, &work, jiffies); __writeback_inodes_wb(wb, &work); spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work.nr_pages; } /* * Explicit flushing or periodic writeback of "old" data. * * Define "old": the first time one of an inode's pages is dirtied, we mark the * dirtying-time in the inode's address_space. So this periodic writeback code * just walks the superblock inode list, writing back any inodes which are * older than a specific point in time. * * Try to run once per dirty_writeback_interval. But if a writeback event * takes longer than a dirty_writeback_interval interval, then leave a * one-second gap. * * dirtied_before takes precedence over nr_to_write. So we'll only write back * all dirty pages if they are all attached to "old" mappings. */ static long wb_writeback(struct bdi_writeback *wb, struct wb_writeback_work *work) { unsigned long wb_start = jiffies; long nr_pages = work->nr_pages; unsigned long dirtied_before = jiffies; struct inode *inode; long progress; struct blk_plug plug; blk_start_plug(&plug); spin_lock(&wb->list_lock); for (;;) { /* * Stop writeback when nr_pages has been consumed */ if (work->nr_pages <= 0) break; /* * Background writeout and kupdate-style writeback may * run forever. Stop them if there is other work to do * so that e.g. sync can proceed. They'll be restarted * after the other works are all done. */ if ((work->for_background || work->for_kupdate) && !list_empty(&wb->work_list)) break; /* * For background writeout, stop when we are below the * background dirty threshold */ if (work->for_background && !wb_over_bg_thresh(wb)) break; /* * Kupdate and background works are special and we want to * include all inodes that need writing. Livelock avoidance is * handled by these works yielding to any other work so we are * safe. */ if (work->for_kupdate) { dirtied_before = jiffies - msecs_to_jiffies(dirty_expire_interval * 10); } else if (work->for_background) dirtied_before = jiffies; trace_writeback_start(wb, work); if (list_empty(&wb->b_io)) queue_io(wb, work, dirtied_before); if (work->sb) progress = writeback_sb_inodes(work->sb, wb, work); else progress = __writeback_inodes_wb(wb, work); trace_writeback_written(wb, work); wb_update_bandwidth(wb, wb_start); /* * Did we write something? Try for more * * Dirty inodes are moved to b_io for writeback in batches. * The completion of the current batch does not necessarily * mean the overall work is done. So we keep looping as long * as made some progress on cleaning pages or inodes. */ if (progress) continue; /* * No more inodes for IO, bail */ if (list_empty(&wb->b_more_io)) break; /* * Nothing written. Wait for some inode to * become available for writeback. Otherwise * we'll just busyloop. */ trace_writeback_wait(wb, work); inode = wb_inode(wb->b_more_io.prev); spin_lock(&inode->i_lock); spin_unlock(&wb->list_lock); /* This function drops i_lock... */ inode_sleep_on_writeback(inode); spin_lock(&wb->list_lock); } spin_unlock(&wb->list_lock); blk_finish_plug(&plug); return nr_pages - work->nr_pages; } /* * Return the next wb_writeback_work struct that hasn't been processed yet. */ static struct wb_writeback_work *get_next_work_item(struct bdi_writeback *wb) { struct wb_writeback_work *work = NULL; spin_lock_bh(&wb->work_lock); if (!list_empty(&wb->work_list)) { work = list_entry(wb->work_list.next, struct wb_writeback_work, list); list_del_init(&work->list); } spin_unlock_bh(&wb->work_lock); return work; } static long wb_check_background_flush(struct bdi_writeback *wb) { if (wb_over_bg_thresh(wb)) { struct wb_writeback_work work = { .nr_pages = LONG_MAX, .sync_mode = WB_SYNC_NONE, .for_background = 1, .range_cyclic = 1, .reason = WB_REASON_BACKGROUND, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_old_data_flush(struct bdi_writeback *wb) { unsigned long expired; long nr_pages; /* * When set to zero, disable periodic writeback */ if (!dirty_writeback_interval) return 0; expired = wb->last_old_flush + msecs_to_jiffies(dirty_writeback_interval * 10); if (time_before(jiffies, expired)) return 0; wb->last_old_flush = jiffies; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = nr_pages, .sync_mode = WB_SYNC_NONE, .for_kupdate = 1, .range_cyclic = 1, .reason = WB_REASON_PERIODIC, }; return wb_writeback(wb, &work); } return 0; } static long wb_check_start_all(struct bdi_writeback *wb) { long nr_pages; if (!test_bit(WB_start_all, &wb->state)) return 0; nr_pages = get_nr_dirty_pages(); if (nr_pages) { struct wb_writeback_work work = { .nr_pages = wb_split_bdi_pages(wb, nr_pages), .sync_mode = WB_SYNC_NONE, .range_cyclic = 1, .reason = wb->start_all_reason, }; nr_pages = wb_writeback(wb, &work); } clear_bit(WB_start_all, &wb->state); return nr_pages; } /* * Retrieve work items and do the writeback they describe */ static long wb_do_writeback(struct bdi_writeback *wb) { struct wb_writeback_work *work; long wrote = 0; set_bit(WB_writeback_running, &wb->state); while ((work = get_next_work_item(wb)) != NULL) { trace_writeback_exec(wb, work); wrote += wb_writeback(wb, work); finish_writeback_work(wb, work); } /* * Check for a flush-everything request */ wrote += wb_check_start_all(wb); /* * Check for periodic writeback, kupdated() style */ wrote += wb_check_old_data_flush(wb); wrote += wb_check_background_flush(wb); clear_bit(WB_writeback_running, &wb->state); return wrote; } /* * Handle writeback of dirty data for the device backed by this bdi. Also * reschedules periodically and does kupdated style flushing. */ void wb_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, dwork); long pages_written; set_worker_desc("flush-%s", bdi_dev_name(wb->bdi)); current->flags |= PF_SWAPWRITE; if (likely(!current_is_workqueue_rescuer() || !test_bit(WB_registered, &wb->state))) { /* * The normal path. Keep writing back @wb until its * work_list is empty. Note that this path is also taken * if @wb is shutting down even when we're running off the * rescuer as work_list needs to be drained. */ do { pages_written = wb_do_writeback(wb); trace_writeback_pages_written(pages_written); } while (!list_empty(&wb->work_list)); } else { /* * bdi_wq can't get enough workers and we're running off * the emergency worker. Don't hog it. Hopefully, 1024 is * enough for efficient IO. */ pages_written = writeback_inodes_wb(wb, 1024, WB_REASON_FORKER_THREAD); trace_writeback_pages_written(pages_written); } if (!list_empty(&wb->work_list)) wb_wakeup(wb); else if (wb_has_dirty_io(wb) && dirty_writeback_interval) wb_wakeup_delayed(wb); current->flags &= ~PF_SWAPWRITE; } /* * Start writeback of `nr_pages' pages on this bdi. If `nr_pages' is zero, * write back the whole world. */ static void __wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { struct bdi_writeback *wb; if (!bdi_has_dirty_io(bdi)) return; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) wb_start_writeback(wb, reason); } void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason) { rcu_read_lock(); __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wakeup the flusher threads to start writeback of all currently dirty pages */ void wakeup_flusher_threads(enum wb_reason reason) { struct backing_dev_info *bdi; /* * If we are expecting writeback progress we must submit plugged IO. */ if (blk_needs_flush_plug(current)) blk_schedule_flush_plug(current); rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) __wakeup_flusher_threads_bdi(bdi, reason); rcu_read_unlock(); } /* * Wake up bdi's periodically to make sure dirtytime inodes gets * written back periodically. We deliberately do *not* check the * b_dirtytime list in wb_has_dirty_io(), since this would cause the * kernel to be constantly waking up once there are any dirtytime * inodes on the system. So instead we define a separate delayed work * function which gets called much more rarely. (By default, only * once every 12 hours.) * * If there is any other write activity going on in the file system, * this function won't be necessary. But if the only thing that has * happened on the file system is a dirtytime inode caused by an atime * update, we need this infrastructure below to make sure that inode * eventually gets pushed out to disk. */ static void wakeup_dirtytime_writeback(struct work_struct *w); static DECLARE_DELAYED_WORK(dirtytime_work, wakeup_dirtytime_writeback); static void wakeup_dirtytime_writeback(struct work_struct *w) { struct backing_dev_info *bdi; rcu_read_lock(); list_for_each_entry_rcu(bdi, &bdi_list, bdi_list) { struct bdi_writeback *wb; list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) if (!list_empty(&wb->b_dirty_time)) wb_wakeup(wb); } rcu_read_unlock(); schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); } static int __init start_dirtytime_writeback(void) { schedule_delayed_work(&dirtytime_work, dirtytime_expire_interval * HZ); return 0; } __initcall(start_dirtytime_writeback); int dirtytime_interval_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) mod_delayed_work(system_wq, &dirtytime_work, 0); return ret; } /** * __mark_inode_dirty - internal function * * @inode: inode to mark * @flags: what kind of dirty (i.e. I_DIRTY_SYNC) * * Mark an inode as dirty. Callers should use mark_inode_dirty or * mark_inode_dirty_sync. * * Put the inode on the super block's dirty list. * * CAREFUL! We mark it dirty unconditionally, but move it onto the * dirty list only if it is hashed or if it refers to a blockdev. * If it was not hashed, it will never be added to the dirty list * even if it is later hashed, as it will have been marked dirty already. * * In short, make sure you hash any inodes _before_ you start marking * them dirty. * * Note that for blockdevs, inode->dirtied_when represents the dirtying time of * the block-special inode (/dev/hda1) itself. And the ->dirtied_when field of * the kernel-internal blockdev inode represents the dirtying time of the * blockdev's pages. This is why for I_DIRTY_PAGES we always use * page->mapping->host, so the page-dirtying time is recorded in the internal * blockdev inode. */ void __mark_inode_dirty(struct inode *inode, int flags) { struct super_block *sb = inode->i_sb; int dirtytime; trace_writeback_mark_inode_dirty(inode, flags); /* * Don't do this for I_DIRTY_PAGES - that doesn't actually * dirty the inode itself */ if (flags & (I_DIRTY_INODE | I_DIRTY_TIME)) { trace_writeback_dirty_inode_start(inode, flags); if (sb->s_op->dirty_inode) sb->s_op->dirty_inode(inode, flags); trace_writeback_dirty_inode(inode, flags); } if (flags & I_DIRTY_INODE) flags &= ~I_DIRTY_TIME; dirtytime = flags & I_DIRTY_TIME; /* * Paired with smp_mb() in __writeback_single_inode() for the * following lockless i_state test. See there for details. */ smp_mb(); if (((inode->i_state & flags) == flags) || (dirtytime && (inode->i_state & I_DIRTY_INODE))) return; spin_lock(&inode->i_lock); if (dirtytime && (inode->i_state & I_DIRTY_INODE)) goto out_unlock_inode; if ((inode->i_state & flags) != flags) { const int was_dirty = inode->i_state & I_DIRTY; inode_attach_wb(inode, NULL); if (flags & I_DIRTY_INODE) inode->i_state &= ~I_DIRTY_TIME; inode->i_state |= flags; /* * If the inode is queued for writeback by flush worker, just * update its dirty state. Once the flush worker is done with * the inode it will place it on the appropriate superblock * list, based upon its state. */ if (inode->i_state & I_SYNC_QUEUED) goto out_unlock_inode; /* * Only add valid (hashed) inodes to the superblock's * dirty list. Add blockdev inodes as well. */ if (!S_ISBLK(inode->i_mode)) { if (inode_unhashed(inode)) goto out_unlock_inode; } if (inode->i_state & I_FREEING) goto out_unlock_inode; /* * If the inode was already on b_dirty/b_io/b_more_io, don't * reposition it (that would break b_dirty time-ordering). */ if (!was_dirty) { struct bdi_writeback *wb; struct list_head *dirty_list; bool wakeup_bdi = false; wb = locked_inode_to_wb_and_lock_list(inode); WARN(bdi_cap_writeback_dirty(wb->bdi) && !test_bit(WB_registered, &wb->state), "bdi-%s not registered\n", wb->bdi->name); inode->dirtied_when = jiffies; if (dirtytime) inode->dirtied_time_when = jiffies; if (inode->i_state & I_DIRTY) dirty_list = &wb->b_dirty; else dirty_list = &wb->b_dirty_time; wakeup_bdi = inode_io_list_move_locked(inode, wb, dirty_list); spin_unlock(&wb->list_lock); trace_writeback_dirty_inode_enqueue(inode); /* * If this is the first dirty inode for this bdi, * we have to wake-up the corresponding bdi thread * to make sure background write-back happens * later. */ if (bdi_cap_writeback_dirty(wb->bdi) && wakeup_bdi) wb_wakeup_delayed(wb); return; } } out_unlock_inode: spin_unlock(&inode->i_lock); } EXPORT_SYMBOL(__mark_inode_dirty); /* * The @s_sync_lock is used to serialise concurrent sync operations * to avoid lock contention problems with concurrent wait_sb_inodes() calls. * Concurrent callers will block on the s_sync_lock rather than doing contending * walks. The queueing maintains sync(2) required behaviour as all the IO that * has been issued up to the time this function is enter is guaranteed to be * completed by the time we have gained the lock and waited for all IO that is * in progress regardless of the order callers are granted the lock. */ static void wait_sb_inodes(struct super_block *sb) { LIST_HEAD(sync_list); /* * We need to be protected against the filesystem going from * r/o to r/w or vice versa. */ WARN_ON(!rwsem_is_locked(&sb->s_umount)); mutex_lock(&sb->s_sync_lock); /* * Splice the writeback list onto a temporary list to avoid waiting on * inodes that have started writeback after this point. * * Use rcu_read_lock() to keep the inodes around until we have a * reference. s_inode_wblist_lock protects sb->s_inodes_wb as well as * the local list because inodes can be dropped from either by writeback * completion. */ rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); list_splice_init(&sb->s_inodes_wb, &sync_list); /* * Data integrity sync. Must wait for all pages under writeback, because * there may have been pages dirtied before our sync call, but which had * writeout started before we write it out. In which case, the inode * may not be on the dirty list, but we still have to wait for that * writeout. */ while (!list_empty(&sync_list)) { struct inode *inode = list_first_entry(&sync_list, struct inode, i_wb_list); struct address_space *mapping = inode->i_mapping; /* * Move each inode back to the wb list before we drop the lock * to preserve consistency between i_wb_list and the mapping * writeback tag. Writeback completion is responsible to remove * the inode from either list once the writeback tag is cleared. */ list_move_tail(&inode->i_wb_list, &sb->s_inodes_wb); /* * The mapping can appear untagged while still on-list since we * do not have the mapping lock. Skip it here, wb completion * will remove it. */ if (!mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) continue; spin_unlock_irq(&sb->s_inode_wblist_lock); spin_lock(&inode->i_lock); if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) { spin_unlock(&inode->i_lock); spin_lock_irq(&sb->s_inode_wblist_lock); continue; } __iget(inode); spin_unlock(&inode->i_lock); rcu_read_unlock(); /* * We keep the error status of individual mapping so that * applications can catch the writeback error using fsync(2). * See filemap_fdatawait_keep_errors() for details. */ filemap_fdatawait_keep_errors(mapping); cond_resched(); iput(inode); rcu_read_lock(); spin_lock_irq(&sb->s_inode_wblist_lock); } spin_unlock_irq(&sb->s_inode_wblist_lock); rcu_read_unlock(); mutex_unlock(&sb->s_sync_lock); } static void __writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason, bool skip_if_busy) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_NONE, .tagged_writepages = 1, .done = &done, .nr_pages = nr, .reason = reason, }; if (!bdi_has_dirty_io(bdi) || bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); bdi_split_work_to_wbs(sb->s_bdi, &work, skip_if_busy); wb_wait_for_completion(&done); } /** * writeback_inodes_sb_nr - writeback dirty inodes from given super_block * @sb: the superblock * @nr: the number of pages to write * @reason: reason why some writeback work initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb_nr(struct super_block *sb, unsigned long nr, enum wb_reason reason) { __writeback_inodes_sb_nr(sb, nr, reason, false); } EXPORT_SYMBOL(writeback_inodes_sb_nr); /** * writeback_inodes_sb - writeback dirty inodes from given super_block * @sb: the superblock * @reason: reason why some writeback work was initiated * * Start writeback on some inodes on this super_block. No guarantees are made * on how many (if any) will be written, and this function does not wait * for IO completion of submitted IO. */ void writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { return writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason); } EXPORT_SYMBOL(writeback_inodes_sb); /** * try_to_writeback_inodes_sb - try to start writeback if none underway * @sb: the superblock * @reason: reason why some writeback work was initiated * * Invoke __writeback_inodes_sb_nr if no writeback is currently underway. */ void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason) { if (!down_read_trylock(&sb->s_umount)) return; __writeback_inodes_sb_nr(sb, get_nr_dirty_pages(), reason, true); up_read(&sb->s_umount); } EXPORT_SYMBOL(try_to_writeback_inodes_sb); /** * sync_inodes_sb - sync sb inode pages * @sb: the superblock * * This function writes and waits on any dirty inode belonging to this * super_block. */ void sync_inodes_sb(struct super_block *sb) { struct backing_dev_info *bdi = sb->s_bdi; DEFINE_WB_COMPLETION(done, bdi); struct wb_writeback_work work = { .sb = sb, .sync_mode = WB_SYNC_ALL, .nr_pages = LONG_MAX, .range_cyclic = 0, .done = &done, .reason = WB_REASON_SYNC, .for_sync = 1, }; /* * Can't skip on !bdi_has_dirty() because we should wait for !dirty * inodes under writeback and I_DIRTY_TIME inodes ignored by * bdi_has_dirty() need to be written out too. */ if (bdi == &noop_backing_dev_info) return; WARN_ON(!rwsem_is_locked(&sb->s_umount)); /* protect against inode wb switch, see inode_switch_wbs_work_fn() */ bdi_down_write_wb_switch_rwsem(bdi); bdi_split_work_to_wbs(bdi, &work, false); wb_wait_for_completion(&done); bdi_up_write_wb_switch_rwsem(bdi); wait_sb_inodes(sb); } EXPORT_SYMBOL(sync_inodes_sb); /** * write_inode_now - write an inode to disk * @inode: inode to write to disk * @sync: whether the write should be synchronous or not * * This function commits an inode to disk immediately if it is dirty. This is * primarily needed by knfsd. * * The caller must either have a ref on the inode or must have set I_WILL_FREE. */ int write_inode_now(struct inode *inode, int sync) { struct writeback_control wbc = { .nr_to_write = LONG_MAX, .sync_mode = sync ? WB_SYNC_ALL : WB_SYNC_NONE, .range_start = 0, .range_end = LLONG_MAX, }; if (!mapping_cap_writeback_dirty(inode->i_mapping)) wbc.nr_to_write = 0; might_sleep(); return writeback_single_inode(inode, &wbc); } EXPORT_SYMBOL(write_inode_now); /** * sync_inode - write an inode and its pages to disk. * @inode: the inode to sync * @wbc: controls the writeback mode * * sync_inode() will write an inode and its pages to disk. It will also * correctly update the inode on its superblock's dirty inode lists and will * update inode->i_state. * * The caller must have a ref on the inode. */ int sync_inode(struct inode *inode, struct writeback_control *wbc) { return writeback_single_inode(inode, wbc); } EXPORT_SYMBOL(sync_inode); /** * sync_inode_metadata - write an inode to disk * @inode: the inode to sync * @wait: wait for I/O to complete. * * Write an inode to disk and adjust its dirty state after completion. * * Note: only writes the actual inode, no associated data or other metadata. */ int sync_inode_metadata(struct inode *inode, int wait) { struct writeback_control wbc = { .sync_mode = wait ? WB_SYNC_ALL : WB_SYNC_NONE, .nr_to_write = 0, /* metadata-only */ }; return sync_inode(inode, &wbc); } EXPORT_SYMBOL(sync_inode_metadata); |
| 490 488 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 | // SPDX-License-Identifier: GPL-2.0 /* * Software nodes for the firmware node framework. * * Copyright (C) 2018, Intel Corporation * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com> */ #include <linux/device.h> #include <linux/kernel.h> #include <linux/property.h> #include <linux/slab.h> struct swnode { int id; struct kobject kobj; struct fwnode_handle fwnode; const struct software_node *node; /* hierarchy */ struct ida child_ids; struct list_head entry; struct list_head children; struct swnode *parent; unsigned int allocated:1; }; static DEFINE_IDA(swnode_root_ids); static struct kset *swnode_kset; #define kobj_to_swnode(_kobj_) container_of(_kobj_, struct swnode, kobj) static const struct fwnode_operations software_node_ops; bool is_software_node(const struct fwnode_handle *fwnode) { return !IS_ERR_OR_NULL(fwnode) && fwnode->ops == &software_node_ops; } EXPORT_SYMBOL_GPL(is_software_node); #define to_swnode(__fwnode) \ ({ \ typeof(__fwnode) __to_swnode_fwnode = __fwnode; \ \ is_software_node(__to_swnode_fwnode) ? \ container_of(__to_swnode_fwnode, \ struct swnode, fwnode) : NULL; \ }) static struct swnode * software_node_to_swnode(const struct software_node *node) { struct swnode *swnode = NULL; struct kobject *k; if (!node) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (swnode->node == node) break; swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode; } const struct software_node *to_software_node(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(to_software_node); struct fwnode_handle *software_node_fwnode(const struct software_node *node) { struct swnode *swnode = software_node_to_swnode(node); return swnode ? &swnode->fwnode : NULL; } EXPORT_SYMBOL_GPL(software_node_fwnode); /* -------------------------------------------------------------------------- */ /* property_entry processing */ static const struct property_entry * property_entry_get(const struct property_entry *prop, const char *name) { if (!prop) return NULL; for (; prop->name; prop++) if (!strcmp(name, prop->name)) return prop; return NULL; } static void property_set_pointer(struct property_entry *prop, const void *pointer) { switch (prop->type) { case DEV_PROP_U8: if (prop->is_array) prop->pointer.u8_data = pointer; else prop->value.u8_data = *((u8 *)pointer); break; case DEV_PROP_U16: if (prop->is_array) prop->pointer.u16_data = pointer; else prop->value.u16_data = *((u16 *)pointer); break; case DEV_PROP_U32: if (prop->is_array) prop->pointer.u32_data = pointer; else prop->value.u32_data = *((u32 *)pointer); break; case DEV_PROP_U64: if (prop->is_array) prop->pointer.u64_data = pointer; else prop->value.u64_data = *((u64 *)pointer); break; case DEV_PROP_STRING: if (prop->is_array) prop->pointer.str = pointer; else prop->value.str = pointer; break; default: break; } } static const void *property_get_pointer(const struct property_entry *prop) { switch (prop->type) { case DEV_PROP_U8: if (prop->is_array) return prop->pointer.u8_data; return &prop->value.u8_data; case DEV_PROP_U16: if (prop->is_array) return prop->pointer.u16_data; return &prop->value.u16_data; case DEV_PROP_U32: if (prop->is_array) return prop->pointer.u32_data; return &prop->value.u32_data; case DEV_PROP_U64: if (prop->is_array) return prop->pointer.u64_data; return &prop->value.u64_data; case DEV_PROP_STRING: if (prop->is_array) return prop->pointer.str; return &prop->value.str; default: return NULL; } } static const void *property_entry_find(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; const void *pointer; prop = property_entry_get(props, propname); if (!prop) return ERR_PTR(-EINVAL); pointer = property_get_pointer(prop); if (!pointer) return ERR_PTR(-ENODATA); if (length > prop->length) return ERR_PTR(-EOVERFLOW); return pointer; } static int property_entry_read_u8_array(const struct property_entry *props, const char *propname, u8 *values, size_t nval) { const void *pointer; size_t length = nval * sizeof(*values); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(values, pointer, length); return 0; } static int property_entry_read_u16_array(const struct property_entry *props, const char *propname, u16 *values, size_t nval) { const void *pointer; size_t length = nval * sizeof(*values); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(values, pointer, length); return 0; } static int property_entry_read_u32_array(const struct property_entry *props, const char *propname, u32 *values, size_t nval) { const void *pointer; size_t length = nval * sizeof(*values); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(values, pointer, length); return 0; } static int property_entry_read_u64_array(const struct property_entry *props, const char *propname, u64 *values, size_t nval) { const void *pointer; size_t length = nval * sizeof(*values); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(values, pointer, length); return 0; } static int property_entry_count_elems_of_size(const struct property_entry *props, const char *propname, size_t length) { const struct property_entry *prop; prop = property_entry_get(props, propname); if (!prop) return -EINVAL; return prop->length / length; } static int property_entry_read_int_array(const struct property_entry *props, const char *name, unsigned int elem_size, void *val, size_t nval) { if (!val) return property_entry_count_elems_of_size(props, name, elem_size); switch (elem_size) { case sizeof(u8): return property_entry_read_u8_array(props, name, val, nval); case sizeof(u16): return property_entry_read_u16_array(props, name, val, nval); case sizeof(u32): return property_entry_read_u32_array(props, name, val, nval); case sizeof(u64): return property_entry_read_u64_array(props, name, val, nval); } return -ENXIO; } static int property_entry_read_string_array(const struct property_entry *props, const char *propname, const char **strings, size_t nval) { const struct property_entry *prop; const void *pointer; size_t array_len, length; /* Find out the array length. */ prop = property_entry_get(props, propname); if (!prop) return -EINVAL; if (prop->is_array) /* Find the length of an array. */ array_len = property_entry_count_elems_of_size(props, propname, sizeof(const char *)); else /* The array length for a non-array string property is 1. */ array_len = 1; /* Return how many there are if strings is NULL. */ if (!strings) return array_len; array_len = min(nval, array_len); length = array_len * sizeof(*strings); pointer = property_entry_find(props, propname, length); if (IS_ERR(pointer)) return PTR_ERR(pointer); memcpy(strings, pointer, length); return array_len; } static void property_entry_free_data(const struct property_entry *p) { const void *pointer = property_get_pointer(p); size_t i, nval; if (p->is_array) { if (p->type == DEV_PROP_STRING && p->pointer.str) { nval = p->length / sizeof(const char *); for (i = 0; i < nval; i++) kfree(p->pointer.str[i]); } kfree(pointer); } else if (p->type == DEV_PROP_STRING) { kfree(p->value.str); } kfree(p->name); } static int property_copy_string_array(struct property_entry *dst, const struct property_entry *src) { const char **d; size_t nval = src->length / sizeof(*d); int i; d = kcalloc(nval, sizeof(*d), GFP_KERNEL); if (!d) return -ENOMEM; for (i = 0; i < nval; i++) { d[i] = kstrdup(src->pointer.str[i], GFP_KERNEL); if (!d[i] && src->pointer.str[i]) { while (--i >= 0) kfree(d[i]); kfree(d); return -ENOMEM; } } dst->pointer.str = d; return 0; } static int property_entry_copy_data(struct property_entry *dst, const struct property_entry *src) { const void *pointer = property_get_pointer(src); const void *new; int error; if (src->is_array) { if (!src->length) return -ENODATA; if (src->type == DEV_PROP_STRING) { error = property_copy_string_array(dst, src); if (error) return error; new = dst->pointer.str; } else { new = kmemdup(pointer, src->length, GFP_KERNEL); if (!new) return -ENOMEM; } } else if (src->type == DEV_PROP_STRING) { new = kstrdup(src->value.str, GFP_KERNEL); if (!new && src->value.str) return -ENOMEM; } else { new = pointer; } dst->length = src->length; dst->is_array = src->is_array; dst->type = src->type; property_set_pointer(dst, new); dst->name = kstrdup(src->name, GFP_KERNEL); if (!dst->name) goto out_free_data; return 0; out_free_data: property_entry_free_data(dst); return -ENOMEM; } /** * property_entries_dup - duplicate array of properties * @properties: array of properties to copy * * This function creates a deep copy of the given NULL-terminated array * of property entries. */ struct property_entry * property_entries_dup(const struct property_entry *properties) { struct property_entry *p; int i, n = 0; int ret; if (!properties) return NULL; while (properties[n].name) n++; p = kcalloc(n + 1, sizeof(*p), GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); for (i = 0; i < n; i++) { ret = property_entry_copy_data(&p[i], &properties[i]); if (ret) { while (--i >= 0) property_entry_free_data(&p[i]); kfree(p); return ERR_PTR(ret); } } return p; } EXPORT_SYMBOL_GPL(property_entries_dup); /** * property_entries_free - free previously allocated array of properties * @properties: array of properties to destroy * * This function frees given NULL-terminated array of property entries, * along with their data. */ void property_entries_free(const struct property_entry *properties) { const struct property_entry *p; if (!properties) return; for (p = properties; p->name; p++) property_entry_free_data(p); kfree(properties); } EXPORT_SYMBOL_GPL(property_entries_free); /* -------------------------------------------------------------------------- */ /* fwnode operations */ static struct fwnode_handle *software_node_get(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_get(&swnode->kobj); return &swnode->fwnode; } static void software_node_put(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); kobject_put(&swnode->kobj); } static bool software_node_property_present(const struct fwnode_handle *fwnode, const char *propname) { struct swnode *swnode = to_swnode(fwnode); return !!property_entry_get(swnode->node->properties, propname); } static int software_node_read_int_array(const struct fwnode_handle *fwnode, const char *propname, unsigned int elem_size, void *val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_int_array(swnode->node->properties, propname, elem_size, val, nval); } static int software_node_read_string_array(const struct fwnode_handle *fwnode, const char *propname, const char **val, size_t nval) { struct swnode *swnode = to_swnode(fwnode); return property_entry_read_string_array(swnode->node->properties, propname, val, nval); } static struct fwnode_handle * software_node_get_parent(const struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode || !swnode->parent) return NULL; return fwnode_handle_get(&swnode->parent->fwnode); } static struct fwnode_handle * software_node_get_next_child(const struct fwnode_handle *fwnode, struct fwnode_handle *child) { struct swnode *p = to_swnode(fwnode); struct swnode *c = to_swnode(child); if (!p || list_empty(&p->children) || (c && list_is_last(&c->entry, &p->children))) { fwnode_handle_put(child); return NULL; } if (c) c = list_next_entry(c, entry); else c = list_first_entry(&p->children, struct swnode, entry); fwnode_handle_put(child); return fwnode_handle_get(&c->fwnode); } static struct fwnode_handle * software_node_get_named_child_node(const struct fwnode_handle *fwnode, const char *childname) { struct swnode *swnode = to_swnode(fwnode); struct swnode *child; if (!swnode || list_empty(&swnode->children)) return NULL; list_for_each_entry(child, &swnode->children, entry) { if (!strcmp(childname, kobject_name(&child->kobj))) { kobject_get(&child->kobj); return &child->fwnode; } } return NULL; } static int software_node_get_reference_args(const struct fwnode_handle *fwnode, const char *propname, const char *nargs_prop, unsigned int nargs, unsigned int index, struct fwnode_reference_args *args) { struct swnode *swnode = to_swnode(fwnode); const struct software_node_reference *ref; const struct property_entry *prop; struct fwnode_handle *refnode; int i; if (!swnode || !swnode->node->references) return -ENOENT; for (ref = swnode->node->references; ref->name; ref++) if (!strcmp(ref->name, propname)) break; if (!ref->name || index > (ref->nrefs - 1)) return -ENOENT; refnode = software_node_fwnode(ref->refs[index].node); if (!refnode) return -ENOENT; if (nargs_prop) { prop = property_entry_get(swnode->node->properties, nargs_prop); if (!prop) return -EINVAL; nargs = prop->value.u32_data; } if (nargs > NR_FWNODE_REFERENCE_ARGS) return -EINVAL; if (!args) return 0; args->fwnode = software_node_get(refnode); args->nargs = nargs; for (i = 0; i < nargs; i++) args->args[i] = ref->refs[index].args[i]; return 0; } static const struct fwnode_operations software_node_ops = { .get = software_node_get, .put = software_node_put, .property_present = software_node_property_present, .property_read_int_array = software_node_read_int_array, .property_read_string_array = software_node_read_string_array, .get_parent = software_node_get_parent, .get_next_child_node = software_node_get_next_child, .get_named_child_node = software_node_get_named_child_node, .get_reference_args = software_node_get_reference_args }; /* -------------------------------------------------------------------------- */ /** * software_node_find_by_name - Find software node by name * @parent: Parent of the software node * @name: Name of the software node * * The function will find a node that is child of @parent and that is named * @name. If no node is found, the function returns NULL. * * NOTE: you will need to drop the reference with fwnode_handle_put() after use. */ const struct software_node * software_node_find_by_name(const struct software_node *parent, const char *name) { struct swnode *swnode = NULL; struct kobject *k; if (!name) return NULL; spin_lock(&swnode_kset->list_lock); list_for_each_entry(k, &swnode_kset->list, entry) { swnode = kobj_to_swnode(k); if (parent == swnode->node->parent && swnode->node->name && !strcmp(name, swnode->node->name)) { kobject_get(&swnode->kobj); break; } swnode = NULL; } spin_unlock(&swnode_kset->list_lock); return swnode ? swnode->node : NULL; } EXPORT_SYMBOL_GPL(software_node_find_by_name); static int software_node_register_properties(struct software_node *node, const struct property_entry *properties) { struct property_entry *props; props = property_entries_dup(properties); if (IS_ERR(props)) return PTR_ERR(props); node->properties = props; return 0; } static void software_node_release(struct kobject *kobj) { struct swnode *swnode = kobj_to_swnode(kobj); if (swnode->parent) { ida_simple_remove(&swnode->parent->child_ids, swnode->id); list_del(&swnode->entry); } else { ida_simple_remove(&swnode_root_ids, swnode->id); } if (swnode->allocated) { property_entries_free(swnode->node->properties); kfree(swnode->node); } ida_destroy(&swnode->child_ids); kfree(swnode); } static struct kobj_type software_node_type = { .release = software_node_release, .sysfs_ops = &kobj_sysfs_ops, }; static struct fwnode_handle * swnode_register(const struct software_node *node, struct swnode *parent, unsigned int allocated) { struct swnode *swnode; int ret; swnode = kzalloc(sizeof(*swnode), GFP_KERNEL); if (!swnode) { ret = -ENOMEM; goto out_err; } ret = ida_simple_get(parent ? &parent->child_ids : &swnode_root_ids, 0, 0, GFP_KERNEL); if (ret < 0) { kfree(swnode); goto out_err; } swnode->id = ret; swnode->node = node; swnode->parent = parent; swnode->allocated = allocated; swnode->kobj.kset = swnode_kset; swnode->fwnode.ops = &software_node_ops; ida_init(&swnode->child_ids); INIT_LIST_HEAD(&swnode->entry); INIT_LIST_HEAD(&swnode->children); if (node->name) ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "%s", node->name); else ret = kobject_init_and_add(&swnode->kobj, &software_node_type, parent ? &parent->kobj : NULL, "node%d", swnode->id); if (ret) { kobject_put(&swnode->kobj); return ERR_PTR(ret); } if (parent) list_add_tail(&swnode->entry, &parent->children); kobject_uevent(&swnode->kobj, KOBJ_ADD); return &swnode->fwnode; out_err: if (allocated) property_entries_free(node->properties); return ERR_PTR(ret); } /** * software_node_register_nodes - Register an array of software nodes * @nodes: Zero terminated array of software nodes to be registered * * Register multiple software nodes at once. */ int software_node_register_nodes(const struct software_node *nodes) { int ret; int i; for (i = 0; nodes[i].name; i++) { ret = software_node_register(&nodes[i]); if (ret) { software_node_unregister_nodes(nodes); return ret; } } return 0; } EXPORT_SYMBOL_GPL(software_node_register_nodes); /** * software_node_unregister_nodes - Unregister an array of software nodes * @nodes: Zero terminated array of software nodes to be unregistered * * Unregister multiple software nodes at once. */ void software_node_unregister_nodes(const struct software_node *nodes) { struct swnode *swnode; int i; for (i = 0; nodes[i].name; i++) { swnode = software_node_to_swnode(&nodes[i]); if (swnode) fwnode_remove_software_node(&swnode->fwnode); } } EXPORT_SYMBOL_GPL(software_node_unregister_nodes); /** * software_node_register - Register static software node * @node: The software node to be registered */ int software_node_register(const struct software_node *node) { struct swnode *parent = software_node_to_swnode(node->parent); if (software_node_to_swnode(node)) return -EEXIST; if (node->parent && !parent) return -EINVAL; return PTR_ERR_OR_ZERO(swnode_register(node, parent, 0)); } EXPORT_SYMBOL_GPL(software_node_register); struct fwnode_handle * fwnode_create_software_node(const struct property_entry *properties, const struct fwnode_handle *parent) { struct software_node *node; struct swnode *p = NULL; int ret; if (parent) { if (IS_ERR(parent)) return ERR_CAST(parent); if (!is_software_node(parent)) return ERR_PTR(-EINVAL); p = to_swnode(parent); } node = kzalloc(sizeof(*node), GFP_KERNEL); if (!node) return ERR_PTR(-ENOMEM); ret = software_node_register_properties(node, properties); if (ret) { kfree(node); return ERR_PTR(ret); } node->parent = p ? p->node : NULL; return swnode_register(node, p, 1); } EXPORT_SYMBOL_GPL(fwnode_create_software_node); void fwnode_remove_software_node(struct fwnode_handle *fwnode) { struct swnode *swnode = to_swnode(fwnode); if (!swnode) return; kobject_put(&swnode->kobj); } EXPORT_SYMBOL_GPL(fwnode_remove_software_node); int software_node_notify(struct device *dev, unsigned long action) { struct fwnode_handle *fwnode = dev_fwnode(dev); struct swnode *swnode; int ret; if (!fwnode) return 0; if (!is_software_node(fwnode)) fwnode = fwnode->secondary; if (!is_software_node(fwnode)) return 0; swnode = to_swnode(fwnode); switch (action) { case KOBJ_ADD: ret = sysfs_create_link(&dev->kobj, &swnode->kobj, "software_node"); if (ret) break; ret = sysfs_create_link(&swnode->kobj, &dev->kobj, dev_name(dev)); if (ret) { sysfs_remove_link(&dev->kobj, "software_node"); break; } kobject_get(&swnode->kobj); break; case KOBJ_REMOVE: sysfs_remove_link(&swnode->kobj, dev_name(dev)); sysfs_remove_link(&dev->kobj, "software_node"); kobject_put(&swnode->kobj); break; default: break; } return 0; } static int __init software_node_init(void) { swnode_kset = kset_create_and_add("software_nodes", NULL, kernel_kobj); if (!swnode_kset) return -ENOMEM; return 0; } postcore_initcall(software_node_init); static void __exit software_node_exit(void) { ida_destroy(&swnode_root_ids); kset_unregister(swnode_kset); } __exitcall(software_node_exit); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_UIDGID_H #define _LINUX_UIDGID_H /* * A set of types for the internal kernel types representing uids and gids. * * The types defined in this header allow distinguishing which uids and gids in * the kernel are values used by userspace and which uid and gid values are * the internal kernel values. With the addition of user namespaces the values * can be different. Using the type system makes it possible for the compiler * to detect when we overlook these differences. * */ #include <linux/types.h> #include <linux/highuid.h> struct user_namespace; extern struct user_namespace init_user_ns; typedef struct { uid_t val; } kuid_t; typedef struct { gid_t val; } kgid_t; #define KUIDT_INIT(value) (kuid_t){ value } #define KGIDT_INIT(value) (kgid_t){ value } #ifdef CONFIG_MULTIUSER static inline uid_t __kuid_val(kuid_t uid) { return uid.val; } static inline gid_t __kgid_val(kgid_t gid) { return gid.val; } #else static inline uid_t __kuid_val(kuid_t uid) { return 0; } static inline gid_t __kgid_val(kgid_t gid) { return 0; } #endif #define GLOBAL_ROOT_UID KUIDT_INIT(0) #define GLOBAL_ROOT_GID KGIDT_INIT(0) #define INVALID_UID KUIDT_INIT(-1) #define INVALID_GID KGIDT_INIT(-1) static inline bool uid_eq(kuid_t left, kuid_t right) { return __kuid_val(left) == __kuid_val(right); } static inline bool gid_eq(kgid_t left, kgid_t right) { return __kgid_val(left) == __kgid_val(right); } static inline bool uid_gt(kuid_t left, kuid_t right) { return __kuid_val(left) > __kuid_val(right); } static inline bool gid_gt(kgid_t left, kgid_t right) { return __kgid_val(left) > __kgid_val(right); } static inline bool uid_gte(kuid_t left, kuid_t right) { return __kuid_val(left) >= __kuid_val(right); } static inline bool gid_gte(kgid_t left, kgid_t right) { return __kgid_val(left) >= __kgid_val(right); } static inline bool uid_lt(kuid_t left, kuid_t right) { return __kuid_val(left) < __kuid_val(right); } static inline bool gid_lt(kgid_t left, kgid_t right) { return __kgid_val(left) < __kgid_val(right); } static inline bool uid_lte(kuid_t left, kuid_t right) { return __kuid_val(left) <= __kuid_val(right); } static inline bool gid_lte(kgid_t left, kgid_t right) { return __kgid_val(left) <= __kgid_val(right); } static inline bool uid_valid(kuid_t uid) { return __kuid_val(uid) != (uid_t) -1; } static inline bool gid_valid(kgid_t gid) { return __kgid_val(gid) != (gid_t) -1; } #ifdef CONFIG_USER_NS extern kuid_t make_kuid(struct user_namespace *from, uid_t uid); extern kgid_t make_kgid(struct user_namespace *from, gid_t gid); extern uid_t from_kuid(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid(struct user_namespace *to, kgid_t gid); extern uid_t from_kuid_munged(struct user_namespace *to, kuid_t uid); extern gid_t from_kgid_munged(struct user_namespace *to, kgid_t gid); static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return from_kuid(ns, uid) != (uid_t) -1; } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return from_kgid(ns, gid) != (gid_t) -1; } #else static inline kuid_t make_kuid(struct user_namespace *from, uid_t uid) { return KUIDT_INIT(uid); } static inline kgid_t make_kgid(struct user_namespace *from, gid_t gid) { return KGIDT_INIT(gid); } static inline uid_t from_kuid(struct user_namespace *to, kuid_t kuid) { return __kuid_val(kuid); } static inline gid_t from_kgid(struct user_namespace *to, kgid_t kgid) { return __kgid_val(kgid); } static inline uid_t from_kuid_munged(struct user_namespace *to, kuid_t kuid) { uid_t uid = from_kuid(to, kuid); if (uid == (uid_t)-1) uid = overflowuid; return uid; } static inline gid_t from_kgid_munged(struct user_namespace *to, kgid_t kgid) { gid_t gid = from_kgid(to, kgid); if (gid == (gid_t)-1) gid = overflowgid; return gid; } static inline bool kuid_has_mapping(struct user_namespace *ns, kuid_t uid) { return uid_valid(uid); } static inline bool kgid_has_mapping(struct user_namespace *ns, kgid_t gid) { return gid_valid(gid); } #endif /* CONFIG_USER_NS */ #endif /* _LINUX_UIDGID_H */ |
| 279 23 153 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> linux/include/linux/rbtree.h To use rbtrees you'll have to implement your own insert and search cores. This will avoid us to use callbacks and to drop drammatically performances. I know it's not the cleaner way, but in C (not in C++) to get performances and genericity... See Documentation/rbtree.txt for documentation and samples. */ #ifndef _LINUX_RBTREE_H #define _LINUX_RBTREE_H #include <linux/kernel.h> #include <linux/stddef.h> #include <linux/rcupdate.h> struct rb_node { unsigned long __rb_parent_color; struct rb_node *rb_right; struct rb_node *rb_left; } __attribute__((aligned(sizeof(long)))); /* The alignment might seem pointless, but allegedly CRIS needs it */ struct rb_root { struct rb_node *rb_node; }; #define rb_parent(r) ((struct rb_node *)((r)->__rb_parent_color & ~3)) #define RB_ROOT (struct rb_root) { NULL, } #define rb_entry(ptr, type, member) container_of(ptr, type, member) #define RB_EMPTY_ROOT(root) (READ_ONCE((root)->rb_node) == NULL) /* 'empty' nodes are nodes that are known not to be inserted in an rbtree */ #define RB_EMPTY_NODE(node) \ ((node)->__rb_parent_color == (unsigned long)(node)) #define RB_CLEAR_NODE(node) \ ((node)->__rb_parent_color = (unsigned long)(node)) extern void rb_insert_color(struct rb_node *, struct rb_root *); extern void rb_erase(struct rb_node *, struct rb_root *); /* Find logical next and previous nodes in a tree */ extern struct rb_node *rb_next(const struct rb_node *); extern struct rb_node *rb_prev(const struct rb_node *); extern struct rb_node *rb_first(const struct rb_root *); extern struct rb_node *rb_last(const struct rb_root *); /* Postorder iteration - always visit the parent after its children */ extern struct rb_node *rb_first_postorder(const struct rb_root *); extern struct rb_node *rb_next_postorder(const struct rb_node *); /* Fast replacement of a single node without remove/rebalance/add/rebalance */ extern void rb_replace_node(struct rb_node *victim, struct rb_node *new, struct rb_root *root); extern void rb_replace_node_rcu(struct rb_node *victim, struct rb_node *new, struct rb_root *root); static inline void rb_link_node(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; *rb_link = node; } static inline void rb_link_node_rcu(struct rb_node *node, struct rb_node *parent, struct rb_node **rb_link) { node->__rb_parent_color = (unsigned long)parent; node->rb_left = node->rb_right = NULL; rcu_assign_pointer(*rb_link, node); } #define rb_entry_safe(ptr, type, member) \ ({ typeof(ptr) ____ptr = (ptr); \ ____ptr ? rb_entry(____ptr, type, member) : NULL; \ }) /** * rbtree_postorder_for_each_entry_safe - iterate in post-order over rb_root of * given type allowing the backing memory of @pos to be invalidated * * @pos: the 'type *' to use as a loop cursor. * @n: another 'type *' to use as temporary storage * @root: 'rb_root *' of the rbtree. * @field: the name of the rb_node field within 'type'. * * rbtree_postorder_for_each_entry_safe() provides a similar guarantee as * list_for_each_entry_safe() and allows the iteration to continue independent * of changes to @pos by the body of the loop. * * Note, however, that it cannot handle other modifications that re-order the * rbtree it is iterating over. This includes calling rb_erase() on @pos, as * rb_erase() may rebalance the tree, causing us to miss some nodes. */ #define rbtree_postorder_for_each_entry_safe(pos, n, root, field) \ for (pos = rb_entry_safe(rb_first_postorder(root), typeof(*pos), field); \ pos && ({ n = rb_entry_safe(rb_next_postorder(&pos->field), \ typeof(*pos), field); 1; }); \ pos = n) /* * Leftmost-cached rbtrees. * * We do not cache the rightmost node based on footprint * size vs number of potential users that could benefit * from O(1) rb_last(). Just not worth it, users that want * this feature can always implement the logic explicitly. * Furthermore, users that want to cache both pointers may * find it a bit asymmetric, but that's ok. */ struct rb_root_cached { struct rb_root rb_root; struct rb_node *rb_leftmost; }; #define RB_ROOT_CACHED (struct rb_root_cached) { {NULL, }, NULL } /* Same as rb_first(), but O(1) */ #define rb_first_cached(root) (root)->rb_leftmost static inline void rb_insert_color_cached(struct rb_node *node, struct rb_root_cached *root, bool leftmost) { if (leftmost) root->rb_leftmost = node; rb_insert_color(node, &root->rb_root); } static inline void rb_erase_cached(struct rb_node *node, struct rb_root_cached *root) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase(node, &root->rb_root); } static inline void rb_replace_node_cached(struct rb_node *victim, struct rb_node *new, struct rb_root_cached *root) { if (root->rb_leftmost == victim) root->rb_leftmost = new; rb_replace_node(victim, new, &root->rb_root); } #endif /* _LINUX_RBTREE_H */ |
| 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 | // SPDX-License-Identifier: GPL-2.0 /* xfrm_hash.c: Common hash table code. * * Copyright (C) 2006 David S. Miller (davem@davemloft.net) */ #include <linux/kernel.h> #include <linux/mm.h> #include <linux/memblock.h> #include <linux/vmalloc.h> #include <linux/slab.h> #include <linux/xfrm.h> #include "xfrm_hash.h" struct hlist_head *xfrm_hash_alloc(unsigned int sz) { struct hlist_head *n; if (sz <= PAGE_SIZE) n = kzalloc(sz, GFP_KERNEL); else if (hashdist) n = vzalloc(sz); else n = (struct hlist_head *) __get_free_pages(GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO, get_order(sz)); return n; } void xfrm_hash_free(struct hlist_head *n, unsigned int sz) { if (sz <= PAGE_SIZE) kfree(n); else if (hashdist) vfree(n); else free_pages((unsigned long)n, get_order(sz)); } |
| 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "peer.h" #include "device.h" #include "queueing.h" #include "timers.h" #include "peerlookup.h" #include "noise.h" #include <linux/kref.h> #include <linux/lockdep.h> #include <linux/rcupdate.h> #include <linux/list.h> static struct kmem_cache *peer_cache; static atomic64_t peer_counter = ATOMIC64_INIT(0); struct wg_peer *wg_peer_create(struct wg_device *wg, const u8 public_key[NOISE_PUBLIC_KEY_LEN], const u8 preshared_key[NOISE_SYMMETRIC_KEY_LEN]) { struct wg_peer *peer; int ret = -ENOMEM; lockdep_assert_held(&wg->device_update_lock); if (wg->num_peers >= MAX_PEERS_PER_DEVICE) return ERR_PTR(ret); peer = kmem_cache_zalloc(peer_cache, GFP_KERNEL); if (unlikely(!peer)) return ERR_PTR(ret); if (unlikely(dst_cache_init(&peer->endpoint_cache, GFP_KERNEL))) goto err; peer->device = wg; wg_noise_handshake_init(&peer->handshake, &wg->static_identity, public_key, preshared_key, peer); peer->internal_id = atomic64_inc_return(&peer_counter); peer->serial_work_cpu = nr_cpumask_bits; wg_cookie_init(&peer->latest_cookie); wg_timers_init(peer); wg_cookie_checker_precompute_peer_keys(peer); spin_lock_init(&peer->keypairs.keypair_update_lock); INIT_WORK(&peer->transmit_handshake_work, wg_packet_handshake_send_worker); INIT_WORK(&peer->transmit_packet_work, wg_packet_tx_worker); wg_prev_queue_init(&peer->tx_queue); wg_prev_queue_init(&peer->rx_queue); rwlock_init(&peer->endpoint_lock); kref_init(&peer->refcount); skb_queue_head_init(&peer->staged_packet_queue); wg_noise_reset_last_sent_handshake(&peer->last_sent_handshake); set_bit(NAPI_STATE_NO_BUSY_POLL, &peer->napi.state); netif_napi_add(wg->dev, &peer->napi, wg_packet_rx_poll, NAPI_POLL_WEIGHT); napi_enable(&peer->napi); list_add_tail(&peer->peer_list, &wg->peer_list); INIT_LIST_HEAD(&peer->allowedips_list); wg_pubkey_hashtable_add(wg->peer_hashtable, peer); ++wg->num_peers; pr_debug("%s: Peer %llu created\n", wg->dev->name, peer->internal_id); return peer; err: kmem_cache_free(peer_cache, peer); return ERR_PTR(ret); } struct wg_peer *wg_peer_get_maybe_zero(struct wg_peer *peer) { RCU_LOCKDEP_WARN(!rcu_read_lock_bh_held(), "Taking peer reference without holding the RCU read lock"); if (unlikely(!peer || !kref_get_unless_zero(&peer->refcount))) return NULL; return peer; } static void peer_make_dead(struct wg_peer *peer) { /* Remove from configuration-time lookup structures. */ list_del_init(&peer->peer_list); wg_allowedips_remove_by_peer(&peer->device->peer_allowedips, peer, &peer->device->device_update_lock); wg_pubkey_hashtable_remove(peer->device->peer_hashtable, peer); /* Mark as dead, so that we don't allow jumping contexts after. */ WRITE_ONCE(peer->is_dead, true); /* The caller must now synchronize_net() for this to take effect. */ } static void peer_remove_after_dead(struct wg_peer *peer) { WARN_ON(!peer->is_dead); /* No more keypairs can be created for this peer, since is_dead protects * add_new_keypair, so we can now destroy existing ones. */ wg_noise_keypairs_clear(&peer->keypairs); /* Destroy all ongoing timers that were in-flight at the beginning of * this function. */ wg_timers_stop(peer); /* The transition between packet encryption/decryption queues isn't * guarded by is_dead, but each reference's life is strictly bounded by * two generations: once for parallel crypto and once for serial * ingestion, so we can simply flush twice, and be sure that we no * longer have references inside these queues. */ /* a) For encrypt/decrypt. */ flush_workqueue(peer->device->packet_crypt_wq); /* b.1) For send (but not receive, since that's napi). */ flush_workqueue(peer->device->packet_crypt_wq); /* b.2.1) For receive (but not send, since that's wq). */ napi_disable(&peer->napi); /* b.2.1) It's now safe to remove the napi struct, which must be done * here from process context. */ netif_napi_del(&peer->napi); /* Ensure any workstructs we own (like transmit_handshake_work or * clear_peer_work) no longer are in use. */ flush_workqueue(peer->device->handshake_send_wq); /* After the above flushes, a peer might still be active in a few * different contexts: 1) from xmit(), before hitting is_dead and * returning, 2) from wg_packet_consume_data(), before hitting is_dead * and returning, 3) from wg_receive_handshake_packet() after a point * where it has processed an incoming handshake packet, but where * all calls to pass it off to timers fails because of is_dead. We won't * have new references in (1) eventually, because we're removed from * allowedips; we won't have new references in (2) eventually, because * wg_index_hashtable_lookup will always return NULL, since we removed * all existing keypairs and no more can be created; we won't have new * references in (3) eventually, because we're removed from the pubkey * hash table, which allows for a maximum of one handshake response, * via the still-uncleared index hashtable entry, but not more than one, * and in wg_cookie_message_consume, the lookup eventually gets a peer * with a refcount of zero, so no new reference is taken. */ --peer->device->num_peers; wg_peer_put(peer); } /* We have a separate "remove" function make sure that all active places where * a peer is currently operating will eventually come to an end and not pass * their reference onto another context. */ void wg_peer_remove(struct wg_peer *peer) { if (unlikely(!peer)) return; lockdep_assert_held(&peer->device->device_update_lock); peer_make_dead(peer); synchronize_net(); peer_remove_after_dead(peer); } void wg_peer_remove_all(struct wg_device *wg) { struct wg_peer *peer, *temp; LIST_HEAD(dead_peers); lockdep_assert_held(&wg->device_update_lock); /* Avoid having to traverse individually for each one. */ wg_allowedips_free(&wg->peer_allowedips, &wg->device_update_lock); list_for_each_entry_safe(peer, temp, &wg->peer_list, peer_list) { peer_make_dead(peer); list_add_tail(&peer->peer_list, &dead_peers); } synchronize_net(); list_for_each_entry_safe(peer, temp, &dead_peers, peer_list) peer_remove_after_dead(peer); } static void rcu_release(struct rcu_head *rcu) { struct wg_peer *peer = container_of(rcu, struct wg_peer, rcu); dst_cache_destroy(&peer->endpoint_cache); WARN_ON(wg_prev_queue_peek(&peer->tx_queue) || wg_prev_queue_peek(&peer->rx_queue)); /* The final zeroing takes care of clearing any remaining handshake key * material and other potentially sensitive information. */ memzero_explicit(peer, sizeof(*peer)); kmem_cache_free(peer_cache, peer); } static void kref_release(struct kref *refcount) { struct wg_peer *peer = container_of(refcount, struct wg_peer, refcount); pr_debug("%s: Peer %llu (%pISpfsc) destroyed\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); /* Remove ourself from dynamic runtime lookup structures, now that the * last reference is gone. */ wg_index_hashtable_remove(peer->device->index_hashtable, &peer->handshake.entry); /* Remove any lingering packets that didn't have a chance to be * transmitted. */ wg_packet_purge_staged_packets(peer); /* Free the memory used. */ call_rcu(&peer->rcu, rcu_release); } void wg_peer_put(struct wg_peer *peer) { if (unlikely(!peer)) return; kref_put(&peer->refcount, kref_release); } int __init wg_peer_init(void) { peer_cache = KMEM_CACHE(wg_peer, 0); return peer_cache ? 0 : -ENOMEM; } void wg_peer_uninit(void) { kmem_cache_destroy(peer_cache); } |
| 27 117 188 74 390 111 301 303 19 18 1 4 14 46 46 31 61 65 62 62 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> */ #ifndef _NET_IPV6_H #define _NET_IPV6_H #include <linux/ipv6.h> #include <linux/hardirq.h> #include <linux/jhash.h> #include <linux/refcount.h> #include <linux/jump_label_ratelimit.h> #include <net/if_inet6.h> #include <net/ndisc.h> #include <net/flow.h> #include <net/flow_dissector.h> #include <net/snmp.h> #include <net/netns/hash.h> #define SIN6_LEN_RFC2133 24 #define IPV6_MAXPLEN 65535 /* * NextHeader field of IPv6 header */ #define NEXTHDR_HOP 0 /* Hop-by-hop option header. */ #define NEXTHDR_TCP 6 /* TCP segment. */ #define NEXTHDR_UDP 17 /* UDP message. */ #define NEXTHDR_IPV6 41 /* IPv6 in IPv6 */ #define NEXTHDR_ROUTING 43 /* Routing header. */ #define NEXTHDR_FRAGMENT 44 /* Fragmentation/reassembly header. */ #define NEXTHDR_GRE 47 /* GRE header. */ #define NEXTHDR_ESP 50 /* Encapsulating security payload. */ #define NEXTHDR_AUTH 51 /* Authentication header. */ #define NEXTHDR_ICMP 58 /* ICMP for IPv6. */ #define NEXTHDR_NONE 59 /* No next header */ #define NEXTHDR_DEST 60 /* Destination options header. */ #define NEXTHDR_SCTP 132 /* SCTP message. */ #define NEXTHDR_MOBILITY 135 /* Mobility header. */ #define NEXTHDR_MAX 255 #define IPV6_DEFAULT_HOPLIMIT 64 #define IPV6_DEFAULT_MCASTHOPS 1 /* Limits on Hop-by-Hop and Destination options. * * Per RFC8200 there is no limit on the maximum number or lengths of options in * Hop-by-Hop or Destination options other then the packet must fit in an MTU. * We allow configurable limits in order to mitigate potential denial of * service attacks. * * There are three limits that may be set: * - Limit the number of options in a Hop-by-Hop or Destination options * extension header * - Limit the byte length of a Hop-by-Hop or Destination options extension * header * - Disallow unknown options * * The limits are expressed in corresponding sysctls: * * ipv6.sysctl.max_dst_opts_cnt * ipv6.sysctl.max_hbh_opts_cnt * ipv6.sysctl.max_dst_opts_len * ipv6.sysctl.max_hbh_opts_len * * max_*_opts_cnt is the number of TLVs that are allowed for Destination * options or Hop-by-Hop options. If the number is less than zero then unknown * TLVs are disallowed and the number of known options that are allowed is the * absolute value. Setting the value to INT_MAX indicates no limit. * * max_*_opts_len is the length limit in bytes of a Destination or * Hop-by-Hop options extension header. Setting the value to INT_MAX * indicates no length limit. * * If a limit is exceeded when processing an extension header the packet is * silently discarded. */ /* Default limits for Hop-by-Hop and Destination options */ #define IP6_DEFAULT_MAX_DST_OPTS_CNT 8 #define IP6_DEFAULT_MAX_HBH_OPTS_CNT 8 #define IP6_DEFAULT_MAX_DST_OPTS_LEN INT_MAX /* No limit */ #define IP6_DEFAULT_MAX_HBH_OPTS_LEN INT_MAX /* No limit */ /* * Addr type * * type - unicast | multicast * scope - local | site | global * v4 - compat * v4mapped * any * loopback */ #define IPV6_ADDR_ANY 0x0000U #define IPV6_ADDR_UNICAST 0x0001U #define IPV6_ADDR_MULTICAST 0x0002U #define IPV6_ADDR_LOOPBACK 0x0010U #define IPV6_ADDR_LINKLOCAL 0x0020U #define IPV6_ADDR_SITELOCAL 0x0040U #define IPV6_ADDR_COMPATv4 0x0080U #define IPV6_ADDR_SCOPE_MASK 0x00f0U #define IPV6_ADDR_MAPPED 0x1000U /* * Addr scopes */ #define IPV6_ADDR_MC_SCOPE(a) \ ((a)->s6_addr[1] & 0x0f) /* nonstandard */ #define __IPV6_ADDR_SCOPE_INVALID -1 #define IPV6_ADDR_SCOPE_NODELOCAL 0x01 #define IPV6_ADDR_SCOPE_LINKLOCAL 0x02 #define IPV6_ADDR_SCOPE_SITELOCAL 0x05 #define IPV6_ADDR_SCOPE_ORGLOCAL 0x08 #define IPV6_ADDR_SCOPE_GLOBAL 0x0e /* * Addr flags */ #define IPV6_ADDR_MC_FLAG_TRANSIENT(a) \ ((a)->s6_addr[1] & 0x10) #define IPV6_ADDR_MC_FLAG_PREFIX(a) \ ((a)->s6_addr[1] & 0x20) #define IPV6_ADDR_MC_FLAG_RENDEZVOUS(a) \ ((a)->s6_addr[1] & 0x40) /* * fragmentation header */ struct frag_hdr { __u8 nexthdr; __u8 reserved; __be16 frag_off; __be32 identification; }; #define IP6_MF 0x0001 #define IP6_OFFSET 0xFFF8 struct ip6_fraglist_iter { struct ipv6hdr *tmp_hdr; struct sk_buff *frag; int offset; unsigned int hlen; __be32 frag_id; u8 nexthdr; }; int ip6_fraglist_init(struct sk_buff *skb, unsigned int hlen, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_fraglist_iter *iter); void ip6_fraglist_prepare(struct sk_buff *skb, struct ip6_fraglist_iter *iter); static inline struct sk_buff *ip6_fraglist_next(struct ip6_fraglist_iter *iter) { struct sk_buff *skb = iter->frag; iter->frag = skb->next; skb_mark_not_on_list(skb); return skb; } struct ip6_frag_state { u8 *prevhdr; unsigned int hlen; unsigned int mtu; unsigned int left; int offset; int ptr; int hroom; int troom; __be32 frag_id; u8 nexthdr; }; void ip6_frag_init(struct sk_buff *skb, unsigned int hlen, unsigned int mtu, unsigned short needed_tailroom, int hdr_room, u8 *prevhdr, u8 nexthdr, __be32 frag_id, struct ip6_frag_state *state); struct sk_buff *ip6_frag_next(struct sk_buff *skb, struct ip6_frag_state *state); #define IP6_REPLY_MARK(net, mark) \ ((net)->ipv6.sysctl.fwmark_reflect ? (mark) : 0) #include <net/sock.h> /* sysctls */ extern int sysctl_mld_max_msf; extern int sysctl_mld_qrv; #define _DEVINC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_INC_STATS64((_idev)->stats.statname, (field));\ mod##SNMP_INC_STATS64((net)->mib.statname##_statistics, (field));\ }) /* per device counters are atomic_long_t */ #define _DEVINCATOMIC(net, statname, mod, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ mod##SNMP_INC_STATS((net)->mib.statname##_statistics, (field));\ }) /* per device and per net counters are atomic_long_t */ #define _DEVINC_ATOMIC_ATOMIC(net, statname, idev, field) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ SNMP_INC_STATS_ATOMIC_LONG((_idev)->stats.statname##dev, (field)); \ SNMP_INC_STATS_ATOMIC_LONG((net)->mib.statname##_statistics, (field));\ }) #define _DEVADD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_ADD_STATS((_idev)->stats.statname, (field), (val)); \ mod##SNMP_ADD_STATS((net)->mib.statname##_statistics, (field), (val));\ }) #define _DEVUPD(net, statname, mod, idev, field, val) \ ({ \ struct inet6_dev *_idev = (idev); \ if (likely(_idev != NULL)) \ mod##SNMP_UPD_PO_STATS((_idev)->stats.statname, field, (val)); \ mod##SNMP_UPD_PO_STATS((net)->mib.statname##_statistics, field, (val));\ }) /* MIBs */ #define IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, , idev, field) #define __IP6_INC_STATS(net, idev,field) \ _DEVINC(net, ipv6, __, idev, field) #define IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, , idev, field, val) #define __IP6_ADD_STATS(net, idev,field,val) \ _DEVADD(net, ipv6, __, idev, field, val) #define IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, , idev, field, val) #define __IP6_UPD_PO_STATS(net, idev,field,val) \ _DEVUPD(net, ipv6, __, idev, field, val) #define ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, , idev, field) #define __ICMP6_INC_STATS(net, idev, field) \ _DEVINCATOMIC(net, icmpv6, __, idev, field) #define ICMP6MSGOUT_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field +256) #define ICMP6MSGIN_INC_STATS(net, idev, field) \ _DEVINC_ATOMIC_ATOMIC(net, icmpv6msg, idev, field) struct ip6_ra_chain { struct ip6_ra_chain *next; struct sock *sk; int sel; void (*destructor)(struct sock *); }; extern struct ip6_ra_chain *ip6_ra_chain; extern rwlock_t ip6_ra_lock; /* This structure is prepared by protocol, when parsing ancillary data and passed to IPv6. */ struct ipv6_txoptions { refcount_t refcnt; /* Length of this structure */ int tot_len; /* length of extension headers */ __u16 opt_flen; /* after fragment hdr */ __u16 opt_nflen; /* before fragment hdr */ struct ipv6_opt_hdr *hopopt; struct ipv6_opt_hdr *dst0opt; struct ipv6_rt_hdr *srcrt; /* Routing Header */ struct ipv6_opt_hdr *dst1opt; struct rcu_head rcu; /* Option buffer, as read by IPV6_PKTOPTIONS, starts here. */ }; /* flowlabel_reflect sysctl values */ enum flowlabel_reflect { FLOWLABEL_REFLECT_ESTABLISHED = 1, FLOWLABEL_REFLECT_TCP_RESET = 2, FLOWLABEL_REFLECT_ICMPV6_ECHO_REPLIES = 4, }; struct ip6_flowlabel { struct ip6_flowlabel __rcu *next; __be32 label; atomic_t users; struct in6_addr dst; struct ipv6_txoptions *opt; unsigned long linger; struct rcu_head rcu; u8 share; union { struct pid *pid; kuid_t uid; } owner; unsigned long lastuse; unsigned long expires; struct net *fl_net; }; #define IPV6_FLOWINFO_MASK cpu_to_be32(0x0FFFFFFF) #define IPV6_FLOWLABEL_MASK cpu_to_be32(0x000FFFFF) #define IPV6_FLOWLABEL_STATELESS_FLAG cpu_to_be32(0x00080000) #define IPV6_TCLASS_MASK (IPV6_FLOWINFO_MASK & ~IPV6_FLOWLABEL_MASK) #define IPV6_TCLASS_SHIFT 20 struct ipv6_fl_socklist { struct ipv6_fl_socklist __rcu *next; struct ip6_flowlabel *fl; struct rcu_head rcu; }; struct ipcm6_cookie { struct sockcm_cookie sockc; __s16 hlimit; __s16 tclass; __s8 dontfrag; struct ipv6_txoptions *opt; __u16 gso_size; }; static inline void ipcm6_init(struct ipcm6_cookie *ipc6) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = -1, .dontfrag = -1, }; } static inline void ipcm6_init_sk(struct ipcm6_cookie *ipc6, const struct ipv6_pinfo *np) { *ipc6 = (struct ipcm6_cookie) { .hlimit = -1, .tclass = np->tclass, .dontfrag = np->dontfrag, }; } static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) { struct ipv6_txoptions *opt; rcu_read_lock(); opt = rcu_dereference(np->opt); if (opt) { if (!refcount_inc_not_zero(&opt->refcnt)) opt = NULL; else opt = rcu_pointer_handoff(opt); } rcu_read_unlock(); return opt; } static inline void txopt_put(struct ipv6_txoptions *opt) { if (opt && refcount_dec_and_test(&opt->refcnt)) kfree_rcu(opt, rcu); } struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label); extern struct static_key_false_deferred ipv6_flowlabel_exclusive; static inline struct ip6_flowlabel *fl6_sock_lookup(struct sock *sk, __be32 label) { if (static_branch_unlikely(&ipv6_flowlabel_exclusive.key)) return __fl6_sock_lookup(sk, label) ? : ERR_PTR(-ENOENT); return NULL; } struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt); void fl6_free_socklist(struct sock *sk); int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen); int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags); int ip6_flowlabel_init(void); void ip6_flowlabel_cleanup(void); bool ip6_autoflowlabel(struct net *net, const struct ipv6_pinfo *np); static inline void fl6_sock_release(struct ip6_flowlabel *fl) { if (fl) atomic_dec(&fl->users); } void icmpv6_notify(struct sk_buff *skb, u8 type, u8 code, __be32 info); void icmpv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct icmp6hdr *thdr, int len); int ip6_ra_control(struct sock *sk, int sel); int ipv6_parse_hopopts(struct sk_buff *skb); struct ipv6_txoptions *ipv6_dup_options(struct sock *sk, struct ipv6_txoptions *opt); struct ipv6_txoptions *ipv6_renew_options(struct sock *sk, struct ipv6_txoptions *opt, int newtype, struct ipv6_opt_hdr *newopt); struct ipv6_txoptions *ipv6_fixup_options(struct ipv6_txoptions *opt_space, struct ipv6_txoptions *opt); bool ipv6_opt_accepted(const struct sock *sk, const struct sk_buff *skb, const struct inet6_skb_parm *opt); struct ipv6_txoptions *ipv6_update_options(struct sock *sk, struct ipv6_txoptions *opt); static inline bool ipv6_accept_ra(struct inet6_dev *idev) { /* If forwarding is enabled, RA are not accepted unless the special * hybrid mode (accept_ra=2) is enabled. */ return idev->cnf.forwarding ? idev->cnf.accept_ra == 2 : idev->cnf.accept_ra; } #define IPV6_FRAG_HIGH_THRESH (4 * 1024*1024) /* 4194304 */ #define IPV6_FRAG_LOW_THRESH (3 * 1024*1024) /* 3145728 */ #define IPV6_FRAG_TIMEOUT (60 * HZ) /* 60 seconds */ int __ipv6_addr_type(const struct in6_addr *addr); static inline int ipv6_addr_type(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & 0xffff; } static inline int ipv6_addr_scope(const struct in6_addr *addr) { return __ipv6_addr_type(addr) & IPV6_ADDR_SCOPE_MASK; } static inline int __ipv6_addr_src_scope(int type) { return (type == IPV6_ADDR_ANY) ? __IPV6_ADDR_SCOPE_INVALID : (type >> 16); } static inline int ipv6_addr_src_scope(const struct in6_addr *addr) { return __ipv6_addr_src_scope(__ipv6_addr_type(addr)); } static inline bool __ipv6_addr_needs_scope_id(int type) { return type & IPV6_ADDR_LINKLOCAL || (type & IPV6_ADDR_MULTICAST && (type & (IPV6_ADDR_LOOPBACK|IPV6_ADDR_LINKLOCAL))); } static inline __u32 ipv6_iface_scope_id(const struct in6_addr *addr, int iface) { return __ipv6_addr_needs_scope_id(__ipv6_addr_type(addr)) ? iface : 0; } static inline int ipv6_addr_cmp(const struct in6_addr *a1, const struct in6_addr *a2) { return memcmp(a1, a2, sizeof(struct in6_addr)); } static inline bool ipv6_masked_addr_cmp(const struct in6_addr *a1, const struct in6_addr *m, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ulm = (const unsigned long *)m; const unsigned long *ul2 = (const unsigned long *)a2; return !!(((ul1[0] ^ ul2[0]) & ulm[0]) | ((ul1[1] ^ ul2[1]) & ulm[1])); #else return !!(((a1->s6_addr32[0] ^ a2->s6_addr32[0]) & m->s6_addr32[0]) | ((a1->s6_addr32[1] ^ a2->s6_addr32[1]) & m->s6_addr32[1]) | ((a1->s6_addr32[2] ^ a2->s6_addr32[2]) & m->s6_addr32[2]) | ((a1->s6_addr32[3] ^ a2->s6_addr32[3]) & m->s6_addr32[3])); #endif } static inline void ipv6_addr_prefix(struct in6_addr *pfx, const struct in6_addr *addr, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memset(pfx->s6_addr, 0, sizeof(pfx->s6_addr)); memcpy(pfx->s6_addr, addr, o); if (b != 0) pfx->s6_addr[o] = addr->s6_addr[o] & (0xff00 >> b); } static inline void ipv6_addr_prefix_copy(struct in6_addr *addr, const struct in6_addr *pfx, int plen) { /* caller must guarantee 0 <= plen <= 128 */ int o = plen >> 3, b = plen & 0x7; memcpy(addr->s6_addr, pfx, o); if (b != 0) { addr->s6_addr[o] &= ~(0xff00 >> b); addr->s6_addr[o] |= (pfx->s6_addr[o] & (0xff00 >> b)); } } static inline void __ipv6_addr_set_half(__be32 *addr, __be32 wh, __be32 wl) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 #if defined(__BIG_ENDIAN) if (__builtin_constant_p(wh) && __builtin_constant_p(wl)) { *(__force u64 *)addr = ((__force u64)(wh) << 32 | (__force u64)(wl)); return; } #elif defined(__LITTLE_ENDIAN) if (__builtin_constant_p(wl) && __builtin_constant_p(wh)) { *(__force u64 *)addr = ((__force u64)(wl) << 32 | (__force u64)(wh)); return; } #endif #endif addr[0] = wh; addr[1] = wl; } static inline void ipv6_addr_set(struct in6_addr *addr, __be32 w1, __be32 w2, __be32 w3, __be32 w4) { __ipv6_addr_set_half(&addr->s6_addr32[0], w1, w2); __ipv6_addr_set_half(&addr->s6_addr32[2], w3, w4); } static inline bool ipv6_addr_equal(const struct in6_addr *a1, const struct in6_addr *a2) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul1 = (const unsigned long *)a1; const unsigned long *ul2 = (const unsigned long *)a2; return ((ul1[0] ^ ul2[0]) | (ul1[1] ^ ul2[1])) == 0UL; #else return ((a1->s6_addr32[0] ^ a2->s6_addr32[0]) | (a1->s6_addr32[1] ^ a2->s6_addr32[1]) | (a1->s6_addr32[2] ^ a2->s6_addr32[2]) | (a1->s6_addr32[3] ^ a2->s6_addr32[3])) == 0; #endif } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline bool __ipv6_prefix_equal64_half(const __be64 *a1, const __be64 *a2, unsigned int len) { if (len && ((*a1 ^ *a2) & cpu_to_be64((~0UL) << (64 - len)))) return false; return true; } static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be64 *a1 = (const __be64 *)addr1; const __be64 *a2 = (const __be64 *)addr2; if (prefixlen >= 64) { if (a1[0] ^ a2[0]) return false; return __ipv6_prefix_equal64_half(a1 + 1, a2 + 1, prefixlen - 64); } return __ipv6_prefix_equal64_half(a1, a2, prefixlen); } #else static inline bool ipv6_prefix_equal(const struct in6_addr *addr1, const struct in6_addr *addr2, unsigned int prefixlen) { const __be32 *a1 = addr1->s6_addr32; const __be32 *a2 = addr2->s6_addr32; unsigned int pdw, pbi; /* check complete u32 in prefix */ pdw = prefixlen >> 5; if (pdw && memcmp(a1, a2, pdw << 2)) return false; /* check incomplete u32 in prefix */ pbi = prefixlen & 0x1f; if (pbi && ((a1[pdw] ^ a2[pdw]) & htonl((0xffffffff) << (32 - pbi)))) return false; return true; } #endif static inline bool ipv6_addr_any(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; return (ul[0] | ul[1]) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | a->s6_addr32[3]) == 0; #endif } static inline u32 ipv6_addr_hash(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const unsigned long *ul = (const unsigned long *)a; unsigned long x = ul[0] ^ ul[1]; return (u32)(x ^ (x >> 32)); #else return (__force u32)(a->s6_addr32[0] ^ a->s6_addr32[1] ^ a->s6_addr32[2] ^ a->s6_addr32[3]); #endif } /* more secured version of ipv6_addr_hash() */ static inline u32 __ipv6_addr_jhash(const struct in6_addr *a, const u32 initval) { return jhash2((__force const u32 *)a->s6_addr32, ARRAY_SIZE(a->s6_addr32), initval); } static inline bool ipv6_addr_loopback(const struct in6_addr *a) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 const __be64 *be = (const __be64 *)a; return (be[0] | (be[1] ^ cpu_to_be64(1))) == 0UL; #else return (a->s6_addr32[0] | a->s6_addr32[1] | a->s6_addr32[2] | (a->s6_addr32[3] ^ cpu_to_be32(1))) == 0; #endif } /* * Note that we must __force cast these to unsigned long to make sparse happy, * since all of the endian-annotated types are fixed size regardless of arch. */ static inline bool ipv6_addr_v4mapped(const struct in6_addr *a) { return ( #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 *(unsigned long *)a | #else (__force unsigned long)(a->s6_addr32[0] | a->s6_addr32[1]) | #endif (__force unsigned long)(a->s6_addr32[2] ^ cpu_to_be32(0x0000ffff))) == 0UL; } static inline u32 ipv6_portaddr_hash(const struct net *net, const struct in6_addr *addr6, unsigned int port) { unsigned int hash, mix = net_hash_mix(net); if (ipv6_addr_any(addr6)) hash = jhash_1word(0, mix); else if (ipv6_addr_v4mapped(addr6)) hash = jhash_1word((__force u32)addr6->s6_addr32[3], mix); else hash = jhash2((__force u32 *)addr6->s6_addr32, 4, mix); return hash ^ port; } /* * Check for a RFC 4843 ORCHID address * (Overlay Routable Cryptographic Hash Identifiers) */ static inline bool ipv6_addr_orchid(const struct in6_addr *a) { return (a->s6_addr32[0] & htonl(0xfffffff0)) == htonl(0x20010010); } static inline bool ipv6_addr_is_multicast(const struct in6_addr *addr) { return (addr->s6_addr32[0] & htonl(0xFF000000)) == htonl(0xFF000000); } static inline void ipv6_addr_set_v4mapped(const __be32 addr, struct in6_addr *v4mapped) { ipv6_addr_set(v4mapped, 0, 0, htonl(0x0000FFFF), addr); } /* * find the first different bit between two addresses * length of address must be a multiple of 32bits */ static inline int __ipv6_addr_diff32(const void *token1, const void *token2, int addrlen) { const __be32 *a1 = token1, *a2 = token2; int i; addrlen >>= 2; for (i = 0; i < addrlen; i++) { __be32 xb = a1[i] ^ a2[i]; if (xb) return i * 32 + 31 - __fls(ntohl(xb)); } /* * we should *never* get to this point since that * would mean the addrs are equal * * However, we do get to it 8) And exacly, when * addresses are equal 8) * * ip route add 1111::/128 via ... * ip route add 1111::/64 via ... * and we are here. * * Ideally, this function should stop comparison * at prefix length. It does not, but it is still OK, * if returned value is greater than prefix length. * --ANK (980803) */ return addrlen << 5; } #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 static inline int __ipv6_addr_diff64(const void *token1, const void *token2, int addrlen) { const __be64 *a1 = token1, *a2 = token2; int i; addrlen >>= 3; for (i = 0; i < addrlen; i++) { __be64 xb = a1[i] ^ a2[i]; if (xb) return i * 64 + 63 - __fls(be64_to_cpu(xb)); } return addrlen << 6; } #endif static inline int __ipv6_addr_diff(const void *token1, const void *token2, int addrlen) { #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && BITS_PER_LONG == 64 if (__builtin_constant_p(addrlen) && !(addrlen & 7)) return __ipv6_addr_diff64(token1, token2, addrlen); #endif return __ipv6_addr_diff32(token1, token2, addrlen); } static inline int ipv6_addr_diff(const struct in6_addr *a1, const struct in6_addr *a2) { return __ipv6_addr_diff(a1, a2, sizeof(struct in6_addr)); } __be32 ipv6_select_ident(struct net *net, const struct in6_addr *daddr, const struct in6_addr *saddr); __be32 ipv6_proxy_select_ident(struct net *net, struct sk_buff *skb); int ip6_dst_hoplimit(struct dst_entry *dst); static inline int ip6_sk_dst_hoplimit(struct ipv6_pinfo *np, struct flowi6 *fl6, struct dst_entry *dst) { int hlimit; if (ipv6_addr_is_multicast(&fl6->daddr)) hlimit = np->mcast_hops; else hlimit = np->hop_limit; if (hlimit < 0) hlimit = ip6_dst_hoplimit(dst); return hlimit; } /* copy IPv6 saddr & daddr to flow_keys, possibly using 64bit load/store * Equivalent to : flow->v6addrs.src = iph->saddr; * flow->v6addrs.dst = iph->daddr; */ static inline void iph_to_flow_copy_v6addrs(struct flow_keys *flow, const struct ipv6hdr *iph) { BUILD_BUG_ON(offsetof(typeof(flow->addrs), v6addrs.dst) != offsetof(typeof(flow->addrs), v6addrs.src) + sizeof(flow->addrs.v6addrs.src)); memcpy(&flow->addrs.v6addrs, &iph->saddr, sizeof(flow->addrs.v6addrs)); flow->control.addr_type = FLOW_DISSECTOR_KEY_IPV6_ADDRS; } #if IS_ENABLED(CONFIG_IPV6) static inline bool ipv6_can_nonlocal_bind(struct net *net, struct inet_sock *inet) { return net->ipv6.sysctl.ip_nonlocal_bind || inet->freebind || inet->transparent; } /* Sysctl settings for net ipv6.auto_flowlabels */ #define IP6_AUTO_FLOW_LABEL_OFF 0 #define IP6_AUTO_FLOW_LABEL_OPTOUT 1 #define IP6_AUTO_FLOW_LABEL_OPTIN 2 #define IP6_AUTO_FLOW_LABEL_FORCED 3 #define IP6_AUTO_FLOW_LABEL_MAX IP6_AUTO_FLOW_LABEL_FORCED #define IP6_DEFAULT_AUTO_FLOW_LABELS IP6_AUTO_FLOW_LABEL_OPTOUT static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { u32 hash; /* @flowlabel may include more than a flow label, eg, the traffic class. * Here we want only the flow label value. */ flowlabel &= IPV6_FLOWLABEL_MASK; if (flowlabel || net->ipv6.sysctl.auto_flowlabels == IP6_AUTO_FLOW_LABEL_OFF || (!autolabel && net->ipv6.sysctl.auto_flowlabels != IP6_AUTO_FLOW_LABEL_FORCED)) return flowlabel; hash = skb_get_hash_flowi6(skb, fl6); /* Since this is being sent on the wire obfuscate hash a bit * to minimize possbility that any useful information to an * attacker is leaked. Only lower 20 bits are relevant. */ hash = rol32(hash, 16); flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; if (net->ipv6.sysctl.flowlabel_state_ranges) flowlabel |= IPV6_FLOWLABEL_STATELESS_FLAG; return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { switch (net->ipv6.sysctl.auto_flowlabels) { case IP6_AUTO_FLOW_LABEL_OFF: case IP6_AUTO_FLOW_LABEL_OPTIN: default: return 0; case IP6_AUTO_FLOW_LABEL_OPTOUT: case IP6_AUTO_FLOW_LABEL_FORCED: return 1; } } #else static inline void ip6_set_txhash(struct sock *sk) { } static inline __be32 ip6_make_flowlabel(struct net *net, struct sk_buff *skb, __be32 flowlabel, bool autolabel, struct flowi6 *fl6) { return flowlabel; } static inline int ip6_default_np_autolabel(struct net *net) { return 0; } #endif #if IS_ENABLED(CONFIG_IPV6) static inline int ip6_multipath_hash_policy(const struct net *net) { return net->ipv6.sysctl.multipath_hash_policy; } #else static inline int ip6_multipath_hash_policy(const struct net *net) { return 0; } #endif /* * Header manipulation */ static inline void ip6_flow_hdr(struct ipv6hdr *hdr, unsigned int tclass, __be32 flowlabel) { *(__be32 *)hdr = htonl(0x60000000 | (tclass << 20)) | flowlabel; } static inline __be32 ip6_flowinfo(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWINFO_MASK; } static inline __be32 ip6_flowlabel(const struct ipv6hdr *hdr) { return *(__be32 *)hdr & IPV6_FLOWLABEL_MASK; } static inline u8 ip6_tclass(__be32 flowinfo) { return ntohl(flowinfo & IPV6_TCLASS_MASK) >> IPV6_TCLASS_SHIFT; } static inline __be32 ip6_make_flowinfo(unsigned int tclass, __be32 flowlabel) { return htonl(tclass << IPV6_TCLASS_SHIFT) | flowlabel; } static inline __be32 flowi6_get_flowlabel(const struct flowi6 *fl6) { return fl6->flowlabel & IPV6_FLOWLABEL_MASK; } /* * Prototypes exported by ipv6 */ /* * rcv function (called from netdevice level) */ int ipv6_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); void ipv6_list_rcv(struct list_head *head, struct packet_type *pt, struct net_device *orig_dev); int ip6_rcv_finish(struct net *net, struct sock *sk, struct sk_buff *skb); /* * upper-layer output functions */ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6, __u32 mark, struct ipv6_txoptions *opt, int tclass, u32 priority); int ip6_find_1stfragopt(struct sk_buff *skb, u8 **nexthdr); int ip6_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags); int ip6_push_pending_frames(struct sock *sk); void ip6_flush_pending_frames(struct sock *sk); int ip6_send_skb(struct sk_buff *skb); struct sk_buff *__ip6_make_skb(struct sock *sk, struct sk_buff_head *queue, struct inet_cork_full *cork, struct inet6_cork *v6_cork); struct sk_buff *ip6_make_skb(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, struct inet_cork_full *cork); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) { return __ip6_make_skb(sk, &sk->sk_write_queue, &inet_sk(sk)->cork, &inet6_sk(sk)->cork); } int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst); struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst, bool connected); struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *orig_dst); /* * skb processing functions */ int ip6_output(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_forward(struct sk_buff *skb); int ip6_input(struct sk_buff *skb); int ip6_mc_input(struct sk_buff *skb); void ip6_protocol_deliver_rcu(struct net *net, struct sk_buff *skb, int nexthdr, bool have_final); int __ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); int ip6_local_out(struct net *net, struct sock *sk, struct sk_buff *skb); /* * Extension header (options) processing */ void ipv6_push_nfrag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto, struct in6_addr **daddr_p, struct in6_addr *saddr); void ipv6_push_frag_opts(struct sk_buff *skb, struct ipv6_txoptions *opt, u8 *proto); int ipv6_skip_exthdr(const struct sk_buff *, int start, u8 *nexthdrp, __be16 *frag_offp); bool ipv6_ext_hdr(u8 nexthdr); enum { IP6_FH_F_FRAG = (1 << 0), IP6_FH_F_AUTH = (1 << 1), IP6_FH_F_SKIP_RH = (1 << 2), }; /* find specified header and get offset to it */ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, int target, unsigned short *fragoff, int *fragflg); int ipv6_find_tlv(const struct sk_buff *skb, int offset, int type); struct in6_addr *fl6_update_dst(struct flowi6 *fl6, const struct ipv6_txoptions *opt, struct in6_addr *orig); /* * socket options (ipv6_sockglue.c) */ int ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); int ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int compat_ipv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen); int compat_ipv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen); int __ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_connect_v6_only(struct sock *sk, struct sockaddr *addr, int addr_len); int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr); void ip6_datagram_release_cb(struct sock *sk); int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len); int ipv6_recv_rxpmtu(struct sock *sk, struct msghdr *msg, int len, int *addr_len); void ipv6_icmp_error(struct sock *sk, struct sk_buff *skb, int err, __be16 port, u32 info, u8 *payload); void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); void inet6_cleanup_sock(struct sock *sk); void inet6_sock_destruct(struct sock *sk); int inet6_release(struct socket *sock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); int inet6_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); int inet6_hash_connect(struct inet_timewait_death_row *death_row, struct sock *sk); /* * reassembly.c */ extern const struct proto_ops inet6_stream_ops; extern const struct proto_ops inet6_dgram_ops; extern const struct proto_ops inet6_sockraw_ops; struct group_source_req; struct group_filter; int ip6_mc_source(int add, int omode, struct sock *sk, struct group_source_req *pgsr); int ip6_mc_msfilter(struct sock *sk, struct group_filter *gsf); int ip6_mc_msfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen); #ifdef CONFIG_PROC_FS int ac6_proc_init(struct net *net); void ac6_proc_exit(struct net *net); int raw6_proc_init(void); void raw6_proc_exit(void); int tcp6_proc_init(struct net *net); void tcp6_proc_exit(struct net *net); int udp6_proc_init(struct net *net); void udp6_proc_exit(struct net *net); int udplite6_proc_init(void); void udplite6_proc_exit(void); int ipv6_misc_proc_init(void); void ipv6_misc_proc_exit(void); int snmp6_register_dev(struct inet6_dev *idev); int snmp6_unregister_dev(struct inet6_dev *idev); #else static inline int ac6_proc_init(struct net *net) { return 0; } static inline void ac6_proc_exit(struct net *net) { } static inline int snmp6_register_dev(struct inet6_dev *idev) { return 0; } static inline int snmp6_unregister_dev(struct inet6_dev *idev) { return 0; } #endif #ifdef CONFIG_SYSCTL struct ctl_table *ipv6_icmp_sysctl_init(struct net *net); struct ctl_table *ipv6_route_sysctl_init(struct net *net); int ipv6_sysctl_register(void); void ipv6_sysctl_unregister(void); #endif int ipv6_sock_mc_join(struct sock *sk, int ifindex, const struct in6_addr *addr); int ipv6_sock_mc_join_ssm(struct sock *sk, int ifindex, const struct in6_addr *addr, unsigned int mode); int ipv6_sock_mc_drop(struct sock *sk, int ifindex, const struct in6_addr *addr); #endif /* _NET_IPV6_H */ |
| 212 213 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * Universal/legacy driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. * * Supports: ISA-compatible 8250/16550 ports * PNP 8250/16550 ports * early_serial_setup() ports * userspace-configurable "phantom" ports * "serial8250" platform devices * serial8250_register_8250_port() ports */ #include <linux/acpi.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/console.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/pm_runtime.h> #include <linux/io.h> #ifdef CONFIG_SPARC #include <linux/sunserialcore.h> #endif #include <asm/irq.h> #include "8250.h" /* * Configuration: * share_irqs - whether we pass IRQF_SHARED to request_irq(). This option * is unsafe when used on edge-triggered interrupts. */ static unsigned int share_irqs = SERIAL8250_SHARE_IRQS; static unsigned int nr_uarts = CONFIG_SERIAL_8250_RUNTIME_UARTS; static struct uart_driver serial8250_reg; static unsigned int skip_txen_test; /* force skip of txen test at init time */ #define PASS_LIMIT 512 #include <asm/serial.h> /* * SERIAL_PORT_DFNS tells us about built-in ports that have no * standard enumeration mechanism. Platforms that can find all * serial ports via mechanisms like ACPI or PCI need not supply it. */ #ifndef SERIAL_PORT_DFNS #define SERIAL_PORT_DFNS #endif static const struct old_serial_port old_serial_port[] = { SERIAL_PORT_DFNS /* defined in asm/serial.h */ }; #define UART_NR CONFIG_SERIAL_8250_NR_UARTS #ifdef CONFIG_SERIAL_8250_RSA #define PORT_RSA_MAX 4 static unsigned long probe_rsa[PORT_RSA_MAX]; static unsigned int probe_rsa_count; #endif /* CONFIG_SERIAL_8250_RSA */ struct irq_info { struct hlist_node node; int irq; spinlock_t lock; /* Protects list not the hash */ struct list_head *head; }; #define NR_IRQ_HASH 32 /* Can be adjusted later */ static struct hlist_head irq_lists[NR_IRQ_HASH]; static DEFINE_MUTEX(hash_mutex); /* Used to walk the hash */ /* * This is the serial driver's interrupt routine. * * Arjan thinks the old way was overly complex, so it got simplified. * Alan disagrees, saying that need the complexity to handle the weird * nature of ISA shared interrupts. (This is a special exception.) * * In order to handle ISA shared interrupts properly, we need to check * that all ports have been serviced, and therefore the ISA interrupt * line has been de-asserted. * * This means we need to loop through all ports. checking that they * don't have an interrupt pending. */ static irqreturn_t serial8250_interrupt(int irq, void *dev_id) { struct irq_info *i = dev_id; struct list_head *l, *end = NULL; int pass_counter = 0, handled = 0; pr_debug("%s(%d): start\n", __func__, irq); spin_lock(&i->lock); l = i->head; do { struct uart_8250_port *up; struct uart_port *port; up = list_entry(l, struct uart_8250_port, list); port = &up->port; if (port->handle_irq(port)) { handled = 1; end = NULL; } else if (end == NULL) end = l; l = l->next; if (l == i->head && pass_counter++ > PASS_LIMIT) break; } while (l != end); spin_unlock(&i->lock); pr_debug("%s(%d): end\n", __func__, irq); return IRQ_RETVAL(handled); } /* * To support ISA shared interrupts, we need to have one interrupt * handler that ensures that the IRQ line has been deasserted * before returning. Failing to do this will result in the IRQ * line being stuck active, and, since ISA irqs are edge triggered, * no more IRQs will be seen. */ static void serial_do_unlink(struct irq_info *i, struct uart_8250_port *up) { spin_lock_irq(&i->lock); if (!list_empty(i->head)) { if (i->head == &up->list) i->head = i->head->next; list_del(&up->list); } else { BUG_ON(i->head != &up->list); i->head = NULL; } spin_unlock_irq(&i->lock); /* List empty so throw away the hash node */ if (i->head == NULL) { hlist_del(&i->node); kfree(i); } } static int serial_link_irq_chain(struct uart_8250_port *up) { struct hlist_head *h; struct hlist_node *n; struct irq_info *i; int ret; mutex_lock(&hash_mutex); h = &irq_lists[up->port.irq % NR_IRQ_HASH]; hlist_for_each(n, h) { i = hlist_entry(n, struct irq_info, node); if (i->irq == up->port.irq) break; } if (n == NULL) { i = kzalloc(sizeof(struct irq_info), GFP_KERNEL); if (i == NULL) { mutex_unlock(&hash_mutex); return -ENOMEM; } spin_lock_init(&i->lock); i->irq = up->port.irq; hlist_add_head(&i->node, h); } mutex_unlock(&hash_mutex); spin_lock_irq(&i->lock); if (i->head) { list_add(&up->list, i->head); spin_unlock_irq(&i->lock); ret = 0; } else { INIT_LIST_HEAD(&up->list); i->head = &up->list; spin_unlock_irq(&i->lock); ret = request_irq(up->port.irq, serial8250_interrupt, up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); } return ret; } static void serial_unlink_irq_chain(struct uart_8250_port *up) { /* * yes, some broken gcc emit "warning: 'i' may be used uninitialized" * but no, we are not going to take a patch that assigns NULL below. */ struct irq_info *i; struct hlist_node *n; struct hlist_head *h; mutex_lock(&hash_mutex); h = &irq_lists[up->port.irq % NR_IRQ_HASH]; hlist_for_each(n, h) { i = hlist_entry(n, struct irq_info, node); if (i->irq == up->port.irq) break; } BUG_ON(n == NULL); BUG_ON(i->head == NULL); if (list_empty(i->head)) free_irq(up->port.irq, i); serial_do_unlink(i, up); mutex_unlock(&hash_mutex); } /* * This function is used to handle ports that do not have an * interrupt. This doesn't work very well for 16450's, but gives * barely passable results for a 16550A. (Although at the expense * of much CPU overhead). */ static void serial8250_timeout(struct timer_list *t) { struct uart_8250_port *up = from_timer(up, t, timer); up->port.handle_irq(&up->port); mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port)); } static void serial8250_backup_timeout(struct timer_list *t) { struct uart_8250_port *up = from_timer(up, t, timer); unsigned int iir, ier = 0, lsr; unsigned long flags; spin_lock_irqsave(&up->port.lock, flags); /* * Must disable interrupts or else we risk racing with the interrupt * based handler. */ if (up->port.irq) { ier = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); } iir = serial_in(up, UART_IIR); /* * This should be a safe test for anyone who doesn't trust the * IIR bits on their UART, but it's specifically designed for * the "Diva" UART used on the management processor on many HP * ia64 and parisc boxes. */ lsr = serial_in(up, UART_LSR); up->lsr_saved_flags |= lsr & LSR_SAVE_FLAGS; if ((iir & UART_IIR_NO_INT) && (up->ier & UART_IER_THRI) && (!uart_circ_empty(&up->port.state->xmit) || up->port.x_char) && (lsr & UART_LSR_THRE)) { iir &= ~(UART_IIR_ID | UART_IIR_NO_INT); iir |= UART_IIR_THRI; } if (!(iir & UART_IIR_NO_INT)) serial8250_tx_chars(up); if (up->port.irq) serial_out(up, UART_IER, ier); spin_unlock_irqrestore(&up->port.lock, flags); /* Standard timer interval plus 0.2s to keep the port running */ mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port) + HZ / 5); } static int univ8250_setup_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; int retval = 0; /* * The above check will only give an accurate result the first time * the port is opened so this value needs to be preserved. */ if (up->bugs & UART_BUG_THRE) { pr_debug("%s - using backup timer\n", port->name); up->timer.function = serial8250_backup_timeout; mod_timer(&up->timer, jiffies + uart_poll_timeout(port) + HZ / 5); } /* * If the "interrupt" for this port doesn't correspond with any * hardware interrupt, we use a timer-based system. The original * driver used to do this with IRQ0. */ if (!port->irq) { mod_timer(&up->timer, jiffies + uart_poll_timeout(port)); } else retval = serial_link_irq_chain(up); return retval; } static void univ8250_release_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; del_timer_sync(&up->timer); up->timer.function = serial8250_timeout; if (port->irq) serial_unlink_irq_chain(up); } #ifdef CONFIG_SERIAL_8250_RSA static int serial8250_request_rsa_resource(struct uart_8250_port *up) { unsigned long start = UART_RSA_BASE << up->port.regshift; unsigned int size = 8 << up->port.regshift; struct uart_port *port = &up->port; int ret = -EINVAL; switch (port->iotype) { case UPIO_HUB6: case UPIO_PORT: start += port->iobase; if (request_region(start, size, "serial-rsa")) ret = 0; else ret = -EBUSY; break; } return ret; } static void serial8250_release_rsa_resource(struct uart_8250_port *up) { unsigned long offset = UART_RSA_BASE << up->port.regshift; unsigned int size = 8 << up->port.regshift; struct uart_port *port = &up->port; switch (port->iotype) { case UPIO_HUB6: case UPIO_PORT: release_region(port->iobase + offset, size); break; } } #endif static const struct uart_ops *base_ops; static struct uart_ops univ8250_port_ops; static const struct uart_8250_ops univ8250_driver_ops = { .setup_irq = univ8250_setup_irq, .release_irq = univ8250_release_irq, }; static struct uart_8250_port serial8250_ports[UART_NR]; /** * serial8250_get_port - retrieve struct uart_8250_port * @line: serial line number * * This function retrieves struct uart_8250_port for the specific line. * This struct *must* *not* be used to perform a 8250 or serial core operation * which is not accessible otherwise. Its only purpose is to make the struct * accessible to the runtime-pm callbacks for context suspend/restore. * The lock assumption made here is none because runtime-pm suspend/resume * callbacks should not be invoked if there is any operation performed on the * port. */ struct uart_8250_port *serial8250_get_port(int line) { return &serial8250_ports[line]; } EXPORT_SYMBOL_GPL(serial8250_get_port); static void (*serial8250_isa_config)(int port, struct uart_port *up, u32 *capabilities); void serial8250_set_isa_configurator( void (*v)(int port, struct uart_port *up, u32 *capabilities)) { serial8250_isa_config = v; } EXPORT_SYMBOL(serial8250_set_isa_configurator); #ifdef CONFIG_SERIAL_8250_RSA static void univ8250_config_port(struct uart_port *port, int flags) { struct uart_8250_port *up = up_to_u8250p(port); up->probe &= ~UART_PROBE_RSA; if (port->type == PORT_RSA) { if (serial8250_request_rsa_resource(up) == 0) up->probe |= UART_PROBE_RSA; } else if (flags & UART_CONFIG_TYPE) { int i; for (i = 0; i < probe_rsa_count; i++) { if (probe_rsa[i] == up->port.iobase) { if (serial8250_request_rsa_resource(up) == 0) up->probe |= UART_PROBE_RSA; break; } } } base_ops->config_port(port, flags); if (port->type != PORT_RSA && up->probe & UART_PROBE_RSA) serial8250_release_rsa_resource(up); } static int univ8250_request_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); int ret; ret = base_ops->request_port(port); if (ret == 0 && port->type == PORT_RSA) { ret = serial8250_request_rsa_resource(up); if (ret < 0) base_ops->release_port(port); } return ret; } static void univ8250_release_port(struct uart_port *port) { struct uart_8250_port *up = up_to_u8250p(port); if (port->type == PORT_RSA) serial8250_release_rsa_resource(up); base_ops->release_port(port); } static void univ8250_rsa_support(struct uart_ops *ops) { ops->config_port = univ8250_config_port; ops->request_port = univ8250_request_port; ops->release_port = univ8250_release_port; } #else #define univ8250_rsa_support(x) do { } while (0) #endif /* CONFIG_SERIAL_8250_RSA */ static inline void serial8250_apply_quirks(struct uart_8250_port *up) { up->port.quirks |= skip_txen_test ? UPQ_NO_TXEN_TEST : 0; } static void __init serial8250_isa_init_ports(void) { struct uart_8250_port *up; static int first = 1; int i, irqflag = 0; if (!first) return; first = 0; if (nr_uarts > UART_NR) nr_uarts = UART_NR; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; struct uart_port *port = &up->port; port->line = i; serial8250_init_port(up); if (!base_ops) base_ops = port->ops; port->ops = &univ8250_port_ops; timer_setup(&up->timer, serial8250_timeout, 0); up->ops = &univ8250_driver_ops; /* * ALPHA_KLUDGE_MCR needs to be killed. */ up->mcr_mask = ~ALPHA_KLUDGE_MCR; up->mcr_force = ALPHA_KLUDGE_MCR; serial8250_set_defaults(up); } /* chain base port ops to support Remote Supervisor Adapter */ univ8250_port_ops = *base_ops; univ8250_rsa_support(&univ8250_port_ops); if (share_irqs) irqflag = IRQF_SHARED; for (i = 0, up = serial8250_ports; i < ARRAY_SIZE(old_serial_port) && i < nr_uarts; i++, up++) { struct uart_port *port = &up->port; port->iobase = old_serial_port[i].port; port->irq = irq_canonicalize(old_serial_port[i].irq); port->irqflags = 0; port->uartclk = old_serial_port[i].baud_base * 16; port->flags = old_serial_port[i].flags; port->hub6 = 0; port->membase = old_serial_port[i].iomem_base; port->iotype = old_serial_port[i].io_type; port->regshift = old_serial_port[i].iomem_reg_shift; port->irqflags |= irqflag; if (serial8250_isa_config != NULL) serial8250_isa_config(i, &up->port, &up->capabilities); } } static void __init serial8250_register_ports(struct uart_driver *drv, struct device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type == PORT_8250_CIR) continue; if (up->port.dev) continue; up->port.dev = dev; serial8250_apply_quirks(up); uart_add_one_port(drv, &up->port); } } #ifdef CONFIG_SERIAL_8250_CONSOLE static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { struct uart_8250_port *up = &serial8250_ports[co->index]; serial8250_console_write(up, s, count); } static int univ8250_console_setup(struct console *co, char *options) { struct uart_port *port; int retval; /* * Check whether an invalid uart number has been specified, and * if so, search for the first available port that does have * console support. */ if (co->index >= nr_uarts) co->index = 0; port = &serial8250_ports[co->index].port; /* link port to console */ port->cons = co; retval = serial8250_console_setup(port, options, false); if (retval != 0) port->cons = NULL; return retval; } /** * univ8250_console_match - non-standard console matching * @co: registering console * @name: name from console command line * @idx: index from console command line * @options: ptr to option string from console command line * * Only attempts to match console command lines of the form: * console=uart[8250],io|mmio|mmio16|mmio32,<addr>[,<options>] * console=uart[8250],0x<addr>[,<options>] * This form is used to register an initial earlycon boot console and * replace it with the serial8250_console at 8250 driver init. * * Performs console setup for a match (as required by interface) * If no <options> are specified, then assume the h/w is already setup. * * Returns 0 if console matches; otherwise non-zero to use default matching */ static int univ8250_console_match(struct console *co, char *name, int idx, char *options) { char match[] = "uart"; /* 8250-specific earlycon name */ unsigned char iotype; resource_size_t addr; int i; if (strncmp(name, match, 4) != 0) return -ENODEV; if (uart_parse_earlycon(options, &iotype, &addr, &options)) return -ENODEV; /* try to match the port specified on the command line */ for (i = 0; i < nr_uarts; i++) { struct uart_port *port = &serial8250_ports[i].port; if (port->iotype != iotype) continue; if ((iotype == UPIO_MEM || iotype == UPIO_MEM16 || iotype == UPIO_MEM32 || iotype == UPIO_MEM32BE) && (port->mapbase != addr)) continue; if (iotype == UPIO_PORT && port->iobase != addr) continue; co->index = i; port->cons = co; return serial8250_console_setup(port, options, true); } return -ENODEV; } static struct console univ8250_console = { .name = "ttyS", .write = univ8250_console_write, .device = uart_console_device, .setup = univ8250_console_setup, .match = univ8250_console_match, .flags = CON_PRINTBUFFER | CON_ANYTIME, .index = -1, .data = &serial8250_reg, }; static int __init univ8250_console_init(void) { if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); register_console(&univ8250_console); return 0; } console_initcall(univ8250_console_init); #define SERIAL8250_CONSOLE (&univ8250_console) #else #define SERIAL8250_CONSOLE NULL #endif static struct uart_driver serial8250_reg = { .owner = THIS_MODULE, .driver_name = "serial", .dev_name = "ttyS", .major = TTY_MAJOR, .minor = 64, .cons = SERIAL8250_CONSOLE, }; /* * early_serial_setup - early registration for 8250 ports * * Setup an 8250 port structure prior to console initialisation. Use * after console initialisation will cause undefined behaviour. */ int __init early_serial_setup(struct uart_port *port) { struct uart_port *p; if (port->line >= ARRAY_SIZE(serial8250_ports) || nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); p = &serial8250_ports[port->line].port; p->iobase = port->iobase; p->membase = port->membase; p->irq = port->irq; p->irqflags = port->irqflags; p->uartclk = port->uartclk; p->fifosize = port->fifosize; p->regshift = port->regshift; p->iotype = port->iotype; p->flags = port->flags; p->mapbase = port->mapbase; p->mapsize = port->mapsize; p->private_data = port->private_data; p->type = port->type; p->line = port->line; serial8250_set_defaults(up_to_u8250p(p)); if (port->serial_in) p->serial_in = port->serial_in; if (port->serial_out) p->serial_out = port->serial_out; if (port->handle_irq) p->handle_irq = port->handle_irq; return 0; } /** * serial8250_suspend_port - suspend one serial port * @line: serial line number * * Suspend one serial port. */ void serial8250_suspend_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; if (!console_suspend_enabled && uart_console(port) && port->type != PORT_8250) { unsigned char canary = 0xa5; serial_out(up, UART_SCR, canary); if (serial_in(up, UART_SCR) == canary) up->canary = canary; } uart_suspend_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_suspend_port); /** * serial8250_resume_port - resume one serial port * @line: serial line number * * Resume one serial port. */ void serial8250_resume_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; up->canary = 0; if (up->capabilities & UART_NATSEMI) { /* Ensure it's still in high speed mode */ serial_port_out(port, UART_LCR, 0xE0); ns16550a_goto_highspeed(up); serial_port_out(port, UART_LCR, 0); port->uartclk = 921600*16; } uart_resume_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_resume_port); /* * Register a set of serial devices attached to a platform device. The * list is terminated with a zero flags entry, which means we expect * all entries to have at least UPF_BOOT_AUTOCONF set. */ static int serial8250_probe(struct platform_device *dev) { struct plat_serial8250_port *p = dev_get_platdata(&dev->dev); struct uart_8250_port uart; int ret, i, irqflag = 0; memset(&uart, 0, sizeof(uart)); if (share_irqs) irqflag = IRQF_SHARED; for (i = 0; p && p->flags != 0; p++, i++) { uart.port.iobase = p->iobase; uart.port.membase = p->membase; uart.port.irq = p->irq; uart.port.irqflags = p->irqflags; uart.port.uartclk = p->uartclk; uart.port.regshift = p->regshift; uart.port.iotype = p->iotype; uart.port.flags = p->flags; uart.port.mapbase = p->mapbase; uart.port.hub6 = p->hub6; uart.port.private_data = p->private_data; uart.port.type = p->type; uart.port.serial_in = p->serial_in; uart.port.serial_out = p->serial_out; uart.port.handle_irq = p->handle_irq; uart.port.handle_break = p->handle_break; uart.port.set_termios = p->set_termios; uart.port.set_ldisc = p->set_ldisc; uart.port.get_mctrl = p->get_mctrl; uart.port.pm = p->pm; uart.port.dev = &dev->dev; uart.port.irqflags |= irqflag; ret = serial8250_register_8250_port(&uart); if (ret < 0) { dev_err(&dev->dev, "unable to register port at index %d " "(IO%lx MEM%llx IRQ%d): %d\n", i, p->iobase, (unsigned long long)p->mapbase, p->irq, ret); } } return 0; } /* * Remove serial ports registered against a platform device. */ static int serial8250_remove(struct platform_device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.dev == &dev->dev) serial8250_unregister_port(i); } return 0; } static int serial8250_suspend(struct platform_device *dev, pm_message_t state) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) uart_suspend_port(&serial8250_reg, &up->port); } return 0; } static int serial8250_resume(struct platform_device *dev) { int i; for (i = 0; i < UART_NR; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type != PORT_UNKNOWN && up->port.dev == &dev->dev) serial8250_resume_port(i); } return 0; } static struct platform_driver serial8250_isa_driver = { .probe = serial8250_probe, .remove = serial8250_remove, .suspend = serial8250_suspend, .resume = serial8250_resume, .driver = { .name = "serial8250", }, }; /* * This "device" covers _all_ ISA 8250-compatible serial devices listed * in the table in include/asm/serial.h */ static struct platform_device *serial8250_isa_devs; /* * serial8250_register_8250_port and serial8250_unregister_port allows for * 16x50 serial ports to be configured at run-time, to support PCMCIA * modems and PCI multiport cards. */ static DEFINE_MUTEX(serial_mutex); static struct uart_8250_port *serial8250_find_match_or_unused(struct uart_port *port) { int i; /* * First, find a port entry which matches. */ for (i = 0; i < nr_uarts; i++) if (uart_match_port(&serial8250_ports[i].port, port)) return &serial8250_ports[i]; /* try line number first if still available */ i = port->line; if (i < nr_uarts && serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * We didn't find a matching entry, so look for the first * free entry. We look for one which hasn't been previously * used (indicated by zero iobase). */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * That also failed. Last resort is to find any entry which * doesn't have a real port associated with it. */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN) return &serial8250_ports[i]; return NULL; } static void serial_8250_overrun_backoff_work(struct work_struct *work) { struct uart_8250_port *up = container_of(to_delayed_work(work), struct uart_8250_port, overrun_backoff); struct uart_port *port = &up->port; unsigned long flags; spin_lock_irqsave(&port->lock, flags); up->ier |= UART_IER_RLSI | UART_IER_RDI; up->port.read_status_mask |= UART_LSR_DR; serial_out(up, UART_IER, up->ier); spin_unlock_irqrestore(&port->lock, flags); } /** * serial8250_register_8250_port - register a serial port * @up: serial port template * * Configure the serial port specified by the request. If the * port exists and is in use, it is hung up and unregistered * first. * * The port is then probed and if necessary the IRQ is autodetected * If this fails an error is returned. * * On success the port is ready to use and the line number is returned. */ int serial8250_register_8250_port(struct uart_8250_port *up) { struct uart_8250_port *uart; int ret = -ENOSPC; if (up->port.uartclk == 0) return -EINVAL; mutex_lock(&serial_mutex); uart = serial8250_find_match_or_unused(&up->port); if (uart && uart->port.type != PORT_8250_CIR) { struct mctrl_gpios *gpios; if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); uart->port.iobase = up->port.iobase; uart->port.membase = up->port.membase; uart->port.irq = up->port.irq; uart->port.irqflags = up->port.irqflags; uart->port.uartclk = up->port.uartclk; uart->port.fifosize = up->port.fifosize; uart->port.regshift = up->port.regshift; uart->port.iotype = up->port.iotype; uart->port.flags = up->port.flags | UPF_BOOT_AUTOCONF; uart->bugs = up->bugs; uart->port.mapbase = up->port.mapbase; uart->port.mapsize = up->port.mapsize; uart->port.private_data = up->port.private_data; uart->tx_loadsz = up->tx_loadsz; uart->capabilities = up->capabilities; uart->port.throttle = up->port.throttle; uart->port.unthrottle = up->port.unthrottle; uart->port.rs485_config = up->port.rs485_config; uart->port.rs485 = up->port.rs485; uart->dma = up->dma; /* Take tx_loadsz from fifosize if it wasn't set separately */ if (uart->port.fifosize && !uart->tx_loadsz) uart->tx_loadsz = uart->port.fifosize; if (up->port.dev) uart->port.dev = up->port.dev; if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; /* * Only call mctrl_gpio_init(), if the device has no ACPI * companion device */ if (!has_acpi_companion(uart->port.dev)) { gpios = mctrl_gpio_init(&uart->port, 0); if (IS_ERR(gpios)) { ret = PTR_ERR(gpios); goto err; } else { uart->gpios = gpios; } } serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ if (up->port.serial_in) uart->port.serial_in = up->port.serial_in; if (up->port.serial_out) uart->port.serial_out = up->port.serial_out; if (up->port.handle_irq) uart->port.handle_irq = up->port.handle_irq; /* Possibly override set_termios call */ if (up->port.set_termios) uart->port.set_termios = up->port.set_termios; if (up->port.set_ldisc) uart->port.set_ldisc = up->port.set_ldisc; if (up->port.get_mctrl) uart->port.get_mctrl = up->port.get_mctrl; if (up->port.set_mctrl) uart->port.set_mctrl = up->port.set_mctrl; if (up->port.get_divisor) uart->port.get_divisor = up->port.get_divisor; if (up->port.set_divisor) uart->port.set_divisor = up->port.set_divisor; if (up->port.startup) uart->port.startup = up->port.startup; if (up->port.shutdown) uart->port.shutdown = up->port.shutdown; if (up->port.pm) uart->port.pm = up->port.pm; if (up->port.handle_break) uart->port.handle_break = up->port.handle_break; if (up->dl_read) uart->dl_read = up->dl_read; if (up->dl_write) uart->dl_write = up->dl_write; if (uart->port.type != PORT_8250_CIR) { if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); serial8250_apply_quirks(uart); ret = uart_add_one_port(&serial8250_reg, &uart->port); if (ret) goto err; ret = uart->port.line; } else { dev_info(uart->port.dev, "skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n", uart->port.iobase, (unsigned long long)uart->port.mapbase, uart->port.irq); ret = 0; } /* Initialise interrupt backoff work if required */ if (up->overrun_backoff_time_ms > 0) { uart->overrun_backoff_time_ms = up->overrun_backoff_time_ms; INIT_DELAYED_WORK(&uart->overrun_backoff, serial_8250_overrun_backoff_work); } else { uart->overrun_backoff_time_ms = 0; } } mutex_unlock(&serial_mutex); return ret; err: uart->port.dev = NULL; mutex_unlock(&serial_mutex); return ret; } EXPORT_SYMBOL(serial8250_register_8250_port); /** * serial8250_unregister_port - remove a 16x50 serial port at runtime * @line: serial line number * * Remove one serial port. This may not be called from interrupt * context. We hand the port back to the our control. */ void serial8250_unregister_port(int line) { struct uart_8250_port *uart = &serial8250_ports[line]; mutex_lock(&serial_mutex); if (uart->em485) { unsigned long flags; spin_lock_irqsave(&uart->port.lock, flags); serial8250_em485_destroy(uart); spin_unlock_irqrestore(&uart->port.lock, flags); } uart_remove_one_port(&serial8250_reg, &uart->port); if (serial8250_isa_devs) { uart->port.flags &= ~UPF_BOOT_AUTOCONF; uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->capabilities = 0; serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { uart->port.dev = NULL; } mutex_unlock(&serial_mutex); } EXPORT_SYMBOL(serial8250_unregister_port); static int __init serial8250_init(void) { int ret; if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); pr_info("Serial: 8250/16550 driver, %d ports, IRQ sharing %sabled\n", nr_uarts, share_irqs ? "en" : "dis"); #ifdef CONFIG_SPARC ret = sunserial_register_minors(&serial8250_reg, UART_NR); #else serial8250_reg.nr = UART_NR; ret = uart_register_driver(&serial8250_reg); #endif if (ret) goto out; ret = serial8250_pnp_init(); if (ret) goto unreg_uart_drv; serial8250_isa_devs = platform_device_alloc("serial8250", PLAT8250_DEV_LEGACY); if (!serial8250_isa_devs) { ret = -ENOMEM; goto unreg_pnp; } ret = platform_device_add(serial8250_isa_devs); if (ret) goto put_dev; serial8250_register_ports(&serial8250_reg, &serial8250_isa_devs->dev); ret = platform_driver_register(&serial8250_isa_driver); if (ret == 0) goto out; platform_device_del(serial8250_isa_devs); put_dev: platform_device_put(serial8250_isa_devs); unreg_pnp: serial8250_pnp_exit(); unreg_uart_drv: #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif out: return ret; } static void __exit serial8250_exit(void) { struct platform_device *isa_dev = serial8250_isa_devs; /* * This tells serial8250_unregister_port() not to re-register * the ports (thereby making serial8250_isa_driver permanently * in use.) */ serial8250_isa_devs = NULL; platform_driver_unregister(&serial8250_isa_driver); platform_device_unregister(isa_dev); serial8250_pnp_exit(); #ifdef CONFIG_SPARC sunserial_unregister_minors(&serial8250_reg, UART_NR); #else uart_unregister_driver(&serial8250_reg); #endif } module_init(serial8250_init); module_exit(serial8250_exit); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic 8250/16x50 serial driver"); module_param_hw(share_irqs, uint, other, 0644); MODULE_PARM_DESC(share_irqs, "Share IRQs with other non-8250/16x50 devices (unsafe)"); module_param(nr_uarts, uint, 0644); MODULE_PARM_DESC(nr_uarts, "Maximum number of UARTs supported. (1-" __MODULE_STRING(CONFIG_SERIAL_8250_NR_UARTS) ")"); module_param(skip_txen_test, uint, 0644); MODULE_PARM_DESC(skip_txen_test, "Skip checking for the TXEN bug at init time"); #ifdef CONFIG_SERIAL_8250_RSA module_param_hw_array(probe_rsa, ulong, ioport, &probe_rsa_count, 0444); MODULE_PARM_DESC(probe_rsa, "Probe I/O ports for RSA"); #endif MODULE_ALIAS_CHARDEV_MAJOR(TTY_MAJOR); #ifdef CONFIG_SERIAL_8250_DEPRECATED_OPTIONS #ifndef MODULE /* This module was renamed to 8250_core in 3.7. Keep the old "8250" name * working as well for the module options so we don't break people. We * need to keep the names identical and the convenient macros will happily * refuse to let us do that by failing the build with redefinition errors * of global variables. So we stick them inside a dummy function to avoid * those conflicts. The options still get parsed, and the redefined * MODULE_PARAM_PREFIX lets us keep the "8250." syntax alive. * * This is hacky. I'm sorry. */ static void __used s8250_options(void) { #undef MODULE_PARAM_PREFIX #define MODULE_PARAM_PREFIX "8250_core." module_param_cb(share_irqs, ¶m_ops_uint, &share_irqs, 0644); module_param_cb(nr_uarts, ¶m_ops_uint, &nr_uarts, 0644); module_param_cb(skip_txen_test, ¶m_ops_uint, &skip_txen_test, 0644); #ifdef CONFIG_SERIAL_8250_RSA __module_param_call(MODULE_PARAM_PREFIX, probe_rsa, ¶m_array_ops, .arr = &__param_arr_probe_rsa, 0444, -1, 0); #endif } #else MODULE_ALIAS("8250_core"); #endif #endif |
| 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 | // SPDX-License-Identifier: ((GPL-2.0 WITH Linux-syscall-note) OR BSD-3-Clause) /* * proc.c - procfs support for Protocol family CAN core module * * Copyright (c) 2002-2007 Volkswagen Group Electronic Research * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions * are met: * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the name of Volkswagen nor the names of its contributors * may be used to endorse or promote products derived from this software * without specific prior written permission. * * Alternatively, provided that this notice is retained in full, this * software may be distributed under the terms of the GNU General * Public License ("GPL") version 2, in which case the provisions of the * GPL apply INSTEAD OF those given above. * * The provided data structures and external interfaces from this code * are not restricted to be used by modules with a GPL compatible license. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS * "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR * A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT * OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, * DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY * THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH * DAMAGE. * */ #include <linux/module.h> #include <linux/proc_fs.h> #include <linux/list.h> #include <linux/rcupdate.h> #include <linux/if_arp.h> #include <linux/can/can-ml.h> #include <linux/can/core.h> #include "af_can.h" /* * proc filenames for the PF_CAN core */ #define CAN_PROC_VERSION "version" #define CAN_PROC_STATS "stats" #define CAN_PROC_RESET_STATS "reset_stats" #define CAN_PROC_RCVLIST_ALL "rcvlist_all" #define CAN_PROC_RCVLIST_FIL "rcvlist_fil" #define CAN_PROC_RCVLIST_INV "rcvlist_inv" #define CAN_PROC_RCVLIST_SFF "rcvlist_sff" #define CAN_PROC_RCVLIST_EFF "rcvlist_eff" #define CAN_PROC_RCVLIST_ERR "rcvlist_err" static int user_reset; static const char rx_list_name[][8] = { [RX_ERR] = "rx_err", [RX_ALL] = "rx_all", [RX_FIL] = "rx_fil", [RX_INV] = "rx_inv", }; /* * af_can statistics stuff */ static void can_init_stats(struct net *net) { struct can_pkg_stats *pkg_stats = net->can.pkg_stats; struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; /* * This memset function is called from a timer context (when * can_stattimer is active which is the default) OR in a process * context (reading the proc_fs when can_stattimer is disabled). */ memset(pkg_stats, 0, sizeof(struct can_pkg_stats)); pkg_stats->jiffies_init = jiffies; rcv_lists_stats->stats_reset++; if (user_reset) { user_reset = 0; rcv_lists_stats->user_reset++; } } static unsigned long calc_rate(unsigned long oldjif, unsigned long newjif, unsigned long count) { unsigned long rate; if (oldjif == newjif) return 0; /* see can_stat_update() - this should NEVER happen! */ if (count > (ULONG_MAX / HZ)) { printk(KERN_ERR "can: calc_rate: count exceeded! %ld\n", count); return 99999999; } rate = (count * HZ) / (newjif - oldjif); return rate; } void can_stat_update(struct timer_list *t) { struct net *net = from_timer(net, t, can.stattimer); struct can_pkg_stats *pkg_stats = net->can.pkg_stats; unsigned long j = jiffies; /* snapshot */ long rx_frames = atomic_long_read(&pkg_stats->rx_frames); long tx_frames = atomic_long_read(&pkg_stats->tx_frames); long matches = atomic_long_read(&pkg_stats->matches); long rx_frames_delta = atomic_long_read(&pkg_stats->rx_frames_delta); long tx_frames_delta = atomic_long_read(&pkg_stats->tx_frames_delta); long matches_delta = atomic_long_read(&pkg_stats->matches_delta); /* restart counting in timer context on user request */ if (user_reset) can_init_stats(net); /* restart counting on jiffies overflow */ if (j < pkg_stats->jiffies_init) can_init_stats(net); /* prevent overflow in calc_rate() */ if (rx_frames > (LONG_MAX / HZ)) can_init_stats(net); /* prevent overflow in calc_rate() */ if (tx_frames > (LONG_MAX / HZ)) can_init_stats(net); /* matches overflow - very improbable */ if (matches > (LONG_MAX / 100)) can_init_stats(net); /* calc total values */ if (rx_frames) pkg_stats->total_rx_match_ratio = (matches * 100) / rx_frames; pkg_stats->total_tx_rate = calc_rate(pkg_stats->jiffies_init, j, tx_frames); pkg_stats->total_rx_rate = calc_rate(pkg_stats->jiffies_init, j, rx_frames); /* calc current values */ if (rx_frames_delta) pkg_stats->current_rx_match_ratio = (matches_delta * 100) / rx_frames_delta; pkg_stats->current_tx_rate = calc_rate(0, HZ, tx_frames_delta); pkg_stats->current_rx_rate = calc_rate(0, HZ, rx_frames_delta); /* check / update maximum values */ if (pkg_stats->max_tx_rate < pkg_stats->current_tx_rate) pkg_stats->max_tx_rate = pkg_stats->current_tx_rate; if (pkg_stats->max_rx_rate < pkg_stats->current_rx_rate) pkg_stats->max_rx_rate = pkg_stats->current_rx_rate; if (pkg_stats->max_rx_match_ratio < pkg_stats->current_rx_match_ratio) pkg_stats->max_rx_match_ratio = pkg_stats->current_rx_match_ratio; /* clear values for 'current rate' calculation */ atomic_long_set(&pkg_stats->tx_frames_delta, 0); atomic_long_set(&pkg_stats->rx_frames_delta, 0); atomic_long_set(&pkg_stats->matches_delta, 0); /* restart timer (one second) */ mod_timer(&net->can.stattimer, round_jiffies(jiffies + HZ)); } /* * proc read functions */ static void can_print_rcvlist(struct seq_file *m, struct hlist_head *rx_list, struct net_device *dev) { struct receiver *r; hlist_for_each_entry_rcu(r, rx_list, list) { char *fmt = (r->can_id & CAN_EFF_FLAG)? " %-5s %08x %08x %pK %pK %8ld %s\n" : " %-5s %03x %08x %pK %pK %8ld %s\n"; seq_printf(m, fmt, DNAME(dev), r->can_id, r->mask, r->func, r->data, r->matches, r->ident); } } static void can_print_recv_banner(struct seq_file *m) { /* * can1. 00000000 00000000 00000000 * ....... 0 tp20 */ seq_puts(m, " device can_id can_mask function" " userdata matches ident\n"); } static int can_stats_proc_show(struct seq_file *m, void *v) { struct net *net = m->private; struct can_pkg_stats *pkg_stats = net->can.pkg_stats; struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; seq_putc(m, '\n'); seq_printf(m, " %8ld transmitted frames (TXF)\n", atomic_long_read(&pkg_stats->tx_frames)); seq_printf(m, " %8ld received frames (RXF)\n", atomic_long_read(&pkg_stats->rx_frames)); seq_printf(m, " %8ld matched frames (RXMF)\n", atomic_long_read(&pkg_stats->matches)); seq_putc(m, '\n'); if (net->can.stattimer.function == can_stat_update) { seq_printf(m, " %8ld %% total match ratio (RXMR)\n", pkg_stats->total_rx_match_ratio); seq_printf(m, " %8ld frames/s total tx rate (TXR)\n", pkg_stats->total_tx_rate); seq_printf(m, " %8ld frames/s total rx rate (RXR)\n", pkg_stats->total_rx_rate); seq_putc(m, '\n'); seq_printf(m, " %8ld %% current match ratio (CRXMR)\n", pkg_stats->current_rx_match_ratio); seq_printf(m, " %8ld frames/s current tx rate (CTXR)\n", pkg_stats->current_tx_rate); seq_printf(m, " %8ld frames/s current rx rate (CRXR)\n", pkg_stats->current_rx_rate); seq_putc(m, '\n'); seq_printf(m, " %8ld %% max match ratio (MRXMR)\n", pkg_stats->max_rx_match_ratio); seq_printf(m, " %8ld frames/s max tx rate (MTXR)\n", pkg_stats->max_tx_rate); seq_printf(m, " %8ld frames/s max rx rate (MRXR)\n", pkg_stats->max_rx_rate); seq_putc(m, '\n'); } seq_printf(m, " %8ld current receive list entries (CRCV)\n", rcv_lists_stats->rcv_entries); seq_printf(m, " %8ld maximum receive list entries (MRCV)\n", rcv_lists_stats->rcv_entries_max); if (rcv_lists_stats->stats_reset) seq_printf(m, "\n %8ld statistic resets (STR)\n", rcv_lists_stats->stats_reset); if (rcv_lists_stats->user_reset) seq_printf(m, " %8ld user statistic resets (USTR)\n", rcv_lists_stats->user_reset); seq_putc(m, '\n'); return 0; } static int can_reset_stats_proc_show(struct seq_file *m, void *v) { struct net *net = m->private; struct can_rcv_lists_stats *rcv_lists_stats = net->can.rcv_lists_stats; struct can_pkg_stats *pkg_stats = net->can.pkg_stats; user_reset = 1; if (net->can.stattimer.function == can_stat_update) { seq_printf(m, "Scheduled statistic reset #%ld.\n", rcv_lists_stats->stats_reset + 1); } else { if (pkg_stats->jiffies_init != jiffies) can_init_stats(net); seq_printf(m, "Performed statistic reset #%ld.\n", rcv_lists_stats->stats_reset); } return 0; } static int can_version_proc_show(struct seq_file *m, void *v) { seq_printf(m, "%s\n", CAN_VERSION_STRING); return 0; } static inline void can_rcvlist_proc_show_one(struct seq_file *m, int idx, struct net_device *dev, struct can_dev_rcv_lists *dev_rcv_lists) { if (!hlist_empty(&dev_rcv_lists->rx[idx])) { can_print_recv_banner(m); can_print_rcvlist(m, &dev_rcv_lists->rx[idx], dev); } else seq_printf(m, " (%s: no entry)\n", DNAME(dev)); } static int can_rcvlist_proc_show(struct seq_file *m, void *v) { /* double cast to prevent GCC warning */ int idx = (int)(long)PDE_DATA(m->file->f_inode); struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; seq_printf(m, "\nreceive list '%s':\n", rx_list_name[idx]); rcu_read_lock(); /* receive list for 'all' CAN devices (dev == NULL) */ dev_rcv_lists = net->can.rx_alldev_list; can_rcvlist_proc_show_one(m, idx, NULL, dev_rcv_lists); /* receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { struct can_ml_priv *can_ml = can_get_ml_priv(dev); if (can_ml) can_rcvlist_proc_show_one(m, idx, dev, &can_ml->dev_rcv_lists); } rcu_read_unlock(); seq_putc(m, '\n'); return 0; } static inline void can_rcvlist_proc_show_array(struct seq_file *m, struct net_device *dev, struct hlist_head *rcv_array, unsigned int rcv_array_sz) { unsigned int i; int all_empty = 1; /* check whether at least one list is non-empty */ for (i = 0; i < rcv_array_sz; i++) if (!hlist_empty(&rcv_array[i])) { all_empty = 0; break; } if (!all_empty) { can_print_recv_banner(m); for (i = 0; i < rcv_array_sz; i++) { if (!hlist_empty(&rcv_array[i])) can_print_rcvlist(m, &rcv_array[i], dev); } } else seq_printf(m, " (%s: no entry)\n", DNAME(dev)); } static int can_rcvlist_sff_proc_show(struct seq_file *m, void *v) { struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; /* RX_SFF */ seq_puts(m, "\nreceive list 'rx_sff':\n"); rcu_read_lock(); /* sff receive list for 'all' CAN devices (dev == NULL) */ dev_rcv_lists = net->can.rx_alldev_list; can_rcvlist_proc_show_array(m, NULL, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); /* sff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { struct can_ml_priv *can_ml = can_get_ml_priv(dev); if (can_ml) { dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_sff, ARRAY_SIZE(dev_rcv_lists->rx_sff)); } } rcu_read_unlock(); seq_putc(m, '\n'); return 0; } static int can_rcvlist_eff_proc_show(struct seq_file *m, void *v) { struct net_device *dev; struct can_dev_rcv_lists *dev_rcv_lists; struct net *net = m->private; /* RX_EFF */ seq_puts(m, "\nreceive list 'rx_eff':\n"); rcu_read_lock(); /* eff receive list for 'all' CAN devices (dev == NULL) */ dev_rcv_lists = net->can.rx_alldev_list; can_rcvlist_proc_show_array(m, NULL, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); /* eff receive list for registered CAN devices */ for_each_netdev_rcu(net, dev) { struct can_ml_priv *can_ml = can_get_ml_priv(dev); if (can_ml) { dev_rcv_lists = &can_ml->dev_rcv_lists; can_rcvlist_proc_show_array(m, dev, dev_rcv_lists->rx_eff, ARRAY_SIZE(dev_rcv_lists->rx_eff)); } } rcu_read_unlock(); seq_putc(m, '\n'); return 0; } /* * can_init_proc - create main CAN proc directory and procfs entries */ void can_init_proc(struct net *net) { /* create /proc/net/can directory */ net->can.proc_dir = proc_net_mkdir(net, "can", net->proc_net); if (!net->can.proc_dir) { printk(KERN_INFO "can: failed to create /proc/net/can . " "CONFIG_PROC_FS missing?\n"); return; } /* own procfs entries from the AF_CAN core */ net->can.pde_version = proc_create_net_single(CAN_PROC_VERSION, 0644, net->can.proc_dir, can_version_proc_show, NULL); net->can.pde_stats = proc_create_net_single(CAN_PROC_STATS, 0644, net->can.proc_dir, can_stats_proc_show, NULL); net->can.pde_reset_stats = proc_create_net_single(CAN_PROC_RESET_STATS, 0644, net->can.proc_dir, can_reset_stats_proc_show, NULL); net->can.pde_rcvlist_err = proc_create_net_single(CAN_PROC_RCVLIST_ERR, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_ERR); net->can.pde_rcvlist_all = proc_create_net_single(CAN_PROC_RCVLIST_ALL, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_ALL); net->can.pde_rcvlist_fil = proc_create_net_single(CAN_PROC_RCVLIST_FIL, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_FIL); net->can.pde_rcvlist_inv = proc_create_net_single(CAN_PROC_RCVLIST_INV, 0644, net->can.proc_dir, can_rcvlist_proc_show, (void *)RX_INV); net->can.pde_rcvlist_eff = proc_create_net_single(CAN_PROC_RCVLIST_EFF, 0644, net->can.proc_dir, can_rcvlist_eff_proc_show, NULL); net->can.pde_rcvlist_sff = proc_create_net_single(CAN_PROC_RCVLIST_SFF, 0644, net->can.proc_dir, can_rcvlist_sff_proc_show, NULL); } /* * can_remove_proc - remove procfs entries and main CAN proc directory */ void can_remove_proc(struct net *net) { if (!net->can.proc_dir) return; if (net->can.pde_version) remove_proc_entry(CAN_PROC_VERSION, net->can.proc_dir); if (net->can.pde_stats) remove_proc_entry(CAN_PROC_STATS, net->can.proc_dir); if (net->can.pde_reset_stats) remove_proc_entry(CAN_PROC_RESET_STATS, net->can.proc_dir); if (net->can.pde_rcvlist_err) remove_proc_entry(CAN_PROC_RCVLIST_ERR, net->can.proc_dir); if (net->can.pde_rcvlist_all) remove_proc_entry(CAN_PROC_RCVLIST_ALL, net->can.proc_dir); if (net->can.pde_rcvlist_fil) remove_proc_entry(CAN_PROC_RCVLIST_FIL, net->can.proc_dir); if (net->can.pde_rcvlist_inv) remove_proc_entry(CAN_PROC_RCVLIST_INV, net->can.proc_dir); if (net->can.pde_rcvlist_eff) remove_proc_entry(CAN_PROC_RCVLIST_EFF, net->can.proc_dir); if (net->can.pde_rcvlist_sff) remove_proc_entry(CAN_PROC_RCVLIST_SFF, net->can.proc_dir); remove_proc_entry("can", net->proc_net); } |
| 164 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 | /* * net/tipc/bearer.h: Include file for TIPC bearer code * * Copyright (c) 1996-2006, 2013-2016, Ericsson AB * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #ifndef _TIPC_BEARER_H #define _TIPC_BEARER_H #include "netlink.h" #include "core.h" #include "msg.h" #include <net/genetlink.h> #define MAX_MEDIA 3 /* Identifiers associated with TIPC message header media address info * - address info field is 32 bytes long * - the field's actual content and length is defined per media * - remaining unused bytes in the field are set to zero */ #define TIPC_MEDIA_INFO_SIZE 32 #define TIPC_MEDIA_TYPE_OFFSET 3 #define TIPC_MEDIA_ADDR_OFFSET 4 /* * Identifiers of supported TIPC media types */ #define TIPC_MEDIA_TYPE_ETH 1 #define TIPC_MEDIA_TYPE_IB 2 #define TIPC_MEDIA_TYPE_UDP 3 /* Minimum bearer MTU */ #define TIPC_MIN_BEARER_MTU (MAX_H_SIZE + INT_H_SIZE) /* Identifiers for distinguishing between broadcast/multicast and replicast */ #define TIPC_BROADCAST_SUPPORT 1 #define TIPC_REPLICAST_SUPPORT 2 /** * struct tipc_media_addr - destination address used by TIPC bearers * @value: address info (format defined by media) * @media_id: TIPC media type identifier * @broadcast: non-zero if address is a broadcast address */ struct tipc_media_addr { u8 value[TIPC_MEDIA_INFO_SIZE]; u8 media_id; u8 broadcast; }; struct tipc_bearer; /** * struct tipc_media - Media specific info exposed to generic bearer layer * @send_msg: routine which handles buffer transmission * @enable_media: routine which enables a media * @disable_media: routine which disables a media * @addr2str: convert media address format to string * @addr2msg: convert from media addr format to discovery msg addr format * @msg2addr: convert from discovery msg addr format to media addr format * @raw2addr: convert from raw addr format to media addr format * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @window: default window (in packets) before declaring link congestion * @mtu: max packet size bearer can support for media type not dependent on * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name */ struct tipc_media { int (*send_msg)(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); int (*enable_media)(struct net *net, struct tipc_bearer *b, struct nlattr *attr[]); void (*disable_media)(struct tipc_bearer *b); int (*addr2str)(struct tipc_media_addr *addr, char *strbuf, int bufsz); int (*addr2msg)(char *msg, struct tipc_media_addr *addr); int (*msg2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *msg); int (*raw2addr)(struct tipc_bearer *b, struct tipc_media_addr *addr, char *raw); u32 priority; u32 tolerance; u32 window; u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; }; /** * struct tipc_bearer - Generic TIPC bearer structure * @media_ptr: pointer to additional media-specific information about bearer * @mtu: max packet size bearer can support * @addr: media-specific address associated with bearer * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @bcast_addr: media address used in broadcasting * @pt: packet type for bearer * @rcu: rcu struct for tipc_bearer * @priority: default link priority for bearer * @window: default window size for bearer * @tolerance: default link tolerance for bearer * @domain: network domain to which links can be established * @identity: array index of this bearer within TIPC bearer array * @link_req: ptr to (optional) structure making periodic link setup requests * @net_plane: network plane ('A' through 'H') currently associated with bearer * * Note: media-specific code is responsible for initialization of the fields * indicated below when a bearer is enabled; TIPC's generic bearer code takes * care of initializing all other fields. */ struct tipc_bearer { void __rcu *media_ptr; /* initalized by media */ u32 mtu; /* initalized by media */ struct tipc_media_addr addr; /* initalized by media */ char name[TIPC_MAX_BEARER_NAME]; struct tipc_media *media; struct tipc_media_addr bcast_addr; struct packet_type pt; struct rcu_head rcu; u32 priority; u32 window; u32 tolerance; u32 domain; u32 identity; struct tipc_discoverer *disc; char net_plane; unsigned long up; refcount_t refcnt; }; struct tipc_bearer_names { char media_name[TIPC_MAX_MEDIA_NAME]; char if_name[TIPC_MAX_IF_NAME]; }; /* * TIPC routines available to supported media types */ void tipc_rcv(struct net *net, struct sk_buff *skb, struct tipc_bearer *b); /* * Routines made available to TIPC by supported media types */ extern struct tipc_media eth_media_info; #ifdef CONFIG_TIPC_MEDIA_IB extern struct tipc_media ib_media_info; #endif #ifdef CONFIG_TIPC_MEDIA_UDP extern struct tipc_media udp_media_info; #endif int tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_disable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_enable(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_bearer_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info); int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_dump(struct sk_buff *skb, struct netlink_callback *cb); int tipc_nl_media_get(struct sk_buff *skb, struct genl_info *info); int tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info); int tipc_media_set_priority(const char *name, u32 new_value); int tipc_media_set_window(const char *name, u32 new_value); int tipc_media_addr_printf(char *buf, int len, struct tipc_media_addr *a); int tipc_enable_l2_media(struct net *net, struct tipc_bearer *b, struct nlattr *attrs[]); bool tipc_bearer_hold(struct tipc_bearer *b); void tipc_bearer_put(struct tipc_bearer *b); void tipc_disable_l2_media(struct tipc_bearer *b); int tipc_l2_send_msg(struct net *net, struct sk_buff *buf, struct tipc_bearer *b, struct tipc_media_addr *dest); void tipc_bearer_add_dest(struct net *net, u32 bearer_id, u32 dest); void tipc_bearer_remove_dest(struct net *net, u32 bearer_id, u32 dest); struct tipc_bearer *tipc_bearer_find(struct net *net, const char *name); int tipc_bearer_get_name(struct net *net, char *name, u32 bearer_id); struct tipc_media *tipc_media_find(const char *name); int tipc_bearer_setup(void); void tipc_bearer_cleanup(void); void tipc_bearer_stop(struct net *net); int tipc_bearer_mtu(struct net *net, u32 bearer_id); bool tipc_bearer_bcast_support(struct net *net, u32 bearer_id); void tipc_bearer_xmit_skb(struct net *net, u32 bearer_id, struct sk_buff *skb, struct tipc_media_addr *dest); void tipc_bearer_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq, struct tipc_media_addr *dst); void tipc_bearer_bc_xmit(struct net *net, u32 bearer_id, struct sk_buff_head *xmitq); void tipc_clone_to_loopback(struct net *net, struct sk_buff_head *pkts); int tipc_attach_loopback(struct net *net); void tipc_detach_loopback(struct net *net); static inline void tipc_loopback_trace(struct net *net, struct sk_buff_head *pkts) { if (unlikely(dev_nit_active(net->loopback_dev))) tipc_clone_to_loopback(net, pkts); } /* check if device MTU is too low for tipc headers */ static inline bool tipc_mtu_bad(struct net_device *dev, unsigned int reserve) { if (dev->mtu >= TIPC_MIN_BEARER_MTU + reserve) return false; netdev_warn(dev, "MTU too low for tipc bearer\n"); return true; } #endif /* _TIPC_BEARER_H */ |
| 79 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* taskstats_kern.h - kernel header for per-task statistics interface * * Copyright (C) Shailabh Nagar, IBM Corp. 2006 * (C) Balbir Singh, IBM Corp. 2006 */ #ifndef _LINUX_TASKSTATS_KERN_H #define _LINUX_TASKSTATS_KERN_H #include <linux/taskstats.h> #include <linux/sched/signal.h> #include <linux/slab.h> #ifdef CONFIG_TASKSTATS extern struct kmem_cache *taskstats_cache; extern struct mutex taskstats_exit_mutex; static inline void taskstats_tgid_free(struct signal_struct *sig) { if (sig->stats) kmem_cache_free(taskstats_cache, sig->stats); } extern void taskstats_exit(struct task_struct *, int group_dead); extern void taskstats_init_early(void); #else static inline void taskstats_exit(struct task_struct *tsk, int group_dead) {} static inline void taskstats_tgid_free(struct signal_struct *sig) {} static inline void taskstats_init_early(void) {} #endif /* CONFIG_TASKSTATS */ #endif |
| 85 27 28 28 4 4 4 6 9 7 3 25 25 25 25 9 3 4 27 2 27 2 2 6 4 26 26 26 26 26 6 5 2 4 6 6 30 30 30 6 27 25 25 8 22 25 2 25 82 82 6 81 81 81 273 273 272 272 272 273 2 2 187 185 216 217 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * User-space Probes (UProbes) * * Copyright (C) IBM Corporation, 2008-2012 * Authors: * Srikar Dronamraju * Jim Keniston * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra */ #include <linux/kernel.h> #include <linux/highmem.h> #include <linux/pagemap.h> /* read_mapping_page */ #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/export.h> #include <linux/rmap.h> /* anon_vma_prepare */ #include <linux/mmu_notifier.h> /* set_pte_at_notify */ #include <linux/swap.h> /* try_to_free_swap */ #include <linux/ptrace.h> /* user_enable_single_step */ #include <linux/kdebug.h> /* notifier mechanism */ #include "../../mm/internal.h" /* munlock_vma_page */ #include <linux/percpu-rwsem.h> #include <linux/task_work.h> #include <linux/shmem_fs.h> #include <linux/khugepaged.h> #include <linux/uprobes.h> #define UINSNS_PER_PAGE (PAGE_SIZE/UPROBE_XOL_SLOT_BYTES) #define MAX_UPROBE_XOL_SLOTS UINSNS_PER_PAGE static struct rb_root uprobes_tree = RB_ROOT; /* * allows us to skip the uprobe_mmap if there are no uprobe events active * at this time. Probably a fine grained per inode count is better? */ #define no_uprobe_events() RB_EMPTY_ROOT(&uprobes_tree) static DEFINE_SPINLOCK(uprobes_treelock); /* serialize rbtree access */ #define UPROBES_HASH_SZ 13 /* serialize uprobe->pending_list */ static struct mutex uprobes_mmap_mutex[UPROBES_HASH_SZ]; #define uprobes_mmap_hash(v) (&uprobes_mmap_mutex[((unsigned long)(v)) % UPROBES_HASH_SZ]) DEFINE_STATIC_PERCPU_RWSEM(dup_mmap_sem); /* Have a copy of original instruction */ #define UPROBE_COPY_INSN 0 struct uprobe { struct rb_node rb_node; /* node in the rb tree */ refcount_t ref; struct rw_semaphore register_rwsem; struct rw_semaphore consumer_rwsem; struct list_head pending_list; struct uprobe_consumer *consumers; struct inode *inode; /* Also hold a ref to inode */ loff_t offset; loff_t ref_ctr_offset; unsigned long flags; /* * The generic code assumes that it has two members of unknown type * owned by the arch-specific code: * * insn - copy_insn() saves the original instruction here for * arch_uprobe_analyze_insn(). * * ixol - potentially modified instruction to execute out of * line, copied to xol_area by xol_get_insn_slot(). */ struct arch_uprobe arch; }; struct delayed_uprobe { struct list_head list; struct uprobe *uprobe; struct mm_struct *mm; }; static DEFINE_MUTEX(delayed_uprobe_lock); static LIST_HEAD(delayed_uprobe_list); /* * Execute out of line area: anonymous executable mapping installed * by the probed task to execute the copy of the original instruction * mangled by set_swbp(). * * On a breakpoint hit, thread contests for a slot. It frees the * slot after singlestep. Currently a fixed number of slots are * allocated. */ struct xol_area { wait_queue_head_t wq; /* if all slots are busy */ atomic_t slot_count; /* number of in-use slots */ unsigned long *bitmap; /* 0 = free slot */ struct vm_special_mapping xol_mapping; struct page *pages[2]; /* * We keep the vma's vm_start rather than a pointer to the vma * itself. The probed process or a naughty kernel module could make * the vma go away, and we must handle that reasonably gracefully. */ unsigned long vaddr; /* Page(s) of instruction slots */ }; /* * valid_vma: Verify if the specified vma is an executable vma * Relax restrictions while unregistering: vm_flags might have * changed after breakpoint was inserted. * - is_register: indicates if we are in register context. * - Return 1 if the specified virtual address is in an * executable vma. */ static bool valid_vma(struct vm_area_struct *vma, bool is_register) { vm_flags_t flags = VM_HUGETLB | VM_MAYEXEC | VM_MAYSHARE; if (is_register) flags |= VM_WRITE; return vma->vm_file && (vma->vm_flags & flags) == VM_MAYEXEC; } static unsigned long offset_to_vaddr(struct vm_area_struct *vma, loff_t offset) { return vma->vm_start + offset - ((loff_t)vma->vm_pgoff << PAGE_SHIFT); } static loff_t vaddr_to_offset(struct vm_area_struct *vma, unsigned long vaddr) { return ((loff_t)vma->vm_pgoff << PAGE_SHIFT) + (vaddr - vma->vm_start); } /** * __replace_page - replace page in vma by new page. * based on replace_page in mm/ksm.c * * @vma: vma that holds the pte pointing to page * @addr: address the old @page is mapped at * @old_page: the page we are replacing by new_page * @new_page: the modified page we replace page by * * If @new_page is NULL, only unmap @old_page. * * Returns 0 on success, negative error code otherwise. */ static int __replace_page(struct vm_area_struct *vma, unsigned long addr, struct page *old_page, struct page *new_page) { struct mm_struct *mm = vma->vm_mm; struct page_vma_mapped_walk pvmw = { .page = compound_head(old_page), .vma = vma, .address = addr, }; int err; struct mmu_notifier_range range; struct mem_cgroup *memcg; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma, mm, addr, addr + PAGE_SIZE); if (new_page) { err = mem_cgroup_try_charge(new_page, vma->vm_mm, GFP_KERNEL, &memcg, false); if (err) return err; } /* For try_to_free_swap() and munlock_vma_page() below */ lock_page(old_page); mmu_notifier_invalidate_range_start(&range); err = -EAGAIN; if (!page_vma_mapped_walk(&pvmw)) { if (new_page) mem_cgroup_cancel_charge(new_page, memcg, false); goto unlock; } VM_BUG_ON_PAGE(addr != pvmw.address, old_page); if (new_page) { get_page(new_page); page_add_new_anon_rmap(new_page, vma, addr, false); mem_cgroup_commit_charge(new_page, memcg, false, false); lru_cache_add_active_or_unevictable(new_page, vma); } else /* no new page, just dec_mm_counter for old_page */ dec_mm_counter(mm, MM_ANONPAGES); if (!PageAnon(old_page)) { dec_mm_counter(mm, mm_counter_file(old_page)); inc_mm_counter(mm, MM_ANONPAGES); } flush_cache_page(vma, addr, pte_pfn(*pvmw.pte)); ptep_clear_flush_notify(vma, addr, pvmw.pte); if (new_page) set_pte_at_notify(mm, addr, pvmw.pte, mk_pte(new_page, vma->vm_page_prot)); page_remove_rmap(old_page, false); if (!page_mapped(old_page)) try_to_free_swap(old_page); page_vma_mapped_walk_done(&pvmw); if ((vma->vm_flags & VM_LOCKED) && !PageCompound(old_page)) munlock_vma_page(old_page); put_page(old_page); err = 0; unlock: mmu_notifier_invalidate_range_end(&range); unlock_page(old_page); return err; } /** * is_swbp_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_swbp_insn * Returns true if @insn is a breakpoint instruction. */ bool __weak is_swbp_insn(uprobe_opcode_t *insn) { return *insn == UPROBE_SWBP_INSN; } /** * is_trap_insn - check if instruction is breakpoint instruction. * @insn: instruction to be checked. * Default implementation of is_trap_insn * Returns true if @insn is a breakpoint instruction. * * This function is needed for the case where an architecture has multiple * trap instructions (like powerpc). */ bool __weak is_trap_insn(uprobe_opcode_t *insn) { return is_swbp_insn(insn); } static void copy_from_page(struct page *page, unsigned long vaddr, void *dst, int len) { void *kaddr = kmap_atomic(page); memcpy(dst, kaddr + (vaddr & ~PAGE_MASK), len); kunmap_atomic(kaddr); } static void copy_to_page(struct page *page, unsigned long vaddr, const void *src, int len) { void *kaddr = kmap_atomic(page); memcpy(kaddr + (vaddr & ~PAGE_MASK), src, len); kunmap_atomic(kaddr); } static int verify_opcode(struct page *page, unsigned long vaddr, uprobe_opcode_t *new_opcode) { uprobe_opcode_t old_opcode; bool is_swbp; /* * Note: We only check if the old_opcode is UPROBE_SWBP_INSN here. * We do not check if it is any other 'trap variant' which could * be conditional trap instruction such as the one powerpc supports. * * The logic is that we do not care if the underlying instruction * is a trap variant; uprobes always wins over any other (gdb) * breakpoint. */ copy_from_page(page, vaddr, &old_opcode, UPROBE_SWBP_INSN_SIZE); is_swbp = is_swbp_insn(&old_opcode); if (is_swbp_insn(new_opcode)) { if (is_swbp) /* register: already installed? */ return 0; } else { if (!is_swbp) /* unregister: was it changed by us? */ return 0; } return 1; } static struct delayed_uprobe * delayed_uprobe_check(struct uprobe *uprobe, struct mm_struct *mm) { struct delayed_uprobe *du; list_for_each_entry(du, &delayed_uprobe_list, list) if (du->uprobe == uprobe && du->mm == mm) return du; return NULL; } static int delayed_uprobe_add(struct uprobe *uprobe, struct mm_struct *mm) { struct delayed_uprobe *du; if (delayed_uprobe_check(uprobe, mm)) return 0; du = kzalloc(sizeof(*du), GFP_KERNEL); if (!du) return -ENOMEM; du->uprobe = uprobe; du->mm = mm; list_add(&du->list, &delayed_uprobe_list); return 0; } static void delayed_uprobe_delete(struct delayed_uprobe *du) { if (WARN_ON(!du)) return; list_del(&du->list); kfree(du); } static void delayed_uprobe_remove(struct uprobe *uprobe, struct mm_struct *mm) { struct list_head *pos, *q; struct delayed_uprobe *du; if (!uprobe && !mm) return; list_for_each_safe(pos, q, &delayed_uprobe_list) { du = list_entry(pos, struct delayed_uprobe, list); if (uprobe && du->uprobe != uprobe) continue; if (mm && du->mm != mm) continue; delayed_uprobe_delete(du); } } static bool valid_ref_ctr_vma(struct uprobe *uprobe, struct vm_area_struct *vma) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->ref_ctr_offset); return uprobe->ref_ctr_offset && vma->vm_file && file_inode(vma->vm_file) == uprobe->inode && (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && vma->vm_start <= vaddr && vma->vm_end > vaddr; } static struct vm_area_struct * find_ref_ctr_vma(struct uprobe *uprobe, struct mm_struct *mm) { struct vm_area_struct *tmp; for (tmp = mm->mmap; tmp; tmp = tmp->vm_next) if (valid_ref_ctr_vma(uprobe, tmp)) return tmp; return NULL; } static int __update_ref_ctr(struct mm_struct *mm, unsigned long vaddr, short d) { void *kaddr; struct page *page; struct vm_area_struct *vma; int ret; short *ptr; if (!vaddr || !d) return -EINVAL; ret = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_WRITE, &page, &vma, NULL); if (unlikely(ret <= 0)) { /* * We are asking for 1 page. If get_user_pages_remote() fails, * it may return 0, in that case we have to return error. */ return ret == 0 ? -EBUSY : ret; } kaddr = kmap_atomic(page); ptr = kaddr + (vaddr & ~PAGE_MASK); if (unlikely(*ptr + d < 0)) { pr_warn("ref_ctr going negative. vaddr: 0x%lx, " "curr val: %d, delta: %d\n", vaddr, *ptr, d); ret = -EINVAL; goto out; } *ptr += d; ret = 0; out: kunmap_atomic(kaddr); put_page(page); return ret; } static void update_ref_ctr_warn(struct uprobe *uprobe, struct mm_struct *mm, short d) { pr_warn("ref_ctr %s failed for inode: 0x%lx offset: " "0x%llx ref_ctr_offset: 0x%llx of mm: 0x%pK\n", d > 0 ? "increment" : "decrement", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) uprobe->ref_ctr_offset, mm); } static int update_ref_ctr(struct uprobe *uprobe, struct mm_struct *mm, short d) { struct vm_area_struct *rc_vma; unsigned long rc_vaddr; int ret = 0; rc_vma = find_ref_ctr_vma(uprobe, mm); if (rc_vma) { rc_vaddr = offset_to_vaddr(rc_vma, uprobe->ref_ctr_offset); ret = __update_ref_ctr(mm, rc_vaddr, d); if (ret) update_ref_ctr_warn(uprobe, mm, d); if (d > 0) return ret; } mutex_lock(&delayed_uprobe_lock); if (d > 0) ret = delayed_uprobe_add(uprobe, mm); else delayed_uprobe_remove(uprobe, mm); mutex_unlock(&delayed_uprobe_lock); return ret; } /* * NOTE: * Expect the breakpoint instruction to be the smallest size instruction for * the architecture. If an arch has variable length instruction and the * breakpoint instruction is not of the smallest length instruction * supported by that architecture then we need to modify is_trap_at_addr and * uprobe_write_opcode accordingly. This would never be a problem for archs * that have fixed length instructions. * * uprobe_write_opcode - write the opcode at a given virtual address. * @mm: the probed process address space. * @vaddr: the virtual address to store the opcode. * @opcode: opcode to be written at @vaddr. * * Called with mm->mmap_sem held for write. * Return 0 (success) or a negative errno. */ int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t opcode) { struct uprobe *uprobe; struct page *old_page, *new_page; struct vm_area_struct *vma; int ret, is_register, ref_ctr_updated = 0; bool orig_page_huge = false; unsigned int gup_flags = FOLL_FORCE; is_register = is_swbp_insn(&opcode); uprobe = container_of(auprobe, struct uprobe, arch); retry: if (is_register) gup_flags |= FOLL_SPLIT_PMD; /* Read the page with vaddr into memory */ ret = get_user_pages_remote(NULL, mm, vaddr, 1, gup_flags, &old_page, &vma, NULL); if (ret <= 0) return ret; ret = verify_opcode(old_page, vaddr, &opcode); if (ret <= 0) goto put_old; if (WARN(!is_register && PageCompound(old_page), "uprobe unregister should never work on compound page\n")) { ret = -EINVAL; goto put_old; } /* We are going to replace instruction, update ref_ctr. */ if (!ref_ctr_updated && uprobe->ref_ctr_offset) { ret = update_ref_ctr(uprobe, mm, is_register ? 1 : -1); if (ret) goto put_old; ref_ctr_updated = 1; } ret = 0; if (!is_register && !PageAnon(old_page)) goto put_old; ret = anon_vma_prepare(vma); if (ret) goto put_old; ret = -ENOMEM; new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, vaddr); if (!new_page) goto put_old; __SetPageUptodate(new_page); copy_highpage(new_page, old_page); copy_to_page(new_page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); if (!is_register) { struct page *orig_page; pgoff_t index; VM_BUG_ON_PAGE(!PageAnon(old_page), old_page); index = vaddr_to_offset(vma, vaddr & PAGE_MASK) >> PAGE_SHIFT; orig_page = find_get_page(vma->vm_file->f_inode->i_mapping, index); if (orig_page) { if (PageUptodate(orig_page) && pages_identical(new_page, orig_page)) { /* let go new_page */ put_page(new_page); new_page = NULL; if (PageCompound(orig_page)) orig_page_huge = true; } put_page(orig_page); } } ret = __replace_page(vma, vaddr, old_page, new_page); if (new_page) put_page(new_page); put_old: put_page(old_page); if (unlikely(ret == -EAGAIN)) goto retry; /* Revert back reference counter if instruction update failed. */ if (ret && is_register && ref_ctr_updated) update_ref_ctr(uprobe, mm, -1); /* try collapse pmd for compound page */ if (!ret && orig_page_huge) collapse_pte_mapped_thp(mm, vaddr); return ret; } /** * set_swbp - store breakpoint at a given address. * @auprobe: arch specific probepoint information. * @mm: the probed process address space. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, store the breakpoint instruction at @vaddr. * Return 0 (success) or a negative errno. */ int __weak set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { return uprobe_write_opcode(auprobe, mm, vaddr, UPROBE_SWBP_INSN); } /** * set_orig_insn - Restore the original instruction. * @mm: the probed process address space. * @auprobe: arch specific probepoint information. * @vaddr: the virtual address to insert the opcode. * * For mm @mm, restore the original opcode (opcode) at @vaddr. * Return 0 (success) or a negative errno. */ int __weak set_orig_insn(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr) { return uprobe_write_opcode(auprobe, mm, vaddr, *(uprobe_opcode_t *)&auprobe->insn); } static struct uprobe *get_uprobe(struct uprobe *uprobe) { refcount_inc(&uprobe->ref); return uprobe; } static void put_uprobe(struct uprobe *uprobe) { if (refcount_dec_and_test(&uprobe->ref)) { /* * If application munmap(exec_vma) before uprobe_unregister() * gets called, we don't get a chance to remove uprobe from * delayed_uprobe_list from remove_breakpoint(). Do it here. */ mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(uprobe, NULL); mutex_unlock(&delayed_uprobe_lock); kfree(uprobe); } } static int match_uprobe(struct uprobe *l, struct uprobe *r) { if (l->inode < r->inode) return -1; if (l->inode > r->inode) return 1; if (l->offset < r->offset) return -1; if (l->offset > r->offset) return 1; return 0; } static struct uprobe *__find_uprobe(struct inode *inode, loff_t offset) { struct uprobe u = { .inode = inode, .offset = offset }; struct rb_node *n = uprobes_tree.rb_node; struct uprobe *uprobe; int match; while (n) { uprobe = rb_entry(n, struct uprobe, rb_node); match = match_uprobe(&u, uprobe); if (!match) return get_uprobe(uprobe); if (match < 0) n = n->rb_left; else n = n->rb_right; } return NULL; } /* * Find a uprobe corresponding to a given inode:offset * Acquires uprobes_treelock */ static struct uprobe *find_uprobe(struct inode *inode, loff_t offset) { struct uprobe *uprobe; spin_lock(&uprobes_treelock); uprobe = __find_uprobe(inode, offset); spin_unlock(&uprobes_treelock); return uprobe; } static struct uprobe *__insert_uprobe(struct uprobe *uprobe) { struct rb_node **p = &uprobes_tree.rb_node; struct rb_node *parent = NULL; struct uprobe *u; int match; while (*p) { parent = *p; u = rb_entry(parent, struct uprobe, rb_node); match = match_uprobe(uprobe, u); if (!match) return get_uprobe(u); if (match < 0) p = &parent->rb_left; else p = &parent->rb_right; } u = NULL; rb_link_node(&uprobe->rb_node, parent, p); rb_insert_color(&uprobe->rb_node, &uprobes_tree); /* get access + creation ref */ refcount_set(&uprobe->ref, 2); return u; } /* * Acquire uprobes_treelock. * Matching uprobe already exists in rbtree; * increment (access refcount) and return the matching uprobe. * * No matching uprobe; insert the uprobe in rb_tree; * get a double refcount (access + creation) and return NULL. */ static struct uprobe *insert_uprobe(struct uprobe *uprobe) { struct uprobe *u; spin_lock(&uprobes_treelock); u = __insert_uprobe(uprobe); spin_unlock(&uprobes_treelock); return u; } static void ref_ctr_mismatch_warn(struct uprobe *cur_uprobe, struct uprobe *uprobe) { pr_warn("ref_ctr_offset mismatch. inode: 0x%lx offset: 0x%llx " "ref_ctr_offset(old): 0x%llx ref_ctr_offset(new): 0x%llx\n", uprobe->inode->i_ino, (unsigned long long) uprobe->offset, (unsigned long long) cur_uprobe->ref_ctr_offset, (unsigned long long) uprobe->ref_ctr_offset); } static struct uprobe *alloc_uprobe(struct inode *inode, loff_t offset, loff_t ref_ctr_offset) { struct uprobe *uprobe, *cur_uprobe; uprobe = kzalloc(sizeof(struct uprobe), GFP_KERNEL); if (!uprobe) return NULL; uprobe->inode = inode; uprobe->offset = offset; uprobe->ref_ctr_offset = ref_ctr_offset; init_rwsem(&uprobe->register_rwsem); init_rwsem(&uprobe->consumer_rwsem); /* add to uprobes_tree, sorted on inode:offset */ cur_uprobe = insert_uprobe(uprobe); /* a uprobe exists for this inode:offset combination */ if (cur_uprobe) { if (cur_uprobe->ref_ctr_offset != uprobe->ref_ctr_offset) { ref_ctr_mismatch_warn(cur_uprobe, uprobe); put_uprobe(cur_uprobe); kfree(uprobe); return ERR_PTR(-EINVAL); } kfree(uprobe); uprobe = cur_uprobe; } return uprobe; } static void consumer_add(struct uprobe *uprobe, struct uprobe_consumer *uc) { down_write(&uprobe->consumer_rwsem); uc->next = uprobe->consumers; uprobe->consumers = uc; up_write(&uprobe->consumer_rwsem); } /* * For uprobe @uprobe, delete the consumer @uc. * Return true if the @uc is deleted successfully * or return false. */ static bool consumer_del(struct uprobe *uprobe, struct uprobe_consumer *uc) { struct uprobe_consumer **con; bool ret = false; down_write(&uprobe->consumer_rwsem); for (con = &uprobe->consumers; *con; con = &(*con)->next) { if (*con == uc) { *con = uc->next; ret = true; break; } } up_write(&uprobe->consumer_rwsem); return ret; } static int __copy_insn(struct address_space *mapping, struct file *filp, void *insn, int nbytes, loff_t offset) { struct page *page; /* * Ensure that the page that has the original instruction is populated * and in page-cache. If ->readpage == NULL it must be shmem_mapping(), * see uprobe_register(). */ if (mapping->a_ops->readpage) page = read_mapping_page(mapping, offset >> PAGE_SHIFT, filp); else page = shmem_read_mapping_page(mapping, offset >> PAGE_SHIFT); if (IS_ERR(page)) return PTR_ERR(page); copy_from_page(page, offset, insn, nbytes); put_page(page); return 0; } static int copy_insn(struct uprobe *uprobe, struct file *filp) { struct address_space *mapping = uprobe->inode->i_mapping; loff_t offs = uprobe->offset; void *insn = &uprobe->arch.insn; int size = sizeof(uprobe->arch.insn); int len, err = -EIO; /* Copy only available bytes, -EIO if nothing was read */ do { if (offs >= i_size_read(uprobe->inode)) break; len = min_t(int, size, PAGE_SIZE - (offs & ~PAGE_MASK)); err = __copy_insn(mapping, filp, insn, len, offs); if (err) break; insn += len; offs += len; size -= len; } while (size); return err; } static int prepare_uprobe(struct uprobe *uprobe, struct file *file, struct mm_struct *mm, unsigned long vaddr) { int ret = 0; if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) return ret; /* TODO: move this into _register, until then we abuse this sem. */ down_write(&uprobe->consumer_rwsem); if (test_bit(UPROBE_COPY_INSN, &uprobe->flags)) goto out; ret = copy_insn(uprobe, file); if (ret) goto out; ret = -ENOTSUPP; if (is_trap_insn((uprobe_opcode_t *)&uprobe->arch.insn)) goto out; ret = arch_uprobe_analyze_insn(&uprobe->arch, mm, vaddr); if (ret) goto out; smp_wmb(); /* pairs with the smp_rmb() in handle_swbp() */ set_bit(UPROBE_COPY_INSN, &uprobe->flags); out: up_write(&uprobe->consumer_rwsem); return ret; } static inline bool consumer_filter(struct uprobe_consumer *uc, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { return !uc->filter || uc->filter(uc, ctx, mm); } static bool filter_chain(struct uprobe *uprobe, enum uprobe_filter_ctx ctx, struct mm_struct *mm) { struct uprobe_consumer *uc; bool ret = false; down_read(&uprobe->consumer_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { ret = consumer_filter(uc, ctx, mm); if (ret) break; } up_read(&uprobe->consumer_rwsem); return ret; } static int install_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long vaddr) { bool first_uprobe; int ret; ret = prepare_uprobe(uprobe, vma->vm_file, mm, vaddr); if (ret) return ret; /* * set MMF_HAS_UPROBES in advance for uprobe_pre_sstep_notifier(), * the task can hit this breakpoint right after __replace_page(). */ first_uprobe = !test_bit(MMF_HAS_UPROBES, &mm->flags); if (first_uprobe) set_bit(MMF_HAS_UPROBES, &mm->flags); ret = set_swbp(&uprobe->arch, mm, vaddr); if (!ret) clear_bit(MMF_RECALC_UPROBES, &mm->flags); else if (first_uprobe) clear_bit(MMF_HAS_UPROBES, &mm->flags); return ret; } static int remove_breakpoint(struct uprobe *uprobe, struct mm_struct *mm, unsigned long vaddr) { set_bit(MMF_RECALC_UPROBES, &mm->flags); return set_orig_insn(&uprobe->arch, mm, vaddr); } static inline bool uprobe_is_active(struct uprobe *uprobe) { return !RB_EMPTY_NODE(&uprobe->rb_node); } /* * There could be threads that have already hit the breakpoint. They * will recheck the current insn and restart if find_uprobe() fails. * See find_active_uprobe(). */ static void delete_uprobe(struct uprobe *uprobe) { if (WARN_ON(!uprobe_is_active(uprobe))) return; spin_lock(&uprobes_treelock); rb_erase(&uprobe->rb_node, &uprobes_tree); spin_unlock(&uprobes_treelock); RB_CLEAR_NODE(&uprobe->rb_node); /* for uprobe_is_active() */ put_uprobe(uprobe); } struct map_info { struct map_info *next; struct mm_struct *mm; unsigned long vaddr; }; static inline struct map_info *free_map_info(struct map_info *info) { struct map_info *next = info->next; kfree(info); return next; } static struct map_info * build_map_info(struct address_space *mapping, loff_t offset, bool is_register) { unsigned long pgoff = offset >> PAGE_SHIFT; struct vm_area_struct *vma; struct map_info *curr = NULL; struct map_info *prev = NULL; struct map_info *info; int more = 0; again: i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { if (!valid_vma(vma, is_register)) continue; if (!prev && !more) { /* * Needs GFP_NOWAIT to avoid i_mmap_rwsem recursion through * reclaim. This is optimistic, no harm done if it fails. */ prev = kmalloc(sizeof(struct map_info), GFP_NOWAIT | __GFP_NOMEMALLOC | __GFP_NOWARN); if (prev) prev->next = NULL; } if (!prev) { more++; continue; } if (!mmget_not_zero(vma->vm_mm)) continue; info = prev; prev = prev->next; info->next = curr; curr = info; info->mm = vma->vm_mm; info->vaddr = offset_to_vaddr(vma, offset); } i_mmap_unlock_read(mapping); if (!more) goto out; prev = curr; while (curr) { mmput(curr->mm); curr = curr->next; } do { info = kmalloc(sizeof(struct map_info), GFP_KERNEL); if (!info) { curr = ERR_PTR(-ENOMEM); goto out; } info->next = prev; prev = info; } while (--more); goto again; out: while (prev) prev = free_map_info(prev); return curr; } static int register_for_each_vma(struct uprobe *uprobe, struct uprobe_consumer *new) { bool is_register = !!new; struct map_info *info; int err = 0; percpu_down_write(&dup_mmap_sem); info = build_map_info(uprobe->inode->i_mapping, uprobe->offset, is_register); if (IS_ERR(info)) { err = PTR_ERR(info); goto out; } while (info) { struct mm_struct *mm = info->mm; struct vm_area_struct *vma; if (err && is_register) goto free; down_write(&mm->mmap_sem); vma = find_vma(mm, info->vaddr); if (!vma || !valid_vma(vma, is_register) || file_inode(vma->vm_file) != uprobe->inode) goto unlock; if (vma->vm_start > info->vaddr || vaddr_to_offset(vma, info->vaddr) != uprobe->offset) goto unlock; if (is_register) { /* consult only the "caller", new consumer. */ if (consumer_filter(new, UPROBE_FILTER_REGISTER, mm)) err = install_breakpoint(uprobe, mm, vma, info->vaddr); } else if (test_bit(MMF_HAS_UPROBES, &mm->flags)) { if (!filter_chain(uprobe, UPROBE_FILTER_UNREGISTER, mm)) err |= remove_breakpoint(uprobe, mm, info->vaddr); } unlock: up_write(&mm->mmap_sem); free: mmput(mm); info = free_map_info(info); } out: percpu_up_write(&dup_mmap_sem); return err; } static void __uprobe_unregister(struct uprobe *uprobe, struct uprobe_consumer *uc) { int err; if (WARN_ON(!consumer_del(uprobe, uc))) return; err = register_for_each_vma(uprobe, NULL); /* TODO : cant unregister? schedule a worker thread */ if (!uprobe->consumers && !err) delete_uprobe(uprobe); } /* * uprobe_unregister - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: identify which probe if multiple probes are colocated. */ void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; uprobe = find_uprobe(inode, offset); if (WARN_ON(!uprobe)) return; down_write(&uprobe->register_rwsem); __uprobe_unregister(uprobe, uc); up_write(&uprobe->register_rwsem); put_uprobe(uprobe); } EXPORT_SYMBOL_GPL(uprobe_unregister); /* * __uprobe_register - register a probe * @inode: the file in which the probe has to be placed. * @offset: offset from the start of the file. * @uc: information on howto handle the probe.. * * Apart from the access refcount, __uprobe_register() takes a creation * refcount (thro alloc_uprobe) if and only if this @uprobe is getting * inserted into the rbtree (i.e first consumer for a @inode:@offset * tuple). Creation refcount stops uprobe_unregister from freeing the * @uprobe even before the register operation is complete. Creation * refcount is released when the last @uc for the @uprobe * unregisters. Caller of __uprobe_register() is required to keep @inode * (and the containing mount) referenced. * * Return errno if it cannot successully install probes * else return 0 (success) */ static int __uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { struct uprobe *uprobe; int ret; /* Uprobe must have at least one set consumer */ if (!uc->handler && !uc->ret_handler) return -EINVAL; /* copy_insn() uses read_mapping_page() or shmem_read_mapping_page() */ if (!inode->i_mapping->a_ops->readpage && !shmem_mapping(inode->i_mapping)) return -EIO; /* Racy, just to catch the obvious mistakes */ if (offset > i_size_read(inode)) return -EINVAL; /* * This ensures that copy_from_page(), copy_to_page() and * __update_ref_ctr() can't cross page boundary. */ if (!IS_ALIGNED(offset, UPROBE_SWBP_INSN_SIZE)) return -EINVAL; if (!IS_ALIGNED(ref_ctr_offset, sizeof(short))) return -EINVAL; retry: uprobe = alloc_uprobe(inode, offset, ref_ctr_offset); if (!uprobe) return -ENOMEM; if (IS_ERR(uprobe)) return PTR_ERR(uprobe); /* * We can race with uprobe_unregister()->delete_uprobe(). * Check uprobe_is_active() and retry if it is false. */ down_write(&uprobe->register_rwsem); ret = -EAGAIN; if (likely(uprobe_is_active(uprobe))) { consumer_add(uprobe, uc); ret = register_for_each_vma(uprobe, uc); if (ret) __uprobe_unregister(uprobe, uc); } up_write(&uprobe->register_rwsem); put_uprobe(uprobe); if (unlikely(ret == -EAGAIN)) goto retry; return ret; } int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc) { return __uprobe_register(inode, offset, 0, uc); } EXPORT_SYMBOL_GPL(uprobe_register); int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc) { return __uprobe_register(inode, offset, ref_ctr_offset, uc); } EXPORT_SYMBOL_GPL(uprobe_register_refctr); /* * uprobe_apply - unregister an already registered probe. * @inode: the file in which the probe has to be removed. * @offset: offset from the start of the file. * @uc: consumer which wants to add more or remove some breakpoints * @add: add or remove the breakpoints */ int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add) { struct uprobe *uprobe; struct uprobe_consumer *con; int ret = -ENOENT; uprobe = find_uprobe(inode, offset); if (WARN_ON(!uprobe)) return ret; down_write(&uprobe->register_rwsem); for (con = uprobe->consumers; con && con != uc ; con = con->next) ; if (con) ret = register_for_each_vma(uprobe, add ? uc : NULL); up_write(&uprobe->register_rwsem); put_uprobe(uprobe); return ret; } static int unapply_uprobe(struct uprobe *uprobe, struct mm_struct *mm) { struct vm_area_struct *vma; int err = 0; down_read(&mm->mmap_sem); for (vma = mm->mmap; vma; vma = vma->vm_next) { unsigned long vaddr; loff_t offset; if (!valid_vma(vma, false) || file_inode(vma->vm_file) != uprobe->inode) continue; offset = (loff_t)vma->vm_pgoff << PAGE_SHIFT; if (uprobe->offset < offset || uprobe->offset >= offset + vma->vm_end - vma->vm_start) continue; vaddr = offset_to_vaddr(vma, uprobe->offset); err |= remove_breakpoint(uprobe, mm, vaddr); } up_read(&mm->mmap_sem); return err; } static struct rb_node * find_node_in_range(struct inode *inode, loff_t min, loff_t max) { struct rb_node *n = uprobes_tree.rb_node; while (n) { struct uprobe *u = rb_entry(n, struct uprobe, rb_node); if (inode < u->inode) { n = n->rb_left; } else if (inode > u->inode) { n = n->rb_right; } else { if (max < u->offset) n = n->rb_left; else if (min > u->offset) n = n->rb_right; else break; } } return n; } /* * For a given range in vma, build a list of probes that need to be inserted. */ static void build_probe_list(struct inode *inode, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct list_head *head) { loff_t min, max; struct rb_node *n, *t; struct uprobe *u; INIT_LIST_HEAD(head); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); if (n) { for (t = n; t; t = rb_prev(t)) { u = rb_entry(t, struct uprobe, rb_node); if (u->inode != inode || u->offset < min) break; list_add(&u->pending_list, head); get_uprobe(u); } for (t = n; (t = rb_next(t)); ) { u = rb_entry(t, struct uprobe, rb_node); if (u->inode != inode || u->offset > max) break; list_add(&u->pending_list, head); get_uprobe(u); } } spin_unlock(&uprobes_treelock); } /* @vma contains reference counter, not the probed instruction. */ static int delayed_ref_ctr_inc(struct vm_area_struct *vma) { struct list_head *pos, *q; struct delayed_uprobe *du; unsigned long vaddr; int ret = 0, err = 0; mutex_lock(&delayed_uprobe_lock); list_for_each_safe(pos, q, &delayed_uprobe_list) { du = list_entry(pos, struct delayed_uprobe, list); if (du->mm != vma->vm_mm || !valid_ref_ctr_vma(du->uprobe, vma)) continue; vaddr = offset_to_vaddr(vma, du->uprobe->ref_ctr_offset); ret = __update_ref_ctr(vma->vm_mm, vaddr, 1); if (ret) { update_ref_ctr_warn(du->uprobe, vma->vm_mm, 1); if (!err) err = ret; } delayed_uprobe_delete(du); } mutex_unlock(&delayed_uprobe_lock); return err; } /* * Called from mmap_region/vma_adjust with mm->mmap_sem acquired. * * Currently we ignore all errors and always return 0, the callers * can't handle the failure anyway. */ int uprobe_mmap(struct vm_area_struct *vma) { struct list_head tmp_list; struct uprobe *uprobe, *u; struct inode *inode; if (no_uprobe_events()) return 0; if (vma->vm_file && (vma->vm_flags & (VM_WRITE|VM_SHARED)) == VM_WRITE && test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags)) delayed_ref_ctr_inc(vma); if (!valid_vma(vma, true)) return 0; inode = file_inode(vma->vm_file); if (!inode) return 0; mutex_lock(uprobes_mmap_hash(inode)); build_probe_list(inode, vma, vma->vm_start, vma->vm_end, &tmp_list); /* * We can race with uprobe_unregister(), this uprobe can be already * removed. But in this case filter_chain() must return false, all * consumers have gone away. */ list_for_each_entry_safe(uprobe, u, &tmp_list, pending_list) { if (!fatal_signal_pending(current) && filter_chain(uprobe, UPROBE_FILTER_MMAP, vma->vm_mm)) { unsigned long vaddr = offset_to_vaddr(vma, uprobe->offset); install_breakpoint(uprobe, vma->vm_mm, vma, vaddr); } put_uprobe(uprobe); } mutex_unlock(uprobes_mmap_hash(inode)); return 0; } static bool vma_has_uprobes(struct vm_area_struct *vma, unsigned long start, unsigned long end) { loff_t min, max; struct inode *inode; struct rb_node *n; inode = file_inode(vma->vm_file); min = vaddr_to_offset(vma, start); max = min + (end - start) - 1; spin_lock(&uprobes_treelock); n = find_node_in_range(inode, min, max); spin_unlock(&uprobes_treelock); return !!n; } /* * Called in context of a munmap of a vma. */ void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (no_uprobe_events() || !valid_vma(vma, false)) return; if (!atomic_read(&vma->vm_mm->mm_users)) /* called by mmput() ? */ return; if (!test_bit(MMF_HAS_UPROBES, &vma->vm_mm->flags) || test_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags)) return; if (vma_has_uprobes(vma, start, end)) set_bit(MMF_RECALC_UPROBES, &vma->vm_mm->flags); } /* Slot allocation for XOL */ static int xol_add_vma(struct mm_struct *mm, struct xol_area *area) { struct vm_area_struct *vma; int ret; if (down_write_killable(&mm->mmap_sem)) return -EINTR; if (mm->uprobes_state.xol_area) { ret = -EALREADY; goto fail; } if (!area->vaddr) { /* Try to map as high as possible, this is only a hint. */ area->vaddr = get_unmapped_area(NULL, TASK_SIZE - PAGE_SIZE, PAGE_SIZE, 0, 0); if (area->vaddr & ~PAGE_MASK) { ret = area->vaddr; goto fail; } } vma = _install_special_mapping(mm, area->vaddr, PAGE_SIZE, VM_EXEC|VM_MAYEXEC|VM_DONTCOPY|VM_IO, &area->xol_mapping); if (IS_ERR(vma)) { ret = PTR_ERR(vma); goto fail; } ret = 0; /* pairs with get_xol_area() */ smp_store_release(&mm->uprobes_state.xol_area, area); /* ^^^ */ fail: up_write(&mm->mmap_sem); return ret; } static struct xol_area *__create_xol_area(unsigned long vaddr) { struct mm_struct *mm = current->mm; uprobe_opcode_t insn = UPROBE_SWBP_INSN; struct xol_area *area; area = kzalloc(sizeof(*area), GFP_KERNEL); if (unlikely(!area)) goto out; area->bitmap = kcalloc(BITS_TO_LONGS(UINSNS_PER_PAGE), sizeof(long), GFP_KERNEL); if (!area->bitmap) goto free_area; area->xol_mapping.name = "[uprobes]"; area->xol_mapping.pages = area->pages; area->pages[0] = alloc_page(GFP_HIGHUSER | __GFP_ZERO); if (!area->pages[0]) goto free_bitmap; area->pages[1] = NULL; area->vaddr = vaddr; init_waitqueue_head(&area->wq); /* Reserve the 1st slot for get_trampoline_vaddr() */ set_bit(0, area->bitmap); atomic_set(&area->slot_count, 1); arch_uprobe_copy_ixol(area->pages[0], 0, &insn, UPROBE_SWBP_INSN_SIZE); if (!xol_add_vma(mm, area)) return area; __free_page(area->pages[0]); free_bitmap: kfree(area->bitmap); free_area: kfree(area); out: return NULL; } /* * get_xol_area - Allocate process's xol_area if necessary. * This area will be used for storing instructions for execution out of line. * * Returns the allocated area or NULL. */ static struct xol_area *get_xol_area(void) { struct mm_struct *mm = current->mm; struct xol_area *area; if (!mm->uprobes_state.xol_area) __create_xol_area(0); /* Pairs with xol_add_vma() smp_store_release() */ area = READ_ONCE(mm->uprobes_state.xol_area); /* ^^^ */ return area; } /* * uprobe_clear_state - Free the area allocated for slots. */ void uprobe_clear_state(struct mm_struct *mm) { struct xol_area *area = mm->uprobes_state.xol_area; mutex_lock(&delayed_uprobe_lock); delayed_uprobe_remove(NULL, mm); mutex_unlock(&delayed_uprobe_lock); if (!area) return; put_page(area->pages[0]); kfree(area->bitmap); kfree(area); } void uprobe_start_dup_mmap(void) { percpu_down_read(&dup_mmap_sem); } void uprobe_end_dup_mmap(void) { percpu_up_read(&dup_mmap_sem); } void uprobe_dup_mmap(struct mm_struct *oldmm, struct mm_struct *newmm) { if (test_bit(MMF_HAS_UPROBES, &oldmm->flags)) { set_bit(MMF_HAS_UPROBES, &newmm->flags); /* unconditionally, dup_mmap() skips VM_DONTCOPY vmas */ set_bit(MMF_RECALC_UPROBES, &newmm->flags); } } /* * - search for a free slot. */ static unsigned long xol_take_insn_slot(struct xol_area *area) { unsigned long slot_addr; int slot_nr; do { slot_nr = find_first_zero_bit(area->bitmap, UINSNS_PER_PAGE); if (slot_nr < UINSNS_PER_PAGE) { if (!test_and_set_bit(slot_nr, area->bitmap)) break; slot_nr = UINSNS_PER_PAGE; continue; } wait_event(area->wq, (atomic_read(&area->slot_count) < UINSNS_PER_PAGE)); } while (slot_nr >= UINSNS_PER_PAGE); slot_addr = area->vaddr + (slot_nr * UPROBE_XOL_SLOT_BYTES); atomic_inc(&area->slot_count); return slot_addr; } /* * xol_get_insn_slot - allocate a slot for xol. * Returns the allocated slot address or 0. */ static unsigned long xol_get_insn_slot(struct uprobe *uprobe) { struct xol_area *area; unsigned long xol_vaddr; area = get_xol_area(); if (!area) return 0; xol_vaddr = xol_take_insn_slot(area); if (unlikely(!xol_vaddr)) return 0; arch_uprobe_copy_ixol(area->pages[0], xol_vaddr, &uprobe->arch.ixol, sizeof(uprobe->arch.ixol)); return xol_vaddr; } /* * xol_free_insn_slot - If slot was earlier allocated by * @xol_get_insn_slot(), make the slot available for * subsequent requests. */ static void xol_free_insn_slot(struct task_struct *tsk) { struct xol_area *area; unsigned long vma_end; unsigned long slot_addr; if (!tsk->mm || !tsk->mm->uprobes_state.xol_area || !tsk->utask) return; slot_addr = tsk->utask->xol_vaddr; if (unlikely(!slot_addr)) return; area = tsk->mm->uprobes_state.xol_area; vma_end = area->vaddr + PAGE_SIZE; if (area->vaddr <= slot_addr && slot_addr < vma_end) { unsigned long offset; int slot_nr; offset = slot_addr - area->vaddr; slot_nr = offset / UPROBE_XOL_SLOT_BYTES; if (slot_nr >= UINSNS_PER_PAGE) return; clear_bit(slot_nr, area->bitmap); atomic_dec(&area->slot_count); smp_mb__after_atomic(); /* pairs with prepare_to_wait() */ if (waitqueue_active(&area->wq)) wake_up(&area->wq); tsk->utask->xol_vaddr = 0; } } void __weak arch_uprobe_copy_ixol(struct page *page, unsigned long vaddr, void *src, unsigned long len) { /* Initialize the slot */ copy_to_page(page, vaddr, src, len); /* * We probably need flush_icache_user_range() but it needs vma. * This should work on most of architectures by default. If * architecture needs to do something different it can define * its own version of the function. */ flush_dcache_page(page); } /** * uprobe_get_swbp_addr - compute address of swbp given post-swbp regs * @regs: Reflects the saved state of the task after it has hit a breakpoint * instruction. * Return the address of the breakpoint instruction. */ unsigned long __weak uprobe_get_swbp_addr(struct pt_regs *regs) { return instruction_pointer(regs) - UPROBE_SWBP_INSN_SIZE; } unsigned long uprobe_get_trap_addr(struct pt_regs *regs) { struct uprobe_task *utask = current->utask; if (unlikely(utask && utask->active_uprobe)) return utask->vaddr; return instruction_pointer(regs); } static struct return_instance *free_ret_instance(struct return_instance *ri) { struct return_instance *next = ri->next; put_uprobe(ri->uprobe); kfree(ri); return next; } /* * Called with no locks held. * Called in context of an exiting or an exec-ing thread. */ void uprobe_free_utask(struct task_struct *t) { struct uprobe_task *utask = t->utask; struct return_instance *ri; if (!utask) return; if (utask->active_uprobe) put_uprobe(utask->active_uprobe); ri = utask->return_instances; while (ri) ri = free_ret_instance(ri); xol_free_insn_slot(t); kfree(utask); t->utask = NULL; } /* * Allocate a uprobe_task object for the task if if necessary. * Called when the thread hits a breakpoint. * * Returns: * - pointer to new uprobe_task on success * - NULL otherwise */ static struct uprobe_task *get_utask(void) { if (!current->utask) current->utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); return current->utask; } static int dup_utask(struct task_struct *t, struct uprobe_task *o_utask) { struct uprobe_task *n_utask; struct return_instance **p, *o, *n; n_utask = kzalloc(sizeof(struct uprobe_task), GFP_KERNEL); if (!n_utask) return -ENOMEM; t->utask = n_utask; p = &n_utask->return_instances; for (o = o_utask->return_instances; o; o = o->next) { n = kmalloc(sizeof(struct return_instance), GFP_KERNEL); if (!n) return -ENOMEM; *n = *o; get_uprobe(n->uprobe); n->next = NULL; *p = n; p = &n->next; n_utask->depth++; } return 0; } static void uprobe_warn(struct task_struct *t, const char *msg) { pr_warn("uprobe: %s:%d failed to %s\n", current->comm, current->pid, msg); } static void dup_xol_work(struct callback_head *work) { if (current->flags & PF_EXITING) return; if (!__create_xol_area(current->utask->dup_xol_addr) && !fatal_signal_pending(current)) uprobe_warn(current, "dup xol area"); } /* * Called in context of a new clone/fork from copy_process. */ void uprobe_copy_process(struct task_struct *t, unsigned long flags) { struct uprobe_task *utask = current->utask; struct mm_struct *mm = current->mm; struct xol_area *area; t->utask = NULL; if (!utask || !utask->return_instances) return; if (mm == t->mm && !(flags & CLONE_VFORK)) return; if (dup_utask(t, utask)) return uprobe_warn(t, "dup ret instances"); /* The task can fork() after dup_xol_work() fails */ area = mm->uprobes_state.xol_area; if (!area) return uprobe_warn(t, "dup xol area"); if (mm == t->mm) return; t->utask->dup_xol_addr = area->vaddr; init_task_work(&t->utask->dup_xol_work, dup_xol_work); task_work_add(t, &t->utask->dup_xol_work, true); } /* * Current area->vaddr notion assume the trampoline address is always * equal area->vaddr. * * Returns -1 in case the xol_area is not allocated. */ static unsigned long get_trampoline_vaddr(void) { struct xol_area *area; unsigned long trampoline_vaddr = -1; /* Pairs with xol_add_vma() smp_store_release() */ area = READ_ONCE(current->mm->uprobes_state.xol_area); /* ^^^ */ if (area) trampoline_vaddr = area->vaddr; return trampoline_vaddr; } static void cleanup_return_instances(struct uprobe_task *utask, bool chained, struct pt_regs *regs) { struct return_instance *ri = utask->return_instances; enum rp_check ctx = chained ? RP_CHECK_CHAIN_CALL : RP_CHECK_CALL; while (ri && !arch_uretprobe_is_alive(ri, ctx, regs)) { ri = free_ret_instance(ri); utask->depth--; } utask->return_instances = ri; } static void prepare_uretprobe(struct uprobe *uprobe, struct pt_regs *regs) { struct return_instance *ri; struct uprobe_task *utask; unsigned long orig_ret_vaddr, trampoline_vaddr; bool chained; if (!get_xol_area()) return; utask = get_utask(); if (!utask) return; if (utask->depth >= MAX_URETPROBE_DEPTH) { printk_ratelimited(KERN_INFO "uprobe: omit uretprobe due to" " nestedness limit pid/tgid=%d/%d\n", current->pid, current->tgid); return; } ri = kmalloc(sizeof(struct return_instance), GFP_KERNEL); if (!ri) return; trampoline_vaddr = get_trampoline_vaddr(); orig_ret_vaddr = arch_uretprobe_hijack_return_addr(trampoline_vaddr, regs); if (orig_ret_vaddr == -1) goto fail; /* drop the entries invalidated by longjmp() */ chained = (orig_ret_vaddr == trampoline_vaddr); cleanup_return_instances(utask, chained, regs); /* * We don't want to keep trampoline address in stack, rather keep the * original return address of first caller thru all the consequent * instances. This also makes breakpoint unwrapping easier. */ if (chained) { if (!utask->return_instances) { /* * This situation is not possible. Likely we have an * attack from user-space. */ uprobe_warn(current, "handle tail call"); goto fail; } orig_ret_vaddr = utask->return_instances->orig_ret_vaddr; } ri->uprobe = get_uprobe(uprobe); ri->func = instruction_pointer(regs); ri->stack = user_stack_pointer(regs); ri->orig_ret_vaddr = orig_ret_vaddr; ri->chained = chained; utask->depth++; ri->next = utask->return_instances; utask->return_instances = ri; return; fail: kfree(ri); } /* Prepare to single-step probed instruction out of line. */ static int pre_ssout(struct uprobe *uprobe, struct pt_regs *regs, unsigned long bp_vaddr) { struct uprobe_task *utask; unsigned long xol_vaddr; int err; utask = get_utask(); if (!utask) return -ENOMEM; xol_vaddr = xol_get_insn_slot(uprobe); if (!xol_vaddr) return -ENOMEM; utask->xol_vaddr = xol_vaddr; utask->vaddr = bp_vaddr; err = arch_uprobe_pre_xol(&uprobe->arch, regs); if (unlikely(err)) { xol_free_insn_slot(current); return err; } utask->active_uprobe = uprobe; utask->state = UTASK_SSTEP; return 0; } /* * If we are singlestepping, then ensure this thread is not connected to * non-fatal signals until completion of singlestep. When xol insn itself * triggers the signal, restart the original insn even if the task is * already SIGKILL'ed (since coredump should report the correct ip). This * is even more important if the task has a handler for SIGSEGV/etc, The * _same_ instruction should be repeated again after return from the signal * handler, and SSTEP can never finish in this case. */ bool uprobe_deny_signal(void) { struct task_struct *t = current; struct uprobe_task *utask = t->utask; if (likely(!utask || !utask->active_uprobe)) return false; WARN_ON_ONCE(utask->state != UTASK_SSTEP); if (signal_pending(t)) { spin_lock_irq(&t->sighand->siglock); clear_tsk_thread_flag(t, TIF_SIGPENDING); spin_unlock_irq(&t->sighand->siglock); if (__fatal_signal_pending(t) || arch_uprobe_xol_was_trapped(t)) { utask->state = UTASK_SSTEP_TRAPPED; set_tsk_thread_flag(t, TIF_UPROBE); } } return true; } static void mmf_recalc_uprobes(struct mm_struct *mm) { struct vm_area_struct *vma; for (vma = mm->mmap; vma; vma = vma->vm_next) { if (!valid_vma(vma, false)) continue; /* * This is not strictly accurate, we can race with * uprobe_unregister() and see the already removed * uprobe if delete_uprobe() was not yet called. * Or this uprobe can be filtered out. */ if (vma_has_uprobes(vma, vma->vm_start, vma->vm_end)) return; } clear_bit(MMF_HAS_UPROBES, &mm->flags); } static int is_trap_at_addr(struct mm_struct *mm, unsigned long vaddr) { struct page *page; uprobe_opcode_t opcode; int result; if (WARN_ON_ONCE(!IS_ALIGNED(vaddr, UPROBE_SWBP_INSN_SIZE))) return -EINVAL; pagefault_disable(); result = __get_user(opcode, (uprobe_opcode_t __user *)vaddr); pagefault_enable(); if (likely(result == 0)) goto out; /* * The NULL 'tsk' here ensures that any faults that occur here * will not be accounted to the task. 'mm' *is* current->mm, * but we treat this as a 'remote' access since it is * essentially a kernel access to the memory. */ result = get_user_pages_remote(NULL, mm, vaddr, 1, FOLL_FORCE, &page, NULL, NULL); if (result < 0) return result; copy_from_page(page, vaddr, &opcode, UPROBE_SWBP_INSN_SIZE); put_page(page); out: /* This needs to return true for any variant of the trap insn */ return is_trap_insn(&opcode); } static struct uprobe *find_active_uprobe(unsigned long bp_vaddr, int *is_swbp) { struct mm_struct *mm = current->mm; struct uprobe *uprobe = NULL; struct vm_area_struct *vma; down_read(&mm->mmap_sem); vma = find_vma(mm, bp_vaddr); if (vma && vma->vm_start <= bp_vaddr) { if (valid_vma(vma, false)) { struct inode *inode = file_inode(vma->vm_file); loff_t offset = vaddr_to_offset(vma, bp_vaddr); uprobe = find_uprobe(inode, offset); } if (!uprobe) *is_swbp = is_trap_at_addr(mm, bp_vaddr); } else { *is_swbp = -EFAULT; } if (!uprobe && test_and_clear_bit(MMF_RECALC_UPROBES, &mm->flags)) mmf_recalc_uprobes(mm); up_read(&mm->mmap_sem); return uprobe; } static void handler_chain(struct uprobe *uprobe, struct pt_regs *regs) { struct uprobe_consumer *uc; int remove = UPROBE_HANDLER_REMOVE; bool need_prep = false; /* prepare return uprobe, when needed */ down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { int rc = 0; if (uc->handler) { rc = uc->handler(uc, regs); WARN(rc & ~UPROBE_HANDLER_MASK, "bad rc=0x%x from %ps()\n", rc, uc->handler); } if (uc->ret_handler) need_prep = true; remove &= rc; } if (need_prep && !remove) prepare_uretprobe(uprobe, regs); /* put bp at return */ if (remove && uprobe->consumers) { WARN_ON(!uprobe_is_active(uprobe)); unapply_uprobe(uprobe, current->mm); } up_read(&uprobe->register_rwsem); } static void handle_uretprobe_chain(struct return_instance *ri, struct pt_regs *regs) { struct uprobe *uprobe = ri->uprobe; struct uprobe_consumer *uc; down_read(&uprobe->register_rwsem); for (uc = uprobe->consumers; uc; uc = uc->next) { if (uc->ret_handler) uc->ret_handler(uc, ri->func, regs); } up_read(&uprobe->register_rwsem); } static struct return_instance *find_next_ret_chain(struct return_instance *ri) { bool chained; do { chained = ri->chained; ri = ri->next; /* can't be NULL if chained */ } while (chained); return ri; } static void handle_trampoline(struct pt_regs *regs) { struct uprobe_task *utask; struct return_instance *ri, *next; bool valid; utask = current->utask; if (!utask) goto sigill; ri = utask->return_instances; if (!ri) goto sigill; do { /* * We should throw out the frames invalidated by longjmp(). * If this chain is valid, then the next one should be alive * or NULL; the latter case means that nobody but ri->func * could hit this trampoline on return. TODO: sigaltstack(). */ next = find_next_ret_chain(ri); valid = !next || arch_uretprobe_is_alive(next, RP_CHECK_RET, regs); instruction_pointer_set(regs, ri->orig_ret_vaddr); do { if (valid) handle_uretprobe_chain(ri, regs); ri = free_ret_instance(ri); utask->depth--; } while (ri != next); } while (!valid); utask->return_instances = ri; return; sigill: uprobe_warn(current, "handle uretprobe, sending SIGILL."); force_sig(SIGILL); } bool __weak arch_uprobe_ignore(struct arch_uprobe *aup, struct pt_regs *regs) { return false; } bool __weak arch_uretprobe_is_alive(struct return_instance *ret, enum rp_check ctx, struct pt_regs *regs) { return true; } /* * Run handler and ask thread to singlestep. * Ensure all non-fatal signals cannot interrupt thread while it singlesteps. */ static void handle_swbp(struct pt_regs *regs) { struct uprobe *uprobe; unsigned long bp_vaddr; int is_swbp; bp_vaddr = uprobe_get_swbp_addr(regs); if (bp_vaddr == get_trampoline_vaddr()) return handle_trampoline(regs); uprobe = find_active_uprobe(bp_vaddr, &is_swbp); if (!uprobe) { if (is_swbp > 0) { /* No matching uprobe; signal SIGTRAP. */ force_sig(SIGTRAP); } else { /* * Either we raced with uprobe_unregister() or we can't * access this memory. The latter is only possible if * another thread plays with our ->mm. In both cases * we can simply restart. If this vma was unmapped we * can pretend this insn was not executed yet and get * the (correct) SIGSEGV after restart. */ instruction_pointer_set(regs, bp_vaddr); } return; } /* change it in advance for ->handler() and restart */ instruction_pointer_set(regs, bp_vaddr); /* * TODO: move copy_insn/etc into _register and remove this hack. * After we hit the bp, _unregister + _register can install the * new and not-yet-analyzed uprobe at the same address, restart. */ if (unlikely(!test_bit(UPROBE_COPY_INSN, &uprobe->flags))) goto out; /* * Pairs with the smp_wmb() in prepare_uprobe(). * * Guarantees that if we see the UPROBE_COPY_INSN bit set, then * we must also see the stores to &uprobe->arch performed by the * prepare_uprobe() call. */ smp_rmb(); /* Tracing handlers use ->utask to communicate with fetch methods */ if (!get_utask()) goto out; if (arch_uprobe_ignore(&uprobe->arch, regs)) goto out; handler_chain(uprobe, regs); if (arch_uprobe_skip_sstep(&uprobe->arch, regs)) goto out; if (!pre_ssout(uprobe, regs, bp_vaddr)) return; /* arch_uprobe_skip_sstep() succeeded, or restart if can't singlestep */ out: put_uprobe(uprobe); } /* * Perform required fix-ups and disable singlestep. * Allow pending signals to take effect. */ static void handle_singlestep(struct uprobe_task *utask, struct pt_regs *regs) { struct uprobe *uprobe; int err = 0; uprobe = utask->active_uprobe; if (utask->state == UTASK_SSTEP_ACK) err = arch_uprobe_post_xol(&uprobe->arch, regs); else if (utask->state == UTASK_SSTEP_TRAPPED) arch_uprobe_abort_xol(&uprobe->arch, regs); else WARN_ON_ONCE(1); put_uprobe(uprobe); utask->active_uprobe = NULL; utask->state = UTASK_RUNNING; xol_free_insn_slot(current); spin_lock_irq(¤t->sighand->siglock); recalc_sigpending(); /* see uprobe_deny_signal() */ spin_unlock_irq(¤t->sighand->siglock); if (unlikely(err)) { uprobe_warn(current, "execute the probed insn, sending SIGILL."); force_sig(SIGILL); } } /* * On breakpoint hit, breakpoint notifier sets the TIF_UPROBE flag and * allows the thread to return from interrupt. After that handle_swbp() * sets utask->active_uprobe. * * On singlestep exception, singlestep notifier sets the TIF_UPROBE flag * and allows the thread to return from interrupt. * * While returning to userspace, thread notices the TIF_UPROBE flag and calls * uprobe_notify_resume(). */ void uprobe_notify_resume(struct pt_regs *regs) { struct uprobe_task *utask; clear_thread_flag(TIF_UPROBE); utask = current->utask; if (utask && utask->active_uprobe) handle_singlestep(utask, regs); else handle_swbp(regs); } /* * uprobe_pre_sstep_notifier gets called from interrupt context as part of * notifier mechanism. Set TIF_UPROBE flag and indicate breakpoint hit. */ int uprobe_pre_sstep_notifier(struct pt_regs *regs) { if (!current->mm) return 0; if (!test_bit(MMF_HAS_UPROBES, ¤t->mm->flags) && (!current->utask || !current->utask->return_instances)) return 0; set_thread_flag(TIF_UPROBE); return 1; } /* * uprobe_post_sstep_notifier gets called in interrupt context as part of notifier * mechanism. Set TIF_UPROBE flag and indicate completion of singlestep. */ int uprobe_post_sstep_notifier(struct pt_regs *regs) { struct uprobe_task *utask = current->utask; if (!current->mm || !utask || !utask->active_uprobe) /* task is currently not uprobed */ return 0; utask->state = UTASK_SSTEP_ACK; set_thread_flag(TIF_UPROBE); return 1; } static struct notifier_block uprobe_exception_nb = { .notifier_call = arch_uprobe_exception_notify, .priority = INT_MAX-1, /* notified after kprobes, kgdb */ }; void __init uprobes_init(void) { int i; for (i = 0; i < UPROBES_HASH_SZ; i++) mutex_init(&uprobes_mmap_mutex[i]); BUG_ON(register_die_notifier(&uprobe_exception_nb)); } |
| 151 68 57 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 | /* 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 Forwarding Information Base. * * Authors: A.N.Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #ifndef _NET_IP_FIB_H #define _NET_IP_FIB_H #include <net/flow.h> #include <linux/seq_file.h> #include <linux/rcupdate.h> #include <net/fib_notifier.h> #include <net/fib_rules.h> #include <net/inetpeer.h> #include <linux/percpu.h> #include <linux/notifier.h> #include <linux/refcount.h> struct fib_config { u8 fc_dst_len; u8 fc_tos; u8 fc_protocol; u8 fc_scope; u8 fc_type; u8 fc_gw_family; /* 2 bytes unused */ u32 fc_table; __be32 fc_dst; union { __be32 fc_gw4; struct in6_addr fc_gw6; }; int fc_oif; u32 fc_flags; u32 fc_priority; __be32 fc_prefsrc; u32 fc_nh_id; struct nlattr *fc_mx; struct rtnexthop *fc_mp; int fc_mx_len; int fc_mp_len; u32 fc_flow; u32 fc_nlflags; struct nl_info fc_nlinfo; struct nlattr *fc_encap; u16 fc_encap_type; }; struct fib_info; struct rtable; struct fib_nh_exception { struct fib_nh_exception __rcu *fnhe_next; int fnhe_genid; __be32 fnhe_daddr; u32 fnhe_pmtu; bool fnhe_mtu_locked; __be32 fnhe_gw; unsigned long fnhe_expires; struct rtable __rcu *fnhe_rth_input; struct rtable __rcu *fnhe_rth_output; unsigned long fnhe_stamp; struct rcu_head rcu; }; struct fnhe_hash_bucket { struct fib_nh_exception __rcu *chain; }; #define FNHE_HASH_SHIFT 11 #define FNHE_HASH_SIZE (1 << FNHE_HASH_SHIFT) #define FNHE_RECLAIM_DEPTH 5 struct fib_nh_common { struct net_device *nhc_dev; int nhc_oif; unsigned char nhc_scope; u8 nhc_family; u8 nhc_gw_family; unsigned char nhc_flags; struct lwtunnel_state *nhc_lwtstate; union { __be32 ipv4; struct in6_addr ipv6; } nhc_gw; int nhc_weight; atomic_t nhc_upper_bound; /* v4 specific, but allows fib6_nh with v4 routes */ struct rtable __rcu * __percpu *nhc_pcpu_rth_output; struct rtable __rcu *nhc_rth_input; struct fnhe_hash_bucket __rcu *nhc_exceptions; }; struct fib_nh { struct fib_nh_common nh_common; struct hlist_node nh_hash; struct fib_info *nh_parent; #ifdef CONFIG_IP_ROUTE_CLASSID __u32 nh_tclassid; #endif __be32 nh_saddr; int nh_saddr_genid; #define fib_nh_family nh_common.nhc_family #define fib_nh_dev nh_common.nhc_dev #define fib_nh_oif nh_common.nhc_oif #define fib_nh_flags nh_common.nhc_flags #define fib_nh_lws nh_common.nhc_lwtstate #define fib_nh_scope nh_common.nhc_scope #define fib_nh_gw_family nh_common.nhc_gw_family #define fib_nh_gw4 nh_common.nhc_gw.ipv4 #define fib_nh_gw6 nh_common.nhc_gw.ipv6 #define fib_nh_weight nh_common.nhc_weight #define fib_nh_upper_bound nh_common.nhc_upper_bound }; /* * This structure contains data shared by many of routes. */ struct nexthop; struct fib_info { struct hlist_node fib_hash; struct hlist_node fib_lhash; struct list_head nh_list; struct net *fib_net; int fib_treeref; refcount_t fib_clntref; unsigned int fib_flags; unsigned char fib_dead; unsigned char fib_protocol; unsigned char fib_scope; unsigned char fib_type; __be32 fib_prefsrc; u32 fib_tb_id; u32 fib_priority; struct dst_metrics *fib_metrics; #define fib_mtu fib_metrics->metrics[RTAX_MTU-1] #define fib_window fib_metrics->metrics[RTAX_WINDOW-1] #define fib_rtt fib_metrics->metrics[RTAX_RTT-1] #define fib_advmss fib_metrics->metrics[RTAX_ADVMSS-1] int fib_nhs; bool fib_nh_is_v6; bool nh_updated; struct nexthop *nh; struct rcu_head rcu; struct fib_nh fib_nh[0]; }; #ifdef CONFIG_IP_MULTIPLE_TABLES struct fib_rule; #endif struct fib_table; struct fib_result { __be32 prefix; unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; u32 tclassid; struct fib_nh_common *nhc; struct fib_info *fi; struct fib_table *table; struct hlist_head *fa_head; }; struct fib_result_nl { __be32 fl_addr; /* To be looked up*/ u32 fl_mark; unsigned char fl_tos; unsigned char fl_scope; unsigned char tb_id_in; unsigned char tb_id; /* Results */ unsigned char prefixlen; unsigned char nh_sel; unsigned char type; unsigned char scope; int err; }; #ifdef CONFIG_IP_MULTIPLE_TABLES #define FIB_TABLE_HASHSZ 256 #else #define FIB_TABLE_HASHSZ 2 #endif __be32 fib_info_update_nhc_saddr(struct net *net, struct fib_nh_common *nhc, unsigned char scope); __be32 fib_result_prefsrc(struct net *net, struct fib_result *res); #define FIB_RES_NHC(res) ((res).nhc) #define FIB_RES_DEV(res) (FIB_RES_NHC(res)->nhc_dev) #define FIB_RES_OIF(res) (FIB_RES_NHC(res)->nhc_oif) struct fib_entry_notifier_info { struct fib_notifier_info info; /* must be first */ u32 dst; int dst_len; struct fib_info *fi; u8 tos; u8 type; u32 tb_id; }; struct fib_nh_notifier_info { struct fib_notifier_info info; /* must be first */ struct fib_nh *fib_nh; }; int call_fib4_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int call_fib4_notifiers(struct net *net, enum fib_event_type event_type, struct fib_notifier_info *info); int __net_init fib4_notifier_init(struct net *net); void __net_exit fib4_notifier_exit(struct net *net); void fib_info_notify_update(struct net *net, struct nl_info *info); void fib_notify(struct net *net, struct notifier_block *nb); struct fib_table { struct hlist_node tb_hlist; u32 tb_id; int tb_num_default; struct rcu_head rcu; unsigned long *tb_data; unsigned long __data[0]; }; struct fib_dump_filter { u32 table_id; /* filter_set is an optimization that an entry is set */ bool filter_set; bool dump_routes; bool dump_exceptions; unsigned char protocol; unsigned char rt_type; unsigned int flags; struct net_device *dev; }; int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, struct fib_result *res, int fib_flags); int fib_table_insert(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_delete(struct net *, struct fib_table *, struct fib_config *, struct netlink_ext_ack *extack); int fib_table_dump(struct fib_table *table, struct sk_buff *skb, struct netlink_callback *cb, struct fib_dump_filter *filter); int fib_table_flush(struct net *net, struct fib_table *table, bool flush_all); struct fib_table *fib_trie_unmerge(struct fib_table *main_tb); void fib_table_flush_external(struct fib_table *table); void fib_free_table(struct fib_table *tb); #ifndef CONFIG_IP_MULTIPLE_TABLES #define TABLE_LOCAL_INDEX (RT_TABLE_LOCAL & (FIB_TABLE_HASHSZ - 1)) #define TABLE_MAIN_INDEX (RT_TABLE_MAIN & (FIB_TABLE_HASHSZ - 1)) static inline struct fib_table *fib_get_table(struct net *net, u32 id) { struct hlist_node *tb_hlist; struct hlist_head *ptr; ptr = id == RT_TABLE_LOCAL ? &net->ipv4.fib_table_hash[TABLE_LOCAL_INDEX] : &net->ipv4.fib_table_hash[TABLE_MAIN_INDEX]; tb_hlist = rcu_dereference_rtnl(hlist_first_rcu(ptr)); return hlist_entry(tb_hlist, struct fib_table, tb_hlist); } static inline struct fib_table *fib_new_table(struct net *net, u32 id) { return fib_get_table(net, id); } static inline int fib_lookup(struct net *net, const struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; rcu_read_lock(); tb = fib_get_table(net, RT_TABLE_MAIN); if (tb) err = fib_table_lookup(tb, flp, res, flags | FIB_LOOKUP_NOREF); if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } static inline bool fib4_rule_default(const struct fib_rule *rule) { return true; } static inline int fib4_rules_dump(struct net *net, struct notifier_block *nb) { return 0; } static inline unsigned int fib4_rules_seq_read(struct net *net) { return 0; } static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { return false; } #else /* CONFIG_IP_MULTIPLE_TABLES */ int __net_init fib4_rules_init(struct net *net); void __net_exit fib4_rules_exit(struct net *net); struct fib_table *fib_new_table(struct net *net, u32 id); struct fib_table *fib_get_table(struct net *net, u32 id); int __fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags); static inline int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res, unsigned int flags) { struct fib_table *tb; int err = -ENETUNREACH; flags |= FIB_LOOKUP_NOREF; if (net->ipv4.fib_has_custom_rules) return __fib_lookup(net, flp, res, flags); rcu_read_lock(); res->tclassid = 0; tb = rcu_dereference_rtnl(net->ipv4.fib_main); if (tb) err = fib_table_lookup(tb, flp, res, flags); if (!err) goto out; tb = rcu_dereference_rtnl(net->ipv4.fib_default); if (tb) err = fib_table_lookup(tb, flp, res, flags); out: if (err == -EAGAIN) err = -ENETUNREACH; rcu_read_unlock(); return err; } bool fib4_rule_default(const struct fib_rule *rule); int fib4_rules_dump(struct net *net, struct notifier_block *nb); unsigned int fib4_rules_seq_read(struct net *net); static inline bool fib4_rules_early_flow_dissect(struct net *net, struct sk_buff *skb, struct flowi4 *fl4, struct flow_keys *flkeys) { unsigned int flag = FLOW_DISSECTOR_F_STOP_AT_ENCAP; if (!net->ipv4.fib_rules_require_fldissect) return false; skb_flow_dissect_flow_keys(skb, flkeys, flag); fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; fl4->flowi4_proto = flkeys->basic.ip_proto; return true; } #endif /* CONFIG_IP_MULTIPLE_TABLES */ /* Exported by fib_frontend.c */ extern const struct nla_policy rtm_ipv4_policy[]; void ip_fib_init(void); int fib_gw_from_via(struct fib_config *cfg, struct nlattr *nla, struct netlink_ext_ack *extack); __be32 fib_compute_spec_dst(struct sk_buff *skb); bool fib_info_nh_uses_dev(struct fib_info *fi, const struct net_device *dev); int fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, struct in_device *idev, u32 *itag); #ifdef CONFIG_IP_ROUTE_CLASSID static inline int fib_num_tclassid_users(struct net *net) { return atomic_read(&net->ipv4.fib_num_tclassid_users); } #else static inline int fib_num_tclassid_users(struct net *net) { return 0; } #endif int fib_unmerge(struct net *net); static inline bool nhc_l3mdev_matches_dev(const struct fib_nh_common *nhc, const struct net_device *dev) { if (nhc->nhc_dev == dev || l3mdev_master_ifindex_rcu(nhc->nhc_dev) == dev->ifindex) return true; return false; } /* Exported by fib_semantics.c */ int ip_fib_check_default(__be32 gw, struct net_device *dev); int fib_sync_down_dev(struct net_device *dev, unsigned long event, bool force); int fib_sync_down_addr(struct net_device *dev, __be32 local); int fib_sync_up(struct net_device *dev, unsigned char nh_flags); void fib_sync_mtu(struct net_device *dev, u32 orig_mtu); void fib_nhc_update_mtu(struct fib_nh_common *nhc, u32 new, u32 orig); #ifdef CONFIG_IP_ROUTE_MULTIPATH int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, const struct sk_buff *skb, struct flow_keys *flkeys); #endif int fib_check_nh(struct net *net, struct fib_nh *nh, u32 table, u8 scope, struct netlink_ext_ack *extack); void fib_select_multipath(struct fib_result *res, int hash); void fib_select_path(struct net *net, struct fib_result *res, struct flowi4 *fl4, const struct sk_buff *skb); int fib_nh_init(struct net *net, struct fib_nh *fib_nh, struct fib_config *cfg, int nh_weight, struct netlink_ext_ack *extack); void fib_nh_release(struct net *net, struct fib_nh *fib_nh); int fib_nh_common_init(struct fib_nh_common *nhc, struct nlattr *fc_encap, u16 fc_encap_type, void *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack); void fib_nh_common_release(struct fib_nh_common *nhc); /* Exported by fib_trie.c */ void fib_trie_init(void); struct fib_table *fib_trie_table(u32 id, struct fib_table *alias); static inline void fib_combine_itag(u32 *itag, const struct fib_result *res) { #ifdef CONFIG_IP_ROUTE_CLASSID struct fib_nh_common *nhc = res->nhc; #ifdef CONFIG_IP_MULTIPLE_TABLES u32 rtag; #endif if (nhc->nhc_family == AF_INET) { struct fib_nh *nh; nh = container_of(nhc, struct fib_nh, nh_common); *itag = nh->nh_tclassid << 16; } else { *itag = 0; } #ifdef CONFIG_IP_MULTIPLE_TABLES rtag = res->tclassid; if (*itag == 0) *itag = (rtag<<16); *itag |= (rtag>>16); #endif #endif } void fib_flush(struct net *net); void free_fib_info(struct fib_info *fi); static inline void fib_info_hold(struct fib_info *fi) { refcount_inc(&fi->fib_clntref); } static inline void fib_info_put(struct fib_info *fi) { if (refcount_dec_and_test(&fi->fib_clntref)) free_fib_info(fi); } #ifdef CONFIG_PROC_FS int __net_init fib_proc_init(struct net *net); void __net_exit fib_proc_exit(struct net *net); #else static inline int fib_proc_init(struct net *net) { return 0; } static inline void fib_proc_exit(struct net *net) { } #endif u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr); int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, struct fib_dump_filter *filter, struct netlink_callback *cb); int fib_nexthop_info(struct sk_buff *skb, const struct fib_nh_common *nh, u8 rt_family, unsigned char *flags, bool skip_oif); int fib_add_nexthop(struct sk_buff *skb, const struct fib_nh_common *nh, int nh_weight, u8 rt_family, u32 nh_tclassid); #endif /* _NET_FIB_H */ |
