| 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * linux/drivers/char/serial_core.h * * Copyright (C) 2000 Deep Blue Solutions Ltd. */ #ifndef LINUX_SERIAL_CORE_H #define LINUX_SERIAL_CORE_H #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/console.h> #include <linux/interrupt.h> #include <linux/spinlock.h> #include <linux/sched.h> #include <linux/tty.h> #include <linux/mutex.h> #include <linux/sysrq.h> #include <uapi/linux/serial_core.h> #ifdef CONFIG_SERIAL_CORE_CONSOLE #define uart_console(port) \ ((port)->cons && (port)->cons->index == (port)->line) #else #define uart_console(port) ({ (void)port; 0; }) #endif struct uart_port; struct serial_struct; struct serial_port_device; struct device; struct gpio_desc; /** * struct uart_ops -- interface between serial_core and the driver * * This structure describes all the operations that can be done on the * physical hardware. * * @tx_empty: ``unsigned int ()(struct uart_port *port)`` * * This function tests whether the transmitter fifo and shifter for the * @port is empty. If it is empty, this function should return * %TIOCSER_TEMT, otherwise return 0. If the port does not support this * operation, then it should return %TIOCSER_TEMT. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @set_mctrl: ``void ()(struct uart_port *port, unsigned int mctrl)`` * * This function sets the modem control lines for @port to the state * described by @mctrl. The relevant bits of @mctrl are: * * - %TIOCM_RTS RTS signal. * - %TIOCM_DTR DTR signal. * - %TIOCM_OUT1 OUT1 signal. * - %TIOCM_OUT2 OUT2 signal. * - %TIOCM_LOOP Set the port into loopback mode. * * If the appropriate bit is set, the signal should be driven * active. If the bit is clear, the signal should be driven * inactive. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @get_mctrl: ``unsigned int ()(struct uart_port *port)`` * * Returns the current state of modem control inputs of @port. The state * of the outputs should not be returned, since the core keeps track of * their state. The state information should include: * * - %TIOCM_CAR state of DCD signal * - %TIOCM_CTS state of CTS signal * - %TIOCM_DSR state of DSR signal * - %TIOCM_RI state of RI signal * * The bit is set if the signal is currently driven active. If * the port does not support CTS, DCD or DSR, the driver should * indicate that the signal is permanently active. If RI is * not available, the signal should not be indicated as active. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_tx: ``void ()(struct uart_port *port)`` * * Stop transmitting characters. This might be due to the CTS line * becoming inactive or the tty layer indicating we want to stop * transmission due to an %XOFF character. * * The driver should stop transmitting characters as soon as possible. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @start_tx: ``void ()(struct uart_port *port)`` * * Start transmitting characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @throttle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that input buffers for the line discipline are * close to full, and it should somehow signal that no more characters * should be sent to the serial port. * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @unthrottle() and termios modification by the * tty layer. * * @unthrottle: ``void ()(struct uart_port *port)`` * * Notify the serial driver that characters can now be sent to the serial * port without fear of overrunning the input buffers of the line * disciplines. * * This will be called only if hardware assisted flow control is enabled. * * Locking: serialized with @throttle() and termios modification by the * tty layer. * * @send_xchar: ``void ()(struct uart_port *port, char ch)`` * * Transmit a high priority character, even if the port is stopped. This * is used to implement XON/XOFF flow control and tcflow(). If the serial * driver does not implement this function, the tty core will append the * character to the circular buffer and then call start_tx() / stop_tx() * to flush the data out. * * Do not transmit if @ch == '\0' (%__DISABLED_CHAR). * * Locking: none. * Interrupts: caller dependent. * * @start_rx: ``void ()(struct uart_port *port)`` * * Start receiving characters. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @stop_rx: ``void ()(struct uart_port *port)`` * * Stop receiving characters; the @port is in the process of being closed. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @enable_ms: ``void ()(struct uart_port *port)`` * * Enable the modem status interrupts. * * This method may be called multiple times. Modem status interrupts * should be disabled when the @shutdown() method is called. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @break_ctl: ``void ()(struct uart_port *port, int ctl)`` * * Control the transmission of a break signal. If @ctl is nonzero, the * break signal should be transmitted. The signal should be terminated * when another call is made with a zero @ctl. * * Locking: caller holds tty_port->mutex * * @startup: ``int ()(struct uart_port *port)`` * * Grab any interrupt resources and initialise any low level driver state. * Enable the port for reception. It should not activate RTS nor DTR; * this will be done via a separate call to @set_mctrl(). * * This method will only be called when the port is initially opened. * * Locking: port_sem taken. * Interrupts: globally disabled. * * @shutdown: ``void ()(struct uart_port *port)`` * * Disable the @port, disable any break condition that may be in effect, * and free any interrupt resources. It should not disable RTS nor DTR; * this will have already been done via a separate call to @set_mctrl(). * * Drivers must not access @port->state once this call has completed. * * This method will only be called when there are no more users of this * @port. * * Locking: port_sem taken. * Interrupts: caller dependent. * * @flush_buffer: ``void ()(struct uart_port *port)`` * * Flush any write buffers, reset any DMA state and stop any ongoing DMA * transfers. * * This will be called whenever the @port->state->xmit circular buffer is * cleared. * * Locking: @port->lock taken. * Interrupts: locally disabled. * This call must not sleep * * @set_termios: ``void ()(struct uart_port *port, struct ktermios *new, * struct ktermios *old)`` * * Change the @port parameters, including word length, parity, stop bits. * Update @port->read_status_mask and @port->ignore_status_mask to * indicate the types of events we are interested in receiving. Relevant * ktermios::c_cflag bits are: * * - %CSIZE - word size * - %CSTOPB - 2 stop bits * - %PARENB - parity enable * - %PARODD - odd parity (when %PARENB is in force) * - %ADDRB - address bit (changed through uart_port::rs485_config()). * - %CREAD - enable reception of characters (if not set, still receive * characters from the port, but throw them away). * - %CRTSCTS - if set, enable CTS status change reporting. * - %CLOCAL - if not set, enable modem status change reporting. * * Relevant ktermios::c_iflag bits are: * * - %INPCK - enable frame and parity error events to be passed to the TTY * layer. * - %BRKINT / %PARMRK - both of these enable break events to be passed to * the TTY layer. * - %IGNPAR - ignore parity and framing errors. * - %IGNBRK - ignore break errors. If %IGNPAR is also set, ignore overrun * errors as well. * * The interaction of the ktermios::c_iflag bits is as follows (parity * error given as an example): * * ============ ======= ======= ========================================= * Parity error INPCK IGNPAR * ============ ======= ======= ========================================= * n/a 0 n/a character received, marked as %TTY_NORMAL * None 1 n/a character received, marked as %TTY_NORMAL * Yes 1 0 character received, marked as %TTY_PARITY * Yes 1 1 character discarded * ============ ======= ======= ========================================= * * Other flags may be used (eg, xon/xoff characters) if your hardware * supports hardware "soft" flow control. * * Locking: caller holds tty_port->mutex * Interrupts: caller dependent. * This call must not sleep * * @set_ldisc: ``void ()(struct uart_port *port, struct ktermios *termios)`` * * Notifier for discipline change. See * Documentation/driver-api/tty/tty_ldisc.rst. * * Locking: caller holds tty_port->mutex * * @pm: ``void ()(struct uart_port *port, unsigned int state, * unsigned int oldstate)`` * * Perform any power management related activities on the specified @port. * @state indicates the new state (defined by enum uart_pm_state), * @oldstate indicates the previous state. * * This function should not be used to grab any resources. * * This will be called when the @port is initially opened and finally * closed, except when the @port is also the system console. This will * occur even if %CONFIG_PM is not set. * * Locking: none. * Interrupts: caller dependent. * * @type: ``const char *()(struct uart_port *port)`` * * Return a pointer to a string constant describing the specified @port, * or return %NULL, in which case the string 'unknown' is substituted. * * Locking: none. * Interrupts: caller dependent. * * @release_port: ``void ()(struct uart_port *port)`` * * Release any memory and IO region resources currently in use by the * @port. * * Locking: none. * Interrupts: caller dependent. * * @request_port: ``int ()(struct uart_port *port)`` * * Request any memory and IO region resources required by the port. If any * fail, no resources should be registered when this function returns, and * it should return -%EBUSY on failure. * * Locking: none. * Interrupts: caller dependent. * * @config_port: ``void ()(struct uart_port *port, int type)`` * * Perform any autoconfiguration steps required for the @port. @type * contains a bit mask of the required configuration. %UART_CONFIG_TYPE * indicates that the port requires detection and identification. * @port->type should be set to the type found, or %PORT_UNKNOWN if no * port was detected. * * %UART_CONFIG_IRQ indicates autoconfiguration of the interrupt signal, * which should be probed using standard kernel autoprobing techniques. * This is not necessary on platforms where ports have interrupts * internally hard wired (eg, system on a chip implementations). * * Locking: none. * Interrupts: caller dependent. * * @verify_port: ``int ()(struct uart_port *port, * struct serial_struct *serinfo)`` * * Verify the new serial port information contained within @serinfo is * suitable for this port type. * * Locking: none. * Interrupts: caller dependent. * * @ioctl: ``int ()(struct uart_port *port, unsigned int cmd, * unsigned long arg)`` * * Perform any port specific IOCTLs. IOCTL commands must be defined using * the standard numbering system found in <asm/ioctl.h>. * * Locking: none. * Interrupts: caller dependent. * * @poll_init: ``int ()(struct uart_port *port)`` * * Called by kgdb to perform the minimal hardware initialization needed to * support @poll_put_char() and @poll_get_char(). Unlike @startup(), this * should not request interrupts. * * Locking: %tty_mutex and tty_port->mutex taken. * Interrupts: n/a. * * @poll_put_char: ``void ()(struct uart_port *port, unsigned char ch)`` * * Called by kgdb to write a single character @ch directly to the serial * @port. It can and should block until there is space in the TX FIFO. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep * * @poll_get_char: ``int ()(struct uart_port *port)`` * * Called by kgdb to read a single character directly from the serial * port. If data is available, it should be returned; otherwise the * function should return %NO_POLL_CHAR immediately. * * Locking: none. * Interrupts: caller dependent. * This call must not sleep */ struct uart_ops { unsigned int (*tx_empty)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int mctrl); unsigned int (*get_mctrl)(struct uart_port *); void (*stop_tx)(struct uart_port *); void (*start_tx)(struct uart_port *); void (*throttle)(struct uart_port *); void (*unthrottle)(struct uart_port *); void (*send_xchar)(struct uart_port *, char ch); void (*stop_rx)(struct uart_port *); void (*start_rx)(struct uart_port *); void (*enable_ms)(struct uart_port *); void (*break_ctl)(struct uart_port *, int ctl); int (*startup)(struct uart_port *); void (*shutdown)(struct uart_port *); void (*flush_buffer)(struct uart_port *); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); void (*pm)(struct uart_port *, unsigned int state, unsigned int oldstate); const char *(*type)(struct uart_port *); void (*release_port)(struct uart_port *); int (*request_port)(struct uart_port *); void (*config_port)(struct uart_port *, int); int (*verify_port)(struct uart_port *, struct serial_struct *); int (*ioctl)(struct uart_port *, unsigned int, unsigned long); #ifdef CONFIG_CONSOLE_POLL int (*poll_init)(struct uart_port *); void (*poll_put_char)(struct uart_port *, unsigned char); int (*poll_get_char)(struct uart_port *); #endif }; #define NO_POLL_CHAR 0x00ff0000 #define UART_CONFIG_TYPE (1 << 0) #define UART_CONFIG_IRQ (1 << 1) struct uart_icount { __u32 cts; __u32 dsr; __u32 rng; __u32 dcd; __u32 rx; __u32 tx; __u32 frame; __u32 overrun; __u32 parity; __u32 brk; __u32 buf_overrun; }; typedef u64 __bitwise upf_t; typedef unsigned int __bitwise upstat_t; struct uart_port { spinlock_t lock; /* port lock */ unsigned long iobase; /* in/out[bwl] */ unsigned char __iomem *membase; /* read/write[bwl] */ unsigned int (*serial_in)(struct uart_port *, int); void (*serial_out)(struct uart_port *, int, int); void (*set_termios)(struct uart_port *, struct ktermios *new, const struct ktermios *old); void (*set_ldisc)(struct uart_port *, struct ktermios *); unsigned int (*get_mctrl)(struct uart_port *); void (*set_mctrl)(struct uart_port *, unsigned int); unsigned int (*get_divisor)(struct uart_port *, unsigned int baud, unsigned int *frac); void (*set_divisor)(struct uart_port *, unsigned int baud, unsigned int quot, unsigned int quot_frac); int (*startup)(struct uart_port *port); void (*shutdown)(struct uart_port *port); void (*throttle)(struct uart_port *port); void (*unthrottle)(struct uart_port *port); int (*handle_irq)(struct uart_port *); void (*pm)(struct uart_port *, unsigned int state, unsigned int old); void (*handle_break)(struct uart_port *); int (*rs485_config)(struct uart_port *, struct ktermios *termios, struct serial_rs485 *rs485); int (*iso7816_config)(struct uart_port *, struct serial_iso7816 *iso7816); unsigned int ctrl_id; /* optional serial core controller id */ unsigned int port_id; /* optional serial core port id */ unsigned int irq; /* irq number */ unsigned long irqflags; /* irq flags */ unsigned int uartclk; /* base uart clock */ unsigned int fifosize; /* tx fifo size */ unsigned char x_char; /* xon/xoff char */ unsigned char regshift; /* reg offset shift */ unsigned char iotype; /* io access style */ #define UPIO_UNKNOWN ((unsigned char)~0U) /* UCHAR_MAX */ #define UPIO_PORT (SERIAL_IO_PORT) /* 8b I/O port access */ #define UPIO_HUB6 (SERIAL_IO_HUB6) /* Hub6 ISA card */ #define UPIO_MEM (SERIAL_IO_MEM) /* driver-specific */ #define UPIO_MEM32 (SERIAL_IO_MEM32) /* 32b little endian */ #define UPIO_AU (SERIAL_IO_AU) /* Au1x00 and RT288x type IO */ #define UPIO_TSI (SERIAL_IO_TSI) /* Tsi108/109 type IO */ #define UPIO_MEM32BE (SERIAL_IO_MEM32BE) /* 32b big endian */ #define UPIO_MEM16 (SERIAL_IO_MEM16) /* 16b little endian */ unsigned char quirks; /* internal quirks */ /* internal quirks must be updated while holding port mutex */ #define UPQ_NO_TXEN_TEST BIT(0) unsigned int read_status_mask; /* driver specific */ unsigned int ignore_status_mask; /* driver specific */ struct uart_state *state; /* pointer to parent state */ struct uart_icount icount; /* statistics */ struct console *cons; /* struct console, if any */ /* flags must be updated while holding port mutex */ upf_t flags; /* * These flags must be equivalent to the flags defined in * include/uapi/linux/tty_flags.h which are the userspace definitions * assigned from the serial_struct flags in uart_set_info() * [for bit definitions in the UPF_CHANGE_MASK] * * Bits [0..ASYNCB_LAST_USER] are userspace defined/visible/changeable * The remaining bits are serial-core specific and not modifiable by * userspace. */ #define UPF_FOURPORT ((__force upf_t) ASYNC_FOURPORT /* 1 */ ) #define UPF_SAK ((__force upf_t) ASYNC_SAK /* 2 */ ) #define UPF_SPD_HI ((__force upf_t) ASYNC_SPD_HI /* 4 */ ) #define UPF_SPD_VHI ((__force upf_t) ASYNC_SPD_VHI /* 5 */ ) #define UPF_SPD_CUST ((__force upf_t) ASYNC_SPD_CUST /* 0x0030 */ ) #define UPF_SPD_WARP ((__force upf_t) ASYNC_SPD_WARP /* 0x1010 */ ) #define UPF_SPD_MASK ((__force upf_t) ASYNC_SPD_MASK /* 0x1030 */ ) #define UPF_SKIP_TEST ((__force upf_t) ASYNC_SKIP_TEST /* 6 */ ) #define UPF_AUTO_IRQ ((__force upf_t) ASYNC_AUTO_IRQ /* 7 */ ) #define UPF_HARDPPS_CD ((__force upf_t) ASYNC_HARDPPS_CD /* 11 */ ) #define UPF_SPD_SHI ((__force upf_t) ASYNC_SPD_SHI /* 12 */ ) #define UPF_LOW_LATENCY ((__force upf_t) ASYNC_LOW_LATENCY /* 13 */ ) #define UPF_BUGGY_UART ((__force upf_t) ASYNC_BUGGY_UART /* 14 */ ) #define UPF_MAGIC_MULTIPLIER ((__force upf_t) ASYNC_MAGIC_MULTIPLIER /* 16 */ ) #define UPF_NO_THRE_TEST ((__force upf_t) BIT_ULL(19)) /* Port has hardware-assisted h/w flow control */ #define UPF_AUTO_CTS ((__force upf_t) BIT_ULL(20)) #define UPF_AUTO_RTS ((__force upf_t) BIT_ULL(21)) #define UPF_HARD_FLOW ((__force upf_t) (UPF_AUTO_CTS | UPF_AUTO_RTS)) /* Port has hardware-assisted s/w flow control */ #define UPF_SOFT_FLOW ((__force upf_t) BIT_ULL(22)) #define UPF_CONS_FLOW ((__force upf_t) BIT_ULL(23)) #define UPF_SHARE_IRQ ((__force upf_t) BIT_ULL(24)) #define UPF_EXAR_EFR ((__force upf_t) BIT_ULL(25)) #define UPF_BUG_THRE ((__force upf_t) BIT_ULL(26)) /* The exact UART type is known and should not be probed. */ #define UPF_FIXED_TYPE ((__force upf_t) BIT_ULL(27)) #define UPF_BOOT_AUTOCONF ((__force upf_t) BIT_ULL(28)) #define UPF_FIXED_PORT ((__force upf_t) BIT_ULL(29)) #define UPF_DEAD ((__force upf_t) BIT_ULL(30)) #define UPF_IOREMAP ((__force upf_t) BIT_ULL(31)) #define UPF_FULL_PROBE ((__force upf_t) BIT_ULL(32)) #define __UPF_CHANGE_MASK 0x17fff #define UPF_CHANGE_MASK ((__force upf_t) __UPF_CHANGE_MASK) #define UPF_USR_MASK ((__force upf_t) (UPF_SPD_MASK|UPF_LOW_LATENCY)) #if __UPF_CHANGE_MASK > ASYNC_FLAGS #error Change mask not equivalent to userspace-visible bit defines #endif /* * Must hold termios_rwsem, port mutex and port lock to change; * can hold any one lock to read. */ upstat_t status; #define UPSTAT_CTS_ENABLE ((__force upstat_t) (1 << 0)) #define UPSTAT_DCD_ENABLE ((__force upstat_t) (1 << 1)) #define UPSTAT_AUTORTS ((__force upstat_t) (1 << 2)) #define UPSTAT_AUTOCTS ((__force upstat_t) (1 << 3)) #define UPSTAT_AUTOXOFF ((__force upstat_t) (1 << 4)) #define UPSTAT_SYNC_FIFO ((__force upstat_t) (1 << 5)) bool hw_stopped; /* sw-assisted CTS flow state */ unsigned int mctrl; /* current modem ctrl settings */ unsigned int frame_time; /* frame timing in ns */ unsigned int type; /* port type */ const struct uart_ops *ops; unsigned int custom_divisor; unsigned int line; /* port index */ unsigned int minor; resource_size_t mapbase; /* for ioremap */ resource_size_t mapsize; struct device *dev; /* serial port physical parent device */ struct serial_port_device *port_dev; /* serial core port device */ unsigned long sysrq; /* sysrq timeout */ u8 sysrq_ch; /* char for sysrq */ unsigned char has_sysrq; unsigned char sysrq_seq; /* index in sysrq_toggle_seq */ unsigned char hub6; /* this should be in the 8250 driver */ unsigned char suspended; unsigned char console_reinit; const char *name; /* port name */ struct attribute_group *attr_group; /* port specific attributes */ const struct attribute_group **tty_groups; /* all attributes (serial core use only) */ struct serial_rs485 rs485; struct serial_rs485 rs485_supported; /* Supported mask for serial_rs485 */ struct gpio_desc *rs485_term_gpio; /* enable RS485 bus termination */ struct gpio_desc *rs485_rx_during_tx_gpio; /* Output GPIO that sets the state of RS485 RX during TX */ struct serial_iso7816 iso7816; void *private_data; /* generic platform data pointer */ }; /** * uart_port_lock - Lock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_lock(struct uart_port *up) { spin_lock(&up->lock); } /** * uart_port_lock_irq - Lock the UART port and disable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_lock_irq(struct uart_port *up) { spin_lock_irq(&up->lock); } /** * uart_port_lock_irqsave - Lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage */ static inline void uart_port_lock_irqsave(struct uart_port *up, unsigned long *flags) { spin_lock_irqsave(&up->lock, *flags); } /** * uart_port_trylock - Try to lock the UART port * @up: Pointer to UART port structure * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock(struct uart_port *up) { return spin_trylock(&up->lock); } /** * uart_port_trylock_irqsave - Try to lock the UART port, save and disable interrupts * @up: Pointer to UART port structure * @flags: Pointer to interrupt flags storage * * Returns: True if lock was acquired, false otherwise */ static inline bool uart_port_trylock_irqsave(struct uart_port *up, unsigned long *flags) { return spin_trylock_irqsave(&up->lock, *flags); } /** * uart_port_unlock - Unlock the UART port * @up: Pointer to UART port structure */ static inline void uart_port_unlock(struct uart_port *up) { spin_unlock(&up->lock); } /** * uart_port_unlock_irq - Unlock the UART port and re-enable interrupts * @up: Pointer to UART port structure */ static inline void uart_port_unlock_irq(struct uart_port *up) { spin_unlock_irq(&up->lock); } /** * uart_port_unlock_irqrestore - Unlock the UART port, restore interrupts * @up: Pointer to UART port structure * @flags: The saved interrupt flags for restore */ static inline void uart_port_unlock_irqrestore(struct uart_port *up, unsigned long flags) { spin_unlock_irqrestore(&up->lock, flags); } static inline int serial_port_in(struct uart_port *up, int offset) { return up->serial_in(up, offset); } static inline void serial_port_out(struct uart_port *up, int offset, int value) { up->serial_out(up, offset, value); } /** * enum uart_pm_state - power states for UARTs * @UART_PM_STATE_ON: UART is powered, up and operational * @UART_PM_STATE_OFF: UART is powered off * @UART_PM_STATE_UNDEFINED: sentinel */ enum uart_pm_state { UART_PM_STATE_ON = 0, UART_PM_STATE_OFF = 3, /* number taken from ACPI */ UART_PM_STATE_UNDEFINED, }; /* * This is the state information which is persistent across opens. */ struct uart_state { struct tty_port port; enum uart_pm_state pm_state; atomic_t refcount; wait_queue_head_t remove_wait; struct uart_port *uart_port; }; #define UART_XMIT_SIZE PAGE_SIZE /* number of characters left in xmit buffer before we ask for more */ #define WAKEUP_CHARS 256 /** * uart_xmit_advance - Advance xmit buffer and account Tx'ed chars * @up: uart_port structure describing the port * @chars: number of characters sent * * This function advances the tail of circular xmit buffer by the number of * @chars transmitted and handles accounting of transmitted bytes (into * @up's icount.tx). */ static inline void uart_xmit_advance(struct uart_port *up, unsigned int chars) { struct tty_port *tport = &up->state->port; kfifo_skip_count(&tport->xmit_fifo, chars); up->icount.tx += chars; } static inline unsigned int uart_fifo_out(struct uart_port *up, unsigned char *buf, unsigned int chars) { struct tty_port *tport = &up->state->port; chars = kfifo_out(&tport->xmit_fifo, buf, chars); up->icount.tx += chars; return chars; } static inline unsigned int uart_fifo_get(struct uart_port *up, unsigned char *ch) { struct tty_port *tport = &up->state->port; unsigned int chars; chars = kfifo_get(&tport->xmit_fifo, ch); up->icount.tx += chars; return chars; } struct module; struct tty_driver; struct uart_driver { struct module *owner; const char *driver_name; const char *dev_name; int major; int minor; int nr; struct console *cons; /* * these are private; the low level driver should not * touch these; they should be initialised to NULL */ struct uart_state *state; struct tty_driver *tty_driver; }; void uart_write_wakeup(struct uart_port *port); /** * enum UART_TX_FLAGS -- flags for uart_port_tx_flags() * * @UART_TX_NOSTOP: don't call port->ops->stop_tx() on empty buffer */ enum UART_TX_FLAGS { UART_TX_NOSTOP = BIT(0), }; #define __uart_port_tx(uport, ch, flags, tx_ready, put_char, tx_done, \ for_test, for_post) \ ({ \ struct uart_port *__port = (uport); \ struct tty_port *__tport = &__port->state->port; \ unsigned int pending; \ \ for (; (for_test) && (tx_ready); (for_post), __port->icount.tx++) { \ if (__port->x_char) { \ (ch) = __port->x_char; \ (put_char); \ __port->x_char = 0; \ continue; \ } \ \ if (uart_tx_stopped(__port)) \ break; \ \ if (!kfifo_get(&__tport->xmit_fifo, &(ch))) \ break; \ \ (put_char); \ } \ \ (tx_done); \ \ pending = kfifo_len(&__tport->xmit_fifo); \ if (pending < WAKEUP_CHARS) { \ uart_write_wakeup(__port); \ \ if (!((flags) & UART_TX_NOSTOP) && pending == 0) \ __port->ops->stop_tx(__port); \ } \ \ pending; \ }) /** * uart_port_tx_limited -- transmit helper for uart_port with count limiting * @port: uart port * @ch: variable to store a character to be written to the HW * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * This helper transmits characters from the xmit buffer to the hardware using * @put_char(). It does so until @count characters are sent and while @tx_ready * evaluates to true. * * Returns: the number of characters in the xmit buffer when done. * * The expression in macro parameters shall be designed as follows: * * **tx_ready:** should evaluate to true if the HW can accept more data to * be sent. This parameter can be %true, which means the HW is always ready. * * **put_char:** shall write @ch to the device of @port. * * **tx_done:** when the write loop is done, this can perform arbitrary * action before potential invocation of ops->stop_tx() happens. If the * driver does not need to do anything, use e.g. ({}). * * For all of them, @port->lock is held, interrupts are locally disabled and * the expressions must not sleep. */ #define uart_port_tx_limited(port, ch, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, 0, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx_limited_flags -- transmit helper for uart_port with count limiting with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @count: a limit of characters to send * @tx_ready: can HW accept more data function * @put_char: function to write a character * @tx_done: function to call after the loop is done * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_limited_flags(port, ch, flags, count, tx_ready, put_char, tx_done) ({ \ unsigned int __count = (count); \ __uart_port_tx(port, ch, flags, tx_ready, put_char, tx_done, __count, \ __count--); \ }) /** * uart_port_tx -- transmit helper for uart_port * @port: uart port * @ch: variable to store a character to be written to the HW * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx(port, ch, tx_ready, put_char) \ __uart_port_tx(port, ch, 0, tx_ready, put_char, ({}), true, ({})) /** * uart_port_tx_flags -- transmit helper for uart_port with flags * @port: uart port * @ch: variable to store a character to be written to the HW * @flags: %UART_TX_NOSTOP or similar * @tx_ready: can HW accept more data function * @put_char: function to write a character * * See uart_port_tx_limited() for more details. */ #define uart_port_tx_flags(port, ch, flags, tx_ready, put_char) \ __uart_port_tx(port, ch, flags, tx_ready, put_char, ({}), true, ({})) /* * Baud rate helpers. */ void uart_update_timeout(struct uart_port *port, unsigned int cflag, unsigned int baud); unsigned int uart_get_baud_rate(struct uart_port *port, struct ktermios *termios, const struct ktermios *old, unsigned int min, unsigned int max); unsigned int uart_get_divisor(struct uart_port *port, unsigned int baud); /* * Calculates FIFO drain time. */ static inline unsigned long uart_fifo_timeout(struct uart_port *port) { u64 fifo_timeout = (u64)READ_ONCE(port->frame_time) * port->fifosize; /* Add .02 seconds of slop */ fifo_timeout += 20 * NSEC_PER_MSEC; return max(nsecs_to_jiffies(fifo_timeout), 1UL); } /* Base timer interval for polling */ static inline unsigned long uart_poll_timeout(struct uart_port *port) { unsigned long timeout = uart_fifo_timeout(port); return timeout > 6 ? (timeout / 2 - 2) : 1; } /* * Console helpers. */ struct earlycon_device { struct console *con; struct uart_port port; char options[32]; /* e.g., 115200n8 */ unsigned int baud; }; struct earlycon_id { char name[15]; char name_term; /* In case compiler didn't '\0' term name */ char compatible[128]; int (*setup)(struct earlycon_device *, const char *options); }; extern const struct earlycon_id __earlycon_table[]; extern const struct earlycon_id __earlycon_table_end[]; #if defined(CONFIG_SERIAL_EARLYCON) && !defined(MODULE) #define EARLYCON_USED_OR_UNUSED __used #else #define EARLYCON_USED_OR_UNUSED __maybe_unused #endif #define OF_EARLYCON_DECLARE(_name, compat, fn) \ static const struct earlycon_id __UNIQUE_ID(__earlycon_##_name) \ EARLYCON_USED_OR_UNUSED __section("__earlycon_table") \ __aligned(__alignof__(struct earlycon_id)) \ = { .name = __stringify(_name), \ .compatible = compat, \ .setup = fn } #define EARLYCON_DECLARE(_name, fn) OF_EARLYCON_DECLARE(_name, "", fn) int of_setup_earlycon(const struct earlycon_id *match, unsigned long node, const char *options); #ifdef CONFIG_SERIAL_EARLYCON extern bool earlycon_acpi_spcr_enable __initdata; int setup_earlycon(char *buf); #else static const bool earlycon_acpi_spcr_enable EARLYCON_USED_OR_UNUSED; static inline int setup_earlycon(char *buf) { return 0; } #endif /* Variant of uart_console_registered() when the console_list_lock is held. */ static inline bool uart_console_registered_locked(struct uart_port *port) { return uart_console(port) && console_is_registered_locked(port->cons); } static inline bool uart_console_registered(struct uart_port *port) { return uart_console(port) && console_is_registered(port->cons); } struct uart_port *uart_get_console(struct uart_port *ports, int nr, struct console *c); int uart_parse_earlycon(char *p, unsigned char *iotype, resource_size_t *addr, char **options); void uart_parse_options(const char *options, int *baud, int *parity, int *bits, int *flow); int uart_set_options(struct uart_port *port, struct console *co, int baud, int parity, int bits, int flow); struct tty_driver *uart_console_device(struct console *co, int *index); void uart_console_write(struct uart_port *port, const char *s, unsigned int count, void (*putchar)(struct uart_port *, unsigned char)); /* * Port/driver registration/removal */ int uart_register_driver(struct uart_driver *uart); void uart_unregister_driver(struct uart_driver *uart); int uart_add_one_port(struct uart_driver *reg, struct uart_port *port); void uart_remove_one_port(struct uart_driver *reg, struct uart_port *port); int uart_read_port_properties(struct uart_port *port); int uart_read_and_validate_port_properties(struct uart_port *port); bool uart_match_port(const struct uart_port *port1, const struct uart_port *port2); /* * Power Management */ int uart_suspend_port(struct uart_driver *reg, struct uart_port *port); int uart_resume_port(struct uart_driver *reg, struct uart_port *port); static inline int uart_tx_stopped(struct uart_port *port) { struct tty_struct *tty = port->state->port.tty; if ((tty && tty->flow.stopped) || port->hw_stopped) return 1; return 0; } static inline bool uart_cts_enabled(struct uart_port *uport) { return !!(uport->status & UPSTAT_CTS_ENABLE); } static inline bool uart_softcts_mode(struct uart_port *uport) { upstat_t mask = UPSTAT_CTS_ENABLE | UPSTAT_AUTOCTS; return ((uport->status & mask) == UPSTAT_CTS_ENABLE); } /* * The following are helper functions for the low level drivers. */ void uart_handle_dcd_change(struct uart_port *uport, bool active); void uart_handle_cts_change(struct uart_port *uport, bool active); void uart_insert_char(struct uart_port *port, unsigned int status, unsigned int overrun, u8 ch, u8 flag); void uart_xchar_out(struct uart_port *uport, int offset); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL #define SYSRQ_TIMEOUT (HZ * 5) bool uart_try_toggle_sysrq(struct uart_port *port, u8 ch); static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { handle_sysrq(ch); port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { if (!port->sysrq) return 0; if (ch && time_before(jiffies, port->sysrq)) { if (sysrq_mask()) { port->sysrq_ch = ch; port->sysrq = 0; return 1; } if (uart_try_toggle_sysrq(port, ch)) return 1; } port->sysrq = 0; return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock(port); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock(port); if (sysrq_ch) handle_sysrq(sysrq_ch); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { u8 sysrq_ch; if (!port->has_sysrq) { uart_port_unlock_irqrestore(port, flags); return; } sysrq_ch = port->sysrq_ch; port->sysrq_ch = 0; uart_port_unlock_irqrestore(port, flags); if (sysrq_ch) handle_sysrq(sysrq_ch); } #else /* CONFIG_MAGIC_SYSRQ_SERIAL */ static inline int uart_handle_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline int uart_prepare_sysrq_char(struct uart_port *port, u8 ch) { return 0; } static inline void uart_unlock_and_check_sysrq(struct uart_port *port) { uart_port_unlock(port); } static inline void uart_unlock_and_check_sysrq_irqrestore(struct uart_port *port, unsigned long flags) { uart_port_unlock_irqrestore(port, flags); } #endif /* CONFIG_MAGIC_SYSRQ_SERIAL */ /* * We do the SysRQ and SAK checking like this... */ static inline int uart_handle_break(struct uart_port *port) { struct uart_state *state = port->state; if (port->handle_break) port->handle_break(port); #ifdef CONFIG_MAGIC_SYSRQ_SERIAL if (port->has_sysrq && uart_console(port)) { if (!port->sysrq) { port->sysrq = jiffies + SYSRQ_TIMEOUT; return 1; } port->sysrq = 0; } #endif if (port->flags & UPF_SAK) do_SAK(state->port.tty); return 0; } /* * UART_ENABLE_MS - determine if port should enable modem status irqs */ #define UART_ENABLE_MS(port,cflag) ((port)->flags & UPF_HARDPPS_CD || \ (cflag) & CRTSCTS || \ !((cflag) & CLOCAL)) int uart_get_rs485_mode(struct uart_port *port); #endif /* LINUX_SERIAL_CORE_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 | // SPDX-License-Identifier: GPL-2.0 /* * lib/smp_processor_id.c * * DEBUG_PREEMPT variant of smp_processor_id(). */ #include <linux/export.h> #include <linux/kprobes.h> #include <linux/sched.h> noinstr static unsigned int check_preemption_disabled(const char *what1, const char *what2) { int this_cpu = raw_smp_processor_id(); if (likely(preempt_count())) goto out; if (irqs_disabled()) goto out; if (is_percpu_thread()) goto out; #ifdef CONFIG_SMP if (current->migration_disabled) goto out; #endif /* * It is valid to assume CPU-locality during early bootup: */ if (system_state < SYSTEM_SCHEDULING) goto out; /* * Avoid recursion: */ preempt_disable_notrace(); instrumentation_begin(); if (!printk_ratelimit()) goto out_enable; printk(KERN_ERR "BUG: using %s%s() in preemptible [%08x] code: %s/%d\n", what1, what2, preempt_count() - 1, current->comm, current->pid); printk("caller is %pS\n", __builtin_return_address(0)); dump_stack(); out_enable: instrumentation_end(); preempt_enable_no_resched_notrace(); out: return this_cpu; } noinstr unsigned int debug_smp_processor_id(void) { return check_preemption_disabled("smp_processor_id", ""); } EXPORT_SYMBOL(debug_smp_processor_id); noinstr void __this_cpu_preempt_check(const char *op) { check_preemption_disabled("__this_cpu_", op); } EXPORT_SYMBOL(__this_cpu_preempt_check); |