| 7 7 7 7 7 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 | // SPDX-License-Identifier: GPL-2.0 /* * SUCS NET3: * * Generic stream handling routines. These are generic for most * protocols. Even IP. Tonight 8-). * This is used because TCP, LLC (others too) layer all have mostly * identical sendmsg() and recvmsg() code. * So we (will) share it here. * * Authors: Arnaldo Carvalho de Melo <acme@conectiva.com.br> * (from old tcp.c code) * Alan Cox <alan@lxorguk.ukuu.org.uk> (Borrowed comments 8-)) */ #include <linux/module.h> #include <linux/sched/signal.h> #include <linux/net.h> #include <linux/signal.h> #include <linux/tcp.h> #include <linux/wait.h> #include <net/sock.h> /** * sk_stream_write_space - stream socket write_space callback. * @sk: socket * * FIXME: write proper description */ void sk_stream_write_space(struct sock *sk) { struct socket *sock = sk->sk_socket; struct socket_wq *wq; if (__sk_stream_is_writeable(sk, 1) && sock) { clear_bit(SOCK_NOSPACE, &sock->flags); rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_poll(&wq->wait, EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND); if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN)) sock_wake_async(wq, SOCK_WAKE_SPACE, POLL_OUT); rcu_read_unlock(); } } /** * sk_stream_wait_connect - Wait for a socket to get into the connected state * @sk: sock to wait on * @timeo_p: for how long to wait * * Must be called with the socket locked. */ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct task_struct *tsk = current; int done; do { int err = sock_error(sk); if (err) return err; if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV)) return -EPIPE; if (!*timeo_p) return -EAGAIN; if (signal_pending(tsk)) return sock_intr_errno(*timeo_p); add_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending++; done = sk_wait_event(sk, timeo_p, !sk->sk_err && !((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)), &wait); remove_wait_queue(sk_sleep(sk), &wait); sk->sk_write_pending--; } while (!done); return 0; } EXPORT_SYMBOL(sk_stream_wait_connect); /** * sk_stream_closing - Return 1 if we still have things to send in our buffers. * @sk: socket to verify */ static inline int sk_stream_closing(struct sock *sk) { return (1 << sk->sk_state) & (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK); } void sk_stream_wait_close(struct sock *sk, long timeout) { if (timeout) { DEFINE_WAIT_FUNC(wait, woken_wake_function); add_wait_queue(sk_sleep(sk), &wait); do { if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk), &wait)) break; } while (!signal_pending(current) && timeout); remove_wait_queue(sk_sleep(sk), &wait); } } EXPORT_SYMBOL(sk_stream_wait_close); /** * sk_stream_wait_memory - Wait for more memory for a socket * @sk: socket to wait for memory * @timeo_p: for how long */ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) { int err = 0; long vm_wait = 0; long current_timeo = *timeo_p; DEFINE_WAIT_FUNC(wait, woken_wake_function); if (sk_stream_memory_free(sk)) current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2; add_wait_queue(sk_sleep(sk), &wait); while (1) { sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto do_error; if (!*timeo_p) goto do_eagain; if (signal_pending(current)) goto do_interrupted; sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); if (sk_stream_memory_free(sk) && !vm_wait) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; sk_wait_event(sk, ¤t_timeo, sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN) || (sk_stream_memory_free(sk) && !vm_wait), &wait); sk->sk_write_pending--; if (vm_wait) { vm_wait -= current_timeo; current_timeo = *timeo_p; if (current_timeo != MAX_SCHEDULE_TIMEOUT && (current_timeo -= vm_wait) < 0) current_timeo = 0; vm_wait = 0; } *timeo_p = current_timeo; } out: if (!sock_flag(sk, SOCK_DEAD)) remove_wait_queue(sk_sleep(sk), &wait); return err; do_error: err = -EPIPE; goto out; do_eagain: /* Make sure that whenever EAGAIN is returned, EPOLLOUT event can * be generated later. * When TCP receives ACK packets that make room, tcp_check_space() * only calls tcp_new_space() if SOCK_NOSPACE is set. */ set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); err = -EAGAIN; goto out; do_interrupted: err = sock_intr_errno(*timeo_p); goto out; } EXPORT_SYMBOL(sk_stream_wait_memory); int sk_stream_error(struct sock *sk, int flags, int err) { if (err == -EPIPE) err = sock_error(sk) ? : -EPIPE; if (err == -EPIPE && !(flags & MSG_NOSIGNAL)) send_sig(SIGPIPE, current, 0); return err; } EXPORT_SYMBOL(sk_stream_error); void sk_stream_kill_queues(struct sock *sk) { /* First the read buffer. */ __skb_queue_purge(&sk->sk_receive_queue); /* Next, the error queue. * We need to use queue lock, because other threads might * add packets to the queue without socket lock being held. */ skb_queue_purge(&sk->sk_error_queue); /* Next, the write queue. */ WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ sk_mem_reclaim(sk); WARN_ON(sk->sk_wmem_queued); /* It is _impossible_ for the backlog to contain anything * when we get here. All user references to this socket * have gone away, only the net layer knows can touch it. */ } EXPORT_SYMBOL(sk_stream_kill_queues); |
| 12 12 12 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/in6.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->ipv6_v6only) { int val = 1; err = kernel_setsockopt(sock, IPPROTO_IPV6, IPV6_V6ONLY, (char *) &val, sizeof(val)); if (err < 0) goto error; } if (cfg->bind_ifindex) { err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTOIFINDEX, (void *)&cfg->bind_ifindex, sizeof(cfg->bind_ifindex)); if (err < 0) goto error; } udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr *)&udp6_addr, sizeof(udp6_addr), 0); } if (err < 0) goto error; udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL_GPL(udp_sock_create6); int udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, struct in6_addr *saddr, struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck) { struct udphdr *uh; struct ipv6hdr *ip6h; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6tunnel_xmit(sk, skb, dev); return 0; } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); MODULE_LICENSE("GPL"); |
| 14 2 3 3 6 6 6 2 4 1 1 1 1 2 6 16 20 20 1 7 2 1 3 1 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 | // SPDX-License-Identifier: GPL-2.0 /* XSKMAP used for AF_XDP sockets * Copyright(c) 2018 Intel Corporation. */ #include <linux/bpf.h> #include <linux/capability.h> #include <net/xdp_sock.h> #include <linux/slab.h> #include <linux/sched.h> struct xsk_map { struct bpf_map map; struct xdp_sock **xsk_map; struct list_head __percpu *flush_list; spinlock_t lock; /* Synchronize map updates */ }; int xsk_map_inc(struct xsk_map *map) { struct bpf_map *m = &map->map; m = bpf_map_inc(m, false); return PTR_ERR_OR_ZERO(m); } void xsk_map_put(struct xsk_map *map) { bpf_map_put(&map->map); } static struct xsk_map_node *xsk_map_node_alloc(struct xsk_map *map, struct xdp_sock **map_entry) { struct xsk_map_node *node; int err; node = kzalloc(sizeof(*node), GFP_ATOMIC | __GFP_NOWARN); if (!node) return ERR_PTR(-ENOMEM); err = xsk_map_inc(map); if (err) { kfree(node); return ERR_PTR(err); } node->map = map; node->map_entry = map_entry; return node; } static void xsk_map_node_free(struct xsk_map_node *node) { xsk_map_put(node->map); kfree(node); } static void xsk_map_sock_add(struct xdp_sock *xs, struct xsk_map_node *node) { spin_lock_bh(&xs->map_list_lock); list_add_tail(&node->node, &xs->map_list); spin_unlock_bh(&xs->map_list_lock); } static void xsk_map_sock_delete(struct xdp_sock *xs, struct xdp_sock **map_entry) { struct xsk_map_node *n, *tmp; spin_lock_bh(&xs->map_list_lock); list_for_each_entry_safe(n, tmp, &xs->map_list, node) { if (map_entry == n->map_entry) { list_del(&n->node); xsk_map_node_free(n); } } spin_unlock_bh(&xs->map_list_lock); } static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) { struct xsk_map *m; int cpu, err; u64 cost; if (!capable(CAP_NET_ADMIN)) return ERR_PTR(-EPERM); if (attr->max_entries == 0 || attr->key_size != 4 || attr->value_size != 4 || attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)) return ERR_PTR(-EINVAL); m = kzalloc(sizeof(*m), GFP_USER); if (!m) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&m->map, attr); spin_lock_init(&m->lock); cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); cost += sizeof(struct list_head) * num_possible_cpus(); /* Notice returns -EPERM on if map size is larger than memlock limit */ err = bpf_map_charge_init(&m->map.memory, cost); if (err) goto free_m; err = -ENOMEM; m->flush_list = alloc_percpu(struct list_head); if (!m->flush_list) goto free_charge; for_each_possible_cpu(cpu) INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); m->xsk_map = bpf_map_area_alloc(m->map.max_entries * sizeof(struct xdp_sock *), m->map.numa_node); if (!m->xsk_map) goto free_percpu; return &m->map; free_percpu: free_percpu(m->flush_list); free_charge: bpf_map_charge_finish(&m->map.memory); free_m: kfree(m); return ERR_PTR(err); } static void xsk_map_free(struct bpf_map *map) { struct xsk_map *m = container_of(map, struct xsk_map, map); bpf_clear_redirect_map(map); synchronize_net(); free_percpu(m->flush_list); bpf_map_area_free(m->xsk_map); kfree(m); } static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct xsk_map *m = container_of(map, struct xsk_map, map); u32 index = key ? *(u32 *)key : U32_MAX; u32 *next = next_key; if (index >= m->map.max_entries) { *next = 0; return 0; } if (index == m->map.max_entries - 1) return -ENOENT; *next = index + 1; return 0; } struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct xdp_sock *xs; if (key >= map->max_entries) return NULL; xs = READ_ONCE(m->xsk_map[key]); return xs; } int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, struct xdp_sock *xs) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct list_head *flush_list = this_cpu_ptr(m->flush_list); int err; err = xsk_rcv(xs, xdp); if (err) return err; if (!xs->flush_node.prev) list_add(&xs->flush_node, flush_list); return 0; } void __xsk_map_flush(struct bpf_map *map) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct list_head *flush_list = this_cpu_ptr(m->flush_list); struct xdp_sock *xs, *tmp; list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { xsk_flush(xs); __list_del_clearprev(&xs->flush_node); } } static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) { WARN_ON_ONCE(!rcu_read_lock_held()); return __xsk_map_lookup_elem(map, *(u32 *)key); } static void *xsk_map_lookup_elem_sys_only(struct bpf_map *map, void *key) { return ERR_PTR(-EOPNOTSUPP); } static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct xdp_sock *xs, *old_xs, **map_entry; u32 i = *(u32 *)key, fd = *(u32 *)value; struct xsk_map_node *node; struct socket *sock; int err; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; if (unlikely(i >= m->map.max_entries)) return -E2BIG; sock = sockfd_lookup(fd, &err); if (!sock) return err; if (sock->sk->sk_family != PF_XDP) { sockfd_put(sock); return -EOPNOTSUPP; } xs = (struct xdp_sock *)sock->sk; if (!xsk_is_setup_for_bpf_map(xs)) { sockfd_put(sock); return -EOPNOTSUPP; } map_entry = &m->xsk_map[i]; node = xsk_map_node_alloc(m, map_entry); if (IS_ERR(node)) { sockfd_put(sock); return PTR_ERR(node); } spin_lock_bh(&m->lock); old_xs = READ_ONCE(*map_entry); if (old_xs == xs) { err = 0; goto out; } else if (old_xs && map_flags == BPF_NOEXIST) { err = -EEXIST; goto out; } else if (!old_xs && map_flags == BPF_EXIST) { err = -ENOENT; goto out; } xsk_map_sock_add(xs, node); WRITE_ONCE(*map_entry, xs); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); sockfd_put(sock); return 0; out: spin_unlock_bh(&m->lock); sockfd_put(sock); xsk_map_node_free(node); return err; } static int xsk_map_delete_elem(struct bpf_map *map, void *key) { struct xsk_map *m = container_of(map, struct xsk_map, map); struct xdp_sock *old_xs, **map_entry; int k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; spin_lock_bh(&m->lock); map_entry = &m->xsk_map[k]; old_xs = xchg(map_entry, NULL); if (old_xs) xsk_map_sock_delete(old_xs, map_entry); spin_unlock_bh(&m->lock); return 0; } void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs, struct xdp_sock **map_entry) { spin_lock_bh(&map->lock); if (READ_ONCE(*map_entry) == xs) { WRITE_ONCE(*map_entry, NULL); xsk_map_sock_delete(xs, map_entry); } spin_unlock_bh(&map->lock); } const struct bpf_map_ops xsk_map_ops = { .map_alloc = xsk_map_alloc, .map_free = xsk_map_free, .map_get_next_key = xsk_map_get_next_key, .map_lookup_elem = xsk_map_lookup_elem, .map_lookup_elem_sys_only = xsk_map_lookup_elem_sys_only, .map_update_elem = xsk_map_update_elem, .map_delete_elem = xsk_map_delete_elem, .map_check_btf = map_check_no_btf, }; |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_TASK_STACK_H #define _LINUX_SCHED_TASK_STACK_H /* * task->stack (kernel stack) handling interfaces: */ #include <linux/sched.h> #include <linux/magic.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * When accessing the stack of a non-current task that might exit, use * try_get_task_stack() instead. task_stack_page will return a pointer * that could get freed out from under you. */ static __always_inline void *task_stack_page(const struct task_struct *task) { return task->stack; } #define setup_thread_stack(new,old) do { } while(0) static __always_inline unsigned long *end_of_stack(const struct task_struct *task) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task->stack + THREAD_SIZE) - 1; #else return task->stack; #endif } #elif !defined(__HAVE_THREAD_FUNCTIONS) #define task_stack_page(task) ((void *)(task)->stack) static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org) { *task_thread_info(p) = *task_thread_info(org); task_thread_info(p)->task = p; } /* * Return the address of the last usable long on the stack. * * When the stack grows down, this is just above the thread * info struct. Going any lower will corrupt the threadinfo. * * When the stack grows up, this is the highest address. * Beyond that position, we corrupt data on the next page. */ static inline unsigned long *end_of_stack(struct task_struct *p) { #ifdef CONFIG_STACK_GROWSUP return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1; #else return (unsigned long *)(task_thread_info(p) + 1); #endif } #endif #ifdef CONFIG_THREAD_INFO_IN_TASK static inline void *try_get_task_stack(struct task_struct *tsk) { return refcount_inc_not_zero(&tsk->stack_refcount) ? task_stack_page(tsk) : NULL; } extern void put_task_stack(struct task_struct *tsk); #else static inline void *try_get_task_stack(struct task_struct *tsk) { return task_stack_page(tsk); } static inline void put_task_stack(struct task_struct *tsk) {} #endif #define task_stack_end_corrupted(task) \ (*(end_of_stack(task)) != STACK_END_MAGIC) static inline int object_is_on_stack(const void *obj) { void *stack = task_stack_page(current); return (obj >= stack) && (obj < (stack + THREAD_SIZE)); } extern void thread_stack_cache_init(void); #ifdef CONFIG_DEBUG_STACK_USAGE static inline unsigned long stack_not_used(struct task_struct *p) { unsigned long *n = end_of_stack(p); do { /* Skip over canary */ # ifdef CONFIG_STACK_GROWSUP n--; # else n++; # endif } while (!*n); # ifdef CONFIG_STACK_GROWSUP return (unsigned long)end_of_stack(p) - (unsigned long)n; # else return (unsigned long)n - (unsigned long)end_of_stack(p); # endif } #endif extern void set_task_stack_end_magic(struct task_struct *tsk); #ifndef __HAVE_ARCH_KSTACK_END static inline int kstack_end(void *addr) { /* Reliable end of stack detection: * Some APM bios versions misalign the stack */ return !(((unsigned long)addr+sizeof(void*)-1) & (THREAD_SIZE-sizeof(void*))); } #endif #endif /* _LINUX_SCHED_TASK_STACK_H */ |
| 1370 1259 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PGTABLE_64_H #define _ASM_X86_PGTABLE_64_H #include <linux/const.h> #include <asm/pgtable_64_types.h> #ifndef __ASSEMBLY__ /* * This file contains the functions and defines necessary to modify and use * the x86-64 page table tree. */ #include <asm/processor.h> #include <linux/bitops.h> #include <linux/threads.h> #include <asm/fixmap.h> extern p4d_t level4_kernel_pgt[512]; extern p4d_t level4_ident_pgt[512]; extern pud_t level3_kernel_pgt[512]; extern pud_t level3_ident_pgt[512]; extern pmd_t level2_kernel_pgt[512]; extern pmd_t level2_fixmap_pgt[512]; extern pmd_t level2_ident_pgt[512]; extern pte_t level1_fixmap_pgt[512 * FIXMAP_PMD_NUM]; extern pgd_t init_top_pgt[]; #define swapper_pg_dir init_top_pgt extern void paging_init(void); static inline void sync_initial_page_table(void) { } #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pte_val(e)) #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pmd_val(e)) #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pud_val(e)) #if CONFIG_PGTABLE_LEVELS >= 5 #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %p(%016lx)\n", \ __FILE__, __LINE__, &(e), p4d_val(e)) #endif #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %p(%016lx)\n", \ __FILE__, __LINE__, &(e), pgd_val(e)) struct mm_struct; void set_pte_vaddr_p4d(p4d_t *p4d_page, unsigned long vaddr, pte_t new_pte); void set_pte_vaddr_pud(pud_t *pud_page, unsigned long vaddr, pte_t new_pte); static inline void native_set_pte(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void native_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { native_set_pte(ptep, native_make_pte(0)); } static inline void native_set_pte_atomic(pte_t *ptep, pte_t pte) { native_set_pte(ptep, pte); } static inline void native_set_pmd(pmd_t *pmdp, pmd_t pmd) { WRITE_ONCE(*pmdp, pmd); } static inline void native_pmd_clear(pmd_t *pmd) { native_set_pmd(pmd, native_make_pmd(0)); } static inline pte_t native_ptep_get_and_clear(pte_t *xp) { #ifdef CONFIG_SMP return native_make_pte(xchg(&xp->pte, 0)); #else /* native_local_ptep_get_and_clear, but duplicated because of cyclic dependency */ pte_t ret = *xp; native_pte_clear(NULL, 0, xp); return ret; #endif } static inline pmd_t native_pmdp_get_and_clear(pmd_t *xp) { #ifdef CONFIG_SMP return native_make_pmd(xchg(&xp->pmd, 0)); #else /* native_local_pmdp_get_and_clear, but duplicated because of cyclic dependency */ pmd_t ret = *xp; native_pmd_clear(xp); return ret; #endif } static inline void native_set_pud(pud_t *pudp, pud_t pud) { WRITE_ONCE(*pudp, pud); } static inline void native_pud_clear(pud_t *pud) { native_set_pud(pud, native_make_pud(0)); } static inline pud_t native_pudp_get_and_clear(pud_t *xp) { #ifdef CONFIG_SMP return native_make_pud(xchg(&xp->pud, 0)); #else /* native_local_pudp_get_and_clear, * but duplicated because of cyclic dependency */ pud_t ret = *xp; native_pud_clear(xp); return ret; #endif } static inline void native_set_p4d(p4d_t *p4dp, p4d_t p4d) { pgd_t pgd; if (pgtable_l5_enabled() || !IS_ENABLED(CONFIG_PAGE_TABLE_ISOLATION)) { WRITE_ONCE(*p4dp, p4d); return; } pgd = native_make_pgd(native_p4d_val(p4d)); pgd = pti_set_user_pgtbl((pgd_t *)p4dp, pgd); WRITE_ONCE(*p4dp, native_make_p4d(native_pgd_val(pgd))); } static inline void native_p4d_clear(p4d_t *p4d) { native_set_p4d(p4d, native_make_p4d(0)); } static inline void native_set_pgd(pgd_t *pgdp, pgd_t pgd) { WRITE_ONCE(*pgdp, pti_set_user_pgtbl(pgdp, pgd)); } static inline void native_pgd_clear(pgd_t *pgd) { native_set_pgd(pgd, native_make_pgd(0)); } extern void sync_global_pgds(unsigned long start, unsigned long end); /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ /* * Level 4 access. */ #define mk_kernel_pgd(address) __pgd((address) | _KERNPG_TABLE) /* PUD - Level3 access */ /* PMD - Level 2 access */ /* PTE - Level 1 access. */ /* x86-64 always has all page tables mapped. */ #define pte_offset_map(dir, address) pte_offset_kernel((dir), (address)) #define pte_unmap(pte) ((void)(pte))/* NOP */ /* * Encode and de-code a swap entry * * | ... | 11| 10| 9|8|7|6|5| 4| 3|2| 1|0| <- bit number * | ... |SW3|SW2|SW1|G|L|D|A|CD|WT|U| W|P| <- bit names * | TYPE (59-63) | ~OFFSET (9-58) |0|0|X|X| X| X|X|SD|0| <- swp entry * * G (8) is aliased and used as a PROT_NONE indicator for * !present ptes. We need to start storing swap entries above * there. We also need to avoid using A and D because of an * erratum where they can be incorrectly set by hardware on * non-present PTEs. * * SD (1) in swp entry is used to store soft dirty bit, which helps us * remember soft dirty over page migration * * Bit 7 in swp entry should be 0 because pmd_present checks not only P, * but also L and G. * * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define SWP_TYPE_BITS 5 #define SWP_OFFSET_FIRST_BIT (_PAGE_BIT_PROTNONE + 1) /* We always extract/encode the offset by shifting it all the way up, and then down again */ #define SWP_OFFSET_SHIFT (SWP_OFFSET_FIRST_BIT+SWP_TYPE_BITS) #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > SWP_TYPE_BITS) /* Extract the high bits for type */ #define __swp_type(x) ((x).val >> (64 - SWP_TYPE_BITS)) /* Shift up (to get rid of type), then down to get value */ #define __swp_offset(x) (~(x).val << SWP_TYPE_BITS >> SWP_OFFSET_SHIFT) /* * Shift the offset up "too far" by TYPE bits, then down again * The offset is inverted by a binary not operation to make the high * physical bits set. */ #define __swp_entry(type, offset) ((swp_entry_t) { \ (~(unsigned long)(offset) << SWP_OFFSET_SHIFT >> SWP_TYPE_BITS) \ | ((unsigned long)(type) << (64-SWP_TYPE_BITS)) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val((pte)) }) #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val((pmd)) }) #define __swp_entry_to_pte(x) ((pte_t) { .pte = (x).val }) #define __swp_entry_to_pmd(x) ((pmd_t) { .pmd = (x).val }) extern int kern_addr_valid(unsigned long addr); extern void cleanup_highmap(void); #define HAVE_ARCH_UNMAPPED_AREA #define HAVE_ARCH_UNMAPPED_AREA_TOPDOWN #define PAGE_AGP PAGE_KERNEL_NOCACHE #define HAVE_PAGE_AGP 1 /* fs/proc/kcore.c */ #define kc_vaddr_to_offset(v) ((v) & __VIRTUAL_MASK) #define kc_offset_to_vaddr(o) ((o) | ~__VIRTUAL_MASK) #define __HAVE_ARCH_PTE_SAME #define vmemmap ((struct page *)VMEMMAP_START) extern void init_extra_mapping_uc(unsigned long phys, unsigned long size); extern void init_extra_mapping_wb(unsigned long phys, unsigned long size); #define gup_fast_permitted gup_fast_permitted static inline bool gup_fast_permitted(unsigned long start, unsigned long end) { if (end >> __VIRTUAL_MASK_SHIFT) return false; return true; } #include <asm/pgtable-invert.h> #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PGTABLE_64_H */ |
| 24 51 13 35 43 28 15 70 70 65 65 32 34 34 19 19 62 41 60 12 1 6 8 58 33 33 58 37 58 34 13 4 13 13 13 13 27 21 33 23 54 54 40 54 26 26 26 2 26 27 13 13 16 27 26 3 15 54 26 72 71 59 59 38 59 54 12 26 52 59 47 27 55 26 13 13 54 6 6 6 6 6 1 1 52 52 61 61 47 19 49 26 67 67 67 11 65 65 47 39 39 47 47 3 13 13 13 49 25 26 63 1 64 42 42 3 13 13 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 | /* * net/tipc/group.c: TIPC group messaging code * * Copyright (c) 2017, Ericsson AB * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "core.h" #include "addr.h" #include "group.h" #include "bcast.h" #include "topsrv.h" #include "msg.h" #include "socket.h" #include "node.h" #include "name_table.h" #include "subscr.h" #define ADV_UNIT (((MAX_MSG_SIZE + MAX_H_SIZE) / FLOWCTL_BLK_SZ) + 1) #define ADV_IDLE ADV_UNIT #define ADV_ACTIVE (ADV_UNIT * 12) enum mbr_state { MBR_JOINING, MBR_PUBLISHED, MBR_JOINED, MBR_PENDING, MBR_ACTIVE, MBR_RECLAIMING, MBR_REMITTED, MBR_LEAVING }; struct tipc_member { struct rb_node tree_node; struct list_head list; struct list_head small_win; struct sk_buff_head deferredq; struct tipc_group *group; u32 node; u32 port; u32 instance; enum mbr_state state; u16 advertised; u16 window; u16 bc_rcv_nxt; u16 bc_syncpt; u16 bc_acked; }; struct tipc_group { struct rb_root members; struct list_head small_win; struct list_head pending; struct list_head active; struct tipc_nlist dests; struct net *net; int subid; u32 type; u32 instance; u32 scope; u32 portid; u16 member_cnt; u16 active_cnt; u16 max_active; u16 bc_snd_nxt; u16 bc_ackers; bool *open; bool loopback; bool events; }; static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq); static void tipc_group_open(struct tipc_member *m, bool *wakeup) { *wakeup = false; if (list_empty(&m->small_win)) return; list_del_init(&m->small_win); *m->group->open = true; *wakeup = true; } static void tipc_group_decr_active(struct tipc_group *grp, struct tipc_member *m) { if (m->state == MBR_ACTIVE || m->state == MBR_RECLAIMING || m->state == MBR_REMITTED) grp->active_cnt--; } static int tipc_group_rcvbuf_limit(struct tipc_group *grp) { int max_active, active_pool, idle_pool; int mcnt = grp->member_cnt + 1; /* Limit simultaneous reception from other members */ max_active = min(mcnt / 8, 64); max_active = max(max_active, 16); grp->max_active = max_active; /* Reserve blocks for active and idle members */ active_pool = max_active * ADV_ACTIVE; idle_pool = (mcnt - max_active) * ADV_IDLE; /* Scale to bytes, considering worst-case truesize/msgsize ratio */ return (active_pool + idle_pool) * FLOWCTL_BLK_SZ * 4; } u16 tipc_group_bc_snd_nxt(struct tipc_group *grp) { return grp->bc_snd_nxt; } static bool tipc_group_is_receiver(struct tipc_member *m) { return m && m->state != MBR_JOINING && m->state != MBR_LEAVING; } static bool tipc_group_is_sender(struct tipc_member *m) { return m && m->state != MBR_JOINING && m->state != MBR_PUBLISHED; } u32 tipc_group_exclude(struct tipc_group *grp) { if (!grp->loopback) return grp->portid; return 0; } struct tipc_group *tipc_group_create(struct net *net, u32 portid, struct tipc_group_req *mreq, bool *group_is_open) { u32 filter = TIPC_SUB_PORTS | TIPC_SUB_NO_STATUS; bool global = mreq->scope != TIPC_NODE_SCOPE; struct tipc_group *grp; u32 type = mreq->type; grp = kzalloc(sizeof(*grp), GFP_ATOMIC); if (!grp) return NULL; tipc_nlist_init(&grp->dests, tipc_own_addr(net)); INIT_LIST_HEAD(&grp->small_win); INIT_LIST_HEAD(&grp->active); INIT_LIST_HEAD(&grp->pending); grp->members = RB_ROOT; grp->net = net; grp->portid = portid; grp->type = type; grp->instance = mreq->instance; grp->scope = mreq->scope; grp->loopback = mreq->flags & TIPC_GROUP_LOOPBACK; grp->events = mreq->flags & TIPC_GROUP_MEMBER_EVTS; grp->open = group_is_open; *grp->open = false; filter |= global ? TIPC_SUB_CLUSTER_SCOPE : TIPC_SUB_NODE_SCOPE; if (tipc_topsrv_kern_subscr(net, portid, type, 0, ~0, filter, &grp->subid)) return grp; kfree(grp); return NULL; } void tipc_group_join(struct net *net, struct tipc_group *grp, int *sk_rcvbuf) { struct rb_root *tree = &grp->members; struct tipc_member *m, *tmp; struct sk_buff_head xmitq; __skb_queue_head_init(&xmitq); rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, &xmitq); tipc_group_update_member(m, 0); } tipc_node_distr_xmit(net, &xmitq); *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } void tipc_group_delete(struct net *net, struct tipc_group *grp) { struct rb_root *tree = &grp->members; struct tipc_member *m, *tmp; struct sk_buff_head xmitq; __skb_queue_head_init(&xmitq); rbtree_postorder_for_each_entry_safe(m, tmp, tree, tree_node) { tipc_group_proto_xmit(grp, m, GRP_LEAVE_MSG, &xmitq); __skb_queue_purge(&m->deferredq); list_del(&m->list); kfree(m); } tipc_node_distr_xmit(net, &xmitq); tipc_nlist_purge(&grp->dests); tipc_topsrv_kern_unsubscr(net, grp->subid); kfree(grp); } static struct tipc_member *tipc_group_find_member(struct tipc_group *grp, u32 node, u32 port) { struct rb_node *n = grp->members.rb_node; u64 nkey, key = (u64)node << 32 | port; struct tipc_member *m; while (n) { m = container_of(n, struct tipc_member, tree_node); nkey = (u64)m->node << 32 | m->port; if (key < nkey) n = n->rb_left; else if (key > nkey) n = n->rb_right; else return m; } return NULL; } static struct tipc_member *tipc_group_find_dest(struct tipc_group *grp, u32 node, u32 port) { struct tipc_member *m; m = tipc_group_find_member(grp, node, port); if (m && tipc_group_is_receiver(m)) return m; return NULL; } static struct tipc_member *tipc_group_find_node(struct tipc_group *grp, u32 node) { struct tipc_member *m; struct rb_node *n; for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); if (m->node == node) return m; } return NULL; } static int tipc_group_add_to_tree(struct tipc_group *grp, struct tipc_member *m) { u64 nkey, key = (u64)m->node << 32 | m->port; struct rb_node **n, *parent = NULL; struct tipc_member *tmp; n = &grp->members.rb_node; while (*n) { tmp = container_of(*n, struct tipc_member, tree_node); parent = *n; tmp = container_of(parent, struct tipc_member, tree_node); nkey = (u64)tmp->node << 32 | tmp->port; if (key < nkey) n = &(*n)->rb_left; else if (key > nkey) n = &(*n)->rb_right; else return -EEXIST; } rb_link_node(&m->tree_node, parent, n); rb_insert_color(&m->tree_node, &grp->members); return 0; } static struct tipc_member *tipc_group_create_member(struct tipc_group *grp, u32 node, u32 port, u32 instance, int state) { struct tipc_member *m; int ret; m = kzalloc(sizeof(*m), GFP_ATOMIC); if (!m) return NULL; INIT_LIST_HEAD(&m->list); INIT_LIST_HEAD(&m->small_win); __skb_queue_head_init(&m->deferredq); m->group = grp; m->node = node; m->port = port; m->instance = instance; m->bc_acked = grp->bc_snd_nxt - 1; ret = tipc_group_add_to_tree(grp, m); if (ret < 0) { kfree(m); return NULL; } grp->member_cnt++; tipc_nlist_add(&grp->dests, m->node); m->state = state; return m; } void tipc_group_add_member(struct tipc_group *grp, u32 node, u32 port, u32 instance) { tipc_group_create_member(grp, node, port, instance, MBR_PUBLISHED); } static void tipc_group_delete_member(struct tipc_group *grp, struct tipc_member *m) { rb_erase(&m->tree_node, &grp->members); grp->member_cnt--; /* Check if we were waiting for replicast ack from this member */ if (grp->bc_ackers && less(m->bc_acked, grp->bc_snd_nxt - 1)) grp->bc_ackers--; list_del_init(&m->list); list_del_init(&m->small_win); tipc_group_decr_active(grp, m); /* If last member on a node, remove node from dest list */ if (!tipc_group_find_node(grp, m->node)) tipc_nlist_del(&grp->dests, m->node); kfree(m); } struct tipc_nlist *tipc_group_dests(struct tipc_group *grp) { return &grp->dests; } void tipc_group_self(struct tipc_group *grp, struct tipc_name_seq *seq, int *scope) { seq->type = grp->type; seq->lower = grp->instance; seq->upper = grp->instance; *scope = grp->scope; } void tipc_group_update_member(struct tipc_member *m, int len) { struct tipc_group *grp = m->group; struct tipc_member *_m, *tmp; if (!tipc_group_is_receiver(m)) return; m->window -= len; if (m->window >= ADV_IDLE) return; list_del_init(&m->small_win); /* Sort member into small_window members' list */ list_for_each_entry_safe(_m, tmp, &grp->small_win, small_win) { if (_m->window > m->window) break; } list_add_tail(&m->small_win, &_m->small_win); } void tipc_group_update_bc_members(struct tipc_group *grp, int len, bool ack) { u16 prev = grp->bc_snd_nxt - 1; struct tipc_member *m; struct rb_node *n; u16 ackers = 0; for (n = rb_first(&grp->members); n; n = rb_next(n)) { m = container_of(n, struct tipc_member, tree_node); if (tipc_group_is_receiver(m)) { tipc_group_update_member(m, len); m->bc_acked = prev; ackers++; } } /* Mark number of acknowledges to expect, if any */ if (ack) grp->bc_ackers = ackers; grp->bc_snd_nxt++; } bool tipc_group_cong(struct tipc_group *grp, u32 dnode, u32 dport, int len, struct tipc_member **mbr) { struct sk_buff_head xmitq; struct tipc_member *m; int adv, state; m = tipc_group_find_dest(grp, dnode, dport); if (!tipc_group_is_receiver(m)) { *mbr = NULL; return false; } *mbr = m; if (m->window >= len) return false; *grp->open = false; /* If not fully advertised, do it now to prevent mutual blocking */ adv = m->advertised; state = m->state; if (state == MBR_JOINED && adv == ADV_IDLE) return true; if (state == MBR_ACTIVE && adv == ADV_ACTIVE) return true; if (state == MBR_PENDING && adv == ADV_IDLE) return true; __skb_queue_head_init(&xmitq); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, &xmitq); tipc_node_distr_xmit(grp->net, &xmitq); return true; } bool tipc_group_bc_cong(struct tipc_group *grp, int len) { struct tipc_member *m = NULL; /* If prev bcast was replicast, reject until all receivers have acked */ if (grp->bc_ackers) { *grp->open = false; return true; } if (list_empty(&grp->small_win)) return false; m = list_first_entry(&grp->small_win, struct tipc_member, small_win); if (m->window >= len) return false; return tipc_group_cong(grp, m->node, m->port, len, &m); } /* tipc_group_sort_msg() - sort msg into queue by bcast sequence number */ static void tipc_group_sort_msg(struct sk_buff *skb, struct sk_buff_head *defq) { struct tipc_msg *_hdr, *hdr = buf_msg(skb); u16 bc_seqno = msg_grp_bc_seqno(hdr); struct sk_buff *_skb, *tmp; int mtyp = msg_type(hdr); /* Bcast/mcast may be bypassed by ucast or other bcast, - sort it in */ if (mtyp == TIPC_GRP_BCAST_MSG || mtyp == TIPC_GRP_MCAST_MSG) { skb_queue_walk_safe(defq, _skb, tmp) { _hdr = buf_msg(_skb); if (!less(bc_seqno, msg_grp_bc_seqno(_hdr))) continue; __skb_queue_before(defq, _skb, skb); return; } /* Bcast was not bypassed, - add to tail */ } /* Unicasts are never bypassed, - always add to tail */ __skb_queue_tail(defq, skb); } /* tipc_group_filter_msg() - determine if we should accept arriving message */ void tipc_group_filter_msg(struct tipc_group *grp, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct sk_buff *skb = __skb_dequeue(inputq); bool ack, deliver, update, leave = false; struct sk_buff_head *defq; struct tipc_member *m; struct tipc_msg *hdr; u32 node, port; int mtyp, blks; if (!skb) return; hdr = buf_msg(skb); node = msg_orignode(hdr); port = msg_origport(hdr); if (!msg_in_group(hdr)) goto drop; m = tipc_group_find_member(grp, node, port); if (!tipc_group_is_sender(m)) goto drop; if (less(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) goto drop; TIPC_SKB_CB(skb)->orig_member = m->instance; defq = &m->deferredq; tipc_group_sort_msg(skb, defq); while ((skb = skb_peek(defq))) { hdr = buf_msg(skb); mtyp = msg_type(hdr); blks = msg_blocks(hdr); deliver = true; ack = false; update = false; if (more(msg_grp_bc_seqno(hdr), m->bc_rcv_nxt)) break; /* Decide what to do with message */ switch (mtyp) { case TIPC_GRP_MCAST_MSG: if (msg_nameinst(hdr) != grp->instance) { update = true; deliver = false; } /* Fall thru */ case TIPC_GRP_BCAST_MSG: m->bc_rcv_nxt++; ack = msg_grp_bc_ack_req(hdr); break; case TIPC_GRP_UCAST_MSG: break; case TIPC_GRP_MEMBER_EVT: if (m->state == MBR_LEAVING) leave = true; if (!grp->events) deliver = false; break; default: break; } /* Execute decisions */ __skb_dequeue(defq); if (deliver) __skb_queue_tail(inputq, skb); else kfree_skb(skb); if (ack) tipc_group_proto_xmit(grp, m, GRP_ACK_MSG, xmitq); if (leave) { __skb_queue_purge(defq); tipc_group_delete_member(grp, m); break; } if (!update) continue; tipc_group_update_rcv_win(grp, blks, node, port, xmitq); } return; drop: kfree_skb(skb); } void tipc_group_update_rcv_win(struct tipc_group *grp, int blks, u32 node, u32 port, struct sk_buff_head *xmitq) { struct list_head *active = &grp->active; int max_active = grp->max_active; int reclaim_limit = max_active * 3 / 4; int active_cnt = grp->active_cnt; struct tipc_member *m, *rm, *pm; m = tipc_group_find_member(grp, node, port); if (!m) return; m->advertised -= blks; switch (m->state) { case MBR_JOINED: /* First, decide if member can go active */ if (active_cnt <= max_active) { m->state = MBR_ACTIVE; list_add_tail(&m->list, active); grp->active_cnt++; tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); } else { m->state = MBR_PENDING; list_add_tail(&m->list, &grp->pending); } if (active_cnt < reclaim_limit) break; /* Reclaim from oldest active member, if possible */ if (!list_empty(active)) { rm = list_first_entry(active, struct tipc_member, list); rm->state = MBR_RECLAIMING; list_del_init(&rm->list); tipc_group_proto_xmit(grp, rm, GRP_RECLAIM_MSG, xmitq); break; } /* Nobody to reclaim from; - revert oldest pending to JOINED */ pm = list_first_entry(&grp->pending, struct tipc_member, list); list_del_init(&pm->list); pm->state = MBR_JOINED; tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); break; case MBR_ACTIVE: if (!list_is_last(&m->list, &grp->active)) list_move_tail(&m->list, &grp->active); if (m->advertised > (ADV_ACTIVE * 3 / 4)) break; tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); break; case MBR_REMITTED: if (m->advertised > ADV_IDLE) break; m->state = MBR_JOINED; grp->active_cnt--; if (m->advertised < ADV_IDLE) { pr_warn_ratelimited("Rcv unexpected msg after REMIT\n"); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); } if (list_empty(&grp->pending)) return; /* Set oldest pending member to active and advertise */ pm = list_first_entry(&grp->pending, struct tipc_member, list); pm->state = MBR_ACTIVE; list_move_tail(&pm->list, &grp->active); grp->active_cnt++; tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); break; case MBR_RECLAIMING: case MBR_JOINING: case MBR_LEAVING: default: break; } } static void tipc_group_create_event(struct tipc_group *grp, struct tipc_member *m, u32 event, u16 seqno, struct sk_buff_head *inputq) { u32 dnode = tipc_own_addr(grp->net); struct tipc_event evt; struct sk_buff *skb; struct tipc_msg *hdr; memset(&evt, 0, sizeof(evt)); evt.event = event; evt.found_lower = m->instance; evt.found_upper = m->instance; evt.port.ref = m->port; evt.port.node = m->node; evt.s.seq.type = grp->type; evt.s.seq.lower = m->instance; evt.s.seq.upper = m->instance; skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_GRP_MEMBER_EVT, GROUP_H_SIZE, sizeof(evt), dnode, m->node, grp->portid, m->port, 0); if (!skb) return; hdr = buf_msg(skb); msg_set_nametype(hdr, grp->type); msg_set_grp_evt(hdr, event); msg_set_dest_droppable(hdr, true); msg_set_grp_bc_seqno(hdr, seqno); memcpy(msg_data(hdr), &evt, sizeof(evt)); TIPC_SKB_CB(skb)->orig_member = m->instance; __skb_queue_tail(inputq, skb); } static void tipc_group_proto_xmit(struct tipc_group *grp, struct tipc_member *m, int mtyp, struct sk_buff_head *xmitq) { struct tipc_msg *hdr; struct sk_buff *skb; int adv = 0; skb = tipc_msg_create(GROUP_PROTOCOL, mtyp, INT_H_SIZE, 0, m->node, tipc_own_addr(grp->net), m->port, grp->portid, 0); if (!skb) return; if (m->state == MBR_ACTIVE) adv = ADV_ACTIVE - m->advertised; else if (m->state == MBR_JOINED || m->state == MBR_PENDING) adv = ADV_IDLE - m->advertised; hdr = buf_msg(skb); if (mtyp == GRP_JOIN_MSG) { msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); msg_set_adv_win(hdr, adv); m->advertised += adv; } else if (mtyp == GRP_LEAVE_MSG) { msg_set_grp_bc_syncpt(hdr, grp->bc_snd_nxt); } else if (mtyp == GRP_ADV_MSG) { msg_set_adv_win(hdr, adv); m->advertised += adv; } else if (mtyp == GRP_ACK_MSG) { msg_set_grp_bc_acked(hdr, m->bc_rcv_nxt); } else if (mtyp == GRP_REMIT_MSG) { msg_set_grp_remitted(hdr, m->window); } msg_set_dest_droppable(hdr, true); __skb_queue_tail(xmitq, skb); } void tipc_group_proto_rcv(struct tipc_group *grp, bool *usr_wakeup, struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { u32 node = msg_orignode(hdr); u32 port = msg_origport(hdr); struct tipc_member *m, *pm; u16 remitted, in_flight; if (!grp) return; if (grp->scope == TIPC_NODE_SCOPE && node != tipc_own_addr(grp->net)) return; m = tipc_group_find_member(grp, node, port); switch (msg_type(hdr)) { case GRP_JOIN_MSG: if (!m) m = tipc_group_create_member(grp, node, port, 0, MBR_JOINING); if (!m) return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); m->bc_rcv_nxt = m->bc_syncpt; m->window += msg_adv_win(hdr); /* Wait until PUBLISH event is received if necessary */ if (m->state != MBR_PUBLISHED) return; /* Member can be taken into service */ m->state = MBR_JOINED; tipc_group_open(m, usr_wakeup); tipc_group_update_member(m, 0); tipc_group_proto_xmit(grp, m, GRP_ADV_MSG, xmitq); tipc_group_create_event(grp, m, TIPC_PUBLISHED, m->bc_syncpt, inputq); return; case GRP_LEAVE_MSG: if (!m) return; m->bc_syncpt = msg_grp_bc_syncpt(hdr); list_del_init(&m->list); tipc_group_open(m, usr_wakeup); tipc_group_decr_active(grp, m); m->state = MBR_LEAVING; tipc_group_create_event(grp, m, TIPC_WITHDRAWN, m->bc_syncpt, inputq); return; case GRP_ADV_MSG: if (!m) return; m->window += msg_adv_win(hdr); tipc_group_open(m, usr_wakeup); return; case GRP_ACK_MSG: if (!m) return; m->bc_acked = msg_grp_bc_acked(hdr); if (--grp->bc_ackers) return; list_del_init(&m->small_win); *m->group->open = true; *usr_wakeup = true; tipc_group_update_member(m, 0); return; case GRP_RECLAIM_MSG: if (!m) return; tipc_group_proto_xmit(grp, m, GRP_REMIT_MSG, xmitq); m->window = ADV_IDLE; tipc_group_open(m, usr_wakeup); return; case GRP_REMIT_MSG: if (!m || m->state != MBR_RECLAIMING) return; remitted = msg_grp_remitted(hdr); /* Messages preceding the REMIT still in receive queue */ if (m->advertised > remitted) { m->state = MBR_REMITTED; in_flight = m->advertised - remitted; m->advertised = ADV_IDLE + in_flight; return; } /* This should never happen */ if (m->advertised < remitted) pr_warn_ratelimited("Unexpected REMIT msg\n"); /* All messages preceding the REMIT have been read */ m->state = MBR_JOINED; grp->active_cnt--; m->advertised = ADV_IDLE; /* Set oldest pending member to active and advertise */ if (list_empty(&grp->pending)) return; pm = list_first_entry(&grp->pending, struct tipc_member, list); pm->state = MBR_ACTIVE; list_move_tail(&pm->list, &grp->active); grp->active_cnt++; if (pm->advertised <= (ADV_ACTIVE * 3 / 4)) tipc_group_proto_xmit(grp, pm, GRP_ADV_MSG, xmitq); return; default: pr_warn("Received unknown GROUP_PROTO message\n"); } } /* tipc_group_member_evt() - receive and handle a member up/down event */ void tipc_group_member_evt(struct tipc_group *grp, bool *usr_wakeup, int *sk_rcvbuf, struct tipc_msg *hdr, struct sk_buff_head *inputq, struct sk_buff_head *xmitq) { struct tipc_event *evt = (void *)msg_data(hdr); u32 instance = evt->found_lower; u32 node = evt->port.node; u32 port = evt->port.ref; int event = evt->event; struct tipc_member *m; struct net *net; u32 self; if (!grp) return; net = grp->net; self = tipc_own_addr(net); if (!grp->loopback && node == self && port == grp->portid) return; m = tipc_group_find_member(grp, node, port); switch (event) { case TIPC_PUBLISHED: /* Send and wait for arrival of JOIN message if necessary */ if (!m) { m = tipc_group_create_member(grp, node, port, instance, MBR_PUBLISHED); if (!m) break; tipc_group_update_member(m, 0); tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); break; } if (m->state != MBR_JOINING) break; /* Member can be taken into service */ m->instance = instance; m->state = MBR_JOINED; tipc_group_open(m, usr_wakeup); tipc_group_update_member(m, 0); tipc_group_proto_xmit(grp, m, GRP_JOIN_MSG, xmitq); tipc_group_create_event(grp, m, TIPC_PUBLISHED, m->bc_syncpt, inputq); break; case TIPC_WITHDRAWN: if (!m) break; tipc_group_decr_active(grp, m); m->state = MBR_LEAVING; list_del_init(&m->list); tipc_group_open(m, usr_wakeup); /* Only send event if no LEAVE message can be expected */ if (!tipc_node_is_up(net, node)) tipc_group_create_event(grp, m, TIPC_WITHDRAWN, m->bc_rcv_nxt, inputq); break; default: break; } *sk_rcvbuf = tipc_group_rcvbuf_limit(grp); } int tipc_group_fill_sock_diag(struct tipc_group *grp, struct sk_buff *skb) { struct nlattr *group = nla_nest_start_noflag(skb, TIPC_NLA_SOCK_GROUP); if (!group) return -EMSGSIZE; if (nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_ID, grp->type) || nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_INSTANCE, grp->instance) || nla_put_u32(skb, TIPC_NLA_SOCK_GROUP_BC_SEND_NEXT, grp->bc_snd_nxt)) goto group_msg_cancel; if (grp->scope == TIPC_NODE_SCOPE) if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_NODE_SCOPE)) goto group_msg_cancel; if (grp->scope == TIPC_CLUSTER_SCOPE) if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_CLUSTER_SCOPE)) goto group_msg_cancel; if (*grp->open) if (nla_put_flag(skb, TIPC_NLA_SOCK_GROUP_OPEN)) goto group_msg_cancel; nla_nest_end(skb, group); return 0; group_msg_cancel: nla_nest_cancel(skb, group); return -1; } |
| 765 769 767 767 504 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* CPU control. * (C) 2001, 2002, 2003, 2004 Rusty Russell * * This code is licenced under the GPL. */ #include <linux/sched/mm.h> #include <linux/proc_fs.h> #include <linux/smp.h> #include <linux/init.h> #include <linux/notifier.h> #include <linux/sched/signal.h> #include <linux/sched/hotplug.h> #include <linux/sched/isolation.h> #include <linux/sched/task.h> #include <linux/sched/smt.h> #include <linux/unistd.h> #include <linux/cpu.h> #include <linux/oom.h> #include <linux/rcupdate.h> #include <linux/export.h> #include <linux/bug.h> #include <linux/kthread.h> #include <linux/stop_machine.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/suspend.h> #include <linux/lockdep.h> #include <linux/tick.h> #include <linux/irq.h> #include <linux/nmi.h> #include <linux/smpboot.h> #include <linux/relay.h> #include <linux/slab.h> #include <linux/percpu-rwsem.h> #include <linux/cpuset.h> #include <linux/random.h> #include <trace/events/power.h> #define CREATE_TRACE_POINTS #include <trace/events/cpuhp.h> #include "smpboot.h" /** * cpuhp_cpu_state - Per cpu hotplug state storage * @state: The current cpu state * @target: The target state * @thread: Pointer to the hotplug thread * @should_run: Thread should execute * @rollback: Perform a rollback * @single: Single callback invocation * @bringup: Single callback bringup or teardown selector * @cb_state: The state for a single callback (install/uninstall) * @result: Result of the operation * @done_up: Signal completion to the issuer of the task for cpu-up * @done_down: Signal completion to the issuer of the task for cpu-down */ struct cpuhp_cpu_state { enum cpuhp_state state; enum cpuhp_state target; enum cpuhp_state fail; #ifdef CONFIG_SMP struct task_struct *thread; bool should_run; bool rollback; bool single; bool bringup; struct hlist_node *node; struct hlist_node *last; enum cpuhp_state cb_state; int result; struct completion done_up; struct completion done_down; #endif }; static DEFINE_PER_CPU(struct cpuhp_cpu_state, cpuhp_state) = { .fail = CPUHP_INVALID, }; #ifdef CONFIG_SMP cpumask_t cpus_booted_once_mask; #endif #if defined(CONFIG_LOCKDEP) && defined(CONFIG_SMP) static struct lockdep_map cpuhp_state_up_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-up", &cpuhp_state_up_map); static struct lockdep_map cpuhp_state_down_map = STATIC_LOCKDEP_MAP_INIT("cpuhp_state-down", &cpuhp_state_down_map); static inline void cpuhp_lock_acquire(bool bringup) { lock_map_acquire(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } static inline void cpuhp_lock_release(bool bringup) { lock_map_release(bringup ? &cpuhp_state_up_map : &cpuhp_state_down_map); } #else static inline void cpuhp_lock_acquire(bool bringup) { } static inline void cpuhp_lock_release(bool bringup) { } #endif /** * cpuhp_step - Hotplug state machine step * @name: Name of the step * @startup: Startup function of the step * @teardown: Teardown function of the step * @cant_stop: Bringup/teardown can't be stopped at this step */ struct cpuhp_step { const char *name; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } startup; union { int (*single)(unsigned int cpu); int (*multi)(unsigned int cpu, struct hlist_node *node); } teardown; struct hlist_head list; bool cant_stop; bool multi_instance; }; static DEFINE_MUTEX(cpuhp_state_mutex); static struct cpuhp_step cpuhp_hp_states[]; static struct cpuhp_step *cpuhp_get_step(enum cpuhp_state state) { return cpuhp_hp_states + state; } /** * cpuhp_invoke_callback _ Invoke the callbacks for a given state * @cpu: The cpu for which the callback should be invoked * @state: The state to do callbacks for * @bringup: True if the bringup callback should be invoked * @node: For multi-instance, do a single entry callback for install/remove * @lastp: For multi-instance rollback, remember how far we got * * Called from cpu hotplug and from the state register machinery. */ static int cpuhp_invoke_callback(unsigned int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node, struct hlist_node **lastp) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct cpuhp_step *step = cpuhp_get_step(state); int (*cbm)(unsigned int cpu, struct hlist_node *node); int (*cb)(unsigned int cpu); int ret, cnt; if (st->fail == state) { st->fail = CPUHP_INVALID; if (!(bringup ? step->startup.single : step->teardown.single)) return 0; return -EAGAIN; } if (!step->multi_instance) { WARN_ON_ONCE(lastp && *lastp); cb = bringup ? step->startup.single : step->teardown.single; if (!cb) return 0; trace_cpuhp_enter(cpu, st->target, state, cb); ret = cb(cpu); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } cbm = bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return 0; /* Single invocation for instance add/remove */ if (node) { WARN_ON_ONCE(lastp && *lastp); trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); return ret; } /* State transition. Invoke on all instances */ cnt = 0; hlist_for_each(node, &step->list) { if (lastp && node == *lastp) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); if (ret) { if (!lastp) goto err; *lastp = node; return ret; } cnt++; } if (lastp) *lastp = NULL; return 0; err: /* Rollback the instances if one failed */ cbm = !bringup ? step->startup.multi : step->teardown.multi; if (!cbm) return ret; hlist_for_each(node, &step->list) { if (!cnt--) break; trace_cpuhp_multi_enter(cpu, st->target, state, cbm, node); ret = cbm(cpu, node); trace_cpuhp_exit(cpu, st->state, state, ret); /* * Rollback must not fail, */ WARN_ON_ONCE(ret); } return ret; } #ifdef CONFIG_SMP static bool cpuhp_is_ap_state(enum cpuhp_state state) { /* * The extra check for CPUHP_TEARDOWN_CPU is only for documentation * purposes as that state is handled explicitly in cpu_down. */ return state > CPUHP_BRINGUP_CPU && state != CPUHP_TEARDOWN_CPU; } static inline void wait_for_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; wait_for_completion(done); } static inline void complete_ap_thread(struct cpuhp_cpu_state *st, bool bringup) { struct completion *done = bringup ? &st->done_up : &st->done_down; complete(done); } /* * The former STARTING/DYING states, ran with IRQs disabled and must not fail. */ static bool cpuhp_is_atomic_state(enum cpuhp_state state) { return CPUHP_AP_IDLE_DEAD <= state && state < CPUHP_AP_ONLINE; } /* Serializes the updates to cpu_online_mask, cpu_present_mask */ static DEFINE_MUTEX(cpu_add_remove_lock); bool cpuhp_tasks_frozen; EXPORT_SYMBOL_GPL(cpuhp_tasks_frozen); /* * The following two APIs (cpu_maps_update_begin/done) must be used when * attempting to serialize the updates to cpu_online_mask & cpu_present_mask. */ void cpu_maps_update_begin(void) { mutex_lock(&cpu_add_remove_lock); } void cpu_maps_update_done(void) { mutex_unlock(&cpu_add_remove_lock); } /* * If set, cpu_up and cpu_down will return -EBUSY and do nothing. * Should always be manipulated under cpu_add_remove_lock */ static int cpu_hotplug_disabled; #ifdef CONFIG_HOTPLUG_CPU DEFINE_STATIC_PERCPU_RWSEM(cpu_hotplug_lock); void cpus_read_lock(void) { percpu_down_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_lock); int cpus_read_trylock(void) { return percpu_down_read_trylock(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_trylock); void cpus_read_unlock(void) { percpu_up_read(&cpu_hotplug_lock); } EXPORT_SYMBOL_GPL(cpus_read_unlock); void cpus_write_lock(void) { percpu_down_write(&cpu_hotplug_lock); } void cpus_write_unlock(void) { percpu_up_write(&cpu_hotplug_lock); } void lockdep_assert_cpus_held(void) { /* * We can't have hotplug operations before userspace starts running, * and some init codepaths will knowingly not take the hotplug lock. * This is all valid, so mute lockdep until it makes sense to report * unheld locks. */ if (system_state < SYSTEM_RUNNING) return; percpu_rwsem_assert_held(&cpu_hotplug_lock); } static void lockdep_acquire_cpus_lock(void) { rwsem_acquire(&cpu_hotplug_lock.rw_sem.dep_map, 0, 0, _THIS_IP_); } static void lockdep_release_cpus_lock(void) { rwsem_release(&cpu_hotplug_lock.rw_sem.dep_map, 1, _THIS_IP_); } /* * Wait for currently running CPU hotplug operations to complete (if any) and * disable future CPU hotplug (from sysfs). The 'cpu_add_remove_lock' protects * the 'cpu_hotplug_disabled' flag. The same lock is also acquired by the * hotplug path before performing hotplug operations. So acquiring that lock * guarantees mutual exclusion from any currently running hotplug operations. */ void cpu_hotplug_disable(void) { cpu_maps_update_begin(); cpu_hotplug_disabled++; cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_disable); static void __cpu_hotplug_enable(void) { if (WARN_ONCE(!cpu_hotplug_disabled, "Unbalanced cpu hotplug enable\n")) return; cpu_hotplug_disabled--; } void cpu_hotplug_enable(void) { cpu_maps_update_begin(); __cpu_hotplug_enable(); cpu_maps_update_done(); } EXPORT_SYMBOL_GPL(cpu_hotplug_enable); #else static void lockdep_acquire_cpus_lock(void) { } static void lockdep_release_cpus_lock(void) { } #endif /* CONFIG_HOTPLUG_CPU */ /* * Architectures that need SMT-specific errata handling during SMT hotplug * should override this. */ void __weak arch_smt_update(void) { } #ifdef CONFIG_HOTPLUG_SMT enum cpuhp_smt_control cpu_smt_control __read_mostly = CPU_SMT_ENABLED; void __init cpu_smt_disable(bool force) { if (!cpu_smt_possible()) return; if (force) { pr_info("SMT: Force disabled\n"); cpu_smt_control = CPU_SMT_FORCE_DISABLED; } else { pr_info("SMT: disabled\n"); cpu_smt_control = CPU_SMT_DISABLED; } } /* * The decision whether SMT is supported can only be done after the full * CPU identification. Called from architecture code. */ void __init cpu_smt_check_topology(void) { if (!topology_smt_supported()) cpu_smt_control = CPU_SMT_NOT_SUPPORTED; } static int __init smt_cmdline_disable(char *str) { cpu_smt_disable(str && !strcmp(str, "force")); return 0; } early_param("nosmt", smt_cmdline_disable); static inline bool cpu_smt_allowed(unsigned int cpu) { if (cpu_smt_control == CPU_SMT_ENABLED) return true; if (topology_is_primary_thread(cpu)) return true; /* * On x86 it's required to boot all logical CPUs at least once so * that the init code can get a chance to set CR4.MCE on each * CPU. Otherwise, a broadacasted MCE observing CR4.MCE=0b on any * core will shutdown the machine. */ return !cpumask_test_cpu(cpu, &cpus_booted_once_mask); } /* Returns true if SMT is not supported of forcefully (irreversibly) disabled */ bool cpu_smt_possible(void) { return cpu_smt_control != CPU_SMT_FORCE_DISABLED && cpu_smt_control != CPU_SMT_NOT_SUPPORTED; } EXPORT_SYMBOL_GPL(cpu_smt_possible); #else static inline bool cpu_smt_allowed(unsigned int cpu) { return true; } #endif static inline enum cpuhp_state cpuhp_set_state(struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; st->rollback = false; st->last = NULL; st->target = target; st->single = false; st->bringup = st->state < target; return prev_state; } static inline void cpuhp_reset_state(struct cpuhp_cpu_state *st, enum cpuhp_state prev_state) { st->rollback = true; /* * If we have st->last we need to undo partial multi_instance of this * state first. Otherwise start undo at the previous state. */ if (!st->last) { if (st->bringup) st->state--; else st->state++; } st->target = prev_state; st->bringup = !st->bringup; } /* Regular hotplug invocation of the AP hotplug thread */ static void __cpuhp_kick_ap(struct cpuhp_cpu_state *st) { if (!st->single && st->state == st->target) return; st->result = 0; /* * Make sure the above stores are visible before should_run becomes * true. Paired with the mb() above in cpuhp_thread_fun() */ smp_mb(); st->should_run = true; wake_up_process(st->thread); wait_for_ap_thread(st, st->bringup); } static int cpuhp_kick_ap(struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state; int ret; prev_state = cpuhp_set_state(st, target); __cpuhp_kick_ap(st); if ((ret = st->result)) { cpuhp_reset_state(st, prev_state); __cpuhp_kick_ap(st); } return ret; } static int bringup_wait_for_ap(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); /* Wait for the CPU to reach CPUHP_AP_ONLINE_IDLE */ wait_for_ap_thread(st, true); if (WARN_ON_ONCE((!cpu_online(cpu)))) return -ECANCELED; /* Unpark the hotplug thread of the target cpu */ kthread_unpark(st->thread); /* * SMT soft disabling on X86 requires to bring the CPU out of the * BIOS 'wait for SIPI' state in order to set the CR4.MCE bit. The * CPU marked itself as booted_once in notify_cpu_starting() so the * cpu_smt_allowed() check will now return false if this is not the * primary sibling. */ if (!cpu_smt_allowed(cpu)) return -ECANCELED; if (st->target <= CPUHP_AP_ONLINE_IDLE) return 0; return cpuhp_kick_ap(st, st->target); } static int bringup_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); int ret; /* * Some architectures have to walk the irq descriptors to * setup the vector space for the cpu which comes online. * Prevent irq alloc/free across the bringup. */ irq_lock_sparse(); /* Arch-specific enabling code. */ ret = __cpu_up(cpu, idle); irq_unlock_sparse(); if (ret) return ret; return bringup_wait_for_ap(cpu); } static int finish_cpu(unsigned int cpu) { struct task_struct *idle = idle_thread_get(cpu); struct mm_struct *mm = idle->active_mm; /* * idle_task_exit() will have switched to &init_mm, now * clean up any remaining active_mm state. */ if (mm != &init_mm) idle->active_mm = &init_mm; mmdrop(mm); return 0; } /* * Hotplug state machine related functions */ static void undo_cpu_up(unsigned int cpu, struct cpuhp_cpu_state *st) { for (st->state--; st->state > st->target; st->state--) cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); } static inline bool can_rollback_cpu(struct cpuhp_cpu_state *st) { if (IS_ENABLED(CONFIG_HOTPLUG_CPU)) return true; /* * When CPU hotplug is disabled, then taking the CPU down is not * possible because takedown_cpu() and the architecture and * subsystem specific mechanisms are not available. So the CPU * which would be completely unplugged again needs to stay around * in the current state. */ return st->state <= CPUHP_BRINGUP_CPU; } static int cpuhp_up_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; while (st->state < target) { st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); if (ret) { if (can_rollback_cpu(st)) { st->target = prev_state; undo_cpu_up(cpu, st); } break; } } return ret; } /* * The cpu hotplug threads manage the bringup and teardown of the cpus */ static void cpuhp_create(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); init_completion(&st->done_up); init_completion(&st->done_down); } static int cpuhp_should_run(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); return st->should_run; } /* * Execute teardown/startup callbacks on the plugged cpu. Also used to invoke * callbacks when a state gets [un]installed at runtime. * * Each invocation of this function by the smpboot thread does a single AP * state callback. * * It has 3 modes of operation: * - single: runs st->cb_state * - up: runs ++st->state, while st->state < st->target * - down: runs st->state--, while st->state > st->target * * When complete or on error, should_run is cleared and the completion is fired. */ static void cpuhp_thread_fun(unsigned int cpu) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); bool bringup = st->bringup; enum cpuhp_state state; if (WARN_ON_ONCE(!st->should_run)) return; /* * ACQUIRE for the cpuhp_should_run() load of ->should_run. Ensures * that if we see ->should_run we also see the rest of the state. */ smp_mb(); /* * The BP holds the hotplug lock, but we're now running on the AP, * ensure that anybody asserting the lock is held, will actually find * it so. */ lockdep_acquire_cpus_lock(); cpuhp_lock_acquire(bringup); if (st->single) { state = st->cb_state; st->should_run = false; } else { if (bringup) { st->state++; state = st->state; st->should_run = (st->state < st->target); WARN_ON_ONCE(st->state > st->target); } else { state = st->state; st->state--; st->should_run = (st->state > st->target); WARN_ON_ONCE(st->state < st->target); } } WARN_ON_ONCE(!cpuhp_is_ap_state(state)); if (cpuhp_is_atomic_state(state)) { local_irq_disable(); st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); local_irq_enable(); /* * STARTING/DYING must not fail! */ WARN_ON_ONCE(st->result); } else { st->result = cpuhp_invoke_callback(cpu, state, bringup, st->node, &st->last); } if (st->result) { /* * If we fail on a rollback, we're up a creek without no * paddle, no way forward, no way back. We loose, thanks for * playing. */ WARN_ON_ONCE(st->rollback); st->should_run = false; } cpuhp_lock_release(bringup); lockdep_release_cpus_lock(); if (!st->should_run) complete_ap_thread(st, bringup); } /* Invoke a single callback on a remote cpu */ static int cpuhp_invoke_ap_callback(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int ret; if (!cpu_online(cpu)) return 0; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); /* * If we are up and running, use the hotplug thread. For early calls * we invoke the thread function directly. */ if (!st->thread) return cpuhp_invoke_callback(cpu, state, bringup, node, NULL); st->rollback = false; st->last = NULL; st->node = node; st->bringup = bringup; st->cb_state = state; st->single = true; __cpuhp_kick_ap(st); /* * If we failed and did a partial, do a rollback. */ if ((ret = st->result) && st->last) { st->rollback = true; st->bringup = !bringup; __cpuhp_kick_ap(st); } /* * Clean up the leftovers so the next hotplug operation wont use stale * data. */ st->node = st->last = NULL; return ret; } static int cpuhp_kick_ap_work(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state prev_state = st->state; int ret; cpuhp_lock_acquire(false); cpuhp_lock_release(false); cpuhp_lock_acquire(true); cpuhp_lock_release(true); trace_cpuhp_enter(cpu, st->target, prev_state, cpuhp_kick_ap_work); ret = cpuhp_kick_ap(st, st->target); trace_cpuhp_exit(cpu, st->state, prev_state, ret); return ret; } static struct smp_hotplug_thread cpuhp_threads = { .store = &cpuhp_state.thread, .create = &cpuhp_create, .thread_should_run = cpuhp_should_run, .thread_fn = cpuhp_thread_fun, .thread_comm = "cpuhp/%u", .selfparking = true, }; void __init cpuhp_threads_init(void) { BUG_ON(smpboot_register_percpu_thread(&cpuhp_threads)); kthread_unpark(this_cpu_read(cpuhp_state.thread)); } /* * * Serialize hotplug trainwrecks outside of the cpu_hotplug_lock * protected region. * * The operation is still serialized against concurrent CPU hotplug via * cpu_add_remove_lock, i.e. CPU map protection. But it is _not_ * serialized against other hotplug related activity like adding or * removing of state callbacks and state instances, which invoke either the * startup or the teardown callback of the affected state. * * This is required for subsystems which are unfixable vs. CPU hotplug and * evade lock inversion problems by scheduling work which has to be * completed _before_ cpu_up()/_cpu_down() returns. * * Don't even think about adding anything to this for any new code or even * drivers. It's only purpose is to keep existing lock order trainwrecks * working. * * For cpu_down() there might be valid reasons to finish cleanups which are * not required to be done under cpu_hotplug_lock, but that's a different * story and would be not invoked via this. */ static void cpu_up_down_serialize_trainwrecks(bool tasks_frozen) { /* * cpusets delegate hotplug operations to a worker to "solve" the * lock order problems. Wait for the worker, but only if tasks are * _not_ frozen (suspend, hibernate) as that would wait forever. * * The wait is required because otherwise the hotplug operation * returns with inconsistent state, which could even be observed in * user space when a new CPU is brought up. The CPU plug uevent * would be delivered and user space reacting on it would fail to * move tasks to the newly plugged CPU up to the point where the * work has finished because up to that point the newly plugged CPU * is not assignable in cpusets/cgroups. On unplug that's not * necessarily a visible issue, but it is still inconsistent state, * which is the real problem which needs to be "fixed". This can't * prevent the transient state between scheduling the work and * returning from waiting for it. */ if (!tasks_frozen) cpuset_wait_for_hotplug(); } #ifdef CONFIG_HOTPLUG_CPU #ifndef arch_clear_mm_cpumask_cpu #define arch_clear_mm_cpumask_cpu(cpu, mm) cpumask_clear_cpu(cpu, mm_cpumask(mm)) #endif /** * clear_tasks_mm_cpumask - Safely clear tasks' mm_cpumask for a CPU * @cpu: a CPU id * * This function walks all processes, finds a valid mm struct for each one and * then clears a corresponding bit in mm's cpumask. While this all sounds * trivial, there are various non-obvious corner cases, which this function * tries to solve in a safe manner. * * Also note that the function uses a somewhat relaxed locking scheme, so it may * be called only for an already offlined CPU. */ void clear_tasks_mm_cpumask(int cpu) { struct task_struct *p; /* * This function is called after the cpu is taken down and marked * offline, so its not like new tasks will ever get this cpu set in * their mm mask. -- Peter Zijlstra * Thus, we may use rcu_read_lock() here, instead of grabbing * full-fledged tasklist_lock. */ WARN_ON(cpu_online(cpu)); rcu_read_lock(); for_each_process(p) { struct task_struct *t; /* * Main thread might exit, but other threads may still have * a valid mm. Find one. */ t = find_lock_task_mm(p); if (!t) continue; arch_clear_mm_cpumask_cpu(cpu, t->mm); task_unlock(t); } rcu_read_unlock(); } /* Take this CPU down. */ static int take_cpu_down(void *_param) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); enum cpuhp_state target = max((int)st->target, CPUHP_AP_OFFLINE); int err, cpu = smp_processor_id(); int ret; /* Ensure this CPU doesn't handle any more interrupts. */ err = __cpu_disable(); if (err < 0) return err; /* * We get here while we are in CPUHP_TEARDOWN_CPU state and we must not * do this step again. */ WARN_ON(st->state != CPUHP_TEARDOWN_CPU); st->state--; /* Invoke the former CPU_DYING callbacks */ for (; st->state > target; st->state--) { ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); /* * DYING must not fail! */ WARN_ON_ONCE(ret); } /* Give up timekeeping duties */ tick_handover_do_timer(); /* Remove CPU from timer broadcasting */ tick_offline_cpu(cpu); /* Park the stopper thread */ stop_machine_park(cpu); return 0; } static int takedown_cpu(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int err; /* Park the smpboot threads */ kthread_park(per_cpu_ptr(&cpuhp_state, cpu)->thread); /* * Prevent irq alloc/free while the dying cpu reorganizes the * interrupt affinities. */ irq_lock_sparse(); /* * So now all preempt/rcu users must observe !cpu_active(). */ err = stop_machine_cpuslocked(take_cpu_down, NULL, cpumask_of(cpu)); if (err) { /* CPU refused to die */ irq_unlock_sparse(); /* Unpark the hotplug thread so we can rollback there */ kthread_unpark(per_cpu_ptr(&cpuhp_state, cpu)->thread); return err; } BUG_ON(cpu_online(cpu)); /* * The teardown callback for CPUHP_AP_SCHED_STARTING will have removed * all runnable tasks from the CPU, there's only the idle task left now * that the migration thread is done doing the stop_machine thing. * * Wait for the stop thread to go away. */ wait_for_ap_thread(st, false); BUG_ON(st->state != CPUHP_AP_IDLE_DEAD); /* Interrupts are moved away from the dying cpu, reenable alloc/free */ irq_unlock_sparse(); hotplug_cpu__broadcast_tick_pull(cpu); /* This actually kills the CPU. */ __cpu_die(cpu); tick_cleanup_dead_cpu(cpu); rcutree_migrate_callbacks(cpu); return 0; } static void cpuhp_complete_idle_dead(void *arg) { struct cpuhp_cpu_state *st = arg; complete_ap_thread(st, false); } void cpuhp_report_idle_dead(void) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); BUG_ON(st->state != CPUHP_AP_OFFLINE); rcu_report_dead(smp_processor_id()); st->state = CPUHP_AP_IDLE_DEAD; /* * We cannot call complete after rcu_report_dead() so we delegate it * to an online cpu. */ smp_call_function_single(cpumask_first(cpu_online_mask), cpuhp_complete_idle_dead, st, 0); } static void undo_cpu_down(unsigned int cpu, struct cpuhp_cpu_state *st) { for (st->state++; st->state < st->target; st->state++) cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); } static int cpuhp_down_callbacks(unsigned int cpu, struct cpuhp_cpu_state *st, enum cpuhp_state target) { enum cpuhp_state prev_state = st->state; int ret = 0; for (; st->state > target; st->state--) { ret = cpuhp_invoke_callback(cpu, st->state, false, NULL, NULL); if (ret) { st->target = prev_state; if (st->state < prev_state) undo_cpu_down(cpu, st); break; } } return ret; } /* Requires cpu_add_remove_lock to be held */ static int __ref _cpu_down(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int prev_state, ret = 0; if (num_online_cpus() == 1) return -EBUSY; if (!cpu_present(cpu)) return -EINVAL; cpus_write_lock(); cpuhp_tasks_frozen = tasks_frozen; prev_state = cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread. */ if (st->state > CPUHP_TEARDOWN_CPU) { st->target = max((int)target, CPUHP_TEARDOWN_CPU); ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; /* * We might have stopped still in the range of the AP hotplug * thread. Nothing to do anymore. */ if (st->state > CPUHP_TEARDOWN_CPU) goto out; st->target = target; } /* * The AP brought itself down to CPUHP_TEARDOWN_CPU. So we need * to do the further cleanups. */ ret = cpuhp_down_callbacks(cpu, st, target); if (ret && st->state == CPUHP_TEARDOWN_CPU && st->state < prev_state) { cpuhp_reset_state(st, prev_state); __cpuhp_kick_ap(st); } out: cpus_write_unlock(); /* * Do post unplug cleanup. This is still protected against * concurrent CPU hotplug via cpu_add_remove_lock. */ lockup_detector_cleanup(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int cpu_down_maps_locked(unsigned int cpu, enum cpuhp_state target) { if (cpu_hotplug_disabled) return -EBUSY; return _cpu_down(cpu, 0, target); } static int do_cpu_down(unsigned int cpu, enum cpuhp_state target) { int err; cpu_maps_update_begin(); err = cpu_down_maps_locked(cpu, target); cpu_maps_update_done(); return err; } int cpu_down(unsigned int cpu) { return do_cpu_down(cpu, CPUHP_OFFLINE); } EXPORT_SYMBOL(cpu_down); #else #define takedown_cpu NULL #endif /*CONFIG_HOTPLUG_CPU*/ /** * notify_cpu_starting(cpu) - Invoke the callbacks on the starting CPU * @cpu: cpu that just started * * It must be called by the arch code on the new cpu, before the new cpu * enables interrupts and before the "boot" cpu returns from __cpu_up(). */ void notify_cpu_starting(unsigned int cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); enum cpuhp_state target = min((int)st->target, CPUHP_AP_ONLINE); int ret; rcu_cpu_starting(cpu); /* Enables RCU usage on this CPU. */ cpumask_set_cpu(cpu, &cpus_booted_once_mask); while (st->state < target) { st->state++; ret = cpuhp_invoke_callback(cpu, st->state, true, NULL, NULL); /* * STARTING must not fail! */ WARN_ON_ONCE(ret); } } /* * Called from the idle task. Wake up the controlling task which brings the * hotplug thread of the upcoming CPU up and then delegates the rest of the * online bringup to the hotplug thread. */ void cpuhp_online_idle(enum cpuhp_state state) { struct cpuhp_cpu_state *st = this_cpu_ptr(&cpuhp_state); /* Happens for the boot cpu */ if (state != CPUHP_AP_ONLINE_IDLE) return; /* * Unpart the stopper thread before we start the idle loop (and start * scheduling); this ensures the stopper task is always available. */ stop_machine_unpark(smp_processor_id()); st->state = CPUHP_AP_ONLINE_IDLE; complete_ap_thread(st, true); } /* Requires cpu_add_remove_lock to be held */ static int _cpu_up(unsigned int cpu, int tasks_frozen, enum cpuhp_state target) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); struct task_struct *idle; int ret = 0; cpus_write_lock(); if (!cpu_present(cpu)) { ret = -EINVAL; goto out; } /* * The caller of do_cpu_up might have raced with another * caller. Ignore it for now. */ if (st->state >= target) goto out; if (st->state == CPUHP_OFFLINE) { /* Let it fail before we try to bring the cpu up */ idle = idle_thread_get(cpu); if (IS_ERR(idle)) { ret = PTR_ERR(idle); goto out; } } cpuhp_tasks_frozen = tasks_frozen; cpuhp_set_state(st, target); /* * If the current CPU state is in the range of the AP hotplug thread, * then we need to kick the thread once more. */ if (st->state > CPUHP_BRINGUP_CPU) { ret = cpuhp_kick_ap_work(cpu); /* * The AP side has done the error rollback already. Just * return the error code.. */ if (ret) goto out; } /* * Try to reach the target state. We max out on the BP at * CPUHP_BRINGUP_CPU. After that the AP hotplug thread is * responsible for bringing it up to the target state. */ target = min((int)target, CPUHP_BRINGUP_CPU); ret = cpuhp_up_callbacks(cpu, st, target); out: cpus_write_unlock(); arch_smt_update(); cpu_up_down_serialize_trainwrecks(tasks_frozen); return ret; } static int do_cpu_up(unsigned int cpu, enum cpuhp_state target) { int err = 0; if (!cpu_possible(cpu)) { pr_err("can't online cpu %d because it is not configured as may-hotadd at boot time\n", cpu); #if defined(CONFIG_IA64) pr_err("please check additional_cpus= boot parameter\n"); #endif return -EINVAL; } err = try_online_node(cpu_to_node(cpu)); if (err) return err; cpu_maps_update_begin(); if (cpu_hotplug_disabled) { err = -EBUSY; goto out; } if (!cpu_smt_allowed(cpu)) { err = -EPERM; goto out; } err = _cpu_up(cpu, 0, target); out: cpu_maps_update_done(); return err; } int cpu_up(unsigned int cpu) { return do_cpu_up(cpu, CPUHP_ONLINE); } EXPORT_SYMBOL_GPL(cpu_up); #ifdef CONFIG_PM_SLEEP_SMP static cpumask_var_t frozen_cpus; int __freeze_secondary_cpus(int primary, bool suspend) { int cpu, error = 0; cpu_maps_update_begin(); if (primary == -1) { primary = cpumask_first(cpu_online_mask); if (!housekeeping_cpu(primary, HK_FLAG_TIMER)) primary = housekeeping_any_cpu(HK_FLAG_TIMER); } else { if (!cpu_online(primary)) primary = cpumask_first(cpu_online_mask); } /* * We take down all of the non-boot CPUs in one shot to avoid races * with the userspace trying to use the CPU hotplug at the same time */ cpumask_clear(frozen_cpus); pr_info("Disabling non-boot CPUs ...\n"); for_each_online_cpu(cpu) { if (cpu == primary) continue; if (suspend && pm_wakeup_pending()) { pr_info("Wakeup pending. Abort CPU freeze\n"); error = -EBUSY; break; } trace_suspend_resume(TPS("CPU_OFF"), cpu, true); error = _cpu_down(cpu, 1, CPUHP_OFFLINE); trace_suspend_resume(TPS("CPU_OFF"), cpu, false); if (!error) cpumask_set_cpu(cpu, frozen_cpus); else { pr_err("Error taking CPU%d down: %d\n", cpu, error); break; } } if (!error) BUG_ON(num_online_cpus() > 1); else pr_err("Non-boot CPUs are not disabled\n"); /* * Make sure the CPUs won't be enabled by someone else. We need to do * this even in case of failure as all disable_nonboot_cpus() users are * supposed to do enable_nonboot_cpus() on the failure path. */ cpu_hotplug_disabled++; cpu_maps_update_done(); return error; } void __weak arch_enable_nonboot_cpus_begin(void) { } void __weak arch_enable_nonboot_cpus_end(void) { } void enable_nonboot_cpus(void) { int cpu, error; struct device *cpu_device; /* Allow everyone to use the CPU hotplug again */ cpu_maps_update_begin(); __cpu_hotplug_enable(); if (cpumask_empty(frozen_cpus)) goto out; pr_info("Enabling non-boot CPUs ...\n"); arch_enable_nonboot_cpus_begin(); for_each_cpu(cpu, frozen_cpus) { trace_suspend_resume(TPS("CPU_ON"), cpu, true); error = _cpu_up(cpu, 1, CPUHP_ONLINE); trace_suspend_resume(TPS("CPU_ON"), cpu, false); if (!error) { pr_info("CPU%d is up\n", cpu); cpu_device = get_cpu_device(cpu); if (!cpu_device) pr_err("%s: failed to get cpu%d device\n", __func__, cpu); else kobject_uevent(&cpu_device->kobj, KOBJ_ONLINE); continue; } pr_warn("Error taking CPU%d up: %d\n", cpu, error); } arch_enable_nonboot_cpus_end(); cpumask_clear(frozen_cpus); out: cpu_maps_update_done(); } static int __init alloc_frozen_cpus(void) { if (!alloc_cpumask_var(&frozen_cpus, GFP_KERNEL|__GFP_ZERO)) return -ENOMEM; return 0; } core_initcall(alloc_frozen_cpus); /* * When callbacks for CPU hotplug notifications are being executed, we must * ensure that the state of the system with respect to the tasks being frozen * or not, as reported by the notification, remains unchanged *throughout the * duration* of the execution of the callbacks. * Hence we need to prevent the freezer from racing with regular CPU hotplug. * * This synchronization is implemented by mutually excluding regular CPU * hotplug and Suspend/Hibernate call paths by hooking onto the Suspend/ * Hibernate notifications. */ static int cpu_hotplug_pm_callback(struct notifier_block *nb, unsigned long action, void *ptr) { switch (action) { case PM_SUSPEND_PREPARE: case PM_HIBERNATION_PREPARE: cpu_hotplug_disable(); break; case PM_POST_SUSPEND: case PM_POST_HIBERNATION: cpu_hotplug_enable(); break; default: return NOTIFY_DONE; } return NOTIFY_OK; } static int __init cpu_hotplug_pm_sync_init(void) { /* * cpu_hotplug_pm_callback has higher priority than x86 * bsp_pm_callback which depends on cpu_hotplug_pm_callback * to disable cpu hotplug to avoid cpu hotplug race. */ pm_notifier(cpu_hotplug_pm_callback, 0); return 0; } core_initcall(cpu_hotplug_pm_sync_init); #endif /* CONFIG_PM_SLEEP_SMP */ int __boot_cpu_id; /* Horrific hacks because we can't add more to cpuhp_hp_states. */ static int random_and_perf_prepare_fusion(unsigned int cpu) { #ifdef CONFIG_PERF_EVENTS perf_event_init_cpu(cpu); #endif random_prepare_cpu(cpu); return 0; } static int random_and_workqueue_online_fusion(unsigned int cpu) { workqueue_online_cpu(cpu); random_online_cpu(cpu); return 0; } #endif /* CONFIG_SMP */ /* Boot processor state steps */ static struct cpuhp_step cpuhp_hp_states[] = { [CPUHP_OFFLINE] = { .name = "offline", .startup.single = NULL, .teardown.single = NULL, }, #ifdef CONFIG_SMP [CPUHP_CREATE_THREADS]= { .name = "threads:prepare", .startup.single = smpboot_create_threads, .teardown.single = NULL, .cant_stop = true, }, [CPUHP_PERF_PREPARE] = { .name = "perf:prepare", .startup.single = random_and_perf_prepare_fusion, .teardown.single = perf_event_exit_cpu, }, [CPUHP_WORKQUEUE_PREP] = { .name = "workqueue:prepare", .startup.single = workqueue_prepare_cpu, .teardown.single = NULL, }, [CPUHP_HRTIMERS_PREPARE] = { .name = "hrtimers:prepare", .startup.single = hrtimers_prepare_cpu, .teardown.single = hrtimers_dead_cpu, }, [CPUHP_SMPCFD_PREPARE] = { .name = "smpcfd:prepare", .startup.single = smpcfd_prepare_cpu, .teardown.single = smpcfd_dead_cpu, }, [CPUHP_RELAY_PREPARE] = { .name = "relay:prepare", .startup.single = relay_prepare_cpu, .teardown.single = NULL, }, [CPUHP_SLAB_PREPARE] = { .name = "slab:prepare", .startup.single = slab_prepare_cpu, .teardown.single = slab_dead_cpu, }, [CPUHP_RCUTREE_PREP] = { .name = "RCU/tree:prepare", .startup.single = rcutree_prepare_cpu, .teardown.single = rcutree_dead_cpu, }, /* * On the tear-down path, timers_dead_cpu() must be invoked * before blk_mq_queue_reinit_notify() from notify_dead(), * otherwise a RCU stall occurs. */ [CPUHP_TIMERS_PREPARE] = { .name = "timers:prepare", .startup.single = timers_prepare_cpu, .teardown.single = timers_dead_cpu, }, /* Kicks the plugged cpu into life */ [CPUHP_BRINGUP_CPU] = { .name = "cpu:bringup", .startup.single = bringup_cpu, .teardown.single = finish_cpu, .cant_stop = true, }, /* Final state before CPU kills itself */ [CPUHP_AP_IDLE_DEAD] = { .name = "idle:dead", }, /* * Last state before CPU enters the idle loop to die. Transient state * for synchronization. */ [CPUHP_AP_OFFLINE] = { .name = "ap:offline", .cant_stop = true, }, /* First state is scheduler control. Interrupts are disabled */ [CPUHP_AP_SCHED_STARTING] = { .name = "sched:starting", .startup.single = sched_cpu_starting, .teardown.single = sched_cpu_dying, }, [CPUHP_AP_RCUTREE_DYING] = { .name = "RCU/tree:dying", .startup.single = NULL, .teardown.single = rcutree_dying_cpu, }, [CPUHP_AP_SMPCFD_DYING] = { .name = "smpcfd:dying", .startup.single = NULL, .teardown.single = smpcfd_dying_cpu, }, /* Entry state on starting. Interrupts enabled from here on. Transient * state for synchronsization */ [CPUHP_AP_ONLINE] = { .name = "ap:online", }, /* * Handled on controll processor until the plugged processor manages * this itself. */ [CPUHP_TEARDOWN_CPU] = { .name = "cpu:teardown", .startup.single = NULL, .teardown.single = takedown_cpu, .cant_stop = true, }, /* Handle smpboot threads park/unpark */ [CPUHP_AP_SMPBOOT_THREADS] = { .name = "smpboot/threads:online", .startup.single = smpboot_unpark_threads, .teardown.single = smpboot_park_threads, }, [CPUHP_AP_IRQ_AFFINITY_ONLINE] = { .name = "irq/affinity:online", .startup.single = irq_affinity_online_cpu, .teardown.single = NULL, }, [CPUHP_AP_PERF_ONLINE] = { .name = "perf:online", .startup.single = perf_event_init_cpu, .teardown.single = perf_event_exit_cpu, }, [CPUHP_AP_WATCHDOG_ONLINE] = { .name = "lockup_detector:online", .startup.single = lockup_detector_online_cpu, .teardown.single = lockup_detector_offline_cpu, }, [CPUHP_AP_WORKQUEUE_ONLINE] = { .name = "workqueue:online", .startup.single = random_and_workqueue_online_fusion, .teardown.single = workqueue_offline_cpu, }, [CPUHP_AP_RCUTREE_ONLINE] = { .name = "RCU/tree:online", .startup.single = rcutree_online_cpu, .teardown.single = rcutree_offline_cpu, }, #endif /* * The dynamically registered state space is here */ #ifdef CONFIG_SMP /* Last state is scheduler control setting the cpu active */ [CPUHP_AP_ACTIVE] = { .name = "sched:active", .startup.single = sched_cpu_activate, .teardown.single = sched_cpu_deactivate, }, #endif /* CPU is fully up and running. */ [CPUHP_ONLINE] = { .name = "online", .startup.single = NULL, .teardown.single = NULL, }, }; /* Sanity check for callbacks */ static int cpuhp_cb_check(enum cpuhp_state state) { if (state <= CPUHP_OFFLINE || state >= CPUHP_ONLINE) return -EINVAL; return 0; } /* * Returns a free for dynamic slot assignment of the Online state. The states * are protected by the cpuhp_slot_states mutex and an empty slot is identified * by having no name assigned. */ static int cpuhp_reserve_state(enum cpuhp_state state) { enum cpuhp_state i, end; struct cpuhp_step *step; switch (state) { case CPUHP_AP_ONLINE_DYN: step = cpuhp_hp_states + CPUHP_AP_ONLINE_DYN; end = CPUHP_AP_ONLINE_DYN_END; break; case CPUHP_BP_PREPARE_DYN: step = cpuhp_hp_states + CPUHP_BP_PREPARE_DYN; end = CPUHP_BP_PREPARE_DYN_END; break; default: return -EINVAL; } for (i = state; i <= end; i++, step++) { if (!step->name) return i; } WARN(1, "No more dynamic states available for CPU hotplug\n"); return -ENOSPC; } static int cpuhp_store_callbacks(enum cpuhp_state state, const char *name, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { /* (Un)Install the callbacks for further cpu hotplug operations */ struct cpuhp_step *sp; int ret = 0; /* * If name is NULL, then the state gets removed. * * CPUHP_AP_ONLINE_DYN and CPUHP_BP_PREPARE_DYN are handed out on * the first allocation from these dynamic ranges, so the removal * would trigger a new allocation and clear the wrong (already * empty) state, leaving the callbacks of the to be cleared state * dangling, which causes wreckage on the next hotplug operation. */ if (name && (state == CPUHP_AP_ONLINE_DYN || state == CPUHP_BP_PREPARE_DYN)) { ret = cpuhp_reserve_state(state); if (ret < 0) return ret; state = ret; } sp = cpuhp_get_step(state); if (name && sp->name) return -EBUSY; sp->startup.single = startup; sp->teardown.single = teardown; sp->name = name; sp->multi_instance = multi_instance; INIT_HLIST_HEAD(&sp->list); return ret; } static void *cpuhp_get_teardown_cb(enum cpuhp_state state) { return cpuhp_get_step(state)->teardown.single; } /* * Call the startup/teardown function for a step either on the AP or * on the current CPU. */ static int cpuhp_issue_call(int cpu, enum cpuhp_state state, bool bringup, struct hlist_node *node) { struct cpuhp_step *sp = cpuhp_get_step(state); int ret; /* * If there's nothing to do, we done. * Relies on the union for multi_instance. */ if ((bringup && !sp->startup.single) || (!bringup && !sp->teardown.single)) return 0; /* * The non AP bound callbacks can fail on bringup. On teardown * e.g. module removal we crash for now. */ #ifdef CONFIG_SMP if (cpuhp_is_ap_state(state)) ret = cpuhp_invoke_ap_callback(cpu, state, bringup, node); else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #else ret = cpuhp_invoke_callback(cpu, state, bringup, node, NULL); #endif BUG_ON(ret && !bringup); return ret; } /* * Called from __cpuhp_setup_state on a recoverable failure. * * Note: The teardown callbacks for rollback are not allowed to fail! */ static void cpuhp_rollback_install(int failedcpu, enum cpuhp_state state, struct hlist_node *node) { int cpu; /* Roll back the already executed steps on the other cpus */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpu >= failedcpu) break; /* Did we invoke the startup call on that cpu ? */ if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } } int __cpuhp_state_add_instance_cpuslocked(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp; int cpu; int ret; lockdep_assert_cpus_held(); sp = cpuhp_get_step(state); if (sp->multi_instance == false) return -EINVAL; mutex_lock(&cpuhp_state_mutex); if (!invoke || !sp->startup.multi) goto add_node; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, node); if (ret) { if (sp->teardown.multi) cpuhp_rollback_install(cpu, state, node); goto unlock; } } add_node: ret = 0; hlist_add_head(node, &sp->list); unlock: mutex_unlock(&cpuhp_state_mutex); return ret; } int __cpuhp_state_add_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { int ret; cpus_read_lock(); ret = __cpuhp_state_add_instance_cpuslocked(state, node, invoke); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(__cpuhp_state_add_instance); /** * __cpuhp_setup_state_cpuslocked - Setup the callbacks for an hotplug machine state * @state: The state to setup * @invoke: If true, the startup function is invoked for cpus where * cpu state >= @state * @startup: startup callback function * @teardown: teardown callback function * @multi_instance: State is set up for multiple instances which get * added afterwards. * * The caller needs to hold cpus read locked while calling this function. * Returns: * On success: * Positive state number if @state is CPUHP_AP_ONLINE_DYN * 0 for all other states * On failure: proper (negative) error code */ int __cpuhp_setup_state_cpuslocked(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int cpu, ret = 0; bool dynstate; lockdep_assert_cpus_held(); if (cpuhp_cb_check(state) || !name) return -EINVAL; mutex_lock(&cpuhp_state_mutex); ret = cpuhp_store_callbacks(state, name, startup, teardown, multi_instance); dynstate = state == CPUHP_AP_ONLINE_DYN; if (ret > 0 && dynstate) { state = ret; ret = 0; } if (ret || !invoke || !startup) goto out; /* * Try to call the startup callback for each present cpu * depending on the hotplug state of the cpu. */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate < state) continue; ret = cpuhp_issue_call(cpu, state, true, NULL); if (ret) { if (teardown) cpuhp_rollback_install(cpu, state, NULL); cpuhp_store_callbacks(state, NULL, NULL, NULL, false); goto out; } } out: mutex_unlock(&cpuhp_state_mutex); /* * If the requested state is CPUHP_AP_ONLINE_DYN, return the * dynamically allocated state in case of success. */ if (!ret && dynstate) return state; return ret; } EXPORT_SYMBOL(__cpuhp_setup_state_cpuslocked); int __cpuhp_setup_state(enum cpuhp_state state, const char *name, bool invoke, int (*startup)(unsigned int cpu), int (*teardown)(unsigned int cpu), bool multi_instance) { int ret; cpus_read_lock(); ret = __cpuhp_setup_state_cpuslocked(state, name, invoke, startup, teardown, multi_instance); cpus_read_unlock(); return ret; } EXPORT_SYMBOL(__cpuhp_setup_state); int __cpuhp_state_remove_instance(enum cpuhp_state state, struct hlist_node *node, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); if (!sp->multi_instance) return -EINVAL; cpus_read_lock(); mutex_lock(&cpuhp_state_mutex); if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, node); } remove: hlist_del(node); mutex_unlock(&cpuhp_state_mutex); cpus_read_unlock(); return 0; } EXPORT_SYMBOL_GPL(__cpuhp_state_remove_instance); /** * __cpuhp_remove_state_cpuslocked - Remove the callbacks for an hotplug machine state * @state: The state to remove * @invoke: If true, the teardown function is invoked for cpus where * cpu state >= @state * * The caller needs to hold cpus read locked while calling this function. * The teardown callback is currently not allowed to fail. Think * about module removal! */ void __cpuhp_remove_state_cpuslocked(enum cpuhp_state state, bool invoke) { struct cpuhp_step *sp = cpuhp_get_step(state); int cpu; BUG_ON(cpuhp_cb_check(state)); lockdep_assert_cpus_held(); mutex_lock(&cpuhp_state_mutex); if (sp->multi_instance) { WARN(!hlist_empty(&sp->list), "Error: Removing state %d which has instances left.\n", state); goto remove; } if (!invoke || !cpuhp_get_teardown_cb(state)) goto remove; /* * Call the teardown callback for each present cpu depending * on the hotplug state of the cpu. This function is not * allowed to fail currently! */ for_each_present_cpu(cpu) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, cpu); int cpustate = st->state; if (cpustate >= state) cpuhp_issue_call(cpu, state, false, NULL); } remove: cpuhp_store_callbacks(state, NULL, NULL, NULL, false); mutex_unlock(&cpuhp_state_mutex); } EXPORT_SYMBOL(__cpuhp_remove_state_cpuslocked); void __cpuhp_remove_state(enum cpuhp_state state, bool invoke) { cpus_read_lock(); __cpuhp_remove_state_cpuslocked(state, invoke); cpus_read_unlock(); } EXPORT_SYMBOL(__cpuhp_remove_state); #ifdef CONFIG_HOTPLUG_SMT static void cpuhp_offline_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = true; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_OFFLINE); } static void cpuhp_online_cpu_device(unsigned int cpu) { struct device *dev = get_cpu_device(cpu); dev->offline = false; /* Tell user space about the state change */ kobject_uevent(&dev->kobj, KOBJ_ONLINE); } int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval) { int cpu, ret = 0; cpu_maps_update_begin(); for_each_online_cpu(cpu) { if (topology_is_primary_thread(cpu)) continue; ret = cpu_down_maps_locked(cpu, CPUHP_OFFLINE); if (ret) break; /* * As this needs to hold the cpu maps lock it's impossible * to call device_offline() because that ends up calling * cpu_down() which takes cpu maps lock. cpu maps lock * needs to be held as this might race against in kernel * abusers of the hotplug machinery (thermal management). * * So nothing would update device:offline state. That would * leave the sysfs entry stale and prevent onlining after * smt control has been changed to 'off' again. This is * called under the sysfs hotplug lock, so it is properly * serialized against the regular offline usage. */ cpuhp_offline_cpu_device(cpu); } if (!ret) cpu_smt_control = ctrlval; cpu_maps_update_done(); return ret; } int cpuhp_smt_enable(void) { int cpu, ret = 0; cpu_maps_update_begin(); cpu_smt_control = CPU_SMT_ENABLED; for_each_present_cpu(cpu) { /* Skip online CPUs and CPUs on offline nodes */ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu))) continue; ret = _cpu_up(cpu, 0, CPUHP_ONLINE); if (ret) break; /* See comment in cpuhp_smt_disable() */ cpuhp_online_cpu_device(cpu); } cpu_maps_update_done(); return ret; } #endif #if defined(CONFIG_SYSFS) && defined(CONFIG_HOTPLUG_CPU) static ssize_t show_cpuhp_state(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->state); } static DEVICE_ATTR(state, 0444, show_cpuhp_state, NULL); static ssize_t write_cpuhp_target(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int target, ret; ret = kstrtoint(buf, 10, &target); if (ret) return ret; #ifdef CONFIG_CPU_HOTPLUG_STATE_CONTROL if (target < CPUHP_OFFLINE || target > CPUHP_ONLINE) return -EINVAL; #else if (target != CPUHP_OFFLINE && target != CPUHP_ONLINE) return -EINVAL; #endif ret = lock_device_hotplug_sysfs(); if (ret) return ret; mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(target); ret = !sp->name || sp->cant_stop ? -EINVAL : 0; mutex_unlock(&cpuhp_state_mutex); if (ret) goto out; if (st->state < target) ret = do_cpu_up(dev->id, target); else ret = do_cpu_down(dev->id, target); out: unlock_device_hotplug(); return ret ? ret : count; } static ssize_t show_cpuhp_target(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->target); } static DEVICE_ATTR(target, 0644, show_cpuhp_target, write_cpuhp_target); static ssize_t write_cpuhp_fail(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); struct cpuhp_step *sp; int fail, ret; ret = kstrtoint(buf, 10, &fail); if (ret) return ret; if (fail < CPUHP_OFFLINE || fail > CPUHP_ONLINE) return -EINVAL; /* * Cannot fail STARTING/DYING callbacks. */ if (cpuhp_is_atomic_state(fail)) return -EINVAL; /* * Cannot fail anything that doesn't have callbacks. */ mutex_lock(&cpuhp_state_mutex); sp = cpuhp_get_step(fail); if (!sp->startup.single && !sp->teardown.single) ret = -EINVAL; mutex_unlock(&cpuhp_state_mutex); if (ret) return ret; st->fail = fail; return count; } static ssize_t show_cpuhp_fail(struct device *dev, struct device_attribute *attr, char *buf) { struct cpuhp_cpu_state *st = per_cpu_ptr(&cpuhp_state, dev->id); return sprintf(buf, "%d\n", st->fail); } static DEVICE_ATTR(fail, 0644, show_cpuhp_fail, write_cpuhp_fail); static struct attribute *cpuhp_cpu_attrs[] = { &dev_attr_state.attr, &dev_attr_target.attr, &dev_attr_fail.attr, NULL }; static const struct attribute_group cpuhp_cpu_attr_group = { .attrs = cpuhp_cpu_attrs, .name = "hotplug", NULL }; static ssize_t show_cpuhp_states(struct device *dev, struct device_attribute *attr, char *buf) { ssize_t cur, res = 0; int i; mutex_lock(&cpuhp_state_mutex); for (i = CPUHP_OFFLINE; i <= CPUHP_ONLINE; i++) { struct cpuhp_step *sp = cpuhp_get_step(i); if (sp->name) { cur = sprintf(buf, "%3d: %s\n", i, sp->name); buf += cur; res += cur; } } mutex_unlock(&cpuhp_state_mutex); return res; } static DEVICE_ATTR(states, 0444, show_cpuhp_states, NULL); static struct attribute *cpuhp_cpu_root_attrs[] = { &dev_attr_states.attr, NULL }; static const struct attribute_group cpuhp_cpu_root_attr_group = { .attrs = cpuhp_cpu_root_attrs, .name = "hotplug", NULL }; #ifdef CONFIG_HOTPLUG_SMT static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ctrlval, ret; if (sysfs_streq(buf, "on")) ctrlval = CPU_SMT_ENABLED; else if (sysfs_streq(buf, "off")) ctrlval = CPU_SMT_DISABLED; else if (sysfs_streq(buf, "forceoff")) ctrlval = CPU_SMT_FORCE_DISABLED; else return -EINVAL; if (cpu_smt_control == CPU_SMT_FORCE_DISABLED) return -EPERM; if (cpu_smt_control == CPU_SMT_NOT_SUPPORTED) return -ENODEV; ret = lock_device_hotplug_sysfs(); if (ret) return ret; if (ctrlval != cpu_smt_control) { switch (ctrlval) { case CPU_SMT_ENABLED: ret = cpuhp_smt_enable(); break; case CPU_SMT_DISABLED: case CPU_SMT_FORCE_DISABLED: ret = cpuhp_smt_disable(ctrlval); break; } } unlock_device_hotplug(); return ret ? ret : count; } #else /* !CONFIG_HOTPLUG_SMT */ static ssize_t __store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return -ENODEV; } #endif /* CONFIG_HOTPLUG_SMT */ static const char *smt_states[] = { [CPU_SMT_ENABLED] = "on", [CPU_SMT_DISABLED] = "off", [CPU_SMT_FORCE_DISABLED] = "forceoff", [CPU_SMT_NOT_SUPPORTED] = "notsupported", [CPU_SMT_NOT_IMPLEMENTED] = "notimplemented", }; static ssize_t show_smt_control(struct device *dev, struct device_attribute *attr, char *buf) { const char *state = smt_states[cpu_smt_control]; return snprintf(buf, PAGE_SIZE - 2, "%s\n", state); } static ssize_t store_smt_control(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { return __store_smt_control(dev, attr, buf, count); } static DEVICE_ATTR(control, 0644, show_smt_control, store_smt_control); static ssize_t show_smt_active(struct device *dev, struct device_attribute *attr, char *buf) { return snprintf(buf, PAGE_SIZE - 2, "%d\n", sched_smt_active()); } static DEVICE_ATTR(active, 0444, show_smt_active, NULL); static struct attribute *cpuhp_smt_attrs[] = { &dev_attr_control.attr, &dev_attr_active.attr, NULL }; static const struct attribute_group cpuhp_smt_attr_group = { .attrs = cpuhp_smt_attrs, .name = "smt", NULL }; static int __init cpu_smt_sysfs_init(void) { return sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_smt_attr_group); } static int __init cpuhp_sysfs_init(void) { int cpu, ret; ret = cpu_smt_sysfs_init(); if (ret) return ret; ret = sysfs_create_group(&cpu_subsys.dev_root->kobj, &cpuhp_cpu_root_attr_group); if (ret) return ret; for_each_possible_cpu(cpu) { struct device *dev = get_cpu_device(cpu); if (!dev) continue; ret = sysfs_create_group(&dev->kobj, &cpuhp_cpu_attr_group); if (ret) return ret; } return 0; } device_initcall(cpuhp_sysfs_init); #endif /* CONFIG_SYSFS && CONFIG_HOTPLUG_CPU */ /* * cpu_bit_bitmap[] is a special, "compressed" data structure that * represents all NR_CPUS bits binary values of 1<<nr. * * It is used by cpumask_of() to get a constant address to a CPU * mask value that has a single bit set only. */ /* cpu_bit_bitmap[0] is empty - so we can back into it */ #define MASK_DECLARE_1(x) [x+1][0] = (1UL << (x)) #define MASK_DECLARE_2(x) MASK_DECLARE_1(x), MASK_DECLARE_1(x+1) #define MASK_DECLARE_4(x) MASK_DECLARE_2(x), MASK_DECLARE_2(x+2) #define MASK_DECLARE_8(x) MASK_DECLARE_4(x), MASK_DECLARE_4(x+4) const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)] = { MASK_DECLARE_8(0), MASK_DECLARE_8(8), MASK_DECLARE_8(16), MASK_DECLARE_8(24), #if BITS_PER_LONG > 32 MASK_DECLARE_8(32), MASK_DECLARE_8(40), MASK_DECLARE_8(48), MASK_DECLARE_8(56), #endif }; EXPORT_SYMBOL_GPL(cpu_bit_bitmap); const DECLARE_BITMAP(cpu_all_bits, NR_CPUS) = CPU_BITS_ALL; EXPORT_SYMBOL(cpu_all_bits); #ifdef CONFIG_INIT_ALL_POSSIBLE struct cpumask __cpu_possible_mask __read_mostly = {CPU_BITS_ALL}; #else struct cpumask __cpu_possible_mask __read_mostly; #endif EXPORT_SYMBOL(__cpu_possible_mask); struct cpumask __cpu_online_mask __read_mostly; EXPORT_SYMBOL(__cpu_online_mask); struct cpumask __cpu_present_mask __read_mostly; EXPORT_SYMBOL(__cpu_present_mask); struct cpumask __cpu_active_mask __read_mostly; EXPORT_SYMBOL(__cpu_active_mask); atomic_t __num_online_cpus __read_mostly; EXPORT_SYMBOL(__num_online_cpus); void init_cpu_present(const struct cpumask *src) { cpumask_copy(&__cpu_present_mask, src); } void init_cpu_possible(const struct cpumask *src) { cpumask_copy(&__cpu_possible_mask, src); } void init_cpu_online(const struct cpumask *src) { cpumask_copy(&__cpu_online_mask, src); } void set_cpu_online(unsigned int cpu, bool online) { /* * atomic_inc/dec() is required to handle the horrid abuse of this * function by the reboot and kexec code which invoke it from * IPI/NMI broadcasts when shutting down CPUs. Invocation from * regular CPU hotplug is properly serialized. * * Note, that the fact that __num_online_cpus is of type atomic_t * does not protect readers which are not serialized against * concurrent hotplug operations. */ if (online) { if (!cpumask_test_and_set_cpu(cpu, &__cpu_online_mask)) atomic_inc(&__num_online_cpus); } else { if (cpumask_test_and_clear_cpu(cpu, &__cpu_online_mask)) atomic_dec(&__num_online_cpus); } } /* * Activate the first processor. */ void __init boot_cpu_init(void) { int cpu = smp_processor_id(); /* Mark the boot cpu "present", "online" etc for SMP and UP case */ set_cpu_online(cpu, true); set_cpu_active(cpu, true); set_cpu_present(cpu, true); set_cpu_possible(cpu, true); #ifdef CONFIG_SMP __boot_cpu_id = cpu; #endif } /* * Must be called _AFTER_ setting up the per_cpu areas */ void __init boot_cpu_hotplug_init(void) { #ifdef CONFIG_SMP cpumask_set_cpu(smp_processor_id(), &cpus_booted_once_mask); #endif this_cpu_write(cpuhp_state.state, CPUHP_ONLINE); } /* * These are used for a global "mitigations=" cmdline option for toggling * optional CPU mitigations. */ enum cpu_mitigations { CPU_MITIGATIONS_OFF, CPU_MITIGATIONS_AUTO, CPU_MITIGATIONS_AUTO_NOSMT, }; static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO; static int __init mitigations_parse_cmdline(char *arg) { if (!strcmp(arg, "off")) cpu_mitigations = CPU_MITIGATIONS_OFF; else if (!strcmp(arg, "auto")) cpu_mitigations = CPU_MITIGATIONS_AUTO; else if (!strcmp(arg, "auto,nosmt")) cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT; else pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n", arg); return 0; } early_param("mitigations", mitigations_parse_cmdline); /* mitigations=off */ bool cpu_mitigations_off(void) { return cpu_mitigations == CPU_MITIGATIONS_OFF; } EXPORT_SYMBOL_GPL(cpu_mitigations_off); /* mitigations=auto,nosmt */ bool cpu_mitigations_auto_nosmt(void) { return cpu_mitigations == CPU_MITIGATIONS_AUTO_NOSMT; } EXPORT_SYMBOL_GPL(cpu_mitigations_auto_nosmt); |
| 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 | /* BlueZ - Bluetooth protocol stack for Linux Copyright (C) 2000-2001 Qualcomm Incorporated Written 2000,2001 by Maxim Krasnyansky <maxk@qualcomm.com> This program is free software; you can redistribute it and/or modify it under the terms of the GNU General Public License version 2 as published by the Free Software Foundation; THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL THE COPYRIGHT HOLDER(S) AND AUTHOR(S) BE LIABLE FOR ANY CLAIM, OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. ALL LIABILITY, INCLUDING LIABILITY FOR INFRINGEMENT OF ANY PATENTS, COPYRIGHTS, TRADEMARKS OR OTHER RIGHTS, RELATING TO USE OF THIS SOFTWARE IS DISCLAIMED. */ /* Bluetooth address family and sockets. */ #include <linux/module.h> #include <linux/debugfs.h> #include <linux/stringify.h> #include <linux/sched/signal.h> #include <asm/ioctls.h> #include <net/bluetooth/bluetooth.h> #include <linux/proc_fs.h> #include "leds.h" #include "selftest.h" /* Bluetooth sockets */ #define BT_MAX_PROTO 8 static const struct net_proto_family *bt_proto[BT_MAX_PROTO]; static DEFINE_RWLOCK(bt_proto_lock); static struct lock_class_key bt_lock_key[BT_MAX_PROTO]; static const char *const bt_key_strings[BT_MAX_PROTO] = { "sk_lock-AF_BLUETOOTH-BTPROTO_L2CAP", "sk_lock-AF_BLUETOOTH-BTPROTO_HCI", "sk_lock-AF_BLUETOOTH-BTPROTO_SCO", "sk_lock-AF_BLUETOOTH-BTPROTO_RFCOMM", "sk_lock-AF_BLUETOOTH-BTPROTO_BNEP", "sk_lock-AF_BLUETOOTH-BTPROTO_CMTP", "sk_lock-AF_BLUETOOTH-BTPROTO_HIDP", "sk_lock-AF_BLUETOOTH-BTPROTO_AVDTP", }; static struct lock_class_key bt_slock_key[BT_MAX_PROTO]; static const char *const bt_slock_key_strings[BT_MAX_PROTO] = { "slock-AF_BLUETOOTH-BTPROTO_L2CAP", "slock-AF_BLUETOOTH-BTPROTO_HCI", "slock-AF_BLUETOOTH-BTPROTO_SCO", "slock-AF_BLUETOOTH-BTPROTO_RFCOMM", "slock-AF_BLUETOOTH-BTPROTO_BNEP", "slock-AF_BLUETOOTH-BTPROTO_CMTP", "slock-AF_BLUETOOTH-BTPROTO_HIDP", "slock-AF_BLUETOOTH-BTPROTO_AVDTP", }; void bt_sock_reclassify_lock(struct sock *sk, int proto) { BUG_ON(!sk); BUG_ON(!sock_allow_reclassification(sk)); sock_lock_init_class_and_name(sk, bt_slock_key_strings[proto], &bt_slock_key[proto], bt_key_strings[proto], &bt_lock_key[proto]); } EXPORT_SYMBOL(bt_sock_reclassify_lock); int bt_sock_register(int proto, const struct net_proto_family *ops) { int err = 0; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; write_lock(&bt_proto_lock); if (bt_proto[proto]) err = -EEXIST; else bt_proto[proto] = ops; write_unlock(&bt_proto_lock); return err; } EXPORT_SYMBOL(bt_sock_register); void bt_sock_unregister(int proto) { if (proto < 0 || proto >= BT_MAX_PROTO) return; write_lock(&bt_proto_lock); bt_proto[proto] = NULL; write_unlock(&bt_proto_lock); } EXPORT_SYMBOL(bt_sock_unregister); static int bt_sock_create(struct net *net, struct socket *sock, int proto, int kern) { int err; if (net != &init_net) return -EAFNOSUPPORT; if (proto < 0 || proto >= BT_MAX_PROTO) return -EINVAL; if (!bt_proto[proto]) request_module("bt-proto-%d", proto); err = -EPROTONOSUPPORT; read_lock(&bt_proto_lock); if (bt_proto[proto] && try_module_get(bt_proto[proto]->owner)) { err = bt_proto[proto]->create(net, sock, proto, kern); if (!err) bt_sock_reclassify_lock(sock->sk, proto); module_put(bt_proto[proto]->owner); } read_unlock(&bt_proto_lock); return err; } void bt_sock_link(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_add_node(sk, &l->head); write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_link); void bt_sock_unlink(struct bt_sock_list *l, struct sock *sk) { write_lock(&l->lock); sk_del_node_init(sk); write_unlock(&l->lock); } EXPORT_SYMBOL(bt_sock_unlink); void bt_accept_enqueue(struct sock *parent, struct sock *sk, bool bh) { BT_DBG("parent %p, sk %p", parent, sk); sock_hold(sk); if (bh) bh_lock_sock_nested(sk); else lock_sock_nested(sk, SINGLE_DEPTH_NESTING); list_add_tail(&bt_sk(sk)->accept_q, &bt_sk(parent)->accept_q); bt_sk(sk)->parent = parent; if (bh) bh_unlock_sock(sk); else release_sock(sk); parent->sk_ack_backlog++; } EXPORT_SYMBOL(bt_accept_enqueue); /* Calling function must hold the sk lock. * bt_sk(sk)->parent must be non-NULL meaning sk is in the parent list. */ void bt_accept_unlink(struct sock *sk) { BT_DBG("sk %p state %d", sk, sk->sk_state); list_del_init(&bt_sk(sk)->accept_q); bt_sk(sk)->parent->sk_ack_backlog--; bt_sk(sk)->parent = NULL; sock_put(sk); } EXPORT_SYMBOL(bt_accept_unlink); struct sock *bt_accept_dequeue(struct sock *parent, struct socket *newsock) { struct bt_sock *s, *n; struct sock *sk; BT_DBG("parent %p", parent); restart: list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; /* Prevent early freeing of sk due to unlink and sock_kill */ sock_hold(sk); lock_sock(sk); /* Check sk has not already been unlinked via * bt_accept_unlink() due to serialisation caused by sk locking */ if (!bt_sk(sk)->parent) { BT_DBG("sk %p, already unlinked", sk); release_sock(sk); sock_put(sk); /* Restart the loop as sk is no longer in the list * and also avoid a potential infinite loop because * list_for_each_entry_safe() is not thread safe. */ goto restart; } /* sk is safely in the parent list so reduce reference count */ sock_put(sk); /* FIXME: Is this check still needed */ if (sk->sk_state == BT_CLOSED) { bt_accept_unlink(sk); release_sock(sk); continue; } if (sk->sk_state == BT_CONNECTED || !newsock || test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags)) { bt_accept_unlink(sk); if (newsock) sock_graft(sk, newsock); release_sock(sk); return sk; } release_sock(sk); } return NULL; } EXPORT_SYMBOL(bt_accept_dequeue); int bt_sock_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, int flags) { int noblock = flags & MSG_DONTWAIT; struct sock *sk = sock->sk; struct sk_buff *skb; size_t copied; size_t skblen; int err; BT_DBG("sock %p sk %p len %zu", sock, sk, len); if (flags & MSG_OOB) return -EOPNOTSUPP; skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) { if (sk->sk_shutdown & RCV_SHUTDOWN) return 0; return err; } skblen = skb->len; copied = skb->len; if (len < copied) { msg->msg_flags |= MSG_TRUNC; copied = len; } skb_reset_transport_header(skb); err = skb_copy_datagram_msg(skb, 0, msg, copied); if (err == 0) { sock_recv_ts_and_drops(msg, sk, skb); if (msg->msg_name && bt_sk(sk)->skb_msg_name) bt_sk(sk)->skb_msg_name(skb, msg->msg_name, &msg->msg_namelen); } skb_free_datagram(sk, skb); if (flags & MSG_TRUNC) copied = skblen; return err ? : copied; } EXPORT_SYMBOL(bt_sock_recvmsg); static long bt_sock_data_wait(struct sock *sk, long timeo) { DECLARE_WAITQUEUE(wait, current); add_wait_queue(sk_sleep(sk), &wait); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (!skb_queue_empty(&sk->sk_receive_queue)) break; if (sk->sk_err || (sk->sk_shutdown & RCV_SHUTDOWN)) break; if (signal_pending(current) || !timeo) break; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); sk_clear_bit(SOCKWQ_ASYNC_WAITDATA, sk); } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return timeo; } int bt_sock_stream_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; int err = 0; size_t target, copied = 0; long timeo; if (flags & MSG_OOB) return -EOPNOTSUPP; BT_DBG("sk %p size %zu", sk, size); lock_sock(sk); target = sock_rcvlowat(sk, flags & MSG_WAITALL, size); timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb; int chunk; skb = skb_dequeue(&sk->sk_receive_queue); if (!skb) { if (copied >= target) break; err = sock_error(sk); if (err) break; if (sk->sk_shutdown & RCV_SHUTDOWN) break; err = -EAGAIN; if (!timeo) break; timeo = bt_sock_data_wait(sk, timeo); if (signal_pending(current)) { err = sock_intr_errno(timeo); goto out; } continue; } chunk = min_t(unsigned int, skb->len, size); if (skb_copy_datagram_msg(skb, 0, msg, chunk)) { skb_queue_head(&sk->sk_receive_queue, skb); if (!copied) copied = -EFAULT; break; } copied += chunk; size -= chunk; sock_recv_ts_and_drops(msg, sk, skb); if (!(flags & MSG_PEEK)) { int skb_len = skb_headlen(skb); if (chunk <= skb_len) { __skb_pull(skb, chunk); } else { struct sk_buff *frag; __skb_pull(skb, skb_len); chunk -= skb_len; skb_walk_frags(skb, frag) { if (chunk <= frag->len) { /* Pulling partial data */ skb->len -= chunk; skb->data_len -= chunk; __skb_pull(frag, chunk); break; } else if (frag->len) { /* Pulling all frag data */ chunk -= frag->len; skb->len -= frag->len; skb->data_len -= frag->len; __skb_pull(frag, frag->len); } } } if (skb->len) { skb_queue_head(&sk->sk_receive_queue, skb); break; } kfree_skb(skb); } else { /* put message back and return */ skb_queue_head(&sk->sk_receive_queue, skb); break; } } while (size); out: release_sock(sk); return copied ? : err; } EXPORT_SYMBOL(bt_sock_stream_recvmsg); static inline __poll_t bt_accept_poll(struct sock *parent) { struct bt_sock *s, *n; struct sock *sk; list_for_each_entry_safe(s, n, &bt_sk(parent)->accept_q, accept_q) { sk = (struct sock *)s; if (sk->sk_state == BT_CONNECTED || (test_bit(BT_SK_DEFER_SETUP, &bt_sk(parent)->flags) && sk->sk_state == BT_CONNECT2)) return EPOLLIN | EPOLLRDNORM; } return 0; } __poll_t bt_sock_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; __poll_t mask = 0; BT_DBG("sock %p, sk %p", sock, sk); poll_wait(file, sk_sleep(sk), wait); if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) mask |= EPOLLHUP; if (sk->sk_state == BT_CONNECT || sk->sk_state == BT_CONNECT2 || sk->sk_state == BT_CONFIG) return mask; if (!test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags) && sock_writeable(sk)) mask |= EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND; else sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); return mask; } EXPORT_SYMBOL(bt_sock_poll); int bt_sock_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct sock *sk = sock->sk; struct sk_buff *skb; long amount; int err; BT_DBG("sk %p cmd %x arg %lx", sk, cmd, arg); switch (cmd) { case TIOCOUTQ: if (sk->sk_state == BT_LISTEN) return -EINVAL; amount = sk->sk_sndbuf - sk_wmem_alloc_get(sk); if (amount < 0) amount = 0; err = put_user(amount, (int __user *) arg); break; case TIOCINQ: if (sk->sk_state == BT_LISTEN) return -EINVAL; lock_sock(sk); skb = skb_peek(&sk->sk_receive_queue); amount = skb ? skb->len : 0; release_sock(sk); err = put_user(amount, (int __user *) arg); break; default: err = -ENOIOCTLCMD; break; } return err; } EXPORT_SYMBOL(bt_sock_ioctl); /* This function expects the sk lock to be held when called */ int bt_sock_wait_state(struct sock *sk, int state, unsigned long timeo) { DECLARE_WAITQUEUE(wait, current); int err = 0; BT_DBG("sk %p", sk); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (sk->sk_state != state) { if (!timeo) { err = -EINPROGRESS; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_state); /* This function expects the sk lock to be held when called */ int bt_sock_wait_ready(struct sock *sk, unsigned long flags) { DECLARE_WAITQUEUE(wait, current); unsigned long timeo; int err = 0; BT_DBG("sk %p", sk); timeo = sock_sndtimeo(sk, flags & O_NONBLOCK); add_wait_queue(sk_sleep(sk), &wait); set_current_state(TASK_INTERRUPTIBLE); while (test_bit(BT_SK_SUSPEND, &bt_sk(sk)->flags)) { if (!timeo) { err = -EAGAIN; break; } if (signal_pending(current)) { err = sock_intr_errno(timeo); break; } release_sock(sk); timeo = schedule_timeout(timeo); lock_sock(sk); set_current_state(TASK_INTERRUPTIBLE); err = sock_error(sk); if (err) break; } __set_current_state(TASK_RUNNING); remove_wait_queue(sk_sleep(sk), &wait); return err; } EXPORT_SYMBOL(bt_sock_wait_ready); #ifdef CONFIG_PROC_FS static void *bt_seq_start(struct seq_file *seq, loff_t *pos) __acquires(seq->private->l->lock) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); read_lock(&l->lock); return seq_hlist_start_head(&l->head, *pos); } static void *bt_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); return seq_hlist_next(v, &l->head, pos); } static void bt_seq_stop(struct seq_file *seq, void *v) __releases(seq->private->l->lock) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); read_unlock(&l->lock); } static int bt_seq_show(struct seq_file *seq, void *v) { struct bt_sock_list *l = PDE_DATA(file_inode(seq->file)); if (v == SEQ_START_TOKEN) { seq_puts(seq ,"sk RefCnt Rmem Wmem User Inode Parent"); if (l->custom_seq_show) { seq_putc(seq, ' '); l->custom_seq_show(seq, v); } seq_putc(seq, '\n'); } else { struct sock *sk = sk_entry(v); struct bt_sock *bt = bt_sk(sk); seq_printf(seq, "%pK %-6d %-6u %-6u %-6u %-6lu %-6lu", sk, refcount_read(&sk->sk_refcnt), sk_rmem_alloc_get(sk), sk_wmem_alloc_get(sk), from_kuid(seq_user_ns(seq), sock_i_uid(sk)), sock_i_ino(sk), bt->parent? sock_i_ino(bt->parent): 0LU); if (l->custom_seq_show) { seq_putc(seq, ' '); l->custom_seq_show(seq, v); } seq_putc(seq, '\n'); } return 0; } static const struct seq_operations bt_seq_ops = { .start = bt_seq_start, .next = bt_seq_next, .stop = bt_seq_stop, .show = bt_seq_show, }; int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (* seq_show)(struct seq_file *, void *)) { sk_list->custom_seq_show = seq_show; if (!proc_create_seq_data(name, 0, net->proc_net, &bt_seq_ops, sk_list)) return -ENOMEM; return 0; } void bt_procfs_cleanup(struct net *net, const char *name) { remove_proc_entry(name, net->proc_net); } #else int bt_procfs_init(struct net *net, const char *name, struct bt_sock_list *sk_list, int (* seq_show)(struct seq_file *, void *)) { return 0; } void bt_procfs_cleanup(struct net *net, const char *name) { } #endif EXPORT_SYMBOL(bt_procfs_init); EXPORT_SYMBOL(bt_procfs_cleanup); static const struct net_proto_family bt_sock_family_ops = { .owner = THIS_MODULE, .family = PF_BLUETOOTH, .create = bt_sock_create, }; struct dentry *bt_debugfs; EXPORT_SYMBOL_GPL(bt_debugfs); #define VERSION __stringify(BT_SUBSYS_VERSION) "." \ __stringify(BT_SUBSYS_REVISION) static int __init bt_init(void) { int err; sock_skb_cb_check_size(sizeof(struct bt_skb_cb)); BT_INFO("Core ver %s", VERSION); err = bt_selftest(); if (err < 0) return err; bt_debugfs = debugfs_create_dir("bluetooth", NULL); bt_leds_init(); err = bt_sysfs_init(); if (err < 0) goto cleanup_led; err = sock_register(&bt_sock_family_ops); if (err) goto cleanup_sysfs; BT_INFO("HCI device and connection manager initialized"); err = hci_sock_init(); if (err) goto unregister_socket; err = l2cap_init(); if (err) goto cleanup_socket; err = sco_init(); if (err) goto cleanup_cap; err = mgmt_init(); if (err) goto cleanup_sco; return 0; cleanup_sco: sco_exit(); cleanup_cap: l2cap_exit(); cleanup_socket: hci_sock_cleanup(); unregister_socket: sock_unregister(PF_BLUETOOTH); cleanup_sysfs: bt_sysfs_cleanup(); cleanup_led: bt_leds_cleanup(); debugfs_remove_recursive(bt_debugfs); return err; } static void __exit bt_exit(void) { mgmt_exit(); sco_exit(); l2cap_exit(); hci_sock_cleanup(); sock_unregister(PF_BLUETOOTH); bt_sysfs_cleanup(); bt_leds_cleanup(); debugfs_remove_recursive(bt_debugfs); } subsys_initcall(bt_init); module_exit(bt_exit); MODULE_AUTHOR("Marcel Holtmann <marcel@holtmann.org>"); MODULE_DESCRIPTION("Bluetooth Core ver " VERSION); MODULE_VERSION(VERSION); MODULE_LICENSE("GPL"); MODULE_ALIAS_NETPROTO(PF_BLUETOOTH); |
| 172 73 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | // SPDX-License-Identifier: GPL-2.0-only /* * This is the 1999 rewrite of IP Firewalling, aiming for kernel 2.3.x. * * Copyright (C) 1999 Paul `Rusty' Russell & Michael J. Neuling * Copyright (C) 2000-2004 Netfilter Core Team <coreteam@netfilter.org> */ #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/slab.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("ip6tables filter table"); #define FILTER_VALID_HOOKS ((1 << NF_INET_LOCAL_IN) | \ (1 << NF_INET_FORWARD) | \ (1 << NF_INET_LOCAL_OUT)) static int __net_init ip6table_filter_table_init(struct net *net); static const struct xt_table packet_filter = { .name = "filter", .valid_hooks = FILTER_VALID_HOOKS, .me = THIS_MODULE, .af = NFPROTO_IPV6, .priority = NF_IP6_PRI_FILTER, .table_init = ip6table_filter_table_init, }; /* The work comes in here from netfilter.c. */ static unsigned int ip6table_filter_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { return ip6t_do_table(skb, state, state->net->ipv6.ip6table_filter); } static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ static bool forward = true; module_param(forward, bool, 0000); static int __net_init ip6table_filter_table_init(struct net *net) { struct ip6t_replace *repl; int err; if (net->ipv6.ip6table_filter) return 0; repl = ip6t_alloc_initial_table(&packet_filter); if (repl == NULL) return -ENOMEM; /* Entry 1 is the FORWARD hook */ ((struct ip6t_standard *)repl->entries)[1].target.verdict = forward ? -NF_ACCEPT - 1 : -NF_DROP - 1; err = ip6t_register_table(net, &packet_filter, repl, filter_ops, &net->ipv6.ip6table_filter); kfree(repl); return err; } static int __net_init ip6table_filter_net_init(struct net *net) { if (net == &init_net || !forward) return ip6table_filter_table_init(net); return 0; } static void __net_exit ip6table_filter_net_exit(struct net *net) { if (!net->ipv6.ip6table_filter) return; ip6t_unregister_table(net, net->ipv6.ip6table_filter, filter_ops); net->ipv6.ip6table_filter = NULL; } static struct pernet_operations ip6table_filter_net_ops = { .init = ip6table_filter_net_init, .exit = ip6table_filter_net_exit, }; static int __init ip6table_filter_init(void) { int ret; filter_ops = xt_hook_ops_alloc(&packet_filter, ip6table_filter_hook); if (IS_ERR(filter_ops)) return PTR_ERR(filter_ops); ret = register_pernet_subsys(&ip6table_filter_net_ops); if (ret < 0) kfree(filter_ops); return ret; } static void __exit ip6table_filter_fini(void) { unregister_pernet_subsys(&ip6table_filter_net_ops); kfree(filter_ops); } module_init(ip6table_filter_init); module_exit(ip6table_filter_fini); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMSTAT_H #define _LINUX_VMSTAT_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/mmzone.h> #include <linux/vm_event_item.h> #include <linux/atomic.h> #include <linux/static_key.h> extern int sysctl_stat_interval; #ifdef CONFIG_NUMA #define ENABLE_NUMA_STAT 1 #define DISABLE_NUMA_STAT 0 extern int sysctl_vm_numa_stat; DECLARE_STATIC_KEY_TRUE(vm_numa_stat_key); extern int sysctl_vm_numa_stat_handler(struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos); #endif struct reclaim_stat { unsigned nr_dirty; unsigned nr_unqueued_dirty; unsigned nr_congested; unsigned nr_writeback; unsigned nr_immediate; unsigned nr_activate[2]; unsigned nr_ref_keep; unsigned nr_unmap_fail; }; #ifdef CONFIG_VM_EVENT_COUNTERS /* * Light weight per cpu counter implementation. * * Counters should only be incremented and no critical kernel component * should rely on the counter values. * * Counters are handled completely inline. On many platforms the code * generated will simply be the increment of a global address. */ struct vm_event_state { unsigned long event[NR_VM_EVENT_ITEMS]; }; DECLARE_PER_CPU(struct vm_event_state, vm_event_states); /* * vm counters are allowed to be racy. Use raw_cpu_ops to avoid the * local_irq_disable overhead. */ static inline void __count_vm_event(enum vm_event_item item) { raw_cpu_inc(vm_event_states.event[item]); } static inline void count_vm_event(enum vm_event_item item) { this_cpu_inc(vm_event_states.event[item]); } static inline void __count_vm_events(enum vm_event_item item, long delta) { raw_cpu_add(vm_event_states.event[item], delta); } static inline void count_vm_events(enum vm_event_item item, long delta) { this_cpu_add(vm_event_states.event[item], delta); } extern void all_vm_events(unsigned long *); extern void vm_events_fold_cpu(int cpu); #else /* Disable counters */ static inline void count_vm_event(enum vm_event_item item) { } static inline void count_vm_events(enum vm_event_item item, long delta) { } static inline void __count_vm_event(enum vm_event_item item) { } static inline void __count_vm_events(enum vm_event_item item, long delta) { } static inline void all_vm_events(unsigned long *ret) { } static inline void vm_events_fold_cpu(int cpu) { } #endif /* CONFIG_VM_EVENT_COUNTERS */ #ifdef CONFIG_NUMA_BALANCING #define count_vm_numa_event(x) count_vm_event(x) #define count_vm_numa_events(x, y) count_vm_events(x, y) #else #define count_vm_numa_event(x) do {} while (0) #define count_vm_numa_events(x, y) do { (void)(y); } while (0) #endif /* CONFIG_NUMA_BALANCING */ #ifdef CONFIG_DEBUG_TLBFLUSH #define count_vm_tlb_event(x) count_vm_event(x) #define count_vm_tlb_events(x, y) count_vm_events(x, y) #else #define count_vm_tlb_event(x) do {} while (0) #define count_vm_tlb_events(x, y) do { (void)(y); } while (0) #endif #ifdef CONFIG_DEBUG_VM_VMACACHE #define count_vm_vmacache_event(x) count_vm_event(x) #else #define count_vm_vmacache_event(x) do {} while (0) #endif #define __count_zid_vm_events(item, zid, delta) \ __count_vm_events(item##_NORMAL - ZONE_NORMAL + zid, delta) /* * Zone and node-based page accounting with per cpu differentials. */ extern atomic_long_t vm_zone_stat[NR_VM_ZONE_STAT_ITEMS]; extern atomic_long_t vm_numa_stat[NR_VM_NUMA_STAT_ITEMS]; extern atomic_long_t vm_node_stat[NR_VM_NODE_STAT_ITEMS]; #ifdef CONFIG_NUMA static inline void zone_numa_state_add(long x, struct zone *zone, enum numa_stat_item item) { atomic_long_add(x, &zone->vm_numa_stat[item]); atomic_long_add(x, &vm_numa_stat[item]); } static inline unsigned long global_numa_state(enum numa_stat_item item) { long x = atomic_long_read(&vm_numa_stat[item]); return x; } static inline unsigned long zone_numa_state_snapshot(struct zone *zone, enum numa_stat_item item) { long x = atomic_long_read(&zone->vm_numa_stat[item]); int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_numa_stat_diff[item]; return x; } #endif /* CONFIG_NUMA */ static inline void zone_page_state_add(long x, struct zone *zone, enum zone_stat_item item) { atomic_long_add(x, &zone->vm_stat[item]); atomic_long_add(x, &vm_zone_stat[item]); } static inline void node_page_state_add(long x, struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_add(x, &pgdat->vm_stat[item]); atomic_long_add(x, &vm_node_stat[item]); } static inline unsigned long global_zone_page_state(enum zone_stat_item item) { long x = atomic_long_read(&vm_zone_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long global_node_page_state(enum node_stat_item item) { long x = atomic_long_read(&vm_node_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long zone_page_state(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * More accurate version that also considers the currently pending * deltas. For that we need to loop over all cpus to find the current * deltas. There is no synchronization so the result cannot be * exactly accurate either. */ static inline unsigned long zone_page_state_snapshot(struct zone *zone, enum zone_stat_item item) { long x = atomic_long_read(&zone->vm_stat[item]); #ifdef CONFIG_SMP int cpu; for_each_online_cpu(cpu) x += per_cpu_ptr(zone->pageset, cpu)->vm_stat_diff[item]; if (x < 0) x = 0; #endif return x; } #ifdef CONFIG_NUMA extern void __inc_numa_state(struct zone *zone, enum numa_stat_item item); extern unsigned long sum_zone_node_page_state(int node, enum zone_stat_item item); extern unsigned long sum_zone_numa_state(int node, enum numa_stat_item item); extern unsigned long node_page_state(struct pglist_data *pgdat, enum node_stat_item item); #else #define sum_zone_node_page_state(node, item) global_zone_page_state(item) #define node_page_state(node, item) global_node_page_state(item) #endif /* CONFIG_NUMA */ #ifdef CONFIG_SMP void __mod_zone_page_state(struct zone *, enum zone_stat_item item, long); void __inc_zone_page_state(struct page *, enum zone_stat_item); void __dec_zone_page_state(struct page *, enum zone_stat_item); void __mod_node_page_state(struct pglist_data *, enum node_stat_item item, long); void __inc_node_page_state(struct page *, enum node_stat_item); void __dec_node_page_state(struct page *, enum node_stat_item); void mod_zone_page_state(struct zone *, enum zone_stat_item, long); void inc_zone_page_state(struct page *, enum zone_stat_item); void dec_zone_page_state(struct page *, enum zone_stat_item); void mod_node_page_state(struct pglist_data *, enum node_stat_item, long); void inc_node_page_state(struct page *, enum node_stat_item); void dec_node_page_state(struct page *, enum node_stat_item); extern void inc_node_state(struct pglist_data *, enum node_stat_item); extern void __inc_zone_state(struct zone *, enum zone_stat_item); extern void __inc_node_state(struct pglist_data *, enum node_stat_item); extern void dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_zone_state(struct zone *, enum zone_stat_item); extern void __dec_node_state(struct pglist_data *, enum node_stat_item); void quiet_vmstat(void); void cpu_vm_stats_fold(int cpu); void refresh_zone_stat_thresholds(void); struct ctl_table; int vmstat_refresh(struct ctl_table *, int write, void __user *buffer, size_t *lenp, loff_t *ppos); void drain_zonestat(struct zone *zone, struct per_cpu_pageset *); int calculate_pressure_threshold(struct zone *zone); int calculate_normal_threshold(struct zone *zone); void set_pgdat_percpu_threshold(pg_data_t *pgdat, int (*calculate_pressure)(struct zone *)); #else /* CONFIG_SMP */ /* * We do not maintain differentials in a single processor configuration. * The functions directly modify the zone and global counters. */ static inline void __mod_zone_page_state(struct zone *zone, enum zone_stat_item item, long delta) { zone_page_state_add(delta, zone, item); } static inline void __mod_node_page_state(struct pglist_data *pgdat, enum node_stat_item item, int delta) { node_page_state_add(delta, pgdat, item); } static inline void __inc_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_inc(&zone->vm_stat[item]); atomic_long_inc(&vm_zone_stat[item]); } static inline void __inc_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_inc(&pgdat->vm_stat[item]); atomic_long_inc(&vm_node_stat[item]); } static inline void __dec_zone_state(struct zone *zone, enum zone_stat_item item) { atomic_long_dec(&zone->vm_stat[item]); atomic_long_dec(&vm_zone_stat[item]); } static inline void __dec_node_state(struct pglist_data *pgdat, enum node_stat_item item) { atomic_long_dec(&pgdat->vm_stat[item]); atomic_long_dec(&vm_node_stat[item]); } static inline void __inc_zone_page_state(struct page *page, enum zone_stat_item item) { __inc_zone_state(page_zone(page), item); } static inline void __inc_node_page_state(struct page *page, enum node_stat_item item) { __inc_node_state(page_pgdat(page), item); } static inline void __dec_zone_page_state(struct page *page, enum zone_stat_item item) { __dec_zone_state(page_zone(page), item); } static inline void __dec_node_page_state(struct page *page, enum node_stat_item item) { __dec_node_state(page_pgdat(page), item); } /* * We only use atomic operations to update counters. So there is no need to * disable interrupts. */ #define inc_zone_page_state __inc_zone_page_state #define dec_zone_page_state __dec_zone_page_state #define mod_zone_page_state __mod_zone_page_state #define inc_node_page_state __inc_node_page_state #define dec_node_page_state __dec_node_page_state #define mod_node_page_state __mod_node_page_state #define inc_zone_state __inc_zone_state #define inc_node_state __inc_node_state #define dec_zone_state __dec_zone_state #define set_pgdat_percpu_threshold(pgdat, callback) { } static inline void refresh_zone_stat_thresholds(void) { } static inline void cpu_vm_stats_fold(int cpu) { } static inline void quiet_vmstat(void) { } static inline void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { } #endif /* CONFIG_SMP */ static inline void __mod_zone_freepage_state(struct zone *zone, int nr_pages, int migratetype) { __mod_zone_page_state(zone, NR_FREE_PAGES, nr_pages); if (is_migrate_cma(migratetype)) __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, nr_pages); } extern const char * const vmstat_text[]; #endif /* _LINUX_VMSTAT_H */ |
| 1847 8 1836 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 | // SPDX-License-Identifier: GPL-2.0-only /* * The "user cache". * * (C) Copyright 1991-2000 Linus Torvalds * * We have a per-user structure to keep track of how many * processes, files etc the user has claimed, in order to be * able to have per-user limits for system resources. */ #include <linux/init.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/bitops.h> #include <linux/key.h> #include <linux/sched/user.h> #include <linux/interrupt.h> #include <linux/export.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> /* * userns count is 1 for root user, 1 for init_uts_ns, * and 1 for... ? */ struct user_namespace init_user_ns = { .uid_map = { .nr_extents = 1, { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, }, }, .gid_map = { .nr_extents = 1, { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, }, }, .projid_map = { .nr_extents = 1, { .extent[0] = { .first = 0, .lower_first = 0, .count = 4294967295U, }, }, }, .count = ATOMIC_INIT(3), .owner = GLOBAL_ROOT_UID, .group = GLOBAL_ROOT_GID, .ns.inum = PROC_USER_INIT_INO, #ifdef CONFIG_USER_NS .ns.ops = &userns_operations, #endif .flags = USERNS_INIT_FLAGS, #ifdef CONFIG_KEYS .keyring_name_list = LIST_HEAD_INIT(init_user_ns.keyring_name_list), .keyring_sem = __RWSEM_INITIALIZER(init_user_ns.keyring_sem), #endif }; EXPORT_SYMBOL_GPL(init_user_ns); /* * UID task count cache, to get fast user lookup in "alloc_uid" * when changing user ID's (ie setuid() and friends). */ #define UIDHASH_BITS (CONFIG_BASE_SMALL ? 3 : 7) #define UIDHASH_SZ (1 << UIDHASH_BITS) #define UIDHASH_MASK (UIDHASH_SZ - 1) #define __uidhashfn(uid) (((uid >> UIDHASH_BITS) + uid) & UIDHASH_MASK) #define uidhashentry(uid) (uidhash_table + __uidhashfn((__kuid_val(uid)))) static struct kmem_cache *uid_cachep; struct hlist_head uidhash_table[UIDHASH_SZ]; /* * The uidhash_lock is mostly taken from process context, but it is * occasionally also taken from softirq/tasklet context, when * task-structs get RCU-freed. Hence all locking must be softirq-safe. * But free_uid() is also called with local interrupts disabled, and running * local_bh_enable() with local interrupts disabled is an error - we'll run * softirq callbacks, and they can unconditionally enable interrupts, and * the caller of free_uid() didn't expect that.. */ static DEFINE_SPINLOCK(uidhash_lock); /* root_user.__count is 1, for init task cred */ struct user_struct root_user = { .__count = REFCOUNT_INIT(1), .processes = ATOMIC_INIT(1), .sigpending = ATOMIC_INIT(0), .locked_shm = 0, .uid = GLOBAL_ROOT_UID, .ratelimit = RATELIMIT_STATE_INIT(root_user.ratelimit, 0, 0), }; /* * These routines must be called with the uidhash spinlock held! */ static void uid_hash_insert(struct user_struct *up, struct hlist_head *hashent) { hlist_add_head(&up->uidhash_node, hashent); } static void uid_hash_remove(struct user_struct *up) { hlist_del_init(&up->uidhash_node); } static struct user_struct *uid_hash_find(kuid_t uid, struct hlist_head *hashent) { struct user_struct *user; hlist_for_each_entry(user, hashent, uidhash_node) { if (uid_eq(user->uid, uid)) { refcount_inc(&user->__count); return user; } } return NULL; } /* IRQs are disabled and uidhash_lock is held upon function entry. * IRQ state (as stored in flags) is restored and uidhash_lock released * upon function exit. */ static void free_user(struct user_struct *up, unsigned long flags) __releases(&uidhash_lock) { uid_hash_remove(up); spin_unlock_irqrestore(&uidhash_lock, flags); kmem_cache_free(uid_cachep, up); } /* * Locate the user_struct for the passed UID. If found, take a ref on it. The * caller must undo that ref with free_uid(). * * If the user_struct could not be found, return NULL. */ struct user_struct *find_user(kuid_t uid) { struct user_struct *ret; unsigned long flags; spin_lock_irqsave(&uidhash_lock, flags); ret = uid_hash_find(uid, uidhashentry(uid)); spin_unlock_irqrestore(&uidhash_lock, flags); return ret; } void free_uid(struct user_struct *up) { unsigned long flags; if (!up) return; if (refcount_dec_and_lock_irqsave(&up->__count, &uidhash_lock, &flags)) free_user(up, flags); } struct user_struct *alloc_uid(kuid_t uid) { struct hlist_head *hashent = uidhashentry(uid); struct user_struct *up, *new; spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); spin_unlock_irq(&uidhash_lock); if (!up) { new = kmem_cache_zalloc(uid_cachep, GFP_KERNEL); if (!new) return NULL; new->uid = uid; refcount_set(&new->__count, 1); ratelimit_state_init(&new->ratelimit, HZ, 100); ratelimit_set_flags(&new->ratelimit, RATELIMIT_MSG_ON_RELEASE); /* * Before adding this, check whether we raced * on adding the same user already.. */ spin_lock_irq(&uidhash_lock); up = uid_hash_find(uid, hashent); if (up) { kmem_cache_free(uid_cachep, new); } else { uid_hash_insert(new, hashent); up = new; } spin_unlock_irq(&uidhash_lock); } return up; } static int __init uid_cache_init(void) { int n; uid_cachep = kmem_cache_create("uid_cache", sizeof(struct user_struct), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL); for(n = 0; n < UIDHASH_SZ; ++n) INIT_HLIST_HEAD(uidhash_table + n); /* Insert the root user immediately (init already runs as root) */ spin_lock_irq(&uidhash_lock); uid_hash_insert(&root_user, uidhashentry(GLOBAL_ROOT_UID)); spin_unlock_irq(&uidhash_lock); return 0; } subsys_initcall(uid_cache_init); |
| 20 1 1 171 171 20 1502 1505 36 249 36 36 36 35 272 270 36 4085 47 4012 4105 171 23 94 1 169 246 245 244 246 246 243 244 244 243 245 247 243 246 245 247 82 173 250 21 12 11 248 251 249 171 172 251 251 1503 980 1508 1499 20 1505 7234 3520 7231 7229 238 5411 5426 232 243 245 981 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the kernel access vector cache (AVC). * * Authors: Stephen Smalley, <sds@tycho.nsa.gov> * James Morris <jmorris@redhat.com> * * Update: KaiGai, Kohei <kaigai@ak.jp.nec.com> * Replaced the avc_lock spinlock by RCU. * * Copyright (C) 2003 Red Hat, Inc., James Morris <jmorris@redhat.com> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/fs.h> #include <linux/dcache.h> #include <linux/init.h> #include <linux/skbuff.h> #include <linux/percpu.h> #include <linux/list.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/ip.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <net/ipv6.h> #include "avc.h" #include "avc_ss.h" #include "classmap.h" #define CREATE_TRACE_POINTS #include <trace/events/avc.h> #define AVC_CACHE_SLOTS 512 #define AVC_DEF_CACHE_THRESHOLD 512 #define AVC_CACHE_RECLAIM 16 #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS #define avc_cache_stats_incr(field) this_cpu_inc(avc_cache_stats.field) #else #define avc_cache_stats_incr(field) do {} while (0) #endif struct avc_entry { u32 ssid; u32 tsid; u16 tclass; struct av_decision avd; struct avc_xperms_node *xp_node; }; struct avc_node { struct avc_entry ae; struct hlist_node list; /* anchored in avc_cache->slots[i] */ struct rcu_head rhead; }; struct avc_xperms_decision_node { struct extended_perms_decision xpd; struct list_head xpd_list; /* list of extended_perms_decision */ }; struct avc_xperms_node { struct extended_perms xp; struct list_head xpd_head; /* list head of extended_perms_decision */ }; struct avc_cache { struct hlist_head slots[AVC_CACHE_SLOTS]; /* head for avc_node->list */ spinlock_t slots_lock[AVC_CACHE_SLOTS]; /* lock for writes */ atomic_t lru_hint; /* LRU hint for reclaim scan */ atomic_t active_nodes; u32 latest_notif; /* latest revocation notification */ }; struct avc_callback_node { int (*callback) (u32 event); u32 events; struct avc_callback_node *next; }; #ifdef CONFIG_SECURITY_SELINUX_AVC_STATS DEFINE_PER_CPU(struct avc_cache_stats, avc_cache_stats) = { 0 }; #endif struct selinux_avc { unsigned int avc_cache_threshold; struct avc_cache avc_cache; }; static struct selinux_avc selinux_avc; void selinux_avc_init(struct selinux_avc **avc) { int i; selinux_avc.avc_cache_threshold = AVC_DEF_CACHE_THRESHOLD; for (i = 0; i < AVC_CACHE_SLOTS; i++) { INIT_HLIST_HEAD(&selinux_avc.avc_cache.slots[i]); spin_lock_init(&selinux_avc.avc_cache.slots_lock[i]); } atomic_set(&selinux_avc.avc_cache.active_nodes, 0); atomic_set(&selinux_avc.avc_cache.lru_hint, 0); *avc = &selinux_avc; } unsigned int avc_get_cache_threshold(struct selinux_avc *avc) { return avc->avc_cache_threshold; } void avc_set_cache_threshold(struct selinux_avc *avc, unsigned int cache_threshold) { avc->avc_cache_threshold = cache_threshold; } static struct avc_callback_node *avc_callbacks; static struct kmem_cache *avc_node_cachep; static struct kmem_cache *avc_xperms_data_cachep; static struct kmem_cache *avc_xperms_decision_cachep; static struct kmem_cache *avc_xperms_cachep; static inline int avc_hash(u32 ssid, u32 tsid, u16 tclass) { return (ssid ^ (tsid<<2) ^ (tclass<<4)) & (AVC_CACHE_SLOTS - 1); } /** * avc_init - Initialize the AVC. * * Initialize the access vector cache. */ void __init avc_init(void) { avc_node_cachep = kmem_cache_create("avc_node", sizeof(struct avc_node), 0, SLAB_PANIC, NULL); avc_xperms_cachep = kmem_cache_create("avc_xperms_node", sizeof(struct avc_xperms_node), 0, SLAB_PANIC, NULL); avc_xperms_decision_cachep = kmem_cache_create( "avc_xperms_decision_node", sizeof(struct avc_xperms_decision_node), 0, SLAB_PANIC, NULL); avc_xperms_data_cachep = kmem_cache_create("avc_xperms_data", sizeof(struct extended_perms_data), 0, SLAB_PANIC, NULL); } int avc_get_hash_stats(struct selinux_avc *avc, char *page) { int i, chain_len, max_chain_len, slots_used; struct avc_node *node; struct hlist_head *head; rcu_read_lock(); slots_used = 0; max_chain_len = 0; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc->avc_cache.slots[i]; if (!hlist_empty(head)) { slots_used++; chain_len = 0; hlist_for_each_entry_rcu(node, head, list) chain_len++; if (chain_len > max_chain_len) max_chain_len = chain_len; } } rcu_read_unlock(); return scnprintf(page, PAGE_SIZE, "entries: %d\nbuckets used: %d/%d\n" "longest chain: %d\n", atomic_read(&avc->avc_cache.active_nodes), slots_used, AVC_CACHE_SLOTS, max_chain_len); } /* * using a linked list for extended_perms_decision lookup because the list is * always small. i.e. less than 5, typically 1 */ static struct extended_perms_decision *avc_xperms_decision_lookup(u8 driver, struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node; list_for_each_entry(xpd_node, &xp_node->xpd_head, xpd_list) { if (xpd_node->xpd.driver == driver) return &xpd_node->xpd; } return NULL; } static inline unsigned int avc_xperms_has_perm(struct extended_perms_decision *xpd, u8 perm, u8 which) { unsigned int rc = 0; if ((which == XPERMS_ALLOWED) && (xpd->used & XPERMS_ALLOWED)) rc = security_xperm_test(xpd->allowed->p, perm); else if ((which == XPERMS_AUDITALLOW) && (xpd->used & XPERMS_AUDITALLOW)) rc = security_xperm_test(xpd->auditallow->p, perm); else if ((which == XPERMS_DONTAUDIT) && (xpd->used & XPERMS_DONTAUDIT)) rc = security_xperm_test(xpd->dontaudit->p, perm); return rc; } static void avc_xperms_allow_perm(struct avc_xperms_node *xp_node, u8 driver, u8 perm) { struct extended_perms_decision *xpd; security_xperm_set(xp_node->xp.drivers.p, driver); xpd = avc_xperms_decision_lookup(driver, xp_node); if (xpd && xpd->allowed) security_xperm_set(xpd->allowed->p, perm); } static void avc_xperms_decision_free(struct avc_xperms_decision_node *xpd_node) { struct extended_perms_decision *xpd; xpd = &xpd_node->xpd; if (xpd->allowed) kmem_cache_free(avc_xperms_data_cachep, xpd->allowed); if (xpd->auditallow) kmem_cache_free(avc_xperms_data_cachep, xpd->auditallow); if (xpd->dontaudit) kmem_cache_free(avc_xperms_data_cachep, xpd->dontaudit); kmem_cache_free(avc_xperms_decision_cachep, xpd_node); } static void avc_xperms_free(struct avc_xperms_node *xp_node) { struct avc_xperms_decision_node *xpd_node, *tmp; if (!xp_node) return; list_for_each_entry_safe(xpd_node, tmp, &xp_node->xpd_head, xpd_list) { list_del(&xpd_node->xpd_list); avc_xperms_decision_free(xpd_node); } kmem_cache_free(avc_xperms_cachep, xp_node); } static void avc_copy_xperms_decision(struct extended_perms_decision *dest, struct extended_perms_decision *src) { dest->driver = src->driver; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) memcpy(dest->allowed->p, src->allowed->p, sizeof(src->allowed->p)); if (dest->used & XPERMS_AUDITALLOW) memcpy(dest->auditallow->p, src->auditallow->p, sizeof(src->auditallow->p)); if (dest->used & XPERMS_DONTAUDIT) memcpy(dest->dontaudit->p, src->dontaudit->p, sizeof(src->dontaudit->p)); } /* * similar to avc_copy_xperms_decision, but only copy decision * information relevant to this perm */ static inline void avc_quick_copy_xperms_decision(u8 perm, struct extended_perms_decision *dest, struct extended_perms_decision *src) { /* * compute index of the u32 of the 256 bits (8 u32s) that contain this * command permission */ u8 i = perm >> 5; dest->used = src->used; if (dest->used & XPERMS_ALLOWED) dest->allowed->p[i] = src->allowed->p[i]; if (dest->used & XPERMS_AUDITALLOW) dest->auditallow->p[i] = src->auditallow->p[i]; if (dest->used & XPERMS_DONTAUDIT) dest->dontaudit->p[i] = src->dontaudit->p[i]; } static struct avc_xperms_decision_node *avc_xperms_decision_alloc(u8 which) { struct avc_xperms_decision_node *xpd_node; struct extended_perms_decision *xpd; xpd_node = kmem_cache_zalloc(avc_xperms_decision_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd_node) return NULL; xpd = &xpd_node->xpd; if (which & XPERMS_ALLOWED) { xpd->allowed = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->allowed) goto error; } if (which & XPERMS_AUDITALLOW) { xpd->auditallow = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->auditallow) goto error; } if (which & XPERMS_DONTAUDIT) { xpd->dontaudit = kmem_cache_zalloc(avc_xperms_data_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xpd->dontaudit) goto error; } return xpd_node; error: avc_xperms_decision_free(xpd_node); return NULL; } static int avc_add_xperms_decision(struct avc_node *node, struct extended_perms_decision *src) { struct avc_xperms_decision_node *dest_xpd; dest_xpd = avc_xperms_decision_alloc(src->used); if (!dest_xpd) return -ENOMEM; avc_copy_xperms_decision(&dest_xpd->xpd, src); list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head); node->ae.xp_node->xp.len++; return 0; } static struct avc_xperms_node *avc_xperms_alloc(void) { struct avc_xperms_node *xp_node; xp_node = kmem_cache_zalloc(avc_xperms_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!xp_node) return xp_node; INIT_LIST_HEAD(&xp_node->xpd_head); return xp_node; } static int avc_xperms_populate(struct avc_node *node, struct avc_xperms_node *src) { struct avc_xperms_node *dest; struct avc_xperms_decision_node *dest_xpd; struct avc_xperms_decision_node *src_xpd; if (src->xp.len == 0) return 0; dest = avc_xperms_alloc(); if (!dest) return -ENOMEM; memcpy(dest->xp.drivers.p, src->xp.drivers.p, sizeof(dest->xp.drivers.p)); dest->xp.len = src->xp.len; /* for each source xpd allocate a destination xpd and copy */ list_for_each_entry(src_xpd, &src->xpd_head, xpd_list) { dest_xpd = avc_xperms_decision_alloc(src_xpd->xpd.used); if (!dest_xpd) goto error; avc_copy_xperms_decision(&dest_xpd->xpd, &src_xpd->xpd); list_add(&dest_xpd->xpd_list, &dest->xpd_head); } node->ae.xp_node = dest; return 0; error: avc_xperms_free(dest); return -ENOMEM; } static inline u32 avc_xperms_audit_required(u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, u32 *deniedp) { u32 denied, audited; denied = requested & ~avd->allowed; if (unlikely(denied)) { audited = denied & avd->auditdeny; if (audited && xpd) { if (avc_xperms_has_perm(xpd, perm, XPERMS_DONTAUDIT)) audited &= ~requested; } } else if (result) { audited = denied = requested; } else { audited = requested & avd->auditallow; if (audited && xpd) { if (!avc_xperms_has_perm(xpd, perm, XPERMS_AUDITALLOW)) audited &= ~requested; } } *deniedp = denied; return audited; } static inline int avc_xperms_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct av_decision *avd, struct extended_perms_decision *xpd, u8 perm, int result, struct common_audit_data *ad) { u32 audited, denied; audited = avc_xperms_audit_required( requested, avd, xpd, perm, result, &denied); if (likely(!audited)) return 0; return slow_avc_audit(state, ssid, tsid, tclass, requested, audited, denied, result, ad); } static void avc_node_free(struct rcu_head *rhead) { struct avc_node *node = container_of(rhead, struct avc_node, rhead); avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); } static void avc_node_delete(struct selinux_avc *avc, struct avc_node *node) { hlist_del_rcu(&node->list); call_rcu(&node->rhead, avc_node_free); atomic_dec(&avc->avc_cache.active_nodes); } static void avc_node_kill(struct selinux_avc *avc, struct avc_node *node) { avc_xperms_free(node->ae.xp_node); kmem_cache_free(avc_node_cachep, node); avc_cache_stats_incr(frees); atomic_dec(&avc->avc_cache.active_nodes); } static void avc_node_replace(struct selinux_avc *avc, struct avc_node *new, struct avc_node *old) { hlist_replace_rcu(&old->list, &new->list); call_rcu(&old->rhead, avc_node_free); atomic_dec(&avc->avc_cache.active_nodes); } static inline int avc_reclaim_node(struct selinux_avc *avc) { struct avc_node *node; int hvalue, try, ecx; unsigned long flags; struct hlist_head *head; spinlock_t *lock; for (try = 0, ecx = 0; try < AVC_CACHE_SLOTS; try++) { hvalue = atomic_inc_return(&avc->avc_cache.lru_hint) & (AVC_CACHE_SLOTS - 1); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; if (!spin_trylock_irqsave(lock, flags)) continue; rcu_read_lock(); hlist_for_each_entry(node, head, list) { avc_node_delete(avc, node); avc_cache_stats_incr(reclaims); ecx++; if (ecx >= AVC_CACHE_RECLAIM) { rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); goto out; } } rcu_read_unlock(); spin_unlock_irqrestore(lock, flags); } out: return ecx; } static struct avc_node *avc_alloc_node(struct selinux_avc *avc) { struct avc_node *node; node = kmem_cache_zalloc(avc_node_cachep, GFP_NOWAIT | __GFP_NOWARN); if (!node) goto out; INIT_HLIST_NODE(&node->list); avc_cache_stats_incr(allocations); if (atomic_inc_return(&avc->avc_cache.active_nodes) > avc->avc_cache_threshold) avc_reclaim_node(avc); out: return node; } static void avc_node_populate(struct avc_node *node, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd) { node->ae.ssid = ssid; node->ae.tsid = tsid; node->ae.tclass = tclass; memcpy(&node->ae.avd, avd, sizeof(node->ae.avd)); } static inline struct avc_node *avc_search_node(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node, *ret = NULL; int hvalue; struct hlist_head *head; hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; hlist_for_each_entry_rcu(node, head, list) { if (ssid == node->ae.ssid && tclass == node->ae.tclass && tsid == node->ae.tsid) { ret = node; break; } } return ret; } /** * avc_lookup - Look up an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * * Look up an AVC entry that is valid for the * (@ssid, @tsid), interpreting the permissions * based on @tclass. If a valid AVC entry exists, * then this function returns the avc_node. * Otherwise, this function returns NULL. */ static struct avc_node *avc_lookup(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass) { struct avc_node *node; avc_cache_stats_incr(lookups); node = avc_search_node(avc, ssid, tsid, tclass); if (node) return node; avc_cache_stats_incr(misses); return NULL; } static int avc_latest_notif_update(struct selinux_avc *avc, int seqno, int is_insert) { int ret = 0; static DEFINE_SPINLOCK(notif_lock); unsigned long flag; spin_lock_irqsave(¬if_lock, flag); if (is_insert) { if (seqno < avc->avc_cache.latest_notif) { pr_warn("SELinux: avc: seqno %d < latest_notif %d\n", seqno, avc->avc_cache.latest_notif); ret = -EAGAIN; } } else { if (seqno > avc->avc_cache.latest_notif) avc->avc_cache.latest_notif = seqno; } spin_unlock_irqrestore(¬if_lock, flag); return ret; } /** * avc_insert - Insert an AVC entry. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @avd: resulting av decision * @xp_node: resulting extended permissions * * Insert an AVC entry for the SID pair * (@ssid, @tsid) and class @tclass. * The access vectors and the sequence number are * normally provided by the security server in * response to a security_compute_av() call. If the * sequence number @avd->seqno is not less than the latest * revocation notification, then the function copies * the access vectors into a cache entry, returns * avc_node inserted. Otherwise, this function returns NULL. */ static struct avc_node *avc_insert(struct selinux_avc *avc, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { struct avc_node *pos, *node = NULL; int hvalue; unsigned long flag; spinlock_t *lock; struct hlist_head *head; if (avc_latest_notif_update(avc, avd->seqno, 1)) return NULL; node = avc_alloc_node(avc); if (!node) return NULL; avc_node_populate(node, ssid, tsid, tclass, avd); if (avc_xperms_populate(node, xp_node)) { avc_node_kill(avc, node); return NULL; } hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (pos->ae.ssid == ssid && pos->ae.tsid == tsid && pos->ae.tclass == tclass) { avc_node_replace(avc, node, pos); goto found; } } hlist_add_head_rcu(&node->list, head); found: spin_unlock_irqrestore(lock, flag); return node; } /** * avc_audit_pre_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_pre_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; u32 av = sad->audited; const char **perms; int i, perm; audit_log_format(ab, "avc: %s ", sad->denied ? "denied" : "granted"); if (av == 0) { audit_log_format(ab, " null"); return; } perms = secclass_map[sad->tclass-1].perms; audit_log_format(ab, " {"); i = 0; perm = 1; while (i < (sizeof(av) * 8)) { if ((perm & av) && perms[i]) { audit_log_format(ab, " %s", perms[i]); av &= ~perm; } i++; perm <<= 1; } if (av) audit_log_format(ab, " 0x%x", av); audit_log_format(ab, " } for "); } /** * avc_audit_post_callback - SELinux specific information * will be called by generic audit code * @ab: the audit buffer * @a: audit_data */ static void avc_audit_post_callback(struct audit_buffer *ab, void *a) { struct common_audit_data *ad = a; struct selinux_audit_data *sad = ad->selinux_audit_data; char *scontext = NULL; char *tcontext = NULL; const char *tclass = NULL; u32 scontext_len; u32 tcontext_len; int rc; rc = security_sid_to_context(sad->state, sad->ssid, &scontext, &scontext_len); if (rc) audit_log_format(ab, " ssid=%d", sad->ssid); else audit_log_format(ab, " scontext=%s", scontext); rc = security_sid_to_context(sad->state, sad->tsid, &tcontext, &tcontext_len); if (rc) audit_log_format(ab, " tsid=%d", sad->tsid); else audit_log_format(ab, " tcontext=%s", tcontext); tclass = secclass_map[sad->tclass-1].name; audit_log_format(ab, " tclass=%s", tclass); if (sad->denied) audit_log_format(ab, " permissive=%u", sad->result ? 0 : 1); trace_selinux_audited(sad, scontext, tcontext, tclass); kfree(tcontext); kfree(scontext); /* in case of invalid context report also the actual context string */ rc = security_sid_to_context_inval(sad->state, sad->ssid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " srawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } rc = security_sid_to_context_inval(sad->state, sad->tsid, &scontext, &scontext_len); if (!rc && scontext) { if (scontext_len && scontext[scontext_len - 1] == '\0') scontext_len--; audit_log_format(ab, " trawcon="); audit_log_n_untrustedstring(ab, scontext, scontext_len); kfree(scontext); } } /* This is the slow part of avc audit with big stack footprint */ noinline int slow_avc_audit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u32 audited, u32 denied, int result, struct common_audit_data *a) { struct common_audit_data stack_data; struct selinux_audit_data sad; if (WARN_ON(!tclass || tclass >= ARRAY_SIZE(secclass_map))) return -EINVAL; if (!a) { a = &stack_data; a->type = LSM_AUDIT_DATA_NONE; } sad.tclass = tclass; sad.requested = requested; sad.ssid = ssid; sad.tsid = tsid; sad.audited = audited; sad.denied = denied; sad.result = result; sad.state = state; a->selinux_audit_data = &sad; common_lsm_audit(a, avc_audit_pre_callback, avc_audit_post_callback); return 0; } /** * avc_add_callback - Register a callback for security events. * @callback: callback function * @events: security events * * Register a callback function for events in the set @events. * Returns %0 on success or -%ENOMEM if insufficient memory * exists to add the callback. */ int __init avc_add_callback(int (*callback)(u32 event), u32 events) { struct avc_callback_node *c; int rc = 0; c = kmalloc(sizeof(*c), GFP_KERNEL); if (!c) { rc = -ENOMEM; goto out; } c->callback = callback; c->events = events; c->next = avc_callbacks; avc_callbacks = c; out: return rc; } /** * avc_update_node Update an AVC entry * @event : Updating event * @perms : Permission mask bits * @ssid,@tsid,@tclass : identifier of an AVC entry * @seqno : sequence number when decision was made * @xpd: extended_perms_decision to be added to the node * @flags: the AVC_* flags, e.g. AVC_NONBLOCKING, AVC_EXTENDED_PERMS, or 0. * * if a valid AVC entry doesn't exist,this function returns -ENOENT. * if kmalloc() called internal returns NULL, this function returns -ENOMEM. * otherwise, this function updates the AVC entry. The original AVC-entry object * will release later by RCU. */ static int avc_update_node(struct selinux_avc *avc, u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid, u32 tsid, u16 tclass, u32 seqno, struct extended_perms_decision *xpd, u32 flags) { int hvalue, rc = 0; unsigned long flag; struct avc_node *pos, *node, *orig = NULL; struct hlist_head *head; spinlock_t *lock; /* * If we are in a non-blocking code path, e.g. VFS RCU walk, * then we must not add permissions to a cache entry * because we will not audit the denial. Otherwise, * during the subsequent blocking retry (e.g. VFS ref walk), we * will find the permissions already granted in the cache entry * and won't audit anything at all, leading to silent denials in * permissive mode that only appear when in enforcing mode. * * See the corresponding handling of MAY_NOT_BLOCK in avc_audit() * and selinux_inode_permission(). */ if (flags & AVC_NONBLOCKING) return 0; node = avc_alloc_node(avc); if (!node) { rc = -ENOMEM; goto out; } /* Lock the target slot */ hvalue = avc_hash(ssid, tsid, tclass); head = &avc->avc_cache.slots[hvalue]; lock = &avc->avc_cache.slots_lock[hvalue]; spin_lock_irqsave(lock, flag); hlist_for_each_entry(pos, head, list) { if (ssid == pos->ae.ssid && tsid == pos->ae.tsid && tclass == pos->ae.tclass && seqno == pos->ae.avd.seqno){ orig = pos; break; } } if (!orig) { rc = -ENOENT; avc_node_kill(avc, node); goto out_unlock; } /* * Copy and replace original node. */ avc_node_populate(node, ssid, tsid, tclass, &orig->ae.avd); if (orig->ae.xp_node) { rc = avc_xperms_populate(node, orig->ae.xp_node); if (rc) { avc_node_kill(avc, node); goto out_unlock; } } switch (event) { case AVC_CALLBACK_GRANT: node->ae.avd.allowed |= perms; if (node->ae.xp_node && (flags & AVC_EXTENDED_PERMS)) avc_xperms_allow_perm(node->ae.xp_node, driver, xperm); break; case AVC_CALLBACK_TRY_REVOKE: case AVC_CALLBACK_REVOKE: node->ae.avd.allowed &= ~perms; break; case AVC_CALLBACK_AUDITALLOW_ENABLE: node->ae.avd.auditallow |= perms; break; case AVC_CALLBACK_AUDITALLOW_DISABLE: node->ae.avd.auditallow &= ~perms; break; case AVC_CALLBACK_AUDITDENY_ENABLE: node->ae.avd.auditdeny |= perms; break; case AVC_CALLBACK_AUDITDENY_DISABLE: node->ae.avd.auditdeny &= ~perms; break; case AVC_CALLBACK_ADD_XPERMS: avc_add_xperms_decision(node, xpd); break; } avc_node_replace(avc, node, orig); out_unlock: spin_unlock_irqrestore(lock, flag); out: return rc; } /** * avc_flush - Flush the cache */ static void avc_flush(struct selinux_avc *avc) { struct hlist_head *head; struct avc_node *node; spinlock_t *lock; unsigned long flag; int i; for (i = 0; i < AVC_CACHE_SLOTS; i++) { head = &avc->avc_cache.slots[i]; lock = &avc->avc_cache.slots_lock[i]; spin_lock_irqsave(lock, flag); /* * With preemptable RCU, the outer spinlock does not * prevent RCU grace periods from ending. */ rcu_read_lock(); hlist_for_each_entry(node, head, list) avc_node_delete(avc, node); rcu_read_unlock(); spin_unlock_irqrestore(lock, flag); } } /** * avc_ss_reset - Flush the cache and revalidate migrated permissions. * @seqno: policy sequence number */ int avc_ss_reset(struct selinux_avc *avc, u32 seqno) { struct avc_callback_node *c; int rc = 0, tmprc; avc_flush(avc); for (c = avc_callbacks; c; c = c->next) { if (c->events & AVC_CALLBACK_RESET) { tmprc = c->callback(AVC_CALLBACK_RESET); /* save the first error encountered for the return value and continue processing the callbacks */ if (!rc) rc = tmprc; } } avc_latest_notif_update(avc, seqno, 0); return rc; } /* * Slow-path helper function for avc_has_perm_noaudit, * when the avc_node lookup fails. We get called with * the RCU read lock held, and need to return with it * still held, but drop if for the security compute. * * Don't inline this, since it's the slow-path and just * results in a bigger stack frame. */ static noinline struct avc_node *avc_compute_av(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, struct av_decision *avd, struct avc_xperms_node *xp_node) { rcu_read_unlock(); INIT_LIST_HEAD(&xp_node->xpd_head); security_compute_av(state, ssid, tsid, tclass, avd, &xp_node->xp); rcu_read_lock(); return avc_insert(state->avc, ssid, tsid, tclass, avd, xp_node); } static noinline int avc_denied(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 xperm, unsigned int flags, struct av_decision *avd) { if (flags & AVC_STRICT) return -EACCES; if (enforcing_enabled(state) && !(avd->flags & AVD_FLAGS_PERMISSIVE)) return -EACCES; avc_update_node(state->avc, AVC_CALLBACK_GRANT, requested, driver, xperm, ssid, tsid, tclass, avd->seqno, NULL, flags); return 0; } /* * The avc extended permissions logic adds an additional 256 bits of * permissions to an avc node when extended permissions for that node are * specified in the avtab. If the additional 256 permissions is not adequate, * as-is the case with ioctls, then multiple may be chained together and the * driver field is used to specify which set contains the permission. */ int avc_has_extended_perms(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, u8 driver, u8 xperm, struct common_audit_data *ad) { struct avc_node *node; struct av_decision avd; u32 denied; struct extended_perms_decision local_xpd; struct extended_perms_decision *xpd = NULL; struct extended_perms_data allowed; struct extended_perms_data auditallow; struct extended_perms_data dontaudit; struct avc_xperms_node local_xp_node; struct avc_xperms_node *xp_node; int rc = 0, rc2; xp_node = &local_xp_node; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) { node = avc_compute_av(state, ssid, tsid, tclass, &avd, xp_node); } else { memcpy(&avd, &node->ae.avd, sizeof(avd)); xp_node = node->ae.xp_node; } /* if extended permissions are not defined, only consider av_decision */ if (!xp_node || !xp_node->xp.len) goto decision; local_xpd.allowed = &allowed; local_xpd.auditallow = &auditallow; local_xpd.dontaudit = &dontaudit; xpd = avc_xperms_decision_lookup(driver, xp_node); if (unlikely(!xpd)) { /* * Compute the extended_perms_decision only if the driver * is flagged */ if (!security_xperm_test(xp_node->xp.drivers.p, driver)) { avd.allowed &= ~requested; goto decision; } rcu_read_unlock(); security_compute_xperms_decision(state, ssid, tsid, tclass, driver, &local_xpd); rcu_read_lock(); avc_update_node(state->avc, AVC_CALLBACK_ADD_XPERMS, requested, driver, xperm, ssid, tsid, tclass, avd.seqno, &local_xpd, 0); } else { avc_quick_copy_xperms_decision(xperm, &local_xpd, xpd); } xpd = &local_xpd; if (!avc_xperms_has_perm(xpd, xperm, XPERMS_ALLOWED)) avd.allowed &= ~requested; decision: denied = requested & ~(avd.allowed); if (unlikely(denied)) rc = avc_denied(state, ssid, tsid, tclass, requested, driver, xperm, AVC_EXTENDED_PERMS, &avd); rcu_read_unlock(); rc2 = avc_xperms_audit(state, ssid, tsid, tclass, requested, &avd, xpd, xperm, rc, ad); if (rc2) return rc2; return rc; } /** * avc_has_perm_noaudit - Check permissions but perform no auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @flags: AVC_STRICT, AVC_NONBLOCKING, or 0 * @avd: access vector decisions * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Return a copy of the decisions * in @avd. Return %0 if all @requested permissions are granted, * -%EACCES if any permissions are denied, or another -errno upon * other errors. This function is typically called by avc_has_perm(), * but may also be called directly to separate permission checking from * auditing, e.g. in cases where a lock must be held for the check but * should be released for the auditing. */ inline int avc_has_perm_noaudit(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, unsigned int flags, struct av_decision *avd) { struct avc_node *node; struct avc_xperms_node xp_node; int rc = 0; u32 denied; if (WARN_ON(!requested)) return -EACCES; rcu_read_lock(); node = avc_lookup(state->avc, ssid, tsid, tclass); if (unlikely(!node)) node = avc_compute_av(state, ssid, tsid, tclass, avd, &xp_node); else memcpy(avd, &node->ae.avd, sizeof(*avd)); denied = requested & ~(avd->allowed); if (unlikely(denied)) rc = avc_denied(state, ssid, tsid, tclass, requested, 0, 0, flags, avd); rcu_read_unlock(); return rc; } /** * avc_has_perm - Check permissions and perform any appropriate auditing. * @ssid: source security identifier * @tsid: target security identifier * @tclass: target security class * @requested: requested permissions, interpreted based on @tclass * @auditdata: auxiliary audit data * * Check the AVC to determine whether the @requested permissions are granted * for the SID pair (@ssid, @tsid), interpreting the permissions * based on @tclass, and call the security server on a cache miss to obtain * a new decision and add it to the cache. Audit the granting or denial of * permissions in accordance with the policy. Return %0 if all @requested * permissions are granted, -%EACCES if any permissions are denied, or * another -errno upon other errors. */ int avc_has_perm(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, 0, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, auditdata, 0); if (rc2) return rc2; return rc; } int avc_has_perm_flags(struct selinux_state *state, u32 ssid, u32 tsid, u16 tclass, u32 requested, struct common_audit_data *auditdata, int flags) { struct av_decision avd; int rc, rc2; rc = avc_has_perm_noaudit(state, ssid, tsid, tclass, requested, (flags & MAY_NOT_BLOCK) ? AVC_NONBLOCKING : 0, &avd); rc2 = avc_audit(state, ssid, tsid, tclass, requested, &avd, rc, auditdata, flags); if (rc2) return rc2; return rc; } u32 avc_policy_seqno(struct selinux_state *state) { return state->avc->avc_cache.latest_notif; } void avc_disable(void) { /* * If you are looking at this because you have realized that we are * not destroying the avc_node_cachep it might be easy to fix, but * I don't know the memory barrier semantics well enough to know. It's * possible that some other task dereferenced security_ops when * it still pointed to selinux operations. If that is the case it's * possible that it is about to use the avc and is about to need the * avc_node_cachep. I know I could wrap the security.c security_ops call * in an rcu_lock, but seriously, it's not worth it. Instead I just flush * the cache and get that memory back. */ if (avc_node_cachep) { avc_flush(selinux_state.avc); /* kmem_cache_destroy(avc_node_cachep); */ } } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (C) 2010: YOSHIFUJI Hideaki <yoshfuji@linux-ipv6.org> * Copyright (C) 2015: Linus Lüssing <linus.luessing@c0d3.blue> * * Based on the MLD support added to br_multicast.c by YOSHIFUJI Hideaki. */ #include <linux/skbuff.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/addrconf.h> #include <net/ip6_checksum.h> static int ipv6_mc_check_ip6hdr(struct sk_buff *skb) { const struct ipv6hdr *ip6h; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*ip6h); if (!pskb_may_pull(skb, offset)) return -EINVAL; ip6h = ipv6_hdr(skb); if (ip6h->version != 6) return -EINVAL; len = offset + ntohs(ip6h->payload_len); if (skb->len < len || len <= offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ipv6_mc_check_exthdrs(struct sk_buff *skb) { const struct ipv6hdr *ip6h; int offset; u8 nexthdr; __be16 frag_off; ip6h = ipv6_hdr(skb); if (ip6h->nexthdr != IPPROTO_HOPOPTS) return -ENOMSG; nexthdr = ip6h->nexthdr; offset = skb_network_offset(skb) + sizeof(*ip6h); offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) return -EINVAL; if (nexthdr != IPPROTO_ICMPV6) return -ENOMSG; skb_set_transport_header(skb, offset); return 0; } static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct mld2_report); return ipv6_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ipv6_mc_check_mld_query(struct sk_buff *skb) { unsigned int transport_len = ipv6_transport_len(skb); struct mld_msg *mld; unsigned int len; /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) return -EINVAL; /* MLDv1? */ if (transport_len != sizeof(struct mld_msg)) { /* or MLDv2? */ if (transport_len < sizeof(struct mld2_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct mld2_query); if (!ipv6_mc_may_pull(skb, len)) return -EINVAL; } mld = (struct mld_msg *)skb_transport_header(skb); /* RFC2710+RFC3810 (MLDv1+MLDv2) require the multicast link layer * all-nodes destination address (ff02::1) for general queries */ if (ipv6_addr_any(&mld->mld_mca) && !ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) return -EINVAL; return 0; } static int ipv6_mc_check_mld_msg(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg); struct mld_msg *mld; if (!ipv6_mc_may_pull(skb, len)) return -ENODATA; mld = (struct mld_msg *)skb_transport_header(skb); switch (mld->mld_type) { case ICMPV6_MGM_REDUCTION: case ICMPV6_MGM_REPORT: return 0; case ICMPV6_MLD2_REPORT: return ipv6_mc_check_mld_reportv2(skb); case ICMPV6_MGM_QUERY: return ipv6_mc_check_mld_query(skb); default: return -ENODATA; } } static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo); } static int ipv6_mc_check_icmpv6(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct icmp6hdr); unsigned int transport_len = ipv6_transport_len(skb); struct sk_buff *skb_chk; if (!ipv6_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ipv6_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ipv6_mc_check_mld - checks whether this is a sane MLD packet * @skb: the skb to validate * * Checks whether an IPv6 packet is a valid MLD packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an ICMPv6 packet * with a hop-by-hop option. * -ENODATA: IP+ICMPv6 header with hop-by-hop option validation succeeded * but it is not an MLD packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ipv6_mc_check_mld(struct sk_buff *skb) { int ret; ret = ipv6_mc_check_ip6hdr(skb); if (ret < 0) return ret; ret = ipv6_mc_check_exthdrs(skb); if (ret < 0) return ret; ret = ipv6_mc_check_icmpv6(skb); if (ret < 0) return ret; return ipv6_mc_check_mld_msg(skb); } EXPORT_SYMBOL(ipv6_mc_check_mld); |
| 5 1 79 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SCHED_MM_H #define _LINUX_SCHED_MM_H #include <linux/kernel.h> #include <linux/atomic.h> #include <linux/sched.h> #include <linux/mm_types.h> #include <linux/gfp.h> #include <linux/sync_core.h> /* * Routines for handling mm_structs */ extern struct mm_struct *mm_alloc(void); /** * mmgrab() - Pin a &struct mm_struct. * @mm: The &struct mm_struct to pin. * * Make sure that @mm will not get freed even after the owning task * exits. This doesn't guarantee that the associated address space * will still exist later on and mmget_not_zero() has to be used before * accessing it. * * This is a preferred way to to pin @mm for a longer/unbounded amount * of time. * * Use mmdrop() to release the reference acquired by mmgrab(). * * See also <Documentation/vm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmgrab(struct mm_struct *mm) { atomic_inc(&mm->mm_count); } extern void __mmdrop(struct mm_struct *mm); static inline void mmdrop(struct mm_struct *mm) { /* * The implicit full barrier implied by atomic_dec_and_test() is * required by the membarrier system call before returning to * user-space, after storing to rq->curr. */ if (unlikely(atomic_dec_and_test(&mm->mm_count))) __mmdrop(mm); } void mmdrop(struct mm_struct *mm); /* * This has to be called after a get_task_mm()/mmget_not_zero() * followed by taking the mmap_sem for writing before modifying the * vmas or anything the coredump pretends not to change from under it. * * It also has to be called when mmgrab() is used in the context of * the process, but then the mm_count refcount is transferred outside * the context of the process to run down_write() on that pinned mm. * * NOTE: find_extend_vma() called from GUP context is the only place * that can modify the "mm" (notably the vm_start/end) under mmap_sem * for reading and outside the context of the process, so it is also * the only case that holds the mmap_sem for reading that must call * this function. Generally if the mmap_sem is hold for reading * there's no need of this check after get_task_mm()/mmget_not_zero(). * * This function can be obsoleted and the check can be removed, after * the coredump code will hold the mmap_sem for writing before * invoking the ->core_dump methods. */ static inline bool mmget_still_valid(struct mm_struct *mm) { return likely(!mm->core_state); } /** * mmget() - Pin the address space associated with a &struct mm_struct. * @mm: The address space to pin. * * Make sure that the address space of the given &struct mm_struct doesn't * go away. This does not protect against parts of the address space being * modified or freed, however. * * Never use this function to pin this address space for an * unbounded/indefinite amount of time. * * Use mmput() to release the reference acquired by mmget(). * * See also <Documentation/vm/active_mm.rst> for an in-depth explanation * of &mm_struct.mm_count vs &mm_struct.mm_users. */ static inline void mmget(struct mm_struct *mm) { atomic_inc(&mm->mm_users); } static inline bool mmget_not_zero(struct mm_struct *mm) { return atomic_inc_not_zero(&mm->mm_users); } /* mmput gets rid of the mappings and all user-space */ extern void mmput(struct mm_struct *); #ifdef CONFIG_MMU /* same as above but performs the slow path from the async context. Can * be called from the atomic context as well */ void mmput_async(struct mm_struct *); #endif /* Grab a reference to a task's mm, if it is not already going away */ extern struct mm_struct *get_task_mm(struct task_struct *task); /* * Grab a reference to a task's mm, if it is not already going away * and ptrace_may_access with the mode parameter passed to it * succeeds. */ extern struct mm_struct *mm_access(struct task_struct *task, unsigned int mode); /* Remove the current tasks stale references to the old mm_struct on exit() */ extern void exit_mm_release(struct task_struct *, struct mm_struct *); /* Remove the current tasks stale references to the old mm_struct on exec() */ extern void exec_mm_release(struct task_struct *, struct mm_struct *); #ifdef CONFIG_MEMCG extern void mm_update_next_owner(struct mm_struct *mm); #else static inline void mm_update_next_owner(struct mm_struct *mm) { } #endif /* CONFIG_MEMCG */ #ifdef CONFIG_MMU #ifndef arch_get_mmap_end #define arch_get_mmap_end(addr) (TASK_SIZE) #endif #ifndef arch_get_mmap_base #define arch_get_mmap_base(addr, base) (base) #endif extern void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack); extern unsigned long arch_get_unmapped_area(struct file *, unsigned long, unsigned long, unsigned long, unsigned long); extern unsigned long arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); #else static inline void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) {} #endif static inline bool in_vfork(struct task_struct *tsk) { bool ret; /* * need RCU to access ->real_parent if CLONE_VM was used along with * CLONE_PARENT. * * We check real_parent->mm == tsk->mm because CLONE_VFORK does not * imply CLONE_VM * * CLONE_VFORK can be used with CLONE_PARENT/CLONE_THREAD and thus * ->real_parent is not necessarily the task doing vfork(), so in * theory we can't rely on task_lock() if we want to dereference it. * * And in this case we can't trust the real_parent->mm == tsk->mm * check, it can be false negative. But we do not care, if init or * another oom-unkillable task does this it should blame itself. */ rcu_read_lock(); ret = tsk->vfork_done && rcu_dereference(tsk->real_parent)->mm == tsk->mm; rcu_read_unlock(); return ret; } /* * Applies per-task gfp context to the given allocation flags. * PF_MEMALLOC_NOIO implies GFP_NOIO * PF_MEMALLOC_NOFS implies GFP_NOFS * PF_MEMALLOC_NOCMA implies no allocation from CMA region. */ static inline gfp_t current_gfp_context(gfp_t flags) { if (unlikely(current->flags & (PF_MEMALLOC_NOIO | PF_MEMALLOC_NOFS | PF_MEMALLOC_NOCMA))) { /* * NOIO implies both NOIO and NOFS and it is a weaker context * so always make sure it makes precedence */ if (current->flags & PF_MEMALLOC_NOIO) flags &= ~(__GFP_IO | __GFP_FS); else if (current->flags & PF_MEMALLOC_NOFS) flags &= ~__GFP_FS; #ifdef CONFIG_CMA if (current->flags & PF_MEMALLOC_NOCMA) flags &= ~__GFP_MOVABLE; #endif } return flags; } #ifdef CONFIG_LOCKDEP extern void __fs_reclaim_acquire(void); extern void __fs_reclaim_release(void); extern void fs_reclaim_acquire(gfp_t gfp_mask); extern void fs_reclaim_release(gfp_t gfp_mask); #else static inline void __fs_reclaim_acquire(void) { } static inline void __fs_reclaim_release(void) { } static inline void fs_reclaim_acquire(gfp_t gfp_mask) { } static inline void fs_reclaim_release(gfp_t gfp_mask) { } #endif /** * memalloc_noio_save - Marks implicit GFP_NOIO allocation scope. * * This functions marks the beginning of the GFP_NOIO allocation scope. * All further allocations will implicitly drop __GFP_IO flag and so * they are safe for the IO critical section from the allocation recursion * point of view. Use memalloc_noio_restore to end the scope with flags * returned by this function. * * This function is safe to be used from any context. */ static inline unsigned int memalloc_noio_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOIO; current->flags |= PF_MEMALLOC_NOIO; return flags; } /** * memalloc_noio_restore - Ends the implicit GFP_NOIO scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOIO scope started by memalloc_noio_save function. * Always make sure that that the given flags is the return value from the * pairing memalloc_noio_save call. */ static inline void memalloc_noio_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOIO) | flags; } /** * memalloc_nofs_save - Marks implicit GFP_NOFS allocation scope. * * This functions marks the beginning of the GFP_NOFS allocation scope. * All further allocations will implicitly drop __GFP_FS flag and so * they are safe for the FS critical section from the allocation recursion * point of view. Use memalloc_nofs_restore to end the scope with flags * returned by this function. * * This function is safe to be used from any context. */ static inline unsigned int memalloc_nofs_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOFS; current->flags |= PF_MEMALLOC_NOFS; return flags; } /** * memalloc_nofs_restore - Ends the implicit GFP_NOFS scope. * @flags: Flags to restore. * * Ends the implicit GFP_NOFS scope started by memalloc_nofs_save function. * Always make sure that that the given flags is the return value from the * pairing memalloc_nofs_save call. */ static inline void memalloc_nofs_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOFS) | flags; } static inline unsigned int memalloc_noreclaim_save(void) { unsigned int flags = current->flags & PF_MEMALLOC; current->flags |= PF_MEMALLOC; return flags; } static inline void memalloc_noreclaim_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC) | flags; } #ifdef CONFIG_CMA static inline unsigned int memalloc_nocma_save(void) { unsigned int flags = current->flags & PF_MEMALLOC_NOCMA; current->flags |= PF_MEMALLOC_NOCMA; return flags; } static inline void memalloc_nocma_restore(unsigned int flags) { current->flags = (current->flags & ~PF_MEMALLOC_NOCMA) | flags; } #else static inline unsigned int memalloc_nocma_save(void) { return 0; } static inline void memalloc_nocma_restore(unsigned int flags) { } #endif #ifdef CONFIG_MEMCG /** * memalloc_use_memcg - Starts the remote memcg charging scope. * @memcg: memcg to charge. * * This function marks the beginning of the remote memcg charging scope. All the * __GFP_ACCOUNT allocations till the end of the scope will be charged to the * given memcg. * * NOTE: This function is not nesting safe. */ static inline void memalloc_use_memcg(struct mem_cgroup *memcg) { WARN_ON_ONCE(current->active_memcg); current->active_memcg = memcg; } /** * memalloc_unuse_memcg - Ends the remote memcg charging scope. * * This function marks the end of the remote memcg charging scope started by * memalloc_use_memcg(). */ static inline void memalloc_unuse_memcg(void) { current->active_memcg = NULL; } #else static inline void memalloc_use_memcg(struct mem_cgroup *memcg) { } static inline void memalloc_unuse_memcg(void) { } #endif #ifdef CONFIG_MEMBARRIER enum { MEMBARRIER_STATE_PRIVATE_EXPEDITED_READY = (1U << 0), MEMBARRIER_STATE_PRIVATE_EXPEDITED = (1U << 1), MEMBARRIER_STATE_GLOBAL_EXPEDITED_READY = (1U << 2), MEMBARRIER_STATE_GLOBAL_EXPEDITED = (1U << 3), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE_READY = (1U << 4), MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE = (1U << 5), }; enum { MEMBARRIER_FLAG_SYNC_CORE = (1U << 0), }; #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS #include <asm/membarrier.h> #endif static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { if (current->mm != mm) return; if (likely(!(atomic_read(&mm->membarrier_state) & MEMBARRIER_STATE_PRIVATE_EXPEDITED_SYNC_CORE))) return; sync_core_before_usermode(); } extern void membarrier_exec_mmap(struct mm_struct *mm); #else #ifdef CONFIG_ARCH_HAS_MEMBARRIER_CALLBACKS static inline void membarrier_arch_switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk) { } #endif static inline void membarrier_exec_mmap(struct mm_struct *mm) { } static inline void membarrier_mm_sync_core_before_usermode(struct mm_struct *mm) { } #endif #endif /* _LINUX_SCHED_MM_H */ |
| 8 9 9 129 119 9 6 2 4 6 79 79 1 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * RAW sockets for IPv6 * Linux INET6 implementation * * Authors: * Pedro Roque <roque@di.fc.ul.pt> * * Adapted from linux/net/ipv4/raw.c * * Fixes: * Hideaki YOSHIFUJI : sin6_scope_id support * YOSHIFUJI,H.@USAGI : raw checksum (RFC2292(bis) compliance) * Kazunori MIYAZAWA @USAGI: change process style to use ip6_append_data */ #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/slab.h> #include <linux/sockios.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv6.h> #include <linux/skbuff.h> #include <linux/compat.h> #include <linux/uaccess.h> #include <asm/ioctls.h> #include <net/net_namespace.h> #include <net/ip.h> #include <net/sock.h> #include <net/snmp.h> #include <net/ipv6.h> #include <net/ndisc.h> #include <net/protocol.h> #include <net/ip6_route.h> #include <net/ip6_checksum.h> #include <net/addrconf.h> #include <net/transp_v6.h> #include <net/udp.h> #include <net/inet_common.h> #include <net/tcp_states.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #include <linux/mroute6.h> #include <net/raw.h> #include <net/rawv6.h> #include <net/xfrm.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/export.h> #define ICMPV6_HDRLEN 4 /* ICMPv6 header, RFC 4443 Section 2.1 */ struct raw_hashinfo raw_v6_hashinfo = { .lock = __RW_LOCK_UNLOCKED(raw_v6_hashinfo.lock), }; EXPORT_SYMBOL_GPL(raw_v6_hashinfo); struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, unsigned short num, const struct in6_addr *loc_addr, const struct in6_addr *rmt_addr, int dif, int sdif) { bool is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk) if (inet_sk(sk)->inet_num == num) { if (!net_eq(sock_net(sk), net)) continue; if (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) continue; if (!raw_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) continue; if (!ipv6_addr_any(&sk->sk_v6_rcv_saddr)) { if (ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr)) goto found; if (is_multicast && inet6_mc_check(sk, loc_addr, rmt_addr)) goto found; continue; } goto found; } sk = NULL; found: return sk; } EXPORT_SYMBOL_GPL(__raw_v6_lookup); /* * 0 - deliver * 1 - block */ static int icmpv6_filter(const struct sock *sk, const struct sk_buff *skb) { struct icmp6hdr _hdr; const struct icmp6hdr *hdr; /* We require only the four bytes of the ICMPv6 header, not any * additional bytes of message body in "struct icmp6hdr". */ hdr = skb_header_pointer(skb, skb_transport_offset(skb), ICMPV6_HDRLEN, &_hdr); if (hdr) { const __u32 *data = &raw6_sk(sk)->filter.data[0]; unsigned int type = hdr->icmp6_type; return (data[type >> 5] & (1U << (type & 31))) != 0; } return 1; } #if IS_ENABLED(CONFIG_IPV6_MIP6) typedef int mh_filter_t(struct sock *sock, struct sk_buff *skb); static mh_filter_t __rcu *mh_filter __read_mostly; int rawv6_mh_filter_register(mh_filter_t filter) { rcu_assign_pointer(mh_filter, filter); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_register); int rawv6_mh_filter_unregister(mh_filter_t filter) { RCU_INIT_POINTER(mh_filter, NULL); synchronize_rcu(); return 0; } EXPORT_SYMBOL(rawv6_mh_filter_unregister); #endif /* * demultiplex raw sockets. * (should consider queueing the skb in the sock receive_queue * without calling rawv6.c) * * Caller owns SKB so we must make clones. */ static bool ipv6_raw_deliver(struct sk_buff *skb, int nexthdr) { const struct in6_addr *saddr; const struct in6_addr *daddr; struct sock *sk; bool delivered = false; __u8 hash; struct net *net; saddr = &ipv6_hdr(skb)->saddr; daddr = saddr + 1; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (!sk) goto out; net = dev_net(skb->dev); sk = __raw_v6_lookup(net, sk, nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); while (sk) { int filtered; delivered = true; switch (nexthdr) { case IPPROTO_ICMPV6: filtered = icmpv6_filter(sk, skb); break; #if IS_ENABLED(CONFIG_IPV6_MIP6) case IPPROTO_MH: { /* XXX: To validate MH only once for each packet, * this is placed here. It should be after checking * xfrm policy, however it doesn't. The checking xfrm * policy is placed in rawv6_rcv() because it is * required for each socket. */ mh_filter_t *filter; filter = rcu_dereference(mh_filter); filtered = filter ? (*filter)(sk, skb) : 0; break; } #endif default: filtered = 0; break; } if (filtered < 0) break; if (filtered == 0) { struct sk_buff *clone = skb_clone(skb, GFP_ATOMIC); /* Not releasing hash table! */ if (clone) { nf_reset_ct(clone); rawv6_rcv(sk, clone); } } sk = __raw_v6_lookup(net, sk_next(sk), nexthdr, daddr, saddr, inet6_iif(skb), inet6_sdif(skb)); } out: read_unlock(&raw_v6_hashinfo.lock); return delivered; } bool raw6_local_deliver(struct sk_buff *skb, int nexthdr) { struct sock *raw_sk; raw_sk = sk_head(&raw_v6_hashinfo.ht[nexthdr & (RAW_HTABLE_SIZE - 1)]); if (raw_sk && !ipv6_raw_deliver(skb, nexthdr)) raw_sk = NULL; return raw_sk != NULL; } /* This cleans up af_inet6 a bit. -DaveM */ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct sockaddr_in6 *addr = (struct sockaddr_in6 *) uaddr; __be32 v4addr = 0; int addr_type; int err; if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (addr->sin6_family != AF_INET6) return -EINVAL; addr_type = ipv6_addr_type(&addr->sin6_addr); /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) return -EADDRNOTAVAIL; lock_sock(sk); err = -EINVAL; if (sk->sk_state != TCP_CLOSE) goto out; rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; if (__ipv6_addr_needs_scope_id(addr_type)) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { /* Override any existing binding, if another * one is supplied by user. */ sk->sk_bound_dev_if = addr->sin6_scope_id; } /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) goto out_unlock; } if (sk->sk_bound_dev_if) { err = -ENODEV; dev = dev_get_by_index_rcu(sock_net(sk), sk->sk_bound_dev_if); if (!dev) goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the * unspecified and mapped address have a v4 equivalent. */ v4addr = LOOPBACK4_IPV6; if (!(addr_type & IPV6_ADDR_MULTICAST) && !ipv6_can_nonlocal_bind(sock_net(sk), inet)) { err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { goto out_unlock; } } } inet->inet_rcv_saddr = inet->inet_saddr = v4addr; sk->sk_v6_rcv_saddr = addr->sin6_addr; if (!(addr_type & IPV6_ADDR_MULTICAST)) np->saddr = addr->sin6_addr; err = 0; out_unlock: rcu_read_unlock(); out: release_sock(sk); return err; } static void rawv6_err(struct sock *sk, struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); int err; int harderr; /* Report error on raw socket, if: 1. User requested recverr. 2. Socket is connected (otherwise the error indication is useless without recverr and error is hard. */ if (!np->recverr && sk->sk_state != TCP_ESTABLISHED) return; harderr = icmpv6_err_convert(type, code, &err); if (type == ICMPV6_PKT_TOOBIG) { ip6_sk_update_pmtu(skb, sk, info); harderr = (np->pmtudisc == IPV6_PMTUDISC_DO); } if (type == NDISC_REDIRECT) { ip6_sk_redirect(skb, sk); return; } if (np->recverr) { u8 *payload = skb->data; if (!inet->hdrincl) payload += offset; ipv6_icmp_error(sk, skb, err, 0, ntohl(info), payload); } if (np->recverr || harderr) { sk->sk_err = err; sk->sk_error_report(sk); } } void raw6_icmp_error(struct sk_buff *skb, int nexthdr, u8 type, u8 code, int inner_offset, __be32 info) { struct sock *sk; int hash; const struct in6_addr *saddr, *daddr; struct net *net; hash = nexthdr & (RAW_HTABLE_SIZE - 1); read_lock(&raw_v6_hashinfo.lock); sk = sk_head(&raw_v6_hashinfo.ht[hash]); if (sk) { /* Note: ipv6_hdr(skb) != skb->data */ const struct ipv6hdr *ip6h = (const struct ipv6hdr *)skb->data; saddr = &ip6h->saddr; daddr = &ip6h->daddr; net = dev_net(skb->dev); while ((sk = __raw_v6_lookup(net, sk, nexthdr, saddr, daddr, inet6_iif(skb), inet6_iif(skb)))) { rawv6_err(sk, skb, NULL, type, code, inner_offset, info); sk = sk_next(sk); } } read_unlock(&raw_v6_hashinfo.lock); } static inline int rawv6_rcv_skb(struct sock *sk, struct sk_buff *skb) { if ((raw6_sk(sk)->checksum || rcu_access_pointer(sk->sk_filter)) && skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } /* Charge it to the socket. */ skb_dst_drop(skb); if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } return 0; } /* * This is next to useless... * if we demultiplex in network layer we don't need the extra call * just to queue the skb... * maybe we could have the network decide upon a hint if it * should call raw_rcv for demultiplexing */ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) { struct inet_sock *inet = inet_sk(sk); struct raw6_sock *rp = raw6_sk(sk); if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } if (!rp->checksum) skb->ip_summed = CHECKSUM_UNNECESSARY; if (skb->ip_summed == CHECKSUM_COMPLETE) { skb_postpull_rcsum(skb, skb_network_header(skb), skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { atomic_inc(&sk->sk_drops); kfree_skb(skb); return NET_RX_DROP; } } rawv6_rcv_skb(sk, skb); return 0; } /* * This should be easy, if there is something there * we return it, otherwise we block. */ static int rawv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct ipv6_pinfo *np = inet6_sk(sk); DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct sk_buff *skb; size_t copied; int err; if (flags & MSG_OOB) return -EOPNOTSUPP; if (flags & MSG_ERRQUEUE) return ipv6_recv_error(sk, msg, len, addr_len); if (np->rxpmtu && np->rxopt.bits.rxpmtu) return ipv6_recv_rxpmtu(sk, msg, len, addr_len); skb = skb_recv_datagram(sk, flags, noblock, &err); if (!skb) goto out; copied = skb->len; if (copied > len) { copied = len; msg->msg_flags |= MSG_TRUNC; } if (skb_csum_unnecessary(skb)) { err = skb_copy_datagram_msg(skb, 0, msg, copied); } else if (msg->msg_flags&MSG_TRUNC) { if (__skb_checksum_complete(skb)) goto csum_copy_err; err = skb_copy_datagram_msg(skb, 0, msg, copied); } else { err = skb_copy_and_csum_datagram_msg(skb, 0, msg); if (err == -EINVAL) goto csum_copy_err; } if (err) goto out_free; /* Copy the address. */ if (sin6) { sin6->sin6_family = AF_INET6; sin6->sin6_port = 0; sin6->sin6_addr = ipv6_hdr(skb)->saddr; sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = ipv6_iface_scope_id(&sin6->sin6_addr, inet6_iif(skb)); *addr_len = sizeof(*sin6); } sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) ip6_datagram_recv_ctl(sk, msg, skb); err = copied; if (flags & MSG_TRUNC) err = skb->len; out_free: skb_free_datagram(sk, skb); out: return err; csum_copy_err: skb_kill_datagram(sk, skb, flags); /* Error for blocking case is chosen to masquerade as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; goto out; } static int rawv6_push_pending_frames(struct sock *sk, struct flowi6 *fl6, struct raw6_sock *rp) { struct ipv6_txoptions *opt; struct sk_buff *skb; int err = 0; int offset; int len; int total_len; __wsum tmp_csum; __sum16 csum; if (!rp->checksum) goto send; skb = skb_peek(&sk->sk_write_queue); if (!skb) goto out; offset = rp->offset; total_len = inet_sk(sk)->cork.base.length; opt = inet6_sk(sk)->cork.opt; total_len -= opt ? opt->opt_flen : 0; if (offset >= total_len - 1) { err = -EINVAL; ip6_flush_pending_frames(sk); goto out; } /* should be check HW csum miyazawa */ if (skb_queue_len(&sk->sk_write_queue) == 1) { /* * Only one fragment on the socket. */ tmp_csum = skb->csum; } else { struct sk_buff *csum_skb = NULL; tmp_csum = 0; skb_queue_walk(&sk->sk_write_queue, skb) { tmp_csum = csum_add(tmp_csum, skb->csum); if (csum_skb) continue; len = skb->len - skb_transport_offset(skb); if (offset >= len) { offset -= len; continue; } csum_skb = skb; } skb = csum_skb; } offset += skb_transport_offset(skb); err = skb_copy_bits(skb, offset, &csum, 2); if (err < 0) { ip6_flush_pending_frames(sk); goto out; } /* in case cksum was not initialized */ if (unlikely(csum)) tmp_csum = csum_sub(tmp_csum, csum_unfold(csum)); csum = csum_ipv6_magic(&fl6->saddr, &fl6->daddr, total_len, fl6->flowi6_proto, tmp_csum); if (csum == 0 && fl6->flowi6_proto == IPPROTO_UDP) csum = CSUM_MANGLED_0; BUG_ON(skb_store_bits(skb, offset, &csum, 2)); send: err = ip6_push_pending_frames(sk); out: return err; } static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, struct flowi6 *fl6, struct dst_entry **dstp, unsigned int flags, const struct sockcm_cookie *sockc) { struct ipv6_pinfo *np = inet6_sk(sk); struct net *net = sock_net(sk); struct ipv6hdr *iph; struct sk_buff *skb; int err; struct rt6_info *rt = (struct rt6_info *)*dstp; int hlen = LL_RESERVED_SPACE(rt->dst.dev); int tlen = rt->dst.dev->needed_tailroom; if (length > rt->dst.dev->mtu) { ipv6_local_error(sk, EMSGSIZE, fl6, rt->dst.dev->mtu); return -EMSGSIZE; } if (length < sizeof(struct ipv6hdr)) return -EINVAL; if (flags&MSG_PROBE) goto out; skb = sock_alloc_send_skb(sk, length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (!skb) goto error; skb_reserve(skb, hlen); skb->protocol = htons(ETH_P_IPV6); skb->priority = sk->sk_priority; skb->mark = sockc->mark; skb->tstamp = sockc->transmit_time; skb_put(skb, length); skb_reset_network_header(skb); iph = ipv6_hdr(skb); skb->ip_summed = CHECKSUM_NONE; skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); skb->transport_header = skb->network_header; err = memcpy_from_msg(iph, msg, length); if (err) { err = -EFAULT; kfree_skb(skb); goto error; } skb_dst_set(skb, &rt->dst); *dstp = NULL; /* if egress device is enslaved to an L3 master device pass the * skb to its handler for processing */ skb = l3mdev_ip6_out(sk, skb); if (unlikely(!skb)) return 0; /* Acquire rcu_read_lock() in case we need to use rt->rt6i_idev * in the error path. Since skb has been freed, the dst could * have been queued for deletion. */ rcu_read_lock(); IP6_UPD_PO_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUT, skb->len); err = NF_HOOK(NFPROTO_IPV6, NF_INET_LOCAL_OUT, net, sk, skb, NULL, rt->dst.dev, dst_output); if (err > 0) err = net_xmit_errno(err); if (err) { IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); rcu_read_unlock(); goto error_check; } rcu_read_unlock(); out: return 0; error: IP6_INC_STATS(net, rt->rt6i_idev, IPSTATS_MIB_OUTDISCARDS); error_check: if (err == -ENOBUFS && !np->recverr) err = 0; return err; } struct raw6_frag_vec { struct msghdr *msg; int hlen; char c[4]; }; static int rawv6_probe_proto_opt(struct raw6_frag_vec *rfv, struct flowi6 *fl6) { int err = 0; switch (fl6->flowi6_proto) { case IPPROTO_ICMPV6: rfv->hlen = 2; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) { fl6->fl6_icmp_type = rfv->c[0]; fl6->fl6_icmp_code = rfv->c[1]; } break; case IPPROTO_MH: rfv->hlen = 4; err = memcpy_from_msg(rfv->c, rfv->msg, rfv->hlen); if (!err) fl6->fl6_mh_type = rfv->c[2]; } return err; } static int raw6_getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb) { struct raw6_frag_vec *rfv = from; if (offset < rfv->hlen) { int copy = min(rfv->hlen - offset, len); if (skb->ip_summed == CHECKSUM_PARTIAL) memcpy(to, rfv->c + offset, copy); else skb->csum = csum_block_add( skb->csum, csum_partial_copy_nocheck(rfv->c + offset, to, copy, 0), odd); odd = 0; offset += copy; to += copy; len -= copy; if (!len) return 0; } offset -= rfv->hlen; return ip_generic_getfrag(rfv->msg, to, offset, len, odd, skb); } static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct ipv6_txoptions *opt_to_free = NULL; struct ipv6_txoptions opt_space; DECLARE_SOCKADDR(struct sockaddr_in6 *, sin6, msg->msg_name); struct in6_addr *daddr, *final_p, final; struct inet_sock *inet = inet_sk(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct raw6_sock *rp = raw6_sk(sk); struct ipv6_txoptions *opt = NULL; struct ip6_flowlabel *flowlabel = NULL; struct dst_entry *dst = NULL; struct raw6_frag_vec rfv; struct flowi6 fl6; struct ipcm6_cookie ipc6; int addr_len = msg->msg_namelen; int hdrincl; u16 proto; int err; /* Rough check on arithmetic overflow, better check is made in ip6_append_data(). */ if (len > INT_MAX) return -EMSGSIZE; /* Mirror BSD error message compatibility */ if (msg->msg_flags & MSG_OOB) return -EOPNOTSUPP; /* hdrincl should be READ_ONCE(inet->hdrincl) * but READ_ONCE() doesn't work with bit fields. * Doing this indirectly yields the same result. */ hdrincl = inet->hdrincl; hdrincl = READ_ONCE(hdrincl); /* * Get and verify the address. */ memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = sk->sk_mark; fl6.flowi6_uid = sk->sk_uid; ipcm6_init(&ipc6); ipc6.sockc.tsflags = sk->sk_tsflags; ipc6.sockc.mark = sk->sk_mark; if (sin6) { if (addr_len < SIN6_LEN_RFC2133) return -EINVAL; if (sin6->sin6_family && sin6->sin6_family != AF_INET6) return -EAFNOSUPPORT; /* port is the proto value [0..255] carried in nexthdr */ proto = ntohs(sin6->sin6_port); if (!proto) proto = inet->inet_num; else if (proto != inet->inet_num && inet->inet_num != IPPROTO_RAW) return -EINVAL; if (proto > 255) return -EINVAL; daddr = &sin6->sin6_addr; if (np->sndflow) { fl6.flowlabel = sin6->sin6_flowinfo&IPV6_FLOWINFO_MASK; if (fl6.flowlabel&IPV6_FLOWLABEL_MASK) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } } /* * Otherwise it will be difficult to maintain * sk->sk_dst_cache. */ if (sk->sk_state == TCP_ESTABLISHED && ipv6_addr_equal(daddr, &sk->sk_v6_daddr)) daddr = &sk->sk_v6_daddr; if (addr_len >= sizeof(struct sockaddr_in6) && sin6->sin6_scope_id && __ipv6_addr_needs_scope_id(__ipv6_addr_type(daddr))) fl6.flowi6_oif = sin6->sin6_scope_id; } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; proto = inet->inet_num; daddr = &sk->sk_v6_daddr; fl6.flowlabel = np->flow_label; } if (fl6.flowi6_oif == 0) fl6.flowi6_oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); opt->tot_len = sizeof(struct ipv6_txoptions); ipc6.opt = opt; err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); if (err < 0) { fl6_sock_release(flowlabel); return err; } if ((fl6.flowlabel&IPV6_FLOWLABEL_MASK) && !flowlabel) { flowlabel = fl6_sock_lookup(sk, fl6.flowlabel); if (IS_ERR(flowlabel)) return -EINVAL; } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; } if (!opt) { opt = txopt_get(np); opt_to_free = opt; } if (flowlabel) opt = fl6_merge_options(&opt_space, flowlabel, opt); opt = ipv6_fixup_options(&opt_space, opt); fl6.flowi6_proto = proto; fl6.flowi6_mark = ipc6.sockc.mark; if (!hdrincl) { rfv.msg = msg; rfv.hlen = 0; err = rawv6_probe_proto_opt(&rfv, &fl6); if (err) goto out; } if (!ipv6_addr_any(daddr)) fl6.daddr = *daddr; else fl6.daddr.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl6.saddr) && !ipv6_addr_any(&np->saddr)) fl6.saddr = np->saddr; final_p = fl6_update_dst(&fl6, opt, &final); if (!fl6.flowi6_oif && ipv6_addr_is_multicast(&fl6.daddr)) fl6.flowi6_oif = np->mcast_oif; else if (!fl6.flowi6_oif) fl6.flowi6_oif = np->ucast_oif; security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); if (hdrincl) fl6.flowi6_flags |= FLOWI_FLAG_KNOWN_NH; if (ipc6.tclass < 0) ipc6.tclass = np->tclass; fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; } if (ipc6.hlimit < 0) ipc6.hlimit = ip6_sk_dst_hoplimit(np, &fl6, dst); if (ipc6.dontfrag < 0) ipc6.dontfrag = np->dontfrag; if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: if (hdrincl) err = rawv6_send_hdrinc(sk, msg, len, &fl6, &dst, msg->msg_flags, &ipc6.sockc); else { ipc6.opt = opt; lock_sock(sk); err = ip6_append_data(sk, raw6_getfrag, &rfv, len, 0, &ipc6, &fl6, (struct rt6_info *)dst, msg->msg_flags); if (err) ip6_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) err = rawv6_push_pending_frames(sk, &fl6, rp); release_sock(sk); } done: dst_release(dst); out: fl6_sock_release(flowlabel); txopt_put(opt_to_free); return err < 0 ? err : len; do_confirm: if (msg->msg_flags & MSG_PROBE) dst_confirm_neigh(dst, &fl6.daddr); if (!(msg->msg_flags & MSG_PROBE) || len) goto back_from_confirm; err = 0; goto done; } static int rawv6_seticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int optlen) { switch (optname) { case ICMPV6_FILTER: if (optlen > sizeof(struct icmp6_filter)) optlen = sizeof(struct icmp6_filter); if (copy_from_user(&raw6_sk(sk)->filter, optval, optlen)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int rawv6_geticmpfilter(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { int len; switch (optname) { case ICMPV6_FILTER: if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; if (len > sizeof(struct icmp6_filter)) len = sizeof(struct icmp6_filter); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &raw6_sk(sk)->filter, len)) return -EFAULT; return 0; default: return -ENOPROTOOPT; } return 0; } static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { struct raw6_sock *rp = raw6_sk(sk); int val; if (get_user(val, (int __user *)optval)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: if (sk->sk_type != SOCK_RAW) return -EINVAL; inet_sk(sk)->hdrincl = !!val; return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket * option in the IPPROTO_IPV6 level is not * allowed on ICMPv6 sockets. * If you want to set it, use IPPROTO_RAW * level IPV6_CHECKSUM socket option * (Linux extension). */ return -EINVAL; } /* You may get strange result with a positive odd offset; RFC2292bis agrees with me. */ if (val > 0 && (val&1)) return -EINVAL; if (val < 0) { rp->checksum = 0; } else { rp->checksum = 1; rp->offset = val; } return 0; default: return -ENOPROTOOPT; } } static int rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; /* fall through */ default: return ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } #ifdef CONFIG_COMPAT static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; /* fall through */ default: return compat_ipv6_setsockopt(sk, level, optname, optval, optlen); } return do_rawv6_setsockopt(sk, level, optname, optval, optlen); } #endif static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { struct raw6_sock *rp = raw6_sk(sk); int val, len; if (get_user(len, optlen)) return -EFAULT; switch (optname) { case IPV6_HDRINCL: val = inet_sk(sk)->hdrincl; break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level * IPV6_CHECKSUM socket option on ICMPv6 sockets * since RFC3542 is silent about it. */ if (rp->checksum == 0) val = -1; else val = rp->offset; break; default: return -ENOPROTOOPT; } len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } static int rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; /* fall through */ default: return ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } #ifdef CONFIG_COMPAT static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { switch (level) { case SOL_RAW: break; case SOL_ICMPV6: if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: if (optname == IPV6_CHECKSUM || optname == IPV6_HDRINCL) break; /* fall through */ default: return compat_ipv6_getsockopt(sk, level, optname, optval, optlen); } return do_rawv6_getsockopt(sk, level, optname, optval, optlen); } #endif static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: { int amount = sk_wmem_alloc_get(sk); return put_user(amount, (int __user *)arg); } case SIOCINQ: { struct sk_buff *skb; int amount = 0; spin_lock_bh(&sk->sk_receive_queue.lock); skb = skb_peek(&sk->sk_receive_queue); if (skb) amount = skb->len; spin_unlock_bh(&sk->sk_receive_queue.lock); return put_user(amount, (int __user *)arg); } default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_ioctl(sk, cmd, (void __user *)arg); #else return -ENOIOCTLCMD; #endif } } #ifdef CONFIG_COMPAT static int compat_rawv6_ioctl(struct sock *sk, unsigned int cmd, unsigned long arg) { switch (cmd) { case SIOCOUTQ: case SIOCINQ: return -ENOIOCTLCMD; default: #ifdef CONFIG_IPV6_MROUTE return ip6mr_compat_ioctl(sk, cmd, compat_ptr(arg)); #else return -ENOIOCTLCMD; #endif } } #endif static void rawv6_close(struct sock *sk, long timeout) { if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); } static void raw6_destroy(struct sock *sk) { lock_sock(sk); ip6_flush_pending_frames(sk); release_sock(sk); } static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; break; case IPPROTO_MH: rp->checksum = 1; rp->offset = 4; break; default: break; } return 0; } struct proto rawv6_prot = { .name = "RAWv6", .owner = THIS_MODULE, .close = rawv6_close, .destroy = raw6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .ioctl = rawv6_ioctl, .init = rawv6_init_sk, .setsockopt = rawv6_setsockopt, .getsockopt = rawv6_getsockopt, .sendmsg = rawv6_sendmsg, .recvmsg = rawv6_recvmsg, .bind = rawv6_bind, .backlog_rcv = rawv6_rcv_skb, .hash = raw_hash_sk, .unhash = raw_unhash_sk, .obj_size = sizeof(struct raw6_sock), .useroffset = offsetof(struct raw6_sock, filter), .usersize = sizeof_field(struct raw6_sock, filter), .h.raw_hash = &raw_v6_hashinfo, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_rawv6_setsockopt, .compat_getsockopt = compat_rawv6_getsockopt, .compat_ioctl = compat_rawv6_ioctl, #endif .diag_destroy = raw_abort, }; #ifdef CONFIG_PROC_FS static int raw6_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) { seq_puts(seq, IPV6_SEQ_DGRAM_HEADER); } else { struct sock *sp = v; __u16 srcp = inet_sk(sp)->inet_num; ip6_dgram_sock_seq_show(seq, v, srcp, 0, raw_seq_private(seq)->bucket); } return 0; } static const struct seq_operations raw6_seq_ops = { .start = raw_seq_start, .next = raw_seq_next, .stop = raw_seq_stop, .show = raw6_seq_show, }; static int __net_init raw6_init_net(struct net *net) { if (!proc_create_net_data("raw6", 0444, net->proc_net, &raw6_seq_ops, sizeof(struct raw_iter_state), &raw_v6_hashinfo)) return -ENOMEM; return 0; } static void __net_exit raw6_exit_net(struct net *net) { remove_proc_entry("raw6", net->proc_net); } static struct pernet_operations raw6_net_ops = { .init = raw6_init_net, .exit = raw6_exit_net, }; int __init raw6_proc_init(void) { return register_pernet_subsys(&raw6_net_ops); } void raw6_proc_exit(void) { unregister_pernet_subsys(&raw6_net_ops); } #endif /* CONFIG_PROC_FS */ /* Same as inet6_dgram_ops, sans udp_poll. */ const struct proto_ops inet6_sockraw_ops = { .family = PF_INET6, .owner = THIS_MODULE, .release = inet6_release, .bind = inet6_bind, .connect = inet_dgram_connect, /* ok */ .socketpair = sock_no_socketpair, /* a do nothing */ .accept = sock_no_accept, /* a do nothing */ .getname = inet6_getname, .poll = datagram_poll, /* ok */ .ioctl = inet6_ioctl, /* must change */ .gettstamp = sock_gettstamp, .listen = sock_no_listen, /* ok */ .shutdown = inet_shutdown, /* ok */ .setsockopt = sock_common_setsockopt, /* ok */ .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = sock_common_recvmsg, /* ok */ .mmap = sock_no_mmap, .sendpage = sock_no_sendpage, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, #endif }; static struct inet_protosw rawv6_protosw = { .type = SOCK_RAW, .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, .flags = INET_PROTOSW_REUSE, }; int __init rawv6_init(void) { return inet6_register_protosw(&rawv6_protosw); } void rawv6_exit(void) { inet6_unregister_protosw(&rawv6_protosw); } |
| 23 4 17 17 18 17 6 3 2 1 2 1 1 34 34 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include "cgroup-internal.h" #include <linux/ctype.h> #include <linux/kmod.h> #include <linux/sort.h> #include <linux/delay.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <linux/delayacct.h> #include <linux/pid_namespace.h> #include <linux/cgroupstats.h> #include <linux/fs_parser.h> #include <linux/cpu.h> #include <trace/events/cgroup.h> #include <trace/hooks/cgroup.h> #define cg_invalf(fc, fmt, ...) invalf(fc, fmt, ## __VA_ARGS__) /* * pidlists linger the following amount before being destroyed. The goal * is avoiding frequent destruction in the middle of consecutive read calls * Expiring in the middle is a performance problem not a correctness one. * 1 sec should be enough. */ #define CGROUP_PIDLIST_DESTROY_DELAY HZ /* Controllers blocked by the commandline in v1 */ static u16 cgroup_no_v1_mask; /* disable named v1 mounts */ static bool cgroup_no_v1_named; /* * pidlist destructions need to be flushed on cgroup destruction. Use a * separate workqueue as flush domain. */ static struct workqueue_struct *cgroup_pidlist_destroy_wq; /* * Protects cgroup_subsys->release_agent_path. Modifying it also requires * cgroup_mutex. Reading requires either cgroup_mutex or this spinlock. */ static DEFINE_SPINLOCK(release_agent_path_lock); bool cgroup1_ssid_disabled(int ssid) { return cgroup_no_v1_mask & (1 << ssid); } /** * cgroup_attach_task_all - attach task 'tsk' to all cgroups of task 'from' * @from: attach to all cgroups of a given task * @tsk: the task to be attached */ int cgroup_attach_task_all(struct task_struct *from, struct task_struct *tsk) { struct cgroup_root *root; int retval = 0; mutex_lock(&cgroup_mutex); cpus_read_lock(); percpu_down_write(&cgroup_threadgroup_rwsem); for_each_root(root) { struct cgroup *from_cgrp; if (root == &cgrp_dfl_root) continue; spin_lock_irq(&css_set_lock); from_cgrp = task_cgroup_from_root(from, root); spin_unlock_irq(&css_set_lock); retval = cgroup_attach_task(from_cgrp, tsk, false); if (retval) break; } percpu_up_write(&cgroup_threadgroup_rwsem); cpus_read_unlock(); mutex_unlock(&cgroup_mutex); return retval; } EXPORT_SYMBOL_GPL(cgroup_attach_task_all); /** * cgroup_trasnsfer_tasks - move tasks from one cgroup to another * @to: cgroup to which the tasks will be moved * @from: cgroup in which the tasks currently reside * * Locking rules between cgroup_post_fork() and the migration path * guarantee that, if a task is forking while being migrated, the new child * is guaranteed to be either visible in the source cgroup after the * parent's migration is complete or put into the target cgroup. No task * can slip out of migration through forking. */ int cgroup_transfer_tasks(struct cgroup *to, struct cgroup *from) { DEFINE_CGROUP_MGCTX(mgctx); struct cgrp_cset_link *link; struct css_task_iter it; struct task_struct *task; int ret; if (cgroup_on_dfl(to)) return -EINVAL; ret = cgroup_migrate_vet_dst(to); if (ret) return ret; mutex_lock(&cgroup_mutex); percpu_down_write(&cgroup_threadgroup_rwsem); /* all tasks in @from are being moved, all csets are source */ spin_lock_irq(&css_set_lock); list_for_each_entry(link, &from->cset_links, cset_link) cgroup_migrate_add_src(link->cset, to, &mgctx); spin_unlock_irq(&css_set_lock); ret = cgroup_migrate_prepare_dst(&mgctx); if (ret) goto out_err; /* * Migrate tasks one-by-one until @from is empty. This fails iff * ->can_attach() fails. */ do { css_task_iter_start(&from->self, 0, &it); do { task = css_task_iter_next(&it); } while (task && (task->flags & PF_EXITING)); if (task) get_task_struct(task); css_task_iter_end(&it); if (task) { ret = cgroup_migrate(task, false, &mgctx); if (!ret) TRACE_CGROUP_PATH(transfer_tasks, to, task, false); put_task_struct(task); } } while (task && !ret); out_err: cgroup_migrate_finish(&mgctx); percpu_up_write(&cgroup_threadgroup_rwsem); mutex_unlock(&cgroup_mutex); return ret; } /* * Stuff for reading the 'tasks'/'procs' files. * * Reading this file can return large amounts of data if a cgroup has * *lots* of attached tasks. So it may need several calls to read(), * but we cannot guarantee that the information we produce is correct * unless we produce it entirely atomically. * */ /* which pidlist file are we talking about? */ enum cgroup_filetype { CGROUP_FILE_PROCS, CGROUP_FILE_TASKS, }; /* * A pidlist is a list of pids that virtually represents the contents of one * of the cgroup files ("procs" or "tasks"). We keep a list of such pidlists, * a pair (one each for procs, tasks) for each pid namespace that's relevant * to the cgroup. */ struct cgroup_pidlist { /* * used to find which pidlist is wanted. doesn't change as long as * this particular list stays in the list. */ struct { enum cgroup_filetype type; struct pid_namespace *ns; } key; /* array of xids */ pid_t *list; /* how many elements the above list has */ int length; /* each of these stored in a list by its cgroup */ struct list_head links; /* pointer to the cgroup we belong to, for list removal purposes */ struct cgroup *owner; /* for delayed destruction */ struct delayed_work destroy_dwork; }; /* * Used to destroy all pidlists lingering waiting for destroy timer. None * should be left afterwards. */ void cgroup1_pidlist_destroy_all(struct cgroup *cgrp) { struct cgroup_pidlist *l, *tmp_l; mutex_lock(&cgrp->pidlist_mutex); list_for_each_entry_safe(l, tmp_l, &cgrp->pidlists, links) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, 0); mutex_unlock(&cgrp->pidlist_mutex); flush_workqueue(cgroup_pidlist_destroy_wq); BUG_ON(!list_empty(&cgrp->pidlists)); } static void cgroup_pidlist_destroy_work_fn(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct cgroup_pidlist *l = container_of(dwork, struct cgroup_pidlist, destroy_dwork); struct cgroup_pidlist *tofree = NULL; mutex_lock(&l->owner->pidlist_mutex); /* * Destroy iff we didn't get queued again. The state won't change * as destroy_dwork can only be queued while locked. */ if (!delayed_work_pending(dwork)) { list_del(&l->links); kvfree(l->list); put_pid_ns(l->key.ns); tofree = l; } mutex_unlock(&l->owner->pidlist_mutex); kfree(tofree); } /* * pidlist_uniq - given a kmalloc()ed list, strip out all duplicate entries * Returns the number of unique elements. */ static int pidlist_uniq(pid_t *list, int length) { int src, dest = 1; /* * we presume the 0th element is unique, so i starts at 1. trivial * edge cases first; no work needs to be done for either */ if (length == 0 || length == 1) return length; /* src and dest walk down the list; dest counts unique elements */ for (src = 1; src < length; src++) { /* find next unique element */ while (list[src] == list[src-1]) { src++; if (src == length) goto after; } /* dest always points to where the next unique element goes */ list[dest] = list[src]; dest++; } after: return dest; } /* * The two pid files - task and cgroup.procs - guaranteed that the result * is sorted, which forced this whole pidlist fiasco. As pid order is * different per namespace, each namespace needs differently sorted list, * making it impossible to use, for example, single rbtree of member tasks * sorted by task pointer. As pidlists can be fairly large, allocating one * per open file is dangerous, so cgroup had to implement shared pool of * pidlists keyed by cgroup and namespace. */ static int cmppid(const void *a, const void *b) { return *(pid_t *)a - *(pid_t *)b; } static struct cgroup_pidlist *cgroup_pidlist_find(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; /* don't need task_nsproxy() if we're looking at ourself */ struct pid_namespace *ns = task_active_pid_ns(current); lockdep_assert_held(&cgrp->pidlist_mutex); list_for_each_entry(l, &cgrp->pidlists, links) if (l->key.type == type && l->key.ns == ns) return l; return NULL; } /* * find the appropriate pidlist for our purpose (given procs vs tasks) * returns with the lock on that pidlist already held, and takes care * of the use count, or returns NULL with no locks held if we're out of * memory. */ static struct cgroup_pidlist *cgroup_pidlist_find_create(struct cgroup *cgrp, enum cgroup_filetype type) { struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); l = cgroup_pidlist_find(cgrp, type); if (l) return l; /* entry not found; create a new one */ l = kzalloc(sizeof(struct cgroup_pidlist), GFP_KERNEL); if (!l) return l; INIT_DELAYED_WORK(&l->destroy_dwork, cgroup_pidlist_destroy_work_fn); l->key.type = type; /* don't need task_nsproxy() if we're looking at ourself */ l->key.ns = get_pid_ns(task_active_pid_ns(current)); l->owner = cgrp; list_add(&l->links, &cgrp->pidlists); return l; } /* * Load a cgroup's pidarray with either procs' tgids or tasks' pids */ static int pidlist_array_load(struct cgroup *cgrp, enum cgroup_filetype type, struct cgroup_pidlist **lp) { pid_t *array; int length; int pid, n = 0; /* used for populating the array */ struct css_task_iter it; struct task_struct *tsk; struct cgroup_pidlist *l; lockdep_assert_held(&cgrp->pidlist_mutex); /* * If cgroup gets more users after we read count, we won't have * enough space - tough. This race is indistinguishable to the * caller from the case that the additional cgroup users didn't * show up until sometime later on. */ length = cgroup_task_count(cgrp); array = kvmalloc_array(length, sizeof(pid_t), GFP_KERNEL); if (!array) return -ENOMEM; /* now, populate the array */ css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { if (unlikely(n == length)) break; /* get tgid or pid for procs or tasks file respectively */ if (type == CGROUP_FILE_PROCS) pid = task_tgid_vnr(tsk); else pid = task_pid_vnr(tsk); if (pid > 0) /* make sure to only use valid results */ array[n++] = pid; } css_task_iter_end(&it); length = n; /* now sort & strip out duplicates (tgids or recycled thread PIDs) */ sort(array, length, sizeof(pid_t), cmppid, NULL); length = pidlist_uniq(array, length); l = cgroup_pidlist_find_create(cgrp, type); if (!l) { kvfree(array); return -ENOMEM; } /* store array, freeing old if necessary */ kvfree(l->list); l->list = array; l->length = length; *lp = l; return 0; } /* * seq_file methods for the tasks/procs files. The seq_file position is the * next pid to display; the seq_file iterator is a pointer to the pid * in the cgroup->l->list array. */ static void *cgroup_pidlist_start(struct seq_file *s, loff_t *pos) { /* * Initially we receive a position value that corresponds to * one more than the last pid shown (or 0 on the first call or * after a seek to the start). Use a binary-search to find the * next pid to display, if any */ struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup *cgrp = seq_css(s)->cgroup; struct cgroup_pidlist *l; enum cgroup_filetype type = seq_cft(s)->private; int index = 0, pid = *pos; int *iter, ret; mutex_lock(&cgrp->pidlist_mutex); /* * !NULL @ctx->procs1.pidlist indicates that this isn't the first * start() after open. If the matching pidlist is around, we can use * that. Look for it. Note that @ctx->procs1.pidlist can't be used * directly. It could already have been destroyed. */ if (ctx->procs1.pidlist) ctx->procs1.pidlist = cgroup_pidlist_find(cgrp, type); /* * Either this is the first start() after open or the matching * pidlist has been destroyed inbetween. Create a new one. */ if (!ctx->procs1.pidlist) { ret = pidlist_array_load(cgrp, type, &ctx->procs1.pidlist); if (ret) return ERR_PTR(ret); } l = ctx->procs1.pidlist; if (pid) { int end = l->length; while (index < end) { int mid = (index + end) / 2; if (l->list[mid] == pid) { index = mid; break; } else if (l->list[mid] <= pid) index = mid + 1; else end = mid; } } /* If we're off the end of the array, we're done */ if (index >= l->length) return NULL; /* Update the abstract position to be the actual pid that we found */ iter = l->list + index; *pos = *iter; return iter; } static void cgroup_pidlist_stop(struct seq_file *s, void *v) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; if (l) mod_delayed_work(cgroup_pidlist_destroy_wq, &l->destroy_dwork, CGROUP_PIDLIST_DESTROY_DELAY); mutex_unlock(&seq_css(s)->cgroup->pidlist_mutex); } static void *cgroup_pidlist_next(struct seq_file *s, void *v, loff_t *pos) { struct kernfs_open_file *of = s->private; struct cgroup_file_ctx *ctx = of->priv; struct cgroup_pidlist *l = ctx->procs1.pidlist; pid_t *p = v; pid_t *end = l->list + l->length; /* * Advance to the next pid in the array. If this goes off the * end, we're done */ p++; if (p >= end) { (*pos)++; return NULL; } else { *pos = *p; return p; } } static int cgroup_pidlist_show(struct seq_file *s, void *v) { seq_printf(s, "%d\n", *(int *)v); return 0; } static ssize_t __cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off, bool threadgroup) { struct cgroup *cgrp; struct task_struct *task; const struct cred *cred, *tcred; ssize_t ret; bool locked; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; task = cgroup_procs_write_start(buf, threadgroup, &locked); ret = PTR_ERR_OR_ZERO(task); if (ret) goto out_unlock; /* * Even if we're attaching all tasks in the thread group, we only need * to check permissions on one of them. Check permissions using the * credentials from file open to protect against inherited fd attacks. */ cred = of->file->f_cred; tcred = get_task_cred(task); if (!uid_eq(cred->euid, GLOBAL_ROOT_UID) && !uid_eq(cred->euid, tcred->uid) && !uid_eq(cred->euid, tcred->suid) && !ns_capable(tcred->user_ns, CAP_SYS_NICE)) ret = -EACCES; put_cred(tcred); if (ret) goto out_finish; ret = cgroup_attach_task(cgrp, task, threadgroup); trace_android_vh_cgroup_set_task(ret, task); out_finish: cgroup_procs_write_finish(task, locked); out_unlock: cgroup_kn_unlock(of->kn); return ret ?: nbytes; } static ssize_t cgroup1_procs_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, true); } static ssize_t cgroup1_tasks_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { return __cgroup1_procs_write(of, buf, nbytes, off, false); } static ssize_t cgroup_release_agent_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cgroup *cgrp; struct cgroup_file_ctx *ctx; BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ ctx = of->priv; if ((ctx->ns->user_ns != &init_user_ns) || !file_ns_capable(of->file, &init_user_ns, CAP_SYS_ADMIN)) return -EPERM; cgrp = cgroup_kn_lock_live(of->kn, false); if (!cgrp) return -ENODEV; spin_lock(&release_agent_path_lock); strlcpy(cgrp->root->release_agent_path, strstrip(buf), sizeof(cgrp->root->release_agent_path)); spin_unlock(&release_agent_path_lock); cgroup_kn_unlock(of->kn); return nbytes; } static int cgroup_release_agent_show(struct seq_file *seq, void *v) { struct cgroup *cgrp = seq_css(seq)->cgroup; spin_lock(&release_agent_path_lock); seq_puts(seq, cgrp->root->release_agent_path); spin_unlock(&release_agent_path_lock); seq_putc(seq, '\n'); return 0; } static int cgroup_sane_behavior_show(struct seq_file *seq, void *v) { seq_puts(seq, "0\n"); return 0; } static u64 cgroup_read_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft) { return notify_on_release(css->cgroup); } static int cgroup_write_notify_on_release(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); else clear_bit(CGRP_NOTIFY_ON_RELEASE, &css->cgroup->flags); return 0; } static u64 cgroup_clone_children_read(struct cgroup_subsys_state *css, struct cftype *cft) { return test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); } static int cgroup_clone_children_write(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { if (val) set_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); else clear_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags); return 0; } /* cgroup core interface files for the legacy hierarchies */ struct cftype cgroup1_base_files[] = { { .name = "cgroup.procs", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_PROCS, .write = cgroup1_procs_write, }, { .name = "cgroup.clone_children", .read_u64 = cgroup_clone_children_read, .write_u64 = cgroup_clone_children_write, }, { .name = "cgroup.sane_behavior", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_sane_behavior_show, }, { .name = "tasks", .seq_start = cgroup_pidlist_start, .seq_next = cgroup_pidlist_next, .seq_stop = cgroup_pidlist_stop, .seq_show = cgroup_pidlist_show, .private = CGROUP_FILE_TASKS, .write = cgroup1_tasks_write, }, { .name = "notify_on_release", .read_u64 = cgroup_read_notify_on_release, .write_u64 = cgroup_write_notify_on_release, }, { .name = "release_agent", .flags = CFTYPE_ONLY_ON_ROOT, .seq_show = cgroup_release_agent_show, .write = cgroup_release_agent_write, .max_write_len = PATH_MAX - 1, }, { } /* terminate */ }; /* Display information about each subsystem and each hierarchy */ int proc_cgroupstats_show(struct seq_file *m, void *v) { struct cgroup_subsys *ss; int i; seq_puts(m, "#subsys_name\thierarchy\tnum_cgroups\tenabled\n"); /* * ideally we don't want subsystems moving around while we do this. * cgroup_mutex is also necessary to guarantee an atomic snapshot of * subsys/hierarchy state. */ mutex_lock(&cgroup_mutex); for_each_subsys(ss, i) seq_printf(m, "%s\t%d\t%d\t%d\n", ss->legacy_name, ss->root->hierarchy_id, atomic_read(&ss->root->nr_cgrps), cgroup_ssid_enabled(i)); mutex_unlock(&cgroup_mutex); return 0; } /** * cgroupstats_build - build and fill cgroupstats * @stats: cgroupstats to fill information into * @dentry: A dentry entry belonging to the cgroup for which stats have * been requested. * * Build and fill cgroupstats so that taskstats can export it to user * space. */ int cgroupstats_build(struct cgroupstats *stats, struct dentry *dentry) { struct kernfs_node *kn = kernfs_node_from_dentry(dentry); struct cgroup *cgrp; struct css_task_iter it; struct task_struct *tsk; /* it should be kernfs_node belonging to cgroupfs and is a directory */ if (dentry->d_sb->s_type != &cgroup_fs_type || !kn || kernfs_type(kn) != KERNFS_DIR) return -EINVAL; mutex_lock(&cgroup_mutex); /* * We aren't being called from kernfs and there's no guarantee on * @kn->priv's validity. For this and css_tryget_online_from_dir(), * @kn->priv is RCU safe. Let's do the RCU dancing. */ rcu_read_lock(); cgrp = rcu_dereference(*(void __rcu __force **)&kn->priv); if (!cgrp || cgroup_is_dead(cgrp)) { rcu_read_unlock(); mutex_unlock(&cgroup_mutex); return -ENOENT; } rcu_read_unlock(); css_task_iter_start(&cgrp->self, 0, &it); while ((tsk = css_task_iter_next(&it))) { switch (tsk->state) { case TASK_RUNNING: stats->nr_running++; break; case TASK_INTERRUPTIBLE: stats->nr_sleeping++; break; case TASK_UNINTERRUPTIBLE: stats->nr_uninterruptible++; break; case TASK_STOPPED: stats->nr_stopped++; break; default: if (delayacct_is_task_waiting_on_io(tsk)) stats->nr_io_wait++; break; } } css_task_iter_end(&it); mutex_unlock(&cgroup_mutex); return 0; } void cgroup1_check_for_release(struct cgroup *cgrp) { if (notify_on_release(cgrp) && !cgroup_is_populated(cgrp) && !css_has_online_children(&cgrp->self) && !cgroup_is_dead(cgrp)) schedule_work(&cgrp->release_agent_work); } /* * Notify userspace when a cgroup is released, by running the * configured release agent with the name of the cgroup (path * relative to the root of cgroup file system) as the argument. * * Most likely, this user command will try to rmdir this cgroup. * * This races with the possibility that some other task will be * attached to this cgroup before it is removed, or that some other * user task will 'mkdir' a child cgroup of this cgroup. That's ok. * The presumed 'rmdir' will fail quietly if this cgroup is no longer * unused, and this cgroup will be reprieved from its death sentence, * to continue to serve a useful existence. Next time it's released, * we will get notified again, if it still has 'notify_on_release' set. * * The final arg to call_usermodehelper() is UMH_WAIT_EXEC, which * means only wait until the task is successfully execve()'d. The * separate release agent task is forked by call_usermodehelper(), * then control in this thread returns here, without waiting for the * release agent task. We don't bother to wait because the caller of * this routine has no use for the exit status of the release agent * task, so no sense holding our caller up for that. */ void cgroup1_release_agent(struct work_struct *work) { struct cgroup *cgrp = container_of(work, struct cgroup, release_agent_work); char *pathbuf = NULL, *agentbuf = NULL; char *argv[3], *envp[3]; int ret; mutex_lock(&cgroup_mutex); pathbuf = kmalloc(PATH_MAX, GFP_KERNEL); agentbuf = kstrdup(cgrp->root->release_agent_path, GFP_KERNEL); if (!pathbuf || !agentbuf || !strlen(agentbuf)) goto out; spin_lock_irq(&css_set_lock); ret = cgroup_path_ns_locked(cgrp, pathbuf, PATH_MAX, &init_cgroup_ns); spin_unlock_irq(&css_set_lock); if (ret < 0 || ret >= PATH_MAX) goto out; argv[0] = agentbuf; argv[1] = pathbuf; argv[2] = NULL; /* minimal command environment */ envp[0] = "HOME=/"; envp[1] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin"; envp[2] = NULL; mutex_unlock(&cgroup_mutex); call_usermodehelper(argv[0], argv, envp, UMH_WAIT_EXEC); goto out_free; out: mutex_unlock(&cgroup_mutex); out_free: kfree(agentbuf); kfree(pathbuf); } /* * cgroup_rename - Only allow simple rename of directories in place. */ static int cgroup1_rename(struct kernfs_node *kn, struct kernfs_node *new_parent, const char *new_name_str) { struct cgroup *cgrp = kn->priv; int ret; /* do not accept '\n' to prevent making /proc/<pid>/cgroup unparsable */ if (strchr(new_name_str, '\n')) return -EINVAL; if (kernfs_type(kn) != KERNFS_DIR) return -ENOTDIR; if (kn->parent != new_parent) return -EIO; /* * We're gonna grab cgroup_mutex which nests outside kernfs * active_ref. kernfs_rename() doesn't require active_ref * protection. Break them before grabbing cgroup_mutex. */ kernfs_break_active_protection(new_parent); kernfs_break_active_protection(kn); mutex_lock(&cgroup_mutex); ret = kernfs_rename(kn, new_parent, new_name_str); if (!ret) TRACE_CGROUP_PATH(rename, cgrp); mutex_unlock(&cgroup_mutex); kernfs_unbreak_active_protection(kn); kernfs_unbreak_active_protection(new_parent); return ret; } static int cgroup1_show_options(struct seq_file *seq, struct kernfs_root *kf_root) { struct cgroup_root *root = cgroup_root_from_kf(kf_root); struct cgroup_subsys *ss; int ssid; for_each_subsys(ss, ssid) if (root->subsys_mask & (1 << ssid)) seq_show_option(seq, ss->legacy_name, NULL); if (root->flags & CGRP_ROOT_NOPREFIX) seq_puts(seq, ",noprefix"); if (root->flags & CGRP_ROOT_XATTR) seq_puts(seq, ",xattr"); if (root->flags & CGRP_ROOT_CPUSET_V2_MODE) seq_puts(seq, ",cpuset_v2_mode"); spin_lock(&release_agent_path_lock); if (strlen(root->release_agent_path)) seq_show_option(seq, "release_agent", root->release_agent_path); spin_unlock(&release_agent_path_lock); if (test_bit(CGRP_CPUSET_CLONE_CHILDREN, &root->cgrp.flags)) seq_puts(seq, ",clone_children"); if (strlen(root->name)) seq_show_option(seq, "name", root->name); return 0; } enum cgroup1_param { Opt_all, Opt_clone_children, Opt_cpuset_v2_mode, Opt_name, Opt_none, Opt_noprefix, Opt_release_agent, Opt_xattr, }; static const struct fs_parameter_spec cgroup1_param_specs[] = { fsparam_flag ("all", Opt_all), fsparam_flag ("clone_children", Opt_clone_children), fsparam_flag ("cpuset_v2_mode", Opt_cpuset_v2_mode), fsparam_string("name", Opt_name), fsparam_flag ("none", Opt_none), fsparam_flag ("noprefix", Opt_noprefix), fsparam_string("release_agent", Opt_release_agent), fsparam_flag ("xattr", Opt_xattr), {} }; const struct fs_parameter_description cgroup1_fs_parameters = { .name = "cgroup1", .specs = cgroup1_param_specs, }; int cgroup1_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_subsys *ss; struct fs_parse_result result; int opt, i; opt = fs_parse(fc, &cgroup1_fs_parameters, param, &result); if (opt == -ENOPARAM) { if (strcmp(param->key, "source") == 0) { if (param->type != fs_value_is_string) return invalf(fc, "Non-string source"); if (fc->source) return invalf(fc, "Multiple sources not supported"); fc->source = param->string; param->string = NULL; return 0; } for_each_subsys(ss, i) { if (strcmp(param->key, ss->legacy_name)) continue; if (!cgroup_ssid_enabled(i) || cgroup1_ssid_disabled(i)) return invalf(fc, "Disabled controller '%s'", param->key); ctx->subsys_mask |= (1 << i); return 0; } return cg_invalf(fc, "cgroup1: Unknown subsys name '%s'", param->key); } if (opt < 0) return opt; switch (opt) { case Opt_none: /* Explicitly have no subsystems */ ctx->none = true; break; case Opt_all: ctx->all_ss = true; break; case Opt_noprefix: ctx->flags |= CGRP_ROOT_NOPREFIX; break; case Opt_clone_children: ctx->cpuset_clone_children = true; break; case Opt_cpuset_v2_mode: ctx->flags |= CGRP_ROOT_CPUSET_V2_MODE; break; case Opt_xattr: ctx->flags |= CGRP_ROOT_XATTR; break; case Opt_release_agent: /* Specifying two release agents is forbidden */ if (ctx->release_agent) return cg_invalf(fc, "cgroup1: release_agent respecified"); /* * Release agent gets called with all capabilities, * require capabilities to set release agent. */ if ((fc->user_ns != &init_user_ns) || !capable(CAP_SYS_ADMIN)) return cg_invalf(fc, "cgroup1: Setting release_agent not allowed"); ctx->release_agent = param->string; param->string = NULL; break; case Opt_name: /* blocked by boot param? */ if (cgroup_no_v1_named) return -ENOENT; /* Can't specify an empty name */ if (!param->size) return cg_invalf(fc, "cgroup1: Empty name"); if (param->size > MAX_CGROUP_ROOT_NAMELEN - 1) return cg_invalf(fc, "cgroup1: Name too long"); /* Must match [\w.-]+ */ for (i = 0; i < param->size; i++) { char c = param->string[i]; if (isalnum(c)) continue; if ((c == '.') || (c == '-') || (c == '_')) continue; return cg_invalf(fc, "cgroup1: Invalid name"); } /* Specifying two names is forbidden */ if (ctx->name) return cg_invalf(fc, "cgroup1: name respecified"); ctx->name = param->string; param->string = NULL; break; } return 0; } static int check_cgroupfs_options(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); u16 mask = U16_MAX; u16 enabled = 0; struct cgroup_subsys *ss; int i; #ifdef CONFIG_CPUSETS mask = ~((u16)1 << cpuset_cgrp_id); #endif for_each_subsys(ss, i) if (cgroup_ssid_enabled(i) && !cgroup1_ssid_disabled(i)) enabled |= 1 << i; ctx->subsys_mask &= enabled; /* * In absense of 'none', 'name=' or subsystem name options, * let's default to 'all'. */ if (!ctx->subsys_mask && !ctx->none && !ctx->name) ctx->all_ss = true; if (ctx->all_ss) { /* Mutually exclusive option 'all' + subsystem name */ if (ctx->subsys_mask) return cg_invalf(fc, "cgroup1: subsys name conflicts with all"); /* 'all' => select all the subsystems */ ctx->subsys_mask = enabled; } /* * We either have to specify by name or by subsystems. (So all * empty hierarchies must have a name). */ if (!ctx->subsys_mask && !ctx->name) return cg_invalf(fc, "cgroup1: Need name or subsystem set"); /* * Option noprefix was introduced just for backward compatibility * with the old cpuset, so we allow noprefix only if mounting just * the cpuset subsystem. */ if ((ctx->flags & CGRP_ROOT_NOPREFIX) && (ctx->subsys_mask & mask)) return cg_invalf(fc, "cgroup1: noprefix used incorrectly"); /* Can't specify "none" and some subsystems */ if (ctx->subsys_mask && ctx->none) return cg_invalf(fc, "cgroup1: none used incorrectly"); return 0; } int cgroup1_reconfigure(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct kernfs_root *kf_root = kernfs_root_from_sb(fc->root->d_sb); struct cgroup_root *root = cgroup_root_from_kf(kf_root); int ret = 0; u16 added_mask, removed_mask; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); /* See what subsystems are wanted */ ret = check_cgroupfs_options(fc); if (ret) goto out_unlock; if (ctx->subsys_mask != root->subsys_mask || ctx->release_agent) pr_warn("option changes via remount are deprecated (pid=%d comm=%s)\n", task_tgid_nr(current), current->comm); added_mask = ctx->subsys_mask & ~root->subsys_mask; removed_mask = root->subsys_mask & ~ctx->subsys_mask; /* Don't allow flags or name to change at remount */ if ((ctx->flags ^ root->flags) || (ctx->name && strcmp(ctx->name, root->name))) { cg_invalf(fc, "option or name mismatch, new: 0x%x \"%s\", old: 0x%x \"%s\"", ctx->flags, ctx->name ?: "", root->flags, root->name); ret = -EINVAL; goto out_unlock; } /* remounting is not allowed for populated hierarchies */ if (!list_empty(&root->cgrp.self.children)) { ret = -EBUSY; goto out_unlock; } ret = rebind_subsystems(root, added_mask); if (ret) goto out_unlock; WARN_ON(rebind_subsystems(&cgrp_dfl_root, removed_mask)); if (ctx->release_agent) { spin_lock(&release_agent_path_lock); strcpy(root->release_agent_path, ctx->release_agent); spin_unlock(&release_agent_path_lock); } trace_cgroup_remount(root); out_unlock: mutex_unlock(&cgroup_mutex); return ret; } struct kernfs_syscall_ops cgroup1_kf_syscall_ops = { .rename = cgroup1_rename, .show_options = cgroup1_show_options, .mkdir = cgroup_mkdir, .rmdir = cgroup_rmdir, .show_path = cgroup_show_path, }; /* * The guts of cgroup1 mount - find or create cgroup_root to use. * Called with cgroup_mutex held; returns 0 on success, -E... on * error and positive - in case when the candidate is busy dying. * On success it stashes a reference to cgroup_root into given * cgroup_fs_context; that reference is *NOT* counting towards the * cgroup_root refcount. */ static int cgroup1_root_to_use(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); struct cgroup_root *root; struct cgroup_subsys *ss; int i, ret; /* First find the desired set of subsystems */ ret = check_cgroupfs_options(fc); if (ret) return ret; /* * Destruction of cgroup root is asynchronous, so subsystems may * still be dying after the previous unmount. Let's drain the * dying subsystems. We just need to ensure that the ones * unmounted previously finish dying and don't care about new ones * starting. Testing ref liveliness is good enough. */ for_each_subsys(ss, i) { if (!(ctx->subsys_mask & (1 << i)) || ss->root == &cgrp_dfl_root) continue; if (!percpu_ref_tryget_live(&ss->root->cgrp.self.refcnt)) return 1; /* restart */ cgroup_put(&ss->root->cgrp); } for_each_root(root) { bool name_match = false; if (root == &cgrp_dfl_root) continue; /* * If we asked for a name then it must match. Also, if * name matches but sybsys_mask doesn't, we should fail. * Remember whether name matched. */ if (ctx->name) { if (strcmp(ctx->name, root->name)) continue; name_match = true; } /* * If we asked for subsystems (or explicitly for no * subsystems) then they must match. */ if ((ctx->subsys_mask || ctx->none) && (ctx->subsys_mask != root->subsys_mask)) { if (!name_match) continue; return -EBUSY; } if (root->flags ^ ctx->flags) pr_warn("new mount options do not match the existing superblock, will be ignored\n"); ctx->root = root; return 0; } /* * No such thing, create a new one. name= matching without subsys * specification is allowed for already existing hierarchies but we * can't create new one without subsys specification. */ if (!ctx->subsys_mask && !ctx->none) return cg_invalf(fc, "cgroup1: No subsys list or none specified"); /* Hierarchies may only be created in the initial cgroup namespace. */ if (ctx->ns != &init_cgroup_ns) return -EPERM; root = kzalloc(sizeof(*root), GFP_KERNEL); if (!root) return -ENOMEM; ctx->root = root; init_cgroup_root(ctx); ret = cgroup_setup_root(root, ctx->subsys_mask); if (ret) cgroup_free_root(root); return ret; } int cgroup1_get_tree(struct fs_context *fc) { struct cgroup_fs_context *ctx = cgroup_fc2context(fc); int ret; /* Check if the caller has permission to mount. */ if (!ns_capable(ctx->ns->user_ns, CAP_SYS_ADMIN)) return -EPERM; cgroup_lock_and_drain_offline(&cgrp_dfl_root.cgrp); ret = cgroup1_root_to_use(fc); if (!ret && !percpu_ref_tryget_live(&ctx->root->cgrp.self.refcnt)) ret = 1; /* restart */ mutex_unlock(&cgroup_mutex); if (!ret) ret = cgroup_do_get_tree(fc); if (!ret && percpu_ref_is_dying(&ctx->root->cgrp.self.refcnt)) { fc_drop_locked(fc); ret = 1; } if (unlikely(ret > 0)) { msleep(10); return restart_syscall(); } return ret; } static int __init cgroup1_wq_init(void) { /* * Used to destroy pidlists and separate to serve as flush domain. * Cap @max_active to 1 too. */ cgroup_pidlist_destroy_wq = alloc_workqueue("cgroup_pidlist_destroy", 0, 1); BUG_ON(!cgroup_pidlist_destroy_wq); return 0; } core_initcall(cgroup1_wq_init); static int __init cgroup_no_v1(char *str) { struct cgroup_subsys *ss; char *token; int i; while ((token = strsep(&str, ",")) != NULL) { if (!*token) continue; if (!strcmp(token, "all")) { cgroup_no_v1_mask = U16_MAX; continue; } if (!strcmp(token, "named")) { cgroup_no_v1_named = true; continue; } for_each_subsys(ss, i) { if (strcmp(token, ss->name) && strcmp(token, ss->legacy_name)) continue; cgroup_no_v1_mask |= 1 << i; } } return 1; } __setup("cgroup_no_v1=", cgroup_no_v1); |
| 14 14 2 12 12 12 12 16 14 14 27 28 12 14 16 16 16 16 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 2015-2019 Jason A. Donenfeld <Jason@zx2c4.com>. All Rights Reserved. */ #include "queueing.h" #include "timers.h" #include "device.h" #include "peer.h" #include "socket.h" #include "messages.h" #include "cookie.h" #include <linux/uio.h> #include <linux/inetdevice.h> #include <linux/socket.h> #include <net/ip_tunnels.h> #include <net/udp.h> #include <net/sock.h> static void wg_packet_send_handshake_initiation(struct wg_peer *peer) { struct message_handshake_initiation packet; if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT)) return; /* This function is rate limited. */ atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake initiation to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_initiation(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); wg_timers_handshake_initiated(peer); } } void wg_packet_handshake_send_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_handshake_work); wg_packet_send_handshake_initiation(peer); wg_peer_put(peer); } void wg_packet_send_queued_handshake_initiation(struct wg_peer *peer, bool is_retry) { if (!is_retry) peer->timer_handshake_attempts = 0; rcu_read_lock_bh(); /* We check last_sent_handshake here in addition to the actual function * we're queueing up, so that we don't queue things if not strictly * necessary: */ if (!wg_birthdate_has_expired(atomic64_read(&peer->last_sent_handshake), REKEY_TIMEOUT) || unlikely(READ_ONCE(peer->is_dead))) goto out; wg_peer_get(peer); /* Queues up calling packet_send_queued_handshakes(peer), where we do a * peer_put(peer) after: */ if (!queue_work(peer->device->handshake_send_wq, &peer->transmit_handshake_work)) /* If the work was already queued, we want to drop the * extra reference: */ wg_peer_put(peer); out: rcu_read_unlock_bh(); } void wg_packet_send_handshake_response(struct wg_peer *peer) { struct message_handshake_response packet; atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); net_dbg_ratelimited("%s: Sending handshake response to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); if (wg_noise_handshake_create_response(&packet, &peer->handshake)) { wg_cookie_add_mac_to_packet(&packet, sizeof(packet), peer); if (wg_noise_handshake_begin_session(&peer->handshake, &peer->keypairs)) { wg_timers_session_derived(peer); wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); atomic64_set(&peer->last_sent_handshake, ktime_get_coarse_boottime_ns()); wg_socket_send_buffer_to_peer(peer, &packet, sizeof(packet), HANDSHAKE_DSCP); } } } void wg_packet_send_handshake_cookie(struct wg_device *wg, struct sk_buff *initiating_skb, __le32 sender_index) { struct message_handshake_cookie packet; net_dbg_skb_ratelimited("%s: Sending cookie response for denied handshake message for %pISpfsc\n", wg->dev->name, initiating_skb); wg_cookie_message_create(&packet, initiating_skb, sender_index, &wg->cookie_checker); wg_socket_send_buffer_as_reply_to_skb(wg, initiating_skb, &packet, sizeof(packet)); } static void keep_key_fresh(struct wg_peer *peer) { struct noise_keypair *keypair; bool send; rcu_read_lock_bh(); keypair = rcu_dereference_bh(peer->keypairs.current_keypair); send = keypair && READ_ONCE(keypair->sending.is_valid) && (atomic64_read(&keypair->sending_counter) > REKEY_AFTER_MESSAGES || (keypair->i_am_the_initiator && wg_birthdate_has_expired(keypair->sending.birthdate, REKEY_AFTER_TIME))); rcu_read_unlock_bh(); if (unlikely(send)) wg_packet_send_queued_handshake_initiation(peer, false); } static unsigned int calculate_skb_padding(struct sk_buff *skb) { unsigned int padded_size, last_unit = skb->len; if (unlikely(!PACKET_CB(skb)->mtu)) return ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE) - last_unit; /* We do this modulo business with the MTU, just in case the networking * layer gives us a packet that's bigger than the MTU. In that case, we * wouldn't want the final subtraction to overflow in the case of the * padded_size being clamped. Fortunately, that's very rarely the case, * so we optimize for that not happening. */ if (unlikely(last_unit > PACKET_CB(skb)->mtu)) last_unit %= PACKET_CB(skb)->mtu; padded_size = min(PACKET_CB(skb)->mtu, ALIGN(last_unit, MESSAGE_PADDING_MULTIPLE)); return padded_size - last_unit; } static bool encrypt_packet(struct sk_buff *skb, struct noise_keypair *keypair) { unsigned int padding_len, plaintext_len, trailer_len; struct scatterlist sg[MAX_SKB_FRAGS + 8]; struct message_data *header; struct sk_buff *trailer; int num_frags; /* Force hash calculation before encryption so that flow analysis is * consistent over the inner packet. */ skb_get_hash(skb); /* Calculate lengths. */ padding_len = calculate_skb_padding(skb); trailer_len = padding_len + noise_encrypted_len(0); plaintext_len = skb->len + padding_len; /* Expand data section to have room for padding and auth tag. */ num_frags = skb_cow_data(skb, trailer_len, &trailer); if (unlikely(num_frags < 0 || num_frags > ARRAY_SIZE(sg))) return false; /* Set the padding to zeros, and make sure it and the auth tag are part * of the skb. */ memset(skb_tail_pointer(trailer), 0, padding_len); /* Expand head section to have room for our header and the network * stack's headers. */ if (unlikely(skb_cow_head(skb, DATA_PACKET_HEAD_ROOM) < 0)) return false; /* Finalize checksum calculation for the inner packet, if required. */ if (unlikely(skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb))) return false; /* Only after checksumming can we safely add on the padding at the end * and the header. */ skb_set_inner_network_header(skb, 0); header = (struct message_data *)skb_push(skb, sizeof(*header)); header->header.type = cpu_to_le32(MESSAGE_DATA); header->key_idx = keypair->remote_index; header->counter = cpu_to_le64(PACKET_CB(skb)->nonce); pskb_put(skb, trailer, trailer_len); /* Now we can encrypt the scattergather segments */ sg_init_table(sg, num_frags); if (skb_to_sgvec(skb, sg, sizeof(struct message_data), noise_encrypted_len(plaintext_len)) <= 0) return false; return chacha20poly1305_encrypt_sg_inplace(sg, plaintext_len, NULL, 0, PACKET_CB(skb)->nonce, keypair->sending.key); } void wg_packet_send_keepalive(struct wg_peer *peer) { struct sk_buff *skb; if (skb_queue_empty_lockless(&peer->staged_packet_queue)) { skb = alloc_skb(DATA_PACKET_HEAD_ROOM + MESSAGE_MINIMUM_LENGTH, GFP_ATOMIC); if (unlikely(!skb)) return; skb_reserve(skb, DATA_PACKET_HEAD_ROOM); skb->dev = peer->device->dev; PACKET_CB(skb)->mtu = skb->dev->mtu; skb_queue_tail(&peer->staged_packet_queue, skb); net_dbg_ratelimited("%s: Sending keepalive packet to peer %llu (%pISpfsc)\n", peer->device->dev->name, peer->internal_id, &peer->endpoint.addr); } wg_packet_send_staged_packets(peer); } static void wg_packet_create_data_done(struct wg_peer *peer, struct sk_buff *first) { struct sk_buff *skb, *next; bool is_keepalive, data_sent = false; wg_timers_any_authenticated_packet_traversal(peer); wg_timers_any_authenticated_packet_sent(peer); skb_list_walk_safe(first, skb, next) { is_keepalive = skb->len == message_data_len(0); if (likely(!wg_socket_send_skb_to_peer(peer, skb, PACKET_CB(skb)->ds) && !is_keepalive)) data_sent = true; } if (likely(data_sent)) wg_timers_data_sent(peer); keep_key_fresh(peer); } void wg_packet_tx_worker(struct work_struct *work) { struct wg_peer *peer = container_of(work, struct wg_peer, transmit_packet_work); struct noise_keypair *keypair; enum packet_state state; struct sk_buff *first; while ((first = wg_prev_queue_peek(&peer->tx_queue)) != NULL && (state = atomic_read_acquire(&PACKET_CB(first)->state)) != PACKET_STATE_UNCRYPTED) { wg_prev_queue_drop_peeked(&peer->tx_queue); keypair = PACKET_CB(first)->keypair; if (likely(state == PACKET_STATE_CRYPTED)) wg_packet_create_data_done(peer, first); else kfree_skb_list(first); wg_noise_keypair_put(keypair, false); wg_peer_put(peer); if (need_resched()) cond_resched(); } } void wg_packet_encrypt_worker(struct work_struct *work) { struct crypt_queue *queue = container_of(work, struct multicore_worker, work)->ptr; struct sk_buff *first, *skb, *next; while ((first = ptr_ring_consume_bh(&queue->ring)) != NULL) { enum packet_state state = PACKET_STATE_CRYPTED; skb_list_walk_safe(first, skb, next) { if (likely(encrypt_packet(skb, PACKET_CB(first)->keypair))) { wg_reset_packet(skb, true); } else { state = PACKET_STATE_DEAD; break; } } wg_queue_enqueue_per_peer_tx(first, state); if (need_resched()) cond_resched(); } } static void wg_packet_create_data(struct wg_peer *peer, struct sk_buff *first) { struct wg_device *wg = peer->device; int ret = -EINVAL; rcu_read_lock_bh(); if (unlikely(READ_ONCE(peer->is_dead))) goto err; ret = wg_queue_enqueue_per_device_and_peer(&wg->encrypt_queue, &peer->tx_queue, first, wg->packet_crypt_wq); if (unlikely(ret == -EPIPE)) wg_queue_enqueue_per_peer_tx(first, PACKET_STATE_DEAD); err: rcu_read_unlock_bh(); if (likely(!ret || ret == -EPIPE)) return; wg_noise_keypair_put(PACKET_CB(first)->keypair, false); wg_peer_put(peer); kfree_skb_list(first); } void wg_packet_purge_staged_packets(struct wg_peer *peer) { spin_lock_bh(&peer->staged_packet_queue.lock); peer->device->dev->stats.tx_dropped += peer->staged_packet_queue.qlen; __skb_queue_purge(&peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); } void wg_packet_send_staged_packets(struct wg_peer *peer) { struct noise_keypair *keypair; struct sk_buff_head packets; struct sk_buff *skb; /* Steal the current queue into our local one. */ __skb_queue_head_init(&packets); spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice_init(&peer->staged_packet_queue, &packets); spin_unlock_bh(&peer->staged_packet_queue.lock); if (unlikely(skb_queue_empty(&packets))) return; /* First we make sure we have a valid reference to a valid key. */ rcu_read_lock_bh(); keypair = wg_noise_keypair_get( rcu_dereference_bh(peer->keypairs.current_keypair)); rcu_read_unlock_bh(); if (unlikely(!keypair)) goto out_nokey; if (unlikely(!READ_ONCE(keypair->sending.is_valid))) goto out_nokey; if (unlikely(wg_birthdate_has_expired(keypair->sending.birthdate, REJECT_AFTER_TIME))) goto out_invalid; /* After we know we have a somewhat valid key, we now try to assign * nonces to all of the packets in the queue. If we can't assign nonces * for all of them, we just consider it a failure and wait for the next * handshake. */ skb_queue_walk(&packets, skb) { /* 0 for no outer TOS: no leak. TODO: at some later point, we * might consider using flowi->tos as outer instead. */ PACKET_CB(skb)->ds = ip_tunnel_ecn_encap(0, ip_hdr(skb), skb); PACKET_CB(skb)->nonce = atomic64_inc_return(&keypair->sending_counter) - 1; if (unlikely(PACKET_CB(skb)->nonce >= REJECT_AFTER_MESSAGES)) goto out_invalid; } packets.prev->next = NULL; wg_peer_get(keypair->entry.peer); PACKET_CB(packets.next)->keypair = keypair; wg_packet_create_data(peer, packets.next); return; out_invalid: WRITE_ONCE(keypair->sending.is_valid, false); out_nokey: wg_noise_keypair_put(keypair, false); /* We orphan the packets if we're waiting on a handshake, so that they * don't block a socket's pool. */ skb_queue_walk(&packets, skb) skb_orphan(skb); /* Then we put them back on the top of the queue. We're not too * concerned about accidentally getting things a little out of order if * packets are being added really fast, because this queue is for before * packets can even be sent and it's small anyway. */ spin_lock_bh(&peer->staged_packet_queue.lock); skb_queue_splice(&packets, &peer->staged_packet_queue); spin_unlock_bh(&peer->staged_packet_queue.lock); /* If we're exiting because there's something wrong with the key, it * means we should initiate a new handshake. */ wg_packet_send_queued_handshake_initiation(peer, false); } |
| 24 9 50 42 197 165 32 197 137 136 56 137 56 50 37 12 32 32 32 241 241 242 241 2 2 238 6 2 225 216 200 14 2 5 142 71 3 140 69 2 15 191 206 11 161 32 705 707 243 94 311 76 307 71 309 31 42 11 2 25 13 38 38 4 5 4 5 37 4 19 2 13 28 15 22 9 28 17 11 61 61 61 46 46 61 3 3 5 41 2 11 16 1 5 8 26 36 1 36 36 2 2 34 30 5 3 2 33 1 32 30 10 9 24 37 37 4 11 6 21 41 1 13 29 40 9 10 25 13 5 91 76 26 26 77 63 35 6 6 56 6 50 81 65 16 163 89 81 81 31 21 11 11 11 76 41 37 20 1 19 6 6 32 21 11 13 4 8 2 18 8 1 12 2 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/bpf.h> #include <linux/btf.h> #include <linux/jhash.h> #include <linux/filter.h> #include <linux/rculist_nulls.h> #include <linux/random.h> #include <uapi/linux/btf.h> #include "percpu_freelist.h" #include "bpf_lru_list.h" #include "map_in_map.h" #define HTAB_CREATE_FLAG_MASK \ (BPF_F_NO_PREALLOC | BPF_F_NO_COMMON_LRU | BPF_F_NUMA_NODE | \ BPF_F_ACCESS_MASK | BPF_F_ZERO_SEED) struct bucket { struct hlist_nulls_head head; raw_spinlock_t lock; }; struct bpf_htab { struct bpf_map map; struct bucket *buckets; void *elems; union { struct pcpu_freelist freelist; struct bpf_lru lru; }; struct htab_elem *__percpu *extra_elems; atomic_t count; /* number of elements in this hashtable */ u32 n_buckets; /* number of hash buckets */ u32 elem_size; /* size of each element in bytes */ u32 hashrnd; }; /* each htab element is struct htab_elem + key + value */ struct htab_elem { union { struct hlist_nulls_node hash_node; struct { void *padding; union { struct bpf_htab *htab; struct pcpu_freelist_node fnode; }; }; }; union { struct rcu_head rcu; struct bpf_lru_node lru_node; }; u32 hash; char key[0] __aligned(8); }; static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node); static bool htab_is_lru(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_LRU_HASH || htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } static bool htab_is_percpu(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH || htab->map.map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH; } static bool htab_is_prealloc(const struct bpf_htab *htab) { return !(htab->map.map_flags & BPF_F_NO_PREALLOC); } static inline void htab_elem_set_ptr(struct htab_elem *l, u32 key_size, void __percpu *pptr) { *(void __percpu **)(l->key + key_size) = pptr; } static inline void __percpu *htab_elem_get_ptr(struct htab_elem *l, u32 key_size) { return *(void __percpu **)(l->key + key_size); } static void *fd_htab_map_get_ptr(const struct bpf_map *map, struct htab_elem *l) { return *(void **)(l->key + roundup(map->key_size, 8)); } static struct htab_elem *get_htab_elem(struct bpf_htab *htab, int i) { return (struct htab_elem *) (htab->elems + i * htab->elem_size); } static void htab_free_elems(struct bpf_htab *htab) { int i; if (!htab_is_percpu(htab)) goto free_elems; for (i = 0; i < htab->map.max_entries; i++) { void __percpu *pptr; pptr = htab_elem_get_ptr(get_htab_elem(htab, i), htab->map.key_size); free_percpu(pptr); cond_resched(); } free_elems: bpf_map_area_free(htab->elems); } static struct htab_elem *prealloc_lru_pop(struct bpf_htab *htab, void *key, u32 hash) { struct bpf_lru_node *node = bpf_lru_pop_free(&htab->lru, hash); struct htab_elem *l; if (node) { l = container_of(node, struct htab_elem, lru_node); memcpy(l->key, key, htab->map.key_size); return l; } return NULL; } static int prealloc_init(struct bpf_htab *htab) { u32 num_entries = htab->map.max_entries; int err = -ENOMEM, i; if (!htab_is_percpu(htab) && !htab_is_lru(htab)) num_entries += num_possible_cpus(); htab->elems = bpf_map_area_alloc(htab->elem_size * num_entries, htab->map.numa_node); if (!htab->elems) return -ENOMEM; if (!htab_is_percpu(htab)) goto skip_percpu_elems; for (i = 0; i < num_entries; i++) { u32 size = round_up(htab->map.value_size, 8); void __percpu *pptr; pptr = __alloc_percpu_gfp(size, 8, GFP_USER | __GFP_NOWARN); if (!pptr) goto free_elems; htab_elem_set_ptr(get_htab_elem(htab, i), htab->map.key_size, pptr); cond_resched(); } skip_percpu_elems: if (htab_is_lru(htab)) err = bpf_lru_init(&htab->lru, htab->map.map_flags & BPF_F_NO_COMMON_LRU, offsetof(struct htab_elem, hash) - offsetof(struct htab_elem, lru_node), htab_lru_map_delete_node, htab); else err = pcpu_freelist_init(&htab->freelist); if (err) goto free_elems; if (htab_is_lru(htab)) bpf_lru_populate(&htab->lru, htab->elems, offsetof(struct htab_elem, lru_node), htab->elem_size, num_entries); else pcpu_freelist_populate(&htab->freelist, htab->elems + offsetof(struct htab_elem, fnode), htab->elem_size, num_entries); return 0; free_elems: htab_free_elems(htab); return err; } static void prealloc_destroy(struct bpf_htab *htab) { htab_free_elems(htab); if (htab_is_lru(htab)) bpf_lru_destroy(&htab->lru); else pcpu_freelist_destroy(&htab->freelist); } static int alloc_extra_elems(struct bpf_htab *htab) { struct htab_elem *__percpu *pptr, *l_new; struct pcpu_freelist_node *l; int cpu; pptr = __alloc_percpu_gfp(sizeof(struct htab_elem *), 8, GFP_USER | __GFP_NOWARN); if (!pptr) return -ENOMEM; for_each_possible_cpu(cpu) { l = pcpu_freelist_pop(&htab->freelist); /* pop will succeed, since prealloc_init() * preallocated extra num_possible_cpus elements */ l_new = container_of(l, struct htab_elem, fnode); *per_cpu_ptr(pptr, cpu) = l_new; } htab->extra_elems = pptr; return 0; } /* Called from syscall */ static int htab_map_alloc_check(union bpf_attr *attr) { bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH || attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); /* percpu_lru means each cpu has its own LRU list. * it is different from BPF_MAP_TYPE_PERCPU_HASH where * the map's value itself is percpu. percpu_lru has * nothing to do with the map's value. */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); bool zero_seed = (attr->map_flags & BPF_F_ZERO_SEED); int numa_node = bpf_map_attr_numa_node(attr); BUILD_BUG_ON(offsetof(struct htab_elem, htab) != offsetof(struct htab_elem, hash_node.pprev)); BUILD_BUG_ON(offsetof(struct htab_elem, fnode.next) != offsetof(struct htab_elem, hash_node.pprev)); if (lru && !capable(CAP_SYS_ADMIN)) /* LRU implementation is much complicated than other * maps. Hence, limit to CAP_SYS_ADMIN for now. */ return -EPERM; if (zero_seed && !capable(CAP_SYS_ADMIN)) /* Guard against local DoS, and discourage production use. */ return -EPERM; if (attr->map_flags & ~HTAB_CREATE_FLAG_MASK || !bpf_map_flags_access_ok(attr->map_flags)) return -EINVAL; if (!lru && percpu_lru) return -EINVAL; if (lru && !prealloc) return -ENOTSUPP; if (numa_node != NUMA_NO_NODE && (percpu || percpu_lru)) return -EINVAL; /* check sanity of attributes. * value_size == 0 may be allowed in the future to use map as a set */ if (attr->max_entries == 0 || attr->key_size == 0 || attr->value_size == 0) return -EINVAL; if (attr->key_size > MAX_BPF_STACK) /* eBPF programs initialize keys on stack, so they cannot be * larger than max stack size */ return -E2BIG; if (attr->value_size >= KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct htab_elem)) /* if value_size is bigger, the user space won't be able to * access the elements via bpf syscall. This check also makes * sure that the elem_size doesn't overflow and it's * kmalloc-able later in htab_map_update_elem() */ return -E2BIG; /* percpu map value size is bound by PCPU_MIN_UNIT_SIZE */ if (percpu && round_up(attr->value_size, 8) > PCPU_MIN_UNIT_SIZE) return -E2BIG; return 0; } static struct bpf_map *htab_map_alloc(union bpf_attr *attr) { bool percpu = (attr->map_type == BPF_MAP_TYPE_PERCPU_HASH || attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); bool lru = (attr->map_type == BPF_MAP_TYPE_LRU_HASH || attr->map_type == BPF_MAP_TYPE_LRU_PERCPU_HASH); /* percpu_lru means each cpu has its own LRU list. * it is different from BPF_MAP_TYPE_PERCPU_HASH where * the map's value itself is percpu. percpu_lru has * nothing to do with the map's value. */ bool percpu_lru = (attr->map_flags & BPF_F_NO_COMMON_LRU); bool prealloc = !(attr->map_flags & BPF_F_NO_PREALLOC); struct bpf_htab *htab; int err, i; u64 cost; htab = kzalloc(sizeof(*htab), GFP_USER); if (!htab) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&htab->map, attr); if (percpu_lru) { /* ensure each CPU's lru list has >=1 elements. * since we are at it, make each lru list has the same * number of elements. */ htab->map.max_entries = roundup(attr->max_entries, num_possible_cpus()); if (htab->map.max_entries < attr->max_entries) htab->map.max_entries = rounddown(attr->max_entries, num_possible_cpus()); } /* hash table size must be power of 2; roundup_pow_of_two() can overflow * into UB on 32-bit arches, so check that first */ err = -E2BIG; if (htab->map.max_entries > 1UL << 31) goto free_htab; htab->n_buckets = roundup_pow_of_two(htab->map.max_entries); htab->elem_size = sizeof(struct htab_elem) + round_up(htab->map.key_size, 8); if (percpu) htab->elem_size += sizeof(void *); else htab->elem_size += round_up(htab->map.value_size, 8); /* check for u32 overflow */ if (htab->n_buckets > U32_MAX / sizeof(struct bucket)) goto free_htab; cost = (u64) htab->n_buckets * sizeof(struct bucket) + (u64) htab->elem_size * htab->map.max_entries; if (percpu) cost += (u64) round_up(htab->map.value_size, 8) * num_possible_cpus() * htab->map.max_entries; else cost += (u64) htab->elem_size * num_possible_cpus(); /* if map size is larger than memlock limit, reject it */ err = bpf_map_charge_init(&htab->map.memory, cost); if (err) goto free_htab; err = -ENOMEM; htab->buckets = bpf_map_area_alloc(htab->n_buckets * sizeof(struct bucket), htab->map.numa_node); if (!htab->buckets) goto free_charge; if (htab->map.map_flags & BPF_F_ZERO_SEED) htab->hashrnd = 0; else htab->hashrnd = get_random_int(); for (i = 0; i < htab->n_buckets; i++) { INIT_HLIST_NULLS_HEAD(&htab->buckets[i].head, i); raw_spin_lock_init(&htab->buckets[i].lock); } if (prealloc) { err = prealloc_init(htab); if (err) goto free_buckets; if (!percpu && !lru) { /* lru itself can remove the least used element, so * there is no need for an extra elem during map_update. */ err = alloc_extra_elems(htab); if (err) goto free_prealloc; } } return &htab->map; free_prealloc: prealloc_destroy(htab); free_buckets: bpf_map_area_free(htab->buckets); free_charge: bpf_map_charge_finish(&htab->map.memory); free_htab: kfree(htab); return ERR_PTR(err); } static inline u32 htab_map_hash(const void *key, u32 key_len, u32 hashrnd) { return jhash(key, key_len, hashrnd); } static inline struct bucket *__select_bucket(struct bpf_htab *htab, u32 hash) { return &htab->buckets[hash & (htab->n_buckets - 1)]; } static inline struct hlist_nulls_head *select_bucket(struct bpf_htab *htab, u32 hash) { return &__select_bucket(htab, hash)->head; } /* this lookup function can only be called with bucket lock taken */ static struct htab_elem *lookup_elem_raw(struct hlist_nulls_head *head, u32 hash, void *key, u32 key_size) { struct hlist_nulls_node *n; struct htab_elem *l; hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l->hash == hash && !memcmp(&l->key, key, key_size)) return l; return NULL; } /* can be called without bucket lock. it will repeat the loop in * the unlikely event when elements moved from one bucket into another * while link list is being walked */ static struct htab_elem *lookup_nulls_elem_raw(struct hlist_nulls_head *head, u32 hash, void *key, u32 key_size, u32 n_buckets) { struct hlist_nulls_node *n; struct htab_elem *l; again: hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l->hash == hash && !memcmp(&l->key, key, key_size)) return l; if (unlikely(get_nulls_value(n) != (hash & (n_buckets - 1)))) goto again; return NULL; } /* Called from syscall or from eBPF program directly, so * arguments have to match bpf_map_lookup_elem() exactly. * The return value is adjusted by BPF instructions * in htab_map_gen_lookup(). */ static void *__htab_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; struct htab_elem *l; u32 hash, key_size; /* Must be called with rcu_read_lock. */ WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); head = select_bucket(htab, hash); l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); return l; } static void *htab_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); if (l) return l->key + round_up(map->key_size, 8); return NULL; } /* inline bpf_map_lookup_elem() call. * Instead of: * bpf_prog * bpf_map_lookup_elem * map->ops->map_lookup_elem * htab_map_lookup_elem * __htab_map_lookup_elem * do: * bpf_prog * __htab_map_lookup_elem */ static u32 htab_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + round_up(map->key_size, 8)); return insn - insn_buf; } static __always_inline void *__htab_lru_map_lookup_elem(struct bpf_map *map, void *key, const bool mark) { struct htab_elem *l = __htab_map_lookup_elem(map, key); if (l) { if (mark) bpf_lru_node_set_ref(&l->lru_node); return l->key + round_up(map->key_size, 8); } return NULL; } static void *htab_lru_map_lookup_elem(struct bpf_map *map, void *key) { return __htab_lru_map_lookup_elem(map, key, true); } static void *htab_lru_map_lookup_elem_sys(struct bpf_map *map, void *key) { return __htab_lru_map_lookup_elem(map, key, false); } static u32 htab_lru_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; const int ref_reg = BPF_REG_1; BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 4); *insn++ = BPF_LDX_MEM(BPF_B, ref_reg, ret, offsetof(struct htab_elem, lru_node) + offsetof(struct bpf_lru_node, ref)); *insn++ = BPF_JMP_IMM(BPF_JNE, ref_reg, 0, 1); *insn++ = BPF_ST_MEM(BPF_B, ret, offsetof(struct htab_elem, lru_node) + offsetof(struct bpf_lru_node, ref), 1); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + round_up(map->key_size, 8)); return insn - insn_buf; } /* It is called from the bpf_lru_list when the LRU needs to delete * older elements from the htab. */ static bool htab_lru_map_delete_node(void *arg, struct bpf_lru_node *node) { struct bpf_htab *htab = (struct bpf_htab *)arg; struct htab_elem *l = NULL, *tgt_l; struct hlist_nulls_head *head; struct hlist_nulls_node *n; unsigned long flags; struct bucket *b; tgt_l = container_of(node, struct htab_elem, lru_node); b = __select_bucket(htab, tgt_l->hash); head = &b->head; raw_spin_lock_irqsave(&b->lock, flags); hlist_nulls_for_each_entry_rcu(l, n, head, hash_node) if (l == tgt_l) { hlist_nulls_del_rcu(&l->hash_node); break; } raw_spin_unlock_irqrestore(&b->lock, flags); return l == tgt_l; } /* Called from syscall */ static int htab_map_get_next_key(struct bpf_map *map, void *key, void *next_key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; struct htab_elem *l, *next_l; u32 hash, key_size; int i = 0; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; if (!key) goto find_first_elem; hash = htab_map_hash(key, key_size, htab->hashrnd); head = select_bucket(htab, hash); /* lookup the key */ l = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); if (!l) goto find_first_elem; /* key was found, get next key in the same bucket */ next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_next_rcu(&l->hash_node)), struct htab_elem, hash_node); if (next_l) { /* if next elem in this hash list is non-zero, just return it */ memcpy(next_key, next_l->key, key_size); return 0; } /* no more elements in this hash list, go to the next bucket */ i = hash & (htab->n_buckets - 1); i++; find_first_elem: /* iterate over buckets */ for (; i < htab->n_buckets; i++) { head = select_bucket(htab, i); /* pick first element in the bucket */ next_l = hlist_nulls_entry_safe(rcu_dereference_raw(hlist_nulls_first_rcu(head)), struct htab_elem, hash_node); if (next_l) { /* if it's not empty, just return it */ memcpy(next_key, next_l->key, key_size); return 0; } } /* iterated over all buckets and all elements */ return -ENOENT; } static void htab_elem_free(struct bpf_htab *htab, struct htab_elem *l) { if (htab->map.map_type == BPF_MAP_TYPE_PERCPU_HASH) free_percpu(htab_elem_get_ptr(l, htab->map.key_size)); kfree(l); } static void htab_elem_free_rcu(struct rcu_head *head) { struct htab_elem *l = container_of(head, struct htab_elem, rcu); struct bpf_htab *htab = l->htab; htab_elem_free(htab, l); } static void htab_put_fd_value(struct bpf_htab *htab, struct htab_elem *l) { struct bpf_map *map = &htab->map; void *ptr; if (map->ops->map_fd_put_ptr) { ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } } static void free_htab_elem(struct bpf_htab *htab, struct htab_elem *l) { htab_put_fd_value(htab, l); if (htab_is_prealloc(htab)) { __pcpu_freelist_push(&htab->freelist, &l->fnode); } else { atomic_dec(&htab->count); l->htab = htab; call_rcu(&l->rcu, htab_elem_free_rcu); } } static void pcpu_copy_value(struct bpf_htab *htab, void __percpu *pptr, void *value, bool onallcpus) { if (!onallcpus) { /* copy true value_size bytes */ memcpy(this_cpu_ptr(pptr), value, htab->map.value_size); } else { u32 size = round_up(htab->map.value_size, 8); int off = 0, cpu; for_each_possible_cpu(cpu) { bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value + off, size); off += size; } } } static void pcpu_init_value(struct bpf_htab *htab, void __percpu *pptr, void *value, bool onallcpus) { /* When using prealloc and not setting the initial value on all cpus, * zero-fill element values for other cpus (just as what happens when * not using prealloc). Otherwise, bpf program has no way to ensure * known initial values for cpus other than current one * (onallcpus=false always when coming from bpf prog). */ if (htab_is_prealloc(htab) && !onallcpus) { u32 size = round_up(htab->map.value_size, 8); int current_cpu = raw_smp_processor_id(); int cpu; for_each_possible_cpu(cpu) { if (cpu == current_cpu) bpf_long_memcpy(per_cpu_ptr(pptr, cpu), value, size); else memset(per_cpu_ptr(pptr, cpu), 0, size); } } else { pcpu_copy_value(htab, pptr, value, onallcpus); } } static bool fd_htab_map_needs_adjust(const struct bpf_htab *htab) { return htab->map.map_type == BPF_MAP_TYPE_HASH_OF_MAPS && BITS_PER_LONG == 64; } static struct htab_elem *alloc_htab_elem(struct bpf_htab *htab, void *key, void *value, u32 key_size, u32 hash, bool percpu, bool onallcpus, struct htab_elem *old_elem) { u32 size = htab->map.value_size; bool prealloc = htab_is_prealloc(htab); struct htab_elem *l_new, **pl_new; void __percpu *pptr; if (prealloc) { if (old_elem) { /* if we're updating the existing element, * use per-cpu extra elems to avoid freelist_pop/push */ pl_new = this_cpu_ptr(htab->extra_elems); l_new = *pl_new; htab_put_fd_value(htab, old_elem); *pl_new = old_elem; } else { struct pcpu_freelist_node *l; l = __pcpu_freelist_pop(&htab->freelist); if (!l) return ERR_PTR(-E2BIG); l_new = container_of(l, struct htab_elem, fnode); } } else { if (atomic_inc_return(&htab->count) > htab->map.max_entries) if (!old_elem) { /* when map is full and update() is replacing * old element, it's ok to allocate, since * old element will be freed immediately. * Otherwise return an error */ l_new = ERR_PTR(-E2BIG); goto dec_count; } l_new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN, htab->map.numa_node); if (!l_new) { l_new = ERR_PTR(-ENOMEM); goto dec_count; } check_and_init_map_lock(&htab->map, l_new->key + round_up(key_size, 8)); } memcpy(l_new->key, key, key_size); if (percpu) { size = round_up(size, 8); if (prealloc) { pptr = htab_elem_get_ptr(l_new, key_size); } else { /* alloc_percpu zero-fills */ pptr = __alloc_percpu_gfp(size, 8, GFP_ATOMIC | __GFP_NOWARN); if (!pptr) { kfree(l_new); l_new = ERR_PTR(-ENOMEM); goto dec_count; } } pcpu_init_value(htab, pptr, value, onallcpus); if (!prealloc) htab_elem_set_ptr(l_new, key_size, pptr); } else if (fd_htab_map_needs_adjust(htab)) { size = round_up(size, 8); memcpy(l_new->key + round_up(key_size, 8), value, size); } else { copy_map_value(&htab->map, l_new->key + round_up(key_size, 8), value); } l_new->hash = hash; return l_new; dec_count: atomic_dec(&htab->count); return l_new; } static int check_flags(struct bpf_htab *htab, struct htab_elem *l_old, u64 map_flags) { if (l_old && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) /* elem already exists */ return -EEXIST; if (!l_old && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) /* elem doesn't exist, cannot update it */ return -ENOENT; return 0; } /* Called from syscall or from eBPF program */ static int htab_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; int ret; if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST)) /* unknown flags */ return -EINVAL; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; if (unlikely(map_flags & BPF_F_LOCK)) { if (unlikely(!map_value_has_spin_lock(map))) return -EINVAL; /* find an element without taking the bucket lock */ l_old = lookup_nulls_elem_raw(head, hash, key, key_size, htab->n_buckets); ret = check_flags(htab, l_old, map_flags); if (ret) return ret; if (l_old) { /* grab the element lock and update value in place */ copy_map_value_locked(map, l_old->key + round_up(key_size, 8), value, false); return 0; } /* fall through, grab the bucket lock and lookup again. * 99.9% chance that the element won't be found, * but second lookup under lock has to be done. */ } /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); ret = check_flags(htab, l_old, map_flags); if (ret) goto err; if (unlikely(l_old && (map_flags & BPF_F_LOCK))) { /* first lookup without the bucket lock didn't find the element, * but second lookup with the bucket lock found it. * This case is highly unlikely, but has to be dealt with: * grab the element lock in addition to the bucket lock * and update element in place */ copy_map_value_locked(map, l_old->key + round_up(key_size, 8), value, false); ret = 0; goto err; } l_new = alloc_htab_elem(htab, key, value, key_size, hash, false, false, l_old); if (IS_ERR(l_new)) { /* all pre-allocated elements are in use or memory exhausted */ ret = PTR_ERR(l_new); goto err; } /* add new element to the head of the list, so that * concurrent search will find it before old elem */ hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { hlist_nulls_del_rcu(&l_old->hash_node); if (!htab_is_prealloc(htab)) free_htab_elem(htab, l_old); } ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); return ret; } static int htab_lru_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new, *l_old = NULL; struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; int ret; if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; /* For LRU, we need to alloc before taking bucket's * spinlock because getting free nodes from LRU may need * to remove older elements from htab and this removal * operation will need a bucket lock. */ l_new = prealloc_lru_pop(htab, key, hash); if (!l_new) return -ENOMEM; memcpy(l_new->key + round_up(map->key_size, 8), value, map->value_size); /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); ret = check_flags(htab, l_old, map_flags); if (ret) goto err; /* add new element to the head of the list, so that * concurrent search will find it before old elem */ hlist_nulls_add_head_rcu(&l_new->hash_node, head); if (l_old) { bpf_lru_node_set_ref(&l_new->lru_node); hlist_nulls_del_rcu(&l_old->hash_node); } ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); if (ret) bpf_lru_push_free(&htab->lru, &l_new->lru_node); else if (l_old) bpf_lru_push_free(&htab->lru, &l_old->lru_node); return ret; } static int __htab_percpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags, bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; int ret; if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); ret = check_flags(htab, l_old, map_flags); if (ret) goto err; if (l_old) { /* per-cpu hash map can update value in-place */ pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { l_new = alloc_htab_elem(htab, key, value, key_size, hash, true, onallcpus, NULL); if (IS_ERR(l_new)) { ret = PTR_ERR(l_new); goto err; } hlist_nulls_add_head_rcu(&l_new->hash_node, head); } ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); return ret; } static int __htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags, bool onallcpus) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct htab_elem *l_new = NULL, *l_old; struct hlist_nulls_head *head; unsigned long flags; struct bucket *b; u32 key_size, hash; int ret; if (unlikely(map_flags > BPF_EXIST)) /* unknown flags */ return -EINVAL; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; /* For LRU, we need to alloc before taking bucket's * spinlock because LRU's elem alloc may need * to remove older elem from htab and this removal * operation will need a bucket lock. */ if (map_flags != BPF_EXIST) { l_new = prealloc_lru_pop(htab, key, hash); if (!l_new) return -ENOMEM; } /* bpf_map_update_elem() can be called in_irq() */ raw_spin_lock_irqsave(&b->lock, flags); l_old = lookup_elem_raw(head, hash, key, key_size); ret = check_flags(htab, l_old, map_flags); if (ret) goto err; if (l_old) { bpf_lru_node_set_ref(&l_old->lru_node); /* per-cpu hash map can update value in-place */ pcpu_copy_value(htab, htab_elem_get_ptr(l_old, key_size), value, onallcpus); } else { pcpu_init_value(htab, htab_elem_get_ptr(l_new, key_size), value, onallcpus); hlist_nulls_add_head_rcu(&l_new->hash_node, head); l_new = NULL; } ret = 0; err: raw_spin_unlock_irqrestore(&b->lock, flags); if (l_new) bpf_lru_push_free(&htab->lru, &l_new->lru_node); return ret; } static int htab_percpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __htab_percpu_map_update_elem(map, key, value, map_flags, false); } static int htab_lru_percpu_map_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { return __htab_lru_percpu_map_update_elem(map, key, value, map_flags, false); } /* Called from syscall or from eBPF program */ static int htab_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; u32 hash, key_size; int ret = -ENOENT; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; raw_spin_lock_irqsave(&b->lock, flags); l = lookup_elem_raw(head, hash, key, key_size); if (l) { hlist_nulls_del_rcu(&l->hash_node); free_htab_elem(htab, l); ret = 0; } raw_spin_unlock_irqrestore(&b->lock, flags); return ret; } static int htab_lru_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_head *head; struct bucket *b; struct htab_elem *l; unsigned long flags; u32 hash, key_size; int ret = -ENOENT; WARN_ON_ONCE(!rcu_read_lock_held()); key_size = map->key_size; hash = htab_map_hash(key, key_size, htab->hashrnd); b = __select_bucket(htab, hash); head = &b->head; raw_spin_lock_irqsave(&b->lock, flags); l = lookup_elem_raw(head, hash, key, key_size); if (l) { hlist_nulls_del_rcu(&l->hash_node); ret = 0; } raw_spin_unlock_irqrestore(&b->lock, flags); if (l) bpf_lru_push_free(&htab->lru, &l->lru_node); return ret; } static void delete_all_elements(struct bpf_htab *htab) { int i; for (i = 0; i < htab->n_buckets; i++) { struct hlist_nulls_head *head = select_bucket(htab, i); struct hlist_nulls_node *n; struct htab_elem *l; hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { hlist_nulls_del_rcu(&l->hash_node); htab_elem_free(htab, l); } } } /* Called when map->refcnt goes to zero, either from workqueue or from syscall */ static void htab_map_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); /* at this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were * disconnected from events. Wait for outstanding critical sections in * these programs to complete */ synchronize_rcu(); /* some of free_htab_elem() callbacks for elements of this map may * not have executed. Wait for them. */ rcu_barrier(); if (!htab_is_prealloc(htab)) delete_all_elements(htab); else prealloc_destroy(htab); free_percpu(htab->extra_elems); bpf_map_area_free(htab->buckets); kfree(htab); } static void htab_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { void *value; rcu_read_lock(); value = htab_map_lookup_elem(map, key); if (!value) { rcu_read_unlock(); return; } btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); seq_puts(m, ": "); btf_type_seq_show(map->btf, map->btf_value_type_id, value, m); seq_puts(m, "\n"); rcu_read_unlock(); } const struct bpf_map_ops htab_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_map_lookup_elem, .map_update_elem = htab_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_gen_lookup = htab_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, }; const struct bpf_map_ops htab_lru_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_map_lookup_elem, .map_lookup_elem_sys_only = htab_lru_map_lookup_elem_sys, .map_update_elem = htab_lru_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_gen_lookup = htab_lru_map_gen_lookup, .map_seq_show_elem = htab_map_seq_show_elem, }; /* Called from eBPF program */ static void *htab_percpu_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); if (l) return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size)); else return NULL; } static void *htab_lru_percpu_map_lookup_elem(struct bpf_map *map, void *key) { struct htab_elem *l = __htab_map_lookup_elem(map, key); if (l) { bpf_lru_node_set_ref(&l->lru_node); return this_cpu_ptr(htab_elem_get_ptr(l, map->key_size)); } return NULL; } int bpf_percpu_hash_copy(struct bpf_map *map, void *key, void *value) { struct htab_elem *l; void __percpu *pptr; int ret = -ENOENT; int cpu, off = 0; u32 size; /* per_cpu areas are zero-filled and bpf programs can only * access 'value_size' of them, so copying rounded areas * will not leak any kernel data */ size = round_up(map->value_size, 8); rcu_read_lock(); l = __htab_map_lookup_elem(map, key); if (!l) goto out; /* We do not mark LRU map element here in order to not mess up * eviction heuristics when user space does a map walk. */ pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { bpf_long_memcpy(value + off, per_cpu_ptr(pptr, cpu), size); off += size; } ret = 0; out: rcu_read_unlock(); return ret; } int bpf_percpu_hash_update(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); int ret; rcu_read_lock(); if (htab_is_lru(htab)) ret = __htab_lru_percpu_map_update_elem(map, key, value, map_flags, true); else ret = __htab_percpu_map_update_elem(map, key, value, map_flags, true); rcu_read_unlock(); return ret; } static void htab_percpu_map_seq_show_elem(struct bpf_map *map, void *key, struct seq_file *m) { struct htab_elem *l; void __percpu *pptr; int cpu; rcu_read_lock(); l = __htab_map_lookup_elem(map, key); if (!l) { rcu_read_unlock(); return; } btf_type_seq_show(map->btf, map->btf_key_type_id, key, m); seq_puts(m, ": {\n"); pptr = htab_elem_get_ptr(l, map->key_size); for_each_possible_cpu(cpu) { seq_printf(m, "\tcpu%d: ", cpu); btf_type_seq_show(map->btf, map->btf_value_type_id, per_cpu_ptr(pptr, cpu), m); seq_puts(m, "\n"); } seq_puts(m, "}\n"); rcu_read_unlock(); } const struct bpf_map_ops htab_percpu_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_percpu_map_lookup_elem, .map_update_elem = htab_percpu_map_update_elem, .map_delete_elem = htab_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; const struct bpf_map_ops htab_lru_percpu_map_ops = { .map_alloc_check = htab_map_alloc_check, .map_alloc = htab_map_alloc, .map_free = htab_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_lru_percpu_map_lookup_elem, .map_update_elem = htab_lru_percpu_map_update_elem, .map_delete_elem = htab_lru_map_delete_elem, .map_seq_show_elem = htab_percpu_map_seq_show_elem, }; static int fd_htab_map_alloc_check(union bpf_attr *attr) { if (attr->value_size != sizeof(u32)) return -EINVAL; return htab_map_alloc_check(attr); } static void fd_htab_map_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct hlist_nulls_node *n; struct hlist_nulls_head *head; struct htab_elem *l; int i; for (i = 0; i < htab->n_buckets; i++) { head = select_bucket(htab, i); hlist_nulls_for_each_entry_safe(l, n, head, hash_node) { void *ptr = fd_htab_map_get_ptr(map, l); map->ops->map_fd_put_ptr(ptr); } } htab_map_free(map); } /* only called from syscall */ int bpf_fd_htab_map_lookup_elem(struct bpf_map *map, void *key, u32 *value) { void **ptr; int ret = 0; if (!map->ops->map_fd_sys_lookup_elem) return -ENOTSUPP; rcu_read_lock(); ptr = htab_map_lookup_elem(map, key); if (ptr) *value = map->ops->map_fd_sys_lookup_elem(READ_ONCE(*ptr)); else ret = -ENOENT; rcu_read_unlock(); return ret; } /* only called from syscall */ int bpf_fd_htab_map_update_elem(struct bpf_map *map, struct file *map_file, void *key, void *value, u64 map_flags) { void *ptr; int ret; u32 ufd = *(u32 *)value; ptr = map->ops->map_fd_get_ptr(map, map_file, ufd); if (IS_ERR(ptr)) return PTR_ERR(ptr); ret = htab_map_update_elem(map, key, &ptr, map_flags); if (ret) map->ops->map_fd_put_ptr(ptr); return ret; } static struct bpf_map *htab_of_map_alloc(union bpf_attr *attr) { struct bpf_map *map, *inner_map_meta; inner_map_meta = bpf_map_meta_alloc(attr->inner_map_fd); if (IS_ERR(inner_map_meta)) return inner_map_meta; map = htab_map_alloc(attr); if (IS_ERR(map)) { bpf_map_meta_free(inner_map_meta); return map; } map->inner_map_meta = inner_map_meta; return map; } static void *htab_of_map_lookup_elem(struct bpf_map *map, void *key) { struct bpf_map **inner_map = htab_map_lookup_elem(map, key); if (!inner_map) return NULL; return READ_ONCE(*inner_map); } static u32 htab_of_map_gen_lookup(struct bpf_map *map, struct bpf_insn *insn_buf) { struct bpf_insn *insn = insn_buf; const int ret = BPF_REG_0; BUILD_BUG_ON(!__same_type(&__htab_map_lookup_elem, (void *(*)(struct bpf_map *map, void *key))NULL)); *insn++ = BPF_EMIT_CALL(BPF_CAST_CALL(__htab_map_lookup_elem)); *insn++ = BPF_JMP_IMM(BPF_JEQ, ret, 0, 2); *insn++ = BPF_ALU64_IMM(BPF_ADD, ret, offsetof(struct htab_elem, key) + round_up(map->key_size, 8)); *insn++ = BPF_LDX_MEM(BPF_DW, ret, ret, 0); return insn - insn_buf; } static void htab_of_map_free(struct bpf_map *map) { bpf_map_meta_free(map->inner_map_meta); fd_htab_map_free(map); } const struct bpf_map_ops htab_of_maps_map_ops = { .map_alloc_check = fd_htab_map_alloc_check, .map_alloc = htab_of_map_alloc, .map_free = htab_of_map_free, .map_get_next_key = htab_map_get_next_key, .map_lookup_elem = htab_of_map_lookup_elem, .map_delete_elem = htab_map_delete_elem, .map_fd_get_ptr = bpf_map_fd_get_ptr, .map_fd_put_ptr = bpf_map_fd_put_ptr, .map_fd_sys_lookup_elem = bpf_map_fd_sys_lookup_elem, .map_gen_lookup = htab_of_map_gen_lookup, .map_check_btf = map_check_no_btf, }; |
| 316 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _X_TABLES_H #define _X_TABLES_H #include <linux/netdevice.h> #include <linux/static_key.h> #include <linux/netfilter.h> #include <uapi/linux/netfilter/x_tables.h> /* Test a struct->invflags and a boolean for inequality */ #define NF_INVF(ptr, flag, boolean) \ ((boolean) ^ !!((ptr)->invflags & (flag))) /** * struct xt_action_param - parameters for matches/targets * * @match: the match extension * @target: the target extension * @matchinfo: per-match data * @targetinfo: per-target data * @state: pointer to hook state this packet came from * @fragoff: packet is a fragment, this is the data offset * @thoff: position of transport header relative to skb->data * * Fields written to by extensions: * * @hotdrop: drop packet if we had inspection problems */ struct xt_action_param { union { const struct xt_match *match; const struct xt_target *target; }; union { const void *matchinfo, *targinfo; }; const struct nf_hook_state *state; int fragoff; unsigned int thoff; bool hotdrop; }; static inline struct net *xt_net(const struct xt_action_param *par) { return par->state->net; } static inline struct net_device *xt_in(const struct xt_action_param *par) { return par->state->in; } static inline const char *xt_inname(const struct xt_action_param *par) { return par->state->in->name; } static inline struct net_device *xt_out(const struct xt_action_param *par) { return par->state->out; } static inline const char *xt_outname(const struct xt_action_param *par) { return par->state->out->name; } static inline unsigned int xt_hooknum(const struct xt_action_param *par) { return par->state->hook; } static inline u_int8_t xt_family(const struct xt_action_param *par) { return par->state->pf; } /** * struct xt_mtchk_param - parameters for match extensions' * checkentry functions * * @net: network namespace through which the check was invoked * @table: table the rule is tried to be inserted into * @entryinfo: the family-specific rule data * (struct ipt_ip, ip6t_ip, arpt_arp or (note) ebt_entry) * @match: struct xt_match through which this function was invoked * @matchinfo: per-match data * @hook_mask: via which hooks the new rule is reachable * Other fields as above. */ struct xt_mtchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_match *match; void *matchinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /** * struct xt_mdtor_param - match destructor parameters * Fields as above. */ struct xt_mtdtor_param { struct net *net; const struct xt_match *match; void *matchinfo; u_int8_t family; }; /** * struct xt_tgchk_param - parameters for target extensions' * checkentry functions * * @entryinfo: the family-specific rule data * (struct ipt_entry, ip6t_entry, arpt_entry, ebt_entry) * * Other fields see above. */ struct xt_tgchk_param { struct net *net; const char *table; const void *entryinfo; const struct xt_target *target; void *targinfo; unsigned int hook_mask; u_int8_t family; bool nft_compat; }; /* Target destructor parameters */ struct xt_tgdtor_param { struct net *net; const struct xt_target *target; void *targinfo; u_int8_t family; }; struct xt_match { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Return true or false: return FALSE and set *hotdrop = 1 to force immediate packet drop. */ /* Arguments changed since 2.6.9, as this must now handle non-linear skb, using skb_header_pointer and skb_ip_make_writable. */ bool (*match)(const struct sk_buff *skb, struct xt_action_param *); /* Called when user tries to insert an entry of this type. */ int (*checkentry)(const struct xt_mtchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_mtdtor_param *); #ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int matchsize; unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Registration hooks for targets. */ struct xt_target { struct list_head list; const char name[XT_EXTENSION_MAXNAMELEN]; u_int8_t revision; /* Returns verdict. Argument order changed since 2.6.9, as this must now handle non-linear skbs, using skb_copy_bits and skb_ip_make_writable. */ unsigned int (*target)(struct sk_buff *skb, const struct xt_action_param *); /* Called when user tries to insert an entry of this type: hook_mask is a bitmask of hooks from which it can be called. */ /* Should return 0 on success or an error code otherwise (-Exxxx). */ int (*checkentry)(const struct xt_tgchk_param *); /* Called when entry of this type deleted. */ void (*destroy)(const struct xt_tgdtor_param *); #ifdef CONFIG_COMPAT /* Called when userspace align differs from kernel space one */ void (*compat_from_user)(void *dst, const void *src); int (*compat_to_user)(void __user *dst, const void *src); #endif /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; const char *table; unsigned int targetsize; unsigned int usersize; #ifdef CONFIG_COMPAT unsigned int compatsize; #endif unsigned int hooks; unsigned short proto; unsigned short family; }; /* Furniture shopping... */ struct xt_table { struct list_head list; /* What hooks you will enter on */ unsigned int valid_hooks; /* Man behind the curtain... */ struct xt_table_info *private; /* Set this to THIS_MODULE if you are a module, otherwise NULL */ struct module *me; u_int8_t af; /* address/protocol family */ int priority; /* hook order */ /* called when table is needed in the given netns */ int (*table_init)(struct net *net); /* A unique name... */ const char name[XT_TABLE_MAXNAMELEN]; }; #include <linux/netfilter_ipv4.h> /* The table itself */ struct xt_table_info { /* Size per table */ unsigned int size; /* Number of entries: FIXME. --RR */ unsigned int number; /* Initial number of entries. Needed for module usage count */ unsigned int initial_entries; /* Entry points and underflows */ unsigned int hook_entry[NF_INET_NUMHOOKS]; unsigned int underflow[NF_INET_NUMHOOKS]; /* * Number of user chains. Since tables cannot have loops, at most * @stacksize jumps (number of user chains) can possibly be made. */ unsigned int stacksize; void ***jumpstack; unsigned char entries[0] __aligned(8); }; int xt_register_target(struct xt_target *target); void xt_unregister_target(struct xt_target *target); int xt_register_targets(struct xt_target *target, unsigned int n); void xt_unregister_targets(struct xt_target *target, unsigned int n); int xt_register_match(struct xt_match *target); void xt_unregister_match(struct xt_match *target); int xt_register_matches(struct xt_match *match, unsigned int n); void xt_unregister_matches(struct xt_match *match, unsigned int n); int xt_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); int xt_check_table_hooks(const struct xt_table_info *info, unsigned int valid_hooks); unsigned int *xt_alloc_entry_offsets(unsigned int size); bool xt_find_jump_offset(const unsigned int *offsets, unsigned int target, unsigned int size); int xt_check_proc_name(const char *name, unsigned int size); int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto, bool inv_proto); int xt_match_to_user(const struct xt_entry_match *m, struct xt_entry_match __user *u); int xt_target_to_user(const struct xt_entry_target *t, struct xt_entry_target __user *u); int xt_data_to_user(void __user *dst, const void *src, int usersize, int size, int aligned_size); void *xt_copy_counters_from_user(const void __user *user, unsigned int len, struct xt_counters_info *info, bool compat); struct xt_counters *xt_counters_alloc(unsigned int counters); struct xt_table *xt_register_table(struct net *net, const struct xt_table *table, struct xt_table_info *bootstrap, struct xt_table_info *newinfo); void *xt_unregister_table(struct xt_table *table); struct xt_table_info *xt_replace_table(struct xt_table *table, unsigned int num_counters, struct xt_table_info *newinfo, int *error); struct xt_match *xt_find_match(u8 af, const char *name, u8 revision); struct xt_match *xt_request_find_match(u8 af, const char *name, u8 revision); struct xt_target *xt_request_find_target(u8 af, const char *name, u8 revision); int xt_find_revision(u8 af, const char *name, u8 revision, int target, int *err); struct xt_table *xt_find_table_lock(struct net *net, u_int8_t af, const char *name); struct xt_table *xt_request_find_table_lock(struct net *net, u_int8_t af, const char *name); void xt_table_unlock(struct xt_table *t); int xt_proto_init(struct net *net, u_int8_t af); void xt_proto_fini(struct net *net, u_int8_t af); struct xt_table_info *xt_alloc_table_info(unsigned int size); void xt_free_table_info(struct xt_table_info *info); /** * xt_recseq - recursive seqcount for netfilter use * * Packet processing changes the seqcount only if no recursion happened * get_counters() can use read_seqcount_begin()/read_seqcount_retry(), * because we use the normal seqcount convention : * Low order bit set to 1 if a writer is active. */ DECLARE_PER_CPU(seqcount_t, xt_recseq); /* xt_tee_enabled - true if x_tables needs to handle reentrancy * * Enabled if current ip(6)tables ruleset has at least one -j TEE rule. */ extern struct static_key xt_tee_enabled; /** * xt_write_recseq_begin - start of a write section * * Begin packet processing : all readers must wait the end * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) * Returns : * 1 if no recursion on this cpu * 0 if recursion detected */ static inline unsigned int xt_write_recseq_begin(void) { unsigned int addend; /* * Low order bit of sequence is set if we already * called xt_write_recseq_begin(). */ addend = (__this_cpu_read(xt_recseq.sequence) + 1) & 1; /* * This is kind of a write_seqcount_begin(), but addend is 0 or 1 * We dont check addend value to avoid a test and conditional jump, * since addend is most likely 1 */ __this_cpu_add(xt_recseq.sequence, addend); smp_mb(); return addend; } /** * xt_write_recseq_end - end of a write section * @addend: return value from previous xt_write_recseq_begin() * * End packet processing : all readers can proceed * 1) Must be called with preemption disabled * 2) softirqs must be disabled too (or we should use this_cpu_add()) */ static inline void xt_write_recseq_end(unsigned int addend) { /* this is kind of a write_seqcount_end(), but addend is 0 or 1 */ smp_wmb(); __this_cpu_add(xt_recseq.sequence, addend); } /* * This helper is performance critical and must be inlined */ static inline unsigned long ifname_compare_aligned(const char *_a, const char *_b, const char *_mask) { const unsigned long *a = (const unsigned long *)_a; const unsigned long *b = (const unsigned long *)_b; const unsigned long *mask = (const unsigned long *)_mask; unsigned long ret; ret = (a[0] ^ b[0]) & mask[0]; if (IFNAMSIZ > sizeof(unsigned long)) ret |= (a[1] ^ b[1]) & mask[1]; if (IFNAMSIZ > 2 * sizeof(unsigned long)) ret |= (a[2] ^ b[2]) & mask[2]; if (IFNAMSIZ > 3 * sizeof(unsigned long)) ret |= (a[3] ^ b[3]) & mask[3]; BUILD_BUG_ON(IFNAMSIZ > 4 * sizeof(unsigned long)); return ret; } struct xt_percpu_counter_alloc_state { unsigned int off; const char __percpu *mem; }; bool xt_percpu_counter_alloc(struct xt_percpu_counter_alloc_state *state, struct xt_counters *counter); void xt_percpu_counter_free(struct xt_counters *cnt); static inline struct xt_counters * xt_get_this_cpu_counter(struct xt_counters *cnt) { if (nr_cpu_ids > 1) return this_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt); return cnt; } static inline struct xt_counters * xt_get_per_cpu_counter(struct xt_counters *cnt, unsigned int cpu) { if (nr_cpu_ids > 1) return per_cpu_ptr((void __percpu *) (unsigned long) cnt->pcnt, cpu); return cnt; } struct nf_hook_ops *xt_hook_ops_alloc(const struct xt_table *, nf_hookfn *); #ifdef CONFIG_COMPAT #include <net/compat.h> struct compat_xt_entry_match { union { struct { u_int16_t match_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t match_size; compat_uptr_t match; } kernel; u_int16_t match_size; } u; unsigned char data[0]; }; struct compat_xt_entry_target { union { struct { u_int16_t target_size; char name[XT_FUNCTION_MAXNAMELEN - 1]; u_int8_t revision; } user; struct { u_int16_t target_size; compat_uptr_t target; } kernel; u_int16_t target_size; } u; unsigned char data[0]; }; /* FIXME: this works only on 32 bit tasks * need to change whole approach in order to calculate align as function of * current task alignment */ struct compat_xt_counters { compat_u64 pcnt, bcnt; /* Packet and byte counters */ }; struct compat_xt_counters_info { char name[XT_TABLE_MAXNAMELEN]; compat_uint_t num_counters; struct compat_xt_counters counters[0]; }; struct _compat_xt_align { __u8 u8; __u16 u16; __u32 u32; compat_u64 u64; }; #define COMPAT_XT_ALIGN(s) __ALIGN_KERNEL((s), __alignof__(struct _compat_xt_align)) void xt_compat_lock(u_int8_t af); void xt_compat_unlock(u_int8_t af); int xt_compat_add_offset(u_int8_t af, unsigned int offset, int delta); void xt_compat_flush_offsets(u_int8_t af); int xt_compat_init_offsets(u8 af, unsigned int number); int xt_compat_calc_jump(u_int8_t af, unsigned int offset); int xt_compat_match_offset(const struct xt_match *match); void xt_compat_match_from_user(struct xt_entry_match *m, void **dstptr, unsigned int *size); int xt_compat_match_to_user(const struct xt_entry_match *m, void __user **dstptr, unsigned int *size); int xt_compat_target_offset(const struct xt_target *target); void xt_compat_target_from_user(struct xt_entry_target *t, void **dstptr, unsigned int *size); int xt_compat_target_to_user(const struct xt_entry_target *t, void __user **dstptr, unsigned int *size); int xt_compat_check_entry_offsets(const void *base, const char *elems, unsigned int target_offset, unsigned int next_offset); #endif /* CONFIG_COMPAT */ #endif /* _X_TABLES_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef LINUX_MLD_H #define LINUX_MLD_H #include <linux/in6.h> #include <linux/icmpv6.h> /* MLDv1 Query/Report/Done */ struct mld_msg { struct icmp6hdr mld_hdr; struct in6_addr mld_mca; }; #define mld_type mld_hdr.icmp6_type #define mld_code mld_hdr.icmp6_code #define mld_cksum mld_hdr.icmp6_cksum #define mld_maxdelay mld_hdr.icmp6_maxdelay #define mld_reserved mld_hdr.icmp6_dataun.un_data16[1] /* Multicast Listener Discovery version 2 headers */ /* MLDv2 Report */ struct mld2_grec { __u8 grec_type; __u8 grec_auxwords; __be16 grec_nsrcs; struct in6_addr grec_mca; struct in6_addr grec_src[0]; }; struct mld2_report { struct icmp6hdr mld2r_hdr; struct mld2_grec mld2r_grec[0]; }; #define mld2r_type mld2r_hdr.icmp6_type #define mld2r_resv1 mld2r_hdr.icmp6_code #define mld2r_cksum mld2r_hdr.icmp6_cksum #define mld2r_resv2 mld2r_hdr.icmp6_dataun.un_data16[0] #define mld2r_ngrec mld2r_hdr.icmp6_dataun.un_data16[1] /* MLDv2 Query */ struct mld2_query { struct icmp6hdr mld2q_hdr; struct in6_addr mld2q_mca; #if defined(__LITTLE_ENDIAN_BITFIELD) __u8 mld2q_qrv:3, mld2q_suppress:1, mld2q_resv2:4; #elif defined(__BIG_ENDIAN_BITFIELD) __u8 mld2q_resv2:4, mld2q_suppress:1, mld2q_qrv:3; #else #error "Please fix <asm/byteorder.h>" #endif __u8 mld2q_qqic; __be16 mld2q_nsrcs; struct in6_addr mld2q_srcs[0]; }; #define mld2q_type mld2q_hdr.icmp6_type #define mld2q_code mld2q_hdr.icmp6_code #define mld2q_cksum mld2q_hdr.icmp6_cksum #define mld2q_mrc mld2q_hdr.icmp6_maxdelay #define mld2q_resv1 mld2q_hdr.icmp6_dataun.un_data16[1] /* RFC3810, 5.1.3. Maximum Response Code: * * If Maximum Response Code >= 32768, Maximum Response Code represents a * floating-point value as follows: * * 0 1 2 3 4 5 6 7 8 9 A B C D E F * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ */ #define MLDV2_MRC_EXP(value) (((value) >> 12) & 0x0007) #define MLDV2_MRC_MAN(value) ((value) & 0x0fff) /* RFC3810, 5.1.9. QQIC (Querier's Query Interval Code): * * If QQIC >= 128, QQIC represents a floating-point value as follows: * * 0 1 2 3 4 5 6 7 * +-+-+-+-+-+-+-+-+ * |1| exp | mant | * +-+-+-+-+-+-+-+-+ */ #define MLDV2_QQIC_EXP(value) (((value) >> 4) & 0x07) #define MLDV2_QQIC_MAN(value) ((value) & 0x0f) #define MLD_EXP_MIN_LIMIT 32768UL #define MLDV1_MRD_MAX_COMPAT (MLD_EXP_MIN_LIMIT - 1) static inline unsigned long mldv2_mrc(const struct mld2_query *mlh2) { /* RFC3810, 5.1.3. Maximum Response Code */ unsigned long ret, mc_mrc = ntohs(mlh2->mld2q_mrc); if (mc_mrc < MLD_EXP_MIN_LIMIT) { ret = mc_mrc; } else { unsigned long mc_man, mc_exp; mc_exp = MLDV2_MRC_EXP(mc_mrc); mc_man = MLDV2_MRC_MAN(mc_mrc); ret = (mc_man | 0x1000) << (mc_exp + 3); } return ret; } #endif |
| 18 18 18 18 18 18 18 404 399 401 400 402 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/truncate.c - code for taking down pages from address_spaces * * Copyright (C) 2002, Linus Torvalds * * 10Sep2002 Andrew Morton * Initial version. */ #include <linux/kernel.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> #include <linux/export.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/pagevec.h> #include <linux/task_io_accounting_ops.h> #include <linux/buffer_head.h> /* grr. try_to_release_page, do_invalidatepage */ #include <linux/shmem_fs.h> #include <linux/cleancache.h> #include <linux/rmap.h> #include "internal.h" /* * Regular page slots are stabilized by the page lock even without the tree * itself locked. These unlocked entries need verification under the tree * lock. */ static inline void __clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { XA_STATE(xas, &mapping->i_pages, index); xas_set_update(&xas, workingset_update_node); if (xas_load(&xas) != entry) return; xas_store(&xas, NULL); mapping->nrexceptional--; } static void clear_shadow_entry(struct address_space *mapping, pgoff_t index, void *entry) { xa_lock_irq(&mapping->i_pages); __clear_shadow_entry(mapping, index, entry); xa_unlock_irq(&mapping->i_pages); } /* * Unconditionally remove exceptional entries. Usually called from truncate * path. Note that the pagevec may be altered by this function by removing * exceptional entries similar to what pagevec_remove_exceptionals does. */ static void truncate_exceptional_pvec_entries(struct address_space *mapping, struct pagevec *pvec, pgoff_t *indices, pgoff_t end) { int i, j; bool dax, lock; /* Handled by shmem itself */ if (shmem_mapping(mapping)) return; for (j = 0; j < pagevec_count(pvec); j++) if (xa_is_value(pvec->pages[j])) break; if (j == pagevec_count(pvec)) return; dax = dax_mapping(mapping); lock = !dax && indices[j] < end; if (lock) xa_lock_irq(&mapping->i_pages); for (i = j; i < pagevec_count(pvec); i++) { struct page *page = pvec->pages[i]; pgoff_t index = indices[i]; if (!xa_is_value(page)) { pvec->pages[j++] = page; continue; } if (index >= end) continue; if (unlikely(dax)) { dax_delete_mapping_entry(mapping, index); continue; } __clear_shadow_entry(mapping, index, page); } if (lock) xa_unlock_irq(&mapping->i_pages); pvec->nr = j; } /* * Invalidate exceptional entry if easily possible. This handles exceptional * entries for invalidate_inode_pages(). */ static int invalidate_exceptional_entry(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself, or for DAX we do nothing. */ if (shmem_mapping(mapping) || dax_mapping(mapping)) return 1; clear_shadow_entry(mapping, index, entry); return 1; } /* * Invalidate exceptional entry if clean. This handles exceptional entries for * invalidate_inode_pages2() so for DAX it evicts only clean entries. */ static int invalidate_exceptional_entry2(struct address_space *mapping, pgoff_t index, void *entry) { /* Handled by shmem itself */ if (shmem_mapping(mapping)) return 1; if (dax_mapping(mapping)) return dax_invalidate_mapping_entry_sync(mapping, index); clear_shadow_entry(mapping, index, entry); return 1; } /** * do_invalidatepage - invalidate part or all of a page * @page: the page which is affected * @offset: start of the range to invalidate * @length: length of the range to invalidate * * do_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. * * do_invalidatepage() does not have to release all buffers, but it must * ensure that no dirty buffer is left outside @offset and that no I/O * is underway against any of the blocks which are outside the truncation * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ void do_invalidatepage(struct page *page, unsigned int offset, unsigned int length) { void (*invalidatepage)(struct page *, unsigned int, unsigned int); invalidatepage = page->mapping->a_ops->invalidatepage; #ifdef CONFIG_BLOCK if (!invalidatepage) invalidatepage = block_invalidatepage; #endif if (invalidatepage) (*invalidatepage)(page, offset, length); } /* * If truncate cannot remove the fs-private metadata from the page, the page * becomes orphaned. It will be left on the LRU and may even be mapped into * user pagetables if we're racing with filemap_fault(). * * We need to bale out if page->mapping is no longer equal to the original * mapping. This happens a) when the VM reclaimed the page while we waited on * its lock, b) when a concurrent invalidate_mapping_pages got there first and * c) when tmpfs swizzles a page between a tmpfs inode and swapper_space. */ static void truncate_cleanup_page(struct page *page) { if (page_mapped(page)) unmap_mapping_page(page); if (page_has_private(page)) do_invalidatepage(page, 0, PAGE_SIZE); /* * Some filesystems seem to re-dirty the page even after * the VM has canceled the dirty bit (eg ext3 journaling). * Hence dirty accounting check is placed after invalidation. */ cancel_dirty_page(page); ClearPageMappedToDisk(page); } /* * This is for invalidate_mapping_pages(). That function can be called at * any time, and is not supposed to throw away dirty pages. But pages can * be marked dirty at any time too, so use remove_mapping which safely * discards clean, unused pages. * * Returns non-zero if the page was successfully invalidated. */ static int invalidate_complete_page(struct address_space *mapping, struct page *page) { int ret; if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, 0)) return 0; ret = remove_mapping(mapping, page); return ret; } int truncate_inode_page(struct address_space *mapping, struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); if (page->mapping != mapping) return -EIO; truncate_cleanup_page(page); delete_from_page_cache(page); return 0; } /* * Used to get rid of pages on hardware memory corruption. */ int generic_error_remove_page(struct address_space *mapping, struct page *page) { if (!mapping) return -EINVAL; /* * Only punch for normal data pages for now. * Handling other types like directories would need more auditing. */ if (!S_ISREG(mapping->host->i_mode)) return -EIO; return truncate_inode_page(mapping, page); } EXPORT_SYMBOL(generic_error_remove_page); /* * Safely invalidate one page from its pagecache mapping. * It only drops clean, unused pages. The page must be locked. * * Returns 1 if the page is successfully invalidated, otherwise 0. */ int invalidate_inode_page(struct page *page) { struct address_space *mapping = page_mapping(page); if (!mapping) return 0; if (PageDirty(page) || PageWriteback(page)) return 0; if (page_mapped(page)) return 0; return invalidate_complete_page(mapping, page); } /** * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between * specified offsets (and zeroing out partial pages * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass * will wait. This is to prevent as much IO as possible in the affected region. * The first pass will remove most pages, so the search cost of the second pass * is low. * * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. * * Note that since ->invalidatepage() accepts range to invalidate * truncate_inode_pages_range is able to handle cases where lend + 1 is not * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { pgoff_t start; /* inclusive */ pgoff_t end; /* exclusive */ unsigned int partial_start; /* inclusive */ unsigned int partial_end; /* exclusive */ struct pagevec pvec; pgoff_t indices[PAGEVEC_SIZE]; pgoff_t index; int i; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) goto out; /* Offsets within partial pages */ partial_start = lstart & (PAGE_SIZE - 1); partial_end = (lend + 1) & (PAGE_SIZE - 1); /* * 'start' and 'end' always covers the range of pages to be fully * truncated. Partial pages are covered with 'partial_start' at the * start of the range and 'partial_end' at the end of the range. * Note that 'end' is exclusive while 'lend' is inclusive. */ start = (lstart + PAGE_SIZE - 1) >> PAGE_SHIFT; if (lend == -1) /* * lend == -1 indicates end-of-file so we have to set 'end' * to the highest possible pgoff_t and since the type is * unsigned we're using -1. */ end = -1; else end = (lend + 1) >> PAGE_SHIFT; pagevec_init(&pvec); index = start; while (index < end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { /* * Pagevec array has exceptional entries and we may also fail * to lock some pages. So we store pages that can be deleted * in a new pagevec. */ struct pagevec locked_pvec; pagevec_init(&locked_pvec); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index >= end) break; if (xa_is_value(page)) continue; if (!trylock_page(page)) continue; WARN_ON(page_to_index(page) != index); if (PageWriteback(page)) { unlock_page(page); continue; } if (page->mapping != mapping) { unlock_page(page); continue; } pagevec_add(&locked_pvec, page); } for (i = 0; i < pagevec_count(&locked_pvec); i++) truncate_cleanup_page(locked_pvec.pages[i]); delete_from_page_cache_batch(mapping, &locked_pvec); for (i = 0; i < pagevec_count(&locked_pvec); i++) unlock_page(locked_pvec.pages[i]); truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); pagevec_release(&pvec); cond_resched(); index++; } if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { unsigned int top = PAGE_SIZE; if (start > end) { /* Truncation within a single page */ top = partial_end; partial_end = 0; } wait_on_page_writeback(page); zero_user_segment(page, partial_start, top); cleancache_invalidate_page(mapping, page); if (page_has_private(page)) do_invalidatepage(page, partial_start, top - partial_start); unlock_page(page); put_page(page); } } if (partial_end) { struct page *page = find_lock_page(mapping, end); if (page) { wait_on_page_writeback(page); zero_user_segment(page, 0, partial_end); cleancache_invalidate_page(mapping, page); if (page_has_private(page)) do_invalidatepage(page, 0, partial_end); unlock_page(page); put_page(page); } } /* * If the truncation happened within a single page no pages * will be released, just zeroed, so we can bail out now. */ if (start >= end) goto out; index = start; for ( ; ; ) { cond_resched(); if (!pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE), indices)) { /* If all gone from start onwards, we're done */ if (index == start) break; /* Otherwise restart to make sure all gone */ index = start; continue; } if (index == start && indices[0] >= end) { /* All gone out of hole to be punched, we're done */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); break; } for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index >= end) { /* Restart punch to make sure all gone */ index = start - 1; break; } if (xa_is_value(page)) continue; lock_page(page); WARN_ON(page_to_index(page) != index); wait_on_page_writeback(page); truncate_inode_page(mapping, page); unlock_page(page); } truncate_exceptional_pvec_entries(mapping, &pvec, indices, end); pagevec_release(&pvec); index++; } out: cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); /** * truncate_inode_pages - truncate *all* the pages from an offset * @mapping: mapping to truncate * @lstart: offset from which to truncate * * Called under (and serialised by) inode->i_mutex. * * Note: When this function returns, there can be a page in the process of * deletion (inside __delete_from_page_cache()) in the specified range. Thus * mapping->nrpages can be non-zero when this function returns even after * truncation of the whole mapping. */ void truncate_inode_pages(struct address_space *mapping, loff_t lstart) { truncate_inode_pages_range(mapping, lstart, (loff_t)-1); } EXPORT_SYMBOL(truncate_inode_pages); /** * truncate_inode_pages_final - truncate *all* pages before inode dies * @mapping: mapping to truncate * * Called under (and serialized by) inode->i_mutex. * * Filesystems have to use this in the .evict_inode path to inform the * VM that this is the final truncate and the inode is going away. */ void truncate_inode_pages_final(struct address_space *mapping) { unsigned long nrexceptional; unsigned long nrpages; /* * Page reclaim can not participate in regular inode lifetime * management (can't call iput()) and thus can race with the * inode teardown. Tell it when the address space is exiting, * so that it does not install eviction information after the * final truncate has begun. */ mapping_set_exiting(mapping); /* * When reclaim installs eviction entries, it increases * nrexceptional first, then decreases nrpages. Make sure we see * this in the right order or we might miss an entry. */ nrpages = mapping->nrpages; smp_rmb(); nrexceptional = mapping->nrexceptional; if (nrpages || nrexceptional) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree * modification that does not see AS_EXITING is * completed before starting the final truncate. */ xa_lock_irq(&mapping->i_pages); xa_unlock_irq(&mapping->i_pages); } /* * Cleancache needs notification even if there are no pages or shadow * entries. */ truncate_inode_pages(mapping, 0); } EXPORT_SYMBOL(truncate_inode_pages_final); /** * invalidate_mapping_pages - Invalidate all the unlocked pages of one inode * @mapping: the address_space which holds the pages to invalidate * @start: the offset 'from' which to invalidate * @end: the offset 'to' which to invalidate (inclusive) * * This function only removes the unlocked pages, if you want to * remove all the pages of one inode, you must call truncate_inode_pages. * * invalidate_mapping_pages() will not block on IO activity. It will not * invalidate pages which are dirty, locked, under writeback or mapped into * pagetables. * * Return: the number of the pages that were invalidated */ unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index = start; unsigned long ret; unsigned long count = 0; int i; pagevec_init(&pvec); while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index > end) break; if (xa_is_value(page)) { invalidate_exceptional_entry(mapping, index, page); continue; } if (!trylock_page(page)) continue; WARN_ON(page_to_index(page) != index); /* Middle of THP: skip */ if (PageTransTail(page)) { unlock_page(page); continue; } else if (PageTransHuge(page)) { index += HPAGE_PMD_NR - 1; i += HPAGE_PMD_NR - 1; /* * 'end' is in the middle of THP. Don't * invalidate the page as the part outside of * 'end' could be still useful. */ if (index > end) { unlock_page(page); continue; } /* Take a pin outside pagevec */ get_page(page); /* * Drop extra pins before trying to invalidate * the huge page. */ pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); } ret = invalidate_inode_page(page); unlock_page(page); /* * Invalidation is a hint that the page is no longer * of interest and try to speed up its reclaim. */ if (!ret) deactivate_file_page(page); if (PageTransHuge(page)) put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } return count; } EXPORT_SYMBOL(invalidate_mapping_pages); /* * This is like invalidate_complete_page(), except it ignores the page's * refcount. We do this because invalidate_inode_pages2() needs stronger * invalidation guarantees, and cannot afford to leave pages behind because * shrink_page_list() has a temp ref on them, or because they're transiently * sitting in the lru_cache_add() pagevecs. */ static int invalidate_complete_page2(struct address_space *mapping, struct page *page) { unsigned long flags; if (page->mapping != mapping) return 0; if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return 0; xa_lock_irqsave(&mapping->i_pages, flags); if (PageDirty(page)) goto failed; BUG_ON(page_has_private(page)); __delete_from_page_cache(page, NULL); xa_unlock_irqrestore(&mapping->i_pages, flags); if (mapping->a_ops->freepage) mapping->a_ops->freepage(page); put_page(page); /* pagecache ref */ return 1; failed: xa_unlock_irqrestore(&mapping->i_pages, flags); return 0; } static int do_launder_page(struct address_space *mapping, struct page *page) { if (!PageDirty(page)) return 0; if (page->mapping != mapping || mapping->a_ops->launder_page == NULL) return 0; return mapping->a_ops->launder_page(page); } /** * invalidate_inode_pages2_range - remove range of pages from an address_space * @mapping: the address_space * @start: the page offset 'from' which to invalidate * @end: the page offset 'to' which to invalidate (inclusive) * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end) { pgoff_t indices[PAGEVEC_SIZE]; struct pagevec pvec; pgoff_t index; int i; int ret = 0; int ret2 = 0; int did_range_unmap = 0; if (mapping->nrpages == 0 && mapping->nrexceptional == 0) goto out; pagevec_init(&pvec); index = start; while (index <= end && pagevec_lookup_entries(&pvec, mapping, index, min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1, indices)) { for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = indices[i]; if (index > end) break; if (xa_is_value(page)) { if (!invalidate_exceptional_entry2(mapping, index, page)) ret = -EBUSY; continue; } if (!did_range_unmap && page_mapped(page)) { /* * If page is mapped, before taking its lock, * zap the rest of the file in one hit. */ unmap_mapping_pages(mapping, index, (1 + end - index), false); did_range_unmap = 1; } lock_page(page); WARN_ON(page_to_index(page) != index); if (page->mapping != mapping) { unlock_page(page); continue; } wait_on_page_writeback(page); if (page_mapped(page)) unmap_mapping_page(page); BUG_ON(page_mapped(page)); ret2 = do_launder_page(mapping, page); if (ret2 == 0) { if (!invalidate_complete_page2(mapping, page)) ret2 = -EBUSY; } if (ret2 < 0) ret = ret2; unlock_page(page); } pagevec_remove_exceptionals(&pvec); pagevec_release(&pvec); cond_resched(); index++; } /* * For DAX we invalidate page tables after invalidating page cache. We * could invalidate page tables while invalidating each entry however * that would be expensive. And doing range unmapping before doesn't * work as we have no cheap way to find whether page cache entry didn't * get remapped later. */ if (dax_mapping(mapping)) { unmap_mapping_pages(mapping, start, end - start + 1, false); } out: cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); /** * invalidate_inode_pages2 - remove all pages from an address_space * @mapping: the address_space * * Any pages which are found to be mapped into pagetables are unmapped prior to * invalidation. * * Return: -EBUSY if any pages could not be invalidated. */ int invalidate_inode_pages2(struct address_space *mapping) { return invalidate_inode_pages2_range(mapping, 0, -1); } EXPORT_SYMBOL_GPL(invalidate_inode_pages2); /** * truncate_pagecache - unmap and remove pagecache that has been truncated * @inode: inode * @newsize: new file size * * inode's new i_size must already be written before truncate_pagecache * is called. * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache(struct inode *inode, loff_t newsize) { struct address_space *mapping = inode->i_mapping; loff_t holebegin = round_up(newsize, PAGE_SIZE); /* * unmap_mapping_range is called twice, first simply for * efficiency so that truncate_inode_pages does fewer * single-page unmaps. However after this first call, and * before truncate_inode_pages finishes, it is possible for * private pages to be COWed, which remain after * truncate_inode_pages finishes, hence the second * unmap_mapping_range call must be made for correctness. */ unmap_mapping_range(mapping, holebegin, 0, 1); truncate_inode_pages(mapping, newsize); unmap_mapping_range(mapping, holebegin, 0, 1); } EXPORT_SYMBOL(truncate_pagecache); /** * truncate_setsize - update inode and pagecache for a new file size * @inode: inode * @newsize: new file size * * truncate_setsize updates i_size and performs pagecache truncation (if * necessary) to @newsize. It will be typically be called from the filesystem's * setattr function when ATTR_SIZE is passed in. * * Must be called with a lock serializing truncates and writes (generally * i_mutex but e.g. xfs uses a different lock) and before all filesystem * specific block truncation has been performed. */ void truncate_setsize(struct inode *inode, loff_t newsize) { loff_t oldsize = inode->i_size; i_size_write(inode, newsize); if (newsize > oldsize) pagecache_isize_extended(inode, oldsize, newsize); truncate_pagecache(inode, newsize); } EXPORT_SYMBOL(truncate_setsize); /** * pagecache_isize_extended - update pagecache after extension of i_size * @inode: inode for which i_size was extended * @from: original inode size * @to: new inode size * * Handle extension of inode size either caused by extending truncate or by * write starting after current i_size. We mark the page straddling current * i_size RO so that page_mkwrite() is called on the nearest write access to * the page. This way filesystem can be sure that page_mkwrite() is called on * the page before user writes to the page via mmap after the i_size has been * changed. * * The function must be called after i_size is updated so that page fault * coming after we unlock the page will already see the new i_size. * The function must be called while we still hold i_mutex - this not only * makes sure i_size is stable but also that userspace cannot observe new * i_size value before we are prepared to store mmap writes at new inode size. */ void pagecache_isize_extended(struct inode *inode, loff_t from, loff_t to) { int bsize = i_blocksize(inode); loff_t rounded_from; struct page *page; pgoff_t index; WARN_ON(to > inode->i_size); if (from >= to || bsize == PAGE_SIZE) return; /* Page straddling @from will not have any hole block created? */ rounded_from = round_up(from, bsize); if (to <= rounded_from || !(rounded_from & (PAGE_SIZE - 1))) return; index = from >> PAGE_SHIFT; page = find_lock_page(inode->i_mapping, index); /* Page not cached? Nothing to do */ if (!page) return; /* * See clear_page_dirty_for_io() for details why set_page_dirty() * is needed. */ if (page_mkclean(page)) set_page_dirty(page); unlock_page(page); put_page(page); } EXPORT_SYMBOL(pagecache_isize_extended); /** * truncate_pagecache_range - unmap and remove pagecache that is hole-punched * @inode: inode * @lstart: offset of beginning of hole * @lend: offset of last byte of hole * * This function should typically be called before the filesystem * releases resources associated with the freed range (eg. deallocates * blocks). This way, pagecache will always stay logically coherent * with on-disk format, and the filesystem would not have to deal with * situations such as writepage being called for a page that has already * had its underlying blocks deallocated. */ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) { struct address_space *mapping = inode->i_mapping; loff_t unmap_start = round_up(lstart, PAGE_SIZE); loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; /* * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are * doing their own page rounding first. Note that unmap_mapping_range * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* * Unlike in truncate_pagecache, unmap_mapping_range is called only * once (before truncating pagecache), and without "even_cows" flag: * hole-punching should not remove private COWed pages from the hole. */ if ((u64)unmap_end > (u64)unmap_start) unmap_mapping_range(mapping, unmap_start, 1 + unmap_end - unmap_start, 0); truncate_inode_pages_range(mapping, lstart, lend); } EXPORT_SYMBOL(truncate_pagecache_range); |
| 81 320 411 272 319 387 539 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMU_NOTIFIER_H #define _LINUX_MMU_NOTIFIER_H #include <linux/list.h> #include <linux/spinlock.h> #include <linux/mm_types.h> #include <linux/srcu.h> #include <linux/android_kabi.h> struct mmu_notifier; struct mmu_notifier_ops; /** * enum mmu_notifier_event - reason for the mmu notifier callback * @MMU_NOTIFY_UNMAP: either munmap() that unmap the range or a mremap() that * move the range * * @MMU_NOTIFY_CLEAR: clear page table entry (many reasons for this like * madvise() or replacing a page by another one, ...). * * @MMU_NOTIFY_PROTECTION_VMA: update is due to protection change for the range * ie using the vma access permission (vm_page_prot) to update the whole range * is enough no need to inspect changes to the CPU page table (mprotect() * syscall) * * @MMU_NOTIFY_PROTECTION_PAGE: update is due to change in read/write flag for * pages in the range so to mirror those changes the user must inspect the CPU * page table (from the end callback). * * @MMU_NOTIFY_SOFT_DIRTY: soft dirty accounting (still same page and same * access flags). User should soft dirty the page in the end callback to make * sure that anyone relying on soft dirtyness catch pages that might be written * through non CPU mappings. */ enum mmu_notifier_event { MMU_NOTIFY_UNMAP = 0, MMU_NOTIFY_CLEAR, MMU_NOTIFY_PROTECTION_VMA, MMU_NOTIFY_PROTECTION_PAGE, MMU_NOTIFY_SOFT_DIRTY, }; #ifdef CONFIG_MMU_NOTIFIER #ifdef CONFIG_LOCKDEP extern struct lockdep_map __mmu_notifier_invalidate_range_start_map; #endif /* * The mmu notifier_mm structure is allocated and installed in * mm->mmu_notifier_mm inside the mm_take_all_locks() protected * critical section and it's released only when mm_count reaches zero * in mmdrop(). */ struct mmu_notifier_mm { /* all mmu notifiers registerd in this mm are queued in this list */ struct hlist_head list; /* to serialize the list modifications and hlist_unhashed */ spinlock_t lock; }; #define MMU_NOTIFIER_RANGE_BLOCKABLE (1 << 0) struct mmu_notifier_range { struct vm_area_struct *vma; struct mm_struct *mm; unsigned long start; unsigned long end; unsigned flags; enum mmu_notifier_event event; }; struct mmu_notifier_ops { /* * Called either by mmu_notifier_unregister or when the mm is * being destroyed by exit_mmap, always before all pages are * freed. This can run concurrently with other mmu notifier * methods (the ones invoked outside the mm context) and it * should tear down all secondary mmu mappings and freeze the * secondary mmu. If this method isn't implemented you've to * be sure that nothing could possibly write to the pages * through the secondary mmu by the time the last thread with * tsk->mm == mm exits. * * As side note: the pages freed after ->release returns could * be immediately reallocated by the gart at an alias physical * address with a different cache model, so if ->release isn't * implemented because all _software_ driven memory accesses * through the secondary mmu are terminated by the time the * last thread of this mm quits, you've also to be sure that * speculative _hardware_ operations can't allocate dirty * cachelines in the cpu that could not be snooped and made * coherent with the other read and write operations happening * through the gart alias address, so leading to memory * corruption. */ void (*release)(struct mmu_notifier *mn, struct mm_struct *mm); /* * clear_flush_young is called after the VM is * test-and-clearing the young/accessed bitflag in the * pte. This way the VM will provide proper aging to the * accesses to the page through the secondary MMUs and not * only to the ones through the Linux pte. * Start-end is necessary in case the secondary MMU is mapping the page * at a smaller granularity than the primary MMU. */ int (*clear_flush_young)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); /* * clear_young is a lightweight version of clear_flush_young. Like the * latter, it is supposed to test-and-clear the young/accessed bitflag * in the secondary pte, but it may omit flushing the secondary tlb. */ int (*clear_young)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); /* * test_young is called to check the young/accessed bitflag in * the secondary pte. This is used to know if the page is * frequently used without actually clearing the flag or tearing * down the secondary mapping on the page. */ int (*test_young)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address); /* * change_pte is called in cases that pte mapping to page is changed: * for example, when ksm remaps pte to point to a new shared page. */ void (*change_pte)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address, pte_t pte); /* * invalidate_range_start() and invalidate_range_end() must be * paired and are called only when the mmap_sem and/or the * locks protecting the reverse maps are held. If the subsystem * can't guarantee that no additional references are taken to * the pages in the range, it has to implement the * invalidate_range() notifier to remove any references taken * after invalidate_range_start(). * * Invalidation of multiple concurrent ranges may be * optionally permitted by the driver. Either way the * establishment of sptes is forbidden in the range passed to * invalidate_range_begin/end for the whole duration of the * invalidate_range_begin/end critical section. * * invalidate_range_start() is called when all pages in the * range are still mapped and have at least a refcount of one. * * invalidate_range_end() is called when all pages in the * range have been unmapped and the pages have been freed by * the VM. * * The VM will remove the page table entries and potentially * the page between invalidate_range_start() and * invalidate_range_end(). If the page must not be freed * because of pending I/O or other circumstances then the * invalidate_range_start() callback (or the initial mapping * by the driver) must make sure that the refcount is kept * elevated. * * If the driver increases the refcount when the pages are * initially mapped into an address space then either * invalidate_range_start() or invalidate_range_end() may * decrease the refcount. If the refcount is decreased on * invalidate_range_start() then the VM can free pages as page * table entries are removed. If the refcount is only * droppped on invalidate_range_end() then the driver itself * will drop the last refcount but it must take care to flush * any secondary tlb before doing the final free on the * page. Pages will no longer be referenced by the linux * address space but may still be referenced by sptes until * the last refcount is dropped. * * If blockable argument is set to false then the callback cannot * sleep and has to return with -EAGAIN. 0 should be returned * otherwise. Please note that if invalidate_range_start approves * a non-blocking behavior then the same applies to * invalidate_range_end. * */ int (*invalidate_range_start)(struct mmu_notifier *mn, const struct mmu_notifier_range *range); void (*invalidate_range_end)(struct mmu_notifier *mn, const struct mmu_notifier_range *range); /* * invalidate_range() is either called between * invalidate_range_start() and invalidate_range_end() when the * VM has to free pages that where unmapped, but before the * pages are actually freed, or outside of _start()/_end() when * a (remote) TLB is necessary. * * If invalidate_range() is used to manage a non-CPU TLB with * shared page-tables, it not necessary to implement the * invalidate_range_start()/end() notifiers, as * invalidate_range() alread catches the points in time when an * external TLB range needs to be flushed. For more in depth * discussion on this see Documentation/vm/mmu_notifier.rst * * Note that this function might be called with just a sub-range * of what was passed to invalidate_range_start()/end(), if * called between those functions. */ void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end); /* * These callbacks are used with the get/put interface to manage the * lifetime of the mmu_notifier memory. alloc_notifier() returns a new * notifier for use with the mm. * * free_notifier() is only called after the mmu_notifier has been * fully put, calls to any ops callback are prevented and no ops * callbacks are currently running. It is called from a SRCU callback * and cannot sleep. */ struct mmu_notifier *(*alloc_notifier)(struct mm_struct *mm); void (*free_notifier)(struct mmu_notifier *mn); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; /* * The notifier chains are protected by mmap_sem and/or the reverse map * semaphores. Notifier chains are only changed when all reverse maps and * the mmap_sem locks are taken. * * Therefore notifier chains can only be traversed when either * * 1. mmap_sem is held. * 2. One of the reverse map locks is held (i_mmap_rwsem or anon_vma->rwsem). * 3. No other concurrent thread can access the list (release) */ struct mmu_notifier { struct hlist_node hlist; const struct mmu_notifier_ops *ops; struct mm_struct *mm; struct rcu_head rcu; unsigned int users; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; static inline int mm_has_notifiers(struct mm_struct *mm) { return unlikely(mm->mmu_notifier_mm); } struct mmu_notifier *mmu_notifier_get_locked(const struct mmu_notifier_ops *ops, struct mm_struct *mm); static inline struct mmu_notifier * mmu_notifier_get(const struct mmu_notifier_ops *ops, struct mm_struct *mm) { struct mmu_notifier *ret; down_write(&mm->mmap_sem); ret = mmu_notifier_get_locked(ops, mm); up_write(&mm->mmap_sem); return ret; } void mmu_notifier_put(struct mmu_notifier *mn); void mmu_notifier_synchronize(void); extern int mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm); extern int __mmu_notifier_register(struct mmu_notifier *mn, struct mm_struct *mm); extern void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm); extern void __mmu_notifier_mm_destroy(struct mm_struct *mm); extern void __mmu_notifier_release(struct mm_struct *mm); extern int __mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end); extern int __mmu_notifier_test_young(struct mm_struct *mm, unsigned long address); extern void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte); extern int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *r); extern void __mmu_notifier_invalidate_range_end(struct mmu_notifier_range *r, bool only_end); extern void __mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end); extern bool mmu_notifier_range_update_to_read_only(const struct mmu_notifier_range *range); static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return (range->flags & MMU_NOTIFIER_RANGE_BLOCKABLE); } static inline void mmu_notifier_release(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_release(mm); } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_flush_young(mm, start, end); return 0; } static inline int mmu_notifier_clear_young(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) return __mmu_notifier_clear_young(mm, start, end); return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { if (mm_has_notifiers(mm)) return __mmu_notifier_test_young(mm, address); return 0; } static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { if (mm_has_notifiers(mm)) __mmu_notifier_change_pte(mm, address, pte); } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { might_sleep(); lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags |= MMU_NOTIFIER_RANGE_BLOCKABLE; __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { int ret = 0; lock_map_acquire(&__mmu_notifier_invalidate_range_start_map); if (mm_has_notifiers(range->mm)) { range->flags &= ~MMU_NOTIFIER_RANGE_BLOCKABLE; ret = __mmu_notifier_invalidate_range_start(range); } lock_map_release(&__mmu_notifier_invalidate_range_start_map); return ret; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { if (mmu_notifier_range_blockable(range)) might_sleep(); if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range, false); } static inline void mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) { if (mm_has_notifiers(range->mm)) __mmu_notifier_invalidate_range_end(range, true); } static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { if (mm_has_notifiers(mm)) __mmu_notifier_invalidate_range(mm, start, end); } static inline void mmu_notifier_mm_init(struct mm_struct *mm) { mm->mmu_notifier_mm = NULL; } static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) { if (mm_has_notifiers(mm)) __mmu_notifier_mm_destroy(mm); } static inline void mmu_notifier_range_init(struct mmu_notifier_range *range, enum mmu_notifier_event event, unsigned flags, struct vm_area_struct *vma, struct mm_struct *mm, unsigned long start, unsigned long end) { range->vma = vma; range->event = event; range->mm = mm; range->start = start; range->end = end; range->flags = flags; } #define ptep_clear_flush_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_clear_flush_young(___vma, ___address, __ptep); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PAGE_SIZE); \ __young; \ }) #define pmdp_clear_flush_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_clear_flush_young(___vma, ___address, __pmdp); \ __young |= mmu_notifier_clear_flush_young(___vma->vm_mm, \ ___address, \ ___address + \ PMD_SIZE); \ __young; \ }) #define ptep_clear_young_notify(__vma, __address, __ptep) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = ptep_test_and_clear_young(___vma, ___address, __ptep);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PAGE_SIZE); \ __young; \ }) #define pmdp_clear_young_notify(__vma, __address, __pmdp) \ ({ \ int __young; \ struct vm_area_struct *___vma = __vma; \ unsigned long ___address = __address; \ __young = pmdp_test_and_clear_young(___vma, ___address, __pmdp);\ __young |= mmu_notifier_clear_young(___vma->vm_mm, ___address, \ ___address + PMD_SIZE); \ __young; \ }) #define ptep_clear_flush_notify(__vma, __address, __ptep) \ ({ \ unsigned long ___addr = __address & PAGE_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pte_t ___pte; \ \ ___pte = ptep_clear_flush(__vma, __address, __ptep); \ mmu_notifier_invalidate_range(___mm, ___addr, \ ___addr + PAGE_SIZE); \ \ ___pte; \ }) #define pmdp_huge_clear_flush_notify(__vma, __haddr, __pmd) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PMD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pmd_t ___pmd; \ \ ___pmd = pmdp_huge_clear_flush(__vma, __haddr, __pmd); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PMD_SIZE); \ \ ___pmd; \ }) #define pudp_huge_clear_flush_notify(__vma, __haddr, __pud) \ ({ \ unsigned long ___haddr = __haddr & HPAGE_PUD_MASK; \ struct mm_struct *___mm = (__vma)->vm_mm; \ pud_t ___pud; \ \ ___pud = pudp_huge_clear_flush(__vma, __haddr, __pud); \ mmu_notifier_invalidate_range(___mm, ___haddr, \ ___haddr + HPAGE_PUD_SIZE); \ \ ___pud; \ }) /* * set_pte_at_notify() sets the pte _after_ running the notifier. * This is safe to start by updating the secondary MMUs, because the primary MMU * pte invalidate must have already happened with a ptep_clear_flush() before * set_pte_at_notify() has been invoked. Updating the secondary MMUs first is * required when we change both the protection of the mapping from read-only to * read-write and the pfn (like during copy on write page faults). Otherwise the * old page would remain mapped readonly in the secondary MMUs after the new * page is already writable by some CPU through the primary MMU. */ #define set_pte_at_notify(__mm, __address, __ptep, __pte) \ ({ \ struct mm_struct *___mm = __mm; \ unsigned long ___address = __address; \ pte_t ___pte = __pte; \ \ mmu_notifier_change_pte(___mm, ___address, ___pte); \ set_pte_at(___mm, ___address, __ptep, ___pte); \ }) #else /* CONFIG_MMU_NOTIFIER */ struct mmu_notifier_range { unsigned long start; unsigned long end; }; static inline void _mmu_notifier_range_init(struct mmu_notifier_range *range, unsigned long start, unsigned long end) { range->start = start; range->end = end; } #define mmu_notifier_range_init(range,event,flags,vma,mm,start,end) \ _mmu_notifier_range_init(range, start, end) static inline bool mmu_notifier_range_blockable(const struct mmu_notifier_range *range) { return true; } static inline int mm_has_notifiers(struct mm_struct *mm) { return 0; } static inline void mmu_notifier_release(struct mm_struct *mm) { } static inline int mmu_notifier_clear_flush_young(struct mm_struct *mm, unsigned long start, unsigned long end) { return 0; } static inline int mmu_notifier_test_young(struct mm_struct *mm, unsigned long address) { return 0; } static inline void mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address, pte_t pte) { } static inline void mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) { } static inline int mmu_notifier_invalidate_range_start_nonblock(struct mmu_notifier_range *range) { return 0; } static inline void mmu_notifier_invalidate_range_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_invalidate_range_only_end(struct mmu_notifier_range *range) { } static inline void mmu_notifier_invalidate_range(struct mm_struct *mm, unsigned long start, unsigned long end) { } static inline void mmu_notifier_mm_init(struct mm_struct *mm) { } static inline void mmu_notifier_mm_destroy(struct mm_struct *mm) { } #define mmu_notifier_range_update_to_read_only(r) false #define ptep_clear_flush_young_notify ptep_clear_flush_young #define pmdp_clear_flush_young_notify pmdp_clear_flush_young #define ptep_clear_young_notify ptep_test_and_clear_young #define pmdp_clear_young_notify pmdp_test_and_clear_young #define ptep_clear_flush_notify ptep_clear_flush #define pmdp_huge_clear_flush_notify pmdp_huge_clear_flush #define pudp_huge_clear_flush_notify pudp_huge_clear_flush #define set_pte_at_notify set_pte_at static inline void mmu_notifier_synchronize(void) { } #endif /* CONFIG_MMU_NOTIFIER */ #endif /* _LINUX_MMU_NOTIFIER_H */ |
| 3993 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _TIMEKEEPING_INTERNAL_H #define _TIMEKEEPING_INTERNAL_H /* * timekeeping debug functions */ #include <linux/clocksource.h> #include <linux/time.h> #ifdef CONFIG_DEBUG_FS extern void tk_debug_account_sleep_time(const struct timespec64 *t); #else #define tk_debug_account_sleep_time(x) #endif #ifdef CONFIG_CLOCKSOURCE_VALIDATE_LAST_CYCLE static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) { u64 ret = (now - last) & mask; /* * Prevent time going backwards by checking the MSB of mask in * the result. If set, return 0. */ return ret & ~(mask >> 1) ? 0 : ret; } #else static inline u64 clocksource_delta(u64 now, u64 last, u64 mask) { return (now - last) & mask; } #endif #endif /* _TIMEKEEPING_INTERNAL_H */ |
| 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 | #ifndef LLC_H #define LLC_H /* * Copyright (c) 1997 by Procom Technology, Inc. * 2001-2003 by Arnaldo Carvalho de Melo <acme@conectiva.com.br> * * This program can be redistributed or modified under the terms of the * GNU General Public License as published by the Free Software Foundation. * This program is distributed without any warranty or implied warranty * of merchantability or fitness for a particular purpose. * * See the GNU General Public License for more details. */ #include <linux/if.h> #include <linux/if_ether.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/rculist_nulls.h> #include <linux/hash.h> #include <linux/jhash.h> #include <linux/atomic.h> struct net_device; struct packet_type; struct sk_buff; struct llc_addr { unsigned char lsap; unsigned char mac[IFHWADDRLEN]; }; #define LLC_SAP_STATE_INACTIVE 1 #define LLC_SAP_STATE_ACTIVE 2 #define LLC_SK_DEV_HASH_BITS 6 #define LLC_SK_DEV_HASH_ENTRIES (1<<LLC_SK_DEV_HASH_BITS) #define LLC_SK_LADDR_HASH_BITS 6 #define LLC_SK_LADDR_HASH_ENTRIES (1<<LLC_SK_LADDR_HASH_BITS) /** * struct llc_sap - Defines the SAP component * * @station - station this sap belongs to * @state - sap state * @p_bit - only lowest-order bit used * @f_bit - only lowest-order bit used * @laddr - SAP value in this 'lsap' * @node - entry in station sap_list * @sk_list - LLC sockets this one manages */ struct llc_sap { unsigned char state; unsigned char p_bit; unsigned char f_bit; refcount_t refcnt; int (*rcv_func)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); struct llc_addr laddr; struct list_head node; spinlock_t sk_lock; int sk_count; struct hlist_nulls_head sk_laddr_hash[LLC_SK_LADDR_HASH_ENTRIES]; struct hlist_head sk_dev_hash[LLC_SK_DEV_HASH_ENTRIES]; struct rcu_head rcu; }; static inline struct hlist_head *llc_sk_dev_hash(struct llc_sap *sap, int ifindex) { u32 bucket = hash_32(ifindex, LLC_SK_DEV_HASH_BITS); return &sap->sk_dev_hash[bucket]; } static inline u32 llc_sk_laddr_hashfn(struct llc_sap *sap, const struct llc_addr *laddr) { return hash_32(jhash(laddr->mac, sizeof(laddr->mac), 0), LLC_SK_LADDR_HASH_BITS); } static inline struct hlist_nulls_head *llc_sk_laddr_hash(struct llc_sap *sap, const struct llc_addr *laddr) { return &sap->sk_laddr_hash[llc_sk_laddr_hashfn(sap, laddr)]; } #define LLC_DEST_INVALID 0 /* Invalid LLC PDU type */ #define LLC_DEST_SAP 1 /* Type 1 goes here */ #define LLC_DEST_CONN 2 /* Type 2 goes here */ extern struct list_head llc_sap_list; int llc_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev); int llc_mac_hdr_init(struct sk_buff *skb, const unsigned char *sa, const unsigned char *da); void llc_add_pack(int type, void (*handler)(struct llc_sap *sap, struct sk_buff *skb)); void llc_remove_pack(int type); void llc_set_station_handler(void (*handler)(struct sk_buff *skb)); struct llc_sap *llc_sap_open(unsigned char lsap, int (*rcv)(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev)); static inline void llc_sap_hold(struct llc_sap *sap) { refcount_inc(&sap->refcnt); } static inline bool llc_sap_hold_safe(struct llc_sap *sap) { return refcount_inc_not_zero(&sap->refcnt); } void llc_sap_close(struct llc_sap *sap); static inline void llc_sap_put(struct llc_sap *sap) { if (refcount_dec_and_test(&sap->refcnt)) llc_sap_close(sap); } struct llc_sap *llc_sap_find(unsigned char sap_value); int llc_build_and_send_ui_pkt(struct llc_sap *sap, struct sk_buff *skb, unsigned char *dmac, unsigned char dsap); void llc_sap_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_conn_handler(struct llc_sap *sap, struct sk_buff *skb); void llc_station_init(void); void llc_station_exit(void); #ifdef CONFIG_PROC_FS int llc_proc_init(void); void llc_proc_exit(void); #else #define llc_proc_init() (0) #define llc_proc_exit() do { } while(0) #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SYSCTL int llc_sysctl_init(void); void llc_sysctl_exit(void); extern int sysctl_llc2_ack_timeout; extern int sysctl_llc2_busy_timeout; extern int sysctl_llc2_p_timeout; extern int sysctl_llc2_rej_timeout; #else #define llc_sysctl_init() (0) #define llc_sysctl_exit() do { } while(0) #endif /* CONFIG_SYSCTL */ #endif /* LLC_H */ |
| 82 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * An async IO implementation for Linux * Written by Benjamin LaHaise <bcrl@kvack.org> * * Implements an efficient asynchronous io interface. * * Copyright 2000, 2001, 2002 Red Hat, Inc. All Rights Reserved. * Copyright 2018 Christoph Hellwig. * * See ../COPYING for licensing terms. */ #define pr_fmt(fmt) "%s: " fmt, __func__ #include <linux/kernel.h> #include <linux/init.h> #include <linux/errno.h> #include <linux/time.h> #include <linux/aio_abi.h> #include <linux/export.h> #include <linux/syscalls.h> #include <linux/backing-dev.h> #include <linux/refcount.h> #include <linux/uio.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/mm.h> #include <linux/mman.h> #include <linux/mmu_context.h> #include <linux/percpu.h> #include <linux/slab.h> #include <linux/timer.h> #include <linux/aio.h> #include <linux/highmem.h> #include <linux/workqueue.h> #include <linux/security.h> #include <linux/eventfd.h> #include <linux/blkdev.h> #include <linux/compat.h> #include <linux/migrate.h> #include <linux/ramfs.h> #include <linux/percpu-refcount.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <asm/kmap_types.h> #include <linux/uaccess.h> #include <linux/nospec.h> #include "internal.h" #define KIOCB_KEY 0 #define AIO_RING_MAGIC 0xa10a10a1 #define AIO_RING_COMPAT_FEATURES 1 #define AIO_RING_INCOMPAT_FEATURES 0 struct aio_ring { unsigned id; /* kernel internal index number */ unsigned nr; /* number of io_events */ unsigned head; /* Written to by userland or under ring_lock * mutex by aio_read_events_ring(). */ unsigned tail; unsigned magic; unsigned compat_features; unsigned incompat_features; unsigned header_length; /* size of aio_ring */ struct io_event io_events[0]; }; /* 128 bytes + ring size */ /* * Plugging is meant to work with larger batches of IOs. If we don't * have more than the below, then don't bother setting up a plug. */ #define AIO_PLUG_THRESHOLD 2 #define AIO_RING_PAGES 8 struct kioctx_table { struct rcu_head rcu; unsigned nr; struct kioctx __rcu *table[]; }; struct kioctx_cpu { unsigned reqs_available; }; struct ctx_rq_wait { struct completion comp; atomic_t count; }; struct kioctx { struct percpu_ref users; atomic_t dead; struct percpu_ref reqs; unsigned long user_id; struct __percpu kioctx_cpu *cpu; /* * For percpu reqs_available, number of slots we move to/from global * counter at a time: */ unsigned req_batch; /* * This is what userspace passed to io_setup(), it's not used for * anything but counting against the global max_reqs quota. * * The real limit is nr_events - 1, which will be larger (see * aio_setup_ring()) */ unsigned max_reqs; /* Size of ringbuffer, in units of struct io_event */ unsigned nr_events; unsigned long mmap_base; unsigned long mmap_size; struct page **ring_pages; long nr_pages; struct rcu_work free_rwork; /* see free_ioctx() */ /* * signals when all in-flight requests are done */ struct ctx_rq_wait *rq_wait; struct { /* * This counts the number of available slots in the ringbuffer, * so we avoid overflowing it: it's decremented (if positive) * when allocating a kiocb and incremented when the resulting * io_event is pulled off the ringbuffer. * * We batch accesses to it with a percpu version. */ atomic_t reqs_available; } ____cacheline_aligned_in_smp; struct { spinlock_t ctx_lock; struct list_head active_reqs; /* used for cancellation */ } ____cacheline_aligned_in_smp; struct { struct mutex ring_lock; wait_queue_head_t wait; } ____cacheline_aligned_in_smp; struct { unsigned tail; unsigned completed_events; spinlock_t completion_lock; } ____cacheline_aligned_in_smp; struct page *internal_pages[AIO_RING_PAGES]; struct file *aio_ring_file; unsigned id; }; /* * First field must be the file pointer in all the * iocb unions! See also 'struct kiocb' in <linux/fs.h> */ struct fsync_iocb { struct file *file; struct work_struct work; bool datasync; struct cred *creds; }; struct poll_iocb { struct file *file; struct wait_queue_head *head; __poll_t events; bool cancelled; bool work_scheduled; bool work_need_resched; struct wait_queue_entry wait; struct work_struct work; }; /* * NOTE! Each of the iocb union members has the file pointer * as the first entry in their struct definition. So you can * access the file pointer through any of the sub-structs, * or directly as just 'ki_filp' in this struct. */ struct aio_kiocb { union { struct file *ki_filp; struct kiocb rw; struct fsync_iocb fsync; struct poll_iocb poll; }; struct kioctx *ki_ctx; kiocb_cancel_fn *ki_cancel; struct io_event ki_res; struct list_head ki_list; /* the aio core uses this * for cancellation */ refcount_t ki_refcnt; /* * If the aio_resfd field of the userspace iocb is not zero, * this is the underlying eventfd context to deliver events to. */ struct eventfd_ctx *ki_eventfd; }; /*------ sysctl variables----*/ static DEFINE_SPINLOCK(aio_nr_lock); unsigned long aio_nr; /* current system wide number of aio requests */ unsigned long aio_max_nr = 0x10000; /* system wide maximum number of aio requests */ /*----end sysctl variables---*/ static struct kmem_cache *kiocb_cachep; static struct kmem_cache *kioctx_cachep; static struct vfsmount *aio_mnt; static const struct file_operations aio_ring_fops; static const struct address_space_operations aio_ctx_aops; static struct file *aio_private_file(struct kioctx *ctx, loff_t nr_pages) { struct file *file; struct inode *inode = alloc_anon_inode(aio_mnt->mnt_sb); if (IS_ERR(inode)) return ERR_CAST(inode); inode->i_mapping->a_ops = &aio_ctx_aops; inode->i_mapping->private_data = ctx; inode->i_size = PAGE_SIZE * nr_pages; file = alloc_file_pseudo(inode, aio_mnt, "[aio]", O_RDWR, &aio_ring_fops); if (IS_ERR(file)) iput(inode); return file; } static int aio_init_fs_context(struct fs_context *fc) { if (!init_pseudo(fc, AIO_RING_MAGIC)) return -ENOMEM; fc->s_iflags |= SB_I_NOEXEC; return 0; } /* aio_setup * Creates the slab caches used by the aio routines, panic on * failure as this is done early during the boot sequence. */ static int __init aio_setup(void) { static struct file_system_type aio_fs = { .name = "aio", .init_fs_context = aio_init_fs_context, .kill_sb = kill_anon_super, }; aio_mnt = kern_mount(&aio_fs); if (IS_ERR(aio_mnt)) panic("Failed to create aio fs mount."); kiocb_cachep = KMEM_CACHE(aio_kiocb, SLAB_HWCACHE_ALIGN|SLAB_PANIC); kioctx_cachep = KMEM_CACHE(kioctx,SLAB_HWCACHE_ALIGN|SLAB_PANIC); return 0; } __initcall(aio_setup); static void put_aio_ring_file(struct kioctx *ctx) { struct file *aio_ring_file = ctx->aio_ring_file; struct address_space *i_mapping; if (aio_ring_file) { truncate_setsize(file_inode(aio_ring_file), 0); /* Prevent further access to the kioctx from migratepages */ i_mapping = aio_ring_file->f_mapping; spin_lock(&i_mapping->private_lock); i_mapping->private_data = NULL; ctx->aio_ring_file = NULL; spin_unlock(&i_mapping->private_lock); fput(aio_ring_file); } } static void aio_free_ring(struct kioctx *ctx) { int i; /* Disconnect the kiotx from the ring file. This prevents future * accesses to the kioctx from page migration. */ put_aio_ring_file(ctx); for (i = 0; i < ctx->nr_pages; i++) { struct page *page; pr_debug("pid(%d) [%d] page->count=%d\n", current->pid, i, page_count(ctx->ring_pages[i])); page = ctx->ring_pages[i]; if (!page) continue; ctx->ring_pages[i] = NULL; put_page(page); } if (ctx->ring_pages && ctx->ring_pages != ctx->internal_pages) { kfree(ctx->ring_pages); ctx->ring_pages = NULL; } } static int aio_ring_mremap(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct mm_struct *mm = vma->vm_mm; struct kioctx_table *table; int i, res = -EINVAL; spin_lock(&mm->ioctx_lock); rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); if (!table) goto out_unlock; for (i = 0; i < table->nr; i++) { struct kioctx *ctx; ctx = rcu_dereference(table->table[i]); if (ctx && ctx->aio_ring_file == file) { if (!atomic_read(&ctx->dead)) { ctx->user_id = ctx->mmap_base = vma->vm_start; res = 0; } break; } } out_unlock: rcu_read_unlock(); spin_unlock(&mm->ioctx_lock); return res; } static const struct vm_operations_struct aio_ring_vm_ops = { .mremap = aio_ring_mremap, #if IS_ENABLED(CONFIG_MMU) .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, #endif }; static int aio_ring_mmap(struct file *file, struct vm_area_struct *vma) { vma->vm_flags |= VM_DONTEXPAND; vma->vm_ops = &aio_ring_vm_ops; return 0; } static const struct file_operations aio_ring_fops = { .mmap = aio_ring_mmap, }; #if IS_ENABLED(CONFIG_MIGRATION) static int aio_migratepage(struct address_space *mapping, struct page *new, struct page *old, enum migrate_mode mode) { struct kioctx *ctx; unsigned long flags; pgoff_t idx; int rc; /* * We cannot support the _NO_COPY case here, because copy needs to * happen under the ctx->completion_lock. That does not work with the * migration workflow of MIGRATE_SYNC_NO_COPY. */ if (mode == MIGRATE_SYNC_NO_COPY) return -EINVAL; rc = 0; /* mapping->private_lock here protects against the kioctx teardown. */ spin_lock(&mapping->private_lock); ctx = mapping->private_data; if (!ctx) { rc = -EINVAL; goto out; } /* The ring_lock mutex. The prevents aio_read_events() from writing * to the ring's head, and prevents page migration from mucking in * a partially initialized kiotx. */ if (!mutex_trylock(&ctx->ring_lock)) { rc = -EAGAIN; goto out; } idx = old->index; if (idx < (pgoff_t)ctx->nr_pages) { /* Make sure the old page hasn't already been changed */ if (ctx->ring_pages[idx] != old) rc = -EAGAIN; } else rc = -EINVAL; if (rc != 0) goto out_unlock; /* Writeback must be complete */ BUG_ON(PageWriteback(old)); get_page(new); rc = migrate_page_move_mapping(mapping, new, old, 1); if (rc != MIGRATEPAGE_SUCCESS) { put_page(new); goto out_unlock; } /* Take completion_lock to prevent other writes to the ring buffer * while the old page is copied to the new. This prevents new * events from being lost. */ spin_lock_irqsave(&ctx->completion_lock, flags); migrate_page_copy(new, old); BUG_ON(ctx->ring_pages[idx] != old); ctx->ring_pages[idx] = new; spin_unlock_irqrestore(&ctx->completion_lock, flags); /* The old page is no longer accessible. */ put_page(old); out_unlock: mutex_unlock(&ctx->ring_lock); out: spin_unlock(&mapping->private_lock); return rc; } #endif static const struct address_space_operations aio_ctx_aops = { .set_page_dirty = __set_page_dirty_no_writeback, #if IS_ENABLED(CONFIG_MIGRATION) .migratepage = aio_migratepage, #endif }; static int aio_setup_ring(struct kioctx *ctx, unsigned int nr_events) { struct aio_ring *ring; struct mm_struct *mm = current->mm; unsigned long size, unused; int nr_pages; int i; struct file *file; /* Compensate for the ring buffer's head/tail overlap entry */ nr_events += 2; /* 1 is required, 2 for good luck */ size = sizeof(struct aio_ring); size += sizeof(struct io_event) * nr_events; nr_pages = PFN_UP(size); if (nr_pages < 0) return -EINVAL; file = aio_private_file(ctx, nr_pages); if (IS_ERR(file)) { ctx->aio_ring_file = NULL; return -ENOMEM; } ctx->aio_ring_file = file; nr_events = (PAGE_SIZE * nr_pages - sizeof(struct aio_ring)) / sizeof(struct io_event); ctx->ring_pages = ctx->internal_pages; if (nr_pages > AIO_RING_PAGES) { ctx->ring_pages = kcalloc(nr_pages, sizeof(struct page *), GFP_KERNEL); if (!ctx->ring_pages) { put_aio_ring_file(ctx); return -ENOMEM; } } for (i = 0; i < nr_pages; i++) { struct page *page; page = find_or_create_page(file->f_mapping, i, GFP_HIGHUSER | __GFP_ZERO); if (!page) break; pr_debug("pid(%d) page[%d]->count=%d\n", current->pid, i, page_count(page)); SetPageUptodate(page); unlock_page(page); ctx->ring_pages[i] = page; } ctx->nr_pages = i; if (unlikely(i != nr_pages)) { aio_free_ring(ctx); return -ENOMEM; } ctx->mmap_size = nr_pages * PAGE_SIZE; pr_debug("attempting mmap of %lu bytes\n", ctx->mmap_size); if (down_write_killable(&mm->mmap_sem)) { ctx->mmap_size = 0; aio_free_ring(ctx); return -EINTR; } ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, 0, &unused, NULL); up_write(&mm->mmap_sem); if (IS_ERR((void *)ctx->mmap_base)) { ctx->mmap_size = 0; aio_free_ring(ctx); return -ENOMEM; } pr_debug("mmap address: 0x%08lx\n", ctx->mmap_base); ctx->user_id = ctx->mmap_base; ctx->nr_events = nr_events; /* trusted copy */ ring = kmap_atomic(ctx->ring_pages[0]); ring->nr = nr_events; /* user copy */ ring->id = ~0U; ring->head = ring->tail = 0; ring->magic = AIO_RING_MAGIC; ring->compat_features = AIO_RING_COMPAT_FEATURES; ring->incompat_features = AIO_RING_INCOMPAT_FEATURES; ring->header_length = sizeof(struct aio_ring); kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); return 0; } #define AIO_EVENTS_PER_PAGE (PAGE_SIZE / sizeof(struct io_event)) #define AIO_EVENTS_FIRST_PAGE ((PAGE_SIZE - sizeof(struct aio_ring)) / sizeof(struct io_event)) #define AIO_EVENTS_OFFSET (AIO_EVENTS_PER_PAGE - AIO_EVENTS_FIRST_PAGE) void kiocb_set_cancel_fn(struct kiocb *iocb, kiocb_cancel_fn *cancel) { struct aio_kiocb *req; struct kioctx *ctx; unsigned long flags; /* * kiocb didn't come from aio or is neither a read nor a write, hence * ignore it. */ if (!(iocb->ki_flags & IOCB_AIO_RW)) return; req = container_of(iocb, struct aio_kiocb, rw); if (WARN_ON_ONCE(!list_empty(&req->ki_list))) return; ctx = req->ki_ctx; spin_lock_irqsave(&ctx->ctx_lock, flags); list_add_tail(&req->ki_list, &ctx->active_reqs); req->ki_cancel = cancel; spin_unlock_irqrestore(&ctx->ctx_lock, flags); } EXPORT_SYMBOL(kiocb_set_cancel_fn); /* * free_ioctx() should be RCU delayed to synchronize against the RCU * protected lookup_ioctx() and also needs process context to call * aio_free_ring(). Use rcu_work. */ static void free_ioctx(struct work_struct *work) { struct kioctx *ctx = container_of(to_rcu_work(work), struct kioctx, free_rwork); pr_debug("freeing %p\n", ctx); aio_free_ring(ctx); free_percpu(ctx->cpu); percpu_ref_exit(&ctx->reqs); percpu_ref_exit(&ctx->users); kmem_cache_free(kioctx_cachep, ctx); } static void free_ioctx_reqs(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, reqs); /* At this point we know that there are no any in-flight requests */ if (ctx->rq_wait && atomic_dec_and_test(&ctx->rq_wait->count)) complete(&ctx->rq_wait->comp); /* Synchronize against RCU protected table->table[] dereferences */ INIT_RCU_WORK(&ctx->free_rwork, free_ioctx); queue_rcu_work(system_wq, &ctx->free_rwork); } /* * When this function runs, the kioctx has been removed from the "hash table" * and ctx->users has dropped to 0, so we know no more kiocbs can be submitted - * now it's safe to cancel any that need to be. */ static void free_ioctx_users(struct percpu_ref *ref) { struct kioctx *ctx = container_of(ref, struct kioctx, users); struct aio_kiocb *req; spin_lock_irq(&ctx->ctx_lock); while (!list_empty(&ctx->active_reqs)) { req = list_first_entry(&ctx->active_reqs, struct aio_kiocb, ki_list); req->ki_cancel(&req->rw); list_del_init(&req->ki_list); } spin_unlock_irq(&ctx->ctx_lock); percpu_ref_kill(&ctx->reqs); percpu_ref_put(&ctx->reqs); } static int ioctx_add_table(struct kioctx *ctx, struct mm_struct *mm) { unsigned i, new_nr; struct kioctx_table *table, *old; struct aio_ring *ring; spin_lock(&mm->ioctx_lock); table = rcu_dereference_raw(mm->ioctx_table); while (1) { if (table) for (i = 0; i < table->nr; i++) if (!rcu_access_pointer(table->table[i])) { ctx->id = i; rcu_assign_pointer(table->table[i], ctx); spin_unlock(&mm->ioctx_lock); /* While kioctx setup is in progress, * we are protected from page migration * changes ring_pages by ->ring_lock. */ ring = kmap_atomic(ctx->ring_pages[0]); ring->id = ctx->id; kunmap_atomic(ring); return 0; } new_nr = (table ? table->nr : 1) * 4; spin_unlock(&mm->ioctx_lock); table = kzalloc(sizeof(*table) + sizeof(struct kioctx *) * new_nr, GFP_KERNEL); if (!table) return -ENOMEM; table->nr = new_nr; spin_lock(&mm->ioctx_lock); old = rcu_dereference_raw(mm->ioctx_table); if (!old) { rcu_assign_pointer(mm->ioctx_table, table); } else if (table->nr > old->nr) { memcpy(table->table, old->table, old->nr * sizeof(struct kioctx *)); rcu_assign_pointer(mm->ioctx_table, table); kfree_rcu(old, rcu); } else { kfree(table); table = old; } } } static void aio_nr_sub(unsigned nr) { spin_lock(&aio_nr_lock); if (WARN_ON(aio_nr - nr > aio_nr)) aio_nr = 0; else aio_nr -= nr; spin_unlock(&aio_nr_lock); } /* ioctx_alloc * Allocates and initializes an ioctx. Returns an ERR_PTR if it failed. */ static struct kioctx *ioctx_alloc(unsigned nr_events) { struct mm_struct *mm = current->mm; struct kioctx *ctx; int err = -ENOMEM; /* * Store the original nr_events -- what userspace passed to io_setup(), * for counting against the global limit -- before it changes. */ unsigned int max_reqs = nr_events; /* * We keep track of the number of available ringbuffer slots, to prevent * overflow (reqs_available), and we also use percpu counters for this. * * So since up to half the slots might be on other cpu's percpu counters * and unavailable, double nr_events so userspace sees what they * expected: additionally, we move req_batch slots to/from percpu * counters at a time, so make sure that isn't 0: */ nr_events = max(nr_events, num_possible_cpus() * 4); nr_events *= 2; /* Prevent overflows */ if (nr_events > (0x10000000U / sizeof(struct io_event))) { pr_debug("ENOMEM: nr_events too high\n"); return ERR_PTR(-EINVAL); } if (!nr_events || (unsigned long)max_reqs > aio_max_nr) return ERR_PTR(-EAGAIN); ctx = kmem_cache_zalloc(kioctx_cachep, GFP_KERNEL); if (!ctx) return ERR_PTR(-ENOMEM); ctx->max_reqs = max_reqs; spin_lock_init(&ctx->ctx_lock); spin_lock_init(&ctx->completion_lock); mutex_init(&ctx->ring_lock); /* Protect against page migration throughout kiotx setup by keeping * the ring_lock mutex held until setup is complete. */ mutex_lock(&ctx->ring_lock); init_waitqueue_head(&ctx->wait); INIT_LIST_HEAD(&ctx->active_reqs); if (percpu_ref_init(&ctx->users, free_ioctx_users, 0, GFP_KERNEL)) goto err; if (percpu_ref_init(&ctx->reqs, free_ioctx_reqs, 0, GFP_KERNEL)) goto err; ctx->cpu = alloc_percpu(struct kioctx_cpu); if (!ctx->cpu) goto err; err = aio_setup_ring(ctx, nr_events); if (err < 0) goto err; atomic_set(&ctx->reqs_available, ctx->nr_events - 1); ctx->req_batch = (ctx->nr_events - 1) / (num_possible_cpus() * 4); if (ctx->req_batch < 1) ctx->req_batch = 1; /* limit the number of system wide aios */ spin_lock(&aio_nr_lock); if (aio_nr + ctx->max_reqs > aio_max_nr || aio_nr + ctx->max_reqs < aio_nr) { spin_unlock(&aio_nr_lock); err = -EAGAIN; goto err_ctx; } aio_nr += ctx->max_reqs; spin_unlock(&aio_nr_lock); percpu_ref_get(&ctx->users); /* io_setup() will drop this ref */ percpu_ref_get(&ctx->reqs); /* free_ioctx_users() will drop this */ err = ioctx_add_table(ctx, mm); if (err) goto err_cleanup; /* Release the ring_lock mutex now that all setup is complete. */ mutex_unlock(&ctx->ring_lock); pr_debug("allocated ioctx %p[%ld]: mm=%p mask=0x%x\n", ctx, ctx->user_id, mm, ctx->nr_events); return ctx; err_cleanup: aio_nr_sub(ctx->max_reqs); err_ctx: atomic_set(&ctx->dead, 1); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); aio_free_ring(ctx); err: mutex_unlock(&ctx->ring_lock); free_percpu(ctx->cpu); percpu_ref_exit(&ctx->reqs); percpu_ref_exit(&ctx->users); kmem_cache_free(kioctx_cachep, ctx); pr_debug("error allocating ioctx %d\n", err); return ERR_PTR(err); } /* kill_ioctx * Cancels all outstanding aio requests on an aio context. Used * when the processes owning a context have all exited to encourage * the rapid destruction of the kioctx. */ static int kill_ioctx(struct mm_struct *mm, struct kioctx *ctx, struct ctx_rq_wait *wait) { struct kioctx_table *table; spin_lock(&mm->ioctx_lock); if (atomic_xchg(&ctx->dead, 1)) { spin_unlock(&mm->ioctx_lock); return -EINVAL; } table = rcu_dereference_raw(mm->ioctx_table); WARN_ON(ctx != rcu_access_pointer(table->table[ctx->id])); RCU_INIT_POINTER(table->table[ctx->id], NULL); spin_unlock(&mm->ioctx_lock); /* free_ioctx_reqs() will do the necessary RCU synchronization */ wake_up_all(&ctx->wait); /* * It'd be more correct to do this in free_ioctx(), after all * the outstanding kiocbs have finished - but by then io_destroy * has already returned, so io_setup() could potentially return * -EAGAIN with no ioctxs actually in use (as far as userspace * could tell). */ aio_nr_sub(ctx->max_reqs); if (ctx->mmap_size) vm_munmap(ctx->mmap_base, ctx->mmap_size); ctx->rq_wait = wait; percpu_ref_kill(&ctx->users); return 0; } /* * exit_aio: called when the last user of mm goes away. At this point, there is * no way for any new requests to be submited or any of the io_* syscalls to be * called on the context. * * There may be outstanding kiocbs, but free_ioctx() will explicitly wait on * them. */ void exit_aio(struct mm_struct *mm) { struct kioctx_table *table = rcu_dereference_raw(mm->ioctx_table); struct ctx_rq_wait wait; int i, skipped; if (!table) return; atomic_set(&wait.count, table->nr); init_completion(&wait.comp); skipped = 0; for (i = 0; i < table->nr; ++i) { struct kioctx *ctx = rcu_dereference_protected(table->table[i], true); if (!ctx) { skipped++; continue; } /* * We don't need to bother with munmap() here - exit_mmap(mm) * is coming and it'll unmap everything. And we simply can't, * this is not necessarily our ->mm. * Since kill_ioctx() uses non-zero ->mmap_size as indicator * that it needs to unmap the area, just set it to 0. */ ctx->mmap_size = 0; kill_ioctx(mm, ctx, &wait); } if (!atomic_sub_and_test(skipped, &wait.count)) { /* Wait until all IO for the context are done. */ wait_for_completion(&wait.comp); } RCU_INIT_POINTER(mm->ioctx_table, NULL); kfree(table); } static void put_reqs_available(struct kioctx *ctx, unsigned nr) { struct kioctx_cpu *kcpu; unsigned long flags; local_irq_save(flags); kcpu = this_cpu_ptr(ctx->cpu); kcpu->reqs_available += nr; while (kcpu->reqs_available >= ctx->req_batch * 2) { kcpu->reqs_available -= ctx->req_batch; atomic_add(ctx->req_batch, &ctx->reqs_available); } local_irq_restore(flags); } static bool __get_reqs_available(struct kioctx *ctx) { struct kioctx_cpu *kcpu; bool ret = false; unsigned long flags; local_irq_save(flags); kcpu = this_cpu_ptr(ctx->cpu); if (!kcpu->reqs_available) { int old, avail = atomic_read(&ctx->reqs_available); do { if (avail < ctx->req_batch) goto out; old = avail; avail = atomic_cmpxchg(&ctx->reqs_available, avail, avail - ctx->req_batch); } while (avail != old); kcpu->reqs_available += ctx->req_batch; } ret = true; kcpu->reqs_available--; out: local_irq_restore(flags); return ret; } /* refill_reqs_available * Updates the reqs_available reference counts used for tracking the * number of free slots in the completion ring. This can be called * from aio_complete() (to optimistically update reqs_available) or * from aio_get_req() (the we're out of events case). It must be * called holding ctx->completion_lock. */ static void refill_reqs_available(struct kioctx *ctx, unsigned head, unsigned tail) { unsigned events_in_ring, completed; /* Clamp head since userland can write to it. */ head %= ctx->nr_events; if (head <= tail) events_in_ring = tail - head; else events_in_ring = ctx->nr_events - (head - tail); completed = ctx->completed_events; if (events_in_ring < completed) completed -= events_in_ring; else completed = 0; if (!completed) return; ctx->completed_events -= completed; put_reqs_available(ctx, completed); } /* user_refill_reqs_available * Called to refill reqs_available when aio_get_req() encounters an * out of space in the completion ring. */ static void user_refill_reqs_available(struct kioctx *ctx) { spin_lock_irq(&ctx->completion_lock); if (ctx->completed_events) { struct aio_ring *ring; unsigned head; /* Access of ring->head may race with aio_read_events_ring() * here, but that's okay since whether we read the old version * or the new version, and either will be valid. The important * part is that head cannot pass tail since we prevent * aio_complete() from updating tail by holding * ctx->completion_lock. Even if head is invalid, the check * against ctx->completed_events below will make sure we do the * safe/right thing. */ ring = kmap_atomic(ctx->ring_pages[0]); head = ring->head; kunmap_atomic(ring); refill_reqs_available(ctx, head, ctx->tail); } spin_unlock_irq(&ctx->completion_lock); } static bool get_reqs_available(struct kioctx *ctx) { if (__get_reqs_available(ctx)) return true; user_refill_reqs_available(ctx); return __get_reqs_available(ctx); } /* aio_get_req * Allocate a slot for an aio request. * Returns NULL if no requests are free. * * The refcount is initialized to 2 - one for the async op completion, * one for the synchronous code that does this. */ static inline struct aio_kiocb *aio_get_req(struct kioctx *ctx) { struct aio_kiocb *req; req = kmem_cache_alloc(kiocb_cachep, GFP_KERNEL); if (unlikely(!req)) return NULL; if (unlikely(!get_reqs_available(ctx))) { kmem_cache_free(kiocb_cachep, req); return NULL; } percpu_ref_get(&ctx->reqs); req->ki_ctx = ctx; INIT_LIST_HEAD(&req->ki_list); refcount_set(&req->ki_refcnt, 2); req->ki_eventfd = NULL; return req; } static struct kioctx *lookup_ioctx(unsigned long ctx_id) { struct aio_ring __user *ring = (void __user *)ctx_id; struct mm_struct *mm = current->mm; struct kioctx *ctx, *ret = NULL; struct kioctx_table *table; unsigned id; if (get_user(id, &ring->id)) return NULL; rcu_read_lock(); table = rcu_dereference(mm->ioctx_table); if (!table || id >= table->nr) goto out; id = array_index_nospec(id, table->nr); ctx = rcu_dereference(table->table[id]); if (ctx && ctx->user_id == ctx_id) { if (percpu_ref_tryget_live(&ctx->users)) ret = ctx; } out: rcu_read_unlock(); return ret; } static inline void iocb_destroy(struct aio_kiocb *iocb) { if (iocb->ki_eventfd) eventfd_ctx_put(iocb->ki_eventfd); if (iocb->ki_filp) fput(iocb->ki_filp); percpu_ref_put(&iocb->ki_ctx->reqs); kmem_cache_free(kiocb_cachep, iocb); } /* aio_complete * Called when the io request on the given iocb is complete. */ static void aio_complete(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; struct aio_ring *ring; struct io_event *ev_page, *event; unsigned tail, pos, head; unsigned long flags; /* * Add a completion event to the ring buffer. Must be done holding * ctx->completion_lock to prevent other code from messing with the tail * pointer since we might be called from irq context. */ spin_lock_irqsave(&ctx->completion_lock, flags); tail = ctx->tail; pos = tail + AIO_EVENTS_OFFSET; if (++tail >= ctx->nr_events) tail = 0; ev_page = kmap_atomic(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); event = ev_page + pos % AIO_EVENTS_PER_PAGE; *event = iocb->ki_res; kunmap_atomic(ev_page); flush_dcache_page(ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]); pr_debug("%p[%u]: %p: %p %Lx %Lx %Lx\n", ctx, tail, iocb, (void __user *)(unsigned long)iocb->ki_res.obj, iocb->ki_res.data, iocb->ki_res.res, iocb->ki_res.res2); /* after flagging the request as done, we * must never even look at it again */ smp_wmb(); /* make event visible before updating tail */ ctx->tail = tail; ring = kmap_atomic(ctx->ring_pages[0]); head = ring->head; ring->tail = tail; kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); ctx->completed_events++; if (ctx->completed_events > 1) refill_reqs_available(ctx, head, tail); spin_unlock_irqrestore(&ctx->completion_lock, flags); pr_debug("added to ring %p at [%u]\n", iocb, tail); /* * Check if the user asked us to deliver the result through an * eventfd. The eventfd_signal() function is safe to be called * from IRQ context. */ if (iocb->ki_eventfd) eventfd_signal(iocb->ki_eventfd, 1); /* * We have to order our ring_info tail store above and test * of the wait list below outside the wait lock. This is * like in wake_up_bit() where clearing a bit has to be * ordered with the unlocked test. */ smp_mb(); if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); } static inline void iocb_put(struct aio_kiocb *iocb) { if (refcount_dec_and_test(&iocb->ki_refcnt)) { aio_complete(iocb); iocb_destroy(iocb); } } /* aio_read_events_ring * Pull an event off of the ioctx's event ring. Returns the number of * events fetched */ static long aio_read_events_ring(struct kioctx *ctx, struct io_event __user *event, long nr) { struct aio_ring *ring; unsigned head, tail, pos; long ret = 0; int copy_ret; /* * The mutex can block and wake us up and that will cause * wait_event_interruptible_hrtimeout() to schedule without sleeping * and repeat. This should be rare enough that it doesn't cause * peformance issues. See the comment in read_events() for more detail. */ sched_annotate_sleep(); mutex_lock(&ctx->ring_lock); /* Access to ->ring_pages here is protected by ctx->ring_lock. */ ring = kmap_atomic(ctx->ring_pages[0]); head = ring->head; tail = ring->tail; kunmap_atomic(ring); /* * Ensure that once we've read the current tail pointer, that * we also see the events that were stored up to the tail. */ smp_rmb(); pr_debug("h%u t%u m%u\n", head, tail, ctx->nr_events); if (head == tail) goto out; head %= ctx->nr_events; tail %= ctx->nr_events; while (ret < nr) { long avail; struct io_event *ev; struct page *page; avail = (head <= tail ? tail : ctx->nr_events) - head; if (head == tail) break; pos = head + AIO_EVENTS_OFFSET; page = ctx->ring_pages[pos / AIO_EVENTS_PER_PAGE]; pos %= AIO_EVENTS_PER_PAGE; avail = min(avail, nr - ret); avail = min_t(long, avail, AIO_EVENTS_PER_PAGE - pos); ev = kmap(page); copy_ret = copy_to_user(event + ret, ev + pos, sizeof(*ev) * avail); kunmap(page); if (unlikely(copy_ret)) { ret = -EFAULT; goto out; } ret += avail; head += avail; head %= ctx->nr_events; } ring = kmap_atomic(ctx->ring_pages[0]); ring->head = head; kunmap_atomic(ring); flush_dcache_page(ctx->ring_pages[0]); pr_debug("%li h%u t%u\n", ret, head, tail); out: mutex_unlock(&ctx->ring_lock); return ret; } static bool aio_read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, long *i) { long ret = aio_read_events_ring(ctx, event + *i, nr - *i); if (ret > 0) *i += ret; if (unlikely(atomic_read(&ctx->dead))) ret = -EINVAL; if (!*i) *i = ret; return ret < 0 || *i >= min_nr; } static long read_events(struct kioctx *ctx, long min_nr, long nr, struct io_event __user *event, ktime_t until) { long ret = 0; /* * Note that aio_read_events() is being called as the conditional - i.e. * we're calling it after prepare_to_wait() has set task state to * TASK_INTERRUPTIBLE. * * But aio_read_events() can block, and if it blocks it's going to flip * the task state back to TASK_RUNNING. * * This should be ok, provided it doesn't flip the state back to * TASK_RUNNING and return 0 too much - that causes us to spin. That * will only happen if the mutex_lock() call blocks, and we then find * the ringbuffer empty. So in practice we should be ok, but it's * something to be aware of when touching this code. */ if (until == 0) aio_read_events(ctx, min_nr, nr, event, &ret); else wait_event_interruptible_hrtimeout(ctx->wait, aio_read_events(ctx, min_nr, nr, event, &ret), until); return ret; } /* sys_io_setup: * Create an aio_context capable of receiving at least nr_events. * ctxp must not point to an aio_context that already exists, and * must be initialized to 0 prior to the call. On successful * creation of the aio_context, *ctxp is filled in with the resulting * handle. May fail with -EINVAL if *ctxp is not initialized, * if the specified nr_events exceeds internal limits. May fail * with -EAGAIN if the specified nr_events exceeds the user's limit * of available events. May fail with -ENOMEM if insufficient kernel * resources are available. May fail with -EFAULT if an invalid * pointer is passed for ctxp. Will fail with -ENOSYS if not * implemented. */ SYSCALL_DEFINE2(io_setup, unsigned, nr_events, aio_context_t __user *, ctxp) { struct kioctx *ioctx = NULL; unsigned long ctx; long ret; ret = get_user(ctx, ctxp); if (unlikely(ret)) goto out; ret = -EINVAL; if (unlikely(ctx || nr_events == 0)) { pr_debug("EINVAL: ctx %lu nr_events %u\n", ctx, nr_events); goto out; } ioctx = ioctx_alloc(nr_events); ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { ret = put_user(ioctx->user_id, ctxp); if (ret) kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } out: return ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_events, u32 __user *, ctx32p) { struct kioctx *ioctx = NULL; unsigned long ctx; long ret; ret = get_user(ctx, ctx32p); if (unlikely(ret)) goto out; ret = -EINVAL; if (unlikely(ctx || nr_events == 0)) { pr_debug("EINVAL: ctx %lu nr_events %u\n", ctx, nr_events); goto out; } ioctx = ioctx_alloc(nr_events); ret = PTR_ERR(ioctx); if (!IS_ERR(ioctx)) { /* truncating is ok because it's a user address */ ret = put_user((u32)ioctx->user_id, ctx32p); if (ret) kill_ioctx(current->mm, ioctx, NULL); percpu_ref_put(&ioctx->users); } out: return ret; } #endif /* sys_io_destroy: * Destroy the aio_context specified. May cancel any outstanding * AIOs and block on completion. Will fail with -ENOSYS if not * implemented. May fail with -EINVAL if the context pointed to * is invalid. */ SYSCALL_DEFINE1(io_destroy, aio_context_t, ctx) { struct kioctx *ioctx = lookup_ioctx(ctx); if (likely(NULL != ioctx)) { struct ctx_rq_wait wait; int ret; init_completion(&wait.comp); atomic_set(&wait.count, 1); /* Pass requests_done to kill_ioctx() where it can be set * in a thread-safe way. If we try to set it here then we have * a race condition if two io_destroy() called simultaneously. */ ret = kill_ioctx(current->mm, ioctx, &wait); percpu_ref_put(&ioctx->users); /* Wait until all IO for the context are done. Otherwise kernel * keep using user-space buffers even if user thinks the context * is destroyed. */ if (!ret) wait_for_completion(&wait.comp); return ret; } pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } static void aio_remove_iocb(struct aio_kiocb *iocb) { struct kioctx *ctx = iocb->ki_ctx; unsigned long flags; spin_lock_irqsave(&ctx->ctx_lock, flags); list_del(&iocb->ki_list); spin_unlock_irqrestore(&ctx->ctx_lock, flags); } static void aio_complete_rw(struct kiocb *kiocb, long res, long res2) { struct aio_kiocb *iocb = container_of(kiocb, struct aio_kiocb, rw); if (!list_empty_careful(&iocb->ki_list)) aio_remove_iocb(iocb); if (kiocb->ki_flags & IOCB_WRITE) { struct inode *inode = file_inode(kiocb->ki_filp); /* * Tell lockdep we inherited freeze protection from submission * thread. */ if (S_ISREG(inode->i_mode)) __sb_writers_acquired(inode->i_sb, SB_FREEZE_WRITE); file_end_write(kiocb->ki_filp); } iocb->ki_res.res = res; iocb->ki_res.res2 = res2; iocb_put(iocb); } static int aio_prep_rw(struct kiocb *req, const struct iocb *iocb) { int ret; req->ki_complete = aio_complete_rw; req->private = NULL; req->ki_pos = iocb->aio_offset; req->ki_flags = iocb_flags(req->ki_filp) | IOCB_AIO_RW; if (iocb->aio_flags & IOCB_FLAG_RESFD) req->ki_flags |= IOCB_EVENTFD; req->ki_hint = ki_hint_validate(file_write_hint(req->ki_filp)); if (iocb->aio_flags & IOCB_FLAG_IOPRIO) { /* * If the IOCB_FLAG_IOPRIO flag of aio_flags is set, then * aio_reqprio is interpreted as an I/O scheduling * class and priority. */ ret = ioprio_check_cap(iocb->aio_reqprio); if (ret) { pr_debug("aio ioprio check cap error: %d\n", ret); return ret; } req->ki_ioprio = iocb->aio_reqprio; } else req->ki_ioprio = get_current_ioprio(); ret = kiocb_set_rw_flags(req, iocb->aio_rw_flags); if (unlikely(ret)) return ret; req->ki_flags &= ~IOCB_HIPRI; /* no one is going to poll for this I/O */ return 0; } static ssize_t aio_setup_rw(int rw, const struct iocb *iocb, struct iovec **iovec, bool vectored, bool compat, struct iov_iter *iter) { void __user *buf = (void __user *)(uintptr_t)iocb->aio_buf; size_t len = iocb->aio_nbytes; if (!vectored) { ssize_t ret = import_single_range(rw, buf, len, *iovec, iter); *iovec = NULL; return ret; } #ifdef CONFIG_COMPAT if (compat) return compat_import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter); #endif return import_iovec(rw, buf, len, UIO_FASTIOV, iovec, iter); } static inline void aio_rw_done(struct kiocb *req, ssize_t ret) { switch (ret) { case -EIOCBQUEUED: break; case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTARTNOHAND: case -ERESTART_RESTARTBLOCK: /* * There's no easy way to restart the syscall since other AIO's * may be already running. Just fail this IO with EINTR. */ ret = -EINTR; /*FALLTHRU*/ default: req->ki_complete(req, ret, 0); } } static int aio_read(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; int ret; ret = aio_prep_rw(req, iocb); if (ret) return ret; file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_READ))) return -EBADF; ret = -EINVAL; if (unlikely(!file->f_op->read_iter)) return -EINVAL; ret = aio_setup_rw(READ, iocb, &iovec, vectored, compat, &iter); if (ret < 0) return ret; ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) aio_rw_done(req, call_read_iter(file, req, &iter)); kfree(iovec); return ret; } static int aio_write(struct kiocb *req, const struct iocb *iocb, bool vectored, bool compat) { struct iovec inline_vecs[UIO_FASTIOV], *iovec = inline_vecs; struct iov_iter iter; struct file *file; int ret; ret = aio_prep_rw(req, iocb); if (ret) return ret; file = req->ki_filp; if (unlikely(!(file->f_mode & FMODE_WRITE))) return -EBADF; if (unlikely(!file->f_op->write_iter)) return -EINVAL; ret = aio_setup_rw(WRITE, iocb, &iovec, vectored, compat, &iter); if (ret < 0) return ret; ret = rw_verify_area(WRITE, file, &req->ki_pos, iov_iter_count(&iter)); if (!ret) { /* * Open-code file_start_write here to grab freeze protection, * which will be released by another thread in * aio_complete_rw(). Fool lockdep by telling it the lock got * released so that it doesn't complain about the held lock when * we return to userspace. */ if (S_ISREG(file_inode(file)->i_mode)) { __sb_start_write(file_inode(file)->i_sb, SB_FREEZE_WRITE, true); __sb_writers_release(file_inode(file)->i_sb, SB_FREEZE_WRITE); } req->ki_flags |= IOCB_WRITE; aio_rw_done(req, call_write_iter(file, req, &iter)); } kfree(iovec); return ret; } static void aio_fsync_work(struct work_struct *work) { struct aio_kiocb *iocb = container_of(work, struct aio_kiocb, fsync.work); const struct cred *old_cred = override_creds(iocb->fsync.creds); iocb->ki_res.res = vfs_fsync(iocb->fsync.file, iocb->fsync.datasync); revert_creds(old_cred); put_cred(iocb->fsync.creds); iocb_put(iocb); } static int aio_fsync(struct fsync_iocb *req, const struct iocb *iocb, bool datasync) { if (unlikely(iocb->aio_buf || iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags)) return -EINVAL; if (unlikely(!req->file->f_op->fsync)) return -EINVAL; req->creds = prepare_creds(); if (!req->creds) return -ENOMEM; req->datasync = datasync; INIT_WORK(&req->work, aio_fsync_work); schedule_work(&req->work); return 0; } static void aio_poll_put_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); iocb_put(iocb); } /* * Safely lock the waitqueue which the request is on, synchronizing with the * case where the ->poll() provider decides to free its waitqueue early. * * Returns true on success, meaning that req->head->lock was locked, req->wait * is on req->head, and an RCU read lock was taken. Returns false if the * request was already removed from its waitqueue (which might no longer exist). */ static bool poll_iocb_lock_wq(struct poll_iocb *req) { wait_queue_head_t *head; /* * While we hold the waitqueue lock and the waitqueue is nonempty, * wake_up_pollfree() will wait for us. However, taking the waitqueue * lock in the first place can race with the waitqueue being freed. * * We solve this as eventpoll does: by taking advantage of the fact that * all users of wake_up_pollfree() will RCU-delay the actual free. If * we enter rcu_read_lock() and see that the pointer to the queue is * non-NULL, we can then lock it without the memory being freed out from * under us, then check whether the request is still on the queue. * * Keep holding rcu_read_lock() as long as we hold the queue lock, in * case the caller deletes the entry from the queue, leaving it empty. * In that case, only RCU prevents the queue memory from being freed. */ rcu_read_lock(); head = smp_load_acquire(&req->head); if (head) { spin_lock(&head->lock); if (!list_empty(&req->wait.entry)) return true; spin_unlock(&head->lock); } rcu_read_unlock(); return false; } static void poll_iocb_unlock_wq(struct poll_iocb *req) { spin_unlock(&req->head->lock); rcu_read_unlock(); } static void aio_poll_complete_work(struct work_struct *work) { struct poll_iocb *req = container_of(work, struct poll_iocb, work); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); struct poll_table_struct pt = { ._key = req->events }; struct kioctx *ctx = iocb->ki_ctx; __poll_t mask = 0; if (!READ_ONCE(req->cancelled)) mask = vfs_poll(req->file, &pt) & req->events; /* * Note that ->ki_cancel callers also delete iocb from active_reqs after * calling ->ki_cancel. We need the ctx_lock roundtrip here to * synchronize with them. In the cancellation case the list_del_init * itself is not actually needed, but harmless so we keep it in to * avoid further branches in the fast path. */ spin_lock_irq(&ctx->ctx_lock); if (poll_iocb_lock_wq(req)) { if (!mask && !READ_ONCE(req->cancelled)) { /* * The request isn't actually ready to be completed yet. * Reschedule completion if another wakeup came in. */ if (req->work_need_resched) { schedule_work(&req->work); req->work_need_resched = false; } else { req->work_scheduled = false; } poll_iocb_unlock_wq(req); spin_unlock_irq(&ctx->ctx_lock); return; } list_del_init(&req->wait.entry); poll_iocb_unlock_wq(req); } /* else, POLLFREE has freed the waitqueue, so we must complete */ list_del_init(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); spin_unlock_irq(&ctx->ctx_lock); iocb_put(iocb); } /* assumes we are called with irqs disabled */ static int aio_poll_cancel(struct kiocb *iocb) { struct aio_kiocb *aiocb = container_of(iocb, struct aio_kiocb, rw); struct poll_iocb *req = &aiocb->poll; if (poll_iocb_lock_wq(req)) { WRITE_ONCE(req->cancelled, true); if (!req->work_scheduled) { schedule_work(&aiocb->poll.work); req->work_scheduled = true; } poll_iocb_unlock_wq(req); } /* else, the request was force-cancelled by POLLFREE already */ return 0; } static int aio_poll_wake(struct wait_queue_entry *wait, unsigned mode, int sync, void *key) { struct poll_iocb *req = container_of(wait, struct poll_iocb, wait); struct aio_kiocb *iocb = container_of(req, struct aio_kiocb, poll); __poll_t mask = key_to_poll(key); unsigned long flags; /* for instances that support it check for an event match first: */ if (mask && !(mask & req->events)) return 0; /* * Complete the request inline if possible. This requires that three * conditions be met: * 1. An event mask must have been passed. If a plain wakeup was done * instead, then mask == 0 and we have to call vfs_poll() to get * the events, so inline completion isn't possible. * 2. The completion work must not have already been scheduled. * 3. ctx_lock must not be busy. We have to use trylock because we * already hold the waitqueue lock, so this inverts the normal * locking order. Use irqsave/irqrestore because not all * filesystems (e.g. fuse) call this function with IRQs disabled, * yet IRQs have to be disabled before ctx_lock is obtained. */ if (mask && !req->work_scheduled && spin_trylock_irqsave(&iocb->ki_ctx->ctx_lock, flags)) { struct kioctx *ctx = iocb->ki_ctx; list_del_init(&req->wait.entry); list_del(&iocb->ki_list); iocb->ki_res.res = mangle_poll(mask); if (iocb->ki_eventfd && eventfd_signal_count()) { iocb = NULL; INIT_WORK(&req->work, aio_poll_put_work); schedule_work(&req->work); } spin_unlock_irqrestore(&ctx->ctx_lock, flags); if (iocb) iocb_put(iocb); } else { /* * Schedule the completion work if needed. If it was already * scheduled, record that another wakeup came in. * * Don't remove the request from the waitqueue here, as it might * not actually be complete yet (we won't know until vfs_poll() * is called), and we must not miss any wakeups. POLLFREE is an * exception to this; see below. */ if (req->work_scheduled) { req->work_need_resched = true; } else { schedule_work(&req->work); req->work_scheduled = true; } /* * If the waitqueue is being freed early but we can't complete * the request inline, we have to tear down the request as best * we can. That means immediately removing the request from its * waitqueue and preventing all further accesses to the * waitqueue via the request. We also need to schedule the * completion work (done above). Also mark the request as * cancelled, to potentially skip an unneeded call to ->poll(). */ if (mask & POLLFREE) { WRITE_ONCE(req->cancelled, true); list_del_init(&req->wait.entry); /* * Careful: this *must* be the last step, since as soon * as req->head is NULL'ed out, the request can be * completed and freed, since aio_poll_complete_work() * will no longer need to take the waitqueue lock. */ smp_store_release(&req->head, NULL); } } return 1; } struct aio_poll_table { struct poll_table_struct pt; struct aio_kiocb *iocb; bool queued; int error; }; static void aio_poll_queue_proc(struct file *file, struct wait_queue_head *head, struct poll_table_struct *p) { struct aio_poll_table *pt = container_of(p, struct aio_poll_table, pt); /* multiple wait queues per file are not supported */ if (unlikely(pt->queued)) { pt->error = -EINVAL; return; } pt->queued = true; pt->error = 0; pt->iocb->poll.head = head; add_wait_queue(head, &pt->iocb->poll.wait); } static int aio_poll(struct aio_kiocb *aiocb, const struct iocb *iocb) { struct kioctx *ctx = aiocb->ki_ctx; struct poll_iocb *req = &aiocb->poll; struct aio_poll_table apt; bool cancel = false; __poll_t mask; /* reject any unknown events outside the normal event mask. */ if ((u16)iocb->aio_buf != iocb->aio_buf) return -EINVAL; /* reject fields that are not defined for poll */ if (iocb->aio_offset || iocb->aio_nbytes || iocb->aio_rw_flags) return -EINVAL; INIT_WORK(&req->work, aio_poll_complete_work); req->events = demangle_poll(iocb->aio_buf) | EPOLLERR | EPOLLHUP; req->head = NULL; req->cancelled = false; req->work_scheduled = false; req->work_need_resched = false; apt.pt._qproc = aio_poll_queue_proc; apt.pt._key = req->events; apt.iocb = aiocb; apt.queued = false; apt.error = -EINVAL; /* same as no support for IOCB_CMD_POLL */ /* initialized the list so that we can do list_empty checks */ INIT_LIST_HEAD(&req->wait.entry); init_waitqueue_func_entry(&req->wait, aio_poll_wake); mask = vfs_poll(req->file, &apt.pt) & req->events; spin_lock_irq(&ctx->ctx_lock); if (likely(apt.queued)) { bool on_queue = poll_iocb_lock_wq(req); if (!on_queue || req->work_scheduled) { /* * aio_poll_wake() already either scheduled the async * completion work, or completed the request inline. */ if (apt.error) /* unsupported case: multiple queues */ cancel = true; apt.error = 0; mask = 0; } if (mask || apt.error) { /* Steal to complete synchronously. */ list_del_init(&req->wait.entry); } else if (cancel) { /* Cancel if possible (may be too late though). */ WRITE_ONCE(req->cancelled, true); } else if (on_queue) { /* * Actually waiting for an event, so add the request to * active_reqs so that it can be cancelled if needed. */ list_add_tail(&aiocb->ki_list, &ctx->active_reqs); aiocb->ki_cancel = aio_poll_cancel; } if (on_queue) poll_iocb_unlock_wq(req); } if (mask) { /* no async, we'd stolen it */ aiocb->ki_res.res = mangle_poll(mask); apt.error = 0; } spin_unlock_irq(&ctx->ctx_lock); if (mask) iocb_put(aiocb); return apt.error; } static int __io_submit_one(struct kioctx *ctx, const struct iocb *iocb, struct iocb __user *user_iocb, struct aio_kiocb *req, bool compat) { req->ki_filp = fget(iocb->aio_fildes); if (unlikely(!req->ki_filp)) return -EBADF; if (iocb->aio_flags & IOCB_FLAG_RESFD) { struct eventfd_ctx *eventfd; /* * If the IOCB_FLAG_RESFD flag of aio_flags is set, get an * instance of the file* now. The file descriptor must be * an eventfd() fd, and will be signaled for each completed * event using the eventfd_signal() function. */ eventfd = eventfd_ctx_fdget(iocb->aio_resfd); if (IS_ERR(eventfd)) return PTR_ERR(eventfd); req->ki_eventfd = eventfd; } if (unlikely(put_user(KIOCB_KEY, &user_iocb->aio_key))) { pr_debug("EFAULT: aio_key\n"); return -EFAULT; } req->ki_res.obj = (u64)(unsigned long)user_iocb; req->ki_res.data = iocb->aio_data; req->ki_res.res = 0; req->ki_res.res2 = 0; switch (iocb->aio_lio_opcode) { case IOCB_CMD_PREAD: return aio_read(&req->rw, iocb, false, compat); case IOCB_CMD_PWRITE: return aio_write(&req->rw, iocb, false, compat); case IOCB_CMD_PREADV: return aio_read(&req->rw, iocb, true, compat); case IOCB_CMD_PWRITEV: return aio_write(&req->rw, iocb, true, compat); case IOCB_CMD_FSYNC: return aio_fsync(&req->fsync, iocb, false); case IOCB_CMD_FDSYNC: return aio_fsync(&req->fsync, iocb, true); case IOCB_CMD_POLL: return aio_poll(req, iocb); default: pr_debug("invalid aio operation %d\n", iocb->aio_lio_opcode); return -EINVAL; } } static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb, bool compat) { struct aio_kiocb *req; struct iocb iocb; int err; if (unlikely(copy_from_user(&iocb, user_iocb, sizeof(iocb)))) return -EFAULT; /* enforce forwards compatibility on users */ if (unlikely(iocb.aio_reserved2)) { pr_debug("EINVAL: reserve field set\n"); return -EINVAL; } /* prevent overflows */ if (unlikely( (iocb.aio_buf != (unsigned long)iocb.aio_buf) || (iocb.aio_nbytes != (size_t)iocb.aio_nbytes) || ((ssize_t)iocb.aio_nbytes < 0) )) { pr_debug("EINVAL: overflow check\n"); return -EINVAL; } req = aio_get_req(ctx); if (unlikely(!req)) return -EAGAIN; err = __io_submit_one(ctx, &iocb, user_iocb, req, compat); /* Done with the synchronous reference */ iocb_put(req); /* * If err is 0, we'd either done aio_complete() ourselves or have * arranged for that to be done asynchronously. Anything non-zero * means that we need to destroy req ourselves. */ if (unlikely(err)) { iocb_destroy(req); put_reqs_available(ctx, 1); } return err; } /* sys_io_submit: * Queue the nr iocbs pointed to by iocbpp for processing. Returns * the number of iocbs queued. May return -EINVAL if the aio_context * specified by ctx_id is invalid, if nr is < 0, if the iocb at * *iocbpp[0] is not properly initialized, if the operation specified * is invalid for the file descriptor in the iocb. May fail with * -EFAULT if any of the data structures point to invalid data. May * fail with -EBADF if the file descriptor specified in the first * iocb is invalid. May fail with -EAGAIN if insufficient resources * are available to queue any iocbs. Will return 0 if nr is 0. Will * fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_submit, aio_context_t, ctx_id, long, nr, struct iocb __user * __user *, iocbpp) { struct kioctx *ctx; long ret = 0; int i = 0; struct blk_plug plug; if (unlikely(nr < 0)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } if (nr > ctx->nr_events) nr = ctx->nr_events; if (nr > AIO_PLUG_THRESHOLD) blk_start_plug(&plug); for (i = 0; i < nr; i++) { struct iocb __user *user_iocb; if (unlikely(get_user(user_iocb, iocbpp + i))) { ret = -EFAULT; break; } ret = io_submit_one(ctx, user_iocb, false); if (ret) break; } if (nr > AIO_PLUG_THRESHOLD) blk_finish_plug(&plug); percpu_ref_put(&ctx->users); return i ? i : ret; } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, int, nr, compat_uptr_t __user *, iocbpp) { struct kioctx *ctx; long ret = 0; int i = 0; struct blk_plug plug; if (unlikely(nr < 0)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) { pr_debug("EINVAL: invalid context id\n"); return -EINVAL; } if (nr > ctx->nr_events) nr = ctx->nr_events; if (nr > AIO_PLUG_THRESHOLD) blk_start_plug(&plug); for (i = 0; i < nr; i++) { compat_uptr_t user_iocb; if (unlikely(get_user(user_iocb, iocbpp + i))) { ret = -EFAULT; break; } ret = io_submit_one(ctx, compat_ptr(user_iocb), true); if (ret) break; } if (nr > AIO_PLUG_THRESHOLD) blk_finish_plug(&plug); percpu_ref_put(&ctx->users); return i ? i : ret; } #endif /* sys_io_cancel: * Attempts to cancel an iocb previously passed to io_submit. If * the operation is successfully cancelled, the resulting event is * copied into the memory pointed to by result without being placed * into the completion queue and 0 is returned. May fail with * -EFAULT if any of the data structures pointed to are invalid. * May fail with -EINVAL if aio_context specified by ctx_id is * invalid. May fail with -EAGAIN if the iocb specified was not * cancelled. Will fail with -ENOSYS if not implemented. */ SYSCALL_DEFINE3(io_cancel, aio_context_t, ctx_id, struct iocb __user *, iocb, struct io_event __user *, result) { struct kioctx *ctx; struct aio_kiocb *kiocb; int ret = -EINVAL; u32 key; u64 obj = (u64)(unsigned long)iocb; if (unlikely(get_user(key, &iocb->aio_key))) return -EFAULT; if (unlikely(key != KIOCB_KEY)) return -EINVAL; ctx = lookup_ioctx(ctx_id); if (unlikely(!ctx)) return -EINVAL; spin_lock_irq(&ctx->ctx_lock); /* TODO: use a hash or array, this sucks. */ list_for_each_entry(kiocb, &ctx->active_reqs, ki_list) { if (kiocb->ki_res.obj == obj) { ret = kiocb->ki_cancel(&kiocb->rw); list_del_init(&kiocb->ki_list); break; } } spin_unlock_irq(&ctx->ctx_lock); if (!ret) { /* * The result argument is no longer used - the io_event is * always delivered via the ring buffer. -EINPROGRESS indicates * cancellation is progress: */ ret = -EINPROGRESS; } percpu_ref_put(&ctx->users); return ret; } static long do_io_getevents(aio_context_t ctx_id, long min_nr, long nr, struct io_event __user *events, struct timespec64 *ts) { ktime_t until = ts ? timespec64_to_ktime(*ts) : KTIME_MAX; struct kioctx *ioctx = lookup_ioctx(ctx_id); long ret = -EINVAL; if (likely(ioctx)) { if (likely(min_nr <= nr && min_nr >= 0)) ret = read_events(ioctx, min_nr, nr, events, until); percpu_ref_put(&ioctx->users); } return ret; } /* io_getevents: * Attempts to read at least min_nr events and up to nr events from * the completion queue for the aio_context specified by ctx_id. If * it succeeds, the number of read events is returned. May fail with * -EINVAL if ctx_id is invalid, if min_nr is out of range, if nr is * out of range, if timeout is out of range. May fail with -EFAULT * if any of the memory specified is invalid. May return 0 or * < min_nr if the timeout specified by timeout has elapsed * before sufficient events are available, where timeout == NULL * specifies an infinite timeout. Note that the timeout pointed to by * timeout is relative. Will fail with -ENOSYS if not implemented. */ #if !defined(CONFIG_64BIT_TIME) || defined(CONFIG_64BIT) SYSCALL_DEFINE5(io_getevents, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout) { struct timespec64 ts; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); if (!ret && signal_pending(current)) ret = -EINTR; return ret; } #endif struct __aio_sigset { const sigset_t __user *sigmask; size_t sigsetsize; }; SYSCALL_DEFINE6(io_pgetevents, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout, const struct __aio_sigset __user *, usig) { struct __aio_sigset ksig = { NULL, }; struct timespec64 ts; bool interrupted; int ret; if (timeout && unlikely(get_timespec64(&ts, timeout))) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #if defined(CONFIG_COMPAT_32BIT_TIME) && !defined(CONFIG_64BIT) SYSCALL_DEFINE6(io_pgetevents_time32, aio_context_t, ctx_id, long, min_nr, long, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout, const struct __aio_sigset __user *, usig) { struct __aio_sigset ksig = { NULL, }; struct timespec64 ts; bool interrupted; int ret; if (timeout && unlikely(get_old_timespec32(&ts, timeout))) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_user_sigmask(ksig.sigmask, ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &ts : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif #if defined(CONFIG_COMPAT_32BIT_TIME) SYSCALL_DEFINE5(io_getevents_time32, __u32, ctx_id, __s32, min_nr, __s32, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout) { struct timespec64 t; int ret; if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); if (!ret && signal_pending(current)) ret = -EINTR; return ret; } #endif #ifdef CONFIG_COMPAT struct __compat_aio_sigset { compat_uptr_t sigmask; compat_size_t sigsetsize; }; #if defined(CONFIG_COMPAT_32BIT_TIME) COMPAT_SYSCALL_DEFINE6(io_pgetevents, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, struct old_timespec32 __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; if (timeout && get_old_timespec32(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif COMPAT_SYSCALL_DEFINE6(io_pgetevents_time64, compat_aio_context_t, ctx_id, compat_long_t, min_nr, compat_long_t, nr, struct io_event __user *, events, struct __kernel_timespec __user *, timeout, const struct __compat_aio_sigset __user *, usig) { struct __compat_aio_sigset ksig = { 0, }; struct timespec64 t; bool interrupted; int ret; if (timeout && get_timespec64(&t, timeout)) return -EFAULT; if (usig && copy_from_user(&ksig, usig, sizeof(ksig))) return -EFAULT; ret = set_compat_user_sigmask(compat_ptr(ksig.sigmask), ksig.sigsetsize); if (ret) return ret; ret = do_io_getevents(ctx_id, min_nr, nr, events, timeout ? &t : NULL); interrupted = signal_pending(current); restore_saved_sigmask_unless(interrupted); if (interrupted && !ret) ret = -ERESTARTNOHAND; return ret; } #endif |
| 12 72 72 101 10 79 72 15 10 12 29 29 29 29 5 6 21 6 5 20 23 29 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 | // SPDX-License-Identifier: GPL-2.0 /* * Performance events callchain code, extracted from core.c: * * Copyright (C) 2008 Thomas Gleixner <tglx@linutronix.de> * Copyright (C) 2008-2011 Red Hat, Inc., Ingo Molnar * Copyright (C) 2008-2011 Red Hat, Inc., Peter Zijlstra * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com> */ #include <linux/perf_event.h> #include <linux/slab.h> #include <linux/sched/task_stack.h> #include "internal.h" struct callchain_cpus_entries { struct rcu_head rcu_head; struct perf_callchain_entry *cpu_entries[0]; }; int sysctl_perf_event_max_stack __read_mostly = PERF_MAX_STACK_DEPTH; int sysctl_perf_event_max_contexts_per_stack __read_mostly = PERF_MAX_CONTEXTS_PER_STACK; static inline size_t perf_callchain_entry__sizeof(void) { return (sizeof(struct perf_callchain_entry) + sizeof(__u64) * (sysctl_perf_event_max_stack + sysctl_perf_event_max_contexts_per_stack)); } static DEFINE_PER_CPU(int, callchain_recursion[PERF_NR_CONTEXTS]); static atomic_t nr_callchain_events; static DEFINE_MUTEX(callchain_mutex); static struct callchain_cpus_entries *callchain_cpus_entries; __weak void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { } __weak void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs) { } static void release_callchain_buffers_rcu(struct rcu_head *head) { struct callchain_cpus_entries *entries; int cpu; entries = container_of(head, struct callchain_cpus_entries, rcu_head); for_each_possible_cpu(cpu) kfree(entries->cpu_entries[cpu]); kfree(entries); } static void release_callchain_buffers(void) { struct callchain_cpus_entries *entries; entries = callchain_cpus_entries; RCU_INIT_POINTER(callchain_cpus_entries, NULL); call_rcu(&entries->rcu_head, release_callchain_buffers_rcu); } static int alloc_callchain_buffers(void) { int cpu; int size; struct callchain_cpus_entries *entries; /* * We can't use the percpu allocation API for data that can be * accessed from NMI. Use a temporary manual per cpu allocation * until that gets sorted out. */ size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]); entries = kzalloc(size, GFP_KERNEL); if (!entries) return -ENOMEM; size = perf_callchain_entry__sizeof() * PERF_NR_CONTEXTS; for_each_possible_cpu(cpu) { entries->cpu_entries[cpu] = kmalloc_node(size, GFP_KERNEL, cpu_to_node(cpu)); if (!entries->cpu_entries[cpu]) goto fail; } rcu_assign_pointer(callchain_cpus_entries, entries); return 0; fail: for_each_possible_cpu(cpu) kfree(entries->cpu_entries[cpu]); kfree(entries); return -ENOMEM; } int get_callchain_buffers(int event_max_stack) { int err = 0; int count; mutex_lock(&callchain_mutex); count = atomic_inc_return(&nr_callchain_events); if (WARN_ON_ONCE(count < 1)) { err = -EINVAL; goto exit; } /* * If requesting per event more than the global cap, * return a different error to help userspace figure * this out. * * And also do it here so that we have &callchain_mutex held. */ if (event_max_stack > sysctl_perf_event_max_stack) { err = -EOVERFLOW; goto exit; } if (count == 1) err = alloc_callchain_buffers(); exit: if (err) atomic_dec(&nr_callchain_events); mutex_unlock(&callchain_mutex); return err; } void put_callchain_buffers(void) { if (atomic_dec_and_mutex_lock(&nr_callchain_events, &callchain_mutex)) { release_callchain_buffers(); mutex_unlock(&callchain_mutex); } } static struct perf_callchain_entry *get_callchain_entry(int *rctx) { int cpu; struct callchain_cpus_entries *entries; *rctx = get_recursion_context(this_cpu_ptr(callchain_recursion)); if (*rctx == -1) return NULL; entries = rcu_dereference(callchain_cpus_entries); if (!entries) return NULL; cpu = smp_processor_id(); return (((void *)entries->cpu_entries[cpu]) + (*rctx * perf_callchain_entry__sizeof())); } static void put_callchain_entry(int rctx) { put_recursion_context(this_cpu_ptr(callchain_recursion), rctx); } struct perf_callchain_entry * get_perf_callchain(struct pt_regs *regs, u32 init_nr, bool kernel, bool user, u32 max_stack, bool crosstask, bool add_mark) { struct perf_callchain_entry *entry; struct perf_callchain_entry_ctx ctx; int rctx; entry = get_callchain_entry(&rctx); if (rctx == -1) return NULL; if (!entry) goto exit_put; ctx.entry = entry; ctx.max_stack = max_stack; ctx.nr = entry->nr = init_nr; ctx.contexts = 0; ctx.contexts_maxed = false; if (kernel && !user_mode(regs)) { if (add_mark) perf_callchain_store_context(&ctx, PERF_CONTEXT_KERNEL); perf_callchain_kernel(&ctx, regs); } if (user) { if (!user_mode(regs)) { if (current->mm) regs = task_pt_regs(current); else regs = NULL; } if (regs) { mm_segment_t fs; if (crosstask) goto exit_put; if (add_mark) perf_callchain_store_context(&ctx, PERF_CONTEXT_USER); fs = get_fs(); set_fs(USER_DS); perf_callchain_user(&ctx, regs); set_fs(fs); } } exit_put: put_callchain_entry(rctx); return entry; } /* * Used for sysctl_perf_event_max_stack and * sysctl_perf_event_max_contexts_per_stack. */ int perf_event_max_stack_handler(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { int *value = table->data; int new_value = *value, ret; struct ctl_table new_table = *table; new_table.data = &new_value; ret = proc_dointvec_minmax(&new_table, write, buffer, lenp, ppos); if (ret || !write) return ret; mutex_lock(&callchain_mutex); if (atomic_read(&nr_callchain_events)) ret = -EBUSY; else *value = new_value; mutex_unlock(&callchain_mutex); return ret; } |