| 11 11 11 11 11 11 11 11 11 11 11 10 10 10 10 10 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 | // SPDX-License-Identifier: GPL-2.0 /* * arch/arm64/kvm/fpsimd.c: Guest/host FPSIMD context coordination helpers * * Copyright 2018 Arm Limited * Author: Dave Martin <Dave.Martin@arm.com> */ #include <linux/irqflags.h> #include <linux/sched.h> #include <linux/kvm_host.h> #include <asm/fpsimd.h> #include <asm/kvm_asm.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/sysreg.h> /* * Called on entry to KVM_RUN unless this vcpu previously ran at least * once and the most recent prior KVM_RUN for this vcpu was called from * the same task as current (highly likely). * * This is guaranteed to execute before kvm_arch_vcpu_load_fp(vcpu), * such that on entering hyp the relevant parts of current are already * mapped. */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu) { struct user_fpsimd_state *fpsimd = ¤t->thread.uw.fpsimd_state; int ret; /* pKVM has its own tracking of the host fpsimd state. */ if (is_protected_kvm_enabled()) return 0; /* Make sure the host task fpsimd state is visible to hyp: */ ret = kvm_share_hyp(fpsimd, fpsimd + 1); if (ret) return ret; return 0; } /* * Prepare vcpu for saving the host's FPSIMD state and loading the guest's. * The actual loading is done by the FPSIMD access trap taken to hyp. * * Here, we just set the correct metadata to indicate that the FPSIMD * state in the cpu regs (if any) belongs to current on the host. */ void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu) { BUG_ON(!current->mm); if (!system_supports_fpsimd()) return; fpsimd_kvm_prepare(); /* * We will check TIF_FOREIGN_FPSTATE just before entering the * guest in kvm_arch_vcpu_ctxflush_fp() and override this to * FP_STATE_FREE if the flag set. */ *host_data_ptr(fp_owner) = FP_STATE_HOST_OWNED; *host_data_ptr(fpsimd_state) = kern_hyp_va(¤t->thread.uw.fpsimd_state); vcpu_clear_flag(vcpu, HOST_SVE_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_ZEN_EL0EN) vcpu_set_flag(vcpu, HOST_SVE_ENABLED); if (system_supports_sme()) { vcpu_clear_flag(vcpu, HOST_SME_ENABLED); if (read_sysreg(cpacr_el1) & CPACR_EL1_SMEN_EL0EN) vcpu_set_flag(vcpu, HOST_SME_ENABLED); /* * If PSTATE.SM is enabled then save any pending FP * state and disable PSTATE.SM. If we leave PSTATE.SM * enabled and the guest does not enable SME via * CPACR_EL1.SMEN then operations that should be valid * may generate SME traps from EL1 to EL1 which we * can't intercept and which would confuse the guest. * * Do the same for PSTATE.ZA in the case where there * is state in the registers which has not already * been saved, this is very unlikely to happen. */ if (read_sysreg_s(SYS_SVCR) & (SVCR_SM_MASK | SVCR_ZA_MASK)) { *host_data_ptr(fp_owner) = FP_STATE_FREE; fpsimd_save_and_flush_cpu_state(); } } /* * If normal guests gain SME support, maintain this behavior for pKVM * guests, which don't support SME. */ WARN_ON(is_protected_kvm_enabled() && system_supports_sme() && read_sysreg_s(SYS_SVCR)); } /* * Called just before entering the guest once we are no longer preemptible * and interrupts are disabled. If we have managed to run anything using * FP while we were preemptible (such as off the back of an interrupt), * then neither the host nor the guest own the FP hardware (and it was the * responsibility of the code that used FP to save the existing state). */ void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu) { if (test_thread_flag(TIF_FOREIGN_FPSTATE)) *host_data_ptr(fp_owner) = FP_STATE_FREE; } /* * Called just after exiting the guest. If the guest FPSIMD state * was loaded, update the host's context tracking data mark the CPU * FPSIMD regs as dirty and belonging to vcpu so that they will be * written back if the kernel clobbers them due to kernel-mode NEON * before re-entry into the guest. */ void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu) { struct cpu_fp_state fp_state; WARN_ON_ONCE(!irqs_disabled()); if (guest_owns_fp_regs()) { /* * Currently we do not support SME guests so SVCR is * always 0 and we just need a variable to point to. */ fp_state.st = &vcpu->arch.ctxt.fp_regs; fp_state.sve_state = vcpu->arch.sve_state; fp_state.sve_vl = vcpu->arch.sve_max_vl; fp_state.sme_state = NULL; fp_state.svcr = &vcpu->arch.svcr; fp_state.fpmr = &vcpu->arch.fpmr; fp_state.fp_type = &vcpu->arch.fp_type; if (vcpu_has_sve(vcpu)) fp_state.to_save = FP_STATE_SVE; else fp_state.to_save = FP_STATE_FPSIMD; fpsimd_bind_state_to_cpu(&fp_state); clear_thread_flag(TIF_FOREIGN_FPSTATE); } } /* * Write back the vcpu FPSIMD regs if they are dirty, and invalidate the * cpu FPSIMD regs so that they can't be spuriously reused if this vcpu * disappears and another task or vcpu appears that recycles the same * struct fpsimd_state. */ void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu) { unsigned long flags; local_irq_save(flags); /* * If we have VHE then the Hyp code will reset CPACR_EL1 to * the default value and we need to reenable SME. */ if (has_vhe() && system_supports_sme()) { /* Also restore EL0 state seen on entry */ if (vcpu_get_flag(vcpu, HOST_SME_ENABLED)) sysreg_clear_set(CPACR_EL1, 0, CPACR_ELx_SMEN); else sysreg_clear_set(CPACR_EL1, CPACR_EL1_SMEN_EL0EN, CPACR_EL1_SMEN_EL1EN); isb(); } if (guest_owns_fp_regs()) { if (vcpu_has_sve(vcpu)) { u64 zcr = read_sysreg_el1(SYS_ZCR); /* * If the vCPU is in the hyp context then ZCR_EL1 is * loaded with its vEL2 counterpart. */ __vcpu_sys_reg(vcpu, vcpu_sve_zcr_elx(vcpu)) = zcr; /* * Restore the VL that was saved when bound to the CPU, * which is the maximum VL for the guest. Because the * layout of the data when saving the sve state depends * on the VL, we need to use a consistent (i.e., the * maximum) VL. * Note that this means that at guest exit ZCR_EL1 is * not necessarily the same as on guest entry. * * ZCR_EL2 holds the guest hypervisor's VL when running * a nested guest, which could be smaller than the * max for the vCPU. Similar to above, we first need to * switch to a VL consistent with the layout of the * vCPU's SVE state. KVM support for NV implies VHE, so * using the ZCR_EL1 alias is safe. */ if (!has_vhe() || (vcpu_has_nv(vcpu) && !is_hyp_ctxt(vcpu))) sve_cond_update_zcr_vq(vcpu_sve_max_vq(vcpu) - 1, SYS_ZCR_EL1); } /* * Flush (save and invalidate) the fpsimd/sve state so that if * the host tries to use fpsimd/sve, it's not using stale data * from the guest. * * Flushing the state sets the TIF_FOREIGN_FPSTATE bit for the * context unconditionally, in both nVHE and VHE. This allows * the kernel to restore the fpsimd/sve state, including ZCR_EL1 * when needed. */ fpsimd_save_and_flush_cpu_state(); } else if (has_vhe() && system_supports_sve()) { /* * The FPSIMD/SVE state in the CPU has not been touched, and we * have SVE (and VHE): CPACR_EL1 (alias CPTR_EL2) has been * reset by kvm_reset_cptr_el2() in the Hyp code, disabling SVE * for EL0. To avoid spurious traps, restore the trap state * seen by kvm_arch_vcpu_load_fp(): */ if (vcpu_get_flag(vcpu, HOST_SVE_ENABLED)) sysreg_clear_set(CPACR_EL1, 0, CPACR_EL1_ZEN_EL0EN); else sysreg_clear_set(CPACR_EL1, CPACR_EL1_ZEN_EL0EN, 0); } local_irq_restore(flags); } |
| 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* auditfilter.c -- filtering of audit events * * Copyright 2003-2004 Red Hat, Inc. * Copyright 2005 Hewlett-Packard Development Company, L.P. * Copyright 2005 IBM Corporation */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/audit.h> #include <linux/kthread.h> #include <linux/mutex.h> #include <linux/fs.h> #include <linux/namei.h> #include <linux/netlink.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <net/net_namespace.h> #include <net/sock.h> #include "audit.h" /* * Locking model: * * audit_filter_mutex: * Synchronizes writes and blocking reads of audit's filterlist * data. Rcu is used to traverse the filterlist and access * contents of structs audit_entry, audit_watch and opaque * LSM rules during filtering. If modified, these structures * must be copied and replace their counterparts in the filterlist. * An audit_parent struct is not accessed during filtering, so may * be written directly provided audit_filter_mutex is held. */ /* Audit filter lists, defined in <linux/audit.h> */ struct list_head audit_filter_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_filter_list[0]), LIST_HEAD_INIT(audit_filter_list[1]), LIST_HEAD_INIT(audit_filter_list[2]), LIST_HEAD_INIT(audit_filter_list[3]), LIST_HEAD_INIT(audit_filter_list[4]), LIST_HEAD_INIT(audit_filter_list[5]), LIST_HEAD_INIT(audit_filter_list[6]), LIST_HEAD_INIT(audit_filter_list[7]), #if AUDIT_NR_FILTERS != 8 #error Fix audit_filter_list initialiser #endif }; static struct list_head audit_rules_list[AUDIT_NR_FILTERS] = { LIST_HEAD_INIT(audit_rules_list[0]), LIST_HEAD_INIT(audit_rules_list[1]), LIST_HEAD_INIT(audit_rules_list[2]), LIST_HEAD_INIT(audit_rules_list[3]), LIST_HEAD_INIT(audit_rules_list[4]), LIST_HEAD_INIT(audit_rules_list[5]), LIST_HEAD_INIT(audit_rules_list[6]), LIST_HEAD_INIT(audit_rules_list[7]), }; DEFINE_MUTEX(audit_filter_mutex); static void audit_free_lsm_field(struct audit_field *f) { switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: kfree(f->lsm_str); security_audit_rule_free(f->lsm_rule); } } static inline void audit_free_rule(struct audit_entry *e) { int i; struct audit_krule *erule = &e->rule; /* some rules don't have associated watches */ if (erule->watch) audit_put_watch(erule->watch); if (erule->fields) for (i = 0; i < erule->field_count; i++) audit_free_lsm_field(&erule->fields[i]); kfree(erule->fields); kfree(erule->filterkey); kfree(e); } void audit_free_rule_rcu(struct rcu_head *head) { struct audit_entry *e = container_of(head, struct audit_entry, rcu); audit_free_rule(e); } /* Initialize an audit filterlist entry. */ static inline struct audit_entry *audit_init_entry(u32 field_count) { struct audit_entry *entry; struct audit_field *fields; entry = kzalloc(sizeof(*entry), GFP_KERNEL); if (unlikely(!entry)) return NULL; fields = kcalloc(field_count, sizeof(*fields), GFP_KERNEL); if (unlikely(!fields)) { kfree(entry); return NULL; } entry->rule.fields = fields; return entry; } /* Unpack a filter field's string representation from user-space * buffer. */ char *audit_unpack_string(void **bufp, size_t *remain, size_t len) { char *str; if (!*bufp || (len == 0) || (len > *remain)) return ERR_PTR(-EINVAL); /* Of the currently implemented string fields, PATH_MAX * defines the longest valid length. */ if (len > PATH_MAX) return ERR_PTR(-ENAMETOOLONG); str = kmalloc(len + 1, GFP_KERNEL); if (unlikely(!str)) return ERR_PTR(-ENOMEM); memcpy(str, *bufp, len); str[len] = 0; *bufp += len; *remain -= len; return str; } /* Translate an inode field to kernel representation. */ static inline int audit_to_inode(struct audit_krule *krule, struct audit_field *f) { if ((krule->listnr != AUDIT_FILTER_EXIT && krule->listnr != AUDIT_FILTER_URING_EXIT) || krule->inode_f || krule->watch || krule->tree || (f->op != Audit_equal && f->op != Audit_not_equal)) return -EINVAL; krule->inode_f = f; return 0; } static __u32 *classes[AUDIT_SYSCALL_CLASSES]; int __init audit_register_class(int class, unsigned *list) { __u32 *p = kcalloc(AUDIT_BITMASK_SIZE, sizeof(__u32), GFP_KERNEL); if (!p) return -ENOMEM; while (*list != ~0U) { unsigned n = *list++; if (n >= AUDIT_BITMASK_SIZE * 32 - AUDIT_SYSCALL_CLASSES) { kfree(p); return -EINVAL; } p[AUDIT_WORD(n)] |= AUDIT_BIT(n); } if (class >= AUDIT_SYSCALL_CLASSES || classes[class]) { kfree(p); return -EINVAL; } classes[class] = p; return 0; } int audit_match_class(int class, unsigned syscall) { if (unlikely(syscall >= AUDIT_BITMASK_SIZE * 32)) return 0; if (unlikely(class >= AUDIT_SYSCALL_CLASSES || !classes[class])) return 0; return classes[class][AUDIT_WORD(syscall)] & AUDIT_BIT(syscall); } #ifdef CONFIG_AUDITSYSCALL static inline int audit_match_class_bits(int class, u32 *mask) { int i; if (classes[class]) { for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (mask[i] & classes[class][i]) return 0; } return 1; } static int audit_match_signal(struct audit_entry *entry) { struct audit_field *arch = entry->rule.arch_f; if (!arch) { /* When arch is unspecified, we must check both masks on biarch * as syscall number alone is ambiguous. */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask) && audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); } switch (audit_classify_arch(arch->val)) { case 0: /* native */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL, entry->rule.mask)); case 1: /* 32bit on biarch */ return (audit_match_class_bits(AUDIT_CLASS_SIGNAL_32, entry->rule.mask)); default: return 1; } } #endif /* Common user-space to kernel rule translation. */ static inline struct audit_entry *audit_to_entry_common(struct audit_rule_data *rule) { unsigned listnr; struct audit_entry *entry; int i, err; err = -EINVAL; listnr = rule->flags & ~AUDIT_FILTER_PREPEND; switch (listnr) { default: goto exit_err; #ifdef CONFIG_AUDITSYSCALL case AUDIT_FILTER_ENTRY: pr_err("AUDIT_FILTER_ENTRY is deprecated\n"); goto exit_err; case AUDIT_FILTER_EXIT: case AUDIT_FILTER_URING_EXIT: case AUDIT_FILTER_TASK: #endif case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: ; } if (unlikely(rule->action == AUDIT_POSSIBLE)) { pr_err("AUDIT_POSSIBLE is deprecated\n"); goto exit_err; } if (rule->action != AUDIT_NEVER && rule->action != AUDIT_ALWAYS) goto exit_err; if (rule->field_count > AUDIT_MAX_FIELDS) goto exit_err; err = -ENOMEM; entry = audit_init_entry(rule->field_count); if (!entry) goto exit_err; entry->rule.flags = rule->flags & AUDIT_FILTER_PREPEND; entry->rule.listnr = listnr; entry->rule.action = rule->action; entry->rule.field_count = rule->field_count; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) entry->rule.mask[i] = rule->mask[i]; for (i = 0; i < AUDIT_SYSCALL_CLASSES; i++) { int bit = AUDIT_BITMASK_SIZE * 32 - i - 1; __u32 *p = &entry->rule.mask[AUDIT_WORD(bit)]; __u32 *class; if (!(*p & AUDIT_BIT(bit))) continue; *p &= ~AUDIT_BIT(bit); class = classes[i]; if (class) { int j; for (j = 0; j < AUDIT_BITMASK_SIZE; j++) entry->rule.mask[j] |= class[j]; } } return entry; exit_err: return ERR_PTR(err); } static u32 audit_ops[] = { [Audit_equal] = AUDIT_EQUAL, [Audit_not_equal] = AUDIT_NOT_EQUAL, [Audit_bitmask] = AUDIT_BIT_MASK, [Audit_bittest] = AUDIT_BIT_TEST, [Audit_lt] = AUDIT_LESS_THAN, [Audit_gt] = AUDIT_GREATER_THAN, [Audit_le] = AUDIT_LESS_THAN_OR_EQUAL, [Audit_ge] = AUDIT_GREATER_THAN_OR_EQUAL, }; static u32 audit_to_op(u32 op) { u32 n; for (n = Audit_equal; n < Audit_bad && audit_ops[n] != op; n++) ; return n; } /* check if an audit field is valid */ static int audit_field_valid(struct audit_entry *entry, struct audit_field *f) { switch (f->type) { case AUDIT_MSGTYPE: if (entry->rule.listnr != AUDIT_FILTER_EXCLUDE && entry->rule.listnr != AUDIT_FILTER_USER) return -EINVAL; break; case AUDIT_FSTYPE: if (entry->rule.listnr != AUDIT_FILTER_FS) return -EINVAL; break; case AUDIT_PERM: if (entry->rule.listnr == AUDIT_FILTER_URING_EXIT) return -EINVAL; break; } switch (entry->rule.listnr) { case AUDIT_FILTER_FS: switch (f->type) { case AUDIT_FSTYPE: case AUDIT_FILTERKEY: break; default: return -EINVAL; } } /* Check for valid field type and op */ switch (f->type) { case AUDIT_ARG0: case AUDIT_ARG1: case AUDIT_ARG2: case AUDIT_ARG3: case AUDIT_PERS: /* <uapi/linux/personality.h> */ case AUDIT_DEVMINOR: /* all ops are valid */ break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: case AUDIT_PID: case AUDIT_MSGTYPE: case AUDIT_PPID: case AUDIT_DEVMAJOR: case AUDIT_EXIT: case AUDIT_SUCCESS: case AUDIT_INODE: case AUDIT_SESSIONID: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: case AUDIT_SADDR_FAM: /* bit ops are only useful on syscall args */ if (f->op == Audit_bitmask || f->op == Audit_bittest) return -EINVAL; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_WATCH: case AUDIT_DIR: case AUDIT_FILTERKEY: case AUDIT_LOGINUID_SET: case AUDIT_ARCH: case AUDIT_FSTYPE: case AUDIT_PERM: case AUDIT_FILETYPE: case AUDIT_FIELD_COMPARE: case AUDIT_EXE: /* only equal and not equal valid ops */ if (f->op != Audit_not_equal && f->op != Audit_equal) return -EINVAL; break; default: /* field not recognized */ return -EINVAL; } /* Check for select valid field values */ switch (f->type) { case AUDIT_LOGINUID_SET: if ((f->val != 0) && (f->val != 1)) return -EINVAL; break; case AUDIT_PERM: if (f->val & ~15) return -EINVAL; break; case AUDIT_FILETYPE: if (f->val & ~S_IFMT) return -EINVAL; break; case AUDIT_FIELD_COMPARE: if (f->val > AUDIT_MAX_FIELD_COMPARE) return -EINVAL; break; case AUDIT_SADDR_FAM: if (f->val >= AF_MAX) return -EINVAL; break; default: break; } return 0; } /* Translate struct audit_rule_data to kernel's rule representation. */ static struct audit_entry *audit_data_to_entry(struct audit_rule_data *data, size_t datasz) { int err = 0; struct audit_entry *entry; void *bufp; size_t remain = datasz - sizeof(struct audit_rule_data); int i; char *str; struct audit_fsnotify_mark *audit_mark; entry = audit_to_entry_common(data); if (IS_ERR(entry)) goto exit_nofree; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &entry->rule.fields[i]; u32 f_val; err = -EINVAL; f->op = audit_to_op(data->fieldflags[i]); if (f->op == Audit_bad) goto exit_free; f->type = data->fields[i]; f_val = data->values[i]; /* Support legacy tests for a valid loginuid */ if ((f->type == AUDIT_LOGINUID) && (f_val == AUDIT_UID_UNSET)) { f->type = AUDIT_LOGINUID_SET; f_val = 0; entry->rule.pflags |= AUDIT_LOGINUID_LEGACY; } err = audit_field_valid(entry, f); if (err) goto exit_free; err = -EINVAL; switch (f->type) { case AUDIT_LOGINUID: case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_OBJ_UID: f->uid = make_kuid(current_user_ns(), f_val); if (!uid_valid(f->uid)) goto exit_free; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: f->gid = make_kgid(current_user_ns(), f_val); if (!gid_valid(f->gid)) goto exit_free; break; case AUDIT_ARCH: f->val = f_val; entry->rule.arch_f = f; break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; f->lsm_str = str; err = security_audit_rule_init(f->type, f->op, str, (void **)&f->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (err == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", str); err = 0; } else if (err) goto exit_free; break; case AUDIT_WATCH: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_to_watch(&entry->rule, str, f_val, f->op); if (err) { kfree(str); goto exit_free; } entry->rule.buflen += f_val; break; case AUDIT_DIR: str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } err = audit_make_tree(&entry->rule, str, f->op); kfree(str); if (err) goto exit_free; entry->rule.buflen += f_val; break; case AUDIT_INODE: f->val = f_val; err = audit_to_inode(&entry->rule, f); if (err) goto exit_free; break; case AUDIT_FILTERKEY: if (entry->rule.filterkey || f_val > AUDIT_MAX_KEY_LEN) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } entry->rule.buflen += f_val; entry->rule.filterkey = str; break; case AUDIT_EXE: if (entry->rule.exe || f_val > PATH_MAX) goto exit_free; str = audit_unpack_string(&bufp, &remain, f_val); if (IS_ERR(str)) { err = PTR_ERR(str); goto exit_free; } audit_mark = audit_alloc_mark(&entry->rule, str, f_val); if (IS_ERR(audit_mark)) { kfree(str); err = PTR_ERR(audit_mark); goto exit_free; } entry->rule.buflen += f_val; entry->rule.exe = audit_mark; break; default: f->val = f_val; break; } } if (entry->rule.inode_f && entry->rule.inode_f->op == Audit_not_equal) entry->rule.inode_f = NULL; exit_nofree: return entry; exit_free: if (entry->rule.tree) audit_put_tree(entry->rule.tree); /* that's the temporary one */ if (entry->rule.exe) audit_remove_mark(entry->rule.exe); /* that's the template one */ audit_free_rule(entry); return ERR_PTR(err); } /* Pack a filter field's string representation into data block. */ static inline size_t audit_pack_string(void **bufp, const char *str) { size_t len = strlen(str); memcpy(*bufp, str, len); *bufp += len; return len; } /* Translate kernel rule representation to struct audit_rule_data. */ static struct audit_rule_data *audit_krule_to_data(struct audit_krule *krule) { struct audit_rule_data *data; void *bufp; int i; data = kmalloc(struct_size(data, buf, krule->buflen), GFP_KERNEL); if (unlikely(!data)) return NULL; memset(data, 0, sizeof(*data)); data->flags = krule->flags | krule->listnr; data->action = krule->action; data->field_count = krule->field_count; bufp = data->buf; for (i = 0; i < data->field_count; i++) { struct audit_field *f = &krule->fields[i]; data->fields[i] = f->type; data->fieldflags[i] = audit_ops[f->op]; switch (f->type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: data->buflen += data->values[i] = audit_pack_string(&bufp, f->lsm_str); break; case AUDIT_WATCH: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_watch_path(krule->watch)); break; case AUDIT_DIR: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_tree_path(krule->tree)); break; case AUDIT_FILTERKEY: data->buflen += data->values[i] = audit_pack_string(&bufp, krule->filterkey); break; case AUDIT_EXE: data->buflen += data->values[i] = audit_pack_string(&bufp, audit_mark_path(krule->exe)); break; case AUDIT_LOGINUID_SET: if (krule->pflags & AUDIT_LOGINUID_LEGACY && !f->val) { data->fields[i] = AUDIT_LOGINUID; data->values[i] = AUDIT_UID_UNSET; break; } fallthrough; /* if set */ default: data->values[i] = f->val; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) data->mask[i] = krule->mask[i]; return data; } /* Compare two rules in kernel format. Considered success if rules * don't match. */ static int audit_compare_rule(struct audit_krule *a, struct audit_krule *b) { int i; if (a->flags != b->flags || a->pflags != b->pflags || a->listnr != b->listnr || a->action != b->action || a->field_count != b->field_count) return 1; for (i = 0; i < a->field_count; i++) { if (a->fields[i].type != b->fields[i].type || a->fields[i].op != b->fields[i].op) return 1; switch (a->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: if (strcmp(a->fields[i].lsm_str, b->fields[i].lsm_str)) return 1; break; case AUDIT_WATCH: if (strcmp(audit_watch_path(a->watch), audit_watch_path(b->watch))) return 1; break; case AUDIT_DIR: if (strcmp(audit_tree_path(a->tree), audit_tree_path(b->tree))) return 1; break; case AUDIT_FILTERKEY: /* both filterkeys exist based on above type compare */ if (strcmp(a->filterkey, b->filterkey)) return 1; break; case AUDIT_EXE: /* both paths exist based on above type compare */ if (strcmp(audit_mark_path(a->exe), audit_mark_path(b->exe))) return 1; break; case AUDIT_UID: case AUDIT_EUID: case AUDIT_SUID: case AUDIT_FSUID: case AUDIT_LOGINUID: case AUDIT_OBJ_UID: if (!uid_eq(a->fields[i].uid, b->fields[i].uid)) return 1; break; case AUDIT_GID: case AUDIT_EGID: case AUDIT_SGID: case AUDIT_FSGID: case AUDIT_OBJ_GID: if (!gid_eq(a->fields[i].gid, b->fields[i].gid)) return 1; break; default: if (a->fields[i].val != b->fields[i].val) return 1; } } for (i = 0; i < AUDIT_BITMASK_SIZE; i++) if (a->mask[i] != b->mask[i]) return 1; return 0; } /* Duplicate LSM field information. The lsm_rule is opaque, so must be * re-initialized. */ static inline int audit_dupe_lsm_field(struct audit_field *df, struct audit_field *sf) { int ret; char *lsm_str; /* our own copy of lsm_str */ lsm_str = kstrdup(sf->lsm_str, GFP_KERNEL); if (unlikely(!lsm_str)) return -ENOMEM; df->lsm_str = lsm_str; /* our own (refreshed) copy of lsm_rule */ ret = security_audit_rule_init(df->type, df->op, df->lsm_str, (void **)&df->lsm_rule, GFP_KERNEL); /* Keep currently invalid fields around in case they * become valid after a policy reload. */ if (ret == -EINVAL) { pr_warn("audit rule for LSM \'%s\' is invalid\n", df->lsm_str); ret = 0; } return ret; } /* Duplicate an audit rule. This will be a deep copy with the exception * of the watch - that pointer is carried over. The LSM specific fields * will be updated in the copy. The point is to be able to replace the old * rule with the new rule in the filterlist, then free the old rule. * The rlist element is undefined; list manipulations are handled apart from * the initial copy. */ struct audit_entry *audit_dupe_rule(struct audit_krule *old) { u32 fcount = old->field_count; struct audit_entry *entry; struct audit_krule *new; char *fk; int i, err = 0; entry = audit_init_entry(fcount); if (unlikely(!entry)) return ERR_PTR(-ENOMEM); new = &entry->rule; new->flags = old->flags; new->pflags = old->pflags; new->listnr = old->listnr; new->action = old->action; for (i = 0; i < AUDIT_BITMASK_SIZE; i++) new->mask[i] = old->mask[i]; new->prio = old->prio; new->buflen = old->buflen; new->inode_f = old->inode_f; new->field_count = old->field_count; /* * note that we are OK with not refcounting here; audit_match_tree() * never dereferences tree and we can't get false positives there * since we'd have to have rule gone from the list *and* removed * before the chunks found by lookup had been allocated, i.e. before * the beginning of list scan. */ new->tree = old->tree; memcpy(new->fields, old->fields, sizeof(struct audit_field) * fcount); /* deep copy this information, updating the lsm_rule fields, because * the originals will all be freed when the old rule is freed. */ for (i = 0; i < fcount; i++) { switch (new->fields[i].type) { case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: case AUDIT_OBJ_USER: case AUDIT_OBJ_ROLE: case AUDIT_OBJ_TYPE: case AUDIT_OBJ_LEV_LOW: case AUDIT_OBJ_LEV_HIGH: err = audit_dupe_lsm_field(&new->fields[i], &old->fields[i]); break; case AUDIT_FILTERKEY: fk = kstrdup(old->filterkey, GFP_KERNEL); if (unlikely(!fk)) err = -ENOMEM; else new->filterkey = fk; break; case AUDIT_EXE: err = audit_dupe_exe(new, old); break; } if (err) { if (new->exe) audit_remove_mark(new->exe); audit_free_rule(entry); return ERR_PTR(err); } } if (old->watch) { audit_get_watch(old->watch); new->watch = old->watch; } return entry; } /* Find an existing audit rule. * Caller must hold audit_filter_mutex to prevent stale rule data. */ static struct audit_entry *audit_find_rule(struct audit_entry *entry, struct list_head **p) { struct audit_entry *e, *found = NULL; struct list_head *list; int h; if (entry->rule.inode_f) { h = audit_hash_ino(entry->rule.inode_f->val); *p = list = &audit_inode_hash[h]; } else if (entry->rule.watch) { /* we don't know the inode number, so must walk entire hash */ for (h = 0; h < AUDIT_INODE_BUCKETS; h++) { list = &audit_inode_hash[h]; list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } } goto out; } else { *p = list = &audit_filter_list[entry->rule.listnr]; } list_for_each_entry(e, list, list) if (!audit_compare_rule(&entry->rule, &e->rule)) { found = e; goto out; } out: return found; } static u64 prio_low = ~0ULL/2; static u64 prio_high = ~0ULL/2 - 1; /* Add rule to given filterlist if not a duplicate. */ static inline int audit_add_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_watch *watch = entry->rule.watch; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int err = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (e) { mutex_unlock(&audit_filter_mutex); err = -EEXIST; /* normally audit_add_tree_rule() will free it on failure */ if (tree) audit_put_tree(tree); return err; } if (watch) { /* audit_filter_mutex is dropped and re-taken during this call */ err = audit_add_watch(&entry->rule, &list); if (err) { mutex_unlock(&audit_filter_mutex); /* * normally audit_add_tree_rule() will free it * on failure */ if (tree) audit_put_tree(tree); return err; } } if (tree) { err = audit_add_tree_rule(&entry->rule); if (err) { mutex_unlock(&audit_filter_mutex); return err; } } entry->rule.prio = ~0ULL; if (entry->rule.listnr == AUDIT_FILTER_EXIT || entry->rule.listnr == AUDIT_FILTER_URING_EXIT) { if (entry->rule.flags & AUDIT_FILTER_PREPEND) entry->rule.prio = ++prio_high; else entry->rule.prio = --prio_low; } if (entry->rule.flags & AUDIT_FILTER_PREPEND) { list_add(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_rcu(&entry->list, list); entry->rule.flags &= ~AUDIT_FILTER_PREPEND; } else { list_add_tail(&entry->rule.list, &audit_rules_list[entry->rule.listnr]); list_add_tail_rcu(&entry->list, list); } #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules++; if (!audit_match_signal(entry)) audit_signals++; #endif mutex_unlock(&audit_filter_mutex); return err; } /* Remove an existing rule from filterlist. */ int audit_del_rule(struct audit_entry *entry) { struct audit_entry *e; struct audit_tree *tree = entry->rule.tree; struct list_head *list; int ret = 0; #ifdef CONFIG_AUDITSYSCALL int dont_count = 0; /* If any of these, don't count towards total */ switch (entry->rule.listnr) { case AUDIT_FILTER_USER: case AUDIT_FILTER_EXCLUDE: case AUDIT_FILTER_FS: dont_count = 1; } #endif mutex_lock(&audit_filter_mutex); e = audit_find_rule(entry, &list); if (!e) { ret = -ENOENT; goto out; } if (e->rule.watch) audit_remove_watch_rule(&e->rule); if (e->rule.tree) audit_remove_tree_rule(&e->rule); if (e->rule.exe) audit_remove_mark_rule(&e->rule); #ifdef CONFIG_AUDITSYSCALL if (!dont_count) audit_n_rules--; if (!audit_match_signal(entry)) audit_signals--; #endif list_del_rcu(&e->list); list_del(&e->rule.list); call_rcu(&e->rcu, audit_free_rule_rcu); out: mutex_unlock(&audit_filter_mutex); if (tree) audit_put_tree(tree); /* that's the temporary one */ return ret; } /* List rules using struct audit_rule_data. */ static void audit_list_rules(int seq, struct sk_buff_head *q) { struct sk_buff *skb; struct audit_krule *r; int i; /* This is a blocking read, so use audit_filter_mutex instead of rcu * iterator to sync with list writers. */ for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry(r, &audit_rules_list[i], list) { struct audit_rule_data *data; data = audit_krule_to_data(r); if (unlikely(!data)) break; skb = audit_make_reply(seq, AUDIT_LIST_RULES, 0, 1, data, struct_size(data, buf, data->buflen)); if (skb) skb_queue_tail(q, skb); kfree(data); } } skb = audit_make_reply(seq, AUDIT_LIST_RULES, 1, 1, NULL, 0); if (skb) skb_queue_tail(q, skb); } /* Log rule additions and removals */ static void audit_log_rule_change(char *action, struct audit_krule *rule, int res) { struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (!ab) return; audit_log_session_info(ab); audit_log_task_context(ab); audit_log_format(ab, " op=%s", action); audit_log_key(ab, rule->filterkey); audit_log_format(ab, " list=%d res=%d", rule->listnr, res); audit_log_end(ab); } /** * audit_rule_change - apply all rules to the specified message type * @type: audit message type * @seq: netlink audit message sequence (serial) number * @data: payload data * @datasz: size of payload data */ int audit_rule_change(int type, int seq, void *data, size_t datasz) { int err = 0; struct audit_entry *entry; switch (type) { case AUDIT_ADD_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_add_rule(entry); audit_log_rule_change("add_rule", &entry->rule, !err); break; case AUDIT_DEL_RULE: entry = audit_data_to_entry(data, datasz); if (IS_ERR(entry)) return PTR_ERR(entry); err = audit_del_rule(entry); audit_log_rule_change("remove_rule", &entry->rule, !err); break; default: WARN_ON(1); return -EINVAL; } if (err || type == AUDIT_DEL_RULE) { if (entry->rule.exe) audit_remove_mark(entry->rule.exe); audit_free_rule(entry); } return err; } /** * audit_list_rules_send - list the audit rules * @request_skb: skb of request we are replying to (used to target the reply) * @seq: netlink audit message sequence (serial) number */ int audit_list_rules_send(struct sk_buff *request_skb, int seq) { struct task_struct *tsk; struct audit_netlink_list *dest; /* We can't just spew out the rules here because we might fill * the available socket buffer space and deadlock waiting for * auditctl to read from it... which isn't ever going to * happen if we're actually running in the context of auditctl * trying to _send_ the stuff */ dest = kmalloc(sizeof(*dest), GFP_KERNEL); if (!dest) return -ENOMEM; dest->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); dest->portid = NETLINK_CB(request_skb).portid; skb_queue_head_init(&dest->q); mutex_lock(&audit_filter_mutex); audit_list_rules(seq, &dest->q); mutex_unlock(&audit_filter_mutex); tsk = kthread_run(audit_send_list_thread, dest, "audit_send_list"); if (IS_ERR(tsk)) { skb_queue_purge(&dest->q); put_net(dest->net); kfree(dest); return PTR_ERR(tsk); } return 0; } int audit_comparator(u32 left, u32 op, u32 right) { switch (op) { case Audit_equal: return (left == right); case Audit_not_equal: return (left != right); case Audit_lt: return (left < right); case Audit_le: return (left <= right); case Audit_gt: return (left > right); case Audit_ge: return (left >= right); case Audit_bitmask: return (left & right); case Audit_bittest: return ((left & right) == right); default: return 0; } } int audit_uid_comparator(kuid_t left, u32 op, kuid_t right) { switch (op) { case Audit_equal: return uid_eq(left, right); case Audit_not_equal: return !uid_eq(left, right); case Audit_lt: return uid_lt(left, right); case Audit_le: return uid_lte(left, right); case Audit_gt: return uid_gt(left, right); case Audit_ge: return uid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } int audit_gid_comparator(kgid_t left, u32 op, kgid_t right) { switch (op) { case Audit_equal: return gid_eq(left, right); case Audit_not_equal: return !gid_eq(left, right); case Audit_lt: return gid_lt(left, right); case Audit_le: return gid_lte(left, right); case Audit_gt: return gid_gt(left, right); case Audit_ge: return gid_gte(left, right); case Audit_bitmask: case Audit_bittest: default: return 0; } } /** * parent_len - find the length of the parent portion of a pathname * @path: pathname of which to determine length */ int parent_len(const char *path) { int plen; const char *p; plen = strlen(path); if (plen == 0) return plen; /* disregard trailing slashes */ p = path + plen - 1; while ((*p == '/') && (p > path)) p--; /* walk backward until we find the next slash or hit beginning */ while ((*p != '/') && (p > path)) p--; /* did we find a slash? Then increment to include it in path */ if (*p == '/') p++; return p - path; } /** * audit_compare_dname_path - compare given dentry name with last component in * given path. Return of 0 indicates a match. * @dname: dentry name that we're comparing * @path: full pathname that we're comparing * @parentlen: length of the parent if known. Passing in AUDIT_NAME_FULL * here indicates that we must compute this value. */ int audit_compare_dname_path(const struct qstr *dname, const char *path, int parentlen) { int dlen, pathlen; const char *p; dlen = dname->len; pathlen = strlen(path); if (pathlen < dlen) return 1; parentlen = parentlen == AUDIT_NAME_FULL ? parent_len(path) : parentlen; if (pathlen - parentlen != dlen) return 1; p = path + parentlen; return strncmp(p, dname->name, dlen); } int audit_filter(int msgtype, unsigned int listtype) { struct audit_entry *e; int ret = 1; /* Audit by default */ rcu_read_lock(); list_for_each_entry_rcu(e, &audit_filter_list[listtype], list) { int i, result = 0; for (i = 0; i < e->rule.field_count; i++) { struct audit_field *f = &e->rule.fields[i]; pid_t pid; u32 sid; switch (f->type) { case AUDIT_PID: pid = task_pid_nr(current); result = audit_comparator(pid, f->op, f->val); break; case AUDIT_UID: result = audit_uid_comparator(current_uid(), f->op, f->uid); break; case AUDIT_GID: result = audit_gid_comparator(current_gid(), f->op, f->gid); break; case AUDIT_LOGINUID: result = audit_uid_comparator(audit_get_loginuid(current), f->op, f->uid); break; case AUDIT_LOGINUID_SET: result = audit_comparator(audit_loginuid_set(current), f->op, f->val); break; case AUDIT_MSGTYPE: result = audit_comparator(msgtype, f->op, f->val); break; case AUDIT_SUBJ_USER: case AUDIT_SUBJ_ROLE: case AUDIT_SUBJ_TYPE: case AUDIT_SUBJ_SEN: case AUDIT_SUBJ_CLR: if (f->lsm_rule) { security_current_getsecid_subj(&sid); result = security_audit_rule_match(sid, f->type, f->op, f->lsm_rule); } break; case AUDIT_EXE: result = audit_exe_compare(current, e->rule.exe); if (f->op == Audit_not_equal) result = !result; break; default: goto unlock_and_return; } if (result < 0) /* error */ goto unlock_and_return; if (!result) break; } if (result > 0) { if (e->rule.action == AUDIT_NEVER || listtype == AUDIT_FILTER_EXCLUDE) ret = 0; break; } } unlock_and_return: rcu_read_unlock(); return ret; } static int update_lsm_rule(struct audit_krule *r) { struct audit_entry *entry = container_of(r, struct audit_entry, rule); struct audit_entry *nentry; int err = 0; if (!security_audit_rule_known(r)) return 0; nentry = audit_dupe_rule(r); if (entry->rule.exe) audit_remove_mark(entry->rule.exe); if (IS_ERR(nentry)) { /* save the first error encountered for the * return value */ err = PTR_ERR(nentry); audit_panic("error updating LSM filters"); if (r->watch) list_del(&r->rlist); list_del_rcu(&entry->list); list_del(&r->list); } else { if (r->watch || r->tree) list_replace_init(&r->rlist, &nentry->rule.rlist); list_replace_rcu(&entry->list, &nentry->list); list_replace(&r->list, &nentry->rule.list); } call_rcu(&entry->rcu, audit_free_rule_rcu); return err; } /* This function will re-initialize the lsm_rule field of all applicable rules. * It will traverse the filter lists serarching for rules that contain LSM * specific filter fields. When such a rule is found, it is copied, the * LSM field is re-initialized, and the old rule is replaced with the * updated rule. */ int audit_update_lsm_rules(void) { struct audit_krule *r, *n; int i, err = 0; /* audit_filter_mutex synchronizes the writers */ mutex_lock(&audit_filter_mutex); for (i = 0; i < AUDIT_NR_FILTERS; i++) { list_for_each_entry_safe(r, n, &audit_rules_list[i], list) { int res = update_lsm_rule(r); if (!err) err = res; } } mutex_unlock(&audit_filter_mutex); return err; } |
| 203 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 | // SPDX-License-Identifier: GPL-2.0-only /* * A generic implementation of binary search for the Linux kernel * * Copyright (C) 2008-2009 Ksplice, Inc. * Author: Tim Abbott <tabbott@ksplice.com> */ #include <linux/export.h> #include <linux/bsearch.h> #include <linux/kprobes.h> /* * bsearch - binary search an array of elements * @key: pointer to item being searched for * @base: pointer to first element to search * @num: number of elements * @size: size of each element * @cmp: pointer to comparison function * * This function does a binary search on the given array. The * contents of the array should already be in ascending sorted order * under the provided comparison function. * * Note that the key need not have the same type as the elements in * the array, e.g. key could be a string and the comparison function * could compare the string with the struct's name field. However, if * the key and elements in the array are of the same type, you can use * the same comparison function for both sort() and bsearch(). */ void *bsearch(const void *key, const void *base, size_t num, size_t size, cmp_func_t cmp) { return __inline_bsearch(key, base, num, size, cmp); } EXPORT_SYMBOL(bsearch); NOKPROBE_SYMBOL(bsearch); |