| 943 1689 62 2819 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * Read-Copy Update mechanism for mutual exclusion * * Copyright IBM Corporation, 2001 * * Author: Dipankar Sarma <dipankar@in.ibm.com> * * Based on the original work by Paul McKenney <paulmck@vnet.ibm.com> * and inputs from Rusty Russell, Andrea Arcangeli and Andi Kleen. * Papers: * http://www.rdrop.com/users/paulmck/paper/rclockpdcsproof.pdf * http://lse.sourceforge.net/locking/rclock_OLS.2001.05.01c.sc.pdf (OLS2001) * * For detailed explanation of Read-Copy Update mechanism see - * http://lse.sourceforge.net/locking/rcupdate.html * */ #ifndef __LINUX_RCUPDATE_H #define __LINUX_RCUPDATE_H #include <linux/types.h> #include <linux/compiler.h> #include <linux/atomic.h> #include <linux/irqflags.h> #include <linux/preempt.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <asm/processor.h> #include <linux/cpumask.h> #define ULONG_CMP_GE(a, b) (ULONG_MAX / 2 >= (a) - (b)) #define ULONG_CMP_LT(a, b) (ULONG_MAX / 2 < (a) - (b)) #define ulong2long(a) (*(long *)(&(a))) /* Exported common interfaces */ void call_rcu(struct rcu_head *head, rcu_callback_t func); void rcu_barrier_tasks(void); void synchronize_rcu(void); #ifdef CONFIG_PREEMPT_RCU void __rcu_read_lock(void); void __rcu_read_unlock(void); /* * Defined as a macro as it is a very low level header included from * areas that don't even know about current. This gives the rcu_read_lock() * nesting depth, but makes sense only if CONFIG_PREEMPT_RCU -- in other * types of kernel builds, the rcu_read_lock() nesting depth is unknowable. */ #define rcu_preempt_depth() (current->rcu_read_lock_nesting) #else /* #ifdef CONFIG_PREEMPT_RCU */ static inline void __rcu_read_lock(void) { preempt_disable(); } static inline void __rcu_read_unlock(void) { preempt_enable(); } static inline int rcu_preempt_depth(void) { return 0; } #endif /* #else #ifdef CONFIG_PREEMPT_RCU */ /* Internal to kernel */ void rcu_init(void); extern int rcu_scheduler_active __read_mostly; void rcu_sched_clock_irq(int user); void rcu_report_dead(unsigned int cpu); void rcutree_migrate_callbacks(int cpu); #ifdef CONFIG_RCU_STALL_COMMON void rcu_sysrq_start(void); void rcu_sysrq_end(void); #else /* #ifdef CONFIG_RCU_STALL_COMMON */ static inline void rcu_sysrq_start(void) { } static inline void rcu_sysrq_end(void) { } #endif /* #else #ifdef CONFIG_RCU_STALL_COMMON */ #ifdef CONFIG_NO_HZ_FULL void rcu_user_enter(void); void rcu_user_exit(void); #else static inline void rcu_user_enter(void) { } static inline void rcu_user_exit(void) { } #endif /* CONFIG_NO_HZ_FULL */ #ifdef CONFIG_RCU_NOCB_CPU void rcu_init_nohz(void); void rcu_nocb_flush_deferred_wakeup(void); #else /* #ifdef CONFIG_RCU_NOCB_CPU */ static inline void rcu_init_nohz(void) { } static inline void rcu_nocb_flush_deferred_wakeup(void) { } #endif /* #else #ifdef CONFIG_RCU_NOCB_CPU */ /** * RCU_NONIDLE - Indicate idle-loop code that needs RCU readers * @a: Code that RCU needs to pay attention to. * * RCU read-side critical sections are forbidden in the inner idle loop, * that is, between the rcu_idle_enter() and the rcu_idle_exit() -- RCU * will happily ignore any such read-side critical sections. However, * things like powertop need tracepoints in the inner idle loop. * * This macro provides the way out: RCU_NONIDLE(do_something_with_RCU()) * will tell RCU that it needs to pay attention, invoke its argument * (in this example, calling the do_something_with_RCU() function), * and then tell RCU to go back to ignoring this CPU. It is permissible * to nest RCU_NONIDLE() wrappers, but not indefinitely (but the limit is * on the order of a million or so, even on 32-bit systems). It is * not legal to block within RCU_NONIDLE(), nor is it permissible to * transfer control either into or out of RCU_NONIDLE()'s statement. */ #define RCU_NONIDLE(a) \ do { \ rcu_irq_enter_irqson(); \ do { a; } while (0); \ rcu_irq_exit_irqson(); \ } while (0) /* * Note a quasi-voluntary context switch for RCU-tasks's benefit. * This is a macro rather than an inline function to avoid #include hell. */ #ifdef CONFIG_TASKS_RCU #define rcu_tasks_qs(t) \ do { \ if (READ_ONCE((t)->rcu_tasks_holdout)) \ WRITE_ONCE((t)->rcu_tasks_holdout, false); \ } while (0) #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t) void call_rcu_tasks(struct rcu_head *head, rcu_callback_t func); void synchronize_rcu_tasks(void); void exit_tasks_rcu_start(void); void exit_tasks_rcu_finish(void); #else /* #ifdef CONFIG_TASKS_RCU */ #define rcu_tasks_qs(t) do { } while (0) #define rcu_note_voluntary_context_switch(t) do { } while (0) #define call_rcu_tasks call_rcu #define synchronize_rcu_tasks synchronize_rcu static inline void exit_tasks_rcu_start(void) { } static inline void exit_tasks_rcu_finish(void) { } #endif /* #else #ifdef CONFIG_TASKS_RCU */ /** * cond_resched_tasks_rcu_qs - Report potential quiescent states to RCU * * This macro resembles cond_resched(), except that it is defined to * report potential quiescent states to RCU-tasks even if the cond_resched() * machinery were to be shut off, as some advocate for PREEMPT kernels. */ #define cond_resched_tasks_rcu_qs() \ do { \ rcu_tasks_qs(current); \ cond_resched(); \ } while (0) /** * rcu_softirq_qs_periodic - Report RCU and RCU-Tasks quiescent states * @old_ts: jiffies at start of processing. * * This helper is for long-running softirq handlers, such as NAPI threads in * networking. The caller should initialize the variable passed in as @old_ts * at the beginning of the softirq handler. When invoked frequently, this macro * will invoke rcu_softirq_qs() every 100 milliseconds thereafter, which will * provide both RCU and RCU-Tasks quiescent states. Note that this macro * modifies its old_ts argument. * * Because regions of code that have disabled softirq act as RCU read-side * critical sections, this macro should be invoked with softirq (and * preemption) enabled. * * The macro is not needed when CONFIG_PREEMPT_RT is defined. RT kernels would * have more chance to invoke schedule() calls and provide necessary quiescent * states. As a contrast, calling cond_resched() only won't achieve the same * effect because cond_resched() does not provide RCU-Tasks quiescent states. */ #define rcu_softirq_qs_periodic(old_ts) \ do { \ if (!IS_ENABLED(CONFIG_PREEMPT_RT) && \ time_after(jiffies, (old_ts) + HZ / 10)) { \ preempt_disable(); \ rcu_softirq_qs(); \ preempt_enable(); \ (old_ts) = jiffies; \ } \ } while (0) /* * Infrastructure to implement the synchronize_() primitives in * TREE_RCU and rcu_barrier_() primitives in TINY_RCU. */ #if defined(CONFIG_TREE_RCU) || defined(CONFIG_PREEMPT_RCU) #include <linux/rcutree.h> #elif defined(CONFIG_TINY_RCU) #include <linux/rcutiny.h> #else #error "Unknown RCU implementation specified to kernel configuration" #endif /* * The init_rcu_head_on_stack() and destroy_rcu_head_on_stack() calls * are needed for dynamic initialization and destruction of rcu_head * on the stack, and init_rcu_head()/destroy_rcu_head() are needed for * dynamic initialization and destruction of statically allocated rcu_head * structures. However, rcu_head structures allocated dynamically in the * heap don't need any initialization. */ #ifdef CONFIG_DEBUG_OBJECTS_RCU_HEAD void init_rcu_head(struct rcu_head *head); void destroy_rcu_head(struct rcu_head *head); void init_rcu_head_on_stack(struct rcu_head *head); void destroy_rcu_head_on_stack(struct rcu_head *head); #else /* !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ static inline void init_rcu_head(struct rcu_head *head) { } static inline void destroy_rcu_head(struct rcu_head *head) { } static inline void init_rcu_head_on_stack(struct rcu_head *head) { } static inline void destroy_rcu_head_on_stack(struct rcu_head *head) { } #endif /* #else !CONFIG_DEBUG_OBJECTS_RCU_HEAD */ #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) bool rcu_lockdep_current_cpu_online(void); #else /* #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ static inline bool rcu_lockdep_current_cpu_online(void) { return true; } #endif /* #else #if defined(CONFIG_HOTPLUG_CPU) && defined(CONFIG_PROVE_RCU) */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static inline void rcu_lock_acquire(struct lockdep_map *map) { lock_acquire(map, 0, 0, 2, 0, NULL, _THIS_IP_); } static inline void rcu_lock_release(struct lockdep_map *map) { lock_release(map, 1, _THIS_IP_); } extern struct lockdep_map rcu_lock_map; extern struct lockdep_map rcu_bh_lock_map; extern struct lockdep_map rcu_sched_lock_map; extern struct lockdep_map rcu_callback_map; int debug_lockdep_rcu_enabled(void); int rcu_read_lock_held(void); int rcu_read_lock_bh_held(void); int rcu_read_lock_sched_held(void); int rcu_read_lock_any_held(void); #else /* #ifdef CONFIG_DEBUG_LOCK_ALLOC */ # define rcu_lock_acquire(a) do { } while (0) # define rcu_lock_release(a) do { } while (0) static inline int rcu_read_lock_held(void) { return 1; } static inline int rcu_read_lock_bh_held(void) { return 1; } static inline int rcu_read_lock_sched_held(void) { return !preemptible(); } static inline int rcu_read_lock_any_held(void) { return !preemptible(); } #endif /* #else #ifdef CONFIG_DEBUG_LOCK_ALLOC */ #ifdef CONFIG_PROVE_RCU /** * RCU_LOCKDEP_WARN - emit lockdep splat if specified condition is met * @c: condition to check * @s: informative message */ #define RCU_LOCKDEP_WARN(c, s) \ do { \ static bool __section(.data.unlikely) __warned; \ if (debug_lockdep_rcu_enabled() && !__warned && (c)) { \ __warned = true; \ lockdep_rcu_suspicious(__FILE__, __LINE__, s); \ } \ } while (0) #if defined(CONFIG_PROVE_RCU) && !defined(CONFIG_PREEMPT_RCU) static inline void rcu_preempt_sleep_check(void) { RCU_LOCKDEP_WARN(lock_is_held(&rcu_lock_map), "Illegal context switch in RCU read-side critical section"); } #else /* #ifdef CONFIG_PROVE_RCU */ static inline void rcu_preempt_sleep_check(void) { } #endif /* #else #ifdef CONFIG_PROVE_RCU */ #define rcu_sleep_check() \ do { \ rcu_preempt_sleep_check(); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_bh_lock_map), \ "Illegal context switch in RCU-bh read-side critical section"); \ RCU_LOCKDEP_WARN(lock_is_held(&rcu_sched_lock_map), \ "Illegal context switch in RCU-sched read-side critical section"); \ } while (0) #else /* #ifdef CONFIG_PROVE_RCU */ #define RCU_LOCKDEP_WARN(c, s) do { } while (0) #define rcu_sleep_check() do { } while (0) #endif /* #else #ifdef CONFIG_PROVE_RCU */ /* * Helper functions for rcu_dereference_check(), rcu_dereference_protected() * and rcu_assign_pointer(). Some of these could be folded into their * callers, but they are left separate in order to ease introduction of * multiple pointers markings to match different RCU implementations * (e.g., __srcu), should this make sense in the future. */ #ifdef __CHECKER__ #define rcu_check_sparse(p, space) \ ((void)(((typeof(*p) space *)p) == p)) #else /* #ifdef __CHECKER__ */ #define rcu_check_sparse(p, space) #endif /* #else #ifdef __CHECKER__ */ #define __rcu_access_pointer(p, space) \ ({ \ typeof(*p) *_________p1 = (typeof(*p) *__force)READ_ONCE(p); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(_________p1)); \ }) #define __rcu_dereference_check(p, c, space) \ ({ \ /* Dependency order vs. p above. */ \ typeof(*p) *________p1 = (typeof(*p) *__force)READ_ONCE(p); \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_check() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) #define __rcu_dereference_protected(p, c, space) \ ({ \ RCU_LOCKDEP_WARN(!(c), "suspicious rcu_dereference_protected() usage"); \ rcu_check_sparse(p, space); \ ((typeof(*p) __force __kernel *)(p)); \ }) #define rcu_dereference_raw(p) \ ({ \ /* Dependency order vs. p above. */ \ typeof(p) ________p1 = READ_ONCE(p); \ ((typeof(*p) __force __kernel *)(________p1)); \ }) /** * RCU_INITIALIZER() - statically initialize an RCU-protected global variable * @v: The value to statically initialize with. */ #define RCU_INITIALIZER(v) (typeof(*(v)) __force __rcu *)(v) /** * rcu_assign_pointer() - assign to RCU-protected pointer * @p: pointer to assign to * @v: value to assign (publish) * * Assigns the specified value to the specified RCU-protected * pointer, ensuring that any concurrent RCU readers will see * any prior initialization. * * Inserts memory barriers on architectures that require them * (which is most of them), and also prevents the compiler from * reordering the code that initializes the structure after the pointer * assignment. More importantly, this call documents which pointers * will be dereferenced by RCU read-side code. * * In some special cases, you may use RCU_INIT_POINTER() instead * of rcu_assign_pointer(). RCU_INIT_POINTER() is a bit faster due * to the fact that it does not constrain either the CPU or the compiler. * That said, using RCU_INIT_POINTER() when you should have used * rcu_assign_pointer() is a very bad thing that results in * impossible-to-diagnose memory corruption. So please be careful. * See the RCU_INIT_POINTER() comment header for details. * * Note that rcu_assign_pointer() evaluates each of its arguments only * once, appearances notwithstanding. One of the "extra" evaluations * is in typeof() and the other visible only to sparse (__CHECKER__), * neither of which actually execute the argument. As with most cpp * macros, this execute-arguments-only-once property is important, so * please be careful when making changes to rcu_assign_pointer() and the * other macros that it invokes. */ #define rcu_assign_pointer(p, v) \ do { \ uintptr_t _r_a_p__v = (uintptr_t)(v); \ rcu_check_sparse(p, __rcu); \ \ if (__builtin_constant_p(v) && (_r_a_p__v) == (uintptr_t)NULL) \ WRITE_ONCE((p), (typeof(p))(_r_a_p__v)); \ else \ smp_store_release(&p, RCU_INITIALIZER((typeof(p))_r_a_p__v)); \ } while (0) /** * rcu_replace_pointer() - replace an RCU pointer, returning its old value * @rcu_ptr: RCU pointer, whose old value is returned * @ptr: regular pointer * @c: the lockdep conditions under which the dereference will take place * * Perform a replacement, where @rcu_ptr is an RCU-annotated * pointer and @c is the lockdep argument that is passed to the * rcu_dereference_protected() call used to read that pointer. The old * value of @rcu_ptr is returned, and @rcu_ptr is set to @ptr. */ #define rcu_replace_pointer(rcu_ptr, ptr, c) \ ({ \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ __tmp; \ }) /** * rcu_swap_protected() - swap an RCU and a regular pointer * @rcu_ptr: RCU pointer * @ptr: regular pointer * @c: the conditions under which the dereference will take place * * Perform swap(@rcu_ptr, @ptr) where @rcu_ptr is an RCU-annotated pointer and * @c is the argument that is passed to the rcu_dereference_protected() call * used to read that pointer. */ #define rcu_swap_protected(rcu_ptr, ptr, c) do { \ typeof(ptr) __tmp = rcu_dereference_protected((rcu_ptr), (c)); \ rcu_assign_pointer((rcu_ptr), (ptr)); \ (ptr) = __tmp; \ } while (0) /** * rcu_access_pointer() - fetch RCU pointer with no dereferencing * @p: The pointer to read * * Return the value of the specified RCU-protected pointer, but omit the * lockdep checks for being in an RCU read-side critical section. This is * useful when the value of this pointer is accessed, but the pointer is * not dereferenced, for example, when testing an RCU-protected pointer * against NULL. Although rcu_access_pointer() may also be used in cases * where update-side locks prevent the value of the pointer from changing, * you should instead use rcu_dereference_protected() for this use case. * * It is also permissible to use rcu_access_pointer() when read-side * access to the pointer was removed at least one grace period ago, as * is the case in the context of the RCU callback that is freeing up * the data, or after a synchronize_rcu() returns. This can be useful * when tearing down multi-linked structures after a grace period * has elapsed. */ #define rcu_access_pointer(p) __rcu_access_pointer((p), __rcu) /** * rcu_dereference_check() - rcu_dereference with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Do an rcu_dereference(), but check that the conditions under which the * dereference will take place are correct. Typically the conditions * indicate the various locking conditions that should be held at that * point. The check should return true if the conditions are satisfied. * An implicit check for being in an RCU read-side critical section * (rcu_read_lock()) is included. * * For example: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock)); * * could be used to indicate to lockdep that foo->bar may only be dereferenced * if either rcu_read_lock() is held, or that the lock required to replace * the bar struct at foo->bar is held. * * Note that the list of conditions may also include indications of when a lock * need not be held, for example during initialisation or destruction of the * target struct: * * bar = rcu_dereference_check(foo->bar, lockdep_is_held(&foo->lock) || * atomic_read(&foo->usage) == 0); * * Inserts memory barriers on architectures that require them * (currently only the Alpha), prevents the compiler from refetching * (and from merging fetches), and, more importantly, documents exactly * which pointers are protected by RCU and checks that the pointer is * annotated as __rcu. */ #define rcu_dereference_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_held(), __rcu) /** * rcu_dereference_bh_check() - rcu_dereference_bh with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-bh counterpart to rcu_dereference_check(). */ #define rcu_dereference_bh_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_bh_held(), __rcu) /** * rcu_dereference_sched_check() - rcu_dereference_sched with debug checking * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * This is the RCU-sched counterpart to rcu_dereference_check(). */ #define rcu_dereference_sched_check(p, c) \ __rcu_dereference_check((p), (c) || rcu_read_lock_sched_held(), \ __rcu) /* * The tracing infrastructure traces RCU (we want that), but unfortunately * some of the RCU checks causes tracing to lock up the system. * * The no-tracing version of rcu_dereference_raw() must not call * rcu_read_lock_held(). */ #define rcu_dereference_raw_check(p) __rcu_dereference_check((p), 1, __rcu) /** * rcu_dereference_protected() - fetch RCU pointer when updates prevented * @p: The pointer to read, prior to dereferencing * @c: The conditions under which the dereference will take place * * Return the value of the specified RCU-protected pointer, but omit * the READ_ONCE(). This is useful in cases where update-side locks * prevent the value of the pointer from changing. Please note that this * primitive does *not* prevent the compiler from repeating this reference * or combining it with other references, so it should not be used without * protection of appropriate locks. * * This function is only for update-side use. Using this function * when protected only by rcu_read_lock() will result in infrequent * but very ugly failures. */ #define rcu_dereference_protected(p, c) \ __rcu_dereference_protected((p), (c), __rcu) /** * rcu_dereference() - fetch RCU-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * This is a simple wrapper around rcu_dereference_check(). */ #define rcu_dereference(p) rcu_dereference_check(p, 0) /** * rcu_dereference_bh() - fetch an RCU-bh-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_bh(p) rcu_dereference_bh_check(p, 0) /** * rcu_dereference_sched() - fetch RCU-sched-protected pointer for dereferencing * @p: The pointer to read, prior to dereferencing * * Makes rcu_dereference_check() do the dirty work. */ #define rcu_dereference_sched(p) rcu_dereference_sched_check(p, 0) /** * rcu_pointer_handoff() - Hand off a pointer from RCU to other mechanism * @p: The pointer to hand off * * This is simply an identity function, but it documents where a pointer * is handed off from RCU to some other synchronization mechanism, for * example, reference counting or locking. In C11, it would map to * kill_dependency(). It could be used as follows:: * * rcu_read_lock(); * p = rcu_dereference(gp); * long_lived = is_long_lived(p); * if (long_lived) { * if (!atomic_inc_not_zero(p->refcnt)) * long_lived = false; * else * p = rcu_pointer_handoff(p); * } * rcu_read_unlock(); */ #define rcu_pointer_handoff(p) (p) /** * rcu_read_lock() - mark the beginning of an RCU read-side critical section * * When synchronize_rcu() is invoked on one CPU while other CPUs * are within RCU read-side critical sections, then the * synchronize_rcu() is guaranteed to block until after all the other * CPUs exit their critical sections. Similarly, if call_rcu() is invoked * on one CPU while other CPUs are within RCU read-side critical * sections, invocation of the corresponding RCU callback is deferred * until after the all the other CPUs exit their critical sections. * * Note, however, that RCU callbacks are permitted to run concurrently * with new RCU read-side critical sections. One way that this can happen * is via the following sequence of events: (1) CPU 0 enters an RCU * read-side critical section, (2) CPU 1 invokes call_rcu() to register * an RCU callback, (3) CPU 0 exits the RCU read-side critical section, * (4) CPU 2 enters a RCU read-side critical section, (5) the RCU * callback is invoked. This is legal, because the RCU read-side critical * section that was running concurrently with the call_rcu() (and which * therefore might be referencing something that the corresponding RCU * callback would free up) has completed before the corresponding * RCU callback is invoked. * * RCU read-side critical sections may be nested. Any deferred actions * will be deferred until the outermost RCU read-side critical section * completes. * * You can avoid reading and understanding the next paragraph by * following this rule: don't put anything in an rcu_read_lock() RCU * read-side critical section that would block in a !PREEMPT kernel. * But if you want the full story, read on! * * In non-preemptible RCU implementations (TREE_RCU and TINY_RCU), * it is illegal to block while in an RCU read-side critical section. * In preemptible RCU implementations (PREEMPT_RCU) in CONFIG_PREEMPTION * kernel builds, RCU read-side critical sections may be preempted, * but explicit blocking is illegal. Finally, in preemptible RCU * implementations in real-time (with -rt patchset) kernel builds, RCU * read-side critical sections may be preempted and they may also block, but * only when acquiring spinlocks that are subject to priority inheritance. */ static __always_inline void rcu_read_lock(void) { __rcu_read_lock(); __acquire(RCU); rcu_lock_acquire(&rcu_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock() used illegally while idle"); } /* * So where is rcu_write_lock()? It does not exist, as there is no * way for writers to lock out RCU readers. This is a feature, not * a bug -- this property is what provides RCU's performance benefits. * Of course, writers must coordinate with each other. The normal * spinlock primitives work well for this, but any other technique may be * used as well. RCU does not care how the writers keep out of each * others' way, as long as they do so. */ /** * rcu_read_unlock() - marks the end of an RCU read-side critical section. * * In most situations, rcu_read_unlock() is immune from deadlock. * However, in kernels built with CONFIG_RCU_BOOST, rcu_read_unlock() * is responsible for deboosting, which it does via rt_mutex_unlock(). * Unfortunately, this function acquires the scheduler's runqueue and * priority-inheritance spinlocks. This means that deadlock could result * if the caller of rcu_read_unlock() already holds one of these locks or * any lock that is ever acquired while holding them. * * That said, RCU readers are never priority boosted unless they were * preempted. Therefore, one way to avoid deadlock is to make sure * that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with one of * rt_mutex_unlock()'s locks held. Such preemption can be avoided in * a number of ways, for example, by invoking preempt_disable() before * critical section's outermost rcu_read_lock(). * * Given that the set of locks acquired by rt_mutex_unlock() might change * at any time, a somewhat more future-proofed approach is to make sure * that that preemption never happens within any RCU read-side critical * section whose outermost rcu_read_unlock() is called with irqs disabled. * This approach relies on the fact that rt_mutex_unlock() currently only * acquires irq-disabled locks. * * The second of these two approaches is best in most situations, * however, the first approach can also be useful, at least to those * developers willing to keep abreast of the set of locks acquired by * rt_mutex_unlock(). * * See rcu_read_lock() for more information. */ static inline void rcu_read_unlock(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock() used illegally while idle"); __release(RCU); __rcu_read_unlock(); rcu_lock_release(&rcu_lock_map); /* Keep acq info for rls diags. */ } /** * rcu_read_lock_bh() - mark the beginning of an RCU-bh critical section * * This is equivalent of rcu_read_lock(), but also disables softirqs. * Note that anything else that disables softirqs can also serve as * an RCU read-side critical section. * * Note that rcu_read_lock_bh() and the matching rcu_read_unlock_bh() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_bh() from one task if the matching rcu_read_lock_bh() * was invoked from some other task. */ static inline void rcu_read_lock_bh(void) { local_bh_disable(); __acquire(RCU_BH); rcu_lock_acquire(&rcu_bh_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_bh() used illegally while idle"); } /* * rcu_read_unlock_bh - marks the end of a softirq-only RCU critical section * * See rcu_read_lock_bh() for more information. */ static inline void rcu_read_unlock_bh(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_bh() used illegally while idle"); rcu_lock_release(&rcu_bh_lock_map); __release(RCU_BH); local_bh_enable(); } /** * rcu_read_lock_sched() - mark the beginning of a RCU-sched critical section * * This is equivalent of rcu_read_lock(), but disables preemption. * Read-side critical sections can also be introduced by anything else * that disables preemption, including local_irq_disable() and friends. * * Note that rcu_read_lock_sched() and the matching rcu_read_unlock_sched() * must occur in the same context, for example, it is illegal to invoke * rcu_read_unlock_sched() from process context if the matching * rcu_read_lock_sched() was invoked from an NMI handler. */ static inline void rcu_read_lock_sched(void) { preempt_disable(); __acquire(RCU_SCHED); rcu_lock_acquire(&rcu_sched_lock_map); RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_lock_sched() used illegally while idle"); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_lock_sched_notrace(void) { preempt_disable_notrace(); __acquire(RCU_SCHED); } /* * rcu_read_unlock_sched - marks the end of a RCU-classic critical section * * See rcu_read_lock_sched for more information. */ static inline void rcu_read_unlock_sched(void) { RCU_LOCKDEP_WARN(!rcu_is_watching(), "rcu_read_unlock_sched() used illegally while idle"); rcu_lock_release(&rcu_sched_lock_map); __release(RCU_SCHED); preempt_enable(); } /* Used by lockdep and tracing: cannot be traced, cannot call lockdep. */ static inline notrace void rcu_read_unlock_sched_notrace(void) { __release(RCU_SCHED); preempt_enable_notrace(); } /** * RCU_INIT_POINTER() - initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * Initialize an RCU-protected pointer in special cases where readers * do not need ordering constraints on the CPU or the compiler. These * special cases are: * * 1. This use of RCU_INIT_POINTER() is NULLing out the pointer *or* * 2. The caller has taken whatever steps are required to prevent * RCU readers from concurrently accessing this pointer *or* * 3. The referenced data structure has already been exposed to * readers either at compile time or via rcu_assign_pointer() *and* * * a. You have not made *any* reader-visible changes to * this structure since then *or* * b. It is OK for readers accessing this structure from its * new location to see the old state of the structure. (For * example, the changes were to statistical counters or to * other state where exact synchronization is not required.) * * Failure to follow these rules governing use of RCU_INIT_POINTER() will * result in impossible-to-diagnose memory corruption. As in the structures * will look OK in crash dumps, but any concurrent RCU readers might * see pre-initialized values of the referenced data structure. So * please be very careful how you use RCU_INIT_POINTER()!!! * * If you are creating an RCU-protected linked structure that is accessed * by a single external-to-structure RCU-protected pointer, then you may * use RCU_INIT_POINTER() to initialize the internal RCU-protected * pointers, but you must use rcu_assign_pointer() to initialize the * external-to-structure pointer *after* you have completely initialized * the reader-accessible portions of the linked structure. * * Note that unlike rcu_assign_pointer(), RCU_INIT_POINTER() provides no * ordering guarantees for either the CPU or the compiler. */ #define RCU_INIT_POINTER(p, v) \ do { \ rcu_check_sparse(p, __rcu); \ WRITE_ONCE(p, RCU_INITIALIZER(v)); \ } while (0) /** * RCU_POINTER_INITIALIZER() - statically initialize an RCU protected pointer * @p: The pointer to be initialized. * @v: The value to initialized the pointer to. * * GCC-style initialization for an RCU-protected pointer in a structure field. */ #define RCU_POINTER_INITIALIZER(p, v) \ .p = RCU_INITIALIZER(v) /* * Does the specified offset indicate that the corresponding rcu_head * structure can be handled by kfree_rcu()? */ #define __is_kfree_rcu_offset(offset) ((offset) < 4096) /* * Helper macro for kfree_rcu() to prevent argument-expansion eyestrain. */ #define __kfree_rcu(head, offset) \ do { \ BUILD_BUG_ON(!__is_kfree_rcu_offset(offset)); \ kfree_call_rcu(head, (rcu_callback_t)(unsigned long)(offset)); \ } while (0) /** * kfree_rcu() - kfree an object after a grace period. * @ptr: pointer to kfree * @rhf: the name of the struct rcu_head within the type of @ptr. * * Many rcu callbacks functions just call kfree() on the base structure. * These functions are trivial, but their size adds up, and furthermore * when they are used in a kernel module, that module must invoke the * high-latency rcu_barrier() function at module-unload time. * * The kfree_rcu() function handles this issue. Rather than encoding a * function address in the embedded rcu_head structure, kfree_rcu() instead * encodes the offset of the rcu_head structure within the base structure. * Because the functions are not allowed in the low-order 4096 bytes of * kernel virtual memory, offsets up to 4095 bytes can be accommodated. * If the offset is larger than 4095 bytes, a compile-time error will * be generated in __kfree_rcu(). If this error is triggered, you can * either fall back to use of call_rcu() or rearrange the structure to * position the rcu_head structure into the first 4096 bytes. * * Note that the allowable offset might decrease in the future, for example, * to allow something like kmem_cache_free_rcu(). * * The BUILD_BUG_ON check must not involve any function calls, hence the * checks are done in macros here. */ #define kfree_rcu(ptr, rhf) \ do { \ typeof (ptr) ___p = (ptr); \ \ if (___p) \ __kfree_rcu(&((___p)->rhf), offsetof(typeof(*(ptr)), rhf)); \ } while (0) /* * Place this after a lock-acquisition primitive to guarantee that * an UNLOCK+LOCK pair acts as a full barrier. This guarantee applies * if the UNLOCK and LOCK are executed by the same CPU or if the * UNLOCK and LOCK operate on the same lock variable. */ #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE #define smp_mb__after_unlock_lock() smp_mb() /* Full ordering for lock. */ #else /* #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ #define smp_mb__after_unlock_lock() do { } while (0) #endif /* #else #ifdef CONFIG_ARCH_WEAK_RELEASE_ACQUIRE */ /* Has the specified rcu_head structure been handed to call_rcu()? */ /** * rcu_head_init - Initialize rcu_head for rcu_head_after_call_rcu() * @rhp: The rcu_head structure to initialize. * * If you intend to invoke rcu_head_after_call_rcu() to test whether a * given rcu_head structure has already been passed to call_rcu(), then * you must also invoke this rcu_head_init() function on it just after * allocating that structure. Calls to this function must not race with * calls to call_rcu(), rcu_head_after_call_rcu(), or callback invocation. */ static inline void rcu_head_init(struct rcu_head *rhp) { rhp->func = (rcu_callback_t)~0L; } /** * rcu_head_after_call_rcu - Has this rcu_head been passed to call_rcu()? * @rhp: The rcu_head structure to test. * @f: The function passed to call_rcu() along with @rhp. * * Returns @true if the @rhp has been passed to call_rcu() with @func, * and @false otherwise. Emits a warning in any other case, including * the case where @rhp has already been invoked after a grace period. * Calls to this function must not race with callback invocation. One way * to avoid such races is to enclose the call to rcu_head_after_call_rcu() * in an RCU read-side critical section that includes a read-side fetch * of the pointer to the structure containing @rhp. */ static inline bool rcu_head_after_call_rcu(struct rcu_head *rhp, rcu_callback_t f) { rcu_callback_t func = READ_ONCE(rhp->func); if (func == f) return true; WARN_ON_ONCE(func != (rcu_callback_t)~0L); return false; } #endif /* __LINUX_RCUPDATE_H */ |
| 53 12 12 52 52 69 97 54 270 57 272 283 281 116 269 269 98 609 610 609 68 13 64 62 60 118 94 59 12 10 4 4 4 4 1 4 1 16 9 14 14 14 14 118 2 93 57 109 60 60 60 12 60 57 45 60 222 118 118 118 173 221 61 61 60 64 58 58 50 59 51 52 117 80 76 16 226 221 18 227 228 100 179 178 222 18 227 228 172 16 16 16 179 170 85 165 84 198 12 2 16 199 2 18 18 18 18 55 2 55 53 53 16 15 15 553 96 553 552 554 552 552 411 553 1 70 72 51 58 62 63 41 63 13 13 13 13 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0+ /* * XArray implementation * Copyright (c) 2017-2018 Microsoft Corporation * Copyright (c) 2018-2020 Oracle * Author: Matthew Wilcox <willy@infradead.org> */ #include <linux/bitmap.h> #include <linux/export.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/xarray.h> /* * Coding conventions in this file: * * @xa is used to refer to the entire xarray. * @xas is the 'xarray operation state'. It may be either a pointer to * an xa_state, or an xa_state stored on the stack. This is an unfortunate * ambiguity. * @index is the index of the entry being operated on * @mark is an xa_mark_t; a small number indicating one of the mark bits. * @node refers to an xa_node; usually the primary one being operated on by * this function. * @offset is the index into the slots array inside an xa_node. * @parent refers to the @xa_node closer to the head than @node. * @entry refers to something stored in a slot in the xarray */ static inline unsigned int xa_lock_type(const struct xarray *xa) { return (__force unsigned int)xa->xa_flags & 3; } static inline void xas_lock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_lock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_lock_bh(xas); else xas_lock(xas); } static inline void xas_unlock_type(struct xa_state *xas, unsigned int lock_type) { if (lock_type == XA_LOCK_IRQ) xas_unlock_irq(xas); else if (lock_type == XA_LOCK_BH) xas_unlock_bh(xas); else xas_unlock(xas); } static inline bool xa_track_free(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_TRACK_FREE; } static inline bool xa_zero_busy(const struct xarray *xa) { return xa->xa_flags & XA_FLAGS_ZERO_BUSY; } static inline void xa_mark_set(struct xarray *xa, xa_mark_t mark) { if (!(xa->xa_flags & XA_FLAGS_MARK(mark))) xa->xa_flags |= XA_FLAGS_MARK(mark); } static inline void xa_mark_clear(struct xarray *xa, xa_mark_t mark) { if (xa->xa_flags & XA_FLAGS_MARK(mark)) xa->xa_flags &= ~(XA_FLAGS_MARK(mark)); } static inline unsigned long *node_marks(struct xa_node *node, xa_mark_t mark) { return node->marks[(__force unsigned)mark]; } static inline bool node_get_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return test_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_set_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_set_bit(offset, node_marks(node, mark)); } /* returns true if the bit was set */ static inline bool node_clear_mark(struct xa_node *node, unsigned int offset, xa_mark_t mark) { return __test_and_clear_bit(offset, node_marks(node, mark)); } static inline bool node_any_mark(struct xa_node *node, xa_mark_t mark) { return !bitmap_empty(node_marks(node, mark), XA_CHUNK_SIZE); } static inline void node_mark_all(struct xa_node *node, xa_mark_t mark) { bitmap_fill(node_marks(node, mark), XA_CHUNK_SIZE); } #define mark_inc(mark) do { \ mark = (__force xa_mark_t)((__force unsigned)(mark) + 1); \ } while (0) /* * xas_squash_marks() - Merge all marks to the first entry * @xas: Array operation state. * * Set a mark on the first entry if any entry has it set. Clear marks on * all sibling entries. */ static void xas_squash_marks(const struct xa_state *xas) { unsigned int mark = 0; unsigned int limit = xas->xa_offset + xas->xa_sibs + 1; if (!xas->xa_sibs) return; do { unsigned long *marks = xas->xa_node->marks[mark]; if (find_next_bit(marks, limit, xas->xa_offset + 1) == limit) continue; __set_bit(xas->xa_offset, marks); bitmap_clear(marks, xas->xa_offset + 1, xas->xa_sibs); } while (mark++ != (__force unsigned)XA_MARK_MAX); } /* extracts the offset within this node from the index */ static unsigned int get_offset(unsigned long index, struct xa_node *node) { return (index >> node->shift) & XA_CHUNK_MASK; } static void xas_set_offset(struct xa_state *xas) { xas->xa_offset = get_offset(xas->xa_index, xas->xa_node); } /* move the index either forwards (find) or backwards (sibling slot) */ static void xas_move_index(struct xa_state *xas, unsigned long offset) { unsigned int shift = xas->xa_node->shift; xas->xa_index &= ~XA_CHUNK_MASK << shift; xas->xa_index += offset << shift; } static void xas_advance(struct xa_state *xas) { xas->xa_offset++; xas_move_index(xas, xas->xa_offset); } static void *set_bounds(struct xa_state *xas) { xas->xa_node = XAS_BOUNDS; return NULL; } /* * Starts a walk. If the @xas is already valid, we assume that it's on * the right path and just return where we've got to. If we're in an * error state, return NULL. If the index is outside the current scope * of the xarray, return NULL without changing @xas->xa_node. Otherwise * set @xas->xa_node to NULL and return the current head of the array. */ static void *xas_start(struct xa_state *xas) { void *entry; if (xas_valid(xas)) return xas_reload(xas); if (xas_error(xas)) return NULL; entry = xa_head(xas->xa); if (!xa_is_node(entry)) { if (xas->xa_index) return set_bounds(xas); } else { if ((xas->xa_index >> xa_to_node(entry)->shift) > XA_CHUNK_MASK) return set_bounds(xas); } xas->xa_node = NULL; return entry; } static void *xas_descend(struct xa_state *xas, struct xa_node *node) { unsigned int offset = get_offset(xas->xa_index, node); void *entry = xa_entry(xas->xa, node, offset); xas->xa_node = node; if (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); } xas->xa_offset = offset; return entry; } /** * xas_load() - Load an entry from the XArray (advanced). * @xas: XArray operation state. * * Usually walks the @xas to the appropriate state to load the entry * stored at xa_index. However, it will do nothing and return %NULL if * @xas is in an error state. xas_load() will never expand the tree. * * If the xa_state is set up to operate on a multi-index entry, xas_load() * may return %NULL or an internal entry, even if there are entries * present within the range specified by @xas. * * Context: Any context. The caller should hold the xa_lock or the RCU lock. * Return: Usually an entry in the XArray, but see description for exceptions. */ void *xas_load(struct xa_state *xas) { void *entry = xas_start(xas); while (xa_is_node(entry)) { struct xa_node *node = xa_to_node(entry); if (xas->xa_shift > node->shift) break; entry = xas_descend(xas, node); if (node->shift == 0) break; } return entry; } EXPORT_SYMBOL_GPL(xas_load); /* Move the radix tree node cache here */ extern struct kmem_cache *radix_tree_node_cachep; extern void radix_tree_node_rcu_free(struct rcu_head *head); #define XA_RCU_FREE ((struct xarray *)1) static void xa_node_free(struct xa_node *node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->array = XA_RCU_FREE; call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * xas_destroy() - Free any resources allocated during the XArray operation. * @xas: XArray operation state. * * This function is now internal-only. */ static void xas_destroy(struct xa_state *xas) { struct xa_node *next, *node = xas->xa_alloc; while (node) { XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); next = rcu_dereference_raw(node->parent); radix_tree_node_rcu_free(&node->rcu_head); xas->xa_alloc = node = next; } } /** * xas_nomem() - Allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * If we need to add new nodes to the XArray, we try to allocate memory * with GFP_NOWAIT while holding the lock, which will usually succeed. * If it fails, @xas is flagged as needing memory to continue. The caller * should drop the lock and call xas_nomem(). If xas_nomem() succeeds, * the caller should retry the operation. * * Forward progress is guaranteed as one node is allocated here and * stored in the xa_state where it will be found by xas_alloc(). More * nodes will likely be found in the slab allocator, but we do not tie * them up here. * * Return: true if memory was needed, and was successfully allocated. */ bool xas_nomem(struct xa_state *xas, gfp_t gfp) { if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } EXPORT_SYMBOL_GPL(xas_nomem); /* * __xas_nomem() - Drop locks and allocate memory if needed. * @xas: XArray operation state. * @gfp: Memory allocation flags. * * Internal variant of xas_nomem(). * * Return: true if memory was needed, and was successfully allocated. */ static bool __xas_nomem(struct xa_state *xas, gfp_t gfp) __must_hold(xas->xa->xa_lock) { unsigned int lock_type = xa_lock_type(xas->xa); if (xas->xa_node != XA_ERROR(-ENOMEM)) { xas_destroy(xas); return false; } if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; if (gfpflags_allow_blocking(gfp)) { xas_unlock_type(xas, lock_type); xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc(radix_tree_node_cachep, gfp); } if (!xas->xa_alloc) return false; xas->xa_alloc->parent = NULL; XA_NODE_BUG_ON(xas->xa_alloc, !list_empty(&xas->xa_alloc->private_list)); xas->xa_node = XAS_RESTART; return true; } static void xas_update(struct xa_state *xas, struct xa_node *node) { if (xas->xa_update) xas->xa_update(node); else XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); } static void *xas_alloc(struct xa_state *xas, unsigned int shift) { struct xa_node *parent = xas->xa_node; struct xa_node *node = xas->xa_alloc; if (xas_invalid(xas)) return NULL; if (node) { xas->xa_alloc = NULL; } else { gfp_t gfp = GFP_NOWAIT | __GFP_NOWARN; if (xas->xa->xa_flags & XA_FLAGS_ACCOUNT) gfp |= __GFP_ACCOUNT; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) { xas_set_err(xas, -ENOMEM); return NULL; } } if (parent) { node->offset = xas->xa_offset; parent->count++; XA_NODE_BUG_ON(node, parent->count > XA_CHUNK_SIZE); xas_update(xas, parent); } XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); XA_NODE_BUG_ON(node, !list_empty(&node->private_list)); node->shift = shift; node->count = 0; node->nr_values = 0; RCU_INIT_POINTER(node->parent, xas->xa_node); node->array = xas->xa; return node; } #ifdef CONFIG_XARRAY_MULTI /* Returns the number of indices covered by a given xa_state */ static unsigned long xas_size(const struct xa_state *xas) { return (xas->xa_sibs + 1UL) << xas->xa_shift; } #endif /* * Use this to calculate the maximum index that will need to be created * in order to add the entry described by @xas. Because we cannot store a * multi-index entry at index 0, the calculation is a little more complex * than you might expect. */ static unsigned long xas_max(struct xa_state *xas) { unsigned long max = xas->xa_index; #ifdef CONFIG_XARRAY_MULTI if (xas->xa_shift || xas->xa_sibs) { unsigned long mask = xas_size(xas) - 1; max |= mask; if (mask == max) max++; } #endif return max; } /* The maximum index that can be contained in the array without expanding it */ static unsigned long max_index(void *entry) { if (!xa_is_node(entry)) return 0; return (XA_CHUNK_SIZE << xa_to_node(entry)->shift) - 1; } static void xas_shrink(struct xa_state *xas) { struct xarray *xa = xas->xa; struct xa_node *node = xas->xa_node; for (;;) { void *entry; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count != 1) break; entry = xa_entry_locked(xa, node, 0); if (!entry) break; if (!xa_is_node(entry) && node->shift) break; if (xa_is_zero(entry) && xa_zero_busy(xa)) entry = NULL; xas->xa_node = XAS_BOUNDS; RCU_INIT_POINTER(xa->xa_head, entry); if (xa_track_free(xa) && !node_get_mark(node, 0, XA_FREE_MARK)) xa_mark_clear(xa, XA_FREE_MARK); node->count = 0; node->nr_values = 0; if (!xa_is_node(entry)) RCU_INIT_POINTER(node->slots[0], XA_RETRY_ENTRY); xas_update(xas, node); xa_node_free(node); if (!xa_is_node(entry)) break; node = xa_to_node(entry); node->parent = NULL; } } /* * xas_delete_node() - Attempt to delete an xa_node * @xas: Array operation state. * * Attempts to delete the @xas->xa_node. This will fail if xa->node has * a non-zero reference count. */ static void xas_delete_node(struct xa_state *xas) { struct xa_node *node = xas->xa_node; for (;;) { struct xa_node *parent; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); if (node->count) break; parent = xa_parent_locked(xas->xa, node); xas->xa_node = parent; xas->xa_offset = node->offset; xa_node_free(node); if (!parent) { xas->xa->xa_head = NULL; xas->xa_node = XAS_BOUNDS; return; } parent->slots[xas->xa_offset] = NULL; parent->count--; XA_NODE_BUG_ON(parent, parent->count > XA_CHUNK_SIZE); node = parent; xas_update(xas, node); } if (!node->parent) xas_shrink(xas); } /** * xas_free_nodes() - Free this node and all nodes that it references * @xas: Array operation state. * @top: Node to free * * This node has been removed from the tree. We must now free it and all * of its subnodes. There may be RCU walkers with references into the tree, * so we must replace all entries with retry markers. */ static void xas_free_nodes(struct xa_state *xas, struct xa_node *top) { unsigned int offset = 0; struct xa_node *node = top; for (;;) { void *entry = xa_entry_locked(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) { node = xa_to_node(entry); offset = 0; continue; } if (entry) RCU_INIT_POINTER(node->slots[offset], XA_RETRY_ENTRY); offset++; while (offset == XA_CHUNK_SIZE) { struct xa_node *parent; parent = xa_parent_locked(xas->xa, node); offset = node->offset + 1; node->count = 0; node->nr_values = 0; xas_update(xas, node); xa_node_free(node); if (node == top) return; node = parent; } } } /* * xas_expand adds nodes to the head of the tree until it has reached * sufficient height to be able to contain @xas->xa_index */ static int xas_expand(struct xa_state *xas, void *head) { struct xarray *xa = xas->xa; struct xa_node *node = NULL; unsigned int shift = 0; unsigned long max = xas_max(xas); if (!head) { if (max == 0) return 0; while ((max >> shift) >= XA_CHUNK_SIZE) shift += XA_CHUNK_SHIFT; return shift + XA_CHUNK_SHIFT; } else if (xa_is_node(head)) { node = xa_to_node(head); shift = node->shift + XA_CHUNK_SHIFT; } xas->xa_node = NULL; while (max > max_index(head)) { xa_mark_t mark = 0; XA_NODE_BUG_ON(node, shift > BITS_PER_LONG); node = xas_alloc(xas, shift); if (!node) return -ENOMEM; node->count = 1; if (xa_is_value(head)) node->nr_values = 1; RCU_INIT_POINTER(node->slots[0], head); /* Propagate the aggregated mark info to the new child */ for (;;) { if (xa_track_free(xa) && mark == XA_FREE_MARK) { node_mark_all(node, XA_FREE_MARK); if (!xa_marked(xa, XA_FREE_MARK)) { node_clear_mark(node, 0, XA_FREE_MARK); xa_mark_set(xa, XA_FREE_MARK); } } else if (xa_marked(xa, mark)) { node_set_mark(node, 0, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } /* * Now that the new node is fully initialised, we can add * it to the tree */ if (xa_is_node(head)) { xa_to_node(head)->offset = 0; rcu_assign_pointer(xa_to_node(head)->parent, node); } head = xa_mk_node(node); rcu_assign_pointer(xa->xa_head, head); xas_update(xas, node); shift += XA_CHUNK_SHIFT; } xas->xa_node = node; return shift; } /* * xas_create() - Create a slot to store an entry in. * @xas: XArray operation state. * @allow_root: %true if we can store the entry in the root directly * * Most users will not need to call this function directly, as it is called * by xas_store(). It is useful for doing conditional store operations * (see the xa_cmpxchg() implementation for an example). * * Return: If the slot already existed, returns the contents of this slot. * If the slot was newly created, returns %NULL. If it failed to create the * slot, returns %NULL and indicates the error in @xas. */ static void *xas_create(struct xa_state *xas, bool allow_root) { struct xarray *xa = xas->xa; void *entry; void __rcu **slot; struct xa_node *node = xas->xa_node; int shift; unsigned int order = xas->xa_shift; if (xas_top(node)) { entry = xa_head_locked(xa); xas->xa_node = NULL; if (!entry && xa_zero_busy(xa)) entry = XA_ZERO_ENTRY; shift = xas_expand(xas, entry); if (shift < 0) return NULL; if (!shift && !allow_root) shift = XA_CHUNK_SHIFT; entry = xa_head_locked(xa); slot = &xa->xa_head; } else if (xas_error(xas)) { return NULL; } else if (node) { unsigned int offset = xas->xa_offset; shift = node->shift; entry = xa_entry_locked(xa, node, offset); slot = &node->slots[offset]; } else { shift = 0; entry = xa_head_locked(xa); slot = &xa->xa_head; } while (shift > order) { shift -= XA_CHUNK_SHIFT; if (!entry) { node = xas_alloc(xas, shift); if (!node) break; if (xa_track_free(xa)) node_mark_all(node, XA_FREE_MARK); rcu_assign_pointer(*slot, xa_mk_node(node)); } else if (xa_is_node(entry)) { node = xa_to_node(entry); } else { break; } entry = xas_descend(xas, node); slot = &node->slots[xas->xa_offset]; } return entry; } /** * xas_create_range() - Ensure that stores to this range will succeed * @xas: XArray operation state. * * Creates all of the slots in the range covered by @xas. Sets @xas to * create single-index entries and positions it at the beginning of the * range. This is for the benefit of users which have not yet been * converted to use multi-index entries. */ void xas_create_range(struct xa_state *xas) { unsigned long index = xas->xa_index; unsigned char shift = xas->xa_shift; unsigned char sibs = xas->xa_sibs; xas->xa_index |= ((sibs + 1) << shift) - 1; if (xas_is_node(xas) && xas->xa_node->shift == xas->xa_shift) xas->xa_offset |= sibs; xas->xa_shift = 0; xas->xa_sibs = 0; for (;;) { xas_create(xas, true); if (xas_error(xas)) goto restore; if (xas->xa_index <= (index | XA_CHUNK_MASK)) goto success; xas->xa_index -= XA_CHUNK_SIZE; for (;;) { struct xa_node *node = xas->xa_node; if (node->shift >= shift) break; xas->xa_node = xa_parent_locked(xas->xa, node); xas->xa_offset = node->offset - 1; if (node->offset != 0) break; } } restore: xas->xa_shift = shift; xas->xa_sibs = sibs; xas->xa_index = index; return; success: xas->xa_index = index; if (xas->xa_node) xas_set_offset(xas); } EXPORT_SYMBOL_GPL(xas_create_range); static void update_node(struct xa_state *xas, struct xa_node *node, int count, int values) { if (!node || (!count && !values)) return; node->count += count; node->nr_values += values; XA_NODE_BUG_ON(node, node->count > XA_CHUNK_SIZE); XA_NODE_BUG_ON(node, node->nr_values > XA_CHUNK_SIZE); xas_update(xas, node); if (count < 0) xas_delete_node(xas); } /** * xas_store() - Store this entry in the XArray. * @xas: XArray operation state. * @entry: New entry. * * If @xas is operating on a multi-index entry, the entry returned by this * function is essentially meaningless (it may be an internal entry or it * may be %NULL, even if there are non-NULL entries at some of the indices * covered by the range). This is not a problem for any current users, * and can be changed if needed. * * Return: The old entry at this index. */ void *xas_store(struct xa_state *xas, void *entry) { struct xa_node *node; void __rcu **slot = &xas->xa->xa_head; unsigned int offset, max; int count = 0; int values = 0; void *first, *next; bool value = xa_is_value(entry); if (entry) { bool allow_root = !xa_is_node(entry) && !xa_is_zero(entry); first = xas_create(xas, allow_root); } else { first = xas_load(xas); } if (xas_invalid(xas)) return first; node = xas->xa_node; if (node && (xas->xa_shift < node->shift)) xas->xa_sibs = 0; if ((first == entry) && !xas->xa_sibs) return first; next = first; offset = xas->xa_offset; max = xas->xa_offset + xas->xa_sibs; if (node) { slot = &node->slots[offset]; if (xas->xa_sibs) xas_squash_marks(xas); } if (!entry) xas_init_marks(xas); for (;;) { /* * Must clear the marks before setting the entry to NULL, * otherwise xas_for_each_marked may find a NULL entry and * stop early. rcu_assign_pointer contains a release barrier * so the mark clearing will appear to happen before the * entry is set to NULL. */ rcu_assign_pointer(*slot, entry); if (xa_is_node(next) && (!node || node->shift)) xas_free_nodes(xas, xa_to_node(next)); if (!node) break; count += !next - !entry; values += !xa_is_value(first) - !value; if (entry) { if (offset == max) break; if (!xa_is_sibling(entry)) entry = xa_mk_sibling(xas->xa_offset); } else { if (offset == XA_CHUNK_MASK) break; } next = xa_entry_locked(xas->xa, node, ++offset); if (!xa_is_sibling(next)) { if (!entry && (offset > max)) break; first = next; } slot++; } update_node(xas, node, count, values); return first; } EXPORT_SYMBOL_GPL(xas_store); /** * xas_get_mark() - Returns the state of this mark. * @xas: XArray operation state. * @mark: Mark number. * * Return: true if the mark is set, false if the mark is clear or @xas * is in an error state. */ bool xas_get_mark(const struct xa_state *xas, xa_mark_t mark) { if (xas_invalid(xas)) return false; if (!xas->xa_node) return xa_marked(xas->xa, mark); return node_get_mark(xas->xa_node, xas->xa_offset, mark); } EXPORT_SYMBOL_GPL(xas_get_mark); /** * xas_set_mark() - Sets the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Sets the specified mark on this entry, and walks up the tree setting it * on all the ancestor entries. Does nothing if @xas has not been walked to * an entry, or is in an error state. */ void xas_set_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (node_set_mark(node, offset, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (!xa_marked(xas->xa, mark)) xa_mark_set(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_set_mark); /** * xas_clear_mark() - Clears the mark on this entry and its parents. * @xas: XArray operation state. * @mark: Mark number. * * Clears the specified mark on this entry, and walks back to the head * attempting to clear it on all the ancestor entries. Does nothing if * @xas has not been walked to an entry, or is in an error state. */ void xas_clear_mark(const struct xa_state *xas, xa_mark_t mark) { struct xa_node *node = xas->xa_node; unsigned int offset = xas->xa_offset; if (xas_invalid(xas)) return; while (node) { if (!node_clear_mark(node, offset, mark)) return; if (node_any_mark(node, mark)) return; offset = node->offset; node = xa_parent_locked(xas->xa, node); } if (xa_marked(xas->xa, mark)) xa_mark_clear(xas->xa, mark); } EXPORT_SYMBOL_GPL(xas_clear_mark); /** * xas_init_marks() - Initialise all marks for the entry * @xas: Array operations state. * * Initialise all marks for the entry specified by @xas. If we're tracking * free entries with a mark, we need to set it on all entries. All other * marks are cleared. * * This implementation is not as efficient as it could be; we may walk * up the tree multiple times. */ void xas_init_marks(const struct xa_state *xas) { xa_mark_t mark = 0; for (;;) { if (xa_track_free(xas->xa) && mark == XA_FREE_MARK) xas_set_mark(xas, mark); else xas_clear_mark(xas, mark); if (mark == XA_MARK_MAX) break; mark_inc(mark); } } EXPORT_SYMBOL_GPL(xas_init_marks); #ifdef CONFIG_XARRAY_MULTI static unsigned int node_get_marks(struct xa_node *node, unsigned int offset) { unsigned int marks = 0; xa_mark_t mark = XA_MARK_0; for (;;) { if (node_get_mark(node, offset, mark)) marks |= 1 << (__force unsigned int)mark; if (mark == XA_MARK_MAX) break; mark_inc(mark); } return marks; } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int marks) { xa_mark_t mark = XA_MARK_0; for (;;) { if (marks & (1 << (__force unsigned int)mark)) { node_set_mark(node, offset, mark); if (child) node_mark_all(child, mark); } if (mark == XA_MARK_MAX) break; mark_inc(mark); } } /** * xas_split_alloc() - Allocate memory for splitting an entry. * @xas: XArray operation state. * @entry: New entry which will be stored in the array. * @order: New entry order. * @gfp: Memory allocation flags. * * This function should be called before calling xas_split(). * If necessary, it will allocate new nodes (and fill them with @entry) * to prepare for the upcoming split of an entry of @order size into * entries of the order stored in the @xas. * * Context: May sleep if @gfp flags permit. */ void xas_split_alloc(struct xa_state *xas, void *entry, unsigned int order, gfp_t gfp) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int mask = xas->xa_sibs; /* XXX: no support for splitting really large entries yet */ if (WARN_ON(xas->xa_shift + 2 * XA_CHUNK_SHIFT < order)) goto nomem; if (xas->xa_shift + XA_CHUNK_SHIFT > order) return; do { unsigned int i; void *sibling; struct xa_node *node; node = kmem_cache_alloc(radix_tree_node_cachep, gfp); if (!node) goto nomem; node->array = xas->xa; for (i = 0; i < XA_CHUNK_SIZE; i++) { if ((i & mask) == 0) { RCU_INIT_POINTER(node->slots[i], entry); sibling = xa_mk_sibling(0); } else { RCU_INIT_POINTER(node->slots[i], sibling); } } RCU_INIT_POINTER(node->parent, xas->xa_alloc); xas->xa_alloc = node; } while (sibs-- > 0); return; nomem: xas_destroy(xas); xas_set_err(xas, -ENOMEM); } EXPORT_SYMBOL_GPL(xas_split_alloc); /** * xas_split() - Split a multi-index entry into smaller entries. * @xas: XArray operation state. * @entry: New entry to store in the array. * @order: New entry order. * * The value in the entry is copied to all the replacement entries. * * Context: Any context. The caller should hold the xa_lock. */ void xas_split(struct xa_state *xas, void *entry, unsigned int order) { unsigned int sibs = (1 << (order % XA_CHUNK_SHIFT)) - 1; unsigned int offset, marks; struct xa_node *node; void *curr = xas_load(xas); int values = 0; node = xas->xa_node; if (xas_top(node)) return; marks = node_get_marks(node, xas->xa_offset); offset = xas->xa_offset + sibs; do { if (xas->xa_shift < node->shift) { struct xa_node *child = xas->xa_alloc; xas->xa_alloc = rcu_dereference_raw(child->parent); child->shift = node->shift - XA_CHUNK_SHIFT; child->offset = offset; child->count = XA_CHUNK_SIZE; child->nr_values = xa_is_value(entry) ? XA_CHUNK_SIZE : 0; RCU_INIT_POINTER(child->parent, node); node_set_marks(node, offset, child, marks); rcu_assign_pointer(node->slots[offset], xa_mk_node(child)); if (xa_is_value(curr)) values--; xas_update(xas, child); } else { unsigned int canon = offset - xas->xa_sibs; node_set_marks(node, canon, NULL, marks); rcu_assign_pointer(node->slots[canon], entry); while (offset > canon) rcu_assign_pointer(node->slots[offset--], xa_mk_sibling(canon)); values += (xa_is_value(entry) - xa_is_value(curr)) * (xas->xa_sibs + 1); } } while (offset-- > xas->xa_offset); node->nr_values += values; xas_update(xas, node); } EXPORT_SYMBOL_GPL(xas_split); #endif /** * xas_pause() - Pause a walk to drop a lock. * @xas: XArray operation state. * * 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 @xas 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 xas_pause(), the xa_for_each() * iterator may be more appropriate. * * Note that xas_pause() only works for forward iteration. If a user needs * to pause a reverse iteration, we will need a xas_pause_rev(). */ void xas_pause(struct xa_state *xas) { struct xa_node *node = xas->xa_node; if (xas_invalid(xas)) return; xas->xa_node = XAS_RESTART; if (node) { unsigned long offset = xas->xa_offset; while (++offset < XA_CHUNK_SIZE) { if (!xa_is_sibling(xa_entry(xas->xa, node, offset))) break; } xas->xa_index += (offset - xas->xa_offset) << node->shift; if (xas->xa_index == 0) xas->xa_node = XAS_BOUNDS; } else { xas->xa_index++; } } EXPORT_SYMBOL_GPL(xas_pause); /* * __xas_prev() - Find the previous entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_prev() which handles all the complex cases * out of line. */ void *__xas_prev(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index--; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset--; while (xas->xa_offset == 255) { xas->xa_offset = xas->xa_node->offset - 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_prev); /* * __xas_next() - Find the next entry in the XArray. * @xas: XArray operation state. * * Helper function for xas_next() which handles all the complex cases * out of line. */ void *__xas_next(struct xa_state *xas) { void *entry; if (!xas_frozen(xas->xa_node)) xas->xa_index++; if (!xas->xa_node) return set_bounds(xas); if (xas_not_node(xas->xa_node)) return xas_load(xas); if (xas->xa_offset != get_offset(xas->xa_index, xas->xa_node)) xas->xa_offset++; while (xas->xa_offset == XA_CHUNK_SIZE) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) return set_bounds(xas); } for (;;) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } } EXPORT_SYMBOL_GPL(__xas_next); /** * xas_find() - Find the next present entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * * If the @xas has not yet been walked to an entry, return the entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we move to the * next entry. * * If no entry is found and the array is smaller than @max, the iterator * is set to the smallest index not yet in the array. This allows @xas * to be immediately passed to xas_store(). * * Return: The entry, if found, otherwise %NULL. */ void *xas_find(struct xa_state *xas, unsigned long max) { void *entry; if (xas_error(xas) || xas->xa_node == XAS_BOUNDS) return NULL; if (xas->xa_index > max) return set_bounds(xas); if (!xas->xa_node) { xas->xa_index = 1; return set_bounds(xas); } else if (xas->xa_node == XAS_RESTART) { entry = xas_load(xas); if (entry || xas_not_node(xas->xa_node)) return entry; } else if (!xas->xa_node->shift && xas->xa_offset != (xas->xa_index & XA_CHUNK_MASK)) { xas->xa_offset = ((xas->xa_index - 1) & XA_CHUNK_MASK) + 1; } xas_advance(xas); while (xas->xa_node && (xas->xa_index <= max)) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_node(entry)) { xas->xa_node = xa_to_node(entry); xas->xa_offset = 0; continue; } if (entry && !xa_is_sibling(entry)) return entry; xas_advance(xas); } if (!xas->xa_node) xas->xa_node = XAS_BOUNDS; return NULL; } EXPORT_SYMBOL_GPL(xas_find); /** * xas_find_marked() - Find the next marked entry in the XArray. * @xas: XArray operation state. * @max: Highest index to return. * @mark: Mark number to search for. * * If the @xas has not yet been walked to an entry, return the marked entry * which has an index >= xas.xa_index. If it has been walked, the entry * currently being pointed at has been processed, and so we return the * first marked entry with an index > xas.xa_index. * * If no marked entry is found and the array is smaller than @max, @xas is * set to the bounds state and xas->xa_index is set to the smallest index * not yet in the array. This allows @xas to be immediately passed to * xas_store(). * * If no entry is found before @max is reached, @xas is set to the restart * state. * * Return: The entry, if found, otherwise %NULL. */ void *xas_find_marked(struct xa_state *xas, unsigned long max, xa_mark_t mark) { bool advance = true; unsigned int offset; void *entry; if (xas_error(xas)) return NULL; if (xas->xa_index > max) goto max; if (!xas->xa_node) { xas->xa_index = 1; goto out; } else if (xas_top(xas->xa_node)) { advance = false; entry = xa_head(xas->xa); xas->xa_node = NULL; if (xas->xa_index > max_index(entry)) goto out; if (!xa_is_node(entry)) { if (xa_marked(xas->xa, mark)) return entry; xas->xa_index = 1; goto out; } xas->xa_node = xa_to_node(entry); xas->xa_offset = xas->xa_index >> xas->xa_node->shift; } while (xas->xa_index <= max) { if (unlikely(xas->xa_offset == XA_CHUNK_SIZE)) { xas->xa_offset = xas->xa_node->offset + 1; xas->xa_node = xa_parent(xas->xa, xas->xa_node); if (!xas->xa_node) break; advance = false; continue; } if (!advance) { entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (xa_is_sibling(entry)) { xas->xa_offset = xa_to_sibling(entry); xas_move_index(xas, xas->xa_offset); } } offset = xas_find_chunk(xas, advance, mark); if (offset > xas->xa_offset) { advance = false; xas_move_index(xas, offset); /* Mind the wrap */ if ((xas->xa_index - 1) >= max) goto max; xas->xa_offset = offset; if (offset == XA_CHUNK_SIZE) continue; } entry = xa_entry(xas->xa, xas->xa_node, xas->xa_offset); if (!entry && !(xa_track_free(xas->xa) && mark == XA_FREE_MARK)) continue; if (!xa_is_node(entry)) return entry; xas->xa_node = xa_to_node(entry); xas_set_offset(xas); } out: if (xas->xa_index > max) goto max; return set_bounds(xas); max: xas->xa_node = XAS_RESTART; return NULL; } EXPORT_SYMBOL_GPL(xas_find_marked); /** * xas_find_conflict() - Find the next present entry in a range. * @xas: XArray operation state. * * The @xas describes both a range and a position within that range. * * Context: Any context. Expects xa_lock to be held. * Return: The next entry in the range covered by @xas or %NULL. */ void *xas_find_conflict(struct xa_state *xas) { void *curr; if (xas_error(xas)) return NULL; if (!xas->xa_node) return NULL; if (xas_top(xas->xa_node)) { curr = xas_start(xas); if (!curr) return NULL; while (xa_is_node(curr)) { struct xa_node *node = xa_to_node(curr); curr = xas_descend(xas, node); } if (curr) return curr; } if (xas->xa_node->shift > xas->xa_shift) return NULL; for (;;) { if (xas->xa_node->shift == xas->xa_shift) { if ((xas->xa_offset & xas->xa_sibs) == xas->xa_sibs) break; } else if (xas->xa_offset == XA_CHUNK_MASK) { xas->xa_offset = xas->xa_node->offset; xas->xa_node = xa_parent_locked(xas->xa, xas->xa_node); if (!xas->xa_node) break; continue; } curr = xa_entry_locked(xas->xa, xas->xa_node, ++xas->xa_offset); if (xa_is_sibling(curr)) continue; while (xa_is_node(curr)) { xas->xa_node = xa_to_node(curr); xas->xa_offset = 0; curr = xa_entry_locked(xas->xa, xas->xa_node, 0); } if (curr) return curr; } xas->xa_offset -= xas->xa_sibs; return NULL; } EXPORT_SYMBOL_GPL(xas_find_conflict); /** * xa_load() - Load an entry from an XArray. * @xa: XArray. * @index: index into array. * * Context: Any context. Takes and releases the RCU lock. * Return: The entry at @index in @xa. */ void *xa_load(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); do { entry = xas_load(&xas); if (xa_is_zero(entry)) entry = NULL; } while (xas_retry(&xas, entry)); rcu_read_unlock(); return entry; } EXPORT_SYMBOL(xa_load); static void *xas_result(struct xa_state *xas, void *curr) { if (xa_is_zero(curr)) return NULL; if (xas_error(xas)) curr = xas->xa_node; return curr; } /** * __xa_erase() - Erase this entry from the XArray while locked. * @xa: XArray. * @index: Index into array. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Expects xa_lock to be held on entry. * Return: The entry which used to be at this index. */ void *__xa_erase(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); return xas_result(&xas, xas_store(&xas, NULL)); } EXPORT_SYMBOL(__xa_erase); /** * xa_erase() - Erase this entry from the XArray. * @xa: XArray. * @index: Index of entry. * * After this function returns, loading from @index will return %NULL. * If the index is part of a multi-index entry, all indices will be erased * and none of the entries will be part of a multi-index entry. * * Context: Any context. Takes and releases the xa_lock. * Return: The entry which used to be at this index. */ void *xa_erase(struct xarray *xa, unsigned long index) { void *entry; xa_lock(xa); entry = __xa_erase(xa, index); xa_unlock(xa); return entry; } EXPORT_SYMBOL(xa_erase); /** * __xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); if (xa_track_free(xa) && !entry) entry = XA_ZERO_ENTRY; do { curr = xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_store); /** * xa_store() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from this index will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Any context. Takes and releases the xa_lock. * May sleep if the @gfp flags permit. * Return: The old entry at this index on success, xa_err(-EINVAL) if @entry * cannot be stored in an XArray, or xa_err(-ENOMEM) if memory allocation * failed. */ void *xa_store(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { void *curr; xa_lock(xa); curr = __xa_store(xa, index, entry, gfp); xa_unlock(xa); return curr; } EXPORT_SYMBOL(xa_store); /** * __xa_cmpxchg() - Store this entry in the XArray. * @xa: XArray. * @index: Index into array. * @old: Old value to test against. * @entry: New entry. * @gfp: Memory allocation flags. * * You must already be holding the xa_lock when calling this function. * It will drop the lock if needed to allocate memory, and then reacquire * it afterwards. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: The old entry at this index or xa_err() if an error happened. */ void *__xa_cmpxchg(struct xarray *xa, unsigned long index, void *old, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return XA_ERROR(-EINVAL); do { curr = xas_load(&xas); if (curr == old) { xas_store(&xas, entry); if (xa_track_free(xa) && entry && !curr) xas_clear_mark(&xas, XA_FREE_MARK); } } while (__xas_nomem(&xas, gfp)); return xas_result(&xas, curr); } EXPORT_SYMBOL(__xa_cmpxchg); /** * __xa_insert() - Store this entry in the XArray if no entry is present. * @xa: XArray. * @index: Index into array. * @entry: New entry. * @gfp: Memory allocation flags. * * Inserting a NULL entry will store a reserved entry (like xa_reserve()) * if no entry is present. Inserting will fail if a reserved entry is * present, even though loading from this index will return NULL. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 if the store succeeded. -EBUSY if another entry was present. * -ENOMEM if memory could not be allocated. */ int __xa_insert(struct xarray *xa, unsigned long index, void *entry, gfp_t gfp) { XA_STATE(xas, xa, index); void *curr; if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { curr = xas_load(&xas); if (!curr) { xas_store(&xas, entry); if (xa_track_free(xa)) xas_clear_mark(&xas, XA_FREE_MARK); } else { xas_set_err(&xas, -EBUSY); } } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_insert); #ifdef CONFIG_XARRAY_MULTI static void xas_set_range(struct xa_state *xas, unsigned long first, unsigned long last) { unsigned int shift = 0; unsigned long sibs = last - first; unsigned int offset = XA_CHUNK_MASK; xas_set(xas, first); while ((first & XA_CHUNK_MASK) == 0) { if (sibs < XA_CHUNK_MASK) break; if ((sibs == XA_CHUNK_MASK) && (offset < XA_CHUNK_MASK)) break; shift += XA_CHUNK_SHIFT; if (offset == XA_CHUNK_MASK) offset = sibs & XA_CHUNK_MASK; sibs >>= XA_CHUNK_SHIFT; first >>= XA_CHUNK_SHIFT; } offset = first & XA_CHUNK_MASK; if (offset + sibs > XA_CHUNK_MASK) sibs = XA_CHUNK_MASK - offset; if ((((first + sibs + 1) << shift) - 1) > last) sibs -= 1; xas->xa_shift = shift; xas->xa_sibs = sibs; } /** * xa_store_range() - Store this entry at a range of indices in the XArray. * @xa: XArray. * @first: First index to affect. * @last: Last index to affect. * @entry: New entry. * @gfp: Memory allocation flags. * * After this function returns, loads from any index between @first and @last, * inclusive will return @entry. * Storing into an existing multi-index entry updates the entry of every index. * The marks associated with @index are unaffected unless @entry is %NULL. * * Context: Process context. Takes and releases the xa_lock. May sleep * if the @gfp flags permit. * Return: %NULL on success, xa_err(-EINVAL) if @entry cannot be stored in * an XArray, or xa_err(-ENOMEM) if memory allocation failed. */ void *xa_store_range(struct xarray *xa, unsigned long first, unsigned long last, void *entry, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_internal(entry))) return XA_ERROR(-EINVAL); if (last < first) return XA_ERROR(-EINVAL); do { xas_lock(&xas); if (entry) { unsigned int order = BITS_PER_LONG; if (last + 1) order = __ffs(last + 1); xas_set_order(&xas, last, order); xas_create(&xas, true); if (xas_error(&xas)) goto unlock; } do { xas_set_range(&xas, first, last); xas_store(&xas, entry); if (xas_error(&xas)) goto unlock; first += xas_size(&xas); } while (first <= last); unlock: xas_unlock(&xas); } while (xas_nomem(&xas, gfp)); return xas_result(&xas, NULL); } EXPORT_SYMBOL(xa_store_range); /** * xa_get_order() - Get the order of an entry. * @xa: XArray. * @index: Index of the entry. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xa_get_order(struct xarray *xa, unsigned long index) { XA_STATE(xas, xa, index); void *entry; int order = 0; rcu_read_lock(); entry = xas_load(&xas); if (!entry) goto unlock; if (!xas.xa_node) goto unlock; for (;;) { unsigned int slot = xas.xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xas.xa_node->slots[slot])) break; order++; } order += xas.xa_node->shift; unlock: rcu_read_unlock(); return order; } EXPORT_SYMBOL(xa_get_order); #endif /* CONFIG_XARRAY_MULTI */ /** * __xa_alloc() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @limit: Range for allocated ID. * @entry: New entry. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @gfp flags permit. * Return: 0 on success, -ENOMEM if memory could not be allocated or * -EBUSY if there are no free entries in @limit. */ int __xa_alloc(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, gfp_t gfp) { XA_STATE(xas, xa, 0); if (WARN_ON_ONCE(xa_is_advanced(entry))) return -EINVAL; if (WARN_ON_ONCE(!xa_track_free(xa))) return -EINVAL; if (!entry) entry = XA_ZERO_ENTRY; do { xas.xa_index = limit.min; xas_find_marked(&xas, limit.max, XA_FREE_MARK); if (xas.xa_node == XAS_RESTART) xas_set_err(&xas, -EBUSY); else *id = xas.xa_index; xas_store(&xas, entry); xas_clear_mark(&xas, XA_FREE_MARK); } while (__xas_nomem(&xas, gfp)); return xas_error(&xas); } EXPORT_SYMBOL(__xa_alloc); /** * __xa_alloc_cyclic() - Find somewhere to store this entry in the XArray. * @xa: XArray. * @id: Pointer to ID. * @entry: New entry. * @limit: Range of allocated ID. * @next: Pointer to next ID to allocate. * @gfp: Memory allocation flags. * * Finds an empty entry in @xa between @limit.min and @limit.max, * stores the index into the @id pointer, then stores the entry at * that index. A concurrent lookup will not see an uninitialised @id. * The search for an empty entry will start at @next and will wrap * around if necessary. * * Context: Any context. Expects xa_lock to be held on entry. May * release and reacquire xa_lock if @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 or -EBUSY if there are no free entries in @limit. */ int __xa_alloc_cyclic(struct xarray *xa, u32 *id, void *entry, struct xa_limit limit, u32 *next, gfp_t gfp) { u32 min = limit.min; int ret; limit.min = max(min, *next); ret = __xa_alloc(xa, id, entry, limit, gfp); if ((xa->xa_flags & XA_FLAGS_ALLOC_WRAPPED) && ret == 0) { xa->xa_flags &= ~XA_FLAGS_ALLOC_WRAPPED; ret = 1; } if (ret < 0 && limit.min > min) { limit.min = min; ret = __xa_alloc(xa, id, entry, limit, gfp); if (ret == 0) ret = 1; } if (ret >= 0) { *next = *id + 1; if (*next == 0) xa->xa_flags |= XA_FLAGS_ALLOC_WRAPPED; } return ret; } EXPORT_SYMBOL(__xa_alloc_cyclic); /** * __xa_set_mark() - Set this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_set_mark(&xas, mark); } EXPORT_SYMBOL(__xa_set_mark); /** * __xa_clear_mark() - Clear this mark on this entry while locked. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Context: Any context. Expects xa_lock to be held on entry. */ void __xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry = xas_load(&xas); if (entry) xas_clear_mark(&xas, mark); } EXPORT_SYMBOL(__xa_clear_mark); /** * xa_get_mark() - Inquire whether this mark is set on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * This function uses the RCU read lock, so the result may be out of date * by the time it returns. If you need the result to be stable, use a lock. * * Context: Any context. Takes and releases the RCU lock. * Return: True if the entry at @index has this mark set, false if it doesn't. */ bool xa_get_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { XA_STATE(xas, xa, index); void *entry; rcu_read_lock(); entry = xas_start(&xas); while (xas_get_mark(&xas, mark)) { if (!xa_is_node(entry)) goto found; entry = xas_descend(&xas, xa_to_node(entry)); } rcu_read_unlock(); return false; found: rcu_read_unlock(); return true; } EXPORT_SYMBOL(xa_get_mark); /** * xa_set_mark() - Set this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Attempting to set a mark on a %NULL entry does not succeed. * * Context: Process context. Takes and releases the xa_lock. */ void xa_set_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_set_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_set_mark); /** * xa_clear_mark() - Clear this mark on this entry. * @xa: XArray. * @index: Index of entry. * @mark: Mark number. * * Clearing a mark always succeeds. * * Context: Process context. Takes and releases the xa_lock. */ void xa_clear_mark(struct xarray *xa, unsigned long index, xa_mark_t mark) { xa_lock(xa); __xa_clear_mark(xa, index, mark); xa_unlock(xa); } EXPORT_SYMBOL(xa_clear_mark); /** * xa_find() - Search the XArray for an entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter, and has the lowest * index that is at least @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may not find * entries which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The entry, if found, otherwise %NULL. */ void *xa_find(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp); void *entry; rcu_read_lock(); do { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); } while (xas_retry(&xas, entry)); rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find); static bool xas_sibling(struct xa_state *xas) { struct xa_node *node = xas->xa_node; unsigned long mask; if (!node) return false; mask = (XA_CHUNK_SIZE << node->shift) - 1; return (xas->xa_index & mask) > ((unsigned long)xas->xa_offset << node->shift); } /** * xa_find_after() - Search the XArray for a present entry. * @xa: XArray. * @indexp: Pointer to an index. * @max: Maximum index to search to. * @filter: Selection criterion. * * Finds the entry in @xa which matches the @filter and has the lowest * index that is above @indexp and no more than @max. * If an entry is found, @indexp is updated to be the index of the entry. * This function is protected by the RCU read lock, so it may miss entries * which are being simultaneously added. It will not return an * %XA_RETRY_ENTRY; if you need to see retry entries, use xas_find(). * * Context: Any context. Takes and releases the RCU lock. * Return: The pointer, if found, otherwise %NULL. */ void *xa_find_after(struct xarray *xa, unsigned long *indexp, unsigned long max, xa_mark_t filter) { XA_STATE(xas, xa, *indexp + 1); void *entry; if (xas.xa_index == 0) return NULL; rcu_read_lock(); for (;;) { if ((__force unsigned int)filter < XA_MAX_MARKS) entry = xas_find_marked(&xas, max, filter); else entry = xas_find(&xas, max); if (xas_invalid(&xas)) break; if (xas_sibling(&xas)) continue; if (!xas_retry(&xas, entry)) break; } rcu_read_unlock(); if (entry) *indexp = xas.xa_index; return entry; } EXPORT_SYMBOL(xa_find_after); static unsigned int xas_extract_present(struct xa_state *xas, void **dst, unsigned long max, unsigned int n) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each(xas, entry, max) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } static unsigned int xas_extract_marked(struct xa_state *xas, void **dst, unsigned long max, unsigned int n, xa_mark_t mark) { void *entry; unsigned int i = 0; rcu_read_lock(); xas_for_each_marked(xas, entry, max, mark) { if (xas_retry(xas, entry)) continue; dst[i++] = entry; if (i == n) break; } rcu_read_unlock(); return i; } /** * xa_extract() - Copy selected entries from the XArray into a normal array. * @xa: The source XArray to copy from. * @dst: The buffer to copy entries into. * @start: The first index in the XArray eligible to be selected. * @max: The last index in the XArray eligible to be selected. * @n: The maximum number of entries to copy. * @filter: Selection criterion. * * Copies up to @n entries that match @filter from the XArray. The * copied entries will have indices between @start and @max, inclusive. * * The @filter may be an XArray mark value, in which case entries which are * marked with that mark will be copied. It may also be %XA_PRESENT, in * which case all entries which are not %NULL will be copied. * * The entries returned may not represent a snapshot of the XArray at a * moment in time. For example, if another thread stores to index 5, then * index 10, calling xa_extract() may return the old contents of index 5 * and the new contents of index 10. Indices not modified while this * function is running will not be skipped. * * If you need stronger guarantees, holding the xa_lock across calls to this * function will prevent concurrent modification. * * Context: Any context. Takes and releases the RCU lock. * Return: The number of entries copied. */ unsigned int xa_extract(struct xarray *xa, void **dst, unsigned long start, unsigned long max, unsigned int n, xa_mark_t filter) { XA_STATE(xas, xa, start); if (!n) return 0; if ((__force unsigned int)filter < XA_MAX_MARKS) return xas_extract_marked(&xas, dst, max, n, filter); return xas_extract_present(&xas, dst, max, n); } EXPORT_SYMBOL(xa_extract); /** * xa_destroy() - Free all internal data structures. * @xa: XArray. * * After calling this function, the XArray is empty and has freed all memory * allocated for its internal data structures. You are responsible for * freeing the objects referenced by the XArray. * * Context: Any context. Takes and releases the xa_lock, interrupt-safe. */ void xa_destroy(struct xarray *xa) { XA_STATE(xas, xa, 0); unsigned long flags; void *entry; xas.xa_node = NULL; xas_lock_irqsave(&xas, flags); entry = xa_head_locked(xa); RCU_INIT_POINTER(xa->xa_head, NULL); xas_init_marks(&xas); if (xa_zero_busy(xa)) xa_mark_clear(xa, XA_FREE_MARK); /* lockdep checks we're still holding the lock in xas_free_nodes() */ if (xa_is_node(entry)) xas_free_nodes(&xas, xa_to_node(entry)); xas_unlock_irqrestore(&xas, flags); } EXPORT_SYMBOL(xa_destroy); #ifdef XA_DEBUG void xa_dump_node(const struct xa_node *node) { unsigned i, j; if (!node) return; if ((unsigned long)node & 3) { pr_cont("node %px\n", node); return; } pr_cont("node %px %s %d parent %px shift %d count %d values %d " "array %px list %px %px marks", node, node->parent ? "offset" : "max", node->offset, node->parent, node->shift, node->count, node->nr_values, node->array, node->private_list.prev, node->private_list.next); for (i = 0; i < XA_MAX_MARKS; i++) for (j = 0; j < XA_MARK_LONGS; j++) pr_cont(" %lx", node->marks[i][j]); pr_cont("\n"); } void xa_dump_index(unsigned long index, unsigned int shift) { if (!shift) pr_info("%lu: ", index); else if (shift >= BITS_PER_LONG) pr_info("0-%lu: ", ~0UL); else pr_info("%lu-%lu: ", index, index | ((1UL << shift) - 1)); } void xa_dump_entry(const void *entry, unsigned long index, unsigned long shift) { if (!entry) return; xa_dump_index(index, shift); if (xa_is_node(entry)) { if (shift == 0) { pr_cont("%px\n", entry); } else { unsigned long i; struct xa_node *node = xa_to_node(entry); xa_dump_node(node); for (i = 0; i < XA_CHUNK_SIZE; i++) xa_dump_entry(node->slots[i], index + (i << node->shift), node->shift); } } else if (xa_is_value(entry)) pr_cont("value %ld (0x%lx) [%px]\n", xa_to_value(entry), xa_to_value(entry), entry); else if (!xa_is_internal(entry)) pr_cont("%px\n", entry); else if (xa_is_retry(entry)) pr_cont("retry (%ld)\n", xa_to_internal(entry)); else if (xa_is_sibling(entry)) pr_cont("sibling (slot %ld)\n", xa_to_sibling(entry)); else if (xa_is_zero(entry)) pr_cont("zero (%ld)\n", xa_to_internal(entry)); else pr_cont("UNKNOWN ENTRY (%px)\n", entry); } void xa_dump(const struct xarray *xa) { void *entry = xa->xa_head; unsigned int shift = 0; pr_info("xarray: %px head %px flags %x marks %d %d %d\n", xa, entry, xa->xa_flags, xa_marked(xa, XA_MARK_0), xa_marked(xa, XA_MARK_1), xa_marked(xa, XA_MARK_2)); if (xa_is_node(entry)) shift = xa_to_node(entry)->shift + XA_CHUNK_SHIFT; xa_dump_entry(entry, 0, shift); } #endif |
| 2 9 9 9 9 9 74 74 74 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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. * * Implementation of the Transmission Control Protocol(TCP). * * IPv4 specific functions * * code split from: * linux/ipv4/tcp.c * linux/ipv4/tcp_input.c * linux/ipv4/tcp_output.c * * See tcp.c for author information */ /* * Changes: * David S. Miller : New socket lookup architecture. * This code is dedicated to John Dyson. * David S. Miller : Change semantics of established hash, * half is devoted to TIME_WAIT sockets * and the rest go in the other half. * Andi Kleen : Add support for syncookies and fixed * some bugs: ip options weren't passed to * the TCP layer, missed a check for an * ACK bit. * Andi Kleen : Implemented fast path mtu discovery. * Fixed many serious bugs in the * request_sock handling and moved * most of it into the af independent code. * Added tail drop and some other bugfixes. * Added new listen semantics. * Mike McLagan : Routing by source * Juan Jose Ciarlante: ip_dynaddr bits * Andi Kleen: various fixes. * Vitaly E. Lavrov : Transparent proxy revived after year * coma. * Andi Kleen : Fix new listen. * Andi Kleen : Fix accept error reporting. * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov allow both IPv4 and IPv6 sockets to bind * a single port at the same time. */ #define pr_fmt(fmt) "TCP: " fmt #include <linux/bottom_half.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/random.h> #include <linux/cache.h> #include <linux/jhash.h> #include <linux/init.h> #include <linux/times.h> #include <linux/slab.h> #include <net/net_namespace.h> #include <net/icmp.h> #include <net/inet_hashtables.h> #include <net/tcp.h> #include <net/transp_v6.h> #include <net/ipv6.h> #include <net/inet_common.h> #include <net/timewait_sock.h> #include <net/xfrm.h> #include <net/secure_seq.h> #include <net/busy_poll.h> #include <linux/inet.h> #include <linux/ipv6.h> #include <linux/stddef.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/inetdevice.h> #include <crypto/hash.h> #include <linux/scatterlist.h> #include <trace/events/tcp.h> #ifdef CONFIG_TCP_MD5SIG static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th); #endif struct inet_hashinfo tcp_hashinfo; EXPORT_SYMBOL(tcp_hashinfo); static u32 tcp_v4_init_seq(const struct sk_buff *skb) { return secure_tcp_seq(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, tcp_hdr(skb)->dest, tcp_hdr(skb)->source); } static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) { return secure_tcp_ts_off(net, ip_hdr(skb)->daddr, ip_hdr(skb)->saddr); } int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); if (tw->tw_substate == TCP_FIN_WAIT2) reuse = 0; if (reuse == 2) { /* Still does not detect *everything* that goes through * lo, since we require a loopback src or dst address * or direct binding to 'lo' interface. */ bool loopback = false; if (tw->tw_bound_dev_if == LOOPBACK_IFINDEX) loopback = true; #if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { if (ipv6_addr_loopback(&tw->tw_v6_daddr) || (ipv6_addr_v4mapped(&tw->tw_v6_daddr) && (tw->tw_v6_daddr.s6_addr[12] == 127)) || ipv6_addr_loopback(&tw->tw_v6_rcv_saddr) || (ipv6_addr_v4mapped(&tw->tw_v6_rcv_saddr) && (tw->tw_v6_rcv_saddr.s6_addr[12] == 127))) loopback = true; } else #endif { if (ipv4_is_loopback(tw->tw_daddr) || ipv4_is_loopback(tw->tw_rcv_saddr)) loopback = true; } if (!loopback) reuse = 0; } /* With PAWS, it is safe from the viewpoint of data integrity. Even without PAWS it is safe provided sequence spaces do not overlap i.e. at data rates <= 80Mbit/sec. Actually, the idea is close to VJ's one, only timestamp cache is held not per host, but per port pair and TW bucket is used as state holder. If TW bucket has been already destroyed we fall back to VJ's scheme and use initial timestamp retrieved from peer table. */ if (tcptw->tw_ts_recent_stamp && (!twp || (reuse && time_after32(ktime_get_seconds(), tcptw->tw_ts_recent_stamp)))) { /* inet_twsk_hashdance() sets sk_refcnt after putting twsk * and releasing the bucket lock. */ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt))) return 0; /* In case of repair and re-using TIME-WAIT sockets we still * want to be sure that it is safe as above but honor the * sequence numbers and time stamps set as part of the repair * process. * * Without this check re-using a TIME-WAIT socket with TCP * repair would accumulate a -1 on the repair assigned * sequence number. The first time it is reused the sequence * is -1, the second time -2, etc. This fixes that issue * without appearing to create any others. */ if (likely(!tp->repair)) { u32 seq = tcptw->tw_snd_nxt + 65535 + 2; if (!seq) seq = 1; WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } return 1; } return 0; } EXPORT_SYMBOL_GPL(tcp_twsk_unique); static int tcp_v4_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { /* This check is replicated from tcp_v4_connect() and intended to * prevent BPF program called below from accessing bytes that are out * of the bound specified by user in addr_len. */ if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; sock_owned_by_me(sk); return BPF_CGROUP_RUN_PROG_INET4_CONNECT(sk, uaddr); } /* This will initiate an outgoing connection. */ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) { struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); __be16 orig_sport, orig_dport; __be32 daddr, nexthop; struct flowi4 *fl4; struct rtable *rt; int err; struct ip_options_rcu *inet_opt; struct inet_timewait_death_row *tcp_death_row = &sock_net(sk)->ipv4.tcp_death_row; if (addr_len < sizeof(struct sockaddr_in)) return -EINVAL; if (usin->sin_family != AF_INET) return -EAFNOSUPPORT; nexthop = daddr = usin->sin_addr.s_addr; inet_opt = rcu_dereference_protected(inet->inet_opt, lockdep_sock_is_held(sk)); if (inet_opt && inet_opt->opt.srr) { if (!daddr) return -EINVAL; nexthop = inet_opt->opt.faddr; } orig_sport = inet->inet_sport; orig_dport = usin->sin_port; fl4 = &inet->cork.fl.u.ip4; rt = ip_route_connect(fl4, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, orig_sport, orig_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); if (err == -ENETUNREACH) IP_INC_STATS(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); return err; } if (rt->rt_flags & (RTCF_MULTICAST | RTCF_BROADCAST)) { ip_rt_put(rt); return -ENETUNREACH; } if (!inet_opt || !inet_opt->opt.srr) daddr = fl4->daddr; if (!inet->inet_saddr) inet->inet_saddr = fl4->saddr; sk_rcv_saddr_set(sk, inet->inet_saddr); if (tp->rx_opt.ts_recent_stamp && inet->inet_daddr != daddr) { /* Reset inherited state */ tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; sk_daddr_set(sk, daddr); inet_csk(sk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(sk)->icsk_ext_hdr_len = inet_opt->opt.optlen; tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT; /* Socket identity is still unknown (sport may be zero). * However we set state to SYN-SENT and not releasing socket * lock select source port, enter ourselves into the hash tables and * complete initialization after this. */ tcp_set_state(sk, TCP_SYN_SENT); err = inet_hash_connect(tcp_death_row, sk); if (err) goto failure; sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto failure; } /* OK, now commit destination to socket. */ sk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(sk, &rt->dst); rt = NULL; if (likely(!tp->repair)) { if (!tp->write_seq) WRITE_ONCE(tp->write_seq, secure_tcp_seq(inet->inet_saddr, inet->inet_daddr, inet->inet_sport, usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); } inet->inet_id = prandom_u32(); if (tcp_fastopen_defer_connect(sk, &err)) return err; if (err) goto failure; err = tcp_connect(sk); if (err) goto failure; return 0; failure: /* * This unhashes the socket and releases the local port, * if necessary. */ tcp_set_state(sk, TCP_CLOSE); if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); ip_rt_put(rt); sk->sk_route_caps = 0; inet->inet_dport = 0; return err; } EXPORT_SYMBOL(tcp_v4_connect); /* * This routine reacts to ICMP_FRAG_NEEDED mtu indications as defined in RFC1191. * It can be called through tcp_release_cb() if socket was owned by user * at the time tcp_v4_err() was called to handle ICMP message. */ void tcp_v4_mtu_reduced(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct dst_entry *dst; u32 mtu; if ((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) return; mtu = READ_ONCE(tcp_sk(sk)->mtu_info); dst = inet_csk_update_pmtu(sk, mtu); if (!dst) return; /* Something is about to be wrong... Remember soft error * for the case, if this connection will not able to recover. */ if (mtu < dst_mtu(dst) && ip_dont_fragment(sk, dst)) sk->sk_err_soft = EMSGSIZE; mtu = dst_mtu(dst); if (inet->pmtudisc != IP_PMTUDISC_DONT && ip_sk_accept_pmtu(sk) && inet_csk(sk)->icsk_pmtu_cookie > mtu) { tcp_sync_mss(sk, mtu); /* Resend the TCP packet because it's * clear that the old packet has been * dropped. This is the new "fast" path mtu * discovery. */ tcp_simple_retransmit(sk); } /* else let the usual retransmit timer handle it */ } EXPORT_SYMBOL(tcp_v4_mtu_reduced); static void do_redirect(struct sk_buff *skb, struct sock *sk) { struct dst_entry *dst = __sk_dst_check(sk, 0); if (dst) dst->ops->redirect(dst, sk, skb); } /* handle ICMP messages on TCP_NEW_SYN_RECV request sockets */ void tcp_req_err(struct sock *sk, u32 seq, bool abort) { struct request_sock *req = inet_reqsk(sk); struct net *net = sock_net(sk); /* ICMPs are not backlogged, hence we cannot get * an established socket here. */ if (seq != tcp_rsk(req)->snt_isn) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); } else if (abort) { /* * Still in SYN_RECV, just remove it silently. * There is no good way to pass the error to the newly * created socket, and POSIX does not want network * errors returned from accept(). */ inet_csk_reqsk_queue_drop(req->rsk_listener, req); tcp_listendrop(req->rsk_listener); } reqsk_put(req); } EXPORT_SYMBOL(tcp_req_err); /* * This routine is called by the ICMP module when it gets some * sort of error condition. If err < 0 then the socket should * be closed and the error returned to the user. If err > 0 * it's just the icmp type << 8 | icmp code. After adjustment * header points to the first 8 bytes of the tcp header. We need * to find the appropriate port. * * The locking strategy used here is very "optimistic". When * someone else accesses the socket the ICMP is just dropped * and for some paths there is no check at all. * A more general error queue to queue errors for later handling * is probably better. * */ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) { const struct iphdr *iph = (const struct iphdr *)icmp_skb->data; struct tcphdr *th = (struct tcphdr *)(icmp_skb->data + (iph->ihl << 2)); struct inet_connection_sock *icsk; struct tcp_sock *tp; struct inet_sock *inet; const int type = icmp_hdr(icmp_skb)->type; const int code = icmp_hdr(icmp_skb)->code; struct sock *sk; struct sk_buff *skb; struct request_sock *fastopen; u32 seq, snd_una; s32 remaining; u32 delta_us; int err; struct net *net = dev_net(icmp_skb->dev); sk = __inet_lookup_established(net, &tcp_hashinfo, iph->daddr, th->dest, iph->saddr, ntohs(th->source), inet_iif(icmp_skb), 0); if (!sk) { __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); return -ENOENT; } if (sk->sk_state == TCP_TIME_WAIT) { inet_twsk_put(inet_twsk(sk)); return 0; } seq = ntohl(th->seq); if (sk->sk_state == TCP_NEW_SYN_RECV) { tcp_req_err(sk, seq, type == ICMP_PARAMETERPROB || type == ICMP_TIME_EXCEEDED || (type == ICMP_DEST_UNREACH && (code == ICMP_NET_UNREACH || code == ICMP_HOST_UNREACH))); return 0; } bh_lock_sock(sk); /* If too many ICMPs get dropped on busy * servers this needs to be solved differently. * We do take care of PMTU discovery (RFC1191) special case : * we can receive locally generated ICMP messages while socket is held. */ if (sock_owned_by_user(sk)) { if (!(type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED)) __NET_INC_STATS(net, LINUX_MIB_LOCKDROPPEDICMPS); } if (sk->sk_state == TCP_CLOSE) goto out; if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto out; } icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { __NET_INC_STATS(net, LINUX_MIB_OUTOFWINDOWICMPS); goto out; } switch (type) { case ICMP_REDIRECT: if (!sock_owned_by_user(sk)) do_redirect(icmp_skb, sk); goto out; case ICMP_SOURCE_QUENCH: /* Just silently ignore these. */ goto out; case ICMP_PARAMETERPROB: err = EPROTO; break; case ICMP_DEST_UNREACH: if (code > NR_ICMP_UNREACH) goto out; if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */ /* We are not interested in TCP_LISTEN and open_requests * (SYN-ACKs send out by Linux are always <576bytes so * they should go through unfragmented). */ if (sk->sk_state == TCP_LISTEN) goto out; WRITE_ONCE(tp->mtu_info, info); if (!sock_owned_by_user(sk)) { tcp_v4_mtu_reduced(sk); } else { if (!test_and_set_bit(TCP_MTU_REDUCED_DEFERRED, &sk->sk_tsq_flags)) sock_hold(sk); } goto out; } err = icmp_err_convert[code].errno; /* check if icmp_skb allows revert of backoff * (see draft-zimmermann-tcp-lcd) */ if (code != ICMP_NET_UNREACH && code != ICMP_HOST_UNREACH) break; if (seq != tp->snd_una || !icsk->icsk_retransmits || !icsk->icsk_backoff || fastopen) break; if (sock_owned_by_user(sk)) break; skb = tcp_rtx_queue_head(sk); if (WARN_ON_ONCE(!skb)) break; icsk->icsk_backoff--; icsk->icsk_rto = tp->srtt_us ? __tcp_set_rto(tp) : TCP_TIMEOUT_INIT; icsk->icsk_rto = inet_csk_rto_backoff(icsk, TCP_RTO_MAX); tcp_mstamp_refresh(tp); delta_us = (u32)(tp->tcp_mstamp - tcp_skb_timestamp_us(skb)); remaining = icsk->icsk_rto - usecs_to_jiffies(delta_us); if (remaining > 0) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); } else { /* RTO revert clocked out retransmission. * Will retransmit now */ tcp_retransmit_timer(sk); } break; case ICMP_TIME_EXCEEDED: err = EHOSTUNREACH; break; default: goto out; } switch (sk->sk_state) { case TCP_SYN_SENT: case TCP_SYN_RECV: /* Only in fast or simultaneous open. If a fast open socket is * is already accepted it is treated as a connected one below. */ if (fastopen && !fastopen->sk) break; if (!sock_owned_by_user(sk)) { sk->sk_err = err; sk->sk_error_report(sk); tcp_done(sk); } else { sk->sk_err_soft = err; } goto out; } /* If we've already connected we will keep trying * until we time out, or the user gives up. * * rfc1122 4.2.3.9 allows to consider as hard errors * only PROTO_UNREACH and PORT_UNREACH (well, FRAG_FAILED too, * but it is obsoleted by pmtu discovery). * * Note, that in modern internet, where routing is unreliable * and in each dark corner broken firewalls sit, sending random * errors ordered by their masters even this two messages finally lose * their original sense (even Linux sends invalid PORT_UNREACHs) * * Now we are in compliance with RFCs. * --ANK (980905) */ inet = inet_sk(sk); if (!sock_owned_by_user(sk) && inet->recverr) { sk->sk_err = err; sk->sk_error_report(sk); } else { /* Only an error on timeout */ sk->sk_err_soft = err; } out: bh_unlock_sock(sk); sock_put(sk); return 0; } void __tcp_v4_send_check(struct sk_buff *skb, __be32 saddr, __be32 daddr) { struct tcphdr *th = tcp_hdr(skb); th->check = ~tcp_v4_check(skb->len, saddr, daddr, 0); skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct tcphdr, check); } /* This routine computes an IPv4 TCP checksum. */ void tcp_v4_send_check(struct sock *sk, struct sk_buff *skb) { const struct inet_sock *inet = inet_sk(sk); __tcp_v4_send_check(skb, inet->inet_saddr, inet->inet_daddr); } EXPORT_SYMBOL(tcp_v4_send_check); /* * This routine will send an RST to the other tcp. * * Someone asks: why I NEVER use socket parameters (TOS, TTL etc.) * for reset. * Answer: if a packet caused RST, it is not for a socket * existing in our system, if it is matched to a socket, * it is just duplicate segment or bug in other side's TCP. * So that we build reply only basing on parameters * arrived with segment. * Exception: precedence violation. We do not implement it in any case. */ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; #ifdef CONFIG_TCP_MD5SIG __be32 opt[(TCPOLEN_MD5SIG_ALIGNED >> 2)]; #endif } rep; struct ip_reply_arg arg; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key = NULL; const __u8 *hash_location = NULL; unsigned char newhash[16]; int genhash; struct sock *sk1 = NULL; #endif u64 transmit_time = 0; struct sock *ctl_sk; struct net *net; /* Never send a reset in response to a reset. */ if (th->rst) return; /* If sk not NULL, it means we did a successful lookup and incoming * route had to be correct. prequeue might have dropped our dst. */ if (!sk && skb_rtable(skb)->rt_type != RTN_LOCAL) return; /* Swap the send and the receive. */ memset(&rep, 0, sizeof(rep)); rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = sizeof(struct tcphdr) / 4; rep.th.rst = 1; if (th->ack) { rep.th.seq = th->ack_seq; } else { rep.th.ack = 1; rep.th.ack_seq = htonl(ntohl(th->seq) + th->syn + th->fin + skb->len - (th->doff << 2)); } memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); net = sk ? sock_net(sk) : dev_net(skb_dst(skb)->dev); #ifdef CONFIG_TCP_MD5SIG rcu_read_lock(); hash_location = tcp_parse_md5sig_option(th); if (sk && sk_fullsock(sk)) { key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *) &ip_hdr(skb)->saddr, AF_INET); } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. * we are not loose security here: * Incoming packet is checked with md5 hash with finding key, * no RST generated if md5 hash doesn't match. */ sk1 = __inet_lookup_listener(net, &tcp_hashinfo, NULL, 0, ip_hdr(skb)->saddr, th->source, ip_hdr(skb)->daddr, ntohs(th->source), inet_iif(skb), tcp_v4_sdif(skb)); /* don't send rst if it can't find key */ if (!sk1) goto out; key = tcp_md5_do_lookup(sk1, (union tcp_md5_addr *) &ip_hdr(skb)->saddr, AF_INET); if (!key) goto out; genhash = tcp_v4_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto out; } if (key) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); /* Update length and the length the header thinks exists */ arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len / 4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[1], key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; arg.flags = (sk && inet_sk_transparent(sk)) ? IP_REPLY_ARG_NOSRCCHECK : 0; /* When socket is gone, all binding information is lost. * routing might fail in this case. No choice here, if we choose to force * input interface, we will misroute in case of asymmetric route. */ if (sk) { arg.bound_dev_if = sk->sk_bound_dev_if; if (sk_fullsock(sk)) trace_tcp_send_reset(sk, skb); } BUILD_BUG_ON(offsetof(struct sock, sk_bound_dev_if) != offsetof(struct inet_timewait_sock, tw_bound_dev_if)); arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); if (sk) { ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); } ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time); ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); #ifdef CONFIG_TCP_MD5SIG out: rcu_read_unlock(); #endif } /* The code following below sending ACKs in SYN-RECV and TIME-WAIT states outside socket context is ugly, certainly. What can I do? */ static void tcp_v4_send_ack(const struct sock *sk, struct sk_buff *skb, u32 seq, u32 ack, u32 win, u32 tsval, u32 tsecr, int oif, struct tcp_md5sig_key *key, int reply_flags, u8 tos) { const struct tcphdr *th = tcp_hdr(skb); struct { struct tcphdr th; __be32 opt[(TCPOLEN_TSTAMP_ALIGNED >> 2) #ifdef CONFIG_TCP_MD5SIG + (TCPOLEN_MD5SIG_ALIGNED >> 2) #endif ]; } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; struct sock *ctl_sk; u64 transmit_time; memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); arg.iov[0].iov_base = (unsigned char *)&rep; arg.iov[0].iov_len = sizeof(rep.th); if (tsecr) { rep.opt[0] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_TIMESTAMP << 8) | TCPOLEN_TIMESTAMP); rep.opt[1] = htonl(tsval); rep.opt[2] = htonl(tsecr); arg.iov[0].iov_len += TCPOLEN_TSTAMP_ALIGNED; } /* Swap the send and the receive. */ rep.th.dest = th->source; rep.th.source = th->dest; rep.th.doff = arg.iov[0].iov_len / 4; rep.th.seq = htonl(seq); rep.th.ack_seq = htonl(ack); rep.th.ack = 1; rep.th.window = htons(win); #ifdef CONFIG_TCP_MD5SIG if (key) { int offset = (tsecr) ? 3 : 0; rep.opt[offset++] = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) | (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG); arg.iov[0].iov_len += TCPOLEN_MD5SIG_ALIGNED; rep.th.doff = arg.iov[0].iov_len/4; tcp_v4_md5_hash_hdr((__u8 *) &rep.opt[offset], key, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &rep.th); } #endif arg.flags = reply_flags; arg.csum = csum_tcpudp_nofold(ip_hdr(skb)->daddr, ip_hdr(skb)->saddr, /* XXX */ arg.iov[0].iov_len, IPPROTO_TCP, 0); arg.csumoffset = offsetof(struct tcphdr, check) / 2; if (oif) arg.bound_dev_if = oif; arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); ctl_sk = this_cpu_read(*net->ipv4.tcp_sk); ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_mark : sk->sk_mark; ctl_sk->sk_priority = (sk->sk_state == TCP_TIME_WAIT) ? inet_twsk(sk)->tw_priority : sk->sk_priority; transmit_time = tcp_transmit_time(sk); ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len, transmit_time); ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb) { struct inet_timewait_sock *tw = inet_twsk(sk); struct tcp_timewait_sock *tcptw = tcp_twsk(sk); tcp_v4_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt, tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp_raw() + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0, tw->tw_tos ); inet_twsk_put(tw); } static void tcp_v4_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, struct request_sock *req) { /* sk->sk_state == TCP_LISTEN -> for regular TCP_SYN_RECV * sk->sk_state == TCP_SYN_RECV -> for Fast Open. */ u32 seq = (sk->sk_state == TCP_LISTEN) ? tcp_rsk(req)->snt_isn + 1 : tcp_sk(sk)->snd_nxt; /* RFC 7323 2.3 * The window field (SEG.WND) of every outgoing segment, with the * exception of <SYN> segments, MUST be right-shifted by * Rcv.Wind.Shift bits: */ tcp_v4_send_ack(sk, skb, seq, tcp_rsk(req)->rcv_nxt, req->rsk_rcv_wnd >> inet_rsk(req)->rcv_wscale, tcp_time_stamp_raw() + tcp_rsk(req)->ts_off, req->ts_recent, 0, tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&ip_hdr(skb)->saddr, AF_INET), inet_rsk(req)->no_srccheck ? IP_REPLY_ARG_NOSRCCHECK : 0, ip_hdr(skb)->tos); } /* * Send a SYN-ACK after having received a SYN. * This still operates on a request_sock only, not on a big * socket. */ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, struct flowi *fl, struct request_sock *req, struct tcp_fastopen_cookie *foc, enum tcp_synack_type synack_type) { const struct inet_request_sock *ireq = inet_rsk(req); struct flowi4 fl4; int err = -1; struct sk_buff *skb; /* First, grab a route. */ if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL) return -1; skb = tcp_make_synack(sk, dst, req, foc, synack_type); if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); rcu_read_lock(); err = ip_build_and_send_pkt(skb, sk, ireq->ir_loc_addr, ireq->ir_rmt_addr, rcu_dereference(ireq->ireq_opt)); rcu_read_unlock(); err = net_xmit_eval(err); } return err; } /* * IPv4 request_sock destructor. */ static void tcp_v4_reqsk_destructor(struct request_sock *req) { kfree(rcu_dereference_protected(inet_rsk(req)->ireq_opt, 1)); } #ifdef CONFIG_TCP_MD5SIG /* * RFC2385 MD5 checksumming requires a mapping of * IP address->MD5 Key. * We need to maintain these in the sk structure. */ DEFINE_STATIC_KEY_FALSE(tcp_md5_needed); EXPORT_SYMBOL(tcp_md5_needed); /* Find the Key structure for an address. */ struct tcp_md5sig_key *__tcp_md5_do_lookup(const struct sock *sk, const union tcp_md5_addr *addr, int family) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; const struct tcp_md5sig_info *md5sig; __be32 mask; struct tcp_md5sig_key *best_match = NULL; bool match; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; if (family == AF_INET) { mask = inet_make_mask(key->prefixlen); match = (key->addr.a4.s_addr & mask) == (addr->a4.s_addr & mask); #if IS_ENABLED(CONFIG_IPV6) } else if (family == AF_INET6) { match = ipv6_prefix_equal(&key->addr.a6, &addr->a6, key->prefixlen); #endif } else { match = false; } if (match && (!best_match || key->prefixlen > best_match->prefixlen)) best_match = key; } return best_match; } EXPORT_SYMBOL(__tcp_md5_do_lookup); static struct tcp_md5sig_key *tcp_md5_do_lookup_exact(const struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen) { const struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; unsigned int size = sizeof(struct in_addr); const struct tcp_md5sig_info *md5sig; /* caller either holds rcu_read_lock() or socket lock */ md5sig = rcu_dereference_check(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) return NULL; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) size = sizeof(struct in6_addr); #endif hlist_for_each_entry_rcu(key, &md5sig->head, node) { if (key->family != family) continue; if (!memcmp(&key->addr, addr, size) && key->prefixlen == prefixlen) return key; } return NULL; } struct tcp_md5sig_key *tcp_v4_md5_lookup(const struct sock *sk, const struct sock *addr_sk) { const union tcp_md5_addr *addr; addr = (const union tcp_md5_addr *)&addr_sk->sk_daddr; return tcp_md5_do_lookup(sk, addr, AF_INET); } EXPORT_SYMBOL(tcp_v4_md5_lookup); /* This can be called on a newly created socket, from other files */ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen, const u8 *newkey, u8 newkeylen, gfp_t gfp) { /* Add Key to the list */ struct tcp_md5sig_key *key; struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_info *md5sig; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { /* Pre-existing entry - just update that one. * Note that the key might be used concurrently. */ memcpy(key->key, newkey, newkeylen); /* Pairs with READ_ONCE() in tcp_md5_hash_key(). * Also note that a reader could catch new key->keylen value * but old key->key[], this is the reason we use __GFP_ZERO * at sock_kmalloc() time below these lines. */ WRITE_ONCE(key->keylen, newkeylen); return 0; } md5sig = rcu_dereference_protected(tp->md5sig_info, lockdep_sock_is_held(sk)); if (!md5sig) { md5sig = kmalloc(sizeof(*md5sig), gfp); if (!md5sig) return -ENOMEM; sk_nocaps_add(sk, NETIF_F_GSO_MASK); INIT_HLIST_HEAD(&md5sig->head); rcu_assign_pointer(tp->md5sig_info, md5sig); } key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { sock_kfree_s(sk, key, sizeof(*key)); return -ENOMEM; } memcpy(key->key, newkey, newkeylen); key->keylen = newkeylen; key->family = family; key->prefixlen = prefixlen; memcpy(&key->addr, addr, (family == AF_INET6) ? sizeof(struct in6_addr) : sizeof(struct in_addr)); hlist_add_head_rcu(&key->node, &md5sig->head); return 0; } EXPORT_SYMBOL(tcp_md5_do_add); int tcp_md5_do_del(struct sock *sk, const union tcp_md5_addr *addr, int family, u8 prefixlen) { struct tcp_md5sig_key *key; key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (!key) return -ENOENT; hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); return 0; } EXPORT_SYMBOL(tcp_md5_do_del); static void tcp_clear_md5_list(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct tcp_md5sig_key *key; struct hlist_node *n; struct tcp_md5sig_info *md5sig; md5sig = rcu_dereference_protected(tp->md5sig_info, 1); hlist_for_each_entry_safe(key, n, &md5sig->head, node) { hlist_del_rcu(&key->node); atomic_sub(sizeof(*key), &sk->sk_omem_alloc); kfree_rcu(key, rcu); } } static int tcp_v4_parse_md5_keys(struct sock *sk, int optname, char __user *optval, int optlen) { struct tcp_md5sig cmd; struct sockaddr_in *sin = (struct sockaddr_in *)&cmd.tcpm_addr; u8 prefixlen = 32; if (optlen < sizeof(cmd)) return -EINVAL; if (copy_from_user(&cmd, optval, sizeof(cmd))) return -EFAULT; if (sin->sin_family != AF_INET) return -EINVAL; if (optname == TCP_MD5SIG_EXT && cmd.tcpm_flags & TCP_MD5SIG_FLAG_PREFIX) { prefixlen = cmd.tcpm_prefixlen; if (prefixlen > 32) return -EINVAL; } if (!cmd.tcpm_keylen) return tcp_md5_do_del(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, AF_INET, prefixlen); if (cmd.tcpm_keylen > TCP_MD5SIG_MAXKEYLEN) return -EINVAL; return tcp_md5_do_add(sk, (union tcp_md5_addr *)&sin->sin_addr.s_addr, AF_INET, prefixlen, cmd.tcpm_key, cmd.tcpm_keylen, GFP_KERNEL); } static int tcp_v4_md5_hash_headers(struct tcp_md5sig_pool *hp, __be32 daddr, __be32 saddr, const struct tcphdr *th, int nbytes) { struct tcp4_pseudohdr *bp; struct scatterlist sg; struct tcphdr *_th; bp = hp->scratch; bp->saddr = saddr; bp->daddr = daddr; bp->pad = 0; bp->protocol = IPPROTO_TCP; bp->len = cpu_to_be16(nbytes); _th = (struct tcphdr *)(bp + 1); memcpy(_th, th, sizeof(*th)); _th->check = 0; sg_init_one(&sg, bp, sizeof(*bp) + sizeof(*th)); ahash_request_set_crypt(hp->md5_req, &sg, NULL, sizeof(*bp) + sizeof(*th)); return crypto_ahash_update(hp->md5_req); } static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key, __be32 daddr, __be32 saddr, const struct tcphdr *th) { struct tcp_md5sig_pool *hp; struct ahash_request *req; hp = tcp_get_md5sig_pool(); if (!hp) goto clear_hash_noput; req = hp->md5_req; if (crypto_ahash_init(req)) goto clear_hash; if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(hp, key)) goto clear_hash; ahash_request_set_crypt(req, NULL, md5_hash, 0); if (crypto_ahash_final(req)) goto clear_hash; tcp_put_md5sig_pool(); return 0; clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); return 1; } int tcp_v4_md5_hash_skb(char *md5_hash, const struct tcp_md5sig_key *key, const struct sock *sk, const struct sk_buff *skb) { struct tcp_md5sig_pool *hp; struct ahash_request *req; const struct tcphdr *th = tcp_hdr(skb); __be32 saddr, daddr; if (sk) { /* valid for establish/request sockets */ saddr = sk->sk_rcv_saddr; daddr = sk->sk_daddr; } else { const struct iphdr *iph = ip_hdr(skb); saddr = iph->saddr; daddr = iph->daddr; } hp = tcp_get_md5sig_pool(); if (!hp) goto clear_hash_noput; req = hp->md5_req; if (crypto_ahash_init(req)) goto clear_hash; if (tcp_v4_md5_hash_headers(hp, daddr, saddr, th, skb->len)) goto clear_hash; if (tcp_md5_hash_skb_data(hp, skb, th->doff << 2)) goto clear_hash; if (tcp_md5_hash_key(hp, key)) goto clear_hash; ahash_request_set_crypt(req, NULL, md5_hash, 0); if (crypto_ahash_final(req)) goto clear_hash; tcp_put_md5sig_pool(); return 0; clear_hash: tcp_put_md5sig_pool(); clear_hash_noput: memset(md5_hash, 0, 16); return 1; } EXPORT_SYMBOL(tcp_v4_md5_hash_skb); #endif /* Called with rcu_read_lock() */ static bool tcp_v4_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb) { #ifdef CONFIG_TCP_MD5SIG /* * This gets called for each TCP segment that arrives * so we want to be efficient. * We have 3 drop cases: * o No MD5 hash and one expected. * o MD5 hash and we're not expecting one. * o MD5 hash and its wrong. */ const __u8 *hash_location = NULL; struct tcp_md5sig_key *hash_expected; const struct iphdr *iph = ip_hdr(skb); const struct tcphdr *th = tcp_hdr(skb); int genhash; unsigned char newhash[16]; hash_expected = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&iph->saddr, AF_INET); hash_location = tcp_parse_md5sig_option(th); /* We've parsed the options - do we have a hash? */ if (!hash_expected && !hash_location) return false; if (hash_expected && !hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5NOTFOUND); return true; } if (!hash_expected && hash_location) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5UNEXPECTED); return true; } /* Okay, so this is hash_expected and hash_location - * so we need to calculate the checksum. */ genhash = tcp_v4_md5_hash_skb(newhash, hash_expected, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); net_info_ratelimited("MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", &iph->saddr, ntohs(th->source), &iph->daddr, ntohs(th->dest), genhash ? " tcp_v4_calc_md5_hash failed" : ""); return true; } return false; #endif return false; } static void tcp_v4_init_req(struct request_sock *req, const struct sock *sk_listener, struct sk_buff *skb) { struct inet_request_sock *ireq = inet_rsk(req); struct net *net = sock_net(sk_listener); sk_rcv_saddr_set(req_to_sk(req), ip_hdr(skb)->daddr); sk_daddr_set(req_to_sk(req), ip_hdr(skb)->saddr); RCU_INIT_POINTER(ireq->ireq_opt, tcp_v4_save_options(net, skb)); } static struct dst_entry *tcp_v4_route_req(const struct sock *sk, struct flowi *fl, const struct request_sock *req) { return inet_csk_route_req(sk, &fl->u.ip4, req); } struct request_sock_ops tcp_request_sock_ops __read_mostly = { .family = PF_INET, .obj_size = sizeof(struct tcp_request_sock), .rtx_syn_ack = tcp_rtx_synack, .send_ack = tcp_v4_reqsk_send_ack, .destructor = tcp_v4_reqsk_destructor, .send_reset = tcp_v4_send_reset, .syn_ack_timeout = tcp_syn_ack_timeout, }; const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, #endif .init_req = tcp_v4_init_req, #ifdef CONFIG_SYN_COOKIES .cookie_init_seq = cookie_v4_init_sequence, #endif .route_req = tcp_v4_route_req, .init_seq = tcp_v4_init_seq, .init_ts_off = tcp_v4_init_ts_off, .send_synack = tcp_v4_send_synack, }; int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { /* Never answer to SYNs send to broadcast or multicast */ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST)) goto drop; return tcp_conn_request(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, skb); drop: tcp_listendrop(sk); return 0; } EXPORT_SYMBOL(tcp_v4_conn_request); /* * The three way handshake has completed - we got a valid synack - * now create the new socket. */ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct dst_entry *dst, struct request_sock *req_unhash, bool *own_req) { struct inet_request_sock *ireq; bool found_dup_sk = false; struct inet_sock *newinet; struct tcp_sock *newtp; struct sock *newsk; #ifdef CONFIG_TCP_MD5SIG struct tcp_md5sig_key *key; #endif struct ip_options_rcu *inet_opt; if (sk_acceptq_is_full(sk)) goto exit_overflow; newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; inet_sk_rx_dst_set(newsk, skb); newtp = tcp_sk(newsk); newinet = inet_sk(newsk); ireq = inet_rsk(req); sk_daddr_set(newsk, ireq->ir_rmt_addr); sk_rcv_saddr_set(newsk, ireq->ir_loc_addr); newsk->sk_bound_dev_if = ireq->ir_iif; newinet->inet_saddr = ireq->ir_loc_addr; inet_opt = rcu_dereference(ireq->ireq_opt); RCU_INIT_POINTER(newinet->inet_opt, inet_opt); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = prandom_u32(); if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); if (!dst) goto put_and_exit; } else { /* syncookie case : see end of cookie_v4_check() */ } sk_setup_caps(newsk, dst); tcp_ca_openreq_child(newsk, dst); tcp_sync_mss(newsk, dst_mtu(dst)); newtp->advmss = tcp_mss_clamp(tcp_sk(sk), dst_metric_advmss(dst)); tcp_initialize_rcv_mss(newsk); #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ key = tcp_md5_do_lookup(sk, (union tcp_md5_addr *)&newinet->inet_daddr, AF_INET); if (key) { /* * We're using one, so create a matching key * on the newsk structure. If we fail to get * memory, then we end up not copying the key * across. Shucks. */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newinet->inet_daddr, AF_INET, 32, key->key, key->keylen, GFP_ATOMIC); sk_nocaps_add(newsk, NETIF_F_GSO_MASK); } #endif if (__inet_inherit_port(sk, newsk) < 0) goto put_and_exit; *own_req = inet_ehash_nolisten(newsk, req_to_sk(req_unhash), &found_dup_sk); if (likely(*own_req)) { tcp_move_syn(newtp, req); ireq->ireq_opt = NULL; } else { newinet->inet_opt = NULL; if (!req_unhash && found_dup_sk) { /* This code path should only be executed in the * syncookie case only */ bh_unlock_sock(newsk); sock_put(newsk); newsk = NULL; } } return newsk; exit_overflow: NET_INC_STATS(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); exit_nonewsk: dst_release(dst); exit: tcp_listendrop(sk); return NULL; put_and_exit: newinet->inet_opt = NULL; inet_csk_prepare_forced_close(newsk); tcp_done(newsk); goto exit; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); static struct sock *tcp_v4_cookie_check(struct sock *sk, struct sk_buff *skb) { #ifdef CONFIG_SYN_COOKIES const struct tcphdr *th = tcp_hdr(skb); if (!th->syn) sk = cookie_v4_check(sk, skb); #endif return sk; } u16 tcp_v4_get_syncookie(struct sock *sk, struct iphdr *iph, struct tcphdr *th, u32 *cookie) { u16 mss = 0; #ifdef CONFIG_SYN_COOKIES mss = tcp_get_syncookie_mss(&tcp_request_sock_ops, &tcp_request_sock_ipv4_ops, sk, th); if (mss) { *cookie = __cookie_v4_init_sequence(iph, th, &mss); tcp_synq_overflow(sk); } #endif return mss; } /* The socket must have it's spinlock held when we get * here, unless it is a TCP_LISTEN socket. * * We have a potential double-lock case here, so even when * doing backlog processing we use the BH locking scheme. * This is because we cannot sleep with the original spinlock * held. */ int tcp_v4_do_rcv(struct sock *sk, struct sk_buff *skb) { struct sock *rsk; if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst; dst = rcu_dereference_protected(sk->sk_rx_dst, lockdep_sock_is_held(sk)); sock_rps_save_rxhash(sk, skb); sk_mark_napi_id(sk, skb); if (dst) { if (inet_sk(sk)->rx_dst_ifindex != skb->skb_iif || !dst->ops->check(dst, 0)) { RCU_INIT_POINTER(sk->sk_rx_dst, NULL); dst_release(dst); } } tcp_rcv_established(sk, skb); return 0; } if (tcp_checksum_complete(skb)) goto csum_err; if (sk->sk_state == TCP_LISTEN) { struct sock *nsk = tcp_v4_cookie_check(sk, skb); if (!nsk) goto discard; if (nsk != sk) { if (tcp_child_process(sk, nsk, skb)) { rsk = nsk; goto reset; } return 0; } } else sock_rps_save_rxhash(sk, skb); if (tcp_rcv_state_process(sk, skb)) { rsk = sk; goto reset; } return 0; reset: tcp_v4_send_reset(rsk, skb); discard: kfree_skb(skb); /* Be careful here. If this function gets more complicated and * gcc suffers from register pressure on the x86, sk (in %ebx) * might be destroyed here. This current version compiles correctly, * but you have been warned. */ return 0; csum_err: TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); goto discard; } EXPORT_SYMBOL(tcp_v4_do_rcv); int tcp_v4_early_demux(struct sk_buff *skb) { const struct iphdr *iph; const struct tcphdr *th; struct sock *sk; if (skb->pkt_type != PACKET_HOST) return 0; if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct tcphdr))) return 0; iph = ip_hdr(skb); th = tcp_hdr(skb); if (th->doff < sizeof(struct tcphdr) / 4) return 0; sk = __inet_lookup_established(dev_net(skb->dev), &tcp_hashinfo, iph->saddr, th->source, iph->daddr, ntohs(th->dest), skb->skb_iif, inet_sdif(skb)); if (sk) { skb->sk = sk; skb->destructor = sock_edemux; if (sk_fullsock(sk)) { struct dst_entry *dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); if (dst && inet_sk(sk)->rx_dst_ifindex == skb->skb_iif) skb_dst_set_noref(skb, dst); } } return 0; } bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb) { u32 tail_gso_size, tail_gso_segs; struct skb_shared_info *shinfo; const struct tcphdr *th; struct tcphdr *thtail; struct sk_buff *tail; unsigned int hdrlen; bool fragstolen; u32 gso_segs; u32 gso_size; u64 limit; int delta; /* In case all data was pulled from skb frags (in __pskb_pull_tail()), * we can fix skb->truesize to its real value to avoid future drops. * This is valid because skb is not yet charged to the socket. * It has been noticed pure SACK packets were sometimes dropped * (if cooked by drivers without copybreak feature). */ skb_condense(skb); skb_dst_drop(skb); if (unlikely(tcp_checksum_complete(skb))) { bh_unlock_sock(sk); __TCP_INC_STATS(sock_net(sk), TCP_MIB_CSUMERRORS); __TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS); return true; } /* Attempt coalescing to last skb in backlog, even if we are * above the limits. * This is okay because skb capacity is limited to MAX_SKB_FRAGS. */ th = (const struct tcphdr *)skb->data; hdrlen = th->doff * 4; tail = sk->sk_backlog.tail; if (!tail) goto no_coalesce; thtail = (struct tcphdr *)tail->data; if (TCP_SKB_CB(tail)->end_seq != TCP_SKB_CB(skb)->seq || TCP_SKB_CB(tail)->ip_dsfield != TCP_SKB_CB(skb)->ip_dsfield || ((TCP_SKB_CB(tail)->tcp_flags | TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_SYN | TCPHDR_RST | TCPHDR_URG)) || !((TCP_SKB_CB(tail)->tcp_flags & TCP_SKB_CB(skb)->tcp_flags) & TCPHDR_ACK) || ((TCP_SKB_CB(tail)->tcp_flags ^ TCP_SKB_CB(skb)->tcp_flags) & (TCPHDR_ECE | TCPHDR_CWR)) || #ifdef CONFIG_TLS_DEVICE tail->decrypted != skb->decrypted || #endif thtail->doff != th->doff || memcmp(thtail + 1, th + 1, hdrlen - sizeof(*th))) goto no_coalesce; __skb_pull(skb, hdrlen); shinfo = skb_shinfo(skb); gso_size = shinfo->gso_size ?: skb->len; gso_segs = shinfo->gso_segs ?: 1; shinfo = skb_shinfo(tail); tail_gso_size = shinfo->gso_size ?: (tail->len - hdrlen); tail_gso_segs = shinfo->gso_segs ?: 1; if (skb_try_coalesce(tail, skb, &fragstolen, &delta)) { TCP_SKB_CB(tail)->end_seq = TCP_SKB_CB(skb)->end_seq; if (likely(!before(TCP_SKB_CB(skb)->ack_seq, TCP_SKB_CB(tail)->ack_seq))) { TCP_SKB_CB(tail)->ack_seq = TCP_SKB_CB(skb)->ack_seq; thtail->window = th->window; } /* We have to update both TCP_SKB_CB(tail)->tcp_flags and * thtail->fin, so that the fast path in tcp_rcv_established() * is not entered if we append a packet with a FIN. * SYN, RST, URG are not present. * ACK is set on both packets. * PSH : we do not really care in TCP stack, * at least for 'GRO' packets. */ thtail->fin |= th->fin; TCP_SKB_CB(tail)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags; if (TCP_SKB_CB(skb)->has_rxtstamp) { TCP_SKB_CB(tail)->has_rxtstamp = true; tail->tstamp = skb->tstamp; skb_hwtstamps(tail)->hwtstamp = skb_hwtstamps(skb)->hwtstamp; } /* Not as strict as GRO. We only need to carry mss max value */ shinfo->gso_size = max(gso_size, tail_gso_size); shinfo->gso_segs = min_t(u32, gso_segs + tail_gso_segs, 0xFFFF); sk->sk_backlog.len += delta; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGCOALESCE); kfree_skb_partial(skb, fragstolen); return false; } __skb_push(skb, hdrlen); no_coalesce: /* sk->sk_backlog.len is reset only at the end of __release_sock(). * Both sk->sk_backlog.len and sk->sk_rmem_alloc could reach * sk_rcvbuf in normal conditions. */ limit = ((u64)READ_ONCE(sk->sk_rcvbuf)) << 1; limit += ((u32)READ_ONCE(sk->sk_sndbuf)) >> 1; /* Only socket owner can try to collapse/prune rx queues * to reduce memory overhead, so add a little headroom here. * Few sockets backlog are possibly concurrently non empty. */ limit += 64 * 1024; limit = min_t(u64, limit, UINT_MAX); if (unlikely(sk_add_backlog(sk, skb, limit))) { bh_unlock_sock(sk); __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP); return true; } return false; } EXPORT_SYMBOL(tcp_add_backlog); int tcp_filter(struct sock *sk, struct sk_buff *skb) { struct tcphdr *th = (struct tcphdr *)skb->data; return sk_filter_trim_cap(sk, skb, th->doff * 4); } EXPORT_SYMBOL(tcp_filter); static void tcp_v4_restore_cb(struct sk_buff *skb) { memmove(IPCB(skb), &TCP_SKB_CB(skb)->header.h4, sizeof(struct inet_skb_parm)); } static void tcp_v4_fill_cb(struct sk_buff *skb, const struct iphdr *iph, const struct tcphdr *th) { /* This is tricky : We move IPCB at its correct location into TCP_SKB_CB() * barrier() makes sure compiler wont play fool^Waliasing games. */ memmove(&TCP_SKB_CB(skb)->header.h4, IPCB(skb), sizeof(struct inet_skb_parm)); barrier(); TCP_SKB_CB(skb)->seq = ntohl(th->seq); TCP_SKB_CB(skb)->end_seq = (TCP_SKB_CB(skb)->seq + th->syn + th->fin + skb->len - th->doff * 4); TCP_SKB_CB(skb)->ack_seq = ntohl(th->ack_seq); TCP_SKB_CB(skb)->tcp_flags = tcp_flag_byte(th); TCP_SKB_CB(skb)->tcp_tw_isn = 0; TCP_SKB_CB(skb)->ip_dsfield = ipv4_get_dsfield(iph); TCP_SKB_CB(skb)->sacked = 0; TCP_SKB_CB(skb)->has_rxtstamp = skb->tstamp || skb_hwtstamps(skb)->hwtstamp; } /* * From tcp_input.c */ int tcp_v4_rcv(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); struct sk_buff *skb_to_free; int sdif = inet_sdif(skb); const struct iphdr *iph; const struct tcphdr *th; bool refcounted; struct sock *sk; int ret; if (skb->pkt_type != PACKET_HOST) goto discard_it; /* Count it even if it's bad */ __TCP_INC_STATS(net, TCP_MIB_INSEGS); if (!pskb_may_pull(skb, sizeof(struct tcphdr))) goto discard_it; th = (const struct tcphdr *)skb->data; if (unlikely(th->doff < sizeof(struct tcphdr) / 4)) goto bad_packet; if (!pskb_may_pull(skb, th->doff * 4)) goto discard_it; /* An explanation is required here, I think. * Packet length and doff are validated by header prediction, * provided case of th->doff==0 is eliminated. * So, we defer the checks. */ if (skb_checksum_init(skb, IPPROTO_TCP, inet_compute_pseudo)) goto csum_error; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); lookup: sk = __inet_lookup_skb(&tcp_hashinfo, skb, __tcp_hdrlen(th), th->source, th->dest, sdif, &refcounted); if (!sk) goto no_tcp_socket; process: if (sk->sk_state == TCP_TIME_WAIT) goto do_time_wait; if (sk->sk_state == TCP_NEW_SYN_RECV) { struct request_sock *req = inet_reqsk(sk); bool req_stolen = false; struct sock *nsk; sk = req->rsk_listener; if (unlikely(tcp_v4_inbound_md5_hash(sk, skb))) { sk_drops_add(sk, skb); reqsk_put(req); goto discard_it; } if (tcp_checksum_complete(skb)) { reqsk_put(req); goto csum_error; } if (unlikely(sk->sk_state != TCP_LISTEN)) { inet_csk_reqsk_queue_drop_and_put(sk, req); goto lookup; } /* We own a reference on the listener, increase it again * as we might lose it too soon. */ sock_hold(sk); refcounted = true; nsk = NULL; if (!tcp_filter(sk, skb)) { th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); nsk = tcp_check_req(sk, skb, req, false, &req_stolen); } if (!nsk) { reqsk_put(req); if (req_stolen) { /* Another cpu got exclusive access to req * and created a full blown socket. * Try to feed this packet to this socket * instead of discarding it. */ tcp_v4_restore_cb(skb); sock_put(sk); goto lookup; } goto discard_and_relse; } if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); } else if (tcp_child_process(sk, nsk, skb)) { tcp_v4_send_reset(nsk, skb); goto discard_and_relse; } else { sock_put(sk); return 0; } } if (unlikely(iph->ttl < inet_sk(sk)->min_ttl)) { __NET_INC_STATS(net, LINUX_MIB_TCPMINTTLDROP); goto discard_and_relse; } if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) goto discard_and_relse; if (tcp_v4_inbound_md5_hash(sk, skb)) goto discard_and_relse; nf_reset_ct(skb); if (tcp_filter(sk, skb)) goto discard_and_relse; th = (const struct tcphdr *)skb->data; iph = ip_hdr(skb); tcp_v4_fill_cb(skb, iph, th); skb->dev = NULL; if (sk->sk_state == TCP_LISTEN) { ret = tcp_v4_do_rcv(sk, skb); goto put_and_return; } sk_incoming_cpu_update(sk); bh_lock_sock_nested(sk); tcp_segs_in(tcp_sk(sk), skb); ret = 0; if (!sock_owned_by_user(sk)) { skb_to_free = sk->sk_rx_skb_cache; sk->sk_rx_skb_cache = NULL; ret = tcp_v4_do_rcv(sk, skb); } else { if (tcp_add_backlog(sk, skb)) goto discard_and_relse; skb_to_free = NULL; } bh_unlock_sock(sk); if (skb_to_free) __kfree_skb(skb_to_free); put_and_return: if (refcounted) sock_put(sk); return ret; no_tcp_socket: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto discard_it; tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { csum_error: __TCP_INC_STATS(net, TCP_MIB_CSUMERRORS); bad_packet: __TCP_INC_STATS(net, TCP_MIB_INERRS); } else { tcp_v4_send_reset(NULL, skb); } discard_it: /* Discard frame. */ kfree_skb(skb); return 0; discard_and_relse: sk_drops_add(sk, skb); if (refcounted) sock_put(sk); goto discard_it; do_time_wait: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { inet_twsk_put(inet_twsk(sk)); goto discard_it; } tcp_v4_fill_cb(skb, iph, th); if (tcp_checksum_complete(skb)) { inet_twsk_put(inet_twsk(sk)); goto csum_error; } switch (tcp_timewait_state_process(inet_twsk(sk), skb, th)) { case TCP_TW_SYN: { struct sock *sk2 = inet_lookup_listener(dev_net(skb->dev), &tcp_hashinfo, skb, __tcp_hdrlen(th), iph->saddr, th->source, iph->daddr, th->dest, inet_iif(skb), sdif); if (sk2) { inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; tcp_v4_restore_cb(skb); refcounted = false; goto process; } } /* to ACK */ /* fall through */ case TCP_TW_ACK: tcp_v4_timewait_ack(sk, skb); break; case TCP_TW_RST: tcp_v4_send_reset(sk, skb); inet_twsk_deschedule_put(inet_twsk(sk)); goto discard_it; case TCP_TW_SUCCESS:; } goto discard_it; } static struct timewait_sock_ops tcp_timewait_sock_ops = { .twsk_obj_size = sizeof(struct tcp_timewait_sock), .twsk_unique = tcp_twsk_unique, .twsk_destructor= tcp_twsk_destructor, }; void inet_sk_rx_dst_set(struct sock *sk, const struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); if (dst && dst_hold_safe(dst)) { rcu_assign_pointer(sk->sk_rx_dst, dst); inet_sk(sk)->rx_dst_ifindex = skb->skb_iif; } } EXPORT_SYMBOL(inet_sk_rx_dst_set); const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, .send_check = tcp_v4_send_check, .rebuild_header = inet_sk_rebuild_header, .sk_rx_dst_set = inet_sk_rx_dst_set, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, .addr2sockaddr = inet_csk_addr2sockaddr, .sockaddr_len = sizeof(struct sockaddr_in), #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ip_setsockopt, .compat_getsockopt = compat_ip_getsockopt, #endif .mtu_reduced = tcp_v4_mtu_reduced, }; EXPORT_SYMBOL(ipv4_specific); #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv4_specific = { .md5_lookup = tcp_v4_md5_lookup, .calc_md5_hash = tcp_v4_md5_hash_skb, .md5_parse = tcp_v4_parse_md5_keys, }; #endif /* NOTE: A lot of things set to zero explicitly by call to * sk_alloc() so need not be done here. */ static int tcp_v4_init_sock(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_init_sock(sk); icsk->icsk_af_ops = &ipv4_specific; #ifdef CONFIG_TCP_MD5SIG tcp_sk(sk)->af_specific = &tcp_sock_ipv4_specific; #endif return 0; } void tcp_v4_destroy_sock(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); trace_tcp_destroy_sock(sk); tcp_clear_xmit_timers(sk); tcp_cleanup_congestion_control(sk); tcp_cleanup_ulp(sk); /* Cleanup up the write buffer. */ tcp_write_queue_purge(sk); /* Check if we want to disable active TFO */ tcp_fastopen_active_disable_ofo_check(sk); /* Cleans up our, hopefully empty, out_of_order_queue. */ skb_rbtree_purge(&tp->out_of_order_queue); #ifdef CONFIG_TCP_MD5SIG /* Clean up the MD5 key list, if any */ if (tp->md5sig_info) { tcp_clear_md5_list(sk); kfree_rcu(rcu_dereference_protected(tp->md5sig_info, 1), rcu); tp->md5sig_info = NULL; } #endif /* Clean up a referenced TCP bind bucket. */ if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); tcp_fastopen_destroy_cipher(sk); tcp_saved_syn_free(tp); sk_sockets_allocated_dec(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ /* * Get next listener socket follow cur. If cur is NULL, get first socket * starting from bucket given in st->bucket; when st->bucket is zero the * very first socket in the hash table is returned. */ static void *listening_get_next(struct seq_file *seq, void *cur) { struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } ilb = &tcp_hashinfo.listening_hash[st->bucket]; ++st->num; ++st->offset; sk = sk_nulls_next(sk); get_sk: sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) return sk; } spin_unlock(&ilb->lock); st->offset = 0; if (++st->bucket < INET_LHTABLE_SIZE) goto get_head; return NULL; } static void *listening_get_idx(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; st->offset = 0; rc = listening_get_next(seq, NULL); while (rc && *pos) { rc = listening_get_next(seq, rc); --*pos; } return rc; } static inline bool empty_bucket(const struct tcp_iter_state *st) { return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain); } /* * Get first established socket starting from bucket given in st->bucket. * If st->bucket is zero, the very first socket in the hash is returned. */ static void *established_get_first(struct seq_file *seq) { struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); void *rc = NULL; st->offset = 0; for (; st->bucket <= tcp_hashinfo.ehash_mask; ++st->bucket) { struct sock *sk; struct hlist_nulls_node *node; spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); /* Lockless fast path for the common case of empty buckets */ if (empty_bucket(st)) continue; spin_lock_bh(lock); sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { if (sk->sk_family != afinfo->family || !net_eq(sock_net(sk), net)) { continue; } rc = sk; goto out; } spin_unlock_bh(lock); } out: return rc; } static void *established_get_next(struct seq_file *seq, void *cur) { struct tcp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); struct sock *sk = cur; struct hlist_nulls_node *node; struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); ++st->num; ++st->offset; sk = sk_nulls_next(sk); sk_nulls_for_each_from(sk, node) { if (sk->sk_family == afinfo->family && net_eq(sock_net(sk), net)) return sk; } spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); ++st->bucket; return established_get_first(seq); } static void *established_get_idx(struct seq_file *seq, loff_t pos) { struct tcp_iter_state *st = seq->private; void *rc; st->bucket = 0; rc = established_get_first(seq); while (rc && pos) { rc = established_get_next(seq, rc); --pos; } return rc; } static void *tcp_get_idx(struct seq_file *seq, loff_t pos) { void *rc; struct tcp_iter_state *st = seq->private; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_idx(seq, &pos); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } return rc; } static void *tcp_seek_last_pos(struct seq_file *seq) { struct tcp_iter_state *st = seq->private; int bucket = st->bucket; int offset = st->offset; int orig_num = st->num; void *rc = NULL; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (st->bucket >= INET_LHTABLE_SIZE) break; st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_next(seq, NULL); while (offset-- && rc && bucket == st->bucket) rc = listening_get_next(seq, rc); if (rc) break; st->bucket = 0; st->state = TCP_SEQ_STATE_ESTABLISHED; /* Fallthrough */ case TCP_SEQ_STATE_ESTABLISHED: if (st->bucket > tcp_hashinfo.ehash_mask) break; rc = established_get_first(seq); while (offset-- && rc && bucket == st->bucket) rc = established_get_next(seq, rc); } st->num = orig_num; return rc; } void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc; if (*pos && *pos == st->last_pos) { rc = tcp_seek_last_pos(seq); if (rc) goto out; } st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; st->bucket = 0; st->offset = 0; rc = *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; out: st->last_pos = *pos; return rc; } EXPORT_SYMBOL(tcp_seq_start); void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct tcp_iter_state *st = seq->private; void *rc = NULL; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); goto out; } switch (st->state) { case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { st->state = TCP_SEQ_STATE_ESTABLISHED; st->bucket = 0; st->offset = 0; rc = established_get_first(seq); } break; case TCP_SEQ_STATE_ESTABLISHED: rc = established_get_next(seq, v); break; } out: ++*pos; st->last_pos = *pos; return rc; } EXPORT_SYMBOL(tcp_seq_next); void tcp_seq_stop(struct seq_file *seq, void *v) { struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) spin_unlock(&tcp_hashinfo.listening_hash[st->bucket].lock); break; case TCP_SEQ_STATE_ESTABLISHED: if (v) spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); break; } } EXPORT_SYMBOL(tcp_seq_stop); static void get_openreq4(const struct request_sock *req, struct seq_file *f, int i) { const struct inet_request_sock *ireq = inet_rsk(req); long delta = req->rsk_timer.expires - jiffies; seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5u %8d %u %d %pK", i, ireq->ir_loc_addr, ireq->ir_num, ireq->ir_rmt_addr, ntohs(ireq->ir_rmt_port), TCP_SYN_RECV, 0, 0, /* could print option size, but that is af dependent. */ 1, /* timers active (only the expire timer) */ jiffies_delta_to_clock_t(delta), req->num_timeout, from_kuid_munged(seq_user_ns(f), sock_i_uid(req->rsk_listener)), 0, /* non standard timer */ 0, /* open_requests have no inode */ 0, req); } static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) { int timer_active; unsigned long timer_expires; const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); const struct inet_sock *inet = inet_sk(sk); const struct fastopen_queue *fastopenq = &icsk->icsk_accept_queue.fastopenq; __be32 dest = inet->inet_daddr; __be32 src = inet->inet_rcv_saddr; __u16 destp = ntohs(inet->inet_dport); __u16 srcp = ntohs(inet->inet_sport); int rx_queue; int state; if (icsk->icsk_pending == ICSK_TIME_RETRANS || icsk->icsk_pending == ICSK_TIME_REO_TIMEOUT || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) { timer_active = 1; timer_expires = icsk->icsk_timeout; } else if (icsk->icsk_pending == ICSK_TIME_PROBE0) { timer_active = 4; timer_expires = icsk->icsk_timeout; } else if (timer_pending(&sk->sk_timer)) { timer_active = 2; timer_expires = sk->sk_timer.expires; } else { timer_active = 0; timer_expires = jiffies; } state = inet_sk_state_load(sk); if (state == TCP_LISTEN) rx_queue = READ_ONCE(sk->sk_ack_backlog); else /* Because we don't lock the socket, * we might find a transient negative value. */ rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), icsk->icsk_retransmits, from_kuid_munged(seq_user_ns(f), sock_i_uid(sk)), icsk->icsk_probes_out, sock_i_ino(sk), refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), tp->snd_cwnd, state == TCP_LISTEN ? fastopenq->max_qlen : (tcp_in_initial_slowstart(tp) ? -1 : tp->snd_ssthresh)); } static void get_timewait4_sock(const struct inet_timewait_sock *tw, struct seq_file *f, int i) { long delta = tw->tw_timer.expires - jiffies; __be32 dest, src; __u16 destp, srcp; dest = tw->tw_daddr; src = tw->tw_rcv_saddr; destp = ntohs(tw->tw_dport); srcp = ntohs(tw->tw_sport); seq_printf(f, "%4d: %08X:%04X %08X:%04X" " %02X %08X:%08X %02X:%08lX %08X %5d %8d %d %d %pK", i, src, srcp, dest, destp, tw->tw_substate, 0, 0, 3, jiffies_delta_to_clock_t(delta), 0, 0, 0, 0, refcount_read(&tw->tw_refcnt), tw); } #define TMPSZ 150 static int tcp4_seq_show(struct seq_file *seq, void *v) { struct tcp_iter_state *st; struct sock *sk = v; seq_setwidth(seq, TMPSZ - 1); if (v == SEQ_START_TOKEN) { seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " "inode"); goto out; } st = seq->private; if (sk->sk_state == TCP_TIME_WAIT) get_timewait4_sock(v, seq, st->num); else if (sk->sk_state == TCP_NEW_SYN_RECV) get_openreq4(v, seq, st->num); else get_tcp4_sock(v, seq, st->num); out: seq_pad(seq, '\n'); return 0; } static const struct seq_operations tcp4_seq_ops = { .show = tcp4_seq_show, .start = tcp_seq_start, .next = tcp_seq_next, .stop = tcp_seq_stop, }; static struct tcp_seq_afinfo tcp4_seq_afinfo = { .family = AF_INET, }; static int __net_init tcp4_proc_init_net(struct net *net) { if (!proc_create_net_data("tcp", 0444, net->proc_net, &tcp4_seq_ops, sizeof(struct tcp_iter_state), &tcp4_seq_afinfo)) return -ENOMEM; return 0; } static void __net_exit tcp4_proc_exit_net(struct net *net) { remove_proc_entry("tcp", net->proc_net); } static struct pernet_operations tcp4_net_ops = { .init = tcp4_proc_init_net, .exit = tcp4_proc_exit_net, }; int __init tcp4_proc_init(void) { return register_pernet_subsys(&tcp4_net_ops); } void tcp4_proc_exit(void) { unregister_pernet_subsys(&tcp4_net_ops); } #endif /* CONFIG_PROC_FS */ struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, .close = tcp_close, .pre_connect = tcp_v4_pre_connect, .connect = tcp_v4_connect, .disconnect = tcp_disconnect, .accept = inet_csk_accept, .ioctl = tcp_ioctl, .init = tcp_v4_init_sock, .destroy = tcp_v4_destroy_sock, .shutdown = tcp_shutdown, .setsockopt = tcp_setsockopt, .getsockopt = tcp_getsockopt, .keepalive = tcp_set_keepalive, .recvmsg = tcp_recvmsg, .sendmsg = tcp_sendmsg, .sendpage = tcp_sendpage, .backlog_rcv = tcp_v4_do_rcv, .release_cb = tcp_release_cb, .hash = inet_hash, .unhash = inet_unhash, .get_port = inet_csk_get_port, .enter_memory_pressure = tcp_enter_memory_pressure, .leave_memory_pressure = tcp_leave_memory_pressure, .stream_memory_free = tcp_stream_memory_free, .sockets_allocated = &tcp_sockets_allocated, .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_tcp_wmem), .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_tcp_rmem), .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), .slab_flags = SLAB_TYPESAFE_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, .h.hashinfo = &tcp_hashinfo, .no_autobind = true, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif .diag_destroy = tcp_abort, }; EXPORT_SYMBOL(tcp_prot); static void __net_exit tcp_sk_exit(struct net *net) { int cpu; if (net->ipv4.tcp_congestion_control) module_put(net->ipv4.tcp_congestion_control->owner); for_each_possible_cpu(cpu) inet_ctl_sock_destroy(*per_cpu_ptr(net->ipv4.tcp_sk, cpu)); free_percpu(net->ipv4.tcp_sk); } static int __net_init tcp_sk_init(struct net *net) { int res, cpu, cnt; net->ipv4.tcp_sk = alloc_percpu(struct sock *); if (!net->ipv4.tcp_sk) return -ENOMEM; for_each_possible_cpu(cpu) { struct sock *sk; res = inet_ctl_sock_create(&sk, PF_INET, SOCK_RAW, IPPROTO_TCP, net); if (res) goto fail; sock_set_flag(sk, SOCK_USE_WRITE_QUEUE); /* Please enforce IP_DF and IPID==0 for RST and * ACK sent in SYN-RECV and TIME-WAIT state. */ inet_sk(sk)->pmtudisc = IP_PMTUDISC_DO; *per_cpu_ptr(net->ipv4.tcp_sk, cpu) = sk; } net->ipv4.sysctl_tcp_ecn = 2; net->ipv4.sysctl_tcp_ecn_fallback = 1; net->ipv4.sysctl_tcp_base_mss = TCP_BASE_MSS; net->ipv4.sysctl_tcp_min_snd_mss = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_probe_threshold = TCP_PROBE_THRESHOLD; net->ipv4.sysctl_tcp_probe_interval = TCP_PROBE_INTERVAL; net->ipv4.sysctl_tcp_mtu_probe_floor = TCP_MIN_SND_MSS; net->ipv4.sysctl_tcp_keepalive_time = TCP_KEEPALIVE_TIME; net->ipv4.sysctl_tcp_keepalive_probes = TCP_KEEPALIVE_PROBES; net->ipv4.sysctl_tcp_keepalive_intvl = TCP_KEEPALIVE_INTVL; net->ipv4.sysctl_tcp_syn_retries = TCP_SYN_RETRIES; net->ipv4.sysctl_tcp_synack_retries = TCP_SYNACK_RETRIES; net->ipv4.sysctl_tcp_syncookies = 1; net->ipv4.sysctl_tcp_reordering = TCP_FASTRETRANS_THRESH; net->ipv4.sysctl_tcp_retries1 = TCP_RETR1; net->ipv4.sysctl_tcp_retries2 = TCP_RETR2; net->ipv4.sysctl_tcp_orphan_retries = 0; net->ipv4.sysctl_tcp_fin_timeout = TCP_FIN_TIMEOUT; net->ipv4.sysctl_tcp_notsent_lowat = UINT_MAX; net->ipv4.sysctl_tcp_tw_reuse = 2; cnt = tcp_hashinfo.ehash_mask + 1; net->ipv4.tcp_death_row.sysctl_max_tw_buckets = cnt / 2; net->ipv4.tcp_death_row.hashinfo = &tcp_hashinfo; net->ipv4.sysctl_max_syn_backlog = max(128, cnt / 128); net->ipv4.sysctl_tcp_sack = 1; net->ipv4.sysctl_tcp_window_scaling = 1; net->ipv4.sysctl_tcp_timestamps = 1; net->ipv4.sysctl_tcp_early_retrans = 3; net->ipv4.sysctl_tcp_recovery = TCP_RACK_LOSS_DETECTION; net->ipv4.sysctl_tcp_slow_start_after_idle = 1; /* By default, RFC2861 behavior. */ net->ipv4.sysctl_tcp_retrans_collapse = 1; net->ipv4.sysctl_tcp_max_reordering = 300; net->ipv4.sysctl_tcp_dsack = 1; net->ipv4.sysctl_tcp_app_win = 31; net->ipv4.sysctl_tcp_adv_win_scale = 1; net->ipv4.sysctl_tcp_frto = 2; net->ipv4.sysctl_tcp_moderate_rcvbuf = 1; /* This limits the percentage of the congestion window which we * will allow a single TSO frame to consume. Building TSO frames * which are too large can cause TCP streams to be bursty. */ net->ipv4.sysctl_tcp_tso_win_divisor = 3; /* Default TSQ limit of 16 TSO segments */ net->ipv4.sysctl_tcp_limit_output_bytes = 16 * 65536; /* rfc5961 challenge ack rate limiting */ net->ipv4.sysctl_tcp_challenge_ack_limit = 1000; net->ipv4.sysctl_tcp_min_tso_segs = 2; net->ipv4.sysctl_tcp_min_rtt_wlen = 300; net->ipv4.sysctl_tcp_autocorking = 1; net->ipv4.sysctl_tcp_invalid_ratelimit = HZ/2; net->ipv4.sysctl_tcp_pacing_ss_ratio = 200; net->ipv4.sysctl_tcp_pacing_ca_ratio = 120; if (net != &init_net) { memcpy(net->ipv4.sysctl_tcp_rmem, init_net.ipv4.sysctl_tcp_rmem, sizeof(init_net.ipv4.sysctl_tcp_rmem)); memcpy(net->ipv4.sysctl_tcp_wmem, init_net.ipv4.sysctl_tcp_wmem, sizeof(init_net.ipv4.sysctl_tcp_wmem)); } net->ipv4.sysctl_tcp_comp_sack_delay_ns = NSEC_PER_MSEC; net->ipv4.sysctl_tcp_comp_sack_nr = 44; net->ipv4.sysctl_tcp_fastopen = TFO_CLIENT_ENABLE; spin_lock_init(&net->ipv4.tcp_fastopen_ctx_lock); net->ipv4.sysctl_tcp_fastopen_blackhole_timeout = 60 * 60; atomic_set(&net->ipv4.tfo_active_disable_times, 0); /* Reno is always built in */ if (!net_eq(net, &init_net) && try_module_get(init_net.ipv4.tcp_congestion_control->owner)) net->ipv4.tcp_congestion_control = init_net.ipv4.tcp_congestion_control; else net->ipv4.tcp_congestion_control = &tcp_reno; return 0; fail: tcp_sk_exit(net); return res; } static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list) { struct net *net; inet_twsk_purge(&tcp_hashinfo, AF_INET); list_for_each_entry(net, net_exit_list, exit_list) tcp_fastopen_ctx_destroy(net); } static struct pernet_operations __net_initdata tcp_sk_ops = { .init = tcp_sk_init, .exit = tcp_sk_exit, .exit_batch = tcp_sk_exit_batch, }; void __init tcp_v4_init(void) { if (register_pernet_subsys(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); } |
| 10 27 7 11 16 12 2 11 1 12 27 1 27 31 28 28 3 28 26 26 26 26 7 5 24 10 7 10 10 5 1 10 10 10 10 10 10 10 10 10 10 10 10 10 10 10 3 10 10 10 10 10 10 10 10 10 3 7 10 3 7 4 32 2 3 2 10 10 10 1 39 5 5 5 5 5 5 5 3 17 3 3 5 1 1 2 5 11 9 3 2 9 8 1 6 5 11 11 3 11 11 11 11 11 11 11 1 11 11 11 11 1 2 1 1 1 2 3 3 3 3 59 59 59 36 23 59 31 31 31 30 2 31 1 31 2 30 30 187 187 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * kernel/cpuset.c * * Processor and Memory placement constraints for sets of tasks. * * Copyright (C) 2003 BULL SA. * Copyright (C) 2004-2007 Silicon Graphics, Inc. * Copyright (C) 2006 Google, Inc * * Portions derived from Patrick Mochel's sysfs code. * sysfs is Copyright (c) 2001-3 Patrick Mochel * * 2003-10-10 Written by Simon Derr. * 2003-10-22 Updates by Stephen Hemminger. * 2004 May-July Rework by Paul Jackson. * 2006 Rework by Paul Menage to use generic cgroups * 2008 Rework of the scheduler domains and CPU hotplug handling * by Max Krasnyansky * * This file is subject to the terms and conditions of the GNU General Public * License. See the file COPYING in the main directory of the Linux * distribution for more details. */ #include "cgroup-internal.h" #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/cpuset.h> #include <linux/err.h> #include <linux/errno.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <linux/kmod.h> #include <linux/kthread.h> #include <linux/list.h> #include <linux/mempolicy.h> #include <linux/mm.h> #include <linux/memory.h> #include <linux/export.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/pagemap.h> #include <linux/proc_fs.h> #include <linux/rcupdate.h> #include <linux/sched.h> #include <linux/sched/deadline.h> #include <linux/sched/mm.h> #include <linux/sched/task.h> #include <linux/seq_file.h> #include <linux/security.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/stat.h> #include <linux/string.h> #include <linux/time.h> #include <linux/time64.h> #include <linux/backing-dev.h> #include <linux/sort.h> #include <linux/oom.h> #include <linux/sched/isolation.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <linux/mutex.h> #include <linux/cgroup.h> #include <linux/wait.h> DEFINE_STATIC_KEY_FALSE(cpusets_pre_enable_key); DEFINE_STATIC_KEY_FALSE(cpusets_enabled_key); /* See "Frequency meter" comments, below. */ struct fmeter { int cnt; /* unprocessed events count */ int val; /* most recent output value */ time64_t time; /* clock (secs) when val computed */ spinlock_t lock; /* guards read or write of above */ }; struct cpuset { struct cgroup_subsys_state css; unsigned long flags; /* "unsigned long" so bitops work */ /* * On default hierarchy: * * The user-configured masks can only be changed by writing to * cpuset.cpus and cpuset.mems, and won't be limited by the * parent masks. * * The effective masks is the real masks that apply to the tasks * in the cpuset. They may be changed if the configured masks are * changed or hotplug happens. * * effective_mask == configured_mask & parent's effective_mask, * and if it ends up empty, it will inherit the parent's mask. * * * On legacy hierachy: * * The user-configured masks are always the same with effective masks. */ /* user-configured CPUs and Memory Nodes allow to tasks */ cpumask_var_t cpus_allowed; cpumask_var_t cpus_requested; nodemask_t mems_allowed; /* effective CPUs and Memory Nodes allow to tasks */ cpumask_var_t effective_cpus; nodemask_t effective_mems; /* * CPUs allocated to child sub-partitions (default hierarchy only) * - CPUs granted by the parent = effective_cpus U subparts_cpus * - effective_cpus and subparts_cpus are mutually exclusive. * * effective_cpus contains only onlined CPUs, but subparts_cpus * may have offlined ones. */ cpumask_var_t subparts_cpus; /* * This is old Memory Nodes tasks took on. * * - top_cpuset.old_mems_allowed is initialized to mems_allowed. * - A new cpuset's old_mems_allowed is initialized when some * task is moved into it. * - old_mems_allowed is used in cpuset_migrate_mm() when we change * cpuset.mems_allowed and have tasks' nodemask updated, and * then old_mems_allowed is updated to mems_allowed. */ nodemask_t old_mems_allowed; struct fmeter fmeter; /* memory_pressure filter */ /* * Tasks are being attached to this cpuset. Used to prevent * zeroing cpus/mems_allowed between ->can_attach() and ->attach(). */ int attach_in_progress; /* partition number for rebuild_sched_domains() */ int pn; /* for custom sched domain */ int relax_domain_level; /* number of CPUs in subparts_cpus */ int nr_subparts_cpus; /* partition root state */ int partition_root_state; /* * Default hierarchy only: * use_parent_ecpus - set if using parent's effective_cpus * child_ecpus_count - # of children with use_parent_ecpus set */ int use_parent_ecpus; int child_ecpus_count; }; /* * Partition root states: * * 0 - not a partition root * * 1 - partition root * * -1 - invalid partition root * None of the cpus in cpus_allowed can be put into the parent's * subparts_cpus. In this case, the cpuset is not a real partition * root anymore. However, the CPU_EXCLUSIVE bit will still be set * and the cpuset can be restored back to a partition root if the * parent cpuset can give more CPUs back to this child cpuset. */ #define PRS_DISABLED 0 #define PRS_ENABLED 1 #define PRS_ERROR -1 /* * Temporary cpumasks for working with partitions that are passed among * functions to avoid memory allocation in inner functions. */ struct tmpmasks { cpumask_var_t addmask, delmask; /* For partition root */ cpumask_var_t new_cpus; /* For update_cpumasks_hier() */ }; static inline struct cpuset *css_cs(struct cgroup_subsys_state *css) { return css ? container_of(css, struct cpuset, css) : NULL; } /* Retrieve the cpuset for a task */ static inline struct cpuset *task_cs(struct task_struct *task) { return css_cs(task_css(task, cpuset_cgrp_id)); } static inline struct cpuset *parent_cs(struct cpuset *cs) { return css_cs(cs->css.parent); } /* bits in struct cpuset flags field */ typedef enum { CS_ONLINE, CS_CPU_EXCLUSIVE, CS_MEM_EXCLUSIVE, CS_MEM_HARDWALL, CS_MEMORY_MIGRATE, CS_SCHED_LOAD_BALANCE, CS_SPREAD_PAGE, CS_SPREAD_SLAB, } cpuset_flagbits_t; /* convenient tests for these bits */ static inline bool is_cpuset_online(struct cpuset *cs) { return test_bit(CS_ONLINE, &cs->flags) && !css_is_dying(&cs->css); } static inline int is_cpu_exclusive(const struct cpuset *cs) { return test_bit(CS_CPU_EXCLUSIVE, &cs->flags); } static inline int is_mem_exclusive(const struct cpuset *cs) { return test_bit(CS_MEM_EXCLUSIVE, &cs->flags); } static inline int is_mem_hardwall(const struct cpuset *cs) { return test_bit(CS_MEM_HARDWALL, &cs->flags); } static inline int is_sched_load_balance(const struct cpuset *cs) { return test_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); } static inline int is_memory_migrate(const struct cpuset *cs) { return test_bit(CS_MEMORY_MIGRATE, &cs->flags); } static inline int is_spread_page(const struct cpuset *cs) { return test_bit(CS_SPREAD_PAGE, &cs->flags); } static inline int is_spread_slab(const struct cpuset *cs) { return test_bit(CS_SPREAD_SLAB, &cs->flags); } static inline int is_partition_root(const struct cpuset *cs) { return cs->partition_root_state > 0; } static struct cpuset top_cpuset = { .flags = ((1 << CS_ONLINE) | (1 << CS_CPU_EXCLUSIVE) | (1 << CS_MEM_EXCLUSIVE)), .partition_root_state = PRS_ENABLED, }; /** * cpuset_for_each_child - traverse online children of a cpuset * @child_cs: loop cursor pointing to the current child * @pos_css: used for iteration * @parent_cs: target cpuset to walk children of * * Walk @child_cs through the online children of @parent_cs. Must be used * with RCU read locked. */ #define cpuset_for_each_child(child_cs, pos_css, parent_cs) \ css_for_each_child((pos_css), &(parent_cs)->css) \ if (is_cpuset_online(((child_cs) = css_cs((pos_css))))) /** * cpuset_for_each_descendant_pre - pre-order walk of a cpuset's descendants * @des_cs: loop cursor pointing to the current descendant * @pos_css: used for iteration * @root_cs: target cpuset to walk ancestor of * * Walk @des_cs through the online descendants of @root_cs. Must be used * with RCU read locked. The caller may modify @pos_css by calling * css_rightmost_descendant() to skip subtree. @root_cs is included in the * iteration and the first node to be visited. */ #define cpuset_for_each_descendant_pre(des_cs, pos_css, root_cs) \ css_for_each_descendant_pre((pos_css), &(root_cs)->css) \ if (is_cpuset_online(((des_cs) = css_cs((pos_css))))) /* * There are two global locks guarding cpuset structures - cpuset_mutex and * callback_lock. We also require taking task_lock() when dereferencing a * task's cpuset pointer. See "The task_lock() exception", at the end of this * comment. * * A task must hold both locks to modify cpusets. If a task holds * cpuset_mutex, then it blocks others wanting that mutex, ensuring that it * is the only task able to also acquire callback_lock and be able to * modify cpusets. It can perform various checks on the cpuset structure * first, knowing nothing will change. It can also allocate memory while * just holding cpuset_mutex. While it is performing these checks, various * callback routines can briefly acquire callback_lock to query cpusets. * Once it is ready to make the changes, it takes callback_lock, blocking * everyone else. * * Calls to the kernel memory allocator can not be made while holding * callback_lock, as that would risk double tripping on callback_lock * from one of the callbacks into the cpuset code from within * __alloc_pages(). * * If a task is only holding callback_lock, then it has read-only * access to cpusets. * * Now, the task_struct fields mems_allowed and mempolicy may be changed * by other task, we use alloc_lock in the task_struct fields to protect * them. * * The cpuset_common_file_read() handlers only hold callback_lock across * small pieces of code, such as when reading out possibly multi-word * cpumasks and nodemasks. * * Accessing a task's cpuset should be done in accordance with the * guidelines for accessing subsystem state in kernel/cgroup.c */ DEFINE_STATIC_PERCPU_RWSEM(cpuset_rwsem); static DEFINE_SPINLOCK(callback_lock); static struct workqueue_struct *cpuset_migrate_mm_wq; /* * CPU / memory hotplug is handled asynchronously. */ static void cpuset_hotplug_workfn(struct work_struct *work); static DECLARE_WORK(cpuset_hotplug_work, cpuset_hotplug_workfn); static DECLARE_WAIT_QUEUE_HEAD(cpuset_attach_wq); /* * Cgroup v2 behavior is used when on default hierarchy or the * cgroup_v2_mode flag is set. */ static inline bool is_in_v2_mode(void) { return cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || (cpuset_cgrp_subsys.root->flags & CGRP_ROOT_CPUSET_V2_MODE); } /* * Return in pmask the portion of a cpusets's cpus_allowed that * are online. If none are online, walk up the cpuset hierarchy * until we find one that does have some online cpus. * * One way or another, we guarantee to return some non-empty subset * of cpu_online_mask. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_cpus(struct cpuset *cs, struct cpumask *pmask) { while (!cpumask_intersects(cs->effective_cpus, cpu_online_mask)) { cs = parent_cs(cs); if (unlikely(!cs)) { /* * The top cpuset doesn't have any online cpu as a * consequence of a race between cpuset_hotplug_work * and cpu hotplug notifier. But we know the top * cpuset's effective_cpus is on its way to to be * identical to cpu_online_mask. */ cpumask_copy(pmask, cpu_online_mask); return; } } cpumask_and(pmask, cs->effective_cpus, cpu_online_mask); } /* * Return in *pmask the portion of a cpusets's mems_allowed that * are online, with memory. If none are online with memory, walk * up the cpuset hierarchy until we find one that does have some * online mems. The top cpuset always has some mems online. * * One way or another, we guarantee to return some non-empty subset * of node_states[N_MEMORY]. * * Call with callback_lock or cpuset_mutex held. */ static void guarantee_online_mems(struct cpuset *cs, nodemask_t *pmask) { while (!nodes_intersects(cs->effective_mems, node_states[N_MEMORY])) cs = parent_cs(cs); nodes_and(*pmask, cs->effective_mems, node_states[N_MEMORY]); } /* * update task's spread flag if cpuset's page/slab spread flag is set * * Call with callback_lock or cpuset_mutex held. */ static void cpuset_update_task_spread_flag(struct cpuset *cs, struct task_struct *tsk) { if (is_spread_page(cs)) task_set_spread_page(tsk); else task_clear_spread_page(tsk); if (is_spread_slab(cs)) task_set_spread_slab(tsk); else task_clear_spread_slab(tsk); } /* * is_cpuset_subset(p, q) - Is cpuset p a subset of cpuset q? * * One cpuset is a subset of another if all its allowed CPUs and * Memory Nodes are a subset of the other, and its exclusive flags * are only set if the other's are set. Call holding cpuset_mutex. */ static int is_cpuset_subset(const struct cpuset *p, const struct cpuset *q) { return cpumask_subset(p->cpus_requested, q->cpus_requested) && nodes_subset(p->mems_allowed, q->mems_allowed) && is_cpu_exclusive(p) <= is_cpu_exclusive(q) && is_mem_exclusive(p) <= is_mem_exclusive(q); } /** * alloc_cpumasks - allocate three cpumasks for cpuset * @cs: the cpuset that have cpumasks to be allocated. * @tmp: the tmpmasks structure pointer * Return: 0 if successful, -ENOMEM otherwise. * * Only one of the two input arguments should be non-NULL. */ static inline int alloc_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { cpumask_var_t *pmask1, *pmask2, *pmask3; if (cs) { pmask1 = &cs->cpus_allowed; pmask2 = &cs->effective_cpus; pmask3 = &cs->subparts_cpus; } else { pmask1 = &tmp->new_cpus; pmask2 = &tmp->addmask; pmask3 = &tmp->delmask; } if (!zalloc_cpumask_var(pmask1, GFP_KERNEL)) return -ENOMEM; if (!zalloc_cpumask_var(pmask2, GFP_KERNEL)) goto free_one; if (!zalloc_cpumask_var(pmask3, GFP_KERNEL)) goto free_two; if (cs && !zalloc_cpumask_var(&cs->cpus_requested, GFP_KERNEL)) goto free_three; return 0; free_three: free_cpumask_var(*pmask3); free_two: free_cpumask_var(*pmask2); free_one: free_cpumask_var(*pmask1); return -ENOMEM; } /** * free_cpumasks - free cpumasks in a tmpmasks structure * @cs: the cpuset that have cpumasks to be free. * @tmp: the tmpmasks structure pointer */ static inline void free_cpumasks(struct cpuset *cs, struct tmpmasks *tmp) { if (cs) { free_cpumask_var(cs->cpus_allowed); free_cpumask_var(cs->cpus_requested); free_cpumask_var(cs->effective_cpus); free_cpumask_var(cs->subparts_cpus); } if (tmp) { free_cpumask_var(tmp->new_cpus); free_cpumask_var(tmp->addmask); free_cpumask_var(tmp->delmask); } } /** * alloc_trial_cpuset - allocate a trial cpuset * @cs: the cpuset that the trial cpuset duplicates */ static struct cpuset *alloc_trial_cpuset(struct cpuset *cs) { struct cpuset *trial; trial = kmemdup(cs, sizeof(*cs), GFP_KERNEL); if (!trial) return NULL; if (alloc_cpumasks(trial, NULL)) { kfree(trial); return NULL; } cpumask_copy(trial->cpus_allowed, cs->cpus_allowed); cpumask_copy(trial->cpus_requested, cs->cpus_requested); cpumask_copy(trial->effective_cpus, cs->effective_cpus); return trial; } /** * free_cpuset - free the cpuset * @cs: the cpuset to be freed */ static inline void free_cpuset(struct cpuset *cs) { free_cpumasks(cs, NULL); kfree(cs); } /* * validate_change() - Used to validate that any proposed cpuset change * follows the structural rules for cpusets. * * If we replaced the flag and mask values of the current cpuset * (cur) with those values in the trial cpuset (trial), would * our various subset and exclusive rules still be valid? Presumes * cpuset_mutex held. * * 'cur' is the address of an actual, in-use cpuset. Operations * such as list traversal that depend on the actual address of the * cpuset in the list must use cur below, not trial. * * 'trial' is the address of bulk structure copy of cur, with * perhaps one or more of the fields cpus_allowed, mems_allowed, * or flags changed to new, trial values. * * Return 0 if valid, -errno if not. */ static int validate_change(struct cpuset *cur, struct cpuset *trial) { struct cgroup_subsys_state *css; struct cpuset *c, *par; int ret; rcu_read_lock(); /* Each of our child cpusets must be a subset of us */ ret = -EBUSY; cpuset_for_each_child(c, css, cur) if (!is_cpuset_subset(c, trial)) goto out; /* Remaining checks don't apply to root cpuset */ ret = 0; if (cur == &top_cpuset) goto out; par = parent_cs(cur); /* On legacy hiearchy, we must be a subset of our parent cpuset. */ ret = -EACCES; if (!is_in_v2_mode() && !is_cpuset_subset(trial, par)) goto out; /* * If either I or some sibling (!= me) is exclusive, we can't * overlap */ ret = -EINVAL; cpuset_for_each_child(c, css, par) { if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) && c != cur && cpumask_intersects(trial->cpus_requested, c->cpus_requested)) goto out; if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) && c != cur && nodes_intersects(trial->mems_allowed, c->mems_allowed)) goto out; } /* * Cpusets with tasks - existing or newly being attached - can't * be changed to have empty cpus_allowed or mems_allowed. */ ret = -ENOSPC; if ((cgroup_is_populated(cur->css.cgroup) || cur->attach_in_progress)) { if (!cpumask_empty(cur->cpus_allowed) && cpumask_empty(trial->cpus_allowed)) goto out; if (!nodes_empty(cur->mems_allowed) && nodes_empty(trial->mems_allowed)) goto out; } /* * We can't shrink if we won't have enough room for SCHED_DEADLINE * tasks. */ ret = -EBUSY; if (is_cpu_exclusive(cur) && !cpuset_cpumask_can_shrink(cur->cpus_allowed, trial->cpus_allowed)) goto out; ret = 0; out: rcu_read_unlock(); return ret; } #ifdef CONFIG_SMP /* * Helper routine for generate_sched_domains(). * Do cpusets a, b have overlapping effective cpus_allowed masks? */ static int cpusets_overlap(struct cpuset *a, struct cpuset *b) { return cpumask_intersects(a->effective_cpus, b->effective_cpus); } static void update_domain_attr(struct sched_domain_attr *dattr, struct cpuset *c) { if (dattr->relax_domain_level < c->relax_domain_level) dattr->relax_domain_level = c->relax_domain_level; return; } static void update_domain_attr_tree(struct sched_domain_attr *dattr, struct cpuset *root_cs) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, root_cs) { /* skip the whole subtree if @cp doesn't have any CPU */ if (cpumask_empty(cp->cpus_allowed)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (is_sched_load_balance(cp)) update_domain_attr(dattr, cp); } rcu_read_unlock(); } /* Must be called with cpuset_mutex held. */ static inline int nr_cpusets(void) { /* jump label reference count + the top-level cpuset */ return static_key_count(&cpusets_enabled_key.key) + 1; } /* * generate_sched_domains() * * This function builds a partial partition of the systems CPUs * A 'partial partition' is a set of non-overlapping subsets whose * union is a subset of that set. * The output of this function needs to be passed to kernel/sched/core.c * partition_sched_domains() routine, which will rebuild the scheduler's * load balancing domains (sched domains) as specified by that partial * partition. * * See "What is sched_load_balance" in Documentation/admin-guide/cgroup-v1/cpusets.rst * for a background explanation of this. * * Does not return errors, on the theory that the callers of this * routine would rather not worry about failures to rebuild sched * domains when operating in the severe memory shortage situations * that could cause allocation failures below. * * Must be called with cpuset_mutex held. * * The three key local variables below are: * cp - cpuset pointer, used (together with pos_css) to perform a * top-down scan of all cpusets. For our purposes, rebuilding * the schedulers sched domains, we can ignore !is_sched_load_ * balance cpusets. * csa - (for CpuSet Array) Array of pointers to all the cpusets * that need to be load balanced, for convenient iterative * access by the subsequent code that finds the best partition, * i.e the set of domains (subsets) of CPUs such that the * cpus_allowed of every cpuset marked is_sched_load_balance * is a subset of one of these domains, while there are as * many such domains as possible, each as small as possible. * doms - Conversion of 'csa' to an array of cpumasks, for passing to * the kernel/sched/core.c routine partition_sched_domains() in a * convenient format, that can be easily compared to the prior * value to determine what partition elements (sched domains) * were changed (added or removed.) * * Finding the best partition (set of domains): * The triple nested loops below over i, j, k scan over the * load balanced cpusets (using the array of cpuset pointers in * csa[]) looking for pairs of cpusets that have overlapping * cpus_allowed, but which don't have the same 'pn' partition * number and gives them in the same partition number. It keeps * looping on the 'restart' label until it can no longer find * any such pairs. * * The union of the cpus_allowed masks from the set of * all cpusets having the same 'pn' value then form the one * element of the partition (one sched domain) to be passed to * partition_sched_domains(). */ static int generate_sched_domains(cpumask_var_t **domains, struct sched_domain_attr **attributes) { struct cpuset *cp; /* top-down scan of cpusets */ struct cpuset **csa; /* array of all cpuset ptrs */ int csn; /* how many cpuset ptrs in csa so far */ int i, j, k; /* indices for partition finding loops */ cpumask_var_t *doms; /* resulting partition; i.e. sched domains */ struct sched_domain_attr *dattr; /* attributes for custom domains */ int ndoms = 0; /* number of sched domains in result */ int nslot; /* next empty doms[] struct cpumask slot */ struct cgroup_subsys_state *pos_css; bool root_load_balance = is_sched_load_balance(&top_cpuset); doms = NULL; dattr = NULL; csa = NULL; /* Special case for the 99% of systems with one, full, sched domain */ if (root_load_balance && !top_cpuset.nr_subparts_cpus) { ndoms = 1; doms = alloc_sched_domains(ndoms); if (!doms) goto done; dattr = kmalloc(sizeof(struct sched_domain_attr), GFP_KERNEL); if (dattr) { *dattr = SD_ATTR_INIT; update_domain_attr_tree(dattr, &top_cpuset); } cpumask_and(doms[0], top_cpuset.effective_cpus, housekeeping_cpumask(HK_FLAG_DOMAIN)); goto done; } csa = kmalloc_array(nr_cpusets(), sizeof(cp), GFP_KERNEL); if (!csa) goto done; csn = 0; rcu_read_lock(); if (root_load_balance) csa[csn++] = &top_cpuset; cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) { if (cp == &top_cpuset) continue; /* * Continue traversing beyond @cp iff @cp has some CPUs and * isn't load balancing. The former is obvious. The * latter: All child cpusets contain a subset of the * parent's cpus, so just skip them, and then we call * update_domain_attr_tree() to calc relax_domain_level of * the corresponding sched domain. * * If root is load-balancing, we can skip @cp if it * is a subset of the root's effective_cpus. */ if (!cpumask_empty(cp->cpus_allowed) && !(is_sched_load_balance(cp) && cpumask_intersects(cp->cpus_allowed, housekeeping_cpumask(HK_FLAG_DOMAIN)))) continue; if (root_load_balance && cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus)) continue; if (is_sched_load_balance(cp) && !cpumask_empty(cp->effective_cpus)) csa[csn++] = cp; /* skip @cp's subtree if not a partition root */ if (!is_partition_root(cp)) pos_css = css_rightmost_descendant(pos_css); } rcu_read_unlock(); for (i = 0; i < csn; i++) csa[i]->pn = i; ndoms = csn; restart: /* Find the best partition (set of sched domains) */ for (i = 0; i < csn; i++) { struct cpuset *a = csa[i]; int apn = a->pn; for (j = 0; j < csn; j++) { struct cpuset *b = csa[j]; int bpn = b->pn; if (apn != bpn && cpusets_overlap(a, b)) { for (k = 0; k < csn; k++) { struct cpuset *c = csa[k]; if (c->pn == bpn) c->pn = apn; } ndoms--; /* one less element */ goto restart; } } } /* * Now we know how many domains to create. * Convert <csn, csa> to <ndoms, doms> and populate cpu masks. */ doms = alloc_sched_domains(ndoms); if (!doms) goto done; /* * The rest of the code, including the scheduler, can deal with * dattr==NULL case. No need to abort if alloc fails. */ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr), GFP_KERNEL); for (nslot = 0, i = 0; i < csn; i++) { struct cpuset *a = csa[i]; struct cpumask *dp; int apn = a->pn; if (apn < 0) { /* Skip completed partitions */ continue; } dp = doms[nslot]; if (nslot == ndoms) { static int warnings = 10; if (warnings) { pr_warn("rebuild_sched_domains confused: nslot %d, ndoms %d, csn %d, i %d, apn %d\n", nslot, ndoms, csn, i, apn); warnings--; } continue; } cpumask_clear(dp); if (dattr) *(dattr + nslot) = SD_ATTR_INIT; for (j = i; j < csn; j++) { struct cpuset *b = csa[j]; if (apn == b->pn) { cpumask_or(dp, dp, b->effective_cpus); cpumask_and(dp, dp, housekeeping_cpumask(HK_FLAG_DOMAIN)); if (dattr) update_domain_attr_tree(dattr + nslot, b); /* Done with this partition */ b->pn = -1; } } nslot++; } BUG_ON(nslot != ndoms); done: kfree(csa); /* * Fallback to the default domain if kmalloc() failed. * See comments in partition_sched_domains(). */ if (doms == NULL) ndoms = 1; *domains = doms; *attributes = dattr; return ndoms; } static void update_tasks_root_domain(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) dl_add_task_root_domain(task); css_task_iter_end(&it); } static void rebuild_root_domains(void) { struct cpuset *cs = NULL; struct cgroup_subsys_state *pos_css; percpu_rwsem_assert_held(&cpuset_rwsem); lockdep_assert_cpus_held(); lockdep_assert_held(&sched_domains_mutex); cgroup_enable_task_cg_lists(); rcu_read_lock(); /* * Clear default root domain DL accounting, it will be computed again * if a task belongs to it. */ dl_clear_root_domain(&def_root_domain); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cpumask_empty(cs->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } css_get(&cs->css); rcu_read_unlock(); update_tasks_root_domain(cs); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } static void partition_and_rebuild_sched_domains(int ndoms_new, cpumask_var_t doms_new[], struct sched_domain_attr *dattr_new) { mutex_lock(&sched_domains_mutex); partition_sched_domains_locked(ndoms_new, doms_new, dattr_new); rebuild_root_domains(); mutex_unlock(&sched_domains_mutex); } /* * Rebuild scheduler domains. * * If the flag 'sched_load_balance' of any cpuset with non-empty * 'cpus' changes, or if the 'cpus' allowed changes in any cpuset * which has that flag enabled, or if any cpuset with a non-empty * 'cpus' is removed, then call this routine to rebuild the * scheduler's dynamic sched domains. * * Call with cpuset_mutex held. Takes get_online_cpus(). */ static void rebuild_sched_domains_locked(void) { struct cgroup_subsys_state *pos_css; struct sched_domain_attr *attr; cpumask_var_t *doms; struct cpuset *cs; int ndoms; lockdep_assert_cpus_held(); percpu_rwsem_assert_held(&cpuset_rwsem); /* * If we have raced with CPU hotplug, return early to avoid * passing doms with offlined cpu to partition_sched_domains(). * Anyways, cpuset_hotplug_workfn() will rebuild sched domains. * * With no CPUs in any subpartitions, top_cpuset's effective CPUs * should be the same as the active CPUs, so checking only top_cpuset * is enough to detect racing CPU offlines. */ if (!top_cpuset.nr_subparts_cpus && !cpumask_equal(top_cpuset.effective_cpus, cpu_active_mask)) return; /* * With subpartition CPUs, however, the effective CPUs of a partition * root should be only a subset of the active CPUs. Since a CPU in any * partition root could be offlined, all must be checked. */ if (top_cpuset.nr_subparts_cpus) { rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (!is_partition_root(cs)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!cpumask_subset(cs->effective_cpus, cpu_active_mask)) { rcu_read_unlock(); return; } } rcu_read_unlock(); } /* Generate domain masks and attrs */ ndoms = generate_sched_domains(&doms, &attr); /* Have scheduler rebuild the domains */ partition_and_rebuild_sched_domains(ndoms, doms, attr); } #else /* !CONFIG_SMP */ static void rebuild_sched_domains_locked(void) { } #endif /* CONFIG_SMP */ void rebuild_sched_domains(void) { get_online_cpus(); percpu_down_write(&cpuset_rwsem); rebuild_sched_domains_locked(); percpu_up_write(&cpuset_rwsem); put_online_cpus(); } /** * update_tasks_cpumask - Update the cpumasks of tasks in the cpuset. * @cs: the cpuset in which each task's cpus_allowed mask needs to be changed * * Iterate through each task of @cs updating its cpus_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_cpumask(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; bool top_cs = cs == &top_cpuset; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { /* * Percpu kthreads in top_cpuset are ignored */ if (top_cs && (task->flags & PF_KTHREAD) && kthread_is_per_cpu(task)) continue; set_cpus_allowed_ptr(task, cs->effective_cpus); } css_task_iter_end(&it); } /** * compute_effective_cpumask - Compute the effective cpumask of the cpuset * @new_cpus: the temp variable for the new effective_cpus mask * @cs: the cpuset the need to recompute the new effective_cpus mask * @parent: the parent cpuset * * If the parent has subpartition CPUs, include them in the list of * allowable CPUs in computing the new effective_cpus mask. Since offlined * CPUs are not removed from subparts_cpus, we have to use cpu_active_mask * to mask those out. */ static void compute_effective_cpumask(struct cpumask *new_cpus, struct cpuset *cs, struct cpuset *parent) { if (parent->nr_subparts_cpus) { cpumask_or(new_cpus, parent->effective_cpus, parent->subparts_cpus); cpumask_and(new_cpus, new_cpus, cs->cpus_requested); cpumask_and(new_cpus, new_cpus, cpu_active_mask); } else { cpumask_and(new_cpus, cs->cpus_requested, parent_cs(cs)->effective_cpus); } } /* * Commands for update_parent_subparts_cpumask */ enum subparts_cmd { partcmd_enable, /* Enable partition root */ partcmd_disable, /* Disable partition root */ partcmd_update, /* Update parent's subparts_cpus */ }; /** * update_parent_subparts_cpumask - update subparts_cpus mask of parent cpuset * @cpuset: The cpuset that requests change in partition root state * @cmd: Partition root state change command * @newmask: Optional new cpumask for partcmd_update * @tmp: Temporary addmask and delmask * Return: 0, 1 or an error code * * For partcmd_enable, the cpuset is being transformed from a non-partition * root to a partition root. The cpus_allowed mask of the given cpuset will * be put into parent's subparts_cpus and taken away from parent's * effective_cpus. The function will return 0 if all the CPUs listed in * cpus_allowed can be granted or an error code will be returned. * * For partcmd_disable, the cpuset is being transofrmed from a partition * root back to a non-partition root. any CPUs in cpus_allowed that are in * parent's subparts_cpus will be taken away from that cpumask and put back * into parent's effective_cpus. 0 should always be returned. * * For partcmd_update, if the optional newmask is specified, the cpu * list is to be changed from cpus_allowed to newmask. Otherwise, * cpus_allowed is assumed to remain the same. The cpuset should either * be a partition root or an invalid partition root. The partition root * state may change if newmask is NULL and none of the requested CPUs can * be granted by the parent. The function will return 1 if changes to * parent's subparts_cpus and effective_cpus happen or 0 otherwise. * Error code should only be returned when newmask is non-NULL. * * The partcmd_enable and partcmd_disable commands are used by * update_prstate(). The partcmd_update command is used by * update_cpumasks_hier() with newmask NULL and update_cpumask() with * newmask set. * * The checking is more strict when enabling partition root than the * other two commands. * * Because of the implicit cpu exclusive nature of a partition root, * cpumask changes that violates the cpu exclusivity rule will not be * permitted when checked by validate_change(). The validate_change() * function will also prevent any changes to the cpu list if it is not * a superset of children's cpu lists. */ static int update_parent_subparts_cpumask(struct cpuset *cpuset, int cmd, struct cpumask *newmask, struct tmpmasks *tmp) { struct cpuset *parent = parent_cs(cpuset); int adding; /* Moving cpus from effective_cpus to subparts_cpus */ int deleting; /* Moving cpus from subparts_cpus to effective_cpus */ bool part_error = false; /* Partition error? */ percpu_rwsem_assert_held(&cpuset_rwsem); /* * The parent must be a partition root. * The new cpumask, if present, or the current cpus_allowed must * not be empty. */ if (!is_partition_root(parent) || (newmask && cpumask_empty(newmask)) || (!newmask && cpumask_empty(cpuset->cpus_allowed))) return -EINVAL; /* * Enabling/disabling partition root is not allowed if there are * online children. */ if ((cmd != partcmd_update) && css_has_online_children(&cpuset->css)) return -EBUSY; /* * Enabling partition root is not allowed if not all the CPUs * can be granted from parent's effective_cpus or at least one * CPU will be left after that. */ if ((cmd == partcmd_enable) && (!cpumask_subset(cpuset->cpus_allowed, parent->effective_cpus) || cpumask_equal(cpuset->cpus_allowed, parent->effective_cpus))) return -EINVAL; /* * A cpumask update cannot make parent's effective_cpus become empty. */ adding = deleting = false; if (cmd == partcmd_enable) { cpumask_copy(tmp->addmask, cpuset->cpus_allowed); adding = true; } else if (cmd == partcmd_disable) { deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } else if (newmask) { /* * partcmd_update with newmask: * * delmask = cpus_allowed & ~newmask & parent->subparts_cpus * addmask = newmask & parent->effective_cpus * & ~parent->subparts_cpus */ cpumask_andnot(tmp->delmask, cpuset->cpus_allowed, newmask); deleting = cpumask_and(tmp->delmask, tmp->delmask, parent->subparts_cpus); cpumask_and(tmp->addmask, newmask, parent->effective_cpus); adding = cpumask_andnot(tmp->addmask, tmp->addmask, parent->subparts_cpus); /* * Return error if the new effective_cpus could become empty. */ if (adding && cpumask_equal(parent->effective_cpus, tmp->addmask)) { if (!deleting) return -EINVAL; /* * As some of the CPUs in subparts_cpus might have * been offlined, we need to compute the real delmask * to confirm that. */ if (!cpumask_and(tmp->addmask, tmp->delmask, cpu_active_mask)) return -EINVAL; cpumask_copy(tmp->addmask, parent->effective_cpus); } } else { /* * partcmd_update w/o newmask: * * addmask = cpus_allowed & parent->effectiveb_cpus * * Note that parent's subparts_cpus may have been * pre-shrunk in case there is a change in the cpu list. * So no deletion is needed. */ adding = cpumask_and(tmp->addmask, cpuset->cpus_allowed, parent->effective_cpus); part_error = cpumask_equal(tmp->addmask, parent->effective_cpus); } if (cmd == partcmd_update) { int prev_prs = cpuset->partition_root_state; /* * Check for possible transition between PRS_ENABLED * and PRS_ERROR. */ switch (cpuset->partition_root_state) { case PRS_ENABLED: if (part_error) cpuset->partition_root_state = PRS_ERROR; break; case PRS_ERROR: if (!part_error) cpuset->partition_root_state = PRS_ENABLED; break; } /* * Set part_error if previously in invalid state. */ part_error = (prev_prs == PRS_ERROR); } if (!part_error && (cpuset->partition_root_state == PRS_ERROR)) return 0; /* Nothing need to be done */ if (cpuset->partition_root_state == PRS_ERROR) { /* * Remove all its cpus from parent's subparts_cpus. */ adding = false; deleting = cpumask_and(tmp->delmask, cpuset->cpus_allowed, parent->subparts_cpus); } if (!adding && !deleting) return 0; /* * Change the parent's subparts_cpus. * Newly added CPUs will be removed from effective_cpus and * newly deleted ones will be added back to effective_cpus. */ spin_lock_irq(&callback_lock); if (adding) { cpumask_or(parent->subparts_cpus, parent->subparts_cpus, tmp->addmask); cpumask_andnot(parent->effective_cpus, parent->effective_cpus, tmp->addmask); } if (deleting) { cpumask_andnot(parent->subparts_cpus, parent->subparts_cpus, tmp->delmask); /* * Some of the CPUs in subparts_cpus might have been offlined. */ cpumask_and(tmp->delmask, tmp->delmask, cpu_active_mask); cpumask_or(parent->effective_cpus, parent->effective_cpus, tmp->delmask); } parent->nr_subparts_cpus = cpumask_weight(parent->subparts_cpus); spin_unlock_irq(&callback_lock); return cmd == partcmd_update; } /* * update_cpumasks_hier - Update effective cpumasks and tasks in the subtree * @cs: the cpuset to consider * @tmp: temp variables for calculating effective_cpus & partition setup * * When congifured cpumask is changed, the effective cpumasks of this cpuset * and all its descendants need to be updated. * * On legacy hierachy, effective_cpus will be the same with cpu_allowed. * * Called with cpuset_mutex held */ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; bool need_rebuild_sched_domains = false; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); compute_effective_cpumask(tmp->new_cpus, cp, parent); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some CPUs. */ if (is_in_v2_mode() && cpumask_empty(tmp->new_cpus)) { cpumask_copy(tmp->new_cpus, parent->effective_cpus); if (!cp->use_parent_ecpus) { cp->use_parent_ecpus = true; parent->child_ecpus_count++; } } else if (cp->use_parent_ecpus) { cp->use_parent_ecpus = false; WARN_ON_ONCE(!parent->child_ecpus_count); parent->child_ecpus_count--; } /* * Skip the whole subtree if the cpumask remains the same * and has no partition root state. */ if (!cp->partition_root_state && cpumask_equal(tmp->new_cpus, cp->effective_cpus)) { pos_css = css_rightmost_descendant(pos_css); continue; } /* * update_parent_subparts_cpumask() should have been called * for cs already in update_cpumask(). We should also call * update_tasks_cpumask() again for tasks in the parent * cpuset if the parent's subparts_cpus changes. */ if ((cp != cs) && cp->partition_root_state) { switch (parent->partition_root_state) { case PRS_DISABLED: /* * If parent is not a partition root or an * invalid partition root, clear the state * state and the CS_CPU_EXCLUSIVE flag. */ WARN_ON_ONCE(cp->partition_root_state != PRS_ERROR); cp->partition_root_state = 0; /* * clear_bit() is an atomic operation and * readers aren't interested in the state * of CS_CPU_EXCLUSIVE anyway. So we can * just update the flag without holding * the callback_lock. */ clear_bit(CS_CPU_EXCLUSIVE, &cp->flags); break; case PRS_ENABLED: if (update_parent_subparts_cpumask(cp, partcmd_update, NULL, tmp)) update_tasks_cpumask(parent); break; case PRS_ERROR: /* * When parent is invalid, it has to be too. */ cp->partition_root_state = PRS_ERROR; if (cp->nr_subparts_cpus) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } break; } } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cpumask_copy(cp->effective_cpus, tmp->new_cpus); if (cp->nr_subparts_cpus && (cp->partition_root_state != PRS_ENABLED)) { cp->nr_subparts_cpus = 0; cpumask_clear(cp->subparts_cpus); } else if (cp->nr_subparts_cpus) { /* * Make sure that effective_cpus & subparts_cpus * are mutually exclusive. * * In the unlikely event that effective_cpus * becomes empty. we clear cp->nr_subparts_cpus and * let its child partition roots to compete for * CPUs again. */ cpumask_andnot(cp->effective_cpus, cp->effective_cpus, cp->subparts_cpus); if (cpumask_empty(cp->effective_cpus)) { cpumask_copy(cp->effective_cpus, tmp->new_cpus); cpumask_clear(cp->subparts_cpus); cp->nr_subparts_cpus = 0; } else if (!cpumask_subset(cp->subparts_cpus, tmp->new_cpus)) { cpumask_andnot(cp->subparts_cpus, cp->subparts_cpus, tmp->new_cpus); cp->nr_subparts_cpus = cpumask_weight(cp->subparts_cpus); } } spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !cpumask_equal(cp->cpus_allowed, cp->effective_cpus)); update_tasks_cpumask(cp); /* * On legacy hierarchy, if the effective cpumask of any non- * empty cpuset is changed, we need to rebuild sched domains. * On default hierarchy, the cpuset needs to be a partition * root as well. */ if (!cpumask_empty(cp->cpus_allowed) && is_sched_load_balance(cp) && (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) || is_partition_root(cp))) need_rebuild_sched_domains = true; rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); if (need_rebuild_sched_domains) rebuild_sched_domains_locked(); } /** * update_sibling_cpumasks - Update siblings cpumasks * @parent: Parent cpuset * @cs: Current cpuset * @tmp: Temp variables */ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs, struct tmpmasks *tmp) { struct cpuset *sibling; struct cgroup_subsys_state *pos_css; percpu_rwsem_assert_held(&cpuset_rwsem); /* * Check all its siblings and call update_cpumasks_hier() * if their use_parent_ecpus flag is set in order for them * to use the right effective_cpus value. * * The update_cpumasks_hier() function may sleep. So we have to * release the RCU read lock before calling it. */ rcu_read_lock(); cpuset_for_each_child(sibling, pos_css, parent) { if (sibling == cs) continue; if (!sibling->use_parent_ecpus) continue; if (!css_tryget_online(&sibling->css)) continue; rcu_read_unlock(); update_cpumasks_hier(sibling, tmp); rcu_read_lock(); css_put(&sibling->css); } rcu_read_unlock(); } /** * update_cpumask - update the cpus_allowed mask of a cpuset and all tasks in it * @cs: the cpuset to consider * @trialcs: trial cpuset * @buf: buffer of cpu numbers written to this cpuset */ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; struct tmpmasks tmp; /* top_cpuset.cpus_allowed tracks cpu_online_mask; it's read-only */ if (cs == &top_cpuset) return -EACCES; /* * An empty cpus_requested is ok only if the cpuset has no tasks. * Since cpulist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have cpus. */ if (!*buf) { cpumask_clear(trialcs->cpus_requested); } else { retval = cpulist_parse(buf, trialcs->cpus_requested); if (retval < 0) return retval; } if (!cpumask_subset(trialcs->cpus_requested, cpu_present_mask)) return -EINVAL; cpumask_and(trialcs->cpus_allowed, trialcs->cpus_requested, cpu_active_mask); /* Nothing to do if the cpus didn't change */ if (cpumask_equal(cs->cpus_requested, trialcs->cpus_requested)) return 0; retval = validate_change(cs, trialcs); if (retval < 0) return retval; #ifdef CONFIG_CPUMASK_OFFSTACK /* * Use the cpumasks in trialcs for tmpmasks when they are pointers * to allocated cpumasks. */ tmp.addmask = trialcs->subparts_cpus; tmp.delmask = trialcs->effective_cpus; tmp.new_cpus = trialcs->cpus_allowed; #endif if (cs->partition_root_state) { /* Cpumask of a partition root cannot be empty */ if (cpumask_empty(trialcs->cpus_allowed)) return -EINVAL; if (update_parent_subparts_cpumask(cs, partcmd_update, trialcs->cpus_allowed, &tmp) < 0) return -EINVAL; } spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, trialcs->cpus_allowed); cpumask_copy(cs->cpus_requested, trialcs->cpus_requested); /* * Make sure that subparts_cpus is a subset of cpus_allowed. */ if (cs->nr_subparts_cpus) { cpumask_and(cs->subparts_cpus, cs->subparts_cpus, cs->cpus_allowed); cs->nr_subparts_cpus = cpumask_weight(cs->subparts_cpus); } spin_unlock_irq(&callback_lock); update_cpumasks_hier(cs, &tmp); if (cs->partition_root_state) { struct cpuset *parent = parent_cs(cs); /* * For partition root, update the cpumasks of sibling * cpusets if they use parent's effective_cpus. */ if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmp); } return 0; } /* * Migrate memory region from one set of nodes to another. This is * performed asynchronously as it can be called from process migration path * holding locks involved in process management. All mm migrations are * performed in the queued order and can be waited for by flushing * cpuset_migrate_mm_wq. */ struct cpuset_migrate_mm_work { struct work_struct work; struct mm_struct *mm; nodemask_t from; nodemask_t to; }; static void cpuset_migrate_mm_workfn(struct work_struct *work) { struct cpuset_migrate_mm_work *mwork = container_of(work, struct cpuset_migrate_mm_work, work); /* on a wq worker, no need to worry about %current's mems_allowed */ do_migrate_pages(mwork->mm, &mwork->from, &mwork->to, MPOL_MF_MOVE_ALL); mmput(mwork->mm); kfree(mwork); } static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to) { struct cpuset_migrate_mm_work *mwork; mwork = kzalloc(sizeof(*mwork), GFP_KERNEL); if (mwork) { mwork->mm = mm; mwork->from = *from; mwork->to = *to; INIT_WORK(&mwork->work, cpuset_migrate_mm_workfn); queue_work(cpuset_migrate_mm_wq, &mwork->work); } else { mmput(mm); } } static void cpuset_post_attach(void) { flush_workqueue(cpuset_migrate_mm_wq); } /* * cpuset_change_task_nodemask - change task's mems_allowed and mempolicy * @tsk: the task to change * @newmems: new nodes that the task will be set * * We use the mems_allowed_seq seqlock to safely update both tsk->mems_allowed * and rebind an eventual tasks' mempolicy. If the task is allocating in * parallel, it might temporarily see an empty intersection, which results in * a seqlock check and retry before OOM or allocation failure. */ static void cpuset_change_task_nodemask(struct task_struct *tsk, nodemask_t *newmems) { task_lock(tsk); local_irq_disable(); write_seqcount_begin(&tsk->mems_allowed_seq); nodes_or(tsk->mems_allowed, tsk->mems_allowed, *newmems); mpol_rebind_task(tsk, newmems); tsk->mems_allowed = *newmems; write_seqcount_end(&tsk->mems_allowed_seq); local_irq_enable(); task_unlock(tsk); } static void *cpuset_being_rebound; /** * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset. * @cs: the cpuset in which each task's mems_allowed mask needs to be changed * * Iterate through each task of @cs updating its mems_allowed to the * effective cpuset's. As this function is called with cpuset_mutex held, * cpuset membership stays stable. */ static void update_tasks_nodemask(struct cpuset *cs) { static nodemask_t newmems; /* protected by cpuset_mutex */ struct css_task_iter it; struct task_struct *task; cpuset_being_rebound = cs; /* causes mpol_dup() rebind */ guarantee_online_mems(cs, &newmems); /* * The mpol_rebind_mm() call takes mmap_sem, which we couldn't * take while holding tasklist_lock. Forks can happen - the * mpol_dup() cpuset_being_rebound check will catch such forks, * and rebind their vma mempolicies too. Because we still hold * the global cpuset_mutex, we know that no other rebind effort * will be contending for the global variable cpuset_being_rebound. * It's ok if we rebind the same mm twice; mpol_rebind_mm() * is idempotent. Also migrate pages in each mm to new nodes. */ css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) { struct mm_struct *mm; bool migrate; cpuset_change_task_nodemask(task, &newmems); mm = get_task_mm(task); if (!mm) continue; migrate = is_memory_migrate(cs); mpol_rebind_mm(mm, &cs->mems_allowed); if (migrate) cpuset_migrate_mm(mm, &cs->old_mems_allowed, &newmems); else mmput(mm); } css_task_iter_end(&it); /* * All the tasks' nodemasks have been updated, update * cs->old_mems_allowed. */ cs->old_mems_allowed = newmems; /* We're done rebinding vmas to this cpuset's new mems_allowed. */ cpuset_being_rebound = NULL; } /* * update_nodemasks_hier - Update effective nodemasks and tasks in the subtree * @cs: the cpuset to consider * @new_mems: a temp variable for calculating new effective_mems * * When configured nodemask is changed, the effective nodemasks of this cpuset * and all its descendants need to be updated. * * On legacy hiearchy, effective_mems will be the same with mems_allowed. * * Called with cpuset_mutex held */ static void update_nodemasks_hier(struct cpuset *cs, nodemask_t *new_mems) { struct cpuset *cp; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cp, pos_css, cs) { struct cpuset *parent = parent_cs(cp); nodes_and(*new_mems, cp->mems_allowed, parent->effective_mems); /* * If it becomes empty, inherit the effective mask of the * parent, which is guaranteed to have some MEMs. */ if (is_in_v2_mode() && nodes_empty(*new_mems)) *new_mems = parent->effective_mems; /* Skip the whole subtree if the nodemask remains the same. */ if (nodes_equal(*new_mems, cp->effective_mems)) { pos_css = css_rightmost_descendant(pos_css); continue; } if (!css_tryget_online(&cp->css)) continue; rcu_read_unlock(); spin_lock_irq(&callback_lock); cp->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); WARN_ON(!is_in_v2_mode() && !nodes_equal(cp->mems_allowed, cp->effective_mems)); update_tasks_nodemask(cp); rcu_read_lock(); css_put(&cp->css); } rcu_read_unlock(); } /* * Handle user request to change the 'mems' memory placement * of a cpuset. Needs to validate the request, update the * cpusets mems_allowed, and for each task in the cpuset, * update mems_allowed and rebind task's mempolicy and any vma * mempolicies and if the cpuset is marked 'memory_migrate', * migrate the tasks pages to the new memory. * * Call with cpuset_mutex held. May take callback_lock during call. * Will take tasklist_lock, scan tasklist for tasks in cpuset cs, * lock each such tasks mm->mmap_sem, scan its vma's and rebind * their mempolicies to the cpusets new mems_allowed. */ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs, const char *buf) { int retval; /* * top_cpuset.mems_allowed tracks node_stats[N_MEMORY]; * it's read-only */ if (cs == &top_cpuset) { retval = -EACCES; goto done; } /* * An empty mems_allowed is ok iff there are no tasks in the cpuset. * Since nodelist_parse() fails on an empty mask, we special case * that parsing. The validate_change() call ensures that cpusets * with tasks have memory. */ if (!*buf) { nodes_clear(trialcs->mems_allowed); } else { retval = nodelist_parse(buf, trialcs->mems_allowed); if (retval < 0) goto done; if (!nodes_subset(trialcs->mems_allowed, top_cpuset.mems_allowed)) { retval = -EINVAL; goto done; } } if (nodes_equal(cs->mems_allowed, trialcs->mems_allowed)) { retval = 0; /* Too easy - nothing to do */ goto done; } retval = validate_change(cs, trialcs); if (retval < 0) goto done; spin_lock_irq(&callback_lock); cs->mems_allowed = trialcs->mems_allowed; spin_unlock_irq(&callback_lock); /* use trialcs->mems_allowed as a temp variable */ update_nodemasks_hier(cs, &trialcs->mems_allowed); done: return retval; } bool current_cpuset_is_being_rebound(void) { bool ret; rcu_read_lock(); ret = task_cs(current) == cpuset_being_rebound; rcu_read_unlock(); return ret; } static int update_relax_domain_level(struct cpuset *cs, s64 val) { #ifdef CONFIG_SMP if (val < -1 || val > sched_domain_level_max + 1) return -EINVAL; #endif if (val != cs->relax_domain_level) { cs->relax_domain_level = val; if (!cpumask_empty(cs->cpus_allowed) && is_sched_load_balance(cs)) rebuild_sched_domains_locked(); } return 0; } /** * update_tasks_flags - update the spread flags of tasks in the cpuset. * @cs: the cpuset in which each task's spread flags needs to be changed * * Iterate through each task of @cs updating its spread flags. As this * function is called with cpuset_mutex held, cpuset membership stays * stable. */ static void update_tasks_flags(struct cpuset *cs) { struct css_task_iter it; struct task_struct *task; css_task_iter_start(&cs->css, 0, &it); while ((task = css_task_iter_next(&it))) cpuset_update_task_spread_flag(cs, task); css_task_iter_end(&it); } /* * update_flag - read a 0 or a 1 in a file and update associated flag * bit: the bit to update (see cpuset_flagbits_t) * cs: the cpuset to update * turning_on: whether the flag is being set or cleared * * Call with cpuset_mutex held. */ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs, int turning_on) { struct cpuset *trialcs; int balance_flag_changed; int spread_flag_changed; int err; trialcs = alloc_trial_cpuset(cs); if (!trialcs) return -ENOMEM; if (turning_on) set_bit(bit, &trialcs->flags); else clear_bit(bit, &trialcs->flags); err = validate_change(cs, trialcs); if (err < 0) goto out; balance_flag_changed = (is_sched_load_balance(cs) != is_sched_load_balance(trialcs)); spread_flag_changed = ((is_spread_slab(cs) != is_spread_slab(trialcs)) || (is_spread_page(cs) != is_spread_page(trialcs))); spin_lock_irq(&callback_lock); cs->flags = trialcs->flags; spin_unlock_irq(&callback_lock); if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed) rebuild_sched_domains_locked(); if (spread_flag_changed) update_tasks_flags(cs); out: free_cpuset(trialcs); return err; } /* * update_prstate - update partititon_root_state * cs: the cpuset to update * val: 0 - disabled, 1 - enabled * * Call with cpuset_mutex held. */ static int update_prstate(struct cpuset *cs, int val) { int err; struct cpuset *parent = parent_cs(cs); struct tmpmasks tmp; if ((val != 0) && (val != 1)) return -EINVAL; if (val == cs->partition_root_state) return 0; /* * Cannot force a partial or invalid partition root to a full * partition root. */ if (val && cs->partition_root_state) return -EINVAL; if (alloc_cpumasks(NULL, &tmp)) return -ENOMEM; err = -EINVAL; if (!cs->partition_root_state) { /* * Turning on partition root requires setting the * CS_CPU_EXCLUSIVE bit implicitly as well and cpus_allowed * cannot be NULL. */ if (cpumask_empty(cs->cpus_allowed)) goto out; err = update_flag(CS_CPU_EXCLUSIVE, cs, 1); if (err) goto out; err = update_parent_subparts_cpumask(cs, partcmd_enable, NULL, &tmp); if (err) { update_flag(CS_CPU_EXCLUSIVE, cs, 0); goto out; } cs->partition_root_state = PRS_ENABLED; } else { /* * Turning off partition root will clear the * CS_CPU_EXCLUSIVE bit. */ if (cs->partition_root_state == PRS_ERROR) { cs->partition_root_state = 0; update_flag(CS_CPU_EXCLUSIVE, cs, 0); err = 0; goto out; } err = update_parent_subparts_cpumask(cs, partcmd_disable, NULL, &tmp); if (err) goto out; cs->partition_root_state = 0; /* Turning off CS_CPU_EXCLUSIVE will not return error */ update_flag(CS_CPU_EXCLUSIVE, cs, 0); } update_tasks_cpumask(parent); if (parent->child_ecpus_count) update_sibling_cpumasks(parent, cs, &tmp); rebuild_sched_domains_locked(); out: free_cpumasks(NULL, &tmp); return err; } /* * Frequency meter - How fast is some event occurring? * * These routines manage a digitally filtered, constant time based, * event frequency meter. There are four routines: * fmeter_init() - initialize a frequency meter. * fmeter_markevent() - called each time the event happens. * fmeter_getrate() - returns the recent rate of such events. * fmeter_update() - internal routine used to update fmeter. * * A common data structure is passed to each of these routines, * which is used to keep track of the state required to manage the * frequency meter and its digital filter. * * The filter works on the number of events marked per unit time. * The filter is single-pole low-pass recursive (IIR). The time unit * is 1 second. Arithmetic is done using 32-bit integers scaled to * simulate 3 decimal digits of precision (multiplied by 1000). * * With an FM_COEF of 933, and a time base of 1 second, the filter * has a half-life of 10 seconds, meaning that if the events quit * happening, then the rate returned from the fmeter_getrate() * will be cut in half each 10 seconds, until it converges to zero. * * It is not worth doing a real infinitely recursive filter. If more * than FM_MAXTICKS ticks have elapsed since the last filter event, * just compute FM_MAXTICKS ticks worth, by which point the level * will be stable. * * Limit the count of unprocessed events to FM_MAXCNT, so as to avoid * arithmetic overflow in the fmeter_update() routine. * * Given the simple 32 bit integer arithmetic used, this meter works * best for reporting rates between one per millisecond (msec) and * one per 32 (approx) seconds. At constant rates faster than one * per msec it maxes out at values just under 1,000,000. At constant * rates between one per msec, and one per second it will stabilize * to a value N*1000, where N is the rate of events per second. * At constant rates between one per second and one per 32 seconds, * it will be choppy, moving up on the seconds that have an event, * and then decaying until the next event. At rates slower than * about one in 32 seconds, it decays all the way back to zero between * each event. */ #define FM_COEF 933 /* coefficient for half-life of 10 secs */ #define FM_MAXTICKS ((u32)99) /* useless computing more ticks than this */ #define FM_MAXCNT 1000000 /* limit cnt to avoid overflow */ #define FM_SCALE 1000 /* faux fixed point scale */ /* Initialize a frequency meter */ static void fmeter_init(struct fmeter *fmp) { fmp->cnt = 0; fmp->val = 0; fmp->time = 0; spin_lock_init(&fmp->lock); } /* Internal meter update - process cnt events and update value */ static void fmeter_update(struct fmeter *fmp) { time64_t now; u32 ticks; now = ktime_get_seconds(); ticks = now - fmp->time; if (ticks == 0) return; ticks = min(FM_MAXTICKS, ticks); while (ticks-- > 0) fmp->val = (FM_COEF * fmp->val) / FM_SCALE; fmp->time = now; fmp->val += ((FM_SCALE - FM_COEF) * fmp->cnt) / FM_SCALE; fmp->cnt = 0; } /* Process any previous ticks, then bump cnt by one (times scale). */ static void fmeter_markevent(struct fmeter *fmp) { spin_lock(&fmp->lock); fmeter_update(fmp); fmp->cnt = min(FM_MAXCNT, fmp->cnt + FM_SCALE); spin_unlock(&fmp->lock); } /* Process any previous ticks, then return current value. */ static int fmeter_getrate(struct fmeter *fmp) { int val; spin_lock(&fmp->lock); fmeter_update(fmp); val = fmp->val; spin_unlock(&fmp->lock); return val; } static struct cpuset *cpuset_attach_old_cs; /* Called by cgroups to determine if a cpuset is usable; cpuset_mutex held */ static int cpuset_can_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; struct task_struct *task; int ret; /* used later by cpuset_attach() */ cpuset_attach_old_cs = task_cs(cgroup_taskset_first(tset, &css)); cs = css_cs(css); percpu_down_write(&cpuset_rwsem); /* allow moving tasks into an empty cpuset if on default hierarchy */ ret = -ENOSPC; if (!is_in_v2_mode() && (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))) goto out_unlock; cgroup_taskset_for_each(task, css, tset) { ret = task_can_attach(task, cs->cpus_allowed); if (ret) goto out_unlock; ret = security_task_setscheduler(task); if (ret) goto out_unlock; } /* * Mark attach is in progress. This makes validate_change() fail * changes which zero cpus/mems_allowed. */ cs->attach_in_progress++; ret = 0; out_unlock: percpu_up_write(&cpuset_rwsem); return ret; } static void cpuset_cancel_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct cpuset *cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); percpu_down_write(&cpuset_rwsem); cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); } /* * Protected by cpuset_mutex. cpus_attach is used only by cpuset_attach() * but we can't allocate it dynamically there. Define it global and * allocate from cpuset_init(). */ static cpumask_var_t cpus_attach; static void cpuset_attach(struct cgroup_taskset *tset) { /* static buf protected by cpuset_mutex */ static nodemask_t cpuset_attach_nodemask_to; struct task_struct *task; struct task_struct *leader; struct cgroup_subsys_state *css; struct cpuset *cs; struct cpuset *oldcs = cpuset_attach_old_cs; cgroup_taskset_first(tset, &css); cs = css_cs(css); lockdep_assert_cpus_held(); /* see cgroup_attach_lock() */ percpu_down_write(&cpuset_rwsem); /* prepare for attach */ if (cs == &top_cpuset) cpumask_copy(cpus_attach, cpu_possible_mask); else guarantee_online_cpus(cs, cpus_attach); guarantee_online_mems(cs, &cpuset_attach_nodemask_to); cgroup_taskset_for_each(task, css, tset) { /* * can_attach beforehand should guarantee that this doesn't * fail. TODO: have a better way to handle failure here */ WARN_ON_ONCE(set_cpus_allowed_ptr(task, cpus_attach)); cpuset_change_task_nodemask(task, &cpuset_attach_nodemask_to); cpuset_update_task_spread_flag(cs, task); } /* * Change mm for all threadgroup leaders. This is expensive and may * sleep and should be moved outside migration path proper. */ cpuset_attach_nodemask_to = cs->effective_mems; cgroup_taskset_for_each_leader(leader, css, tset) { struct mm_struct *mm = get_task_mm(leader); if (mm) { mpol_rebind_mm(mm, &cpuset_attach_nodemask_to); /* * old_mems_allowed is the same with mems_allowed * here, except if this task is being moved * automatically due to hotplug. In that case * @mems_allowed has been updated and is empty, so * @old_mems_allowed is the right nodesets that we * migrate mm from. */ if (is_memory_migrate(cs)) cpuset_migrate_mm(mm, &oldcs->old_mems_allowed, &cpuset_attach_nodemask_to); else mmput(mm); } } cs->old_mems_allowed = cpuset_attach_nodemask_to; cs->attach_in_progress--; if (!cs->attach_in_progress) wake_up(&cpuset_attach_wq); percpu_up_write(&cpuset_rwsem); } /* The various types of files and directories in a cpuset file system */ typedef enum { FILE_MEMORY_MIGRATE, FILE_CPULIST, FILE_MEMLIST, FILE_EFFECTIVE_CPULIST, FILE_EFFECTIVE_MEMLIST, FILE_SUBPARTS_CPULIST, FILE_CPU_EXCLUSIVE, FILE_MEM_EXCLUSIVE, FILE_MEM_HARDWALL, FILE_SCHED_LOAD_BALANCE, FILE_PARTITION_ROOT, FILE_SCHED_RELAX_DOMAIN_LEVEL, FILE_MEMORY_PRESSURE_ENABLED, FILE_MEMORY_PRESSURE, FILE_SPREAD_PAGE, FILE_SPREAD_SLAB, } cpuset_filetype_t; static int cpuset_write_u64(struct cgroup_subsys_state *css, struct cftype *cft, u64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = 0; get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) { retval = -ENODEV; goto out_unlock; } switch (type) { case FILE_CPU_EXCLUSIVE: retval = update_flag(CS_CPU_EXCLUSIVE, cs, val); break; case FILE_MEM_EXCLUSIVE: retval = update_flag(CS_MEM_EXCLUSIVE, cs, val); break; case FILE_MEM_HARDWALL: retval = update_flag(CS_MEM_HARDWALL, cs, val); break; case FILE_SCHED_LOAD_BALANCE: retval = update_flag(CS_SCHED_LOAD_BALANCE, cs, val); break; case FILE_MEMORY_MIGRATE: retval = update_flag(CS_MEMORY_MIGRATE, cs, val); break; case FILE_MEMORY_PRESSURE_ENABLED: cpuset_memory_pressure_enabled = !!val; break; case FILE_SPREAD_PAGE: retval = update_flag(CS_SPREAD_PAGE, cs, val); break; case FILE_SPREAD_SLAB: retval = update_flag(CS_SPREAD_SLAB, cs, val); break; default: retval = -EINVAL; break; } out_unlock: percpu_up_write(&cpuset_rwsem); put_online_cpus(); return retval; } static int cpuset_write_s64(struct cgroup_subsys_state *css, struct cftype *cft, s64 val) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; int retval = -ENODEV; get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: retval = update_relax_domain_level(cs, val); break; default: retval = -EINVAL; break; } out_unlock: percpu_up_write(&cpuset_rwsem); put_online_cpus(); return retval; } /* * Common handling for a write to a "cpus" or "mems" file. */ static ssize_t cpuset_write_resmask(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); struct cpuset *trialcs; int retval = -ENODEV; buf = strstrip(buf); /* * CPU or memory hotunplug may leave @cs w/o any execution * resources, in which case the hotplug code asynchronously updates * configuration and transfers all tasks to the nearest ancestor * which can execute. * * As writes to "cpus" or "mems" may restore @cs's execution * resources, wait for the previously scheduled operations before * proceeding, so that we don't end up keep removing tasks added * after execution capability is restored. * * cpuset_hotplug_work calls back into cgroup core via * cgroup_transfer_tasks() and waiting for it from a cgroupfs * operation like this one can lead to a deadlock through kernfs * active_ref protection. Let's break the protection. Losing the * protection is okay as we check whether @cs is online after * grabbing cpuset_mutex anyway. This only happens on the legacy * hierarchies. */ css_get(&cs->css); kernfs_break_active_protection(of->kn); flush_work(&cpuset_hotplug_work); get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; trialcs = alloc_trial_cpuset(cs); if (!trialcs) { retval = -ENOMEM; goto out_unlock; } switch (of_cft(of)->private) { case FILE_CPULIST: retval = update_cpumask(cs, trialcs, buf); break; case FILE_MEMLIST: retval = update_nodemask(cs, trialcs, buf); break; default: retval = -EINVAL; break; } free_cpuset(trialcs); out_unlock: percpu_up_write(&cpuset_rwsem); put_online_cpus(); kernfs_unbreak_active_protection(of->kn); css_put(&cs->css); flush_workqueue(cpuset_migrate_mm_wq); return retval ?: nbytes; } /* * These ascii lists should be read in a single call, by using a user * buffer large enough to hold the entire map. If read in smaller * chunks, there is no guarantee of atomicity. Since the display format * used, list of ranges of sequential numbers, is variable length, * and since these maps can change value dynamically, one could read * gibberish by doing partial reads while a list was changing. */ static int cpuset_common_seq_show(struct seq_file *sf, void *v) { struct cpuset *cs = css_cs(seq_css(sf)); cpuset_filetype_t type = seq_cft(sf)->private; int ret = 0; spin_lock_irq(&callback_lock); switch (type) { case FILE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->cpus_requested)); break; case FILE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->mems_allowed)); break; case FILE_EFFECTIVE_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->effective_cpus)); break; case FILE_EFFECTIVE_MEMLIST: seq_printf(sf, "%*pbl\n", nodemask_pr_args(&cs->effective_mems)); break; case FILE_SUBPARTS_CPULIST: seq_printf(sf, "%*pbl\n", cpumask_pr_args(cs->subparts_cpus)); break; default: ret = -EINVAL; } spin_unlock_irq(&callback_lock); return ret; } static u64 cpuset_read_u64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_CPU_EXCLUSIVE: return is_cpu_exclusive(cs); case FILE_MEM_EXCLUSIVE: return is_mem_exclusive(cs); case FILE_MEM_HARDWALL: return is_mem_hardwall(cs); case FILE_SCHED_LOAD_BALANCE: return is_sched_load_balance(cs); case FILE_MEMORY_MIGRATE: return is_memory_migrate(cs); case FILE_MEMORY_PRESSURE_ENABLED: return cpuset_memory_pressure_enabled; case FILE_MEMORY_PRESSURE: return fmeter_getrate(&cs->fmeter); case FILE_SPREAD_PAGE: return is_spread_page(cs); case FILE_SPREAD_SLAB: return is_spread_slab(cs); default: BUG(); } /* Unreachable but makes gcc happy */ return 0; } static s64 cpuset_read_s64(struct cgroup_subsys_state *css, struct cftype *cft) { struct cpuset *cs = css_cs(css); cpuset_filetype_t type = cft->private; switch (type) { case FILE_SCHED_RELAX_DOMAIN_LEVEL: return cs->relax_domain_level; default: BUG(); } /* Unrechable but makes gcc happy */ return 0; } static int sched_partition_show(struct seq_file *seq, void *v) { struct cpuset *cs = css_cs(seq_css(seq)); switch (cs->partition_root_state) { case PRS_ENABLED: seq_puts(seq, "root\n"); break; case PRS_DISABLED: seq_puts(seq, "member\n"); break; case PRS_ERROR: seq_puts(seq, "root invalid\n"); break; } return 0; } static ssize_t sched_partition_write(struct kernfs_open_file *of, char *buf, size_t nbytes, loff_t off) { struct cpuset *cs = css_cs(of_css(of)); int val; int retval = -ENODEV; buf = strstrip(buf); /* * Convert "root" to ENABLED, and convert "member" to DISABLED. */ if (!strcmp(buf, "root")) val = PRS_ENABLED; else if (!strcmp(buf, "member")) val = PRS_DISABLED; else return -EINVAL; css_get(&cs->css); get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (!is_cpuset_online(cs)) goto out_unlock; retval = update_prstate(cs, val); out_unlock: percpu_up_write(&cpuset_rwsem); put_online_cpus(); css_put(&cs->css); return retval ?: nbytes; } /* * for the common functions, 'private' gives the type of file */ static struct cftype legacy_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, }, { .name = "effective_cpus", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "effective_mems", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpu_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_CPU_EXCLUSIVE, }, { .name = "mem_exclusive", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_EXCLUSIVE, }, { .name = "mem_hardwall", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEM_HARDWALL, }, { .name = "sched_load_balance", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SCHED_LOAD_BALANCE, }, { .name = "sched_relax_domain_level", .read_s64 = cpuset_read_s64, .write_s64 = cpuset_write_s64, .private = FILE_SCHED_RELAX_DOMAIN_LEVEL, }, { .name = "memory_migrate", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_MIGRATE, }, { .name = "memory_pressure", .read_u64 = cpuset_read_u64, .private = FILE_MEMORY_PRESSURE, }, { .name = "memory_spread_page", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_PAGE, }, { .name = "memory_spread_slab", .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_SPREAD_SLAB, }, { .name = "memory_pressure_enabled", .flags = CFTYPE_ONLY_ON_ROOT, .read_u64 = cpuset_read_u64, .write_u64 = cpuset_write_u64, .private = FILE_MEMORY_PRESSURE_ENABLED, }, { } /* terminate */ }; /* * This is currently a minimal set for the default hierarchy. It can be * expanded later on by migrating more features and control files from v1. */ static struct cftype dfl_files[] = { { .name = "cpus", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * NR_CPUS), .private = FILE_CPULIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "mems", .seq_show = cpuset_common_seq_show, .write = cpuset_write_resmask, .max_write_len = (100U + 6 * MAX_NUMNODES), .private = FILE_MEMLIST, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_CPULIST, }, { .name = "mems.effective", .seq_show = cpuset_common_seq_show, .private = FILE_EFFECTIVE_MEMLIST, }, { .name = "cpus.partition", .seq_show = sched_partition_show, .write = sched_partition_write, .private = FILE_PARTITION_ROOT, .flags = CFTYPE_NOT_ON_ROOT, }, { .name = "cpus.subpartitions", .seq_show = cpuset_common_seq_show, .private = FILE_SUBPARTS_CPULIST, .flags = CFTYPE_DEBUG, }, { } /* terminate */ }; /* * cpuset_css_alloc - allocate a cpuset css * cgrp: control group that the new cpuset will be part of */ static struct cgroup_subsys_state * cpuset_css_alloc(struct cgroup_subsys_state *parent_css) { struct cpuset *cs; if (!parent_css) return &top_cpuset.css; cs = kzalloc(sizeof(*cs), GFP_KERNEL); if (!cs) return ERR_PTR(-ENOMEM); if (alloc_cpumasks(cs, NULL)) { kfree(cs); return ERR_PTR(-ENOMEM); } set_bit(CS_SCHED_LOAD_BALANCE, &cs->flags); nodes_clear(cs->mems_allowed); nodes_clear(cs->effective_mems); fmeter_init(&cs->fmeter); cs->relax_domain_level = -1; return &cs->css; } static int cpuset_css_online(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); struct cpuset *parent = parent_cs(cs); struct cpuset *tmp_cs; struct cgroup_subsys_state *pos_css; if (!parent) return 0; get_online_cpus(); percpu_down_write(&cpuset_rwsem); set_bit(CS_ONLINE, &cs->flags); if (is_spread_page(parent)) set_bit(CS_SPREAD_PAGE, &cs->flags); if (is_spread_slab(parent)) set_bit(CS_SPREAD_SLAB, &cs->flags); cpuset_inc(); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(cs->effective_cpus, parent->effective_cpus); cs->effective_mems = parent->effective_mems; cs->use_parent_ecpus = true; parent->child_ecpus_count++; } spin_unlock_irq(&callback_lock); if (!test_bit(CGRP_CPUSET_CLONE_CHILDREN, &css->cgroup->flags)) goto out_unlock; /* * Clone @parent's configuration if CGRP_CPUSET_CLONE_CHILDREN is * set. This flag handling is implemented in cgroup core for * histrical reasons - the flag may be specified during mount. * * Currently, if any sibling cpusets have exclusive cpus or mem, we * refuse to clone the configuration - thereby refusing the task to * be entered, and as a result refusing the sys_unshare() or * clone() which initiated it. If this becomes a problem for some * users who wish to allow that scenario, then this could be * changed to grant parent->cpus_allowed-sibling_cpus_exclusive * (and likewise for mems) to the new cgroup. */ rcu_read_lock(); cpuset_for_each_child(tmp_cs, pos_css, parent) { if (is_mem_exclusive(tmp_cs) || is_cpu_exclusive(tmp_cs)) { rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); spin_lock_irq(&callback_lock); cs->mems_allowed = parent->mems_allowed; cs->effective_mems = parent->mems_allowed; cpumask_copy(cs->cpus_allowed, parent->cpus_allowed); cpumask_copy(cs->cpus_requested, parent->cpus_requested); cpumask_copy(cs->effective_cpus, parent->cpus_allowed); spin_unlock_irq(&callback_lock); out_unlock: percpu_up_write(&cpuset_rwsem); put_online_cpus(); return 0; } /* * If the cpuset being removed has its flag 'sched_load_balance' * enabled, then simulate turning sched_load_balance off, which * will call rebuild_sched_domains_locked(). That is not needed * in the default hierarchy where only changes in partition * will cause repartitioning. * * If the cpuset has the 'sched.partition' flag enabled, simulate * turning 'sched.partition" off. */ static void cpuset_css_offline(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); get_online_cpus(); percpu_down_write(&cpuset_rwsem); if (is_partition_root(cs)) update_prstate(cs, 0); if (!cgroup_subsys_on_dfl(cpuset_cgrp_subsys) && is_sched_load_balance(cs)) update_flag(CS_SCHED_LOAD_BALANCE, cs, 0); if (cs->use_parent_ecpus) { struct cpuset *parent = parent_cs(cs); cs->use_parent_ecpus = false; parent->child_ecpus_count--; } cpuset_dec(); clear_bit(CS_ONLINE, &cs->flags); percpu_up_write(&cpuset_rwsem); put_online_cpus(); } static void cpuset_css_free(struct cgroup_subsys_state *css) { struct cpuset *cs = css_cs(css); free_cpuset(cs); } static void cpuset_bind(struct cgroup_subsys_state *root_css) { percpu_down_write(&cpuset_rwsem); spin_lock_irq(&callback_lock); if (is_in_v2_mode()) { cpumask_copy(top_cpuset.cpus_allowed, cpu_possible_mask); top_cpuset.mems_allowed = node_possible_map; } else { cpumask_copy(top_cpuset.cpus_allowed, top_cpuset.effective_cpus); top_cpuset.mems_allowed = top_cpuset.effective_mems; } spin_unlock_irq(&callback_lock); percpu_up_write(&cpuset_rwsem); } /* * Make sure the new task conform to the current state of its parent, * which could have been changed by cpuset just after it inherits the * state from the parent and before it sits on the cgroup's task list. */ static void cpuset_fork(struct task_struct *task) { if (task_css_is_root(task, cpuset_cgrp_id)) return; set_cpus_allowed_ptr(task, current->cpus_ptr); task->mems_allowed = current->mems_allowed; } struct cgroup_subsys cpuset_cgrp_subsys = { .css_alloc = cpuset_css_alloc, .css_online = cpuset_css_online, .css_offline = cpuset_css_offline, .css_free = cpuset_css_free, .can_attach = cpuset_can_attach, .cancel_attach = cpuset_cancel_attach, .attach = cpuset_attach, .post_attach = cpuset_post_attach, .bind = cpuset_bind, .fork = cpuset_fork, .legacy_cftypes = legacy_files, .dfl_cftypes = dfl_files, .early_init = true, .threaded = true, }; /** * cpuset_init - initialize cpusets at system boot * * Description: Initialize top_cpuset **/ int __init cpuset_init(void) { BUG_ON(percpu_init_rwsem(&cpuset_rwsem)); BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_allowed, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.effective_cpus, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&top_cpuset.subparts_cpus, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&top_cpuset.cpus_requested, GFP_KERNEL)); cpumask_setall(top_cpuset.cpus_allowed); cpumask_setall(top_cpuset.cpus_requested); nodes_setall(top_cpuset.mems_allowed); cpumask_setall(top_cpuset.effective_cpus); nodes_setall(top_cpuset.effective_mems); fmeter_init(&top_cpuset.fmeter); set_bit(CS_SCHED_LOAD_BALANCE, &top_cpuset.flags); top_cpuset.relax_domain_level = -1; BUG_ON(!alloc_cpumask_var(&cpus_attach, GFP_KERNEL)); return 0; } /* * If CPU and/or memory hotplug handlers, below, unplug any CPUs * or memory nodes, we need to walk over the cpuset hierarchy, * removing that CPU or node from all cpusets. If this removes the * last CPU or node from a cpuset, then move the tasks in the empty * cpuset to its next-highest non-empty parent. */ static void remove_tasks_in_empty_cpuset(struct cpuset *cs) { struct cpuset *parent; /* * Find its next-highest non-empty parent, (top cpuset * has online cpus, so can't be empty). */ parent = parent_cs(cs); while (cpumask_empty(parent->cpus_allowed) || nodes_empty(parent->mems_allowed)) parent = parent_cs(parent); if (cgroup_transfer_tasks(parent->css.cgroup, cs->css.cgroup)) { pr_err("cpuset: failed to transfer tasks out of empty cpuset "); pr_cont_cgroup_name(cs->css.cgroup); pr_cont("\n"); } } static void hotplug_update_tasks_legacy(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { bool is_empty; spin_lock_irq(&callback_lock); cpumask_copy(cs->cpus_allowed, new_cpus); cpumask_copy(cs->effective_cpus, new_cpus); cs->mems_allowed = *new_mems; cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); /* * Don't call update_tasks_cpumask() if the cpuset becomes empty, * as the tasks will be migratecd to an ancestor. */ if (cpus_updated && !cpumask_empty(cs->cpus_allowed)) update_tasks_cpumask(cs); if (mems_updated && !nodes_empty(cs->mems_allowed)) update_tasks_nodemask(cs); is_empty = cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed); percpu_up_write(&cpuset_rwsem); /* * Move tasks to the nearest ancestor with execution resources, * This is full cgroup operation which will also call back into * cpuset. Should be done outside any lock. */ if (is_empty) remove_tasks_in_empty_cpuset(cs); percpu_down_write(&cpuset_rwsem); } static void hotplug_update_tasks(struct cpuset *cs, struct cpumask *new_cpus, nodemask_t *new_mems, bool cpus_updated, bool mems_updated) { if (cpumask_empty(new_cpus)) cpumask_copy(new_cpus, parent_cs(cs)->effective_cpus); if (nodes_empty(*new_mems)) *new_mems = parent_cs(cs)->effective_mems; spin_lock_irq(&callback_lock); cpumask_copy(cs->effective_cpus, new_cpus); cs->effective_mems = *new_mems; spin_unlock_irq(&callback_lock); if (cpus_updated) update_tasks_cpumask(cs); if (mems_updated) update_tasks_nodemask(cs); } static bool force_rebuild; void cpuset_force_rebuild(void) { force_rebuild = true; } /** * cpuset_hotplug_update_tasks - update tasks in a cpuset for hotunplug * @cs: cpuset in interest * @tmp: the tmpmasks structure pointer * * Compare @cs's cpu and mem masks against top_cpuset and if some have gone * offline, update @cs accordingly. If @cs ends up with no CPU or memory, * all its tasks are moved to the nearest ancestor with both resources. */ static void cpuset_hotplug_update_tasks(struct cpuset *cs, struct tmpmasks *tmp) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated; bool mems_updated; struct cpuset *parent; retry: wait_event(cpuset_attach_wq, cs->attach_in_progress == 0); percpu_down_write(&cpuset_rwsem); /* * We have raced with task attaching. We wait until attaching * is finished, so we won't attach a task to an empty cpuset. */ if (cs->attach_in_progress) { percpu_up_write(&cpuset_rwsem); goto retry; } parent = parent_cs(cs); compute_effective_cpumask(&new_cpus, cs, parent); nodes_and(new_mems, cs->mems_allowed, parent->effective_mems); if (cs->nr_subparts_cpus) /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. */ cpumask_andnot(&new_cpus, &new_cpus, cs->subparts_cpus); if (!tmp || !cs->partition_root_state) goto update_tasks; /* * In the unlikely event that a partition root has empty * effective_cpus or its parent becomes erroneous, we have to * transition it to the erroneous state. */ if (is_partition_root(cs) && (cpumask_empty(&new_cpus) || (parent->partition_root_state == PRS_ERROR))) { if (cs->nr_subparts_cpus) { cs->nr_subparts_cpus = 0; cpumask_clear(cs->subparts_cpus); compute_effective_cpumask(&new_cpus, cs, parent); } /* * If the effective_cpus is empty because the child * partitions take away all the CPUs, we can keep * the current partition and let the child partitions * fight for available CPUs. */ if ((parent->partition_root_state == PRS_ERROR) || cpumask_empty(&new_cpus)) { update_parent_subparts_cpumask(cs, partcmd_disable, NULL, tmp); cs->partition_root_state = PRS_ERROR; } cpuset_force_rebuild(); } /* * On the other hand, an erroneous partition root may be transitioned * back to a regular one or a partition root with no CPU allocated * from the parent may change to erroneous. */ if (is_partition_root(parent) && ((cs->partition_root_state == PRS_ERROR) || !cpumask_intersects(&new_cpus, parent->subparts_cpus)) && update_parent_subparts_cpumask(cs, partcmd_update, NULL, tmp)) cpuset_force_rebuild(); update_tasks: cpus_updated = !cpumask_equal(&new_cpus, cs->effective_cpus); mems_updated = !nodes_equal(new_mems, cs->effective_mems); if (is_in_v2_mode()) hotplug_update_tasks(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); else hotplug_update_tasks_legacy(cs, &new_cpus, &new_mems, cpus_updated, mems_updated); percpu_up_write(&cpuset_rwsem); } /** * cpuset_hotplug_workfn - handle CPU/memory hotunplug for a cpuset * * This function is called after either CPU or memory configuration has * changed and updates cpuset accordingly. The top_cpuset is always * synchronized to cpu_active_mask and N_MEMORY, which is necessary in * order to make cpusets transparent (of no affect) on systems that are * actively using CPU hotplug but making no active use of cpusets. * * Non-root cpusets are only affected by offlining. If any CPUs or memory * nodes have been taken down, cpuset_hotplug_update_tasks() is invoked on * all descendants. * * Note that CPU offlining during suspend is ignored. We don't modify * cpusets across suspend/resume cycles at all. */ static void cpuset_hotplug_workfn(struct work_struct *work) { static cpumask_t new_cpus; static nodemask_t new_mems; bool cpus_updated, mems_updated; bool on_dfl = is_in_v2_mode(); struct tmpmasks tmp, *ptmp = NULL; if (on_dfl && !alloc_cpumasks(NULL, &tmp)) ptmp = &tmp; percpu_down_write(&cpuset_rwsem); /* fetch the available cpus/mems and find out which changed how */ cpumask_copy(&new_cpus, cpu_active_mask); new_mems = node_states[N_MEMORY]; /* * If subparts_cpus is populated, it is likely that the check below * will produce a false positive on cpus_updated when the cpu list * isn't changed. It is extra work, but it is better to be safe. */ cpus_updated = !cpumask_equal(top_cpuset.effective_cpus, &new_cpus); mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems); /* * In the rare case that hotplug removes all the cpus in subparts_cpus, * we assumed that cpus are updated. */ if (!cpus_updated && top_cpuset.nr_subparts_cpus) cpus_updated = true; /* synchronize cpus_allowed to cpu_active_mask */ if (cpus_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) cpumask_copy(top_cpuset.cpus_allowed, &new_cpus); /* * Make sure that CPUs allocated to child partitions * do not show up in effective_cpus. If no CPU is left, * we clear the subparts_cpus & let the child partitions * fight for the CPUs again. */ if (top_cpuset.nr_subparts_cpus) { if (cpumask_subset(&new_cpus, top_cpuset.subparts_cpus)) { top_cpuset.nr_subparts_cpus = 0; cpumask_clear(top_cpuset.subparts_cpus); } else { cpumask_andnot(&new_cpus, &new_cpus, top_cpuset.subparts_cpus); } } cpumask_copy(top_cpuset.effective_cpus, &new_cpus); spin_unlock_irq(&callback_lock); /* we don't mess with cpumasks of tasks in top_cpuset */ } /* synchronize mems_allowed to N_MEMORY */ if (mems_updated) { spin_lock_irq(&callback_lock); if (!on_dfl) top_cpuset.mems_allowed = new_mems; top_cpuset.effective_mems = new_mems; spin_unlock_irq(&callback_lock); update_tasks_nodemask(&top_cpuset); } percpu_up_write(&cpuset_rwsem); /* if cpus or mems changed, we need to propagate to descendants */ if (cpus_updated || mems_updated) { struct cpuset *cs; struct cgroup_subsys_state *pos_css; rcu_read_lock(); cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) { if (cs == &top_cpuset || !css_tryget_online(&cs->css)) continue; rcu_read_unlock(); cpuset_hotplug_update_tasks(cs, ptmp); rcu_read_lock(); css_put(&cs->css); } rcu_read_unlock(); } /* rebuild sched domains if cpus_allowed has changed */ if (cpus_updated || force_rebuild) { force_rebuild = false; rebuild_sched_domains(); } free_cpumasks(NULL, ptmp); } void cpuset_update_active_cpus(void) { /* * We're inside cpu hotplug critical region which usually nests * inside cgroup synchronization. Bounce actual hotplug processing * to a work item to avoid reverse locking order. */ schedule_work(&cpuset_hotplug_work); } void cpuset_wait_for_hotplug(void) { flush_work(&cpuset_hotplug_work); } /* * Keep top_cpuset.mems_allowed tracking node_states[N_MEMORY]. * Call this routine anytime after node_states[N_MEMORY] changes. * See cpuset_update_active_cpus() for CPU hotplug handling. */ static int cpuset_track_online_nodes(struct notifier_block *self, unsigned long action, void *arg) { schedule_work(&cpuset_hotplug_work); return NOTIFY_OK; } static struct notifier_block cpuset_track_online_nodes_nb = { .notifier_call = cpuset_track_online_nodes, .priority = 10, /* ??! */ }; /** * cpuset_init_smp - initialize cpus_allowed * * Description: Finish top cpuset after cpu, node maps are initialized */ void __init cpuset_init_smp(void) { /* * cpus_allowd/mems_allowed set to v2 values in the initial * cpuset_bind() call will be reset to v1 values in another * cpuset_bind() call when v1 cpuset is mounted. */ top_cpuset.old_mems_allowed = top_cpuset.mems_allowed; cpumask_copy(top_cpuset.effective_cpus, cpu_active_mask); top_cpuset.effective_mems = node_states[N_MEMORY]; register_hotmemory_notifier(&cpuset_track_online_nodes_nb); cpuset_migrate_mm_wq = alloc_ordered_workqueue("cpuset_migrate_mm", 0); BUG_ON(!cpuset_migrate_mm_wq); } /** * cpuset_cpus_allowed - return cpus_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->cpus_allowed. * @pmask: pointer to struct cpumask variable to receive cpus_allowed set. * * Description: Returns the cpumask_var_t cpus_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of cpu_online_mask, even if this means going outside the * tasks cpuset. **/ void cpuset_cpus_allowed(struct task_struct *tsk, struct cpumask *pmask) { unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_cpus(task_cs(tsk), pmask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); } /** * cpuset_cpus_allowed_fallback - final fallback before complete catastrophe. * @tsk: pointer to task_struct with which the scheduler is struggling * * Description: In the case that the scheduler cannot find an allowed cpu in * tsk->cpus_allowed, we fall back to task_cs(tsk)->cpus_allowed. In legacy * mode however, this value is the same as task_cs(tsk)->effective_cpus, * which will not contain a sane cpumask during cases such as cpu hotplugging. * This is the absolute last resort for the scheduler and it is only used if * _every_ other avenue has been traveled. **/ void cpuset_cpus_allowed_fallback(struct task_struct *tsk) { rcu_read_lock(); do_set_cpus_allowed(tsk, is_in_v2_mode() ? task_cs(tsk)->cpus_allowed : cpu_possible_mask); rcu_read_unlock(); /* * We own tsk->cpus_allowed, nobody can change it under us. * * But we used cs && cs->cpus_allowed lockless and thus can * race with cgroup_attach_task() or update_cpumask() and get * the wrong tsk->cpus_allowed. However, both cases imply the * subsequent cpuset_change_cpumask()->set_cpus_allowed_ptr() * which takes task_rq_lock(). * * If we are called after it dropped the lock we must see all * changes in tsk_cs()->cpus_allowed. Otherwise we can temporary * set any mask even if it is not right from task_cs() pov, * the pending set_cpus_allowed_ptr() will fix things. * * select_fallback_rq() will fix things ups and set cpu_possible_mask * if required. */ } void __init cpuset_init_current_mems_allowed(void) { nodes_setall(current->mems_allowed); } /** * cpuset_mems_allowed - return mems_allowed mask from a tasks cpuset. * @tsk: pointer to task_struct from which to obtain cpuset->mems_allowed. * * Description: Returns the nodemask_t mems_allowed of the cpuset * attached to the specified @tsk. Guaranteed to return some non-empty * subset of node_states[N_MEMORY], even if this means going outside the * tasks cpuset. **/ nodemask_t cpuset_mems_allowed(struct task_struct *tsk) { nodemask_t mask; unsigned long flags; spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); guarantee_online_mems(task_cs(tsk), &mask); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return mask; } /** * cpuset_nodemask_valid_mems_allowed - check nodemask vs. curremt mems_allowed * @nodemask: the nodemask to be checked * * Are any of the nodes in the nodemask allowed in current->mems_allowed? */ int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask) { return nodes_intersects(*nodemask, current->mems_allowed); } /* * nearest_hardwall_ancestor() - Returns the nearest mem_exclusive or * mem_hardwall ancestor to the specified cpuset. Call holding * callback_lock. If no ancestor is mem_exclusive or mem_hardwall * (an unusual configuration), then returns the root cpuset. */ static struct cpuset *nearest_hardwall_ancestor(struct cpuset *cs) { while (!(is_mem_exclusive(cs) || is_mem_hardwall(cs)) && parent_cs(cs)) cs = parent_cs(cs); return cs; } /** * cpuset_node_allowed - Can we allocate on a memory node? * @node: is this an allowed node? * @gfp_mask: memory allocation flags * * If we're in interrupt, yes, we can always allocate. If @node is set in * current's mems_allowed, yes. If it's not a __GFP_HARDWALL request and this * node is set in the nearest hardwalled cpuset ancestor to current's cpuset, * yes. If current has access to memory reserves as an oom victim, yes. * Otherwise, no. * * GFP_USER allocations are marked with the __GFP_HARDWALL bit, * and do not allow allocations outside the current tasks cpuset * unless the task has been OOM killed. * GFP_KERNEL allocations are not so marked, so can escape to the * nearest enclosing hardwalled ancestor cpuset. * * Scanning up parent cpusets requires callback_lock. The * __alloc_pages() routine only calls here with __GFP_HARDWALL bit * _not_ set if it's a GFP_KERNEL allocation, and all nodes in the * current tasks mems_allowed came up empty on the first pass over * the zonelist. So only GFP_KERNEL allocations, if all nodes in the * cpuset are short of memory, might require taking the callback_lock. * * The first call here from mm/page_alloc:get_page_from_freelist() * has __GFP_HARDWALL set in gfp_mask, enforcing hardwall cpusets, * so no allocation on a node outside the cpuset is allowed (unless * in interrupt, of course). * * The second pass through get_page_from_freelist() doesn't even call * here for GFP_ATOMIC calls. For those calls, the __alloc_pages() * variable 'wait' is not set, and the bit ALLOC_CPUSET is not set * in alloc_flags. That logic and the checks below have the combined * affect that: * in_interrupt - any node ok (current task context irrelevant) * GFP_ATOMIC - any node ok * tsk_is_oom_victim - any node ok * GFP_KERNEL - any node in enclosing hardwalled cpuset ok * GFP_USER - only nodes in current tasks mems allowed ok. */ bool __cpuset_node_allowed(int node, gfp_t gfp_mask) { struct cpuset *cs; /* current cpuset ancestors */ int allowed; /* is allocation in zone z allowed? */ unsigned long flags; if (in_interrupt()) return true; if (node_isset(node, current->mems_allowed)) return true; /* * Allow tasks that have access to memory reserves because they have * been OOM killed to get memory anywhere. */ if (unlikely(tsk_is_oom_victim(current))) return true; if (gfp_mask & __GFP_HARDWALL) /* If hardwall request, stop here */ return false; if (current->flags & PF_EXITING) /* Let dying task have memory */ return true; /* Not hardwall and node outside mems_allowed: scan up cpusets */ spin_lock_irqsave(&callback_lock, flags); rcu_read_lock(); cs = nearest_hardwall_ancestor(task_cs(current)); allowed = node_isset(node, cs->mems_allowed); rcu_read_unlock(); spin_unlock_irqrestore(&callback_lock, flags); return allowed; } /** * cpuset_mem_spread_node() - On which node to begin search for a file page * cpuset_slab_spread_node() - On which node to begin search for a slab page * * If a task is marked PF_SPREAD_PAGE or PF_SPREAD_SLAB (as for * tasks in a cpuset with is_spread_page or is_spread_slab set), * and if the memory allocation used cpuset_mem_spread_node() * to determine on which node to start looking, as it will for * certain page cache or slab cache pages such as used for file * system buffers and inode caches, then instead of starting on the * local node to look for a free page, rather spread the starting * node around the tasks mems_allowed nodes. * * We don't have to worry about the returned node being offline * because "it can't happen", and even if it did, it would be ok. * * The routines calling guarantee_online_mems() are careful to * only set nodes in task->mems_allowed that are online. So it * should not be possible for the following code to return an * offline node. But if it did, that would be ok, as this routine * is not returning the node where the allocation must be, only * the node where the search should start. The zonelist passed to * __alloc_pages() will include all nodes. If the slab allocator * is passed an offline node, it will fall back to the local node. * See kmem_cache_alloc_node(). */ static int cpuset_spread_node(int *rotor) { return *rotor = next_node_in(*rotor, current->mems_allowed); } int cpuset_mem_spread_node(void) { if (current->cpuset_mem_spread_rotor == NUMA_NO_NODE) current->cpuset_mem_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_mem_spread_rotor); } int cpuset_slab_spread_node(void) { if (current->cpuset_slab_spread_rotor == NUMA_NO_NODE) current->cpuset_slab_spread_rotor = node_random(¤t->mems_allowed); return cpuset_spread_node(¤t->cpuset_slab_spread_rotor); } EXPORT_SYMBOL_GPL(cpuset_mem_spread_node); /** * cpuset_mems_allowed_intersects - Does @tsk1's mems_allowed intersect @tsk2's? * @tsk1: pointer to task_struct of some task. * @tsk2: pointer to task_struct of some other task. * * Description: Return true if @tsk1's mems_allowed intersects the * mems_allowed of @tsk2. Used by the OOM killer to determine if * one of the task's memory usage might impact the memory available * to the other. **/ int cpuset_mems_allowed_intersects(const struct task_struct *tsk1, const struct task_struct *tsk2) { return nodes_intersects(tsk1->mems_allowed, tsk2->mems_allowed); } /** * cpuset_print_current_mems_allowed - prints current's cpuset and mems_allowed * * Description: Prints current's name, cpuset name, and cached copy of its * mems_allowed to the kernel log. */ void cpuset_print_current_mems_allowed(void) { struct cgroup *cgrp; rcu_read_lock(); cgrp = task_cs(current)->css.cgroup; pr_cont(",cpuset="); pr_cont_cgroup_name(cgrp); pr_cont(",mems_allowed=%*pbl", nodemask_pr_args(¤t->mems_allowed)); rcu_read_unlock(); } /* * Collection of memory_pressure is suppressed unless * this flag is enabled by writing "1" to the special * cpuset file 'memory_pressure_enabled' in the root cpuset. */ int cpuset_memory_pressure_enabled __read_mostly; /** * cpuset_memory_pressure_bump - keep stats of per-cpuset reclaims. * * Keep a running average of the rate of synchronous (direct) * page reclaim efforts initiated by tasks in each cpuset. * * This represents the rate at which some task in the cpuset * ran low on memory on all nodes it was allowed to use, and * had to enter the kernels page reclaim code in an effort to * create more free memory by tossing clean pages or swapping * or writing dirty pages. * * Display to user space in the per-cpuset read-only file * "memory_pressure". Value displayed is an integer * representing the recent rate of entry into the synchronous * (direct) page reclaim by any task attached to the cpuset. **/ void __cpuset_memory_pressure_bump(void) { rcu_read_lock(); fmeter_markevent(&task_cs(current)->fmeter); rcu_read_unlock(); } #ifdef CONFIG_PROC_PID_CPUSET /* * proc_cpuset_show() * - Print tasks cpuset path into seq_file. * - Used for /proc/<pid>/cpuset. * - No need to task_lock(tsk) on this tsk->cpuset reference, as it * doesn't really matter if tsk->cpuset changes after we read it, * and we take cpuset_mutex, keeping cpuset_attach() from changing it * anyway. */ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *tsk) { char *buf; struct cgroup_subsys_state *css; int retval; retval = -ENOMEM; buf = kmalloc(PATH_MAX, GFP_KERNEL); if (!buf) goto out; rcu_read_lock(); spin_lock_irq(&css_set_lock); css = task_css(tsk, cpuset_cgrp_id); retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX, current->nsproxy->cgroup_ns); spin_unlock_irq(&css_set_lock); rcu_read_unlock(); if (retval >= PATH_MAX) retval = -ENAMETOOLONG; if (retval < 0) goto out_free; seq_puts(m, buf); seq_putc(m, '\n'); retval = 0; out_free: kfree(buf); out: return retval; } #endif /* CONFIG_PROC_PID_CPUSET */ /* Display task mems_allowed in /proc/<pid>/status file. */ void cpuset_task_status_allowed(struct seq_file *m, struct task_struct *task) { seq_printf(m, "Mems_allowed:\t%*pb\n", nodemask_pr_args(&task->mems_allowed)); seq_printf(m, "Mems_allowed_list:\t%*pbl\n", nodemask_pr_args(&task->mems_allowed)); } |
| 143 143 143 141 141 136 136 14 14 13 9 4 13 13 5 5 3 3 4 4 4 24 1 23 5 12 11 9 4 14 14 14 5 80 2 77 79 79 79 77 74 74 74 74 74 88 88 88 76 76 76 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: GRE over IP protocol decoder. * * Authors: Alexey Kuznetsov (kuznet@ms2.inr.ac.ru) */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/netfilter_ipv4.h> #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/protocol.h> #include <net/ip_tunnels.h> #include <net/arp.h> #include <net/checksum.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> #include <net/dst_metadata.h> #include <net/erspan.h> /* Problems & solutions -------------------- 1. The most important issue is detecting local dead loops. They would cause complete host lockup in transmit, which would be "resolved" by stack overflow or, if queueing is enabled, with infinite looping in net_bh. We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), and silently drop packet when it expires. It is a good solution, but it supposes maintaining new variable in ALL skb, even if no tunneling is used. Current solution: xmit_recursion breaks dead loops. This is a percpu counter, since when we enter the first ndo_xmit(), cpu migration is forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, if we copy it from packet being encapsulated to upper header. It is very good solution, but it introduces two problems: - Routing protocols, using packets with ttl=1 (OSPF, RIP2), do not work over tunnels. - traceroute does not work. I planned to relay ICMP from tunnel, so that this problem would be solved and traceroute output would even more informative. This idea appeared to be wrong: only Linux complies to rfc1812 now (yes, guys, Linux is the only true router now :-)), all routers (at least, in neighbourhood of mine) return only 8 bytes of payload. It is the end. Hence, if we want that OSPF worked or traceroute said something reasonable, we should search for another solution. One of them is to parse packet trying to detect inner encapsulation made by our node. It is difficult or even impossible, especially, taking into account fragmentation. TO be short, ttl is not solution at all. Current solution: The solution was UNEXPECTEDLY SIMPLE. We force DF flag on tunnels with preconfigured hop limit, that is ALL. :-) Well, it does not remove the problem completely, but exponential growth of network traffic is changed to linear (branches, that exceed pmtu are pruned) and tunnel mtu rapidly degrades to value <68, where looping stops. Yes, it is not good if there exists a router in the loop, which does not force DF, even when encapsulating packets have DF set. But it is not our problem! Nobody could accuse us, we made all that we could make. Even if it is your gated who injected fatal route to network, even if it were you who configured fatal static route: you are innocent. :-) Alexey Kuznetsov. */ static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static struct rtnl_link_ops ipgre_link_ops __read_mostly; static int ipgre_tunnel_init(struct net_device *dev); static void erspan_build_header(struct sk_buff *skb, u32 id, u32 index, bool truncate, bool is_ipv4); static unsigned int ipgre_net_id __read_mostly; static unsigned int gre_tap_net_id __read_mostly; static unsigned int erspan_net_id __read_mostly; static int ipgre_err(struct sk_buff *skb, u32 info, const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. Moreover, Cisco "wise men" put GRE key to the third word in GRE header. It makes impossible maintaining even soft state for keyed GRE tunnels with enabled checksum. Tell them "thank you". Well, I wonder, rfc1812 was written by Cisco employee, what the hell these idiots break standards established by themselves??? */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; const struct iphdr *iph; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; unsigned int data_len = 0; struct ip_tunnel *t; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else if (tpi->proto == htons(ETH_P_ERSPAN) || tpi->proto == htons(ETH_P_ERSPAN2)) itn = net_generic(net, erspan_net_id); else itn = net_generic(net, ipgre_net_id); iph = (const struct iphdr *)(icmp_hdr(skb) + 1); t = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->daddr, iph->saddr, tpi->key); if (!t) return -ENOENT; switch (type) { default: case ICMP_PARAMETERPROB: return 0; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ return 0; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) return 0; data_len = icmp_hdr(skb)->un.reserved[1] * 4; /* RFC 4884 4.1 */ break; case ICMP_REDIRECT: break; } #if IS_ENABLED(CONFIG_IPV6) if (tpi->proto == htons(ETH_P_IPV6) && !ip6_err_gen_icmpv6_unreach(skb, iph->ihl * 4 + tpi->hdr_len, type, data_len)) return 0; #endif if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) return 0; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) return 0; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; return 0; } static void gre_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. * * Moreover, Cisco "wise men" put GRE key to the third word * in GRE header. It makes impossible maintaining even soft * state for keyed * GRE tunnels with enabled checksum. Tell them "thank you". * * Well, I wonder, rfc1812 was written by Cisco employee, * what the hell these idiots break standards established * by themselves??? */ const struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct tnl_ptk_info tpi; if (gre_parse_header(skb, &tpi, NULL, htons(ETH_P_IP), iph->ihl * 4) < 0) return; if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, dev_net(skb->dev), info, skb->dev->ifindex, IPPROTO_GRE); return; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, IPPROTO_GRE); return; } ipgre_err(skb, info, &tpi); } static bool is_erspan_type1(int gre_hdr_len) { /* Both ERSPAN type I (version 0) and type II (version 1) use * protocol 0x88BE, but the type I has only 4-byte GRE header, * while type II has 8-byte. */ return gre_hdr_len == 4; } static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, int gre_hdr_len) { struct net *net = dev_net(skb->dev); struct metadata_dst *tun_dst = NULL; struct erspan_base_hdr *ershdr; struct ip_tunnel_net *itn; struct ip_tunnel *tunnel; const struct iphdr *iph; struct erspan_md2 *md2; int ver; int len; itn = net_generic(net, erspan_net_id); iph = ip_hdr(skb); if (is_erspan_type1(gre_hdr_len)) { ver = 0; tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { if (unlikely(!pskb_may_pull(skb, gre_hdr_len + sizeof(*ershdr)))) return PACKET_REJECT; ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); } if (tunnel) { if (is_erspan_type1(gre_hdr_len)) len = gre_hdr_len; else len = gre_hdr_len + erspan_hdr_len(ver); if (unlikely(!pskb_may_pull(skb, len))) return PACKET_REJECT; if (__iptunnel_pull_header(skb, len, htons(ETH_P_TEB), false, false) < 0) goto drop; if (tunnel->collect_md) { struct erspan_metadata *pkt_md, *md; struct ip_tunnel_info *info; unsigned char *gh; __be64 tun_id; __be16 flags; tpi->flags |= TUNNEL_KEY; flags = tpi->flags; tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, sizeof(*md)); if (!tun_dst) return PACKET_REJECT; /* skb can be uncloned in __iptunnel_pull_header, so * old pkt_md is no longer valid and we need to reset * it */ gh = skb_network_header(skb) + skb_network_header_len(skb); pkt_md = (struct erspan_metadata *)(gh + gre_hdr_len + sizeof(*ershdr)); md = ip_tunnel_info_opts(&tun_dst->u.tun_info); md->version = ver; md2 = &md->u.md2; memcpy(md2, pkt_md, ver == 1 ? ERSPAN_V1_MDSIZE : ERSPAN_V2_MDSIZE); info = &tun_dst->u.tun_info; info->key.tun_flags |= TUNNEL_ERSPAN_OPT; info->options_len = sizeof(*md); } skb_reset_mac_header(skb); ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; drop: kfree_skb(skb); return PACKET_RCVD; } static int __ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct ip_tunnel_net *itn, int hdr_len, bool raw_proto) { struct metadata_dst *tun_dst = NULL; const struct iphdr *iph; struct ip_tunnel *tunnel; iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags, iph->saddr, iph->daddr, tpi->key); if (tunnel) { if (__iptunnel_pull_header(skb, hdr_len, tpi->proto, raw_proto, false) < 0) goto drop; if (tunnel->dev->type != ARPHRD_NONE) skb_pop_mac_header(skb); else skb_reset_mac_header(skb); if (tunnel->collect_md) { __be16 flags; __be64 tun_id; flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); tun_id = key32_to_tunnel_id(tpi->key); tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); if (!tun_dst) return PACKET_REJECT; } ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_NEXT; drop: kfree_skb(skb); return PACKET_RCVD; } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi, int hdr_len) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn; int res; if (tpi->proto == htons(ETH_P_TEB)) itn = net_generic(net, gre_tap_net_id); else itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, false); if (res == PACKET_NEXT && tpi->proto == htons(ETH_P_TEB)) { /* ipgre tunnels in collect metadata mode should receive * also ETH_P_TEB traffic. */ itn = net_generic(net, ipgre_net_id); res = __ipgre_rcv(skb, tpi, itn, hdr_len, true); } return res; } static int gre_rcv(struct sk_buff *skb) { struct tnl_ptk_info tpi; bool csum_err = false; int hdr_len; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { /* Looped back packet, drop it! */ if (rt_is_output_route(skb_rtable(skb))) goto drop; } #endif hdr_len = gre_parse_header(skb, &tpi, &csum_err, htons(ETH_P_IP), 0); if (hdr_len < 0) goto drop; if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { if (erspan_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; goto out; } if (ipgre_rcv(skb, &tpi, hdr_len) == PACKET_RCVD) return 0; out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); drop: kfree_skb(skb); return 0; } static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); __be16 flags = tunnel->parms.o_flags; /* Push GRE header. */ gre_build_header(skb, tunnel->tun_hlen, flags, proto, tunnel->parms.o_key, (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } static int gre_handle_offloads(struct sk_buff *skb, bool csum) { return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; int tunnel_hlen; __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) goto err_free_skb; flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); gre_build_header(skb, tunnel_hlen, flags, proto, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(atomic_fetch_inc(&tunnel->o_seqno)) : 0); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); dev->stats.tx_dropped++; } static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; bool truncate = false; __be16 proto; int tunnel_hlen; int version; int nhoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET)) goto err_free_skb; key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; if (tun_info->options_len < sizeof(*md)) goto err_free_skb; md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); if (skb_cow_head(skb, dev->needed_headroom)) goto err_free_skb; if (gre_handle_offloads(skb, false)) goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } nhoff = skb_network_offset(skb); if (skb->protocol == htons(ETH_P_IP) && (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; if (skb->protocol == htons(ETH_P_IPV6)) { int thoff; if (skb_transport_header_was_set(skb)) thoff = skb_transport_offset(skb); else thoff = nhoff + sizeof(struct ipv6hdr); if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) truncate = true; } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); proto = htons(ETH_P_ERSPAN); } else if (version == 2) { erspan_build_header_v2(skb, ntohl(tunnel_id_to_key32(key->tun_id)), md->u.md2.dir, get_hwid(&md->u.md2), truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto err_free_skb; } gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(atomic_fetch_inc(&tunnel->o_seqno))); ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); return; err_free_skb: kfree_skb(skb); dev->stats.tx_dropped++; } static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; key = &info->key; ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, tunnel_id_to_key32(key->tun_id), key->tos & ~INET_ECN_MASK, 0, skb->mark, skb_get_hash(skb)); rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); ip_rt_put(rt); info->key.u.ipv4.src = fl4.saddr; return 0; } static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, skb->protocol); return NETDEV_TX_OK; } if (dev->header_ops) { int pull_len = tunnel->hlen + sizeof(struct iphdr); if (skb_cow_head(skb, 0)) goto free_skb; if (!pskb_may_pull(skb, pull_len)) goto free_skb; tnl_params = (const struct iphdr *)skb->data; /* ip_tunnel_xmit() needs skb->data pointing to gre header. */ skb_pull(skb, pull_len); skb_reset_mac_header(skb); if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_start(skb) < skb->data) goto free_skb; } else { if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; tnl_params = &tunnel->parms.iph; } if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) goto free_skb; __gre_xmit(skb, dev, tnl_params, skb->protocol); return NETDEV_TX_OK; free_skb: kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static netdev_tx_t erspan_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); bool truncate = false; __be16 proto; if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { erspan_fb_xmit(skb, dev); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, false)) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { pskb_trim(skb, dev->mtu + dev->hard_header_len); truncate = true; } /* Push ERSPAN header */ if (tunnel->erspan_ver == 0) { proto = htons(ETH_P_ERSPAN); tunnel->parms.o_flags &= ~TUNNEL_SEQ; } else if (tunnel->erspan_ver == 1) { erspan_build_header(skb, ntohl(tunnel->parms.o_key), tunnel->index, truncate, true); proto = htons(ETH_P_ERSPAN); } else if (tunnel->erspan_ver == 2) { erspan_build_header_v2(skb, ntohl(tunnel->parms.o_key), tunnel->dir, tunnel->hwid, truncate, true); proto = htons(ETH_P_ERSPAN2); } else { goto free_skb; } tunnel->parms.o_flags &= ~TUNNEL_KEY; __gre_xmit(skb, dev, &tunnel->parms.iph, proto); return NETDEV_TX_OK; free_skb: kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (!pskb_inet_may_pull(skb)) goto free_skb; if (tunnel->collect_md) { gre_fb_xmit(skb, dev, htons(ETH_P_TEB)); return NETDEV_TX_OK; } if (gre_handle_offloads(skb, !!(tunnel->parms.o_flags & TUNNEL_CSUM))) goto free_skb; if (skb_cow_head(skb, dev->needed_headroom)) goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); return NETDEV_TX_OK; free_skb: kfree_skb(skb); dev->stats.tx_dropped++; return NETDEV_TX_OK; } static void ipgre_link_update(struct net_device *dev, bool set_mtu) { struct ip_tunnel *tunnel = netdev_priv(dev); int len; len = tunnel->tun_hlen; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); len = tunnel->tun_hlen - len; tunnel->hlen = tunnel->hlen + len; if (dev->header_ops) dev->hard_header_len += len; else dev->needed_headroom += len; if (set_mtu) dev->mtu = max_t(int, dev->mtu - len, 68); if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) { if (!(tunnel->parms.o_flags & TUNNEL_CSUM) || tunnel->encap.type == TUNNEL_ENCAP_NONE) { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } else { dev->features &= ~NETIF_F_GSO_SOFTWARE; dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; } dev->features |= NETIF_F_LLTX; } else { dev->hw_features &= ~NETIF_F_GSO_SOFTWARE; dev->features &= ~(NETIF_F_LLTX | NETIF_F_GSO_SOFTWARE); } } static int ipgre_tunnel_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) { struct ip_tunnel_parm p; int err; if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) return -EFAULT; if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p.iph.version != 4 || p.iph.protocol != IPPROTO_GRE || p.iph.ihl != 5 || (p.iph.frag_off & htons(~IP_DF)) || ((p.i_flags | p.o_flags) & (GRE_VERSION | GRE_ROUTING))) return -EINVAL; } p.i_flags = gre_flags_to_tnl_flags(p.i_flags); p.o_flags = gre_flags_to_tnl_flags(p.o_flags); err = ip_tunnel_ioctl(dev, &p, cmd); if (err) return err; if (cmd == SIOCCHGTUNNEL) { struct ip_tunnel *t = netdev_priv(dev); t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; if (strcmp(dev->rtnl_link_ops->kind, "erspan")) ipgre_link_update(dev, true); } p.i_flags = gre_tnl_flags_to_gre_flags(p.i_flags); p.o_flags = gre_tnl_flags_to_gre_flags(p.o_flags); if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) return -EFAULT; return 0; } /* Nice toy. Unfortunately, useless in real life :-) It allows to construct virtual multiprotocol broadcast "LAN" over the Internet, provided multicast routing is tuned. I have no idea was this bicycle invented before me, so that I had to set ARPHRD_IPGRE to a random value. I have an impression, that Cisco could make something similar, but this feature is apparently missing in IOS<=11.2(8). I set up 10.66.66/24 and fec0:6666:6666::0/96 as virtual networks with broadcast 224.66.66.66. If you have access to mbone, play with me :-) ping -t 255 224.66.66.66 If nobody answers, mbone does not work. ip tunnel add Universe mode gre remote 224.66.66.66 local <Your_real_addr> ttl 255 ip addr add 10.66.66.<somewhat>/24 dev Universe ifconfig Universe up ifconfig Universe add fe80::<Your_real_addr>/10 ifconfig Universe add fec0:6666:6666::<Your_real_addr>/96 ftp 10.66.66.66 ... ftp fec0:6666:6666::193.233.7.65 ... */ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph; struct gre_base_hdr *greh; iph = skb_push(skb, t->hlen + sizeof(*iph)); greh = (struct gre_base_hdr *)(iph+1); greh->flags = gre_tnl_flags_to_gre_flags(t->parms.o_flags); greh->protocol = htons(type); memcpy(iph, &t->parms.iph, sizeof(struct iphdr)); /* Set the source hardware address. */ if (saddr) memcpy(&iph->saddr, saddr, 4); if (daddr) memcpy(&iph->daddr, daddr, 4); if (iph->daddr) return t->hlen + sizeof(*iph); return -(t->hlen + sizeof(*iph)); } static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { const struct iphdr *iph = (const struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } static const struct header_ops ipgre_header_ops = { .create = ipgre_header, .parse = ipgre_header_parse, }; #ifdef CONFIG_NET_IPGRE_BROADCAST static int ipgre_open(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi4 fl4; struct rtable *rt; rt = ip_route_output_gre(t->net, &fl4, t->parms.iph.daddr, t->parms.iph.saddr, t->parms.o_key, RT_TOS(t->parms.iph.tos), t->parms.link); if (IS_ERR(rt)) return -EADDRNOTAVAIL; dev = rt->dst.dev; ip_rt_put(rt); if (!__in_dev_get_rtnl(dev)) return -EADDRNOTAVAIL; t->mlink = dev->ifindex; ip_mc_inc_group(__in_dev_get_rtnl(dev), t->parms.iph.daddr); } return 0; } static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(t->net, t->mlink); if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); } return 0; } #endif static const struct net_device_ops ipgre_netdev_ops = { .ndo_init = ipgre_tunnel_init, .ndo_uninit = ip_tunnel_uninit, #ifdef CONFIG_NET_IPGRE_BROADCAST .ndo_open = ipgre_open, .ndo_stop = ipgre_close, #endif .ndo_start_xmit = ipgre_xmit, .ndo_do_ioctl = ipgre_tunnel_ioctl, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, }; #define GRE_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_HW_CSUM) static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; dev->type = ARPHRD_IPGRE; ip_tunnel_setup(dev, ipgre_net_id); } static void __gre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel; tunnel = netdev_priv(dev); tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; dev->needed_headroom = tunnel->hlen + sizeof(tunnel->parms.iph); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; if (!(tunnel->parms.o_flags & TUNNEL_SEQ)) { /* TCP offload with GRE SEQ is not supported, nor * can we support 2 levels of outer headers requiring * an update. */ if (!(tunnel->parms.o_flags & TUNNEL_CSUM) || (tunnel->encap.type == TUNNEL_ENCAP_NONE)) { dev->features |= NETIF_F_GSO_SOFTWARE; dev->hw_features |= NETIF_F_GSO_SOFTWARE; } /* Can use a lockless transmit, unless we generate * output sequences */ dev->features |= NETIF_F_LLTX; } } static int ipgre_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; __gre_tunnel_init(dev); memcpy(dev->dev_addr, &iph->saddr, 4); memcpy(dev->broadcast, &iph->daddr, 4); dev->flags = IFF_NOARP; netif_keep_dst(dev); dev->addr_len = 4; if (iph->daddr && !tunnel->collect_md) { #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { if (!iph->saddr) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } #endif } else if (!tunnel->collect_md) { dev->header_ops = &ipgre_header_ops; dev->hard_header_len = tunnel->hlen + sizeof(*iph); dev->needed_headroom = 0; } return ip_tunnel_init(dev); } static const struct gre_protocol ipgre_protocol = { .handler = gre_rcv, .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) { return ip_tunnel_init_net(net, ipgre_net_id, &ipgre_link_ops, NULL); } static void __net_exit ipgre_exit_batch_net(struct list_head *list_net) { ip_tunnel_delete_nets(list_net, ipgre_net_id, &ipgre_link_ops); } static struct pernet_operations ipgre_net_ops = { .init = ipgre_init_net, .exit_batch = ipgre_exit_batch_net, .id = &ipgre_net_id, .size = sizeof(struct ip_tunnel_net), }; static int ipgre_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags; if (!data) return 0; flags = 0; if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (flags & (GRE_VERSION|GRE_ROUTING)) return -EINVAL; if (data[IFLA_GRE_COLLECT_METADATA] && data[IFLA_GRE_ENCAP_TYPE] && nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]) != TUNNEL_ENCAP_NONE) return -EINVAL; return 0; } static int ipgre_tap_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be32 daddr; if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) goto out; if (data[IFLA_GRE_REMOTE]) { memcpy(&daddr, nla_data(data[IFLA_GRE_REMOTE]), 4); if (!daddr) return -EINVAL; } out: return ipgre_tunnel_validate(tb, data, extack); } static int erspan_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { __be16 flags = 0; int ret; if (!data) return 0; ret = ipgre_tap_validate(tb, data, extack); if (ret) return ret; if (data[IFLA_GRE_ERSPAN_VER] && nla_get_u8(data[IFLA_GRE_ERSPAN_VER]) == 0) return 0; /* ERSPAN type II/III should only have GRE sequence and key flag */ if (data[IFLA_GRE_OFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_OFLAGS]); if (data[IFLA_GRE_IFLAGS]) flags |= nla_get_be16(data[IFLA_GRE_IFLAGS]); if (!data[IFLA_GRE_COLLECT_METADATA] && flags != (GRE_SEQ | GRE_KEY)) return -EINVAL; /* ERSPAN Session ID only has 10-bit. Since we reuse * 32-bit key field as ID, check it's range. */ if (data[IFLA_GRE_IKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_IKEY])) & ~ID_MASK)) return -EINVAL; if (data[IFLA_GRE_OKEY] && (ntohl(nla_get_be32(data[IFLA_GRE_OKEY])) & ~ID_MASK)) return -EINVAL; return 0; } static int ipgre_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); memset(parms, 0, sizeof(*parms)); parms->iph.protocol = IPPROTO_GRE; if (!data) return 0; if (data[IFLA_GRE_LINK]) parms->link = nla_get_u32(data[IFLA_GRE_LINK]); if (data[IFLA_GRE_IFLAGS]) parms->i_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_IFLAGS])); if (data[IFLA_GRE_OFLAGS]) parms->o_flags = gre_flags_to_tnl_flags(nla_get_be16(data[IFLA_GRE_OFLAGS])); if (data[IFLA_GRE_IKEY]) parms->i_key = nla_get_be32(data[IFLA_GRE_IKEY]); if (data[IFLA_GRE_OKEY]) parms->o_key = nla_get_be32(data[IFLA_GRE_OKEY]); if (data[IFLA_GRE_LOCAL]) parms->iph.saddr = nla_get_in_addr(data[IFLA_GRE_LOCAL]); if (data[IFLA_GRE_REMOTE]) parms->iph.daddr = nla_get_in_addr(data[IFLA_GRE_REMOTE]); if (data[IFLA_GRE_TTL]) parms->iph.ttl = nla_get_u8(data[IFLA_GRE_TTL]); if (data[IFLA_GRE_TOS]) parms->iph.tos = nla_get_u8(data[IFLA_GRE_TOS]); if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) { if (t->ignore_df) return -EINVAL; parms->iph.frag_off = htons(IP_DF); } if (data[IFLA_GRE_COLLECT_METADATA]) { t->collect_md = true; if (dev->type == ARPHRD_IPGRE) dev->type = ARPHRD_NONE; } if (data[IFLA_GRE_IGNORE_DF]) { if (nla_get_u8(data[IFLA_GRE_IGNORE_DF]) && (parms->iph.frag_off & htons(IP_DF))) return -EINVAL; t->ignore_df = !!nla_get_u8(data[IFLA_GRE_IGNORE_DF]); } if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); return 0; } static int erspan_netlink_parms(struct net_device *dev, struct nlattr *data[], struct nlattr *tb[], struct ip_tunnel_parm *parms, __u32 *fwmark) { struct ip_tunnel *t = netdev_priv(dev); int err; err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); if (err) return err; if (!data) return 0; if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); if (t->erspan_ver > 2) return -EINVAL; } if (t->erspan_ver == 1) { if (data[IFLA_GRE_ERSPAN_INDEX]) { t->index = nla_get_u32(data[IFLA_GRE_ERSPAN_INDEX]); if (t->index & ~INDEX_MASK) return -EINVAL; } } else if (t->erspan_ver == 2) { if (data[IFLA_GRE_ERSPAN_DIR]) { t->dir = nla_get_u8(data[IFLA_GRE_ERSPAN_DIR]); if (t->dir & ~(DIR_MASK >> DIR_OFFSET)) return -EINVAL; } if (data[IFLA_GRE_ERSPAN_HWID]) { t->hwid = nla_get_u16(data[IFLA_GRE_ERSPAN_HWID]); if (t->hwid & ~(HWID_MASK >> HWID_OFFSET)) return -EINVAL; } } return 0; } /* This function returns true when ENCAP attributes are present in the nl msg */ static bool ipgre_netlink_encap_parms(struct nlattr *data[], struct ip_tunnel_encap *ipencap) { bool ret = false; memset(ipencap, 0, sizeof(*ipencap)); if (!data) return ret; if (data[IFLA_GRE_ENCAP_TYPE]) { ret = true; ipencap->type = nla_get_u16(data[IFLA_GRE_ENCAP_TYPE]); } if (data[IFLA_GRE_ENCAP_FLAGS]) { ret = true; ipencap->flags = nla_get_u16(data[IFLA_GRE_ENCAP_FLAGS]); } if (data[IFLA_GRE_ENCAP_SPORT]) { ret = true; ipencap->sport = nla_get_be16(data[IFLA_GRE_ENCAP_SPORT]); } if (data[IFLA_GRE_ENCAP_DPORT]) { ret = true; ipencap->dport = nla_get_be16(data[IFLA_GRE_ENCAP_DPORT]); } return ret; } static int gre_tap_init(struct net_device *dev) { __gre_tunnel_init(dev); dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops gre_tap_netdev_ops = { .ndo_init = gre_tap_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = gre_tap_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static int erspan_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); if (tunnel->erspan_ver == 0) tunnel->tun_hlen = 4; /* 4-byte GRE hdr. */ else tunnel->tun_hlen = 8; /* 8-byte GRE hdr. */ tunnel->parms.iph.protocol = IPPROTO_GRE; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + erspan_hdr_len(tunnel->erspan_ver); dev->features |= GRE_FEATURES; dev->hw_features |= GRE_FEATURES; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); return ip_tunnel_init(dev); } static const struct net_device_ops erspan_netdev_ops = { .ndo_init = erspan_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = erspan_xmit, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = ip_tunnel_get_stats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_fill_metadata_dst = gre_fill_metadata_dst, }; static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &gre_tap_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, gre_tap_net_id); } static int ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { struct ip_tunnel_encap ipencap; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } return 0; } static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int erspan_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel_parm p; __u32 fwmark = 0; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; ipgre_link_update(dev, !tb[IFLA_MTU]); return 0; } static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; err = ipgre_newlink_encap_setup(dev, data); if (err) return err; err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; err = ip_tunnel_changelink(dev, tb, &p, fwmark); if (err < 0) return err; t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; return 0; } static size_t ipgre_get_size(const struct net_device *dev) { return /* IFLA_GRE_LINK */ nla_total_size(4) + /* IFLA_GRE_IFLAGS */ nla_total_size(2) + /* IFLA_GRE_OFLAGS */ nla_total_size(2) + /* IFLA_GRE_IKEY */ nla_total_size(4) + /* IFLA_GRE_OKEY */ nla_total_size(4) + /* IFLA_GRE_LOCAL */ nla_total_size(4) + /* IFLA_GRE_REMOTE */ nla_total_size(4) + /* IFLA_GRE_TTL */ nla_total_size(1) + /* IFLA_GRE_TOS */ nla_total_size(1) + /* IFLA_GRE_PMTUDISC */ nla_total_size(1) + /* IFLA_GRE_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_GRE_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_GRE_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_GRE_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_GRE_IGNORE_DF */ nla_total_size(1) + /* IFLA_GRE_FWMARK */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_INDEX */ nla_total_size(4) + /* IFLA_GRE_ERSPAN_VER */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_DIR */ nla_total_size(1) + /* IFLA_GRE_ERSPAN_HWID */ nla_total_size(2) + 0; } static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_parm *p = &t->parms; __be16 o_flags = p->o_flags; if (nla_put_u32(skb, IFLA_GRE_LINK, p->link) || nla_put_be16(skb, IFLA_GRE_IFLAGS, gre_tnl_flags_to_gre_flags(p->i_flags)) || nla_put_be16(skb, IFLA_GRE_OFLAGS, gre_tnl_flags_to_gre_flags(o_flags)) || nla_put_be32(skb, IFLA_GRE_IKEY, p->i_key) || nla_put_be32(skb, IFLA_GRE_OKEY, p->o_key) || nla_put_in_addr(skb, IFLA_GRE_LOCAL, p->iph.saddr) || nla_put_in_addr(skb, IFLA_GRE_REMOTE, p->iph.daddr) || nla_put_u8(skb, IFLA_GRE_TTL, p->iph.ttl) || nla_put_u8(skb, IFLA_GRE_TOS, p->iph.tos) || nla_put_u8(skb, IFLA_GRE_PMTUDISC, !!(p->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_GRE_FWMARK, t->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ENCAP_TYPE, t->encap.type) || nla_put_be16(skb, IFLA_GRE_ENCAP_SPORT, t->encap.sport) || nla_put_be16(skb, IFLA_GRE_ENCAP_DPORT, t->encap.dport) || nla_put_u16(skb, IFLA_GRE_ENCAP_FLAGS, t->encap.flags)) goto nla_put_failure; if (nla_put_u8(skb, IFLA_GRE_IGNORE_DF, t->ignore_df)) goto nla_put_failure; if (t->collect_md) { if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int erspan_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); if (t->erspan_ver <= 2) { if (t->erspan_ver != 0 && !t->collect_md) t->parms.o_flags |= TUNNEL_KEY; if (nla_put_u8(skb, IFLA_GRE_ERSPAN_VER, t->erspan_ver)) goto nla_put_failure; if (t->erspan_ver == 1) { if (nla_put_u32(skb, IFLA_GRE_ERSPAN_INDEX, t->index)) goto nla_put_failure; } else if (t->erspan_ver == 2) { if (nla_put_u8(skb, IFLA_GRE_ERSPAN_DIR, t->dir)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_GRE_ERSPAN_HWID, t->hwid)) goto nla_put_failure; } } return ipgre_fill_info(skb, dev); nla_put_failure: return -EMSGSIZE; } static void erspan_setup(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); ether_setup(dev); dev->max_mtu = 0; dev->netdev_ops = &erspan_netdev_ops; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; ip_tunnel_setup(dev, erspan_net_id); t->erspan_ver = 1; } static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_LINK] = { .type = NLA_U32 }, [IFLA_GRE_IFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_OFLAGS] = { .type = NLA_U16 }, [IFLA_GRE_IKEY] = { .type = NLA_U32 }, [IFLA_GRE_OKEY] = { .type = NLA_U32 }, [IFLA_GRE_LOCAL] = { .len = FIELD_SIZEOF(struct iphdr, saddr) }, [IFLA_GRE_REMOTE] = { .len = FIELD_SIZEOF(struct iphdr, daddr) }, [IFLA_GRE_TTL] = { .type = NLA_U8 }, [IFLA_GRE_TOS] = { .type = NLA_U8 }, [IFLA_GRE_PMTUDISC] = { .type = NLA_U8 }, [IFLA_GRE_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_GRE_IGNORE_DF] = { .type = NLA_U8 }, [IFLA_GRE_FWMARK] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_INDEX] = { .type = NLA_U32 }, [IFLA_GRE_ERSPAN_VER] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_DIR] = { .type = NLA_U8 }, [IFLA_GRE_ERSPAN_HWID] = { .type = NLA_U16 }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { .kind = "gre", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tunnel_setup, .validate = ipgre_tunnel_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .kind = "gretap", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipgre_tap_setup, .validate = ipgre_tap_validate, .newlink = ipgre_newlink, .changelink = ipgre_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct rtnl_link_ops erspan_link_ops __read_mostly = { .kind = "erspan", .maxtype = IFLA_GRE_MAX, .policy = ipgre_policy, .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, .newlink = erspan_newlink, .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = erspan_fill_info, .get_link_net = ip_tunnel_get_link_net, }; struct net_device *gretap_fb_dev_create(struct net *net, const char *name, u8 name_assign_type) { struct nlattr *tb[IFLA_MAX + 1]; struct net_device *dev; LIST_HEAD(list_kill); struct ip_tunnel *t; int err; memset(&tb, 0, sizeof(tb)); dev = rtnl_create_link(net, name, name_assign_type, &ipgre_tap_ops, tb, NULL); if (IS_ERR(dev)) return dev; /* Configure flow based GRE device. */ t = netdev_priv(dev); t->collect_md = true; err = ipgre_newlink(net, dev, tb, NULL, NULL); if (err < 0) { free_netdev(dev); return ERR_PTR(err); } /* openvswitch users expect packet sizes to be unrestricted, * so set the largest MTU we can. */ err = __ip_tunnel_change_mtu(dev, IP_MAX_MTU, false); if (err) goto out; err = rtnl_configure_link(dev, NULL); if (err < 0) goto out; return dev; out: ip_tunnel_dellink(dev, &list_kill); unregister_netdevice_many(&list_kill); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(gretap_fb_dev_create); static int __net_init ipgre_tap_init_net(struct net *net) { return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_batch_net(struct list_head *list_net) { ip_tunnel_delete_nets(list_net, gre_tap_net_id, &ipgre_tap_ops); } static struct pernet_operations ipgre_tap_net_ops = { .init = ipgre_tap_init_net, .exit_batch = ipgre_tap_exit_batch_net, .id = &gre_tap_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __net_init erspan_init_net(struct net *net) { return ip_tunnel_init_net(net, erspan_net_id, &erspan_link_ops, "erspan0"); } static void __net_exit erspan_exit_batch_net(struct list_head *net_list) { ip_tunnel_delete_nets(net_list, erspan_net_id, &erspan_link_ops); } static struct pernet_operations erspan_net_ops = { .init = erspan_init_net, .exit_batch = erspan_exit_batch_net, .id = &erspan_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipgre_init(void) { int err; pr_info("GRE over IPv4 tunneling driver\n"); err = register_pernet_device(&ipgre_net_ops); if (err < 0) return err; err = register_pernet_device(&ipgre_tap_net_ops); if (err < 0) goto pnet_tap_failed; err = register_pernet_device(&erspan_net_ops); if (err < 0) goto pnet_erspan_failed; err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; } err = rtnl_link_register(&ipgre_link_ops); if (err < 0) goto rtnl_link_failed; err = rtnl_link_register(&ipgre_tap_ops); if (err < 0) goto tap_ops_failed; err = rtnl_link_register(&erspan_link_ops); if (err < 0) goto erspan_link_failed; return 0; erspan_link_failed: rtnl_link_unregister(&ipgre_tap_ops); tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&erspan_net_ops); pnet_erspan_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_failed: unregister_pernet_device(&ipgre_net_ops); return err; } static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); rtnl_link_unregister(&erspan_link_ops); gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); unregister_pernet_device(&erspan_net_ops); } module_init(ipgre_init); module_exit(ipgre_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); MODULE_ALIAS_RTNL_LINK("erspan"); MODULE_ALIAS_NETDEV("gre0"); MODULE_ALIAS_NETDEV("gretap0"); MODULE_ALIAS_NETDEV("erspan0"); |
| 37 37 36 37 37 37 37 22 55 4 36 37 36 37 37 36 36 37 36 36 37 37 37 36 37 37 37 37 36 37 37 37 37 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 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/attr.c * * Copyright (C) 1991, 1992 Linus Torvalds * changes by Thomas Schoebel-Theuer */ #include <linux/export.h> #include <linux/time.h> #include <linux/mm.h> #include <linux/string.h> #include <linux/sched/signal.h> #include <linux/capability.h> #include <linux/fsnotify.h> #include <linux/fcntl.h> #include <linux/security.h> #include <linux/evm.h> #include <linux/ima.h> static bool chown_ok(const struct inode *inode, kuid_t uid) { if (uid_eq(current_fsuid(), inode->i_uid) && uid_eq(uid, inode->i_uid)) return true; if (capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return true; if (uid_eq(inode->i_uid, INVALID_UID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } static bool chgrp_ok(const struct inode *inode, kgid_t gid) { if (uid_eq(current_fsuid(), inode->i_uid) && (in_group_p(gid) || gid_eq(gid, inode->i_gid))) return true; if (capable_wrt_inode_uidgid(inode, CAP_CHOWN)) return true; if (gid_eq(inode->i_gid, INVALID_GID) && ns_capable(inode->i_sb->s_user_ns, CAP_CHOWN)) return true; return false; } /** * setattr_prepare - check if attribute changes to a dentry are allowed * @dentry: dentry to check * @attr: attributes to change * * Check if we are allowed to change the attributes contained in @attr * in the given dentry. This includes the normal unix access permission * checks, as well as checks for rlimits and others. The function also clears * SGID bit from mode if user is not allowed to set it. Also file capabilities * and IMA extended attributes are cleared if ATTR_KILL_PRIV is set. * * Should be called as the first thing in ->setattr implementations, * possibly after taking additional locks. */ int setattr_prepare(struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); unsigned int ia_valid = attr->ia_valid; /* * First check size constraints. These can't be overriden using * ATTR_FORCE. */ if (ia_valid & ATTR_SIZE) { int error = inode_newsize_ok(inode, attr->ia_size); if (error) return error; } /* If force is set do it anyway. */ if (ia_valid & ATTR_FORCE) goto kill_priv; /* Make sure a caller can chown. */ if ((ia_valid & ATTR_UID) && !chown_ok(inode, attr->ia_uid)) return -EPERM; /* Make sure caller can chgrp. */ if ((ia_valid & ATTR_GID) && !chgrp_ok(inode, attr->ia_gid)) return -EPERM; /* Make sure a caller can chmod. */ if (ia_valid & ATTR_MODE) { if (!inode_owner_or_capable(inode)) return -EPERM; /* Also check the setgid bit! */ if (!in_group_p((ia_valid & ATTR_GID) ? attr->ia_gid : inode->i_gid) && !capable_wrt_inode_uidgid(inode, CAP_FSETID)) attr->ia_mode &= ~S_ISGID; } /* Check for setting the inode time. */ if (ia_valid & (ATTR_MTIME_SET | ATTR_ATIME_SET | ATTR_TIMES_SET)) { if (!inode_owner_or_capable(inode)) return -EPERM; } kill_priv: /* User has permission for the change */ if (ia_valid & ATTR_KILL_PRIV) { int error; error = security_inode_killpriv(dentry); if (error) return error; } return 0; } EXPORT_SYMBOL(setattr_prepare); /** * inode_newsize_ok - may this inode be truncated to a given size * @inode: the inode to be truncated * @offset: the new size to assign to the inode * * inode_newsize_ok must be called with i_mutex held. * * inode_newsize_ok will check filesystem limits and ulimits to check that the * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ * when necessary. Caller must not proceed with inode size change if failure is * returned. @inode must be a file (not directory), with appropriate * permissions to allow truncate (inode_newsize_ok does NOT check these * conditions). * * Return: 0 on success, -ve errno on failure */ int inode_newsize_ok(const struct inode *inode, loff_t offset) { if (offset < 0) return -EINVAL; if (inode->i_size < offset) { unsigned long limit; limit = rlimit(RLIMIT_FSIZE); if (limit != RLIM_INFINITY && offset > limit) goto out_sig; if (offset > inode->i_sb->s_maxbytes) goto out_big; } else { /* * truncation of in-use swapfiles is disallowed - it would * cause subsequent swapout to scribble on the now-freed * blocks. */ if (IS_SWAPFILE(inode)) return -ETXTBSY; } return 0; out_sig: send_sig(SIGXFSZ, current, 0); out_big: return -EFBIG; } EXPORT_SYMBOL(inode_newsize_ok); /** * setattr_copy - copy simple metadata updates into the generic inode * @inode: the inode to be updated * @attr: the new attributes * * setattr_copy must be called with i_mutex held. * * setattr_copy updates the inode's metadata with that specified * in attr. Noticeably missing is inode size update, which is more complex * as it requires pagecache updates. * * The inode is not marked as dirty after this operation. The rationale is * that for "simple" filesystems, the struct inode is the inode storage. * The caller is free to mark the inode dirty afterwards if needed. */ void setattr_copy(struct inode *inode, const struct iattr *attr) { unsigned int ia_valid = attr->ia_valid; if (ia_valid & ATTR_UID) inode->i_uid = attr->ia_uid; if (ia_valid & ATTR_GID) inode->i_gid = attr->ia_gid; if (ia_valid & ATTR_ATIME) inode->i_atime = attr->ia_atime; if (ia_valid & ATTR_MTIME) inode->i_mtime = attr->ia_mtime; if (ia_valid & ATTR_CTIME) inode->i_ctime = attr->ia_ctime; if (ia_valid & ATTR_MODE) { umode_t mode = attr->ia_mode; if (!in_group_p(inode->i_gid) && !capable_wrt_inode_uidgid(inode, CAP_FSETID)) mode &= ~S_ISGID; inode->i_mode = mode; } } EXPORT_SYMBOL(setattr_copy); /** * notify_change - modify attributes of a filesytem object * @dentry: object affected * @attr: new attributes * @delegated_inode: returns inode, if the inode is delegated * * The caller must hold the i_mutex on the affected object. * * If notify_change discovers a delegation in need of breaking, * it will return -EWOULDBLOCK and return a reference to the inode in * delegated_inode. The caller should then break the delegation and * retry. Because breaking a delegation may take a long time, the * caller should drop the i_mutex before doing so. * * Alternatively, a caller may pass NULL for delegated_inode. This may * be appropriate for callers that expect the underlying filesystem not * to be NFS exported. Also, passing NULL is fine for callers holding * the file open for write, as there can be no conflicting delegation in * that case. */ int notify_change(struct dentry * dentry, struct iattr * attr, struct inode **delegated_inode) { struct inode *inode = dentry->d_inode; umode_t mode = inode->i_mode; int error; struct timespec64 now; unsigned int ia_valid = attr->ia_valid; WARN_ON_ONCE(!inode_is_locked(inode)); if (ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID | ATTR_TIMES_SET)) { if (IS_IMMUTABLE(inode) || IS_APPEND(inode)) return -EPERM; } /* * If utimes(2) and friends are called with times == NULL (or both * times are UTIME_NOW), then we need to check for write permission */ if (ia_valid & ATTR_TOUCH) { if (IS_IMMUTABLE(inode)) return -EPERM; if (!inode_owner_or_capable(inode)) { error = inode_permission(inode, MAY_WRITE); if (error) return error; } } if ((ia_valid & ATTR_MODE)) { /* * Don't allow changing the mode of symlinks: * * (1) The vfs doesn't take the mode of symlinks into account * during permission checking. * (2) This has never worked correctly. Most major filesystems * did return EOPNOTSUPP due to interactions with POSIX ACLs * but did still updated the mode of the symlink. * This inconsistency led system call wrapper providers such * as libc to block changing the mode of symlinks with * EOPNOTSUPP already. * (3) To even do this in the first place one would have to use * specific file descriptors and quite some effort. */ if (S_ISLNK(inode->i_mode)) return -EOPNOTSUPP; /* Flag setting protected by i_mutex */ if (is_sxid(attr->ia_mode)) inode->i_flags &= ~S_NOSEC; } now = current_time(inode); attr->ia_ctime = now; if (!(ia_valid & ATTR_ATIME_SET)) attr->ia_atime = now; else attr->ia_atime = timestamp_truncate(attr->ia_atime, inode); if (!(ia_valid & ATTR_MTIME_SET)) attr->ia_mtime = now; else attr->ia_mtime = timestamp_truncate(attr->ia_mtime, inode); if (ia_valid & ATTR_KILL_PRIV) { error = security_inode_need_killpriv(dentry); if (error < 0) return error; if (error == 0) ia_valid = attr->ia_valid &= ~ATTR_KILL_PRIV; } /* * We now pass ATTR_KILL_S*ID to the lower level setattr function so * that the function has the ability to reinterpret a mode change * that's due to these bits. This adds an implicit restriction that * no function will ever call notify_change with both ATTR_MODE and * ATTR_KILL_S*ID set. */ if ((ia_valid & (ATTR_KILL_SUID|ATTR_KILL_SGID)) && (ia_valid & ATTR_MODE)) BUG(); if (ia_valid & ATTR_KILL_SUID) { if (mode & S_ISUID) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = (inode->i_mode & ~S_ISUID); } } if (ia_valid & ATTR_KILL_SGID) { if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { if (!(ia_valid & ATTR_MODE)) { ia_valid = attr->ia_valid |= ATTR_MODE; attr->ia_mode = inode->i_mode; } attr->ia_mode &= ~S_ISGID; } } if (!(attr->ia_valid & ~(ATTR_KILL_SUID | ATTR_KILL_SGID))) return 0; /* * Verify that uid/gid changes are valid in the target * namespace of the superblock. */ if (ia_valid & ATTR_UID && !kuid_has_mapping(inode->i_sb->s_user_ns, attr->ia_uid)) return -EOVERFLOW; if (ia_valid & ATTR_GID && !kgid_has_mapping(inode->i_sb->s_user_ns, attr->ia_gid)) return -EOVERFLOW; /* Don't allow modifications of files with invalid uids or * gids unless those uids & gids are being made valid. */ if (!(ia_valid & ATTR_UID) && !uid_valid(inode->i_uid)) return -EOVERFLOW; if (!(ia_valid & ATTR_GID) && !gid_valid(inode->i_gid)) return -EOVERFLOW; error = security_inode_setattr(dentry, attr); if (error) return error; error = try_break_deleg(inode, delegated_inode); if (error) return error; if (inode->i_op->setattr) error = inode->i_op->setattr(dentry, attr); else error = simple_setattr(dentry, attr); if (!error) { fsnotify_change(dentry, ia_valid); ima_inode_post_setattr(dentry); evm_inode_post_setattr(dentry, ia_valid); } return error; } EXPORT_SYMBOL(notify_change); |
| 51 51 50 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 | // SPDX-License-Identifier: GPL-2.0 #include <linux/cache.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/pid_namespace.h> #include "internal.h" /* * /proc/self: */ static const char *proc_self_get_link(struct dentry *dentry, struct inode *inode, struct delayed_call *done) { struct pid_namespace *ns = proc_pid_ns(inode); pid_t tgid = task_tgid_nr_ns(current, ns); char *name; /* * Not currently supported. Once we can inherit all of struct pid, * we can allow this. */ if (current->flags & PF_KTHREAD) return ERR_PTR(-EOPNOTSUPP); if (!tgid) return ERR_PTR(-ENOENT); /* max length of unsigned int in decimal + NULL term */ name = kmalloc(10 + 1, dentry ? GFP_KERNEL : GFP_ATOMIC); if (unlikely(!name)) return dentry ? ERR_PTR(-ENOMEM) : ERR_PTR(-ECHILD); sprintf(name, "%u", tgid); set_delayed_call(done, kfree_link, name); return name; } static const struct inode_operations proc_self_inode_operations = { .get_link = proc_self_get_link, }; static unsigned self_inum __ro_after_init; int proc_setup_self(struct super_block *s) { struct inode *root_inode = d_inode(s->s_root); struct pid_namespace *ns = proc_pid_ns(root_inode); struct dentry *self; int ret = -ENOMEM; inode_lock(root_inode); self = d_alloc_name(s->s_root, "self"); if (self) { struct inode *inode = new_inode(s); if (inode) { inode->i_ino = self_inum; inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode); inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_uid = GLOBAL_ROOT_UID; inode->i_gid = GLOBAL_ROOT_GID; inode->i_op = &proc_self_inode_operations; d_add(self, inode); ret = 0; } else { dput(self); } } inode_unlock(root_inode); if (ret) pr_err("proc_fill_super: can't allocate /proc/self\n"); else ns->proc_self = self; return ret; } void __init proc_self_init(void) { proc_alloc_inum(&self_inum); } |
| 12 12 6 1942 1943 1945 1950 2 507 507 414 1931 1948 413 505 95 95 91 1196 1201 413 420 6 6 3 58 58 15 15 16 16 12 3 9 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/user_namespace.h> #include <linux/proc_ns.h> #include <linux/highuid.h> #include <linux/cred.h> #include <linux/securebits.h> #include <linux/keyctl.h> #include <linux/key-type.h> #include <keys/user-type.h> #include <linux/seq_file.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/ctype.h> #include <linux/projid.h> #include <linux/fs_struct.h> #include <linux/bsearch.h> #include <linux/sort.h> static struct kmem_cache *user_ns_cachep __read_mostly; static DEFINE_MUTEX(userns_state_mutex); static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *map); static void free_user_ns(struct work_struct *work); static struct ucounts *inc_user_namespaces(struct user_namespace *ns, kuid_t uid) { return inc_ucount(ns, uid, UCOUNT_USER_NAMESPACES); } static void dec_user_namespaces(struct ucounts *ucounts) { return dec_ucount(ucounts, UCOUNT_USER_NAMESPACES); } static void set_cred_user_ns(struct cred *cred, struct user_namespace *user_ns) { /* Start with the same capabilities as init but useless for doing * anything as the capabilities are bound to the new user namespace. */ cred->securebits = SECUREBITS_DEFAULT; cred->cap_inheritable = CAP_EMPTY_SET; cred->cap_permitted = CAP_FULL_SET; cred->cap_effective = CAP_FULL_SET; cred->cap_ambient = CAP_EMPTY_SET; cred->cap_bset = CAP_FULL_SET; #ifdef CONFIG_KEYS key_put(cred->request_key_auth); cred->request_key_auth = NULL; #endif /* tgcred will be cleared in our caller bc CLONE_THREAD won't be set */ cred->user_ns = user_ns; } /* * Create a new user namespace, deriving the creator from the user in the * passed credentials, and replacing that user with the new root user for the * new namespace. * * This is called by copy_creds(), which will finish setting the target task's * credentials. */ int create_user_ns(struct cred *new) { struct user_namespace *ns, *parent_ns = new->user_ns; kuid_t owner = new->euid; kgid_t group = new->egid; struct ucounts *ucounts; int ret, i; ret = -ENOSPC; if (parent_ns->level > 32) goto fail; ucounts = inc_user_namespaces(parent_ns, owner); if (!ucounts) goto fail; /* * Verify that we can not violate the policy of which files * may be accessed that is specified by the root directory, * by verifing that the root directory is at the root of the * mount namespace which allows all files to be accessed. */ ret = -EPERM; if (current_chrooted()) goto fail_dec; /* The creator needs a mapping in the parent user namespace * or else we won't be able to reasonably tell userspace who * created a user_namespace. */ ret = -EPERM; if (!kuid_has_mapping(parent_ns, owner) || !kgid_has_mapping(parent_ns, group)) goto fail_dec; ret = -ENOMEM; ns = kmem_cache_zalloc(user_ns_cachep, GFP_KERNEL); if (!ns) goto fail_dec; ret = ns_alloc_inum(&ns->ns); if (ret) goto fail_free; ns->ns.ops = &userns_operations; atomic_set(&ns->count, 1); /* Leave the new->user_ns reference with the new user namespace. */ ns->parent = parent_ns; ns->level = parent_ns->level + 1; ns->owner = owner; ns->group = group; INIT_WORK(&ns->work, free_user_ns); for (i = 0; i < UCOUNT_COUNTS; i++) { ns->ucount_max[i] = INT_MAX; } ns->ucounts = ucounts; /* Inherit USERNS_SETGROUPS_ALLOWED from our parent */ mutex_lock(&userns_state_mutex); ns->flags = parent_ns->flags; mutex_unlock(&userns_state_mutex); #ifdef CONFIG_KEYS INIT_LIST_HEAD(&ns->keyring_name_list); init_rwsem(&ns->keyring_sem); #endif ret = -ENOMEM; if (!setup_userns_sysctls(ns)) goto fail_keyring; set_cred_user_ns(new, ns); return 0; fail_keyring: #ifdef CONFIG_PERSISTENT_KEYRINGS key_put(ns->persistent_keyring_register); #endif ns_free_inum(&ns->ns); fail_free: kmem_cache_free(user_ns_cachep, ns); fail_dec: dec_user_namespaces(ucounts); fail: return ret; } int unshare_userns(unsigned long unshare_flags, struct cred **new_cred) { struct cred *cred; int err = -ENOMEM; if (!(unshare_flags & CLONE_NEWUSER)) return 0; cred = prepare_creds(); if (cred) { err = create_user_ns(cred); if (err) put_cred(cred); else *new_cred = cred; } return err; } static void free_user_ns(struct work_struct *work) { struct user_namespace *parent, *ns = container_of(work, struct user_namespace, work); do { struct ucounts *ucounts = ns->ucounts; parent = ns->parent; if (ns->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->gid_map.forward); kfree(ns->gid_map.reverse); } if (ns->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->uid_map.forward); kfree(ns->uid_map.reverse); } if (ns->projid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(ns->projid_map.forward); kfree(ns->projid_map.reverse); } retire_userns_sysctls(ns); key_free_user_ns(ns); ns_free_inum(&ns->ns); kmem_cache_free(user_ns_cachep, ns); dec_user_namespaces(ucounts); ns = parent; } while (atomic_dec_and_test(&parent->count)); } void __put_user_ns(struct user_namespace *ns) { schedule_work(&ns->work); } EXPORT_SYMBOL(__put_user_ns); /** * idmap_key struct holds the information necessary to find an idmapping in a * sorted idmap array. It is passed to cmp_map_id() as first argument. */ struct idmap_key { bool map_up; /* true -> id from kid; false -> kid from id */ u32 id; /* id to find */ u32 count; /* == 0 unless used with map_id_range_down() */ }; /** * cmp_map_id - Function to be passed to bsearch() to find the requested * idmapping. Expects struct idmap_key to be passed via @k. */ static int cmp_map_id(const void *k, const void *e) { u32 first, last, id2; const struct idmap_key *key = k; const struct uid_gid_extent *el = e; id2 = key->id + key->count - 1; /* handle map_id_{down,up}() */ if (key->map_up) first = el->lower_first; else first = el->first; last = first + el->count - 1; if (key->id >= first && key->id <= last && (id2 >= first && id2 <= last)) return 0; if (key->id < first || id2 < first) return -1; return 1; } /** * map_id_range_down_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_max(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { struct idmap_key key; key.map_up = false; key.count = count; key.id = id; return bsearch(&key, map->forward, extents, sizeof(struct uid_gid_extent), cmp_map_id); } /** * map_id_range_down_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_range_down_base(unsigned extents, struct uid_gid_map *map, u32 id, u32 count) { unsigned idx; u32 first, last, id2; id2 = id + count - 1; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last && (id2 >= first && id2 <= last)) return &map->extent[idx]; } return NULL; } static u32 map_id_range_down(struct uid_gid_map *map, u32 id, u32 count) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_range_down_base(extents, map, id, count); else extent = map_id_range_down_max(extents, map, id, count); /* Map the id or note failure */ if (extent) id = (id - extent->first) + extent->lower_first; else id = (u32) -1; return id; } static u32 map_id_down(struct uid_gid_map *map, u32 id) { return map_id_range_down(map, id, 1); } /** * map_id_up_base - Find idmap via binary search in static extent array. * Can only be called if number of mappings is equal or less than * UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_base(unsigned extents, struct uid_gid_map *map, u32 id) { unsigned idx; u32 first, last; /* Find the matching extent */ for (idx = 0; idx < extents; idx++) { first = map->extent[idx].lower_first; last = first + map->extent[idx].count - 1; if (id >= first && id <= last) return &map->extent[idx]; } return NULL; } /** * map_id_up_max - Find idmap via binary search in ordered idmap array. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static struct uid_gid_extent * map_id_up_max(unsigned extents, struct uid_gid_map *map, u32 id) { struct idmap_key key; key.map_up = true; key.count = 1; key.id = id; return bsearch(&key, map->reverse, extents, sizeof(struct uid_gid_extent), cmp_map_id); } static u32 map_id_up(struct uid_gid_map *map, u32 id) { struct uid_gid_extent *extent; unsigned extents = map->nr_extents; smp_rmb(); if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) extent = map_id_up_base(extents, map, id); else extent = map_id_up_max(extents, map, id); /* Map the id or note failure */ if (extent) id = (id - extent->lower_first) + extent->first; else id = (u32) -1; return id; } /** * make_kuid - Map a user-namespace uid pair into a kuid. * @ns: User namespace that the uid is in * @uid: User identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace uid * pair INVALID_UID is returned. Callers are expected to test * for and handle INVALID_UID being returned. INVALID_UID * may be tested for using uid_valid(). */ kuid_t make_kuid(struct user_namespace *ns, uid_t uid) { /* Map the uid to a global kernel uid */ return KUIDT_INIT(map_id_down(&ns->uid_map, uid)); } EXPORT_SYMBOL(make_kuid); /** * from_kuid - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * If @kuid has no mapping in @targ (uid_t)-1 is returned. */ uid_t from_kuid(struct user_namespace *targ, kuid_t kuid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->uid_map, __kuid_val(kuid)); } EXPORT_SYMBOL(from_kuid); /** * from_kuid_munged - Create a uid from a kuid user-namespace pair. * @targ: The user namespace we want a uid in. * @kuid: The kernel internal uid to start with. * * Map @kuid into the user-namespace specified by @targ and * return the resulting uid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kuid from_kuid_munged never fails and always * returns a valid uid. This makes from_kuid_munged appropriate * for use in syscalls like stat and getuid where failing the * system call and failing to provide a valid uid are not an * options. * * If @kuid has no mapping in @targ overflowuid is returned. */ uid_t from_kuid_munged(struct user_namespace *targ, kuid_t kuid) { uid_t uid; uid = from_kuid(targ, kuid); if (uid == (uid_t) -1) uid = overflowuid; return uid; } EXPORT_SYMBOL(from_kuid_munged); /** * make_kgid - Map a user-namespace gid pair into a kgid. * @ns: User namespace that the gid is in * @gid: group identifier * * Maps a user-namespace gid pair into a kernel internal kgid, * and returns that kgid. * * When there is no mapping defined for the user-namespace gid * pair INVALID_GID is returned. Callers are expected to test * for and handle INVALID_GID being returned. INVALID_GID may be * tested for using gid_valid(). */ kgid_t make_kgid(struct user_namespace *ns, gid_t gid) { /* Map the gid to a global kernel gid */ return KGIDT_INIT(map_id_down(&ns->gid_map, gid)); } EXPORT_SYMBOL(make_kgid); /** * from_kgid - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * If @kgid has no mapping in @targ (gid_t)-1 is returned. */ gid_t from_kgid(struct user_namespace *targ, kgid_t kgid) { /* Map the gid from a global kernel gid */ return map_id_up(&targ->gid_map, __kgid_val(kgid)); } EXPORT_SYMBOL(from_kgid); /** * from_kgid_munged - Create a gid from a kgid user-namespace pair. * @targ: The user namespace we want a gid in. * @kgid: The kernel internal gid to start with. * * Map @kgid into the user-namespace specified by @targ and * return the resulting gid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kgid from_kgid_munged never fails and always * returns a valid gid. This makes from_kgid_munged appropriate * for use in syscalls like stat and getgid where failing the * system call and failing to provide a valid gid are not options. * * If @kgid has no mapping in @targ overflowgid is returned. */ gid_t from_kgid_munged(struct user_namespace *targ, kgid_t kgid) { gid_t gid; gid = from_kgid(targ, kgid); if (gid == (gid_t) -1) gid = overflowgid; return gid; } EXPORT_SYMBOL(from_kgid_munged); /** * make_kprojid - Map a user-namespace projid pair into a kprojid. * @ns: User namespace that the projid is in * @projid: Project identifier * * Maps a user-namespace uid pair into a kernel internal kuid, * and returns that kuid. * * When there is no mapping defined for the user-namespace projid * pair INVALID_PROJID is returned. Callers are expected to test * for and handle handle INVALID_PROJID being returned. INVALID_PROJID * may be tested for using projid_valid(). */ kprojid_t make_kprojid(struct user_namespace *ns, projid_t projid) { /* Map the uid to a global kernel uid */ return KPROJIDT_INIT(map_id_down(&ns->projid_map, projid)); } EXPORT_SYMBOL(make_kprojid); /** * from_kprojid - Create a projid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal project identifier to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * If @kprojid has no mapping in @targ (projid_t)-1 is returned. */ projid_t from_kprojid(struct user_namespace *targ, kprojid_t kprojid) { /* Map the uid from a global kernel uid */ return map_id_up(&targ->projid_map, __kprojid_val(kprojid)); } EXPORT_SYMBOL(from_kprojid); /** * from_kprojid_munged - Create a projiid from a kprojid user-namespace pair. * @targ: The user namespace we want a projid in. * @kprojid: The kernel internal projid to start with. * * Map @kprojid into the user-namespace specified by @targ and * return the resulting projid. * * There is always a mapping into the initial user_namespace. * * Unlike from_kprojid from_kprojid_munged never fails and always * returns a valid projid. This makes from_kprojid_munged * appropriate for use in syscalls like stat and where * failing the system call and failing to provide a valid projid are * not an options. * * If @kprojid has no mapping in @targ OVERFLOW_PROJID is returned. */ projid_t from_kprojid_munged(struct user_namespace *targ, kprojid_t kprojid) { projid_t projid; projid = from_kprojid(targ, kprojid); if (projid == (projid_t) -1) projid = OVERFLOW_PROJID; return projid; } EXPORT_SYMBOL(from_kprojid_munged); static int uid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; uid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kuid(lower_ns, KUIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int gid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; gid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kgid(lower_ns, KGIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static int projid_m_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; struct uid_gid_extent *extent = v; struct user_namespace *lower_ns; projid_t lower; lower_ns = seq_user_ns(seq); if ((lower_ns == ns) && lower_ns->parent) lower_ns = lower_ns->parent; lower = from_kprojid(lower_ns, KPROJIDT_INIT(extent->lower_first)); seq_printf(seq, "%10u %10u %10u\n", extent->first, lower, extent->count); return 0; } static void *m_start(struct seq_file *seq, loff_t *ppos, struct uid_gid_map *map) { loff_t pos = *ppos; unsigned extents = map->nr_extents; smp_rmb(); if (pos >= extents) return NULL; if (extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return &map->extent[pos]; return &map->forward[pos]; } static void *uid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->uid_map); } static void *gid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->gid_map); } static void *projid_m_start(struct seq_file *seq, loff_t *ppos) { struct user_namespace *ns = seq->private; return m_start(seq, ppos, &ns->projid_map); } static void *m_next(struct seq_file *seq, void *v, loff_t *pos) { (*pos)++; return seq->op->start(seq, pos); } static void m_stop(struct seq_file *seq, void *v) { return; } const struct seq_operations proc_uid_seq_operations = { .start = uid_m_start, .stop = m_stop, .next = m_next, .show = uid_m_show, }; const struct seq_operations proc_gid_seq_operations = { .start = gid_m_start, .stop = m_stop, .next = m_next, .show = gid_m_show, }; const struct seq_operations proc_projid_seq_operations = { .start = projid_m_start, .stop = m_stop, .next = m_next, .show = projid_m_show, }; static bool mappings_overlap(struct uid_gid_map *new_map, struct uid_gid_extent *extent) { u32 upper_first, lower_first, upper_last, lower_last; unsigned idx; upper_first = extent->first; lower_first = extent->lower_first; upper_last = upper_first + extent->count - 1; lower_last = lower_first + extent->count - 1; for (idx = 0; idx < new_map->nr_extents; idx++) { u32 prev_upper_first, prev_lower_first; u32 prev_upper_last, prev_lower_last; struct uid_gid_extent *prev; if (new_map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) prev = &new_map->extent[idx]; else prev = &new_map->forward[idx]; prev_upper_first = prev->first; prev_lower_first = prev->lower_first; prev_upper_last = prev_upper_first + prev->count - 1; prev_lower_last = prev_lower_first + prev->count - 1; /* Does the upper range intersect a previous extent? */ if ((prev_upper_first <= upper_last) && (prev_upper_last >= upper_first)) return true; /* Does the lower range intersect a previous extent? */ if ((prev_lower_first <= lower_last) && (prev_lower_last >= lower_first)) return true; } return false; } /** * insert_extent - Safely insert a new idmap extent into struct uid_gid_map. * Takes care to allocate a 4K block of memory if the number of mappings exceeds * UID_GID_MAP_MAX_BASE_EXTENTS. */ static int insert_extent(struct uid_gid_map *map, struct uid_gid_extent *extent) { struct uid_gid_extent *dest; if (map->nr_extents == UID_GID_MAP_MAX_BASE_EXTENTS) { struct uid_gid_extent *forward; /* Allocate memory for 340 mappings. */ forward = kmalloc_array(UID_GID_MAP_MAX_EXTENTS, sizeof(struct uid_gid_extent), GFP_KERNEL); if (!forward) return -ENOMEM; /* Copy over memory. Only set up memory for the forward pointer. * Defer the memory setup for the reverse pointer. */ memcpy(forward, map->extent, map->nr_extents * sizeof(map->extent[0])); map->forward = forward; map->reverse = NULL; } if (map->nr_extents < UID_GID_MAP_MAX_BASE_EXTENTS) dest = &map->extent[map->nr_extents]; else dest = &map->forward[map->nr_extents]; *dest = *extent; map->nr_extents++; return 0; } /* cmp function to sort() forward mappings */ static int cmp_extents_forward(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->first < e2->first) return -1; if (e1->first > e2->first) return 1; return 0; } /* cmp function to sort() reverse mappings */ static int cmp_extents_reverse(const void *a, const void *b) { const struct uid_gid_extent *e1 = a; const struct uid_gid_extent *e2 = b; if (e1->lower_first < e2->lower_first) return -1; if (e1->lower_first > e2->lower_first) return 1; return 0; } /** * sort_idmaps - Sorts an array of idmap entries. * Can only be called if number of mappings exceeds UID_GID_MAP_MAX_BASE_EXTENTS. */ static int sort_idmaps(struct uid_gid_map *map) { if (map->nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) return 0; /* Sort forward array. */ sort(map->forward, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_forward, NULL); /* Only copy the memory from forward we actually need. */ map->reverse = kmemdup(map->forward, map->nr_extents * sizeof(struct uid_gid_extent), GFP_KERNEL); if (!map->reverse) return -ENOMEM; /* Sort reverse array. */ sort(map->reverse, map->nr_extents, sizeof(struct uid_gid_extent), cmp_extents_reverse, NULL); return 0; } static ssize_t map_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos, int cap_setid, struct uid_gid_map *map, struct uid_gid_map *parent_map) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct uid_gid_map new_map; unsigned idx; struct uid_gid_extent extent; char *kbuf = NULL, *pos, *next_line; ssize_t ret; /* 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); /* * The userns_state_mutex serializes all writes to any given map. * * Any map is only ever written once. * * An id map fits within 1 cache line on most architectures. * * On read nothing needs to be done unless you are on an * architecture with a crazy cache coherency model like alpha. * * There is a one time data dependency between reading the * count of the extents and the values of the extents. The * desired behavior is to see the values of the extents that * were written before the count of the extents. * * To achieve this smp_wmb() is used on guarantee the write * order and smp_rmb() is guaranteed that we don't have crazy * architectures returning stale data. */ mutex_lock(&userns_state_mutex); memset(&new_map, 0, sizeof(struct uid_gid_map)); ret = -EPERM; /* Only allow one successful write to the map */ if (map->nr_extents != 0) goto out; /* * Adjusting namespace settings requires capabilities on the target. */ if (cap_valid(cap_setid) && !file_ns_capable(file, ns, CAP_SYS_ADMIN)) goto out; /* Parse the user data */ ret = -EINVAL; pos = kbuf; for (; pos; pos = next_line) { /* Find the end of line and ensure I 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; } pos = skip_spaces(pos); extent.first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.lower_first = simple_strtoul(pos, &pos, 10); if (!isspace(*pos)) goto out; pos = skip_spaces(pos); extent.count = simple_strtoul(pos, &pos, 10); if (*pos && !isspace(*pos)) goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; /* Verify we have been given valid starting values */ if ((extent.first == (u32) -1) || (extent.lower_first == (u32) -1)) goto out; /* Verify count is not zero and does not cause the * extent to wrap */ if ((extent.first + extent.count) <= extent.first) goto out; if ((extent.lower_first + extent.count) <= extent.lower_first) goto out; /* Do the ranges in extent overlap any previous extents? */ if (mappings_overlap(&new_map, &extent)) goto out; if ((new_map.nr_extents + 1) == UID_GID_MAP_MAX_EXTENTS && (next_line != NULL)) goto out; ret = insert_extent(&new_map, &extent); if (ret < 0) goto out; ret = -EINVAL; } /* Be very certaint the new map actually exists */ if (new_map.nr_extents == 0) goto out; ret = -EPERM; /* Validate the user is allowed to use user id's mapped to. */ if (!new_idmap_permitted(file, ns, cap_setid, &new_map)) goto out; ret = -EPERM; /* Map the lower ids from the parent user namespace to the * kernel global id space. */ for (idx = 0; idx < new_map.nr_extents; idx++) { struct uid_gid_extent *e; u32 lower_first; if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) e = &new_map.extent[idx]; else e = &new_map.forward[idx]; lower_first = map_id_range_down(parent_map, e->lower_first, e->count); /* Fail if we can not map the specified extent to * the kernel global id space. */ if (lower_first == (u32) -1) goto out; e->lower_first = lower_first; } /* * If we want to use binary search for lookup, this clones the extent * array and sorts both copies. */ ret = sort_idmaps(&new_map); if (ret < 0) goto out; /* Install the map */ if (new_map.nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { memcpy(map->extent, new_map.extent, new_map.nr_extents * sizeof(new_map.extent[0])); } else { map->forward = new_map.forward; map->reverse = new_map.reverse; } smp_wmb(); map->nr_extents = new_map.nr_extents; *ppos = count; ret = count; out: if (ret < 0 && new_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(new_map.forward); kfree(new_map.reverse); map->forward = NULL; map->reverse = NULL; map->nr_extents = 0; } mutex_unlock(&userns_state_mutex); kfree(kbuf); return ret; } ssize_t proc_uid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETUID, &ns->uid_map, &ns->parent->uid_map); } ssize_t proc_gid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; return map_write(file, buf, size, ppos, CAP_SETGID, &ns->gid_map, &ns->parent->gid_map); } ssize_t proc_projid_map_write(struct file *file, const char __user *buf, size_t size, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; struct user_namespace *seq_ns = seq_user_ns(seq); if (!ns->parent) return -EPERM; if ((seq_ns != ns) && (seq_ns != ns->parent)) return -EPERM; /* Anyone can set any valid project id no capability needed */ return map_write(file, buf, size, ppos, -1, &ns->projid_map, &ns->parent->projid_map); } static bool new_idmap_permitted(const struct file *file, struct user_namespace *ns, int cap_setid, struct uid_gid_map *new_map) { const struct cred *cred = file->f_cred; /* Don't allow mappings that would allow anything that wouldn't * be allowed without the establishment of unprivileged mappings. */ if ((new_map->nr_extents == 1) && (new_map->extent[0].count == 1) && uid_eq(ns->owner, cred->euid)) { u32 id = new_map->extent[0].lower_first; if (cap_setid == CAP_SETUID) { kuid_t uid = make_kuid(ns->parent, id); if (uid_eq(uid, cred->euid)) return true; } else if (cap_setid == CAP_SETGID) { kgid_t gid = make_kgid(ns->parent, id); if (!(ns->flags & USERNS_SETGROUPS_ALLOWED) && gid_eq(gid, cred->egid)) return true; } } /* Allow anyone to set a mapping that doesn't require privilege */ if (!cap_valid(cap_setid)) return true; /* Allow the specified ids if we have the appropriate capability * (CAP_SETUID or CAP_SETGID) over the parent user namespace. * And the opener of the id file also had the approprpiate capability. */ if (ns_capable(ns->parent, cap_setid) && file_ns_capable(file, ns->parent, cap_setid)) return true; return false; } int proc_setgroups_show(struct seq_file *seq, void *v) { struct user_namespace *ns = seq->private; unsigned long userns_flags = READ_ONCE(ns->flags); seq_printf(seq, "%s\n", (userns_flags & USERNS_SETGROUPS_ALLOWED) ? "allow" : "deny"); return 0; } ssize_t proc_setgroups_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { struct seq_file *seq = file->private_data; struct user_namespace *ns = seq->private; char kbuf[8], *pos; bool setgroups_allowed; ssize_t ret; /* Only allow a very narrow range of strings to be written */ ret = -EINVAL; if ((*ppos != 0) || (count >= sizeof(kbuf))) goto out; /* What was written? */ ret = -EFAULT; if (copy_from_user(kbuf, buf, count)) goto out; kbuf[count] = '\0'; pos = kbuf; /* What is being requested? */ ret = -EINVAL; if (strncmp(pos, "allow", 5) == 0) { pos += 5; setgroups_allowed = true; } else if (strncmp(pos, "deny", 4) == 0) { pos += 4; setgroups_allowed = false; } else goto out; /* Verify there is not trailing junk on the line */ pos = skip_spaces(pos); if (*pos != '\0') goto out; ret = -EPERM; mutex_lock(&userns_state_mutex); if (setgroups_allowed) { /* Enabling setgroups after setgroups has been disabled * is not allowed. */ if (!(ns->flags & USERNS_SETGROUPS_ALLOWED)) goto out_unlock; } else { /* Permanently disabling setgroups after setgroups has * been enabled by writing the gid_map is not allowed. */ if (ns->gid_map.nr_extents != 0) goto out_unlock; ns->flags &= ~USERNS_SETGROUPS_ALLOWED; } mutex_unlock(&userns_state_mutex); /* Report a successful write */ *ppos = count; ret = count; out: return ret; out_unlock: mutex_unlock(&userns_state_mutex); goto out; } bool userns_may_setgroups(const struct user_namespace *ns) { bool allowed; mutex_lock(&userns_state_mutex); /* It is not safe to use setgroups until a gid mapping in * the user namespace has been established. */ allowed = ns->gid_map.nr_extents != 0; /* Is setgroups allowed? */ allowed = allowed && (ns->flags & USERNS_SETGROUPS_ALLOWED); mutex_unlock(&userns_state_mutex); return allowed; } /* * Returns true if @child is the same namespace or a descendant of * @ancestor. */ bool in_userns(const struct user_namespace *ancestor, const struct user_namespace *child) { const struct user_namespace *ns; for (ns = child; ns->level > ancestor->level; ns = ns->parent) ; return (ns == ancestor); } bool current_in_userns(const struct user_namespace *target_ns) { return in_userns(target_ns, current_user_ns()); } EXPORT_SYMBOL(current_in_userns); static inline struct user_namespace *to_user_ns(struct ns_common *ns) { return container_of(ns, struct user_namespace, ns); } static struct ns_common *userns_get(struct task_struct *task) { struct user_namespace *user_ns; rcu_read_lock(); user_ns = get_user_ns(__task_cred(task)->user_ns); rcu_read_unlock(); return user_ns ? &user_ns->ns : NULL; } static void userns_put(struct ns_common *ns) { put_user_ns(to_user_ns(ns)); } static int userns_install(struct nsproxy *nsproxy, struct ns_common *ns) { struct user_namespace *user_ns = to_user_ns(ns); struct cred *cred; /* Don't allow gaining capabilities by reentering * the same user namespace. */ if (user_ns == current_user_ns()) return -EINVAL; /* Tasks that share a thread group must share a user namespace */ if (!thread_group_empty(current)) return -EINVAL; if (current->fs->users != 1) return -EINVAL; if (!ns_capable(user_ns, CAP_SYS_ADMIN)) return -EPERM; cred = prepare_creds(); if (!cred) return -ENOMEM; put_user_ns(cred->user_ns); set_cred_user_ns(cred, get_user_ns(user_ns)); return commit_creds(cred); } struct ns_common *ns_get_owner(struct ns_common *ns) { struct user_namespace *my_user_ns = current_user_ns(); struct user_namespace *owner, *p; /* See if the owner is in the current user namespace */ owner = p = ns->ops->owner(ns); for (;;) { if (!p) return ERR_PTR(-EPERM); if (p == my_user_ns) break; p = p->parent; } return &get_user_ns(owner)->ns; } static struct user_namespace *userns_owner(struct ns_common *ns) { return to_user_ns(ns)->parent; } const struct proc_ns_operations userns_operations = { .name = "user", .type = CLONE_NEWUSER, .get = userns_get, .put = userns_put, .install = userns_install, .owner = userns_owner, .get_parent = ns_get_owner, }; static __init int user_namespaces_init(void) { user_ns_cachep = KMEM_CACHE(user_namespace, SLAB_PANIC); return 0; } subsys_initcall(user_namespaces_init); |
| 66 1 94 19 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * Definitions for the 'struct skb_array' datastructure. * * Author: * Michael S. Tsirkin <mst@redhat.com> * * Copyright (C) 2016 Red Hat, Inc. * * Limited-size FIFO of skbs. Can be used more or less whenever * sk_buff_head can be used, except you need to know the queue size in * advance. * Implemented as a type-safe wrapper around ptr_ring. */ #ifndef _LINUX_SKB_ARRAY_H #define _LINUX_SKB_ARRAY_H 1 #ifdef __KERNEL__ #include <linux/ptr_ring.h> #include <linux/skbuff.h> #include <linux/if_vlan.h> #endif struct skb_array { struct ptr_ring ring; }; /* Might be slightly faster than skb_array_full below, but callers invoking * this in a loop must use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_full(struct skb_array *a) { return __ptr_ring_full(&a->ring); } static inline bool skb_array_full(struct skb_array *a) { return ptr_ring_full(&a->ring); } static inline int skb_array_produce(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce(&a->ring, skb); } static inline int skb_array_produce_irq(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_irq(&a->ring, skb); } static inline int skb_array_produce_bh(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_bh(&a->ring, skb); } static inline int skb_array_produce_any(struct skb_array *a, struct sk_buff *skb) { return ptr_ring_produce_any(&a->ring, skb); } /* Might be slightly faster than skb_array_empty below, but only safe if the * array is never resized. Also, callers invoking this in a loop must take care * to use a compiler barrier, for example cpu_relax(). */ static inline bool __skb_array_empty(struct skb_array *a) { return __ptr_ring_empty(&a->ring); } static inline struct sk_buff *__skb_array_peek(struct skb_array *a) { return __ptr_ring_peek(&a->ring); } static inline bool skb_array_empty(struct skb_array *a) { return ptr_ring_empty(&a->ring); } static inline bool skb_array_empty_bh(struct skb_array *a) { return ptr_ring_empty_bh(&a->ring); } static inline bool skb_array_empty_irq(struct skb_array *a) { return ptr_ring_empty_irq(&a->ring); } static inline bool skb_array_empty_any(struct skb_array *a) { return ptr_ring_empty_any(&a->ring); } static inline struct sk_buff *__skb_array_consume(struct skb_array *a) { return __ptr_ring_consume(&a->ring); } static inline struct sk_buff *skb_array_consume(struct skb_array *a) { return ptr_ring_consume(&a->ring); } static inline int skb_array_consume_batched(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_irq(struct skb_array *a) { return ptr_ring_consume_irq(&a->ring); } static inline int skb_array_consume_batched_irq(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_irq(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_any(struct skb_array *a) { return ptr_ring_consume_any(&a->ring); } static inline int skb_array_consume_batched_any(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_any(&a->ring, (void **)array, n); } static inline struct sk_buff *skb_array_consume_bh(struct skb_array *a) { return ptr_ring_consume_bh(&a->ring); } static inline int skb_array_consume_batched_bh(struct skb_array *a, struct sk_buff **array, int n) { return ptr_ring_consume_batched_bh(&a->ring, (void **)array, n); } static inline int __skb_array_len_with_tag(struct sk_buff *skb) { if (likely(skb)) { int len = skb->len; if (skb_vlan_tag_present(skb)) len += VLAN_HLEN; return len; } else { return 0; } } static inline int skb_array_peek_len(struct skb_array *a) { return PTR_RING_PEEK_CALL(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_irq(struct skb_array *a) { return PTR_RING_PEEK_CALL_IRQ(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_bh(struct skb_array *a) { return PTR_RING_PEEK_CALL_BH(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_peek_len_any(struct skb_array *a) { return PTR_RING_PEEK_CALL_ANY(&a->ring, __skb_array_len_with_tag); } static inline int skb_array_init(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_init(&a->ring, size, gfp); } static void __skb_array_destroy_skb(void *ptr) { kfree_skb(ptr); } static inline void skb_array_unconsume(struct skb_array *a, struct sk_buff **skbs, int n) { ptr_ring_unconsume(&a->ring, (void **)skbs, n, __skb_array_destroy_skb); } static inline int skb_array_resize(struct skb_array *a, int size, gfp_t gfp) { return ptr_ring_resize(&a->ring, size, gfp, __skb_array_destroy_skb); } static inline int skb_array_resize_multiple(struct skb_array **rings, int nrings, unsigned int size, gfp_t gfp) { BUILD_BUG_ON(offsetof(struct skb_array, ring)); return ptr_ring_resize_multiple((struct ptr_ring **)rings, nrings, size, gfp, __skb_array_destroy_skb); } static inline void skb_array_cleanup(struct skb_array *a) { ptr_ring_cleanup(&a->ring, __skb_array_destroy_skb); } #endif /* _LINUX_SKB_ARRAY_H */ |
| 21 22 21 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip6_flowlabel.c IPv6 flowlabel manager. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> */ #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/socket.h> #include <linux/net.h> #include <linux/netdevice.h> #include <linux/in6.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/pid_namespace.h> #include <linux/jump_label_ratelimit.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/ipv6.h> #include <net/rawv6.h> #include <net/transp_v6.h> #include <linux/uaccess.h> #define FL_MIN_LINGER 6 /* Minimal linger. It is set to 6sec specified in old IPv6 RFC. Well, it was reasonable value. */ #define FL_MAX_LINGER 150 /* Maximal linger timeout */ /* FL hash table */ #define FL_MAX_PER_SOCK 32 #define FL_MAX_SIZE 4096 #define FL_HASH_MASK 255 #define FL_HASH(l) (ntohl(l)&FL_HASH_MASK) static atomic_t fl_size = ATOMIC_INIT(0); static struct ip6_flowlabel __rcu *fl_ht[FL_HASH_MASK+1]; static void ip6_fl_gc(struct timer_list *unused); static DEFINE_TIMER(ip6_fl_gc_timer, ip6_fl_gc); /* FL hash table lock: it protects only of GC */ static DEFINE_SPINLOCK(ip6_fl_lock); /* Big socket sock */ static DEFINE_SPINLOCK(ip6_sk_fl_lock); DEFINE_STATIC_KEY_DEFERRED_FALSE(ipv6_flowlabel_exclusive, HZ); EXPORT_SYMBOL(ipv6_flowlabel_exclusive); #define for_each_fl_rcu(hash, fl) \ for (fl = rcu_dereference_bh(fl_ht[(hash)]); \ fl != NULL; \ fl = rcu_dereference_bh(fl->next)) #define for_each_fl_continue_rcu(fl) \ for (fl = rcu_dereference_bh(fl->next); \ fl != NULL; \ fl = rcu_dereference_bh(fl->next)) #define for_each_sk_fl_rcu(np, sfl) \ for (sfl = rcu_dereference_bh(np->ipv6_fl_list); \ sfl != NULL; \ sfl = rcu_dereference_bh(sfl->next)) static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; for_each_fl_rcu(FL_HASH(label), fl) { if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } return NULL; } static struct ip6_flowlabel *fl_lookup(struct net *net, __be32 label) { struct ip6_flowlabel *fl; rcu_read_lock_bh(); fl = __fl_lookup(net, label); if (fl && !atomic_inc_not_zero(&fl->users)) fl = NULL; rcu_read_unlock_bh(); return fl; } static bool fl_shared_exclusive(struct ip6_flowlabel *fl) { return fl->share == IPV6_FL_S_EXCL || fl->share == IPV6_FL_S_PROCESS || fl->share == IPV6_FL_S_USER; } static void fl_free_rcu(struct rcu_head *head) { struct ip6_flowlabel *fl = container_of(head, struct ip6_flowlabel, rcu); if (fl->share == IPV6_FL_S_PROCESS) put_pid(fl->owner.pid); kfree(fl->opt); kfree(fl); } static void fl_free(struct ip6_flowlabel *fl) { if (!fl) return; if (fl_shared_exclusive(fl) || fl->opt) static_branch_slow_dec_deferred(&ipv6_flowlabel_exclusive); call_rcu(&fl->rcu, fl_free_rcu); } static void fl_release(struct ip6_flowlabel *fl) { spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (atomic_dec_and_test(&fl->users)) { unsigned long ttd = fl->lastuse + fl->linger; if (time_after(ttd, fl->expires)) fl->expires = ttd; ttd = fl->expires; if (fl->opt && fl->share == IPV6_FL_S_EXCL) { struct ipv6_txoptions *opt = fl->opt; fl->opt = NULL; kfree(opt); } if (!timer_pending(&ip6_fl_gc_timer) || time_after(ip6_fl_gc_timer.expires, ttd)) mod_timer(&ip6_fl_gc_timer, ttd); } spin_unlock_bh(&ip6_fl_lock); } static void ip6_fl_gc(struct timer_list *unused) { int i; unsigned long now = jiffies; unsigned long sched = 0; spin_lock(&ip6_fl_lock); for (i = 0; i <= FL_HASH_MASK; i++) { struct ip6_flowlabel *fl; struct ip6_flowlabel __rcu **flp; flp = &fl_ht[i]; while ((fl = rcu_dereference_protected(*flp, lockdep_is_held(&ip6_fl_lock))) != NULL) { if (atomic_read(&fl->users) == 0) { unsigned long ttd = fl->lastuse + fl->linger; if (time_after(ttd, fl->expires)) fl->expires = ttd; ttd = fl->expires; if (time_after_eq(now, ttd)) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); continue; } if (!sched || time_before(ttd, sched)) sched = ttd; } flp = &fl->next; } } if (!sched && atomic_read(&fl_size)) sched = now + FL_MAX_LINGER; if (sched) { mod_timer(&ip6_fl_gc_timer, sched); } spin_unlock(&ip6_fl_lock); } static void __net_exit ip6_fl_purge(struct net *net) { int i; spin_lock_bh(&ip6_fl_lock); for (i = 0; i <= FL_HASH_MASK; i++) { struct ip6_flowlabel *fl; struct ip6_flowlabel __rcu **flp; flp = &fl_ht[i]; while ((fl = rcu_dereference_protected(*flp, lockdep_is_held(&ip6_fl_lock))) != NULL) { if (net_eq(fl->fl_net, net) && atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); continue; } flp = &fl->next; } } spin_unlock_bh(&ip6_fl_lock); } static struct ip6_flowlabel *fl_intern(struct net *net, struct ip6_flowlabel *fl, __be32 label) { struct ip6_flowlabel *lfl; fl->label = label & IPV6_FLOWLABEL_MASK; spin_lock_bh(&ip6_fl_lock); if (label == 0) { for (;;) { fl->label = htonl(prandom_u32())&IPV6_FLOWLABEL_MASK; if (fl->label) { lfl = __fl_lookup(net, fl->label); if (!lfl) break; } } } else { /* * we dropper the ip6_fl_lock, so this entry could reappear * and we need to recheck with it. * * OTOH no need to search the active socket first, like it is * done in ipv6_flowlabel_opt - sock is locked, so new entry * with the same label can only appear on another sock */ lfl = __fl_lookup(net, fl->label); if (lfl) { atomic_inc(&lfl->users); spin_unlock_bh(&ip6_fl_lock); return lfl; } } fl->lastuse = jiffies; fl->next = fl_ht[FL_HASH(fl->label)]; rcu_assign_pointer(fl_ht[FL_HASH(fl->label)], fl); atomic_inc(&fl_size); spin_unlock_bh(&ip6_fl_lock); return NULL; } /* Socket flowlabel lists */ struct ip6_flowlabel *__fl6_sock_lookup(struct sock *sk, __be32 label) { struct ipv6_fl_socklist *sfl; struct ipv6_pinfo *np = inet6_sk(sk); label &= IPV6_FLOWLABEL_MASK; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { struct ip6_flowlabel *fl = sfl->fl; if (fl->label == label && atomic_inc_not_zero(&fl->users)) { fl->lastuse = jiffies; rcu_read_unlock_bh(); return fl; } } rcu_read_unlock_bh(); return NULL; } EXPORT_SYMBOL_GPL(__fl6_sock_lookup); void fl6_free_socklist(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; if (!rcu_access_pointer(np->ipv6_fl_list)) return; spin_lock_bh(&ip6_sk_fl_lock); while ((sfl = rcu_dereference_protected(np->ipv6_fl_list, lockdep_is_held(&ip6_sk_fl_lock))) != NULL) { np->ipv6_fl_list = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); spin_lock_bh(&ip6_sk_fl_lock); } spin_unlock_bh(&ip6_sk_fl_lock); } /* Service routines */ /* It is the only difficult place. flowlabel enforces equal headers before and including routing header, however user may supply options following rthdr. */ struct ipv6_txoptions *fl6_merge_options(struct ipv6_txoptions *opt_space, struct ip6_flowlabel *fl, struct ipv6_txoptions *fopt) { struct ipv6_txoptions *fl_opt = fl->opt; if (!fopt || fopt->opt_flen == 0) return fl_opt; if (fl_opt) { opt_space->hopopt = fl_opt->hopopt; opt_space->dst0opt = fl_opt->dst0opt; opt_space->srcrt = fl_opt->srcrt; opt_space->opt_nflen = fl_opt->opt_nflen; } else { if (fopt->opt_nflen == 0) return fopt; opt_space->hopopt = NULL; opt_space->dst0opt = NULL; opt_space->srcrt = NULL; opt_space->opt_nflen = 0; } opt_space->dst1opt = fopt->dst1opt; opt_space->opt_flen = fopt->opt_flen; opt_space->tot_len = fopt->tot_len; return opt_space; } EXPORT_SYMBOL_GPL(fl6_merge_options); static unsigned long check_linger(unsigned long ttl) { if (ttl < FL_MIN_LINGER) return FL_MIN_LINGER*HZ; if (ttl > FL_MAX_LINGER && !capable(CAP_NET_ADMIN)) return 0; return ttl*HZ; } static int fl6_renew(struct ip6_flowlabel *fl, unsigned long linger, unsigned long expires) { linger = check_linger(linger); if (!linger) return -EPERM; expires = check_linger(expires); if (!expires) return -EPERM; spin_lock_bh(&ip6_fl_lock); fl->lastuse = jiffies; if (time_before(fl->linger, linger)) fl->linger = linger; if (time_before(expires, fl->linger)) expires = fl->linger; if (time_before(fl->expires, fl->lastuse + expires)) fl->expires = fl->lastuse + expires; spin_unlock_bh(&ip6_fl_lock); return 0; } static struct ip6_flowlabel * fl_create(struct net *net, struct sock *sk, struct in6_flowlabel_req *freq, char __user *optval, int optlen, int *err_p) { struct ip6_flowlabel *fl = NULL; int olen; int addr_type; int err; olen = optlen - CMSG_ALIGN(sizeof(*freq)); err = -EINVAL; if (olen > 64 * 1024) goto done; err = -ENOMEM; fl = kzalloc(sizeof(*fl), GFP_KERNEL); if (!fl) goto done; if (olen > 0) { struct msghdr msg; struct flowi6 flowi6; struct ipcm6_cookie ipc6; err = -ENOMEM; fl->opt = kmalloc(sizeof(*fl->opt) + olen, GFP_KERNEL); if (!fl->opt) goto done; memset(fl->opt, 0, sizeof(*fl->opt)); fl->opt->tot_len = sizeof(*fl->opt) + olen; err = -EFAULT; if (copy_from_user(fl->opt+1, optval+CMSG_ALIGN(sizeof(*freq)), olen)) goto done; msg.msg_controllen = olen; msg.msg_control = (void *)(fl->opt+1); memset(&flowi6, 0, sizeof(flowi6)); ipc6.opt = fl->opt; err = ip6_datagram_send_ctl(net, sk, &msg, &flowi6, &ipc6); if (err) goto done; err = -EINVAL; if (fl->opt->opt_flen) goto done; if (fl->opt->opt_nflen == 0) { kfree(fl->opt); fl->opt = NULL; } } fl->fl_net = net; fl->expires = jiffies; err = fl6_renew(fl, freq->flr_linger, freq->flr_expires); if (err) goto done; fl->share = freq->flr_share; addr_type = ipv6_addr_type(&freq->flr_dst); if ((addr_type & IPV6_ADDR_MAPPED) || addr_type == IPV6_ADDR_ANY) { err = -EINVAL; goto done; } fl->dst = freq->flr_dst; atomic_set(&fl->users, 1); switch (fl->share) { case IPV6_FL_S_EXCL: case IPV6_FL_S_ANY: break; case IPV6_FL_S_PROCESS: fl->owner.pid = get_task_pid(current, PIDTYPE_PID); break; case IPV6_FL_S_USER: fl->owner.uid = current_euid(); break; default: err = -EINVAL; goto done; } if (fl_shared_exclusive(fl) || fl->opt) static_branch_deferred_inc(&ipv6_flowlabel_exclusive); return fl; done: if (fl) { kfree(fl->opt); kfree(fl); } *err_p = err; return NULL; } static int mem_check(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; int room = FL_MAX_SIZE - atomic_read(&fl_size); int count = 0; if (room > FL_MAX_SIZE - FL_MAX_PER_SOCK) return 0; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) count++; rcu_read_unlock_bh(); if (room <= 0 || ((count >= FL_MAX_PER_SOCK || (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && !capable(CAP_NET_ADMIN))) return -ENOBUFS; return 0; } static inline void fl_link(struct ipv6_pinfo *np, struct ipv6_fl_socklist *sfl, struct ip6_flowlabel *fl) { spin_lock_bh(&ip6_sk_fl_lock); sfl->fl = fl; sfl->next = np->ipv6_fl_list; rcu_assign_pointer(np->ipv6_fl_list, sfl); spin_unlock_bh(&ip6_sk_fl_lock); } int ipv6_flowlabel_opt_get(struct sock *sk, struct in6_flowlabel_req *freq, int flags) { struct ipv6_pinfo *np = inet6_sk(sk); struct ipv6_fl_socklist *sfl; if (flags & IPV6_FL_F_REMOTE) { freq->flr_label = np->rcv_flowinfo & IPV6_FLOWLABEL_MASK; return 0; } if (np->repflow) { freq->flr_label = np->flow_label; return 0; } rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == (np->flow_label & IPV6_FLOWLABEL_MASK)) { spin_lock_bh(&ip6_fl_lock); freq->flr_label = sfl->fl->label; freq->flr_dst = sfl->fl->dst; freq->flr_share = sfl->fl->share; freq->flr_expires = (sfl->fl->expires - jiffies) / HZ; freq->flr_linger = sfl->fl->linger / HZ; spin_unlock_bh(&ip6_fl_lock); rcu_read_unlock_bh(); return 0; } } rcu_read_unlock_bh(); return -ENOENT; } int ipv6_flowlabel_opt(struct sock *sk, char __user *optval, int optlen) { int err; struct net *net = sock_net(sk); struct ipv6_pinfo *np = inet6_sk(sk); struct in6_flowlabel_req freq; struct ipv6_fl_socklist *sfl1 = NULL; struct ipv6_fl_socklist *sfl; struct ipv6_fl_socklist __rcu **sflp; struct ip6_flowlabel *fl, *fl1 = NULL; if (optlen < sizeof(freq)) return -EINVAL; if (copy_from_user(&freq, optval, sizeof(freq))) return -EFAULT; switch (freq.flr_action) { case IPV6_FL_A_PUT: if (freq.flr_flags & IPV6_FL_F_REFLECT) { if (sk->sk_protocol != IPPROTO_TCP) return -ENOPROTOOPT; if (!np->repflow) return -ESRCH; np->flow_label = 0; np->repflow = 0; return 0; } spin_lock_bh(&ip6_sk_fl_lock); for (sflp = &np->ipv6_fl_list; (sfl = rcu_dereference_protected(*sflp, lockdep_is_held(&ip6_sk_fl_lock))) != NULL; sflp = &sfl->next) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_label == (np->flow_label&IPV6_FLOWLABEL_MASK)) np->flow_label &= ~IPV6_FLOWLABEL_MASK; *sflp = sfl->next; spin_unlock_bh(&ip6_sk_fl_lock); fl_release(sfl->fl); kfree_rcu(sfl, rcu); return 0; } } spin_unlock_bh(&ip6_sk_fl_lock); return -ESRCH; case IPV6_FL_A_RENEW: rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq.flr_label) { err = fl6_renew(sfl->fl, freq.flr_linger, freq.flr_expires); rcu_read_unlock_bh(); return err; } } rcu_read_unlock_bh(); if (freq.flr_share == IPV6_FL_S_NONE && ns_capable(net->user_ns, CAP_NET_ADMIN)) { fl = fl_lookup(net, freq.flr_label); if (fl) { err = fl6_renew(fl, freq.flr_linger, freq.flr_expires); fl_release(fl); return err; } } return -ESRCH; case IPV6_FL_A_GET: if (freq.flr_flags & IPV6_FL_F_REFLECT) { struct net *net = sock_net(sk); if (net->ipv6.sysctl.flowlabel_consistency) { net_info_ratelimited("Can not set IPV6_FL_F_REFLECT if flowlabel_consistency sysctl is enable\n"); return -EPERM; } if (sk->sk_protocol != IPPROTO_TCP) return -ENOPROTOOPT; np->repflow = 1; return 0; } if (freq.flr_label & ~IPV6_FLOWLABEL_MASK) return -EINVAL; if (net->ipv6.sysctl.flowlabel_state_ranges && (freq.flr_label & IPV6_FLOWLABEL_STATELESS_FLAG)) return -ERANGE; fl = fl_create(net, sk, &freq, optval, optlen, &err); if (!fl) return err; sfl1 = kmalloc(sizeof(*sfl1), GFP_KERNEL); if (freq.flr_label) { err = -EEXIST; rcu_read_lock_bh(); for_each_sk_fl_rcu(np, sfl) { if (sfl->fl->label == freq.flr_label) { if (freq.flr_flags&IPV6_FL_F_EXCL) { rcu_read_unlock_bh(); goto done; } fl1 = sfl->fl; if (!atomic_inc_not_zero(&fl1->users)) fl1 = NULL; break; } } rcu_read_unlock_bh(); if (!fl1) fl1 = fl_lookup(net, freq.flr_label); if (fl1) { recheck: err = -EEXIST; if (freq.flr_flags&IPV6_FL_F_EXCL) goto release; err = -EPERM; if (fl1->share == IPV6_FL_S_EXCL || fl1->share != fl->share || ((fl1->share == IPV6_FL_S_PROCESS) && (fl1->owner.pid != fl->owner.pid)) || ((fl1->share == IPV6_FL_S_USER) && !uid_eq(fl1->owner.uid, fl->owner.uid))) goto release; err = -ENOMEM; if (!sfl1) goto release; if (fl->linger > fl1->linger) fl1->linger = fl->linger; if ((long)(fl->expires - fl1->expires) > 0) fl1->expires = fl->expires; fl_link(np, sfl1, fl1); fl_free(fl); return 0; release: fl_release(fl1); goto done; } } err = -ENOENT; if (!(freq.flr_flags&IPV6_FL_F_CREATE)) goto done; err = -ENOMEM; if (!sfl1) goto done; err = mem_check(sk); if (err != 0) goto done; fl1 = fl_intern(net, fl, freq.flr_label); if (fl1) goto recheck; if (!freq.flr_label) { if (copy_to_user(&((struct in6_flowlabel_req __user *) optval)->flr_label, &fl->label, sizeof(fl->label))) { /* Intentionally ignore fault. */ } } fl_link(np, sfl1, fl); return 0; default: return -EINVAL; } done: fl_free(fl); kfree(sfl1); return err; } #ifdef CONFIG_PROC_FS struct ip6fl_iter_state { struct seq_net_private p; struct pid_namespace *pid_ns; int bucket; }; #define ip6fl_seq_private(seq) ((struct ip6fl_iter_state *)(seq)->private) static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) { struct ip6_flowlabel *fl = NULL; struct ip6fl_iter_state *state = ip6fl_seq_private(seq); struct net *net = seq_file_net(seq); for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { for_each_fl_rcu(state->bucket, fl) { if (net_eq(fl->fl_net, net)) goto out; } } fl = NULL; out: return fl; } static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flowlabel *fl) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); struct net *net = seq_file_net(seq); for_each_fl_continue_rcu(fl) { if (net_eq(fl->fl_net, net)) goto out; } try_again: if (++state->bucket <= FL_HASH_MASK) { for_each_fl_rcu(state->bucket, fl) { if (net_eq(fl->fl_net, net)) goto out; } goto try_again; } fl = NULL; out: return fl; } static struct ip6_flowlabel *ip6fl_get_idx(struct seq_file *seq, loff_t pos) { struct ip6_flowlabel *fl = ip6fl_get_first(seq); if (fl) while (pos && (fl = ip6fl_get_next(seq, fl)) != NULL) --pos; return pos ? NULL : fl; } static void *ip6fl_seq_start(struct seq_file *seq, loff_t *pos) __acquires(RCU) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); state->pid_ns = proc_pid_ns(file_inode(seq->file)); rcu_read_lock_bh(); return *pos ? ip6fl_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *ip6fl_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip6_flowlabel *fl; if (v == SEQ_START_TOKEN) fl = ip6fl_get_first(seq); else fl = ip6fl_get_next(seq, v); ++*pos; return fl; } static void ip6fl_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { rcu_read_unlock_bh(); } static int ip6fl_seq_show(struct seq_file *seq, void *v) { struct ip6fl_iter_state *state = ip6fl_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Label S Owner Users Linger Expires Dst Opt\n"); } else { struct ip6_flowlabel *fl = v; seq_printf(seq, "%05X %-1d %-6d %-6d %-6ld %-8ld %pi6 %-4d\n", (unsigned int)ntohl(fl->label), fl->share, ((fl->share == IPV6_FL_S_PROCESS) ? pid_nr_ns(fl->owner.pid, state->pid_ns) : ((fl->share == IPV6_FL_S_USER) ? from_kuid_munged(seq_user_ns(seq), fl->owner.uid) : 0)), atomic_read(&fl->users), fl->linger/HZ, (long)(fl->expires - jiffies)/HZ, &fl->dst, fl->opt ? fl->opt->opt_nflen : 0); } return 0; } static const struct seq_operations ip6fl_seq_ops = { .start = ip6fl_seq_start, .next = ip6fl_seq_next, .stop = ip6fl_seq_stop, .show = ip6fl_seq_show, }; static int __net_init ip6_flowlabel_proc_init(struct net *net) { if (!proc_create_net("ip6_flowlabel", 0444, net->proc_net, &ip6fl_seq_ops, sizeof(struct ip6fl_iter_state))) return -ENOMEM; return 0; } static void __net_exit ip6_flowlabel_proc_fini(struct net *net) { remove_proc_entry("ip6_flowlabel", net->proc_net); } #else static inline int ip6_flowlabel_proc_init(struct net *net) { return 0; } static inline void ip6_flowlabel_proc_fini(struct net *net) { } #endif static void __net_exit ip6_flowlabel_net_exit(struct net *net) { ip6_fl_purge(net); ip6_flowlabel_proc_fini(net); } static struct pernet_operations ip6_flowlabel_net_ops = { .init = ip6_flowlabel_proc_init, .exit = ip6_flowlabel_net_exit, }; int ip6_flowlabel_init(void) { return register_pernet_subsys(&ip6_flowlabel_net_ops); } void ip6_flowlabel_cleanup(void) { static_key_deferred_flush(&ipv6_flowlabel_exclusive); del_timer(&ip6_fl_gc_timer); unregister_pernet_subsys(&ip6_flowlabel_net_ops); } |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BACKING_DEV_DEFS_H #define __LINUX_BACKING_DEV_DEFS_H #include <linux/list.h> #include <linux/radix-tree.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/percpu_counter.h> #include <linux/percpu-refcount.h> #include <linux/flex_proportions.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/kref.h> #include <linux/refcount.h> #include <linux/android_kabi.h> struct page; struct device; struct dentry; /* * Bits in bdi_writeback.state */ enum wb_state { WB_registered, /* bdi_register() was done */ WB_writeback_running, /* Writeback is in progress */ WB_has_dirty_io, /* Dirty inodes on ->b_{dirty|io|more_io} */ WB_start_all, /* nr_pages == 0 (all) work pending */ }; enum wb_congested_state { WB_async_congested, /* The async (write) queue is getting full */ WB_sync_congested, /* The sync queue is getting full */ }; typedef int (congested_fn)(void *, int); enum wb_stat_item { WB_RECLAIMABLE, WB_WRITEBACK, WB_DIRTIED, WB_WRITTEN, NR_WB_STAT_ITEMS }; #define WB_STAT_BATCH (8*(1+ilog2(nr_cpu_ids))) /* * why some writeback work was initiated */ enum wb_reason { WB_REASON_BACKGROUND, WB_REASON_VMSCAN, WB_REASON_SYNC, WB_REASON_PERIODIC, WB_REASON_LAPTOP_TIMER, WB_REASON_FREE_MORE_MEM, WB_REASON_FS_FREE_SPACE, /* * There is no bdi forker thread any more and works are done * by emergency worker, however, this is TPs userland visible * and we'll be exposing exactly the same information, * so it has a mismatch name. */ WB_REASON_FORKER_THREAD, WB_REASON_FOREIGN_FLUSH, WB_REASON_MAX, }; struct wb_completion { atomic_t cnt; wait_queue_head_t *waitq; }; #define __WB_COMPLETION_INIT(_waitq) \ (struct wb_completion){ .cnt = ATOMIC_INIT(1), .waitq = (_waitq) } /* * If one wants to wait for one or more wb_writeback_works, each work's * ->done should be set to a wb_completion defined using the following * macro. Once all work items are issued with wb_queue_work(), the caller * can wait for the completion of all using wb_wait_for_completion(). Work * items which are waited upon aren't freed automatically on completion. */ #define WB_COMPLETION_INIT(bdi) __WB_COMPLETION_INIT(&(bdi)->wb_waitq) #define DEFINE_WB_COMPLETION(cmpl, bdi) \ struct wb_completion cmpl = WB_COMPLETION_INIT(bdi) /* * For cgroup writeback, multiple wb's may map to the same blkcg. Those * wb's can operate mostly independently but should share the congested * state. To facilitate such sharing, the congested state is tracked using * the following struct which is created on demand, indexed by blkcg ID on * its bdi, and refcounted. */ struct bdi_writeback_congested { unsigned long state; /* WB_[a]sync_congested flags */ refcount_t refcnt; /* nr of attached wb's and blkg */ #ifdef CONFIG_CGROUP_WRITEBACK struct backing_dev_info *__bdi; /* the associated bdi, set to NULL * on bdi unregistration. For memcg-wb * internal use only! */ int blkcg_id; /* ID of the associated blkcg */ struct rb_node rb_node; /* on bdi->cgwb_congestion_tree */ #endif }; /* * Each wb (bdi_writeback) can perform writeback operations, is measured * and throttled, independently. Without cgroup writeback, each bdi * (bdi_writeback) is served by its embedded bdi->wb. * * On the default hierarchy, blkcg implicitly enables memcg. This allows * using memcg's page ownership for attributing writeback IOs, and every * memcg - blkcg combination can be served by its own wb by assigning a * dedicated wb to each memcg, which enables isolation across different * cgroups and propagation of IO back pressure down from the IO layer upto * the tasks which are generating the dirty pages to be written back. * * A cgroup wb is indexed on its bdi by the ID of the associated memcg, * refcounted with the number of inodes attached to it, and pins the memcg * and the corresponding blkcg. As the corresponding blkcg for a memcg may * change as blkcg is disabled and enabled higher up in the hierarchy, a wb * is tested for blkcg after lookup and removed from index on mismatch so * that a new wb for the combination can be created. */ struct bdi_writeback { struct backing_dev_info *bdi; /* our parent bdi */ unsigned long state; /* Always use atomic bitops on this */ unsigned long last_old_flush; /* last old data flush */ struct list_head b_dirty; /* dirty inodes */ struct list_head b_io; /* parked for writeback */ struct list_head b_more_io; /* parked for more writeback */ struct list_head b_dirty_time; /* time stamps are dirty */ spinlock_t list_lock; /* protects the b_* lists */ struct percpu_counter stat[NR_WB_STAT_ITEMS]; struct bdi_writeback_congested *congested; unsigned long bw_time_stamp; /* last time write bw is updated */ unsigned long dirtied_stamp; unsigned long written_stamp; /* pages written at bw_time_stamp */ unsigned long write_bandwidth; /* the estimated write bandwidth */ unsigned long avg_write_bandwidth; /* further smoothed write bw, > 0 */ /* * The base dirty throttle rate, re-calculated on every 200ms. * All the bdi tasks' dirty rate will be curbed under it. * @dirty_ratelimit tracks the estimated @balanced_dirty_ratelimit * in small steps and is much more smooth/stable than the latter. */ unsigned long dirty_ratelimit; unsigned long balanced_dirty_ratelimit; struct fprop_local_percpu completions; int dirty_exceeded; enum wb_reason start_all_reason; spinlock_t work_lock; /* protects work_list & dwork scheduling */ struct list_head work_list; struct delayed_work dwork; /* work item used for writeback */ unsigned long dirty_sleep; /* last wait */ struct list_head bdi_node; /* anchored at bdi->wb_list */ #ifdef CONFIG_CGROUP_WRITEBACK struct percpu_ref refcnt; /* used only for !root wb's */ struct fprop_local_percpu memcg_completions; struct cgroup_subsys_state *memcg_css; /* the associated memcg */ struct cgroup_subsys_state *blkcg_css; /* and blkcg */ struct list_head memcg_node; /* anchored at memcg->cgwb_list */ struct list_head blkcg_node; /* anchored at blkcg->cgwb_list */ union { struct work_struct release_work; struct rcu_head rcu; }; #endif ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; struct backing_dev_info { u64 id; struct rb_node rb_node; /* keyed by ->id */ struct list_head bdi_list; unsigned long ra_pages; /* max readahead in PAGE_SIZE units */ unsigned long io_pages; /* max allowed IO size */ congested_fn *congested_fn; /* Function pointer if device is md/dm */ void *congested_data; /* Pointer to aux data for congested func */ const char *name; struct kref refcnt; /* Reference counter for the structure */ unsigned int capabilities; /* Device capabilities */ unsigned int min_ratio; unsigned int max_ratio, max_prop_frac; /* * Sum of avg_write_bw of wbs with dirty inodes. > 0 if there are * any dirty wbs, which is depended upon by bdi_has_dirty(). */ atomic_long_t tot_write_bandwidth; struct bdi_writeback wb; /* the root writeback info for this bdi */ struct list_head wb_list; /* list of all wbs */ #ifdef CONFIG_CGROUP_WRITEBACK struct radix_tree_root cgwb_tree; /* radix tree of active cgroup wbs */ struct rb_root cgwb_congested_tree; /* their congested states */ struct mutex cgwb_release_mutex; /* protect shutdown of wb structs */ struct rw_semaphore wb_switch_rwsem; /* no cgwb switch while syncing */ #else struct bdi_writeback_congested *wb_congested; #endif wait_queue_head_t wb_waitq; struct device *dev; char dev_name[64]; struct device *owner; struct timer_list laptop_mode_wb_timer; #ifdef CONFIG_DEBUG_FS struct dentry *debug_dir; #endif ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; enum { BLK_RW_ASYNC = 0, BLK_RW_SYNC = 1, }; void clear_wb_congested(struct bdi_writeback_congested *congested, int sync); void set_wb_congested(struct bdi_writeback_congested *congested, int sync); static inline void clear_bdi_congested(struct backing_dev_info *bdi, int sync) { clear_wb_congested(bdi->wb.congested, sync); } static inline void set_bdi_congested(struct backing_dev_info *bdi, int sync) { set_wb_congested(bdi->wb.congested, sync); } struct wb_lock_cookie { bool locked; unsigned long flags; }; #ifdef CONFIG_CGROUP_WRITEBACK /** * wb_tryget - try to increment a wb's refcount * @wb: bdi_writeback to get */ static inline bool wb_tryget(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) return percpu_ref_tryget(&wb->refcnt); return true; } /** * wb_get - increment a wb's refcount * @wb: bdi_writeback to get */ static inline void wb_get(struct bdi_writeback *wb) { if (wb != &wb->bdi->wb) percpu_ref_get(&wb->refcnt); } /** * wb_put - decrement a wb's refcount * @wb: bdi_writeback to put */ static inline void wb_put(struct bdi_writeback *wb) { if (WARN_ON_ONCE(!wb->bdi)) { /* * A driver bug might cause a file to be removed before bdi was * initialized. */ return; } if (wb != &wb->bdi->wb) percpu_ref_put(&wb->refcnt); } /** * wb_dying - is a wb dying? * @wb: bdi_writeback of interest * * Returns whether @wb is unlinked and being drained. */ static inline bool wb_dying(struct bdi_writeback *wb) { return percpu_ref_is_dying(&wb->refcnt); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool wb_tryget(struct bdi_writeback *wb) { return true; } static inline void wb_get(struct bdi_writeback *wb) { } static inline void wb_put(struct bdi_writeback *wb) { } static inline bool wb_dying(struct bdi_writeback *wb) { return false; } #endif /* CONFIG_CGROUP_WRITEBACK */ #endif /* __LINUX_BACKING_DEV_DEFS_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * A policy database (policydb) specifies the * configuration data for the security policy. * * Author : Stephen Smalley, <sds@tycho.nsa.gov> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * * Support for enhanced MLS infrastructure. * * Updated: Frank Mayer <mayerf@tresys.com> and Karl MacMillan <kmacmillan@tresys.com> * * Added conditional policy language extensions * * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * Copyright (C) 2003 - 2004 Tresys Technology, LLC */ #ifndef _SS_POLICYDB_H_ #define _SS_POLICYDB_H_ #include "symtab.h" #include "avtab.h" #include "sidtab.h" #include "ebitmap.h" #include "mls_types.h" #include "context.h" #include "constraint.h" /* * A datum type is defined for each kind of symbol * in the configuration data: individual permissions, * common prefixes for access vectors, classes, * users, roles, types, sensitivities, categories, etc. */ /* Permission attributes */ struct perm_datum { u32 value; /* permission bit + 1 */ }; /* Attributes of a common prefix for access vectors */ struct common_datum { u32 value; /* internal common value */ struct symtab permissions; /* common permissions */ }; /* Class attributes */ struct class_datum { u32 value; /* class value */ char *comkey; /* common name */ struct common_datum *comdatum; /* common datum */ struct symtab permissions; /* class-specific permission symbol table */ struct constraint_node *constraints; /* constraints on class permissions */ struct constraint_node *validatetrans; /* special transition rules */ /* Options how a new object user, role, and type should be decided */ #define DEFAULT_SOURCE 1 #define DEFAULT_TARGET 2 char default_user; char default_role; char default_type; /* Options how a new object range should be decided */ #define DEFAULT_SOURCE_LOW 1 #define DEFAULT_SOURCE_HIGH 2 #define DEFAULT_SOURCE_LOW_HIGH 3 #define DEFAULT_TARGET_LOW 4 #define DEFAULT_TARGET_HIGH 5 #define DEFAULT_TARGET_LOW_HIGH 6 char default_range; }; /* Role attributes */ struct role_datum { u32 value; /* internal role value */ u32 bounds; /* boundary of role */ struct ebitmap dominates; /* set of roles dominated by this role */ struct ebitmap types; /* set of authorized types for role */ }; struct role_trans { u32 role; /* current role */ u32 type; /* program executable type, or new object type */ u32 tclass; /* process class, or new object class */ u32 new_role; /* new role */ struct role_trans *next; }; struct filename_trans { u32 stype; /* current process */ u32 ttype; /* parent dir context */ u16 tclass; /* class of new object */ const char *name; /* last path component */ }; struct filename_trans_datum { u32 otype; /* expected of new object */ }; struct role_allow { u32 role; /* current role */ u32 new_role; /* new role */ struct role_allow *next; }; /* Type attributes */ struct type_datum { u32 value; /* internal type value */ u32 bounds; /* boundary of type */ unsigned char primary; /* primary name? */ unsigned char attribute;/* attribute ?*/ }; /* User attributes */ struct user_datum { u32 value; /* internal user value */ u32 bounds; /* bounds of user */ struct ebitmap roles; /* set of authorized roles for user */ struct mls_range range; /* MLS range (min - max) for user */ struct mls_level dfltlevel; /* default login MLS level for user */ }; /* Sensitivity attributes */ struct level_datum { struct mls_level *level; /* sensitivity and associated categories */ unsigned char isalias; /* is this sensitivity an alias for another? */ }; /* Category attributes */ struct cat_datum { u32 value; /* internal category bit + 1 */ unsigned char isalias; /* is this category an alias for another? */ }; struct range_trans { u32 source_type; u32 target_type; u32 target_class; }; /* Boolean data type */ struct cond_bool_datum { __u32 value; /* internal type value */ int state; }; struct cond_node; /* * type set preserves data needed to determine constraint info from * policy source. This is not used by the kernel policy but allows * utilities such as audit2allow to determine constraint denials. */ struct type_set { struct ebitmap types; struct ebitmap negset; u32 flags; }; /* * The configuration data includes security contexts for * initial SIDs, unlabeled file systems, TCP and UDP port numbers, * network interfaces, and nodes. This structure stores the * relevant data for one such entry. Entries of the same kind * (e.g. all initial SIDs) are linked together into a list. */ struct ocontext { union { char *name; /* name of initial SID, fs, netif, fstype, path */ struct { u8 protocol; u16 low_port; u16 high_port; } port; /* TCP or UDP port information */ struct { u32 addr; u32 mask; } node; /* node information */ struct { u32 addr[4]; u32 mask[4]; } node6; /* IPv6 node information */ struct { u64 subnet_prefix; u16 low_pkey; u16 high_pkey; } ibpkey; struct { char *dev_name; u8 port; } ibendport; } u; union { u32 sclass; /* security class for genfs */ u32 behavior; /* labeling behavior for fs_use */ } v; struct context context[2]; /* security context(s) */ u32 sid[2]; /* SID(s) */ struct ocontext *next; }; struct genfs { char *fstype; struct ocontext *head; struct genfs *next; }; /* symbol table array indices */ #define SYM_COMMONS 0 #define SYM_CLASSES 1 #define SYM_ROLES 2 #define SYM_TYPES 3 #define SYM_USERS 4 #define SYM_BOOLS 5 #define SYM_LEVELS 6 #define SYM_CATS 7 #define SYM_NUM 8 /* object context array indices */ #define OCON_ISID 0 /* initial SIDs */ #define OCON_FS 1 /* unlabeled file systems */ #define OCON_PORT 2 /* TCP and UDP port numbers */ #define OCON_NETIF 3 /* network interfaces */ #define OCON_NODE 4 /* nodes */ #define OCON_FSUSE 5 /* fs_use */ #define OCON_NODE6 6 /* IPv6 nodes */ #define OCON_IBPKEY 7 /* Infiniband PKeys */ #define OCON_IBENDPORT 8 /* Infiniband end ports */ #define OCON_NUM 9 /* The policy database */ struct policydb { int mls_enabled; int android_netlink_route; int android_netlink_getneigh; /* symbol tables */ struct symtab symtab[SYM_NUM]; #define p_commons symtab[SYM_COMMONS] #define p_classes symtab[SYM_CLASSES] #define p_roles symtab[SYM_ROLES] #define p_types symtab[SYM_TYPES] #define p_users symtab[SYM_USERS] #define p_bools symtab[SYM_BOOLS] #define p_levels symtab[SYM_LEVELS] #define p_cats symtab[SYM_CATS] /* symbol names indexed by (value - 1) */ char **sym_val_to_name[SYM_NUM]; /* class, role, and user attributes indexed by (value - 1) */ struct class_datum **class_val_to_struct; struct role_datum **role_val_to_struct; struct user_datum **user_val_to_struct; struct type_datum **type_val_to_struct; /* type enforcement access vectors and transitions */ struct avtab te_avtab; /* role transitions */ struct role_trans *role_tr; /* file transitions with the last path component */ /* quickly exclude lookups when parent ttype has no rules */ struct ebitmap filename_trans_ttypes; /* actual set of filename_trans rules */ struct hashtab *filename_trans; /* bools indexed by (value - 1) */ struct cond_bool_datum **bool_val_to_struct; /* type enforcement conditional access vectors and transitions */ struct avtab te_cond_avtab; /* linked list indexing te_cond_avtab by conditional */ struct cond_node *cond_list; /* role allows */ struct role_allow *role_allow; /* security contexts of initial SIDs, unlabeled file systems, TCP or UDP port numbers, network interfaces and nodes */ struct ocontext *ocontexts[OCON_NUM]; /* security contexts for files in filesystems that cannot support a persistent label mapping or use another fixed labeling behavior. */ struct genfs *genfs; /* range transitions table (range_trans_key -> mls_range) */ struct hashtab *range_tr; /* type -> attribute reverse mapping */ struct ebitmap *type_attr_map_array; struct ebitmap policycaps; struct ebitmap permissive_map; /* length of this policy when it was loaded */ size_t len; unsigned int policyvers; unsigned int reject_unknown : 1; unsigned int allow_unknown : 1; u16 process_class; u32 process_trans_perms; }; extern void policydb_destroy(struct policydb *p); extern int policydb_load_isids(struct policydb *p, struct sidtab *s); extern int policydb_context_isvalid(struct policydb *p, struct context *c); extern int policydb_class_isvalid(struct policydb *p, unsigned int class); extern int policydb_type_isvalid(struct policydb *p, unsigned int type); extern int policydb_role_isvalid(struct policydb *p, unsigned int role); extern int policydb_read(struct policydb *p, void *fp); extern int policydb_write(struct policydb *p, void *fp); #define PERM_SYMTAB_SIZE 32 #define POLICYDB_CONFIG_MLS 1 #define POLICYDB_CONFIG_ANDROID_NETLINK_ROUTE (1 << 31) #define POLICYDB_CONFIG_ANDROID_NETLINK_GETNEIGH (1 << 30) /* the config flags related to unknown classes/perms are bits 2 and 3 */ #define REJECT_UNKNOWN 0x00000002 #define ALLOW_UNKNOWN 0x00000004 #define OBJECT_R "object_r" #define OBJECT_R_VAL 1 #define POLICYDB_MAGIC SELINUX_MAGIC #define POLICYDB_STRING "SE Linux" struct policy_file { char *data; size_t len; }; struct policy_data { struct policydb *p; void *fp; }; static inline int next_entry(void *buf, struct policy_file *fp, size_t bytes) { if (bytes > fp->len) return -EINVAL; memcpy(buf, fp->data, bytes); fp->data += bytes; fp->len -= bytes; return 0; } static inline int put_entry(const void *buf, size_t bytes, int num, struct policy_file *fp) { size_t len = bytes * num; if (len > fp->len) return -EINVAL; memcpy(fp->data, buf, len); fp->data += len; fp->len -= len; return 0; } static inline char *sym_name(struct policydb *p, unsigned int sym_num, unsigned int element_nr) { return p->sym_val_to_name[sym_num][element_nr]; } extern u16 string_to_security_class(struct policydb *p, const char *name); extern u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name); #endif /* _SS_POLICYDB_H_ */ |
| 1856 801 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 | #ifndef __LICENSE_H #define __LICENSE_H static inline int license_is_gpl_compatible(const char *license) { return (strcmp(license, "GPL") == 0 || strcmp(license, "GPL v2") == 0 || strcmp(license, "GPL and additional rights") == 0 || strcmp(license, "Dual BSD/GPL") == 0 || strcmp(license, "Dual MIT/GPL") == 0 || strcmp(license, "Dual MPL/GPL") == 0); } #endif |
| 399 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * include/linux/eventpoll.h ( Efficient event polling implementation ) * Copyright (C) 2001,...,2006 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #ifndef _LINUX_EVENTPOLL_H #define _LINUX_EVENTPOLL_H #include <uapi/linux/eventpoll.h> #include <uapi/linux/kcmp.h> /* Forward declarations to avoid compiler errors */ struct file; #ifdef CONFIG_EPOLL #ifdef CONFIG_CHECKPOINT_RESTORE struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* Used to initialize the epoll bits inside the "struct file" */ static inline void eventpoll_init_file(struct file *file) { INIT_LIST_HEAD(&file->f_ep_links); INIT_LIST_HEAD(&file->f_tfile_llink); } /* Used to release the epoll bits inside the "struct file" */ void eventpoll_release_file(struct file *file); /* * This is called from inside fs/file_table.c:__fput() to unlink files * from the eventpoll interface. We need to have this facility to cleanup * correctly files that are closed without being removed from the eventpoll * interface. */ static inline void eventpoll_release(struct file *file) { /* * Fast check to avoid the get/release of the semaphore. Since * we're doing this outside the semaphore lock, it might return * false negatives, but we don't care. It'll help in 99.99% of cases * to avoid the semaphore lock. False positives simply cannot happen * because the file in on the way to be removed and nobody ( but * eventpoll ) has still a reference to this file. */ if (likely(list_empty(&file->f_ep_links))) return; /* * The file is being closed while it is still linked to an epoll * descriptor. We need to handle this by correctly unlinking it * from its containers. */ eventpoll_release_file(file); } #else static inline void eventpoll_init_file(struct file *file) {} static inline void eventpoll_release(struct file *file) {} #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 9 9 9 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 | // SPDX-License-Identifier: GPL-2.0 #include <linux/crypto.h> #include <linux/err.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> #include <linux/tcp.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <net/inetpeer.h> #include <net/tcp.h> void tcp_fastopen_init_key_once(struct net *net) { u8 key[TCP_FASTOPEN_KEY_LENGTH]; struct tcp_fastopen_context *ctxt; rcu_read_lock(); ctxt = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctxt) { rcu_read_unlock(); return; } rcu_read_unlock(); /* tcp_fastopen_reset_cipher publishes the new context * atomically, so we allow this race happening here. * * All call sites of tcp_fastopen_cookie_gen also check * for a valid cookie, so this is an acceptable risk. */ get_random_bytes(key, sizeof(key)); tcp_fastopen_reset_cipher(net, NULL, key, NULL); } static void tcp_fastopen_ctx_free(struct rcu_head *head) { struct tcp_fastopen_context *ctx = container_of(head, struct tcp_fastopen_context, rcu); kzfree(ctx); } void tcp_fastopen_destroy_cipher(struct sock *sk) { struct tcp_fastopen_context *ctx; ctx = rcu_dereference_protected( inet_csk(sk)->icsk_accept_queue.fastopenq.ctx, 1); if (ctx) call_rcu(&ctx->rcu, tcp_fastopen_ctx_free); } void tcp_fastopen_ctx_destroy(struct net *net) { struct tcp_fastopen_context *ctxt; spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); ctxt = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, NULL); spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); if (ctxt) call_rcu(&ctxt->rcu, tcp_fastopen_ctx_free); } int tcp_fastopen_reset_cipher(struct net *net, struct sock *sk, void *primary_key, void *backup_key) { struct tcp_fastopen_context *ctx, *octx; struct fastopen_queue *q; int err = 0; ctx = kmalloc(sizeof(*ctx), GFP_KERNEL); if (!ctx) { err = -ENOMEM; goto out; } ctx->key[0].key[0] = get_unaligned_le64(primary_key); ctx->key[0].key[1] = get_unaligned_le64(primary_key + 8); if (backup_key) { ctx->key[1].key[0] = get_unaligned_le64(backup_key); ctx->key[1].key[1] = get_unaligned_le64(backup_key + 8); ctx->num = 2; } else { ctx->num = 1; } spin_lock(&net->ipv4.tcp_fastopen_ctx_lock); if (sk) { q = &inet_csk(sk)->icsk_accept_queue.fastopenq; octx = rcu_dereference_protected(q->ctx, lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); rcu_assign_pointer(q->ctx, ctx); } else { octx = rcu_dereference_protected(net->ipv4.tcp_fastopen_ctx, lockdep_is_held(&net->ipv4.tcp_fastopen_ctx_lock)); rcu_assign_pointer(net->ipv4.tcp_fastopen_ctx, ctx); } spin_unlock(&net->ipv4.tcp_fastopen_ctx_lock); if (octx) call_rcu(&octx->rcu, tcp_fastopen_ctx_free); out: return err; } int tcp_fastopen_get_cipher(struct net *net, struct inet_connection_sock *icsk, u64 *key) { struct tcp_fastopen_context *ctx; int n_keys = 0, i; rcu_read_lock(); if (icsk) ctx = rcu_dereference(icsk->icsk_accept_queue.fastopenq.ctx); else ctx = rcu_dereference(net->ipv4.tcp_fastopen_ctx); if (ctx) { n_keys = tcp_fastopen_context_len(ctx); for (i = 0; i < n_keys; i++) { put_unaligned_le64(ctx->key[i].key[0], key + (i * 2)); put_unaligned_le64(ctx->key[i].key[1], key + (i * 2) + 1); } } rcu_read_unlock(); return n_keys; } static bool __tcp_fastopen_cookie_gen_cipher(struct request_sock *req, struct sk_buff *syn, const siphash_key_t *key, struct tcp_fastopen_cookie *foc) { BUILD_BUG_ON(TCP_FASTOPEN_COOKIE_SIZE != sizeof(u64)); if (req->rsk_ops->family == AF_INET) { const struct iphdr *iph = ip_hdr(syn); foc->val[0] = cpu_to_le64(siphash(&iph->saddr, sizeof(iph->saddr) + sizeof(iph->daddr), key)); foc->len = TCP_FASTOPEN_COOKIE_SIZE; return true; } #if IS_ENABLED(CONFIG_IPV6) if (req->rsk_ops->family == AF_INET6) { const struct ipv6hdr *ip6h = ipv6_hdr(syn); foc->val[0] = cpu_to_le64(siphash(&ip6h->saddr, sizeof(ip6h->saddr) + sizeof(ip6h->daddr), key)); foc->len = TCP_FASTOPEN_COOKIE_SIZE; return true; } #endif return false; } /* Generate the fastopen cookie by applying SipHash to both the source and * destination addresses. */ static void tcp_fastopen_cookie_gen(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *foc) { struct tcp_fastopen_context *ctx; rcu_read_lock(); ctx = tcp_fastopen_get_ctx(sk); if (ctx) __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[0], foc); rcu_read_unlock(); } /* If an incoming SYN or SYNACK frame contains a payload and/or FIN, * queue this additional data / FIN. */ void tcp_fastopen_add_skb(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); if (TCP_SKB_CB(skb)->end_seq == tp->rcv_nxt) return; skb = skb_clone(skb, GFP_ATOMIC); if (!skb) return; skb_dst_drop(skb); /* segs_in has been initialized to 1 in tcp_create_openreq_child(). * Hence, reset segs_in to 0 before calling tcp_segs_in() * to avoid double counting. Also, tcp_segs_in() expects * skb->len to include the tcp_hdrlen. Hence, it should * be called before __skb_pull(). */ tp->segs_in = 0; tcp_segs_in(tp, skb); __skb_pull(skb, tcp_hdrlen(skb)); sk_forced_mem_schedule(sk, skb->truesize); skb_set_owner_r(skb, sk); TCP_SKB_CB(skb)->seq++; TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_SYN; tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq; __skb_queue_tail(&sk->sk_receive_queue, skb); tp->syn_data_acked = 1; /* u64_stats_update_begin(&tp->syncp) not needed here, * as we certainly are not changing upper 32bit value (0) */ tp->bytes_received = skb->len; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) tcp_fin(sk); } /* returns 0 - no key match, 1 for primary, 2 for backup */ static int tcp_fastopen_cookie_gen_check(struct sock *sk, struct request_sock *req, struct sk_buff *syn, struct tcp_fastopen_cookie *orig, struct tcp_fastopen_cookie *valid_foc) { struct tcp_fastopen_cookie search_foc = { .len = -1 }; struct tcp_fastopen_cookie *foc = valid_foc; struct tcp_fastopen_context *ctx; int i, ret = 0; rcu_read_lock(); ctx = tcp_fastopen_get_ctx(sk); if (!ctx) goto out; for (i = 0; i < tcp_fastopen_context_len(ctx); i++) { __tcp_fastopen_cookie_gen_cipher(req, syn, &ctx->key[i], foc); if (tcp_fastopen_cookie_match(foc, orig)) { ret = i + 1; goto out; } foc = &search_foc; } out: rcu_read_unlock(); return ret; } static struct sock *tcp_fastopen_create_child(struct sock *sk, struct sk_buff *skb, struct request_sock *req) { struct tcp_sock *tp; struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; struct sock *child; bool own_req; child = inet_csk(sk)->icsk_af_ops->syn_recv_sock(sk, skb, req, NULL, NULL, &own_req); if (!child) return NULL; spin_lock(&queue->fastopenq.lock); queue->fastopenq.qlen++; spin_unlock(&queue->fastopenq.lock); /* Initialize the child socket. Have to fix some values to take * into account the child is a Fast Open socket and is created * only out of the bits carried in the SYN packet. */ tp = tcp_sk(child); rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never * scaled. So correct it appropriately. */ tp->snd_wnd = ntohs(tcp_hdr(skb)->window); tp->max_window = tp->snd_wnd; /* Activate the retrans timer so that SYNACK can be retransmitted. * The request socket is not added to the ehash * because it's been added to the accept queue directly. */ inet_csk_reset_xmit_timer(child, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT, TCP_RTO_MAX); refcount_set(&req->rsk_refcnt, 2); /* Now finish processing the fastopen child socket. */ tcp_init_transfer(child, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; tcp_fastopen_add_skb(child, skb); tcp_rsk(req)->rcv_nxt = tp->rcv_nxt; tp->rcv_wup = tp->rcv_nxt; /* tcp_conn_request() is sending the SYNACK, * and queues the child into listener accept queue. */ return child; } static bool tcp_fastopen_queue_check(struct sock *sk) { struct fastopen_queue *fastopenq; int max_qlen; /* Make sure the listener has enabled fastopen, and we don't * exceed the max # of pending TFO requests allowed before trying * to validating the cookie in order to avoid burning CPU cycles * unnecessarily. * * XXX (TFO) - The implication of checking the max_qlen before * processing a cookie request is that clients can't differentiate * between qlen overflow causing Fast Open to be disabled * temporarily vs a server not supporting Fast Open at all. */ fastopenq = &inet_csk(sk)->icsk_accept_queue.fastopenq; max_qlen = READ_ONCE(fastopenq->max_qlen); if (max_qlen == 0) return false; if (fastopenq->qlen >= max_qlen) { struct request_sock *req1; spin_lock(&fastopenq->lock); req1 = fastopenq->rskq_rst_head; if (!req1 || time_after(req1->rsk_timer.expires, jiffies)) { __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENLISTENOVERFLOW); spin_unlock(&fastopenq->lock); return false; } fastopenq->rskq_rst_head = req1->dl_next; fastopenq->qlen--; spin_unlock(&fastopenq->lock); reqsk_put(req1); } return true; } static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } /* Returns true if we should perform Fast Open on the SYN. The cookie (foc) * may be updated and return the client in the SYN-ACK later. E.g., Fast Open * cookie request (foc->len == 0). */ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct tcp_fastopen_cookie *foc, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; int ret = 0; if (foc->len == 0) /* Client requests a cookie */ NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENCOOKIEREQD); if (!((tcp_fastopen & TFO_SERVER_ENABLE) && (syn_data || foc->len >= 0) && tcp_fastopen_queue_check(sk))) { foc->len = -1; return NULL; } if (tcp_fastopen_no_cookie(sk, dst, TFO_SERVER_COOKIE_NOT_REQD)) goto fastopen; if (foc->len == 0) { /* Client requests a cookie. */ tcp_fastopen_cookie_gen(sk, req, skb, &valid_foc); } else if (foc->len > 0) { ret = tcp_fastopen_cookie_gen_check(sk, req, skb, foc, &valid_foc); if (!ret) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } else { /* Cookie is valid. Create a (full) child socket to * accept the data in SYN before returning a SYN-ACK to * ack the data. If we fail to create the socket, fall * back and ack the ISN only but includes the same * cookie. * * Note: Data-less SYN with valid cookie is allowed to * send data in SYN_RECV state. */ fastopen: child = tcp_fastopen_create_child(sk, skb, req); if (child) { if (ret == 2) { valid_foc.exp = foc->exp; *foc = valid_foc; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEALTKEY); } else { foc->len = -1; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVE); return child; } NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENPASSIVEFAIL); } } valid_foc.exp = foc->exp; *foc = valid_foc; return NULL; } bool tcp_fastopen_cookie_check(struct sock *sk, u16 *mss, struct tcp_fastopen_cookie *cookie) { const struct dst_entry *dst; tcp_fastopen_cache_get(sk, mss, cookie); /* Firewall blackhole issue check */ if (tcp_fastopen_active_should_disable(sk)) { cookie->len = -1; return false; } dst = __sk_dst_get(sk); if (tcp_fastopen_no_cookie(sk, dst, TFO_CLIENT_NO_COOKIE)) { cookie->len = -1; return true; } if (cookie->len > 0) return true; tcp_sk(sk)->fastopen_client_fail = TFO_COOKIE_UNAVAILABLE; return false; } /* This function checks if we want to defer sending SYN until the first * write(). We defer under the following conditions: * 1. fastopen_connect sockopt is set * 2. we have a valid cookie * Return value: return true if we want to defer until application writes data * return false if we want to send out SYN immediately */ bool tcp_fastopen_defer_connect(struct sock *sk, int *err) { struct tcp_fastopen_cookie cookie = { .len = 0 }; struct tcp_sock *tp = tcp_sk(sk); u16 mss; if (tp->fastopen_connect && !tp->fastopen_req) { if (tcp_fastopen_cookie_check(sk, &mss, &cookie)) { inet_sk(sk)->defer_connect = 1; return true; } /* Alloc fastopen_req in order for FO option to be included * in SYN */ tp->fastopen_req = kzalloc(sizeof(*tp->fastopen_req), sk->sk_allocation); if (tp->fastopen_req) tp->fastopen_req->cookie = cookie; else *err = -ENOBUFS; } return false; } EXPORT_SYMBOL(tcp_fastopen_defer_connect); /* * The following code block is to deal with middle box issues with TFO: * Middlebox firewall issues can potentially cause server's data being * blackholed after a successful 3WHS using TFO. * The proposed solution is to disable active TFO globally under the * following circumstances: * 1. client side TFO socket receives out of order FIN * 2. client side TFO socket receives out of order RST * 3. client side TFO socket has timed out three times consecutively during * or after handshake * We disable active side TFO globally for 1hr at first. Then if it * happens again, we disable it for 2h, then 4h, 8h, ... * And we reset the timeout back to 1hr when we see a successful active * TFO connection with data exchanges. */ /* Disable active TFO and record current jiffies and * tfo_active_disable_times */ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ WRITE_ONCE(net->ipv4.tfo_active_disable_stamp, jiffies); /* Paired with smp_rmb() in tcp_fastopen_active_should_disable(). * We want net->ipv4.tfo_active_disable_stamp to be updated first. */ smp_mb__before_atomic(); atomic_inc(&net->ipv4.tfo_active_disable_times); NET_INC_STATS(net, LINUX_MIB_TCPFASTOPENBLACKHOLE); } /* Calculate timeout for tfo active disable * Return true if we are still in the active TFO disable period * Return false if timeout already expired and we should use active TFO */ bool tcp_fastopen_active_should_disable(struct sock *sk) { unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; int tfo_da_times = atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times); unsigned long timeout; int multiplier; if (!tfo_da_times) return false; /* Paired with smp_mb__before_atomic() in tcp_fastopen_active_disable() */ smp_rmb(); /* Limit timout to max: 2^6 * initial timeout */ multiplier = 1 << min(tfo_da_times - 1, 6); /* Paired with the WRITE_ONCE() in tcp_fastopen_active_disable(). */ timeout = READ_ONCE(sock_net(sk)->ipv4.tfo_active_disable_stamp) + multiplier * tfo_bh_timeout * HZ; if (time_before(jiffies, timeout)) return true; /* Mark check bit so we can check for successful active TFO * condition and reset tfo_active_disable_times */ tcp_sk(sk)->syn_fastopen_ch = 1; return false; } /* Disable active TFO if FIN is the only packet in the ofo queue * and no data is received. * Also check if we can reset tfo_active_disable_times if data is * received successfully on a marked active TFO sockets opened on * a non-loopback interface */ void tcp_fastopen_active_disable_ofo_check(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct dst_entry *dst; struct sk_buff *skb; if (!tp->syn_fastopen) return; if (!tp->data_segs_in) { skb = skb_rb_first(&tp->out_of_order_queue); if (skb && !skb_rb_next(skb)) { if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) { tcp_fastopen_active_disable(sk); return; } } } else if (tp->syn_fastopen_ch && atomic_read(&sock_net(sk)->ipv4.tfo_active_disable_times)) { dst = sk_dst_get(sk); if (!(dst && dst->dev && (dst->dev->flags & IFF_LOOPBACK))) atomic_set(&sock_net(sk)->ipv4.tfo_active_disable_times, 0); dst_release(dst); } } void tcp_fastopen_active_detect_blackhole(struct sock *sk, bool expired) { u32 timeouts = inet_csk(sk)->icsk_retransmits; struct tcp_sock *tp = tcp_sk(sk); /* Broken middle-boxes may black-hole Fast Open connection during or * even after the handshake. Be extremely conservative and pause * Fast Open globally after hitting the third consecutive timeout or * exceeding the configured timeout limit. */ if ((tp->syn_fastopen || tp->syn_data || tp->syn_data_acked) && (timeouts == 2 || (timeouts < 2 && expired))) { tcp_fastopen_active_disable(sk); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVEFAIL); } } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PTRACE_H #define _ASM_X86_PTRACE_H #include <asm/segment.h> #include <asm/page_types.h> #include <uapi/asm/ptrace.h> #ifndef __ASSEMBLY__ #ifdef __i386__ struct pt_regs { /* * NB: 32-bit x86 CPUs are inconsistent as what happens in the * following cases (where %seg represents a segment register): * * - pushl %seg: some do a 16-bit write and leave the high * bits alone * - movl %seg, [mem]: some do a 16-bit write despite the movl * - IDT entry: some (e.g. 486) will leave the high bits of CS * and (if applicable) SS undefined. * * Fortunately, x86-32 doesn't read the high bits on POP or IRET, * so we can just treat all of the segment registers as 16-bit * values. */ unsigned long bx; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; unsigned long bp; unsigned long ax; unsigned short ds; unsigned short __dsh; unsigned short es; unsigned short __esh; unsigned short fs; unsigned short __fsh; /* On interrupt, gs and __gsh store the vector number. */ unsigned short gs; unsigned short __gsh; /* On interrupt, this is the error code. */ unsigned long orig_ax; unsigned long ip; unsigned short cs; unsigned short __csh; unsigned long flags; unsigned long sp; unsigned short ss; unsigned short __ssh; }; #else /* __i386__ */ struct pt_regs { /* * C ABI says these regs are callee-preserved. They aren't saved on kernel entry * unless syscall needs a complete, fully filled "struct pt_regs". */ unsigned long r15; unsigned long r14; unsigned long r13; unsigned long r12; unsigned long bp; unsigned long bx; /* These regs are callee-clobbered. Always saved on kernel entry. */ unsigned long r11; unsigned long r10; unsigned long r9; unsigned long r8; unsigned long ax; unsigned long cx; unsigned long dx; unsigned long si; unsigned long di; /* * On syscall entry, this is syscall#. On CPU exception, this is error code. * On hw interrupt, it's IRQ number: */ unsigned long orig_ax; /* Return frame for iretq */ unsigned long ip; unsigned long cs; unsigned long flags; unsigned long sp; unsigned long ss; /* top of stack page */ }; #endif /* !__i386__ */ #ifdef CONFIG_PARAVIRT #include <asm/paravirt_types.h> #endif struct cpuinfo_x86; struct task_struct; extern unsigned long profile_pc(struct pt_regs *regs); extern unsigned long convert_ip_to_linear(struct task_struct *child, struct pt_regs *regs); extern void send_sigtrap(struct pt_regs *regs, int error_code, int si_code); static inline unsigned long regs_return_value(struct pt_regs *regs) { return regs->ax; } static inline void regs_set_return_value(struct pt_regs *regs, unsigned long rc) { regs->ax = rc; } /* * user_mode(regs) determines whether a register set came from user * mode. On x86_32, this is true if V8086 mode was enabled OR if the * register set was from protected mode with RPL-3 CS value. This * tricky test checks that with one comparison. * * On x86_64, vm86 mode is mercifully nonexistent, and we don't need * the extra check. */ static inline int user_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return ((regs->cs & SEGMENT_RPL_MASK) | (regs->flags & X86_VM_MASK)) >= USER_RPL; #else return !!(regs->cs & 3); #endif } static inline int v8086_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_32 return (regs->flags & X86_VM_MASK); #else return 0; /* No V86 mode support in long mode */ #endif } static inline bool user_64bit_mode(struct pt_regs *regs) { #ifdef CONFIG_X86_64 #ifndef CONFIG_PARAVIRT_XXL /* * On non-paravirt systems, this is the only long mode CPL 3 * selector. We do not allow long mode selectors in the LDT. */ return regs->cs == __USER_CS; #else /* Headers are too twisted for this to go in paravirt.h. */ return regs->cs == __USER_CS || regs->cs == pv_info.extra_user_64bit_cs; #endif #else /* !CONFIG_X86_64 */ return false; #endif } #ifdef CONFIG_X86_64 #define current_user_stack_pointer() current_pt_regs()->sp #define compat_user_stack_pointer() current_pt_regs()->sp #endif static inline unsigned long kernel_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline unsigned long instruction_pointer(struct pt_regs *regs) { return regs->ip; } static inline void instruction_pointer_set(struct pt_regs *regs, unsigned long val) { regs->ip = val; } static inline unsigned long frame_pointer(struct pt_regs *regs) { return regs->bp; } static inline unsigned long user_stack_pointer(struct pt_regs *regs) { return regs->sp; } static inline void user_stack_pointer_set(struct pt_regs *regs, unsigned long val) { regs->sp = val; } /* Query offset/name of register from its name/offset */ extern int regs_query_register_offset(const char *name); extern const char *regs_query_register_name(unsigned int offset); #define MAX_REG_OFFSET (offsetof(struct pt_regs, ss)) /** * regs_get_register() - get register value from its offset * @regs: pt_regs from which register value is gotten. * @offset: offset number of the register. * * regs_get_register returns the value of a register. The @offset is the * offset of the register in struct pt_regs address which specified by @regs. * If @offset is bigger than MAX_REG_OFFSET, this returns 0. */ static inline unsigned long regs_get_register(struct pt_regs *regs, unsigned int offset) { if (unlikely(offset > MAX_REG_OFFSET)) return 0; #ifdef CONFIG_X86_32 /* The selector fields are 16-bit. */ if (offset == offsetof(struct pt_regs, cs) || offset == offsetof(struct pt_regs, ss) || offset == offsetof(struct pt_regs, ds) || offset == offsetof(struct pt_regs, es) || offset == offsetof(struct pt_regs, fs) || offset == offsetof(struct pt_regs, gs)) { return *(u16 *)((unsigned long)regs + offset); } #endif return *(unsigned long *)((unsigned long)regs + offset); } /** * regs_within_kernel_stack() - check the address in the stack * @regs: pt_regs which contains kernel stack pointer. * @addr: address which is checked. * * regs_within_kernel_stack() checks @addr is within the kernel stack page(s). * If @addr is within the kernel stack, it returns true. If not, returns false. */ static inline int regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (regs->sp & ~(THREAD_SIZE - 1))); } /** * regs_get_kernel_stack_nth_addr() - get the address of the Nth entry on stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns the address of the @n th entry of the * kernel stack which is specified by @regs. If the @n th entry is NOT in * the kernel stack, this returns NULL. */ static inline unsigned long *regs_get_kernel_stack_nth_addr(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)regs->sp; addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return addr; else return NULL; } /* To avoid include hell, we can't include uaccess.h */ extern long probe_kernel_read(void *dst, const void *src, size_t size); /** * regs_get_kernel_stack_nth() - get Nth entry of the stack * @regs: pt_regs which contains kernel stack pointer. * @n: stack entry number. * * regs_get_kernel_stack_nth() returns @n th entry of the kernel stack which * is specified by @regs. If the @n th entry is NOT in the kernel stack * this returns 0. */ static inline unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr; unsigned long val; long ret; addr = regs_get_kernel_stack_nth_addr(regs, n); if (addr) { ret = probe_kernel_read(&val, addr, sizeof(val)); if (!ret) return val; } return 0; } /** * regs_get_kernel_argument() - get Nth function argument in kernel * @regs: pt_regs of that context * @n: function argument number (start from 0) * * regs_get_argument() returns @n th argument of the function call. * Note that this chooses most probably assignment, in some case * it can be incorrect. * This is expected to be called from kprobes or ftrace with regs * where the top of stack is the return address. */ static inline unsigned long regs_get_kernel_argument(struct pt_regs *regs, unsigned int n) { static const unsigned int argument_offs[] = { #ifdef __i386__ offsetof(struct pt_regs, ax), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), #define NR_REG_ARGUMENTS 3 #else offsetof(struct pt_regs, di), offsetof(struct pt_regs, si), offsetof(struct pt_regs, dx), offsetof(struct pt_regs, cx), offsetof(struct pt_regs, r8), offsetof(struct pt_regs, r9), #define NR_REG_ARGUMENTS 6 #endif }; if (n >= NR_REG_ARGUMENTS) { n -= NR_REG_ARGUMENTS - 1; return regs_get_kernel_stack_nth(regs, n); } else return regs_get_register(regs, argument_offs[n]); } #define arch_has_single_step() (1) #ifdef CONFIG_X86_DEBUGCTLMSR #define arch_has_block_step() (1) #else #define arch_has_block_step() (boot_cpu_data.x86 >= 6) #endif #define ARCH_HAS_USER_SINGLE_STEP_REPORT /* * When hitting ptrace_stop(), we cannot return using SYSRET because * that does not restore the full CPU state, only a minimal set. The * ptracer can change arbitrary register values, which is usually okay * because the usual ptrace stops run off the signal delivery path which * forces IRET; however, ptrace_event() stops happen in arbitrary places * in the kernel and don't force IRET path. * * So force IRET path after a ptrace stop. */ #define arch_ptrace_stop_needed(code, info) \ ({ \ force_iret(); \ false; \ }) struct user_desc; extern int do_get_thread_area(struct task_struct *p, int idx, struct user_desc __user *info); extern int do_set_thread_area(struct task_struct *p, int idx, struct user_desc __user *info, int can_allocate); #endif /* !__ASSEMBLY__ */ #endif /* _ASM_X86_PTRACE_H */ |
| 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_PARAVIRT_H #define _ASM_X86_PARAVIRT_H /* Various instructions on x86 need to be replaced for * para-virtualization: those hooks are defined here. */ #ifdef CONFIG_PARAVIRT #include <asm/pgtable_types.h> #include <asm/asm.h> #include <asm/nospec-branch.h> #include <asm/paravirt_types.h> #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/types.h> #include <linux/cpumask.h> #include <asm/frame.h> static inline unsigned long long paravirt_sched_clock(void) { return PVOP_CALL0(unsigned long long, time.sched_clock); } struct static_key; extern struct static_key paravirt_steal_enabled; extern struct static_key paravirt_steal_rq_enabled; __visible void __native_queued_spin_unlock(struct qspinlock *lock); bool pv_is_native_spin_unlock(void); __visible bool __native_vcpu_is_preempted(long cpu); bool pv_is_native_vcpu_is_preempted(void); static inline u64 paravirt_steal_clock(int cpu) { return PVOP_CALL1(u64, time.steal_clock, cpu); } /* The paravirtualized I/O functions */ static inline void slow_down_io(void) { pv_ops.cpu.io_delay(); #ifdef REALLY_SLOW_IO pv_ops.cpu.io_delay(); pv_ops.cpu.io_delay(); pv_ops.cpu.io_delay(); #endif } static inline void __flush_tlb(void) { PVOP_VCALL0(mmu.flush_tlb_user); } static inline void __flush_tlb_global(void) { PVOP_VCALL0(mmu.flush_tlb_kernel); } static inline void __flush_tlb_one_user(unsigned long addr) { PVOP_VCALL1(mmu.flush_tlb_one_user, addr); } static inline void flush_tlb_others(const struct cpumask *cpumask, const struct flush_tlb_info *info) { PVOP_VCALL2(mmu.flush_tlb_others, cpumask, info); } static inline void paravirt_tlb_remove_table(struct mmu_gather *tlb, void *table) { PVOP_VCALL2(mmu.tlb_remove_table, tlb, table); } static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) { PVOP_VCALL1(mmu.exit_mmap, mm); } #ifdef CONFIG_PARAVIRT_XXL static inline void load_sp0(unsigned long sp0) { PVOP_VCALL1(cpu.load_sp0, sp0); } /* The paravirtualized CPUID instruction. */ static inline void __cpuid(unsigned int *eax, unsigned int *ebx, unsigned int *ecx, unsigned int *edx) { PVOP_VCALL4(cpu.cpuid, eax, ebx, ecx, edx); } /* * These special macros can be used to get or set a debugging register */ static inline unsigned long paravirt_get_debugreg(int reg) { return PVOP_CALL1(unsigned long, cpu.get_debugreg, reg); } #define get_debugreg(var, reg) var = paravirt_get_debugreg(reg) static inline void set_debugreg(unsigned long val, int reg) { PVOP_VCALL2(cpu.set_debugreg, reg, val); } static inline unsigned long read_cr0(void) { return PVOP_CALL0(unsigned long, cpu.read_cr0); } static inline void write_cr0(unsigned long x) { PVOP_VCALL1(cpu.write_cr0, x); } static inline unsigned long read_cr2(void) { return PVOP_CALLEE0(unsigned long, mmu.read_cr2); } static inline void write_cr2(unsigned long x) { PVOP_VCALL1(mmu.write_cr2, x); } static inline unsigned long __read_cr3(void) { return PVOP_CALL0(unsigned long, mmu.read_cr3); } static inline void write_cr3(unsigned long x) { PVOP_VCALL1(mmu.write_cr3, x); } static inline void __write_cr4(unsigned long x) { PVOP_VCALL1(cpu.write_cr4, x); } static inline void arch_safe_halt(void) { PVOP_VCALL0(irq.safe_halt); } static inline void halt(void) { PVOP_VCALL0(irq.halt); } static inline void wbinvd(void) { PVOP_VCALL0(cpu.wbinvd); } #define get_kernel_rpl() (pv_info.kernel_rpl) static inline u64 paravirt_read_msr(unsigned msr) { return PVOP_CALL1(u64, cpu.read_msr, msr); } static inline void paravirt_write_msr(unsigned msr, unsigned low, unsigned high) { PVOP_VCALL3(cpu.write_msr, msr, low, high); } static inline u64 paravirt_read_msr_safe(unsigned msr, int *err) { return PVOP_CALL2(u64, cpu.read_msr_safe, msr, err); } static inline int paravirt_write_msr_safe(unsigned msr, unsigned low, unsigned high) { return PVOP_CALL3(int, cpu.write_msr_safe, msr, low, high); } #define rdmsr(msr, val1, val2) \ do { \ u64 _l = paravirt_read_msr(msr); \ val1 = (u32)_l; \ val2 = _l >> 32; \ } while (0) #define wrmsr(msr, val1, val2) \ do { \ paravirt_write_msr(msr, val1, val2); \ } while (0) #define rdmsrl(msr, val) \ do { \ val = paravirt_read_msr(msr); \ } while (0) static inline void wrmsrl(unsigned msr, u64 val) { wrmsr(msr, (u32)val, (u32)(val>>32)); } #define wrmsr_safe(msr, a, b) paravirt_write_msr_safe(msr, a, b) /* rdmsr with exception handling */ #define rdmsr_safe(msr, a, b) \ ({ \ int _err; \ u64 _l = paravirt_read_msr_safe(msr, &_err); \ (*a) = (u32)_l; \ (*b) = _l >> 32; \ _err; \ }) static inline int rdmsrl_safe(unsigned msr, unsigned long long *p) { int err; *p = paravirt_read_msr_safe(msr, &err); return err; } static inline unsigned long long paravirt_read_pmc(int counter) { return PVOP_CALL1(u64, cpu.read_pmc, counter); } #define rdpmc(counter, low, high) \ do { \ u64 _l = paravirt_read_pmc(counter); \ low = (u32)_l; \ high = _l >> 32; \ } while (0) #define rdpmcl(counter, val) ((val) = paravirt_read_pmc(counter)) static inline void paravirt_alloc_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(cpu.alloc_ldt, ldt, entries); } static inline void paravirt_free_ldt(struct desc_struct *ldt, unsigned entries) { PVOP_VCALL2(cpu.free_ldt, ldt, entries); } static inline void load_TR_desc(void) { PVOP_VCALL0(cpu.load_tr_desc); } static inline void load_gdt(const struct desc_ptr *dtr) { PVOP_VCALL1(cpu.load_gdt, dtr); } static inline void load_idt(const struct desc_ptr *dtr) { PVOP_VCALL1(cpu.load_idt, dtr); } static inline void set_ldt(const void *addr, unsigned entries) { PVOP_VCALL2(cpu.set_ldt, addr, entries); } static inline unsigned long paravirt_store_tr(void) { return PVOP_CALL0(unsigned long, cpu.store_tr); } #define store_tr(tr) ((tr) = paravirt_store_tr()) static inline void load_TLS(struct thread_struct *t, unsigned cpu) { PVOP_VCALL2(cpu.load_tls, t, cpu); } #ifdef CONFIG_X86_64 static inline void load_gs_index(unsigned int gs) { PVOP_VCALL1(cpu.load_gs_index, gs); } #endif static inline void write_ldt_entry(struct desc_struct *dt, int entry, const void *desc) { PVOP_VCALL3(cpu.write_ldt_entry, dt, entry, desc); } static inline void write_gdt_entry(struct desc_struct *dt, int entry, void *desc, int type) { PVOP_VCALL4(cpu.write_gdt_entry, dt, entry, desc, type); } static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g) { PVOP_VCALL3(cpu.write_idt_entry, dt, entry, g); } static inline void set_iopl_mask(unsigned mask) { PVOP_VCALL1(cpu.set_iopl_mask, mask); } static inline void paravirt_activate_mm(struct mm_struct *prev, struct mm_struct *next) { PVOP_VCALL2(mmu.activate_mm, prev, next); } static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { PVOP_VCALL2(mmu.dup_mmap, oldmm, mm); } static inline int paravirt_pgd_alloc(struct mm_struct *mm) { return PVOP_CALL1(int, mmu.pgd_alloc, mm); } static inline void paravirt_pgd_free(struct mm_struct *mm, pgd_t *pgd) { PVOP_VCALL2(mmu.pgd_free, mm, pgd); } static inline void paravirt_alloc_pte(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_pte, mm, pfn); } static inline void paravirt_release_pte(unsigned long pfn) { PVOP_VCALL1(mmu.release_pte, pfn); } static inline void paravirt_alloc_pmd(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_pmd, mm, pfn); } static inline void paravirt_release_pmd(unsigned long pfn) { PVOP_VCALL1(mmu.release_pmd, pfn); } static inline void paravirt_alloc_pud(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_pud, mm, pfn); } static inline void paravirt_release_pud(unsigned long pfn) { PVOP_VCALL1(mmu.release_pud, pfn); } static inline void paravirt_alloc_p4d(struct mm_struct *mm, unsigned long pfn) { PVOP_VCALL2(mmu.alloc_p4d, mm, pfn); } static inline void paravirt_release_p4d(unsigned long pfn) { PVOP_VCALL1(mmu.release_p4d, pfn); } static inline pte_t __pte(pteval_t val) { pteval_t ret; if (sizeof(pteval_t) > sizeof(long)) ret = PVOP_CALLEE2(pteval_t, mmu.make_pte, val, (u64)val >> 32); else ret = PVOP_CALLEE1(pteval_t, mmu.make_pte, val); return (pte_t) { .pte = ret }; } static inline pteval_t pte_val(pte_t pte) { pteval_t ret; if (sizeof(pteval_t) > sizeof(long)) ret = PVOP_CALLEE2(pteval_t, mmu.pte_val, pte.pte, (u64)pte.pte >> 32); else ret = PVOP_CALLEE1(pteval_t, mmu.pte_val, pte.pte); return ret; } static inline pgd_t __pgd(pgdval_t val) { pgdval_t ret; if (sizeof(pgdval_t) > sizeof(long)) ret = PVOP_CALLEE2(pgdval_t, mmu.make_pgd, val, (u64)val >> 32); else ret = PVOP_CALLEE1(pgdval_t, mmu.make_pgd, val); return (pgd_t) { ret }; } static inline pgdval_t pgd_val(pgd_t pgd) { pgdval_t ret; if (sizeof(pgdval_t) > sizeof(long)) ret = PVOP_CALLEE2(pgdval_t, mmu.pgd_val, pgd.pgd, (u64)pgd.pgd >> 32); else ret = PVOP_CALLEE1(pgdval_t, mmu.pgd_val, pgd.pgd); return ret; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pteval_t ret; ret = PVOP_CALL3(pteval_t, mmu.ptep_modify_prot_start, vma, addr, ptep); return (pte_t) { .pte = ret }; } static inline void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { if (sizeof(pteval_t) > sizeof(long)) /* 5 arg words */ pv_ops.mmu.ptep_modify_prot_commit(vma, addr, ptep, pte); else PVOP_VCALL4(mmu.ptep_modify_prot_commit, vma, addr, ptep, pte.pte); } static inline void set_pte(pte_t *ptep, pte_t pte) { if (sizeof(pteval_t) > sizeof(long)) PVOP_VCALL3(mmu.set_pte, ptep, pte.pte, (u64)pte.pte >> 32); else PVOP_VCALL2(mmu.set_pte, ptep, pte.pte); } static inline void set_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (sizeof(pteval_t) > sizeof(long)) /* 5 arg words */ pv_ops.mmu.set_pte_at(mm, addr, ptep, pte); else PVOP_VCALL4(mmu.set_pte_at, mm, addr, ptep, pte.pte); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { pmdval_t val = native_pmd_val(pmd); if (sizeof(pmdval_t) > sizeof(long)) PVOP_VCALL3(mmu.set_pmd, pmdp, val, (u64)val >> 32); else PVOP_VCALL2(mmu.set_pmd, pmdp, val); } #if CONFIG_PGTABLE_LEVELS >= 3 static inline pmd_t __pmd(pmdval_t val) { pmdval_t ret; if (sizeof(pmdval_t) > sizeof(long)) ret = PVOP_CALLEE2(pmdval_t, mmu.make_pmd, val, (u64)val >> 32); else ret = PVOP_CALLEE1(pmdval_t, mmu.make_pmd, val); return (pmd_t) { ret }; } static inline pmdval_t pmd_val(pmd_t pmd) { pmdval_t ret; if (sizeof(pmdval_t) > sizeof(long)) ret = PVOP_CALLEE2(pmdval_t, mmu.pmd_val, pmd.pmd, (u64)pmd.pmd >> 32); else ret = PVOP_CALLEE1(pmdval_t, mmu.pmd_val, pmd.pmd); return ret; } static inline void set_pud(pud_t *pudp, pud_t pud) { pudval_t val = native_pud_val(pud); if (sizeof(pudval_t) > sizeof(long)) PVOP_VCALL3(mmu.set_pud, pudp, val, (u64)val >> 32); else PVOP_VCALL2(mmu.set_pud, pudp, val); } #if CONFIG_PGTABLE_LEVELS >= 4 static inline pud_t __pud(pudval_t val) { pudval_t ret; ret = PVOP_CALLEE1(pudval_t, mmu.make_pud, val); return (pud_t) { ret }; } static inline pudval_t pud_val(pud_t pud) { return PVOP_CALLEE1(pudval_t, mmu.pud_val, pud.pud); } static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); } static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { p4dval_t val = native_p4d_val(p4d); PVOP_VCALL2(mmu.set_p4d, p4dp, val); } #if CONFIG_PGTABLE_LEVELS >= 5 static inline p4d_t __p4d(p4dval_t val) { p4dval_t ret = PVOP_CALLEE1(p4dval_t, mmu.make_p4d, val); return (p4d_t) { ret }; } static inline p4dval_t p4d_val(p4d_t p4d) { return PVOP_CALLEE1(p4dval_t, mmu.p4d_val, p4d.p4d); } static inline void __set_pgd(pgd_t *pgdp, pgd_t pgd) { PVOP_VCALL2(mmu.set_pgd, pgdp, native_pgd_val(pgd)); } #define set_pgd(pgdp, pgdval) do { \ if (pgtable_l5_enabled()) \ __set_pgd(pgdp, pgdval); \ else \ set_p4d((p4d_t *)(pgdp), (p4d_t) { (pgdval).pgd }); \ } while (0) #define pgd_clear(pgdp) do { \ if (pgtable_l5_enabled()) \ set_pgd(pgdp, __pgd(0)); \ } while (0) #endif /* CONFIG_PGTABLE_LEVELS == 5 */ static inline void p4d_clear(p4d_t *p4dp) { set_p4d(p4dp, __p4d(0)); } #endif /* CONFIG_PGTABLE_LEVELS == 4 */ #endif /* CONFIG_PGTABLE_LEVELS >= 3 */ #ifdef CONFIG_X86_PAE /* Special-case pte-setting operations for PAE, which can't update a 64-bit pte atomically */ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) { PVOP_VCALL3(mmu.set_pte_atomic, ptep, pte.pte, pte.pte >> 32); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { PVOP_VCALL3(mmu.pte_clear, mm, addr, ptep); } static inline void pmd_clear(pmd_t *pmdp) { PVOP_VCALL1(mmu.pmd_clear, pmdp); } #else /* !CONFIG_X86_PAE */ static inline void set_pte_atomic(pte_t *ptep, pte_t pte) { set_pte(ptep, pte); } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { set_pte_at(mm, addr, ptep, __pte(0)); } static inline void pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, __pmd(0)); } #endif /* CONFIG_X86_PAE */ #define __HAVE_ARCH_START_CONTEXT_SWITCH static inline void arch_start_context_switch(struct task_struct *prev) { PVOP_VCALL1(cpu.start_context_switch, prev); } static inline void arch_end_context_switch(struct task_struct *next) { PVOP_VCALL1(cpu.end_context_switch, next); } #define __HAVE_ARCH_ENTER_LAZY_MMU_MODE static inline void arch_enter_lazy_mmu_mode(void) { PVOP_VCALL0(mmu.lazy_mode.enter); } static inline void arch_leave_lazy_mmu_mode(void) { PVOP_VCALL0(mmu.lazy_mode.leave); } static inline void arch_flush_lazy_mmu_mode(void) { PVOP_VCALL0(mmu.lazy_mode.flush); } static inline void __set_fixmap(unsigned /* enum fixed_addresses */ idx, phys_addr_t phys, pgprot_t flags) { pv_ops.mmu.set_fixmap(idx, phys, flags); } #endif #if defined(CONFIG_SMP) && defined(CONFIG_PARAVIRT_SPINLOCKS) static __always_inline void pv_queued_spin_lock_slowpath(struct qspinlock *lock, u32 val) { PVOP_VCALL2(lock.queued_spin_lock_slowpath, lock, val); } static __always_inline void pv_queued_spin_unlock(struct qspinlock *lock) { PVOP_VCALLEE1(lock.queued_spin_unlock, lock); } static __always_inline void pv_wait(u8 *ptr, u8 val) { PVOP_VCALL2(lock.wait, ptr, val); } static __always_inline void pv_kick(int cpu) { PVOP_VCALL1(lock.kick, cpu); } static __always_inline bool pv_vcpu_is_preempted(long cpu) { return PVOP_CALLEE1(bool, lock.vcpu_is_preempted, cpu); } void __raw_callee_save___native_queued_spin_unlock(struct qspinlock *lock); bool __raw_callee_save___native_vcpu_is_preempted(long cpu); #endif /* SMP && PARAVIRT_SPINLOCKS */ #ifdef CONFIG_X86_32 #define PV_SAVE_REGS "pushl %ecx; pushl %edx;" #define PV_RESTORE_REGS "popl %edx; popl %ecx;" /* save and restore all caller-save registers, except return value */ #define PV_SAVE_ALL_CALLER_REGS "pushl %ecx;" #define PV_RESTORE_ALL_CALLER_REGS "popl %ecx;" #define PV_FLAGS_ARG "0" #define PV_EXTRA_CLOBBERS #define PV_VEXTRA_CLOBBERS #else /* save and restore all caller-save registers, except return value */ #define PV_SAVE_ALL_CALLER_REGS \ "push %rcx;" \ "push %rdx;" \ "push %rsi;" \ "push %rdi;" \ "push %r8;" \ "push %r9;" \ "push %r10;" \ "push %r11;" #define PV_RESTORE_ALL_CALLER_REGS \ "pop %r11;" \ "pop %r10;" \ "pop %r9;" \ "pop %r8;" \ "pop %rdi;" \ "pop %rsi;" \ "pop %rdx;" \ "pop %rcx;" /* We save some registers, but all of them, that's too much. We clobber all * caller saved registers but the argument parameter */ #define PV_SAVE_REGS "pushq %%rdi;" #define PV_RESTORE_REGS "popq %%rdi;" #define PV_EXTRA_CLOBBERS EXTRA_CLOBBERS, "rcx" , "rdx", "rsi" #define PV_VEXTRA_CLOBBERS EXTRA_CLOBBERS, "rdi", "rcx" , "rdx", "rsi" #define PV_FLAGS_ARG "D" #endif /* * Generate a thunk around a function which saves all caller-save * registers except for the return value. This allows C functions to * be called from assembler code where fewer than normal registers are * available. It may also help code generation around calls from C * code if the common case doesn't use many registers. * * When a callee is wrapped in a thunk, the caller can assume that all * arg regs and all scratch registers are preserved across the * call. The return value in rax/eax will not be saved, even for void * functions. */ #define PV_THUNK_NAME(func) "__raw_callee_save_" #func #define PV_CALLEE_SAVE_REGS_THUNK(func) \ extern typeof(func) __raw_callee_save_##func; \ \ asm(".pushsection .text;" \ ".globl " PV_THUNK_NAME(func) ";" \ ".type " PV_THUNK_NAME(func) ", @function;" \ PV_THUNK_NAME(func) ":" \ FRAME_BEGIN \ PV_SAVE_ALL_CALLER_REGS \ "call " #func ";" \ PV_RESTORE_ALL_CALLER_REGS \ FRAME_END \ "ret;" \ ".size " PV_THUNK_NAME(func) ", .-" PV_THUNK_NAME(func) ";" \ ".popsection") /* Get a reference to a callee-save function */ #define PV_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { __raw_callee_save_##func }) /* Promise that "func" already uses the right calling convention */ #define __PV_IS_CALLEE_SAVE(func) \ ((struct paravirt_callee_save) { func }) #ifdef CONFIG_PARAVIRT_XXL static inline notrace unsigned long arch_local_save_flags(void) { return PVOP_CALLEE0(unsigned long, irq.save_fl); } static inline notrace void arch_local_irq_restore(unsigned long f) { PVOP_VCALLEE1(irq.restore_fl, f); } static inline notrace void arch_local_irq_disable(void) { PVOP_VCALLEE0(irq.irq_disable); } static inline notrace void arch_local_irq_enable(void) { PVOP_VCALLEE0(irq.irq_enable); } static inline notrace unsigned long arch_local_irq_save(void) { unsigned long f; f = arch_local_save_flags(); arch_local_irq_disable(); return f; } #endif /* Make sure as little as possible of this mess escapes. */ #undef PARAVIRT_CALL #undef __PVOP_CALL #undef __PVOP_VCALL #undef PVOP_VCALL0 #undef PVOP_CALL0 #undef PVOP_VCALL1 #undef PVOP_CALL1 #undef PVOP_VCALL2 #undef PVOP_CALL2 #undef PVOP_VCALL3 #undef PVOP_CALL3 #undef PVOP_VCALL4 #undef PVOP_CALL4 extern void default_banner(void); #else /* __ASSEMBLY__ */ #define _PVSITE(ptype, ops, word, algn) \ 771:; \ ops; \ 772:; \ .pushsection .parainstructions,"a"; \ .align algn; \ word 771b; \ .byte ptype; \ .byte 772b-771b; \ .popsection #define COND_PUSH(set, mask, reg) \ .if ((~(set)) & mask); push %reg; .endif #define COND_POP(set, mask, reg) \ .if ((~(set)) & mask); pop %reg; .endif #ifdef CONFIG_X86_64 #define PV_SAVE_REGS(set) \ COND_PUSH(set, CLBR_RAX, rax); \ COND_PUSH(set, CLBR_RCX, rcx); \ COND_PUSH(set, CLBR_RDX, rdx); \ COND_PUSH(set, CLBR_RSI, rsi); \ COND_PUSH(set, CLBR_RDI, rdi); \ COND_PUSH(set, CLBR_R8, r8); \ COND_PUSH(set, CLBR_R9, r9); \ COND_PUSH(set, CLBR_R10, r10); \ COND_PUSH(set, CLBR_R11, r11) #define PV_RESTORE_REGS(set) \ COND_POP(set, CLBR_R11, r11); \ COND_POP(set, CLBR_R10, r10); \ COND_POP(set, CLBR_R9, r9); \ COND_POP(set, CLBR_R8, r8); \ COND_POP(set, CLBR_RDI, rdi); \ COND_POP(set, CLBR_RSI, rsi); \ COND_POP(set, CLBR_RDX, rdx); \ COND_POP(set, CLBR_RCX, rcx); \ COND_POP(set, CLBR_RAX, rax) #define PARA_PATCH(off) ((off) / 8) #define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .quad, 8) #define PARA_INDIRECT(addr) *addr(%rip) #else #define PV_SAVE_REGS(set) \ COND_PUSH(set, CLBR_EAX, eax); \ COND_PUSH(set, CLBR_EDI, edi); \ COND_PUSH(set, CLBR_ECX, ecx); \ COND_PUSH(set, CLBR_EDX, edx) #define PV_RESTORE_REGS(set) \ COND_POP(set, CLBR_EDX, edx); \ COND_POP(set, CLBR_ECX, ecx); \ COND_POP(set, CLBR_EDI, edi); \ COND_POP(set, CLBR_EAX, eax) #define PARA_PATCH(off) ((off) / 4) #define PARA_SITE(ptype, ops) _PVSITE(ptype, ops, .long, 4) #define PARA_INDIRECT(addr) *%cs:addr #endif #ifdef CONFIG_PARAVIRT_XXL #define INTERRUPT_RETURN \ PARA_SITE(PARA_PATCH(PV_CPU_iret), \ ANNOTATE_RETPOLINE_SAFE; \ jmp PARA_INDIRECT(pv_ops+PV_CPU_iret);) #define DISABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(PV_IRQ_irq_disable), \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_ops+PV_IRQ_irq_disable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #define ENABLE_INTERRUPTS(clobbers) \ PARA_SITE(PARA_PATCH(PV_IRQ_irq_enable), \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_ops+PV_IRQ_irq_enable); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif #ifdef CONFIG_X86_64 #ifdef CONFIG_PARAVIRT_XXL /* * If swapgs is used while the userspace stack is still current, * there's no way to call a pvop. The PV replacement *must* be * inlined, or the swapgs instruction must be trapped and emulated. */ #define SWAPGS_UNSAFE_STACK \ PARA_SITE(PARA_PATCH(PV_CPU_swapgs), swapgs) /* * Note: swapgs is very special, and in practise is either going to be * implemented with a single "swapgs" instruction or something very * special. Either way, we don't need to save any registers for * it. */ #define SWAPGS \ PARA_SITE(PARA_PATCH(PV_CPU_swapgs), \ ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_ops+PV_CPU_swapgs); \ ) #define USERGS_SYSRET64 \ PARA_SITE(PARA_PATCH(PV_CPU_usergs_sysret64), \ ANNOTATE_RETPOLINE_SAFE; \ jmp PARA_INDIRECT(pv_ops+PV_CPU_usergs_sysret64);) #ifdef CONFIG_DEBUG_ENTRY #define SAVE_FLAGS(clobbers) \ PARA_SITE(PARA_PATCH(PV_IRQ_save_fl), \ PV_SAVE_REGS(clobbers | CLBR_CALLEE_SAVE); \ ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_ops+PV_IRQ_save_fl); \ PV_RESTORE_REGS(clobbers | CLBR_CALLEE_SAVE);) #endif #endif /* CONFIG_PARAVIRT_XXL */ #endif /* CONFIG_X86_64 */ #ifdef CONFIG_PARAVIRT_XXL #define GET_CR2_INTO_AX \ PARA_SITE(PARA_PATCH(PV_MMU_read_cr2), \ ANNOTATE_RETPOLINE_SAFE; \ call PARA_INDIRECT(pv_ops+PV_MMU_read_cr2); \ ) #endif /* CONFIG_PARAVIRT_XXL */ #endif /* __ASSEMBLY__ */ #else /* CONFIG_PARAVIRT */ # define default_banner x86_init_noop #endif /* !CONFIG_PARAVIRT */ #ifndef __ASSEMBLY__ #ifndef CONFIG_PARAVIRT_XXL static inline void paravirt_arch_dup_mmap(struct mm_struct *oldmm, struct mm_struct *mm) { } #endif #ifndef CONFIG_PARAVIRT static inline void paravirt_arch_exit_mmap(struct mm_struct *mm) { } #endif #endif /* __ASSEMBLY__ */ #endif /* _ASM_X86_PARAVIRT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NET_AFUNIX_H #define __LINUX_NET_AFUNIX_H #include <linux/socket.h> #include <linux/un.h> #include <linux/mutex.h> #include <linux/refcount.h> #include <net/sock.h> void unix_inflight(struct user_struct *user, struct file *fp); void unix_notinflight(struct user_struct *user, struct file *fp); void unix_destruct_scm(struct sk_buff *skb); void unix_gc(void); void wait_for_unix_gc(void); struct sock *unix_get_socket(struct file *filp); struct sock *unix_peer_get(struct sock *sk); #define UNIX_HASH_SIZE 256 #define UNIX_HASH_BITS 8 extern unsigned int unix_tot_inflight; extern spinlock_t unix_table_lock; extern struct hlist_head unix_socket_table[2 * UNIX_HASH_SIZE]; struct unix_address { refcount_t refcnt; int len; unsigned int hash; struct sockaddr_un name[0]; }; struct unix_skb_parms { struct pid *pid; /* Skb credentials */ kuid_t uid; kgid_t gid; struct scm_fp_list *fp; /* Passed files */ #ifdef CONFIG_SECURITY_NETWORK u32 secid; /* Security ID */ #endif u32 consumed; } __randomize_layout; #define UNIXCB(skb) (*(struct unix_skb_parms *)&((skb)->cb)) /* The AF_UNIX socket */ struct unix_sock { /* WARNING: sk has to be the first member */ struct sock sk; struct unix_address *addr; struct path path; struct mutex iolock, bindlock; struct sock *peer; struct list_head link; unsigned long inflight; spinlock_t lock; unsigned long gc_flags; #define UNIX_GC_CANDIDATE 0 #define UNIX_GC_MAYBE_CYCLE 1 struct socket_wq peer_wq; wait_queue_entry_t peer_wake; }; static inline struct unix_sock *unix_sk(const struct sock *sk) { return (struct unix_sock *)sk; } #define unix_state_lock(s) spin_lock(&unix_sk(s)->lock) #define unix_state_unlock(s) spin_unlock(&unix_sk(s)->lock) enum unix_socket_lock_class { U_LOCK_NORMAL, U_LOCK_SECOND, /* for double locking, see unix_state_double_lock(). */ U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */ U_LOCK_GC_LISTENER, /* used for listening socket while determining gc * candidates to close a small race window. */ }; static inline void unix_state_lock_nested(struct sock *sk, enum unix_socket_lock_class subclass) { spin_lock_nested(&unix_sk(sk)->lock, subclass); } #define peer_wait peer_wq.wait long unix_inq_len(struct sock *sk); long unix_outq_len(struct sock *sk); #ifdef CONFIG_SYSCTL int unix_sysctl_register(struct net *net); void unix_sysctl_unregister(struct net *net); #else static inline int unix_sysctl_register(struct net *net) { return 0; } static inline void unix_sysctl_unregister(struct net *net) {} #endif #endif |