| 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2015, 2016 ARM Ltd. */ #ifndef __KVM_ARM_VGIC_H #define __KVM_ARM_VGIC_H #include <linux/bits.h> #include <linux/kvm.h> #include <linux/irqreturn.h> #include <linux/kref.h> #include <linux/mutex.h> #include <linux/spinlock.h> #include <linux/static_key.h> #include <linux/types.h> #include <linux/xarray.h> #include <kvm/iodev.h> #include <linux/list.h> #include <linux/jump_label.h> #include <linux/irqchip/arm-gic-v4.h> #define VGIC_V3_MAX_CPUS 512 #define VGIC_V2_MAX_CPUS 8 #define VGIC_NR_IRQS_LEGACY 256 #define VGIC_NR_SGIS 16 #define VGIC_NR_PPIS 16 #define VGIC_NR_PRIVATE_IRQS (VGIC_NR_SGIS + VGIC_NR_PPIS) #define VGIC_MAX_PRIVATE (VGIC_NR_PRIVATE_IRQS - 1) #define VGIC_MAX_SPI 1019 #define VGIC_MAX_RESERVED 1023 #define VGIC_MIN_LPI 8192 #define KVM_IRQCHIP_NUM_PINS (1020 - 32) #define irq_is_ppi(irq) ((irq) >= VGIC_NR_SGIS && (irq) < VGIC_NR_PRIVATE_IRQS) #define irq_is_spi(irq) ((irq) >= VGIC_NR_PRIVATE_IRQS && \ (irq) <= VGIC_MAX_SPI) enum vgic_type { VGIC_V2, /* Good ol' GICv2 */ VGIC_V3, /* New fancy GICv3 */ }; /* same for all guests, as depending only on the _host's_ GIC model */ struct vgic_global { /* type of the host GIC */ enum vgic_type type; /* Physical address of vgic virtual cpu interface */ phys_addr_t vcpu_base; /* GICV mapping, kernel VA */ void __iomem *vcpu_base_va; /* GICV mapping, HYP VA */ void __iomem *vcpu_hyp_va; /* virtual control interface mapping, kernel VA */ void __iomem *vctrl_base; /* virtual control interface mapping, HYP VA */ void __iomem *vctrl_hyp; /* Number of implemented list registers */ int nr_lr; /* Maintenance IRQ number */ unsigned int maint_irq; /* maximum number of VCPUs allowed (GICv2 limits us to 8) */ int max_gic_vcpus; /* Only needed for the legacy KVM_CREATE_IRQCHIP */ bool can_emulate_gicv2; /* Hardware has GICv4? */ bool has_gicv4; bool has_gicv4_1; /* Pseudo GICv3 from outer space */ bool no_hw_deactivation; /* GIC system register CPU interface */ struct static_key_false gicv3_cpuif; u32 ich_vtr_el2; }; extern struct vgic_global kvm_vgic_global_state; #define VGIC_V2_MAX_LRS (1 << 6) #define VGIC_V3_MAX_LRS 16 #define VGIC_V3_LR_INDEX(lr) (VGIC_V3_MAX_LRS - 1 - lr) enum vgic_irq_config { VGIC_CONFIG_EDGE = 0, VGIC_CONFIG_LEVEL }; /* * Per-irq ops overriding some common behavious. * * Always called in non-preemptible section and the functions can use * kvm_arm_get_running_vcpu() to get the vcpu pointer for private IRQs. */ struct irq_ops { /* Per interrupt flags for special-cased interrupts */ unsigned long flags; #define VGIC_IRQ_SW_RESAMPLE BIT(0) /* Clear the active state for resampling */ /* * Callback function pointer to in-kernel devices that can tell us the * state of the input level of mapped level-triggered IRQ faster than * peaking into the physical GIC. */ bool (*get_input_level)(int vintid); }; struct vgic_irq { raw_spinlock_t irq_lock; /* Protects the content of the struct */ struct rcu_head rcu; struct list_head ap_list; struct kvm_vcpu *vcpu; /* SGIs and PPIs: The VCPU * SPIs and LPIs: The VCPU whose ap_list * this is queued on. */ struct kvm_vcpu *target_vcpu; /* The VCPU that this interrupt should * be sent to, as a result of the * targets reg (v2) or the * affinity reg (v3). */ u32 intid; /* Guest visible INTID */ bool line_level; /* Level only */ bool pending_latch; /* The pending latch state used to calculate * the pending state for both level * and edge triggered IRQs. */ bool active; /* not used for LPIs */ bool enabled; bool hw; /* Tied to HW IRQ */ struct kref refcount; /* Used for LPIs */ u32 hwintid; /* HW INTID number */ unsigned int host_irq; /* linux irq corresponding to hwintid */ union { u8 targets; /* GICv2 target VCPUs mask */ u32 mpidr; /* GICv3 target VCPU */ }; u8 source; /* GICv2 SGIs only */ u8 active_source; /* GICv2 SGIs only */ u8 priority; u8 group; /* 0 == group 0, 1 == group 1 */ enum vgic_irq_config config; /* Level or edge */ struct irq_ops *ops; void *owner; /* Opaque pointer to reserve an interrupt for in-kernel devices. */ }; static inline bool vgic_irq_needs_resampling(struct vgic_irq *irq) { return irq->ops && (irq->ops->flags & VGIC_IRQ_SW_RESAMPLE); } struct vgic_register_region; struct vgic_its; enum iodev_type { IODEV_CPUIF, IODEV_DIST, IODEV_REDIST, IODEV_ITS }; struct vgic_io_device { gpa_t base_addr; union { struct kvm_vcpu *redist_vcpu; struct vgic_its *its; }; const struct vgic_register_region *regions; enum iodev_type iodev_type; int nr_regions; struct kvm_io_device dev; }; struct vgic_its { /* The base address of the ITS control register frame */ gpa_t vgic_its_base; bool enabled; struct vgic_io_device iodev; struct kvm_device *dev; /* These registers correspond to GITS_BASER{0,1} */ u64 baser_device_table; u64 baser_coll_table; /* Protects the command queue */ struct mutex cmd_lock; u64 cbaser; u32 creadr; u32 cwriter; /* migration ABI revision in use */ u32 abi_rev; /* Protects the device and collection lists */ struct mutex its_lock; struct list_head device_list; struct list_head collection_list; /* * Caches the (device_id, event_id) -> vgic_irq translation for * LPIs that are mapped and enabled. */ struct xarray translation_cache; }; struct vgic_state_iter; struct vgic_redist_region { u32 index; gpa_t base; u32 count; /* number of redistributors or 0 if single region */ u32 free_index; /* index of the next free redistributor */ struct list_head list; }; struct vgic_dist { bool in_kernel; bool ready; bool initialized; /* vGIC model the kernel emulates for the guest (GICv2 or GICv3) */ u32 vgic_model; /* Implementation revision as reported in the GICD_IIDR */ u32 implementation_rev; #define KVM_VGIC_IMP_REV_2 2 /* GICv2 restorable groups */ #define KVM_VGIC_IMP_REV_3 3 /* GICv3 GICR_CTLR.{IW,CES,RWP} */ #define KVM_VGIC_IMP_REV_LATEST KVM_VGIC_IMP_REV_3 /* Userspace can write to GICv2 IGROUPR */ bool v2_groups_user_writable; /* Do injected MSIs require an additional device ID? */ bool msis_require_devid; int nr_spis; /* base addresses in guest physical address space: */ gpa_t vgic_dist_base; /* distributor */ union { /* either a GICv2 CPU interface */ gpa_t vgic_cpu_base; /* or a number of GICv3 redistributor regions */ struct list_head rd_regions; }; /* distributor enabled */ bool enabled; /* Wants SGIs without active state */ bool nassgireq; struct vgic_irq *spis; struct vgic_io_device dist_iodev; bool has_its; bool table_write_in_progress; /* * Contains the attributes and gpa of the LPI configuration table. * Since we report GICR_TYPER.CommonLPIAff as 0b00, we can share * one address across all redistributors. * GICv3 spec: IHI 0069E 6.1.1 "LPI Configuration tables" */ u64 propbaser; #define LPI_XA_MARK_DEBUG_ITER XA_MARK_0 struct xarray lpi_xa; /* used by vgic-debug */ struct vgic_state_iter *iter; /* * GICv4 ITS per-VM data, containing the IRQ domain, the VPE * array, the property table pointer as well as allocation * data. This essentially ties the Linux IRQ core and ITS * together, and avoids leaking KVM's data structures anywhere * else. */ struct its_vm its_vm; }; struct vgic_v2_cpu_if { u32 vgic_hcr; u32 vgic_vmcr; u32 vgic_apr; u32 vgic_lr[VGIC_V2_MAX_LRS]; unsigned int used_lrs; }; struct vgic_v3_cpu_if { u32 vgic_hcr; u32 vgic_vmcr; u32 vgic_sre; /* Restored only, change ignored */ u32 vgic_ap0r[4]; u32 vgic_ap1r[4]; u64 vgic_lr[VGIC_V3_MAX_LRS]; /* * GICv4 ITS per-VPE data, containing the doorbell IRQ, the * pending table pointer, the its_vm pointer and a few other * HW specific things. As for the its_vm structure, this is * linking the Linux IRQ subsystem and the ITS together. */ struct its_vpe its_vpe; unsigned int used_lrs; }; struct vgic_cpu { /* CPU vif control registers for world switch */ union { struct vgic_v2_cpu_if vgic_v2; struct vgic_v3_cpu_if vgic_v3; }; struct vgic_irq *private_irqs; raw_spinlock_t ap_list_lock; /* Protects the ap_list */ /* * List of IRQs that this VCPU should consider because they are either * Active or Pending (hence the name; AP list), or because they recently * were one of the two and need to be migrated off this list to another * VCPU. */ struct list_head ap_list_head; /* * Members below are used with GICv3 emulation only and represent * parts of the redistributor. */ struct vgic_io_device rd_iodev; struct vgic_redist_region *rdreg; u32 rdreg_index; atomic_t syncr_busy; /* Contains the attributes and gpa of the LPI pending tables. */ u64 pendbaser; /* GICR_CTLR.{ENABLE_LPIS,RWP} */ atomic_t ctlr; /* Cache guest priority bits */ u32 num_pri_bits; /* Cache guest interrupt ID bits */ u32 num_id_bits; }; extern struct static_key_false vgic_v2_cpuif_trap; extern struct static_key_false vgic_v3_cpuif_trap; int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr); void kvm_vgic_early_init(struct kvm *kvm); int kvm_vgic_vcpu_init(struct kvm_vcpu *vcpu); int kvm_vgic_create(struct kvm *kvm, u32 type); void kvm_vgic_destroy(struct kvm *kvm); void kvm_vgic_vcpu_destroy(struct kvm_vcpu *vcpu); int kvm_vgic_map_resources(struct kvm *kvm); int kvm_vgic_hyp_init(void); void kvm_vgic_init_cpu_hardware(void); int kvm_vgic_inject_irq(struct kvm *kvm, struct kvm_vcpu *vcpu, unsigned int intid, bool level, void *owner); int kvm_vgic_map_phys_irq(struct kvm_vcpu *vcpu, unsigned int host_irq, u32 vintid, struct irq_ops *ops); int kvm_vgic_unmap_phys_irq(struct kvm_vcpu *vcpu, unsigned int vintid); int kvm_vgic_get_map(struct kvm_vcpu *vcpu, unsigned int vintid); bool kvm_vgic_map_is_active(struct kvm_vcpu *vcpu, unsigned int vintid); int kvm_vgic_vcpu_pending_irq(struct kvm_vcpu *vcpu); void kvm_vgic_load(struct kvm_vcpu *vcpu); void kvm_vgic_put(struct kvm_vcpu *vcpu); #define irqchip_in_kernel(k) (!!((k)->arch.vgic.in_kernel)) #define vgic_initialized(k) ((k)->arch.vgic.initialized) #define vgic_ready(k) ((k)->arch.vgic.ready) #define vgic_valid_spi(k, i) (((i) >= VGIC_NR_PRIVATE_IRQS) && \ ((i) < (k)->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS)) bool kvm_vcpu_has_pending_irqs(struct kvm_vcpu *vcpu); void kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu); void kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu); void kvm_vgic_reset_mapped_irq(struct kvm_vcpu *vcpu, u32 vintid); void vgic_v3_dispatch_sgi(struct kvm_vcpu *vcpu, u64 reg, bool allow_group1); /** * kvm_vgic_get_max_vcpus - Get the maximum number of VCPUs allowed by HW * * The host's GIC naturally limits the maximum amount of VCPUs a guest * can use. */ static inline int kvm_vgic_get_max_vcpus(void) { return kvm_vgic_global_state.max_gic_vcpus; } /** * kvm_vgic_setup_default_irq_routing: * Setup a default flat gsi routing table mapping all SPIs */ int kvm_vgic_setup_default_irq_routing(struct kvm *kvm); int kvm_vgic_set_owner(struct kvm_vcpu *vcpu, unsigned int intid, void *owner); struct kvm_kernel_irq_routing_entry; int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int irq, struct kvm_kernel_irq_routing_entry *irq_entry); int vgic_v4_load(struct kvm_vcpu *vcpu); void vgic_v4_commit(struct kvm_vcpu *vcpu); int vgic_v4_put(struct kvm_vcpu *vcpu); /* CPU HP callbacks */ void kvm_vgic_cpu_up(void); void kvm_vgic_cpu_down(void); #endif /* __KVM_ARM_VGIC_H */ |
| 1 1 1 1 1 1 1 1 1 5 5 1 1 1 1 1 1 6 1 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/irqchip/arm-gic-v3.h> #include <linux/irq.h> #include <linux/irqdomain.h> #include <linux/kstrtox.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #include <asm/kvm_asm.h> #include "vgic.h" static bool group0_trap; static bool group1_trap; static bool common_trap; static bool dir_trap; static bool gicv4_enable; void vgic_v3_set_underflow(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpuif = &vcpu->arch.vgic_cpu.vgic_v3; cpuif->vgic_hcr |= ICH_HCR_UIE; } static bool lr_signals_eoi_mi(u64 lr_val) { return !(lr_val & ICH_LR_STATE) && (lr_val & ICH_LR_EOI) && !(lr_val & ICH_LR_HW); } void vgic_v3_fold_lr_state(struct kvm_vcpu *vcpu) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; struct vgic_v3_cpu_if *cpuif = &vgic_cpu->vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; int lr; DEBUG_SPINLOCK_BUG_ON(!irqs_disabled()); cpuif->vgic_hcr &= ~ICH_HCR_UIE; for (lr = 0; lr < cpuif->used_lrs; lr++) { u64 val = cpuif->vgic_lr[lr]; u32 intid, cpuid; struct vgic_irq *irq; bool is_v2_sgi = false; bool deactivated; cpuid = val & GICH_LR_PHYSID_CPUID; cpuid >>= GICH_LR_PHYSID_CPUID_SHIFT; if (model == KVM_DEV_TYPE_ARM_VGIC_V3) { intid = val & ICH_LR_VIRTUAL_ID_MASK; } else { intid = val & GICH_LR_VIRTUALID; is_v2_sgi = vgic_irq_is_sgi(intid); } /* Notify fds when the guest EOI'ed a level-triggered IRQ */ if (lr_signals_eoi_mi(val) && vgic_valid_spi(vcpu->kvm, intid)) kvm_notify_acked_irq(vcpu->kvm, 0, intid - VGIC_NR_PRIVATE_IRQS); irq = vgic_get_irq(vcpu->kvm, vcpu, intid); if (!irq) /* An LPI could have been unmapped. */ continue; raw_spin_lock(&irq->irq_lock); /* Always preserve the active bit, note deactivation */ deactivated = irq->active && !(val & ICH_LR_ACTIVE_BIT); irq->active = !!(val & ICH_LR_ACTIVE_BIT); if (irq->active && is_v2_sgi) irq->active_source = cpuid; /* Edge is the only case where we preserve the pending bit */ if (irq->config == VGIC_CONFIG_EDGE && (val & ICH_LR_PENDING_BIT)) { irq->pending_latch = true; if (is_v2_sgi) irq->source |= (1 << cpuid); } /* * Clear soft pending state when level irqs have been acked. */ if (irq->config == VGIC_CONFIG_LEVEL && !(val & ICH_LR_STATE)) irq->pending_latch = false; /* Handle resampling for mapped interrupts if required */ vgic_irq_handle_resampling(irq, deactivated, val & ICH_LR_PENDING_BIT); raw_spin_unlock(&irq->irq_lock); vgic_put_irq(vcpu->kvm, irq); } cpuif->used_lrs = 0; } /* Requires the irq to be locked already */ void vgic_v3_populate_lr(struct kvm_vcpu *vcpu, struct vgic_irq *irq, int lr) { u32 model = vcpu->kvm->arch.vgic.vgic_model; u64 val = irq->intid; bool allow_pending = true, is_v2_sgi; is_v2_sgi = (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2); if (irq->active) { val |= ICH_LR_ACTIVE_BIT; if (is_v2_sgi) val |= irq->active_source << GICH_LR_PHYSID_CPUID_SHIFT; if (vgic_irq_is_multi_sgi(irq)) { allow_pending = false; val |= ICH_LR_EOI; } } if (irq->hw && !vgic_irq_needs_resampling(irq)) { val |= ICH_LR_HW; val |= ((u64)irq->hwintid) << ICH_LR_PHYS_ID_SHIFT; /* * Never set pending+active on a HW interrupt, as the * pending state is kept at the physical distributor * level. */ if (irq->active) allow_pending = false; } else { if (irq->config == VGIC_CONFIG_LEVEL) { val |= ICH_LR_EOI; /* * Software resampling doesn't work very well * if we allow P+A, so let's not do that. */ if (irq->active) allow_pending = false; } } if (allow_pending && irq_is_pending(irq)) { val |= ICH_LR_PENDING_BIT; if (irq->config == VGIC_CONFIG_EDGE) irq->pending_latch = false; if (vgic_irq_is_sgi(irq->intid) && model == KVM_DEV_TYPE_ARM_VGIC_V2) { u32 src = ffs(irq->source); if (WARN_RATELIMIT(!src, "No SGI source for INTID %d\n", irq->intid)) return; val |= (src - 1) << GICH_LR_PHYSID_CPUID_SHIFT; irq->source &= ~(1 << (src - 1)); if (irq->source) { irq->pending_latch = true; val |= ICH_LR_EOI; } } } /* * Level-triggered mapped IRQs are special because we only observe * rising edges as input to the VGIC. We therefore lower the line * level here, so that we can take new virtual IRQs. See * vgic_v3_fold_lr_state for more info. */ if (vgic_irq_is_mapped_level(irq) && (val & ICH_LR_PENDING_BIT)) irq->line_level = false; if (irq->group) val |= ICH_LR_GROUP; val |= (u64)irq->priority << ICH_LR_PRIORITY_SHIFT; vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = val; } void vgic_v3_clear_lr(struct kvm_vcpu *vcpu, int lr) { vcpu->arch.vgic_cpu.vgic_v3.vgic_lr[lr] = 0; } void vgic_v3_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcr = (vmcrp->ackctl << ICH_VMCR_ACK_CTL_SHIFT) & ICH_VMCR_ACK_CTL_MASK; vmcr |= (vmcrp->fiqen << ICH_VMCR_FIQ_EN_SHIFT) & ICH_VMCR_FIQ_EN_MASK; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcr = ICH_VMCR_FIQ_EN_MASK; } vmcr |= (vmcrp->cbpr << ICH_VMCR_CBPR_SHIFT) & ICH_VMCR_CBPR_MASK; vmcr |= (vmcrp->eoim << ICH_VMCR_EOIM_SHIFT) & ICH_VMCR_EOIM_MASK; vmcr |= (vmcrp->abpr << ICH_VMCR_BPR1_SHIFT) & ICH_VMCR_BPR1_MASK; vmcr |= (vmcrp->bpr << ICH_VMCR_BPR0_SHIFT) & ICH_VMCR_BPR0_MASK; vmcr |= (vmcrp->pmr << ICH_VMCR_PMR_SHIFT) & ICH_VMCR_PMR_MASK; vmcr |= (vmcrp->grpen0 << ICH_VMCR_ENG0_SHIFT) & ICH_VMCR_ENG0_MASK; vmcr |= (vmcrp->grpen1 << ICH_VMCR_ENG1_SHIFT) & ICH_VMCR_ENG1_MASK; cpu_if->vgic_vmcr = vmcr; } void vgic_v3_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcrp) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; u32 model = vcpu->kvm->arch.vgic.vgic_model; u32 vmcr; vmcr = cpu_if->vgic_vmcr; if (model == KVM_DEV_TYPE_ARM_VGIC_V2) { vmcrp->ackctl = (vmcr & ICH_VMCR_ACK_CTL_MASK) >> ICH_VMCR_ACK_CTL_SHIFT; vmcrp->fiqen = (vmcr & ICH_VMCR_FIQ_EN_MASK) >> ICH_VMCR_FIQ_EN_SHIFT; } else { /* * When emulating GICv3 on GICv3 with SRE=1 on the * VFIQEn bit is RES1 and the VAckCtl bit is RES0. */ vmcrp->fiqen = 1; vmcrp->ackctl = 0; } vmcrp->cbpr = (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; vmcrp->eoim = (vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT; vmcrp->abpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; vmcrp->bpr = (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; vmcrp->pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; vmcrp->grpen0 = (vmcr & ICH_VMCR_ENG0_MASK) >> ICH_VMCR_ENG0_SHIFT; vmcrp->grpen1 = (vmcr & ICH_VMCR_ENG1_MASK) >> ICH_VMCR_ENG1_SHIFT; } #define INITIAL_PENDBASER_VALUE \ (GIC_BASER_CACHEABILITY(GICR_PENDBASER, INNER, RaWb) | \ GIC_BASER_CACHEABILITY(GICR_PENDBASER, OUTER, SameAsInner) | \ GIC_BASER_SHAREABILITY(GICR_PENDBASER, InnerShareable)) void vgic_v3_enable(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *vgic_v3 = &vcpu->arch.vgic_cpu.vgic_v3; /* * By forcing VMCR to zero, the GIC will restore the binary * points to their reset values. Anything else resets to zero * anyway. */ vgic_v3->vgic_vmcr = 0; /* * If we are emulating a GICv3, we do it in an non-GICv2-compatible * way, so we force SRE to 1 to demonstrate this to the guest. * Also, we don't support any form of IRQ/FIQ bypass. * This goes with the spec allowing the value to be RAO/WI. */ if (vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) { vgic_v3->vgic_sre = (ICC_SRE_EL1_DIB | ICC_SRE_EL1_DFB | ICC_SRE_EL1_SRE); vcpu->arch.vgic_cpu.pendbaser = INITIAL_PENDBASER_VALUE; } else { vgic_v3->vgic_sre = 0; } vcpu->arch.vgic_cpu.num_id_bits = (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_ID_BITS_MASK) >> ICH_VTR_ID_BITS_SHIFT; vcpu->arch.vgic_cpu.num_pri_bits = ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_PRI_BITS_MASK) >> ICH_VTR_PRI_BITS_SHIFT) + 1; /* Get the show on the road... */ vgic_v3->vgic_hcr = ICH_HCR_EN; if (group0_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL0; if (group1_trap) vgic_v3->vgic_hcr |= ICH_HCR_TALL1; if (common_trap) vgic_v3->vgic_hcr |= ICH_HCR_TC; if (dir_trap) vgic_v3->vgic_hcr |= ICH_HCR_TDIR; } int vgic_v3_lpi_sync_pending_status(struct kvm *kvm, struct vgic_irq *irq) { struct kvm_vcpu *vcpu; int byte_offset, bit_nr; gpa_t pendbase, ptr; bool status; u8 val; int ret; unsigned long flags; retry: vcpu = irq->target_vcpu; if (!vcpu) return 0; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; status = val & (1 << bit_nr); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->target_vcpu != vcpu) { raw_spin_unlock_irqrestore(&irq->irq_lock, flags); goto retry; } irq->pending_latch = status; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); if (status) { /* clear consumed data */ val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) return ret; } return 0; } /* * The deactivation of the doorbell interrupt will trigger the * unmapping of the associated vPE. */ static void unmap_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) free_irq(dist->its_vm.vpes[i]->irq, kvm_get_vcpu(kvm, i)); } static void map_all_vpes(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; int i; for (i = 0; i < dist->its_vm.nr_vpes; i++) WARN_ON(vgic_v4_request_vpe_irq(kvm_get_vcpu(kvm, i), dist->its_vm.vpes[i]->irq)); } /** * vgic_v3_save_pending_tables - Save the pending tables into guest RAM * kvm lock and all vcpu lock must be held */ int vgic_v3_save_pending_tables(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; gpa_t last_ptr = ~(gpa_t)0; bool vlpi_avail = false; unsigned long index; int ret = 0; u8 val; if (unlikely(!vgic_initialized(kvm))) return -ENXIO; /* * A preparation for getting any VLPI states. * The above vgic initialized check also ensures that the allocation * and enabling of the doorbells have already been done. */ if (kvm_vgic_global_state.has_gicv4_1) { unmap_all_vpes(kvm); vlpi_avail = true; } xa_for_each(&dist->lpi_xa, index, irq) { int byte_offset, bit_nr; struct kvm_vcpu *vcpu; gpa_t pendbase, ptr; bool is_pending; bool stored; vcpu = irq->target_vcpu; if (!vcpu) continue; pendbase = GICR_PENDBASER_ADDRESS(vcpu->arch.vgic_cpu.pendbaser); byte_offset = irq->intid / BITS_PER_BYTE; bit_nr = irq->intid % BITS_PER_BYTE; ptr = pendbase + byte_offset; if (ptr != last_ptr) { ret = kvm_read_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; last_ptr = ptr; } stored = val & (1U << bit_nr); is_pending = irq->pending_latch; if (irq->hw && vlpi_avail) vgic_v4_get_vlpi_state(irq, &is_pending); if (stored == is_pending) continue; if (is_pending) val |= 1 << bit_nr; else val &= ~(1 << bit_nr); ret = vgic_write_guest_lock(kvm, ptr, &val, 1); if (ret) goto out; } out: if (vlpi_avail) map_all_vpes(kvm); return ret; } /** * vgic_v3_rdist_overlap - check if a region overlaps with any * existing redistributor region * * @kvm: kvm handle * @base: base of the region * @size: size of region * * Return: true if there is an overlap */ bool vgic_v3_rdist_overlap(struct kvm *kvm, gpa_t base, size_t size) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, &d->rd_regions, list) { if ((base + size > rdreg->base) && (base < rdreg->base + vgic_v3_rd_region_size(kvm, rdreg))) return true; } return false; } /* * Check for overlapping regions and for regions crossing the end of memory * for base addresses which have already been set. */ bool vgic_v3_check_base(struct kvm *kvm) { struct vgic_dist *d = &kvm->arch.vgic; struct vgic_redist_region *rdreg; if (!IS_VGIC_ADDR_UNDEF(d->vgic_dist_base) && d->vgic_dist_base + KVM_VGIC_V3_DIST_SIZE < d->vgic_dist_base) return false; list_for_each_entry(rdreg, &d->rd_regions, list) { size_t sz = vgic_v3_rd_region_size(kvm, rdreg); if (vgic_check_iorange(kvm, VGIC_ADDR_UNDEF, rdreg->base, SZ_64K, sz)) return false; } if (IS_VGIC_ADDR_UNDEF(d->vgic_dist_base)) return true; return !vgic_v3_rdist_overlap(kvm, d->vgic_dist_base, KVM_VGIC_V3_DIST_SIZE); } /** * vgic_v3_rdist_free_slot - Look up registered rdist regions and identify one * which has free space to put a new rdist region. * * @rd_regions: redistributor region list head * * A redistributor regions maps n redistributors, n = region size / (2 x 64kB). * Stride between redistributors is 0 and regions are filled in the index order. * * Return: the redist region handle, if any, that has space to map a new rdist * region. */ struct vgic_redist_region *vgic_v3_rdist_free_slot(struct list_head *rd_regions) { struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (!vgic_v3_redist_region_full(rdreg)) return rdreg; } return NULL; } struct vgic_redist_region *vgic_v3_rdist_region_from_index(struct kvm *kvm, u32 index) { struct list_head *rd_regions = &kvm->arch.vgic.rd_regions; struct vgic_redist_region *rdreg; list_for_each_entry(rdreg, rd_regions, list) { if (rdreg->index == index) return rdreg; } return NULL; } int vgic_v3_map_resources(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct kvm_vcpu *vcpu; unsigned long c; kvm_for_each_vcpu(c, vcpu, kvm) { struct vgic_cpu *vgic_cpu = &vcpu->arch.vgic_cpu; if (IS_VGIC_ADDR_UNDEF(vgic_cpu->rd_iodev.base_addr)) { kvm_debug("vcpu %ld redistributor base not set\n", c); return -ENXIO; } } if (IS_VGIC_ADDR_UNDEF(dist->vgic_dist_base)) { kvm_debug("Need to set vgic distributor addresses first\n"); return -ENXIO; } if (!vgic_v3_check_base(kvm)) { kvm_debug("VGIC redist and dist frames overlap\n"); return -EINVAL; } /* * For a VGICv3 we require the userland to explicitly initialize * the VGIC before we need to use it. */ if (!vgic_initialized(kvm)) { return -EBUSY; } if (kvm_vgic_global_state.has_gicv4_1) vgic_v4_configure_vsgis(kvm); return 0; } DEFINE_STATIC_KEY_FALSE(vgic_v3_cpuif_trap); static int __init early_group0_trap_cfg(char *buf) { return kstrtobool(buf, &group0_trap); } early_param("kvm-arm.vgic_v3_group0_trap", early_group0_trap_cfg); static int __init early_group1_trap_cfg(char *buf) { return kstrtobool(buf, &group1_trap); } early_param("kvm-arm.vgic_v3_group1_trap", early_group1_trap_cfg); static int __init early_common_trap_cfg(char *buf) { return kstrtobool(buf, &common_trap); } early_param("kvm-arm.vgic_v3_common_trap", early_common_trap_cfg); static int __init early_gicv4_enable(char *buf) { return kstrtobool(buf, &gicv4_enable); } early_param("kvm-arm.vgic_v4_enable", early_gicv4_enable); static const struct midr_range broken_seis[] = { MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_ICESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M1_FIRESTORM_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_PRO), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_BLIZZARD_MAX), MIDR_ALL_VERSIONS(MIDR_APPLE_M2_AVALANCHE_MAX), {}, }; static bool vgic_v3_broken_seis(void) { return ((kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) && is_midr_in_range_list(read_cpuid_id(), broken_seis)); } /** * vgic_v3_probe - probe for a VGICv3 compatible interrupt controller * @info: pointer to the GIC description * * Returns 0 if the VGICv3 has been probed successfully, returns an error code * otherwise */ int vgic_v3_probe(const struct gic_kvm_info *info) { u64 ich_vtr_el2 = kvm_call_hyp_ret(__vgic_v3_get_gic_config); bool has_v2; int ret; has_v2 = ich_vtr_el2 >> 63; ich_vtr_el2 = (u32)ich_vtr_el2; /* * The ListRegs field is 5 bits, but there is an architectural * maximum of 16 list registers. Just ignore bit 4... */ kvm_vgic_global_state.nr_lr = (ich_vtr_el2 & 0xf) + 1; kvm_vgic_global_state.can_emulate_gicv2 = false; kvm_vgic_global_state.ich_vtr_el2 = ich_vtr_el2; /* GICv4 support? */ if (info->has_v4) { kvm_vgic_global_state.has_gicv4 = gicv4_enable; kvm_vgic_global_state.has_gicv4_1 = info->has_v4_1 && gicv4_enable; kvm_info("GICv4%s support %sabled\n", kvm_vgic_global_state.has_gicv4_1 ? ".1" : "", gicv4_enable ? "en" : "dis"); } kvm_vgic_global_state.vcpu_base = 0; if (!info->vcpu.start) { kvm_info("GICv3: no GICV resource entry\n"); } else if (!has_v2) { pr_warn(FW_BUG "CPU interface incapable of MMIO access\n"); } else if (!PAGE_ALIGNED(info->vcpu.start)) { pr_warn("GICV physical address 0x%llx not page aligned\n", (unsigned long long)info->vcpu.start); } else if (kvm_get_mode() != KVM_MODE_PROTECTED) { kvm_vgic_global_state.vcpu_base = info->vcpu.start; kvm_vgic_global_state.can_emulate_gicv2 = true; ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V2); if (ret) { kvm_err("Cannot register GICv2 KVM device.\n"); return ret; } kvm_info("vgic-v2@%llx\n", info->vcpu.start); } ret = kvm_register_vgic_device(KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) { kvm_err("Cannot register GICv3 KVM device.\n"); kvm_unregister_device_ops(KVM_DEV_TYPE_ARM_VGIC_V2); return ret; } if (kvm_vgic_global_state.vcpu_base == 0) kvm_info("disabling GICv2 emulation\n"); if (cpus_have_final_cap(ARM64_WORKAROUND_CAVIUM_30115)) { group0_trap = true; group1_trap = true; } if (vgic_v3_broken_seis()) { kvm_info("GICv3 with broken locally generated SEI\n"); kvm_vgic_global_state.ich_vtr_el2 &= ~ICH_VTR_SEIS_MASK; group0_trap = true; group1_trap = true; if (ich_vtr_el2 & ICH_VTR_TDS_MASK) dir_trap = true; else common_trap = true; } if (group0_trap || group1_trap || common_trap | dir_trap) { kvm_info("GICv3 sysreg trapping enabled ([%s%s%s%s], reduced performance)\n", group0_trap ? "G0" : "", group1_trap ? "G1" : "", common_trap ? "C" : "", dir_trap ? "D" : ""); static_branch_enable(&vgic_v3_cpuif_trap); } kvm_vgic_global_state.vctrl_base = NULL; kvm_vgic_global_state.type = VGIC_V3; kvm_vgic_global_state.max_gic_vcpus = VGIC_V3_MAX_CPUS; return 0; } void vgic_v3_load(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; kvm_call_hyp(__vgic_v3_restore_vmcr_aprs, cpu_if); if (has_vhe()) __vgic_v3_activate_traps(cpu_if); WARN_ON(vgic_v4_load(vcpu)); } void vgic_v3_put(struct kvm_vcpu *vcpu) { struct vgic_v3_cpu_if *cpu_if = &vcpu->arch.vgic_cpu.vgic_v3; kvm_call_hyp(__vgic_v3_save_vmcr_aprs, cpu_if); WARN_ON(vgic_v4_put(vcpu)); if (has_vhe()) __vgic_v3_deactivate_traps(cpu_if); } |
| 262 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2016 ARM Ltd. */ #ifndef __ASM_PGTABLE_PROT_H #define __ASM_PGTABLE_PROT_H #include <asm/memory.h> #include <asm/pgtable-hwdef.h> #include <linux/const.h> /* * Software defined PTE bits definition. */ #define PTE_WRITE (PTE_DBM) /* same as DBM (51) */ #define PTE_SWP_EXCLUSIVE (_AT(pteval_t, 1) << 2) /* only for swp ptes */ #define PTE_DIRTY (_AT(pteval_t, 1) << 55) #define PTE_SPECIAL (_AT(pteval_t, 1) << 56) #define PTE_DEVMAP (_AT(pteval_t, 1) << 57) /* * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be * interpreted according to the HW layout by SW but any attempted HW access to * the address will result in a fault. pte_present() returns true. */ #define PTE_PRESENT_INVALID (PTE_NG) /* only when !PTE_VALID */ #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define PTE_UFFD_WP (_AT(pteval_t, 1) << 58) /* uffd-wp tracking */ #define PTE_SWP_UFFD_WP (_AT(pteval_t, 1) << 3) /* only for swp ptes */ #else #define PTE_UFFD_WP (_AT(pteval_t, 0)) #define PTE_SWP_UFFD_WP (_AT(pteval_t, 0)) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define _PROT_DEFAULT (PTE_TYPE_PAGE | PTE_AF | PTE_SHARED) #define _PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_SECT_AF | PMD_SECT_S) #define PROT_DEFAULT (PTE_TYPE_PAGE | PTE_MAYBE_NG | PTE_MAYBE_SHARED | PTE_AF) #define PROT_SECT_DEFAULT (PMD_TYPE_SECT | PMD_MAYBE_NG | PMD_MAYBE_SHARED | PMD_SECT_AF) #define PROT_DEVICE_nGnRnE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRnE)) #define PROT_DEVICE_nGnRE (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_NORMAL_NC (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_NC)) #define PROT_NORMAL (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL)) #define PROT_NORMAL_TAGGED (PROT_DEFAULT | PTE_PXN | PTE_UXN | PTE_WRITE | PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define PROT_SECT_DEVICE_nGnRE (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PMD_ATTRINDX(MT_DEVICE_nGnRE)) #define PROT_SECT_NORMAL (PROT_SECT_DEFAULT | PMD_SECT_PXN | PMD_SECT_UXN | PTE_WRITE | PMD_ATTRINDX(MT_NORMAL)) #define PROT_SECT_NORMAL_EXEC (PROT_SECT_DEFAULT | PMD_SECT_UXN | PMD_ATTRINDX(MT_NORMAL)) #define _PAGE_DEFAULT (_PROT_DEFAULT | PTE_ATTRINDX(MT_NORMAL)) #define _PAGE_KERNEL (PROT_NORMAL) #define _PAGE_KERNEL_RO ((PROT_NORMAL & ~PTE_WRITE) | PTE_RDONLY) #define _PAGE_KERNEL_ROX ((PROT_NORMAL & ~(PTE_WRITE | PTE_PXN)) | PTE_RDONLY) #define _PAGE_KERNEL_EXEC (PROT_NORMAL & ~PTE_PXN) #define _PAGE_KERNEL_EXEC_CONT ((PROT_NORMAL & ~PTE_PXN) | PTE_CONT) #define _PAGE_SHARED (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN | PTE_WRITE) #define _PAGE_SHARED_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_WRITE) #define _PAGE_READONLY (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) #define _PAGE_READONLY_EXEC (_PAGE_DEFAULT | PTE_USER | PTE_RDONLY | PTE_NG | PTE_PXN) #define _PAGE_EXECONLY (_PAGE_DEFAULT | PTE_RDONLY | PTE_NG | PTE_PXN) #ifndef __ASSEMBLY__ #include <asm/cpufeature.h> #include <asm/pgtable-types.h> extern bool arm64_use_ng_mappings; #define PTE_MAYBE_NG (arm64_use_ng_mappings ? PTE_NG : 0) #define PMD_MAYBE_NG (arm64_use_ng_mappings ? PMD_SECT_NG : 0) #ifndef CONFIG_ARM64_LPA2 #define lpa2_is_enabled() false #define PTE_MAYBE_SHARED PTE_SHARED #define PMD_MAYBE_SHARED PMD_SECT_S #else static inline bool __pure lpa2_is_enabled(void) { return read_tcr() & TCR_DS; } #define PTE_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PTE_SHARED) #define PMD_MAYBE_SHARED (lpa2_is_enabled() ? 0 : PMD_SECT_S) #endif /* * If we have userspace only BTI we don't want to mark kernel pages * guarded even if the system does support BTI. */ #define PTE_MAYBE_GP (system_supports_bti_kernel() ? PTE_GP : 0) #define PAGE_KERNEL __pgprot(_PAGE_KERNEL) #define PAGE_KERNEL_RO __pgprot(_PAGE_KERNEL_RO) #define PAGE_KERNEL_ROX __pgprot(_PAGE_KERNEL_ROX) #define PAGE_KERNEL_EXEC __pgprot(_PAGE_KERNEL_EXEC) #define PAGE_KERNEL_EXEC_CONT __pgprot(_PAGE_KERNEL_EXEC_CONT) #define PAGE_S2_MEMATTR(attr, has_fwb) \ ({ \ u64 __val; \ if (has_fwb) \ __val = PTE_S2_MEMATTR(MT_S2_FWB_ ## attr); \ else \ __val = PTE_S2_MEMATTR(MT_S2_ ## attr); \ __val; \ }) #define PAGE_NONE __pgprot(((_PAGE_DEFAULT) & ~PTE_VALID) | PTE_PRESENT_INVALID | PTE_RDONLY | PTE_NG | PTE_PXN | PTE_UXN) /* shared+writable pages are clean by default, hence PTE_RDONLY|PTE_WRITE */ #define PAGE_SHARED __pgprot(_PAGE_SHARED) #define PAGE_SHARED_EXEC __pgprot(_PAGE_SHARED_EXEC) #define PAGE_READONLY __pgprot(_PAGE_READONLY) #define PAGE_READONLY_EXEC __pgprot(_PAGE_READONLY_EXEC) #define PAGE_EXECONLY __pgprot(_PAGE_EXECONLY) #endif /* __ASSEMBLY__ */ #define pte_pi_index(pte) ( \ ((pte & BIT(PTE_PI_IDX_3)) >> (PTE_PI_IDX_3 - 3)) | \ ((pte & BIT(PTE_PI_IDX_2)) >> (PTE_PI_IDX_2 - 2)) | \ ((pte & BIT(PTE_PI_IDX_1)) >> (PTE_PI_IDX_1 - 1)) | \ ((pte & BIT(PTE_PI_IDX_0)) >> (PTE_PI_IDX_0 - 0))) /* * Page types used via Permission Indirection Extension (PIE). PIE uses * the USER, DBM, PXN and UXN bits to to generate an index which is used * to look up the actual permission in PIR_ELx and PIRE0_EL1. We define * combinations we use on non-PIE systems with the same encoding, for * convenience these are listed here as comments as are the unallocated * encodings. */ /* 0: PAGE_DEFAULT */ /* 1: PTE_USER */ /* 2: PTE_WRITE */ /* 3: PTE_WRITE | PTE_USER */ /* 4: PAGE_EXECONLY PTE_PXN */ /* 5: PAGE_READONLY_EXEC PTE_PXN | PTE_USER */ /* 6: PTE_PXN | PTE_WRITE */ /* 7: PAGE_SHARED_EXEC PTE_PXN | PTE_WRITE | PTE_USER */ /* 8: PAGE_KERNEL_ROX PTE_UXN */ /* 9: PTE_UXN | PTE_USER */ /* a: PAGE_KERNEL_EXEC PTE_UXN | PTE_WRITE */ /* b: PTE_UXN | PTE_WRITE | PTE_USER */ /* c: PAGE_KERNEL_RO PTE_UXN | PTE_PXN */ /* d: PAGE_READONLY PTE_UXN | PTE_PXN | PTE_USER */ /* e: PAGE_KERNEL PTE_UXN | PTE_PXN | PTE_WRITE */ /* f: PAGE_SHARED PTE_UXN | PTE_PXN | PTE_WRITE | PTE_USER */ #define PIE_E0 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_X_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_RX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RWX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW)) #define PIE_E1 ( \ PIRx_ELx_PERM(pte_pi_index(_PAGE_EXECONLY), PIE_NONE_O) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY_EXEC), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED_EXEC), PIE_RW) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_READONLY), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_SHARED), PIE_RW) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_ROX), PIE_RX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_EXEC), PIE_RWX) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL_RO), PIE_R) | \ PIRx_ELx_PERM(pte_pi_index(_PAGE_KERNEL), PIE_RW)) #endif /* __ASM_PGTABLE_PROT_H */ |
| 13 6 6 10 10 10 10 10 10 8 10 10 10 10 158 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/reset.c * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #include <linux/errno.h> #include <linux/kernel.h> #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/hw_breakpoint.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> #include <kvm/arm_arch_timer.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/fpsimd.h> #include <asm/ptrace.h> #include <asm/kvm_arm.h> #include <asm/kvm_asm.h> #include <asm/kvm_emulate.h> #include <asm/kvm_mmu.h> #include <asm/kvm_nested.h> #include <asm/virt.h> /* Maximum phys_shift supported for any VM on this host */ static u32 __ro_after_init kvm_ipa_limit; unsigned int __ro_after_init kvm_host_sve_max_vl; /* * ARMv8 Reset Values */ #define VCPU_RESET_PSTATE_EL1 (PSR_MODE_EL1h | PSR_A_BIT | PSR_I_BIT | \ PSR_F_BIT | PSR_D_BIT) #define VCPU_RESET_PSTATE_EL2 (PSR_MODE_EL2h | PSR_A_BIT | PSR_I_BIT | \ PSR_F_BIT | PSR_D_BIT) #define VCPU_RESET_PSTATE_SVC (PSR_AA32_MODE_SVC | PSR_AA32_A_BIT | \ PSR_AA32_I_BIT | PSR_AA32_F_BIT) unsigned int __ro_after_init kvm_sve_max_vl; int __init kvm_arm_init_sve(void) { if (system_supports_sve()) { kvm_sve_max_vl = sve_max_virtualisable_vl(); kvm_host_sve_max_vl = sve_max_vl(); kvm_nvhe_sym(kvm_host_sve_max_vl) = kvm_host_sve_max_vl; /* * The get_sve_reg()/set_sve_reg() ioctl interface will need * to be extended with multiple register slice support in * order to support vector lengths greater than * VL_ARCH_MAX: */ if (WARN_ON(kvm_sve_max_vl > VL_ARCH_MAX)) kvm_sve_max_vl = VL_ARCH_MAX; /* * Don't even try to make use of vector lengths that * aren't available on all CPUs, for now: */ if (kvm_sve_max_vl < sve_max_vl()) pr_warn("KVM: SVE vector length for guests limited to %u bytes\n", kvm_sve_max_vl); } return 0; } static void kvm_vcpu_enable_sve(struct kvm_vcpu *vcpu) { vcpu->arch.sve_max_vl = kvm_sve_max_vl; /* * Userspace can still customize the vector lengths by writing * KVM_REG_ARM64_SVE_VLS. Allocation is deferred until * kvm_arm_vcpu_finalize(), which freezes the configuration. */ vcpu_set_flag(vcpu, GUEST_HAS_SVE); } /* * Finalize vcpu's maximum SVE vector length, allocating * vcpu->arch.sve_state as necessary. */ static int kvm_vcpu_finalize_sve(struct kvm_vcpu *vcpu) { void *buf; unsigned int vl; size_t reg_sz; int ret; vl = vcpu->arch.sve_max_vl; /* * Responsibility for these properties is shared between * kvm_arm_init_sve(), kvm_vcpu_enable_sve() and * set_sve_vls(). Double-check here just to be sure: */ if (WARN_ON(!sve_vl_valid(vl) || vl > sve_max_virtualisable_vl() || vl > VL_ARCH_MAX)) return -EIO; reg_sz = vcpu_sve_state_size(vcpu); buf = kzalloc(reg_sz, GFP_KERNEL_ACCOUNT); if (!buf) return -ENOMEM; ret = kvm_share_hyp(buf, buf + reg_sz); if (ret) { kfree(buf); return ret; } vcpu->arch.sve_state = buf; vcpu_set_flag(vcpu, VCPU_SVE_FINALIZED); return 0; } int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature) { switch (feature) { case KVM_ARM_VCPU_SVE: if (!vcpu_has_sve(vcpu)) return -EINVAL; if (kvm_arm_vcpu_sve_finalized(vcpu)) return -EPERM; return kvm_vcpu_finalize_sve(vcpu); } return -EINVAL; } bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu) { if (vcpu_has_sve(vcpu) && !kvm_arm_vcpu_sve_finalized(vcpu)) return false; return true; } void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu) { void *sve_state = vcpu->arch.sve_state; kvm_unshare_hyp(vcpu, vcpu + 1); if (sve_state) kvm_unshare_hyp(sve_state, sve_state + vcpu_sve_state_size(vcpu)); kfree(sve_state); kfree(vcpu->arch.ccsidr); } static void kvm_vcpu_reset_sve(struct kvm_vcpu *vcpu) { if (vcpu_has_sve(vcpu)) memset(vcpu->arch.sve_state, 0, vcpu_sve_state_size(vcpu)); } static void kvm_vcpu_enable_ptrauth(struct kvm_vcpu *vcpu) { vcpu_set_flag(vcpu, GUEST_HAS_PTRAUTH); } /** * kvm_reset_vcpu - sets core registers and sys_regs to reset value * @vcpu: The VCPU pointer * * This function sets the registers on the virtual CPU struct to their * architecturally defined reset values, except for registers whose reset is * deferred until kvm_arm_vcpu_finalize(). * * Note: This function can be called from two paths: The KVM_ARM_VCPU_INIT * ioctl or as part of handling a request issued by another VCPU in the PSCI * handling code. In the first case, the VCPU will not be loaded, and in the * second case the VCPU will be loaded. Because this function operates purely * on the memory-backed values of system registers, we want to do a full put if * we were loaded (handling a request) and load the values back at the end of * the function. Otherwise we leave the state alone. In both cases, we * disable preemption around the vcpu reset as we would otherwise race with * preempt notifiers which also call put/load. */ void kvm_reset_vcpu(struct kvm_vcpu *vcpu) { struct vcpu_reset_state reset_state; bool loaded; u32 pstate; spin_lock(&vcpu->arch.mp_state_lock); reset_state = vcpu->arch.reset_state; vcpu->arch.reset_state.reset = false; spin_unlock(&vcpu->arch.mp_state_lock); /* Reset PMU outside of the non-preemptible section */ kvm_pmu_vcpu_reset(vcpu); preempt_disable(); loaded = (vcpu->cpu != -1); if (loaded) kvm_arch_vcpu_put(vcpu); if (!kvm_arm_vcpu_sve_finalized(vcpu)) { if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_SVE)) kvm_vcpu_enable_sve(vcpu); } else { kvm_vcpu_reset_sve(vcpu); } if (vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_ADDRESS) || vcpu_has_feature(vcpu, KVM_ARM_VCPU_PTRAUTH_GENERIC)) kvm_vcpu_enable_ptrauth(vcpu); if (vcpu_el1_is_32bit(vcpu)) pstate = VCPU_RESET_PSTATE_SVC; else if (vcpu_has_nv(vcpu)) pstate = VCPU_RESET_PSTATE_EL2; else pstate = VCPU_RESET_PSTATE_EL1; /* Reset core registers */ memset(vcpu_gp_regs(vcpu), 0, sizeof(*vcpu_gp_regs(vcpu))); memset(&vcpu->arch.ctxt.fp_regs, 0, sizeof(vcpu->arch.ctxt.fp_regs)); vcpu->arch.ctxt.spsr_abt = 0; vcpu->arch.ctxt.spsr_und = 0; vcpu->arch.ctxt.spsr_irq = 0; vcpu->arch.ctxt.spsr_fiq = 0; vcpu_gp_regs(vcpu)->pstate = pstate; /* Reset system registers */ kvm_reset_sys_regs(vcpu); /* * Additional reset state handling that PSCI may have imposed on us. * Must be done after all the sys_reg reset. */ if (reset_state.reset) { unsigned long target_pc = reset_state.pc; /* Gracefully handle Thumb2 entry point */ if (vcpu_mode_is_32bit(vcpu) && (target_pc & 1)) { target_pc &= ~1UL; vcpu_set_thumb(vcpu); } /* Propagate caller endianness */ if (reset_state.be) kvm_vcpu_set_be(vcpu); *vcpu_pc(vcpu) = target_pc; vcpu_set_reg(vcpu, 0, reset_state.r0); } /* Reset timer */ kvm_timer_vcpu_reset(vcpu); if (loaded) kvm_arch_vcpu_load(vcpu, smp_processor_id()); preempt_enable(); } u32 kvm_get_pa_bits(struct kvm *kvm) { /* Fixed limit until we can configure ID_AA64MMFR0.PARange */ return kvm_ipa_limit; } u32 get_kvm_ipa_limit(void) { return kvm_ipa_limit; } int __init kvm_set_ipa_limit(void) { unsigned int parange; u64 mmfr0; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); parange = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); /* * IPA size beyond 48 bits for 4K and 16K page size is only supported * when LPA2 is available. So if we have LPA2, enable it, else cap to 48 * bits, in case it's reported as larger on the system. */ if (!kvm_lpa2_is_enabled() && PAGE_SIZE != SZ_64K) parange = min(parange, (unsigned int)ID_AA64MMFR0_EL1_PARANGE_48); /* * Check with ARMv8.5-GTG that our PAGE_SIZE is supported at * Stage-2. If not, things will stop very quickly. */ switch (cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_2_SHIFT)) { case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_NONE: kvm_err("PAGE_SIZE not supported at Stage-2, giving up\n"); return -EINVAL; case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_DEFAULT: kvm_debug("PAGE_SIZE supported at Stage-2 (default)\n"); break; case ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MIN ... ID_AA64MMFR0_EL1_TGRAN_2_SUPPORTED_MAX: kvm_debug("PAGE_SIZE supported at Stage-2 (advertised)\n"); break; default: kvm_err("Unsupported value for TGRAN_2, giving up\n"); return -EINVAL; } kvm_ipa_limit = id_aa64mmfr0_parange_to_phys_shift(parange); kvm_info("IPA Size Limit: %d bits%s\n", kvm_ipa_limit, ((kvm_ipa_limit < KVM_PHYS_SHIFT) ? " (Reduced IPA size, limited VM/VMM compatibility)" : "")); return 0; } |
| 222 248 179 181 146 147 147 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 | // SPDX-License-Identifier: GPL-2.0 #include <linux/export.h> #include <linux/lockref.h> #if USE_CMPXCHG_LOCKREF /* * Note that the "cmpxchg()" reloads the "old" value for the * failure case. */ #define CMPXCHG_LOOP(CODE, SUCCESS) do { \ int retry = 100; \ struct lockref old; \ BUILD_BUG_ON(sizeof(old) != 8); \ old.lock_count = READ_ONCE(lockref->lock_count); \ while (likely(arch_spin_value_unlocked(old.lock.rlock.raw_lock))) { \ struct lockref new = old; \ CODE \ if (likely(try_cmpxchg64_relaxed(&lockref->lock_count, \ &old.lock_count, \ new.lock_count))) { \ SUCCESS; \ } \ if (!--retry) \ break; \ } \ } while (0) #else #define CMPXCHG_LOOP(CODE, SUCCESS) do { } while (0) #endif /** * lockref_get - Increments reference count unconditionally * @lockref: pointer to lockref structure * * This operation is only valid if you already hold a reference * to the object, so you know the count cannot be zero. */ void lockref_get(struct lockref *lockref) { CMPXCHG_LOOP( new.count++; , return; ); spin_lock(&lockref->lock); lockref->count++; spin_unlock(&lockref->lock); } EXPORT_SYMBOL(lockref_get); /** * lockref_get_not_zero - Increments count unless the count is 0 or dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count was zero */ int lockref_get_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count <= 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_zero); /** * lockref_put_not_zero - Decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count would become zero */ int lockref_put_not_zero(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count--; if (old.count <= 1) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count > 1) { lockref->count--; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_put_not_zero); /** * lockref_put_return - Decrement reference count if possible * @lockref: pointer to lockref structure * * Decrement the reference count and return the new value. * If the lockref was dead or locked, return an error. */ int lockref_put_return(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 0) return -1; , return new.count; ); return -1; } EXPORT_SYMBOL(lockref_put_return); /** * lockref_put_or_lock - decrements count unless count <= 1 before decrement * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if count <= 1 and lock taken */ int lockref_put_or_lock(struct lockref *lockref) { CMPXCHG_LOOP( new.count--; if (old.count <= 1) break; , return 1; ); spin_lock(&lockref->lock); if (lockref->count <= 1) return 0; lockref->count--; spin_unlock(&lockref->lock); return 1; } EXPORT_SYMBOL(lockref_put_or_lock); /** * lockref_mark_dead - mark lockref dead * @lockref: pointer to lockref structure */ void lockref_mark_dead(struct lockref *lockref) { assert_spin_locked(&lockref->lock); lockref->count = -128; } EXPORT_SYMBOL(lockref_mark_dead); /** * lockref_get_not_dead - Increments count unless the ref is dead * @lockref: pointer to lockref structure * Return: 1 if count updated successfully or 0 if lockref was dead */ int lockref_get_not_dead(struct lockref *lockref) { int retval; CMPXCHG_LOOP( new.count++; if (old.count < 0) return 0; , return 1; ); spin_lock(&lockref->lock); retval = 0; if (lockref->count >= 0) { lockref->count++; retval = 1; } spin_unlock(&lockref->lock); return retval; } EXPORT_SYMBOL(lockref_get_not_dead); |
| 10 10 10 10 10 10 10 10 10 2 2 10 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/kvm/coproc.h * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Authors: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_SYS_REGS_LOCAL_H__ #define __ARM64_KVM_SYS_REGS_LOCAL_H__ #include <linux/bsearch.h> #define reg_to_encoding(x) \ sys_reg((u32)(x)->Op0, (u32)(x)->Op1, \ (u32)(x)->CRn, (u32)(x)->CRm, (u32)(x)->Op2) struct sys_reg_params { u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; u64 regval; bool is_write; }; #define encoding_to_params(reg) \ ((struct sys_reg_params){ .Op0 = sys_reg_Op0(reg), \ .Op1 = sys_reg_Op1(reg), \ .CRn = sys_reg_CRn(reg), \ .CRm = sys_reg_CRm(reg), \ .Op2 = sys_reg_Op2(reg) }) #define esr_sys64_to_params(esr) \ ((struct sys_reg_params){ .Op0 = ((esr) >> 20) & 3, \ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) #define esr_cp1x_32_to_params(esr) \ ((struct sys_reg_params){ .Op1 = ((esr) >> 14) & 0x7, \ .CRn = ((esr) >> 10) & 0xf, \ .CRm = ((esr) >> 1) & 0xf, \ .Op2 = ((esr) >> 17) & 0x7, \ .is_write = !((esr) & 1) }) struct sys_reg_desc { /* Sysreg string for debug */ const char *name; enum { AA32_DIRECT, AA32_LO, AA32_HI, } aarch32_map; /* MRS/MSR instruction which accesses it. */ u8 Op0; u8 Op1; u8 CRn; u8 CRm; u8 Op2; /* Trapped access from guest, if non-NULL. */ bool (*access)(struct kvm_vcpu *, struct sys_reg_params *, const struct sys_reg_desc *); /* * Initialization for vcpu. Return initialized value, or KVM * sanitized value for ID registers. */ u64 (*reset)(struct kvm_vcpu *, const struct sys_reg_desc *); /* Index into sys_reg[], or 0 if we don't need to save it. */ int reg; /* Value (usually reset value), or write mask for idregs */ u64 val; /* Custom get/set_user functions, fallback to generic if NULL */ int (*get_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 *val); int (*set_user)(struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd, u64 val); /* Return mask of REG_* runtime visibility overrides */ unsigned int (*visibility)(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *rd); }; #define REG_HIDDEN (1 << 0) /* hidden from userspace and guest */ #define REG_HIDDEN_USER (1 << 1) /* hidden from userspace only */ #define REG_RAZ (1 << 2) /* RAZ from userspace and guest */ #define REG_USER_WI (1 << 3) /* WI from userspace only */ static __printf(2, 3) inline void print_sys_reg_msg(const struct sys_reg_params *p, char *fmt, ...) { va_list va; va_start(va, fmt); /* Look, we even formatted it for you to paste into the table! */ kvm_pr_unimpl("%pV { Op0(%2u), Op1(%2u), CRn(%2u), CRm(%2u), Op2(%2u), func_%s },\n", &(struct va_format){ fmt, &va }, p->Op0, p->Op1, p->CRn, p->CRm, p->Op2, p->is_write ? "write" : "read"); va_end(va); } static inline void print_sys_reg_instr(const struct sys_reg_params *p) { /* GCC warns on an empty format string */ print_sys_reg_msg(p, "%s", ""); } static inline bool ignore_write(struct kvm_vcpu *vcpu, const struct sys_reg_params *p) { return true; } static inline bool read_zero(struct kvm_vcpu *vcpu, struct sys_reg_params *p) { p->regval = 0; return true; } /* Reset functions */ static inline u64 reset_unknown(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_sys_reg(vcpu, r->reg) = 0x1de7ec7edbadc0deULL; return __vcpu_sys_reg(vcpu, r->reg); } static inline u64 reset_val(struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { BUG_ON(!r->reg); BUG_ON(r->reg >= NR_SYS_REGS); __vcpu_sys_reg(vcpu, r->reg) = r->val; return __vcpu_sys_reg(vcpu, r->reg); } static inline unsigned int sysreg_visibility(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return 0; return r->visibility(vcpu, r); } static inline bool sysreg_hidden(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_HIDDEN; } static inline bool sysreg_hidden_user(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { if (likely(!r->visibility)) return false; return r->visibility(vcpu, r) & (REG_HIDDEN | REG_HIDDEN_USER); } static inline bool sysreg_visible_as_raz(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_RAZ; } static inline bool sysreg_user_write_ignore(const struct kvm_vcpu *vcpu, const struct sys_reg_desc *r) { return sysreg_visibility(vcpu, r) & REG_USER_WI; } static inline int cmp_sys_reg(const struct sys_reg_desc *i1, const struct sys_reg_desc *i2) { BUG_ON(i1 == i2); if (!i1) return 1; else if (!i2) return -1; if (i1->Op0 != i2->Op0) return i1->Op0 - i2->Op0; if (i1->Op1 != i2->Op1) return i1->Op1 - i2->Op1; if (i1->CRn != i2->CRn) return i1->CRn - i2->CRn; if (i1->CRm != i2->CRm) return i1->CRm - i2->CRm; return i1->Op2 - i2->Op2; } static inline int match_sys_reg(const void *key, const void *elt) { const unsigned long pval = (unsigned long)key; const struct sys_reg_desc *r = elt; return pval - reg_to_encoding(r); } static inline const struct sys_reg_desc * find_reg(const struct sys_reg_params *params, const struct sys_reg_desc table[], unsigned int num) { unsigned long pval = reg_to_encoding(params); return __inline_bsearch((void *)pval, table, num, sizeof(table[0]), match_sys_reg); } const struct sys_reg_desc *get_reg_by_id(u64 id, const struct sys_reg_desc table[], unsigned int num); int kvm_arm_sys_reg_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_arm_sys_reg_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *); int kvm_sys_reg_get_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); int kvm_sys_reg_set_user(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg, const struct sys_reg_desc table[], unsigned int num); bool triage_sysreg_trap(struct kvm_vcpu *vcpu, int *sr_index); #define AA32(_x) .aarch32_map = AA32_##_x #define Op0(_x) .Op0 = _x #define Op1(_x) .Op1 = _x #define CRn(_x) .CRn = _x #define CRm(_x) .CRm = _x #define Op2(_x) .Op2 = _x #define SYS_DESC(reg) \ .name = #reg, \ Op0(sys_reg_Op0(reg)), Op1(sys_reg_Op1(reg)), \ CRn(sys_reg_CRn(reg)), CRm(sys_reg_CRm(reg)), \ Op2(sys_reg_Op2(reg)) #endif /* __ARM64_KVM_SYS_REGS_LOCAL_H__ */ |