| 1 130 22 4 10 9 9 17 518 516 128 2 230 230 230 32 6 2 33 9 4 2 4 86 6 6 113 114 159 383 228 158 115 228 398 398 7 4 3 3 4 7 7 7 273 270 273 23 23 15 8 22 555 21 11 5 3 449 87 959 2 148 202 10 78 14 49 49 4 4 4 4 1 3 3 557 74 74 158 159 4 1 3 8 8 4 518 1 1 513 3 476 42 42 71 409 113 86 458 2 1 1 20 115 101 230 458 233 1 29 204 72 229 142 88 230 230 233 415 7 2 612 7 415 483 131 6 611 403 3 291 39 69 4 102 391 4 393 379 377 317 66 419 419 14 404 421 1 40 420 401 421 287 40 190 21 207 281 287 9 249 1 46 259 294 271 79 67 79 79 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * NET An implementation of the SOCKET network access protocol. * * Version: @(#)socket.c 1.1.93 18/02/95 * * Authors: Orest Zborowski, <obz@Kodak.COM> * Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * * Fixes: * Anonymous : NOTSOCK/BADF cleanup. Error fix in * shutdown() * Alan Cox : verify_area() fixes * Alan Cox : Removed DDI * Jonathan Kamens : SOCK_DGRAM reconnect bug * Alan Cox : Moved a load of checks to the very * top level. * Alan Cox : Move address structures to/from user * mode above the protocol layers. * Rob Janssen : Allow 0 length sends. * Alan Cox : Asynchronous I/O support (cribbed from the * tty drivers). * Niibe Yutaka : Asynchronous I/O for writes (4.4BSD style) * Jeff Uphoff : Made max number of sockets command-line * configurable. * Matti Aarnio : Made the number of sockets dynamic, * to be allocated when needed, and mr. * Uphoff's max is used as max to be * allowed to allocate. * Linus : Argh. removed all the socket allocation * altogether: it's in the inode now. * Alan Cox : Made sock_alloc()/sock_release() public * for NetROM and future kernel nfsd type * stuff. * Alan Cox : sendmsg/recvmsg basics. * Tom Dyas : Export net symbols. * Marcin Dalecki : Fixed problems with CONFIG_NET="n". * Alan Cox : Added thread locking to sys_* calls * for sockets. May have errors at the * moment. * Kevin Buhr : Fixed the dumb errors in the above. * Andi Kleen : Some small cleanups, optimizations, * and fixed a copy_from_user() bug. * Tigran Aivazian : sys_send(args) calls sys_sendto(args, NULL, 0) * Tigran Aivazian : Made listen(2) backlog sanity checks * protocol-independent * * This module is effectively the top level interface to the BSD socket * paradigm. * * Based upon Swansea University Computer Society NET3.039 */ #include <linux/mm.h> #include <linux/socket.h> #include <linux/file.h> #include <linux/net.h> #include <linux/interrupt.h> #include <linux/thread_info.h> #include <linux/rcupdate.h> #include <linux/netdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/mutex.h> #include <linux/if_bridge.h> #include <linux/if_frad.h> #include <linux/if_vlan.h> #include <linux/ptp_classify.h> #include <linux/init.h> #include <linux/poll.h> #include <linux/cache.h> #include <linux/module.h> #include <linux/highmem.h> #include <linux/mount.h> #include <linux/pseudo_fs.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/compat.h> #include <linux/kmod.h> #include <linux/audit.h> #include <linux/wireless.h> #include <linux/nsproxy.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/nospec.h> #include <linux/indirect_call_wrapper.h> #include <linux/uaccess.h> #include <asm/unistd.h> #include <net/compat.h> #include <net/wext.h> #include <net/cls_cgroup.h> #include <net/sock.h> #include <linux/netfilter.h> #include <linux/if_tun.h> #include <linux/ipv6_route.h> #include <linux/route.h> #include <linux/sockios.h> #include <net/busy_poll.h> #include <linux/errqueue.h> #ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to); static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from); static int sock_mmap(struct file *file, struct vm_area_struct *vma); static int sock_close(struct inode *inode, struct file *file); static __poll_t sock_poll(struct file *file, struct poll_table_struct *wait); static long sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #ifdef CONFIG_COMPAT static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg); #endif static int sock_fasync(int fd, struct file *filp, int on); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more); static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear * in the operation structures but are done directly via the socketcall() multiplexor. */ static const struct file_operations socket_file_ops = { .owner = THIS_MODULE, .llseek = no_llseek, .read_iter = sock_read_iter, .write_iter = sock_write_iter, .poll = sock_poll, .unlocked_ioctl = sock_ioctl, #ifdef CONFIG_COMPAT .compat_ioctl = compat_sock_ioctl, #endif .mmap = sock_mmap, .release = sock_close, .fasync = sock_fasync, .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, }; /* * The protocol list. Each protocol is registered in here. */ static DEFINE_SPINLOCK(net_family_lock); static const struct net_proto_family __rcu *net_families[NPROTO] __read_mostly; /* * Support routines. * Move socket addresses back and forth across the kernel/user * divide and look after the messy bits. */ /** * move_addr_to_kernel - copy a socket address into kernel space * @uaddr: Address in user space * @kaddr: Address in kernel space * @ulen: Length in user space * * The address is copied into kernel space. If the provided address is * too long an error code of -EINVAL is returned. If the copy gives * invalid addresses -EFAULT is returned. On a success 0 is returned. */ int move_addr_to_kernel(void __user *uaddr, int ulen, struct sockaddr_storage *kaddr) { if (ulen < 0 || ulen > sizeof(struct sockaddr_storage)) return -EINVAL; if (ulen == 0) return 0; if (copy_from_user(kaddr, uaddr, ulen)) return -EFAULT; return audit_sockaddr(ulen, kaddr); } /** * move_addr_to_user - copy an address to user space * @kaddr: kernel space address * @klen: length of address in kernel * @uaddr: user space address * @ulen: pointer to user length field * * The value pointed to by ulen on entry is the buffer length available. * This is overwritten with the buffer space used. -EINVAL is returned * if an overlong buffer is specified or a negative buffer size. -EFAULT * is returned if either the buffer or the length field are not * accessible. * After copying the data up to the limit the user specifies, the true * length of the data is written over the length limit the user * specified. Zero is returned for a success. */ static int move_addr_to_user(struct sockaddr_storage *kaddr, int klen, void __user *uaddr, int __user *ulen) { int err; int len; BUG_ON(klen > sizeof(struct sockaddr_storage)); err = get_user(len, ulen); if (err) return err; if (len > klen) len = klen; if (len < 0) return -EINVAL; if (len) { if (audit_sockaddr(klen, kaddr)) return -ENOMEM; if (copy_to_user(uaddr, kaddr, len)) return -EFAULT; } /* * "fromlen shall refer to the value before truncation.." * 1003.1g */ return __put_user(klen, ulen); } static struct kmem_cache *sock_inode_cachep __ro_after_init; static struct inode *sock_alloc_inode(struct super_block *sb) { struct socket_alloc *ei; ei = kmem_cache_alloc(sock_inode_cachep, GFP_KERNEL); if (!ei) return NULL; init_waitqueue_head(&ei->socket.wq.wait); ei->socket.wq.fasync_list = NULL; ei->socket.wq.flags = 0; ei->socket.state = SS_UNCONNECTED; ei->socket.flags = 0; ei->socket.ops = NULL; ei->socket.sk = NULL; ei->socket.file = NULL; return &ei->vfs_inode; } static void sock_free_inode(struct inode *inode) { struct socket_alloc *ei; ei = container_of(inode, struct socket_alloc, vfs_inode); kmem_cache_free(sock_inode_cachep, ei); } static void init_once(void *foo) { struct socket_alloc *ei = (struct socket_alloc *)foo; inode_init_once(&ei->vfs_inode); } static void init_inodecache(void) { sock_inode_cachep = kmem_cache_create("sock_inode_cache", sizeof(struct socket_alloc), 0, (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD | SLAB_ACCOUNT), init_once); BUG_ON(sock_inode_cachep == NULL); } static const struct super_operations sockfs_ops = { .alloc_inode = sock_alloc_inode, .free_inode = sock_free_inode, .statfs = simple_statfs, }; /* * sockfs_dname() is called from d_path(). */ static char *sockfs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(dentry, buffer, buflen, "socket:[%lu]", d_inode(dentry)->i_ino); } static const struct dentry_operations sockfs_dentry_operations = { .d_dname = sockfs_dname, }; static int sockfs_xattr_get(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *suffix, void *value, size_t size, int flags) { if (value) { if (dentry->d_name.len + 1 > size) return -ERANGE; memcpy(value, dentry->d_name.name, dentry->d_name.len + 1); } return dentry->d_name.len + 1; } #define XATTR_SOCKPROTONAME_SUFFIX "sockprotoname" #define XATTR_NAME_SOCKPROTONAME (XATTR_SYSTEM_PREFIX XATTR_SOCKPROTONAME_SUFFIX) #define XATTR_NAME_SOCKPROTONAME_LEN (sizeof(XATTR_NAME_SOCKPROTONAME)-1) static const struct xattr_handler sockfs_xattr_handler = { .name = XATTR_NAME_SOCKPROTONAME, .get = sockfs_xattr_get, }; static int sockfs_security_xattr_set(const struct xattr_handler *handler, struct dentry *dentry, struct inode *inode, const char *suffix, const void *value, size_t size, int flags) { /* Handled by LSM. */ return -EAGAIN; } static const struct xattr_handler sockfs_security_xattr_handler = { .prefix = XATTR_SECURITY_PREFIX, .set = sockfs_security_xattr_set, }; static const struct xattr_handler *sockfs_xattr_handlers[] = { &sockfs_xattr_handler, &sockfs_security_xattr_handler, NULL }; static int sockfs_init_fs_context(struct fs_context *fc) { struct pseudo_fs_context *ctx = init_pseudo(fc, SOCKFS_MAGIC); if (!ctx) return -ENOMEM; ctx->ops = &sockfs_ops; ctx->dops = &sockfs_dentry_operations; ctx->xattr = sockfs_xattr_handlers; return 0; } static struct vfsmount *sock_mnt __read_mostly; static struct file_system_type sock_fs_type = { .name = "sockfs", .init_fs_context = sockfs_init_fs_context, .kill_sb = kill_anon_super, }; /* * Obtains the first available file descriptor and sets it up for use. * * These functions create file structures and maps them to fd space * of the current process. On success it returns file descriptor * and file struct implicitly stored in sock->file. * Note that another thread may close file descriptor before we return * from this function. We use the fact that now we do not refer * to socket after mapping. If one day we will need it, this * function will increment ref. count on file by 1. * * In any case returned fd MAY BE not valid! * This race condition is unavoidable * with shared fd spaces, we cannot solve it inside kernel, * but we take care of internal coherence yet. */ /** * sock_alloc_file - Bind a &socket to a &file * @sock: socket * @flags: file status flags * @dname: protocol name * * Returns the &file bound with @sock, implicitly storing it * in sock->file. If dname is %NULL, sets to "". * On failure the return is a ERR pointer (see linux/err.h). * This function uses GFP_KERNEL internally. */ struct file *sock_alloc_file(struct socket *sock, int flags, const char *dname) { struct file *file; if (!dname) dname = sock->sk ? sock->sk->sk_prot_creator->name : ""; file = alloc_file_pseudo(SOCK_INODE(sock), sock_mnt, dname, O_RDWR | (flags & O_NONBLOCK), &socket_file_ops); if (IS_ERR(file)) { sock_release(sock); return file; } sock->file = file; file->private_data = sock; return file; } EXPORT_SYMBOL(sock_alloc_file); static int sock_map_fd(struct socket *sock, int flags) { struct file *newfile; int fd = get_unused_fd_flags(flags); if (unlikely(fd < 0)) { sock_release(sock); return fd; } newfile = sock_alloc_file(sock, flags, NULL); if (!IS_ERR(newfile)) { fd_install(fd, newfile); return fd; } put_unused_fd(fd); return PTR_ERR(newfile); } /** * sock_from_file - Return the &socket bounded to @file. * @file: file * @err: pointer to an error code return * * On failure returns %NULL and assigns -ENOTSOCK to @err. */ struct socket *sock_from_file(struct file *file, int *err) { if (file->f_op == &socket_file_ops) return file->private_data; /* set in sock_map_fd */ *err = -ENOTSOCK; return NULL; } EXPORT_SYMBOL(sock_from_file); /** * sockfd_lookup - Go from a file number to its socket slot * @fd: file handle * @err: pointer to an error code return * * The file handle passed in is locked and the socket it is bound * to is returned. If an error occurs the err pointer is overwritten * with a negative errno code and NULL is returned. The function checks * for both invalid handles and passing a handle which is not a socket. * * On a success the socket object pointer is returned. */ struct socket *sockfd_lookup(int fd, int *err) { struct file *file; struct socket *sock; file = fget(fd); if (!file) { *err = -EBADF; return NULL; } sock = sock_from_file(file, err); if (!sock) fput(file); return sock; } EXPORT_SYMBOL(sockfd_lookup); static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) { struct fd f = fdget(fd); struct socket *sock; *err = -EBADF; if (f.file) { sock = sock_from_file(f.file, err); if (likely(sock)) { *fput_needed = f.flags & FDPUT_FPUT; return sock; } fdput(f); } return NULL; } static ssize_t sockfs_listxattr(struct dentry *dentry, char *buffer, size_t size) { ssize_t len; ssize_t used = 0; len = security_inode_listsecurity(d_inode(dentry), buffer, size); if (len < 0) return len; used += len; if (buffer) { if (size < used) return -ERANGE; buffer += len; } len = (XATTR_NAME_SOCKPROTONAME_LEN + 1); used += len; if (buffer) { if (size < used) return -ERANGE; memcpy(buffer, XATTR_NAME_SOCKPROTONAME, len); buffer += len; } return used; } static int sockfs_setattr(struct dentry *dentry, struct iattr *iattr) { int err = simple_setattr(dentry, iattr); if (!err && (iattr->ia_valid & ATTR_UID)) { struct socket *sock = SOCKET_I(d_inode(dentry)); if (sock->sk) sock->sk->sk_uid = iattr->ia_uid; else err = -ENOENT; } return err; } static const struct inode_operations sockfs_inode_ops = { .listxattr = sockfs_listxattr, .setattr = sockfs_setattr, }; /** * sock_alloc - allocate a socket * * Allocate a new inode and socket object. The two are bound together * and initialised. The socket is then returned. If we are out of inodes * NULL is returned. This functions uses GFP_KERNEL internally. */ struct socket *sock_alloc(void) { struct inode *inode; struct socket *sock; inode = new_inode_pseudo(sock_mnt->mnt_sb); if (!inode) return NULL; sock = SOCKET_I(inode); inode->i_ino = get_next_ino(); inode->i_mode = S_IFSOCK | S_IRWXUGO; inode->i_uid = current_fsuid(); inode->i_gid = current_fsgid(); inode->i_op = &sockfs_inode_ops; return sock; } EXPORT_SYMBOL(sock_alloc); /** * sock_release - close a socket * @sock: socket to close * * The socket is released from the protocol stack if it has a release * callback, and the inode is then released if the socket is bound to * an inode not a file. */ static void __sock_release(struct socket *sock, struct inode *inode) { if (sock->ops) { struct module *owner = sock->ops->owner; if (inode) inode_lock(inode); sock->ops->release(sock); sock->sk = NULL; if (inode) inode_unlock(inode); sock->ops = NULL; module_put(owner); } if (sock->wq.fasync_list) pr_err("%s: fasync list not empty!\n", __func__); if (!sock->file) { iput(SOCK_INODE(sock)); return; } sock->file = NULL; } void sock_release(struct socket *sock) { __sock_release(sock, NULL); } EXPORT_SYMBOL(sock_release); void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags) { u8 flags = *tx_flags; if (tsflags & SOF_TIMESTAMPING_TX_HARDWARE) flags |= SKBTX_HW_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_SOFTWARE) flags |= SKBTX_SW_TSTAMP; if (tsflags & SOF_TIMESTAMPING_TX_SCHED) flags |= SKBTX_SCHED_TSTAMP; *tx_flags = flags; } EXPORT_SYMBOL(__sock_tx_timestamp); INDIRECT_CALLABLE_DECLARE(int inet_sendmsg(struct socket *, struct msghdr *, size_t)); INDIRECT_CALLABLE_DECLARE(int inet6_sendmsg(struct socket *, struct msghdr *, size_t)); static inline int sock_sendmsg_nosec(struct socket *sock, struct msghdr *msg) { int ret = INDIRECT_CALL_INET(sock->ops->sendmsg, inet6_sendmsg, inet_sendmsg, sock, msg, msg_data_left(msg)); BUG_ON(ret == -EIOCBQUEUED); return ret; } static int __sock_sendmsg(struct socket *sock, struct msghdr *msg) { int err = security_socket_sendmsg(sock, msg, msg_data_left(msg)); return err ?: sock_sendmsg_nosec(sock, msg); } /** * sock_sendmsg - send a message through @sock * @sock: socket * @msg: message to send * * Sends @msg through @sock, passing through LSM. * Returns the number of bytes sent, or an error code. */ int sock_sendmsg(struct socket *sock, struct msghdr *msg) { struct sockaddr_storage *save_addr = (struct sockaddr_storage *)msg->msg_name; struct sockaddr_storage address; int save_len = msg->msg_namelen; int ret; if (msg->msg_name) { memcpy(&address, msg->msg_name, msg->msg_namelen); msg->msg_name = &address; } ret = __sock_sendmsg(sock, msg); msg->msg_name = save_addr; msg->msg_namelen = save_len; return ret; } EXPORT_SYMBOL(sock_sendmsg); /** * kernel_sendmsg - send a message through @sock (kernel-space) * @sock: socket * @msg: message header * @vec: kernel vec * @num: vec array length * @size: total message data size * * Builds the message data with @vec and sends it through @sock. * Returns the number of bytes sent, or an error code. */ int kernel_sendmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock_sendmsg(sock, msg); } EXPORT_SYMBOL(kernel_sendmsg); /** * kernel_sendmsg_locked - send a message through @sock (kernel-space) * @sk: sock * @msg: message header * @vec: output s/g array * @num: output s/g array length * @size: total message data size * * Builds the message data with @vec and sends it through @sock. * Returns the number of bytes sent, or an error code. * Caller must hold @sk. */ int kernel_sendmsg_locked(struct sock *sk, struct msghdr *msg, struct kvec *vec, size_t num, size_t size) { struct socket *sock = sk->sk_socket; if (!sock->ops->sendmsg_locked) return sock_no_sendmsg_locked(sk, msg, size); iov_iter_kvec(&msg->msg_iter, WRITE, vec, num, size); return sock->ops->sendmsg_locked(sk, msg, msg_data_left(msg)); } EXPORT_SYMBOL(kernel_sendmsg_locked); static bool skb_is_err_queue(const struct sk_buff *skb) { /* pkt_type of skbs enqueued on the error queue are set to * PACKET_OUTGOING in skb_set_err_queue(). This is only safe to do * in recvmsg, since skbs received on a local socket will never * have a pkt_type of PACKET_OUTGOING. */ return skb->pkt_type == PACKET_OUTGOING; } /* On transmit, software and hardware timestamps are returned independently. * As the two skb clones share the hardware timestamp, which may be updated * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) { return skb->tstamp && !false_tstamp && skb_is_err_queue(skb); } static void put_ts_pktinfo(struct msghdr *msg, struct sk_buff *skb) { struct scm_ts_pktinfo ts_pktinfo; struct net_device *orig_dev; if (!skb_mac_header_was_set(skb)) return; memset(&ts_pktinfo, 0, sizeof(ts_pktinfo)); rcu_read_lock(); orig_dev = dev_get_by_napi_id(skb_napi_id(skb)); if (orig_dev) ts_pktinfo.if_index = orig_dev->ifindex; rcu_read_unlock(); ts_pktinfo.pkt_length = skb->len - skb_mac_offset(skb); put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_PKTINFO, sizeof(ts_pktinfo), &ts_pktinfo); } /* * called from sock_recv_timestamp() if sock_flag(sk, SOCK_RCVTSTAMP) */ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); struct scm_timestamping_internal tss; int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); /* Race occurred between timestamp enabling and packet receiving. Fill in the current time for now. */ if (need_software_tstamp && skb->tstamp == 0) { __net_timestamp(skb); false_tstamp = 1; } if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { if (new_tstamp) { struct __kernel_sock_timeval tv; skb_get_new_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, sizeof(tv), &tv); } else { struct __kernel_old_timeval tv; skb_get_timestamp(skb, &tv); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, sizeof(tv), &tv); } } else { if (new_tstamp) { struct __kernel_timespec ts; skb_get_new_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, sizeof(ts), &ts); } else { struct timespec ts; skb_get_timestampns(skb, &ts); put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, sizeof(ts), &ts); } } } memset(&tss, 0, sizeof(tss)); if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp) && ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { empty = 0; if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb); } if (!empty) { if (sock_flag(sk, SOCK_TSTAMP_NEW)) put_cmsg_scm_timestamping64(msg, &tss); else put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING_OPT_STATS, skb->len, skb->data); } } EXPORT_SYMBOL_GPL(__sock_recv_timestamp); void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int ack; if (!sock_flag(sk, SOCK_WIFI_STATUS)) return; if (!skb->wifi_acked_valid) return; ack = skb->wifi_acked; put_cmsg(msg, SOL_SOCKET, SCM_WIFI_STATUS, sizeof(ack), &ack); } EXPORT_SYMBOL_GPL(__sock_recv_wifi_status); static inline void sock_recv_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { if (sock_flag(sk, SOCK_RXQ_OVFL) && skb && SOCK_SKB_CB(skb)->dropcount) put_cmsg(msg, SOL_SOCKET, SO_RXQ_OVFL, sizeof(__u32), &SOCK_SKB_CB(skb)->dropcount); } void __sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { sock_recv_timestamp(msg, sk, skb); sock_recv_drops(msg, sk, skb); } EXPORT_SYMBOL_GPL(__sock_recv_ts_and_drops); INDIRECT_CALLABLE_DECLARE(int inet_recvmsg(struct socket *, struct msghdr *, size_t, int)); INDIRECT_CALLABLE_DECLARE(int inet6_recvmsg(struct socket *, struct msghdr *, size_t, int)); static inline int sock_recvmsg_nosec(struct socket *sock, struct msghdr *msg, int flags) { return INDIRECT_CALL_INET(sock->ops->recvmsg, inet6_recvmsg, inet_recvmsg, sock, msg, msg_data_left(msg), flags); } /** * sock_recvmsg - receive a message from @sock * @sock: socket * @msg: message to receive * @flags: message flags * * Receives @msg from @sock, passing through LSM. Returns the total number * of bytes received, or an error. */ int sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags) { int err = security_socket_recvmsg(sock, msg, msg_data_left(msg), flags); return err ?: sock_recvmsg_nosec(sock, msg, flags); } EXPORT_SYMBOL(sock_recvmsg); /** * kernel_recvmsg - Receive a message from a socket (kernel space) * @sock: The socket to receive the message from * @msg: Received message * @vec: Input s/g array for message data * @num: Size of input s/g array * @size: Number of bytes to read * @flags: Message flags (MSG_DONTWAIT, etc...) * * On return the msg structure contains the scatter/gather array passed in the * vec argument. The array is modified so that it consists of the unfilled * portion of the original array. * * The returned value is the total number of bytes received, or an error. */ int kernel_recvmsg(struct socket *sock, struct msghdr *msg, struct kvec *vec, size_t num, size_t size, int flags) { mm_segment_t oldfs = get_fs(); int result; iov_iter_kvec(&msg->msg_iter, READ, vec, num, size); set_fs(KERNEL_DS); result = sock_recvmsg(sock, msg, flags); set_fs(oldfs); return result; } EXPORT_SYMBOL(kernel_recvmsg); static ssize_t sock_sendpage(struct file *file, struct page *page, int offset, size_t size, loff_t *ppos, int more) { struct socket *sock; int flags; sock = file->private_data; flags = (file->f_flags & O_NONBLOCK) ? MSG_DONTWAIT : 0; /* more is a combination of MSG_MORE and MSG_SENDPAGE_NOTLAST */ flags |= more; return kernel_sendpage(sock, page, offset, size, flags); } static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags) { struct socket *sock = file->private_data; if (unlikely(!sock->ops->splice_read)) return generic_file_splice_read(file, ppos, pipe, len, flags); return sock->ops->splice_read(sock, ppos, pipe, len, flags); } static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *to, .msg_iocb = iocb}; ssize_t res; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) return -ESPIPE; if (!iov_iter_count(to)) /* Match SYS5 behaviour */ return 0; res = sock_recvmsg(sock, &msg, msg.msg_flags); *to = msg.msg_iter; return res; } static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) { struct file *file = iocb->ki_filp; struct socket *sock = file->private_data; struct msghdr msg = {.msg_iter = *from, .msg_iocb = iocb}; ssize_t res; if (iocb->ki_pos != 0) return -ESPIPE; if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) msg.msg_flags |= MSG_EOR; res = __sock_sendmsg(sock, &msg); *from = msg.msg_iter; return res; } /* * Atomic setting of ioctl hooks to avoid race * with module unload. */ static DEFINE_MUTEX(br_ioctl_mutex); static int (*br_ioctl_hook) (struct net *, unsigned int cmd, void __user *arg); void brioctl_set(int (*hook) (struct net *, unsigned int, void __user *)) { mutex_lock(&br_ioctl_mutex); br_ioctl_hook = hook; mutex_unlock(&br_ioctl_mutex); } EXPORT_SYMBOL(brioctl_set); static DEFINE_MUTEX(vlan_ioctl_mutex); static int (*vlan_ioctl_hook) (struct net *, void __user *arg); void vlan_ioctl_set(int (*hook) (struct net *, void __user *)) { mutex_lock(&vlan_ioctl_mutex); vlan_ioctl_hook = hook; mutex_unlock(&vlan_ioctl_mutex); } EXPORT_SYMBOL(vlan_ioctl_set); static DEFINE_MUTEX(dlci_ioctl_mutex); static int (*dlci_ioctl_hook) (unsigned int, void __user *); void dlci_ioctl_set(int (*hook) (unsigned int, void __user *)) { mutex_lock(&dlci_ioctl_mutex); dlci_ioctl_hook = hook; mutex_unlock(&dlci_ioctl_mutex); } EXPORT_SYMBOL(dlci_ioctl_set); static long sock_do_ioctl(struct net *net, struct socket *sock, unsigned int cmd, unsigned long arg) { int err; void __user *argp = (void __user *)arg; err = sock->ops->ioctl(sock, cmd, arg); /* * If this ioctl is unknown try to hand it down * to the NIC driver. */ if (err != -ENOIOCTLCMD) return err; if (cmd == SIOCGIFCONF) { struct ifconf ifc; if (copy_from_user(&ifc, argp, sizeof(struct ifconf))) return -EFAULT; rtnl_lock(); err = dev_ifconf(net, &ifc, sizeof(struct ifreq)); rtnl_unlock(); if (!err && copy_to_user(argp, &ifc, sizeof(struct ifconf))) err = -EFAULT; } else if (is_socket_ioctl_cmd(cmd)) { struct ifreq ifr; bool need_copyout; if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } else { err = -ENOTTY; } return err; } /* * With an ioctl, arg may well be a user mode pointer, but we don't know * what to do with it - that's up to the protocol still. */ static long sock_ioctl(struct file *file, unsigned cmd, unsigned long arg) { struct socket *sock; struct sock *sk; void __user *argp = (void __user *)arg; int pid, err; struct net *net; sock = file->private_data; sk = sock->sk; net = sock_net(sk); if (unlikely(cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15))) { struct ifreq ifr; bool need_copyout; if (copy_from_user(&ifr, argp, sizeof(struct ifreq))) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, &need_copyout); if (!err && need_copyout) if (copy_to_user(argp, &ifr, sizeof(struct ifreq))) return -EFAULT; } else #ifdef CONFIG_WEXT_CORE if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST) { err = wext_handle_ioctl(net, cmd, argp); } else #endif switch (cmd) { case FIOSETOWN: case SIOCSPGRP: err = -EFAULT; if (get_user(pid, (int __user *)argp)) break; err = f_setown(sock->file, pid, 1); break; case FIOGETOWN: case SIOCGPGRP: err = put_user(f_getown(sock->file), (int __user *)argp); break; case SIOCGIFBR: case SIOCSIFBR: case SIOCBRADDBR: case SIOCBRDELBR: err = -ENOPKG; if (!br_ioctl_hook) request_module("bridge"); mutex_lock(&br_ioctl_mutex); if (br_ioctl_hook) err = br_ioctl_hook(net, cmd, argp); mutex_unlock(&br_ioctl_mutex); break; case SIOCGIFVLAN: case SIOCSIFVLAN: err = -ENOPKG; if (!vlan_ioctl_hook) request_module("8021q"); mutex_lock(&vlan_ioctl_mutex); if (vlan_ioctl_hook) err = vlan_ioctl_hook(net, argp); mutex_unlock(&vlan_ioctl_mutex); break; case SIOCADDDLCI: case SIOCDELDLCI: err = -ENOPKG; if (!dlci_ioctl_hook) request_module("dlci"); mutex_lock(&dlci_ioctl_mutex); if (dlci_ioctl_hook) err = dlci_ioctl_hook(cmd, argp); mutex_unlock(&dlci_ioctl_mutex); break; case SIOCGSKNS: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = open_related_ns(&net->ns, get_net_ns); break; case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!sock->ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !IS_ENABLED(CONFIG_64BIT)); break; case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: if (!sock->ops->gettstamp) { err = -ENOIOCTLCMD; break; } err = sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_NEW, false); break; default: err = sock_do_ioctl(net, sock, cmd, arg); break; } return err; } /** * sock_create_lite - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * Creates a new socket and assigns it to @res, passing through LSM. * The new socket initialization is not complete, see kernel_accept(). * Returns 0 or an error. On failure @res is set to %NULL. * This function internally uses GFP_KERNEL. */ int sock_create_lite(int family, int type, int protocol, struct socket **res) { int err; struct socket *sock = NULL; err = security_socket_create(family, type, protocol, 1); if (err) goto out; sock = sock_alloc(); if (!sock) { err = -ENOMEM; goto out; } sock->type = type; err = security_socket_post_create(sock, family, type, protocol, 1); if (err) goto out_release; out: *res = sock; return err; out_release: sock_release(sock); sock = NULL; goto out; } EXPORT_SYMBOL(sock_create_lite); /* No kernel lock held - perfect */ static __poll_t sock_poll(struct file *file, poll_table *wait) { struct socket *sock = file->private_data; __poll_t events = poll_requested_events(wait), flag = 0; if (!sock->ops->poll) return 0; if (sk_can_busy_loop(sock->sk)) { /* poll once if requested by the syscall */ if (events & POLL_BUSY_LOOP) sk_busy_loop(sock->sk, 1); /* if this socket can poll_ll, tell the system call */ flag = POLL_BUSY_LOOP; } return sock->ops->poll(file, sock, wait) | flag; } static int sock_mmap(struct file *file, struct vm_area_struct *vma) { struct socket *sock = file->private_data; return sock->ops->mmap(file, sock, vma); } static int sock_close(struct inode *inode, struct file *filp) { __sock_release(SOCKET_I(inode), inode); return 0; } /* * Update the socket async list * * Fasync_list locking strategy. * * 1. fasync_list is modified only under process context socket lock * i.e. under semaphore. * 2. fasync_list is used under read_lock(&sk->sk_callback_lock) * or under socket lock */ static int sock_fasync(int fd, struct file *filp, int on) { struct socket *sock = filp->private_data; struct sock *sk = sock->sk; struct socket_wq *wq = &sock->wq; if (sk == NULL) return -EINVAL; lock_sock(sk); fasync_helper(fd, filp, on, &wq->fasync_list); if (!wq->fasync_list) sock_reset_flag(sk, SOCK_FASYNC); else sock_set_flag(sk, SOCK_FASYNC); release_sock(sk); return 0; } /* This function may be called only under rcu_lock */ int sock_wake_async(struct socket_wq *wq, int how, int band) { if (!wq || !wq->fasync_list) return -1; switch (how) { case SOCK_WAKE_WAITD: if (test_bit(SOCKWQ_ASYNC_WAITDATA, &wq->flags)) break; goto call_kill; case SOCK_WAKE_SPACE: if (!test_and_clear_bit(SOCKWQ_ASYNC_NOSPACE, &wq->flags)) break; /* fall through */ case SOCK_WAKE_IO: call_kill: kill_fasync(&wq->fasync_list, SIGIO, band); break; case SOCK_WAKE_URG: kill_fasync(&wq->fasync_list, SIGURG, band); } return 0; } EXPORT_SYMBOL(sock_wake_async); /** * __sock_create - creates a socket * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * @kern: boolean for kernel space sockets * * Creates a new socket and assigns it to @res, passing through LSM. * Returns 0 or an error. On failure @res is set to %NULL. @kern must * be set to true if the socket resides in kernel space. * This function internally uses GFP_KERNEL. */ int __sock_create(struct net *net, int family, int type, int protocol, struct socket **res, int kern) { int err; struct socket *sock; const struct net_proto_family *pf; /* * Check protocol is in range */ if (family < 0 || family >= NPROTO) return -EAFNOSUPPORT; if (type < 0 || type >= SOCK_MAX) return -EINVAL; /* Compatibility. This uglymoron is moved from INET layer to here to avoid deadlock in module load. */ if (family == PF_INET && type == SOCK_PACKET) { pr_info_once("%s uses obsolete (PF_INET,SOCK_PACKET)\n", current->comm); family = PF_PACKET; } err = security_socket_create(family, type, protocol, kern); if (err) return err; /* * Allocate the socket and allow the family to set things up. if * the protocol is 0, the family is instructed to select an appropriate * default. */ sock = sock_alloc(); if (!sock) { net_warn_ratelimited("socket: no more sockets\n"); return -ENFILE; /* Not exactly a match, but its the closest posix thing */ } sock->type = type; #ifdef CONFIG_MODULES /* Attempt to load a protocol module if the find failed. * * 12/09/1996 Marcin: But! this makes REALLY only sense, if the user * requested real, full-featured networking support upon configuration. * Otherwise module support will break! */ if (rcu_access_pointer(net_families[family]) == NULL) request_module("net-pf-%d", family); #endif rcu_read_lock(); pf = rcu_dereference(net_families[family]); err = -EAFNOSUPPORT; if (!pf) goto out_release; /* * We will call the ->create function, that possibly is in a loadable * module, so we have to bump that loadable module refcnt first. */ if (!try_module_get(pf->owner)) goto out_release; /* Now protected by module ref count */ rcu_read_unlock(); err = pf->create(net, sock, protocol, kern); if (err < 0) goto out_module_put; /* * Now to bump the refcnt of the [loadable] module that owns this * socket at sock_release time we decrement its refcnt. */ if (!try_module_get(sock->ops->owner)) goto out_module_busy; /* * Now that we're done with the ->create function, the [loadable] * module can have its refcnt decremented */ module_put(pf->owner); err = security_socket_post_create(sock, family, type, protocol, kern); if (err) goto out_sock_release; *res = sock; return 0; out_module_busy: err = -EAFNOSUPPORT; out_module_put: sock->ops = NULL; module_put(pf->owner); out_sock_release: sock_release(sock); return err; out_release: rcu_read_unlock(); goto out_sock_release; } EXPORT_SYMBOL(__sock_create); /** * sock_create - creates a socket * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create(int family, int type, int protocol, struct socket **res) { return __sock_create(current->nsproxy->net_ns, family, type, protocol, res, 0); } EXPORT_SYMBOL(sock_create); /** * sock_create_kern - creates a socket (kernel space) * @net: net namespace * @family: protocol family (AF_INET, ...) * @type: communication type (SOCK_STREAM, ...) * @protocol: protocol (0, ...) * @res: new socket * * A wrapper around __sock_create(). * Returns 0 or an error. This function internally uses GFP_KERNEL. */ int sock_create_kern(struct net *net, int family, int type, int protocol, struct socket **res) { return __sock_create(net, family, type, protocol, res, 1); } EXPORT_SYMBOL(sock_create_kern); int __sys_socket(int family, int type, int protocol) { int retval; struct socket *sock; int flags; /* Check the SOCK_* constants for consistency. */ BUILD_BUG_ON(SOCK_CLOEXEC != O_CLOEXEC); BUILD_BUG_ON((SOCK_MAX | SOCK_TYPE_MASK) != SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_CLOEXEC & SOCK_TYPE_MASK); BUILD_BUG_ON(SOCK_NONBLOCK & SOCK_TYPE_MASK); flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; retval = sock_create(family, type, protocol, &sock); if (retval < 0) return retval; return sock_map_fd(sock, flags & (O_CLOEXEC | O_NONBLOCK)); } SYSCALL_DEFINE3(socket, int, family, int, type, int, protocol) { return __sys_socket(family, type, protocol); } /* * Create a pair of connected sockets. */ int __sys_socketpair(int family, int type, int protocol, int __user *usockvec) { struct socket *sock1, *sock2; int fd1, fd2, err; struct file *newfile1, *newfile2; int flags; flags = type & ~SOCK_TYPE_MASK; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; type &= SOCK_TYPE_MASK; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; /* * reserve descriptors and make sure we won't fail * to return them to userland. */ fd1 = get_unused_fd_flags(flags); if (unlikely(fd1 < 0)) return fd1; fd2 = get_unused_fd_flags(flags); if (unlikely(fd2 < 0)) { put_unused_fd(fd1); return fd2; } err = put_user(fd1, &usockvec[0]); if (err) goto out; err = put_user(fd2, &usockvec[1]); if (err) goto out; /* * Obtain the first socket and check if the underlying protocol * supports the socketpair call. */ err = sock_create(family, type, protocol, &sock1); if (unlikely(err < 0)) goto out; err = sock_create(family, type, protocol, &sock2); if (unlikely(err < 0)) { sock_release(sock1); goto out; } err = security_socket_socketpair(sock1, sock2); if (unlikely(err)) { sock_release(sock2); sock_release(sock1); goto out; } err = sock1->ops->socketpair(sock1, sock2); if (unlikely(err < 0)) { sock_release(sock2); sock_release(sock1); goto out; } newfile1 = sock_alloc_file(sock1, flags, NULL); if (IS_ERR(newfile1)) { err = PTR_ERR(newfile1); sock_release(sock2); goto out; } newfile2 = sock_alloc_file(sock2, flags, NULL); if (IS_ERR(newfile2)) { err = PTR_ERR(newfile2); fput(newfile1); goto out; } audit_fd_pair(fd1, fd2); fd_install(fd1, newfile1); fd_install(fd2, newfile2); return 0; out: put_unused_fd(fd2); put_unused_fd(fd1); return err; } SYSCALL_DEFINE4(socketpair, int, family, int, type, int, protocol, int __user *, usockvec) { return __sys_socketpair(family, type, protocol, usockvec); } /* * Bind a name to a socket. Nothing much to do here since it's * the protocol's responsibility to handle the local address. * * We move the socket address to kernel space before we call * the protocol layer (having also checked the address is ok). */ int __sys_bind(int fd, struct sockaddr __user *umyaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { err = move_addr_to_kernel(umyaddr, addrlen, &address); if (!err) { err = security_socket_bind(sock, (struct sockaddr *)&address, addrlen); if (!err) err = sock->ops->bind(sock, (struct sockaddr *) &address, addrlen); } fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE3(bind, int, fd, struct sockaddr __user *, umyaddr, int, addrlen) { return __sys_bind(fd, umyaddr, addrlen); } /* * Perform a listen. Basically, we allow the protocol to do anything * necessary for a listen, and if that works, we mark the socket as * ready for listening. */ int __sys_listen(int fd, int backlog) { struct socket *sock; int err, fput_needed; int somaxconn; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock) { somaxconn = READ_ONCE(sock_net(sock->sk)->core.sysctl_somaxconn); if ((unsigned int)backlog > somaxconn) backlog = somaxconn; err = security_socket_listen(sock, backlog); if (!err) err = sock->ops->listen(sock, backlog); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE2(listen, int, fd, int, backlog) { return __sys_listen(fd, backlog); } /* * For accept, we attempt to create a new socket, set up the link * with the client, wake up the client, then return the new * connected fd. We collect the address of the connector in kernel * space and move it to user at the very end. This is unclean because * we open the socket then return an error. * * 1003.1g adds the ability to recvmsg() to query connection pending * status to recvmsg. We need to add that support in a way thats * clean when we restructure accept also. */ int __sys_accept4(int fd, struct sockaddr __user *upeer_sockaddr, int __user *upeer_addrlen, int flags) { struct socket *sock, *newsock; struct file *newfile; int err, len, newfd, fput_needed; struct sockaddr_storage address; if (flags & ~(SOCK_CLOEXEC | SOCK_NONBLOCK)) return -EINVAL; if (SOCK_NONBLOCK != O_NONBLOCK && (flags & SOCK_NONBLOCK)) flags = (flags & ~SOCK_NONBLOCK) | O_NONBLOCK; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = -ENFILE; newsock = sock_alloc(); if (!newsock) goto out_put; newsock->type = sock->type; newsock->ops = sock->ops; /* * We don't need try_module_get here, as the listening socket (sock) * has the protocol module (sock->ops->owner) held. */ __module_get(newsock->ops->owner); newfd = get_unused_fd_flags(flags); if (unlikely(newfd < 0)) { err = newfd; sock_release(newsock); goto out_put; } newfile = sock_alloc_file(newsock, flags, sock->sk->sk_prot_creator->name); if (IS_ERR(newfile)) { err = PTR_ERR(newfile); put_unused_fd(newfd); goto out_put; } err = security_socket_accept(sock, newsock); if (err) goto out_fd; err = sock->ops->accept(sock, newsock, sock->file->f_flags, false); if (err < 0) goto out_fd; if (upeer_sockaddr) { len = newsock->ops->getname(newsock, (struct sockaddr *)&address, 2); if (len < 0) { err = -ECONNABORTED; goto out_fd; } err = move_addr_to_user(&address, len, upeer_sockaddr, upeer_addrlen); if (err < 0) goto out_fd; } /* File flags are not inherited via accept() unlike another OSes. */ fd_install(newfd, newfile); err = newfd; out_put: fput_light(sock->file, fput_needed); out: return err; out_fd: fput(newfile); put_unused_fd(newfd); goto out_put; } SYSCALL_DEFINE4(accept4, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen, int, flags) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, flags); } SYSCALL_DEFINE3(accept, int, fd, struct sockaddr __user *, upeer_sockaddr, int __user *, upeer_addrlen) { return __sys_accept4(fd, upeer_sockaddr, upeer_addrlen, 0); } /* * Attempt to connect to a socket with the server address. The address * is in user space so we verify it is OK and move it to kernel space. * * For 1003.1g we need to add clean support for a bind to AF_UNSPEC to * break bindings * * NOTE: 1003.1g draft 6.3 is broken with respect to AX.25/NetROM and * other SEQPACKET protocols that take time to connect() as it doesn't * include the -EINPROGRESS status for such sockets. */ int __sys_connect(int fd, struct sockaddr __user *uservaddr, int addrlen) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = move_addr_to_kernel(uservaddr, addrlen, &address); if (err < 0) goto out_put; err = security_socket_connect(sock, (struct sockaddr *)&address, addrlen); if (err) goto out_put; err = sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, sock->file->f_flags); out_put: fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(connect, int, fd, struct sockaddr __user *, uservaddr, int, addrlen) { return __sys_connect(fd, uservaddr, addrlen); } /* * Get the local address ('name') of a socket object. Move the obtained * name to user space. */ int __sys_getsockname(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = security_socket_getsockname(sock); if (err) goto out_put; err = sock->ops->getname(sock, (struct sockaddr *)&address, 0); if (err < 0) goto out_put; /* "err" is actually length in this case */ err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); out_put: fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(getsockname, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getsockname(fd, usockaddr, usockaddr_len); } /* * Get the remote address ('name') of a socket object. Move the obtained * name to user space. */ int __sys_getpeername(int fd, struct sockaddr __user *usockaddr, int __user *usockaddr_len) { struct socket *sock; struct sockaddr_storage address; int err, fput_needed; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_getpeername(sock); if (err) { fput_light(sock->file, fput_needed); return err; } err = sock->ops->getname(sock, (struct sockaddr *)&address, 1); if (err >= 0) /* "err" is actually length in this case */ err = move_addr_to_user(&address, err, usockaddr, usockaddr_len); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE3(getpeername, int, fd, struct sockaddr __user *, usockaddr, int __user *, usockaddr_len) { return __sys_getpeername(fd, usockaddr, usockaddr_len); } /* * Send a datagram to a given address. We move the address into kernel * space and check the user space data area is readable before invoking * the protocol. */ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, struct sockaddr __user *addr, int addr_len) { struct socket *sock; struct sockaddr_storage address; int err; struct msghdr msg; struct iovec iov; int fput_needed; err = import_single_range(WRITE, buff, len, &iov, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; msg.msg_name = NULL; msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) goto out_put; msg.msg_name = (struct sockaddr *)&address; msg.msg_namelen = addr_len; } if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; msg.msg_flags = flags; err = __sock_sendmsg(sock, &msg); out_put: fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE6(sendto, int, fd, void __user *, buff, size_t, len, unsigned int, flags, struct sockaddr __user *, addr, int, addr_len) { return __sys_sendto(fd, buff, len, flags, addr, addr_len); } /* * Send a datagram down a socket. */ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, unsigned int, flags) { return __sys_sendto(fd, buff, len, flags, NULL, 0); } /* * Receive a frame from the socket and optionally record the address of the * sender. We verify the buffers are writable and if needed move the * sender address from kernel to user space. */ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len) { struct socket *sock; struct iovec iov; struct msghdr msg; struct sockaddr_storage address; int err, err2; int fput_needed; err = import_single_range(READ, ubuf, size, &iov, &msg.msg_iter); if (unlikely(err)) return err; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; msg.msg_control = NULL; msg.msg_controllen = 0; /* Save some cycles and don't copy the address if not needed */ msg.msg_name = addr ? (struct sockaddr *)&address : NULL; /* We assume all kernel code knows the size of sockaddr_storage */ msg.msg_namelen = 0; msg.msg_iocb = NULL; msg.msg_flags = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); if (err >= 0 && addr != NULL) { err2 = move_addr_to_user(&address, msg.msg_namelen, addr, addr_len); if (err2 < 0) err = err2; } fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE6(recvfrom, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags, struct sockaddr __user *, addr, int __user *, addr_len) { return __sys_recvfrom(fd, ubuf, size, flags, addr, addr_len); } /* * Receive a datagram from a socket. */ SYSCALL_DEFINE4(recv, int, fd, void __user *, ubuf, size_t, size, unsigned int, flags) { return __sys_recvfrom(fd, ubuf, size, flags, NULL, NULL); } /* * Set a socket option. Because we don't know the option lengths we have * to pass the user mode parameter for the protocols to sort out. */ static int __sys_setsockopt(int fd, int level, int optname, char __user *optval, int optlen) { mm_segment_t oldfs = get_fs(); char *kernel_optval = NULL; int err, fput_needed; struct socket *sock; if (optlen < 0) return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_setsockopt(sock, level, optname); if (err) goto out_put; err = BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock->sk, &level, &optname, optval, &optlen, &kernel_optval); if (err < 0) { goto out_put; } else if (err > 0) { err = 0; goto out_put; } if (kernel_optval) { set_fs(KERNEL_DS); optval = (char __user __force *)kernel_optval; } if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, optval, optlen); else err = sock->ops->setsockopt(sock, level, optname, optval, optlen); if (kernel_optval) { set_fs(oldfs); kfree(kernel_optval); } out_put: fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, char __user *, optval, int, optlen) { return __sys_setsockopt(fd, level, optname, optval, optlen); } /* * Get a socket option. Because we don't know the option lengths we have * to pass a user mode parameter for the protocols to sort out. */ static int __sys_getsockopt(int fd, int level, int optname, char __user *optval, int __user *optlen) { int err, fput_needed; struct socket *sock; int max_optlen; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_getsockopt(sock, level, optname); if (err) goto out_put; max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen); if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, optval, optlen); else err = sock->ops->getsockopt(sock, level, optname, optval, optlen); err = BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock->sk, level, optname, optval, optlen, max_optlen, err); out_put: fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE5(getsockopt, int, fd, int, level, int, optname, char __user *, optval, int __user *, optlen) { return __sys_getsockopt(fd, level, optname, optval, optlen); } /* * Shutdown a socket. */ int __sys_shutdown(int fd, int how) { int err, fput_needed; struct socket *sock; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (sock != NULL) { err = security_socket_shutdown(sock, how); if (!err) err = sock->ops->shutdown(sock, how); fput_light(sock->file, fput_needed); } return err; } SYSCALL_DEFINE2(shutdown, int, fd, int, how) { return __sys_shutdown(fd, how); } /* A couple of helpful macros for getting the address of the 32/64 bit * fields which are the same type (int / unsigned) on our platforms. */ #define COMPAT_MSG(msg, member) ((MSG_CMSG_COMPAT & flags) ? &msg##_compat->member : &msg->member) #define COMPAT_NAMELEN(msg) COMPAT_MSG(msg, msg_namelen) #define COMPAT_FLAGS(msg) COMPAT_MSG(msg, msg_flags) struct used_address { struct sockaddr_storage name; unsigned int name_len; }; static int copy_msghdr_from_user(struct msghdr *kmsg, struct user_msghdr __user *umsg, struct sockaddr __user **save_addr, struct iovec **iov) { struct user_msghdr msg; ssize_t err; if (copy_from_user(&msg, umsg, sizeof(*umsg))) return -EFAULT; kmsg->msg_control = (void __force *)msg.msg_control; kmsg->msg_controllen = msg.msg_controllen; kmsg->msg_flags = msg.msg_flags; kmsg->msg_namelen = msg.msg_namelen; if (!msg.msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) return -EINVAL; if (kmsg->msg_namelen > sizeof(struct sockaddr_storage)) kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) *save_addr = msg.msg_name; if (msg.msg_name && kmsg->msg_namelen) { if (!save_addr) { err = move_addr_to_kernel(msg.msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) return err; } } else { kmsg->msg_name = NULL; kmsg->msg_namelen = 0; } if (msg.msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; err = import_iovec(save_addr ? READ : WRITE, msg.msg_iov, msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } static int ____sys_sendmsg(struct socket *sock, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { unsigned char ctl[sizeof(struct cmsghdr) + 20] __aligned(sizeof(__kernel_size_t)); /* 20 is size of ipv6_pktinfo */ unsigned char *ctl_buf = ctl; int ctl_len; ssize_t err; err = -ENOBUFS; if (msg_sys->msg_controllen > INT_MAX) goto out; flags |= (msg_sys->msg_flags & allowed_msghdr_flags); ctl_len = msg_sys->msg_controllen; if ((MSG_CMSG_COMPAT & flags) && ctl_len) { err = cmsghdr_from_user_compat_to_kern(msg_sys, sock->sk, ctl, sizeof(ctl)); if (err) goto out; ctl_buf = msg_sys->msg_control; ctl_len = msg_sys->msg_controllen; } else if (ctl_len) { BUILD_BUG_ON(sizeof(struct cmsghdr) != CMSG_ALIGN(sizeof(struct cmsghdr))); if (ctl_len > sizeof(ctl)) { ctl_buf = sock_kmalloc(sock->sk, ctl_len, GFP_KERNEL); if (ctl_buf == NULL) goto out; } err = -EFAULT; /* * Careful! Before this, msg_sys->msg_control contains a user pointer. * Afterwards, it will be a kernel pointer. Thus the compiler-assisted * checking falls down on this. */ if (copy_from_user(ctl_buf, (void __user __force *)msg_sys->msg_control, ctl_len)) goto out_freectl; msg_sys->msg_control = ctl_buf; } msg_sys->msg_flags = flags; if (sock->file->f_flags & O_NONBLOCK) msg_sys->msg_flags |= MSG_DONTWAIT; /* * If this is sendmmsg() and current destination address is same as * previously succeeded address, omit asking LSM's decision. * used_address->name_len is initialized to UINT_MAX so that the first * destination address never matches. */ if (used_address && msg_sys->msg_name && used_address->name_len == msg_sys->msg_namelen && !memcmp(&used_address->name, msg_sys->msg_name, used_address->name_len)) { err = sock_sendmsg_nosec(sock, msg_sys); goto out_freectl; } err = __sock_sendmsg(sock, msg_sys); /* * If this is sendmmsg() and sending to current destination address was * successful, remember it. */ if (used_address && err >= 0) { used_address->name_len = msg_sys->msg_namelen; if (msg_sys->msg_name) memcpy(&used_address->name, msg_sys->msg_name, used_address->name_len); } out_freectl: if (ctl_buf != ctl) sock_kfree_s(sock->sk, ctl_buf, ctl_len); out: return err; } static int sendmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct iovec **iov) { int err; if (flags & MSG_CMSG_COMPAT) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, NULL, iov); } else { err = copy_msghdr_from_user(msg, umsg, NULL, iov); } if (err < 0) return err; return 0; } static int ___sys_sendmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, struct used_address *used_address, unsigned int allowed_msghdr_flags) { struct sockaddr_storage address; struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; ssize_t err; msg_sys->msg_name = &address; err = sendmsg_copy_msghdr(msg_sys, msg, flags, &iov); if (err < 0) return err; err = ____sys_sendmsg(sock, msg_sys, flags, used_address, allowed_msghdr_flags); kfree(iov); return err; } /* * BSD sendmsg interface */ long __sys_sendmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, unsigned int flags) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; struct sockaddr_storage address; struct msghdr msg = { .msg_name = &address }; ssize_t err; err = sendmsg_copy_msghdr(&msg, umsg, flags, &iov); if (err) return err; /* disallow ancillary data requests from this path */ if (msg.msg_control || msg.msg_controllen) { err = -EINVAL; goto out; } err = ____sys_sendmsg(sock, &msg, flags, NULL, 0); out: kfree(iov); return err; } long __sys_sendmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = ___sys_sendmsg(sock, msg, &msg_sys, flags, NULL, 0); fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(sendmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_sendmsg(fd, msg, flags, true); } /* * Linux sendmmsg interface */ int __sys_sendmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct used_address used_address; unsigned int oflags = flags; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; if (vlen > UIO_MAXIOV) vlen = UIO_MAXIOV; datagrams = 0; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; used_address.name_len = UINT_MAX; entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; err = 0; flags |= MSG_BATCH; while (datagrams < vlen) { if (datagrams == vlen - 1) flags = oflags; if (MSG_CMSG_COMPAT & flags) { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_sendmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags, &used_address, MSG_EOR); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; if (msg_data_left(&msg_sys)) break; cond_resched(); } fput_light(sock->file, fput_needed); /* We only return an error if no datagrams were able to be sent */ if (datagrams != 0) return datagrams; return err; } SYSCALL_DEFINE4(sendmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags) { return __sys_sendmmsg(fd, mmsg, vlen, flags, true); } static int recvmsg_copy_msghdr(struct msghdr *msg, struct user_msghdr __user *umsg, unsigned flags, struct sockaddr __user **uaddr, struct iovec **iov) { ssize_t err; if (MSG_CMSG_COMPAT & flags) { struct compat_msghdr __user *msg_compat; msg_compat = (struct compat_msghdr __user *) umsg; err = get_compat_msghdr(msg, msg_compat, uaddr, iov); } else { err = copy_msghdr_from_user(msg, umsg, uaddr, iov); } if (err < 0) return err; return 0; } static int ____sys_recvmsg(struct socket *sock, struct msghdr *msg_sys, struct user_msghdr __user *msg, struct sockaddr __user *uaddr, unsigned int flags, int nosec) { struct compat_msghdr __user *msg_compat = (struct compat_msghdr __user *) msg; int __user *uaddr_len = COMPAT_NAMELEN(msg); struct sockaddr_storage addr; unsigned long cmsg_ptr; int len; ssize_t err; msg_sys->msg_name = &addr; cmsg_ptr = (unsigned long)msg_sys->msg_control; msg_sys->msg_flags = flags & (MSG_CMSG_CLOEXEC|MSG_CMSG_COMPAT); /* We assume all kernel code knows the size of sockaddr_storage */ msg_sys->msg_namelen = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = (nosec ? sock_recvmsg_nosec : sock_recvmsg)(sock, msg_sys, flags); if (err < 0) goto out; len = err; if (uaddr != NULL) { err = move_addr_to_user(&addr, msg_sys->msg_namelen, uaddr, uaddr_len); if (err < 0) goto out; } err = __put_user((msg_sys->msg_flags & ~MSG_CMSG_COMPAT), COMPAT_FLAGS(msg)); if (err) goto out; if (MSG_CMSG_COMPAT & flags) err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg_compat->msg_controllen); else err = __put_user((unsigned long)msg_sys->msg_control - cmsg_ptr, &msg->msg_controllen); if (err) goto out; err = len; out: return err; } static int ___sys_recvmsg(struct socket *sock, struct user_msghdr __user *msg, struct msghdr *msg_sys, unsigned int flags, int nosec) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; /* user mode address pointers */ struct sockaddr __user *uaddr; ssize_t err; err = recvmsg_copy_msghdr(msg_sys, msg, flags, &uaddr, &iov); if (err < 0) return err; err = ____sys_recvmsg(sock, msg_sys, msg, uaddr, flags, nosec); kfree(iov); return err; } /* * BSD recvmsg interface */ long __sys_recvmsg_sock(struct socket *sock, struct user_msghdr __user *umsg, unsigned int flags) { struct iovec iovstack[UIO_FASTIOV], *iov = iovstack; struct sockaddr_storage address; struct msghdr msg = { .msg_name = &address }; struct sockaddr __user *uaddr; ssize_t err; err = recvmsg_copy_msghdr(&msg, umsg, flags, &uaddr, &iov); if (err) return err; /* disallow ancillary data requests from this path */ if (msg.msg_control || msg.msg_controllen) { err = -EINVAL; goto out; } err = ____sys_recvmsg(sock, &msg, umsg, uaddr, flags, 0); out: kfree(iov); return err; } long __sys_recvmsg(int fd, struct user_msghdr __user *msg, unsigned int flags, bool forbid_cmsg_compat) { int fput_needed, err; struct msghdr msg_sys; struct socket *sock; if (forbid_cmsg_compat && (flags & MSG_CMSG_COMPAT)) return -EINVAL; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) goto out; err = ___sys_recvmsg(sock, msg, &msg_sys, flags, 0); fput_light(sock->file, fput_needed); out: return err; } SYSCALL_DEFINE3(recvmsg, int, fd, struct user_msghdr __user *, msg, unsigned int, flags) { return __sys_recvmsg(fd, msg, flags, true); } /* * Linux recvmmsg interface */ static int do_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct timespec64 *timeout) { int fput_needed, err, datagrams; struct socket *sock; struct mmsghdr __user *entry; struct compat_mmsghdr __user *compat_entry; struct msghdr msg_sys; struct timespec64 end_time; struct timespec64 timeout64; if (timeout && poll_select_set_timeout(&end_time, timeout->tv_sec, timeout->tv_nsec)) return -EINVAL; datagrams = 0; sock = sockfd_lookup_light(fd, &err, &fput_needed); if (!sock) return err; if (likely(!(flags & MSG_ERRQUEUE))) { err = sock_error(sock->sk); if (err) { datagrams = err; goto out_put; } } entry = mmsg; compat_entry = (struct compat_mmsghdr __user *)mmsg; while (datagrams < vlen) { /* * No need to ask LSM for more than the first datagram. */ if (MSG_CMSG_COMPAT & flags) { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)compat_entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = __put_user(err, &compat_entry->msg_len); ++compat_entry; } else { err = ___sys_recvmsg(sock, (struct user_msghdr __user *)entry, &msg_sys, flags & ~MSG_WAITFORONE, datagrams); if (err < 0) break; err = put_user(err, &entry->msg_len); ++entry; } if (err) break; ++datagrams; /* MSG_WAITFORONE turns on MSG_DONTWAIT after one packet */ if (flags & MSG_WAITFORONE) flags |= MSG_DONTWAIT; if (timeout) { ktime_get_ts64(&timeout64); *timeout = timespec64_sub(end_time, timeout64); if (timeout->tv_sec < 0) { timeout->tv_sec = timeout->tv_nsec = 0; break; } /* Timeout, return less than vlen datagrams */ if (timeout->tv_nsec == 0 && timeout->tv_sec == 0) break; } /* Out of band data, return right away */ if (msg_sys.msg_flags & MSG_OOB) break; cond_resched(); } if (err == 0) goto out_put; if (datagrams == 0) { datagrams = err; goto out_put; } /* * We may return less entries than requested (vlen) if the * sock is non block and there aren't enough datagrams... */ if (err != -EAGAIN) { /* * ... or if recvmsg returns an error after we * received some datagrams, where we record the * error to return on the next call or if the * app asks about it using getsockopt(SO_ERROR). */ WRITE_ONCE(sock->sk->sk_err, -err); } out_put: fput_light(sock->file, fput_needed); return datagrams; } int __sys_recvmmsg(int fd, struct mmsghdr __user *mmsg, unsigned int vlen, unsigned int flags, struct __kernel_timespec __user *timeout, struct old_timespec32 __user *timeout32) { int datagrams; struct timespec64 timeout_sys; if (timeout && get_timespec64(&timeout_sys, timeout)) return -EFAULT; if (timeout32 && get_old_timespec32(&timeout_sys, timeout32)) return -EFAULT; if (!timeout && !timeout32) return do_recvmmsg(fd, mmsg, vlen, flags, NULL); datagrams = do_recvmmsg(fd, mmsg, vlen, flags, &timeout_sys); if (datagrams <= 0) return datagrams; if (timeout && put_timespec64(&timeout_sys, timeout)) datagrams = -EFAULT; if (timeout32 && put_old_timespec32(&timeout_sys, timeout32)) datagrams = -EFAULT; return datagrams; } SYSCALL_DEFINE5(recvmmsg, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct __kernel_timespec __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, timeout, NULL); } #ifdef CONFIG_COMPAT_32BIT_TIME SYSCALL_DEFINE5(recvmmsg_time32, int, fd, struct mmsghdr __user *, mmsg, unsigned int, vlen, unsigned int, flags, struct old_timespec32 __user *, timeout) { if (flags & MSG_CMSG_COMPAT) return -EINVAL; return __sys_recvmmsg(fd, mmsg, vlen, flags, NULL, timeout); } #endif #ifdef __ARCH_WANT_SYS_SOCKETCALL /* Argument list sizes for sys_socketcall */ #define AL(x) ((x) * sizeof(unsigned long)) static const unsigned char nargs[21] = { AL(0), AL(3), AL(3), AL(3), AL(2), AL(3), AL(3), AL(3), AL(4), AL(4), AL(4), AL(6), AL(6), AL(2), AL(5), AL(5), AL(3), AL(3), AL(4), AL(5), AL(4) }; #undef AL /* * System call vectors. * * Argument checking cleaned up. Saved 20% in size. * This function doesn't need to set the kernel lock because * it is set by the callees. */ SYSCALL_DEFINE2(socketcall, int, call, unsigned long __user *, args) { unsigned long a[AUDITSC_ARGS]; unsigned long a0, a1; int err; unsigned int len; if (call < 1 || call > SYS_SENDMMSG) return -EINVAL; call = array_index_nospec(call, SYS_SENDMMSG + 1); len = nargs[call]; if (len > sizeof(a)) return -EINVAL; /* copy_from_user should be SMP safe. */ if (copy_from_user(a, args, len)) return -EFAULT; err = audit_socketcall(nargs[call] / sizeof(unsigned long), a); if (err) return err; a0 = a[0]; a1 = a[1]; switch (call) { case SYS_SOCKET: err = __sys_socket(a0, a1, a[2]); break; case SYS_BIND: err = __sys_bind(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_CONNECT: err = __sys_connect(a0, (struct sockaddr __user *)a1, a[2]); break; case SYS_LISTEN: err = __sys_listen(a0, a1); break; case SYS_ACCEPT: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], 0); break; case SYS_GETSOCKNAME: err = __sys_getsockname(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_GETPEERNAME: err = __sys_getpeername(a0, (struct sockaddr __user *)a1, (int __user *)a[2]); break; case SYS_SOCKETPAIR: err = __sys_socketpair(a0, a1, a[2], (int __user *)a[3]); break; case SYS_SEND: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], NULL, 0); break; case SYS_SENDTO: err = __sys_sendto(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], a[5]); break; case SYS_RECV: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], NULL, NULL); break; case SYS_RECVFROM: err = __sys_recvfrom(a0, (void __user *)a1, a[2], a[3], (struct sockaddr __user *)a[4], (int __user *)a[5]); break; case SYS_SHUTDOWN: err = __sys_shutdown(a0, a1); break; case SYS_SETSOCKOPT: err = __sys_setsockopt(a0, a1, a[2], (char __user *)a[3], a[4]); break; case SYS_GETSOCKOPT: err = __sys_getsockopt(a0, a1, a[2], (char __user *)a[3], (int __user *)a[4]); break; case SYS_SENDMSG: err = __sys_sendmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_SENDMMSG: err = __sys_sendmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], true); break; case SYS_RECVMSG: err = __sys_recvmsg(a0, (struct user_msghdr __user *)a1, a[2], true); break; case SYS_RECVMMSG: if (IS_ENABLED(CONFIG_64BIT) || !IS_ENABLED(CONFIG_64BIT_TIME)) err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], (struct __kernel_timespec __user *)a[4], NULL); else err = __sys_recvmmsg(a0, (struct mmsghdr __user *)a1, a[2], a[3], NULL, (struct old_timespec32 __user *)a[4]); break; case SYS_ACCEPT4: err = __sys_accept4(a0, (struct sockaddr __user *)a1, (int __user *)a[2], a[3]); break; default: err = -EINVAL; break; } return err; } #endif /* __ARCH_WANT_SYS_SOCKETCALL */ /** * sock_register - add a socket protocol handler * @ops: description of protocol * * This function is called by a protocol handler that wants to * advertise its address family, and have it linked into the * socket interface. The value ops->family corresponds to the * socket system call protocol family. */ int sock_register(const struct net_proto_family *ops) { int err; if (ops->family >= NPROTO) { pr_crit("protocol %d >= NPROTO(%d)\n", ops->family, NPROTO); return -ENOBUFS; } spin_lock(&net_family_lock); if (rcu_dereference_protected(net_families[ops->family], lockdep_is_held(&net_family_lock))) err = -EEXIST; else { rcu_assign_pointer(net_families[ops->family], ops); err = 0; } spin_unlock(&net_family_lock); pr_info("NET: Registered protocol family %d\n", ops->family); return err; } EXPORT_SYMBOL(sock_register); /** * sock_unregister - remove a protocol handler * @family: protocol family to remove * * This function is called by a protocol handler that wants to * remove its address family, and have it unlinked from the * new socket creation. * * If protocol handler is a module, then it can use module reference * counts to protect against new references. If protocol handler is not * a module then it needs to provide its own protection in * the ops->create routine. */ void sock_unregister(int family) { BUG_ON(family < 0 || family >= NPROTO); spin_lock(&net_family_lock); RCU_INIT_POINTER(net_families[family], NULL); spin_unlock(&net_family_lock); synchronize_rcu(); pr_info("NET: Unregistered protocol family %d\n", family); } EXPORT_SYMBOL(sock_unregister); bool sock_is_registered(int family) { return family < NPROTO && rcu_access_pointer(net_families[family]); } static int __init sock_init(void) { int err; /* * Initialize the network sysctl infrastructure. */ err = net_sysctl_init(); if (err) goto out; /* * Initialize skbuff SLAB cache */ skb_init(); /* * Initialize the protocols module. */ init_inodecache(); err = register_filesystem(&sock_fs_type); if (err) goto out_fs; sock_mnt = kern_mount(&sock_fs_type); if (IS_ERR(sock_mnt)) { err = PTR_ERR(sock_mnt); goto out_mount; } /* The real protocol initialization is performed in later initcalls. */ #ifdef CONFIG_NETFILTER err = netfilter_init(); if (err) goto out; #endif ptp_classifier_init(); out: return err; out_mount: unregister_filesystem(&sock_fs_type); out_fs: goto out; } core_initcall(sock_init); /* early initcall */ #ifdef CONFIG_PROC_FS void socket_seq_show(struct seq_file *seq) { seq_printf(seq, "sockets: used %d\n", sock_inuse_get(seq->private)); } #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_COMPAT static int compat_dev_ifconf(struct net *net, struct compat_ifconf __user *uifc32) { struct compat_ifconf ifc32; struct ifconf ifc; int err; if (copy_from_user(&ifc32, uifc32, sizeof(struct compat_ifconf))) return -EFAULT; ifc.ifc_len = ifc32.ifc_len; ifc.ifc_req = compat_ptr(ifc32.ifcbuf); rtnl_lock(); err = dev_ifconf(net, &ifc, sizeof(struct compat_ifreq)); rtnl_unlock(); if (err) return err; ifc32.ifc_len = ifc.ifc_len; if (copy_to_user(uifc32, &ifc32, sizeof(struct compat_ifconf))) return -EFAULT; return 0; } static int ethtool_ioctl(struct net *net, struct compat_ifreq __user *ifr32) { struct compat_ethtool_rxnfc __user *compat_rxnfc; bool convert_in = false, convert_out = false; size_t buf_size = 0; struct ethtool_rxnfc __user *rxnfc = NULL; struct ifreq ifr; u32 rule_cnt = 0, actual_rule_cnt; u32 ethcmd; u32 data; int ret; if (get_user(data, &ifr32->ifr_ifru.ifru_data)) return -EFAULT; compat_rxnfc = compat_ptr(data); if (get_user(ethcmd, &compat_rxnfc->cmd)) return -EFAULT; /* Most ethtool structures are defined without padding. * Unfortunately struct ethtool_rxnfc is an exception. */ switch (ethcmd) { default: break; case ETHTOOL_GRXCLSRLALL: /* Buffer size is variable */ if (get_user(rule_cnt, &compat_rxnfc->rule_cnt)) return -EFAULT; if (rule_cnt > KMALLOC_MAX_SIZE / sizeof(u32)) return -ENOMEM; buf_size += rule_cnt * sizeof(u32); /* fall through */ case ETHTOOL_GRXRINGS: case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_SRXCLSRLINS: convert_out = true; /* fall through */ case ETHTOOL_SRXCLSRLDEL: buf_size += sizeof(struct ethtool_rxnfc); convert_in = true; rxnfc = compat_alloc_user_space(buf_size); break; } if (copy_from_user(&ifr.ifr_name, &ifr32->ifr_name, IFNAMSIZ)) return -EFAULT; ifr.ifr_data = convert_in ? rxnfc : (void __user *)compat_rxnfc; if (convert_in) { /* We expect there to be holes between fs.m_ext and * fs.ring_cookie and at the end of fs, but nowhere else. */ BUILD_BUG_ON(offsetof(struct compat_ethtool_rxnfc, fs.m_ext) + sizeof(compat_rxnfc->fs.m_ext) != offsetof(struct ethtool_rxnfc, fs.m_ext) + sizeof(rxnfc->fs.m_ext)); BUILD_BUG_ON( offsetof(struct compat_ethtool_rxnfc, fs.location) - offsetof(struct compat_ethtool_rxnfc, fs.ring_cookie) != offsetof(struct ethtool_rxnfc, fs.location) - offsetof(struct ethtool_rxnfc, fs.ring_cookie)); if (copy_in_user(rxnfc, compat_rxnfc, (void __user *)(&rxnfc->fs.m_ext + 1) - (void __user *)rxnfc) || copy_in_user(&rxnfc->fs.ring_cookie, &compat_rxnfc->fs.ring_cookie, (void __user *)(&rxnfc->fs.location + 1) - (void __user *)&rxnfc->fs.ring_cookie)) return -EFAULT; if (ethcmd == ETHTOOL_GRXCLSRLALL) { if (put_user(rule_cnt, &rxnfc->rule_cnt)) return -EFAULT; } else if (copy_in_user(&rxnfc->rule_cnt, &compat_rxnfc->rule_cnt, sizeof(rxnfc->rule_cnt))) return -EFAULT; } ret = dev_ioctl(net, SIOCETHTOOL, &ifr, NULL); if (ret) return ret; if (convert_out) { if (copy_in_user(compat_rxnfc, rxnfc, (const void __user *)(&rxnfc->fs.m_ext + 1) - (const void __user *)rxnfc) || copy_in_user(&compat_rxnfc->fs.ring_cookie, &rxnfc->fs.ring_cookie, (const void __user *)(&rxnfc->fs.location + 1) - (const void __user *)&rxnfc->fs.ring_cookie) || copy_in_user(&compat_rxnfc->rule_cnt, &rxnfc->rule_cnt, sizeof(rxnfc->rule_cnt))) return -EFAULT; if (ethcmd == ETHTOOL_GRXCLSRLALL) { /* As an optimisation, we only copy the actual * number of rules that the underlying * function returned. Since Mallory might * change the rule count in user memory, we * check that it is less than the rule count * originally given (as the user buffer size), * which has been range-checked. */ if (get_user(actual_rule_cnt, &rxnfc->rule_cnt)) return -EFAULT; if (actual_rule_cnt < rule_cnt) rule_cnt = actual_rule_cnt; if (copy_in_user(&compat_rxnfc->rule_locs[0], &rxnfc->rule_locs[0], rule_cnt * sizeof(u32))) return -EFAULT; } } return 0; } static int compat_siocwandev(struct net *net, struct compat_ifreq __user *uifr32) { compat_uptr_t uptr32; struct ifreq ifr; void __user *saved; int err; if (copy_from_user(&ifr, uifr32, sizeof(struct compat_ifreq))) return -EFAULT; if (get_user(uptr32, &uifr32->ifr_settings.ifs_ifsu)) return -EFAULT; saved = ifr.ifr_settings.ifs_ifsu.raw_hdlc; ifr.ifr_settings.ifs_ifsu.raw_hdlc = compat_ptr(uptr32); err = dev_ioctl(net, SIOCWANDEV, &ifr, NULL); if (!err) { ifr.ifr_settings.ifs_ifsu.raw_hdlc = saved; if (copy_to_user(uifr32, &ifr, sizeof(struct compat_ifreq))) err = -EFAULT; } return err; } /* Handle ioctls that use ifreq::ifr_data and just need struct ifreq converted */ static int compat_ifr_data_ioctl(struct net *net, unsigned int cmd, struct compat_ifreq __user *u_ifreq32) { struct ifreq ifreq; u32 data32; if (!is_socket_ioctl_cmd(cmd)) return -ENOTTY; if (copy_from_user(ifreq.ifr_name, u_ifreq32->ifr_name, IFNAMSIZ)) return -EFAULT; if (get_user(data32, &u_ifreq32->ifr_data)) return -EFAULT; ifreq.ifr_data = compat_ptr(data32); return dev_ioctl(net, cmd, &ifreq, NULL); } static int compat_ifreq_ioctl(struct net *net, struct socket *sock, unsigned int cmd, struct compat_ifreq __user *uifr32) { struct ifreq __user *uifr; int err; /* Handle the fact that while struct ifreq has the same *layout* on * 32/64 for everything but ifreq::ifru_ifmap and ifreq::ifru_data, * which are handled elsewhere, it still has different *size* due to * ifreq::ifru_ifmap (which is 16 bytes on 32 bit, 24 bytes on 64-bit, * resulting in struct ifreq being 32 and 40 bytes respectively). * As a result, if the struct happens to be at the end of a page and * the next page isn't readable/writable, we get a fault. To prevent * that, copy back and forth to the full size. */ uifr = compat_alloc_user_space(sizeof(*uifr)); if (copy_in_user(uifr, uifr32, sizeof(*uifr32))) return -EFAULT; err = sock_do_ioctl(net, sock, cmd, (unsigned long)uifr); if (!err) { switch (cmd) { case SIOCGIFFLAGS: case SIOCGIFMETRIC: case SIOCGIFMTU: case SIOCGIFMEM: case SIOCGIFHWADDR: case SIOCGIFINDEX: case SIOCGIFADDR: case SIOCGIFBRDADDR: case SIOCGIFDSTADDR: case SIOCGIFNETMASK: case SIOCGIFPFLAGS: case SIOCGIFTXQLEN: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCGIFNAME: if (copy_in_user(uifr32, uifr, sizeof(*uifr32))) err = -EFAULT; break; } } return err; } static int compat_sioc_ifmap(struct net *net, unsigned int cmd, struct compat_ifreq __user *uifr32) { struct ifreq ifr; struct compat_ifmap __user *uifmap32; int err; uifmap32 = &uifr32->ifr_ifru.ifru_map; err = copy_from_user(&ifr, uifr32, sizeof(ifr.ifr_name)); err |= get_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); err |= get_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); err |= get_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); err |= get_user(ifr.ifr_map.irq, &uifmap32->irq); err |= get_user(ifr.ifr_map.dma, &uifmap32->dma); err |= get_user(ifr.ifr_map.port, &uifmap32->port); if (err) return -EFAULT; err = dev_ioctl(net, cmd, &ifr, NULL); if (cmd == SIOCGIFMAP && !err) { err = copy_to_user(uifr32, &ifr, sizeof(ifr.ifr_name)); err |= put_user(ifr.ifr_map.mem_start, &uifmap32->mem_start); err |= put_user(ifr.ifr_map.mem_end, &uifmap32->mem_end); err |= put_user(ifr.ifr_map.base_addr, &uifmap32->base_addr); err |= put_user(ifr.ifr_map.irq, &uifmap32->irq); err |= put_user(ifr.ifr_map.dma, &uifmap32->dma); err |= put_user(ifr.ifr_map.port, &uifmap32->port); if (err) err = -EFAULT; } return err; } struct rtentry32 { u32 rt_pad1; struct sockaddr rt_dst; /* target address */ struct sockaddr rt_gateway; /* gateway addr (RTF_GATEWAY) */ struct sockaddr rt_genmask; /* target network mask (IP) */ unsigned short rt_flags; short rt_pad2; u32 rt_pad3; unsigned char rt_tos; unsigned char rt_class; short rt_pad4; short rt_metric; /* +1 for binary compatibility! */ /* char * */ u32 rt_dev; /* forcing the device at add */ u32 rt_mtu; /* per route MTU/Window */ u32 rt_window; /* Window clamping */ unsigned short rt_irtt; /* Initial RTT */ }; struct in6_rtmsg32 { struct in6_addr rtmsg_dst; struct in6_addr rtmsg_src; struct in6_addr rtmsg_gateway; u32 rtmsg_type; u16 rtmsg_dst_len; u16 rtmsg_src_len; u32 rtmsg_metric; u32 rtmsg_info; u32 rtmsg_flags; s32 rtmsg_ifindex; }; static int routing_ioctl(struct net *net, struct socket *sock, unsigned int cmd, void __user *argp) { int ret; void *r = NULL; struct in6_rtmsg r6; struct rtentry r4; char devname[16]; u32 rtdev; mm_segment_t old_fs = get_fs(); if (sock && sock->sk && sock->sk->sk_family == AF_INET6) { /* ipv6 */ struct in6_rtmsg32 __user *ur6 = argp; ret = copy_from_user(&r6.rtmsg_dst, &(ur6->rtmsg_dst), 3 * sizeof(struct in6_addr)); ret |= get_user(r6.rtmsg_type, &(ur6->rtmsg_type)); ret |= get_user(r6.rtmsg_dst_len, &(ur6->rtmsg_dst_len)); ret |= get_user(r6.rtmsg_src_len, &(ur6->rtmsg_src_len)); ret |= get_user(r6.rtmsg_metric, &(ur6->rtmsg_metric)); ret |= get_user(r6.rtmsg_info, &(ur6->rtmsg_info)); ret |= get_user(r6.rtmsg_flags, &(ur6->rtmsg_flags)); ret |= get_user(r6.rtmsg_ifindex, &(ur6->rtmsg_ifindex)); r = (void *) &r6; } else { /* ipv4 */ struct rtentry32 __user *ur4 = argp; ret = copy_from_user(&r4.rt_dst, &(ur4->rt_dst), 3 * sizeof(struct sockaddr)); ret |= get_user(r4.rt_flags, &(ur4->rt_flags)); ret |= get_user(r4.rt_metric, &(ur4->rt_metric)); ret |= get_user(r4.rt_mtu, &(ur4->rt_mtu)); ret |= get_user(r4.rt_window, &(ur4->rt_window)); ret |= get_user(r4.rt_irtt, &(ur4->rt_irtt)); ret |= get_user(rtdev, &(ur4->rt_dev)); if (rtdev) { ret |= copy_from_user(devname, compat_ptr(rtdev), 15); r4.rt_dev = (char __user __force *)devname; devname[15] = 0; } else r4.rt_dev = NULL; r = (void *) &r4; } if (ret) { ret = -EFAULT; goto out; } set_fs(KERNEL_DS); ret = sock_do_ioctl(net, sock, cmd, (unsigned long) r); set_fs(old_fs); out: return ret; } /* Since old style bridge ioctl's endup using SIOCDEVPRIVATE * for some operations; this forces use of the newer bridge-utils that * use compatible ioctls */ static int old_bridge_ioctl(compat_ulong_t __user *argp) { compat_ulong_t tmp; if (get_user(tmp, argp)) return -EFAULT; if (tmp == BRCTL_GET_VERSION) return BRCTL_VERSION + 1; return -EINVAL; } static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, unsigned int cmd, unsigned long arg) { void __user *argp = compat_ptr(arg); struct sock *sk = sock->sk; struct net *net = sock_net(sk); if (cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) return compat_ifr_data_ioctl(net, cmd, argp); switch (cmd) { case SIOCSIFBR: case SIOCGIFBR: return old_bridge_ioctl(argp); case SIOCGIFCONF: return compat_dev_ifconf(net, argp); case SIOCETHTOOL: return ethtool_ioctl(net, argp); case SIOCWANDEV: return compat_siocwandev(net, argp); case SIOCGIFMAP: case SIOCSIFMAP: return compat_sioc_ifmap(net, cmd, argp); case SIOCADDRT: case SIOCDELRT: return routing_ioctl(net, sock, cmd, argp); case SIOCGSTAMP_OLD: case SIOCGSTAMPNS_OLD: if (!sock->ops->gettstamp) return -ENOIOCTLCMD; return sock->ops->gettstamp(sock, argp, cmd == SIOCGSTAMP_OLD, !COMPAT_USE_64BIT_TIME); case SIOCBONDSLAVEINFOQUERY: case SIOCBONDINFOQUERY: case SIOCSHWTSTAMP: case SIOCGHWTSTAMP: return compat_ifr_data_ioctl(net, cmd, argp); case FIOSETOWN: case SIOCSPGRP: case FIOGETOWN: case SIOCGPGRP: case SIOCBRADDBR: case SIOCBRDELBR: case SIOCGIFVLAN: case SIOCSIFVLAN: case SIOCADDDLCI: case SIOCDELDLCI: case SIOCGSKNS: case SIOCGSTAMP_NEW: case SIOCGSTAMPNS_NEW: return sock_ioctl(file, cmd, arg); case SIOCGIFFLAGS: case SIOCSIFFLAGS: case SIOCGIFMETRIC: case SIOCSIFMETRIC: case SIOCGIFMTU: case SIOCSIFMTU: case SIOCGIFMEM: case SIOCSIFMEM: case SIOCGIFHWADDR: case SIOCSIFHWADDR: case SIOCADDMULTI: case SIOCDELMULTI: case SIOCGIFINDEX: case SIOCGIFADDR: case SIOCSIFADDR: case SIOCSIFHWBROADCAST: case SIOCDIFADDR: case SIOCGIFBRDADDR: case SIOCSIFBRDADDR: case SIOCGIFDSTADDR: case SIOCSIFDSTADDR: case SIOCGIFNETMASK: case SIOCSIFNETMASK: case SIOCSIFPFLAGS: case SIOCGIFPFLAGS: case SIOCGIFTXQLEN: case SIOCSIFTXQLEN: case SIOCBRADDIF: case SIOCBRDELIF: case SIOCGIFNAME: case SIOCSIFNAME: case SIOCGMIIPHY: case SIOCGMIIREG: case SIOCSMIIREG: case SIOCBONDENSLAVE: case SIOCBONDRELEASE: case SIOCBONDSETHWADDR: case SIOCBONDCHANGEACTIVE: return compat_ifreq_ioctl(net, sock, cmd, argp); case SIOCSARP: case SIOCGARP: case SIOCDARP: case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } return -ENOIOCTLCMD; } static long compat_sock_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct socket *sock = file->private_data; int ret = -ENOIOCTLCMD; struct sock *sk; struct net *net; sk = sock->sk; net = sock_net(sk); if (sock->ops->compat_ioctl) ret = sock->ops->compat_ioctl(sock, cmd, arg); if (ret == -ENOIOCTLCMD && (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)) ret = compat_wext_handle_ioctl(net, cmd, arg); if (ret == -ENOIOCTLCMD) ret = compat_sock_ioctl_trans(file, sock, cmd, arg); return ret; } #endif /** * kernel_bind - bind an address to a socket (kernel space) * @sock: socket * @addr: address * @addrlen: length of address * * Returns 0 or an error. */ int kernel_bind(struct socket *sock, struct sockaddr *addr, int addrlen) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return sock->ops->bind(sock, (struct sockaddr *)&address, addrlen); } EXPORT_SYMBOL(kernel_bind); /** * kernel_listen - move socket to listening state (kernel space) * @sock: socket * @backlog: pending connections queue size * * Returns 0 or an error. */ int kernel_listen(struct socket *sock, int backlog) { return sock->ops->listen(sock, backlog); } EXPORT_SYMBOL(kernel_listen); /** * kernel_accept - accept a connection (kernel space) * @sock: listening socket * @newsock: new connected socket * @flags: flags * * @flags must be SOCK_CLOEXEC, SOCK_NONBLOCK or 0. * If it fails, @newsock is guaranteed to be %NULL. * Returns 0 or an error. */ int kernel_accept(struct socket *sock, struct socket **newsock, int flags) { struct sock *sk = sock->sk; int err; err = sock_create_lite(sk->sk_family, sk->sk_type, sk->sk_protocol, newsock); if (err < 0) goto done; err = sock->ops->accept(sock, *newsock, flags, true); if (err < 0) { sock_release(*newsock); *newsock = NULL; goto done; } (*newsock)->ops = sock->ops; __module_get((*newsock)->ops->owner); done: return err; } EXPORT_SYMBOL(kernel_accept); /** * kernel_connect - connect a socket (kernel space) * @sock: socket * @addr: address * @addrlen: address length * @flags: flags (O_NONBLOCK, ...) * * For datagram sockets, @addr is the addres to which datagrams are sent * by default, and the only address from which datagrams are received. * For stream sockets, attempts to connect to @addr. * Returns 0 or an error code. */ int kernel_connect(struct socket *sock, struct sockaddr *addr, int addrlen, int flags) { struct sockaddr_storage address; memcpy(&address, addr, addrlen); return sock->ops->connect(sock, (struct sockaddr *)&address, addrlen, flags); } EXPORT_SYMBOL(kernel_connect); /** * kernel_getsockname - get the address which the socket is bound (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is bound. * Returns 0 or an error code. */ int kernel_getsockname(struct socket *sock, struct sockaddr *addr) { return sock->ops->getname(sock, addr, 0); } EXPORT_SYMBOL(kernel_getsockname); /** * kernel_peername - get the address which the socket is connected (kernel space) * @sock: socket * @addr: address holder * * Fills the @addr pointer with the address which the socket is connected. * Returns 0 or an error code. */ int kernel_getpeername(struct socket *sock, struct sockaddr *addr) { return sock->ops->getname(sock, addr, 1); } EXPORT_SYMBOL(kernel_getpeername); /** * kernel_getsockopt - get a socket option (kernel space) * @sock: socket * @level: API level (SOL_SOCKET, ...) * @optname: option tag * @optval: option value * @optlen: option length * * Assigns the option length to @optlen. * Returns 0 or an error. */ int kernel_getsockopt(struct socket *sock, int level, int optname, char *optval, int *optlen) { mm_segment_t oldfs = get_fs(); char __user *uoptval; int __user *uoptlen; int err; uoptval = (char __user __force *) optval; uoptlen = (int __user __force *) optlen; set_fs(KERNEL_DS); if (level == SOL_SOCKET) err = sock_getsockopt(sock, level, optname, uoptval, uoptlen); else err = sock->ops->getsockopt(sock, level, optname, uoptval, uoptlen); set_fs(oldfs); return err; } EXPORT_SYMBOL(kernel_getsockopt); /** * kernel_setsockopt - set a socket option (kernel space) * @sock: socket * @level: API level (SOL_SOCKET, ...) * @optname: option tag * @optval: option value * @optlen: option length * * Returns 0 or an error. */ int kernel_setsockopt(struct socket *sock, int level, int optname, char *optval, unsigned int optlen) { mm_segment_t oldfs = get_fs(); char __user *uoptval; int err; uoptval = (char __user __force *) optval; set_fs(KERNEL_DS); if (level == SOL_SOCKET) err = sock_setsockopt(sock, level, optname, uoptval, optlen); else err = sock->ops->setsockopt(sock, level, optname, uoptval, optlen); set_fs(oldfs); return err; } EXPORT_SYMBOL(kernel_setsockopt); /** * kernel_sendpage - send a &page through a socket (kernel space) * @sock: socket * @page: page * @offset: page offset * @size: total size in bytes * @flags: flags (MSG_DONTWAIT, ...) * * Returns the total amount sent in bytes or an error. */ int kernel_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { if (sock->ops->sendpage) return sock->ops->sendpage(sock, page, offset, size, flags); return sock_no_sendpage(sock, page, offset, size, flags); } EXPORT_SYMBOL(kernel_sendpage); /** * kernel_sendpage_locked - send a &page through the locked sock (kernel space) * @sk: sock * @page: page * @offset: page offset * @size: total size in bytes * @flags: flags (MSG_DONTWAIT, ...) * * Returns the total amount sent in bytes or an error. * Caller must hold @sk. */ int kernel_sendpage_locked(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct socket *sock = sk->sk_socket; if (sock->ops->sendpage_locked) return sock->ops->sendpage_locked(sk, page, offset, size, flags); return sock_no_sendpage_locked(sk, page, offset, size, flags); } EXPORT_SYMBOL(kernel_sendpage_locked); /** * kernel_shutdown - shut down part of a full-duplex connection (kernel space) * @sock: socket * @how: connection part * * Returns 0 or an error. */ int kernel_sock_shutdown(struct socket *sock, enum sock_shutdown_cmd how) { return sock->ops->shutdown(sock, how); } EXPORT_SYMBOL(kernel_sock_shutdown); /** * kernel_sock_ip_overhead - returns the IP overhead imposed by a socket * @sk: socket * * This routine returns the IP overhead imposed by a socket i.e. * the length of the underlying IP header, depending on whether * this is an IPv4 or IPv6 socket and the length from IP options turned * on at the socket. Assumes that the caller has a lock on the socket. */ u32 kernel_sock_ip_overhead(struct sock *sk) { struct inet_sock *inet; struct ip_options_rcu *opt; u32 overhead = 0; #if IS_ENABLED(CONFIG_IPV6) struct ipv6_pinfo *np; struct ipv6_txoptions *optv6 = NULL; #endif /* IS_ENABLED(CONFIG_IPV6) */ if (!sk) return overhead; switch (sk->sk_family) { case AF_INET: inet = inet_sk(sk); overhead += sizeof(struct iphdr); opt = rcu_dereference_protected(inet->inet_opt, sock_owned_by_user(sk)); if (opt) overhead += opt->opt.optlen; return overhead; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: np = inet6_sk(sk); overhead += sizeof(struct ipv6hdr); if (np) optv6 = rcu_dereference_protected(np->opt, sock_owned_by_user(sk)); if (optv6) overhead += (optv6->opt_flen + optv6->opt_nflen); return overhead; #endif /* IS_ENABLED(CONFIG_IPV6) */ default: /* Returns 0 overhead if the socket is not ipv4 or ipv6 */ return overhead; } } EXPORT_SYMBOL(kernel_sock_ip_overhead); |
| 703 684 20 14 4 32 14 33 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 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * http://burtleburtle.net/bob/hash/ * * These are the credits from Bob's sources: * * lookup3.c, by Bob Jenkins, May 2006, Public Domain. * * These are functions for producing 32-bit hashes for hash table lookup. * hashword(), hashlittle(), hashlittle2(), hashbig(), mix(), and final() * are externally useful functions. Routines to test the hash are included * if SELF_TEST is defined. You can use this free for any purpose. It's in * the public domain. It has no warranty. * * Copyright (C) 2009-2010 Jozsef Kadlecsik (kadlec@netfilter.org) * * I've modified Bob's hash to be useful in the Linux kernel, and * any bugs present are my fault. * Jozsef */ #include <linux/bitops.h> #include <linux/unaligned/packed_struct.h> /* Best hash sizes are of power of two */ #define jhash_size(n) ((u32)1<<(n)) /* Mask the hash value, i.e (value & jhash_mask(n)) instead of (value % n) */ #define jhash_mask(n) (jhash_size(n)-1) /* __jhash_mix -- mix 3 32-bit values reversibly. */ #define __jhash_mix(a, b, c) \ { \ a -= c; a ^= rol32(c, 4); c += b; \ b -= a; b ^= rol32(a, 6); a += c; \ c -= b; c ^= rol32(b, 8); b += a; \ a -= c; a ^= rol32(c, 16); c += b; \ b -= a; b ^= rol32(a, 19); a += c; \ c -= b; c ^= rol32(b, 4); b += a; \ } /* __jhash_final - final mixing of 3 32-bit values (a,b,c) into c */ #define __jhash_final(a, b, c) \ { \ c ^= b; c -= rol32(b, 14); \ a ^= c; a -= rol32(c, 11); \ b ^= a; b -= rol32(a, 25); \ c ^= b; c -= rol32(b, 16); \ a ^= c; a -= rol32(c, 4); \ b ^= a; b -= rol32(a, 14); \ c ^= b; c -= rol32(b, 24); \ } /* An arbitrary initial parameter */ #define JHASH_INITVAL 0xdeadbeef /* jhash - hash an arbitrary key * @k: sequence of bytes as key * @length: the length of the key * @initval: the previous hash, or an arbitray value * * The generic version, hashes an arbitrary sequence of bytes. * No alignment or length assumptions are made about the input key. * * Returns the hash value of the key. The result depends on endianness. */ static inline u32 jhash(const void *key, u32 length, u32 initval) { u32 a, b, c; const u8 *k = key; /* Set up the internal state */ a = b = c = JHASH_INITVAL + length + initval; /* All but the last block: affect some 32 bits of (a,b,c) */ while (length > 12) { a += __get_unaligned_cpu32(k); b += __get_unaligned_cpu32(k + 4); c += __get_unaligned_cpu32(k + 8); __jhash_mix(a, b, c); length -= 12; k += 12; } /* Last block: affect all 32 bits of (c) */ switch (length) { case 12: c += (u32)k[11]<<24; /* fall through */ case 11: c += (u32)k[10]<<16; /* fall through */ case 10: c += (u32)k[9]<<8; /* fall through */ case 9: c += k[8]; /* fall through */ case 8: b += (u32)k[7]<<24; /* fall through */ case 7: b += (u32)k[6]<<16; /* fall through */ case 6: b += (u32)k[5]<<8; /* fall through */ case 5: b += k[4]; /* fall through */ case 4: a += (u32)k[3]<<24; /* fall through */ case 3: a += (u32)k[2]<<16; /* fall through */ case 2: a += (u32)k[1]<<8; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ break; } return c; } /* jhash2 - hash an array of u32's * @k: the key which must be an array of u32's * @length: the number of u32's in the key * @initval: the previous hash, or an arbitray value * * Returns the hash value of the key. */ static inline u32 jhash2(const u32 *k, u32 length, u32 initval) { u32 a, b, c; /* Set up the internal state */ a = b = c = JHASH_INITVAL + (length<<2) + initval; /* Handle most of the key */ while (length > 3) { a += k[0]; b += k[1]; c += k[2]; __jhash_mix(a, b, c); length -= 3; k += 3; } /* Handle the last 3 u32's */ switch (length) { case 3: c += k[2]; /* fall through */ case 2: b += k[1]; /* fall through */ case 1: a += k[0]; __jhash_final(a, b, c); case 0: /* Nothing left to add */ break; } return c; } /* __jhash_nwords - hash exactly 3, 2 or 1 word(s) */ static inline u32 __jhash_nwords(u32 a, u32 b, u32 c, u32 initval) { a += initval; b += initval; c += initval; __jhash_final(a, b, c); return c; } static inline u32 jhash_3words(u32 a, u32 b, u32 c, u32 initval) { return __jhash_nwords(a, b, c, initval + JHASH_INITVAL + (3 << 2)); } static inline u32 jhash_2words(u32 a, u32 b, u32 initval) { return __jhash_nwords(a, b, 0, initval + JHASH_INITVAL + (2 << 2)); } static inline u32 jhash_1word(u32 a, u32 initval) { return __jhash_nwords(a, 0, 0, initval + JHASH_INITVAL + (1 << 2)); } #endif /* _LINUX_JHASH_H */ |
| 272 5544 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 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 */ #ifndef _ASM_X86_PAGE_64_H #define _ASM_X86_PAGE_64_H #include <asm/page_64_types.h> #ifndef __ASSEMBLY__ #include <asm/alternative.h> /* duplicated to the one in bootmem.h */ extern unsigned long max_pfn; extern unsigned long phys_base; extern unsigned long page_offset_base; extern unsigned long vmalloc_base; extern unsigned long vmemmap_base; static inline unsigned long __phys_addr_nodebug(unsigned long x) { unsigned long y = x - __START_KERNEL_map; /* use the carry flag to determine if x was < __START_KERNEL_map */ x = y + ((x > y) ? phys_base : (__START_KERNEL_map - PAGE_OFFSET)); return x; } #ifdef CONFIG_DEBUG_VIRTUAL extern unsigned long __phys_addr(unsigned long); extern unsigned long __phys_addr_symbol(unsigned long); #else #define __phys_addr(x) __phys_addr_nodebug(x) #define __phys_addr_symbol(x) \ ((unsigned long)(x) - __START_KERNEL_map + phys_base) #endif #define __phys_reloc_hide(x) (x) #ifdef CONFIG_FLATMEM #define pfn_valid(pfn) ((pfn) < max_pfn) #endif void clear_page_orig(void *page); void clear_page_rep(void *page); void clear_page_erms(void *page); static inline void clear_page(void *page) { alternative_call_2(clear_page_orig, clear_page_rep, X86_FEATURE_REP_GOOD, clear_page_erms, X86_FEATURE_ERMS, "=D" (page), "0" (page) : "cc", "memory", "rax", "rcx"); } void copy_page(void *to, void *from); #endif /* !__ASSEMBLY__ */ #ifdef CONFIG_X86_VSYSCALL_EMULATION # define __HAVE_ARCH_GATE_AREA 1 #endif #endif /* _ASM_X86_PAGE_64_H */ |
| 439 439 439 439 439 74 74 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 | // SPDX-License-Identifier: GPL-2.0 /* sysfs entries for device PM */ #include <linux/device.h> #include <linux/string.h> #include <linux/export.h> #include <linux/pm_qos.h> #include <linux/pm_runtime.h> #include <linux/pm_wakeup.h> #include <linux/atomic.h> #include <linux/jiffies.h> #include "power.h" /* * control - Report/change current runtime PM setting of the device * * Runtime power management of a device can be blocked with the help of * this attribute. All devices have one of the following two values for * the power/control file: * * + "auto\n" to allow the device to be power managed at run time; * + "on\n" to prevent the device from being power managed at run time; * * The default for all devices is "auto", which means that devices may be * subject to automatic power management, depending on their drivers. * Changing this attribute to "on" prevents the driver from power managing * the device at run time. Doing that while the device is suspended causes * it to be woken up. * * wakeup - Report/change current wakeup option for device * * Some devices support "wakeup" events, which are hardware signals * used to activate devices from suspended or low power states. Such * devices have one of three values for the sysfs power/wakeup file: * * + "enabled\n" to issue the events; * + "disabled\n" not to do so; or * + "\n" for temporary or permanent inability to issue wakeup. * * (For example, unconfigured USB devices can't issue wakeups.) * * Familiar examples of devices that can issue wakeup events include * keyboards and mice (both PS2 and USB styles), power buttons, modems, * "Wake-On-LAN" Ethernet links, GPIO lines, and more. Some events * will wake the entire system from a suspend state; others may just * wake up the device (if the system as a whole is already active). * Some wakeup events use normal IRQ lines; other use special out * of band signaling. * * It is the responsibility of device drivers to enable (or disable) * wakeup signaling as part of changing device power states, respecting * the policy choices provided through the driver model. * * Devices may not be able to generate wakeup events from all power * states. Also, the events may be ignored in some configurations; * for example, they might need help from other devices that aren't * active, or which may have wakeup disabled. Some drivers rely on * wakeup events internally (unless they are disabled), keeping * their hardware in low power modes whenever they're unused. This * saves runtime power, without requiring system-wide sleep states. * * async - Report/change current async suspend setting for the device * * Asynchronous suspend and resume of the device during system-wide power * state transitions can be enabled by writing "enabled" to this file. * Analogously, if "disabled" is written to this file, the device will be * suspended and resumed synchronously. * * All devices have one of the following two values for power/async: * * + "enabled\n" to permit the asynchronous suspend/resume of the device; * + "disabled\n" to forbid it; * * NOTE: It generally is unsafe to permit the asynchronous suspend/resume * of a device unless it is certain that all of the PM dependencies of the * device are known to the PM core. However, for some devices this * attribute is set to "enabled" by bus type code or device drivers and in * that cases it should be safe to leave the default value. * * autosuspend_delay_ms - Report/change a device's autosuspend_delay value * * Some drivers don't want to carry out a runtime suspend as soon as a * device becomes idle; they want it always to remain idle for some period * of time before suspending it. This period is the autosuspend_delay * value (expressed in milliseconds) and it can be controlled by the user. * If the value is negative then the device will never be runtime * suspended. * * NOTE: The autosuspend_delay_ms attribute and the autosuspend_delay * value are used only if the driver calls pm_runtime_use_autosuspend(). * * wakeup_count - Report the number of wakeup events related to the device */ const char power_group_name[] = "power"; EXPORT_SYMBOL_GPL(power_group_name); static const char ctrl_auto[] = "auto"; static const char ctrl_on[] = "on"; static ssize_t control_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", dev->power.runtime_auto ? ctrl_auto : ctrl_on); } static ssize_t control_store(struct device * dev, struct device_attribute *attr, const char * buf, size_t n) { device_lock(dev); if (sysfs_streq(buf, ctrl_auto)) pm_runtime_allow(dev); else if (sysfs_streq(buf, ctrl_on)) pm_runtime_forbid(dev); else n = -EINVAL; device_unlock(dev); return n; } static DEVICE_ATTR_RW(control); static ssize_t runtime_active_time_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; u64 tmp = pm_runtime_active_time(dev); do_div(tmp, NSEC_PER_MSEC); ret = sysfs_emit(buf, "%llu\n", tmp); return ret; } static DEVICE_ATTR_RO(runtime_active_time); static ssize_t runtime_suspended_time_show(struct device *dev, struct device_attribute *attr, char *buf) { int ret; u64 tmp = pm_runtime_suspended_time(dev); do_div(tmp, NSEC_PER_MSEC); ret = sysfs_emit(buf, "%llu\n", tmp); return ret; } static DEVICE_ATTR_RO(runtime_suspended_time); static ssize_t runtime_status_show(struct device *dev, struct device_attribute *attr, char *buf) { const char *p; if (dev->power.runtime_error) { p = "error\n"; } else if (dev->power.disable_depth) { p = "unsupported\n"; } else { switch (dev->power.runtime_status) { case RPM_SUSPENDED: p = "suspended\n"; break; case RPM_SUSPENDING: p = "suspending\n"; break; case RPM_RESUMING: p = "resuming\n"; break; case RPM_ACTIVE: p = "active\n"; break; default: return -EIO; } } return sysfs_emit(buf, p); } static DEVICE_ATTR_RO(runtime_status); static ssize_t autosuspend_delay_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { if (!dev->power.use_autosuspend) return -EIO; return sysfs_emit(buf, "%d\n", dev->power.autosuspend_delay); } static ssize_t autosuspend_delay_ms_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { long delay; if (!dev->power.use_autosuspend) return -EIO; if (kstrtol(buf, 10, &delay) != 0 || delay != (int) delay) return -EINVAL; device_lock(dev); pm_runtime_set_autosuspend_delay(dev, delay); device_unlock(dev); return n; } static DEVICE_ATTR_RW(autosuspend_delay_ms); static ssize_t pm_qos_resume_latency_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_requested_resume_latency(dev); if (value == 0) return sysfs_emit(buf, "n/a\n"); if (value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) value = 0; return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_resume_latency_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (!kstrtos32(buf, 0, &value)) { /* * Prevent users from writing negative or "no constraint" values * directly. */ if (value < 0 || value == PM_QOS_RESUME_LATENCY_NO_CONSTRAINT) return -EINVAL; if (value == 0) value = PM_QOS_RESUME_LATENCY_NO_CONSTRAINT; } else if (sysfs_streq(buf, "n/a")) { value = 0; } else { return -EINVAL; } ret = dev_pm_qos_update_request(dev->power.qos->resume_latency_req, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_resume_latency_us); static ssize_t pm_qos_latency_tolerance_us_show(struct device *dev, struct device_attribute *attr, char *buf) { s32 value = dev_pm_qos_get_user_latency_tolerance(dev); if (value < 0) return sysfs_emit(buf, "auto\n"); if (value == PM_QOS_LATENCY_ANY) return sysfs_emit(buf, "any\n"); return sysfs_emit(buf, "%d\n", value); } static ssize_t pm_qos_latency_tolerance_us_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { s32 value; int ret; if (kstrtos32(buf, 0, &value) == 0) { /* Users can't write negative values directly */ if (value < 0) return -EINVAL; } else { if (sysfs_streq(buf, "auto")) value = PM_QOS_LATENCY_TOLERANCE_NO_CONSTRAINT; else if (sysfs_streq(buf, "any")) value = PM_QOS_LATENCY_ANY; else return -EINVAL; } ret = dev_pm_qos_update_user_latency_tolerance(dev, value); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_latency_tolerance_us); static ssize_t pm_qos_no_power_off_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", !!(dev_pm_qos_requested_flags(dev) & PM_QOS_FLAG_NO_POWER_OFF)); } static ssize_t pm_qos_no_power_off_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { int ret; if (kstrtoint(buf, 0, &ret)) return -EINVAL; if (ret != 0 && ret != 1) return -EINVAL; ret = dev_pm_qos_update_flags(dev, PM_QOS_FLAG_NO_POWER_OFF, ret); return ret < 0 ? ret : n; } static DEVICE_ATTR_RW(pm_qos_no_power_off); #ifdef CONFIG_PM_SLEEP static const char _enabled[] = "enabled"; static const char _disabled[] = "disabled"; static ssize_t wakeup_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", device_can_wakeup(dev) ? (device_may_wakeup(dev) ? _enabled : _disabled) : ""); } static ssize_t wakeup_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { if (!device_can_wakeup(dev)) return -EINVAL; if (sysfs_streq(buf, _enabled)) device_set_wakeup_enable(dev, 1); else if (sysfs_streq(buf, _disabled)) device_set_wakeup_enable(dev, 0); else return -EINVAL; return n; } static DEVICE_ATTR_RW(wakeup); static ssize_t wakeup_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->wakeup_count; enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_count); static ssize_t wakeup_active_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->active_count; enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_active_count); static ssize_t wakeup_abort_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->wakeup_count; enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_abort_count); static ssize_t wakeup_expire_count_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned long count = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { count = dev->power.wakeup->expire_count; enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lu\n", count) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_expire_count); static ssize_t wakeup_active_show(struct device *dev, struct device_attribute *attr, char *buf) { unsigned int active = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { active = dev->power.wakeup->active; enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%u\n", active) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_active); static ssize_t wakeup_total_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->total_time); enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_total_time_ms); static ssize_t wakeup_max_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->max_time); enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_max_time_ms); static ssize_t wakeup_last_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->last_time); enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_last_time_ms); #ifdef CONFIG_PM_AUTOSLEEP static ssize_t wakeup_prevent_sleep_time_ms_show(struct device *dev, struct device_attribute *attr, char *buf) { s64 msec = 0; bool enabled = false; spin_lock_irq(&dev->power.lock); if (dev->power.wakeup) { msec = ktime_to_ms(dev->power.wakeup->prevent_sleep_time); enabled = true; } spin_unlock_irq(&dev->power.lock); return enabled ? sprintf(buf, "%lld\n", msec) : sprintf(buf, "\n"); } static DEVICE_ATTR_RO(wakeup_prevent_sleep_time_ms); #endif /* CONFIG_PM_AUTOSLEEP */ #endif /* CONFIG_PM_SLEEP */ #ifdef CONFIG_PM_ADVANCED_DEBUG static ssize_t runtime_usage_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", atomic_read(&dev->power.usage_count)); } static DEVICE_ATTR_RO(runtime_usage); static ssize_t runtime_active_kids_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%d\n", dev->power.ignore_children ? 0 : atomic_read(&dev->power.child_count)); } static DEVICE_ATTR_RO(runtime_active_kids); static ssize_t runtime_enabled_show(struct device *dev, struct device_attribute *attr, char *buf) { if (dev->power.disable_depth && (dev->power.runtime_auto == false)) return sysfs_emit(buf, "disabled & forbidden\n"); if (dev->power.disable_depth) return sysfs_emit(buf, "disabled\n"); if (dev->power.runtime_auto == false) return sysfs_emit(buf, "forbidden\n"); return sysfs_emit(buf, "enabled\n"); } static DEVICE_ATTR_RO(runtime_enabled); #ifdef CONFIG_PM_SLEEP static ssize_t async_show(struct device *dev, struct device_attribute *attr, char *buf) { return sysfs_emit(buf, "%s\n", device_async_suspend_enabled(dev) ? _enabled : _disabled); } static ssize_t async_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t n) { if (sysfs_streq(buf, _enabled)) device_enable_async_suspend(dev); else if (sysfs_streq(buf, _disabled)) device_disable_async_suspend(dev); else return -EINVAL; return n; } static DEVICE_ATTR_RW(async); #endif /* CONFIG_PM_SLEEP */ #endif /* CONFIG_PM_ADVANCED_DEBUG */ static struct attribute *power_attrs[] = { #ifdef CONFIG_PM_ADVANCED_DEBUG #ifdef CONFIG_PM_SLEEP &dev_attr_async.attr, #endif &dev_attr_runtime_status.attr, &dev_attr_runtime_usage.attr, &dev_attr_runtime_active_kids.attr, &dev_attr_runtime_enabled.attr, #endif /* CONFIG_PM_ADVANCED_DEBUG */ NULL, }; static const struct attribute_group pm_attr_group = { .name = power_group_name, .attrs = power_attrs, }; static struct attribute *wakeup_attrs[] = { #ifdef CONFIG_PM_SLEEP &dev_attr_wakeup.attr, &dev_attr_wakeup_count.attr, &dev_attr_wakeup_active_count.attr, &dev_attr_wakeup_abort_count.attr, &dev_attr_wakeup_expire_count.attr, &dev_attr_wakeup_active.attr, &dev_attr_wakeup_total_time_ms.attr, &dev_attr_wakeup_max_time_ms.attr, &dev_attr_wakeup_last_time_ms.attr, #ifdef CONFIG_PM_AUTOSLEEP &dev_attr_wakeup_prevent_sleep_time_ms.attr, #endif #endif NULL, }; static const struct attribute_group pm_wakeup_attr_group = { .name = power_group_name, .attrs = wakeup_attrs, }; static struct attribute *runtime_attrs[] = { #ifndef CONFIG_PM_ADVANCED_DEBUG &dev_attr_runtime_status.attr, #endif &dev_attr_control.attr, &dev_attr_runtime_suspended_time.attr, &dev_attr_runtime_active_time.attr, &dev_attr_autosuspend_delay_ms.attr, NULL, }; static const struct attribute_group pm_runtime_attr_group = { .name = power_group_name, .attrs = runtime_attrs, }; static struct attribute *pm_qos_resume_latency_attrs[] = { &dev_attr_pm_qos_resume_latency_us.attr, NULL, }; static const struct attribute_group pm_qos_resume_latency_attr_group = { .name = power_group_name, .attrs = pm_qos_resume_latency_attrs, }; static struct attribute *pm_qos_latency_tolerance_attrs[] = { &dev_attr_pm_qos_latency_tolerance_us.attr, NULL, }; static const struct attribute_group pm_qos_latency_tolerance_attr_group = { .name = power_group_name, .attrs = pm_qos_latency_tolerance_attrs, }; static struct attribute *pm_qos_flags_attrs[] = { &dev_attr_pm_qos_no_power_off.attr, NULL, }; static const struct attribute_group pm_qos_flags_attr_group = { .name = power_group_name, .attrs = pm_qos_flags_attrs, }; int dpm_sysfs_add(struct device *dev) { int rc; /* No need to create PM sysfs if explicitly disabled. */ if (device_pm_not_required(dev)) return 0; rc = sysfs_create_group(&dev->kobj, &pm_attr_group); if (rc) return rc; if (pm_runtime_callbacks_present(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_runtime_attr_group); if (rc) goto err_out; } if (device_can_wakeup(dev)) { rc = sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); if (rc) goto err_runtime; } if (dev->power.set_latency_tolerance) { rc = sysfs_merge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); if (rc) goto err_wakeup; } rc = pm_wakeup_source_sysfs_add(dev); if (rc) goto err_latency; return 0; err_latency: sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); err_wakeup: sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); err_runtime: sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); err_out: sysfs_remove_group(&dev->kobj, &pm_attr_group); return rc; } int wakeup_sysfs_add(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_wakeup_attr_group); } void wakeup_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); } int pm_qos_sysfs_add_resume_latency(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_resume_latency_attr_group); } void pm_qos_sysfs_remove_resume_latency(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_resume_latency_attr_group); } int pm_qos_sysfs_add_flags(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_flags_attr_group); } void pm_qos_sysfs_remove_flags(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_flags_attr_group); } int pm_qos_sysfs_add_latency_tolerance(struct device *dev) { return sysfs_merge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); } void pm_qos_sysfs_remove_latency_tolerance(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); } void rpm_sysfs_remove(struct device *dev) { sysfs_unmerge_group(&dev->kobj, &pm_runtime_attr_group); } void dpm_sysfs_remove(struct device *dev) { if (device_pm_not_required(dev)) return; sysfs_unmerge_group(&dev->kobj, &pm_qos_latency_tolerance_attr_group); dev_pm_qos_constraints_destroy(dev); rpm_sysfs_remove(dev); sysfs_unmerge_group(&dev->kobj, &pm_wakeup_attr_group); sysfs_remove_group(&dev->kobj, &pm_attr_group); } |
| 14 6 16 16 16 2 2 2 2 6 6 8 16 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _XFRM_HASH_H #define _XFRM_HASH_H #include <linux/xfrm.h> #include <linux/socket.h> #include <linux/jhash.h> static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr) { return ntohl(addr->a4); } static inline unsigned int __xfrm6_addr_hash(const xfrm_address_t *addr) { return jhash2((__force u32 *)addr->a6, 4, 0); } static inline unsigned int __xfrm4_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4; return ntohl((__force __be32)sum); } static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr) { return __xfrm6_addr_hash(daddr) ^ __xfrm6_addr_hash(saddr); } static inline u32 __bits2mask32(__u8 bits) { u32 mask32 = 0xffffffff; if (bits == 0) mask32 = 0; else if (bits < 32) mask32 <<= (32 - bits); return mask32; } static inline unsigned int __xfrm4_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return jhash_2words(ntohl(daddr->a4) & __bits2mask32(dbits), ntohl(saddr->a4) & __bits2mask32(sbits), 0); } static inline unsigned int __xfrm6_pref_hash(const xfrm_address_t *addr, __u8 prefixlen) { unsigned int pdw; unsigned int pbi; u32 initval = 0; pdw = prefixlen >> 5; /* num of whole u32 in prefix */ pbi = prefixlen & 0x1f; /* num of bits in incomplete u32 in prefix */ if (pbi) { __be32 mask; mask = htonl((0xffffffff) << (32 - pbi)); initval = (__force u32)(addr->a6[pdw] & mask); } return jhash2((__force u32 *)addr->a6, pdw, initval); } static inline unsigned int __xfrm6_dpref_spref_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, __u8 dbits, __u8 sbits) { return __xfrm6_pref_hash(daddr, dbits) ^ __xfrm6_pref_hash(saddr, sbits); } static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family, unsigned int hmask) { unsigned int h = family ^ reqid; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_src_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask) { unsigned int h = family; switch (family) { case AF_INET: h ^= __xfrm4_daddr_saddr_hash(daddr, saddr); break; case AF_INET6: h ^= __xfrm6_daddr_saddr_hash(daddr, saddr); break; } return (h ^ (h >> 16)) & hmask; } static inline unsigned int __xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, unsigned int hmask) { unsigned int h = (__force u32)spi ^ proto; switch (family) { case AF_INET: h ^= __xfrm4_addr_hash(daddr); break; case AF_INET6: h ^= __xfrm6_addr_hash(daddr); break; } return (h ^ (h >> 10) ^ (h >> 20)) & hmask; } static inline unsigned int __idx_hash(u32 index, unsigned int hmask) { return (index ^ (index >> 8)) & hmask; } static inline unsigned int __sel_hash(const struct xfrm_selector *sel, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { const xfrm_address_t *daddr = &sel->daddr; const xfrm_address_t *saddr = &sel->saddr; unsigned int h = 0; switch (family) { case AF_INET: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: if (sel->prefixlen_d < dbits || sel->prefixlen_s < sbits) return hmask + 1; h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } static inline unsigned int __addr_hash(const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, unsigned int hmask, u8 dbits, u8 sbits) { unsigned int h = 0; switch (family) { case AF_INET: h = __xfrm4_dpref_spref_hash(daddr, saddr, dbits, sbits); break; case AF_INET6: h = __xfrm6_dpref_spref_hash(daddr, saddr, dbits, sbits); break; } h ^= (h >> 16); return h & hmask; } struct hlist_head *xfrm_hash_alloc(unsigned int sz); void xfrm_hash_free(struct hlist_head *n, unsigned int sz); #endif /* _XFRM_HASH_H */ |
| 837 838 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c. * * Copyright (C) 2004 Paul Mackerras, IBM Corp. */ #include <linux/bsearch.h> #include <linux/module.h> #include <linux/init.h> #include <linux/sort.h> #include <linux/uaccess.h> #include <linux/extable.h> #ifndef ARCH_HAS_RELATIVE_EXTABLE #define ex_to_insn(x) ((x)->insn) #else static inline unsigned long ex_to_insn(const struct exception_table_entry *x) { return (unsigned long)&x->insn + x->insn; } #endif #ifndef ARCH_HAS_SORT_EXTABLE #ifndef ARCH_HAS_RELATIVE_EXTABLE #define swap_ex NULL #else static void swap_ex(void *a, void *b, int size) { struct exception_table_entry *x = a, *y = b, tmp; int delta = b - a; tmp = *x; x->insn = y->insn + delta; y->insn = tmp.insn - delta; #ifdef swap_ex_entry_fixup swap_ex_entry_fixup(x, y, tmp, delta); #else x->fixup = y->fixup + delta; y->fixup = tmp.fixup - delta; #endif } #endif /* ARCH_HAS_RELATIVE_EXTABLE */ /* * The exception table needs to be sorted so that the binary * search that we use to find entries in it works properly. * This is used both for the kernel exception table and for * the exception tables of modules that get loaded. */ static int cmp_ex_sort(const void *a, const void *b) { const struct exception_table_entry *x = a, *y = b; /* avoid overflow */ if (ex_to_insn(x) > ex_to_insn(y)) return 1; if (ex_to_insn(x) < ex_to_insn(y)) return -1; return 0; } void sort_extable(struct exception_table_entry *start, struct exception_table_entry *finish) { sort(start, finish - start, sizeof(struct exception_table_entry), cmp_ex_sort, swap_ex); } #ifdef CONFIG_MODULES /* * If the exception table is sorted, any referring to the module init * will be at the beginning or the end. */ void trim_init_extable(struct module *m) { /*trim the beginning*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[0]), m)) { m->extable++; m->num_exentries--; } /*trim the end*/ while (m->num_exentries && within_module_init(ex_to_insn(&m->extable[m->num_exentries - 1]), m)) m->num_exentries--; } #endif /* CONFIG_MODULES */ #endif /* !ARCH_HAS_SORT_EXTABLE */ #ifndef ARCH_HAS_SEARCH_EXTABLE static int cmp_ex_search(const void *key, const void *elt) { const struct exception_table_entry *_elt = elt; unsigned long _key = *(unsigned long *)key; /* avoid overflow */ if (_key > ex_to_insn(_elt)) return 1; if (_key < ex_to_insn(_elt)) return -1; return 0; } /* * Search one exception table for an entry corresponding to the * given instruction address, and return the address of the entry, * or NULL if none is found. * We use a binary search, and thus we assume that the table is * already sorted. */ const struct exception_table_entry * search_extable(const struct exception_table_entry *base, const size_t num, unsigned long value) { return bsearch(&value, base, num, sizeof(struct exception_table_entry), cmp_ex_search); } #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * This file is part of the Linux kernel. * * Copyright (c) 2011-2014, Intel Corporation * Authors: Fenghua Yu <fenghua.yu@intel.com>, * H. Peter Anvin <hpa@linux.intel.com> */ #ifndef ASM_X86_ARCHRANDOM_H #define ASM_X86_ARCHRANDOM_H #include <asm/processor.h> #include <asm/cpufeature.h> #define RDRAND_RETRY_LOOPS 10 #define RDRAND_INT ".byte 0x0f,0xc7,0xf0" #define RDSEED_INT ".byte 0x0f,0xc7,0xf8" #ifdef CONFIG_X86_64 # define RDRAND_LONG ".byte 0x48,0x0f,0xc7,0xf0" # define RDSEED_LONG ".byte 0x48,0x0f,0xc7,0xf8" #else # define RDRAND_LONG RDRAND_INT # define RDSEED_LONG RDSEED_INT #endif /* Unconditional execution of RDRAND and RDSEED */ static inline bool rdrand_long(unsigned long *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile(RDRAND_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool rdrand_int(unsigned int *v) { bool ok; unsigned int retry = RDRAND_RETRY_LOOPS; do { asm volatile(RDRAND_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); if (ok) return true; } while (--retry); return false; } static inline bool rdseed_long(unsigned long *v) { bool ok; asm volatile(RDSEED_LONG CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; } static inline bool rdseed_int(unsigned int *v) { bool ok; asm volatile(RDSEED_INT CC_SET(c) : CC_OUT(c) (ok), "=a" (*v)); return ok; } /* * These are the generic interfaces; they must not be declared if the * stubs in <linux/random.h> are to be invoked, * i.e. CONFIG_ARCH_RANDOM is not defined. */ #ifdef CONFIG_ARCH_RANDOM static inline bool arch_get_random_long(unsigned long *v) { return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_long(v) : false; } static inline bool arch_get_random_int(unsigned int *v) { return static_cpu_has(X86_FEATURE_RDRAND) ? rdrand_int(v) : false; } static inline bool arch_get_random_seed_long(unsigned long *v) { return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_long(v) : false; } static inline bool arch_get_random_seed_int(unsigned int *v) { return static_cpu_has(X86_FEATURE_RDSEED) ? rdseed_int(v) : false; } extern void x86_init_rdrand(struct cpuinfo_x86 *c); #else /* !CONFIG_ARCH_RANDOM */ static inline void x86_init_rdrand(struct cpuinfo_x86 *c) { } #endif /* !CONFIG_ARCH_RANDOM */ #endif /* ASM_X86_ARCHRANDOM_H */ |
| 744 741 707 75 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/sched/act_mirred.c packet mirroring and redirect actions * * Authors: Jamal Hadi Salim (2002-4) * * TODO: Add ingress support (and socket redirect support) */ #include <linux/types.h> #include <linux/kernel.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <linux/module.h> #include <linux/init.h> #include <linux/gfp.h> #include <linux/if_arp.h> #include <net/net_namespace.h> #include <net/netlink.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> #include <linux/tc_act/tc_mirred.h> #include <net/tc_act/tc_mirred.h> static LIST_HEAD(mirred_list); static DEFINE_SPINLOCK(mirred_list_lock); #define MIRRED_RECURSION_LIMIT 4 static DEFINE_PER_CPU(unsigned int, mirred_rec_level); static bool tcf_mirred_is_act_redirect(int action) { return action == TCA_EGRESS_REDIR || action == TCA_INGRESS_REDIR; } static bool tcf_mirred_act_wants_ingress(int action) { switch (action) { case TCA_EGRESS_REDIR: case TCA_EGRESS_MIRROR: return false; case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: return true; default: BUG(); } } static bool tcf_mirred_can_reinsert(int action) { switch (action) { case TC_ACT_SHOT: case TC_ACT_STOLEN: case TC_ACT_QUEUED: case TC_ACT_TRAP: return true; } return false; } static struct net_device *tcf_mirred_dev_dereference(struct tcf_mirred *m) { return rcu_dereference_protected(m->tcfm_dev, lockdep_is_held(&m->tcf_lock)); } static void tcf_mirred_release(struct tc_action *a) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; spin_lock(&mirred_list_lock); list_del(&m->tcfm_list); spin_unlock(&mirred_list_lock); /* last reference to action, no need to lock */ dev = rcu_dereference_protected(m->tcfm_dev, 1); if (dev) dev_put(dev); } static const struct nla_policy mirred_policy[TCA_MIRRED_MAX + 1] = { [TCA_MIRRED_PARMS] = { .len = sizeof(struct tc_mirred) }, }; static unsigned int mirred_net_id; static struct tc_action_ops act_mirred_ops; static int tcf_mirred_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, int ovr, int bind, bool rtnl_held, struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); struct nlattr *tb[TCA_MIRRED_MAX + 1]; struct tcf_chain *goto_ch = NULL; bool mac_header_xmit = false; struct tc_mirred *parm; struct tcf_mirred *m; struct net_device *dev; bool exists = false; int ret, err; u32 index; if (!nla) { NL_SET_ERR_MSG_MOD(extack, "Mirred requires attributes to be passed"); return -EINVAL; } ret = nla_parse_nested_deprecated(tb, TCA_MIRRED_MAX, nla, mirred_policy, extack); if (ret < 0) return ret; if (!tb[TCA_MIRRED_PARMS]) { NL_SET_ERR_MSG_MOD(extack, "Missing required mirred parameters"); return -EINVAL; } parm = nla_data(tb[TCA_MIRRED_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return 0; switch (parm->eaction) { case TCA_EGRESS_MIRROR: case TCA_EGRESS_REDIR: case TCA_INGRESS_REDIR: case TCA_INGRESS_MIRROR: break; default: if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Unknown mirred option"); return -EINVAL; } if (!exists) { if (!parm->ifindex) { tcf_idr_cleanup(tn, index); NL_SET_ERR_MSG_MOD(extack, "Specified device does not exist"); return -EINVAL; } ret = tcf_idr_create(tn, index, est, a, &act_mirred_ops, bind, true); if (ret) { tcf_idr_cleanup(tn, index); return ret; } ret = ACT_P_CREATED; } else if (!ovr) { tcf_idr_release(*a, bind); return -EEXIST; } m = to_mirred(*a); if (ret == ACT_P_CREATED) INIT_LIST_HEAD(&m->tcfm_list); err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; spin_lock_bh(&m->tcf_lock); if (parm->ifindex) { dev = dev_get_by_index(net, parm->ifindex); if (!dev) { spin_unlock_bh(&m->tcf_lock); err = -ENODEV; goto put_chain; } mac_header_xmit = dev_is_mac_header_xmit(dev); rcu_swap_protected(m->tcfm_dev, dev, lockdep_is_held(&m->tcf_lock)); if (dev) dev_put(dev); m->tcfm_mac_header_xmit = mac_header_xmit; } goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); m->tcfm_eaction = parm->eaction; spin_unlock_bh(&m->tcf_lock); if (goto_ch) tcf_chain_put_by_act(goto_ch); if (ret == ACT_P_CREATED) { spin_lock(&mirred_list_lock); list_add(&m->tcfm_list, &mirred_list); spin_unlock(&mirred_list_lock); } return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_mirred *m = to_mirred(a); struct sk_buff *skb2 = skb; bool m_mac_header_xmit; struct net_device *dev; unsigned int rec_level; int retval, err = 0; bool use_reinsert; bool want_ingress; bool is_redirect; bool expects_nh; bool at_ingress; int m_eaction; int mac_len; bool at_nh; rec_level = __this_cpu_inc_return(mirred_rec_level); if (unlikely(rec_level > MIRRED_RECURSION_LIMIT)) { net_warn_ratelimited("Packet exceeded mirred recursion limit on dev %s\n", netdev_name(skb->dev)); __this_cpu_dec(mirred_rec_level); return TC_ACT_SHOT; } tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); m_mac_header_xmit = READ_ONCE(m->tcfm_mac_header_xmit); m_eaction = READ_ONCE(m->tcfm_eaction); retval = READ_ONCE(m->tcf_action); dev = rcu_dereference_bh(m->tcfm_dev); if (unlikely(!dev)) { pr_notice_once("tc mirred: target device is gone\n"); goto out; } if (unlikely(!(dev->flags & IFF_UP)) || !netif_carrier_ok(dev)) { net_notice_ratelimited("tc mirred to Houston: device %s is down\n", dev->name); goto out; } /* we could easily avoid the clone only if called by ingress and clsact; * since we can't easily detect the clsact caller, skip clone only for * ingress - that covers the TC S/W datapath. */ is_redirect = tcf_mirred_is_act_redirect(m_eaction); at_ingress = skb_at_tc_ingress(skb); use_reinsert = at_ingress && is_redirect && tcf_mirred_can_reinsert(retval); if (!use_reinsert) { skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) goto out; } want_ingress = tcf_mirred_act_wants_ingress(m_eaction); /* All mirred/redirected skbs should clear previous ct info */ nf_reset_ct(skb2); if (want_ingress && !at_ingress) /* drop dst for egress -> ingress */ skb_dst_drop(skb2); expects_nh = want_ingress || !m_mac_header_xmit; at_nh = skb->data == skb_network_header(skb); if (at_nh != expects_nh) { mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : skb_network_header(skb) - skb_mac_header(skb); if (expects_nh) { /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { /* target device/action expect data at mac */ skb_push_rcsum(skb2, mac_len); } } skb2->skb_iif = skb->dev->ifindex; skb2->dev = dev; /* mirror is always swallowed */ if (is_redirect) { skb_set_redirected(skb2, skb2->tc_at_ingress); /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; res->qstats = this_cpu_ptr(m->common.cpu_qstats); skb_tc_reinsert(skb, res); __this_cpu_dec(mirred_rec_level); return TC_ACT_CONSUMED; } } if (!want_ingress) err = dev_queue_xmit(skb2); else err = netif_receive_skb(skb2); if (err) { out: qstats_overlimit_inc(this_cpu_ptr(m->common.cpu_qstats)); if (tcf_mirred_is_act_redirect(m_eaction)) retval = TC_ACT_SHOT; } __this_cpu_dec(mirred_rec_level); return retval; } static void tcf_stats_update(struct tc_action *a, u64 bytes, u32 packets, u64 lastuse, bool hw) { struct tcf_mirred *m = to_mirred(a); struct tcf_t *tm = &m->tcf_tm; _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats), bytes, packets); if (hw) _bstats_cpu_update(this_cpu_ptr(a->cpu_bstats_hw), bytes, packets); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static int tcf_mirred_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { unsigned char *b = skb_tail_pointer(skb); struct tcf_mirred *m = to_mirred(a); struct tc_mirred opt = { .index = m->tcf_index, .refcnt = refcount_read(&m->tcf_refcnt) - ref, .bindcnt = atomic_read(&m->tcf_bindcnt) - bind, }; struct net_device *dev; struct tcf_t t; spin_lock_bh(&m->tcf_lock); opt.action = m->tcf_action; opt.eaction = m->tcfm_eaction; dev = tcf_mirred_dev_dereference(m); if (dev) opt.ifindex = dev->ifindex; if (nla_put(skb, TCA_MIRRED_PARMS, sizeof(opt), &opt)) goto nla_put_failure; tcf_tm_dump(&t, &m->tcf_tm); if (nla_put_64bit(skb, TCA_MIRRED_TM, sizeof(t), &t, TCA_MIRRED_PAD)) goto nla_put_failure; spin_unlock_bh(&m->tcf_lock); return skb->len; nla_put_failure: spin_unlock_bh(&m->tcf_lock); nlmsg_trim(skb, b); return -1; } static int tcf_mirred_walker(struct net *net, struct sk_buff *skb, struct netlink_callback *cb, int type, const struct tc_action_ops *ops, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, mirred_net_id); return tcf_generic_walker(tn, skb, cb, type, ops, extack); } static int tcf_mirred_search(struct net *net, struct tc_action **a, u32 index) { struct tc_action_net *tn = net_generic(net, mirred_net_id); return tcf_idr_search(tn, a, index); } static int mirred_device_event(struct notifier_block *unused, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct tcf_mirred *m; ASSERT_RTNL(); if (event == NETDEV_UNREGISTER) { spin_lock(&mirred_list_lock); list_for_each_entry(m, &mirred_list, tcfm_list) { spin_lock_bh(&m->tcf_lock); if (tcf_mirred_dev_dereference(m) == dev) { dev_put(dev); /* Note : no rcu grace period necessary, as * net_device are already rcu protected. */ RCU_INIT_POINTER(m->tcfm_dev, NULL); } spin_unlock_bh(&m->tcf_lock); } spin_unlock(&mirred_list_lock); } return NOTIFY_DONE; } static struct notifier_block mirred_device_notifier = { .notifier_call = mirred_device_event, }; static void tcf_mirred_dev_put(void *priv) { struct net_device *dev = priv; dev_put(dev); } static struct net_device * tcf_mirred_get_dev(const struct tc_action *a, tc_action_priv_destructor *destructor) { struct tcf_mirred *m = to_mirred(a); struct net_device *dev; rcu_read_lock(); dev = rcu_dereference(m->tcfm_dev); if (dev) { dev_hold(dev); *destructor = tcf_mirred_dev_put; } rcu_read_unlock(); return dev; } static size_t tcf_mirred_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_mirred)); } static struct tc_action_ops act_mirred_ops = { .kind = "mirred", .id = TCA_ID_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred_act, .stats_update = tcf_stats_update, .dump = tcf_mirred_dump, .cleanup = tcf_mirred_release, .init = tcf_mirred_init, .walk = tcf_mirred_walker, .lookup = tcf_mirred_search, .get_fill_size = tcf_mirred_get_fill_size, .size = sizeof(struct tcf_mirred), .get_dev = tcf_mirred_get_dev, }; static __net_init int mirred_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, mirred_net_id); return tc_action_net_init(net, tn, &act_mirred_ops); } static void __net_exit mirred_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, mirred_net_id); } static struct pernet_operations mirred_net_ops = { .init = mirred_init_net, .exit_batch = mirred_exit_net, .id = &mirred_net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Jamal Hadi Salim(2002)"); MODULE_DESCRIPTION("Device Mirror/redirect actions"); MODULE_LICENSE("GPL"); static int __init mirred_init_module(void) { int err = register_netdevice_notifier(&mirred_device_notifier); if (err) return err; pr_info("Mirror/redirect action on\n"); err = tcf_register_action(&act_mirred_ops, &mirred_net_ops); if (err) unregister_netdevice_notifier(&mirred_device_notifier); return err; } static void __exit mirred_cleanup_module(void) { tcf_unregister_action(&act_mirred_ops, &mirred_net_ops); unregister_netdevice_notifier(&mirred_device_notifier); } module_init(mirred_init_module); module_exit(mirred_cleanup_module); |
| 13 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 | /* * net/tipc/addr.c: TIPC address utility routines * * Copyright (c) 2000-2006, 2018, Ericsson AB * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without * modification, are permitted provided that the following conditions are met: * * 1. Redistributions of source code must retain the above copyright * notice, this list of conditions and the following disclaimer. * 2. Redistributions in binary form must reproduce the above copyright * notice, this list of conditions and the following disclaimer in the * documentation and/or other materials provided with the distribution. * 3. Neither the names of the copyright holders nor the names of its * contributors may be used to endorse or promote products derived from * this software without specific prior written permission. * * Alternatively, this software may be distributed under the terms of the * GNU General Public License ("GPL") version 2 as published by the Free * Software Foundation. * * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE * POSSIBILITY OF SUCH DAMAGE. */ #include "addr.h" #include "core.h" bool tipc_in_scope(bool legacy_format, u32 domain, u32 addr) { if (!domain || (domain == addr)) return true; if (!legacy_format) return false; if (domain == tipc_cluster_mask(addr)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_CLUSTER_MASK)) /* domain <Z.C.0> */ return true; if (domain == (addr & TIPC_ZONE_MASK)) /* domain <Z.0.0> */ return true; return false; } void tipc_set_node_id(struct net *net, u8 *id) { struct tipc_net *tn = tipc_net(net); u32 *tmp = (u32 *)id; memcpy(tn->node_id, id, NODE_ID_LEN); tipc_nodeid2string(tn->node_id_string, id); tn->trial_addr = tmp[0] ^ tmp[1] ^ tmp[2] ^ tmp[3]; pr_info("Own node identity %s, cluster identity %u\n", tipc_own_id_string(net), tn->net_id); } void tipc_set_node_addr(struct net *net, u32 addr) { struct tipc_net *tn = tipc_net(net); u8 node_id[NODE_ID_LEN] = {0,}; tn->node_addr = addr; if (!tipc_own_id(net)) { sprintf(node_id, "%x", addr); tipc_set_node_id(net, node_id); } tn->trial_addr = addr; tn->addr_trial_end = jiffies; pr_info("32-bit node address hash set to %x\n", addr); } char *tipc_nodeid2string(char *str, u8 *id) { int i; u8 c; /* Already a string ? */ for (i = 0; i < NODE_ID_LEN; i++) { c = id[i]; if (c >= '0' && c <= '9') continue; if (c >= 'A' && c <= 'Z') continue; if (c >= 'a' && c <= 'z') continue; if (c == '.') continue; if (c == ':') continue; if (c == '_') continue; if (c == '-') continue; if (c == '@') continue; if (c != 0) break; } if (i == NODE_ID_LEN) { memcpy(str, id, NODE_ID_LEN); str[NODE_ID_LEN] = 0; return str; } /* Translate to hex string */ for (i = 0; i < NODE_ID_LEN; i++) sprintf(&str[2 * i], "%02x", id[i]); /* Strip off trailing zeroes */ for (i = NODE_ID_STR_LEN - 2; str[i] == '0'; i--) str[i] = 0; return str; } |
| 221 221 219 2 1 216 124 107 220 77 75 77 9 9 7 5 77 1 77 77 77 77 3 74 77 77 1 11 9 9 98 89 9 3 3 3 3 30 29 1 30 565 16 565 564 473 98 565 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * fs/kernfs/file.c - kernfs file implementation * * Copyright (c) 2001-3 Patrick Mochel * Copyright (c) 2007 SUSE Linux Products GmbH * Copyright (c) 2007, 2013 Tejun Heo <tj@kernel.org> */ #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/pagemap.h> #include <linux/sched/mm.h> #include <linux/fsnotify.h> #include "kernfs-internal.h" /* * There's one kernfs_open_file for each open file and one kernfs_open_node * for each kernfs_node with one or more open files. * * kernfs_node->attr.open points to kernfs_open_node. attr.open is * protected by kernfs_open_node_lock. * * filp->private_data points to seq_file whose ->private points to * kernfs_open_file. kernfs_open_files are chained at * kernfs_open_node->files, which is protected by kernfs_open_file_mutex. */ static DEFINE_SPINLOCK(kernfs_open_node_lock); static DEFINE_MUTEX(kernfs_open_file_mutex); struct kernfs_open_node { atomic_t refcnt; atomic_t event; wait_queue_head_t poll; struct list_head files; /* goes through kernfs_open_file.list */ }; /* * kernfs_notify() may be called from any context and bounces notifications * through a work item. To minimize space overhead in kernfs_node, the * pending queue is implemented as a singly linked list of kernfs_nodes. * The list is terminated with the self pointer so that whether a * kernfs_node is on the list or not can be determined by testing the next * pointer for NULL. */ #define KERNFS_NOTIFY_EOL ((void *)&kernfs_notify_list) static DEFINE_SPINLOCK(kernfs_notify_lock); static struct kernfs_node *kernfs_notify_list = KERNFS_NOTIFY_EOL; static struct kernfs_open_file *kernfs_of(struct file *file) { return ((struct seq_file *)file->private_data)->private; } /* * Determine the kernfs_ops for the given kernfs_node. This function must * be called while holding an active reference. */ static const struct kernfs_ops *kernfs_ops(struct kernfs_node *kn) { if (kn->flags & KERNFS_LOCKDEP) lockdep_assert_held(kn); return kn->attr.ops; } /* * As kernfs_seq_stop() is also called after kernfs_seq_start() or * kernfs_seq_next() failure, it needs to distinguish whether it's stopping * a seq_file iteration which is fully initialized with an active reference * or an aborted kernfs_seq_start() due to get_active failure. The * position pointer is the only context for each seq_file iteration and * thus the stop condition should be encoded in it. As the return value is * directly visible to userland, ERR_PTR(-ENODEV) is the only acceptable * choice to indicate get_active failure. * * Unfortunately, this is complicated due to the optional custom seq_file * operations which may return ERR_PTR(-ENODEV) too. kernfs_seq_stop() * can't distinguish whether ERR_PTR(-ENODEV) is from get_active failure or * custom seq_file operations and thus can't decide whether put_active * should be performed or not only on ERR_PTR(-ENODEV). * * This is worked around by factoring out the custom seq_stop() and * put_active part into kernfs_seq_stop_active(), skipping it from * kernfs_seq_stop() if ERR_PTR(-ENODEV) while invoking it directly after * custom seq_file operations fail with ERR_PTR(-ENODEV) - this ensures * that kernfs_seq_stop_active() is skipped only after get_active failure. */ static void kernfs_seq_stop_active(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_stop) ops->seq_stop(sf, v); kernfs_put_active(of->kn); } static void *kernfs_seq_start(struct seq_file *sf, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops; /* * @of->mutex nests outside active ref and is primarily to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) return ERR_PTR(-ENODEV); ops = kernfs_ops(of->kn); if (ops->seq_start) { void *next = ops->seq_start(sf, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(). Returns * !NULL if pos is at the beginning; otherwise, NULL. */ return NULL + !*ppos; } } static void *kernfs_seq_next(struct seq_file *sf, void *v, loff_t *ppos) { struct kernfs_open_file *of = sf->private; const struct kernfs_ops *ops = kernfs_ops(of->kn); if (ops->seq_next) { void *next = ops->seq_next(sf, v, ppos); /* see the comment above kernfs_seq_stop_active() */ if (next == ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, next); return next; } else { /* * The same behavior and code as single_open(), always * terminate after the initial read. */ ++*ppos; return NULL; } } static void kernfs_seq_stop(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; if (v != ERR_PTR(-ENODEV)) kernfs_seq_stop_active(sf, v); mutex_unlock(&of->mutex); } static int kernfs_seq_show(struct seq_file *sf, void *v) { struct kernfs_open_file *of = sf->private; of->event = atomic_read(&of->kn->attr.open->event); return of->kn->attr.ops->seq_show(sf, v); } static const struct seq_operations kernfs_seq_ops = { .start = kernfs_seq_start, .next = kernfs_seq_next, .stop = kernfs_seq_stop, .show = kernfs_seq_show, }; /* * As reading a bin file can have side-effects, the exact offset and bytes * specified in read(2) call should be passed to the read callback making * it difficult to use seq_file. Implement simplistic custom buffering for * bin files. */ static ssize_t kernfs_file_direct_read(struct kernfs_open_file *of, char __user *user_buf, size_t count, loff_t *ppos) { ssize_t len = min_t(size_t, count, PAGE_SIZE); const struct kernfs_ops *ops; char *buf; buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len, GFP_KERNEL); if (!buf) return -ENOMEM; /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { len = -ENODEV; mutex_unlock(&of->mutex); goto out_free; } of->event = atomic_read(&of->kn->attr.open->event); ops = kernfs_ops(of->kn); if (ops->read) len = ops->read(of, buf, len, *ppos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len < 0) goto out_free; if (copy_to_user(user_buf, buf, len)) { len = -EFAULT; goto out_free; } *ppos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } /** * kernfs_fop_read - kernfs vfs read callback * @file: file pointer * @user_buf: data to write * @count: number of bytes * @ppos: starting offset */ static ssize_t kernfs_fop_read(struct file *file, char __user *user_buf, size_t count, loff_t *ppos) { struct kernfs_open_file *of = kernfs_of(file); if (of->kn->flags & KERNFS_HAS_SEQ_SHOW) return seq_read(file, user_buf, count, ppos); else return kernfs_file_direct_read(of, user_buf, count, ppos); } /** * kernfs_fop_write - kernfs vfs write callback * @file: file pointer * @user_buf: data to write * @count: number of bytes * @ppos: starting offset * * Copy data in from userland and pass it to the matching kernfs write * operation. * * There is no easy way for us to know if userspace is only doing a partial * write, so we don't support them. We expect the entire buffer to come on * the first write. Hint: if you're writing a value, first read the file, * modify only the the value you're changing, then write entire buffer * back. */ static ssize_t kernfs_fop_write(struct file *file, const char __user *user_buf, size_t count, loff_t *ppos) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; ssize_t len; char *buf; if (of->atomic_write_len) { len = count; if (len > of->atomic_write_len) return -E2BIG; } else { len = min_t(size_t, count, PAGE_SIZE); } buf = of->prealloc_buf; if (buf) mutex_lock(&of->prealloc_mutex); else buf = kmalloc(len + 1, GFP_KERNEL); if (!buf) return -ENOMEM; if (copy_from_user(buf, user_buf, len)) { len = -EFAULT; goto out_free; } buf[len] = '\0'; /* guarantee string termination */ /* * @of->mutex nests outside active ref and is used both to ensure that * the ops aren't called concurrently for the same open file. */ mutex_lock(&of->mutex); if (!kernfs_get_active(of->kn)) { mutex_unlock(&of->mutex); len = -ENODEV; goto out_free; } ops = kernfs_ops(of->kn); if (ops->write) len = ops->write(of, buf, len, *ppos); else len = -EINVAL; kernfs_put_active(of->kn); mutex_unlock(&of->mutex); if (len > 0) *ppos += len; out_free: if (buf == of->prealloc_buf) mutex_unlock(&of->prealloc_mutex); else kfree(buf); return len; } static void kernfs_vma_open(struct vm_area_struct *vma) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); if (!of->vm_ops) return; if (!kernfs_get_active(of->kn)) return; if (of->vm_ops->open) of->vm_ops->open(vma); kernfs_put_active(of->kn); } static vm_fault_t kernfs_vma_fault(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = VM_FAULT_SIGBUS; if (of->vm_ops->fault) ret = of->vm_ops->fault(vmf); kernfs_put_active(of->kn); return ret; } static vm_fault_t kernfs_vma_page_mkwrite(struct vm_fault *vmf) { struct file *file = vmf->vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); vm_fault_t ret; if (!of->vm_ops) return VM_FAULT_SIGBUS; if (!kernfs_get_active(of->kn)) return VM_FAULT_SIGBUS; ret = 0; if (of->vm_ops->page_mkwrite) ret = of->vm_ops->page_mkwrite(vmf); else file_update_time(file); kernfs_put_active(of->kn); return ret; } static int kernfs_vma_access(struct vm_area_struct *vma, unsigned long addr, void *buf, int len, int write) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return -EINVAL; if (!kernfs_get_active(of->kn)) return -EINVAL; ret = -EINVAL; if (of->vm_ops->access) ret = of->vm_ops->access(vma, addr, buf, len, write); kernfs_put_active(of->kn); return ret; } #ifdef CONFIG_NUMA static int kernfs_vma_set_policy(struct vm_area_struct *vma, struct mempolicy *new) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); int ret; if (!of->vm_ops) return 0; if (!kernfs_get_active(of->kn)) return -EINVAL; ret = 0; if (of->vm_ops->set_policy) ret = of->vm_ops->set_policy(vma, new); kernfs_put_active(of->kn); return ret; } static struct mempolicy *kernfs_vma_get_policy(struct vm_area_struct *vma, unsigned long addr) { struct file *file = vma->vm_file; struct kernfs_open_file *of = kernfs_of(file); struct mempolicy *pol; if (!of->vm_ops) return vma->vm_policy; if (!kernfs_get_active(of->kn)) return vma->vm_policy; pol = vma->vm_policy; if (of->vm_ops->get_policy) pol = of->vm_ops->get_policy(vma, addr); kernfs_put_active(of->kn); return pol; } #endif static const struct vm_operations_struct kernfs_vm_ops = { .open = kernfs_vma_open, .fault = kernfs_vma_fault, .page_mkwrite = kernfs_vma_page_mkwrite, .access = kernfs_vma_access, #ifdef CONFIG_NUMA .set_policy = kernfs_vma_set_policy, .get_policy = kernfs_vma_get_policy, #endif }; static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma) { struct kernfs_open_file *of = kernfs_of(file); const struct kernfs_ops *ops; int rc; /* * mmap path and of->mutex are prone to triggering spurious lockdep * warnings and we don't want to add spurious locking dependency * between the two. Check whether mmap is actually implemented * without grabbing @of->mutex by testing HAS_MMAP flag. See the * comment in kernfs_file_open() for more details. */ if (!(of->kn->flags & KERNFS_HAS_MMAP)) return -ENODEV; mutex_lock(&of->mutex); rc = -ENODEV; if (!kernfs_get_active(of->kn)) goto out_unlock; ops = kernfs_ops(of->kn); rc = ops->mmap(of, vma); if (rc) goto out_put; /* * PowerPC's pci_mmap of legacy_mem uses shmem_zero_setup() * to satisfy versions of X which crash if the mmap fails: that * substitutes a new vm_file, and we don't then want bin_vm_ops. */ if (vma->vm_file != file) goto out_put; rc = -EINVAL; if (of->mmapped && of->vm_ops != vma->vm_ops) goto out_put; /* * It is not possible to successfully wrap close. * So error if someone is trying to use close. */ rc = -EINVAL; if (vma->vm_ops && vma->vm_ops->close) goto out_put; rc = 0; of->mmapped = true; of->vm_ops = vma->vm_ops; vma->vm_ops = &kernfs_vm_ops; out_put: kernfs_put_active(of->kn); out_unlock: mutex_unlock(&of->mutex); return rc; } /** * kernfs_get_open_node - get or create kernfs_open_node * @kn: target kernfs_node * @of: kernfs_open_file for this instance of open * * If @kn->attr.open exists, increment its reference count; otherwise, * create one. @of is chained to the files list. * * LOCKING: * Kernel thread context (may sleep). * * RETURNS: * 0 on success, -errno on failure. */ static int kernfs_get_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on, *new_on = NULL; retry: mutex_lock(&kernfs_open_file_mutex); spin_lock_irq(&kernfs_open_node_lock); if (!kn->attr.open && new_on) { kn->attr.open = new_on; new_on = NULL; } on = kn->attr.open; if (on) { atomic_inc(&on->refcnt); list_add_tail(&of->list, &on->files); } spin_unlock_irq(&kernfs_open_node_lock); mutex_unlock(&kernfs_open_file_mutex); if (on) { kfree(new_on); return 0; } /* not there, initialize a new one and retry */ new_on = kmalloc(sizeof(*new_on), GFP_KERNEL); if (!new_on) return -ENOMEM; atomic_set(&new_on->refcnt, 0); atomic_set(&new_on->event, 1); init_waitqueue_head(&new_on->poll); INIT_LIST_HEAD(&new_on->files); goto retry; } /** * kernfs_put_open_node - put kernfs_open_node * @kn: target kernfs_nodet * @of: associated kernfs_open_file * * Put @kn->attr.open and unlink @of from the files list. If * reference count reaches zero, disassociate and free it. * * LOCKING: * None. */ static void kernfs_put_open_node(struct kernfs_node *kn, struct kernfs_open_file *of) { struct kernfs_open_node *on = kn->attr.open; unsigned long flags; mutex_lock(&kernfs_open_file_mutex); spin_lock_irqsave(&kernfs_open_node_lock, flags); if (of) list_del(&of->list); if (atomic_dec_and_test(&on->refcnt)) kn->attr.open = NULL; else on = NULL; spin_unlock_irqrestore(&kernfs_open_node_lock, flags); mutex_unlock(&kernfs_open_file_mutex); kfree(on); } static int kernfs_fop_open(struct inode *inode, struct file *file) { struct kernfs_node *kn = inode->i_private; struct kernfs_root *root = kernfs_root(kn); const struct kernfs_ops *ops; struct kernfs_open_file *of; bool has_read, has_write, has_mmap; int error = -EACCES; if (!kernfs_get_active(kn)) return -ENODEV; ops = kernfs_ops(kn); has_read = ops->seq_show || ops->read || ops->mmap; has_write = ops->write || ops->mmap; has_mmap = ops->mmap; /* see the flag definition for details */ if (root->flags & KERNFS_ROOT_EXTRA_OPEN_PERM_CHECK) { if ((file->f_mode & FMODE_WRITE) && (!(inode->i_mode & S_IWUGO) || !has_write)) goto err_out; if ((file->f_mode & FMODE_READ) && (!(inode->i_mode & S_IRUGO) || !has_read)) goto err_out; } /* allocate a kernfs_open_file for the file */ error = -ENOMEM; of = kzalloc(sizeof(struct kernfs_open_file), GFP_KERNEL); if (!of) goto err_out; /* * The following is done to give a different lockdep key to * @of->mutex for files which implement mmap. This is a rather * crude way to avoid false positive lockdep warning around * mm->mmap_sem - mmap nests @of->mutex under mm->mmap_sem and * reading /sys/block/sda/trace/act_mask grabs sr_mutex, under * which mm->mmap_sem nests, while holding @of->mutex. As each * open file has a separate mutex, it's okay as long as those don't * happen on the same file. At this point, we can't easily give * each file a separate locking class. Let's differentiate on * whether the file has mmap or not for now. * * Both paths of the branch look the same. They're supposed to * look that way and give @of->mutex different static lockdep keys. */ if (has_mmap) mutex_init(&of->mutex); else mutex_init(&of->mutex); of->kn = kn; of->file = file; /* * Write path needs to atomic_write_len outside active reference. * Cache it in open_file. See kernfs_fop_write() for details. */ of->atomic_write_len = ops->atomic_write_len; error = -EINVAL; /* * ->seq_show is incompatible with ->prealloc, * as seq_read does its own allocation. * ->read must be used instead. */ if (ops->prealloc && ops->seq_show) goto err_free; if (ops->prealloc) { int len = of->atomic_write_len ?: PAGE_SIZE; of->prealloc_buf = kmalloc(len + 1, GFP_KERNEL); error = -ENOMEM; if (!of->prealloc_buf) goto err_free; mutex_init(&of->prealloc_mutex); } /* * Always instantiate seq_file even if read access doesn't use * seq_file or is not requested. This unifies private data access * and readable regular files are the vast majority anyway. */ if (ops->seq_show) error = seq_open(file, &kernfs_seq_ops); else error = seq_open(file, NULL); if (error) goto err_free; of->seq_file = file->private_data; of->seq_file->private = of; /* seq_file clears PWRITE unconditionally, restore it if WRITE */ if (file->f_mode & FMODE_WRITE) file->f_mode |= FMODE_PWRITE; /* make sure we have open node struct */ error = kernfs_get_open_node(kn, of); if (error) goto err_seq_release; if (ops->open) { /* nobody has access to @of yet, skip @of->mutex */ error = ops->open(of); if (error) goto err_put_node; } /* open succeeded, put active references */ kernfs_put_active(kn); return 0; err_put_node: kernfs_put_open_node(kn, of); err_seq_release: seq_release(inode, file); err_free: kfree(of->prealloc_buf); kfree(of); err_out: kernfs_put_active(kn); return error; } /* used from release/drain to ensure that ->release() is called exactly once */ static void kernfs_release_file(struct kernfs_node *kn, struct kernfs_open_file *of) { /* * @of is guaranteed to have no other file operations in flight and * we just want to synchronize release and drain paths. * @kernfs_open_file_mutex is enough. @of->mutex can't be used * here because drain path may be called from places which can * cause circular dependency. */ lockdep_assert_held(&kernfs_open_file_mutex); if (!of->released) { /* * A file is never detached without being released and we * need to be able to release files which are deactivated * and being drained. Don't use kernfs_ops(). */ kn->attr.ops->release(of); of->released = true; } } static int kernfs_fop_release(struct inode *inode, struct file *filp) { struct kernfs_node *kn = inode->i_private; struct kernfs_open_file *of = kernfs_of(filp); if (kn->flags & KERNFS_HAS_RELEASE) { mutex_lock(&kernfs_open_file_mutex); kernfs_release_file(kn, of); mutex_unlock(&kernfs_open_file_mutex); } kernfs_put_open_node(kn, of); seq_release(inode, filp); kfree(of->prealloc_buf); kfree(of); return 0; } void kernfs_drain_open_files(struct kernfs_node *kn) { struct kernfs_open_node *on; struct kernfs_open_file *of; if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE))) return; spin_lock_irq(&kernfs_open_node_lock); on = kn->attr.open; if (on) atomic_inc(&on->refcnt); spin_unlock_irq(&kernfs_open_node_lock); if (!on) return; mutex_lock(&kernfs_open_file_mutex); list_for_each_entry(of, &on->files, list) { struct inode *inode = file_inode(of->file); if (kn->flags & KERNFS_HAS_MMAP) unmap_mapping_range(inode->i_mapping, 0, 0, 1); if (kn->flags & KERNFS_HAS_RELEASE) kernfs_release_file(kn, of); } mutex_unlock(&kernfs_open_file_mutex); kernfs_put_open_node(kn, NULL); } /* * Kernfs attribute files are pollable. The idea is that you read * the content and then you use 'poll' or 'select' to wait for * the content to change. When the content changes (assuming the * manager for the kobject supports notification), poll will * return EPOLLERR|EPOLLPRI, and select will return the fd whether * it is waiting for read, write, or exceptions. * Once poll/select indicates that the value has changed, you * need to close and re-open the file, or seek to 0 and read again. * Reminder: this only works for attributes which actively support * it, and it is not possible to test an attribute from userspace * to see if it supports poll (Neither 'poll' nor 'select' return * an appropriate error code). When in doubt, set a suitable timeout value. */ __poll_t kernfs_generic_poll(struct kernfs_open_file *of, poll_table *wait) { struct kernfs_node *kn = kernfs_dentry_node(of->file->f_path.dentry); struct kernfs_open_node *on = kn->attr.open; poll_wait(of->file, &on->poll, wait); if (of->event != atomic_read(&on->event)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; return DEFAULT_POLLMASK; } static __poll_t kernfs_fop_poll(struct file *filp, poll_table *wait) { struct kernfs_open_file *of = kernfs_of(filp); struct kernfs_node *kn = kernfs_dentry_node(filp->f_path.dentry); __poll_t ret; if (!kernfs_get_active(kn)) return DEFAULT_POLLMASK|EPOLLERR|EPOLLPRI; if (kn->attr.ops->poll) ret = kn->attr.ops->poll(of, wait); else ret = kernfs_generic_poll(of, wait); kernfs_put_active(kn); return ret; } static void kernfs_notify_workfn(struct work_struct *work) { struct kernfs_node *kn; struct kernfs_super_info *info; repeat: /* pop one off the notify_list */ spin_lock_irq(&kernfs_notify_lock); kn = kernfs_notify_list; if (kn == KERNFS_NOTIFY_EOL) { spin_unlock_irq(&kernfs_notify_lock); return; } kernfs_notify_list = kn->attr.notify_next; kn->attr.notify_next = NULL; spin_unlock_irq(&kernfs_notify_lock); /* kick fsnotify */ mutex_lock(&kernfs_mutex); list_for_each_entry(info, &kernfs_root(kn)->supers, node) { struct kernfs_node *parent; struct inode *inode; struct qstr name; /* * We want fsnotify_modify() on @kn but as the * modifications aren't originating from userland don't * have the matching @file available. Look up the inodes * and generate the events manually. */ inode = ilookup(info->sb, kn->id.ino); if (!inode) continue; name = (struct qstr)QSTR_INIT(kn->name, strlen(kn->name)); parent = kernfs_get_parent(kn); if (parent) { struct inode *p_inode; p_inode = ilookup(info->sb, parent->id.ino); if (p_inode) { fsnotify(p_inode, FS_MODIFY | FS_EVENT_ON_CHILD, inode, FSNOTIFY_EVENT_INODE, &name, 0); iput(p_inode); } kernfs_put(parent); } fsnotify(inode, FS_MODIFY, inode, FSNOTIFY_EVENT_INODE, NULL, 0); iput(inode); } mutex_unlock(&kernfs_mutex); kernfs_put(kn); goto repeat; } /** * kernfs_notify - notify a kernfs file * @kn: file to notify * * Notify @kn such that poll(2) on @kn wakes up. Maybe be called from any * context. */ void kernfs_notify(struct kernfs_node *kn) { static DECLARE_WORK(kernfs_notify_work, kernfs_notify_workfn); unsigned long flags; struct kernfs_open_node *on; if (WARN_ON(kernfs_type(kn) != KERNFS_FILE)) return; /* kick poll immediately */ spin_lock_irqsave(&kernfs_open_node_lock, flags); on = kn->attr.open; if (on) { atomic_inc(&on->event); wake_up_interruptible(&on->poll); } spin_unlock_irqrestore(&kernfs_open_node_lock, flags); /* schedule work to kick fsnotify */ spin_lock_irqsave(&kernfs_notify_lock, flags); if (!kn->attr.notify_next) { kernfs_get(kn); kn->attr.notify_next = kernfs_notify_list; kernfs_notify_list = kn; schedule_work(&kernfs_notify_work); } spin_unlock_irqrestore(&kernfs_notify_lock, flags); } EXPORT_SYMBOL_GPL(kernfs_notify); const struct file_operations kernfs_file_fops = { .read = kernfs_fop_read, .write = kernfs_fop_write, .llseek = generic_file_llseek, .mmap = kernfs_fop_mmap, .open = kernfs_fop_open, .release = kernfs_fop_release, .poll = kernfs_fop_poll, .fsync = noop_fsync, }; /** * __kernfs_create_file - kernfs internal function to create a file * @parent: directory to create the file in * @name: name of the file * @mode: mode of the file * @uid: uid of the file * @gid: gid of the file * @size: size of the file * @ops: kernfs operations for the file * @priv: private data for the file * @ns: optional namespace tag of the file * @key: lockdep key for the file's active_ref, %NULL to disable lockdep * * Returns the created node on success, ERR_PTR() value on error. */ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent, const char *name, umode_t mode, kuid_t uid, kgid_t gid, loff_t size, const struct kernfs_ops *ops, void *priv, const void *ns, struct lock_class_key *key) { struct kernfs_node *kn; unsigned flags; int rc; flags = KERNFS_FILE; kn = kernfs_new_node(parent, name, (mode & S_IALLUGO) | S_IFREG, uid, gid, flags); if (!kn) return ERR_PTR(-ENOMEM); kn->attr.ops = ops; kn->attr.size = size; kn->ns = ns; kn->priv = priv; #ifdef CONFIG_DEBUG_LOCK_ALLOC if (key) { lockdep_init_map(&kn->dep_map, "kn->count", key, 0); kn->flags |= KERNFS_LOCKDEP; } #endif /* * kn->attr.ops is accesible only while holding active ref. We * need to know whether some ops are implemented outside active * ref. Cache their existence in flags. */ if (ops->seq_show) kn->flags |= KERNFS_HAS_SEQ_SHOW; if (ops->mmap) kn->flags |= KERNFS_HAS_MMAP; if (ops->release) kn->flags |= KERNFS_HAS_RELEASE; rc = kernfs_add_one(kn); if (rc) { kernfs_put(kn); return ERR_PTR(rc); } return kn; } |
| 3 5 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SNAP data link layer. Derived from 802.2 * * Alan Cox <alan@lxorguk.ukuu.org.uk>, * from the 802.2 layer by Greg Page. * Merged in additions from Greg Page's psnap.c. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/datalink.h> #include <net/llc.h> #include <net/psnap.h> #include <linux/mm.h> #include <linux/in.h> #include <linux/init.h> #include <linux/rculist.h> static LIST_HEAD(snap_list); static DEFINE_SPINLOCK(snap_lock); static struct llc_sap *snap_sap; /* * Find a snap client by matching the 5 bytes. */ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; list_for_each_entry_rcu(p, &snap_list, node) { if (!memcmp(p->type, desc, 5)) { proto = p; break; } } return proto; } /* * A SNAP packet has arrived */ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { int rc = 1; struct datalink_proto *proto; static struct packet_type snap_packet_type = { .type = cpu_to_be16(ETH_P_SNAP), }; if (unlikely(!pskb_may_pull(skb, 5))) goto drop; rcu_read_lock(); proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ skb_pull_rcsum(skb, 5); skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); if (unlikely(!proto)) goto drop; out: return rc; drop: kfree_skb(skb); goto out; } /* * Put a SNAP header on a frame and pass to 802.2 */ static int snap_request(struct datalink_proto *dl, struct sk_buff *skb, u8 *dest) { memcpy(skb_push(skb, 5), dl->type, 5); llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); return 0; } /* * Set up the SNAP layer */ EXPORT_SYMBOL(register_snap_client); EXPORT_SYMBOL(unregister_snap_client); static const char snap_err_msg[] __initconst = KERN_CRIT "SNAP - unable to register with 802.2\n"; static int __init snap_init(void) { snap_sap = llc_sap_open(0xAA, snap_rcv); if (!snap_sap) { printk(snap_err_msg); return -EBUSY; } return 0; } module_init(snap_init); static void __exit snap_exit(void) { llc_sap_put(snap_sap); } module_exit(snap_exit); /* * Register SNAP clients. We don't yet use this for IP. */ struct datalink_proto *register_snap_client(const unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct datalink_proto *proto = NULL; spin_lock_bh(&snap_lock); if (find_snap_client(desc)) goto out; proto = kmalloc(sizeof(*proto), GFP_ATOMIC); if (proto) { memcpy(proto->type, desc, 5); proto->rcvfunc = rcvfunc; proto->header_length = 5 + 3; /* snap + 802.2 */ proto->request = snap_request; list_add_rcu(&proto->node, &snap_list); } out: spin_unlock_bh(&snap_lock); return proto; } /* * Unregister SNAP clients. Protocols no longer want to play with us ... */ void unregister_snap_client(struct datalink_proto *proto) { spin_lock_bh(&snap_lock); list_del_rcu(&proto->node); spin_unlock_bh(&snap_lock); synchronize_net(); kfree(proto); } MODULE_LICENSE("GPL"); |
| 509 17 230 230 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/backing-dev.h * * low-level device information and state which is propagated up through * to high-level code. */ #ifndef _LINUX_BACKING_DEV_H #define _LINUX_BACKING_DEV_H #include <linux/kernel.h> #include <linux/fs.h> #include <linux/sched.h> #include <linux/blkdev.h> #include <linux/device.h> #include <linux/writeback.h> #include <linux/blk-cgroup.h> #include <linux/backing-dev-defs.h> #include <linux/slab.h> static inline struct backing_dev_info *bdi_get(struct backing_dev_info *bdi) { kref_get(&bdi->refcnt); return bdi; } struct backing_dev_info *bdi_get_by_id(u64 id); void bdi_put(struct backing_dev_info *bdi); __printf(2, 3) int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...); __printf(2, 0) int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args); int bdi_register_owner(struct backing_dev_info *bdi, struct device *owner); void bdi_unregister(struct backing_dev_info *bdi); struct backing_dev_info *bdi_alloc_node(gfp_t gfp_mask, int node_id); static inline struct backing_dev_info *bdi_alloc(gfp_t gfp_mask) { return bdi_alloc_node(gfp_mask, NUMA_NO_NODE); } void wb_start_background_writeback(struct bdi_writeback *wb); void wb_workfn(struct work_struct *work); void wb_wakeup_delayed(struct bdi_writeback *wb); void wb_wait_for_completion(struct wb_completion *done); extern spinlock_t bdi_lock; extern struct list_head bdi_list; extern struct workqueue_struct *bdi_wq; extern struct workqueue_struct *bdi_async_bio_wq; static inline bool wb_has_dirty_io(struct bdi_writeback *wb) { return test_bit(WB_has_dirty_io, &wb->state); } static inline bool bdi_has_dirty_io(struct backing_dev_info *bdi) { /* * @bdi->tot_write_bandwidth is guaranteed to be > 0 if there are * any dirty wbs. See wb_update_write_bandwidth(). */ return atomic_long_read(&bdi->tot_write_bandwidth); } static inline void __add_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item, s64 amount) { percpu_counter_add_batch(&wb->stat[item], amount, WB_STAT_BATCH); } static inline void inc_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { __add_wb_stat(wb, item, 1); } static inline void dec_wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { __add_wb_stat(wb, item, -1); } static inline s64 wb_stat(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_read_positive(&wb->stat[item]); } static inline s64 wb_stat_sum(struct bdi_writeback *wb, enum wb_stat_item item) { return percpu_counter_sum_positive(&wb->stat[item]); } extern void wb_writeout_inc(struct bdi_writeback *wb); /* * maximal error of a stat counter. */ static inline unsigned long wb_stat_error(void) { #ifdef CONFIG_SMP return nr_cpu_ids * WB_STAT_BATCH; #else return 1; #endif } int bdi_set_min_ratio(struct backing_dev_info *bdi, unsigned int min_ratio); int bdi_set_max_ratio(struct backing_dev_info *bdi, unsigned int max_ratio); /* * Flags in backing_dev_info::capability * * The first three flags control whether dirty pages will contribute to the * VM's accounting and whether writepages() should be called for dirty pages * (something that would not, for example, be appropriate for ramfs) * * WARNING: these flags are closely related and should not normally be * used separately. The BDI_CAP_NO_ACCT_AND_WRITEBACK combines these * three flags into a single convenience macro. * * BDI_CAP_NO_ACCT_DIRTY: Dirty pages shouldn't contribute to accounting * BDI_CAP_NO_WRITEBACK: Don't write pages back * BDI_CAP_NO_ACCT_WB: Don't automatically account writeback pages * BDI_CAP_STRICTLIMIT: Keep number of dirty pages below bdi threshold. * * BDI_CAP_CGROUP_WRITEBACK: Supports cgroup-aware writeback. * BDI_CAP_SYNCHRONOUS_IO: Device is so fast that asynchronous IO would be * inefficient. */ #define BDI_CAP_NO_ACCT_DIRTY 0x00000001 #define BDI_CAP_NO_WRITEBACK 0x00000002 #define BDI_CAP_NO_ACCT_WB 0x00000004 #define BDI_CAP_STABLE_WRITES 0x00000008 #define BDI_CAP_STRICTLIMIT 0x00000010 #define BDI_CAP_CGROUP_WRITEBACK 0x00000020 #define BDI_CAP_SYNCHRONOUS_IO 0x00000040 #define BDI_CAP_NO_ACCT_AND_WRITEBACK \ (BDI_CAP_NO_WRITEBACK | BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_ACCT_WB) extern struct backing_dev_info noop_backing_dev_info; /** * writeback_in_progress - determine whether there is writeback in progress * @wb: bdi_writeback of interest * * Determine whether there is writeback waiting to be handled against a * bdi_writeback. */ static inline bool writeback_in_progress(struct bdi_writeback *wb) { return test_bit(WB_writeback_running, &wb->state); } static inline struct backing_dev_info *inode_to_bdi(struct inode *inode) { struct super_block *sb; if (!inode) return &noop_backing_dev_info; sb = inode->i_sb; #ifdef CONFIG_BLOCK if (sb_is_blkdev_sb(sb)) return I_BDEV(inode)->bd_bdi; #endif return sb->s_bdi; } static inline int wb_congested(struct bdi_writeback *wb, int cong_bits) { struct backing_dev_info *bdi = wb->bdi; if (bdi->congested_fn) return bdi->congested_fn(bdi->congested_data, cong_bits); return wb->congested->state & cong_bits; } long congestion_wait(int sync, long timeout); long wait_iff_congested(int sync, long timeout); static inline bool bdi_cap_synchronous_io(struct backing_dev_info *bdi) { return bdi->capabilities & BDI_CAP_SYNCHRONOUS_IO; } static inline bool bdi_cap_stable_pages_required(struct backing_dev_info *bdi) { return bdi->capabilities & BDI_CAP_STABLE_WRITES; } static inline bool bdi_cap_writeback_dirty(struct backing_dev_info *bdi) { return !(bdi->capabilities & BDI_CAP_NO_WRITEBACK); } static inline bool bdi_cap_account_dirty(struct backing_dev_info *bdi) { return !(bdi->capabilities & BDI_CAP_NO_ACCT_DIRTY); } static inline bool bdi_cap_account_writeback(struct backing_dev_info *bdi) { /* Paranoia: BDI_CAP_NO_WRITEBACK implies BDI_CAP_NO_ACCT_WB */ return !(bdi->capabilities & (BDI_CAP_NO_ACCT_WB | BDI_CAP_NO_WRITEBACK)); } static inline bool mapping_cap_writeback_dirty(struct address_space *mapping) { return bdi_cap_writeback_dirty(inode_to_bdi(mapping->host)); } static inline bool mapping_cap_account_dirty(struct address_space *mapping) { return bdi_cap_account_dirty(inode_to_bdi(mapping->host)); } static inline int bdi_sched_wait(void *word) { schedule(); return 0; } #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback_congested * wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp); void wb_congested_put(struct bdi_writeback_congested *congested); struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css); struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp); void wb_memcg_offline(struct mem_cgroup *memcg); void wb_blkcg_offline(struct blkcg *blkcg); int inode_congested(struct inode *inode, int cong_bits); /** * inode_cgwb_enabled - test whether cgroup writeback is enabled on an inode * @inode: inode of interest * * cgroup writeback requires support from both the bdi and filesystem. * Also, both memcg and iocg have to be on the default hierarchy. Test * whether all conditions are met. * * Note that the test result may change dynamically on the same inode * depending on how memcg and iocg are configured. */ static inline bool inode_cgwb_enabled(struct inode *inode) { struct backing_dev_info *bdi = inode_to_bdi(inode); return cgroup_subsys_on_dfl(memory_cgrp_subsys) && cgroup_subsys_on_dfl(io_cgrp_subsys) && bdi_cap_account_dirty(bdi) && (bdi->capabilities & BDI_CAP_CGROUP_WRITEBACK) && (inode->i_sb->s_iflags & SB_I_CGROUPWB); } /** * wb_find_current - find wb for %current on a bdi * @bdi: bdi of interest * * Find the wb of @bdi which matches both the memcg and blkcg of %current. * Must be called under rcu_read_lock() which protects the returend wb. * NULL if not found. */ static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { struct cgroup_subsys_state *memcg_css; struct bdi_writeback *wb; memcg_css = task_css(current, memory_cgrp_id); if (!memcg_css->parent) return &bdi->wb; wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); /* * %current's blkcg equals the effective blkcg of its memcg. No * need to use the relatively expensive cgroup_get_e_css(). */ if (likely(wb && wb->blkcg_css == task_css(current, io_cgrp_id))) return wb; return NULL; } /** * wb_get_create_current - get or create wb for %current on a bdi * @bdi: bdi of interest * @gfp: allocation mask * * Equivalent to wb_get_create() on %current's memcg. This function is * called from a relatively hot path and optimizes the common cases using * wb_find_current(). */ static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { struct bdi_writeback *wb; rcu_read_lock(); wb = wb_find_current(bdi); if (wb && unlikely(!wb_tryget(wb))) wb = NULL; rcu_read_unlock(); if (unlikely(!wb)) { struct cgroup_subsys_state *memcg_css; memcg_css = task_get_css(current, memory_cgrp_id); wb = wb_get_create(bdi, memcg_css, gfp); css_put(memcg_css); } return wb; } /** * inode_to_wb_is_valid - test whether an inode has a wb associated * @inode: inode of interest * * Returns %true if @inode has a wb associated. May be called without any * locking. */ static inline bool inode_to_wb_is_valid(struct inode *inode) { return inode->i_wb; } /** * inode_to_wb - determine the wb of an inode * @inode: inode of interest * * Returns the wb @inode is currently associated with. The caller must be * holding either @inode->i_lock, the i_pages lock, or the * associated wb's list_lock. */ static inline struct bdi_writeback *inode_to_wb(const struct inode *inode) { #ifdef CONFIG_LOCKDEP WARN_ON_ONCE(debug_locks && (!lockdep_is_held(&inode->i_lock) && !lockdep_is_held(&inode->i_mapping->i_pages.xa_lock) && !lockdep_is_held(&inode->i_wb->list_lock))); #endif return inode->i_wb; } /** * unlocked_inode_to_wb_begin - begin unlocked inode wb access transaction * @inode: target inode * @cookie: output param, to be passed to the end function * * The caller wants to access the wb associated with @inode but isn't * holding inode->i_lock, the i_pages lock or wb->list_lock. This * function determines the wb associated with @inode and ensures that the * association doesn't change until the transaction is finished with * unlocked_inode_to_wb_end(). * * The caller must call unlocked_inode_to_wb_end() with *@cookie afterwards and * can't sleep during the transaction. IRQs may or may not be disabled on * return. */ static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { rcu_read_lock(); /* * Paired with store_release in inode_switch_wbs_work_fn() and * ensures that we see the new wb if we see cleared I_WB_SWITCH. */ cookie->locked = smp_load_acquire(&inode->i_state) & I_WB_SWITCH; if (unlikely(cookie->locked)) xa_lock_irqsave(&inode->i_mapping->i_pages, cookie->flags); /* * Protected by either !I_WB_SWITCH + rcu_read_lock() or the i_pages * lock. inode_to_wb() will bark. Deref directly. */ return inode->i_wb; } /** * unlocked_inode_to_wb_end - end inode wb access transaction * @inode: target inode * @cookie: @cookie from unlocked_inode_to_wb_begin() */ static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { if (unlikely(cookie->locked)) xa_unlock_irqrestore(&inode->i_mapping->i_pages, cookie->flags); rcu_read_unlock(); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline bool inode_cgwb_enabled(struct inode *inode) { return false; } static inline struct bdi_writeback_congested * wb_congested_get_create(struct backing_dev_info *bdi, int blkcg_id, gfp_t gfp) { refcount_inc(&bdi->wb_congested->refcnt); return bdi->wb_congested; } static inline void wb_congested_put(struct bdi_writeback_congested *congested) { if (refcount_dec_and_test(&congested->refcnt)) kfree(congested); } static inline struct bdi_writeback *wb_find_current(struct backing_dev_info *bdi) { return &bdi->wb; } static inline struct bdi_writeback * wb_get_create_current(struct backing_dev_info *bdi, gfp_t gfp) { return &bdi->wb; } static inline bool inode_to_wb_is_valid(struct inode *inode) { return true; } static inline struct bdi_writeback *inode_to_wb(struct inode *inode) { return &inode_to_bdi(inode)->wb; } static inline struct bdi_writeback * unlocked_inode_to_wb_begin(struct inode *inode, struct wb_lock_cookie *cookie) { return inode_to_wb(inode); } static inline void unlocked_inode_to_wb_end(struct inode *inode, struct wb_lock_cookie *cookie) { } static inline void wb_memcg_offline(struct mem_cgroup *memcg) { } static inline void wb_blkcg_offline(struct blkcg *blkcg) { } static inline int inode_congested(struct inode *inode, int cong_bits) { return wb_congested(&inode_to_bdi(inode)->wb, cong_bits); } #endif /* CONFIG_CGROUP_WRITEBACK */ static inline int inode_read_congested(struct inode *inode) { return inode_congested(inode, 1 << WB_sync_congested); } static inline int inode_write_congested(struct inode *inode) { return inode_congested(inode, 1 << WB_async_congested); } static inline int inode_rw_congested(struct inode *inode) { return inode_congested(inode, (1 << WB_sync_congested) | (1 << WB_async_congested)); } static inline int bdi_congested(struct backing_dev_info *bdi, int cong_bits) { return wb_congested(&bdi->wb, cong_bits); } static inline int bdi_read_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, 1 << WB_sync_congested); } static inline int bdi_write_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, 1 << WB_async_congested); } static inline int bdi_rw_congested(struct backing_dev_info *bdi) { return bdi_congested(bdi, (1 << WB_sync_congested) | (1 << WB_async_congested)); } const char *bdi_dev_name(struct backing_dev_info *bdi); #endif /* _LINUX_BACKING_DEV_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Copyright (C) 2001 Jens Axboe <axboe@suse.de> */ #ifndef __LINUX_BIO_H #define __LINUX_BIO_H #include <linux/highmem.h> #include <linux/mempool.h> #include <linux/ioprio.h> #include <linux/android_kabi.h> #ifdef CONFIG_BLOCK /* struct bio, bio_vec and BIO_* flags are defined in blk_types.h */ #include <linux/blk_types.h> #define BIO_DEBUG #ifdef BIO_DEBUG #define BIO_BUG_ON BUG_ON #else #define BIO_BUG_ON #endif #define BIO_MAX_PAGES 256 #define bio_prio(bio) (bio)->bi_ioprio #define bio_set_prio(bio, prio) ((bio)->bi_ioprio = prio) #define bio_iter_iovec(bio, iter) \ bvec_iter_bvec((bio)->bi_io_vec, (iter)) #define bio_iter_page(bio, iter) \ bvec_iter_page((bio)->bi_io_vec, (iter)) #define bio_iter_len(bio, iter) \ bvec_iter_len((bio)->bi_io_vec, (iter)) #define bio_iter_offset(bio, iter) \ bvec_iter_offset((bio)->bi_io_vec, (iter)) #define bio_page(bio) bio_iter_page((bio), (bio)->bi_iter) #define bio_offset(bio) bio_iter_offset((bio), (bio)->bi_iter) #define bio_iovec(bio) bio_iter_iovec((bio), (bio)->bi_iter) #define bvec_iter_sectors(iter) ((iter).bi_size >> 9) #define bvec_iter_end_sector(iter) ((iter).bi_sector + bvec_iter_sectors((iter))) #define bio_sectors(bio) bvec_iter_sectors((bio)->bi_iter) #define bio_end_sector(bio) bvec_iter_end_sector((bio)->bi_iter) /* * Return the data direction, READ or WRITE. */ #define bio_data_dir(bio) \ (op_is_write(bio_op(bio)) ? WRITE : READ) /* * Check whether this bio carries any data or not. A NULL bio is allowed. */ static inline bool bio_has_data(struct bio *bio) { if (bio && bio->bi_iter.bi_size && bio_op(bio) != REQ_OP_DISCARD && bio_op(bio) != REQ_OP_SECURE_ERASE && bio_op(bio) != REQ_OP_WRITE_ZEROES) return true; return false; } static inline bool bio_no_advance_iter(struct bio *bio) { return bio_op(bio) == REQ_OP_DISCARD || bio_op(bio) == REQ_OP_SECURE_ERASE || bio_op(bio) == REQ_OP_WRITE_SAME || bio_op(bio) == REQ_OP_WRITE_ZEROES; } static inline bool bio_mergeable(struct bio *bio) { if (bio->bi_opf & REQ_NOMERGE_FLAGS) return false; return true; } static inline unsigned int bio_cur_bytes(struct bio *bio) { if (bio_has_data(bio)) return bio_iovec(bio).bv_len; else /* dataless requests such as discard */ return bio->bi_iter.bi_size; } static inline void *bio_data(struct bio *bio) { if (bio_has_data(bio)) return page_address(bio_page(bio)) + bio_offset(bio); return NULL; } /** * bio_full - check if the bio is full * @bio: bio to check * @len: length of one segment to be added * * Return true if @bio is full and one segment with @len bytes can't be * added to the bio, otherwise return false */ static inline bool bio_full(struct bio *bio, unsigned len) { if (bio->bi_vcnt >= bio->bi_max_vecs) return true; if (bio->bi_iter.bi_size > UINT_MAX - len) return true; return false; } static inline bool bio_next_segment(const struct bio *bio, struct bvec_iter_all *iter) { if (iter->idx >= bio->bi_vcnt) return false; bvec_advance(&bio->bi_io_vec[iter->idx], iter); return true; } /* * drivers should _never_ use the all version - the bio may have been split * before it got to the driver and the driver won't own all of it */ #define bio_for_each_segment_all(bvl, bio, iter) \ for (bvl = bvec_init_iter_all(&iter); bio_next_segment((bio), &iter); ) static inline void bio_advance_iter(struct bio *bio, struct bvec_iter *iter, unsigned bytes) { iter->bi_sector += bytes >> 9; if (bio_no_advance_iter(bio)) iter->bi_size -= bytes; else bvec_iter_advance(bio->bi_io_vec, iter, bytes); /* TODO: It is reasonable to complete bio with error here. */ } #define __bio_for_each_segment(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bio_iter_iovec((bio), (iter))), 1); \ bio_advance_iter((bio), &(iter), (bvl).bv_len)) #define bio_for_each_segment(bvl, bio, iter) \ __bio_for_each_segment(bvl, bio, iter, (bio)->bi_iter) #define __bio_for_each_bvec(bvl, bio, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = mp_bvec_iter_bvec((bio)->bi_io_vec, (iter))), 1); \ bio_advance_iter((bio), &(iter), (bvl).bv_len)) /* iterate over multi-page bvec */ #define bio_for_each_bvec(bvl, bio, iter) \ __bio_for_each_bvec(bvl, bio, iter, (bio)->bi_iter) #define bio_iter_last(bvec, iter) ((iter).bi_size == (bvec).bv_len) static inline unsigned bio_segments(struct bio *bio) { unsigned segs = 0; struct bio_vec bv; struct bvec_iter iter; /* * We special case discard/write same/write zeroes, because they * interpret bi_size differently: */ switch (bio_op(bio)) { case REQ_OP_DISCARD: case REQ_OP_SECURE_ERASE: case REQ_OP_WRITE_ZEROES: return 0; case REQ_OP_WRITE_SAME: return 1; default: break; } bio_for_each_segment(bv, bio, iter) segs++; return segs; } /* * get a reference to a bio, so it won't disappear. the intended use is * something like: * * bio_get(bio); * submit_bio(rw, bio); * if (bio->bi_flags ...) * do_something * bio_put(bio); * * without the bio_get(), it could potentially complete I/O before submit_bio * returns. and then bio would be freed memory when if (bio->bi_flags ...) * runs */ static inline void bio_get(struct bio *bio) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb__before_atomic(); atomic_inc(&bio->__bi_cnt); } static inline void bio_cnt_set(struct bio *bio, unsigned int count) { if (count != 1) { bio->bi_flags |= (1 << BIO_REFFED); smp_mb(); } atomic_set(&bio->__bi_cnt, count); } static inline bool bio_flagged(struct bio *bio, unsigned int bit) { return (bio->bi_flags & (1U << bit)) != 0; } static inline void bio_set_flag(struct bio *bio, unsigned int bit) { bio->bi_flags |= (1U << bit); } static inline void bio_clear_flag(struct bio *bio, unsigned int bit) { bio->bi_flags &= ~(1U << bit); } static inline void bio_get_first_bvec(struct bio *bio, struct bio_vec *bv) { *bv = mp_bvec_iter_bvec(bio->bi_io_vec, bio->bi_iter); } static inline void bio_get_last_bvec(struct bio *bio, struct bio_vec *bv) { struct bvec_iter iter = bio->bi_iter; int idx; bio_get_first_bvec(bio, bv); if (bv->bv_len == bio->bi_iter.bi_size) return; /* this bio only has a single bvec */ bio_advance_iter(bio, &iter, iter.bi_size); if (!iter.bi_bvec_done) idx = iter.bi_idx - 1; else /* in the middle of bvec */ idx = iter.bi_idx; *bv = bio->bi_io_vec[idx]; /* * iter.bi_bvec_done records actual length of the last bvec * if this bio ends in the middle of one io vector */ if (iter.bi_bvec_done) bv->bv_len = iter.bi_bvec_done; } static inline struct bio_vec *bio_first_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return bio->bi_io_vec; } static inline struct page *bio_first_page_all(struct bio *bio) { return bio_first_bvec_all(bio)->bv_page; } static inline struct bio_vec *bio_last_bvec_all(struct bio *bio) { WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED)); return &bio->bi_io_vec[bio->bi_vcnt - 1]; } enum bip_flags { BIP_BLOCK_INTEGRITY = 1 << 0, /* block layer owns integrity data */ BIP_MAPPED_INTEGRITY = 1 << 1, /* ref tag has been remapped */ BIP_CTRL_NOCHECK = 1 << 2, /* disable HBA integrity checking */ BIP_DISK_NOCHECK = 1 << 3, /* disable disk integrity checking */ BIP_IP_CHECKSUM = 1 << 4, /* IP checksum */ }; /* * bio integrity payload */ struct bio_integrity_payload { struct bio *bip_bio; /* parent bio */ struct bvec_iter bip_iter; unsigned short bip_slab; /* slab the bip came from */ unsigned short bip_vcnt; /* # of integrity bio_vecs */ unsigned short bip_max_vcnt; /* integrity bio_vec slots */ unsigned short bip_flags; /* control flags */ struct bvec_iter bio_iter; /* for rewinding parent bio */ struct work_struct bip_work; /* I/O completion */ struct bio_vec *bip_vec; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); struct bio_vec bip_inline_vecs[0];/* embedded bvec array */ }; #if defined(CONFIG_BLK_DEV_INTEGRITY) static inline struct bio_integrity_payload *bio_integrity(struct bio *bio) { if (bio->bi_opf & REQ_INTEGRITY) return bio->bi_integrity; return NULL; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { struct bio_integrity_payload *bip = bio_integrity(bio); if (bip) return bip->bip_flags & flag; return false; } static inline sector_t bip_get_seed(struct bio_integrity_payload *bip) { return bip->bip_iter.bi_sector; } static inline void bip_set_seed(struct bio_integrity_payload *bip, sector_t seed) { bip->bip_iter.bi_sector = seed; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ extern void bio_trim(struct bio *bio, int offset, int size); extern struct bio *bio_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs); /** * bio_next_split - get next @sectors from a bio, splitting if necessary * @bio: bio to split * @sectors: number of sectors to split from the front of @bio * @gfp: gfp mask * @bs: bio set to allocate from * * Returns a bio representing the next @sectors of @bio - if the bio is smaller * than @sectors, returns the original bio unchanged. */ static inline struct bio *bio_next_split(struct bio *bio, int sectors, gfp_t gfp, struct bio_set *bs) { if (sectors >= bio_sectors(bio)) return bio; return bio_split(bio, sectors, gfp, bs); } enum { BIOSET_NEED_BVECS = BIT(0), BIOSET_NEED_RESCUER = BIT(1), }; extern int bioset_init(struct bio_set *, unsigned int, unsigned int, int flags); extern void bioset_exit(struct bio_set *); extern int biovec_init_pool(mempool_t *pool, int pool_entries); extern int bioset_init_from_src(struct bio_set *bs, struct bio_set *src); extern struct bio *bio_alloc_bioset(gfp_t, unsigned int, struct bio_set *); extern void bio_put(struct bio *); extern void __bio_clone_fast(struct bio *, struct bio *); extern struct bio *bio_clone_fast(struct bio *, gfp_t, struct bio_set *); extern struct bio_set fs_bio_set; static inline struct bio *bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, &fs_bio_set); } static inline struct bio *bio_kmalloc(gfp_t gfp_mask, unsigned int nr_iovecs) { return bio_alloc_bioset(gfp_mask, nr_iovecs, NULL); } extern blk_qc_t submit_bio(struct bio *); extern void bio_endio(struct bio *); static inline void bio_io_error(struct bio *bio) { bio->bi_status = BLK_STS_IOERR; bio_endio(bio); } static inline void bio_wouldblock_error(struct bio *bio) { bio->bi_status = BLK_STS_AGAIN; bio_endio(bio); } struct request_queue; extern int submit_bio_wait(struct bio *bio); extern void bio_advance(struct bio *, unsigned); extern void bio_init(struct bio *bio, struct bio_vec *table, unsigned short max_vecs); extern void bio_uninit(struct bio *); extern void bio_reset(struct bio *); void bio_chain(struct bio *, struct bio *); extern int bio_add_page(struct bio *, struct page *, unsigned int,unsigned int); extern int bio_add_pc_page(struct request_queue *, struct bio *, struct page *, unsigned int, unsigned int); bool __bio_try_merge_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off, bool *same_page); void __bio_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int off); int bio_iov_iter_get_pages(struct bio *bio, struct iov_iter *iter); void bio_release_pages(struct bio *bio, bool mark_dirty); struct rq_map_data; extern struct bio *bio_map_user_iov(struct request_queue *, struct iov_iter *, gfp_t); extern void bio_unmap_user(struct bio *); extern struct bio *bio_map_kern(struct request_queue *, void *, unsigned int, gfp_t); extern struct bio *bio_copy_kern(struct request_queue *, void *, unsigned int, gfp_t, int); extern void bio_set_pages_dirty(struct bio *bio); extern void bio_check_pages_dirty(struct bio *bio); void generic_start_io_acct(struct request_queue *q, int op, unsigned long sectors, struct hd_struct *part); void generic_end_io_acct(struct request_queue *q, int op, struct hd_struct *part, unsigned long start_time); extern void bio_copy_data_iter(struct bio *dst, struct bvec_iter *dst_iter, struct bio *src, struct bvec_iter *src_iter); extern void bio_copy_data(struct bio *dst, struct bio *src); extern void bio_list_copy_data(struct bio *dst, struct bio *src); extern void bio_free_pages(struct bio *bio); extern struct bio *bio_copy_user_iov(struct request_queue *, struct rq_map_data *, struct iov_iter *, gfp_t); extern int bio_uncopy_user(struct bio *); void zero_fill_bio_iter(struct bio *bio, struct bvec_iter iter); void bio_truncate(struct bio *bio, unsigned new_size); static inline void zero_fill_bio(struct bio *bio) { zero_fill_bio_iter(bio, bio->bi_iter); } extern struct bio_vec *bvec_alloc(gfp_t, int, unsigned long *, mempool_t *); extern void bvec_free(mempool_t *, struct bio_vec *, unsigned int); extern unsigned int bvec_nr_vecs(unsigned short idx); extern const char *bio_devname(struct bio *bio, char *buffer); #define bio_set_dev(bio, bdev) \ do { \ if ((bio)->bi_disk != (bdev)->bd_disk) \ bio_clear_flag(bio, BIO_THROTTLED);\ (bio)->bi_disk = (bdev)->bd_disk; \ (bio)->bi_partno = (bdev)->bd_partno; \ bio_associate_blkg(bio); \ } while (0) #define bio_copy_dev(dst, src) \ do { \ (dst)->bi_disk = (src)->bi_disk; \ (dst)->bi_partno = (src)->bi_partno; \ bio_clone_blkg_association(dst, src); \ } while (0) #define bio_dev(bio) \ disk_devt((bio)->bi_disk) #if defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void bio_associate_blkg_from_page(struct bio *bio, struct page *page); #else static inline void bio_associate_blkg_from_page(struct bio *bio, struct page *page) { } #endif #ifdef CONFIG_BLK_CGROUP void bio_disassociate_blkg(struct bio *bio); void bio_associate_blkg(struct bio *bio); void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css); void bio_clone_blkg_association(struct bio *dst, struct bio *src); #else /* CONFIG_BLK_CGROUP */ static inline void bio_disassociate_blkg(struct bio *bio) { } static inline void bio_associate_blkg(struct bio *bio) { } static inline void bio_associate_blkg_from_css(struct bio *bio, struct cgroup_subsys_state *css) { } static inline void bio_clone_blkg_association(struct bio *dst, struct bio *src) { } #endif /* CONFIG_BLK_CGROUP */ #ifdef CONFIG_HIGHMEM /* * remember never ever reenable interrupts between a bvec_kmap_irq and * bvec_kunmap_irq! */ static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { unsigned long addr; /* * might not be a highmem page, but the preempt/irq count * balancing is a lot nicer this way */ local_irq_save(*flags); addr = (unsigned long) kmap_atomic(bvec->bv_page); BUG_ON(addr & ~PAGE_MASK); return (char *) addr + bvec->bv_offset; } static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { unsigned long ptr = (unsigned long) buffer & PAGE_MASK; kunmap_atomic((void *) ptr); local_irq_restore(*flags); } #else static inline char *bvec_kmap_irq(struct bio_vec *bvec, unsigned long *flags) { return page_address(bvec->bv_page) + bvec->bv_offset; } static inline void bvec_kunmap_irq(char *buffer, unsigned long *flags) { *flags = 0; } #endif /* * BIO list management for use by remapping drivers (e.g. DM or MD) and loop. * * A bio_list anchors a singly-linked list of bios chained through the bi_next * member of the bio. The bio_list also caches the last list member to allow * fast access to the tail. */ struct bio_list { struct bio *head; struct bio *tail; }; static inline int bio_list_empty(const struct bio_list *bl) { return bl->head == NULL; } static inline void bio_list_init(struct bio_list *bl) { bl->head = bl->tail = NULL; } #define BIO_EMPTY_LIST { NULL, NULL } #define bio_list_for_each(bio, bl) \ for (bio = (bl)->head; bio; bio = bio->bi_next) static inline unsigned bio_list_size(const struct bio_list *bl) { unsigned sz = 0; struct bio *bio; bio_list_for_each(bio, bl) sz++; return sz; } static inline void bio_list_add(struct bio_list *bl, struct bio *bio) { bio->bi_next = NULL; if (bl->tail) bl->tail->bi_next = bio; else bl->head = bio; bl->tail = bio; } static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio) { bio->bi_next = bl->head; bl->head = bio; if (!bl->tail) bl->tail = bio; } static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->tail) bl->tail->bi_next = bl2->head; else bl->head = bl2->head; bl->tail = bl2->tail; } static inline void bio_list_merge_head(struct bio_list *bl, struct bio_list *bl2) { if (!bl2->head) return; if (bl->head) bl2->tail->bi_next = bl->head; else bl->tail = bl2->tail; bl->head = bl2->head; } static inline struct bio *bio_list_peek(struct bio_list *bl) { return bl->head; } static inline struct bio *bio_list_pop(struct bio_list *bl) { struct bio *bio = bl->head; if (bio) { bl->head = bl->head->bi_next; if (!bl->head) bl->tail = NULL; bio->bi_next = NULL; } return bio; } static inline struct bio *bio_list_get(struct bio_list *bl) { struct bio *bio = bl->head; bl->head = bl->tail = NULL; return bio; } /* * Increment chain count for the bio. Make sure the CHAIN flag update * is visible before the raised count. */ static inline void bio_inc_remaining(struct bio *bio) { bio_set_flag(bio, BIO_CHAIN); smp_mb__before_atomic(); atomic_inc(&bio->__bi_remaining); } /* * bio_set is used to allow other portions of the IO system to * allocate their own private memory pools for bio and iovec structures. * These memory pools in turn all allocate from the bio_slab * and the bvec_slabs[]. */ #define BIO_POOL_SIZE 2 struct bio_set { struct kmem_cache *bio_slab; unsigned int front_pad; mempool_t bio_pool; mempool_t bvec_pool; #if defined(CONFIG_BLK_DEV_INTEGRITY) mempool_t bio_integrity_pool; mempool_t bvec_integrity_pool; #endif /* * Deadlock avoidance for stacking block drivers: see comments in * bio_alloc_bioset() for details */ spinlock_t rescue_lock; struct bio_list rescue_list; struct work_struct rescue_work; struct workqueue_struct *rescue_workqueue; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; struct biovec_slab { int nr_vecs; char *name; struct kmem_cache *slab; }; static inline bool bioset_initialized(struct bio_set *bs) { return bs->bio_slab != NULL; } /* * a small number of entries is fine, not going to be performance critical. * basically we just need to survive */ #define BIO_SPLIT_ENTRIES 2 #if defined(CONFIG_BLK_DEV_INTEGRITY) #define bip_for_each_vec(bvl, bip, iter) \ for_each_bvec(bvl, (bip)->bip_vec, iter, (bip)->bip_iter) #define bio_for_each_integrity_vec(_bvl, _bio, _iter) \ for_each_bio(_bio) \ bip_for_each_vec(_bvl, _bio->bi_integrity, _iter) extern struct bio_integrity_payload *bio_integrity_alloc(struct bio *, gfp_t, unsigned int); extern int bio_integrity_add_page(struct bio *, struct page *, unsigned int, unsigned int); extern bool bio_integrity_prep(struct bio *); extern void bio_integrity_advance(struct bio *, unsigned int); extern void bio_integrity_trim(struct bio *); extern int bio_integrity_clone(struct bio *, struct bio *, gfp_t); extern int bioset_integrity_create(struct bio_set *, int); extern void bioset_integrity_free(struct bio_set *); extern void bio_integrity_init(void); #else /* CONFIG_BLK_DEV_INTEGRITY */ static inline void *bio_integrity(struct bio *bio) { return NULL; } static inline int bioset_integrity_create(struct bio_set *bs, int pool_size) { return 0; } static inline void bioset_integrity_free (struct bio_set *bs) { return; } static inline bool bio_integrity_prep(struct bio *bio) { return true; } static inline int bio_integrity_clone(struct bio *bio, struct bio *bio_src, gfp_t gfp_mask) { return 0; } static inline void bio_integrity_advance(struct bio *bio, unsigned int bytes_done) { return; } static inline void bio_integrity_trim(struct bio *bio) { return; } static inline void bio_integrity_init(void) { return; } static inline bool bio_integrity_flagged(struct bio *bio, enum bip_flags flag) { return false; } static inline void *bio_integrity_alloc(struct bio * bio, gfp_t gfp, unsigned int nr) { return ERR_PTR(-EINVAL); } static inline int bio_integrity_add_page(struct bio *bio, struct page *page, unsigned int len, unsigned int offset) { return 0; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ /* * Mark a bio as polled. Note that for async polled IO, the caller must * expect -EWOULDBLOCK if we cannot allocate a request (or other resources). * We cannot block waiting for requests on polled IO, as those completions * must be found by the caller. This is different than IRQ driven IO, where * it's safe to wait for IO to complete. */ static inline void bio_set_polled(struct bio *bio, struct kiocb *kiocb) { bio->bi_opf |= REQ_HIPRI; if (!is_sync_kiocb(kiocb)) bio->bi_opf |= REQ_NOWAIT; } #endif /* CONFIG_BLOCK */ #endif /* __LINUX_BIO_H */ |
| 1369 195 1369 189 189 1387 196 1391 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PERCPU_RWSEM_H #define _LINUX_PERCPU_RWSEM_H #include <linux/atomic.h> #include <linux/rwsem.h> #include <linux/percpu.h> #include <linux/rcuwait.h> #include <linux/rcu_sync.h> #include <linux/lockdep.h> struct percpu_rw_semaphore { struct rcu_sync rss; unsigned int __percpu *read_count; struct rw_semaphore rw_sem; /* slowpath */ struct rcuwait writer; /* blocked writer */ int readers_block; }; #define __DEFINE_PERCPU_RWSEM(name, is_static) \ static DEFINE_PER_CPU(unsigned int, __percpu_rwsem_rc_##name); \ is_static struct percpu_rw_semaphore name = { \ .rss = __RCU_SYNC_INITIALIZER(name.rss), \ .read_count = &__percpu_rwsem_rc_##name, \ .rw_sem = __RWSEM_INITIALIZER(name.rw_sem), \ .writer = __RCUWAIT_INITIALIZER(name.writer), \ } #define DEFINE_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, /* not static */) #define DEFINE_STATIC_PERCPU_RWSEM(name) \ __DEFINE_PERCPU_RWSEM(name, static) extern int __percpu_down_read(struct percpu_rw_semaphore *, int); extern void __percpu_up_read(struct percpu_rw_semaphore *); static inline void percpu_down_read(struct percpu_rw_semaphore *sem) { might_sleep(); rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 0, _RET_IP_); preempt_disable(); /* * We are in an RCU-sched read-side critical section, so the writer * cannot both change sem->state from readers_fast and start checking * counters while we are here. So if we see !sem->state, we know that * the writer won't be checking until we're past the preempt_enable() * and that once the synchronize_rcu() is done, the writer will see * anything we did within this RCU-sched read-size critical section. */ __this_cpu_inc(*sem->read_count); if (unlikely(!rcu_sync_is_idle(&sem->rss))) __percpu_down_read(sem, false); /* Unconditional memory barrier */ /* * The preempt_enable() prevents the compiler from * bleeding the critical section out. */ preempt_enable(); } static inline int percpu_down_read_trylock(struct percpu_rw_semaphore *sem) { int ret = 1; preempt_disable(); /* * Same as in percpu_down_read(). */ __this_cpu_inc(*sem->read_count); if (unlikely(!rcu_sync_is_idle(&sem->rss))) ret = __percpu_down_read(sem, true); /* Unconditional memory barrier */ preempt_enable(); /* * The barrier() from preempt_enable() prevents the compiler from * bleeding the critical section out. */ if (ret) rwsem_acquire_read(&sem->rw_sem.dep_map, 0, 1, _RET_IP_); return ret; } static inline void percpu_up_read(struct percpu_rw_semaphore *sem) { preempt_disable(); /* * Same as in percpu_down_read(). */ if (likely(rcu_sync_is_idle(&sem->rss))) __this_cpu_dec(*sem->read_count); else __percpu_up_read(sem); /* Unconditional memory barrier */ preempt_enable(); rwsem_release(&sem->rw_sem.dep_map, 1, _RET_IP_); } extern void percpu_down_write(struct percpu_rw_semaphore *); extern void percpu_up_write(struct percpu_rw_semaphore *); extern int __percpu_init_rwsem(struct percpu_rw_semaphore *, const char *, struct lock_class_key *); extern void percpu_free_rwsem(struct percpu_rw_semaphore *); #define percpu_init_rwsem(sem) \ ({ \ static struct lock_class_key rwsem_key; \ __percpu_init_rwsem(sem, #sem, &rwsem_key); \ }) #define percpu_rwsem_is_held(sem) lockdep_is_held(&(sem)->rw_sem) #define percpu_rwsem_assert_held(sem) \ lockdep_assert_held(&(sem)->rw_sem) static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_release(&sem->rw_sem.dep_map, 1, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN); #endif } static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem, bool read, unsigned long ip) { lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip); #ifdef CONFIG_RWSEM_SPIN_ON_OWNER if (!read) atomic_long_set(&sem->rw_sem.owner, (long)current); #endif } #endif |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 | /* SPDX-License-Identifier: GPL-2.0 */ /* * ethtool.h: Defines for Linux ethtool. * * Copyright (C) 1998 David S. Miller (davem@redhat.com) * Copyright 2001 Jeff Garzik <jgarzik@pobox.com> * Portions Copyright 2001 Sun Microsystems (thockin@sun.com) * Portions Copyright 2002 Intel (eli.kupermann@intel.com, * christopher.leech@intel.com, * scott.feldman@intel.com) * Portions Copyright (C) Sun Microsystems 2008 */ #ifndef _LINUX_ETHTOOL_H #define _LINUX_ETHTOOL_H #include <linux/bitmap.h> #include <linux/compat.h> #include <linux/android_kabi.h> #include <uapi/linux/ethtool.h> #ifdef CONFIG_COMPAT struct compat_ethtool_rx_flow_spec { u32 flow_type; union ethtool_flow_union h_u; struct ethtool_flow_ext h_ext; union ethtool_flow_union m_u; struct ethtool_flow_ext m_ext; compat_u64 ring_cookie; u32 location; }; struct compat_ethtool_rxnfc { u32 cmd; u32 flow_type; compat_u64 data; struct compat_ethtool_rx_flow_spec fs; u32 rule_cnt; u32 rule_locs[0]; }; #endif /* CONFIG_COMPAT */ #include <linux/rculist.h> /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated * @ETHTOOL_ID_ACTIVE: Physical ID indicator should be activated * @ETHTOOL_ID_ON: LED should be turned on (used iff %ETHTOOL_ID_ACTIVE * is not supported) * @ETHTOOL_ID_OFF: LED should be turned off (used iff %ETHTOOL_ID_ACTIVE * is not supported) */ enum ethtool_phys_id_state { ETHTOOL_ID_INACTIVE, ETHTOOL_ID_ACTIVE, ETHTOOL_ID_ON, ETHTOOL_ID_OFF }; enum { ETH_RSS_HASH_TOP_BIT, /* Configurable RSS hash function - Toeplitz */ ETH_RSS_HASH_XOR_BIT, /* Configurable RSS hash function - Xor */ ETH_RSS_HASH_CRC32_BIT, /* Configurable RSS hash function - Crc32 */ /* * Add your fresh new hash function bits above and remember to update * rss_hash_func_strings[] in ethtool.c */ ETH_RSS_HASH_FUNCS_COUNT }; #define __ETH_RSS_HASH_BIT(bit) ((u32)1 << (bit)) #define __ETH_RSS_HASH(name) __ETH_RSS_HASH_BIT(ETH_RSS_HASH_##name##_BIT) #define ETH_RSS_HASH_TOP __ETH_RSS_HASH(TOP) #define ETH_RSS_HASH_XOR __ETH_RSS_HASH(XOR) #define ETH_RSS_HASH_CRC32 __ETH_RSS_HASH(CRC32) #define ETH_RSS_HASH_UNKNOWN 0 #define ETH_RSS_HASH_NO_CHANGE 0 struct net_device; /* Some generic methods drivers may use in their ethtool_ops */ u32 ethtool_op_get_link(struct net_device *dev); int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *eti); /** * ethtool_rxfh_indir_default - get default value for RX flow hash indirection * @index: Index in RX flow hash indirection table * @n_rx_rings: Number of RX rings to use * * This function provides the default policy for RX flow hash indirection. */ static inline u32 ethtool_rxfh_indir_default(u32 index, u32 n_rx_rings) { return index % n_rx_rings; } /* declare a link mode bitmap */ #define __ETHTOOL_DECLARE_LINK_MODE_MASK(name) \ DECLARE_BITMAP(name, __ETHTOOL_LINK_MODE_MASK_NBITS) /* drivers must ignore base.cmd and base.link_mode_masks_nwords * fields, but they are allowed to overwrite them (will be ignored). */ struct ethtool_link_ksettings { struct ethtool_link_settings base; struct { __ETHTOOL_DECLARE_LINK_MODE_MASK(supported); __ETHTOOL_DECLARE_LINK_MODE_MASK(advertising); __ETHTOOL_DECLARE_LINK_MODE_MASK(lp_advertising); } link_modes; }; /** * ethtool_link_ksettings_zero_link_mode - clear link_ksettings link mode mask * @ptr : pointer to struct ethtool_link_ksettings * @name : one of supported/advertising/lp_advertising */ #define ethtool_link_ksettings_zero_link_mode(ptr, name) \ bitmap_zero((ptr)->link_modes.name, __ETHTOOL_LINK_MODE_MASK_NBITS) /** * ethtool_link_ksettings_add_link_mode - set bit in link_ksettings * link mode mask * @ptr : pointer to struct ethtool_link_ksettings * @name : one of supported/advertising/lp_advertising * @mode : one of the ETHTOOL_LINK_MODE_*_BIT * (not atomic, no bound checking) */ #define ethtool_link_ksettings_add_link_mode(ptr, name, mode) \ __set_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) /** * ethtool_link_ksettings_del_link_mode - clear bit in link_ksettings * link mode mask * @ptr : pointer to struct ethtool_link_ksettings * @name : one of supported/advertising/lp_advertising * @mode : one of the ETHTOOL_LINK_MODE_*_BIT * (not atomic, no bound checking) */ #define ethtool_link_ksettings_del_link_mode(ptr, name, mode) \ __clear_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) /** * ethtool_link_ksettings_test_link_mode - test bit in ksettings link mode mask * @ptr : pointer to struct ethtool_link_ksettings * @name : one of supported/advertising/lp_advertising * @mode : one of the ETHTOOL_LINK_MODE_*_BIT * (not atomic, no bound checking) * * Returns true/false. */ #define ethtool_link_ksettings_test_link_mode(ptr, name, mode) \ test_bit(ETHTOOL_LINK_MODE_ ## mode ## _BIT, (ptr)->link_modes.name) extern int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings); /** * ethtool_intersect_link_masks - Given two link masks, AND them together * @dst: first mask and where result is stored * @src: second mask to intersect with * * Given two link mode masks, AND them together and save the result in dst. */ void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst, struct ethtool_link_ksettings *src); void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32); /* return false if src had higher bits set. lower bits always updated. */ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, const unsigned long *src); /** * struct ethtool_ops - optional netdev operations * @get_drvinfo: Report driver/device information. Should only set the * @driver, @version, @fw_version and @bus_info fields. If not * implemented, the @driver and @bus_info fields will be filled in * according to the netdev's parent device. * @get_regs_len: Get buffer length required for @get_regs * @get_regs: Get device registers * @get_wol: Report whether Wake-on-Lan is enabled * @set_wol: Turn Wake-on-Lan on or off. Returns a negative error code * or zero. * @get_msglevel: Report driver message level. This should be the value * of the @msg_enable field used by netif logging functions. * @set_msglevel: Set driver message level * @nway_reset: Restart autonegotiation. Returns a negative error code * or zero. * @get_link: Report whether physical link is up. Will only be called if * the netdev is up. Should usually be set to ethtool_op_get_link(), * which uses netif_carrier_ok(). * @get_eeprom: Read data from the device EEPROM. * Should fill in the magic field. Don't need to check len for zero * or wraparound. Fill in the data argument with the eeprom values * from offset to offset + len. Update len to the amount read. * Returns an error or zero. * @set_eeprom: Write data to the device EEPROM. * Should validate the magic field. Don't need to check len for zero * or wraparound. Update len to the amount written. Returns an error * or zero. * @get_coalesce: Get interrupt coalescing parameters. Returns a negative * error code or zero. * @set_coalesce: Set interrupt coalescing parameters. Returns a negative * error code or zero. * @get_ringparam: Report ring sizes * @set_ringparam: Set ring sizes. Returns a negative error code or zero. * @get_pauseparam: Report pause parameters * @set_pauseparam: Set pause parameters. Returns a negative error code * or zero. * @self_test: Run specified self-tests * @get_strings: Return a set of strings that describe the requested objects * @set_phys_id: Identify the physical devices, e.g. by flashing an LED * attached to it. The implementation may update the indicator * asynchronously or synchronously, but in either case it must return * quickly. It is initially called with the argument %ETHTOOL_ID_ACTIVE, * and must either activate asynchronous updates and return zero, return * a negative error or return a positive frequency for synchronous * indication (e.g. 1 for one on/off cycle per second). If it returns * a frequency then it will be called again at intervals with the * argument %ETHTOOL_ID_ON or %ETHTOOL_ID_OFF and should set the state of * the indicator accordingly. Finally, it is called with the argument * %ETHTOOL_ID_INACTIVE and must deactivate the indicator. Returns a * negative error code or zero. * @get_ethtool_stats: Return extended statistics about the device. * This is only useful if the device maintains statistics not * included in &struct rtnl_link_stats64. * @begin: Function to be called before any other operation. Returns a * negative error code or zero. * @complete: Function to be called after any other operation except * @begin. Will be called even if the other operation failed. * @get_priv_flags: Report driver-specific feature flags. * @set_priv_flags: Set driver-specific feature flags. Returns a negative * error code or zero. * @get_sset_count: Get number of strings that @get_strings will write. * @get_rxnfc: Get RX flow classification rules. Returns a negative * error code or zero. * @set_rxnfc: Set RX flow classification rules. Returns a negative * error code or zero. * @flash_device: Write a firmware image to device's flash memory. * Returns a negative error code or zero. * @reset: Reset (part of) the device, as specified by a bitmask of * flags from &enum ethtool_reset_flags. Returns a negative * error code or zero. * @get_rxfh_key_size: Get the size of the RX flow hash key. * Returns zero if not supported for this specific device. * @get_rxfh_indir_size: Get the size of the RX flow hash indirection table. * Returns zero if not supported for this specific device. * @get_rxfh: Get the contents of the RX flow hash indirection table, hash key * and/or hash function. * Returns a negative error code or zero. * @set_rxfh: Set the contents of the RX flow hash indirection table, hash * key, and/or hash function. Arguments which are set to %NULL or zero * will remain unchanged. * Returns a negative error code or zero. An error code must be returned * if at least one unsupported change was requested. * @get_rxfh_context: Get the contents of the RX flow hash indirection table, * hash key, and/or hash function assiciated to the given rss context. * Returns a negative error code or zero. * @set_rxfh_context: Create, remove and configure RSS contexts. Allows setting * the contents of the RX flow hash indirection table, hash key, and/or * hash function associated to the given context. Arguments which are set * to %NULL or zero will remain unchanged. * Returns a negative error code or zero. An error code must be returned * if at least one unsupported change was requested. * @get_channels: Get number of channels. * @set_channels: Set number of channels. Returns a negative error code or * zero. * @get_dump_flag: Get dump flag indicating current dump length, version, * and flag of the device. * @get_dump_data: Get dump data. * @set_dump: Set dump specific flags to the device. * @get_ts_info: Get the time stamping and PTP hardware clock capabilities. * Drivers supporting transmit time stamps in software should set this to * ethtool_op_get_ts_info(). * @get_module_info: Get the size and type of the eeprom contained within * a plug-in module. * @get_module_eeprom: Get the eeprom information from the plug-in module * @get_eee: Get Energy-Efficient (EEE) supported and status. * @set_eee: Set EEE status (enable/disable) as well as LPI timers. * @get_per_queue_coalesce: Get interrupt coalescing parameters per queue. * It must check that the given queue number is valid. If neither a RX nor * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, set the inapplicable fields to ~0 and return 0. * Returns a negative error code or zero. * @set_per_queue_coalesce: Set interrupt coalescing parameters per queue. * It must check that the given queue number is valid. If neither a RX nor * a TX queue has this number, return -EINVAL. If only a RX queue or a TX * queue has this number, ignore the inapplicable fields. * Returns a negative error code or zero. * @get_link_ksettings: Get various device settings including Ethernet link * settings. The %cmd and %link_mode_masks_nwords fields should be * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), * any change to them will be overwritten by kernel. Returns a negative * error code or zero. * @set_link_ksettings: Set various device settings including Ethernet link * settings. The %cmd and %link_mode_masks_nwords fields should be * ignored (use %__ETHTOOL_LINK_MODE_MASK_NBITS instead of the latter), * any change to them will be overwritten by kernel. Returns a negative * error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. * @get_ethtool_phy_stats: Return extended statistics about the PHY device. * This is only useful if the device maintains PHY statistics and * cannot use the standard PHY library helpers. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must * hold the RTNL lock. * * See the structures used by these operations for further documentation. * Note that for all operations using a structure ending with a zero- * length array, the array is allocated separately in the kernel and * is passed to the driver as an additional parameter. * * See &struct net_device and &struct net_device_ops for documentation * of the generic netdev features interface. */ struct ethtool_ops { void (*get_drvinfo)(struct net_device *, struct ethtool_drvinfo *); int (*get_regs_len)(struct net_device *); void (*get_regs)(struct net_device *, struct ethtool_regs *, void *); void (*get_wol)(struct net_device *, struct ethtool_wolinfo *); int (*set_wol)(struct net_device *, struct ethtool_wolinfo *); u32 (*get_msglevel)(struct net_device *); void (*set_msglevel)(struct net_device *, u32); int (*nway_reset)(struct net_device *); u32 (*get_link)(struct net_device *); int (*get_eeprom_len)(struct net_device *); int (*get_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); int (*set_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); int (*get_coalesce)(struct net_device *, struct ethtool_coalesce *); int (*set_coalesce)(struct net_device *, struct ethtool_coalesce *); void (*get_ringparam)(struct net_device *, struct ethtool_ringparam *); int (*set_ringparam)(struct net_device *, struct ethtool_ringparam *); void (*get_pauseparam)(struct net_device *, struct ethtool_pauseparam*); int (*set_pauseparam)(struct net_device *, struct ethtool_pauseparam*); void (*self_test)(struct net_device *, struct ethtool_test *, u64 *); void (*get_strings)(struct net_device *, u32 stringset, u8 *); int (*set_phys_id)(struct net_device *, enum ethtool_phys_id_state); void (*get_ethtool_stats)(struct net_device *, struct ethtool_stats *, u64 *); int (*begin)(struct net_device *); void (*complete)(struct net_device *); u32 (*get_priv_flags)(struct net_device *); int (*set_priv_flags)(struct net_device *, u32); int (*get_sset_count)(struct net_device *, int); int (*get_rxnfc)(struct net_device *, struct ethtool_rxnfc *, u32 *rule_locs); int (*set_rxnfc)(struct net_device *, struct ethtool_rxnfc *); int (*flash_device)(struct net_device *, struct ethtool_flash *); int (*reset)(struct net_device *, u32 *); u32 (*get_rxfh_key_size)(struct net_device *); u32 (*get_rxfh_indir_size)(struct net_device *); int (*get_rxfh)(struct net_device *, u32 *indir, u8 *key, u8 *hfunc); int (*set_rxfh)(struct net_device *, const u32 *indir, const u8 *key, const u8 hfunc); int (*get_rxfh_context)(struct net_device *, u32 *indir, u8 *key, u8 *hfunc, u32 rss_context); int (*set_rxfh_context)(struct net_device *, const u32 *indir, const u8 *key, const u8 hfunc, u32 *rss_context, bool delete); void (*get_channels)(struct net_device *, struct ethtool_channels *); int (*set_channels)(struct net_device *, struct ethtool_channels *); int (*get_dump_flag)(struct net_device *, struct ethtool_dump *); int (*get_dump_data)(struct net_device *, struct ethtool_dump *, void *); int (*set_dump)(struct net_device *, struct ethtool_dump *); int (*get_ts_info)(struct net_device *, struct ethtool_ts_info *); int (*get_module_info)(struct net_device *, struct ethtool_modinfo *); int (*get_module_eeprom)(struct net_device *, struct ethtool_eeprom *, u8 *); int (*get_eee)(struct net_device *, struct ethtool_eee *); int (*set_eee)(struct net_device *, struct ethtool_eee *); int (*get_tunable)(struct net_device *, const struct ethtool_tunable *, void *); int (*set_tunable)(struct net_device *, const struct ethtool_tunable *, const void *); int (*get_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); int (*set_per_queue_coalesce)(struct net_device *, u32, struct ethtool_coalesce *); int (*get_link_ksettings)(struct net_device *, struct ethtool_link_ksettings *); int (*set_link_ksettings)(struct net_device *, const struct ethtool_link_ksettings *); int (*get_fecparam)(struct net_device *, struct ethtool_fecparam *); int (*set_fecparam)(struct net_device *, struct ethtool_fecparam *); void (*get_ethtool_phy_stats)(struct net_device *, struct ethtool_stats *, u64 *); ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; struct ethtool_rx_flow_rule { struct flow_rule *rule; unsigned long priv[0]; }; struct ethtool_rx_flow_spec_input { const struct ethtool_rx_flow_spec *fs; u32 rss_ctx; }; struct ethtool_rx_flow_rule * ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input); void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *rule); #endif /* _LINUX_ETHTOOL_H */ |
| 17 100 4 139 68 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_CPUMASK_H #define __LINUX_CPUMASK_H /* * Cpumasks provide a bitmap suitable for representing the * set of CPU's in a system, one bit position per CPU number. In general, * only nr_cpu_ids (<= NR_CPUS) bits are valid. */ #include <linux/kernel.h> #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/atomic.h> #include <linux/bug.h> /* Don't assign or return these: may not be this big! */ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; /** * cpumask_bits - get the bits in a cpumask * @maskp: the struct cpumask * * * You should only assume nr_cpu_ids bits of this mask are valid. This is * a macro so it's const-correct. */ #define cpumask_bits(maskp) ((maskp)->bits) /** * cpumask_pr_args - printf args to output a cpumask * @maskp: cpumask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a cpumask. */ #define cpumask_pr_args(maskp) nr_cpu_ids, cpumask_bits(maskp) #if NR_CPUS == 1 #define nr_cpu_ids 1U #else extern unsigned int nr_cpu_ids; #endif #ifdef CONFIG_CPUMASK_OFFSTACK /* Assuming NR_CPUS is huge, a runtime limit is more efficient. Also, * not all bits may be allocated. */ #define nr_cpumask_bits nr_cpu_ids #else #define nr_cpumask_bits ((unsigned int)NR_CPUS) #endif /* * The following particular system cpumasks and operations manage * possible, present, active and online cpus. * * cpu_possible_mask- has bit 'cpu' set iff cpu is populatable * cpu_present_mask - has bit 'cpu' set iff cpu is populated * cpu_online_mask - has bit 'cpu' set iff cpu available to scheduler * cpu_active_mask - has bit 'cpu' set iff cpu available to migration * * If !CONFIG_HOTPLUG_CPU, present == possible, and active == online. * * The cpu_possible_mask is fixed at boot time, as the set of CPU id's * that it is possible might ever be plugged in at anytime during the * life of that system boot. The cpu_present_mask is dynamic(*), * representing which CPUs are currently plugged in. And * cpu_online_mask is the dynamic subset of cpu_present_mask, * indicating those CPUs available for scheduling. * * If HOTPLUG is enabled, then cpu_possible_mask is forced to have * all NR_CPUS bits set, otherwise it is just the set of CPUs that * ACPI reports present at boot. * * If HOTPLUG is enabled, then cpu_present_mask varies dynamically, * depending on what ACPI reports as currently plugged in, otherwise * cpu_present_mask is just a copy of cpu_possible_mask. * * (*) Well, cpu_present_mask is dynamic in the hotplug case. If not * hotplug, it's a copy of cpu_possible_mask, hence fixed at boot. * * Subtleties: * 1) UP arch's (NR_CPUS == 1, CONFIG_SMP not defined) hardcode * assumption that their single CPU is online. The UP * cpu_{online,possible,present}_masks are placebos. Changing them * will have no useful affect on the following num_*_cpus() * and cpu_*() macros in the UP case. This ugliness is a UP * optimization - don't waste any instructions or memory references * asking if you're online or how many CPUs there are if there is * only one CPU. */ extern struct cpumask __cpu_possible_mask; extern struct cpumask __cpu_online_mask; extern struct cpumask __cpu_present_mask; extern struct cpumask __cpu_active_mask; #define cpu_possible_mask ((const struct cpumask *)&__cpu_possible_mask) #define cpu_online_mask ((const struct cpumask *)&__cpu_online_mask) #define cpu_present_mask ((const struct cpumask *)&__cpu_present_mask) #define cpu_active_mask ((const struct cpumask *)&__cpu_active_mask) extern atomic_t __num_online_cpus; #if NR_CPUS > 1 /** * num_online_cpus() - Read the number of online CPUs * * Despite the fact that __num_online_cpus is of type atomic_t, this * interface gives only a momentary snapshot and is not protected against * concurrent CPU hotplug operations unless invoked from a cpuhp_lock held * region. */ static inline unsigned int num_online_cpus(void) { return atomic_read(&__num_online_cpus); } #define num_possible_cpus() cpumask_weight(cpu_possible_mask) #define num_present_cpus() cpumask_weight(cpu_present_mask) #define num_active_cpus() cpumask_weight(cpu_active_mask) #define cpu_online(cpu) cpumask_test_cpu((cpu), cpu_online_mask) #define cpu_possible(cpu) cpumask_test_cpu((cpu), cpu_possible_mask) #define cpu_present(cpu) cpumask_test_cpu((cpu), cpu_present_mask) #define cpu_active(cpu) cpumask_test_cpu((cpu), cpu_active_mask) #else #define num_online_cpus() 1U #define num_possible_cpus() 1U #define num_present_cpus() 1U #define num_active_cpus() 1U #define cpu_online(cpu) ((cpu) == 0) #define cpu_possible(cpu) ((cpu) == 0) #define cpu_present(cpu) ((cpu) == 0) #define cpu_active(cpu) ((cpu) == 0) #endif extern cpumask_t cpus_booted_once_mask; static inline void cpu_max_bits_warn(unsigned int cpu, unsigned int bits) { #ifdef CONFIG_DEBUG_PER_CPU_MAPS WARN_ON_ONCE(cpu >= bits); #endif /* CONFIG_DEBUG_PER_CPU_MAPS */ } /* verify cpu argument to cpumask_* operators */ static inline unsigned int cpumask_check(unsigned int cpu) { cpu_max_bits_warn(cpu, nr_cpumask_bits); return cpu; } #if NR_CPUS == 1 /* Uniprocessor. Assume all masks are "1". */ static inline unsigned int cpumask_first(const struct cpumask *srcp) { return 0; } static inline unsigned int cpumask_last(const struct cpumask *srcp) { return 0; } /* Valid inputs for n are -1 and 0. */ static inline unsigned int cpumask_next(int n, const struct cpumask *srcp) { return n+1; } static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { return n+1; } static inline unsigned int cpumask_next_and(int n, const struct cpumask *srcp, const struct cpumask *andp) { return n+1; } static inline unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { /* cpu0 unless stop condition, wrap and at cpu0, then nr_cpumask_bits */ return (wrap && n == 0); } /* cpu must be a valid cpu, ie 0, so there's no other choice. */ static inline unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { return 1; } static inline unsigned int cpumask_local_spread(unsigned int i, int node) { return 0; } #define for_each_cpu(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_not(cpu, mask) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask) #define for_each_cpu_wrap(cpu, mask, start) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask, (void)(start)) #define for_each_cpu_and(cpu, mask1, mask2) \ for ((cpu) = 0; (cpu) < 1; (cpu)++, (void)mask1, (void)mask2) #else /** * cpumask_first - get the first cpu in a cpumask * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no cpus set. */ static inline unsigned int cpumask_first(const struct cpumask *srcp) { return find_first_bit(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_last - get the last CPU in a cpumask * @srcp: - the cpumask pointer * * Returns >= nr_cpumask_bits if no CPUs set. */ static inline unsigned int cpumask_last(const struct cpumask *srcp) { return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits); } unsigned int cpumask_next(int n, const struct cpumask *srcp); /** * cpumask_next_zero - get the next unset cpu in a cpumask * @n: the cpu prior to the place to search (ie. return will be > @n) * @srcp: the cpumask pointer * * Returns >= nr_cpu_ids if no further cpus unset. */ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) { /* -1 is a legal arg here. */ if (n != -1) cpumask_check(n); return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } int cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); int cpumask_any_but(const struct cpumask *mask, unsigned int cpu); unsigned int cpumask_local_spread(unsigned int i, int node); /** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu(cpu, mask) \ for ((cpu) = -1; \ (cpu) = cpumask_next((cpu), (mask)), \ (cpu) < nr_cpu_ids;) /** * for_each_cpu_not - iterate over every cpu in a complemented mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_not(cpu, mask) \ for ((cpu) = -1; \ (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask poiter * @start: the start location * * The implementation does not assume any bit in @mask is set (including @start). * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_wrap(cpu, mask, start) \ for ((cpu) = cpumask_next_wrap((start)-1, (mask), (start), false); \ (cpu) < nr_cpumask_bits; \ (cpu) = cpumask_next_wrap((cpu), (mask), (start), true)) /** * for_each_cpu_and - iterate over every cpu in both masks * @cpu: the (optionally unsigned) integer iterator * @mask1: the first cpumask pointer * @mask2: the second cpumask pointer * * This saves a temporary CPU mask in many places. It is equivalent to: * struct cpumask tmp; * cpumask_and(&tmp, &mask1, &mask2); * for_each_cpu(cpu, &tmp) * ... * * After the loop, cpu is >= nr_cpu_ids. */ #define for_each_cpu_and(cpu, mask1, mask2) \ for ((cpu) = -1; \ (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ (cpu) < nr_cpu_ids;) #endif /* SMP */ #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } #define CPU_BITS_CPU0 \ { \ [0] = 1UL \ } /** * cpumask_set_cpu - set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static inline void cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static inline void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp) { __set_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_clear_cpu - clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @dstp: the cpumask pointer */ static inline void cpumask_clear_cpu(int cpu, struct cpumask *dstp) { clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } static inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) { __clear_bit(cpumask_check(cpu), cpumask_bits(dstp)); } /** * cpumask_test_cpu - test for a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in @cpumask, else returns 0 */ static inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } /** * cpumask_test_and_set_cpu - atomically test and set a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 * * test_and_set_bit wrapper for cpumasks. */ static inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_test_and_clear_cpu - atomically test and clear a cpu in a cpumask * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 * * test_and_clear_bit wrapper for cpumasks. */ static inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } /** * cpumask_setall - set all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static inline void cpumask_setall(struct cpumask *dstp) { bitmap_fill(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_clear - clear all cpus (< nr_cpu_ids) in a cpumask * @dstp: the cpumask pointer */ static inline void cpumask_clear(struct cpumask *dstp) { bitmap_zero(cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_and - *dstp = *src1p & *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * If *@dstp is empty, returns 0, else returns 1 */ static inline int cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_and(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_or - *dstp = *src1p | *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static inline void cpumask_or(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_or(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_xor - *dstp = *src1p ^ *src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input */ static inline void cpumask_xor(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { bitmap_xor(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_andnot - *dstp = *src1p & ~*src2p * @dstp: the cpumask result * @src1p: the first input * @src2p: the second input * * If *@dstp is empty, returns 0, else returns 1 */ static inline int cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_andnot(cpumask_bits(dstp), cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_complement - *dstp = ~*srcp * @dstp: the cpumask result * @srcp: the input to invert */ static inline void cpumask_complement(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_complement(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_equal - *src1p == *src2p * @src1p: the first input * @src2p: the second input */ static inline bool cpumask_equal(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_equal(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_or_equal - *src1p | *src2p == *src3p * @src1p: the first input * @src2p: the second input * @src3p: the third input */ static inline bool cpumask_or_equal(const struct cpumask *src1p, const struct cpumask *src2p, const struct cpumask *src3p) { return bitmap_or_equal(cpumask_bits(src1p), cpumask_bits(src2p), cpumask_bits(src3p), nr_cpumask_bits); } /** * cpumask_intersects - (*src1p & *src2p) != 0 * @src1p: the first input * @src2p: the second input */ static inline bool cpumask_intersects(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_intersects(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_subset - (*src1p & ~*src2p) == 0 * @src1p: the first input * @src2p: the second input * * Returns 1 if *@src1p is a subset of *@src2p, else returns 0 */ static inline int cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), nr_cpumask_bits); } /** * cpumask_empty - *srcp == 0 * @srcp: the cpumask to that all cpus < nr_cpu_ids are clear. */ static inline bool cpumask_empty(const struct cpumask *srcp) { return bitmap_empty(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_full - *srcp == 0xFFFFFFFF... * @srcp: the cpumask to that all cpus < nr_cpu_ids are set. */ static inline bool cpumask_full(const struct cpumask *srcp) { return bitmap_full(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_weight - Count of bits in *srcp * @srcp: the cpumask to count bits (< nr_cpu_ids) in. */ static inline unsigned int cpumask_weight(const struct cpumask *srcp) { return bitmap_weight(cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_shift_right - *dstp = *srcp >> n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static inline void cpumask_shift_right(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_right(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_shift_left - *dstp = *srcp << n * @dstp: the cpumask result * @srcp: the input to shift * @n: the number of bits to shift by */ static inline void cpumask_shift_left(struct cpumask *dstp, const struct cpumask *srcp, int n) { bitmap_shift_left(cpumask_bits(dstp), cpumask_bits(srcp), n, nr_cpumask_bits); } /** * cpumask_copy - *dstp = *srcp * @dstp: the result * @srcp: the input cpumask */ static inline void cpumask_copy(struct cpumask *dstp, const struct cpumask *srcp) { bitmap_copy(cpumask_bits(dstp), cpumask_bits(srcp), nr_cpumask_bits); } /** * cpumask_any - pick a "random" cpu from *srcp * @srcp: the input cpumask * * Returns >= nr_cpu_ids if no cpus set. */ #define cpumask_any(srcp) cpumask_first(srcp) /** * cpumask_first_and - return the first cpu from *srcp1 & *srcp2 * @src1p: the first input * @src2p: the second input * * Returns >= nr_cpu_ids if no cpus set in both. See also cpumask_next_and(). */ #define cpumask_first_and(src1p, src2p) cpumask_next_and(-1, (src1p), (src2p)) /** * cpumask_any_and - pick a "random" cpu from *mask1 & *mask2 * @mask1: the first input cpumask * @mask2: the second input cpumask * * Returns >= nr_cpu_ids if no cpus set. */ #define cpumask_any_and(mask1, mask2) cpumask_first_and((mask1), (mask2)) /** * cpumask_of - the cpumask containing just a given cpu * @cpu: the cpu (<= nr_cpu_ids) */ #define cpumask_of(cpu) (get_cpu_mask(cpu)) /** * cpumask_parse_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpumask_parse_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parse_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parselist_user - extract a cpumask from a user string * @buf: the buffer to extract from * @len: the length of the buffer * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpumask_parselist_user(const char __user *buf, int len, struct cpumask *dstp) { return bitmap_parselist_user(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_parse - extract a cpumask from a string * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpumask_parse(const char *buf, struct cpumask *dstp) { unsigned int len = strchrnul(buf, '\n') - buf; return bitmap_parse(buf, len, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpulist_parse - extract a cpumask from a user string of ranges * @buf: the buffer to extract from * @dstp: the cpumask to set. * * Returns -errno, or 0 for success. */ static inline int cpulist_parse(const char *buf, struct cpumask *dstp) { return bitmap_parselist(buf, cpumask_bits(dstp), nr_cpumask_bits); } /** * cpumask_size - size to allocate for a 'struct cpumask' in bytes */ static inline unsigned int cpumask_size(void) { return bitmap_size(nr_cpumask_bits); } /* * cpumask_var_t: struct cpumask for stack usage. * * Oh, the wicked games we play! In order to make kernel coding a * little more difficult, we typedef cpumask_var_t to an array or a * pointer: doing &mask on an array is a noop, so it still works. * * ie. * cpumask_var_t tmpmask; * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) * return -ENOMEM; * * ... use 'tmpmask' like a normal struct cpumask * ... * * free_cpumask_var(tmpmask); * * * However, one notable exception is there. alloc_cpumask_var() allocates * only nr_cpumask_bits bits (in the other hand, real cpumask_t always has * NR_CPUS bits). Therefore you don't have to dereference cpumask_var_t. * * cpumask_var_t tmpmask; * if (!alloc_cpumask_var(&tmpmask, GFP_KERNEL)) * return -ENOMEM; * * var = *tmpmask; * * This code makes NR_CPUS length memcopy and brings to a memory corruption. * cpumask_copy() provide safe copy functionality. * * Note that there is another evil here: If you define a cpumask_var_t * as a percpu variable then the way to obtain the address of the cpumask * structure differently influences what this_cpu_* operation needs to be * used. Please use this_cpu_cpumask_var_t in those cases. The direct use * of this_cpu_ptr() or this_cpu_read() will lead to failures when the * other type of cpumask_var_t implementation is configured. * * Please also note that __cpumask_var_read_mostly can be used to declare * a cpumask_var_t variable itself (not its content) as read mostly. */ #ifdef CONFIG_CPUMASK_OFFSTACK typedef struct cpumask *cpumask_var_t; #define this_cpu_cpumask_var_ptr(x) this_cpu_read(x) #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); static inline bool cpumask_available(cpumask_var_t mask) { return mask != NULL; } #else typedef struct cpumask cpumask_var_t[1]; #define this_cpu_cpumask_var_ptr(x) this_cpu_ptr(x) #define __cpumask_var_read_mostly static inline bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { return true; } static inline bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { return true; } static inline bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) { cpumask_clear(*mask); return true; } static inline bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) { cpumask_clear(*mask); return true; } static inline void alloc_bootmem_cpumask_var(cpumask_var_t *mask) { } static inline void free_cpumask_var(cpumask_var_t mask) { } static inline void free_bootmem_cpumask_var(cpumask_var_t mask) { } static inline bool cpumask_available(cpumask_var_t mask) { return true; } #endif /* CONFIG_CPUMASK_OFFSTACK */ /* It's common to want to use cpu_all_mask in struct member initializers, * so it has to refer to an address rather than a pointer. */ extern const DECLARE_BITMAP(cpu_all_bits, NR_CPUS); #define cpu_all_mask to_cpumask(cpu_all_bits) /* First bits of cpu_bit_bitmap are in fact unset. */ #define cpu_none_mask to_cpumask(cpu_bit_bitmap[0]) #define for_each_possible_cpu(cpu) for_each_cpu((cpu), cpu_possible_mask) #define for_each_online_cpu(cpu) for_each_cpu((cpu), cpu_online_mask) #define for_each_present_cpu(cpu) for_each_cpu((cpu), cpu_present_mask) /* Wrappers for arch boot code to manipulate normally-constant masks */ void init_cpu_present(const struct cpumask *src); void init_cpu_possible(const struct cpumask *src); void init_cpu_online(const struct cpumask *src); static inline void reset_cpu_possible_mask(void) { bitmap_zero(cpumask_bits(&__cpu_possible_mask), NR_CPUS); } static inline void set_cpu_possible(unsigned int cpu, bool possible) { if (possible) cpumask_set_cpu(cpu, &__cpu_possible_mask); else cpumask_clear_cpu(cpu, &__cpu_possible_mask); } static inline void set_cpu_present(unsigned int cpu, bool present) { if (present) cpumask_set_cpu(cpu, &__cpu_present_mask); else cpumask_clear_cpu(cpu, &__cpu_present_mask); } void set_cpu_online(unsigned int cpu, bool online); static inline void set_cpu_active(unsigned int cpu, bool active) { if (active) cpumask_set_cpu(cpu, &__cpu_active_mask); else cpumask_clear_cpu(cpu, &__cpu_active_mask); } /** * to_cpumask - convert an NR_CPUS bitmap to a struct cpumask * * @bitmap: the bitmap * * There are a few places where cpumask_var_t isn't appropriate and * static cpumasks must be used (eg. very early boot), yet we don't * expose the definition of 'struct cpumask'. * * This does the conversion, and can be used as a constant initializer. */ #define to_cpumask(bitmap) \ ((struct cpumask *)(1 ? (bitmap) \ : (void *)sizeof(__check_is_bitmap(bitmap)))) static inline int __check_is_bitmap(const unsigned long *bitmap) { return 1; } /* * Special-case data structure for "single bit set only" constant CPU masks. * * We pre-generate all the 64 (or 32) possible bit positions, with enough * padding to the left and the right, and return the constant pointer * appropriately offset. */ extern const unsigned long cpu_bit_bitmap[BITS_PER_LONG+1][BITS_TO_LONGS(NR_CPUS)]; static inline const struct cpumask *get_cpu_mask(unsigned int cpu) { const unsigned long *p = cpu_bit_bitmap[1 + cpu % BITS_PER_LONG]; p -= cpu / BITS_PER_LONG; return to_cpumask(p); } #define cpu_is_offline(cpu) unlikely(!cpu_online(cpu)) #if NR_CPUS <= BITS_PER_LONG #define CPU_BITS_ALL \ { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #else /* NR_CPUS > BITS_PER_LONG */ #define CPU_BITS_ALL \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } #endif /* NR_CPUS > BITS_PER_LONG */ /** * cpumap_print_to_pagebuf - copies the cpumask into the buffer either * as comma-separated list of cpus or hex values of cpumask * @list: indicates whether the cpumap must be list * @mask: the cpumask to copy * @buf: the buffer to copy into * * Returns the length of the (null-terminated) @buf string, zero if * nothing is copied. */ static inline ssize_t cpumap_print_to_pagebuf(bool list, char *buf, const struct cpumask *mask) { return bitmap_print_to_pagebuf(list, buf, cpumask_bits(mask), nr_cpu_ids); } #if NR_CPUS <= BITS_PER_LONG #define CPU_MASK_ALL \ (cpumask_t) { { \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #else #define CPU_MASK_ALL \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-2] = ~0UL, \ [BITS_TO_LONGS(NR_CPUS)-1] = BITMAP_LAST_WORD_MASK(NR_CPUS) \ } } #endif /* NR_CPUS > BITS_PER_LONG */ #define CPU_MASK_NONE \ (cpumask_t) { { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ } } #define CPU_MASK_CPU0 \ (cpumask_t) { { \ [0] = 1UL \ } } #endif /* __LINUX_CPUMASK_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 | /* SPDX-License-Identifier: GPL-2.0 */ /* * bvec iterator * * Copyright (C) 2001 Ming Lei <ming.lei@canonical.com> */ #ifndef __LINUX_BVEC_ITER_H #define __LINUX_BVEC_ITER_H #include <linux/kernel.h> #include <linux/bug.h> #include <linux/errno.h> #include <linux/mm.h> /* * was unsigned short, but we might as well be ready for > 64kB I/O pages */ struct bio_vec { struct page *bv_page; unsigned int bv_len; unsigned int bv_offset; }; struct bvec_iter { sector_t bi_sector; /* device address in 512 byte sectors */ unsigned int bi_size; /* residual I/O count */ unsigned int bi_idx; /* current index into bvl_vec */ unsigned int bi_bvec_done; /* number of bytes completed in current bvec */ }; struct bvec_iter_all { struct bio_vec bv; int idx; unsigned done; }; /* * various member access, note that bio_data should of course not be used * on highmem page vectors */ #define __bvec_iter_bvec(bvec, iter) (&(bvec)[(iter).bi_idx]) /* multi-page (mp_bvec) helpers */ #define mp_bvec_iter_page(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_page) #define mp_bvec_iter_len(bvec, iter) \ min((iter).bi_size, \ __bvec_iter_bvec((bvec), (iter))->bv_len - (iter).bi_bvec_done) #define mp_bvec_iter_offset(bvec, iter) \ (__bvec_iter_bvec((bvec), (iter))->bv_offset + (iter).bi_bvec_done) #define mp_bvec_iter_page_idx(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) / PAGE_SIZE) #define mp_bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = mp_bvec_iter_page((bvec), (iter)), \ .bv_len = mp_bvec_iter_len((bvec), (iter)), \ .bv_offset = mp_bvec_iter_offset((bvec), (iter)), \ }) /* For building single-page bvec in flight */ #define bvec_iter_offset(bvec, iter) \ (mp_bvec_iter_offset((bvec), (iter)) % PAGE_SIZE) #define bvec_iter_len(bvec, iter) \ min_t(unsigned, mp_bvec_iter_len((bvec), (iter)), \ PAGE_SIZE - bvec_iter_offset((bvec), (iter))) #define bvec_iter_page(bvec, iter) \ (mp_bvec_iter_page((bvec), (iter)) + \ mp_bvec_iter_page_idx((bvec), (iter))) #define bvec_iter_bvec(bvec, iter) \ ((struct bio_vec) { \ .bv_page = bvec_iter_page((bvec), (iter)), \ .bv_len = bvec_iter_len((bvec), (iter)), \ .bv_offset = bvec_iter_offset((bvec), (iter)), \ }) static inline bool bvec_iter_advance(const struct bio_vec *bv, struct bvec_iter *iter, unsigned bytes) { if (WARN_ONCE(bytes > iter->bi_size, "Attempted to advance past end of bvec iter\n")) { iter->bi_size = 0; return false; } while (bytes) { const struct bio_vec *cur = bv + iter->bi_idx; unsigned len = min3(bytes, iter->bi_size, cur->bv_len - iter->bi_bvec_done); bytes -= len; iter->bi_size -= len; iter->bi_bvec_done += len; if (iter->bi_bvec_done == cur->bv_len) { iter->bi_bvec_done = 0; iter->bi_idx++; } } return true; } static inline void bvec_iter_skip_zero_bvec(struct bvec_iter *iter) { iter->bi_bvec_done = 0; iter->bi_idx++; } #define for_each_bvec(bvl, bio_vec, iter, start) \ for (iter = (start); \ (iter).bi_size && \ ((bvl = bvec_iter_bvec((bio_vec), (iter))), 1); \ (bvl).bv_len ? (void)bvec_iter_advance((bio_vec), &(iter), \ (bvl).bv_len) : bvec_iter_skip_zero_bvec(&(iter))) /* for iterating one bio from start to end */ #define BVEC_ITER_ALL_INIT (struct bvec_iter) \ { \ .bi_sector = 0, \ .bi_size = UINT_MAX, \ .bi_idx = 0, \ .bi_bvec_done = 0, \ } static inline struct bio_vec *bvec_init_iter_all(struct bvec_iter_all *iter_all) { iter_all->done = 0; iter_all->idx = 0; return &iter_all->bv; } static inline void bvec_advance(const struct bio_vec *bvec, struct bvec_iter_all *iter_all) { struct bio_vec *bv = &iter_all->bv; if (iter_all->done) { bv->bv_page++; bv->bv_offset = 0; } else { bv->bv_page = bvec->bv_page + (bvec->bv_offset >> PAGE_SHIFT); bv->bv_offset = bvec->bv_offset & ~PAGE_MASK; } bv->bv_len = min_t(unsigned int, PAGE_SIZE - bv->bv_offset, bvec->bv_len - iter_all->done); iter_all->done += bv->bv_len; if (iter_all->done == bvec->bv_len) { iter_all->idx++; iter_all->done = 0; } } /* * Get the last single-page segment from the multi-page bvec and store it * in @seg */ static inline void mp_bvec_last_segment(const struct bio_vec *bvec, struct bio_vec *seg) { unsigned total = bvec->bv_offset + bvec->bv_len; unsigned last_page = (total - 1) / PAGE_SIZE; seg->bv_page = bvec->bv_page + last_page; /* the whole segment is inside the last page */ if (bvec->bv_offset >= last_page * PAGE_SIZE) { seg->bv_offset = bvec->bv_offset % PAGE_SIZE; seg->bv_len = bvec->bv_len; } else { seg->bv_offset = 0; seg->bv_len = total - last_page * PAGE_SIZE; } } #endif /* __LINUX_BVEC_ITER_H */ |
| 9194 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_X86_BARRIER_H #define _ASM_X86_BARRIER_H #include <asm/alternative.h> #include <asm/nops.h> /* * Force strict CPU ordering. * And yes, this might be required on UP too when we're talking * to devices. */ #ifdef CONFIG_X86_32 #define mb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "mfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #define rmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "lfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #define wmb() asm volatile(ALTERNATIVE("lock; addl $0,-4(%%esp)", "sfence", \ X86_FEATURE_XMM2) ::: "memory", "cc") #else #define mb() asm volatile("mfence":::"memory") #define rmb() asm volatile("lfence":::"memory") #define wmb() asm volatile("sfence" ::: "memory") #endif /** * array_index_mask_nospec() - generate a mask that is ~0UL when the * bounds check succeeds and 0 otherwise * @index: array element index * @size: number of elements in array * * Returns: * 0 - (index < size) */ static inline unsigned long array_index_mask_nospec(unsigned long index, unsigned long size) { unsigned long mask; asm volatile ("cmp %1,%2; sbb %0,%0;" :"=r" (mask) :"g"(size),"r" (index) :"cc"); return mask; } /* Override the default implementation from linux/nospec.h. */ #define array_index_mask_nospec array_index_mask_nospec /* Prevent speculative execution past this barrier. */ #define barrier_nospec() alternative("", "lfence", X86_FEATURE_LFENCE_RDTSC) #define dma_rmb() barrier() #define dma_wmb() barrier() #ifdef CONFIG_X86_32 #define __smp_mb() asm volatile("lock; addl $0,-4(%%esp)" ::: "memory", "cc") #else #define __smp_mb() asm volatile("lock; addl $0,-4(%%rsp)" ::: "memory", "cc") #endif #define __smp_rmb() dma_rmb() #define __smp_wmb() barrier() #define __smp_store_mb(var, value) do { (void)xchg(&var, value); } while (0) #define __smp_store_release(p, v) \ do { \ compiletime_assert_atomic_type(*p); \ barrier(); \ WRITE_ONCE(*p, v); \ } while (0) #define __smp_load_acquire(p) \ ({ \ typeof(*p) ___p1 = READ_ONCE(*p); \ compiletime_assert_atomic_type(*p); \ barrier(); \ ___p1; \ }) /* Atomic operations are already serializing on x86 */ #define __smp_mb__before_atomic() do { } while (0) #define __smp_mb__after_atomic() do { } while (0) #include <asm-generic/barrier.h> /* * Make previous memory operations globally visible before * a WRMSR. * * MFENCE makes writes visible, but only affects load/store * instructions. WRMSR is unfortunately not a load/store * instruction and is unaffected by MFENCE. The LFENCE ensures * that the WRMSR is not reordered. * * Most WRMSRs are full serializing instructions themselves and * do not require this barrier. This is only required for the * IA32_TSC_DEADLINE and X2APIC MSRs. */ static inline void weak_wrmsr_fence(void) { asm volatile("mfence; lfence" : : : "memory"); } #endif /* _ASM_X86_BARRIER_H */ |
| 115 115 115 115 471 472 472 471 5 175 175 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 | // SPDX-License-Identifier: GPL-2.0-only /* net/core/xdp.c * * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc. */ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/types.h> #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> #include <net/page_pool.h> #include <net/xdp.h> #include <net/xdp_priv.h> /* struct xdp_mem_allocator */ #include <trace/events/xdp.h> #define REG_STATE_NEW 0x0 #define REG_STATE_REGISTERED 0x1 #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 static DEFINE_IDA(mem_id_pool); static DEFINE_MUTEX(mem_id_lock); #define MEM_ID_MAX 0xFFFE #define MEM_ID_MIN 1 static int mem_id_next = MEM_ID_MIN; static bool mem_id_init; /* false */ static struct rhashtable *mem_id_ht; static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) { const u32 *k = data; const u32 key = *k; BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) != sizeof(u32)); /* Use cyclic increasing ID as direct hash key */ return key; } static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xdp_mem_allocator *xa = ptr; u32 mem_id = *(u32 *)arg->key; return xa->mem.id != mem_id; } static const struct rhashtable_params mem_id_rht_params = { .nelem_hint = 64, .head_offset = offsetof(struct xdp_mem_allocator, node), .key_offset = offsetof(struct xdp_mem_allocator, mem.id), .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), .max_size = MEM_ID_MAX, .min_size = 8, .automatic_shrinking = true, .hashfn = xdp_mem_id_hashfn, .obj_cmpfn = xdp_mem_id_cmp, }; static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) { struct xdp_mem_allocator *xa; xa = container_of(rcu, struct xdp_mem_allocator, rcu); /* Allow this ID to be reused */ ida_simple_remove(&mem_id_pool, xa->mem.id); /* Poison memory */ xa->mem.id = 0xFFFF; xa->mem.type = 0xF0F0; xa->allocator = (void *)0xDEAD9001; kfree(xa); } static void mem_xa_remove(struct xdp_mem_allocator *xa) { trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); } static void mem_allocator_disconnect(void *allocator) { struct xdp_mem_allocator *xa; struct rhashtable_iter iter; mutex_lock(&mem_id_lock); rhashtable_walk_enter(mem_id_ht, &iter); do { rhashtable_walk_start(&iter); while ((xa = rhashtable_walk_next(&iter)) && !IS_ERR(xa)) { if (xa->allocator == allocator) mem_xa_remove(xa); } rhashtable_walk_stop(&iter); } while (xa == ERR_PTR(-EAGAIN)); rhashtable_walk_exit(&iter); mutex_unlock(&mem_id_lock); } static void mem_id_disconnect(int id) { struct xdp_mem_allocator *xa; mutex_lock(&mem_id_lock); xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params); if (!xa) { mutex_unlock(&mem_id_lock); WARN(1, "Request remove non-existing id(%d), driver bug?", id); return; } trace_mem_disconnect(xa); if (!rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params)) call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); mutex_unlock(&mem_id_lock); } void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) { struct xdp_mem_allocator *xa; int id = xdp_rxq->mem.id; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return; } if (id == 0) return; if (xdp_rxq->mem.type == MEM_TYPE_ZERO_COPY) return mem_id_disconnect(id); if (xdp_rxq->mem.type == MEM_TYPE_PAGE_POOL) { rcu_read_lock(); xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); page_pool_destroy(xa->page_pool); rcu_read_unlock(); } } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg_mem_model); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ if (xdp_rxq->reg_state == REG_STATE_UNUSED) return; WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); xdp_rxq_info_unreg_mem_model(xdp_rxq); xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; /* Reset mem info to defaults */ xdp_rxq->mem.id = 0; xdp_rxq->mem.type = 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq) { memset(xdp_rxq, 0, sizeof(*xdp_rxq)); } /* Returns 0 on success, negative on failure */ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index) { if (xdp_rxq->reg_state == REG_STATE_UNUSED) { WARN(1, "Driver promised not to register this"); return -EINVAL; } if (xdp_rxq->reg_state == REG_STATE_REGISTERED) { WARN(1, "Missing unregister, handled but fix driver"); xdp_rxq_info_unreg(xdp_rxq); } if (!dev) { WARN(1, "Missing net_device from driver"); return -ENODEV; } /* State either UNREGISTERED or NEW */ xdp_rxq_info_init(xdp_rxq); xdp_rxq->dev = dev; xdp_rxq->queue_index = queue_index; xdp_rxq->reg_state = REG_STATE_REGISTERED; return 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq) { xdp_rxq->reg_state = REG_STATE_UNUSED; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unused); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) { return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); static int __mem_id_init_hash_table(void) { struct rhashtable *rht; int ret; if (unlikely(mem_id_init)) return 0; rht = kzalloc(sizeof(*rht), GFP_KERNEL); if (!rht) return -ENOMEM; ret = rhashtable_init(rht, &mem_id_rht_params); if (ret < 0) { kfree(rht); return ret; } mem_id_ht = rht; smp_mb(); /* mutex lock should provide enough pairing */ mem_id_init = true; return 0; } /* Allocate a cyclic ID that maps to allocator pointer. * See: https://www.kernel.org/doc/html/latest/core-api/idr.html * * Caller must lock mem_id_lock. */ static int __mem_id_cyclic_get(gfp_t gfp) { int retries = 1; int id; again: id = ida_simple_get(&mem_id_pool, mem_id_next, MEM_ID_MAX, gfp); if (id < 0) { if (id == -ENOSPC) { /* Cyclic allocator, reset next id */ if (retries--) { mem_id_next = MEM_ID_MIN; goto again; } } return id; /* errno */ } mem_id_next = id + 1; return id; } static bool __is_supported_mem_type(enum xdp_mem_type type) { if (type == MEM_TYPE_PAGE_POOL) return is_page_pool_compiled_in(); if (type >= MEM_TYPE_MAX) return false; return true; } int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, enum xdp_mem_type type, void *allocator) { struct xdp_mem_allocator *xdp_alloc; gfp_t gfp = GFP_KERNEL; int id, errno, ret; void *ptr; if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { WARN(1, "Missing register, driver bug"); return -EFAULT; } if (!__is_supported_mem_type(type)) return -EOPNOTSUPP; xdp_rxq->mem.type = type; if (!allocator) { if (type == MEM_TYPE_PAGE_POOL || type == MEM_TYPE_ZERO_COPY) return -EINVAL; /* Setup time check page_pool req */ return 0; } /* Delay init of rhashtable to save memory if feature isn't used */ if (!mem_id_init) { mutex_lock(&mem_id_lock); ret = __mem_id_init_hash_table(); mutex_unlock(&mem_id_lock); if (ret < 0) { WARN_ON(1); return ret; } } xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); if (!xdp_alloc) return -ENOMEM; mutex_lock(&mem_id_lock); id = __mem_id_cyclic_get(gfp); if (id < 0) { errno = id; goto err; } xdp_rxq->mem.id = id; xdp_alloc->mem = xdp_rxq->mem; xdp_alloc->allocator = allocator; /* Insert allocator into ID lookup table */ ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); if (IS_ERR(ptr)) { ida_simple_remove(&mem_id_pool, xdp_rxq->mem.id); xdp_rxq->mem.id = 0; errno = PTR_ERR(ptr); goto err; } if (type == MEM_TYPE_PAGE_POOL) page_pool_use_xdp_mem(allocator, mem_allocator_disconnect); mutex_unlock(&mem_id_lock); trace_mem_connect(xdp_alloc, xdp_rxq); return 0; err: mutex_unlock(&mem_id_lock); kfree(xdp_alloc); return errno; } EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); /* XDP RX runs under NAPI protection, and in different delivery error * scenarios (e.g. queue full), it is possible to return the xdp_frame * while still leveraging this protection. The @napi_direct boolian * is used for those calls sites. Thus, allowing for faster recycling * of xdp_frames/pages in those cases. */ static void __xdp_return(void *data, struct xdp_mem_info *mem, bool napi_direct, unsigned long handle) { struct xdp_mem_allocator *xa; struct page *page; switch (mem->type) { case MEM_TYPE_PAGE_POOL: rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); napi_direct &= !xdp_return_frame_no_direct(); page_pool_put_page(xa->page_pool, page, napi_direct); rcu_read_unlock(); break; case MEM_TYPE_PAGE_SHARED: page_frag_free(data); break; case MEM_TYPE_PAGE_ORDER0: page = virt_to_page(data); /* Assumes order0 page*/ put_page(page); break; case MEM_TYPE_ZERO_COPY: /* NB! Only valid from an xdp_buff! */ rcu_read_lock(); /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); xa->zc_alloc->free(xa->zc_alloc, handle); rcu_read_unlock(); default: /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ break; } } void xdp_return_frame(struct xdp_frame *xdpf) { __xdp_return(xdpf->data, &xdpf->mem, false, 0); } EXPORT_SYMBOL_GPL(xdp_return_frame); void xdp_return_frame_rx_napi(struct xdp_frame *xdpf) { __xdp_return(xdpf->data, &xdpf->mem, true, 0); } EXPORT_SYMBOL_GPL(xdp_return_frame_rx_napi); void xdp_return_buff(struct xdp_buff *xdp) { __xdp_return(xdp->data, &xdp->rxq->mem, true, xdp->handle); } EXPORT_SYMBOL_GPL(xdp_return_buff); /* Only called for MEM_TYPE_PAGE_POOL see xdp.h */ void __xdp_release_frame(void *data, struct xdp_mem_info *mem) { struct xdp_mem_allocator *xa; struct page *page; rcu_read_lock(); xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); page = virt_to_head_page(data); if (xa) page_pool_release_page(xa->page_pool, page); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(__xdp_release_frame); int xdp_attachment_query(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { bpf->prog_id = info->prog ? info->prog->aux->id : 0; bpf->prog_flags = info->prog ? info->flags : 0; return 0; } EXPORT_SYMBOL_GPL(xdp_attachment_query); bool xdp_attachment_flags_ok(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog && (bpf->flags ^ info->flags) & XDP_FLAGS_MODES) { NL_SET_ERR_MSG(bpf->extack, "program loaded with different flags"); return false; } return true; } EXPORT_SYMBOL_GPL(xdp_attachment_flags_ok); void xdp_attachment_setup(struct xdp_attachment_info *info, struct netdev_bpf *bpf) { if (info->prog) bpf_prog_put(info->prog); info->prog = bpf->prog; info->flags = bpf->flags; } EXPORT_SYMBOL_GPL(xdp_attachment_setup); struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp) { unsigned int metasize, totsize; void *addr, *data_to_copy; struct xdp_frame *xdpf; struct page *page; /* Clone into a MEM_TYPE_PAGE_ORDER0 xdp_frame. */ metasize = xdp_data_meta_unsupported(xdp) ? 0 : xdp->data - xdp->data_meta; totsize = xdp->data_end - xdp->data + metasize; if (sizeof(*xdpf) + totsize > PAGE_SIZE) return NULL; page = dev_alloc_page(); if (!page) return NULL; addr = page_to_virt(page); xdpf = addr; memset(xdpf, 0, sizeof(*xdpf)); addr += sizeof(*xdpf); data_to_copy = metasize ? xdp->data_meta : xdp->data; memcpy(addr, data_to_copy, totsize); xdpf->data = addr + metasize; xdpf->len = totsize - metasize; xdpf->headroom = 0; xdpf->metasize = metasize; xdpf->mem.type = MEM_TYPE_PAGE_ORDER0; xdp_return_buff(xdp); return xdpf; } EXPORT_SYMBOL_GPL(xdp_convert_zc_to_xdp_frame); |
| 2213 662 1909 288 30 174 308 158 103 3 1046 646 22 22 22 33 33 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_RCULIST_H #define _LINUX_RCULIST_H #ifdef __KERNEL__ /* * RCU-protected list version */ #include <linux/list.h> #include <linux/rcupdate.h> /* * Why is there no list_empty_rcu()? Because list_empty() serves this * purpose. The list_empty() function fetches the RCU-protected pointer * and compares it to the address of the list head, but neither dereferences * this pointer itself nor provides this pointer to the caller. Therefore, * it is not necessary to use rcu_dereference(), so that list_empty() can * be used anywhere you would want to use a list_empty_rcu(). */ /* * INIT_LIST_HEAD_RCU - Initialize a list_head visible to RCU readers * @list: list to be initialized * * You should instead use INIT_LIST_HEAD() for normal initialization and * cleanup tasks, when readers have no access to the list being initialized. * However, if the list being initialized is visible to readers, you * need to keep the compiler from being too mischievous. */ static inline void INIT_LIST_HEAD_RCU(struct list_head *list) { WRITE_ONCE(list->next, list); WRITE_ONCE(list->prev, list); } /* * return the ->next pointer of a list_head in an rcu safe * way, we must not access it directly */ #define list_next_rcu(list) (*((struct list_head __rcu **)(&(list)->next))) /* * Check during list traversal that we are within an RCU reader */ #define check_arg_count_one(dummy) #ifdef CONFIG_PROVE_RCU_LIST #define __list_check_rcu(dummy, cond, extra...) \ ({ \ check_arg_count_one(extra); \ RCU_LOCKDEP_WARN(!cond && !rcu_read_lock_any_held(), \ "RCU-list traversed in non-reader section!"); \ }) #else #define __list_check_rcu(dummy, cond, extra...) \ ({ check_arg_count_one(extra); }) #endif /* * Insert a new entry between two known consecutive entries. * * This is only for internal list manipulation where we know * the prev/next entries already! */ static inline void __list_add_rcu(struct list_head *new, struct list_head *prev, struct list_head *next) { if (!__list_add_valid(new, prev, next)) return; new->next = next; new->prev = prev; rcu_assign_pointer(list_next_rcu(prev), new); next->prev = new; } /** * list_add_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it after * * Insert a new entry after the specified head. * This is good for implementing stacks. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head, head->next); } /** * list_add_tail_rcu - add a new entry to rcu-protected list * @new: new entry to be added * @head: list head to add it before * * Insert a new entry before the specified head. * This is useful for implementing queues. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_add_tail_rcu() * or list_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). */ static inline void list_add_tail_rcu(struct list_head *new, struct list_head *head) { __list_add_rcu(new, head->prev, head); } /** * list_del_rcu - deletes entry from list without re-initialization * @entry: the element to delete from the list. * * Note: list_empty() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as list_del_rcu() * or list_add_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * list_for_each_entry_rcu(). * * Note that the caller is not permitted to immediately free * the newly deleted entry. Instead, either synchronize_rcu() * or call_rcu() must be used to defer freeing until an RCU * grace period has elapsed. */ static inline void list_del_rcu(struct list_head *entry) { __list_del_entry(entry); entry->prev = LIST_POISON2; } /** * hlist_del_init_rcu - deletes entry from hash list with re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on the node return true after this. It is * useful for RCU based read lockfree traversal if the writer side * must know if the list entry is still hashed or already unhashed. * * In particular, it means that we can not poison the forward pointers * that may still be used for walking the hash list and we can only * zero the pprev pointer so list_unhashed() will return true after * this. * * The caller must take whatever precautions are necessary (such as * holding appropriate locks) to avoid racing with another * list-mutation primitive, such as hlist_add_head_rcu() or * hlist_del_rcu(), running on this same list. However, it is * perfectly legal to run concurrently with the _rcu list-traversal * primitives, such as hlist_for_each_entry_rcu(). */ static inline void hlist_del_init_rcu(struct hlist_node *n) { if (!hlist_unhashed(n)) { __hlist_del(n); n->pprev = NULL; } } /** * list_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. * Note: @old should not be empty. */ static inline void list_replace_rcu(struct list_head *old, struct list_head *new) { new->next = old->next; new->prev = old->prev; rcu_assign_pointer(list_next_rcu(new->prev), new); new->next->prev = new; old->prev = LIST_POISON2; } /** * __list_splice_init_rcu - join an RCU-protected list into an existing list. * @list: the RCU-protected list to splice * @prev: points to the last element of the existing list * @next: points to the first element of the existing list * @sync: synchronize_rcu, synchronize_rcu_expedited, ... * * The list pointed to by @prev and @next can be RCU-read traversed * concurrently with this function. * * Note that this function blocks. * * Important note: the caller must take whatever action is necessary to prevent * any other updates to the existing list. In principle, it is possible to * modify the list as soon as sync() begins execution. If this sort of thing * becomes necessary, an alternative version based on call_rcu() could be * created. But only if -really- needed -- there is no shortage of RCU API * members. */ static inline void __list_splice_init_rcu(struct list_head *list, struct list_head *prev, struct list_head *next, void (*sync)(void)) { struct list_head *first = list->next; struct list_head *last = list->prev; /* * "first" and "last" tracking list, so initialize it. RCU readers * have access to this list, so we must use INIT_LIST_HEAD_RCU() * instead of INIT_LIST_HEAD(). */ INIT_LIST_HEAD_RCU(list); /* * At this point, the list body still points to the source list. * Wait for any readers to finish using the list before splicing * the list body into the new list. Any new readers will see * an empty list. */ sync(); /* * Readers are finished with the source list, so perform splice. * The order is important if the new list is global and accessible * to concurrent RCU readers. Note that RCU readers are not * permitted to traverse the prev pointers without excluding * this function. */ last->next = next; rcu_assign_pointer(list_next_rcu(prev), first); first->prev = prev; next->prev = last; } /** * list_splice_init_rcu - splice an RCU-protected list into an existing list, * designed for stacks. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head, head->next, sync); } /** * list_splice_tail_init_rcu - splice an RCU-protected list into an existing * list, designed for queues. * @list: the RCU-protected list to splice * @head: the place in the existing list to splice the first list into * @sync: synchronize_rcu, synchronize_rcu_expedited, ... */ static inline void list_splice_tail_init_rcu(struct list_head *list, struct list_head *head, void (*sync)(void)) { if (!list_empty(list)) __list_splice_init_rcu(list, head->prev, head, sync); } /** * list_entry_rcu - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_entry_rcu(ptr, type, member) \ container_of(READ_ONCE(ptr), type, member) /* * Where are list_empty_rcu() and list_first_entry_rcu()? * * Implementing those functions following their counterparts list_empty() and * list_first_entry() is not advisable because they lead to subtle race * conditions as the following snippet shows: * * if (!list_empty_rcu(mylist)) { * struct foo *bar = list_first_entry_rcu(mylist, struct foo, list_member); * do_something(bar); * } * * The list may not be empty when list_empty_rcu checks it, but it may be when * list_first_entry_rcu rereads the ->next pointer. * * Rereading the ->next pointer is not a problem for list_empty() and * list_first_entry() because they would be protected by a lock that blocks * writers. * * See list_first_or_null_rcu for an alternative. */ /** * list_first_or_null_rcu - get the first element from a list * @ptr: the list head to take the element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the list is empty, it returns NULL. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_first_or_null_rcu(ptr, type, member) \ ({ \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__ptr != __next) ? list_entry_rcu(__next, type, member) : NULL; \ }) /** * list_next_or_null_rcu - get the first element from a list * @head: the head for the list. * @ptr: the list head to take the next element from. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * Note that if the ptr is at the end of the list, NULL is returned. * * This primitive may safely run concurrently with the _rcu list-mutation * primitives such as list_add_rcu() as long as it's guarded by rcu_read_lock(). */ #define list_next_or_null_rcu(head, ptr, type, member) \ ({ \ struct list_head *__head = (head); \ struct list_head *__ptr = (ptr); \ struct list_head *__next = READ_ONCE(__ptr->next); \ likely(__next != __head) ? list_entry_rcu(__next, type, \ member) : NULL; \ }) /** * list_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as list_add_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define list_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = list_entry_rcu((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_entry_lockless - get the struct for this entry * @ptr: the &struct list_head pointer. * @type: the type of the struct this is embedded in. * @member: the name of the list_head within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_entry_lockless(ptr, type, member) \ container_of((typeof(ptr))READ_ONCE(ptr), type, member) /** * list_for_each_entry_lockless - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_struct within the struct. * * This primitive may safely run concurrently with the _rcu * list-mutation primitives such as list_add_rcu(), but requires some * implicit RCU read-side guarding. One example is running within a special * exception-time environment where preemption is disabled and where lockdep * cannot be invoked. Another example is when items are added to the list, * but never deleted. */ #define list_for_each_entry_lockless(pos, head, member) \ for (pos = list_entry_lockless((head)->next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_lockless(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_continue_rcu - continue iteration over list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_head within the struct. * * Continue to iterate over list of given type, continuing after * the current position which must have been in the list when the RCU read * lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_from_rcu() except * this starts after the given position and that one starts at the given * position. */ #define list_for_each_entry_continue_rcu(pos, head, member) \ for (pos = list_entry_rcu(pos->member.next, typeof(*pos), member); \ &pos->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*pos), member)) /** * list_for_each_entry_from_rcu - iterate over a list from current point * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the list_node within the struct. * * Iterate over the tail of a list starting from a given position, * which must have been in the list when the RCU read lock was taken. * This would typically require either that you obtained the node from a * previous walk of the list in the same RCU read-side critical section, or * that you held some sort of non-RCU reference (such as a reference count) * to keep the node alive *and* in the list. * * This iterator is similar to list_for_each_entry_continue_rcu() except * this starts from the given position and that one starts from the position * after the given position. */ #define list_for_each_entry_from_rcu(pos, head, member) \ for (; &(pos)->member != (head); \ pos = list_entry_rcu(pos->member.next, typeof(*(pos)), member)) /** * hlist_del_rcu - deletes entry from hash list without re-initialization * @n: the element to delete from the hash list. * * Note: list_unhashed() on entry does not return true after this, * the entry is in an undefined state. It is useful for RCU based * lockfree traversal. * * In particular, it means that we can not poison the forward * pointers that may still be used for walking the hash list. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry(). */ static inline void hlist_del_rcu(struct hlist_node *n) { __hlist_del(n); n->pprev = LIST_POISON2; } /** * hlist_replace_rcu - replace old entry by new one * @old : the element to be replaced * @new : the new element to insert * * The @old entry will be replaced with the @new entry atomically. */ static inline void hlist_replace_rcu(struct hlist_node *old, struct hlist_node *new) { struct hlist_node *next = old->next; new->next = next; new->pprev = old->pprev; rcu_assign_pointer(*(struct hlist_node __rcu **)new->pprev, new); if (next) new->next->pprev = &new->next; old->pprev = LIST_POISON2; } /* * return the first or the next element in an RCU protected hlist */ #define hlist_first_rcu(head) (*((struct hlist_node __rcu **)(&(head)->first))) #define hlist_next_rcu(node) (*((struct hlist_node __rcu **)(&(node)->next))) #define hlist_pprev_rcu(node) (*((struct hlist_node __rcu **)((node)->pprev))) /** * hlist_add_head_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_head_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *first = h->first; n->next = first; n->pprev = &h->first; rcu_assign_pointer(hlist_first_rcu(h), n); if (first) first->pprev = &n->next; } /** * hlist_add_tail_rcu * @n: the element to add to the hash list. * @h: the list to add to. * * Description: * Adds the specified element to the specified hlist, * while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. Regardless of the type of CPU, the * list-traversal primitive must be guarded by rcu_read_lock(). */ static inline void hlist_add_tail_rcu(struct hlist_node *n, struct hlist_head *h) { struct hlist_node *i, *last = NULL; /* Note: write side code, so rcu accessors are not needed. */ for (i = h->first; i; i = i->next) last = i; if (last) { n->next = last->next; n->pprev = &last->next; rcu_assign_pointer(hlist_next_rcu(last), n); } else { hlist_add_head_rcu(n, h); } } /** * hlist_add_before_rcu * @n: the new element to add to the hash list. * @next: the existing element to add the new element before. * * Description: * Adds the specified element to the specified hlist * before the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_before_rcu(struct hlist_node *n, struct hlist_node *next) { n->pprev = next->pprev; n->next = next; rcu_assign_pointer(hlist_pprev_rcu(n), n); next->pprev = &n->next; } /** * hlist_add_behind_rcu * @n: the new element to add to the hash list. * @prev: the existing element to add the new element after. * * Description: * Adds the specified element to the specified hlist * after the specified node while permitting racing traversals. * * The caller must take whatever precautions are necessary * (such as holding appropriate locks) to avoid racing * with another list-mutation primitive, such as hlist_add_head_rcu() * or hlist_del_rcu(), running on this same list. * However, it is perfectly legal to run concurrently with * the _rcu list-traversal primitives, such as * hlist_for_each_entry_rcu(), used to prevent memory-consistency * problems on Alpha CPUs. */ static inline void hlist_add_behind_rcu(struct hlist_node *n, struct hlist_node *prev) { n->next = prev->next; n->pprev = &prev->next; rcu_assign_pointer(hlist_next_rcu(prev), n); if (n->next) n->next->pprev = &n->next; } #define __hlist_for_each_rcu(pos, head) \ for (pos = rcu_dereference(hlist_first_rcu(head)); \ pos; \ pos = rcu_dereference(hlist_next_rcu(pos))) /** * hlist_for_each_entry_rcu - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * @cond: optional lockdep expression if called from non-RCU protection. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu(pos, head, member, cond...) \ for (__list_check_rcu(dummy, ## cond, 0), \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_notrace - iterate over rcu list of given type (for tracing) * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). * * This is the same as hlist_for_each_entry_rcu() except that it does * not do any RCU debugging or tracing. */ #define hlist_for_each_entry_rcu_notrace(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw_check(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_rcu_bh - iterate over rcu list of given type * @pos: the type * to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * * This list-traversal primitive may safely run concurrently with * the _rcu list-mutation primitives such as hlist_add_head_rcu() * as long as the traversal is guarded by rcu_read_lock(). */ #define hlist_for_each_entry_rcu_bh(pos, head, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_first_rcu(head)),\ typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu(\ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_continue_rcu_bh - iterate over a hlist continuing after current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_continue_rcu_bh(pos, member) \ for (pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member); \ pos; \ pos = hlist_entry_safe(rcu_dereference_bh(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) /** * hlist_for_each_entry_from_rcu - iterate over a hlist continuing from current point * @pos: the type * to use as a loop cursor. * @member: the name of the hlist_node within the struct. */ #define hlist_for_each_entry_from_rcu(pos, member) \ for (; pos; \ pos = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu( \ &(pos)->member)), typeof(*(pos)), member)) #endif /* __KERNEL__ */ #endif |
| 439 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 | // SPDX-License-Identifier: GPL-2.0 /* * USB-ACPI glue code * * Copyright 2012 Red Hat <mjg@redhat.com> */ #include <linux/module.h> #include <linux/usb.h> #include <linux/device.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/acpi.h> #include <linux/pci.h> #include <linux/usb/hcd.h> #include "hub.h" /** * usb_acpi_power_manageable - check whether usb port has * acpi power resource. * @hdev: USB device belonging to the usb hub * @index: port index based zero * * Return true if the port has acpi power resource and false if no. */ bool usb_acpi_power_manageable(struct usb_device *hdev, int index) { acpi_handle port_handle; int port1 = index + 1; port_handle = usb_get_hub_port_acpi_handle(hdev, port1); if (port_handle) return acpi_bus_power_manageable(port_handle); else return false; } EXPORT_SYMBOL_GPL(usb_acpi_power_manageable); #define UUID_USB_CONTROLLER_DSM "ce2ee385-00e6-48cb-9f05-2edb927c4899" #define USB_DSM_DISABLE_U1_U2_FOR_PORT 5 /** * usb_acpi_port_lpm_incapable - check if lpm should be disabled for a port. * @hdev: USB device belonging to the usb hub * @index: zero based port index * * Some USB3 ports may not support USB3 link power management U1/U2 states * due to different retimer setup. ACPI provides _DSM method which returns 0x01 * if U1 and U2 states should be disabled. Evaluate _DSM with: * Arg0: UUID = ce2ee385-00e6-48cb-9f05-2edb927c4899 * Arg1: Revision ID = 0 * Arg2: Function Index = 5 * Arg3: (empty) * * Return 1 if USB3 port is LPM incapable, negative on error, otherwise 0 */ int usb_acpi_port_lpm_incapable(struct usb_device *hdev, int index) { union acpi_object *obj; acpi_handle port_handle; int port1 = index + 1; guid_t guid; int ret; ret = guid_parse(UUID_USB_CONTROLLER_DSM, &guid); if (ret) return ret; port_handle = usb_get_hub_port_acpi_handle(hdev, port1); if (!port_handle) { dev_dbg(&hdev->dev, "port-%d no acpi handle\n", port1); return -ENODEV; } if (!acpi_check_dsm(port_handle, &guid, 0, BIT(USB_DSM_DISABLE_U1_U2_FOR_PORT))) { dev_dbg(&hdev->dev, "port-%d no _DSM function %d\n", port1, USB_DSM_DISABLE_U1_U2_FOR_PORT); return -ENODEV; } obj = acpi_evaluate_dsm(port_handle, &guid, 0, USB_DSM_DISABLE_U1_U2_FOR_PORT, NULL); if (!obj) return -ENODEV; if (obj->type != ACPI_TYPE_INTEGER) { dev_dbg(&hdev->dev, "evaluate port-%d _DSM failed\n", port1); ACPI_FREE(obj); return -EINVAL; } if (obj->integer.value == 0x01) ret = 1; ACPI_FREE(obj); return ret; } EXPORT_SYMBOL_GPL(usb_acpi_port_lpm_incapable); /** * usb_acpi_set_power_state - control usb port's power via acpi power * resource * @hdev: USB device belonging to the usb hub * @index: port index based zero * @enable: power state expected to be set * * Notice to use usb_acpi_power_manageable() to check whether the usb port * has acpi power resource before invoking this function. * * Returns 0 on success, else negative errno. */ int usb_acpi_set_power_state(struct usb_device *hdev, int index, bool enable) { struct usb_hub *hub = usb_hub_to_struct_hub(hdev); struct usb_port *port_dev; acpi_handle port_handle; unsigned char state; int port1 = index + 1; int error = -EINVAL; if (!hub) return -ENODEV; port_dev = hub->ports[port1 - 1]; port_handle = (acpi_handle) usb_get_hub_port_acpi_handle(hdev, port1); if (!port_handle) return error; if (enable) state = ACPI_STATE_D0; else state = ACPI_STATE_D3_COLD; error = acpi_bus_set_power(port_handle, state); if (!error) dev_dbg(&port_dev->dev, "acpi: power was set to %d\n", enable); else dev_dbg(&port_dev->dev, "acpi: power failed to be set\n"); return error; } EXPORT_SYMBOL_GPL(usb_acpi_set_power_state); static enum usb_port_connect_type usb_acpi_get_connect_type(acpi_handle handle, struct acpi_pld_info *pld) { enum usb_port_connect_type connect_type = USB_PORT_CONNECT_TYPE_UNKNOWN; struct acpi_buffer buffer = { ACPI_ALLOCATE_BUFFER, NULL }; union acpi_object *upc; acpi_status status; /* * According to 9.14 in ACPI Spec 6.2. _PLD indicates whether usb port * is user visible and _UPC indicates whether it is connectable. If * the port was visible and connectable, it could be freely connected * and disconnected with USB devices. If no visible and connectable, * a usb device is directly hard-wired to the port. If no visible and * no connectable, the port would be not used. */ status = acpi_evaluate_object(handle, "_UPC", NULL, &buffer); upc = buffer.pointer; if (!upc || (upc->type != ACPI_TYPE_PACKAGE) || upc->package.count != 4) { goto out; } if (upc->package.elements[0].integer.value) if (pld->user_visible) connect_type = USB_PORT_CONNECT_TYPE_HOT_PLUG; else connect_type = USB_PORT_CONNECT_TYPE_HARD_WIRED; else if (!pld->user_visible) connect_type = USB_PORT_NOT_USED; out: kfree(upc); return connect_type; } /* * Private to usb-acpi, all the core needs to know is that * port_dev->location is non-zero when it has been set by the firmware. */ #define USB_ACPI_LOCATION_VALID (1 << 31) static struct acpi_device *usb_acpi_find_port(struct acpi_device *parent, int raw) { struct acpi_device *adev; if (!parent) return NULL; list_for_each_entry(adev, &parent->children, node) { if (acpi_device_adr(adev) == raw) return adev; } return acpi_find_child_device(parent, raw, false); } static struct acpi_device * usb_acpi_get_companion_for_port(struct usb_port *port_dev) { struct usb_device *udev; struct acpi_device *adev; acpi_handle *parent_handle; int port1; /* Get the struct usb_device point of port's hub */ udev = to_usb_device(port_dev->dev.parent->parent); /* * The root hub ports' parent is the root hub. The non-root-hub * ports' parent is the parent hub port which the hub is * connected to. */ if (!udev->parent) { adev = ACPI_COMPANION(&udev->dev); port1 = usb_hcd_find_raw_port_number(bus_to_hcd(udev->bus), port_dev->portnum); } else { parent_handle = usb_get_hub_port_acpi_handle(udev->parent, udev->portnum); if (!parent_handle) return NULL; acpi_bus_get_device(parent_handle, &adev); port1 = port_dev->portnum; } return usb_acpi_find_port(adev, port1); } static struct acpi_device * usb_acpi_find_companion_for_port(struct usb_port *port_dev) { struct acpi_device *adev; struct acpi_pld_info *pld; acpi_handle *handle; acpi_status status; adev = usb_acpi_get_companion_for_port(port_dev); if (!adev) return NULL; handle = adev->handle; status = acpi_get_physical_device_location(handle, &pld); if (!ACPI_FAILURE(status) && pld) { port_dev->location = USB_ACPI_LOCATION_VALID | pld->group_token << 8 | pld->group_position; port_dev->connect_type = usb_acpi_get_connect_type(handle, pld); ACPI_FREE(pld); } return adev; } static struct acpi_device * usb_acpi_find_companion_for_device(struct usb_device *udev) { struct acpi_device *adev; struct usb_port *port_dev; struct usb_hub *hub; if (!udev->parent) { /* root hub is only child (_ADR=0) under its parent, the HC */ adev = ACPI_COMPANION(udev->dev.parent); return acpi_find_child_device(adev, 0, false); } hub = usb_hub_to_struct_hub(udev->parent); if (!hub) return NULL; /* * This is an embedded USB device connected to a port and such * devices share port's ACPI companion. */ port_dev = hub->ports[udev->portnum - 1]; return usb_acpi_get_companion_for_port(port_dev); } static struct acpi_device *usb_acpi_find_companion(struct device *dev) { /* * The USB hierarchy like following: * * Device (EHC1) * Device (HUBN) * Device (PR01) * Device (PR11) * Device (PR12) * Device (FN12) * Device (FN13) * Device (PR13) * ... * where HUBN is root hub, and PRNN are USB ports and devices * connected to them, and FNNN are individualk functions for * connected composite USB devices. PRNN and FNNN may contain * _CRS and other methods describing sideband resources for * the connected device. * * On the kernel side both root hub and embedded USB devices are * represented as instances of usb_device structure, and ports * are represented as usb_port structures, so the whole process * is split into 2 parts: finding companions for devices and * finding companions for ports. * * Note that we do not handle individual functions of composite * devices yet, for that we would need to assign companions to * devices corresponding to USB interfaces. */ if (is_usb_device(dev)) return usb_acpi_find_companion_for_device(to_usb_device(dev)); else if (is_usb_port(dev)) return usb_acpi_find_companion_for_port(to_usb_port(dev)); return NULL; } static bool usb_acpi_bus_match(struct device *dev) { return is_usb_device(dev) || is_usb_port(dev); } static struct acpi_bus_type usb_acpi_bus = { .name = "USB", .match = usb_acpi_bus_match, .find_companion = usb_acpi_find_companion, }; int usb_acpi_register(void) { return register_acpi_bus_type(&usb_acpi_bus); } void usb_acpi_unregister(void) { unregister_acpi_bus_type(&usb_acpi_bus); } |
| 5 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_BLKDEV_H #define _LINUX_BLKDEV_H #include <linux/sched.h> #include <linux/sched/clock.h> #ifdef CONFIG_BLOCK #include <linux/major.h> #include <linux/genhd.h> #include <linux/list.h> #include <linux/llist.h> #include <linux/timer.h> #include <linux/workqueue.h> #include <linux/pagemap.h> #include <linux/backing-dev-defs.h> #include <linux/wait.h> #include <linux/mempool.h> #include <linux/pfn.h> #include <linux/bio.h> #include <linux/stringify.h> #include <linux/gfp.h> #include <linux/bsg.h> #include <linux/smp.h> #include <linux/rcupdate.h> #include <linux/percpu-refcount.h> #include <linux/scatterlist.h> #include <linux/blkzoned.h> #include <linux/android_kabi.h> struct module; struct scsi_ioctl_command; struct request_queue; struct elevator_queue; struct blk_trace; struct request; struct sg_io_hdr; struct bsg_job; struct blkcg_gq; struct blk_flush_queue; struct pr_ops; struct rq_qos; struct blk_queue_stats; struct blk_stat_callback; struct blk_keyslot_manager; #define BLKDEV_MIN_RQ 4 #define BLKDEV_MAX_RQ 128 /* Default maximum */ /* Must be consistent with blk_mq_poll_stats_bkt() */ #define BLK_MQ_POLL_STATS_BKTS 16 /* Doing classic polling */ #define BLK_MQ_POLL_CLASSIC -1 /* * Maximum number of blkcg policies allowed to be registered concurrently. * Defined here to simplify include dependency. */ #define BLKCG_MAX_POLS 5 static inline int blk_validate_block_size(unsigned long bsize) { if (bsize < 512 || bsize > PAGE_SIZE || !is_power_of_2(bsize)) return -EINVAL; return 0; } typedef void (rq_end_io_fn)(struct request *, blk_status_t); /* * request flags */ typedef __u32 __bitwise req_flags_t; /* elevator knows about this request */ #define RQF_SORTED ((__force req_flags_t)(1 << 0)) /* drive already may have started this one */ #define RQF_STARTED ((__force req_flags_t)(1 << 1)) /* may not be passed by ioscheduler */ #define RQF_SOFTBARRIER ((__force req_flags_t)(1 << 3)) /* request for flush sequence */ #define RQF_FLUSH_SEQ ((__force req_flags_t)(1 << 4)) /* merge of different types, fail separately */ #define RQF_MIXED_MERGE ((__force req_flags_t)(1 << 5)) /* track inflight for MQ */ #define RQF_MQ_INFLIGHT ((__force req_flags_t)(1 << 6)) /* don't call prep for this one */ #define RQF_DONTPREP ((__force req_flags_t)(1 << 7)) /* set for "ide_preempt" requests and also for requests for which the SCSI "quiesce" state must be ignored. */ #define RQF_PREEMPT ((__force req_flags_t)(1 << 8)) /* contains copies of user pages */ #define RQF_COPY_USER ((__force req_flags_t)(1 << 9)) /* vaguely specified driver internal error. Ignored by the block layer */ #define RQF_FAILED ((__force req_flags_t)(1 << 10)) /* don't warn about errors */ #define RQF_QUIET ((__force req_flags_t)(1 << 11)) /* elevator private data attached */ #define RQF_ELVPRIV ((__force req_flags_t)(1 << 12)) /* account into disk and partition IO statistics */ #define RQF_IO_STAT ((__force req_flags_t)(1 << 13)) /* request came from our alloc pool */ #define RQF_ALLOCED ((__force req_flags_t)(1 << 14)) /* runtime pm request */ #define RQF_PM ((__force req_flags_t)(1 << 15)) /* on IO scheduler merge hash */ #define RQF_HASHED ((__force req_flags_t)(1 << 16)) /* track IO completion time */ #define RQF_STATS ((__force req_flags_t)(1 << 17)) /* Look at ->special_vec for the actual data payload instead of the bio chain. */ #define RQF_SPECIAL_PAYLOAD ((__force req_flags_t)(1 << 18)) /* The per-zone write lock is held for this request */ #define RQF_ZONE_WRITE_LOCKED ((__force req_flags_t)(1 << 19)) /* already slept for hybrid poll */ #define RQF_MQ_POLL_SLEPT ((__force req_flags_t)(1 << 20)) /* ->timeout has been called, don't expire again */ #define RQF_TIMED_OUT ((__force req_flags_t)(1 << 21)) /* flags that prevent us from merging requests: */ #define RQF_NOMERGE_FLAGS \ (RQF_STARTED | RQF_SOFTBARRIER | RQF_FLUSH_SEQ | RQF_SPECIAL_PAYLOAD) /* * Request state for blk-mq. */ 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; unsigned int cmd_flags; /* op and common flags */ req_flags_t rq_flags; int tag; int internal_tag; /* 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; struct list_head queuelist; /* * 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 list_head ipi_list; }; /* * The rb_node is only used inside the io scheduler, requests * are pruned when moved to the dispatch queue. So let the * completion_data share space with the rb_node. */ union { struct rb_node rb_node; /* sort/lookup */ struct bio_vec special_vec; void *completion_data; int error_count; /* for legacy drivers, don't use */ }; /* * Three pointers are available for the IO schedulers, if they need * more they have to dynamically allocate it. Flush requests are * never put on the IO scheduler. So let the flush fields share * space with the elevator data. */ union { struct { struct io_cq *icq; void *priv[2]; } elv; struct { unsigned int seq; struct list_head list; rq_end_io_fn *saved_end_io; } flush; }; struct gendisk *rq_disk; struct hd_struct *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; #if defined(CONFIG_BLK_DEV_INTEGRITY) unsigned short nr_integrity_segments; #endif #ifdef CONFIG_BLK_INLINE_ENCRYPTION struct bio_crypt_ctx *crypt_ctx; struct blk_ksm_keyslot *crypt_keyslot; #endif unsigned short write_hint; unsigned short ioprio; unsigned int extra_len; /* length of alignment and padding */ enum mq_rq_state state; refcount_t ref; unsigned int timeout; unsigned long deadline; union { struct __call_single_data csd; u64 fifo_time; }; /* * completion callback. */ rq_end_io_fn *end_io; void *end_io_data; ANDROID_KABI_RESERVE(1); }; static inline bool blk_op_is_scsi(unsigned int op) { return op == REQ_OP_SCSI_IN || op == REQ_OP_SCSI_OUT; } static inline bool blk_op_is_private(unsigned int op) { return op == REQ_OP_DRV_IN || op == REQ_OP_DRV_OUT; } static inline bool blk_rq_is_scsi(struct request *rq) { return blk_op_is_scsi(req_op(rq)); } static inline bool blk_rq_is_private(struct request *rq) { return blk_op_is_private(req_op(rq)); } static inline bool blk_rq_is_passthrough(struct request *rq) { return blk_rq_is_scsi(rq) || blk_rq_is_private(rq); } static inline bool bio_is_passthrough(struct bio *bio) { unsigned op = bio_op(bio); return blk_op_is_scsi(op) || blk_op_is_private(op); } static inline unsigned short req_get_ioprio(struct request *req) { return req->ioprio; } #include <linux/elevator.h> struct blk_queue_ctx; typedef blk_qc_t (make_request_fn) (struct request_queue *q, struct bio *bio); struct bio_vec; typedef int (dma_drain_needed_fn)(struct request *); enum blk_eh_timer_return { BLK_EH_DONE, /* drivers has completed the command */ BLK_EH_RESET_TIMER, /* reset timer and try again */ }; enum blk_queue_state { Queue_down, Queue_up, }; #define BLK_TAG_ALLOC_FIFO 0 /* allocate starting from 0 */ #define BLK_TAG_ALLOC_RR 1 /* allocate starting from last allocated tag */ #define BLK_SCSI_MAX_CMDS (256) #define BLK_SCSI_CMD_PER_LONG (BLK_SCSI_MAX_CMDS / (sizeof(long) * 8)) /* * Zoned block device models (zoned limit). */ enum blk_zoned_model { BLK_ZONED_NONE, /* Regular block device */ BLK_ZONED_HA, /* Host-aware zoned block device */ BLK_ZONED_HM, /* Host-managed zoned block device */ }; struct queue_limits { unsigned long bounce_pfn; 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_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_write_same_sectors; unsigned int max_write_zeroes_sectors; unsigned int discard_granularity; unsigned int discard_alignment; unsigned short max_segments; unsigned short max_integrity_segments; unsigned short max_discard_segments; unsigned char misaligned; unsigned char discard_misaligned; unsigned char raid_partial_stripes_expensive; enum blk_zoned_model zoned; ANDROID_KABI_RESERVE(1); }; typedef int (*report_zones_cb)(struct blk_zone *zone, unsigned int idx, void *data); #ifdef CONFIG_BLK_DEV_ZONED #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); unsigned int blkdev_nr_zones(struct gendisk *disk); extern int blkdev_zone_mgmt(struct block_device *bdev, enum req_opf op, sector_t sectors, sector_t nr_sectors, gfp_t gfp_mask); extern int blk_revalidate_disk_zones(struct gendisk *disk); extern int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); extern int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg); #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blkdev_nr_zones(struct gendisk *disk) { return 0; } static inline int blkdev_report_zones_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } static inline int blkdev_zone_mgmt_ioctl(struct block_device *bdev, fmode_t mode, unsigned int cmd, unsigned long arg) { return -ENOTTY; } #endif /* CONFIG_BLK_DEV_ZONED */ struct request_queue { struct request *last_merge; struct elevator_queue *elevator; struct blk_queue_stats *stats; struct rq_qos *rq_qos; make_request_fn *make_request_fn; dma_drain_needed_fn *dma_drain_needed; const struct blk_mq_ops *mq_ops; /* sw queues */ struct blk_mq_ctx __percpu *queue_ctx; unsigned int nr_queues; unsigned int queue_depth; /* hw dispatch queues */ struct blk_mq_hw_ctx **queue_hw_ctx; unsigned int nr_hw_queues; struct backing_dev_info *backing_dev_info; /* * The queue owner gets to use this for whatever they like. * ll_rw_blk doesn't touch it. */ void *queuedata; /* * various queue flags, see QUEUE_* below */ unsigned long queue_flags; /* * Number of contexts that have called blk_set_pm_only(). If this * counter is above zero then only RQF_PM and RQF_PREEMPT requests are * processed. */ atomic_t pm_only; /* * ida allocated id for this queue. Used to index queues from * ioctx. */ int id; /* * queue needs bounce pages for pages above this limit */ gfp_t bounce_gfp; spinlock_t queue_lock; /* * queue kobject */ struct kobject kobj; /* * mq queue kobject */ struct kobject *mq_kobj; #ifdef CONFIG_BLK_DEV_INTEGRITY struct blk_integrity integrity; #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_PM struct device *dev; int rpm_status; unsigned int nr_pending; #endif /* * queue settings */ unsigned long nr_requests; /* Max # of requests */ unsigned int dma_drain_size; void *dma_drain_buffer; unsigned int dma_pad_mask; unsigned int dma_alignment; #ifdef CONFIG_BLK_INLINE_ENCRYPTION /* Inline crypto capabilities */ struct blk_keyslot_manager *ksm; #endif unsigned int rq_timeout; int poll_nsec; struct blk_stat_callback *poll_cb; struct blk_rq_stat poll_stat[BLK_MQ_POLL_STATS_BKTS]; struct timer_list timeout; struct work_struct timeout_work; 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; #endif struct queue_limits limits; unsigned int required_elevator_features; #ifdef CONFIG_BLK_DEV_ZONED /* * Zoned block device information for request dispatch control. * nr_zones is the total number of zones of the device. This is always * 0 for regular block devices. conv_zones_bitmap is a bitmap of nr_zones * bits which indicates if a zone is conventional (bit set) or * sequential (bit clear). seq_zones_wlock is a bitmap of nr_zones * bits which indicates if a zone is write locked, that is, if a write * request targeting the zone was dispatched. All three fields are * initialized by the low level device driver (e.g. scsi/sd.c). * Stacking drivers (device mappers) may or may not initialize * these fields. * * 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 long *conv_zones_bitmap; unsigned long *seq_zones_wlock; #endif /* CONFIG_BLK_DEV_ZONED */ /* * sg stuff */ unsigned int sg_timeout; unsigned int sg_reserved_size; int node; #ifdef CONFIG_BLK_DEV_IO_TRACE struct blk_trace __rcu *blk_trace; struct mutex blk_trace_mutex; #endif /* * for flush operations */ struct blk_flush_queue *fq; struct list_head requeue_list; spinlock_t requeue_lock; struct delayed_work requeue_work; struct mutex sysfs_lock; struct mutex sysfs_dir_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; #if defined(CONFIG_BLK_DEV_BSG) struct bsg_class_device bsg_dev; #endif #ifdef CONFIG_BLK_DEV_THROTTLING /* Throttle data */ struct throtl_data *td; #endif struct rcu_head rcu_head; 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 percpu_ref q_usage_counter; struct blk_mq_tag_set *tag_set; struct list_head tag_set_list; struct bio_set bio_split; #ifdef CONFIG_BLK_DEBUG_FS struct dentry *debugfs_dir; struct dentry *sched_debugfs_dir; struct dentry *rqos_debugfs_dir; #endif bool mq_sysfs_init_done; size_t cmd_size; struct work_struct release_work; #define BLK_MAX_WRITE_HINTS 5 u64 write_hints[BLK_MAX_WRITE_HINTS]; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); ANDROID_KABI_RESERVE(3); ANDROID_KABI_RESERVE(4); }; /* Keep blk_queue_flag_name[] in sync with the definitions below */ #define QUEUE_FLAG_STOPPED 0 /* queue is stopped */ #define QUEUE_FLAG_DYING 1 /* queue being torn down */ #define QUEUE_FLAG_NOMERGES 3 /* disable merge attempts */ #define QUEUE_FLAG_SAME_COMP 4 /* complete on same CPU-group */ #define QUEUE_FLAG_FAIL_IO 5 /* fake timeout */ #define QUEUE_FLAG_NONROT 6 /* non-rotational device (SSD) */ #define QUEUE_FLAG_VIRT QUEUE_FLAG_NONROT /* paravirt device */ #define QUEUE_FLAG_IO_STAT 7 /* do disk/partitions IO accounting */ #define QUEUE_FLAG_DISCARD 8 /* supports DISCARD */ #define QUEUE_FLAG_NOXMERGES 9 /* No extended merges */ #define QUEUE_FLAG_ADD_RANDOM 10 /* Contributes to random pool */ #define QUEUE_FLAG_SECERASE 11 /* supports secure erase */ #define QUEUE_FLAG_SAME_FORCE 12 /* force complete on same CPU */ #define QUEUE_FLAG_DEAD 13 /* queue tear-down finished */ #define QUEUE_FLAG_INIT_DONE 14 /* queue is initialized */ #define QUEUE_FLAG_POLL 16 /* IO polling enabled if set */ #define QUEUE_FLAG_WC 17 /* Write back caching */ #define QUEUE_FLAG_FUA 18 /* device supports FUA writes */ #define QUEUE_FLAG_DAX 19 /* device supports DAX */ #define QUEUE_FLAG_STATS 20 /* track IO start and completion times */ #define QUEUE_FLAG_POLL_STATS 21 /* collecting stats for hybrid polling */ #define QUEUE_FLAG_REGISTERED 22 /* queue has been registered to a disk */ #define QUEUE_FLAG_SCSI_PASSTHROUGH 23 /* queue supports SCSI commands */ #define QUEUE_FLAG_QUIESCED 24 /* queue has been quiesced */ #define QUEUE_FLAG_PCI_P2PDMA 25 /* device supports PCI p2p requests */ #define QUEUE_FLAG_ZONE_RESETALL 26 /* supports Zone Reset All */ #define QUEUE_FLAG_RQ_ALLOC_TIME 27 /* record rq->alloc_time_ns */ #define QUEUE_FLAG_MQ_DEFAULT ((1 << QUEUE_FLAG_IO_STAT) | \ (1 << 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); bool blk_queue_flag_test_and_set(unsigned int flag, struct request_queue *q); #define blk_queue_stopped(q) test_bit(QUEUE_FLAG_STOPPED, &(q)->queue_flags) #define blk_queue_dying(q) test_bit(QUEUE_FLAG_DYING, &(q)->queue_flags) #define blk_queue_dead(q) test_bit(QUEUE_FLAG_DEAD, &(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_nonrot(q) test_bit(QUEUE_FLAG_NONROT, &(q)->queue_flags) #define blk_queue_io_stat(q) test_bit(QUEUE_FLAG_IO_STAT, &(q)->queue_flags) #define blk_queue_add_random(q) test_bit(QUEUE_FLAG_ADD_RANDOM, &(q)->queue_flags) #define blk_queue_discard(q) test_bit(QUEUE_FLAG_DISCARD, &(q)->queue_flags) #define blk_queue_zone_resetall(q) \ test_bit(QUEUE_FLAG_ZONE_RESETALL, &(q)->queue_flags) #define blk_queue_secure_erase(q) \ (test_bit(QUEUE_FLAG_SECERASE, &(q)->queue_flags)) #define blk_queue_dax(q) test_bit(QUEUE_FLAG_DAX, &(q)->queue_flags) #define blk_queue_scsi_passthrough(q) \ test_bit(QUEUE_FLAG_SCSI_PASSTHROUGH, &(q)->queue_flags) #define blk_queue_pci_p2pdma(q) \ test_bit(QUEUE_FLAG_PCI_P2PDMA, &(q)->queue_flags) #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_fua(q) test_bit(QUEUE_FLAG_FUA, &(q)->queue_flags) #define blk_queue_registered(q) test_bit(QUEUE_FLAG_REGISTERED, &(q)->queue_flags) extern void blk_set_pm_only(struct request_queue *q); extern void blk_clear_pm_only(struct request_queue *q); static inline bool blk_account_rq(struct request *rq) { return (rq->rq_flags & RQF_STARTED) && !blk_rq_is_passthrough(rq); } #define list_entry_rq(ptr) list_entry((ptr), struct request, queuelist) #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) #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; } static inline enum blk_zoned_model blk_queue_zoned_model(struct request_queue *q) { return q->limits.zoned; } static inline bool blk_queue_is_zoned(struct request_queue *q) { switch (blk_queue_zoned_model(q)) { case BLK_ZONED_HA: case BLK_ZONED_HM: return true; default: return false; } } static inline sector_t blk_queue_zone_sectors(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->limits.chunk_sectors : 0; } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return blk_queue_is_zoned(q) ? q->nr_zones : 0; } static inline unsigned int blk_queue_zone_no(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return 0; return sector >> ilog2(q->limits.chunk_sectors); } static inline bool blk_queue_zone_is_seq(struct request_queue *q, sector_t sector) { if (!blk_queue_is_zoned(q)) return false; if (!q->conv_zones_bitmap) return true; return !test_bit(blk_queue_zone_no(q, sector), q->conv_zones_bitmap); } #else /* CONFIG_BLK_DEV_ZONED */ static inline unsigned int blk_queue_nr_zones(struct request_queue *q) { return 0; } #endif /* CONFIG_BLK_DEV_ZONED */ static inline bool rq_is_sync(struct request *rq) { return op_is_sync(rq->cmd_flags); } static inline bool rq_mergeable(struct request *rq) { if (blk_rq_is_passthrough(rq)) return false; if (req_op(rq) == REQ_OP_FLUSH) return false; if (req_op(rq) == REQ_OP_WRITE_ZEROES) return false; if (rq->cmd_flags & REQ_NOMERGE_FLAGS) return false; if (rq->rq_flags & RQF_NOMERGE_FLAGS) return false; return true; } static inline bool blk_write_same_mergeable(struct bio *a, struct bio *b) { if (bio_page(a) == bio_page(b) && bio_offset(a) == bio_offset(b)) return true; return false; } static inline unsigned int blk_queue_depth(struct request_queue *q) { if (q->queue_depth) return q->queue_depth; return q->nr_requests; } extern unsigned long blk_max_low_pfn, blk_max_pfn; /* * standard bounce addresses: * * BLK_BOUNCE_HIGH : bounce all highmem pages * BLK_BOUNCE_ANY : don't bounce anything * BLK_BOUNCE_ISA : bounce pages above ISA DMA boundary */ #if BITS_PER_LONG == 32 #define BLK_BOUNCE_HIGH ((u64)blk_max_low_pfn << PAGE_SHIFT) #else #define BLK_BOUNCE_HIGH -1ULL #endif #define BLK_BOUNCE_ANY (-1ULL) #define BLK_BOUNCE_ISA (DMA_BIT_MASK(24)) /* * default timeout for SG_IO if none specified */ #define BLK_DEFAULT_SG_TIMEOUT (60 * HZ) #define BLK_MIN_SG_TIMEOUT (7 * HZ) struct rq_map_data { struct page **pages; int page_order; int nr_entries; unsigned long offset; int null_mapped; int from_user; }; struct req_iterator { struct bvec_iter iter; struct bio *bio; }; /* This should not be used directly - use rq_for_each_segment */ #define for_each_bio(_bio) \ for (; _bio; _bio = _bio->bi_next) #define __rq_for_each_bio(_bio, rq) \ if ((rq->bio)) \ for (_bio = (rq)->bio; _bio; _bio = _bio->bi_next) #define rq_for_each_segment(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_segment(bvl, _iter.bio, _iter.iter) #define rq_for_each_bvec(bvl, _rq, _iter) \ __rq_for_each_bio(_iter.bio, _rq) \ bio_for_each_bvec(bvl, _iter.bio, _iter.iter) #define rq_iter_last(bvec, _iter) \ (_iter.bio->bi_next == NULL && \ bio_iter_last(bvec, _iter.iter)) #ifndef ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE # error "You should define ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE for your platform" #endif #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE extern void rq_flush_dcache_pages(struct request *rq); #else static inline void rq_flush_dcache_pages(struct request *rq) { } #endif extern int blk_register_queue(struct gendisk *disk); extern void blk_unregister_queue(struct gendisk *disk); extern blk_qc_t generic_make_request(struct bio *bio); extern blk_qc_t direct_make_request(struct bio *bio); extern void blk_rq_init(struct request_queue *q, struct request *rq); extern void blk_put_request(struct request *); extern struct request *blk_get_request(struct request_queue *, unsigned int op, blk_mq_req_flags_t flags); extern int blk_lld_busy(struct request_queue *q); extern int blk_rq_prep_clone(struct request *rq, struct request *rq_src, struct bio_set *bs, gfp_t gfp_mask, int (*bio_ctr)(struct bio *, struct bio *, void *), void *data); extern void blk_rq_unprep_clone(struct request *rq); extern blk_status_t blk_insert_cloned_request(struct request_queue *q, struct request *rq); extern int blk_rq_append_bio(struct request *rq, struct bio **bio); extern void blk_queue_split(struct request_queue *, struct bio **); extern int scsi_verify_blk_ioctl(struct block_device *, unsigned int); extern int scsi_cmd_blk_ioctl(struct block_device *, fmode_t, unsigned int, void __user *); extern int scsi_cmd_ioctl(struct request_queue *, struct gendisk *, fmode_t, unsigned int, void __user *); extern int sg_scsi_ioctl(struct request_queue *, struct gendisk *, fmode_t, struct scsi_ioctl_command __user *); 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); extern int blk_rq_map_user(struct request_queue *, struct request *, struct rq_map_data *, void __user *, unsigned long, gfp_t); extern int blk_rq_unmap_user(struct bio *); extern int blk_rq_map_kern(struct request_queue *, struct request *, void *, unsigned int, gfp_t); extern int blk_rq_map_user_iov(struct request_queue *, struct request *, struct rq_map_data *, const struct iov_iter *, gfp_t); extern void blk_execute_rq(struct request_queue *, struct gendisk *, struct request *, int); extern void blk_execute_rq_nowait(struct request_queue *, struct gendisk *, struct request *, int, rq_end_io_fn *); /* Helper to convert REQ_OP_XXX to its string format XXX */ extern const char *blk_op_str(unsigned int op); int blk_status_to_errno(blk_status_t status); blk_status_t errno_to_blk_status(int errno); int blk_poll(struct request_queue *q, blk_qc_t cookie, bool spin); static inline struct request_queue *bdev_get_queue(struct block_device *bdev) { return bdev->bd_disk->queue; /* this is never NULL */ } /* * The basic unit of block I/O is a sector. It is used in a number of contexts * in Linux (blk, bio, genhd). The size of one sector is 512 = 2**9 * bytes. Variables of type sector_t represent an offset or size that is a * multiple of 512 bytes. Hence these two constants. */ #ifndef SECTOR_SHIFT #define SECTOR_SHIFT 9 #endif #ifndef SECTOR_SIZE #define SECTOR_SIZE (1 << SECTOR_SHIFT) #endif /* * blk_rq_pos() : the current sector * blk_rq_bytes() : bytes left in the entire request * blk_rq_cur_bytes() : bytes left in the current segment * blk_rq_err_bytes() : bytes left till the next error boundary * blk_rq_sectors() : sectors left in the entire request * blk_rq_cur_sectors() : sectors left in the current segment * blk_rq_stats_sectors() : sectors of the entire request used for stats */ static inline sector_t blk_rq_pos(const struct request *rq) { return rq->__sector; } static inline unsigned int blk_rq_bytes(const struct request *rq) { return rq->__data_len; } static inline int blk_rq_cur_bytes(const struct request *rq) { return rq->bio ? bio_cur_bytes(rq->bio) : 0; } extern unsigned int blk_rq_err_bytes(const struct request *rq); static inline unsigned int blk_rq_sectors(const struct request *rq) { return blk_rq_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_cur_sectors(const struct request *rq) { return blk_rq_cur_bytes(rq) >> SECTOR_SHIFT; } static inline unsigned int blk_rq_stats_sectors(const struct request *rq) { return rq->stats_sectors; } #ifdef CONFIG_BLK_DEV_ZONED static inline unsigned int blk_rq_zone_no(struct request *rq) { return blk_queue_zone_no(rq->q, blk_rq_pos(rq)); } static inline unsigned int blk_rq_zone_is_seq(struct request *rq) { return blk_queue_zone_is_seq(rq->q, blk_rq_pos(rq)); } #endif /* CONFIG_BLK_DEV_ZONED */ /* * Some commands like WRITE SAME have a payload or data transfer size which * is different from the size of the request. Any driver that supports such * commands using the RQF_SPECIAL_PAYLOAD flag needs to use this helper to * calculate the data transfer size. */ static inline unsigned int blk_rq_payload_bytes(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec.bv_len; return blk_rq_bytes(rq); } /* * Return the first full biovec in the request. The caller needs to check that * there are any bvecs before calling this helper. */ static inline struct bio_vec req_bvec(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return rq->special_vec; return mp_bvec_iter_bvec(rq->bio->bi_io_vec, rq->bio->bi_iter); } static inline unsigned int blk_queue_get_max_sectors(struct request_queue *q, int op) { if (unlikely(op == REQ_OP_DISCARD || op == REQ_OP_SECURE_ERASE)) return min(q->limits.max_discard_sectors, UINT_MAX >> SECTOR_SHIFT); if (unlikely(op == REQ_OP_WRITE_SAME)) return q->limits.max_write_same_sectors; if (unlikely(op == REQ_OP_WRITE_ZEROES)) return q->limits.max_write_zeroes_sectors; return q->limits.max_sectors; } /* * Return maximum size of a request at given offset. Only valid for * file system requests. */ static inline unsigned int blk_max_size_offset(struct request_queue *q, sector_t offset) { if (!q->limits.chunk_sectors) return q->limits.max_sectors; return min(q->limits.max_sectors, (unsigned int)(q->limits.chunk_sectors - (offset & (q->limits.chunk_sectors - 1)))); } static inline unsigned int blk_rq_get_max_sectors(struct request *rq, sector_t offset) { struct request_queue *q = rq->q; if (blk_rq_is_passthrough(rq)) return q->limits.max_hw_sectors; if (!q->limits.chunk_sectors || req_op(rq) == REQ_OP_DISCARD || req_op(rq) == REQ_OP_SECURE_ERASE) return blk_queue_get_max_sectors(q, req_op(rq)); return min(blk_max_size_offset(q, offset), blk_queue_get_max_sectors(q, req_op(rq))); } static inline unsigned int blk_rq_count_bios(struct request *rq) { unsigned int nr_bios = 0; struct bio *bio; __rq_for_each_bio(bio, rq) nr_bios++; return nr_bios; } void blk_steal_bios(struct bio_list *list, struct request *rq); /* * Request completion related functions. * * blk_update_request() completes given number of bytes and updates * the request without completing it. */ extern bool blk_update_request(struct request *rq, blk_status_t error, unsigned int nr_bytes); extern void __blk_complete_request(struct request *); extern void blk_abort_request(struct request *); /* * Access functions for manipulating queue properties */ extern void blk_cleanup_queue(struct request_queue *); extern void blk_queue_make_request(struct request_queue *, make_request_fn *); extern void blk_queue_bounce_limit(struct request_queue *, u64); extern void blk_queue_max_hw_sectors(struct request_queue *, unsigned int); extern void blk_queue_chunk_sectors(struct request_queue *, unsigned int); extern void blk_queue_max_segments(struct request_queue *, unsigned short); extern void blk_queue_max_discard_segments(struct request_queue *, unsigned short); extern void blk_queue_max_segment_size(struct request_queue *, unsigned int); extern void blk_queue_max_discard_sectors(struct request_queue *q, unsigned int max_discard_sectors); extern void blk_queue_max_write_same_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_max_write_zeroes_sectors(struct request_queue *q, unsigned int max_write_same_sectors); extern void blk_queue_logical_block_size(struct request_queue *, unsigned int); extern void blk_queue_physical_block_size(struct request_queue *, unsigned int); extern void blk_queue_alignment_offset(struct request_queue *q, unsigned int alignment); extern void blk_limits_io_min(struct queue_limits *limits, unsigned int min); extern void blk_queue_io_min(struct request_queue *q, unsigned int min); extern void blk_limits_io_opt(struct queue_limits *limits, unsigned int opt); extern void blk_queue_io_opt(struct request_queue *q, unsigned int opt); extern void blk_set_queue_depth(struct request_queue *q, unsigned int depth); extern void blk_set_default_limits(struct queue_limits *lim); 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); extern int bdev_stack_limits(struct queue_limits *t, struct block_device *bdev, sector_t offset); extern void disk_stack_limits(struct gendisk *disk, struct block_device *bdev, sector_t offset); extern void blk_queue_stack_limits(struct request_queue *t, struct request_queue *b); extern void blk_queue_update_dma_pad(struct request_queue *, unsigned int); extern int blk_queue_dma_drain(struct request_queue *q, dma_drain_needed_fn *dma_drain_needed, void *buf, unsigned int size); extern void blk_queue_segment_boundary(struct request_queue *, unsigned long); extern void blk_queue_virt_boundary(struct request_queue *, unsigned long); extern void blk_queue_dma_alignment(struct request_queue *, int); extern void blk_queue_update_dma_alignment(struct request_queue *, int); extern void blk_queue_rq_timeout(struct request_queue *, unsigned int); extern void blk_queue_write_cache(struct request_queue *q, bool enabled, bool fua); extern void blk_queue_required_elevator_features(struct request_queue *q, unsigned int features); extern bool blk_queue_can_use_dma_map_merging(struct request_queue *q, struct device *dev); /* * Number of physical segments as sent to the device. * * Normally this is the number of discontiguous data segments sent by the * submitter. But for data-less command like discard we might have no * actual data segments submitted, but the driver might have to add it's * own special payload. In that case we still return 1 here so that this * special payload will be mapped. */ static inline unsigned short blk_rq_nr_phys_segments(struct request *rq) { if (rq->rq_flags & RQF_SPECIAL_PAYLOAD) return 1; return rq->nr_phys_segments; } /* * Number of discard segments (or ranges) the driver needs to fill in. * Each discard bio merged into a request is counted as one segment. */ static inline unsigned short blk_rq_nr_discard_segments(struct request *rq) { return max_t(unsigned short, rq->nr_phys_segments, 1); } extern int blk_rq_map_sg(struct request_queue *, struct request *, struct scatterlist *); extern void blk_dump_rq_flags(struct request *, char *); extern long nr_blockdev_pages(void); bool __must_check blk_get_queue(struct request_queue *); struct request_queue *blk_alloc_queue(gfp_t); struct request_queue *blk_alloc_queue_node(gfp_t gfp_mask, int node_id); extern void blk_put_queue(struct request_queue *); extern void blk_set_queue_dying(struct request_queue *); /* * 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, because blk_schedule_flush_list() will only flush * the plug list when the task sleeps by itself. For details, please see * schedule() where blk_schedule_flush_plug() is called. */ struct blk_plug { struct list_head mq_list; /* blk-mq requests */ struct list_head cb_list; /* md requires an unplug callback */ unsigned short rq_count; bool multiple_queues; }; #define BLK_MAX_REQUEST_COUNT 16 #define BLK_PLUG_FLUSH_SIZE (128 * 1024) 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_finish_plug(struct blk_plug *); extern void blk_flush_plug_list(struct blk_plug *, bool); static inline void blk_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, false); } static inline void blk_schedule_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; if (plug) blk_flush_plug_list(plug, true); } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { struct blk_plug *plug = tsk->plug; return plug && (!list_empty(&plug->mq_list) || !list_empty(&plug->cb_list)); } extern int blkdev_issue_flush(struct block_device *, gfp_t, sector_t *); extern int blkdev_issue_write_same(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, struct page *page); #define BLKDEV_DISCARD_SECURE (1 << 0) /* issue a secure erase */ extern int blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, unsigned long flags); extern int __blkdev_issue_discard(struct block_device *bdev, sector_t sector, sector_t nr_sects, gfp_t gfp_mask, int flags, struct bio **biop); #define BLKDEV_ZERO_NOUNMAP (1 << 0) /* do not free blocks */ #define BLKDEV_ZERO_NOFALLBACK (1 << 1) /* don't write explicit zeroes */ 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, flags); } 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); } extern int blk_verify_command(unsigned char *cmd, fmode_t mode); enum blk_default_limits { BLK_MAX_SEGMENTS = 128, BLK_SAFE_MAX_SECTORS = 255, BLK_DEF_MAX_SECTORS = 2560, BLK_MAX_SEGMENT_SIZE = 65536, BLK_SEG_BOUNDARY_MASK = 0xFFFFFFFFUL, }; 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_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 unsigned queue_logical_block_size(const struct request_queue *q) { int retval = 512; if (q && q->limits.logical_block_size) retval = q->limits.logical_block_size; return retval; } 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 int bdev_io_opt(struct block_device *bdev) { return queue_io_opt(bdev_get_queue(bdev)); } static inline int queue_alignment_offset(const struct request_queue *q) { if (q->limits.misaligned) return -1; return q->limits.alignment_offset; } static inline int queue_limit_alignment_offset(struct queue_limits *lim, sector_t sector) { unsigned int granularity = max(lim->physical_block_size, lim->io_min); unsigned int alignment = sector_div(sector, granularity >> SECTOR_SHIFT) << SECTOR_SHIFT; return (granularity + lim->alignment_offset - alignment) % granularity; } static inline int bdev_alignment_offset(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q->limits.misaligned) return -1; if (bdev != bdev->bd_contains) return bdev->bd_part->alignment_offset; return q->limits.alignment_offset; } static inline int queue_discard_alignment(const struct request_queue *q) { if (q->limits.discard_misaligned) return -1; return q->limits.discard_alignment; } static inline int queue_limit_discard_alignment(struct queue_limits *lim, sector_t sector) { unsigned int alignment, granularity, offset; if (!lim->max_discard_sectors) return 0; /* Why are these in bytes, not sectors? */ alignment = lim->discard_alignment >> SECTOR_SHIFT; granularity = lim->discard_granularity >> SECTOR_SHIFT; if (!granularity) return 0; /* Offset of the partition start in 'granularity' sectors */ offset = sector_div(sector, granularity); /* And why do we do this modulus *again* in blkdev_issue_discard()? */ offset = (granularity + alignment - offset) % granularity; /* Turn it back into bytes, gaah */ return offset << SECTOR_SHIFT; } /* * Two cases of handling DISCARD merge: * If max_discard_segments > 1, the driver takes every bio * as a range and send them to controller together. The ranges * needn't to be contiguous. * Otherwise, the bios/requests will be handled as same as * others which should be contiguous. */ static inline bool blk_discard_mergable(struct request *req) { if (req_op(req) == REQ_OP_DISCARD && queue_max_discard_segments(req->q) > 1) return true; return false; } static inline int bdev_discard_alignment(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (bdev != bdev->bd_contains) return bdev->bd_part->discard_alignment; return q->limits.discard_alignment; } static inline unsigned int bdev_write_same(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_same_sectors; return 0; } static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return q->limits.max_write_zeroes_sectors; return 0; } static inline enum blk_zoned_model bdev_zoned_model(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zoned_model(q); return BLK_ZONED_NONE; } static inline bool bdev_is_zoned(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_is_zoned(q); return false; } static inline sector_t bdev_zone_sectors(struct block_device *bdev) { struct request_queue *q = bdev_get_queue(bdev); if (q) return blk_queue_zone_sectors(q); return 0; } static inline int queue_dma_alignment(const struct request_queue *q) { return q ? q->dma_alignment : 511; } static inline int blk_rq_aligned(struct request_queue *q, unsigned long addr, unsigned int len) { unsigned int alignment = queue_dma_alignment(q) | q->dma_pad_mask; return !(addr & alignment) && !(len & alignment); } /* assumes size > 256 */ static inline unsigned int blksize_bits(unsigned int size) { unsigned int bits = 8; do { bits++; size >>= 1; } while (size > 256); return bits; } static inline unsigned int block_size(struct block_device *bdev) { return bdev->bd_block_size; } typedef struct {struct page *v;} Sector; unsigned char *read_dev_sector(struct block_device *, sector_t, Sector *); static inline void put_dev_sector(Sector p) { put_page(p.v); } int kblockd_schedule_work(struct work_struct *work); int kblockd_schedule_work_on(int cpu, 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) "-*") #if defined(CONFIG_BLK_DEV_INTEGRITY) enum blk_integrity_flags { BLK_INTEGRITY_VERIFY = 1 << 0, BLK_INTEGRITY_GENERATE = 1 << 1, BLK_INTEGRITY_DEVICE_CAPABLE = 1 << 2, BLK_INTEGRITY_IP_CHECKSUM = 1 << 3, }; struct blk_integrity_iter { void *prot_buf; void *data_buf; sector_t seed; unsigned int data_size; unsigned short interval; const char *disk_name; }; typedef blk_status_t (integrity_processing_fn) (struct blk_integrity_iter *); typedef void (integrity_prepare_fn) (struct request *); typedef void (integrity_complete_fn) (struct request *, unsigned int); struct blk_integrity_profile { integrity_processing_fn *generate_fn; integrity_processing_fn *verify_fn; integrity_prepare_fn *prepare_fn; integrity_complete_fn *complete_fn; const char *name; }; extern void blk_integrity_register(struct gendisk *, struct blk_integrity *); extern void blk_integrity_unregister(struct gendisk *); extern int blk_integrity_compare(struct gendisk *, struct gendisk *); extern int blk_rq_map_integrity_sg(struct request_queue *, struct bio *, struct scatterlist *); extern int blk_rq_count_integrity_sg(struct request_queue *, struct bio *); extern bool blk_integrity_merge_rq(struct request_queue *, struct request *, struct request *); extern bool blk_integrity_merge_bio(struct request_queue *, struct request *, struct bio *); static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { struct blk_integrity *bi = &disk->queue->integrity; if (!bi->profile) return NULL; return bi; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *bdev) { return blk_get_integrity(bdev->bd_disk); } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return q->integrity.profile; } static inline bool blk_integrity_rq(struct request *rq) { return rq->cmd_flags & REQ_INTEGRITY; } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { q->limits.max_integrity_segments = segs; } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return q->limits.max_integrity_segments; } /** * bio_integrity_intervals - Return number of integrity intervals for a bio * @bi: blk_integrity profile for device * @sectors: Size of the bio in 512-byte sectors * * Description: The block layer calculates everything in 512 byte * sectors but integrity metadata is done in terms of the data integrity * interval size of the storage device. Convert the block layer sectors * to the appropriate number of integrity intervals. */ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return sectors >> (bi->interval_exp - 9); } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return bio_integrity_intervals(bi, sectors) * bi->tuple_size; } /* * Return the first bvec that contains integrity data. Only drivers that are * limited to a single integrity segment should use this helper. */ static inline struct bio_vec *rq_integrity_vec(struct request *rq) { if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1)) return NULL; return rq->bio->bi_integrity->bip_vec; } #else /* CONFIG_BLK_DEV_INTEGRITY */ struct bio; struct block_device; struct gendisk; struct blk_integrity; static inline int blk_integrity_rq(struct request *rq) { return 0; } static inline int blk_rq_count_integrity_sg(struct request_queue *q, struct bio *b) { return 0; } static inline int blk_rq_map_integrity_sg(struct request_queue *q, struct bio *b, struct scatterlist *s) { return 0; } static inline struct blk_integrity *bdev_get_integrity(struct block_device *b) { return NULL; } static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk) { return NULL; } static inline bool blk_integrity_queue_supports_integrity(struct request_queue *q) { return false; } static inline int blk_integrity_compare(struct gendisk *a, struct gendisk *b) { return 0; } static inline void blk_integrity_register(struct gendisk *d, struct blk_integrity *b) { } static inline void blk_integrity_unregister(struct gendisk *d) { } static inline void blk_queue_max_integrity_segments(struct request_queue *q, unsigned int segs) { } static inline unsigned short queue_max_integrity_segments(const struct request_queue *q) { return 0; } static inline bool blk_integrity_merge_rq(struct request_queue *rq, struct request *r1, struct request *r2) { return true; } static inline bool blk_integrity_merge_bio(struct request_queue *rq, struct request *r, struct bio *b) { return true; } static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi, unsigned int sectors) { return 0; } static inline struct bio_vec *rq_integrity_vec(struct request *rq) { return NULL; } #endif /* CONFIG_BLK_DEV_INTEGRITY */ #ifdef CONFIG_BLK_INLINE_ENCRYPTION bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q); void blk_ksm_unregister(struct request_queue *q); #else /* CONFIG_BLK_INLINE_ENCRYPTION */ static inline bool blk_ksm_register(struct blk_keyslot_manager *ksm, struct request_queue *q) { return true; } static inline void blk_ksm_unregister(struct request_queue *q) { } #endif /* CONFIG_BLK_INLINE_ENCRYPTION */ struct block_device_operations { int (*open) (struct block_device *, fmode_t); void (*release) (struct gendisk *, fmode_t); int (*rw_page)(struct block_device *, sector_t, struct page *, unsigned int); int (*ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); int (*compat_ioctl) (struct block_device *, fmode_t, unsigned, unsigned long); unsigned int (*check_events) (struct gendisk *disk, unsigned int clearing); /* ->media_changed() is DEPRECATED, use ->check_events() instead */ int (*media_changed) (struct gendisk *); void (*unlock_native_capacity) (struct gendisk *); int (*revalidate_disk) (struct gendisk *); int (*getgeo)(struct block_device *, struct hd_geometry *); /* 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, report_zones_cb cb, void *data); struct module *owner; const struct pr_ops *pr_ops; ANDROID_KABI_RESERVE(1); ANDROID_KABI_RESERVE(2); }; extern int __blkdev_driver_ioctl(struct block_device *, fmode_t, unsigned int, unsigned long); extern int bdev_read_page(struct block_device *, sector_t, struct page *); extern int bdev_write_page(struct block_device *, sector_t, struct page *, struct writeback_control *); #ifdef CONFIG_BLK_DEV_ZONED bool blk_req_needs_zone_write_lock(struct request *rq); void __blk_req_zone_write_lock(struct request *rq); void __blk_req_zone_write_unlock(struct request *rq); static inline void blk_req_zone_write_lock(struct request *rq) { if (blk_req_needs_zone_write_lock(rq)) __blk_req_zone_write_lock(rq); } static inline void blk_req_zone_write_unlock(struct request *rq) { if (rq->rq_flags & RQF_ZONE_WRITE_LOCKED) __blk_req_zone_write_unlock(rq); } static inline bool blk_req_zone_is_write_locked(struct request *rq) { return rq->q->seq_zones_wlock && test_bit(blk_rq_zone_no(rq), rq->q->seq_zones_wlock); } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) { if (!blk_req_needs_zone_write_lock(rq)) return true; return !blk_req_zone_is_write_locked(rq); } #else static inline bool blk_req_needs_zone_write_lock(struct request *rq) { return false; } static inline void blk_req_zone_write_lock(struct request *rq) { } static inline void blk_req_zone_write_unlock(struct request *rq) { } static inline bool blk_req_zone_is_write_locked(struct request *rq) { return false; } static inline bool blk_req_can_dispatch_to_zone(struct request *rq) { return true; } #endif /* CONFIG_BLK_DEV_ZONED */ #else /* CONFIG_BLOCK */ struct block_device; /* * stubs for when the block layer is configured out */ #define buffer_heads_over_limit 0 static inline long nr_blockdev_pages(void) { return 0; } struct blk_plug { }; 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 task_struct *task) { } static inline void blk_schedule_flush_plug(struct task_struct *task) { } static inline bool blk_needs_flush_plug(struct task_struct *tsk) { return false; } static inline int blkdev_issue_flush(struct block_device *bdev, gfp_t gfp_mask, sector_t *error_sector) { return 0; } #endif /* CONFIG_BLOCK */ 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); } #endif |
| 53 74 74 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Internal procfs definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/proc_fs.h> #include <linux/proc_ns.h> #include <linux/refcount.h> #include <linux/spinlock.h> #include <linux/atomic.h> #include <linux/binfmts.h> #include <linux/sched/coredump.h> #include <linux/sched/task.h> struct ctl_table_header; struct mempolicy; /* * This is not completely implemented yet. The idea is to * create an in-memory tree (like the actual /proc filesystem * tree) of these proc_dir_entries, so that we can dynamically * add new files to /proc. * * parent/subdir are used for the directory structure (every /proc file has a * parent, but "subdir" is empty for all non-directory entries). * subdir_node is used to build the rb tree "subdir" of the parent. */ struct proc_dir_entry { /* * number of callers into module in progress; * negative -> it's going away RSN */ atomic_t in_use; refcount_t refcnt; struct list_head pde_openers; /* who did ->open, but not ->release */ /* protects ->pde_openers and all struct pde_opener instances */ spinlock_t pde_unload_lock; struct completion *pde_unload_completion; const struct inode_operations *proc_iops; const struct file_operations *proc_fops; const struct dentry_operations *proc_dops; union { const struct seq_operations *seq_ops; int (*single_show)(struct seq_file *, void *); }; proc_write_t write; void *data; unsigned int state_size; unsigned int low_ino; nlink_t nlink; kuid_t uid; kgid_t gid; loff_t size; struct proc_dir_entry *parent; struct rb_root subdir; struct rb_node subdir_node; char *name; umode_t mode; u8 namelen; char inline_name[]; } __randomize_layout; #define SIZEOF_PDE ( \ sizeof(struct proc_dir_entry) < 128 ? 128 : \ sizeof(struct proc_dir_entry) < 192 ? 192 : \ sizeof(struct proc_dir_entry) < 256 ? 256 : \ sizeof(struct proc_dir_entry) < 512 ? 512 : \ 0) #define SIZEOF_PDE_INLINE_NAME (SIZEOF_PDE - sizeof(struct proc_dir_entry)) extern struct kmem_cache *proc_dir_entry_cache; void pde_free(struct proc_dir_entry *pde); union proc_op { int (*proc_get_link)(struct dentry *, struct path *); int (*proc_show)(struct seq_file *m, struct pid_namespace *ns, struct pid *pid, struct task_struct *task); const char *lsm; }; struct proc_inode { struct pid *pid; unsigned int fd; union proc_op op; struct proc_dir_entry *pde; struct ctl_table_header *sysctl; struct ctl_table *sysctl_entry; struct hlist_node sysctl_inodes; const struct proc_ns_operations *ns_ops; struct inode vfs_inode; } __randomize_layout; /* * General functions */ static inline struct proc_inode *PROC_I(const struct inode *inode) { return container_of(inode, struct proc_inode, vfs_inode); } static inline struct proc_dir_entry *PDE(const struct inode *inode) { return PROC_I(inode)->pde; } static inline void *__PDE_DATA(const struct inode *inode) { return PDE(inode)->data; } static inline struct pid *proc_pid(const struct inode *inode) { return PROC_I(inode)->pid; } static inline struct task_struct *get_proc_task(const struct inode *inode) { return get_pid_task(proc_pid(inode), PIDTYPE_PID); } void task_dump_owner(struct task_struct *task, umode_t mode, kuid_t *ruid, kgid_t *rgid); unsigned name_to_int(const struct qstr *qstr); /* * Offset of the first process in the /proc root directory.. */ #define FIRST_PROCESS_ENTRY 256 /* Worst case buffer size needed for holding an integer. */ #define PROC_NUMBUF 13 /* * array.c */ extern const struct file_operations proc_tid_children_operations; extern void proc_task_name(struct seq_file *m, struct task_struct *p, bool escape); extern int proc_tid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_tgid_stat(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_pid_status(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); extern int proc_pid_statm(struct seq_file *, struct pid_namespace *, struct pid *, struct task_struct *); /* * base.c */ extern const struct dentry_operations pid_dentry_operations; extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int); extern int proc_setattr(struct dentry *, struct iattr *); extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t); extern void pid_update_inode(struct task_struct *, struct inode *); extern int pid_delete_dentry(const struct dentry *); extern int proc_pid_readdir(struct file *, struct dir_context *); struct dentry *proc_pid_lookup(struct dentry *, unsigned int); extern loff_t mem_lseek(struct file *, loff_t, int); /* Lookups */ typedef struct dentry *instantiate_t(struct dentry *, struct task_struct *, const void *); bool proc_fill_cache(struct file *, struct dir_context *, const char *, unsigned int, instantiate_t, struct task_struct *, const void *); /* * generic.c */ struct proc_dir_entry *proc_create_reg(const char *name, umode_t mode, struct proc_dir_entry **parent, void *data); struct proc_dir_entry *proc_register(struct proc_dir_entry *dir, struct proc_dir_entry *dp); extern struct dentry *proc_lookup(struct inode *, struct dentry *, unsigned int); struct dentry *proc_lookup_de(struct inode *, struct dentry *, struct proc_dir_entry *); extern int proc_readdir(struct file *, struct dir_context *); int proc_readdir_de(struct file *, struct dir_context *, struct proc_dir_entry *); static inline struct proc_dir_entry *pde_get(struct proc_dir_entry *pde) { refcount_inc(&pde->refcnt); return pde; } extern void pde_put(struct proc_dir_entry *); static inline bool is_empty_pde(const struct proc_dir_entry *pde) { return S_ISDIR(pde->mode) && !pde->proc_iops; } extern ssize_t proc_simple_write(struct file *, const char __user *, size_t, loff_t *); /* * inode.c */ struct pde_opener { struct file *file; struct list_head lh; bool closing; struct completion *c; } __randomize_layout; extern const struct inode_operations proc_link_inode_operations; extern const struct inode_operations proc_pid_link_inode_operations; extern const struct super_operations proc_sops; void proc_init_kmemcache(void); void set_proc_pid_nlink(void); extern struct inode *proc_get_inode(struct super_block *, struct proc_dir_entry *); extern void proc_entry_rundown(struct proc_dir_entry *); /* * proc_namespaces.c */ extern const struct inode_operations proc_ns_dir_inode_operations; extern const struct file_operations proc_ns_dir_operations; /* * proc_net.c */ extern const struct file_operations proc_net_operations; extern const struct inode_operations proc_net_inode_operations; #ifdef CONFIG_NET extern int proc_net_init(void); #else static inline int proc_net_init(void) { return 0; } #endif /* * proc_self.c */ extern int proc_setup_self(struct super_block *); /* * proc_thread_self.c */ extern int proc_setup_thread_self(struct super_block *); extern void proc_thread_self_init(void); /* * proc_sysctl.c */ #ifdef CONFIG_PROC_SYSCTL extern int proc_sys_init(void); extern void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head); #else static inline void proc_sys_init(void) { } static inline void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head) { } #endif /* * proc_tty.c */ #ifdef CONFIG_TTY extern void proc_tty_init(void); #else static inline void proc_tty_init(void) {} #endif /* * root.c */ extern struct proc_dir_entry proc_root; extern void proc_self_init(void); /* * task_[no]mmu.c */ struct mem_size_stats; struct proc_maps_private { struct inode *inode; struct task_struct *task; struct mm_struct *mm; #ifdef CONFIG_MMU struct vm_area_struct *tail_vma; #endif #ifdef CONFIG_NUMA struct mempolicy *task_mempolicy; #endif } __randomize_layout; struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode); extern const struct file_operations proc_pid_maps_operations; extern const struct file_operations proc_pid_numa_maps_operations; extern const struct file_operations proc_pid_smaps_operations; extern const struct file_operations proc_pid_smaps_rollup_operations; extern const struct file_operations proc_clear_refs_operations; extern const struct file_operations proc_pagemap_operations; extern unsigned long task_vsize(struct mm_struct *); extern unsigned long task_statm(struct mm_struct *, unsigned long *, unsigned long *, unsigned long *, unsigned long *); extern void task_mem(struct seq_file *, struct mm_struct *); extern const struct dentry_operations proc_net_dentry_ops; static inline void pde_force_lookup(struct proc_dir_entry *pde) { /* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */ pde->proc_dops = &proc_net_dentry_ops; } |
| 299 272 266 181 8 180 19 395 394 395 80 81 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 | // SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/rmap.h> #include <linux/interval_tree_generic.h> static inline unsigned long vma_start_pgoff(struct vm_area_struct *v) { return v->vm_pgoff; } static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) { return v->vm_pgoff + vma_pages(v) - 1; } INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff,, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ void vma_interval_tree_insert_after(struct vm_area_struct *node, struct vm_area_struct *prev, struct rb_root_cached *root) { struct rb_node **link; struct vm_area_struct *parent; unsigned long last = vma_last_pgoff(node); VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); if (!prev->shared.rb.rb_right) { parent = prev; link = &prev->shared.rb.rb_right; } else { parent = rb_entry(prev->shared.rb.rb_right, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; while (parent->shared.rb.rb_left) { parent = rb_entry(parent->shared.rb.rb_left, struct vm_area_struct, shared.rb); if (parent->shared.rb_subtree_last < last) parent->shared.rb_subtree_last = last; } link = &parent->shared.rb.rb_left; } node->shared.rb_subtree_last = last; rb_link_node(&node->shared.rb, &parent->shared.rb, link); rb_insert_augmented(&node->shared.rb, &root->rb_root, &vma_interval_tree_augment); } static inline unsigned long avc_start_pgoff(struct anon_vma_chain *avc) { return vma_start_pgoff(avc->vma); } static inline unsigned long avc_last_pgoff(struct anon_vma_chain *avc) { return vma_last_pgoff(avc->vma); } INTERVAL_TREE_DEFINE(struct anon_vma_chain, rb, unsigned long, rb_subtree_last, avc_start_pgoff, avc_last_pgoff, static inline, __anon_vma_interval_tree) void anon_vma_interval_tree_insert(struct anon_vma_chain *node, struct rb_root_cached *root) { #ifdef CONFIG_DEBUG_VM_RB node->cached_vma_start = avc_start_pgoff(node); node->cached_vma_last = avc_last_pgoff(node); #endif __anon_vma_interval_tree_insert(node, root); } void anon_vma_interval_tree_remove(struct anon_vma_chain *node, struct rb_root_cached *root) { __anon_vma_interval_tree_remove(node, root); } struct anon_vma_chain * anon_vma_interval_tree_iter_first(struct rb_root_cached *root, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_first(root, first, last); } struct anon_vma_chain * anon_vma_interval_tree_iter_next(struct anon_vma_chain *node, unsigned long first, unsigned long last) { return __anon_vma_interval_tree_iter_next(node, first, last); } #ifdef CONFIG_DEBUG_VM_RB void anon_vma_interval_tree_verify(struct anon_vma_chain *node) { WARN_ON_ONCE(node->cached_vma_start != avc_start_pgoff(node)); WARN_ON_ONCE(node->cached_vma_last != avc_last_pgoff(node)); } #endif |
| 15 10 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Handle incoming frames * Linux ethernet bridge * * Authors: * Lennert Buytenhek <buytenh@gnu.org> */ #include <linux/slab.h> #include <linux/kernel.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> #include <linux/netfilter_bridge.h> #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE #include <net/netfilter/nf_queue.h> #endif #include <linux/neighbour.h> #include <net/arp.h> #include <linux/export.h> #include <linux/rculist.h> #include "br_private.h" #include "br_private_tunnel.h" static int br_netif_receive_skb(struct net *net, struct sock *sk, struct sk_buff *skb) { br_drop_fake_rtable(skb); return netif_receive_skb(skb); } static int br_pass_frame_up(struct sk_buff *skb) { struct net_device *indev, *brdev = BR_INPUT_SKB_CB(skb)->brdev; struct net_bridge *br = netdev_priv(brdev); struct net_bridge_vlan_group *vg; struct pcpu_sw_netstats *brstats = this_cpu_ptr(br->stats); u64_stats_update_begin(&brstats->syncp); brstats->rx_packets++; brstats->rx_bytes += skb->len; u64_stats_update_end(&brstats->syncp); vg = br_vlan_group_rcu(br); /* Reset the offload_fwd_mark because there could be a stacked * bridge above, and it should not think this bridge it doing * that bridge's work forwarding out its ports. */ br_switchdev_frame_unmark(skb); /* Bridge is just like any other port. Make sure the * packet is allowed except in promisc modue when someone * may be running packet capture. */ if (!(brdev->flags & IFF_PROMISC) && !br_allowed_egress(vg, skb)) { kfree_skb(skb); return NET_RX_DROP; } indev = skb->dev; skb->dev = brdev; skb = br_handle_vlan(br, NULL, vg, skb); if (!skb) return NET_RX_DROP; /* update the multicast stats if the packet is IGMP/MLD */ br_multicast_count(br, NULL, skb, br_multicast_igmp_type(skb), BR_MCAST_DIR_TX); return NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(indev), NULL, skb, indev, NULL, br_netif_receive_skb); } /* note: already called with rcu_read_lock */ int br_handle_frame_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); enum br_pkt_type pkt_type = BR_PKT_UNICAST; struct net_bridge_fdb_entry *dst = NULL; struct net_bridge_mdb_entry *mdst; bool local_rcv, mcast_hit = false; struct net_bridge *br; u16 vid = 0; if (!p || p->state == BR_STATE_DISABLED) goto drop; if (!br_allowed_ingress(p->br, nbp_vlan_group_rcu(p), skb, &vid)) goto out; nbp_switchdev_frame_mark(p, skb); /* insert into forwarding database after filtering to avoid spoofing */ br = p->br; if (p->flags & BR_LEARNING) br_fdb_update(br, p, eth_hdr(skb)->h_source, vid, false); local_rcv = !!(br->dev->flags & IFF_PROMISC); if (is_multicast_ether_addr(eth_hdr(skb)->h_dest)) { /* by definition the broadcast is also a multicast address */ if (is_broadcast_ether_addr(eth_hdr(skb)->h_dest)) { pkt_type = BR_PKT_BROADCAST; local_rcv = true; } else { pkt_type = BR_PKT_MULTICAST; if (br_multicast_rcv(br, p, skb, vid)) goto drop; } } if (p->state == BR_STATE_LEARNING) goto drop; BR_INPUT_SKB_CB(skb)->brdev = br->dev; BR_INPUT_SKB_CB(skb)->src_port_isolated = !!(p->flags & BR_ISOLATED); if (IS_ENABLED(CONFIG_INET) && (skb->protocol == htons(ETH_P_ARP) || skb->protocol == htons(ETH_P_RARP))) { br_do_proxy_suppress_arp(skb, br, vid, p); } else if (IS_ENABLED(CONFIG_IPV6) && skb->protocol == htons(ETH_P_IPV6) && br_opt_get(br, BROPT_NEIGH_SUPPRESS_ENABLED) && pskb_may_pull(skb, sizeof(struct ipv6hdr) + sizeof(struct nd_msg)) && ipv6_hdr(skb)->nexthdr == IPPROTO_ICMPV6) { struct nd_msg *msg, _msg; msg = br_is_nd_neigh_msg(skb, &_msg); if (msg) br_do_suppress_nd(skb, br, vid, p, msg); } switch (pkt_type) { case BR_PKT_MULTICAST: mdst = br_mdb_get(br, skb, vid); if ((mdst || BR_INPUT_SKB_CB_MROUTERS_ONLY(skb)) && br_multicast_querier_exists(br, eth_hdr(skb))) { if ((mdst && mdst->host_joined) || br_multicast_is_router(br)) { local_rcv = true; br->dev->stats.multicast++; } mcast_hit = true; } else { local_rcv = true; br->dev->stats.multicast++; } break; case BR_PKT_UNICAST: dst = br_fdb_find_rcu(br, eth_hdr(skb)->h_dest, vid); default: break; } if (dst) { unsigned long now = jiffies; if (test_bit(BR_FDB_LOCAL, &dst->flags)) return br_pass_frame_up(skb); if (now != dst->used) dst->used = now; br_forward(dst->dst, skb, local_rcv, false); } else { if (!mcast_hit) br_flood(br, skb, pkt_type, local_rcv, false); else br_multicast_flood(mdst, skb, local_rcv, false); } if (local_rcv) return br_pass_frame_up(skb); out: return 0; drop: kfree_skb(skb); goto out; } EXPORT_SYMBOL_GPL(br_handle_frame_finish); static void __br_handle_local_finish(struct sk_buff *skb) { struct net_bridge_port *p = br_port_get_rcu(skb->dev); u16 vid = 0; /* check if vlan is allowed, to avoid spoofing */ if ((p->flags & BR_LEARNING) && !br_opt_get(p->br, BROPT_NO_LL_LEARN) && br_should_learn(p, skb, &vid)) br_fdb_update(p->br, p, eth_hdr(skb)->h_source, vid, false); } /* note: already called with rcu_read_lock */ static int br_handle_local_finish(struct net *net, struct sock *sk, struct sk_buff *skb) { __br_handle_local_finish(skb); /* return 1 to signal the okfn() was called so it's ok to use the skb */ return 1; } static int nf_hook_bridge_pre(struct sk_buff *skb, struct sk_buff **pskb) { #ifdef CONFIG_NETFILTER_FAMILY_BRIDGE struct nf_hook_entries *e = NULL; struct nf_hook_state state; unsigned int verdict, i; struct net *net; int ret; net = dev_net(skb->dev); #ifdef HAVE_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_BRIDGE][NF_BR_PRE_ROUTING])) goto frame_finish; #endif e = rcu_dereference(net->nf.hooks_bridge[NF_BR_PRE_ROUTING]); if (!e) goto frame_finish; nf_hook_state_init(&state, NF_BR_PRE_ROUTING, NFPROTO_BRIDGE, skb->dev, NULL, NULL, net, br_handle_frame_finish); for (i = 0; i < e->num_hook_entries; i++) { verdict = nf_hook_entry_hookfn(&e->hooks[i], skb, &state); switch (verdict & NF_VERDICT_MASK) { case NF_ACCEPT: if (BR_INPUT_SKB_CB(skb)->br_netfilter_broute) { *pskb = skb; return RX_HANDLER_PASS; } break; case NF_DROP: kfree_skb(skb); return RX_HANDLER_CONSUMED; case NF_QUEUE: ret = nf_queue(skb, &state, i, verdict); if (ret == 1) continue; return RX_HANDLER_CONSUMED; default: /* STOLEN */ return RX_HANDLER_CONSUMED; } } frame_finish: net = dev_net(skb->dev); br_handle_frame_finish(net, NULL, skb); #else br_handle_frame_finish(dev_net(skb->dev), NULL, skb); #endif return RX_HANDLER_CONSUMED; } /* * Return NULL if skb is handled * note: already called with rcu_read_lock */ rx_handler_result_t br_handle_frame(struct sk_buff **pskb) { struct net_bridge_port *p; struct sk_buff *skb = *pskb; const unsigned char *dest = eth_hdr(skb)->h_dest; if (unlikely(skb->pkt_type == PACKET_LOOPBACK)) return RX_HANDLER_PASS; if (!is_valid_ether_addr(eth_hdr(skb)->h_source)) goto drop; skb = skb_share_check(skb, GFP_ATOMIC); if (!skb) return RX_HANDLER_CONSUMED; memset(skb->cb, 0, sizeof(struct br_input_skb_cb)); p = br_port_get_rcu(skb->dev); if (p->flags & BR_VLAN_TUNNEL) { if (br_handle_ingress_vlan_tunnel(skb, p, nbp_vlan_group_rcu(p))) goto drop; } if (unlikely(is_link_local_ether_addr(dest))) { u16 fwd_mask = p->br->group_fwd_mask_required; /* * See IEEE 802.1D Table 7-10 Reserved addresses * * Assignment Value * Bridge Group Address 01-80-C2-00-00-00 * (MAC Control) 802.3 01-80-C2-00-00-01 * (Link Aggregation) 802.3 01-80-C2-00-00-02 * 802.1X PAE address 01-80-C2-00-00-03 * * 802.1AB LLDP 01-80-C2-00-00-0E * * Others reserved for future standardization */ fwd_mask |= p->group_fwd_mask; switch (dest[5]) { case 0x00: /* Bridge Group Address */ /* If STP is turned off, then must forward to keep loop detection */ if (p->br->stp_enabled == BR_NO_STP || fwd_mask & (1u << dest[5])) goto forward; *pskb = skb; __br_handle_local_finish(skb); return RX_HANDLER_PASS; case 0x01: /* IEEE MAC (Pause) */ goto drop; case 0x0E: /* 802.1AB LLDP */ fwd_mask |= p->br->group_fwd_mask; if (fwd_mask & (1u << dest[5])) goto forward; *pskb = skb; __br_handle_local_finish(skb); return RX_HANDLER_PASS; default: /* Allow selective forwarding for most other protocols */ fwd_mask |= p->br->group_fwd_mask; if (fwd_mask & (1u << dest[5])) goto forward; } /* The else clause should be hit when nf_hook(): * - returns < 0 (drop/error) * - returns = 0 (stolen/nf_queue) * Thus return 1 from the okfn() to signal the skb is ok to pass */ if (NF_HOOK(NFPROTO_BRIDGE, NF_BR_LOCAL_IN, dev_net(skb->dev), NULL, skb, skb->dev, NULL, br_handle_local_finish) == 1) { return RX_HANDLER_PASS; } else { return RX_HANDLER_CONSUMED; } } forward: switch (p->state) { case BR_STATE_FORWARDING: case BR_STATE_LEARNING: if (ether_addr_equal(p->br->dev->dev_addr, dest)) skb->pkt_type = PACKET_HOST; return nf_hook_bridge_pre(skb, pskb); default: drop: kfree_skb(skb); } return RX_HANDLER_CONSUMED; } |
| 735 196 731 684 735 737 196 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __NET_NETLINK_H #define __NET_NETLINK_H #include <linux/types.h> #include <linux/netlink.h> #include <linux/jiffies.h> #include <linux/in6.h> /* ======================================================================== * Netlink Messages and Attributes Interface (As Seen On TV) * ------------------------------------------------------------------------ * Messages Interface * ------------------------------------------------------------------------ * * Message Format: * <--- nlmsg_total_size(payload) ---> * <-- nlmsg_msg_size(payload) -> * +----------+- - -+-------------+- - -+-------- - - * | nlmsghdr | Pad | Payload | Pad | nlmsghdr * +----------+- - -+-------------+- - -+-------- - - * nlmsg_data(nlh)---^ ^ * nlmsg_next(nlh)-----------------------+ * * Payload Format: * <---------------------- nlmsg_len(nlh) ---------------------> * <------ hdrlen ------> <- nlmsg_attrlen(nlh, hdrlen) -> * +----------------------+- - -+--------------------------------+ * | Family Header | Pad | Attributes | * +----------------------+- - -+--------------------------------+ * nlmsg_attrdata(nlh, hdrlen)---^ * * Data Structures: * struct nlmsghdr netlink message header * * Message Construction: * nlmsg_new() create a new netlink message * nlmsg_put() add a netlink message to an skb * nlmsg_put_answer() callback based nlmsg_put() * nlmsg_end() finalize netlink message * nlmsg_get_pos() return current position in message * nlmsg_trim() trim part of message * nlmsg_cancel() cancel message construction * nlmsg_free() free a netlink message * * Message Sending: * nlmsg_multicast() multicast message to several groups * nlmsg_unicast() unicast a message to a single socket * nlmsg_notify() send notification message * * Message Length Calculations: * nlmsg_msg_size(payload) length of message w/o padding * nlmsg_total_size(payload) length of message w/ padding * nlmsg_padlen(payload) length of padding at tail * * Message Payload Access: * nlmsg_data(nlh) head of message payload * nlmsg_len(nlh) length of message payload * nlmsg_attrdata(nlh, hdrlen) head of attributes data * nlmsg_attrlen(nlh, hdrlen) length of attributes data * * Message Parsing: * nlmsg_ok(nlh, remaining) does nlh fit into remaining bytes? * nlmsg_next(nlh, remaining) get next netlink message * nlmsg_parse() parse attributes of a message * nlmsg_find_attr() find an attribute in a message * nlmsg_for_each_msg() loop over all messages * nlmsg_validate() validate netlink message incl. attrs * nlmsg_for_each_attr() loop over all attributes * * Misc: * nlmsg_report() report back to application? * * ------------------------------------------------------------------------ * Attributes Interface * ------------------------------------------------------------------------ * * Attribute Format: * <------- nla_total_size(payload) -------> * <---- nla_attr_size(payload) -----> * +----------+- - -+- - - - - - - - - +- - -+-------- - - * | Header | Pad | Payload | Pad | Header * +----------+- - -+- - - - - - - - - +- - -+-------- - - * <- nla_len(nla) -> ^ * nla_data(nla)----^ | * nla_next(nla)-----------------------------' * * Data Structures: * struct nlattr netlink attribute header * * Attribute Construction: * nla_reserve(skb, type, len) reserve room for an attribute * nla_reserve_nohdr(skb, len) reserve room for an attribute w/o hdr * nla_put(skb, type, len, data) add attribute to skb * nla_put_nohdr(skb, len, data) add attribute w/o hdr * nla_append(skb, len, data) append data to skb * * Attribute Construction for Basic Types: * nla_put_u8(skb, type, value) add u8 attribute to skb * nla_put_u16(skb, type, value) add u16 attribute to skb * nla_put_u32(skb, type, value) add u32 attribute to skb * nla_put_u64_64bit(skb, type, * value, padattr) add u64 attribute to skb * nla_put_s8(skb, type, value) add s8 attribute to skb * nla_put_s16(skb, type, value) add s16 attribute to skb * nla_put_s32(skb, type, value) add s32 attribute to skb * nla_put_s64(skb, type, value, * padattr) add s64 attribute to skb * nla_put_string(skb, type, str) add string attribute to skb * nla_put_flag(skb, type) add flag attribute to skb * nla_put_msecs(skb, type, jiffies, * padattr) add msecs attribute to skb * nla_put_in_addr(skb, type, addr) add IPv4 address attribute to skb * nla_put_in6_addr(skb, type, addr) add IPv6 address attribute to skb * * Nested Attributes Construction: * nla_nest_start(skb, type) start a nested attribute * nla_nest_end(skb, nla) finalize a nested attribute * nla_nest_cancel(skb, nla) cancel nested attribute construction * * Attribute Length Calculations: * nla_attr_size(payload) length of attribute w/o padding * nla_total_size(payload) length of attribute w/ padding * nla_padlen(payload) length of padding * * Attribute Payload Access: * nla_data(nla) head of attribute payload * nla_len(nla) length of attribute payload * * Attribute Payload Access for Basic Types: * nla_get_u8(nla) get payload for a u8 attribute * nla_get_u16(nla) get payload for a u16 attribute * nla_get_u32(nla) get payload for a u32 attribute * nla_get_u64(nla) get payload for a u64 attribute * nla_get_s8(nla) get payload for a s8 attribute * nla_get_s16(nla) get payload for a s16 attribute * nla_get_s32(nla) get payload for a s32 attribute * nla_get_s64(nla) get payload for a s64 attribute * nla_get_flag(nla) return 1 if flag is true * nla_get_msecs(nla) get payload for a msecs attribute * * Attribute Misc: * nla_memcpy(dest, nla, count) copy attribute into memory * nla_memcmp(nla, data, size) compare attribute with memory area * nla_strlcpy(dst, nla, size) copy attribute to a sized string * nla_strcmp(nla, str) compare attribute with string * * Attribute Parsing: * nla_ok(nla, remaining) does nla fit into remaining bytes? * nla_next(nla, remaining) get next netlink attribute * nla_validate() validate a stream of attributes * nla_validate_nested() validate a stream of nested attributes * nla_find() find attribute in stream of attributes * nla_find_nested() find attribute in nested attributes * nla_parse() parse and validate stream of attrs * nla_parse_nested() parse nested attributes * nla_for_each_attr() loop over all attributes * nla_for_each_nested() loop over the nested attributes *========================================================================= */ /** * Standard attribute types to specify validation policy */ enum { NLA_UNSPEC, NLA_U8, NLA_U16, NLA_U32, NLA_U64, NLA_STRING, NLA_FLAG, NLA_MSECS, NLA_NESTED, NLA_NESTED_ARRAY, NLA_NUL_STRING, NLA_BINARY, NLA_S8, NLA_S16, NLA_S32, NLA_S64, NLA_BITFIELD32, NLA_REJECT, NLA_EXACT_LEN, NLA_EXACT_LEN_WARN, NLA_MIN_LEN, __NLA_TYPE_MAX, }; #define NLA_TYPE_MAX (__NLA_TYPE_MAX - 1) enum nla_policy_validation { NLA_VALIDATE_NONE, NLA_VALIDATE_RANGE, NLA_VALIDATE_MIN, NLA_VALIDATE_MAX, NLA_VALIDATE_FUNCTION, }; /** * struct nla_policy - attribute validation policy * @type: Type of attribute or NLA_UNSPEC * @validation_type: type of attribute validation done in addition to * type-specific validation (e.g. range, function call), see * &enum nla_policy_validation * @len: Type specific length of payload * * Policies are defined as arrays of this struct, the array must be * accessible by attribute type up to the highest identifier to be expected. * * Meaning of `len' field: * NLA_STRING Maximum length of string * NLA_NUL_STRING Maximum length of string (excluding NUL) * NLA_FLAG Unused * NLA_BINARY Maximum length of attribute payload * NLA_MIN_LEN Minimum length of attribute payload * NLA_NESTED, * NLA_NESTED_ARRAY Length verification is done by checking len of * nested header (or empty); len field is used if * validation_data is also used, for the max attr * number in the nested policy. * NLA_U8, NLA_U16, * NLA_U32, NLA_U64, * NLA_S8, NLA_S16, * NLA_S32, NLA_S64, * NLA_MSECS Leaving the length field zero will verify the * given type fits, using it verifies minimum length * just like "All other" * NLA_BITFIELD32 Unused * NLA_REJECT Unused * NLA_EXACT_LEN Attribute must have exactly this length, otherwise * it is rejected. * NLA_EXACT_LEN_WARN Attribute should have exactly this length, a warning * is logged if it is longer, shorter is rejected. * NLA_MIN_LEN Minimum length of attribute payload * All other Minimum length of attribute payload * * Meaning of `validation_data' field: * NLA_BITFIELD32 This is a 32-bit bitmap/bitselector attribute and * validation data must point to a u32 value of valid * flags * NLA_REJECT This attribute is always rejected and validation data * may point to a string to report as the error instead * of the generic one in extended ACK. * NLA_NESTED Points to a nested policy to validate, must also set * `len' to the max attribute number. * Note that nla_parse() will validate, but of course not * parse, the nested sub-policies. * NLA_NESTED_ARRAY Points to a nested policy to validate, must also set * `len' to the max attribute number. The difference to * NLA_NESTED is the structure - NLA_NESTED has the * nested attributes directly inside, while an array has * the nested attributes at another level down and the * attributes directly in the nesting don't matter. * All other Unused - but note that it's a union * * Meaning of `min' and `max' fields, use via NLA_POLICY_MIN, NLA_POLICY_MAX * and NLA_POLICY_RANGE: * NLA_U8, * NLA_U16, * NLA_U32, * NLA_U64, * NLA_S8, * NLA_S16, * NLA_S32, * NLA_S64 These are used depending on the validation_type * field, if that is min/max/range then the minimum, * maximum and both are used (respectively) to check * the value of the integer attribute. * Note that in the interest of code simplicity and * struct size both limits are s16, so you cannot * enforce a range that doesn't fall within the range * of s16 - do that as usual in the code instead. * All other Unused - but note that it's a union * * Meaning of `validate' field, use via NLA_POLICY_VALIDATE_FN: * NLA_BINARY Validation function called for the attribute, * not compatible with use of the validation_data * as in NLA_BITFIELD32, NLA_REJECT, NLA_NESTED and * NLA_NESTED_ARRAY. * All other Unused - but note that it's a union * * Example: * static const struct nla_policy my_policy[ATTR_MAX+1] = { * [ATTR_FOO] = { .type = NLA_U16 }, * [ATTR_BAR] = { .type = NLA_STRING, .len = BARSIZ }, * [ATTR_BAZ] = { .type = NLA_EXACT_LEN, .len = sizeof(struct mystruct) }, * [ATTR_GOO] = { .type = NLA_BITFIELD32, .validation_data = &myvalidflags }, * }; */ struct nla_policy { u8 type; u8 validation_type; u16 len; union { const void *validation_data; struct { s16 min, max; }; int (*validate)(const struct nlattr *attr, struct netlink_ext_ack *extack); /* This entry is special, and used for the attribute at index 0 * only, and specifies special data about the policy, namely it * specifies the "boundary type" where strict length validation * starts for any attribute types >= this value, also, strict * nesting validation starts here. * * Additionally, it means that NLA_UNSPEC is actually NLA_REJECT * for any types >= this, so need to use NLA_MIN_LEN to get the * previous pure { .len = xyz } behaviour. The advantage of this * is that types not specified in the policy will be rejected. * * For completely new families it should be set to 1 so that the * validation is enforced for all attributes. For existing ones * it should be set at least when new attributes are added to * the enum used by the policy, and be set to the new value that * was added to enforce strict validation from thereon. */ u16 strict_start_type; }; }; #define NLA_POLICY_EXACT_LEN(_len) { .type = NLA_EXACT_LEN, .len = _len } #define NLA_POLICY_EXACT_LEN_WARN(_len) { .type = NLA_EXACT_LEN_WARN, \ .len = _len } #define NLA_POLICY_MIN_LEN(_len) { .type = NLA_MIN_LEN, .len = _len } #define NLA_POLICY_ETH_ADDR NLA_POLICY_EXACT_LEN(ETH_ALEN) #define NLA_POLICY_ETH_ADDR_COMPAT NLA_POLICY_EXACT_LEN_WARN(ETH_ALEN) #define _NLA_POLICY_NESTED(maxattr, policy) \ { .type = NLA_NESTED, .validation_data = policy, .len = maxattr } #define _NLA_POLICY_NESTED_ARRAY(maxattr, policy) \ { .type = NLA_NESTED_ARRAY, .validation_data = policy, .len = maxattr } #define NLA_POLICY_NESTED(policy) \ _NLA_POLICY_NESTED(ARRAY_SIZE(policy) - 1, policy) #define NLA_POLICY_NESTED_ARRAY(policy) \ _NLA_POLICY_NESTED_ARRAY(ARRAY_SIZE(policy) - 1, policy) #define __NLA_ENSURE(condition) BUILD_BUG_ON_ZERO(!(condition)) #define NLA_ENSURE_INT_TYPE(tp) \ (__NLA_ENSURE(tp == NLA_S8 || tp == NLA_U8 || \ tp == NLA_S16 || tp == NLA_U16 || \ tp == NLA_S32 || tp == NLA_U32 || \ tp == NLA_S64 || tp == NLA_U64) + tp) #define NLA_ENSURE_NO_VALIDATION_PTR(tp) \ (__NLA_ENSURE(tp != NLA_BITFIELD32 && \ tp != NLA_REJECT && \ tp != NLA_NESTED && \ tp != NLA_NESTED_ARRAY) + tp) #define NLA_POLICY_RANGE(tp, _min, _max) { \ .type = NLA_ENSURE_INT_TYPE(tp), \ .validation_type = NLA_VALIDATE_RANGE, \ .min = _min, \ .max = _max \ } #define NLA_POLICY_MIN(tp, _min) { \ .type = NLA_ENSURE_INT_TYPE(tp), \ .validation_type = NLA_VALIDATE_MIN, \ .min = _min, \ } #define NLA_POLICY_MAX(tp, _max) { \ .type = NLA_ENSURE_INT_TYPE(tp), \ .validation_type = NLA_VALIDATE_MAX, \ .max = _max, \ } #define NLA_POLICY_VALIDATE_FN(tp, fn, ...) { \ .type = NLA_ENSURE_NO_VALIDATION_PTR(tp), \ .validation_type = NLA_VALIDATE_FUNCTION, \ .validate = fn, \ .len = __VA_ARGS__ + 0, \ } /** * struct nl_info - netlink source information * @nlh: Netlink message header of original request * @nl_net: Network namespace * @portid: Netlink PORTID of requesting application * @skip_notify: Skip netlink notifications to user space * @skip_notify_kernel: Skip selected in-kernel notifications */ struct nl_info { struct nlmsghdr *nlh; struct net *nl_net; u32 portid; u8 skip_notify:1, skip_notify_kernel:1; }; /** * enum netlink_validation - netlink message/attribute validation levels * @NL_VALIDATE_LIBERAL: Old-style "be liberal" validation, not caring about * extra data at the end of the message, attributes being longer than * they should be, or unknown attributes being present. * @NL_VALIDATE_TRAILING: Reject junk data encountered after attribute parsing. * @NL_VALIDATE_MAXTYPE: Reject attributes > max type; Together with _TRAILING * this is equivalent to the old nla_parse_strict()/nlmsg_parse_strict(). * @NL_VALIDATE_UNSPEC: Reject attributes with NLA_UNSPEC in the policy. * This can safely be set by the kernel when the given policy has no * NLA_UNSPEC anymore, and can thus be used to ensure policy entries * are enforced going forward. * @NL_VALIDATE_STRICT_ATTRS: strict attribute policy parsing (e.g. * U8, U16, U32 must have exact size, etc.) * @NL_VALIDATE_NESTED: Check that NLA_F_NESTED is set for NLA_NESTED(_ARRAY) * and unset for other policies. */ enum netlink_validation { NL_VALIDATE_LIBERAL = 0, NL_VALIDATE_TRAILING = BIT(0), NL_VALIDATE_MAXTYPE = BIT(1), NL_VALIDATE_UNSPEC = BIT(2), NL_VALIDATE_STRICT_ATTRS = BIT(3), NL_VALIDATE_NESTED = BIT(4), }; #define NL_VALIDATE_DEPRECATED_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE) #define NL_VALIDATE_STRICT (NL_VALIDATE_TRAILING |\ NL_VALIDATE_MAXTYPE |\ NL_VALIDATE_UNSPEC |\ NL_VALIDATE_STRICT_ATTRS |\ NL_VALIDATE_NESTED) int netlink_rcv_skb(struct sk_buff *skb, int (*cb)(struct sk_buff *, struct nlmsghdr *, struct netlink_ext_ack *)); int nlmsg_notify(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, int report, gfp_t flags); int __nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int __nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack); int nla_policy_len(const struct nla_policy *, int); struct nlattr *nla_find(const struct nlattr *head, int len, int attrtype); size_t nla_strlcpy(char *dst, const struct nlattr *nla, size_t dstsize); char *nla_strdup(const struct nlattr *nla, gfp_t flags); int nla_memcpy(void *dest, const struct nlattr *src, int count); int nla_memcmp(const struct nlattr *nla, const void *data, size_t size); int nla_strcmp(const struct nlattr *nla, const char *str); struct nlattr *__nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *__nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *__nla_reserve_nohdr(struct sk_buff *skb, int attrlen); struct nlattr *nla_reserve(struct sk_buff *skb, int attrtype, int attrlen); struct nlattr *nla_reserve_64bit(struct sk_buff *skb, int attrtype, int attrlen, int padattr); void *nla_reserve_nohdr(struct sk_buff *skb, int attrlen); void __nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); void __nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); void __nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_put(struct sk_buff *skb, int attrtype, int attrlen, const void *data); int nla_put_64bit(struct sk_buff *skb, int attrtype, int attrlen, const void *data, int padattr); int nla_put_nohdr(struct sk_buff *skb, int attrlen, const void *data); int nla_append(struct sk_buff *skb, int attrlen, const void *data); /************************************************************************** * Netlink Messages **************************************************************************/ /** * nlmsg_msg_size - length of netlink message not including padding * @payload: length of message payload */ static inline int nlmsg_msg_size(int payload) { return NLMSG_HDRLEN + payload; } /** * nlmsg_total_size - length of netlink message including padding * @payload: length of message payload */ static inline int nlmsg_total_size(int payload) { return NLMSG_ALIGN(nlmsg_msg_size(payload)); } /** * nlmsg_padlen - length of padding at the message's tail * @payload: length of message payload */ static inline int nlmsg_padlen(int payload) { return nlmsg_total_size(payload) - nlmsg_msg_size(payload); } /** * nlmsg_data - head of message payload * @nlh: netlink message header */ static inline void *nlmsg_data(const struct nlmsghdr *nlh) { return (unsigned char *) nlh + NLMSG_HDRLEN; } /** * nlmsg_len - length of message payload * @nlh: netlink message header */ static inline int nlmsg_len(const struct nlmsghdr *nlh) { return nlh->nlmsg_len - NLMSG_HDRLEN; } /** * nlmsg_attrdata - head of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline struct nlattr *nlmsg_attrdata(const struct nlmsghdr *nlh, int hdrlen) { unsigned char *data = nlmsg_data(nlh); return (struct nlattr *) (data + NLMSG_ALIGN(hdrlen)); } /** * nlmsg_attrlen - length of attributes data * @nlh: netlink message header * @hdrlen: length of family specific header */ static inline int nlmsg_attrlen(const struct nlmsghdr *nlh, int hdrlen) { return nlmsg_len(nlh) - NLMSG_ALIGN(hdrlen); } /** * nlmsg_ok - check if the netlink message fits into the remaining bytes * @nlh: netlink message header * @remaining: number of bytes remaining in message stream */ static inline int nlmsg_ok(const struct nlmsghdr *nlh, int remaining) { return (remaining >= (int) sizeof(struct nlmsghdr) && nlh->nlmsg_len >= sizeof(struct nlmsghdr) && nlh->nlmsg_len <= remaining); } /** * nlmsg_next - next netlink message in message stream * @nlh: netlink message header * @remaining: number of bytes remaining in message stream * * Returns the next netlink message in the message stream and * decrements remaining by the size of the current message. */ static inline struct nlmsghdr * nlmsg_next(const struct nlmsghdr *nlh, int *remaining) { int totlen = NLMSG_ALIGN(nlh->nlmsg_len); *remaining -= totlen; return (struct nlmsghdr *) ((unsigned char *) nlh + totlen); } /** * nla_parse - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected, policy must be specified, attributes * will be validated in the strictest way possible. * * Returns 0 on success or a negative error code. */ static inline int nla_parse(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_deprecated - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be ignored and attributes from the policy are not * always strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_parse_deprecated_strict - Parse a stream of attributes into a tb buffer * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @head: head of attribute stream * @len: length of attribute stream * @policy: validation policy * @extack: extended ACK pointer * * Parses a stream of attributes and stores a pointer to each attribute in * the tb array accessible via the attribute type. Attributes with a type * exceeding maxtype will be rejected as well as trailing data, but the * policy is not completely strictly validated (only for new attributes). * * Returns 0 on success or a negative error code. */ static inline int nla_parse_deprecated_strict(struct nlattr **tb, int maxtype, const struct nlattr *head, int len, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, head, len, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * __nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() */ static inline int __nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) { NL_SET_ERR_MSG(extack, "Invalid header length"); return -EINVAL; } return __nla_parse(tb, maxtype, nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), policy, validate, extack); } /** * nlmsg_parse - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @validate: validation strictness * @extack: extended ACK report struct * * See nla_parse() */ static inline int nlmsg_parse(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_parse_deprecated - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nlmsg_parse_deprecated(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_parse_deprecated_strict - parse attributes of a netlink message * @nlh: netlink message header * @hdrlen: length of family specific header * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @extack: extended ACK report struct * * See nla_parse_deprecated_strict() */ static inline int nlmsg_parse_deprecated_strict(const struct nlmsghdr *nlh, int hdrlen, struct nlattr *tb[], int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nlmsg_parse(nlh, hdrlen, tb, maxtype, policy, NL_VALIDATE_DEPRECATED_STRICT, extack); } /** * nlmsg_find_attr - find a specific attribute in a netlink message * @nlh: netlink message header * @hdrlen: length of familiy specific header * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr *nlmsg_find_attr(const struct nlmsghdr *nlh, int hdrlen, int attrtype) { return nla_find(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), attrtype); } /** * nla_validate_deprecated - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in liberal mode. * See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate_deprecated(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_validate - Validate a stream of attributes * @head: head of attribute stream * @len: length of attribute stream * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the specified attribute stream against the * specified policy. Validation is done in strict mode. * See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int nla_validate(const struct nlattr *head, int len, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate(head, len, maxtype, policy, NL_VALIDATE_STRICT, extack); } /** * nlmsg_validate_deprecated - validate a netlink message including attributes * @nlh: netlinket message header * @hdrlen: length of familiy specific header * @maxtype: maximum attribute type to be expected * @policy: validation policy * @extack: extended ACK report struct */ static inline int nlmsg_validate_deprecated(const struct nlmsghdr *nlh, int hdrlen, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (nlh->nlmsg_len < nlmsg_msg_size(hdrlen)) return -EINVAL; return __nla_validate(nlmsg_attrdata(nlh, hdrlen), nlmsg_attrlen(nlh, hdrlen), maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nlmsg_report - need to report back to application? * @nlh: netlink message header * * Returns 1 if a report back to the application is requested. */ static inline int nlmsg_report(const struct nlmsghdr *nlh) { return !!(nlh->nlmsg_flags & NLM_F_ECHO); } /** * nlmsg_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @nlh: netlink message header * @hdrlen: length of familiy specific header * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_attr(pos, nlh, hdrlen, rem) \ nla_for_each_attr(pos, nlmsg_attrdata(nlh, hdrlen), \ nlmsg_attrlen(nlh, hdrlen), rem) /** * nlmsg_put - Add a new netlink message to an skb * @skb: socket buffer to store message in * @portid: netlink PORTID of requesting application * @seq: sequence number of message * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put(struct sk_buff *skb, u32 portid, u32 seq, int type, int payload, int flags) { if (unlikely(skb_tailroom(skb) < nlmsg_total_size(payload))) return NULL; return __nlmsg_put(skb, portid, seq, type, payload, flags); } /** * nlmsg_put_answer - Add a new callback based netlink message to an skb * @skb: socket buffer to store message in * @cb: netlink callback * @type: message type * @payload: length of message payload * @flags: message flags * * Returns NULL if the tailroom of the skb is insufficient to store * the message header and payload. */ static inline struct nlmsghdr *nlmsg_put_answer(struct sk_buff *skb, struct netlink_callback *cb, int type, int payload, int flags) { return nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, type, payload, flags); } /** * nlmsg_new - Allocate a new netlink message * @payload: size of the message payload * @flags: the type of memory to allocate. * * Use NLMSG_DEFAULT_SIZE if the size of the payload isn't known * and a good default is needed. */ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags) { return alloc_skb(nlmsg_total_size(payload), flags); } /** * nlmsg_end - Finalize a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Corrects the netlink message header to include the appeneded * attributes. Only necessary if attributes have been added to * the message. */ static inline void nlmsg_end(struct sk_buff *skb, struct nlmsghdr *nlh) { nlh->nlmsg_len = skb_tail_pointer(skb) - (unsigned char *)nlh; } /** * nlmsg_get_pos - return current position in netlink message * @skb: socket buffer the message is stored in * * Returns a pointer to the current tail of the message. */ static inline void *nlmsg_get_pos(struct sk_buff *skb) { return skb_tail_pointer(skb); } /** * nlmsg_trim - Trim message to a mark * @skb: socket buffer the message is stored in * @mark: mark to trim to * * Trims the message to the provided mark. */ static inline void nlmsg_trim(struct sk_buff *skb, const void *mark) { if (mark) { WARN_ON((unsigned char *) mark < skb->data); skb_trim(skb, (unsigned char *) mark - skb->data); } } /** * nlmsg_cancel - Cancel construction of a netlink message * @skb: socket buffer the message is stored in * @nlh: netlink message header * * Removes the complete netlink message including all * attributes from the socket buffer again. */ static inline void nlmsg_cancel(struct sk_buff *skb, struct nlmsghdr *nlh) { nlmsg_trim(skb, nlh); } /** * nlmsg_free - free a netlink message * @skb: socket buffer of netlink message */ static inline void nlmsg_free(struct sk_buff *skb) { kfree_skb(skb); } /** * nlmsg_multicast - multicast a netlink message * @sk: netlink socket to spread messages to * @skb: netlink message as socket buffer * @portid: own netlink portid to avoid sending to yourself * @group: multicast group id * @flags: allocation flags */ static inline int nlmsg_multicast(struct sock *sk, struct sk_buff *skb, u32 portid, unsigned int group, gfp_t flags) { int err; NETLINK_CB(skb).dst_group = group; err = netlink_broadcast(sk, skb, portid, group, flags); if (err > 0) err = 0; return err; } /** * nlmsg_unicast - unicast a netlink message * @sk: netlink socket to spread message to * @skb: netlink message as socket buffer * @portid: netlink portid of the destination socket */ static inline int nlmsg_unicast(struct sock *sk, struct sk_buff *skb, u32 portid) { int err; err = netlink_unicast(sk, skb, portid, MSG_DONTWAIT); if (err > 0) err = 0; return err; } /** * nlmsg_for_each_msg - iterate over a stream of messages * @pos: loop counter, set to current message * @head: head of message stream * @len: length of message stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nlmsg_for_each_msg(pos, head, len, rem) \ for (pos = head, rem = len; \ nlmsg_ok(pos, rem); \ pos = nlmsg_next(pos, &(rem))) /** * nl_dump_check_consistent - check if sequence is consistent and advertise if not * @cb: netlink callback structure that stores the sequence number * @nlh: netlink message header to write the flag to * * This function checks if the sequence (generation) number changed during dump * and if it did, advertises it in the netlink message header. * * The correct way to use it is to set cb->seq to the generation counter when * all locks for dumping have been acquired, and then call this function for * each message that is generated. * * Note that due to initialisation concerns, 0 is an invalid sequence number * and must not be used by code that uses this functionality. */ static inline void nl_dump_check_consistent(struct netlink_callback *cb, struct nlmsghdr *nlh) { if (cb->prev_seq && cb->seq != cb->prev_seq) nlh->nlmsg_flags |= NLM_F_DUMP_INTR; cb->prev_seq = cb->seq; } /************************************************************************** * Netlink Attributes **************************************************************************/ /** * nla_attr_size - length of attribute not including padding * @payload: length of payload */ static inline int nla_attr_size(int payload) { return NLA_HDRLEN + payload; } /** * nla_total_size - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size(int payload) { return NLA_ALIGN(nla_attr_size(payload)); } /** * nla_padlen - length of padding at the tail of attribute * @payload: length of payload */ static inline int nla_padlen(int payload) { return nla_total_size(payload) - nla_attr_size(payload); } /** * nla_type - attribute type * @nla: netlink attribute */ static inline int nla_type(const struct nlattr *nla) { return nla->nla_type & NLA_TYPE_MASK; } /** * nla_data - head of payload * @nla: netlink attribute */ static inline void *nla_data(const struct nlattr *nla) { return (char *) nla + NLA_HDRLEN; } /** * nla_len - length of payload * @nla: netlink attribute */ static inline int nla_len(const struct nlattr *nla) { return nla->nla_len - NLA_HDRLEN; } /** * nla_ok - check if the netlink attribute fits into the remaining bytes * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream */ static inline int nla_ok(const struct nlattr *nla, int remaining) { return remaining >= (int) sizeof(*nla) && nla->nla_len >= sizeof(*nla) && nla->nla_len <= remaining; } /** * nla_next - next netlink attribute in attribute stream * @nla: netlink attribute * @remaining: number of bytes remaining in attribute stream * * Returns the next netlink attribute in the attribute stream and * decrements remaining by the size of the current attribute. */ static inline struct nlattr *nla_next(const struct nlattr *nla, int *remaining) { unsigned int totlen = NLA_ALIGN(nla->nla_len); *remaining -= totlen; return (struct nlattr *) ((char *) nla + totlen); } /** * nla_find_nested - find attribute in a set of nested attributes * @nla: attribute containing the nested attributes * @attrtype: type of attribute to look for * * Returns the first attribute which matches the specified type. */ static inline struct nlattr * nla_find_nested(const struct nlattr *nla, int attrtype) { return nla_find(nla_data(nla), nla_len(nla), attrtype); } /** * nla_parse_nested - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse() */ static inline int nla_parse_nested(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { if (!(nla->nla_type & NLA_F_NESTED)) { NL_SET_ERR_MSG_ATTR(extack, nla, "NLA_F_NESTED is missing"); return -EINVAL; } return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_STRICT, extack); } /** * nla_parse_nested_deprecated - parse nested attributes * @tb: destination array with maxtype+1 elements * @maxtype: maximum attribute type to be expected * @nla: attribute containing the nested attributes * @policy: validation policy * @extack: extended ACK report struct * * See nla_parse_deprecated() */ static inline int nla_parse_nested_deprecated(struct nlattr *tb[], int maxtype, const struct nlattr *nla, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_put_u8 - Add a u8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u8(struct sk_buff *skb, int attrtype, u8 value) { /* temporary variables to work around GCC PR81715 with asan-stack=1 */ u8 tmp = value; return nla_put(skb, attrtype, sizeof(u8), &tmp); } /** * nla_put_u16 - Add a u16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u16(struct sk_buff *skb, int attrtype, u16 value) { u16 tmp = value; return nla_put(skb, attrtype, sizeof(u16), &tmp); } /** * nla_put_be16 - Add a __be16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put(skb, attrtype, sizeof(__be16), &tmp); } /** * nla_put_net16 - Add 16-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net16(struct sk_buff *skb, int attrtype, __be16 value) { __be16 tmp = value; return nla_put_be16(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le16 - Add a __le16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le16(struct sk_buff *skb, int attrtype, __le16 value) { __le16 tmp = value; return nla_put(skb, attrtype, sizeof(__le16), &tmp); } /** * nla_put_u32 - Add a u32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_u32(struct sk_buff *skb, int attrtype, u32 value) { u32 tmp = value; return nla_put(skb, attrtype, sizeof(u32), &tmp); } /** * nla_put_be32 - Add a __be32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_be32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put(skb, attrtype, sizeof(__be32), &tmp); } /** * nla_put_net32 - Add 32-bit network byte order netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_net32(struct sk_buff *skb, int attrtype, __be32 value) { __be32 tmp = value; return nla_put_be32(skb, attrtype | NLA_F_NET_BYTEORDER, tmp); } /** * nla_put_le32 - Add a __le32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_le32(struct sk_buff *skb, int attrtype, __le32 value) { __le32 tmp = value; return nla_put(skb, attrtype, sizeof(__le32), &tmp); } /** * nla_put_u64_64bit - Add a u64 netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_u64_64bit(struct sk_buff *skb, int attrtype, u64 value, int padattr) { u64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_be64 - Add a __be64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_be64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__be64), &tmp, padattr); } /** * nla_put_net64 - Add 64-bit network byte order nlattr to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_net64(struct sk_buff *skb, int attrtype, __be64 value, int padattr) { __be64 tmp = value; return nla_put_be64(skb, attrtype | NLA_F_NET_BYTEORDER, tmp, padattr); } /** * nla_put_le64 - Add a __le64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_le64(struct sk_buff *skb, int attrtype, __le64 value, int padattr) { __le64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(__le64), &tmp, padattr); } /** * nla_put_s8 - Add a s8 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s8(struct sk_buff *skb, int attrtype, s8 value) { s8 tmp = value; return nla_put(skb, attrtype, sizeof(s8), &tmp); } /** * nla_put_s16 - Add a s16 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s16(struct sk_buff *skb, int attrtype, s16 value) { s16 tmp = value; return nla_put(skb, attrtype, sizeof(s16), &tmp); } /** * nla_put_s32 - Add a s32 netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value */ static inline int nla_put_s32(struct sk_buff *skb, int attrtype, s32 value) { s32 tmp = value; return nla_put(skb, attrtype, sizeof(s32), &tmp); } /** * nla_put_s64 - Add a s64 netlink attribute to a socket buffer and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @value: numeric value * @padattr: attribute type for the padding */ static inline int nla_put_s64(struct sk_buff *skb, int attrtype, s64 value, int padattr) { s64 tmp = value; return nla_put_64bit(skb, attrtype, sizeof(s64), &tmp, padattr); } /** * nla_put_string - Add a string netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @str: NUL terminated string */ static inline int nla_put_string(struct sk_buff *skb, int attrtype, const char *str) { return nla_put(skb, attrtype, strlen(str) + 1, str); } /** * nla_put_flag - Add a flag netlink attribute to a socket buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type */ static inline int nla_put_flag(struct sk_buff *skb, int attrtype) { return nla_put(skb, attrtype, 0, NULL); } /** * nla_put_msecs - Add a msecs netlink attribute to a skb and align it * @skb: socket buffer to add attribute to * @attrtype: attribute type * @njiffies: number of jiffies to convert to msecs * @padattr: attribute type for the padding */ static inline int nla_put_msecs(struct sk_buff *skb, int attrtype, unsigned long njiffies, int padattr) { u64 tmp = jiffies_to_msecs(njiffies); return nla_put_64bit(skb, attrtype, sizeof(u64), &tmp, padattr); } /** * nla_put_in_addr - Add an IPv4 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv4 address */ static inline int nla_put_in_addr(struct sk_buff *skb, int attrtype, __be32 addr) { __be32 tmp = addr; return nla_put_be32(skb, attrtype, tmp); } /** * nla_put_in6_addr - Add an IPv6 address netlink attribute to a socket * buffer * @skb: socket buffer to add attribute to * @attrtype: attribute type * @addr: IPv6 address */ static inline int nla_put_in6_addr(struct sk_buff *skb, int attrtype, const struct in6_addr *addr) { return nla_put(skb, attrtype, sizeof(*addr), addr); } /** * nla_get_u32 - return payload of u32 attribute * @nla: u32 netlink attribute */ static inline u32 nla_get_u32(const struct nlattr *nla) { return *(u32 *) nla_data(nla); } /** * nla_get_be32 - return payload of __be32 attribute * @nla: __be32 netlink attribute */ static inline __be32 nla_get_be32(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_le32 - return payload of __le32 attribute * @nla: __le32 netlink attribute */ static inline __le32 nla_get_le32(const struct nlattr *nla) { return *(__le32 *) nla_data(nla); } /** * nla_get_u16 - return payload of u16 attribute * @nla: u16 netlink attribute */ static inline u16 nla_get_u16(const struct nlattr *nla) { return *(u16 *) nla_data(nla); } /** * nla_get_be16 - return payload of __be16 attribute * @nla: __be16 netlink attribute */ static inline __be16 nla_get_be16(const struct nlattr *nla) { return *(__be16 *) nla_data(nla); } /** * nla_get_le16 - return payload of __le16 attribute * @nla: __le16 netlink attribute */ static inline __le16 nla_get_le16(const struct nlattr *nla) { return *(__le16 *) nla_data(nla); } /** * nla_get_u8 - return payload of u8 attribute * @nla: u8 netlink attribute */ static inline u8 nla_get_u8(const struct nlattr *nla) { return *(u8 *) nla_data(nla); } /** * nla_get_u64 - return payload of u64 attribute * @nla: u64 netlink attribute */ static inline u64 nla_get_u64(const struct nlattr *nla) { u64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_be64 - return payload of __be64 attribute * @nla: __be64 netlink attribute */ static inline __be64 nla_get_be64(const struct nlattr *nla) { __be64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_le64 - return payload of __le64 attribute * @nla: __le64 netlink attribute */ static inline __le64 nla_get_le64(const struct nlattr *nla) { return *(__le64 *) nla_data(nla); } /** * nla_get_s32 - return payload of s32 attribute * @nla: s32 netlink attribute */ static inline s32 nla_get_s32(const struct nlattr *nla) { return *(s32 *) nla_data(nla); } /** * nla_get_s16 - return payload of s16 attribute * @nla: s16 netlink attribute */ static inline s16 nla_get_s16(const struct nlattr *nla) { return *(s16 *) nla_data(nla); } /** * nla_get_s8 - return payload of s8 attribute * @nla: s8 netlink attribute */ static inline s8 nla_get_s8(const struct nlattr *nla) { return *(s8 *) nla_data(nla); } /** * nla_get_s64 - return payload of s64 attribute * @nla: s64 netlink attribute */ static inline s64 nla_get_s64(const struct nlattr *nla) { s64 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_flag - return payload of flag attribute * @nla: flag netlink attribute */ static inline int nla_get_flag(const struct nlattr *nla) { return !!nla; } /** * nla_get_msecs - return payload of msecs attribute * @nla: msecs netlink attribute * * Returns the number of milliseconds in jiffies. */ static inline unsigned long nla_get_msecs(const struct nlattr *nla) { u64 msecs = nla_get_u64(nla); return msecs_to_jiffies((unsigned long) msecs); } /** * nla_get_in_addr - return payload of IPv4 address attribute * @nla: IPv4 address netlink attribute */ static inline __be32 nla_get_in_addr(const struct nlattr *nla) { return *(__be32 *) nla_data(nla); } /** * nla_get_in6_addr - return payload of IPv6 address attribute * @nla: IPv6 address netlink attribute */ static inline struct in6_addr nla_get_in6_addr(const struct nlattr *nla) { struct in6_addr tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_get_bitfield32 - return payload of 32 bitfield attribute * @nla: nla_bitfield32 attribute */ static inline struct nla_bitfield32 nla_get_bitfield32(const struct nlattr *nla) { struct nla_bitfield32 tmp; nla_memcpy(&tmp, nla, sizeof(tmp)); return tmp; } /** * nla_memdup - duplicate attribute memory (kmemdup) * @src: netlink attribute to duplicate from * @gfp: GFP mask */ static inline void *nla_memdup(const struct nlattr *src, gfp_t gfp) { return kmemdup(nla_data(src), nla_len(src), gfp); } /** * nla_nest_start_noflag - Start a new level of nested attributes * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * This function exists for backward compatibility to use in APIs which never * marked their nest attributes with NLA_F_NESTED flag. New APIs should use * nla_nest_start() which sets the flag. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start_noflag(struct sk_buff *skb, int attrtype) { struct nlattr *start = (struct nlattr *)skb_tail_pointer(skb); if (nla_put(skb, attrtype, 0, NULL) < 0) return NULL; return start; } /** * nla_nest_start - Start a new level of nested attributes, with NLA_F_NESTED * @skb: socket buffer to add attributes to * @attrtype: attribute type of container * * Unlike nla_nest_start_noflag(), mark the nest attribute with NLA_F_NESTED * flag. This is the preferred function to use in new code. * * Returns the container attribute or NULL on error */ static inline struct nlattr *nla_nest_start(struct sk_buff *skb, int attrtype) { return nla_nest_start_noflag(skb, attrtype | NLA_F_NESTED); } /** * nla_nest_end - Finalize nesting of attributes * @skb: socket buffer the attributes are stored in * @start: container attribute * * Corrects the container attribute header to include the all * appeneded attributes. * * Returns the total data length of the skb. */ static inline int nla_nest_end(struct sk_buff *skb, struct nlattr *start) { start->nla_len = skb_tail_pointer(skb) - (unsigned char *)start; return skb->len; } /** * nla_nest_cancel - Cancel nesting of attributes * @skb: socket buffer the message is stored in * @start: container attribute * * Removes the container attribute and including all nested * attributes. Returns -EMSGSIZE */ static inline void nla_nest_cancel(struct sk_buff *skb, struct nlattr *start) { nlmsg_trim(skb, start); } /** * nla_validate_nested - Validate a stream of nested attributes * @start: container attribute * @maxtype: maximum attribute type to be expected * @policy: validation policy * @validate: validation strictness * @extack: extended ACK report struct * * Validates all attributes in the nested attribute stream against the * specified policy. Attributes with a type exceeding maxtype will be * ignored. See documenation of struct nla_policy for more details. * * Returns 0 on success or a negative error code. */ static inline int __nla_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, unsigned int validate, struct netlink_ext_ack *extack) { return __nla_validate(nla_data(start), nla_len(start), maxtype, policy, validate, extack); } static inline int nl80211_validate_nested(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_STRICT, extack); } static inline int nla_validate_nested_deprecated(const struct nlattr *start, int maxtype, const struct nla_policy *policy, struct netlink_ext_ack *extack) { return __nla_validate_nested(start, maxtype, policy, NL_VALIDATE_LIBERAL, extack); } /** * nla_need_padding_for_64bit - test 64-bit alignment of the next attribute * @skb: socket buffer the message is stored in * * Return true if padding is needed to align the next attribute (nla_data()) to * a 64-bit aligned area. */ static inline bool nla_need_padding_for_64bit(struct sk_buff *skb) { #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS /* The nlattr header is 4 bytes in size, that's why we test * if the skb->data _is_ aligned. A NOP attribute, plus * nlattr header for next attribute, will make nla_data() * 8-byte aligned. */ if (IS_ALIGNED((unsigned long)skb_tail_pointer(skb), 8)) return true; #endif return false; } /** * nla_align_64bit - 64-bit align the nla_data() of next attribute * @skb: socket buffer the message is stored in * @padattr: attribute type for the padding * * Conditionally emit a padding netlink attribute in order to make * the next attribute we emit have a 64-bit aligned nla_data() area. * This will only be done in architectures which do not have * CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS defined. * * Returns zero on success or a negative error code. */ static inline int nla_align_64bit(struct sk_buff *skb, int padattr) { if (nla_need_padding_for_64bit(skb) && !nla_reserve(skb, padattr, 0)) return -EMSGSIZE; return 0; } /** * nla_total_size_64bit - total length of attribute including padding * @payload: length of payload */ static inline int nla_total_size_64bit(int payload) { return NLA_ALIGN(nla_attr_size(payload)) #ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS + NLA_ALIGN(nla_attr_size(0)) #endif ; } /** * nla_for_each_attr - iterate over a stream of attributes * @pos: loop counter, set to current attribute * @head: head of attribute stream * @len: length of attribute stream * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_attr(pos, head, len, rem) \ for (pos = head, rem = len; \ nla_ok(pos, rem); \ pos = nla_next(pos, &(rem))) /** * nla_for_each_nested - iterate over nested attributes * @pos: loop counter, set to current attribute * @nla: attribute containing the nested attributes * @rem: initialized to len, holds bytes currently remaining in stream */ #define nla_for_each_nested(pos, nla, rem) \ nla_for_each_attr(pos, nla_data(nla), nla_len(nla), rem) /** * nla_is_last - Test if attribute is last in stream * @nla: attribute to test * @rem: bytes remaining in stream */ static inline bool nla_is_last(const struct nlattr *nla, int rem) { return nla->nla_len == rem; } #endif |
| 35 35 268 269 35 1755 1755 121 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> struct mem_cgroup; struct page; struct mm_struct; struct kmem_cache; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_CACHE = NR_VM_NODE_STAT_ITEMS, MEMCG_RSS, MEMCG_RSS_HUGE, MEMCG_SWAP, MEMCG_SOCK, /* XXX: why are these zone and not node counters? */ MEMCG_KERNEL_STACK_KB, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_NR_MEMORY_EVENTS, }; enum mem_cgroup_protection { MEMCG_PROT_NONE, MEMCG_PROT_LOW, MEMCG_PROT_MIN, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; int priority; unsigned int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 #define MEM_CGROUP_ID_MAX USHRT_MAX struct mem_cgroup_id { int id; refcount_t ref; }; /* * Per memcg event counter is incremented at every pagein/pageout. With THP, * it will be incremated by the number of pages. This counter is used for * for trigger some periodic events. This is straightforward and better * than using jiffies etc. to handle periodic memcg event. */ enum mem_cgroup_events_target { MEM_CGROUP_TARGET_THRESH, MEM_CGROUP_TARGET_SOFTLIMIT, MEM_CGROUP_TARGET_NUMAINFO, MEM_CGROUP_NTARGETS, }; struct memcg_vmstats_percpu { long stat[MEMCG_NR_STAT]; unsigned long events[NR_VM_EVENT_ITEMS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ unsigned int generation; }; struct lruvec_stat { long count[NR_VM_NODE_STAT_ITEMS]; }; /* * Bitmap of shrinker::id corresponding to memcg-aware shrinkers, * which have elements charged to this memcg. */ struct memcg_shrinker_map { struct rcu_head rcu; unsigned long map[0]; }; /* * per-zone information in memory controller. */ struct mem_cgroup_per_node { struct lruvec lruvec; /* Legacy local VM stats */ struct lruvec_stat __percpu *lruvec_stat_local; /* Subtree VM stats (batched updates) */ struct lruvec_stat __percpu *lruvec_stat_cpu; atomic_long_t lruvec_stat[NR_VM_NODE_STAT_ITEMS]; unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter[DEF_PRIORITY + 1]; struct memcg_shrinker_map __rcu *shrinker_map; struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; bool congested; /* memcg has many dirty pages */ /* backed by a congested BDI */ struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[0]; }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; enum memcg_kmem_state { KMEM_NONE, KMEM_ALLOCATED, KMEM_ONLINE, }; #if defined(CONFIG_SMP) struct memcg_padding { char x[0]; } ____cacheline_internodealigned_in_smp; #define MEMCG_PADDING(name) struct memcg_padding name; #else #define MEMCG_PADDING(name) #endif /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_id id; /* Accounted resources */ struct page_counter memory; struct page_counter swap; /* Legacy consumer-oriented counters */ struct page_counter memsw; struct page_counter kmem; struct page_counter tcpmem; /* Upper bound of normal memory consumption range */ unsigned long high; /* Range enforcement for interrupt charges */ struct work_struct high_work; unsigned long soft_limit; /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the accounting and control be hierarchical, per subtree? */ bool use_hierarchy; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; int swappiness; /* OOM-Killer disable */ int oom_kill_disable; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* * Should we move charges of a task when a task is moved into this * mem_cgroup ? And what type of charges should we move ? */ unsigned long move_charge_at_immigrate; /* taken only while moving_account > 0 */ spinlock_t move_lock; unsigned long move_lock_flags; MEMCG_PADDING(_pad1_); /* * set > 0 if pages under this cgroup are moving to other cgroup. */ atomic_t moving_account; struct task_struct *move_lock_task; /* Legacy local VM stats and events */ struct memcg_vmstats_percpu __percpu *vmstats_local; /* Subtree VM stats and events (batched updates) */ struct memcg_vmstats_percpu __percpu *vmstats_percpu; MEMCG_PADDING(_pad2_); atomic_long_t vmstats[MEMCG_NR_STAT]; atomic_long_t vmevents[NR_VM_EVENT_ITEMS]; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; unsigned long socket_pressure; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; #ifdef CONFIG_MEMCG_KMEM /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; enum memcg_kmem_state kmem_state; struct list_head kmem_caches; #endif int last_scanned_node; #if MAX_NUMNODES > 1 nodemask_t scan_nodes; atomic_t numainfo_events; atomic_t numainfo_updating; #endif #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #ifdef CONFIG_TRANSPARENT_HUGEPAGE struct deferred_split deferred_split_queue; #endif struct mem_cgroup_per_node *nodeinfo[0]; /* WARNING: nodeinfo must be the last member here */ }; /* * size of first charge trial. "32" comes from vmscan.c's magic value. * TODO: maybe necessary to use big numbers in big irons. */ #define MEMCG_CHARGE_BATCH 32U extern struct mem_cgroup *root_mem_cgroup; static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; if (mem_cgroup_disabled()) return; /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_protected calculation is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } enum mem_cgroup_protection mem_cgroup_protected(struct mem_cgroup *root, struct mem_cgroup *memcg); int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, bool compound); int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, bool compound); void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare, bool compound); void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, bool compound); void mem_cgroup_uncharge(struct page *page); void mem_cgroup_uncharge_list(struct list_head *page_list); void mem_cgroup_migrate(struct page *oldpage, struct page *newpage); static struct mem_cgroup_per_node * mem_cgroup_nodeinfo(struct mem_cgroup *memcg, int nid) { return memcg->nodeinfo[nid]; } /** * mem_cgroup_lruvec - get the lru list vector for a node or a memcg zone * @node: node of the wanted lruvec * @memcg: memcg of the wanted lruvec * * Returns the lru list vector holding pages for a given @node or a given * @memcg and @zone. This can be the node lruvec, if the memory controller * is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, struct mem_cgroup *memcg) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = node_lruvec(pgdat); goto out; } mz = mem_cgroup_nodeinfo(memcg, pgdat->node_id); lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } struct lruvec *mem_cgroup_page_lruvec(struct page *, struct pglist_data *); struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_page(struct page *page); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); int mem_cgroup_scan_tasks(struct mem_cgroup *, int (*)(struct task_struct *, void *), void *); static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_id(unsigned short id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root or the memory * controller is in legacy no-hierarchy mode. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { if (!memcg->memory.parent) return NULL; return mem_cgroup_from_counter(memcg->memory.parent, memory); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; if (!root->use_hierarchy) return false; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return !!(memcg->css.flags & CSS_ONLINE); } /* * For memory reclaim. */ int mem_cgroup_select_victim_node(struct mem_cgroup *memcg); void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, int nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->lru_zone_size[zone_idx][lru]; } void mem_cgroup_handle_over_high(void); unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); unsigned long mem_cgroup_size(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } bool mem_cgroup_oom_synchronize(bool wait); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); #ifdef CONFIG_MEMCG_SWAP extern int do_swap_account; #endif struct mem_cgroup *lock_page_memcg(struct page *page); void __unlock_page_memcg(struct mem_cgroup *memcg); void unlock_page_memcg(struct page *page); /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { long x = atomic_long_read(&memcg->vmstats[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } /* * idx can be of type enum memcg_stat_item or node_stat_item. * Keep in sync with memcg_exact_page_state(). */ static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { long x = 0; int cpu; for_each_possible_cpu(cpu) x += per_cpu(memcg->vmstats_local->stat[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val); /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) { unsigned long flags; local_irq_save(flags); __mod_memcg_state(memcg, idx, val); local_irq_restore(flags); } /** * mod_memcg_page_state - update page state statistics * @page: the page * @idx: page state item to account * @val: number of pages (positive or negative) * * The @page must be locked or the caller must use lock_page_memcg() * to prevent double accounting when the page is concurrently being * moved to another memcg: * * lock_page(page) or lock_page_memcg(page) * if (TestClearPageState(page)) * mod_memcg_page_state(page, state, -1); * unlock_page(page) or unlock_page_memcg(page) * * Kernel pages are an exception to this, since they'll never move. */ static inline void __mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) __mod_memcg_state(page->mem_cgroup, idx, val); } static inline void mod_memcg_page_state(struct page *page, int idx, int val) { if (page->mem_cgroup) mod_memcg_state(page->mem_cgroup, idx, val); } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); x = atomic_long_read(&pn->lruvec_stat[idx]); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { struct mem_cgroup_per_node *pn; long x = 0; int cpu; if (mem_cgroup_disabled()) return node_page_state(lruvec_pgdat(lruvec), idx); pn = container_of(lruvec, struct mem_cgroup_per_node, lruvec); for_each_possible_cpu(cpu) x += per_cpu(pn->lruvec_stat_local->count[idx], cpu); #ifdef CONFIG_SMP if (x < 0) x = 0; #endif return x; } void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val); void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val); void mod_memcg_obj_state(void *p, int idx, int val); static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_state(lruvec, idx, val); local_irq_restore(flags); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { pg_data_t *pgdat = page_pgdat(page); struct lruvec *lruvec; /* Untracked pages have no memcg, no lruvec. Update only the node */ if (!page->mem_cgroup) { __mod_node_page_state(pgdat, idx, val); return; } lruvec = mem_cgroup_lruvec(pgdat, page->mem_cgroup); __mod_lruvec_state(lruvec, idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { unsigned long flags; local_irq_save(flags); __mod_lruvec_page_state(page, idx, val); local_irq_restore(flags); } unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { unsigned long flags; local_irq_save(flags); __count_memcg_events(memcg, idx, count); local_irq_restore(flags); } static inline void count_memcg_page_event(struct page *page, enum vm_event_item idx) { if (page->mem_cgroup) count_memcg_events(page->mem_cgroup, idx, 1); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, 1); rcu_read_unlock(); } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { atomic_long_inc(&memcg->memory_events_local[event]); cgroup_file_notify(&memcg->events_local_file); do { atomic_long_inc(&memcg->memory_events[event]); cgroup_file_notify(&memcg->events_file); if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) break; if (cgrp_dfl_root.flags & CGRP_ROOT_MEMORY_LOCAL_EVENTS) break; } while ((memcg = parent_mem_cgroup(memcg)) && !mem_cgroup_is_root(memcg)); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE void mem_cgroup_split_huge_fixup(struct page *head); #endif #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define MEM_CGROUP_ID_MAX 0 struct mem_cgroup; static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low) { *min = *low = 0; } static inline enum mem_cgroup_protection mem_cgroup_protected( struct mem_cgroup *root, struct mem_cgroup *memcg) { return MEMCG_PROT_NONE; } static inline int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, bool compound) { *memcgp = NULL; return 0; } static inline int mem_cgroup_try_charge_delay(struct page *page, struct mm_struct *mm, gfp_t gfp_mask, struct mem_cgroup **memcgp, bool compound) { *memcgp = NULL; return 0; } static inline void mem_cgroup_commit_charge(struct page *page, struct mem_cgroup *memcg, bool lrucare, bool compound) { } static inline void mem_cgroup_cancel_charge(struct page *page, struct mem_cgroup *memcg, bool compound) { } static inline void mem_cgroup_uncharge(struct page *page) { } static inline void mem_cgroup_uncharge_list(struct list_head *page_list) { } static inline void mem_cgroup_migrate(struct page *old, struct page *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct pglist_data *pgdat, struct mem_cgroup *memcg) { return node_lruvec(pgdat); } static inline struct lruvec *mem_cgroup_page_lruvec(struct page *page, struct pglist_data *pgdat) { return &pgdat->lruvec; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_page(struct page *page) { return NULL; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline int mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { return 0; } static inline unsigned short mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline unsigned long mem_cgroup_size(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline struct mem_cgroup *lock_page_memcg(struct page *page) { return NULL; } static inline void __unlock_page_memcg(struct mem_cgroup *memcg) { } static inline void unlock_page_memcg(struct page *page) { } static inline void mem_cgroup_handle_over_high(void) { } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long memcg_page_state_local(struct mem_cgroup *memcg, int idx) { return 0; } static inline void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, int idx, int nr) { } static inline void __mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, int idx, int nr) { } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { __mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, int val) { mod_node_page_state(lruvec_pgdat(lruvec), idx, val); } static inline void __mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_lruvec_page_state(struct page *page, enum node_stat_item idx, int val) { mod_node_page_state(page_pgdat(page), idx, val); } static inline void __mod_lruvec_slab_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); __mod_node_page_state(page_pgdat(page), idx, val); } static inline void mod_memcg_obj_state(void *p, int idx, int val) { } static inline unsigned long mem_cgroup_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline void mem_cgroup_split_huge_fixup(struct page *head) { } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_page_event(struct page *page, int idx) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } #endif /* CONFIG_MEMCG */ /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_state(struct mem_cgroup *memcg, int idx) { __mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __inc_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void __dec_memcg_page_state(struct page *page, int idx) { __mod_memcg_page_state(page, idx, -1); } static inline void __inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, 1); } static inline void __dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { __mod_lruvec_state(lruvec, idx, -1); } static inline void __inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, 1); } static inline void __dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { __mod_lruvec_page_state(page, idx, -1); } static inline void __inc_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, 1); } static inline void __dec_lruvec_slab_state(void *p, enum node_stat_item idx) { __mod_lruvec_slab_state(p, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_state(struct mem_cgroup *memcg, int idx) { mod_memcg_state(memcg, idx, -1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void inc_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, 1); } /* idx can be of type enum memcg_stat_item or node_stat_item */ static inline void dec_memcg_page_state(struct page *page, int idx) { mod_memcg_page_state(page, idx, -1); } static inline void inc_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, 1); } static inline void dec_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx) { mod_lruvec_state(lruvec, idx, -1); } static inline void inc_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, 1); } static inline void dec_lruvec_page_state(struct page *page, enum node_stat_item idx) { mod_lruvec_page_state(page, idx, -1); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct page *page, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { if (mem_cgroup_disabled()) return; if (unlikely(&page->mem_cgroup->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(page, wb); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct page *page, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages); #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_pressure) return true; do { if (time_before(jiffies, memcg->socket_pressure)) return true; } while ((memcg = parent_mem_cgroup(memcg))); return false; } extern int memcg_expand_shrinker_maps(int new_id); extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { }; static inline void mem_cgroup_sk_free(struct sock *sk) { }; static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg) { return false; } static inline void memcg_set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } #endif struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep); void memcg_kmem_put_cache(struct kmem_cache *cachep); #ifdef CONFIG_MEMCG_KMEM int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge(struct page *page, int order); int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg); void __memcg_kmem_uncharge_memcg(struct mem_cgroup *memcg, unsigned int nr_pages); extern struct static_key_false memcg_kmem_enabled_key; extern struct workqueue_struct *memcg_kmem_cache_wq; extern int memcg_nr_cache_ids; void memcg_get_cache_ids(void); void memcg_put_cache_ids(void); /* * Helper macro to loop through all memcg-specific caches. Callers must still * check if the cache is valid (it is either valid or NULL). * the slab_mutex must be held when looping through those caches */ #define for_each_memcg_cache_index(_idx) \ for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) static inline bool memcg_kmem_enabled(void) { return static_branch_unlikely(&memcg_kmem_enabled_key); } static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_enabled()) return __memcg_kmem_charge(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge(struct page *page, int order) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge(page, order); } static inline int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct mem_cgroup *memcg) { if (memcg_kmem_enabled()) return __memcg_kmem_charge_memcg(page, gfp, order, memcg); return 0; } static inline void memcg_kmem_uncharge_memcg(struct page *page, int order, struct mem_cgroup *memcg) { if (memcg_kmem_enabled()) __memcg_kmem_uncharge_memcg(memcg, 1 << order); } /* * helper for accessing a memcg's index. It will be used as an index in the * child cache array in kmem_cache, and also to derive its name. This function * will return -1 when this is not a kmem-limited memcg. */ static inline int memcg_cache_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_obj(void *p); #else static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge(struct page *page, int order) { } static inline int __memcg_kmem_charge(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge(struct page *page, int order) { } #define for_each_memcg_cache_index(_idx) \ for (; NULL; ) static inline bool memcg_kmem_enabled(void) { return false; } static inline int memcg_cache_id(struct mem_cgroup *memcg) { return -1; } static inline void memcg_get_cache_ids(void) { } static inline void memcg_put_cache_ids(void) { } static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; } #endif /* CONFIG_MEMCG_KMEM */ #endif /* _LINUX_MEMCONTROL_H */ |
| 2 2 2 2 3 1 1 1 8 7 2 2 3 3 1 1 1 10 10 10 7 1 5 1 1 1 4 2 17 17 3 14 4 4 1 1 2 2 2 1 1 2 2 2 5 5 1 4 2 5 4 1 3 1 1 1 4 4 5 2 3 3 3 2 3 3 3 5 5 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 3 1 2 2 2 2 2 2 2 1 1 1 4 4 2 2 3 3 1 1 2 2 4 4 1 1 5 2 3 3 2 2 2 1 1 1 1 3 1 2 1 2 2 1 1 1 1 1 1 1 1 1 2 2 2 2 3 3 2 1 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 32 31 1 1 1 1 1 1 2 2 1 1 147 6 1 110 100 60 142 25 2 5 5 1 1 2 2 1 1 2 3 2 2 3 1 4 2 2 4 1 5 2 2 3 1 1 1 1 1 5 2 1 1 1 2 3 3 1 1 2 2 3 2 1 1 1 1 32 4 2 1 1 2 1 138 140 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 | // SPDX-License-Identifier: GPL-2.0-or-later /* * net/core/ethtool.c - Ethtool ioctl handler * Copyright (c) 2003 Matthew Wilcox <matthew@wil.cx> * * This file is where we call all the ethtool_ops commands to get * the information ethtool needs. */ #include <linux/module.h> #include <linux/types.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/ethtool.h> #include <linux/netdevice.h> #include <linux/net_tstamp.h> #include <linux/phy.h> #include <linux/bitops.h> #include <linux/uaccess.h> #include <linux/vmalloc.h> #include <linux/sfp.h> #include <linux/slab.h> #include <linux/rtnetlink.h> #include <linux/sched/signal.h> #include <linux/net.h> #include <net/devlink.h> #include <net/xdp_sock.h> #include <net/flow_offload.h> /* * Some useful ethtool_ops methods that're device independent. * If we find that all drivers want to do the same thing here, * we can turn these into dev_() function calls. */ u32 ethtool_op_get_link(struct net_device *dev) { return netif_carrier_ok(dev) ? 1 : 0; } EXPORT_SYMBOL(ethtool_op_get_link); int ethtool_op_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info) { info->so_timestamping = SOF_TIMESTAMPING_TX_SOFTWARE | SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; info->phc_index = -1; return 0; } EXPORT_SYMBOL(ethtool_op_get_ts_info); /* Handlers for each ethtool command */ #define ETHTOOL_DEV_FEATURE_WORDS ((NETDEV_FEATURE_COUNT + 31) / 32) static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] = { [NETIF_F_SG_BIT] = "tx-scatter-gather", [NETIF_F_IP_CSUM_BIT] = "tx-checksum-ipv4", [NETIF_F_HW_CSUM_BIT] = "tx-checksum-ip-generic", [NETIF_F_IPV6_CSUM_BIT] = "tx-checksum-ipv6", [NETIF_F_HIGHDMA_BIT] = "highdma", [NETIF_F_FRAGLIST_BIT] = "tx-scatter-gather-fraglist", [NETIF_F_HW_VLAN_CTAG_TX_BIT] = "tx-vlan-hw-insert", [NETIF_F_HW_VLAN_CTAG_RX_BIT] = "rx-vlan-hw-parse", [NETIF_F_HW_VLAN_CTAG_FILTER_BIT] = "rx-vlan-filter", [NETIF_F_HW_VLAN_STAG_TX_BIT] = "tx-vlan-stag-hw-insert", [NETIF_F_HW_VLAN_STAG_RX_BIT] = "rx-vlan-stag-hw-parse", [NETIF_F_HW_VLAN_STAG_FILTER_BIT] = "rx-vlan-stag-filter", [NETIF_F_VLAN_CHALLENGED_BIT] = "vlan-challenged", [NETIF_F_GSO_BIT] = "tx-generic-segmentation", [NETIF_F_LLTX_BIT] = "tx-lockless", [NETIF_F_NETNS_LOCAL_BIT] = "netns-local", [NETIF_F_GRO_BIT] = "rx-gro", [NETIF_F_GRO_HW_BIT] = "rx-gro-hw", [NETIF_F_LRO_BIT] = "rx-lro", [NETIF_F_TSO_BIT] = "tx-tcp-segmentation", [NETIF_F_GSO_ROBUST_BIT] = "tx-gso-robust", [NETIF_F_TSO_ECN_BIT] = "tx-tcp-ecn-segmentation", [NETIF_F_TSO_MANGLEID_BIT] = "tx-tcp-mangleid-segmentation", [NETIF_F_TSO6_BIT] = "tx-tcp6-segmentation", [NETIF_F_FSO_BIT] = "tx-fcoe-segmentation", [NETIF_F_GSO_GRE_BIT] = "tx-gre-segmentation", [NETIF_F_GSO_GRE_CSUM_BIT] = "tx-gre-csum-segmentation", [NETIF_F_GSO_IPXIP4_BIT] = "tx-ipxip4-segmentation", [NETIF_F_GSO_IPXIP6_BIT] = "tx-ipxip6-segmentation", [NETIF_F_GSO_UDP_TUNNEL_BIT] = "tx-udp_tnl-segmentation", [NETIF_F_GSO_UDP_TUNNEL_CSUM_BIT] = "tx-udp_tnl-csum-segmentation", [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", [NETIF_F_GSO_FRAGLIST_BIT] = "tx-gso-list", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", [NETIF_F_FCOE_MTU_BIT] = "fcoe-mtu", [NETIF_F_NTUPLE_BIT] = "rx-ntuple-filter", [NETIF_F_RXHASH_BIT] = "rx-hashing", [NETIF_F_RXCSUM_BIT] = "rx-checksum", [NETIF_F_NOCACHE_COPY_BIT] = "tx-nocache-copy", [NETIF_F_LOOPBACK_BIT] = "loopback", [NETIF_F_RXFCS_BIT] = "rx-fcs", [NETIF_F_RXALL_BIT] = "rx-all", [NETIF_F_HW_L2FW_DOFFLOAD_BIT] = "l2-fwd-offload", [NETIF_F_HW_TC_BIT] = "hw-tc-offload", [NETIF_F_HW_ESP_BIT] = "esp-hw-offload", [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", [NETIF_F_HW_TLS_RX_BIT] = "tls-hw-rx-offload", }; static const char rss_hash_func_strings[ETH_RSS_HASH_FUNCS_COUNT][ETH_GSTRING_LEN] = { [ETH_RSS_HASH_TOP_BIT] = "toeplitz", [ETH_RSS_HASH_XOR_BIT] = "xor", [ETH_RSS_HASH_CRC32_BIT] = "crc32", }; static const char tunable_strings[__ETHTOOL_TUNABLE_COUNT][ETH_GSTRING_LEN] = { [ETHTOOL_ID_UNSPEC] = "Unspec", [ETHTOOL_RX_COPYBREAK] = "rx-copybreak", [ETHTOOL_TX_COPYBREAK] = "tx-copybreak", [ETHTOOL_PFC_PREVENTION_TOUT] = "pfc-prevention-tout", }; static const char phy_tunable_strings[__ETHTOOL_PHY_TUNABLE_COUNT][ETH_GSTRING_LEN] = { [ETHTOOL_ID_UNSPEC] = "Unspec", [ETHTOOL_PHY_DOWNSHIFT] = "phy-downshift", [ETHTOOL_PHY_FAST_LINK_DOWN] = "phy-fast-link-down", [ETHTOOL_PHY_EDPD] = "phy-energy-detect-power-down", }; static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { struct ethtool_gfeatures cmd = { .cmd = ETHTOOL_GFEATURES, .size = ETHTOOL_DEV_FEATURE_WORDS, }; struct ethtool_get_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; u32 __user *sizeaddr; u32 copy_size; int i; /* in case feature bits run out again */ BUILD_BUG_ON(ETHTOOL_DEV_FEATURE_WORDS * sizeof(u32) > sizeof(netdev_features_t)); for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { features[i].available = (u32)(dev->hw_features >> (32 * i)); features[i].requested = (u32)(dev->wanted_features >> (32 * i)); features[i].active = (u32)(dev->features >> (32 * i)); features[i].never_changed = (u32)(NETIF_F_NEVER_CHANGE >> (32 * i)); } sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); if (get_user(copy_size, sizeaddr)) return -EFAULT; if (copy_size > ETHTOOL_DEV_FEATURE_WORDS) copy_size = ETHTOOL_DEV_FEATURE_WORDS; if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; useraddr += sizeof(cmd); if (copy_to_user(useraddr, features, copy_size * sizeof(*features))) return -EFAULT; return 0; } static int ethtool_set_features(struct net_device *dev, void __user *useraddr) { struct ethtool_sfeatures cmd; struct ethtool_set_features_block features[ETHTOOL_DEV_FEATURE_WORDS]; netdev_features_t wanted = 0, valid = 0; int i, ret = 0; if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; useraddr += sizeof(cmd); if (cmd.size != ETHTOOL_DEV_FEATURE_WORDS) return -EINVAL; if (copy_from_user(features, useraddr, sizeof(features))) return -EFAULT; for (i = 0; i < ETHTOOL_DEV_FEATURE_WORDS; ++i) { valid |= (netdev_features_t)features[i].valid << (32 * i); wanted |= (netdev_features_t)features[i].requested << (32 * i); } if (valid & ~NETIF_F_ETHTOOL_BITS) return -EINVAL; if (valid & ~dev->hw_features) { valid &= dev->hw_features; ret |= ETHTOOL_F_UNSUPPORTED; } dev->wanted_features &= ~valid; dev->wanted_features |= wanted & valid; __netdev_update_features(dev); if ((dev->wanted_features ^ dev->features) & valid) ret |= ETHTOOL_F_WISH; return ret; } static int __ethtool_get_sset_count(struct net_device *dev, int sset) { const struct ethtool_ops *ops = dev->ethtool_ops; if (sset == ETH_SS_FEATURES) return ARRAY_SIZE(netdev_features_strings); if (sset == ETH_SS_RSS_HASH_FUNCS) return ARRAY_SIZE(rss_hash_func_strings); if (sset == ETH_SS_TUNABLES) return ARRAY_SIZE(tunable_strings); if (sset == ETH_SS_PHY_TUNABLES) return ARRAY_SIZE(phy_tunable_strings); if (sset == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats) return phy_ethtool_get_sset_count(dev->phydev); if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); else return -EOPNOTSUPP; } static void __ethtool_get_strings(struct net_device *dev, u32 stringset, u8 *data) { const struct ethtool_ops *ops = dev->ethtool_ops; if (stringset == ETH_SS_FEATURES) memcpy(data, netdev_features_strings, sizeof(netdev_features_strings)); else if (stringset == ETH_SS_RSS_HASH_FUNCS) memcpy(data, rss_hash_func_strings, sizeof(rss_hash_func_strings)); else if (stringset == ETH_SS_TUNABLES) memcpy(data, tunable_strings, sizeof(tunable_strings)); else if (stringset == ETH_SS_PHY_TUNABLES) memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings)); else if (stringset == ETH_SS_PHY_STATS && dev->phydev && !ops->get_ethtool_phy_stats) phy_ethtool_get_strings(dev->phydev, data); else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); } static netdev_features_t ethtool_get_feature_mask(u32 eth_cmd) { /* feature masks of legacy discrete ethtool ops */ switch (eth_cmd) { case ETHTOOL_GTXCSUM: case ETHTOOL_STXCSUM: return NETIF_F_CSUM_MASK | NETIF_F_SCTP_CRC; case ETHTOOL_GRXCSUM: case ETHTOOL_SRXCSUM: return NETIF_F_RXCSUM; case ETHTOOL_GSG: case ETHTOOL_SSG: return NETIF_F_SG; case ETHTOOL_GTSO: case ETHTOOL_STSO: return NETIF_F_ALL_TSO; case ETHTOOL_GGSO: case ETHTOOL_SGSO: return NETIF_F_GSO; case ETHTOOL_GGRO: case ETHTOOL_SGRO: return NETIF_F_GRO; default: BUG(); } } static int ethtool_get_one_feature(struct net_device *dev, char __user *useraddr, u32 ethcmd) { netdev_features_t mask = ethtool_get_feature_mask(ethcmd); struct ethtool_value edata = { .cmd = ethcmd, .data = !!(dev->features & mask), }; if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } static int ethtool_set_one_feature(struct net_device *dev, void __user *useraddr, u32 ethcmd) { struct ethtool_value edata; netdev_features_t mask; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; mask = ethtool_get_feature_mask(ethcmd); mask &= dev->hw_features; if (!mask) return -EOPNOTSUPP; if (edata.data) dev->wanted_features |= mask; else dev->wanted_features &= ~mask; __netdev_update_features(dev); return 0; } #define ETH_ALL_FLAGS (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | \ ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH) #define ETH_ALL_FEATURES (NETIF_F_LRO | NETIF_F_HW_VLAN_CTAG_RX | \ NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_NTUPLE | \ NETIF_F_RXHASH) static u32 __ethtool_get_flags(struct net_device *dev) { u32 flags = 0; if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO; if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) flags |= ETH_FLAG_RXVLAN; if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) flags |= ETH_FLAG_TXVLAN; if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE; if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH; return flags; } static int __ethtool_set_flags(struct net_device *dev, u32 data) { netdev_features_t features = 0, changed; if (data & ~ETH_ALL_FLAGS) return -EINVAL; if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO; if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_CTAG_RX; if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_CTAG_TX; if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE; if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH; /* allow changing only bits set in hw_features */ changed = (features ^ dev->features) & ETH_ALL_FEATURES; if (changed & ~dev->hw_features) return (changed & dev->hw_features) ? -EINVAL : -EOPNOTSUPP; dev->wanted_features = (dev->wanted_features & ~changed) | (features & changed); __netdev_update_features(dev); return 0; } /* Given two link masks, AND them together and save the result in dst. */ void ethtool_intersect_link_masks(struct ethtool_link_ksettings *dst, struct ethtool_link_ksettings *src) { unsigned int size = BITS_TO_LONGS(__ETHTOOL_LINK_MODE_MASK_NBITS); unsigned int idx = 0; for (; idx < size; idx++) { dst->link_modes.supported[idx] &= src->link_modes.supported[idx]; dst->link_modes.advertising[idx] &= src->link_modes.advertising[idx]; } } EXPORT_SYMBOL(ethtool_intersect_link_masks); void ethtool_convert_legacy_u32_to_link_mode(unsigned long *dst, u32 legacy_u32) { bitmap_zero(dst, __ETHTOOL_LINK_MODE_MASK_NBITS); dst[0] = legacy_u32; } EXPORT_SYMBOL(ethtool_convert_legacy_u32_to_link_mode); /* return false if src had higher bits set. lower bits always updated. */ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, const unsigned long *src) { bool retval = true; /* TODO: following test will soon always be true */ if (__ETHTOOL_LINK_MODE_MASK_NBITS > 32) { __ETHTOOL_DECLARE_LINK_MODE_MASK(ext); bitmap_zero(ext, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_fill(ext, 32); bitmap_complement(ext, ext, __ETHTOOL_LINK_MODE_MASK_NBITS); if (bitmap_intersects(ext, src, __ETHTOOL_LINK_MODE_MASK_NBITS)) { /* src mask goes beyond bit 31 */ retval = false; } } *legacy_u32 = src[0]; return retval; } EXPORT_SYMBOL(ethtool_convert_link_mode_to_legacy_u32); /* return false if legacy contained non-0 deprecated fields * maxtxpkt/maxrxpkt. rest of ksettings always updated */ static bool convert_legacy_settings_to_link_ksettings( struct ethtool_link_ksettings *link_ksettings, const struct ethtool_cmd *legacy_settings) { bool retval = true; memset(link_ksettings, 0, sizeof(*link_ksettings)); /* This is used to tell users that driver is still using these * deprecated legacy fields, and they should not use * %ETHTOOL_GLINKSETTINGS/%ETHTOOL_SLINKSETTINGS */ if (legacy_settings->maxtxpkt || legacy_settings->maxrxpkt) retval = false; ethtool_convert_legacy_u32_to_link_mode( link_ksettings->link_modes.supported, legacy_settings->supported); ethtool_convert_legacy_u32_to_link_mode( link_ksettings->link_modes.advertising, legacy_settings->advertising); ethtool_convert_legacy_u32_to_link_mode( link_ksettings->link_modes.lp_advertising, legacy_settings->lp_advertising); link_ksettings->base.speed = ethtool_cmd_speed(legacy_settings); link_ksettings->base.duplex = legacy_settings->duplex; link_ksettings->base.port = legacy_settings->port; link_ksettings->base.phy_address = legacy_settings->phy_address; link_ksettings->base.autoneg = legacy_settings->autoneg; link_ksettings->base.mdio_support = legacy_settings->mdio_support; link_ksettings->base.eth_tp_mdix = legacy_settings->eth_tp_mdix; link_ksettings->base.eth_tp_mdix_ctrl = legacy_settings->eth_tp_mdix_ctrl; return retval; } /* return false if ksettings link modes had higher bits * set. legacy_settings always updated (best effort) */ static bool convert_link_ksettings_to_legacy_settings( struct ethtool_cmd *legacy_settings, const struct ethtool_link_ksettings *link_ksettings) { bool retval = true; memset(legacy_settings, 0, sizeof(*legacy_settings)); /* this also clears the deprecated fields in legacy structure: * __u8 transceiver; * __u32 maxtxpkt; * __u32 maxrxpkt; */ retval &= ethtool_convert_link_mode_to_legacy_u32( &legacy_settings->supported, link_ksettings->link_modes.supported); retval &= ethtool_convert_link_mode_to_legacy_u32( &legacy_settings->advertising, link_ksettings->link_modes.advertising); retval &= ethtool_convert_link_mode_to_legacy_u32( &legacy_settings->lp_advertising, link_ksettings->link_modes.lp_advertising); ethtool_cmd_speed_set(legacy_settings, link_ksettings->base.speed); legacy_settings->duplex = link_ksettings->base.duplex; legacy_settings->port = link_ksettings->base.port; legacy_settings->phy_address = link_ksettings->base.phy_address; legacy_settings->autoneg = link_ksettings->base.autoneg; legacy_settings->mdio_support = link_ksettings->base.mdio_support; legacy_settings->eth_tp_mdix = link_ksettings->base.eth_tp_mdix; legacy_settings->eth_tp_mdix_ctrl = link_ksettings->base.eth_tp_mdix_ctrl; legacy_settings->transceiver = link_ksettings->base.transceiver; return retval; } /* number of 32-bit words to store the user's link mode bitmaps */ #define __ETHTOOL_LINK_MODE_MASK_NU32 \ DIV_ROUND_UP(__ETHTOOL_LINK_MODE_MASK_NBITS, 32) /* layout of the struct passed from/to userland */ struct ethtool_link_usettings { struct ethtool_link_settings base; struct { __u32 supported[__ETHTOOL_LINK_MODE_MASK_NU32]; __u32 advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; __u32 lp_advertising[__ETHTOOL_LINK_MODE_MASK_NU32]; } link_modes; }; /* Internal kernel helper to query a device ethtool_link_settings. */ int __ethtool_get_link_ksettings(struct net_device *dev, struct ethtool_link_ksettings *link_ksettings) { ASSERT_RTNL(); if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; if (!netif_device_present(dev)) return -ENODEV; memset(link_ksettings, 0, sizeof(*link_ksettings)); return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings); } EXPORT_SYMBOL(__ethtool_get_link_ksettings); /* convert ethtool_link_usettings in user space to a kernel internal * ethtool_link_ksettings. return 0 on success, errno on error. */ static int load_link_ksettings_from_user(struct ethtool_link_ksettings *to, const void __user *from) { struct ethtool_link_usettings link_usettings; if (copy_from_user(&link_usettings, from, sizeof(link_usettings))) return -EFAULT; memcpy(&to->base, &link_usettings.base, sizeof(to->base)); bitmap_from_arr32(to->link_modes.supported, link_usettings.link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_from_arr32(to->link_modes.advertising, link_usettings.link_modes.advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_from_arr32(to->link_modes.lp_advertising, link_usettings.link_modes.lp_advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); return 0; } /* convert a kernel internal ethtool_link_ksettings to * ethtool_link_usettings in user space. return 0 on success, errno on * error. */ static int store_link_ksettings_for_user(void __user *to, const struct ethtool_link_ksettings *from) { struct ethtool_link_usettings link_usettings; memcpy(&link_usettings, from, sizeof(link_usettings)); bitmap_to_arr32(link_usettings.link_modes.supported, from->link_modes.supported, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_to_arr32(link_usettings.link_modes.advertising, from->link_modes.advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); bitmap_to_arr32(link_usettings.link_modes.lp_advertising, from->link_modes.lp_advertising, __ETHTOOL_LINK_MODE_MASK_NBITS); if (copy_to_user(to, &link_usettings, sizeof(link_usettings))) return -EFAULT; return 0; } /* Query device for its ethtool_link_settings. */ static int ethtool_get_link_ksettings(struct net_device *dev, void __user *useraddr) { int err = 0; struct ethtool_link_ksettings link_ksettings; ASSERT_RTNL(); if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; /* handle bitmap nbits handshake */ if (copy_from_user(&link_ksettings.base, useraddr, sizeof(link_ksettings.base))) return -EFAULT; if (__ETHTOOL_LINK_MODE_MASK_NU32 != link_ksettings.base.link_mode_masks_nwords) { /* wrong link mode nbits requested */ memset(&link_ksettings, 0, sizeof(link_ksettings)); link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; /* send back number of words required as negative val */ compiletime_assert(__ETHTOOL_LINK_MODE_MASK_NU32 <= S8_MAX, "need too many bits for link modes!"); link_ksettings.base.link_mode_masks_nwords = -((s8)__ETHTOOL_LINK_MODE_MASK_NU32); /* copy the base fields back to user, not the link * mode bitmaps */ if (copy_to_user(useraddr, &link_ksettings.base, sizeof(link_ksettings.base))) return -EFAULT; return 0; } /* handshake successful: user/kernel agree on * link_mode_masks_nwords */ memset(&link_ksettings, 0, sizeof(link_ksettings)); err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); if (err < 0) return err; /* make sure we tell the right values to user */ link_ksettings.base.cmd = ETHTOOL_GLINKSETTINGS; link_ksettings.base.link_mode_masks_nwords = __ETHTOOL_LINK_MODE_MASK_NU32; return store_link_ksettings_for_user(useraddr, &link_ksettings); } /* Update device ethtool_link_settings. */ static int ethtool_set_link_ksettings(struct net_device *dev, void __user *useraddr) { int err; struct ethtool_link_ksettings link_ksettings; ASSERT_RTNL(); if (!dev->ethtool_ops->set_link_ksettings) return -EOPNOTSUPP; /* make sure nbits field has expected value */ if (copy_from_user(&link_ksettings.base, useraddr, sizeof(link_ksettings.base))) return -EFAULT; if (__ETHTOOL_LINK_MODE_MASK_NU32 != link_ksettings.base.link_mode_masks_nwords) return -EINVAL; /* copy the whole structure, now that we know it has expected * format */ err = load_link_ksettings_from_user(&link_ksettings, useraddr); if (err) return err; /* re-check nwords field, just in case */ if (__ETHTOOL_LINK_MODE_MASK_NU32 != link_ksettings.base.link_mode_masks_nwords) return -EINVAL; return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } /* Query device for its ethtool_cmd settings. * * Backward compatibility note: for compatibility with legacy ethtool, this is * now implemented via get_link_ksettings. When driver reports higher link mode * bits, a kernel warning is logged once (with name of 1st driver/device) to * recommend user to upgrade ethtool, but the command is successful (only the * lower link mode bits reported back to user). Deprecated fields from * ethtool_cmd (transceiver/maxrxpkt/maxtxpkt) are always set to zero. */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; int err; ASSERT_RTNL(); if (!dev->ethtool_ops->get_link_ksettings) return -EOPNOTSUPP; memset(&link_ksettings, 0, sizeof(link_ksettings)); err = dev->ethtool_ops->get_link_ksettings(dev, &link_ksettings); if (err < 0) return err; convert_link_ksettings_to_legacy_settings(&cmd, &link_ksettings); /* send a sensible cmd tag back to user */ cmd.cmd = ETHTOOL_GSET; if (copy_to_user(useraddr, &cmd, sizeof(cmd))) return -EFAULT; return 0; } /* Update device link settings with given ethtool_cmd. * * Backward compatibility note: for compatibility with legacy ethtool, this is * now always implemented via set_link_settings. When user's request updates * deprecated ethtool_cmd fields (transceiver/maxrxpkt/maxtxpkt), a kernel * warning is logged once (with name of 1st driver/device) to recommend user to * upgrade ethtool, and the request is rejected. */ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) { struct ethtool_link_ksettings link_ksettings; struct ethtool_cmd cmd; ASSERT_RTNL(); if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; if (!dev->ethtool_ops->set_link_ksettings) return -EOPNOTSUPP; if (!convert_legacy_settings_to_link_ksettings(&link_ksettings, &cmd)) return -EINVAL; link_ksettings.base.link_mode_masks_nwords = __ETHTOOL_LINK_MODE_MASK_NU32; return dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings); } static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) { struct ethtool_drvinfo info; const struct ethtool_ops *ops = dev->ethtool_ops; memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; if (ops->get_drvinfo) { ops->get_drvinfo(dev, &info); } else if (dev->dev.parent && dev->dev.parent->driver) { strlcpy(info.bus_info, dev_name(dev->dev.parent), sizeof(info.bus_info)); strlcpy(info.driver, dev->dev.parent->driver->name, sizeof(info.driver)); } else { return -EOPNOTSUPP; } /* * this method of obtaining string set info is deprecated; * Use ETHTOOL_GSSET_INFO instead. */ if (ops->get_sset_count) { int rc; rc = ops->get_sset_count(dev, ETH_SS_TEST); if (rc >= 0) info.testinfo_len = rc; rc = ops->get_sset_count(dev, ETH_SS_STATS); if (rc >= 0) info.n_stats = rc; rc = ops->get_sset_count(dev, ETH_SS_PRIV_FLAGS); if (rc >= 0) info.n_priv_flags = rc; } if (ops->get_regs_len) { int ret = ops->get_regs_len(dev); if (ret > 0) info.regdump_len = ret; } if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); if (!info.fw_version[0]) devlink_compat_running_version(dev, info.fw_version, sizeof(info.fw_version)); if (copy_to_user(useraddr, &info, sizeof(info))) return -EFAULT; return 0; } static noinline_for_stack int ethtool_get_sset_info(struct net_device *dev, void __user *useraddr) { struct ethtool_sset_info info; u64 sset_mask; int i, idx = 0, n_bits = 0, ret, rc; u32 *info_buf = NULL; if (copy_from_user(&info, useraddr, sizeof(info))) return -EFAULT; /* store copy of mask, because we zero struct later on */ sset_mask = info.sset_mask; if (!sset_mask) return 0; /* calculate size of return buffer */ n_bits = hweight64(sset_mask); memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GSSET_INFO; info_buf = kcalloc(n_bits, sizeof(u32), GFP_USER); if (!info_buf) return -ENOMEM; /* * fill return buffer based on input bitmask and successful * get_sset_count return */ for (i = 0; i < 64; i++) { if (!(sset_mask & (1ULL << i))) continue; rc = __ethtool_get_sset_count(dev, i); if (rc >= 0) { info.sset_mask |= (1ULL << i); info_buf[idx++] = rc; } } ret = -EFAULT; if (copy_to_user(useraddr, &info, sizeof(info))) goto out; useraddr += offsetof(struct ethtool_sset_info, data); if (copy_to_user(useraddr, info_buf, idx * sizeof(u32))) goto out; ret = 0; out: kfree(info_buf); return ret; } static noinline_for_stack int ethtool_set_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { struct ethtool_rxnfc info; size_t info_size = sizeof(info); int rc; if (!dev->ethtool_ops->set_rxnfc) return -EOPNOTSUPP; /* struct ethtool_rxnfc was originally defined for * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data * members. User-space might still be using that * definition. */ if (cmd == ETHTOOL_SRXFH) info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; rc = dev->ethtool_ops->set_rxnfc(dev, &info); if (rc) return rc; if (cmd == ETHTOOL_SRXCLSRLINS && copy_to_user(useraddr, &info, info_size)) return -EFAULT; return 0; } static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, u32 cmd, void __user *useraddr) { struct ethtool_rxnfc info; size_t info_size = sizeof(info); const struct ethtool_ops *ops = dev->ethtool_ops; int ret; void *rule_buf = NULL; if (!ops->get_rxnfc) return -EOPNOTSUPP; /* struct ethtool_rxnfc was originally defined for * ETHTOOL_{G,S}RXFH with only the cmd, flow_type and data * members. User-space might still be using that * definition. */ if (cmd == ETHTOOL_GRXFH) info_size = (offsetof(struct ethtool_rxnfc, data) + sizeof(info.data)); if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* If FLOW_RSS was requested then user-space must be using the * new definition, as FLOW_RSS is newer. */ if (cmd == ETHTOOL_GRXFH && info.flow_type & FLOW_RSS) { info_size = sizeof(info); if (copy_from_user(&info, useraddr, info_size)) return -EFAULT; /* Since malicious users may modify the original data, * we need to check whether FLOW_RSS is still requested. */ if (!(info.flow_type & FLOW_RSS)) return -EINVAL; } if (info.cmd != cmd) return -EINVAL; if (info.cmd == ETHTOOL_GRXCLSRLALL) { if (info.rule_cnt > 0) { if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32)) rule_buf = kcalloc(info.rule_cnt, sizeof(u32), GFP_USER); if (!rule_buf) return -ENOMEM; } } ret = ops->get_rxnfc(dev, &info, rule_buf); if (ret < 0) goto err_out; ret = -EFAULT; if (copy_to_user(useraddr, &info, info_size)) goto err_out; if (rule_buf) { useraddr += offsetof(struct ethtool_rxnfc, rule_locs); if (copy_to_user(useraddr, rule_buf, info.rule_cnt * sizeof(u32))) goto err_out; } ret = 0; err_out: kfree(rule_buf); return ret; } static int ethtool_copy_validate_indir(u32 *indir, void __user *useraddr, struct ethtool_rxnfc *rx_rings, u32 size) { int i; if (copy_from_user(indir, useraddr, size * sizeof(indir[0]))) return -EFAULT; /* Validate ring indices */ for (i = 0; i < size; i++) if (indir[i] >= rx_rings->data) return -EINVAL; return 0; } u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len) { BUG_ON(len > sizeof(netdev_rss_key)); net_get_random_once(netdev_rss_key, sizeof(netdev_rss_key)); memcpy(buffer, netdev_rss_key, len); } EXPORT_SYMBOL(netdev_rss_key_fill); static int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max) { u32 dev_size, current_max = 0; u32 *indir; int ret; if (!dev->ethtool_ops->get_rxfh_indir_size || !dev->ethtool_ops->get_rxfh) return -EOPNOTSUPP; dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); if (dev_size == 0) return -EOPNOTSUPP; indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); if (!indir) return -ENOMEM; ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); if (ret) goto out; while (dev_size--) current_max = max(current_max, indir[dev_size]); *max = current_max; out: kfree(indir); return ret; } static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, void __user *useraddr) { u32 user_size, dev_size; u32 *indir; int ret; if (!dev->ethtool_ops->get_rxfh_indir_size || !dev->ethtool_ops->get_rxfh) return -EOPNOTSUPP; dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev); if (dev_size == 0) return -EOPNOTSUPP; if (copy_from_user(&user_size, useraddr + offsetof(struct ethtool_rxfh_indir, size), sizeof(user_size))) return -EFAULT; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, size), &dev_size, sizeof(dev_size))) return -EFAULT; /* If the user buffer size is 0, this is just a query for the * device table size. Otherwise, if it's smaller than the * device table size it's an error. */ if (user_size < dev_size) return user_size == 0 ? 0 : -EINVAL; indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); if (!indir) return -ENOMEM; ret = dev->ethtool_ops->get_rxfh(dev, indir, NULL, NULL); if (ret) goto out; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh_indir, ring_index[0]), indir, dev_size * sizeof(indir[0]))) ret = -EFAULT; out: kfree(indir); return ret; } static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, void __user *useraddr) { struct ethtool_rxnfc rx_rings; u32 user_size, dev_size, i; u32 *indir; const struct ethtool_ops *ops = dev->ethtool_ops; int ret; u32 ringidx_offset = offsetof(struct ethtool_rxfh_indir, ring_index[0]); if (!ops->get_rxfh_indir_size || !ops->set_rxfh || !ops->get_rxnfc) return -EOPNOTSUPP; dev_size = ops->get_rxfh_indir_size(dev); if (dev_size == 0) return -EOPNOTSUPP; if (copy_from_user(&user_size, useraddr + offsetof(struct ethtool_rxfh_indir, size), sizeof(user_size))) return -EFAULT; if (user_size != 0 && user_size != dev_size) return -EINVAL; indir = kcalloc(dev_size, sizeof(indir[0]), GFP_USER); if (!indir) return -ENOMEM; rx_rings.cmd = ETHTOOL_GRXRINGS; ret = ops->get_rxnfc(dev, &rx_rings, NULL); if (ret) goto out; if (user_size == 0) { for (i = 0; i < dev_size; i++) indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); } else { ret = ethtool_copy_validate_indir(indir, useraddr + ringidx_offset, &rx_rings, dev_size); if (ret) goto out; } ret = ops->set_rxfh(dev, indir, NULL, ETH_RSS_HASH_NO_CHANGE); if (ret) goto out; /* indicate whether rxfh was set to default */ if (user_size == 0) dev->priv_flags &= ~IFF_RXFH_CONFIGURED; else dev->priv_flags |= IFF_RXFH_CONFIGURED; out: kfree(indir); return ret; } static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev, void __user *useraddr) { int ret; const struct ethtool_ops *ops = dev->ethtool_ops; u32 user_indir_size, user_key_size; u32 dev_indir_size = 0, dev_key_size = 0; struct ethtool_rxfh rxfh; u32 total_size; u32 indir_bytes; u32 *indir = NULL; u8 dev_hfunc = 0; u8 *hkey = NULL; u8 *rss_config; if (!ops->get_rxfh) return -EOPNOTSUPP; if (ops->get_rxfh_indir_size) dev_indir_size = ops->get_rxfh_indir_size(dev); if (ops->get_rxfh_key_size) dev_key_size = ops->get_rxfh_key_size(dev); if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) return -EFAULT; user_indir_size = rxfh.indir_size; user_key_size = rxfh.key_size; /* Check that reserved fields are 0 for now */ if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ if (rxfh.rss_context && !ops->get_rxfh_context) return -EOPNOTSUPP; rxfh.indir_size = dev_indir_size; rxfh.key_size = dev_key_size; if (copy_to_user(useraddr, &rxfh, sizeof(rxfh))) return -EFAULT; if ((user_indir_size && (user_indir_size != dev_indir_size)) || (user_key_size && (user_key_size != dev_key_size))) return -EINVAL; indir_bytes = user_indir_size * sizeof(indir[0]); total_size = indir_bytes + user_key_size; rss_config = kzalloc(total_size, GFP_USER); if (!rss_config) return -ENOMEM; if (user_indir_size) indir = (u32 *)rss_config; if (user_key_size) hkey = rss_config + indir_bytes; if (rxfh.rss_context) ret = dev->ethtool_ops->get_rxfh_context(dev, indir, hkey, &dev_hfunc, rxfh.rss_context); else ret = dev->ethtool_ops->get_rxfh(dev, indir, hkey, &dev_hfunc); if (ret) goto out; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, hfunc), &dev_hfunc, sizeof(rxfh.hfunc))) { ret = -EFAULT; } else if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_config[0]), rss_config, total_size)) { ret = -EFAULT; } out: kfree(rss_config); return ret; } static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev, void __user *useraddr) { int ret; const struct ethtool_ops *ops = dev->ethtool_ops; struct ethtool_rxnfc rx_rings; struct ethtool_rxfh rxfh; u32 dev_indir_size = 0, dev_key_size = 0, i; u32 *indir = NULL, indir_bytes = 0; u8 *hkey = NULL; u8 *rss_config; u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]); bool delete = false; if (!ops->get_rxnfc || !ops->set_rxfh) return -EOPNOTSUPP; if (ops->get_rxfh_indir_size) dev_indir_size = ops->get_rxfh_indir_size(dev); if (ops->get_rxfh_key_size) dev_key_size = ops->get_rxfh_key_size(dev); if (copy_from_user(&rxfh, useraddr, sizeof(rxfh))) return -EFAULT; /* Check that reserved fields are 0 for now */ if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd8[2] || rxfh.rsvd32) return -EINVAL; /* Most drivers don't handle rss_context, check it's 0 as well */ if (rxfh.rss_context && !ops->set_rxfh_context) return -EOPNOTSUPP; /* If either indir, hash key or function is valid, proceed further. * Must request at least one change: indir size, hash key or function. */ if ((rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE && rxfh.indir_size != dev_indir_size) || (rxfh.key_size && (rxfh.key_size != dev_key_size)) || (rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE && rxfh.key_size == 0 && rxfh.hfunc == ETH_RSS_HASH_NO_CHANGE)) return -EINVAL; if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) indir_bytes = dev_indir_size * sizeof(indir[0]); rss_config = kzalloc(indir_bytes + rxfh.key_size, GFP_USER); if (!rss_config) return -ENOMEM; rx_rings.cmd = ETHTOOL_GRXRINGS; ret = ops->get_rxnfc(dev, &rx_rings, NULL); if (ret) goto out; /* rxfh.indir_size == 0 means reset the indir table to default (master * context) or delete the context (other RSS contexts). * rxfh.indir_size == ETH_RXFH_INDIR_NO_CHANGE means leave it unchanged. */ if (rxfh.indir_size && rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) { indir = (u32 *)rss_config; ret = ethtool_copy_validate_indir(indir, useraddr + rss_cfg_offset, &rx_rings, rxfh.indir_size); if (ret) goto out; } else if (rxfh.indir_size == 0) { if (rxfh.rss_context == 0) { indir = (u32 *)rss_config; for (i = 0; i < dev_indir_size; i++) indir[i] = ethtool_rxfh_indir_default(i, rx_rings.data); } else { delete = true; } } if (rxfh.key_size) { hkey = rss_config + indir_bytes; if (copy_from_user(hkey, useraddr + rss_cfg_offset + indir_bytes, rxfh.key_size)) { ret = -EFAULT; goto out; } } if (rxfh.rss_context) ret = ops->set_rxfh_context(dev, indir, hkey, rxfh.hfunc, &rxfh.rss_context, delete); else ret = ops->set_rxfh(dev, indir, hkey, rxfh.hfunc); if (ret) goto out; if (copy_to_user(useraddr + offsetof(struct ethtool_rxfh, rss_context), &rxfh.rss_context, sizeof(rxfh.rss_context))) ret = -EFAULT; if (!rxfh.rss_context) { /* indicate whether rxfh was set to default */ if (rxfh.indir_size == 0) dev->priv_flags &= ~IFF_RXFH_CONFIGURED; else if (rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) dev->priv_flags |= IFF_RXFH_CONFIGURED; } out: kfree(rss_config); return ret; } static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) { struct ethtool_regs regs; const struct ethtool_ops *ops = dev->ethtool_ops; void *regbuf; int reglen, ret; if (!ops->get_regs || !ops->get_regs_len) return -EOPNOTSUPP; if (copy_from_user(®s, useraddr, sizeof(regs))) return -EFAULT; reglen = ops->get_regs_len(dev); if (reglen <= 0) return reglen; if (regs.len > reglen) regs.len = reglen; regbuf = vzalloc(reglen); if (!regbuf) return -ENOMEM; if (regs.len < reglen) reglen = regs.len; ops->get_regs(dev, ®s, regbuf); ret = -EFAULT; if (copy_to_user(useraddr, ®s, sizeof(regs))) goto out; useraddr += offsetof(struct ethtool_regs, data); if (copy_to_user(useraddr, regbuf, reglen)) goto out; ret = 0; out: vfree(regbuf); return ret; } static int ethtool_reset(struct net_device *dev, char __user *useraddr) { struct ethtool_value reset; int ret; if (!dev->ethtool_ops->reset) return -EOPNOTSUPP; if (copy_from_user(&reset, useraddr, sizeof(reset))) return -EFAULT; ret = dev->ethtool_ops->reset(dev, &reset.data); if (ret) return ret; if (copy_to_user(useraddr, &reset, sizeof(reset))) return -EFAULT; return 0; } static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; memset(&wol, 0, sizeof(struct ethtool_wolinfo)); wol.cmd = ETHTOOL_GWOL; dev->ethtool_ops->get_wol(dev, &wol); if (copy_to_user(useraddr, &wol, sizeof(wol))) return -EFAULT; return 0; } static int ethtool_set_wol(struct net_device *dev, char __user *useraddr) { struct ethtool_wolinfo wol; int ret; if (!dev->ethtool_ops->set_wol) return -EOPNOTSUPP; if (copy_from_user(&wol, useraddr, sizeof(wol))) return -EFAULT; ret = dev->ethtool_ops->set_wol(dev, &wol); if (ret) return ret; dev->wol_enabled = !!wol.wolopts; return 0; } static int ethtool_get_eee(struct net_device *dev, char __user *useraddr) { struct ethtool_eee edata; int rc; if (!dev->ethtool_ops->get_eee) return -EOPNOTSUPP; memset(&edata, 0, sizeof(struct ethtool_eee)); edata.cmd = ETHTOOL_GEEE; rc = dev->ethtool_ops->get_eee(dev, &edata); if (rc) return rc; if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } static int ethtool_set_eee(struct net_device *dev, char __user *useraddr) { struct ethtool_eee edata; if (!dev->ethtool_ops->set_eee) return -EOPNOTSUPP; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; return dev->ethtool_ops->set_eee(dev, &edata); } static int ethtool_nway_reset(struct net_device *dev) { if (!dev->ethtool_ops->nway_reset) return -EOPNOTSUPP; return dev->ethtool_ops->nway_reset(dev); } static int ethtool_get_link(struct net_device *dev, char __user *useraddr) { struct ethtool_value edata = { .cmd = ETHTOOL_GLINK }; if (!dev->ethtool_ops->get_link) return -EOPNOTSUPP; edata.data = netif_running(dev) && dev->ethtool_ops->get_link(dev); if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } static int ethtool_get_any_eeprom(struct net_device *dev, void __user *useraddr, int (*getter)(struct net_device *, struct ethtool_eeprom *, u8 *), u32 total_len) { struct ethtool_eeprom eeprom; void __user *userbuf = useraddr + sizeof(eeprom); u32 bytes_remaining; u8 *data; int ret = 0; if (copy_from_user(&eeprom, useraddr, sizeof(eeprom))) return -EFAULT; /* Check for wrap and zero */ if (eeprom.offset + eeprom.len <= eeprom.offset) return -EINVAL; /* Check for exceeding total eeprom len */ if (eeprom.offset + eeprom.len > total_len) return -EINVAL; data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; bytes_remaining = eeprom.len; while (bytes_remaining > 0) { eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE); ret = getter(dev, &eeprom, data); if (ret) break; if (copy_to_user(userbuf, data, eeprom.len)) { ret = -EFAULT; break; } userbuf += eeprom.len; eeprom.offset += eeprom.len; bytes_remaining -= eeprom.len; } eeprom.len = userbuf - (useraddr + sizeof(eeprom)); eeprom.offset -= eeprom.len; if (copy_to_user(useraddr, &eeprom, sizeof(eeprom))) ret = -EFAULT; kfree(data); return ret; } static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) { const struct ethtool_ops *ops = dev->ethtool_ops; if (!ops->get_eeprom || !ops->get_eeprom_len || !ops->get_eeprom_len(dev)) return -EOPNOTSUPP; return ethtool_get_any_eeprom(dev, useraddr, ops->get_eeprom, ops->get_eeprom_len(dev)); } static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; const struct ethtool_ops *ops = dev->ethtool_ops; void __user *userbuf = useraddr + sizeof(eeprom); u32 bytes_remaining; u8 *data; int ret = 0; if (!ops->set_eeprom || !ops->get_eeprom_len || !ops->get_eeprom_len(dev)) return -EOPNOTSUPP; if (copy_from_user(&eeprom, useraddr, sizeof(eeprom))) return -EFAULT; /* Check for wrap and zero */ if (eeprom.offset + eeprom.len <= eeprom.offset) return -EINVAL; /* Check for exceeding total eeprom len */ if (eeprom.offset + eeprom.len > ops->get_eeprom_len(dev)) return -EINVAL; data = kzalloc(PAGE_SIZE, GFP_USER); if (!data) return -ENOMEM; bytes_remaining = eeprom.len; while (bytes_remaining > 0) { eeprom.len = min(bytes_remaining, (u32)PAGE_SIZE); if (copy_from_user(data, userbuf, eeprom.len)) { ret = -EFAULT; break; } ret = ops->set_eeprom(dev, &eeprom, data); if (ret) break; userbuf += eeprom.len; eeprom.offset += eeprom.len; bytes_remaining -= eeprom.len; } kfree(data); return ret; } static noinline_for_stack int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; dev->ethtool_ops->get_coalesce(dev, &coalesce); if (copy_to_user(useraddr, &coalesce, sizeof(coalesce))) return -EFAULT; return 0; } static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce; if (!dev->ethtool_ops->set_coalesce) return -EOPNOTSUPP; if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) return -EFAULT; return dev->ethtool_ops->set_coalesce(dev, &coalesce); } static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) { struct ethtool_ringparam ringparam = { .cmd = ETHTOOL_GRINGPARAM }; if (!dev->ethtool_ops->get_ringparam) return -EOPNOTSUPP; dev->ethtool_ops->get_ringparam(dev, &ringparam); if (copy_to_user(useraddr, &ringparam, sizeof(ringparam))) return -EFAULT; return 0; } static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr) { struct ethtool_ringparam ringparam, max = { .cmd = ETHTOOL_GRINGPARAM }; if (!dev->ethtool_ops->set_ringparam || !dev->ethtool_ops->get_ringparam) return -EOPNOTSUPP; if (copy_from_user(&ringparam, useraddr, sizeof(ringparam))) return -EFAULT; dev->ethtool_ops->get_ringparam(dev, &max); /* ensure new ring parameters are within the maximums */ if (ringparam.rx_pending > max.rx_max_pending || ringparam.rx_mini_pending > max.rx_mini_max_pending || ringparam.rx_jumbo_pending > max.rx_jumbo_max_pending || ringparam.tx_pending > max.tx_max_pending) return -EINVAL; return dev->ethtool_ops->set_ringparam(dev, &ringparam); } static noinline_for_stack int ethtool_get_channels(struct net_device *dev, void __user *useraddr) { struct ethtool_channels channels = { .cmd = ETHTOOL_GCHANNELS }; if (!dev->ethtool_ops->get_channels) return -EOPNOTSUPP; dev->ethtool_ops->get_channels(dev, &channels); if (copy_to_user(useraddr, &channels, sizeof(channels))) return -EFAULT; return 0; } static noinline_for_stack int ethtool_set_channels(struct net_device *dev, void __user *useraddr) { struct ethtool_channels channels, curr = { .cmd = ETHTOOL_GCHANNELS }; u16 from_channel, to_channel; u32 max_rx_in_use = 0; unsigned int i; if (!dev->ethtool_ops->set_channels || !dev->ethtool_ops->get_channels) return -EOPNOTSUPP; if (copy_from_user(&channels, useraddr, sizeof(channels))) return -EFAULT; dev->ethtool_ops->get_channels(dev, &curr); /* ensure new counts are within the maximums */ if (channels.rx_count > curr.max_rx || channels.tx_count > curr.max_tx || channels.combined_count > curr.max_combined || channels.other_count > curr.max_other) return -EINVAL; /* ensure the new Rx count fits within the configured Rx flow * indirection table settings */ if (netif_is_rxfh_configured(dev) && !ethtool_get_max_rxfh_channel(dev, &max_rx_in_use) && (channels.combined_count + channels.rx_count) <= max_rx_in_use) return -EINVAL; /* Disabling channels, query zero-copy AF_XDP sockets */ from_channel = channels.combined_count + min(channels.rx_count, channels.tx_count); to_channel = curr.combined_count + max(curr.rx_count, curr.tx_count); for (i = from_channel; i < to_channel; i++) if (xdp_get_umem_from_qid(dev, i)) return -EINVAL; return dev->ethtool_ops->set_channels(dev, &channels); } static int ethtool_get_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam = { .cmd = ETHTOOL_GPAUSEPARAM }; if (!dev->ethtool_ops->get_pauseparam) return -EOPNOTSUPP; dev->ethtool_ops->get_pauseparam(dev, &pauseparam); if (copy_to_user(useraddr, &pauseparam, sizeof(pauseparam))) return -EFAULT; return 0; } static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr) { struct ethtool_pauseparam pauseparam; if (!dev->ethtool_ops->set_pauseparam) return -EOPNOTSUPP; if (copy_from_user(&pauseparam, useraddr, sizeof(pauseparam))) return -EFAULT; return dev->ethtool_ops->set_pauseparam(dev, &pauseparam); } static int ethtool_self_test(struct net_device *dev, char __user *useraddr) { struct ethtool_test test; const struct ethtool_ops *ops = dev->ethtool_ops; u64 *data; int ret, test_len; if (!ops->self_test || !ops->get_sset_count) return -EOPNOTSUPP; test_len = ops->get_sset_count(dev, ETH_SS_TEST); if (test_len < 0) return test_len; WARN_ON(test_len == 0); if (copy_from_user(&test, useraddr, sizeof(test))) return -EFAULT; test.len = test_len; data = kcalloc(test_len, sizeof(u64), GFP_USER); if (!data) return -ENOMEM; ops->self_test(dev, &test, data); ret = -EFAULT; if (copy_to_user(useraddr, &test, sizeof(test))) goto out; useraddr += sizeof(test); if (copy_to_user(useraddr, data, test.len * sizeof(u64))) goto out; ret = 0; out: kfree(data); return ret; } static int ethtool_get_strings(struct net_device *dev, void __user *useraddr) { struct ethtool_gstrings gstrings; u8 *data; int ret; if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) return -EFAULT; ret = __ethtool_get_sset_count(dev, gstrings.string_set); if (ret < 0) return ret; if (ret > S32_MAX / ETH_GSTRING_LEN) return -ENOMEM; WARN_ON_ONCE(!ret); gstrings.len = ret; if (gstrings.len) { data = vzalloc(array_size(gstrings.len, ETH_GSTRING_LEN)); if (!data) return -ENOMEM; __ethtool_get_strings(dev, gstrings.string_set, data); } else { data = NULL; } ret = -EFAULT; if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) goto out; useraddr += sizeof(gstrings); if (gstrings.len && copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) goto out; ret = 0; out: vfree(data); return ret; } static int ethtool_phys_id(struct net_device *dev, void __user *useraddr) { struct ethtool_value id; static bool busy; const struct ethtool_ops *ops = dev->ethtool_ops; int rc; if (!ops->set_phys_id) return -EOPNOTSUPP; if (busy) return -EBUSY; if (copy_from_user(&id, useraddr, sizeof(id))) return -EFAULT; rc = ops->set_phys_id(dev, ETHTOOL_ID_ACTIVE); if (rc < 0) return rc; /* Drop the RTNL lock while waiting, but prevent reentry or * removal of the device. */ busy = true; dev_hold(dev); rtnl_unlock(); if (rc == 0) { /* Driver will handle this itself */ schedule_timeout_interruptible( id.data ? (id.data * HZ) : MAX_SCHEDULE_TIMEOUT); } else { /* Driver expects to be called at twice the frequency in rc */ int n = rc * 2, i, interval = HZ / n; /* Count down seconds */ do { /* Count down iterations per second */ i = n; do { rtnl_lock(); rc = ops->set_phys_id(dev, (i & 1) ? ETHTOOL_ID_OFF : ETHTOOL_ID_ON); rtnl_unlock(); if (rc) break; schedule_timeout_interruptible(interval); } while (!signal_pending(current) && --i != 0); } while (!signal_pending(current) && (id.data == 0 || --id.data != 0)); } rtnl_lock(); dev_put(dev); busy = false; (void) ops->set_phys_id(dev, ETHTOOL_ID_INACTIVE); return rc; } static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) { struct ethtool_stats stats; const struct ethtool_ops *ops = dev->ethtool_ops; u64 *data; int ret, n_stats; if (!ops->get_ethtool_stats || !ops->get_sset_count) return -EOPNOTSUPP; n_stats = ops->get_sset_count(dev, ETH_SS_STATS); if (n_stats < 0) return n_stats; if (n_stats > S32_MAX / sizeof(u64)) return -ENOMEM; WARN_ON_ONCE(!n_stats); if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; stats.n_stats = n_stats; if (n_stats) { data = vzalloc(array_size(n_stats, sizeof(u64))); if (!data) return -ENOMEM; ops->get_ethtool_stats(dev, &stats, data); } else { data = NULL; } ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) goto out; useraddr += sizeof(stats); if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64))) goto out; ret = 0; out: vfree(data); return ret; } static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) { const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; struct ethtool_stats stats; u64 *data; int ret, n_stats; if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count)) return -EOPNOTSUPP; if (dev->phydev && !ops->get_ethtool_phy_stats) n_stats = phy_ethtool_get_sset_count(dev->phydev); else n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); if (n_stats < 0) return n_stats; if (n_stats > S32_MAX / sizeof(u64)) return -ENOMEM; if (WARN_ON_ONCE(!n_stats)) return -EOPNOTSUPP; if (copy_from_user(&stats, useraddr, sizeof(stats))) return -EFAULT; stats.n_stats = n_stats; if (n_stats) { data = vzalloc(array_size(n_stats, sizeof(u64))); if (!data) return -ENOMEM; if (dev->phydev && !ops->get_ethtool_phy_stats) { ret = phy_ethtool_get_stats(dev->phydev, &stats, data); if (ret < 0) goto out; } else { ops->get_ethtool_phy_stats(dev, &stats, data); } } else { data = NULL; } ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) goto out; useraddr += sizeof(stats); if (n_stats && copy_to_user(useraddr, data, n_stats * sizeof(u64))) goto out; ret = 0; out: vfree(data); return ret; } static int ethtool_get_perm_addr(struct net_device *dev, void __user *useraddr) { struct ethtool_perm_addr epaddr; if (copy_from_user(&epaddr, useraddr, sizeof(epaddr))) return -EFAULT; if (epaddr.size < dev->addr_len) return -ETOOSMALL; epaddr.size = dev->addr_len; if (copy_to_user(useraddr, &epaddr, sizeof(epaddr))) return -EFAULT; useraddr += sizeof(epaddr); if (copy_to_user(useraddr, dev->perm_addr, epaddr.size)) return -EFAULT; return 0; } static int ethtool_get_value(struct net_device *dev, char __user *useraddr, u32 cmd, u32 (*actor)(struct net_device *)) { struct ethtool_value edata = { .cmd = cmd }; if (!actor) return -EOPNOTSUPP; edata.data = actor(dev); if (copy_to_user(useraddr, &edata, sizeof(edata))) return -EFAULT; return 0; } static int ethtool_set_value_void(struct net_device *dev, char __user *useraddr, void (*actor)(struct net_device *, u32)) { struct ethtool_value edata; if (!actor) return -EOPNOTSUPP; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; actor(dev, edata.data); return 0; } static int ethtool_set_value(struct net_device *dev, char __user *useraddr, int (*actor)(struct net_device *, u32)) { struct ethtool_value edata; if (!actor) return -EOPNOTSUPP; if (copy_from_user(&edata, useraddr, sizeof(edata))) return -EFAULT; return actor(dev, edata.data); } static noinline_for_stack int ethtool_flash_device(struct net_device *dev, char __user *useraddr) { struct ethtool_flash efl; if (copy_from_user(&efl, useraddr, sizeof(efl))) return -EFAULT; efl.data[ETHTOOL_FLASH_MAX_FILENAME - 1] = 0; if (!dev->ethtool_ops->flash_device) return devlink_compat_flash_update(dev, efl.data); return dev->ethtool_ops->flash_device(dev, &efl); } static int ethtool_set_dump(struct net_device *dev, void __user *useraddr) { struct ethtool_dump dump; if (!dev->ethtool_ops->set_dump) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) return -EFAULT; return dev->ethtool_ops->set_dump(dev, &dump); } static int ethtool_get_dump_flag(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_dump dump; const struct ethtool_ops *ops = dev->ethtool_ops; if (!ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) return -EFAULT; ret = ops->get_dump_flag(dev, &dump); if (ret) return ret; if (copy_to_user(useraddr, &dump, sizeof(dump))) return -EFAULT; return 0; } static int ethtool_get_dump_data(struct net_device *dev, void __user *useraddr) { int ret; __u32 len; struct ethtool_dump dump, tmp; const struct ethtool_ops *ops = dev->ethtool_ops; void *data = NULL; if (!ops->get_dump_data || !ops->get_dump_flag) return -EOPNOTSUPP; if (copy_from_user(&dump, useraddr, sizeof(dump))) return -EFAULT; memset(&tmp, 0, sizeof(tmp)); tmp.cmd = ETHTOOL_GET_DUMP_FLAG; ret = ops->get_dump_flag(dev, &tmp); if (ret) return ret; len = min(tmp.len, dump.len); if (!len) return -EFAULT; /* Don't ever let the driver think there's more space available * than it requested with .get_dump_flag(). */ dump.len = len; /* Always allocate enough space to hold the whole thing so that the * driver does not need to check the length and bother with partial * dumping. */ data = vzalloc(tmp.len); if (!data) return -ENOMEM; ret = ops->get_dump_data(dev, &dump, data); if (ret) goto out; /* There are two sane possibilities: * 1. The driver's .get_dump_data() does not touch dump.len. * 2. Or it may set dump.len to how much it really writes, which * should be tmp.len (or len if it can do a partial dump). * In any case respond to userspace with the actual length of data * it's receiving. */ WARN_ON(dump.len != len && dump.len != tmp.len); dump.len = len; if (copy_to_user(useraddr, &dump, sizeof(dump))) { ret = -EFAULT; goto out; } useraddr += offsetof(struct ethtool_dump, data); if (copy_to_user(useraddr, data, len)) ret = -EFAULT; out: vfree(data); return ret; } static int ethtool_get_ts_info(struct net_device *dev, void __user *useraddr) { int err = 0; struct ethtool_ts_info info; const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GET_TS_INFO; if (phydev && phydev->drv && phydev->drv->ts_info) { err = phydev->drv->ts_info(phydev, &info); } else if (ops->get_ts_info) { err = ops->get_ts_info(dev, &info); } else { info.so_timestamping = SOF_TIMESTAMPING_RX_SOFTWARE | SOF_TIMESTAMPING_SOFTWARE; info.phc_index = -1; } if (err) return err; if (copy_to_user(useraddr, &info, sizeof(info))) err = -EFAULT; return err; } static int __ethtool_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; if (dev->sfp_bus) return sfp_get_module_info(dev->sfp_bus, modinfo); if (phydev && phydev->drv && phydev->drv->module_info) return phydev->drv->module_info(phydev, modinfo); if (ops->get_module_info) return ops->get_module_info(dev, modinfo); return -EOPNOTSUPP; } static int ethtool_get_module_info(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_modinfo modinfo; if (copy_from_user(&modinfo, useraddr, sizeof(modinfo))) return -EFAULT; ret = __ethtool_get_module_info(dev, &modinfo); if (ret) return ret; if (copy_to_user(useraddr, &modinfo, sizeof(modinfo))) return -EFAULT; return 0; } static int __ethtool_get_module_eeprom(struct net_device *dev, struct ethtool_eeprom *ee, u8 *data) { const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; if (dev->sfp_bus) return sfp_get_module_eeprom(dev->sfp_bus, ee, data); if (phydev && phydev->drv && phydev->drv->module_eeprom) return phydev->drv->module_eeprom(phydev, ee, data); if (ops->get_module_eeprom) return ops->get_module_eeprom(dev, ee, data); return -EOPNOTSUPP; } static int ethtool_get_module_eeprom(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_modinfo modinfo; ret = __ethtool_get_module_info(dev, &modinfo); if (ret) return ret; return ethtool_get_any_eeprom(dev, useraddr, __ethtool_get_module_eeprom, modinfo.eeprom_len); } static int ethtool_tunable_valid(const struct ethtool_tunable *tuna) { switch (tuna->id) { case ETHTOOL_RX_COPYBREAK: case ETHTOOL_TX_COPYBREAK: if (tuna->len != sizeof(u32) || tuna->type_id != ETHTOOL_TUNABLE_U32) return -EINVAL; break; case ETHTOOL_PFC_PREVENTION_TOUT: if (tuna->len != sizeof(u16) || tuna->type_id != ETHTOOL_TUNABLE_U16) return -EINVAL; break; default: return -EINVAL; } return 0; } static int ethtool_get_tunable(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_tunable tuna; const struct ethtool_ops *ops = dev->ethtool_ops; void *data; if (!ops->get_tunable) return -EOPNOTSUPP; if (copy_from_user(&tuna, useraddr, sizeof(tuna))) return -EFAULT; ret = ethtool_tunable_valid(&tuna); if (ret) return ret; data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; ret = ops->get_tunable(dev, &tuna, data); if (ret) goto out; useraddr += sizeof(tuna); ret = -EFAULT; if (copy_to_user(useraddr, data, tuna.len)) goto out; ret = 0; out: kfree(data); return ret; } static int ethtool_set_tunable(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_tunable tuna; const struct ethtool_ops *ops = dev->ethtool_ops; void *data; if (!ops->set_tunable) return -EOPNOTSUPP; if (copy_from_user(&tuna, useraddr, sizeof(tuna))) return -EFAULT; ret = ethtool_tunable_valid(&tuna); if (ret) return ret; useraddr += sizeof(tuna); data = memdup_user(useraddr, tuna.len); if (IS_ERR(data)) return PTR_ERR(data); ret = ops->set_tunable(dev, &tuna, data); kfree(data); return ret; } static noinline_for_stack int ethtool_get_per_queue_coalesce(struct net_device *dev, void __user *useraddr, struct ethtool_per_queue_op *per_queue_opt) { u32 bit; int ret; DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); if (!dev->ethtool_ops->get_per_queue_coalesce) return -EOPNOTSUPP; useraddr += sizeof(*per_queue_opt); bitmap_from_arr32(queue_mask, per_queue_opt->queue_mask, MAX_NUM_QUEUE); for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, &coalesce); if (ret != 0) return ret; if (copy_to_user(useraddr, &coalesce, sizeof(coalesce))) return -EFAULT; useraddr += sizeof(coalesce); } return 0; } static noinline_for_stack int ethtool_set_per_queue_coalesce(struct net_device *dev, void __user *useraddr, struct ethtool_per_queue_op *per_queue_opt) { u32 bit; int i, ret = 0; int n_queue; struct ethtool_coalesce *backup = NULL, *tmp = NULL; DECLARE_BITMAP(queue_mask, MAX_NUM_QUEUE); if ((!dev->ethtool_ops->set_per_queue_coalesce) || (!dev->ethtool_ops->get_per_queue_coalesce)) return -EOPNOTSUPP; useraddr += sizeof(*per_queue_opt); bitmap_from_arr32(queue_mask, per_queue_opt->queue_mask, MAX_NUM_QUEUE); n_queue = bitmap_weight(queue_mask, MAX_NUM_QUEUE); tmp = backup = kmalloc_array(n_queue, sizeof(*backup), GFP_KERNEL); if (!backup) return -ENOMEM; for_each_set_bit(bit, queue_mask, MAX_NUM_QUEUE) { struct ethtool_coalesce coalesce; ret = dev->ethtool_ops->get_per_queue_coalesce(dev, bit, tmp); if (ret != 0) goto roll_back; tmp++; if (copy_from_user(&coalesce, useraddr, sizeof(coalesce))) { ret = -EFAULT; goto roll_back; } ret = dev->ethtool_ops->set_per_queue_coalesce(dev, bit, &coalesce); if (ret != 0) goto roll_back; useraddr += sizeof(coalesce); } roll_back: if (ret != 0) { tmp = backup; for_each_set_bit(i, queue_mask, bit) { dev->ethtool_ops->set_per_queue_coalesce(dev, i, tmp); tmp++; } } kfree(backup); return ret; } static int noinline_for_stack ethtool_set_per_queue(struct net_device *dev, void __user *useraddr, u32 sub_cmd) { struct ethtool_per_queue_op per_queue_opt; if (copy_from_user(&per_queue_opt, useraddr, sizeof(per_queue_opt))) return -EFAULT; if (per_queue_opt.sub_command != sub_cmd) return -EINVAL; switch (per_queue_opt.sub_command) { case ETHTOOL_GCOALESCE: return ethtool_get_per_queue_coalesce(dev, useraddr, &per_queue_opt); case ETHTOOL_SCOALESCE: return ethtool_set_per_queue_coalesce(dev, useraddr, &per_queue_opt); default: return -EOPNOTSUPP; }; } static int ethtool_phy_tunable_valid(const struct ethtool_tunable *tuna) { switch (tuna->id) { case ETHTOOL_PHY_DOWNSHIFT: case ETHTOOL_PHY_FAST_LINK_DOWN: if (tuna->len != sizeof(u8) || tuna->type_id != ETHTOOL_TUNABLE_U8) return -EINVAL; break; case ETHTOOL_PHY_EDPD: if (tuna->len != sizeof(u16) || tuna->type_id != ETHTOOL_TUNABLE_U16) return -EINVAL; break; default: return -EINVAL; } return 0; } static int get_phy_tunable(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_tunable tuna; struct phy_device *phydev = dev->phydev; void *data; if (!(phydev && phydev->drv && phydev->drv->get_tunable)) return -EOPNOTSUPP; if (copy_from_user(&tuna, useraddr, sizeof(tuna))) return -EFAULT; ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; data = kzalloc(tuna.len, GFP_USER); if (!data) return -ENOMEM; mutex_lock(&phydev->lock); ret = phydev->drv->get_tunable(phydev, &tuna, data); mutex_unlock(&phydev->lock); if (ret) goto out; useraddr += sizeof(tuna); ret = -EFAULT; if (copy_to_user(useraddr, data, tuna.len)) goto out; ret = 0; out: kfree(data); return ret; } static int set_phy_tunable(struct net_device *dev, void __user *useraddr) { int ret; struct ethtool_tunable tuna; struct phy_device *phydev = dev->phydev; void *data; if (!(phydev && phydev->drv && phydev->drv->set_tunable)) return -EOPNOTSUPP; if (copy_from_user(&tuna, useraddr, sizeof(tuna))) return -EFAULT; ret = ethtool_phy_tunable_valid(&tuna); if (ret) return ret; useraddr += sizeof(tuna); data = memdup_user(useraddr, tuna.len); if (IS_ERR(data)) return PTR_ERR(data); mutex_lock(&phydev->lock); ret = phydev->drv->set_tunable(phydev, &tuna, data); mutex_unlock(&phydev->lock); kfree(data); return ret; } static int ethtool_get_fecparam(struct net_device *dev, void __user *useraddr) { struct ethtool_fecparam fecparam = { .cmd = ETHTOOL_GFECPARAM }; int rc; if (!dev->ethtool_ops->get_fecparam) return -EOPNOTSUPP; rc = dev->ethtool_ops->get_fecparam(dev, &fecparam); if (rc) return rc; if (copy_to_user(useraddr, &fecparam, sizeof(fecparam))) return -EFAULT; return 0; } static int ethtool_set_fecparam(struct net_device *dev, void __user *useraddr) { struct ethtool_fecparam fecparam; if (!dev->ethtool_ops->set_fecparam) return -EOPNOTSUPP; if (copy_from_user(&fecparam, useraddr, sizeof(fecparam))) return -EFAULT; return dev->ethtool_ops->set_fecparam(dev, &fecparam); } /* The main entry point in this file. Called from net/core/dev_ioctl.c */ int dev_ethtool(struct net *net, struct ifreq *ifr) { struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name); void __user *useraddr = ifr->ifr_data; u32 ethcmd, sub_cmd; int rc; netdev_features_t old_features; if (!dev || !netif_device_present(dev)) return -ENODEV; if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; if (ethcmd == ETHTOOL_PERQUEUE) { if (copy_from_user(&sub_cmd, useraddr + sizeof(ethcmd), sizeof(sub_cmd))) return -EFAULT; } else { sub_cmd = ethcmd; } /* Allow some commands to be done by anyone */ switch (sub_cmd) { case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: case ETHTOOL_GLINK: case ETHTOOL_GCOALESCE: case ETHTOOL_GRINGPARAM: case ETHTOOL_GPAUSEPARAM: case ETHTOOL_GRXCSUM: case ETHTOOL_GTXCSUM: case ETHTOOL_GSG: case ETHTOOL_GSSET_INFO: case ETHTOOL_GSTRINGS: case ETHTOOL_GSTATS: case ETHTOOL_GPHYSTATS: case ETHTOOL_GTSO: case ETHTOOL_GPERMADDR: case ETHTOOL_GUFO: case ETHTOOL_GGSO: case ETHTOOL_GGRO: case ETHTOOL_GFLAGS: case ETHTOOL_GPFLAGS: case ETHTOOL_GRXFH: case ETHTOOL_GRXRINGS: case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: case ETHTOOL_GRXFHINDIR: case ETHTOOL_GRSSH: case ETHTOOL_GFEATURES: case ETHTOOL_GCHANNELS: case ETHTOOL_GET_TS_INFO: case ETHTOOL_GEEE: case ETHTOOL_GTUNABLE: case ETHTOOL_PHY_GTUNABLE: case ETHTOOL_GLINKSETTINGS: case ETHTOOL_GFECPARAM: break; default: if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) return -EPERM; } if (dev->ethtool_ops->begin) { rc = dev->ethtool_ops->begin(dev); if (rc < 0) return rc; } old_features = dev->features; switch (ethcmd) { case ETHTOOL_GSET: rc = ethtool_get_settings(dev, useraddr); break; case ETHTOOL_SSET: rc = ethtool_set_settings(dev, useraddr); break; case ETHTOOL_GDRVINFO: rc = ethtool_get_drvinfo(dev, useraddr); break; case ETHTOOL_GREGS: rc = ethtool_get_regs(dev, useraddr); break; case ETHTOOL_GWOL: rc = ethtool_get_wol(dev, useraddr); break; case ETHTOOL_SWOL: rc = ethtool_set_wol(dev, useraddr); break; case ETHTOOL_GMSGLVL: rc = ethtool_get_value(dev, useraddr, ethcmd, dev->ethtool_ops->get_msglevel); break; case ETHTOOL_SMSGLVL: rc = ethtool_set_value_void(dev, useraddr, dev->ethtool_ops->set_msglevel); break; case ETHTOOL_GEEE: rc = ethtool_get_eee(dev, useraddr); break; case ETHTOOL_SEEE: rc = ethtool_set_eee(dev, useraddr); break; case ETHTOOL_NWAY_RST: rc = ethtool_nway_reset(dev); break; case ETHTOOL_GLINK: rc = ethtool_get_link(dev, useraddr); break; case ETHTOOL_GEEPROM: rc = ethtool_get_eeprom(dev, useraddr); break; case ETHTOOL_SEEPROM: rc = ethtool_set_eeprom(dev, useraddr); break; case ETHTOOL_GCOALESCE: rc = ethtool_get_coalesce(dev, useraddr); break; case ETHTOOL_SCOALESCE: rc = ethtool_set_coalesce(dev, useraddr); break; case ETHTOOL_GRINGPARAM: rc = ethtool_get_ringparam(dev, useraddr); break; case ETHTOOL_SRINGPARAM: rc = ethtool_set_ringparam(dev, useraddr); break; case ETHTOOL_GPAUSEPARAM: rc = ethtool_get_pauseparam(dev, useraddr); break; case ETHTOOL_SPAUSEPARAM: rc = ethtool_set_pauseparam(dev, useraddr); break; case ETHTOOL_TEST: rc = ethtool_self_test(dev, useraddr); break; case ETHTOOL_GSTRINGS: rc = ethtool_get_strings(dev, useraddr); break; case ETHTOOL_PHYS_ID: rc = ethtool_phys_id(dev, useraddr); break; case ETHTOOL_GSTATS: rc = ethtool_get_stats(dev, useraddr); break; case ETHTOOL_GPERMADDR: rc = ethtool_get_perm_addr(dev, useraddr); break; case ETHTOOL_GFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, __ethtool_get_flags); break; case ETHTOOL_SFLAGS: rc = ethtool_set_value(dev, useraddr, __ethtool_set_flags); break; case ETHTOOL_GPFLAGS: rc = ethtool_get_value(dev, useraddr, ethcmd, dev->ethtool_ops->get_priv_flags); break; case ETHTOOL_SPFLAGS: rc = ethtool_set_value(dev, useraddr, dev->ethtool_ops->set_priv_flags); break; case ETHTOOL_GRXFH: case ETHTOOL_GRXRINGS: case ETHTOOL_GRXCLSRLCNT: case ETHTOOL_GRXCLSRULE: case ETHTOOL_GRXCLSRLALL: rc = ethtool_get_rxnfc(dev, ethcmd, useraddr); break; case ETHTOOL_SRXFH: case ETHTOOL_SRXCLSRLDEL: case ETHTOOL_SRXCLSRLINS: rc = ethtool_set_rxnfc(dev, ethcmd, useraddr); break; case ETHTOOL_FLASHDEV: rc = ethtool_flash_device(dev, useraddr); break; case ETHTOOL_RESET: rc = ethtool_reset(dev, useraddr); break; case ETHTOOL_GSSET_INFO: rc = ethtool_get_sset_info(dev, useraddr); break; case ETHTOOL_GRXFHINDIR: rc = ethtool_get_rxfh_indir(dev, useraddr); break; case ETHTOOL_SRXFHINDIR: rc = ethtool_set_rxfh_indir(dev, useraddr); break; case ETHTOOL_GRSSH: rc = ethtool_get_rxfh(dev, useraddr); break; case ETHTOOL_SRSSH: rc = ethtool_set_rxfh(dev, useraddr); break; case ETHTOOL_GFEATURES: rc = ethtool_get_features(dev, useraddr); break; case ETHTOOL_SFEATURES: rc = ethtool_set_features(dev, useraddr); break; case ETHTOOL_GTXCSUM: case ETHTOOL_GRXCSUM: case ETHTOOL_GSG: case ETHTOOL_GTSO: case ETHTOOL_GGSO: case ETHTOOL_GGRO: rc = ethtool_get_one_feature(dev, useraddr, ethcmd); break; case ETHTOOL_STXCSUM: case ETHTOOL_SRXCSUM: case ETHTOOL_SSG: case ETHTOOL_STSO: case ETHTOOL_SGSO: case ETHTOOL_SGRO: rc = ethtool_set_one_feature(dev, useraddr, ethcmd); break; case ETHTOOL_GCHANNELS: rc = ethtool_get_channels(dev, useraddr); break; case ETHTOOL_SCHANNELS: rc = ethtool_set_channels(dev, useraddr); break; case ETHTOOL_SET_DUMP: rc = ethtool_set_dump(dev, useraddr); break; case ETHTOOL_GET_DUMP_FLAG: rc = ethtool_get_dump_flag(dev, useraddr); break; case ETHTOOL_GET_DUMP_DATA: rc = ethtool_get_dump_data(dev, useraddr); break; case ETHTOOL_GET_TS_INFO: rc = ethtool_get_ts_info(dev, useraddr); break; case ETHTOOL_GMODULEINFO: rc = ethtool_get_module_info(dev, useraddr); break; case ETHTOOL_GMODULEEEPROM: rc = ethtool_get_module_eeprom(dev, useraddr); break; case ETHTOOL_GTUNABLE: rc = ethtool_get_tunable(dev, useraddr); break; case ETHTOOL_STUNABLE: rc = ethtool_set_tunable(dev, useraddr); break; case ETHTOOL_GPHYSTATS: rc = ethtool_get_phy_stats(dev, useraddr); break; case ETHTOOL_PERQUEUE: rc = ethtool_set_per_queue(dev, useraddr, sub_cmd); break; case ETHTOOL_GLINKSETTINGS: rc = ethtool_get_link_ksettings(dev, useraddr); break; case ETHTOOL_SLINKSETTINGS: rc = ethtool_set_link_ksettings(dev, useraddr); break; case ETHTOOL_PHY_GTUNABLE: rc = get_phy_tunable(dev, useraddr); break; case ETHTOOL_PHY_STUNABLE: rc = set_phy_tunable(dev, useraddr); break; case ETHTOOL_GFECPARAM: rc = ethtool_get_fecparam(dev, useraddr); break; case ETHTOOL_SFECPARAM: rc = ethtool_set_fecparam(dev, useraddr); break; default: rc = -EOPNOTSUPP; } if (dev->ethtool_ops->complete) dev->ethtool_ops->complete(dev); if (old_features != dev->features) netdev_features_change(dev); return rc; } struct ethtool_rx_flow_key { struct flow_dissector_key_basic basic; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; }; struct flow_dissector_key_ports tp; struct flow_dissector_key_ip ip; struct flow_dissector_key_vlan vlan; struct flow_dissector_key_eth_addrs eth_addrs; } __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ struct ethtool_rx_flow_match { struct flow_dissector dissector; struct ethtool_rx_flow_key key; struct ethtool_rx_flow_key mask; }; struct ethtool_rx_flow_rule * ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) { const struct ethtool_rx_flow_spec *fs = input->fs; static struct in6_addr zero_addr = {}; struct ethtool_rx_flow_match *match; struct ethtool_rx_flow_rule *flow; struct flow_action_entry *act; flow = kzalloc(sizeof(struct ethtool_rx_flow_rule) + sizeof(struct ethtool_rx_flow_match), GFP_KERNEL); if (!flow) return ERR_PTR(-ENOMEM); /* ethtool_rx supports only one single action per rule. */ flow->rule = flow_rule_alloc(1); if (!flow->rule) { kfree(flow); return ERR_PTR(-ENOMEM); } match = (struct ethtool_rx_flow_match *)flow->priv; flow->rule->match.dissector = &match->dissector; flow->rule->match.mask = &match->mask; flow->rule->match.key = &match->key; match->mask.basic.n_proto = htons(0xffff); switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { case ETHER_FLOW: { const struct ethhdr *ether_spec, *ether_m_spec; ether_spec = &fs->h_u.ether_spec; ether_m_spec = &fs->m_u.ether_spec; if (!is_zero_ether_addr(ether_m_spec->h_source)) { ether_addr_copy(match->key.eth_addrs.src, ether_spec->h_source); ether_addr_copy(match->mask.eth_addrs.src, ether_m_spec->h_source); } if (!is_zero_ether_addr(ether_m_spec->h_dest)) { ether_addr_copy(match->key.eth_addrs.dst, ether_spec->h_dest); ether_addr_copy(match->mask.eth_addrs.dst, ether_m_spec->h_dest); } if (ether_m_spec->h_proto) { match->key.basic.n_proto = ether_spec->h_proto; match->mask.basic.n_proto = ether_m_spec->h_proto; } } break; case TCP_V4_FLOW: case UDP_V4_FLOW: { const struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec; match->key.basic.n_proto = htons(ETH_P_IP); v4_spec = &fs->h_u.tcp_ip4_spec; v4_m_spec = &fs->m_u.tcp_ip4_spec; if (v4_m_spec->ip4src) { match->key.ipv4.src = v4_spec->ip4src; match->mask.ipv4.src = v4_m_spec->ip4src; } if (v4_m_spec->ip4dst) { match->key.ipv4.dst = v4_spec->ip4dst; match->mask.ipv4.dst = v4_m_spec->ip4dst; } if (v4_m_spec->ip4src || v4_m_spec->ip4dst) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = offsetof(struct ethtool_rx_flow_key, ipv4); } if (v4_m_spec->psrc) { match->key.tp.src = v4_spec->psrc; match->mask.tp.src = v4_m_spec->psrc; } if (v4_m_spec->pdst) { match->key.tp.dst = v4_spec->pdst; match->mask.tp.dst = v4_m_spec->pdst; } if (v4_m_spec->psrc || v4_m_spec->pdst) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(struct ethtool_rx_flow_key, tp); } if (v4_m_spec->tos) { match->key.ip.tos = v4_spec->tos; match->mask.ip.tos = v4_m_spec->tos; match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = offsetof(struct ethtool_rx_flow_key, ip); } } break; case TCP_V6_FLOW: case UDP_V6_FLOW: { const struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec; match->key.basic.n_proto = htons(ETH_P_IPV6); v6_spec = &fs->h_u.tcp_ip6_spec; v6_m_spec = &fs->m_u.tcp_ip6_spec; if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { memcpy(&match->key.ipv6.src, v6_spec->ip6src, sizeof(match->key.ipv6.src)); memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src, sizeof(match->mask.ipv6.src)); } if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { memcpy(&match->key.ipv6.dst, v6_spec->ip6dst, sizeof(match->key.ipv6.dst)); memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst, sizeof(match->mask.ipv6.dst)); } if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = offsetof(struct ethtool_rx_flow_key, ipv6); } if (v6_m_spec->psrc) { match->key.tp.src = v6_spec->psrc; match->mask.tp.src = v6_m_spec->psrc; } if (v6_m_spec->pdst) { match->key.tp.dst = v6_spec->pdst; match->mask.tp.dst = v6_m_spec->pdst; } if (v6_m_spec->psrc || v6_m_spec->pdst) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_PORTS); match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = offsetof(struct ethtool_rx_flow_key, tp); } if (v6_m_spec->tclass) { match->key.ip.tos = v6_spec->tclass; match->mask.ip.tos = v6_m_spec->tclass; match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_IP); match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = offsetof(struct ethtool_rx_flow_key, ip); } } break; default: ethtool_rx_flow_rule_destroy(flow); return ERR_PTR(-EINVAL); } switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { case TCP_V4_FLOW: case TCP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_TCP; break; case UDP_V4_FLOW: case UDP_V6_FLOW: match->key.basic.ip_proto = IPPROTO_UDP; break; } match->mask.basic.ip_proto = 0xff; match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = offsetof(struct ethtool_rx_flow_key, basic); if (fs->flow_type & FLOW_EXT) { const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; if (ext_m_spec->vlan_etype) { match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype; match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype; } if (ext_m_spec->vlan_tci) { match->key.vlan.vlan_id = ntohs(ext_h_spec->vlan_tci) & 0x0fff; match->mask.vlan.vlan_id = ntohs(ext_m_spec->vlan_tci) & 0x0fff; match->key.vlan.vlan_dei = !!(ext_h_spec->vlan_tci & htons(0x1000)); match->mask.vlan.vlan_dei = !!(ext_m_spec->vlan_tci & htons(0x1000)); match->key.vlan.vlan_priority = (ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13; match->mask.vlan.vlan_priority = (ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13; } if (ext_m_spec->vlan_etype || ext_m_spec->vlan_tci) { match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_VLAN); match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = offsetof(struct ethtool_rx_flow_key, vlan); } } if (fs->flow_type & FLOW_MAC_EXT) { const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; memcpy(match->key.eth_addrs.dst, ext_h_spec->h_dest, ETH_ALEN); memcpy(match->mask.eth_addrs.dst, ext_m_spec->h_dest, ETH_ALEN); match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] = offsetof(struct ethtool_rx_flow_key, eth_addrs); } act = &flow->rule->action.entries[0]; switch (fs->ring_cookie) { case RX_CLS_FLOW_DISC: act->id = FLOW_ACTION_DROP; break; case RX_CLS_FLOW_WAKE: act->id = FLOW_ACTION_WAKE; break; default: act->id = FLOW_ACTION_QUEUE; if (fs->flow_type & FLOW_RSS) act->queue.ctx = input->rss_ctx; act->queue.vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie); act->queue.index = ethtool_get_flow_spec_ring(fs->ring_cookie); break; } return flow; } EXPORT_SYMBOL(ethtool_rx_flow_rule_create); void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *flow) { kfree(flow->rule); kfree(flow); } EXPORT_SYMBOL(ethtool_rx_flow_rule_destroy); |
| 25 25 25 63 8 8 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NDISC_H #define _NDISC_H #include <net/ipv6_stubs.h> /* * ICMP codes for neighbour discovery messages */ #define NDISC_ROUTER_SOLICITATION 133 #define NDISC_ROUTER_ADVERTISEMENT 134 #define NDISC_NEIGHBOUR_SOLICITATION 135 #define NDISC_NEIGHBOUR_ADVERTISEMENT 136 #define NDISC_REDIRECT 137 /* * Router type: cross-layer information from link-layer to * IPv6 layer reported by certain link types (e.g., RFC4214). */ #define NDISC_NODETYPE_UNSPEC 0 /* unspecified (default) */ #define NDISC_NODETYPE_HOST 1 /* host or unauthorized router */ #define NDISC_NODETYPE_NODEFAULT 2 /* non-default router */ #define NDISC_NODETYPE_DEFAULT 3 /* default router */ /* * ndisc options */ enum { __ND_OPT_PREFIX_INFO_END = 0, ND_OPT_SOURCE_LL_ADDR = 1, /* RFC2461 */ ND_OPT_TARGET_LL_ADDR = 2, /* RFC2461 */ ND_OPT_PREFIX_INFO = 3, /* RFC2461 */ ND_OPT_REDIRECT_HDR = 4, /* RFC2461 */ ND_OPT_MTU = 5, /* RFC2461 */ ND_OPT_NONCE = 14, /* RFC7527 */ __ND_OPT_ARRAY_MAX, ND_OPT_ROUTE_INFO = 24, /* RFC4191 */ ND_OPT_RDNSS = 25, /* RFC5006 */ ND_OPT_DNSSL = 31, /* RFC6106 */ ND_OPT_6CO = 34, /* RFC6775 */ ND_OPT_CAPTIVE_PORTAL = 37, /* RFC7710 */ ND_OPT_PREF64 = 38, /* RFC8781 */ __ND_OPT_MAX }; #define MAX_RTR_SOLICITATION_DELAY HZ #define ND_REACHABLE_TIME (30*HZ) #define ND_RETRANS_TIMER HZ #include <linux/compiler.h> #include <linux/icmpv6.h> #include <linux/in6.h> #include <linux/types.h> #include <linux/if_arp.h> #include <linux/netdevice.h> #include <linux/hash.h> #include <net/neighbour.h> /* Set to 3 to get tracing... */ #define ND_DEBUG 1 #define ND_PRINTK(val, level, fmt, ...) \ do { \ if (val <= ND_DEBUG) \ net_##level##_ratelimited(fmt, ##__VA_ARGS__); \ } while (0) struct ctl_table; struct inet6_dev; struct net_device; struct net_proto_family; struct sk_buff; struct prefix_info; extern struct neigh_table nd_tbl; struct nd_msg { struct icmp6hdr icmph; struct in6_addr target; __u8 opt[0]; }; struct rs_msg { struct icmp6hdr icmph; __u8 opt[0]; }; struct ra_msg { struct icmp6hdr icmph; __be32 reachable_time; __be32 retrans_timer; }; struct rd_msg { struct icmp6hdr icmph; struct in6_addr target; struct in6_addr dest; __u8 opt[0]; }; struct nd_opt_hdr { __u8 nd_opt_type; __u8 nd_opt_len; } __packed; /* ND options */ struct ndisc_options { struct nd_opt_hdr *nd_opt_array[__ND_OPT_ARRAY_MAX]; #ifdef CONFIG_IPV6_ROUTE_INFO struct nd_opt_hdr *nd_opts_ri; struct nd_opt_hdr *nd_opts_ri_end; #endif struct nd_opt_hdr *nd_useropts; struct nd_opt_hdr *nd_useropts_end; #if IS_ENABLED(CONFIG_IEEE802154_6LOWPAN) struct nd_opt_hdr *nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR + 1]; #endif }; #define nd_opts_src_lladdr nd_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_opts_tgt_lladdr nd_opt_array[ND_OPT_TARGET_LL_ADDR] #define nd_opts_pi nd_opt_array[ND_OPT_PREFIX_INFO] #define nd_opts_pi_end nd_opt_array[__ND_OPT_PREFIX_INFO_END] #define nd_opts_rh nd_opt_array[ND_OPT_REDIRECT_HDR] #define nd_opts_mtu nd_opt_array[ND_OPT_MTU] #define nd_opts_nonce nd_opt_array[ND_OPT_NONCE] #define nd_802154_opts_src_lladdr nd_802154_opt_array[ND_OPT_SOURCE_LL_ADDR] #define nd_802154_opts_tgt_lladdr nd_802154_opt_array[ND_OPT_TARGET_LL_ADDR] #define NDISC_OPT_SPACE(len) (((len)+2+7)&~7) struct ndisc_options *ndisc_parse_options(const struct net_device *dev, u8 *opt, int opt_len, struct ndisc_options *ndopts); void __ndisc_fill_addr_option(struct sk_buff *skb, int type, void *data, int data_len, int pad); #define NDISC_OPS_REDIRECT_DATA_SPACE 2 /* * This structure defines the hooks for IPv6 neighbour discovery. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*is_useropt)(u8 nd_opt_type): * This function is called when IPv6 decide RA userspace options. if * this function returns 1 then the option given by nd_opt_type will * be handled as userspace option additional to the IPv6 options. * * int (*parse_options)(const struct net_device *dev, * struct nd_opt_hdr *nd_opt, * struct ndisc_options *ndopts): * This function is called while parsing ndisc ops and put each position * as pointer into ndopts. If this function return unequal 0, then this * function took care about the ndisc option, if 0 then the IPv6 ndisc * option parser will take care about that option. * * void (*update)(const struct net_device *dev, struct neighbour *n, * u32 flags, u8 icmp6_type, * const struct ndisc_options *ndopts): * This function is called when IPv6 ndisc updates the neighbour cache * entry. Additional options which can be updated may be previously * parsed by parse_opts callback and accessible over ndopts parameter. * * int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, * struct neighbour *neigh, u8 *ha_buf, * u8 **ha): * This function is called when the necessary option space will be * calculated before allocating a skb. The parameters neigh, ha_buf * abd ha are available on NDISC_REDIRECT messages only. * * void (*fill_addr_option)(const struct net_device *dev, * struct sk_buff *skb, u8 icmp6_type, * const u8 *ha): * This function is called when the skb will finally fill the option * fields inside skb. NOTE: this callback should fill the option * fields to the skb which are previously indicated by opt_space * parameter. That means the decision to add such option should * not lost between these two callbacks, e.g. protected by interface * up state. * * void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, * const struct prefix_info *pinfo, * struct inet6_dev *in6_dev, * struct in6_addr *addr, * int addr_type, u32 addr_flags, * bool sllao, bool tokenized, * __u32 valid_lft, u32 prefered_lft, * bool dev_addr_generated): * This function is called when a RA messages is received with valid * PIO option fields and an IPv6 address will be added to the interface * for autoconfiguration. The parameter dev_addr_generated reports about * if the address was based on dev->dev_addr or not. This can be used * to add a second address if link-layer operates with two link layer * addresses. E.g. 802.15.4 6LoWPAN. */ struct ndisc_ops { int (*is_useropt)(u8 nd_opt_type); int (*parse_options)(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts); void (*update)(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts); int (*opt_addr_space)(const struct net_device *dev, u8 icmp6_type, struct neighbour *neigh, u8 *ha_buf, u8 **ha); void (*fill_addr_option)(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type, const u8 *ha); void (*prefix_rcv_add_addr)(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated); }; #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_ops_is_useropt(const struct net_device *dev, u8 nd_opt_type) { if (dev->ndisc_ops && dev->ndisc_ops->is_useropt) return dev->ndisc_ops->is_useropt(nd_opt_type); else return 0; } static inline int ndisc_ops_parse_options(const struct net_device *dev, struct nd_opt_hdr *nd_opt, struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->parse_options) return dev->ndisc_ops->parse_options(dev, nd_opt, ndopts); else return 0; } static inline void ndisc_ops_update(const struct net_device *dev, struct neighbour *n, u32 flags, u8 icmp6_type, const struct ndisc_options *ndopts) { if (dev->ndisc_ops && dev->ndisc_ops->update) dev->ndisc_ops->update(dev, n, flags, icmp6_type, ndopts); } static inline int ndisc_ops_opt_addr_space(const struct net_device *dev, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space && icmp6_type != NDISC_REDIRECT) return dev->ndisc_ops->opt_addr_space(dev, icmp6_type, NULL, NULL, NULL); else return 0; } static inline int ndisc_ops_redirect_opt_addr_space(const struct net_device *dev, struct neighbour *neigh, u8 *ha_buf, u8 **ha) { if (dev->ndisc_ops && dev->ndisc_ops->opt_addr_space) return dev->ndisc_ops->opt_addr_space(dev, NDISC_REDIRECT, neigh, ha_buf, ha); else return 0; } static inline void ndisc_ops_fill_addr_option(const struct net_device *dev, struct sk_buff *skb, u8 icmp6_type) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option && icmp6_type != NDISC_REDIRECT) dev->ndisc_ops->fill_addr_option(dev, skb, icmp6_type, NULL); } static inline void ndisc_ops_fill_redirect_addr_option(const struct net_device *dev, struct sk_buff *skb, const u8 *ha) { if (dev->ndisc_ops && dev->ndisc_ops->fill_addr_option) dev->ndisc_ops->fill_addr_option(dev, skb, NDISC_REDIRECT, ha); } static inline void ndisc_ops_prefix_rcv_add_addr(struct net *net, struct net_device *dev, const struct prefix_info *pinfo, struct inet6_dev *in6_dev, struct in6_addr *addr, int addr_type, u32 addr_flags, bool sllao, bool tokenized, __u32 valid_lft, u32 prefered_lft, bool dev_addr_generated) { if (dev->ndisc_ops && dev->ndisc_ops->prefix_rcv_add_addr) dev->ndisc_ops->prefix_rcv_add_addr(net, dev, pinfo, in6_dev, addr, addr_type, addr_flags, sllao, tokenized, valid_lft, prefered_lft, dev_addr_generated); } #endif /* * Return the padding between the option length and the start of the * link addr. Currently only IP-over-InfiniBand needs this, although * if RFC 3831 IPv6-over-Fibre Channel is ever implemented it may * also need a pad of 2. */ static inline int ndisc_addr_option_pad(unsigned short type) { switch (type) { case ARPHRD_INFINIBAND: return 2; default: return 0; } } static inline int __ndisc_opt_addr_space(unsigned char addr_len, int pad) { return NDISC_OPT_SPACE(addr_len + pad); } #if IS_ENABLED(CONFIG_IPV6) static inline int ndisc_opt_addr_space(struct net_device *dev, u8 icmp6_type) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_opt_addr_space(dev, icmp6_type); } static inline int ndisc_redirect_opt_addr_space(struct net_device *dev, struct neighbour *neigh, u8 *ops_data_buf, u8 **ops_data) { return __ndisc_opt_addr_space(dev->addr_len, ndisc_addr_option_pad(dev->type)) + ndisc_ops_redirect_opt_addr_space(dev, neigh, ops_data_buf, ops_data); } #endif static inline u8 *__ndisc_opt_addr_data(struct nd_opt_hdr *p, unsigned char addr_len, int prepad) { u8 *lladdr = (u8 *)(p + 1); int lladdrlen = p->nd_opt_len << 3; if (lladdrlen != __ndisc_opt_addr_space(addr_len, prepad)) return NULL; return lladdr + prepad; } static inline u8 *ndisc_opt_addr_data(struct nd_opt_hdr *p, struct net_device *dev) { return __ndisc_opt_addr_data(p, dev->addr_len, ndisc_addr_option_pad(dev->type)); } static inline u32 ndisc_hashfn(const void *pkey, const struct net_device *dev, __u32 *hash_rnd) { const u32 *p32 = pkey; return (((p32[0] ^ hash32_ptr(dev)) * hash_rnd[0]) + (p32[1] * hash_rnd[1]) + (p32[2] * hash_rnd[2]) + (p32[3] * hash_rnd[3])); } static inline struct neighbour *__ipv6_neigh_lookup_noref(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(&nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup_noref_stub(struct net_device *dev, const void *pkey) { return ___neigh_lookup_noref(ipv6_stub->nd_tbl, neigh_key_eq128, ndisc_hashfn, pkey, dev); } static inline struct neighbour *__ipv6_neigh_lookup(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); return n; } static inline void __ipv6_confirm_neigh(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref(dev, pkey); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } static inline void __ipv6_confirm_neigh_stub(struct net_device *dev, const void *pkey) { struct neighbour *n; rcu_read_lock_bh(); n = __ipv6_neigh_lookup_noref_stub(dev, pkey); if (n) { unsigned long now = jiffies; /* avoid dirtying neighbour */ if (READ_ONCE(n->confirmed) != now) WRITE_ONCE(n->confirmed, now); } rcu_read_unlock_bh(); } /* uses ipv6_stub and is meant for use outside of IPv6 core */ static inline struct neighbour *ip_neigh_gw6(struct net_device *dev, const void *addr) { struct neighbour *neigh; neigh = __ipv6_neigh_lookup_noref_stub(dev, addr); if (unlikely(!neigh)) neigh = __neigh_create(ipv6_stub->nd_tbl, addr, dev, false); return neigh; } int ndisc_init(void); int ndisc_late_init(void); void ndisc_late_cleanup(void); void ndisc_cleanup(void); int ndisc_rcv(struct sk_buff *skb); void ndisc_send_ns(struct net_device *dev, const struct in6_addr *solicit, const struct in6_addr *daddr, const struct in6_addr *saddr, u64 nonce); void ndisc_send_rs(struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr); void ndisc_send_na(struct net_device *dev, const struct in6_addr *daddr, const struct in6_addr *solicited_addr, bool router, bool solicited, bool override, bool inc_opt); void ndisc_send_redirect(struct sk_buff *skb, const struct in6_addr *target); int ndisc_mc_map(const struct in6_addr *addr, char *buf, struct net_device *dev, int dir); void ndisc_update(const struct net_device *dev, struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u8 icmp6_type, struct ndisc_options *ndopts); /* * IGMP */ int igmp6_init(void); int igmp6_late_init(void); void igmp6_cleanup(void); void igmp6_late_cleanup(void); int igmp6_event_query(struct sk_buff *skb); int igmp6_event_report(struct sk_buff *skb); #ifdef CONFIG_SYSCTL int ndisc_ifinfo_sysctl_change(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos); int ndisc_ifinfo_sysctl_strategy(struct ctl_table *ctl, void __user *oldval, size_t __user *oldlenp, void __user *newval, size_t newlen); #endif void inet6_ifinfo_notify(int event, struct inet6_dev *idev); #endif |
| 82 82 83 88 14 12 19 12 12 19 19 19 19 81 54 51 32 14 14 14 14 14 131 134 9 9 134 9 9 9 81 81 3 3 3 81 83 82 83 83 14 14 14 14 134 134 134 134 11 11 11 134 82 133 134 134 134 134 134 134 134 11 12 12 3 3 3 4 3 3 12 12 8 4 3 137 138 88 83 82 83 6 77 138 137 138 125 14 138 440 440 133 133 134 81 81 81 84 85 52 52 125 105 21 3 18 74 73 745 742 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: Internet Group Management Protocol [IGMP] * * This code implements the IGMP protocol as defined in RFC1112. There has * been a further revision of this protocol since which is now supported. * * If you have trouble with this module be careful what gcc you have used, * the older version didn't come out right using gcc 2.5.8, the newer one * seems to fall out with gcc 2.6.2. * * Authors: * Alan Cox <alan@lxorguk.ukuu.org.uk> * * Fixes: * * Alan Cox : Added lots of __inline__ to optimise * the memory usage of all the tiny little * functions. * Alan Cox : Dumped the header building experiment. * Alan Cox : Minor tweaks ready for multicast routing * and extended IGMP protocol. * Alan Cox : Removed a load of inline directives. Gcc 2.5.8 * writes utterly bogus code otherwise (sigh) * fixed IGMP loopback to behave in the manner * desired by mrouted, fixed the fact it has been * broken since 1.3.6 and cleaned up a few minor * points. * * Chih-Jen Chang : Tried to revise IGMP to Version 2 * Tsu-Sheng Tsao E-mail: chihjenc@scf.usc.edu and tsusheng@scf.usc.edu * The enhancements are mainly based on Steve Deering's * ipmulti-3.5 source code. * Chih-Jen Chang : Added the igmp_get_mrouter_info and * Tsu-Sheng Tsao igmp_set_mrouter_info to keep track of * the mrouted version on that device. * Chih-Jen Chang : Added the max_resp_time parameter to * Tsu-Sheng Tsao igmp_heard_query(). Using this parameter * to identify the multicast router version * and do what the IGMP version 2 specified. * Chih-Jen Chang : Added a timer to revert to IGMP V2 router * Tsu-Sheng Tsao if the specified time expired. * Alan Cox : Stop IGMP from 0.0.0.0 being accepted. * Alan Cox : Use GFP_ATOMIC in the right places. * Christian Daudt : igmp timer wasn't set for local group * memberships but was being deleted, * which caused a "del_timer() called * from %p with timer not initialized\n" * message (960131). * Christian Daudt : removed del_timer from * igmp_timer_expire function (960205). * Christian Daudt : igmp_heard_report now only calls * igmp_timer_expire if tm->running is * true (960216). * Malcolm Beattie : ttl comparison wrong in igmp_rcv made * igmp_heard_query never trigger. Expiry * miscalculation fixed in igmp_heard_query * and random() made to return unsigned to * prevent negative expiry times. * Alexey Kuznetsov: Wrong group leaving behaviour, backport * fix from pending 2.1.x patches. * Alan Cox: Forget to enable FDDI support earlier. * Alexey Kuznetsov: Fixed leaving groups on device down. * Alexey Kuznetsov: Accordance to igmp-v2-06 draft. * David L Stevens: IGMPv3 support, with help from * Vinay Kulkarni */ #include <linux/module.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/string.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/in.h> #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/inetdevice.h> #include <linux/igmp.h> #include <linux/if_arp.h> #include <linux/rtnetlink.h> #include <linux/times.h> #include <linux/pkt_sched.h> #include <linux/byteorder/generic.h> #include <net/net_namespace.h> #include <net/arp.h> #include <net/ip.h> #include <net/protocol.h> #include <net/route.h> #include <net/sock.h> #include <net/checksum.h> #include <net/inet_common.h> #include <linux/netfilter_ipv4.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif #ifdef CONFIG_PROC_FS #include <linux/proc_fs.h> #include <linux/seq_file.h> #endif #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ #define IGMP_V2_UNSOLICITED_REPORT_INTERVAL (10*HZ) #define IGMP_V3_UNSOLICITED_REPORT_INTERVAL (1*HZ) #define IGMP_QUERY_INTERVAL (125*HZ) #define IGMP_QUERY_RESPONSE_INTERVAL (10*HZ) #define IGMP_INITIAL_REPORT_DELAY (1) /* IGMP_INITIAL_REPORT_DELAY is not from IGMP specs! * IGMP specs require to report membership immediately after * joining a group, but we delay the first report by a * small interval. It seems more natural and still does not * contradict to specs provided this delay is small enough. */ #define IGMP_V1_SEEN(in_dev) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 1 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 1 || \ ((in_dev)->mr_v1_seen && \ time_before(jiffies, (in_dev)->mr_v1_seen))) #define IGMP_V2_SEEN(in_dev) \ (IPV4_DEVCONF_ALL(dev_net(in_dev->dev), FORCE_IGMP_VERSION) == 2 || \ IN_DEV_CONF_GET((in_dev), FORCE_IGMP_VERSION) == 2 || \ ((in_dev)->mr_v2_seen && \ time_before(jiffies, (in_dev)->mr_v2_seen))) static int unsolicited_report_interval(struct in_device *in_dev) { int interval_ms, interval_jiffies; if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV2_UNSOLICITED_REPORT_INTERVAL); else /* v3 */ interval_ms = IN_DEV_CONF_GET( in_dev, IGMPV3_UNSOLICITED_REPORT_INTERVAL); interval_jiffies = msecs_to_jiffies(interval_ms); /* _timer functions can't handle a delay of 0 jiffies so ensure * we always return a positive value. */ if (interval_jiffies <= 0) interval_jiffies = 1; return interval_jiffies; } static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); static void sf_markstate(struct ip_mc_list *pmc); #endif static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); static void ip_ma_put(struct ip_mc_list *im) { if (refcount_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); kfree_rcu(im, rcu); } } #define for_each_pmc_rcu(in_dev, pmc) \ for (pmc = rcu_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rcu_dereference(pmc->next_rcu)) #define for_each_pmc_rtnl(in_dev, pmc) \ for (pmc = rtnl_dereference(in_dev->mc_list); \ pmc != NULL; \ pmc = rtnl_dereference(pmc->next_rcu)) static void ip_sf_list_clear_all(struct ip_sf_list *psf) { struct ip_sf_list *next; while (psf) { next = psf->sf_next; kfree(psf); psf = next; } } #ifdef CONFIG_IP_MULTICAST /* * Timer management */ static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) refcount_dec(&im->refcnt); im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); } /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { int tv = prandom_u32() % max_delay; im->tm_running = 1; if (refcount_inc_not_zero(&im->refcnt)) { if (mod_timer(&im->timer, jiffies + tv + 2)) ip_ma_put(im); } } static void igmp_gq_start_timer(struct in_device *in_dev) { int tv = prandom_u32() % in_dev->mr_maxdelay; unsigned long exp = jiffies + tv + 2; if (in_dev->mr_gq_running && time_after_eq(exp, (in_dev->mr_gq_timer).expires)) return; in_dev->mr_gq_running = 1; if (!mod_timer(&in_dev->mr_gq_timer, exp)) in_dev_hold(in_dev); } static void igmp_ifc_start_timer(struct in_device *in_dev, int delay) { int tv = prandom_u32() % delay; if (!mod_timer(&in_dev->mr_ifc_timer, jiffies+tv+2)) in_dev_hold(in_dev); } static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) { spin_lock_bh(&im->lock); im->unsolicit_count = 0; if (del_timer(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); im->tm_running = 1; spin_unlock_bh(&im->lock); return; } refcount_dec(&im->refcnt); } igmp_start_timer(im, max_delay); spin_unlock_bh(&im->lock); } /* * Send an IGMP report. */ #define IGMP_SIZE (sizeof(struct igmphdr)+sizeof(struct iphdr)+4) static int is_in(struct ip_mc_list *pmc, struct ip_sf_list *psf, int type, int gdeleted, int sdeleted) { switch (type) { case IGMPV3_MODE_IS_INCLUDE: case IGMPV3_MODE_IS_EXCLUDE: if (gdeleted || sdeleted) return 0; if (!(pmc->gsquery && !psf->sf_gsresp)) { if (pmc->sfmode == MCAST_INCLUDE) return 1; /* don't include if this source is excluded * in all filters */ if (psf->sf_count[MCAST_INCLUDE]) return type == IGMPV3_MODE_IS_INCLUDE; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; } return 0; case IGMPV3_CHANGE_TO_INCLUDE: if (gdeleted || sdeleted) return 0; return psf->sf_count[MCAST_INCLUDE] != 0; case IGMPV3_CHANGE_TO_EXCLUDE: if (gdeleted || sdeleted) return 0; if (pmc->sfcount[MCAST_EXCLUDE] == 0 || psf->sf_count[MCAST_INCLUDE]) return 0; return pmc->sfcount[MCAST_EXCLUDE] == psf->sf_count[MCAST_EXCLUDE]; case IGMPV3_ALLOW_NEW_SOURCES: if (gdeleted || !psf->sf_crcount) return 0; return (pmc->sfmode == MCAST_INCLUDE) ^ sdeleted; case IGMPV3_BLOCK_OLD_SOURCES: if (pmc->sfmode == MCAST_INCLUDE) return gdeleted || (psf->sf_crcount && sdeleted); return psf->sf_crcount && !gdeleted && !sdeleted; } return 0; } static int igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct ip_sf_list *psf; int scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (!is_in(pmc, psf, type, gdeleted, sdeleted)) continue; scount++; } return scount; } /* source address selection per RFC 3376 section 4.2.13 */ static __be32 igmpv3_get_srcaddr(struct net_device *dev, const struct flowi4 *fl4) { struct in_device *in_dev = __in_dev_get_rcu(dev); const struct in_ifaddr *ifa; if (!in_dev) return htonl(INADDR_ANY); in_dev_for_each_ifa_rcu(ifa, in_dev) { if (fl4->saddr == ifa->ifa_local) return fl4->saddr; } return htonl(INADDR_ANY); } static struct sk_buff *igmpv3_newpack(struct net_device *dev, unsigned int mtu) { struct sk_buff *skb; struct rtable *rt; struct iphdr *pip; struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; int hlen = LL_RESERVED_SPACE(dev); int tlen = dev->needed_tailroom; unsigned int size; size = min(mtu, IP_MAX_MTU); while (1) { skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; size >>= 1; if (size < 256) return NULL; } skb->priority = TC_PRIO_CONTROL; rt = ip_route_output_ports(net, &fl4, NULL, IGMPV3_ALL_MCR, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) { kfree_skb(skb); return NULL; } skb_dst_set(skb, &rt->dst); skb->dev = dev; skb_reserve(skb, hlen); skb_tailroom_reserve(skb, mtu, tlen); skb_reset_network_header(skb); pip = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); pip->version = 4; pip->ihl = (sizeof(struct iphdr)+4)>>2; pip->tos = 0xc0; pip->frag_off = htons(IP_DF); pip->ttl = 1; pip->daddr = fl4.daddr; rcu_read_lock(); pip->saddr = igmpv3_get_srcaddr(dev, &fl4); rcu_read_unlock(); pip->protocol = IPPROTO_IGMP; pip->tot_len = 0; /* filled in later */ ip_select_ident(net, skb, NULL); ((u8 *)&pip[1])[0] = IPOPT_RA; ((u8 *)&pip[1])[1] = 4; ((u8 *)&pip[1])[2] = 0; ((u8 *)&pip[1])[3] = 0; skb->transport_header = skb->network_header + sizeof(struct iphdr) + 4; skb_put(skb, sizeof(*pig)); pig = igmpv3_report_hdr(skb); pig->type = IGMPV3_HOST_MEMBERSHIP_REPORT; pig->resv1 = 0; pig->csum = 0; pig->resv2 = 0; pig->ngrec = 0; return skb; } static int igmpv3_sendpack(struct sk_buff *skb) { struct igmphdr *pig = igmp_hdr(skb); const int igmplen = skb_tail_pointer(skb) - skb_transport_header(skb); pig->csum = ip_compute_csum(igmp_hdr(skb), igmplen); return ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb); } static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, int type, struct igmpv3_grec **ppgr, unsigned int mtu) { struct net_device *dev = pmc->interface->dev; struct igmpv3_report *pih; struct igmpv3_grec *pgr; if (!skb) { skb = igmpv3_newpack(dev, mtu); if (!skb) return NULL; } pgr = skb_put(skb, sizeof(struct igmpv3_grec)); pgr->grec_type = type; pgr->grec_auxwords = 0; pgr->grec_nsrcs = 0; pgr->grec_mca = pmc->multiaddr; pih = igmpv3_report_hdr(skb); pih->ngrec = htons(ntohs(pih->ngrec)+1); *ppgr = pgr; return skb; } #define AVAILABLE(skb) ((skb) ? skb_availroom(skb) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) { struct net_device *dev = pmc->interface->dev; struct net *net = dev_net(dev); struct igmpv3_report *pih; struct igmpv3_grec *pgr = NULL; struct ip_sf_list *psf, *psf_next, *psf_prev, **psf_list; int scount, stotal, first, isquery, truncate; unsigned int mtu; if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); if (mtu < IPV4_MIN_MTU) return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; truncate = type == IGMPV3_MODE_IS_EXCLUDE || type == IGMPV3_CHANGE_TO_EXCLUDE; stotal = scount = 0; psf_list = sdeleted ? &pmc->tomb : &pmc->sources; if (!*psf_list) goto empty_source; pih = skb ? igmpv3_report_hdr(skb) : NULL; /* EX and TO_EX get a fresh packet, if needed */ if (truncate) { if (pih && pih->ngrec && AVAILABLE(skb) < grec_size(pmc, type, gdeleted, sdeleted)) { if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); } } first = 1; psf_prev = NULL; for (psf = *psf_list; psf; psf = psf_next) { __be32 *psrc; psf_next = psf->sf_next; if (!is_in(pmc, psf, type, gdeleted, sdeleted)) { psf_prev = psf; continue; } /* Based on RFC3376 5.1. Should not send source-list change * records when there is a filter mode change. */ if (((gdeleted && pmc->sfmode == MCAST_EXCLUDE) || (!gdeleted && pmc->crcount)) && (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) goto decrease_sf_crcount; /* clear marks on query responses */ if (isquery) psf->sf_gsresp = 0; if (AVAILABLE(skb) < sizeof(__be32) + first*sizeof(struct igmpv3_grec)) { if (truncate && !first) break; /* truncate these */ if (pgr) pgr->grec_nsrcs = htons(scount); if (skb) igmpv3_sendpack(skb); skb = igmpv3_newpack(dev, mtu); first = 1; scount = 0; } if (first) { skb = add_grhead(skb, pmc, type, &pgr, mtu); first = 0; } if (!skb) return NULL; psrc = skb_put(skb, sizeof(__be32)); *psrc = psf->sf_inaddr; scount++; stotal++; if ((type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) && psf->sf_crcount) { decrease_sf_crcount: psf->sf_crcount--; if ((sdeleted || gdeleted) && psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *psf_list = psf->sf_next; kfree(psf); continue; } } psf_prev = psf; } empty_source: if (!stotal) { if (type == IGMPV3_ALLOW_NEW_SOURCES || type == IGMPV3_BLOCK_OLD_SOURCES) return skb; if (pmc->crcount || isquery) { /* make sure we have room for group header */ if (skb && AVAILABLE(skb) < sizeof(struct igmpv3_grec)) { igmpv3_sendpack(skb); skb = NULL; /* add_grhead will get a new one */ } skb = add_grhead(skb, pmc, type, &pgr, mtu); } } if (pgr) pgr->grec_nsrcs = htons(scount); if (isquery) pmc->gsquery = 0; /* clear query state on report */ return skb; } static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) { struct sk_buff *skb = NULL; struct net *net = dev_net(in_dev->dev); int type; if (!pmc) { rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; else type = IGMPV3_MODE_IS_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } if (!skb) return 0; return igmpv3_sendpack(skb); } /* * remove zero-count source records from a source filter list */ static void igmpv3_clear_zeros(struct ip_sf_list **ppsf) { struct ip_sf_list *psf_prev, *psf_next, *psf; psf_prev = NULL; for (psf = *ppsf; psf; psf = psf_next) { psf_next = psf->sf_next; if (psf->sf_crcount == 0) { if (psf_prev) psf_prev->sf_next = psf->sf_next; else *ppsf = psf->sf_next; kfree(psf); } else psf_prev = psf; } } static void kfree_pmc(struct ip_mc_list *pmc) { ip_sf_list_clear_all(pmc->sources); ip_sf_list_clear_all(pmc->tomb); kfree(pmc); } static void igmpv3_send_cr(struct in_device *in_dev) { struct ip_mc_list *pmc, *pmc_prev, *pmc_next; struct sk_buff *skb = NULL; int type, dtype; rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc_next) { pmc_next = pmc->next; if (pmc->sfmode == MCAST_INCLUDE) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; skb = add_grec(skb, pmc, type, 1, 0); skb = add_grec(skb, pmc, dtype, 1, 1); } if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) { type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 1, 0); } pmc->crcount--; if (pmc->crcount == 0) { igmpv3_clear_zeros(&pmc->tomb); igmpv3_clear_zeros(&pmc->sources); } } if (pmc->crcount == 0 && !pmc->tomb && !pmc->sources) { if (pmc_prev) pmc_prev->next = pmc_next; else in_dev->mc_tomb = pmc_next; in_dev_put(pmc->interface); kfree_pmc(pmc); } else pmc_prev = pmc; } spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; dtype = IGMPV3_ALLOW_NEW_SOURCES; } else { type = IGMPV3_ALLOW_NEW_SOURCES; dtype = IGMPV3_BLOCK_OLD_SOURCES; } skb = add_grec(skb, pmc, type, 0, 0); skb = add_grec(skb, pmc, dtype, 0, 1); /* deleted sources */ /* filter mode changes */ if (pmc->crcount) { if (pmc->sfmode == MCAST_EXCLUDE) type = IGMPV3_CHANGE_TO_EXCLUDE; else type = IGMPV3_CHANGE_TO_INCLUDE; skb = add_grec(skb, pmc, type, 0, 0); pmc->crcount--; } spin_unlock_bh(&pmc->lock); } rcu_read_unlock(); if (!skb) return; (void) igmpv3_sendpack(skb); } static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, int type) { struct sk_buff *skb; struct iphdr *iph; struct igmphdr *ih; struct rtable *rt; struct net_device *dev = in_dev->dev; struct net *net = dev_net(dev); __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; rt = ip_route_output_ports(net, &fl4, NULL, dst, 0, 0, 0, IPPROTO_IGMP, 0, dev->ifindex); if (IS_ERR(rt)) return -1; hlen = LL_RESERVED_SPACE(dev); tlen = dev->needed_tailroom; skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (!skb) { ip_rt_put(rt); return -1; } skb->priority = TC_PRIO_CONTROL; skb_dst_set(skb, &rt->dst); skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); skb_put(skb, sizeof(struct iphdr) + 4); iph->version = 4; iph->ihl = (sizeof(struct iphdr)+4)>>2; iph->tos = 0xc0; iph->frag_off = htons(IP_DF); iph->ttl = 1; iph->daddr = dst; iph->saddr = fl4.saddr; iph->protocol = IPPROTO_IGMP; ip_select_ident(net, skb, NULL); ((u8 *)&iph[1])[0] = IPOPT_RA; ((u8 *)&iph[1])[1] = 4; ((u8 *)&iph[1])[2] = 0; ((u8 *)&iph[1])[3] = 0; ih = skb_put(skb, sizeof(struct igmphdr)); ih->type = type; ih->code = 0; ih->csum = 0; ih->group = group; ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(net, skb->sk, skb); } static void igmp_gq_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_gq_timer); in_dev->mr_gq_running = 0; igmpv3_send_report(in_dev, NULL); in_dev_put(in_dev); } static void igmp_ifc_timer_expire(struct timer_list *t) { struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer); igmpv3_send_cr(in_dev); if (in_dev->mr_ifc_count) { in_dev->mr_ifc_count--; igmp_ifc_start_timer(in_dev, unsolicited_report_interval(in_dev)); } in_dev_put(in_dev); } static void igmp_ifc_event(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; in_dev->mr_ifc_count = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_start_timer(in_dev, 1); } static void igmp_timer_expire(struct timer_list *t) { struct ip_mc_list *im = from_timer(im, t, timer); struct in_device *in_dev = im->interface; spin_lock(&im->lock); im->tm_running = 0; if (im->unsolicit_count && --im->unsolicit_count) igmp_start_timer(im, unsolicited_report_interval(in_dev)); im->reporter = 1; spin_unlock(&im->lock); if (IGMP_V1_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); else if (IGMP_V2_SEEN(in_dev)) igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); else igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); ip_ma_put(im); } /* mark EXCLUDE-mode sources */ static int igmp_xmarksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) { /* skip inactive filters */ if (psf->sf_count[MCAST_INCLUDE] || pmc->sfcount[MCAST_EXCLUDE] != psf->sf_count[MCAST_EXCLUDE]) break; if (srcs[i] == psf->sf_inaddr) { scount++; break; } } } pmc->gsquery = 0; if (scount == nsrcs) /* all sources excluded */ return 0; return 1; } static int igmp_marksources(struct ip_mc_list *pmc, int nsrcs, __be32 *srcs) { struct ip_sf_list *psf; int i, scount; if (pmc->sfmode == MCAST_EXCLUDE) return igmp_xmarksources(pmc, nsrcs, srcs); /* mark INCLUDE-mode sources */ scount = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (scount == nsrcs) break; for (i = 0; i < nsrcs; i++) if (srcs[i] == psf->sf_inaddr) { psf->sf_gsresp = 1; scount++; break; } } if (!scount) { pmc->gsquery = 0; return 0; } pmc->gsquery = 1; return 1; } /* return true if packet was dropped */ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) { struct ip_mc_list *im; struct net *net = dev_net(in_dev->dev); /* Timers are only set for non-local groups */ if (group == IGMP_ALL_HOSTS) return false; if (ipv4_is_local_multicast(group) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } rcu_read_unlock(); return false; } /* return true if packet was dropped */ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, int len) { struct igmphdr *ih = igmp_hdr(skb); struct igmpv3_query *ih3 = igmpv3_query_hdr(skb); struct ip_mc_list *im; __be32 group = ih->group; int max_delay; int mark = 0; struct net *net = dev_net(in_dev->dev); if (len == 8) { if (ih->code == 0) { /* Alas, old v1 router presents here. */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_v1_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; group = 0; } else { /* v2 router present */ max_delay = ih->code*(HZ/IGMP_TIMER_SCALE); in_dev->mr_v2_seen = jiffies + (in_dev->mr_qrv * in_dev->mr_qi) + in_dev->mr_qri; } /* cancel the interface change timer */ in_dev->mr_ifc_count = 0; if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); /* clear deleted report items */ igmpv3_clear_delrec(in_dev); } else if (len < 12) { return true; /* ignore bogus packet; freed by caller */ } else if (IGMP_V1_SEEN(in_dev)) { /* This is a v3 query with v1 queriers present */ max_delay = IGMP_QUERY_RESPONSE_INTERVAL; group = 0; } else if (IGMP_V2_SEEN(in_dev)) { /* this is a v3 query with v2 queriers present; * Interpretation of the max_delay code is problematic here. * A real v2 host would use ih_code directly, while v3 has a * different encoding. We use the v3 encoding as more likely * to be intended in a v3 query. */ max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return true; ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) { if (!pskb_may_pull(skb, sizeof(struct igmpv3_query) + ntohs(ih3->nsrcs)*sizeof(__be32))) return true; ih3 = igmpv3_query_hdr(skb); } max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); if (!max_delay) max_delay = 1; /* can't mod w/ 0 */ in_dev->mr_maxdelay = max_delay; /* RFC3376, 4.1.6. QRV and 4.1.7. QQIC, when the most recently * received value was zero, use the default or statically * configured value. */ in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: * The number of seconds represented by the [Query Response * Interval] must be less than the [Query Interval]. */ if (in_dev->mr_qri >= in_dev->mr_qi) in_dev->mr_qri = (in_dev->mr_qi/HZ - 1)*HZ; if (!group) { /* general query */ if (ih3->nsrcs) return true; /* no sources allowed */ igmp_gq_start_timer(in_dev); return false; } /* mark sources to include, if group & source-specific */ mark = ih3->nsrcs != 0; } /* * - Start the timers in all of our membership records * that the query applies to for the interface on * which the query arrived excl. those that belong * to a "local" group (224.0.0.X) * - For timers already running check if they need to * be reset. * - Use the igmp->igmp_code field as the maximum * delay possible */ rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; else im->gsquery = mark; changed = !im->gsquery || igmp_marksources(im, ntohs(ih3->nsrcs), ih3->srcs); spin_unlock_bh(&im->lock); if (changed) igmp_mod_timer(im, max_delay); } rcu_read_unlock(); return false; } /* called in rcu_read_lock() section */ int igmp_rcv(struct sk_buff *skb) { /* This basically follows the spec line by line -- see RFC1112 */ struct igmphdr *ih; struct net_device *dev = skb->dev; struct in_device *in_dev; int len = skb->len; bool dropped = true; if (netif_is_l3_master(dev)) { dev = dev_get_by_index_rcu(dev_net(dev), IPCB(skb)->iif); if (!dev) goto drop; } in_dev = __in_dev_get_rcu(dev); if (!in_dev) goto drop; if (!pskb_may_pull(skb, sizeof(struct igmphdr))) goto drop; if (skb_checksum_simple_validate(skb)) goto drop; ih = igmp_hdr(skb); switch (ih->type) { case IGMP_HOST_MEMBERSHIP_QUERY: dropped = igmp_heard_query(in_dev, skb, len); break; case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: /* Is it our report looped back? */ if (rt_is_output_route(skb_rtable(skb))) break; /* don't rely on MC router hearing unicast reports */ if (skb->pkt_type == PACKET_MULTICAST || skb->pkt_type == PACKET_BROADCAST) dropped = igmp_heard_report(in_dev, ih->group); break; case IGMP_PIM: #ifdef CONFIG_IP_PIMSM_V1 return pim_rcv_v1(skb); #endif case IGMPV3_HOST_MEMBERSHIP_REPORT: case IGMP_DVMRP: case IGMP_TRACE: case IGMP_HOST_LEAVE_MESSAGE: case IGMP_MTRACE: case IGMP_MTRACE_RESP: break; default: break; } drop: if (dropped) kfree_skb(skb); else consume_skb(skb); return 0; } #endif /* * Add a filter to a device */ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; /* Checking for IFF_MULTICAST here is WRONG-WRONG-WRONG. We will get multicast token leakage, when IFF_MULTICAST is changed. This check should be done in ndo_set_rx_mode routine. Something sort of: if (dev->mc_list && dev->flags&IFF_MULTICAST) { do it; } --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_add(dev, buf); } /* * Remove a filter from a device */ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) { char buf[MAX_ADDR_LEN]; struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) dev_mc_del(dev, buf); } #ifdef CONFIG_IP_MULTICAST /* * deleted ip_mc_list manipulation */ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); /* this is an "ip_mc_list" for convenience; only the fields below * are actually used. In particular, the refcnt and users are not * used for management of the delete list. Using the same structure * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); spin_lock_bh(&im->lock); pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; pmc->tomb = im->tomb; pmc->sources = im->sources; im->tomb = im->sources = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = pmc->crcount; } spin_unlock_bh(&im->lock); spin_lock_bh(&in_dev->mc_tomb_lock); pmc->next = in_dev->mc_tomb; in_dev->mc_tomb = pmc; spin_unlock_bh(&in_dev->mc_tomb_lock); } /* * restore ip_mc_list deleted records */ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list *pmc, *pmc_prev; struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); __be32 multiaddr = im->multiaddr; spin_lock_bh(&in_dev->mc_tomb_lock); pmc_prev = NULL; for (pmc = in_dev->mc_tomb; pmc; pmc = pmc->next) { if (pmc->multiaddr == multiaddr) break; pmc_prev = pmc; } if (pmc) { if (pmc_prev) pmc_prev->next = pmc->next; else in_dev->mc_tomb = pmc->next; } spin_unlock_bh(&in_dev->mc_tomb_lock); spin_lock_bh(&im->lock); if (pmc) { im->interface = pmc->interface; if (im->sfmode == MCAST_INCLUDE) { swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); } spin_unlock_bh(&im->lock); } /* * flush ip_mc_list deleted records */ static void igmpv3_clear_delrec(struct in_device *in_dev) { struct ip_mc_list *pmc, *nextpmc; spin_lock_bh(&in_dev->mc_tomb_lock); pmc = in_dev->mc_tomb; in_dev->mc_tomb = NULL; spin_unlock_bh(&in_dev->mc_tomb_lock); for (; pmc; pmc = nextpmc) { nextpmc = pmc->next; ip_mc_clear_src(pmc); in_dev_put(pmc->interface); kfree_pmc(pmc); } /* clear dead sources, too */ rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf; spin_lock_bh(&pmc->lock); psf = pmc->tomb; pmc->tomb = NULL; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(psf); } rcu_read_unlock(); } #endif static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); int reporter; #endif if (im->loaded) { im->loaded = 0; ip_mc_filter_del(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; igmp_stop_timer(im); if (!in_dev->dead) { if (IGMP_V1_SEEN(in_dev)) return; if (IGMP_V2_SEEN(in_dev)) { if (reporter) igmp_send_report(in_dev, im, IGMP_HOST_LEAVE_MESSAGE); return; } /* IGMPv3 */ igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } static void igmp_group_dropped(struct ip_mc_list *im) { __igmp_group_dropped(im, GFP_KERNEL); } static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST struct net *net = dev_net(in_dev->dev); #endif if (im->loaded == 0) { im->loaded = 1; ip_mc_filter_add(in_dev, im->multiaddr); } #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); spin_unlock_bh(&im->lock); return; } /* else, v3 */ /* Based on RFC3376 5.1, for newly added INCLUDE SSM, we should * not send filter-mode change record as the mode should be from * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif } /* * Multicast list managers */ static u32 ip_mc_hash(const struct ip_mc_list *im) { return hash_32((__force u32)im->multiaddr, MC_HASH_SZ_LOG); } static void ip_mc_hash_add(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash; u32 hash; mc_hash = rtnl_dereference(in_dev->mc_hash); if (mc_hash) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; rcu_assign_pointer(mc_hash[hash], im); return; } /* do not use a hash table for small number of items */ if (in_dev->mc_count < 4) return; mc_hash = kzalloc(sizeof(struct ip_mc_list *) << MC_HASH_SZ_LOG, GFP_KERNEL); if (!mc_hash) return; for_each_pmc_rtnl(in_dev, im) { hash = ip_mc_hash(im); im->next_hash = mc_hash[hash]; RCU_INIT_POINTER(mc_hash[hash], im); } rcu_assign_pointer(in_dev->mc_hash, mc_hash); } static void ip_mc_hash_remove(struct in_device *in_dev, struct ip_mc_list *im) { struct ip_mc_list __rcu **mc_hash = rtnl_dereference(in_dev->mc_hash); struct ip_mc_list *aux; if (!mc_hash) return; mc_hash += ip_mc_hash(im); while ((aux = rtnl_dereference(*mc_hash)) != im) mc_hash = &aux->next_hash; *mc_hash = im->next_hash; } /* * A socket has joined a multicast group on device dev. */ static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, unsigned int mode, gfp_t gfp) { struct ip_mc_list *im; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, mode, 0, NULL, 0); goto out; } } im = kzalloc(sizeof(*im), gfp); if (!im) goto out; im->users = 1; im->interface = in_dev; in_dev_hold(in_dev); im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = mode; im->sfcount[mode] = 1; refcount_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST timer_setup(&im->timer, igmp_timer_expire, 0); #endif im->next_rcu = in_dev->mc_list; in_dev->mc_count++; rcu_assign_pointer(in_dev->mc_list, im); ip_mc_hash_add(in_dev, im); #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im); #endif igmp_group_added(im); if (!in_dev->dead) ip_rt_multicast_event(in_dev); out: return; } void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); } EXPORT_SYMBOL(__ip_mc_inc_group); void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, GFP_KERNEL); } EXPORT_SYMBOL(ip_mc_inc_group); static int ip_mc_check_iphdr(struct sk_buff *skb) { const struct iphdr *iph; unsigned int len; unsigned int offset = skb_network_offset(skb) + sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (iph->version != 4 || ip_hdrlen(skb) < sizeof(*iph)) return -EINVAL; offset += ip_hdrlen(skb) - sizeof(*iph); if (!pskb_may_pull(skb, offset)) return -EINVAL; iph = ip_hdr(skb); if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) return -EINVAL; len = skb_network_offset(skb) + ntohs(iph->tot_len); if (skb->len < len || len < offset) return -EINVAL; skb_set_transport_header(skb, offset); return 0; } static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb); len += sizeof(struct igmpv3_report); return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { unsigned int transport_len = ip_transport_len(skb); unsigned int len; /* IGMPv{1,2}? */ if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ if (transport_len < sizeof(struct igmpv3_query)) return -EINVAL; len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); if (!ip_mc_may_pull(skb, len)) return -EINVAL; } /* RFC2236+RFC3376 (IGMPv2+IGMPv3) require the multicast link layer * all-systems destination addresses (224.0.0.1) for general queries */ if (!igmp_hdr(skb)->group && ip_hdr(skb)->daddr != htonl(INADDR_ALLHOSTS_GROUP)) return -EINVAL; return 0; } static int ip_mc_check_igmp_msg(struct sk_buff *skb) { switch (igmp_hdr(skb)->type) { case IGMP_HOST_LEAVE_MESSAGE: case IGMP_HOST_MEMBERSHIP_REPORT: case IGMPV2_HOST_MEMBERSHIP_REPORT: return 0; case IGMPV3_HOST_MEMBERSHIP_REPORT: return ip_mc_check_igmp_reportv3(skb); case IGMP_HOST_MEMBERSHIP_QUERY: return ip_mc_check_igmp_query(skb); default: return -ENOMSG; } } static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb) { return skb_checksum_simple_validate(skb); } static int ip_mc_check_igmp_csum(struct sk_buff *skb) { unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); unsigned int transport_len = ip_transport_len(skb); struct sk_buff *skb_chk; if (!ip_mc_may_pull(skb, len)) return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) return -EINVAL; if (skb_chk != skb) kfree_skb(skb_chk); return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. * * -EINVAL: A broken packet was detected, i.e. it violates some internet * standard * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); if (ret < 0) return ret; if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; ret = ip_mc_check_igmp_csum(skb); if (ret < 0) return ret; return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); /* * Resend IGMP JOIN report; used by netdev notifier. */ static void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST struct ip_mc_list *im; int type; struct net *net = dev_net(in_dev->dev); ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches * must be notified immediately */ if (IGMP_V1_SEEN(in_dev)) type = IGMP_HOST_MEMBERSHIP_REPORT; else if (IGMP_V2_SEEN(in_dev)) type = IGMPV2_HOST_MEMBERSHIP_REPORT; else type = IGMPV3_HOST_MEMBERSHIP_REPORT; igmp_send_report(in_dev, im, type); } #endif } /* * A socket has left a multicast group on device dev */ void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; ASSERT_RTNL(); for (ip = &in_dev->mc_list; (i = rtnl_dereference(*ip)) != NULL; ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) ip_rt_multicast_event(in_dev); ip_ma_put(i); return; } break; } } } EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ void ip_mc_unmap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); for_each_pmc_rtnl(in_dev, pmc) igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST in_dev->mr_ifc_count = 0; if (del_timer(&in_dev->mr_ifc_timer)) __in_dev_put(in_dev); in_dev->mr_gq_running = 0; if (del_timer(&in_dev->mr_gq_timer)) __in_dev_put(in_dev); #endif ip_mc_dec_group(in_dev, IGMP_ALL_HOSTS); } #ifdef CONFIG_IP_MULTICAST static void ip_mc_reset(struct in_device *in_dev) { struct net *net = dev_net(in_dev->dev); in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) { } #endif void ip_mc_init_dev(struct in_device *in_dev) { ASSERT_RTNL(); #ifdef CONFIG_IP_MULTICAST timer_setup(&in_dev->mr_gq_timer, igmp_gq_timer_expire, 0); timer_setup(&in_dev->mr_ifc_timer, igmp_ifc_timer_expire, 0); #endif ip_mc_reset(in_dev); spin_lock_init(&in_dev->mc_tomb_lock); } /* Device going up */ void ip_mc_up(struct in_device *in_dev) { struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_reset(in_dev); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); for_each_pmc_rtnl(in_dev, pmc) { #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, pmc); #endif igmp_group_added(pmc); } } /* * Device is about to be destroyed: clean up. */ void ip_mc_destroy_dev(struct in_device *in_dev) { struct ip_mc_list *i; ASSERT_RTNL(); /* Deactivate timers */ ip_mc_down(in_dev); #ifdef CONFIG_IP_MULTICAST igmpv3_clear_delrec(in_dev); #endif while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { in_dev->mc_list = i->next_rcu; in_dev->mc_count--; ip_mc_clear_src(i); ip_ma_put(i); } } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct net_device *dev = NULL; struct in_device *idev = NULL; if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); return idev; } if (imr->imr_address.s_addr) { dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; } if (!dev) { struct rtable *rt = ip_route_output(net, imr->imr_multiaddr.s_addr, 0, 0, 0); if (!IS_ERR(rt)) { dev = rt->dst.dev; ip_rt_put(rt); } } if (dev) { imr->imr_ifindex = dev->ifindex; idev = __in_dev_get_rtnl(dev); } return idev; } /* * Join a socket to a group */ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; int rv = 0; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf || psf->sf_count[sfmode] == 0) { /* source filter not found, or count wrong => bug */ return -ESRCH; } psf->sf_count[sfmode]--; if (psf->sf_count[sfmode] == 0) { ip_rt_multicast_event(pmc->interface); } if (!psf->sf_count[MCAST_INCLUDE] && !psf->sf_count[MCAST_EXCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct in_device *in_dev = pmc->interface; struct net *net = dev_net(in_dev->dev); #endif /* no more filters for this source */ if (psf_prev) psf_prev->sf_next = psf->sf_next; else pmc->sources = psf->sf_next; #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; } else #endif kfree(psf); } return rv; } #ifndef CONFIG_IP_MULTICAST #define igmp_ifc_event(x) do { } while (0) #endif static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int changerec = 0; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif if (!delta) { err = -EINVAL; if (!pmc->sfcount[sfmode]) goto out_unlock; pmc->sfcount[sfmode]--; } err = 0; for (i = 0; i < sfcount; i++) { int rv = ip_mc_del1_src(pmc, sfmode, &psfsrc[i]); changerec |= rv > 0; if (!err && rv < 0) err = rv; } if (pmc->sfmode == MCAST_EXCLUDE && pmc->sfcount[MCAST_EXCLUDE] == 0 && pmc->sfcount[MCAST_INCLUDE]) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(in_dev->dev); #endif /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(pmc->interface); } else if (sf_setstate(pmc) || changerec) { igmp_ifc_event(pmc->interface); #endif } out_unlock: spin_unlock_bh(&pmc->lock); return err; } /* * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; psf_prev = NULL; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == *psfsrc) break; psf_prev = psf; } if (!psf) { psf = kzalloc(sizeof(*psf), GFP_ATOMIC); if (!psf) return -ENOBUFS; psf->sf_inaddr = *psfsrc; if (psf_prev) { psf_prev->sf_next = psf; } else pmc->sources = psf; } psf->sf_count[sfmode]++; if (psf->sf_count[sfmode] == 1) { ip_rt_multicast_event(pmc->interface); } return 0; } #ifdef CONFIG_IP_MULTICAST static void sf_markstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; for (psf = pmc->sources; psf; psf = psf->sf_next) if (pmc->sfcount[MCAST_EXCLUDE]) { psf->sf_oldin = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else psf->sf_oldin = psf->sf_count[MCAST_INCLUDE] != 0; } static int sf_setstate(struct ip_mc_list *pmc) { struct ip_sf_list *psf, *dpsf; int mca_xcount = pmc->sfcount[MCAST_EXCLUDE]; int qrv = pmc->interface->mr_qrv; int new_in, rv; rv = 0; for (psf = pmc->sources; psf; psf = psf->sf_next) { if (pmc->sfcount[MCAST_EXCLUDE]) { new_in = mca_xcount == psf->sf_count[MCAST_EXCLUDE] && !psf->sf_count[MCAST_INCLUDE]; } else new_in = psf->sf_count[MCAST_INCLUDE] != 0; if (new_in) { if (!psf->sf_oldin) { struct ip_sf_list *prev = NULL; for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) { if (dpsf->sf_inaddr == psf->sf_inaddr) break; prev = dpsf; } if (dpsf) { if (prev) prev->sf_next = dpsf->sf_next; else pmc->tomb = dpsf->sf_next; kfree(dpsf); } psf->sf_crcount = qrv; rv++; } } else if (psf->sf_oldin) { psf->sf_crcount = 0; /* * add or update "delete" records if an active filter * is now inactive */ for (dpsf = pmc->tomb; dpsf; dpsf = dpsf->sf_next) if (dpsf->sf_inaddr == psf->sf_inaddr) break; if (!dpsf) { dpsf = kmalloc(sizeof(*dpsf), GFP_ATOMIC); if (!dpsf) continue; *dpsf = *psf; /* pmc->lock held by callers */ dpsf->sf_next = pmc->tomb; pmc->tomb = dpsf; } dpsf->sf_crcount = qrv; rv++; } } return rv; } #endif /* * Add multicast source filter list to the interface list */ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta) { struct ip_mc_list *pmc; int isexclude; int i, err; if (!in_dev) return -ENODEV; rcu_read_lock(); for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif isexclude = pmc->sfmode == MCAST_EXCLUDE; if (!delta) pmc->sfcount[sfmode]++; err = 0; for (i = 0; i < sfcount; i++) { err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; if (!delta) pmc->sfcount[sfmode]--; for (j = 0; j < i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { #ifdef CONFIG_IP_MULTICAST struct ip_sf_list *psf; struct net *net = dev_net(pmc->interface->dev); in_dev = pmc->interface; #endif /* filter mode change */ if (pmc->sfcount[MCAST_EXCLUDE]) pmc->sfmode = MCAST_EXCLUDE; else if (pmc->sfcount[MCAST_INCLUDE]) pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_ifc_count = pmc->crcount; for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; igmp_ifc_event(in_dev); } else if (sf_setstate(pmc)) { igmp_ifc_event(in_dev); #endif } spin_unlock_bh(&pmc->lock); return err; } static void ip_mc_clear_src(struct ip_mc_list *pmc) { struct ip_sf_list *tomb, *sources; spin_lock_bh(&pmc->lock); tomb = pmc->tomb; pmc->tomb = NULL; sources = pmc->sources; pmc->sources = NULL; pmc->sfmode = MCAST_EXCLUDE; pmc->sfcount[MCAST_INCLUDE] = 0; pmc->sfcount[MCAST_EXCLUDE] = 1; spin_unlock_bh(&pmc->lock); ip_sf_list_clear_all(tomb); ip_sf_list_clear_all(sources); } /* Join a multicast group */ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { __be32 addr = imr->imr_multiaddr.s_addr; struct ip_mc_socklist *iml, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); int ifindex; int count = 0; int err; ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; in_dev = ip_mc_find_dev(net, imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRINUSE; ifindex = imr->imr_ifindex; for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; count++; } err = -ENOBUFS; if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = mode; rcu_assign_pointer(inet->mc_list, iml); ____ip_mc_inc_group(in_dev, addr, mode, GFP_KERNEL); err = 0; done: return err; } /* Join ASM (Any-Source Multicast) group */ int ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr) { return __ip_mc_join_group(sk, imr, MCAST_EXCLUDE); } EXPORT_SYMBOL(ip_mc_join_group); /* Join SSM (Source-Specific Multicast) group */ int ip_mc_join_group_ssm(struct sock *sk, struct ip_mreqn *imr, unsigned int mode) { return __ip_mc_join_group(sk, imr, mode); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (!psf) { /* any-source empty exclude case */ return ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, 0, NULL, 0); } err = ip_mc_del_src(in_dev, &iml->multi.imr_multiaddr.s_addr, iml->sfmode, psf->sl_count, psf->sl_addr, 0); RCU_INIT_POINTER(iml->sflist, NULL); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psf->sl_max), &sk->sk_omem_alloc); kfree_rcu(psf, rcu); return err; } int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; u32 ifindex; int ret = -EADDRNOTAVAIL; ASSERT_RTNL(); in_dev = ip_mc_find_dev(net, imr); if (!imr->imr_ifindex && !imr->imr_address.s_addr && !in_dev) { ret = -ENODEV; goto out; } ifindex = imr->imr_ifindex; for (imlp = &inet->mc_list; (iml = rtnl_dereference(*imlp)) != NULL; imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { if (iml->multi.imr_ifindex != ifindex) continue; } else if (imr->imr_address.s_addr && imr->imr_address.s_addr != iml->multi.imr_address.s_addr) continue; (void) ip_mc_leave_src(sk, iml, in_dev); *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); return 0; } out: return ret; } EXPORT_SYMBOL(ip_mc_leave_group); int ip_mc_source(int add, int omode, struct sock *sk, struct ip_mreq_source *mreqs, int ifindex) { int err; struct ip_mreqn imr; __be32 addr = mreqs->imr_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev = NULL; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); int leavegroup = 0; int i, j, rv; if (!ipv4_is_multicast(addr)) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = mreqs->imr_multiaddr; imr.imr_address.s_addr = mreqs->imr_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } /* if a source filter was set, must be the same mode as before */ if (pmc->sflist) { if (pmc->sfmode != omode) { err = -EINVAL; goto done; } } else if (pmc->sfmode != omode) { /* allow mode switches for empty-set filters */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 0, NULL, 0); ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, pmc->sfmode, 0, NULL, 0); pmc->sfmode = omode; } psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ rv = !0; for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv) /* source not found */ goto done; /* err = -EADDRNOTAVAIL */ /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (psl->sl_count == 1 && omode == MCAST_INCLUDE) { leavegroup = 1; goto done; } /* update the interface filter */ ip_mc_del_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); for (j = i+1; j < psl->sl_count; j++) psl->sl_addr[j-1] = psl->sl_addr[j]; psl->sl_count--; err = 0; goto done; } /* else, add a new source to the filter */ if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) { err = -ENOBUFS; goto done; } if (!psl || psl->sl_count == psl->sl_max) { struct ip_sf_socklist *newpsl; int count = IP_SFBLOCK; if (psl) count += psl->sl_max; newpsl = sock_kmalloc(sk, IP_SFLSIZE(count), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = count; newpsl->sl_count = count - IP_SFBLOCK; if (psl) { for (i = 0; i < psl->sl_count; i++) newpsl->sl_addr[i] = psl->sl_addr[i]; /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); psl = newpsl; } rv = 1; /* > 0 for insert logic below if sl_count is 0 */ for (i = 0; i < psl->sl_count; i++) { rv = memcmp(&psl->sl_addr[i], &mreqs->imr_sourceaddr, sizeof(__be32)); if (rv == 0) break; } if (rv == 0) /* address already there is an error */ goto done; for (j = psl->sl_count-1; j >= i; j--) psl->sl_addr[j+1] = psl->sl_addr[j]; psl->sl_addr[i] = mreqs->imr_sourceaddr; psl->sl_count++; err = 0; /* update the interface list */ ip_mc_add_src(in_dev, &mreqs->imr_multiaddr, omode, 1, &mreqs->imr_sourceaddr, 1); done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) { int err = 0; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *newpsl, *psl; struct net *net = sock_net(sk); int leavegroup = 0; if (!ipv4_is_multicast(addr)) return -EINVAL; if (msf->imsf_fmode != MCAST_INCLUDE && msf->imsf_fmode != MCAST_EXCLUDE) return -EINVAL; ASSERT_RTNL(); imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = ifindex; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } /* special case - (INCLUDE, empty) == LEAVE_GROUP */ if (msf->imsf_fmode == MCAST_INCLUDE && msf->imsf_numsrc == 0) { leavegroup = 1; goto done; } for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) { /* must have a prior join */ err = -EINVAL; goto done; } if (msf->imsf_numsrc) { newpsl = sock_kmalloc(sk, IP_SFLSIZE(msf->imsf_numsrc), GFP_KERNEL); if (!newpsl) { err = -ENOBUFS; goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; memcpy(newpsl->sl_addr, msf->imsf_slist, msf->imsf_numsrc * sizeof(msf->imsf_slist[0])); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { sock_kfree_s(sk, newpsl, IP_SFLSIZE(newpsl->sl_max)); goto done; } } else { newpsl = NULL; (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); /* decrease mem now to avoid the memleak warning */ atomic_sub(IP_SFLSIZE(psl->sl_max), &sk->sk_omem_alloc); } else { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, 0, NULL, 0); } rcu_assign_pointer(pmc->sflist, newpsl); if (psl) kfree_rcu(psl, rcu); pmc->sfmode = msf->imsf_fmode; err = 0; done: if (leavegroup) err = ip_mc_leave_group(sk, &imr); return err; } int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, struct ip_msfilter __user *optval, int __user *optlen) { int err, len, count, copycount; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; struct net *net = sock_net(sk); ASSERT_RTNL(); if (!ipv4_is_multicast(addr)) return -EINVAL; imr.imr_multiaddr.s_addr = msf->imsf_multiaddr; imr.imr_address.s_addr = msf->imsf_interface; imr.imr_ifindex = 0; in_dev = ip_mc_find_dev(net, &imr); if (!in_dev) { err = -ENODEV; goto done; } err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; } if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); if (!psl) { len = 0; count = 0; } else { count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; len = copycount * sizeof(psl->sl_addr[0]); msf->imsf_numsrc = count; if (put_user(IP_MSFILTER_SIZE(copycount), optlen) || copy_to_user(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && copy_to_user(&optval->imsf_slist[0], psl->sl_addr, len)) return -EFAULT; return 0; done: return err; } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, struct group_filter __user *optval, int __user *optlen) { int err, i, count, copycount; struct sockaddr_in *psin; __be32 addr; struct ip_mc_socklist *pmc; struct inet_sock *inet = inet_sk(sk); struct ip_sf_socklist *psl; ASSERT_RTNL(); psin = (struct sockaddr_in *)&gsf->gf_group; if (psin->sin_family != AF_INET) return -EINVAL; addr = psin->sin_addr.s_addr; if (!ipv4_is_multicast(addr)) return -EINVAL; err = -EADDRNOTAVAIL; for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; } if (!pmc) /* must have a prior join */ goto done; gsf->gf_fmode = pmc->sfmode; psl = rtnl_dereference(pmc->sflist); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; if (put_user(GROUP_FILTER_SIZE(copycount), optlen) || copy_to_user(optval, gsf, GROUP_FILTER_SIZE(0))) { return -EFAULT; } for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; if (copy_to_user(&optval->gf_slist[i], &ss, sizeof(ss))) return -EFAULT; } return 0; done: return err; } /* * check if a multicast source filter allows delivery for a given <src,dst,intf> */ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif, int sdif) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *pmc; struct ip_sf_socklist *psl; int i; int ret; ret = 1; if (!ipv4_is_multicast(loc_addr)) goto out; rcu_read_lock(); for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && (pmc->multi.imr_ifindex == dif || (sdif && pmc->multi.imr_ifindex == sdif))) break; } ret = inet->mc_all; if (!pmc) goto unlock; psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; for (i = 0; i < psl->sl_count; i++) { if (psl->sl_addr[i] == rmt_addr) break; } ret = 0; if (pmc->sfmode == MCAST_INCLUDE && i >= psl->sl_count) goto unlock; if (pmc->sfmode == MCAST_EXCLUDE && i < psl->sl_count) goto unlock; ret = 1; unlock: rcu_read_unlock(); out: return ret; } /* * A socket is closing. */ void ip_mc_drop_socket(struct sock *sk) { struct inet_sock *inet = inet_sk(sk); struct ip_mc_socklist *iml; struct net *net = sock_net(sk); if (!inet->mc_list) return; rtnl_lock(); while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); if (in_dev) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); kfree_rcu(iml, rcu); } rtnl_unlock(); } /* called with rcu_read_lock() */ int ip_check_mc_rcu(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u8 proto) { struct ip_mc_list *im; struct ip_mc_list __rcu **mc_hash; struct ip_sf_list *psf; int rv = 0; mc_hash = rcu_dereference(in_dev->mc_hash); if (mc_hash) { u32 hash = hash_32((__force u32)mc_addr, MC_HASH_SZ_LOG); for (im = rcu_dereference(mc_hash[hash]); im != NULL; im = rcu_dereference(im->next_hash)) { if (im->multiaddr == mc_addr) break; } } else { for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } } if (im && proto == IPPROTO_IGMP) { rv = 1; } else if (im) { if (src_addr) { spin_lock_bh(&im->lock); for (psf = im->sources; psf; psf = psf->sf_next) { if (psf->sf_inaddr == src_addr) break; } if (psf) rv = psf->sf_count[MCAST_INCLUDE] || psf->sf_count[MCAST_EXCLUDE] != im->sfcount[MCAST_EXCLUDE]; else rv = im->sfcount[MCAST_EXCLUDE] != 0; spin_unlock_bh(&im->lock); } else rv = 1; /* unspecified source; tentatively allow */ } return rv; } #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; #define igmp_mc_seq_private(seq) ((struct igmp_mc_iter_state *)(seq)->private) static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *in_dev; in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } } return im; } static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); im = rcu_dereference(im->next_rcu); while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; break; } state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; im = rcu_dereference(state->in_dev->mc_list); } return im; } static struct ip_mc_list *igmp_mc_get_idx(struct seq_file *seq, loff_t pos) { struct ip_mc_list *im = igmp_mc_get_first(seq); if (im) while (pos && (im = igmp_mc_get_next(seq, im)) != NULL) --pos; return pos ? NULL : im; } static void *igmp_mc_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mc_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_mc_list *im; if (v == SEQ_START_TOKEN) im = igmp_mc_get_first(seq); else im = igmp_mc_get_next(seq, v); ++*pos; return im; } static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mc_seq_show(struct seq_file *seq, void *v) { if (v == SEQ_START_TOKEN) seq_puts(seq, "Idx\tDevice : Count Querier\tGroup Users Timer\tReporter\n"); else { struct ip_mc_list *im = (struct ip_mc_list *)v; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); char *querier; long delta; #ifdef CONFIG_IP_MULTICAST querier = IGMP_V1_SEEN(state->in_dev) ? "V1" : IGMP_V2_SEEN(state->in_dev) ? "V2" : "V3"; #else querier = "NONE"; #endif if (rcu_access_pointer(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } delta = im->timer.expires - jiffies; seq_printf(seq, "\t\t\t\t%08X %5d %d:%08lX\t\t%d\n", im->multiaddr, im->users, im->tm_running, im->tm_running ? jiffies_delta_to_clock_t(delta) : 0, im->reporter); } return 0; } static const struct seq_operations igmp_mc_seq_ops = { .start = igmp_mc_seq_start, .next = igmp_mc_seq_next, .stop = igmp_mc_seq_stop, .show = igmp_mc_seq_show, }; struct igmp_mcf_iter_state { struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; }; #define igmp_mcf_seq_private(seq) ((struct igmp_mcf_iter_state *)(seq)->private) static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; for_each_netdev_rcu(net, state->dev) { struct in_device *idev; idev = __in_dev_get_rcu(state->dev); if (unlikely(!idev)) continue; im = rcu_dereference(idev->mc_list); if (likely(im)) { spin_lock_bh(&im->lock); psf = im->sources; if (likely(psf)) { state->im = im; state->idev = idev; break; } spin_unlock_bh(&im->lock); } } return psf; } static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_list *psf) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); psf = psf->sf_next; while (!psf) { spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; state->im = rcu_dereference(state->idev->mc_list); } if (!state->im) break; spin_lock_bh(&state->im->lock); psf = state->im->sources; } out: return psf; } static struct ip_sf_list *igmp_mcf_get_idx(struct seq_file *seq, loff_t pos) { struct ip_sf_list *psf = igmp_mcf_get_first(seq); if (psf) while (pos && (psf = igmp_mcf_get_next(seq, psf)) != NULL) --pos; return pos ? NULL : psf; } static void *igmp_mcf_seq_start(struct seq_file *seq, loff_t *pos) __acquires(rcu) { rcu_read_lock(); return *pos ? igmp_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } static void *igmp_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct ip_sf_list *psf; if (v == SEQ_START_TOKEN) psf = igmp_mcf_get_first(seq); else psf = igmp_mcf_get_next(seq, v); ++*pos; return psf; } static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (likely(state->im)) { spin_unlock_bh(&state->im->lock); state->im = NULL; } state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } static int igmp_mcf_seq_show(struct seq_file *seq, void *v) { struct ip_sf_list *psf = (struct ip_sf_list *)v; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); if (v == SEQ_START_TOKEN) { seq_puts(seq, "Idx Device MCA SRC INC EXC\n"); } else { seq_printf(seq, "%3d %6.6s 0x%08x " "0x%08x %6lu %6lu\n", state->dev->ifindex, state->dev->name, ntohl(state->im->multiaddr), ntohl(psf->sf_inaddr), psf->sf_count[MCAST_INCLUDE], psf->sf_count[MCAST_EXCLUDE]); } return 0; } static const struct seq_operations igmp_mcf_seq_ops = { .start = igmp_mcf_seq_start, .next = igmp_mcf_seq_next, .stop = igmp_mcf_seq_stop, .show = igmp_mcf_seq_show, }; static int __net_init igmp_net_init(struct net *net) { struct proc_dir_entry *pde; int err; pde = proc_create_net("igmp", 0444, net->proc_net, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); if (!pde) goto out_igmp; pde = proc_create_net("mcfilter", 0444, net->proc_net, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); if (!pde) goto out_mcfilter; err = inet_ctl_sock_create(&net->ipv4.mc_autojoin_sk, AF_INET, SOCK_DGRAM, 0, net); if (err < 0) { pr_err("Failed to initialize the IGMP autojoin socket (err %d)\n", err); goto out_sock; } return 0; out_sock: remove_proc_entry("mcfilter", net->proc_net); out_mcfilter: remove_proc_entry("igmp", net->proc_net); out_igmp: return -ENOMEM; } static void __net_exit igmp_net_exit(struct net *net) { remove_proc_entry("mcfilter", net->proc_net); remove_proc_entry("igmp", net->proc_net); inet_ctl_sock_destroy(net->ipv4.mc_autojoin_sk); } static struct pernet_operations igmp_net_ops = { .init = igmp_net_init, .exit = igmp_net_exit, }; #endif static int igmp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct in_device *in_dev; switch (event) { case NETDEV_RESEND_IGMP: in_dev = __in_dev_get_rtnl(dev); if (in_dev) ip_mc_rejoin_groups(in_dev); break; default: break; } return NOTIFY_DONE; } static struct notifier_block igmp_notifier = { .notifier_call = igmp_netdev_event, }; int __init igmp_mc_init(void) { #if defined(CONFIG_PROC_FS) int err; err = register_pernet_subsys(&igmp_net_ops); if (err) return err; err = register_netdevice_notifier(&igmp_notifier); if (err) goto reg_notif_fail; return 0; reg_notif_fail: unregister_pernet_subsys(&igmp_net_ops); return err; #else return register_netdevice_notifier(&igmp_notifier); #endif } |
| 24 36 15 552 553 193 189 89 95 62 120 303 165 101 84 84 84 84 84 84 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 | // SPDX-License-Identifier: GPL-2.0-only /* * IPv6 library code, needed by static components when full IPv6 support is * not configured or static. */ #include <linux/export.h> #include <net/ipv6.h> #include <net/ipv6_stubs.h> #include <net/addrconf.h> #include <net/ip.h> /* if ipv6 module registers this function is used by xfrm to force all * sockets to relookup their nodes - this is fairly expensive, be * careful */ void (*__fib6_flush_trees)(struct net *); EXPORT_SYMBOL(__fib6_flush_trees); #define IPV6_ADDR_SCOPE_TYPE(scope) ((scope) << 16) static inline unsigned int ipv6_addr_scope2type(unsigned int scope) { switch (scope) { case IPV6_ADDR_SCOPE_NODELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_NODELOCAL) | IPV6_ADDR_LOOPBACK); case IPV6_ADDR_SCOPE_LINKLOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL) | IPV6_ADDR_LINKLOCAL); case IPV6_ADDR_SCOPE_SITELOCAL: return (IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL) | IPV6_ADDR_SITELOCAL); } return IPV6_ADDR_SCOPE_TYPE(scope); } int __ipv6_addr_type(const struct in6_addr *addr) { __be32 st; st = addr->s6_addr32[0]; /* Consider all addresses with the first three bits different of 000 and 111 as unicasts. */ if ((st & htonl(0xE0000000)) != htonl(0x00000000) && (st & htonl(0xE0000000)) != htonl(0xE0000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); if ((st & htonl(0xFF000000)) == htonl(0xFF000000)) { /* multicast */ /* addr-select 3.1 */ return (IPV6_ADDR_MULTICAST | ipv6_addr_scope2type(IPV6_ADDR_MC_SCOPE(addr))); } if ((st & htonl(0xFFC00000)) == htonl(0xFE800000)) return (IPV6_ADDR_LINKLOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFFC00000)) == htonl(0xFEC00000)) return (IPV6_ADDR_SITELOCAL | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_SITELOCAL)); /* addr-select 3.1 */ if ((st & htonl(0xFE000000)) == htonl(0xFC000000)) return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* RFC 4193 */ if ((addr->s6_addr32[0] | addr->s6_addr32[1]) == 0) { if (addr->s6_addr32[2] == 0) { if (addr->s6_addr32[3] == 0) return IPV6_ADDR_ANY; if (addr->s6_addr32[3] == htonl(0x00000001)) return (IPV6_ADDR_LOOPBACK | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_LINKLOCAL)); /* addr-select 3.4 */ return (IPV6_ADDR_COMPATv4 | IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } if (addr->s6_addr32[2] == htonl(0x0000ffff)) return (IPV6_ADDR_MAPPED | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.3 */ } return (IPV6_ADDR_UNICAST | IPV6_ADDR_SCOPE_TYPE(IPV6_ADDR_SCOPE_GLOBAL)); /* addr-select 3.4 */ } EXPORT_SYMBOL(__ipv6_addr_type); static ATOMIC_NOTIFIER_HEAD(inet6addr_chain); static BLOCKING_NOTIFIER_HEAD(inet6addr_validator_chain); int register_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_register(&inet6addr_chain, nb); } EXPORT_SYMBOL(register_inet6addr_notifier); int unregister_inet6addr_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&inet6addr_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_notifier); int inet6addr_notifier_call_chain(unsigned long val, void *v) { return atomic_notifier_call_chain(&inet6addr_chain, val, v); } EXPORT_SYMBOL(inet6addr_notifier_call_chain); int register_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_register(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(register_inet6addr_validator_notifier); int unregister_inet6addr_validator_notifier(struct notifier_block *nb) { return blocking_notifier_chain_unregister(&inet6addr_validator_chain, nb); } EXPORT_SYMBOL(unregister_inet6addr_validator_notifier); int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) { return blocking_notifier_call_chain(&inet6addr_validator_chain, val, v); } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) { return -EAFNOSUPPORT; } static struct fib6_table *eafnosupport_fib6_get_table(struct net *net, u32 id) { return NULL; } static int eafnosupport_fib6_table_lookup(struct net *net, struct fib6_table *table, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return -EAFNOSUPPORT; } static int eafnosupport_fib6_lookup(struct net *net, int oif, struct flowi6 *fl6, struct fib6_result *res, int flags) { return -EAFNOSUPPORT; } static void eafnosupport_fib6_select_path(const struct net *net, struct fib6_result *res, struct flowi6 *fl6, int oif, bool have_oif_match, const struct sk_buff *skb, int strict) { } static u32 eafnosupport_ip6_mtu_from_fib6(const struct fib6_result *res, const struct in6_addr *daddr, const struct in6_addr *saddr) { return 0; } static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { NL_SET_ERR_MSG(extack, "IPv6 support not enabled in kernel"); return -EAFNOSUPPORT; } static int eafnosupport_ip6_del_rt(struct net *net, struct fib6_info *rt) { return -EAFNOSUPPORT; } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, .fib6_lookup = eafnosupport_fib6_lookup, .fib6_select_path = eafnosupport_fib6_select_path, .ip6_mtu_from_fib6 = eafnosupport_ip6_mtu_from_fib6, .fib6_nh_init = eafnosupport_fib6_nh_init, .ip6_del_rt = eafnosupport_ip6_del_rt, }; EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) { kfree(idev->stats.icmpv6msgdev); kfree(idev->stats.icmpv6dev); free_percpu(idev->stats.ipv6); } static void in6_dev_finish_destroy_rcu(struct rcu_head *head) { struct inet6_dev *idev = container_of(head, struct inet6_dev, rcu); snmp6_free_dev(idev); kfree(idev); } /* Nobody refers to this device, we may destroy it. */ void in6_dev_finish_destroy(struct inet6_dev *idev) { struct net_device *dev = idev->dev; WARN_ON(!list_empty(&idev->addr_list)); WARN_ON(idev->mc_list); WARN_ON(timer_pending(&idev->rs_timer)); #ifdef NET_REFCNT_DEBUG pr_debug("%s: %s\n", __func__, dev ? dev->name : "NIL"); #endif dev_put(dev); if (!idev->dead) { pr_warn("Freeing alive inet6 device %p\n", idev); return; } call_rcu(&idev->rcu, in6_dev_finish_destroy_rcu); } EXPORT_SYMBOL(in6_dev_finish_destroy); |
| 175 122 3 150 123 3 122 123 122 49 49 14 665 443 14 11 51 411 202 17 11 374 9 1 1 122 122 152 165 260 90 86 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 | // SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com * Copyright (c) 2016 Facebook */ #include <linux/bpf.h> #include "disasm.h" #define __BPF_FUNC_STR_FN(x) [BPF_FUNC_ ## x] = __stringify(bpf_ ## x) static const char * const func_id_str[] = { __BPF_FUNC_MAPPER(__BPF_FUNC_STR_FN) }; #undef __BPF_FUNC_STR_FN static const char *__func_get_name(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, char *buff, size_t len) { BUILD_BUG_ON(ARRAY_SIZE(func_id_str) != __BPF_FUNC_MAX_ID); if (insn->src_reg != BPF_PSEUDO_CALL && insn->imm >= 0 && insn->imm < __BPF_FUNC_MAX_ID && func_id_str[insn->imm]) return func_id_str[insn->imm]; if (cbs && cbs->cb_call) return cbs->cb_call(cbs->private_data, insn); if (insn->src_reg == BPF_PSEUDO_CALL) snprintf(buff, len, "%+d", insn->imm); return buff; } static const char *__func_imm_name(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, u64 full_imm, char *buff, size_t len) { if (cbs && cbs->cb_imm) return cbs->cb_imm(cbs->private_data, insn, full_imm); snprintf(buff, len, "0x%llx", (unsigned long long)full_imm); return buff; } const char *func_id_name(int id) { if (id >= 0 && id < __BPF_FUNC_MAX_ID && func_id_str[id]) return func_id_str[id]; else return "unknown"; } const char *const bpf_class_string[8] = { [BPF_LD] = "ld", [BPF_LDX] = "ldx", [BPF_ST] = "st", [BPF_STX] = "stx", [BPF_ALU] = "alu", [BPF_JMP] = "jmp", [BPF_JMP32] = "jmp32", [BPF_ALU64] = "alu64", }; const char *const bpf_alu_string[16] = { [BPF_ADD >> 4] = "+=", [BPF_SUB >> 4] = "-=", [BPF_MUL >> 4] = "*=", [BPF_DIV >> 4] = "/=", [BPF_OR >> 4] = "|=", [BPF_AND >> 4] = "&=", [BPF_LSH >> 4] = "<<=", [BPF_RSH >> 4] = ">>=", [BPF_NEG >> 4] = "neg", [BPF_MOD >> 4] = "%=", [BPF_XOR >> 4] = "^=", [BPF_MOV >> 4] = "=", [BPF_ARSH >> 4] = "s>>=", [BPF_END >> 4] = "endian", }; static const char *const bpf_ldst_string[] = { [BPF_W >> 3] = "u32", [BPF_H >> 3] = "u16", [BPF_B >> 3] = "u8", [BPF_DW >> 3] = "u64", }; static const char *const bpf_jmp_string[16] = { [BPF_JA >> 4] = "jmp", [BPF_JEQ >> 4] = "==", [BPF_JGT >> 4] = ">", [BPF_JLT >> 4] = "<", [BPF_JGE >> 4] = ">=", [BPF_JLE >> 4] = "<=", [BPF_JSET >> 4] = "&", [BPF_JNE >> 4] = "!=", [BPF_JSGT >> 4] = "s>", [BPF_JSLT >> 4] = "s<", [BPF_JSGE >> 4] = "s>=", [BPF_JSLE >> 4] = "s<=", [BPF_CALL >> 4] = "call", [BPF_EXIT >> 4] = "exit", }; static void print_bpf_end_insn(bpf_insn_print_t verbose, void *private_data, const struct bpf_insn *insn) { verbose(private_data, "(%02x) r%d = %s%d r%d\n", insn->code, insn->dst_reg, BPF_SRC(insn->code) == BPF_TO_BE ? "be" : "le", insn->imm, insn->dst_reg); } void print_bpf_insn(const struct bpf_insn_cbs *cbs, const struct bpf_insn *insn, bool allow_ptr_leaks) { const bpf_insn_print_t verbose = cbs->cb_print; u8 class = BPF_CLASS(insn->code); if (class == BPF_ALU || class == BPF_ALU64) { if (BPF_OP(insn->code) == BPF_END) { if (class == BPF_ALU64) verbose(cbs->private_data, "BUG_alu64_%02x\n", insn->code); else print_bpf_end_insn(verbose, cbs->private_data, insn); } else if (BPF_OP(insn->code) == BPF_NEG) { verbose(cbs->private_data, "(%02x) %c%d = -%c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, class == BPF_ALU ? 'w' : 'r', insn->dst_reg); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) %c%d %s %c%d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], class == BPF_ALU ? 'w' : 'r', insn->src_reg); } else { verbose(cbs->private_data, "(%02x) %c%d %s %d\n", insn->code, class == BPF_ALU ? 'w' : 'r', insn->dst_reg, bpf_alu_string[BPF_OP(insn->code) >> 4], insn->imm); } } else if (class == BPF_STX) { if (BPF_MODE(insn->code) == BPF_MEM) verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); else if (BPF_MODE(insn->code) == BPF_XADD) verbose(cbs->private_data, "(%02x) lock *(%s *)(r%d %+d) += r%d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->src_reg); else verbose(cbs->private_data, "BUG_%02x\n", insn->code); } else if (class == BPF_ST) { if (BPF_MODE(insn->code) == BPF_MEM) { verbose(cbs->private_data, "(%02x) *(%s *)(r%d %+d) = %d\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->dst_reg, insn->off, insn->imm); } else if (BPF_MODE(insn->code) == 0xc0 /* BPF_NOSPEC, no UAPI */) { verbose(cbs->private_data, "(%02x) nospec\n", insn->code); } else { verbose(cbs->private_data, "BUG_st_%02x\n", insn->code); } } else if (class == BPF_LDX) { if (BPF_MODE(insn->code) != BPF_MEM) { verbose(cbs->private_data, "BUG_ldx_%02x\n", insn->code); return; } verbose(cbs->private_data, "(%02x) r%d = *(%s *)(r%d %+d)\n", insn->code, insn->dst_reg, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->off); } else if (class == BPF_LD) { if (BPF_MODE(insn->code) == BPF_ABS) { verbose(cbs->private_data, "(%02x) r0 = *(%s *)skb[%d]\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->imm); } else if (BPF_MODE(insn->code) == BPF_IND) { verbose(cbs->private_data, "(%02x) r0 = *(%s *)skb[r%d + %d]\n", insn->code, bpf_ldst_string[BPF_SIZE(insn->code) >> 3], insn->src_reg, insn->imm); } else if (BPF_MODE(insn->code) == BPF_IMM && BPF_SIZE(insn->code) == BPF_DW) { /* At this point, we already made sure that the second * part of the ldimm64 insn is accessible. */ u64 imm = ((u64)(insn + 1)->imm << 32) | (u32)insn->imm; bool is_ptr = insn->src_reg == BPF_PSEUDO_MAP_FD || insn->src_reg == BPF_PSEUDO_MAP_VALUE; char tmp[64]; if (is_ptr && !allow_ptr_leaks) imm = 0; verbose(cbs->private_data, "(%02x) r%d = %s\n", insn->code, insn->dst_reg, __func_imm_name(cbs, insn, imm, tmp, sizeof(tmp))); } else { verbose(cbs->private_data, "BUG_ld_%02x\n", insn->code); return; } } else if (class == BPF_JMP32 || class == BPF_JMP) { u8 opcode = BPF_OP(insn->code); if (opcode == BPF_CALL) { char tmp[64]; if (insn->src_reg == BPF_PSEUDO_CALL) { verbose(cbs->private_data, "(%02x) call pc%s\n", insn->code, __func_get_name(cbs, insn, tmp, sizeof(tmp))); } else { strcpy(tmp, "unknown"); verbose(cbs->private_data, "(%02x) call %s#%d\n", insn->code, __func_get_name(cbs, insn, tmp, sizeof(tmp)), insn->imm); } } else if (insn->code == (BPF_JMP | BPF_JA)) { verbose(cbs->private_data, "(%02x) goto pc%+d\n", insn->code, insn->off); } else if (insn->code == (BPF_JMP | BPF_EXIT)) { verbose(cbs->private_data, "(%02x) exit\n", insn->code); } else if (BPF_SRC(insn->code) == BPF_X) { verbose(cbs->private_data, "(%02x) if %c%d %s %c%d goto pc%+d\n", insn->code, class == BPF_JMP32 ? 'w' : 'r', insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], class == BPF_JMP32 ? 'w' : 'r', insn->src_reg, insn->off); } else { verbose(cbs->private_data, "(%02x) if %c%d %s 0x%x goto pc%+d\n", insn->code, class == BPF_JMP32 ? 'w' : 'r', insn->dst_reg, bpf_jmp_string[BPF_OP(insn->code) >> 4], insn->imm, insn->off); } } else { verbose(cbs->private_data, "(%02x) %s\n", insn->code, bpf_class_string[class]); } } |
| 2514 73 564 2359 472 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_COMPILER_H #define __LINUX_COMPILER_H #include <linux/compiler_types.h> #ifndef __ASSEMBLY__ #ifdef __KERNEL__ /* * Note: DISABLE_BRANCH_PROFILING can be used by special lowlevel code * to disable branch tracing on a per file basis. */ #if defined(CONFIG_TRACE_BRANCH_PROFILING) \ && !defined(DISABLE_BRANCH_PROFILING) && !defined(__CHECKER__) void ftrace_likely_update(struct ftrace_likely_data *f, int val, int expect, int is_constant); #define likely_notrace(x) __builtin_expect(!!(x), 1) #define unlikely_notrace(x) __builtin_expect(!!(x), 0) #define __branch_check__(x, expect, is_constant) ({ \ long ______r; \ static struct ftrace_likely_data \ __aligned(4) \ __section(_ftrace_annotated_branch) \ ______f = { \ .data.func = __func__, \ .data.file = __FILE__, \ .data.line = __LINE__, \ }; \ ______r = __builtin_expect(!!(x), expect); \ ftrace_likely_update(&______f, ______r, \ expect, is_constant); \ ______r; \ }) /* * Using __builtin_constant_p(x) to ignore cases where the return * value is always the same. This idea is taken from a similar patch * written by Daniel Walker. */ # ifndef likely # define likely(x) (__branch_check__(x, 1, __builtin_constant_p(x))) # endif # ifndef unlikely # define unlikely(x) (__branch_check__(x, 0, __builtin_constant_p(x))) # endif #ifdef CONFIG_PROFILE_ALL_BRANCHES /* * "Define 'is'", Bill Clinton * "Define 'if'", Steven Rostedt */ #define if(cond, ...) if ( __trace_if_var( !!(cond , ## __VA_ARGS__) ) ) #define __trace_if_var(cond) (__builtin_constant_p(cond) ? (cond) : __trace_if_value(cond)) #define __trace_if_value(cond) ({ \ static struct ftrace_branch_data \ __aligned(4) \ __section(_ftrace_branch) \ __if_trace = { \ .func = __func__, \ .file = __FILE__, \ .line = __LINE__, \ }; \ (cond) ? \ (__if_trace.miss_hit[1]++,1) : \ (__if_trace.miss_hit[0]++,0); \ }) #endif /* CONFIG_PROFILE_ALL_BRANCHES */ #else # define likely(x) __builtin_expect(!!(x), 1) # define unlikely(x) __builtin_expect(!!(x), 0) #endif /* Optimization barrier */ #ifndef barrier /* The "volatile" is due to gcc bugs */ # define barrier() __asm__ __volatile__("": : :"memory") #endif #ifndef barrier_data /* * This version is i.e. to prevent dead stores elimination on @ptr * where gcc and llvm may behave differently when otherwise using * normal barrier(): while gcc behavior gets along with a normal * barrier(), llvm needs an explicit input variable to be assumed * clobbered. The issue is as follows: while the inline asm might * access any memory it wants, the compiler could have fit all of * @ptr into memory registers instead, and since @ptr never escaped * from that, it proved that the inline asm wasn't touching any of * it. This version works well with both compilers, i.e. we're telling * the compiler that the inline asm absolutely may see the contents * of @ptr. See also: https://llvm.org/bugs/show_bug.cgi?id=15495 */ # define barrier_data(ptr) __asm__ __volatile__("": :"r"(ptr) :"memory") #endif /* workaround for GCC PR82365 if needed */ #ifndef barrier_before_unreachable # define barrier_before_unreachable() do { } while (0) #endif /* Unreachable code */ #ifdef CONFIG_STACK_VALIDATION /* * These macros help objtool understand GCC code flow for unreachable code. * The __COUNTER__ based labels are a hack to make each instance of the macros * unique, to convince GCC not to merge duplicate inline asm statements. */ #define annotate_reachable() ({ \ asm volatile("%c0:\n\t" \ ".pushsection .discard.reachable\n\t" \ ".long %c0b - .\n\t" \ ".popsection\n\t" : : "i" (__COUNTER__)); \ }) #define annotate_unreachable() ({ \ asm volatile("%c0:\n\t" \ ".pushsection .discard.unreachable\n\t" \ ".long %c0b - .\n\t" \ ".popsection\n\t" : : "i" (__COUNTER__)); \ }) #define ASM_UNREACHABLE \ "999:\n\t" \ ".pushsection .discard.unreachable\n\t" \ ".long 999b - .\n\t" \ ".popsection\n\t" /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(.rodata..c_jump_table) #ifdef CONFIG_DEBUG_ENTRY /* Begin/end of an instrumentation safe region */ #define instrumentation_begin() ({ \ asm volatile("%c0:\n\t" \ ".pushsection .discard.instr_begin\n\t" \ ".long %c0b - .\n\t" \ ".popsection\n\t" : : "i" (__COUNTER__)); \ }) /* * Because instrumentation_{begin,end}() can nest, objtool validation considers * _begin() a +1 and _end() a -1 and computes a sum over the instructions. * When the value is greater than 0, we consider instrumentation allowed. * * There is a problem with code like: * * noinstr void foo() * { * instrumentation_begin(); * ... * if (cond) { * instrumentation_begin(); * ... * instrumentation_end(); * } * bar(); * instrumentation_end(); * } * * If instrumentation_end() would be an empty label, like all the other * annotations, the inner _end(), which is at the end of a conditional block, * would land on the instruction after the block. * * If we then consider the sum of the !cond path, we'll see that the call to * bar() is with a 0-value, even though, we meant it to happen with a positive * value. * * To avoid this, have _end() be a NOP instruction, this ensures it will be * part of the condition block and does not escape. */ #define instrumentation_end() ({ \ asm volatile("%c0: nop\n\t" \ ".pushsection .discard.instr_end\n\t" \ ".long %c0b - .\n\t" \ ".popsection\n\t" : : "i" (__COUNTER__)); \ }) #endif /* CONFIG_DEBUG_ENTRY */ #else #define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif #ifndef instrumentation_begin #define instrumentation_begin() do { } while(0) #define instrumentation_end() do { } while(0) #endif #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif #ifndef unreachable # define unreachable() do { \ annotate_unreachable(); \ __builtin_unreachable(); \ } while (0) #endif /* * KENTRY - kernel entry point * This can be used to annotate symbols (functions or data) that are used * without their linker symbol being referenced explicitly. For example, * interrupt vector handlers, or functions in the kernel image that are found * programatically. * * Not required for symbols exported with EXPORT_SYMBOL, or initcalls. Those * are handled in their own way (with KEEP() in linker scripts). * * KENTRY can be avoided if the symbols in question are marked as KEEP() in the * linker script. For example an architecture could KEEP() its entire * boot/exception vector code rather than annotate each function and data. */ #ifndef KENTRY # define KENTRY(sym) \ extern typeof(sym) sym; \ static const unsigned long __kentry_##sym \ __used \ __section("___kentry" "+" #sym ) \ = (unsigned long)&sym; #endif #ifndef RELOC_HIDE # define RELOC_HIDE(ptr, off) \ ({ unsigned long __ptr; \ __ptr = (unsigned long) (ptr); \ (typeof(ptr)) (__ptr + (off)); }) #endif #define absolute_pointer(val) RELOC_HIDE((void *)(val), 0) #ifndef OPTIMIZER_HIDE_VAR /* Make the optimizer believe the variable can be manipulated arbitrarily. */ #define OPTIMIZER_HIDE_VAR(var) \ __asm__ ("" : "=r" (var) : "0" (var)) #endif /* Not-quite-unique ID. */ #ifndef __UNIQUE_ID # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) #endif #include <uapi/linux/types.h> #define __READ_ONCE_SIZE \ ({ \ switch (size) { \ case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ default: \ barrier(); \ __builtin_memcpy((void *)res, (const void *)p, size); \ barrier(); \ } \ }) static __always_inline void __read_once_size(const volatile void *p, void *res, int size) { __READ_ONCE_SIZE; } #ifdef CONFIG_KASAN /* * We can't declare function 'inline' because __no_sanitize_address confilcts * with inlining. Attempt to inline it may cause a build failure. * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ # define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused #else # define __no_kasan_or_inline __always_inline #endif static __no_kasan_or_inline void __read_once_size_nocheck(const volatile void *p, void *res, int size) { __READ_ONCE_SIZE; } static __always_inline void __write_once_size(volatile void *p, void *res, int size) { switch (size) { case 1: *(volatile __u8 *)p = *(__u8 *)res; break; case 2: *(volatile __u16 *)p = *(__u16 *)res; break; case 4: *(volatile __u32 *)p = *(__u32 *)res; break; case 8: *(volatile __u64 *)p = *(__u64 *)res; break; default: barrier(); __builtin_memcpy((void *)p, (const void *)res, size); barrier(); } } /* * Prevent the compiler from merging or refetching reads or writes. The * compiler is also forbidden from reordering successive instances of * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some * particular ordering. One way to make the compiler aware of ordering is to * put the two invocations of READ_ONCE or WRITE_ONCE in different C * statements. * * These two macros will also work on aggregate data types like structs or * unions. If the size of the accessed data type exceeds the word size of * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will * fall back to memcpy(). There's at least two memcpy()s: one for the * __builtin_memcpy() and then one for the macro doing the copy of variable * - '__u' allocated on the stack. * * Their two major use cases are: (1) Mediating communication between * process-level code and irq/NMI handlers, all running on the same CPU, * and (2) Ensuring that the compiler does not fold, spindle, or otherwise * mutilate accesses that either do not require ordering or that interact * with an explicit memory barrier or atomic instruction that provides the * required ordering. */ #include <asm/barrier.h> #include <linux/kasan-checks.h> #define __READ_ONCE(x, check) \ ({ \ union { typeof(x) __val; char __c[1]; } __u; \ if (check) \ __read_once_size(&(x), __u.__c, sizeof(x)); \ else \ __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ __u.__val; \ }) #define READ_ONCE(x) __READ_ONCE(x, 1) /* * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need * to hide memory access from KASAN. */ #define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) { kasan_check_read(addr, 1); return *(unsigned long *)addr; } #define WRITE_ONCE(x, val) \ ({ \ union { typeof(x) __val; char __c[1]; } __u = \ { .__val = (__force typeof(x)) (val) }; \ __write_once_size(&(x), __u.__c, sizeof(x)); \ __u.__val; \ }) #endif /* __KERNEL__ */ /* * Force the compiler to emit 'sym' as a symbol, so that we can reference * it from inline assembler. Necessary in case 'sym' could be inlined * otherwise, or eliminated entirely due to lack of references that are * visible to the compiler. */ #define __ADDRESSABLE(sym) \ static void * __section(.discard.addressable) __used \ __PASTE(__addressable_##sym, __LINE__) = (void *)&sym; /** * offset_to_ptr - convert a relative memory offset to an absolute pointer * @off: the address of the 32-bit offset value */ static inline void *offset_to_ptr(const int *off) { return (void *)((unsigned long)off + *off); } #endif /* __ASSEMBLY__ */ /* Compile time object size, -1 for unknown */ #ifndef __compiletime_object_size # define __compiletime_object_size(obj) -1 #endif #ifndef __compiletime_warning # define __compiletime_warning(message) #endif #ifndef __compiletime_error # define __compiletime_error(message) #endif #ifdef __OPTIMIZE__ # define __compiletime_assert(condition, msg, prefix, suffix) \ do { \ extern void prefix ## suffix(void) __compiletime_error(msg); \ if (!(condition)) \ prefix ## suffix(); \ } while (0) #else # define __compiletime_assert(condition, msg, prefix, suffix) do { } while (0) #endif #define _compiletime_assert(condition, msg, prefix, suffix) \ __compiletime_assert(condition, msg, prefix, suffix) /** * compiletime_assert - break build and emit msg if condition is false * @condition: a compile-time constant condition to check * @msg: a message to emit if condition is false * * In tradition of POSIX assert, this macro will break the build if the * supplied condition is *false*, emitting the supplied error message if the * compiler has support to do so. */ #define compiletime_assert(condition, msg) \ _compiletime_assert(condition, msg, __compiletime_assert_, __COUNTER__) #define compiletime_assert_atomic_type(t) \ compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) /* * This is needed in functions which generate the stack canary, see * arch/x86/kernel/smpboot.c::start_secondary() for an example. */ #define prevent_tail_call_optimization() mb() #endif /* __LINUX_COMPILER_H */ |
| 6 6 6 11 3 7 5 19 4 15 5 12 12 8 5 3 22 2 7 15 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 | // SPDX-License-Identifier: GPL-2.0-only /* * Minimal file system backend for holding eBPF maps and programs, * used by bpf(2) object pinning. * * Authors: * * Daniel Borkmann <daniel@iogearbox.net> */ #include <linux/init.h> #include <linux/magic.h> #include <linux/major.h> #include <linux/mount.h> #include <linux/namei.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/kdev_t.h> #include <linux/filter.h> #include <linux/bpf.h> #include <linux/bpf_trace.h> enum bpf_type { BPF_TYPE_UNSPEC = 0, BPF_TYPE_PROG, BPF_TYPE_MAP, }; static void *bpf_any_get(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: raw = bpf_prog_inc(raw); break; case BPF_TYPE_MAP: raw = bpf_map_inc(raw, true); break; default: WARN_ON_ONCE(1); break; } return raw; } static void bpf_any_put(void *raw, enum bpf_type type) { switch (type) { case BPF_TYPE_PROG: bpf_prog_put(raw); break; case BPF_TYPE_MAP: bpf_map_put_with_uref(raw); break; default: WARN_ON_ONCE(1); break; } } static void *bpf_fd_probe_obj(u32 ufd, enum bpf_type *type) { void *raw; *type = BPF_TYPE_MAP; raw = bpf_map_get_with_uref(ufd); if (IS_ERR(raw)) { *type = BPF_TYPE_PROG; raw = bpf_prog_get(ufd); } return raw; } static const struct inode_operations bpf_dir_iops; static const struct inode_operations bpf_prog_iops = { }; static const struct inode_operations bpf_map_iops = { }; static struct inode *bpf_get_inode(struct super_block *sb, const struct inode *dir, umode_t mode) { struct inode *inode; switch (mode & S_IFMT) { case S_IFDIR: case S_IFREG: case S_IFLNK: break; default: return ERR_PTR(-EINVAL); } inode = new_inode(sb); if (!inode) return ERR_PTR(-ENOSPC); inode->i_ino = get_next_ino(); inode->i_atime = current_time(inode); inode->i_mtime = inode->i_atime; inode->i_ctime = inode->i_atime; inode_init_owner(inode, dir, mode); return inode; } static int bpf_inode_type(const struct inode *inode, enum bpf_type *type) { *type = BPF_TYPE_UNSPEC; if (inode->i_op == &bpf_prog_iops) *type = BPF_TYPE_PROG; else if (inode->i_op == &bpf_map_iops) *type = BPF_TYPE_MAP; else return -EACCES; return 0; } static void bpf_dentry_finalize(struct dentry *dentry, struct inode *inode, struct inode *dir) { d_instantiate(dentry, inode); dget(dentry); dir->i_mtime = current_time(dir); dir->i_ctime = dir->i_mtime; } static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) { struct inode *inode; inode = bpf_get_inode(dir->i_sb, dir, mode | S_IFDIR); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = &bpf_dir_iops; inode->i_fop = &simple_dir_operations; inc_nlink(inode); inc_nlink(dir); bpf_dentry_finalize(dentry, inode, dir); return 0; } struct map_iter { void *key; bool done; }; static struct map_iter *map_iter(struct seq_file *m) { return m->private; } static struct bpf_map *seq_file_to_map(struct seq_file *m) { return file_inode(m->file)->i_private; } static void map_iter_free(struct map_iter *iter) { if (iter) { kfree(iter->key); kfree(iter); } } static struct map_iter *map_iter_alloc(struct bpf_map *map) { struct map_iter *iter; iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN); if (!iter) goto error; iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN); if (!iter->key) goto error; return iter; error: map_iter_free(iter); return NULL; } static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) { struct bpf_map *map = seq_file_to_map(m); void *key = map_iter(m)->key; void *prev_key; (*pos)++; if (map_iter(m)->done) return NULL; if (unlikely(v == SEQ_START_TOKEN)) prev_key = NULL; else prev_key = key; rcu_read_lock(); if (map->ops->map_get_next_key(map, prev_key, key)) { map_iter(m)->done = true; key = NULL; } rcu_read_unlock(); return key; } static void *map_seq_start(struct seq_file *m, loff_t *pos) { if (map_iter(m)->done) return NULL; return *pos ? map_iter(m)->key : SEQ_START_TOKEN; } static void map_seq_stop(struct seq_file *m, void *v) { } static int map_seq_show(struct seq_file *m, void *v) { struct bpf_map *map = seq_file_to_map(m); void *key = map_iter(m)->key; if (unlikely(v == SEQ_START_TOKEN)) { seq_puts(m, "# WARNING!! The output is for debug purpose only\n"); seq_puts(m, "# WARNING!! The output format will change\n"); } else { map->ops->map_seq_show_elem(map, key, m); } return 0; } static const struct seq_operations bpffs_map_seq_ops = { .start = map_seq_start, .next = map_seq_next, .show = map_seq_show, .stop = map_seq_stop, }; static int bpffs_map_open(struct inode *inode, struct file *file) { struct bpf_map *map = inode->i_private; struct map_iter *iter; struct seq_file *m; int err; iter = map_iter_alloc(map); if (!iter) return -ENOMEM; err = seq_open(file, &bpffs_map_seq_ops); if (err) { map_iter_free(iter); return err; } m = file->private_data; m->private = iter; return 0; } static int bpffs_map_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; map_iter_free(map_iter(m)); return seq_release(inode, file); } /* bpffs_map_fops should only implement the basic * read operation for a BPF map. The purpose is to * provide a simple user intuitive way to do * "cat bpffs/pathto/a-pinned-map". * * Other operations (e.g. write, lookup...) should be realized by * the userspace tools (e.g. bpftool) through the * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update * interface. */ static const struct file_operations bpffs_map_fops = { .open = bpffs_map_open, .read = seq_read, .release = bpffs_map_release, }; static int bpffs_obj_open(struct inode *inode, struct file *file) { return -EIO; } static const struct file_operations bpffs_obj_fops = { .open = bpffs_obj_open, }; static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, const struct inode_operations *iops, const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); if (IS_ERR(inode)) return PTR_ERR(inode); inode->i_op = iops; inode->i_fop = fops; inode->i_private = raw; bpf_dentry_finalize(dentry, inode, dir); return 0; } static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) { return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, &bpffs_obj_fops); } static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) { struct bpf_map *map = arg; return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, bpf_map_support_seq_show(map) ? &bpffs_map_fops : &bpffs_obj_fops); } static struct dentry * bpf_lookup(struct inode *dir, struct dentry *dentry, unsigned flags) { /* Dots in names (e.g. "/sys/fs/bpf/foo.bar") are reserved for future * extensions. */ if (strchr(dentry->d_name.name, '.')) return ERR_PTR(-EPERM); return simple_lookup(dir, dentry, flags); } static int bpf_symlink(struct inode *dir, struct dentry *dentry, const char *target) { char *link = kstrdup(target, GFP_USER | __GFP_NOWARN); struct inode *inode; if (!link) return -ENOMEM; inode = bpf_get_inode(dir->i_sb, dir, S_IRWXUGO | S_IFLNK); if (IS_ERR(inode)) { kfree(link); return PTR_ERR(inode); } inode->i_op = &simple_symlink_inode_operations; inode->i_link = link; bpf_dentry_finalize(dentry, inode, dir); return 0; } static const struct inode_operations bpf_dir_iops = { .lookup = bpf_lookup, .mkdir = bpf_mkdir, .symlink = bpf_symlink, .rmdir = simple_rmdir, .rename = simple_rename, .link = simple_link, .unlink = simple_unlink, }; static int bpf_obj_do_pin(const struct filename *pathname, void *raw, enum bpf_type type) { struct dentry *dentry; struct inode *dir; struct path path; umode_t mode; int ret; dentry = kern_path_create(AT_FDCWD, pathname->name, &path, 0); if (IS_ERR(dentry)) return PTR_ERR(dentry); mode = S_IFREG | ((S_IRUSR | S_IWUSR) & ~current_umask()); ret = security_path_mknod(&path, dentry, mode, 0); if (ret) goto out; dir = d_inode(path.dentry); if (dir->i_op != &bpf_dir_iops) { ret = -EPERM; goto out; } switch (type) { case BPF_TYPE_PROG: ret = vfs_mkobj(dentry, mode, bpf_mkprog, raw); break; case BPF_TYPE_MAP: ret = vfs_mkobj(dentry, mode, bpf_mkmap, raw); break; default: ret = -EPERM; } out: done_path_create(&path, dentry); return ret; } int bpf_obj_pin_user(u32 ufd, const char __user *pathname) { struct filename *pname; enum bpf_type type; void *raw; int ret; pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); raw = bpf_fd_probe_obj(ufd, &type); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; } ret = bpf_obj_do_pin(pname, raw, type); if (ret != 0) bpf_any_put(raw, type); out: putname(pname); return ret; } static void *bpf_obj_do_get(const struct filename *pathname, enum bpf_type *type, int flags) { struct inode *inode; struct path path; void *raw; int ret; ret = kern_path(pathname->name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); inode = d_backing_inode(path.dentry); ret = inode_permission(inode, ACC_MODE(flags)); if (ret) goto out; ret = bpf_inode_type(inode, type); if (ret) goto out; raw = bpf_any_get(inode->i_private, *type); if (!IS_ERR(raw)) touch_atime(&path); path_put(&path); return raw; out: path_put(&path); return ERR_PTR(ret); } int bpf_obj_get_user(const char __user *pathname, int flags) { enum bpf_type type = BPF_TYPE_UNSPEC; struct filename *pname; int ret = -ENOENT; int f_flags; void *raw; f_flags = bpf_get_file_flag(flags); if (f_flags < 0) return f_flags; pname = getname(pathname); if (IS_ERR(pname)) return PTR_ERR(pname); raw = bpf_obj_do_get(pname, &type, f_flags); if (IS_ERR(raw)) { ret = PTR_ERR(raw); goto out; } if (type == BPF_TYPE_PROG) ret = bpf_prog_new_fd(raw); else if (type == BPF_TYPE_MAP) ret = bpf_map_new_fd(raw, f_flags); else goto out; if (ret < 0) bpf_any_put(raw, type); out: putname(pname); return ret; } static struct bpf_prog *__get_prog_inode(struct inode *inode, enum bpf_prog_type type) { struct bpf_prog *prog; int ret = inode_permission(inode, MAY_READ); if (ret) return ERR_PTR(ret); if (inode->i_op == &bpf_map_iops) return ERR_PTR(-EINVAL); if (inode->i_op != &bpf_prog_iops) return ERR_PTR(-EACCES); prog = inode->i_private; ret = security_bpf_prog(prog); if (ret < 0) return ERR_PTR(ret); if (!bpf_prog_get_ok(prog, &type, false)) return ERR_PTR(-EINVAL); return bpf_prog_inc(prog); } struct bpf_prog *bpf_prog_get_type_path(const char *name, enum bpf_prog_type type) { struct bpf_prog *prog; struct path path; int ret = kern_path(name, LOOKUP_FOLLOW, &path); if (ret) return ERR_PTR(ret); prog = __get_prog_inode(d_backing_inode(path.dentry), type); if (!IS_ERR(prog)) touch_atime(&path); path_put(&path); return prog; } EXPORT_SYMBOL(bpf_prog_get_type_path); /* * Display the mount options in /proc/mounts. */ static int bpf_show_options(struct seq_file *m, struct dentry *root) { umode_t mode = d_inode(root)->i_mode & S_IALLUGO & ~S_ISVTX; if (mode != S_IRWXUGO) seq_printf(m, ",mode=%o", mode); return 0; } static void bpf_free_inode(struct inode *inode) { enum bpf_type type; if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); if (!bpf_inode_type(inode, &type)) bpf_any_put(inode->i_private, type); free_inode_nonrcu(inode); } static const struct super_operations bpf_super_ops = { .statfs = simple_statfs, .drop_inode = generic_delete_inode, .show_options = bpf_show_options, .free_inode = bpf_free_inode, }; enum { OPT_MODE, }; static const struct fs_parameter_spec bpf_param_specs[] = { fsparam_u32oct ("mode", OPT_MODE), {} }; static const struct fs_parameter_description bpf_fs_parameters = { .name = "bpf", .specs = bpf_param_specs, }; struct bpf_mount_opts { umode_t mode; }; static int bpf_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct bpf_mount_opts *opts = fc->fs_private; struct fs_parse_result result; int opt; opt = fs_parse(fc, &bpf_fs_parameters, param, &result); if (opt < 0) /* We might like to report bad mount options here, but * traditionally we've ignored all mount options, so we'd * better continue to ignore non-existing options for bpf. */ return opt == -ENOPARAM ? 0 : opt; switch (opt) { case OPT_MODE: opts->mode = result.uint_32 & S_IALLUGO; break; } return 0; } static int bpf_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr bpf_rfiles[] = { { "" } }; struct bpf_mount_opts *opts = fc->fs_private; struct inode *inode; int ret; ret = simple_fill_super(sb, BPF_FS_MAGIC, bpf_rfiles); if (ret) return ret; sb->s_op = &bpf_super_ops; inode = sb->s_root->d_inode; inode->i_op = &bpf_dir_iops; inode->i_mode &= ~S_IALLUGO; inode->i_mode |= S_ISVTX | opts->mode; return 0; } static int bpf_get_tree(struct fs_context *fc) { return get_tree_nodev(fc, bpf_fill_super); } static void bpf_free_fc(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations bpf_context_ops = { .free = bpf_free_fc, .parse_param = bpf_parse_param, .get_tree = bpf_get_tree, }; /* * Set up the filesystem mount context. */ static int bpf_init_fs_context(struct fs_context *fc) { struct bpf_mount_opts *opts; opts = kzalloc(sizeof(struct bpf_mount_opts), GFP_KERNEL); if (!opts) return -ENOMEM; opts->mode = S_IRWXUGO; fc->fs_private = opts; fc->ops = &bpf_context_ops; return 0; } static struct file_system_type bpf_fs_type = { .owner = THIS_MODULE, .name = "bpf", .init_fs_context = bpf_init_fs_context, .parameters = &bpf_fs_parameters, .kill_sb = kill_litter_super, }; static int __init bpf_init(void) { int ret; ret = sysfs_create_mount_point(fs_kobj, "bpf"); if (ret) return ret; ret = register_filesystem(&bpf_fs_type); if (ret) sysfs_remove_mount_point(fs_kobj, "bpf"); return ret; } fs_initcall(bpf_init); |
| 12 14 12 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _IPV6_FRAG_H #define _IPV6_FRAG_H #include <linux/kernel.h> #include <net/addrconf.h> #include <net/ipv6.h> #include <net/inet_frag.h> enum ip6_defrag_users { IP6_DEFRAG_LOCAL_DELIVER, IP6_DEFRAG_CONNTRACK_IN, __IP6_DEFRAG_CONNTRACK_IN = IP6_DEFRAG_CONNTRACK_IN + USHRT_MAX, IP6_DEFRAG_CONNTRACK_OUT, __IP6_DEFRAG_CONNTRACK_OUT = IP6_DEFRAG_CONNTRACK_OUT + USHRT_MAX, IP6_DEFRAG_CONNTRACK_BRIDGE_IN, __IP6_DEFRAG_CONNTRACK_BRIDGE_IN = IP6_DEFRAG_CONNTRACK_BRIDGE_IN + USHRT_MAX, }; /* * Equivalent of ipv4 struct ip */ struct frag_queue { struct inet_frag_queue q; int iif; __u16 nhoffset; u8 ecn; }; #if IS_ENABLED(CONFIG_IPV6) static inline void ip6frag_init(struct inet_frag_queue *q, const void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); const struct frag_v6_compare_key *key = a; q->key.v6 = *key; fq->ecn = 0; } static inline u32 ip6frag_key_hashfn(const void *data, u32 len, u32 seed) { return jhash2(data, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline u32 ip6frag_obj_hashfn(const void *data, u32 len, u32 seed) { const struct inet_frag_queue *fq = data; return jhash2((const u32 *)&fq->key.v6, sizeof(struct frag_v6_compare_key) / sizeof(u32), seed); } static inline int ip6frag_obj_cmpfn(struct rhashtable_compare_arg *arg, const void *ptr) { const struct frag_v6_compare_key *key = arg->key; const struct inet_frag_queue *fq = ptr; return !!memcmp(&fq->key, key, sizeof(*key)); } static inline void ip6frag_expire_frag_queue(struct net *net, struct frag_queue *fq) { struct net_device *dev = NULL; struct sk_buff *head; rcu_read_lock(); /* Paired with the WRITE_ONCE() in fqdir_pre_exit(). */ if (READ_ONCE(fq->q.fqdir->dead)) goto out_rcu_unlock; spin_lock(&fq->q.lock); if (fq->q.flags & INET_FRAG_COMPLETE) goto out; inet_frag_kill(&fq->q); dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) goto out; __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); /* Don't send error if the first segment did not arrive. */ if (!(fq->q.flags & INET_FRAG_FIRST_IN)) goto out; /* sk_buff::dev and sk_buff::rbnode are unionized. So we * pull the head out of the tree in order to be able to * deal with head->dev. */ head = inet_frag_pull_head(&fq->q); if (!head) goto out; head->dev = dev; spin_unlock(&fq->q.lock); icmpv6_send(head, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0); kfree_skb(head); goto out_rcu_unlock; out: spin_unlock(&fq->q.lock); out_rcu_unlock: rcu_read_unlock(); inet_frag_put(&fq->q); } #endif #endif |
| 731 708 56 54 55 56 55 54 54 55 2 7 55 54 55 54 54 37 37 38 50 50 50 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Bridge netlink control interface * * Authors: * Stephen Hemminger <shemminger@osdl.org> */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> #include <net/rtnetlink.h> #include <net/net_namespace.h> #include <net/sock.h> #include <uapi/linux/if_bridge.h> #include "br_private.h" #include "br_private_stp.h" #include "br_private_tunnel.h" static int __get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int num_vlans = 0; if (!(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; pvid = br_get_pvid(vg); /* Count number of vlan infos */ list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; /* only a context, bridge vlan not activated */ if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { if ((vid_range_end - vid_range_start) > 0) num_vlans += 2; else num_vlans += 1; } return num_vlans; } static int br_get_num_vlan_infos(struct net_bridge_vlan_group *vg, u32 filter_mask) { int num_vlans; if (!vg) return 0; if (filter_mask & RTEXT_FILTER_BRVLAN) return vg->num_vlans; rcu_read_lock(); num_vlans = __get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); return num_vlans; } static size_t br_get_link_af_size_filtered(const struct net_device *dev, u32 filter_mask) { struct net_bridge_vlan_group *vg = NULL; struct net_bridge_port *p = NULL; struct net_bridge *br; int num_vlan_infos; size_t vinfo_sz = 0; rcu_read_lock(); if (netif_is_bridge_port(dev)) { p = br_port_get_check_rcu(dev); if (p) vg = nbp_vlan_group_rcu(p); } else if (dev->priv_flags & IFF_EBRIDGE) { br = netdev_priv(dev); vg = br_vlan_group_rcu(br); } num_vlan_infos = br_get_num_vlan_infos(vg, filter_mask); rcu_read_unlock(); if (p && (p->flags & BR_VLAN_TUNNEL)) vinfo_sz += br_get_vlan_tunnel_info_size(vg); /* Each VLAN is returned in bridge_vlan_info along with flags */ vinfo_sz += num_vlan_infos * nla_total_size(sizeof(struct bridge_vlan_info)); return vinfo_sz; } static inline size_t br_port_info_size(void) { return nla_total_size(1) /* IFLA_BRPORT_STATE */ + nla_total_size(2) /* IFLA_BRPORT_PRIORITY */ + nla_total_size(4) /* IFLA_BRPORT_COST */ + nla_total_size(1) /* IFLA_BRPORT_MODE */ + nla_total_size(1) /* IFLA_BRPORT_GUARD */ + nla_total_size(1) /* IFLA_BRPORT_PROTECT */ + nla_total_size(1) /* IFLA_BRPORT_FAST_LEAVE */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_TO_UCAST */ + nla_total_size(1) /* IFLA_BRPORT_LEARNING */ + nla_total_size(1) /* IFLA_BRPORT_UNICAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_MCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_BCAST_FLOOD */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP */ + nla_total_size(1) /* IFLA_BRPORT_PROXYARP_WIFI */ + nla_total_size(1) /* IFLA_BRPORT_VLAN_TUNNEL */ + nla_total_size(1) /* IFLA_BRPORT_NEIGH_SUPPRESS */ + nla_total_size(1) /* IFLA_BRPORT_ISOLATED */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_ROOT_ID */ + nla_total_size(sizeof(struct ifla_bridge_id)) /* IFLA_BRPORT_BRIDGE_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_PORT */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_DESIGNATED_COST */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_ID */ + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_NO */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_TOPOLOGY_CHANGE_ACK */ + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_CONFIG_PENDING */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_MESSAGE_AGE_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_FORWARD_DELAY_TIMER */ + nla_total_size_64bit(sizeof(u64)) /* IFLA_BRPORT_HOLD_TIMER */ #ifdef CONFIG_BRIDGE_IGMP_SNOOPING + nla_total_size(sizeof(u8)) /* IFLA_BRPORT_MULTICAST_ROUTER */ #endif + nla_total_size(sizeof(u16)) /* IFLA_BRPORT_GROUP_FWD_MASK */ + 0; } static inline size_t br_nlmsg_size(struct net_device *dev, u32 filter_mask) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ + nla_total_size(MAX_ADDR_LEN) /* IFLA_ADDRESS */ + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(4) /* IFLA_MTU */ + nla_total_size(4) /* IFLA_LINK */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(br_port_info_size()) /* IFLA_PROTINFO */ + nla_total_size(br_get_link_af_size_filtered(dev, filter_mask)) /* IFLA_AF_SPEC */ + nla_total_size(4); /* IFLA_BRPORT_BACKUP_PORT */ } static int br_port_fill_attrs(struct sk_buff *skb, const struct net_bridge_port *p) { u8 mode = !!(p->flags & BR_HAIRPIN_MODE); struct net_bridge_port *backup_p; u64 timerval; if (nla_put_u8(skb, IFLA_BRPORT_STATE, p->state) || nla_put_u16(skb, IFLA_BRPORT_PRIORITY, p->priority) || nla_put_u32(skb, IFLA_BRPORT_COST, p->path_cost) || nla_put_u8(skb, IFLA_BRPORT_MODE, mode) || nla_put_u8(skb, IFLA_BRPORT_GUARD, !!(p->flags & BR_BPDU_GUARD)) || nla_put_u8(skb, IFLA_BRPORT_PROTECT, !!(p->flags & BR_ROOT_BLOCK)) || nla_put_u8(skb, IFLA_BRPORT_FAST_LEAVE, !!(p->flags & BR_MULTICAST_FAST_LEAVE)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_TO_UCAST, !!(p->flags & BR_MULTICAST_TO_UNICAST)) || nla_put_u8(skb, IFLA_BRPORT_LEARNING, !!(p->flags & BR_LEARNING)) || nla_put_u8(skb, IFLA_BRPORT_UNICAST_FLOOD, !!(p->flags & BR_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_MCAST_FLOOD, !!(p->flags & BR_MCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_BCAST_FLOOD, !!(p->flags & BR_BCAST_FLOOD)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP, !!(p->flags & BR_PROXYARP)) || nla_put_u8(skb, IFLA_BRPORT_PROXYARP_WIFI, !!(p->flags & BR_PROXYARP_WIFI)) || nla_put(skb, IFLA_BRPORT_ROOT_ID, sizeof(struct ifla_bridge_id), &p->designated_root) || nla_put(skb, IFLA_BRPORT_BRIDGE_ID, sizeof(struct ifla_bridge_id), &p->designated_bridge) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_PORT, p->designated_port) || nla_put_u16(skb, IFLA_BRPORT_DESIGNATED_COST, p->designated_cost) || nla_put_u16(skb, IFLA_BRPORT_ID, p->port_id) || nla_put_u16(skb, IFLA_BRPORT_NO, p->port_no) || nla_put_u8(skb, IFLA_BRPORT_TOPOLOGY_CHANGE_ACK, p->topology_change_ack) || nla_put_u8(skb, IFLA_BRPORT_CONFIG_PENDING, p->config_pending) || nla_put_u8(skb, IFLA_BRPORT_VLAN_TUNNEL, !!(p->flags & BR_VLAN_TUNNEL)) || nla_put_u16(skb, IFLA_BRPORT_GROUP_FWD_MASK, p->group_fwd_mask) || nla_put_u8(skb, IFLA_BRPORT_NEIGH_SUPPRESS, !!(p->flags & BR_NEIGH_SUPPRESS)) || nla_put_u8(skb, IFLA_BRPORT_ISOLATED, !!(p->flags & BR_ISOLATED))) return -EMSGSIZE; timerval = br_timer_value(&p->message_age_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_MESSAGE_AGE_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->forward_delay_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_FORWARD_DELAY_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; timerval = br_timer_value(&p->hold_timer); if (nla_put_u64_64bit(skb, IFLA_BRPORT_HOLD_TIMER, timerval, IFLA_BRPORT_PAD)) return -EMSGSIZE; #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (nla_put_u8(skb, IFLA_BRPORT_MULTICAST_ROUTER, p->multicast_router)) return -EMSGSIZE; #endif /* we might be called only with br->lock */ rcu_read_lock(); backup_p = rcu_dereference(p->backup_port); if (backup_p) nla_put_u32(skb, IFLA_BRPORT_BACKUP_PORT, backup_p->dev->ifindex); rcu_read_unlock(); return 0; } static int br_fill_ifvlaninfo_range(struct sk_buff *skb, u16 vid_start, u16 vid_end, u16 flags) { struct bridge_vlan_info vinfo; if ((vid_end - vid_start) > 0) { /* add range to skb */ vinfo.vid = vid_start; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_BEGIN; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; vinfo.vid = vid_end; vinfo.flags = flags | BRIDGE_VLAN_INFO_RANGE_END; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } else { vinfo.vid = vid_start; vinfo.flags = flags; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } static int br_fill_ifvlaninfo_compressed(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *v; u16 vid_range_start = 0, vid_range_end = 0, vid_range_flags = 0; u16 flags, pvid; int err = 0; /* Pack IFLA_BRIDGE_VLAN_INFO's for every vlan * and mark vlan info with begin and end flags * if vlaninfo represents a range */ pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { flags = 0; if (!br_vlan_should_use(v)) continue; if (v->vid == pvid) flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (vid_range_start == 0) { goto initvars; } else if ((v->vid - vid_range_end) == 1 && flags == vid_range_flags) { vid_range_end = v->vid; continue; } else { err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } initvars: vid_range_start = v->vid; vid_range_end = v->vid; vid_range_flags = flags; } if (vid_range_start != 0) { /* Call it once more to send any left over vlans */ err = br_fill_ifvlaninfo_range(skb, vid_range_start, vid_range_end, vid_range_flags); if (err) return err; } return 0; } static int br_fill_ifvlaninfo(struct sk_buff *skb, struct net_bridge_vlan_group *vg) { struct bridge_vlan_info vinfo; struct net_bridge_vlan *v; u16 pvid; pvid = br_get_pvid(vg); list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { if (!br_vlan_should_use(v)) continue; vinfo.vid = v->vid; vinfo.flags = 0; if (v->vid == pvid) vinfo.flags |= BRIDGE_VLAN_INFO_PVID; if (v->flags & BRIDGE_VLAN_INFO_UNTAGGED) vinfo.flags |= BRIDGE_VLAN_INFO_UNTAGGED; if (nla_put(skb, IFLA_BRIDGE_VLAN_INFO, sizeof(vinfo), &vinfo)) goto nla_put_failure; } return 0; nla_put_failure: return -EMSGSIZE; } /* * Create one netlink message for one interface * Contains port and master info as well as carrier and bridge state. */ static int br_fill_ifinfo(struct sk_buff *skb, const struct net_bridge_port *port, u32 pid, u32 seq, int event, unsigned int flags, u32 filter_mask, const struct net_device *dev) { u8 operstate = netif_running(dev) ? dev->operstate : IF_OPER_DOWN; struct net_bridge *br; struct ifinfomsg *hdr; struct nlmsghdr *nlh; if (port) br = port->br; else br = netdev_priv(dev); br_debug(br, "br_fill_info event %d port %s master %s\n", event, dev->name, br->dev->name); nlh = nlmsg_put(skb, pid, seq, event, sizeof(*hdr), flags); if (nlh == NULL) return -EMSGSIZE; hdr = nlmsg_data(nlh); hdr->ifi_family = AF_BRIDGE; hdr->__ifi_pad = 0; hdr->ifi_type = dev->type; hdr->ifi_index = dev->ifindex; hdr->ifi_flags = dev_get_flags(dev); hdr->ifi_change = 0; if (nla_put_string(skb, IFLA_IFNAME, dev->name) || nla_put_u32(skb, IFLA_MASTER, br->dev->ifindex) || nla_put_u32(skb, IFLA_MTU, dev->mtu) || nla_put_u8(skb, IFLA_OPERSTATE, operstate) || (dev->addr_len && nla_put(skb, IFLA_ADDRESS, dev->addr_len, dev->dev_addr)) || (dev->ifindex != dev_get_iflink(dev) && nla_put_u32(skb, IFLA_LINK, dev_get_iflink(dev)))) goto nla_put_failure; if (event == RTM_NEWLINK && port) { struct nlattr *nest; nest = nla_nest_start(skb, IFLA_PROTINFO); if (nest == NULL || br_port_fill_attrs(skb, port) < 0) goto nla_put_failure; nla_nest_end(skb, nest); } /* Check if the VID information is requested */ if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { struct net_bridge_vlan_group *vg; struct nlattr *af; int err; /* RCU needed because of the VLAN locking rules (rcu || rtnl) */ rcu_read_lock(); if (port) vg = nbp_vlan_group_rcu(port); else vg = br_vlan_group_rcu(br); if (!vg || !vg->num_vlans) { rcu_read_unlock(); goto done; } af = nla_nest_start_noflag(skb, IFLA_AF_SPEC); if (!af) { rcu_read_unlock(); goto nla_put_failure; } if (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED) err = br_fill_ifvlaninfo_compressed(skb, vg); else err = br_fill_ifvlaninfo(skb, vg); if (port && (port->flags & BR_VLAN_TUNNEL)) err = br_fill_vlan_tunnel_info(skb, vg); rcu_read_unlock(); if (err) goto nla_put_failure; nla_nest_end(skb, af); } done: nlmsg_end(skb, nlh); return 0; nla_put_failure: nlmsg_cancel(skb, nlh); return -EMSGSIZE; } /* Notify listeners of a change in bridge or port information */ void br_ifinfo_notify(int event, const struct net_bridge *br, const struct net_bridge_port *port) { u32 filter = RTEXT_FILTER_BRVLAN_COMPRESSED; struct net_device *dev; struct sk_buff *skb; int err = -ENOBUFS; struct net *net; u16 port_no = 0; if (WARN_ON(!port && !br)) return; if (port) { dev = port->dev; br = port->br; port_no = port->port_no; } else { dev = br->dev; } net = dev_net(dev); br_debug(br, "port %u(%s) event %d\n", port_no, dev->name, event); skb = nlmsg_new(br_nlmsg_size(dev, filter), GFP_ATOMIC); if (skb == NULL) goto errout; err = br_fill_ifinfo(skb, port, 0, 0, event, 0, filter, dev); if (err < 0) { /* -EMSGSIZE implies BUG in br_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); kfree_skb(skb); goto errout; } rtnl_notify(skb, net, 0, RTNLGRP_LINK, NULL, GFP_ATOMIC); return; errout: rtnl_set_sk_err(net, RTNLGRP_LINK, err); } /* * Dump information about all ports, in response to GETLINK */ int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags) { struct net_bridge_port *port = br_port_get_rtnl(dev); if (!port && !(filter_mask & RTEXT_FILTER_BRVLAN) && !(filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) return 0; return br_fill_ifinfo(skb, port, pid, seq, RTM_NEWLINK, nlflags, filter_mask, dev); } static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo, bool *changed, struct netlink_ext_ack *extack) { bool curr_change; int err = 0; switch (cmd) { case RTM_SETLINK: if (p) { /* if the MASTER flag is set this will act on the global * per-VLAN entry as well */ err = nbp_vlan_add(p, vinfo->vid, vinfo->flags, &curr_change, extack); } else { vinfo->flags |= BRIDGE_VLAN_INFO_BRENTRY; err = br_vlan_add(br, vinfo->vid, vinfo->flags, &curr_change, extack); } if (curr_change) *changed = true; break; case RTM_DELLINK: if (p) { if (!nbp_vlan_delete(p, vinfo->vid)) *changed = true; if ((vinfo->flags & BRIDGE_VLAN_INFO_MASTER) && !br_vlan_delete(p->br, vinfo->vid)) *changed = true; } else if (!br_vlan_delete(br, vinfo->vid)) { *changed = true; } break; } return err; } static int br_process_vlan_info(struct net_bridge *br, struct net_bridge_port *p, int cmd, struct bridge_vlan_info *vinfo_curr, struct bridge_vlan_info **vinfo_last, bool *changed, struct netlink_ext_ack *extack) { if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK) return -EINVAL; if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { /* check if we are already processing a range */ if (*vinfo_last) return -EINVAL; *vinfo_last = vinfo_curr; /* don't allow range of pvids */ if ((*vinfo_last)->flags & BRIDGE_VLAN_INFO_PVID) return -EINVAL; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; int v, err; if (!(vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END)) return -EINVAL; if (vinfo_curr->vid <= (*vinfo_last)->vid) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { tmp_vinfo.vid = v; err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed, extack); if (err) break; } *vinfo_last = NULL; return err; } return br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); } static int br_afspec(struct net_bridge *br, struct net_bridge_port *p, struct nlattr *af_spec, int cmd, bool *changed, struct netlink_ext_ack *extack) { struct bridge_vlan_info *vinfo_curr = NULL; struct bridge_vlan_info *vinfo_last = NULL; struct nlattr *attr; struct vtunnel_info tinfo_last = {}; struct vtunnel_info tinfo_curr = {}; int err = 0, rem; nla_for_each_nested(attr, af_spec, rem) { err = 0; switch (nla_type(attr)) { case IFLA_BRIDGE_VLAN_TUNNEL_INFO: if (!p || !(p->flags & BR_VLAN_TUNNEL)) return -EINVAL; err = br_parse_vlan_tunnel_info(attr, &tinfo_curr); if (err) return err; err = br_process_vlan_tunnel_info(br, p, cmd, &tinfo_curr, &tinfo_last, changed); if (err) return err; break; case IFLA_BRIDGE_VLAN_INFO: if (nla_len(attr) != sizeof(struct bridge_vlan_info)) return -EINVAL; vinfo_curr = nla_data(attr); err = br_process_vlan_info(br, p, cmd, vinfo_curr, &vinfo_last, changed, extack); if (err) return err; break; } } return err; } static const struct nla_policy br_port_policy[IFLA_BRPORT_MAX + 1] = { [IFLA_BRPORT_STATE] = { .type = NLA_U8 }, [IFLA_BRPORT_COST] = { .type = NLA_U32 }, [IFLA_BRPORT_PRIORITY] = { .type = NLA_U16 }, [IFLA_BRPORT_MODE] = { .type = NLA_U8 }, [IFLA_BRPORT_GUARD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROTECT] = { .type = NLA_U8 }, [IFLA_BRPORT_FAST_LEAVE]= { .type = NLA_U8 }, [IFLA_BRPORT_LEARNING] = { .type = NLA_U8 }, [IFLA_BRPORT_UNICAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP] = { .type = NLA_U8 }, [IFLA_BRPORT_PROXYARP_WIFI] = { .type = NLA_U8 }, [IFLA_BRPORT_MULTICAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_TO_UCAST] = { .type = NLA_U8 }, [IFLA_BRPORT_MCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_BCAST_FLOOD] = { .type = NLA_U8 }, [IFLA_BRPORT_VLAN_TUNNEL] = { .type = NLA_U8 }, [IFLA_BRPORT_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BRPORT_NEIGH_SUPPRESS] = { .type = NLA_U8 }, [IFLA_BRPORT_ISOLATED] = { .type = NLA_U8 }, [IFLA_BRPORT_BACKUP_PORT] = { .type = NLA_U32 }, }; /* Change the state of the port and notify spanning tree */ static int br_set_port_state(struct net_bridge_port *p, u8 state) { if (state > BR_STATE_BLOCKING) return -EINVAL; /* if kernel STP is running, don't allow changes */ if (p->br->stp_enabled == BR_KERNEL_STP) return -EBUSY; /* if device is not up, change is not allowed * if link is not present, only allowable state is disabled */ if (!netif_running(p->dev) || (!netif_oper_up(p->dev) && state != BR_STATE_DISABLED)) return -ENETDOWN; br_set_state(p, state); br_port_state_selection(p->br); return 0; } /* Set/clear or port flags based on attribute */ static int br_set_port_flag(struct net_bridge_port *p, struct nlattr *tb[], int attrtype, unsigned long mask) { unsigned long flags; int err; if (!tb[attrtype]) return 0; if (nla_get_u8(tb[attrtype])) flags = p->flags | mask; else flags = p->flags & ~mask; err = br_switchdev_set_port_flag(p, flags, mask); if (err) return err; p->flags = flags; return 0; } /* Process bridge protocol info on port */ static int br_setport(struct net_bridge_port *p, struct nlattr *tb[]) { unsigned long old_flags = p->flags; bool br_vlan_tunnel_old = false; int err; err = br_set_port_flag(p, tb, IFLA_BRPORT_MODE, BR_HAIRPIN_MODE); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_GUARD, BR_BPDU_GUARD); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_FAST_LEAVE, BR_MULTICAST_FAST_LEAVE); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_PROTECT, BR_ROOT_BLOCK); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_LEARNING, BR_LEARNING); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_UNICAST_FLOOD, BR_FLOOD); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_FLOOD, BR_MCAST_FLOOD); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_MCAST_TO_UCAST, BR_MULTICAST_TO_UNICAST); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_BCAST_FLOOD, BR_BCAST_FLOOD); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP, BR_PROXYARP); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_PROXYARP_WIFI, BR_PROXYARP_WIFI); if (err) return err; br_vlan_tunnel_old = (p->flags & BR_VLAN_TUNNEL) ? true : false; err = br_set_port_flag(p, tb, IFLA_BRPORT_VLAN_TUNNEL, BR_VLAN_TUNNEL); if (err) return err; if (br_vlan_tunnel_old && !(p->flags & BR_VLAN_TUNNEL)) nbp_vlan_tunnel_info_flush(p); if (tb[IFLA_BRPORT_COST]) { err = br_stp_set_path_cost(p, nla_get_u32(tb[IFLA_BRPORT_COST])); if (err) return err; } if (tb[IFLA_BRPORT_PRIORITY]) { err = br_stp_set_port_priority(p, nla_get_u16(tb[IFLA_BRPORT_PRIORITY])); if (err) return err; } if (tb[IFLA_BRPORT_STATE]) { err = br_set_port_state(p, nla_get_u8(tb[IFLA_BRPORT_STATE])); if (err) return err; } if (tb[IFLA_BRPORT_FLUSH]) br_fdb_delete_by_port(p->br, p, 0, 0); #ifdef CONFIG_BRIDGE_IGMP_SNOOPING if (tb[IFLA_BRPORT_MULTICAST_ROUTER]) { u8 mcast_router = nla_get_u8(tb[IFLA_BRPORT_MULTICAST_ROUTER]); err = br_multicast_set_port_router(p, mcast_router); if (err) return err; } #endif if (tb[IFLA_BRPORT_GROUP_FWD_MASK]) { u16 fwd_mask = nla_get_u16(tb[IFLA_BRPORT_GROUP_FWD_MASK]); if (fwd_mask & BR_GROUPFWD_MACPAUSE) return -EINVAL; p->group_fwd_mask = fwd_mask; } err = br_set_port_flag(p, tb, IFLA_BRPORT_NEIGH_SUPPRESS, BR_NEIGH_SUPPRESS); if (err) return err; err = br_set_port_flag(p, tb, IFLA_BRPORT_ISOLATED, BR_ISOLATED); if (err) return err; if (tb[IFLA_BRPORT_BACKUP_PORT]) { struct net_device *backup_dev = NULL; u32 backup_ifindex; backup_ifindex = nla_get_u32(tb[IFLA_BRPORT_BACKUP_PORT]); if (backup_ifindex) { backup_dev = __dev_get_by_index(dev_net(p->dev), backup_ifindex); if (!backup_dev) return -ENOENT; } err = nbp_backup_change(p, backup_dev); if (err) return err; } br_port_flags_change(p, old_flags ^ p->flags); return 0; } /* Change state and parameters on port. */ int br_setlink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct nlattr *tb[IFLA_BRPORT_MAX + 1]; struct net_bridge_port *p; struct nlattr *protinfo; struct nlattr *afspec; bool changed = false; int err = 0; protinfo = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_PROTINFO); afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!protinfo && !afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself if the AF_SPEC * is set to see if someone is setting vlan info on the bridge */ if (!p && !afspec) return -EINVAL; if (p && protinfo) { if (protinfo->nla_type & NLA_F_NESTED) { err = nla_parse_nested_deprecated(tb, IFLA_BRPORT_MAX, protinfo, br_port_policy, NULL); if (err) return err; spin_lock_bh(&p->br->lock); err = br_setport(p, tb); spin_unlock_bh(&p->br->lock); } else { /* Binary compatibility with old RSTP */ if (nla_len(protinfo) < sizeof(u8)) return -EINVAL; spin_lock_bh(&p->br->lock); err = br_set_port_state(p, nla_get_u8(protinfo)); spin_unlock_bh(&p->br->lock); } if (err) goto out; changed = true; } if (afspec) err = br_afspec(br, p, afspec, RTM_SETLINK, &changed, extack); if (changed) br_ifinfo_notify(RTM_NEWLINK, br, p); out: return err; } /* Delete port information */ int br_dellink(struct net_device *dev, struct nlmsghdr *nlh, u16 flags) { struct net_bridge *br = (struct net_bridge *)netdev_priv(dev); struct net_bridge_port *p; struct nlattr *afspec; bool changed = false; int err = 0; afspec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (!afspec) return 0; p = br_port_get_rtnl(dev); /* We want to accept dev as bridge itself as well */ if (!p && !(dev->priv_flags & IFF_EBRIDGE)) return -EINVAL; err = br_afspec(br, p, afspec, RTM_DELLINK, &changed, NULL); if (changed) /* Send RTM_NEWLINK because userspace * expects RTM_NEWLINK for vlan dels */ br_ifinfo_notify(RTM_NEWLINK, br, p); return err; } static int br_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { if (tb[IFLA_ADDRESS]) { if (nla_len(tb[IFLA_ADDRESS]) != ETH_ALEN) return -EINVAL; if (!is_valid_ether_addr(nla_data(tb[IFLA_ADDRESS]))) return -EADDRNOTAVAIL; } if (!data) return 0; #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { switch (nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL])) { case htons(ETH_P_8021Q): case htons(ETH_P_8021AD): break; default: return -EPROTONOSUPPORT; } } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { __u16 defpvid = nla_get_u16(data[IFLA_BR_VLAN_DEFAULT_PVID]); if (defpvid >= VLAN_VID_MASK) return -EINVAL; } #endif return 0; } static int br_port_slave_changelink(struct net_device *brdev, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int ret; if (!data) return 0; spin_lock_bh(&br->lock); ret = br_setport(br_port_get_rtnl(dev), data); spin_unlock_bh(&br->lock); return ret; } static int br_port_fill_slave_info(struct sk_buff *skb, const struct net_device *brdev, const struct net_device *dev) { return br_port_fill_attrs(skb, br_port_get_rtnl(dev)); } static size_t br_port_get_slave_size(const struct net_device *brdev, const struct net_device *dev) { return br_port_info_size(); } static const struct nla_policy br_policy[IFLA_BR_MAX + 1] = { [IFLA_BR_FORWARD_DELAY] = { .type = NLA_U32 }, [IFLA_BR_HELLO_TIME] = { .type = NLA_U32 }, [IFLA_BR_MAX_AGE] = { .type = NLA_U32 }, [IFLA_BR_AGEING_TIME] = { .type = NLA_U32 }, [IFLA_BR_STP_STATE] = { .type = NLA_U32 }, [IFLA_BR_PRIORITY] = { .type = NLA_U16 }, [IFLA_BR_VLAN_FILTERING] = { .type = NLA_U8 }, [IFLA_BR_VLAN_PROTOCOL] = { .type = NLA_U16 }, [IFLA_BR_GROUP_FWD_MASK] = { .type = NLA_U16 }, [IFLA_BR_GROUP_ADDR] = { .type = NLA_BINARY, .len = ETH_ALEN }, [IFLA_BR_MCAST_ROUTER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_SNOOPING] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERY_USE_IFADDR] = { .type = NLA_U8 }, [IFLA_BR_MCAST_QUERIER] = { .type = NLA_U8 }, [IFLA_BR_MCAST_HASH_ELASTICITY] = { .type = NLA_U32 }, [IFLA_BR_MCAST_HASH_MAX] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_STARTUP_QUERY_CNT] = { .type = NLA_U32 }, [IFLA_BR_MCAST_LAST_MEMBER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_MEMBERSHIP_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERIER_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_QUERY_RESPONSE_INTVL] = { .type = NLA_U64 }, [IFLA_BR_MCAST_STARTUP_QUERY_INTVL] = { .type = NLA_U64 }, [IFLA_BR_NF_CALL_IPTABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_IP6TABLES] = { .type = NLA_U8 }, [IFLA_BR_NF_CALL_ARPTABLES] = { .type = NLA_U8 }, [IFLA_BR_VLAN_DEFAULT_PVID] = { .type = NLA_U16 }, [IFLA_BR_VLAN_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_STATS_ENABLED] = { .type = NLA_U8 }, [IFLA_BR_MCAST_IGMP_VERSION] = { .type = NLA_U8 }, [IFLA_BR_MCAST_MLD_VERSION] = { .type = NLA_U8 }, [IFLA_BR_VLAN_STATS_PER_PORT] = { .type = NLA_U8 }, [IFLA_BR_MULTI_BOOLOPT] = { .type = NLA_EXACT_LEN, .len = sizeof(struct br_boolopt_multi) }, }; static int br_changelink(struct net_device *brdev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct net_bridge *br = netdev_priv(brdev); int err; if (!data) return 0; if (data[IFLA_BR_FORWARD_DELAY]) { err = br_set_forward_delay(br, nla_get_u32(data[IFLA_BR_FORWARD_DELAY])); if (err) return err; } if (data[IFLA_BR_HELLO_TIME]) { err = br_set_hello_time(br, nla_get_u32(data[IFLA_BR_HELLO_TIME])); if (err) return err; } if (data[IFLA_BR_MAX_AGE]) { err = br_set_max_age(br, nla_get_u32(data[IFLA_BR_MAX_AGE])); if (err) return err; } if (data[IFLA_BR_AGEING_TIME]) { err = br_set_ageing_time(br, nla_get_u32(data[IFLA_BR_AGEING_TIME])); if (err) return err; } if (data[IFLA_BR_STP_STATE]) { u32 stp_enabled = nla_get_u32(data[IFLA_BR_STP_STATE]); br_stp_set_enabled(br, stp_enabled); } if (data[IFLA_BR_PRIORITY]) { u32 priority = nla_get_u16(data[IFLA_BR_PRIORITY]); br_stp_set_bridge_priority(br, priority); } if (data[IFLA_BR_VLAN_FILTERING]) { u8 vlan_filter = nla_get_u8(data[IFLA_BR_VLAN_FILTERING]); err = __br_vlan_filter_toggle(br, vlan_filter); if (err) return err; } #ifdef CONFIG_BRIDGE_VLAN_FILTERING if (data[IFLA_BR_VLAN_PROTOCOL]) { __be16 vlan_proto = nla_get_be16(data[IFLA_BR_VLAN_PROTOCOL]); err = __br_vlan_set_proto(br, vlan_proto); if (err) return err; } if (data[IFLA_BR_VLAN_DEFAULT_PVID]) { |