| 132 128 132 132 324 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_JUMP_LABEL_H #define _LINUX_JUMP_LABEL_H /* * Jump label support * * Copyright (C) 2009-2012 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011-2012 Red Hat, Inc., Peter Zijlstra * * DEPRECATED API: * * The use of 'struct static_key' directly, is now DEPRECATED. In addition * static_key_{true,false}() is also DEPRECATED. IE DO NOT use the following: * * struct static_key false = STATIC_KEY_INIT_FALSE; * struct static_key true = STATIC_KEY_INIT_TRUE; * static_key_true() * static_key_false() * * The updated API replacements are: * * DEFINE_STATIC_KEY_TRUE(key); * DEFINE_STATIC_KEY_FALSE(key); * DEFINE_STATIC_KEY_ARRAY_TRUE(keys, count); * DEFINE_STATIC_KEY_ARRAY_FALSE(keys, count); * static_branch_likely() * static_branch_unlikely() * * Jump labels provide an interface to generate dynamic branches using * self-modifying code. Assuming toolchain and architecture support, if we * define a "key" that is initially false via "DEFINE_STATIC_KEY_FALSE(key)", * an "if (static_branch_unlikely(&key))" statement is an unconditional branch * (which defaults to false - and the true block is placed out of line). * Similarly, we can define an initially true key via * "DEFINE_STATIC_KEY_TRUE(key)", and use it in the same * "if (static_branch_unlikely(&key))", in which case we will generate an * unconditional branch to the out-of-line true branch. Keys that are * initially true or false can be using in both static_branch_unlikely() * and static_branch_likely() statements. * * At runtime we can change the branch target by setting the key * to true via a call to static_branch_enable(), or false using * static_branch_disable(). If the direction of the branch is switched by * these calls then we run-time modify the branch target via a * no-op -> jump or jump -> no-op conversion. For example, for an * initially false key that is used in an "if (static_branch_unlikely(&key))" * statement, setting the key to true requires us to patch in a jump * to the out-of-line of true branch. * * In addition to static_branch_{enable,disable}, we can also reference count * the key or branch direction via static_branch_{inc,dec}. Thus, * static_branch_inc() can be thought of as a 'make more true' and * static_branch_dec() as a 'make more false'. * * Since this relies on modifying code, the branch modifying functions * must be considered absolute slow paths (machine wide synchronization etc.). * OTOH, since the affected branches are unconditional, their runtime overhead * will be absolutely minimal, esp. in the default (off) case where the total * effect is a single NOP of appropriate size. The on case will patch in a jump * to the out-of-line block. * * When the control is directly exposed to userspace, it is prudent to delay the * decrement to avoid high frequency code modifications which can (and do) * cause significant performance degradation. Struct static_key_deferred and * static_key_slow_dec_deferred() provide for this. * * Lacking toolchain and or architecture support, static keys fall back to a * simple conditional branch. * * Additional babbling in: Documentation/staging/static-keys.rst */ #ifndef __ASSEMBLY__ #include <linux/types.h> #include <linux/compiler.h> extern bool static_key_initialized; #define STATIC_KEY_CHECK_USE(key) WARN(!static_key_initialized, \ "%s(): static key '%pS' used before call to jump_label_init()", \ __func__, (key)) struct static_key { atomic_t enabled; #ifdef CONFIG_JUMP_LABEL /* * Note: * To make anonymous unions work with old compilers, the static * initialization of them requires brackets. This creates a dependency * on the order of the struct with the initializers. If any fields * are added, STATIC_KEY_INIT_TRUE and STATIC_KEY_INIT_FALSE may need * to be modified. * * bit 0 => 1 if key is initially true * 0 if initially false * bit 1 => 1 if points to struct static_key_mod * 0 if points to struct jump_entry */ union { unsigned long type; struct jump_entry *entries; struct static_key_mod *next; }; #endif /* CONFIG_JUMP_LABEL */ }; #endif /* __ASSEMBLY__ */ #ifdef CONFIG_JUMP_LABEL #include <asm/jump_label.h> #ifndef __ASSEMBLY__ #ifdef CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE struct jump_entry { s32 code; s32 target; long key; // key may be far away from the core kernel under KASLR }; static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return (unsigned long)&entry->code + entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return (unsigned long)&entry->target + entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { long offset = entry->key & ~3L; return (struct static_key *)((unsigned long)&entry->key + offset); } #else static inline unsigned long jump_entry_code(const struct jump_entry *entry) { return entry->code; } static inline unsigned long jump_entry_target(const struct jump_entry *entry) { return entry->target; } static inline struct static_key *jump_entry_key(const struct jump_entry *entry) { return (struct static_key *)((unsigned long)entry->key & ~3UL); } #endif static inline bool jump_entry_is_branch(const struct jump_entry *entry) { return (unsigned long)entry->key & 1UL; } static inline bool jump_entry_is_init(const struct jump_entry *entry) { return (unsigned long)entry->key & 2UL; } static inline void jump_entry_set_init(struct jump_entry *entry, bool set) { if (set) entry->key |= 2; else entry->key &= ~2; } static inline int jump_entry_size(struct jump_entry *entry) { #ifdef JUMP_LABEL_NOP_SIZE return JUMP_LABEL_NOP_SIZE; #else return arch_jump_entry_size(entry); #endif } #endif #endif #ifndef __ASSEMBLY__ enum jump_label_type { JUMP_LABEL_NOP = 0, JUMP_LABEL_JMP, }; struct module; #ifdef CONFIG_JUMP_LABEL #define JUMP_TYPE_FALSE 0UL #define JUMP_TYPE_TRUE 1UL #define JUMP_TYPE_LINKED 2UL #define JUMP_TYPE_MASK 3UL static __always_inline bool static_key_false(struct static_key *key) { return arch_static_branch(key, false); } static __always_inline bool static_key_true(struct static_key *key) { return !arch_static_branch(key, true); } extern struct jump_entry __start___jump_table[]; extern struct jump_entry __stop___jump_table[]; extern void jump_label_init(void); extern void jump_label_init_ro(void); extern void jump_label_lock(void); extern void jump_label_unlock(void); extern void arch_jump_label_transform(struct jump_entry *entry, enum jump_label_type type); extern bool arch_jump_label_transform_queue(struct jump_entry *entry, enum jump_label_type type); extern void arch_jump_label_transform_apply(void); extern int jump_label_text_reserved(void *start, void *end); extern bool static_key_slow_inc(struct static_key *key); extern bool static_key_fast_inc_not_disabled(struct static_key *key); extern void static_key_slow_dec(struct static_key *key); extern bool static_key_slow_inc_cpuslocked(struct static_key *key); extern void static_key_slow_dec_cpuslocked(struct static_key *key); extern int static_key_count(struct static_key *key); extern void static_key_enable(struct static_key *key); extern void static_key_disable(struct static_key *key); extern void static_key_enable_cpuslocked(struct static_key *key); extern void static_key_disable_cpuslocked(struct static_key *key); extern enum jump_label_type jump_label_init_type(struct jump_entry *entry); /* * We should be using ATOMIC_INIT() for initializing .enabled, but * the inclusion of atomic.h is problematic for inclusion of jump_label.h * in 'low-level' headers. Thus, we are initializing .enabled with a * raw value, but have added a BUILD_BUG_ON() to catch any issues in * jump_label_init() see: kernel/jump_label.c. */ #define STATIC_KEY_INIT_TRUE \ { .enabled = { 1 }, \ { .type = JUMP_TYPE_TRUE } } #define STATIC_KEY_INIT_FALSE \ { .enabled = { 0 }, \ { .type = JUMP_TYPE_FALSE } } #else /* !CONFIG_JUMP_LABEL */ #include <linux/atomic.h> #include <linux/bug.h> static __always_inline int static_key_count(struct static_key *key) { return raw_atomic_read(&key->enabled); } static __always_inline void jump_label_init(void) { static_key_initialized = true; } static __always_inline void jump_label_init_ro(void) { } static __always_inline bool static_key_false(struct static_key *key) { if (unlikely_notrace(static_key_count(key) > 0)) return true; return false; } static __always_inline bool static_key_true(struct static_key *key) { if (likely_notrace(static_key_count(key) > 0)) return true; return false; } static inline bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Prevent key->enabled getting negative to follow the same semantics * as for CONFIG_JUMP_LABEL=y, see kernel/jump_label.c comment. */ v = atomic_read(&key->enabled); do { if (v < 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } #define static_key_slow_inc(key) static_key_fast_inc_not_disabled(key) static inline void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); atomic_dec(&key->enabled); } #define static_key_slow_inc_cpuslocked(key) static_key_slow_inc(key) #define static_key_slow_dec_cpuslocked(key) static_key_slow_dec(key) static inline int jump_label_text_reserved(void *start, void *end) { return 0; } static inline void jump_label_lock(void) {} static inline void jump_label_unlock(void) {} static inline void static_key_enable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } atomic_set(&key->enabled, 1); } static inline void static_key_disable(struct static_key *key) { STATIC_KEY_CHECK_USE(key); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } atomic_set(&key->enabled, 0); } #define static_key_enable_cpuslocked(k) static_key_enable((k)) #define static_key_disable_cpuslocked(k) static_key_disable((k)) #define STATIC_KEY_INIT_TRUE { .enabled = ATOMIC_INIT(1) } #define STATIC_KEY_INIT_FALSE { .enabled = ATOMIC_INIT(0) } #endif /* CONFIG_JUMP_LABEL */ #define STATIC_KEY_INIT STATIC_KEY_INIT_FALSE #define jump_label_enabled static_key_enabled /* -------------------------------------------------------------------------- */ /* * Two type wrappers around static_key, such that we can use compile time * type differentiation to emit the right code. * * All the below code is macros in order to play type games. */ struct static_key_true { struct static_key key; }; struct static_key_false { struct static_key key; }; #define STATIC_KEY_TRUE_INIT (struct static_key_true) { .key = STATIC_KEY_INIT_TRUE, } #define STATIC_KEY_FALSE_INIT (struct static_key_false){ .key = STATIC_KEY_INIT_FALSE, } #define DEFINE_STATIC_KEY_TRUE(name) \ struct static_key_true name = STATIC_KEY_TRUE_INIT #define DEFINE_STATIC_KEY_TRUE_RO(name) \ struct static_key_true name __ro_after_init = STATIC_KEY_TRUE_INIT #define DECLARE_STATIC_KEY_TRUE(name) \ extern struct static_key_true name #define DEFINE_STATIC_KEY_FALSE(name) \ struct static_key_false name = STATIC_KEY_FALSE_INIT #define DEFINE_STATIC_KEY_FALSE_RO(name) \ struct static_key_false name __ro_after_init = STATIC_KEY_FALSE_INIT #define DECLARE_STATIC_KEY_FALSE(name) \ extern struct static_key_false name #define DEFINE_STATIC_KEY_ARRAY_TRUE(name, count) \ struct static_key_true name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_TRUE_INIT, \ } #define DEFINE_STATIC_KEY_ARRAY_FALSE(name, count) \ struct static_key_false name[count] = { \ [0 ... (count) - 1] = STATIC_KEY_FALSE_INIT, \ } #define _DEFINE_STATIC_KEY_1(name) DEFINE_STATIC_KEY_TRUE(name) #define _DEFINE_STATIC_KEY_0(name) DEFINE_STATIC_KEY_FALSE(name) #define DEFINE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_, IS_ENABLED(cfg))(name) #define _DEFINE_STATIC_KEY_RO_1(name) DEFINE_STATIC_KEY_TRUE_RO(name) #define _DEFINE_STATIC_KEY_RO_0(name) DEFINE_STATIC_KEY_FALSE_RO(name) #define DEFINE_STATIC_KEY_MAYBE_RO(cfg, name) \ __PASTE(_DEFINE_STATIC_KEY_RO_, IS_ENABLED(cfg))(name) #define _DECLARE_STATIC_KEY_1(name) DECLARE_STATIC_KEY_TRUE(name) #define _DECLARE_STATIC_KEY_0(name) DECLARE_STATIC_KEY_FALSE(name) #define DECLARE_STATIC_KEY_MAYBE(cfg, name) \ __PASTE(_DECLARE_STATIC_KEY_, IS_ENABLED(cfg))(name) extern bool ____wrong_branch_error(void); #define static_key_enabled(x) \ ({ \ if (!__builtin_types_compatible_p(typeof(*x), struct static_key) && \ !__builtin_types_compatible_p(typeof(*x), struct static_key_true) &&\ !__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ ____wrong_branch_error(); \ static_key_count((struct static_key *)x) > 0; \ }) #ifdef CONFIG_JUMP_LABEL /* * Combine the right initial value (type) with the right branch order * to generate the desired result. * * * type\branch| likely (1) | unlikely (0) * -----------+-----------------------+------------------ * | | * true (1) | ... | ... * | NOP | JMP L * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * | | * false (0) | ... | ... * | JMP L | NOP * | <br-stmts> | 1: ... * | L: ... | * | | * | | L: <br-stmts> * | | jmp 1b * | | * -----------+-----------------------+------------------ * * The initial value is encoded in the LSB of static_key::entries, * type: 0 = false, 1 = true. * * The branch type is encoded in the LSB of jump_entry::key, * branch: 0 = unlikely, 1 = likely. * * This gives the following logic table: * * enabled type branch instuction * -----------------------------+----------- * 0 0 0 | NOP * 0 0 1 | JMP * 0 1 0 | NOP * 0 1 1 | JMP * * 1 0 0 | JMP * 1 0 1 | NOP * 1 1 0 | JMP * 1 1 1 | NOP * * Which gives the following functions: * * dynamic: instruction = enabled ^ branch * static: instruction = type ^ branch * * See jump_label_type() / jump_label_init_type(). */ #define static_branch_likely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = !arch_static_branch(&(x)->key, true); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = !arch_static_branch_jump(&(x)->key, true); \ else \ branch = ____wrong_branch_error(); \ likely_notrace(branch); \ }) #define static_branch_unlikely(x) \ ({ \ bool branch; \ if (__builtin_types_compatible_p(typeof(*x), struct static_key_true)) \ branch = arch_static_branch_jump(&(x)->key, false); \ else if (__builtin_types_compatible_p(typeof(*x), struct static_key_false)) \ branch = arch_static_branch(&(x)->key, false); \ else \ branch = ____wrong_branch_error(); \ unlikely_notrace(branch); \ }) #else /* !CONFIG_JUMP_LABEL */ #define static_branch_likely(x) likely_notrace(static_key_enabled(&(x)->key)) #define static_branch_unlikely(x) unlikely_notrace(static_key_enabled(&(x)->key)) #endif /* CONFIG_JUMP_LABEL */ #define static_branch_maybe(config, x) \ (IS_ENABLED(config) ? static_branch_likely(x) \ : static_branch_unlikely(x)) /* * Advanced usage; refcount, branch is enabled when: count != 0 */ #define static_branch_inc(x) static_key_slow_inc(&(x)->key) #define static_branch_dec(x) static_key_slow_dec(&(x)->key) #define static_branch_inc_cpuslocked(x) static_key_slow_inc_cpuslocked(&(x)->key) #define static_branch_dec_cpuslocked(x) static_key_slow_dec_cpuslocked(&(x)->key) /* * Normal usage; boolean enable/disable. */ #define static_branch_enable(x) static_key_enable(&(x)->key) #define static_branch_disable(x) static_key_disable(&(x)->key) #define static_branch_enable_cpuslocked(x) static_key_enable_cpuslocked(&(x)->key) #define static_branch_disable_cpuslocked(x) static_key_disable_cpuslocked(&(x)->key) #endif /* __ASSEMBLY__ */ #endif /* _LINUX_JUMP_LABEL_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 | #ifndef _LINUX_JHASH_H #define _LINUX_JHASH_H /* jhash.h: Jenkins hash support. * * Copyright (C) 2006. Bob Jenkins (bob_jenkins@burtleburtle.net) * * https://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; fallthrough; case 11: c += (u32)k[10]<<16; fallthrough; case 10: c += (u32)k[9]<<8; fallthrough; case 9: c += k[8]; fallthrough; case 8: b += (u32)k[7]<<24; fallthrough; case 7: b += (u32)k[6]<<16; fallthrough; case 6: b += (u32)k[5]<<8; fallthrough; case 5: b += k[4]; fallthrough; case 4: a += (u32)k[3]<<24; fallthrough; case 3: a += (u32)k[2]<<16; fallthrough; case 2: a += (u32)k[1]<<8; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; 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]; fallthrough; case 2: b += k[1]; fallthrough; case 1: a += k[0]; __jhash_final(a, b, c); break; 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 */ |
| 132 132 147 147 86 86 147 147 147 128 128 1 128 146 16 16 12 12 11 11 11 11 11 16 11 16 16 16 132 132 132 11 132 132 132 132 132 132 132 132 132 132 132 132 131 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 | // SPDX-License-Identifier: GPL-2.0-only /* * jump label support * * Copyright (C) 2009 Jason Baron <jbaron@redhat.com> * Copyright (C) 2011 Peter Zijlstra * */ #include <linux/memory.h> #include <linux/uaccess.h> #include <linux/module.h> #include <linux/list.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/err.h> #include <linux/static_key.h> #include <linux/jump_label_ratelimit.h> #include <linux/bug.h> #include <linux/cpu.h> #include <asm/sections.h> /* mutex to protect coming/going of the jump_label table */ static DEFINE_MUTEX(jump_label_mutex); void jump_label_lock(void) { mutex_lock(&jump_label_mutex); } void jump_label_unlock(void) { mutex_unlock(&jump_label_mutex); } static int jump_label_cmp(const void *a, const void *b) { const struct jump_entry *jea = a; const struct jump_entry *jeb = b; /* * Entrires are sorted by key. */ if (jump_entry_key(jea) < jump_entry_key(jeb)) return -1; if (jump_entry_key(jea) > jump_entry_key(jeb)) return 1; /* * In the batching mode, entries should also be sorted by the code * inside the already sorted list of entries, enabling a bsearch in * the vector. */ if (jump_entry_code(jea) < jump_entry_code(jeb)) return -1; if (jump_entry_code(jea) > jump_entry_code(jeb)) return 1; return 0; } static void jump_label_swap(void *a, void *b, int size) { long delta = (unsigned long)a - (unsigned long)b; struct jump_entry *jea = a; struct jump_entry *jeb = b; struct jump_entry tmp = *jea; jea->code = jeb->code - delta; jea->target = jeb->target - delta; jea->key = jeb->key - delta; jeb->code = tmp.code + delta; jeb->target = tmp.target + delta; jeb->key = tmp.key + delta; } static void jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop) { unsigned long size; void *swapfn = NULL; if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE)) swapfn = jump_label_swap; size = (((unsigned long)stop - (unsigned long)start) / sizeof(struct jump_entry)); sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn); } static void jump_label_update(struct static_key *key); /* * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h. * The use of 'atomic_read()' requires atomic.h and its problematic for some * kernel headers such as kernel.h and others. Since static_key_count() is not * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok * to have it be a function here. Similarly, for 'static_key_enable()' and * 'static_key_disable()', which require bug.h. This should allow jump_label.h * to be included from most/all places for CONFIG_JUMP_LABEL. */ int static_key_count(struct static_key *key) { /* * -1 means the first static_key_slow_inc() is in progress. * static_key_enabled() must return true, so return 1 here. */ int n = atomic_read(&key->enabled); return n >= 0 ? n : 1; } EXPORT_SYMBOL_GPL(static_key_count); /* * static_key_fast_inc_not_disabled - adds a user for a static key * @key: static key that must be already enabled * * The caller must make sure that the static key can't get disabled while * in this function. It doesn't patch jump labels, only adds a user to * an already enabled static key. * * Returns true if the increment was done. Unlike refcount_t the ref counter * is not saturated, but will fail to increment on overflow. */ bool static_key_fast_inc_not_disabled(struct static_key *key) { int v; STATIC_KEY_CHECK_USE(key); /* * Negative key->enabled has a special meaning: it sends * static_key_slow_inc() down the slow path, and it is non-zero * so it counts as "enabled" in jump_label_update(). Note that * atomic_inc_unless_negative() checks >= 0, so roll our own. */ v = atomic_read(&key->enabled); do { if (v <= 0 || (v + 1) < 0) return false; } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1))); return true; } EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled); bool static_key_slow_inc_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); /* * Careful if we get concurrent static_key_slow_inc() calls; * later calls must wait for the first one to _finish_ the * jump_label_update() process. At the same time, however, * the jump_label_update() call below wants to see * static_key_enabled(&key) for jumps to be updated properly. */ if (static_key_fast_inc_not_disabled(key)) return true; jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * Ensure that if the above cmpxchg loop observes our positive * value, it must also observe all the text changes. */ atomic_set_release(&key->enabled, 1); } else { if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) { jump_label_unlock(); return false; } } jump_label_unlock(); return true; } bool static_key_slow_inc(struct static_key *key) { bool ret; cpus_read_lock(); ret = static_key_slow_inc_cpuslocked(key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(static_key_slow_inc); void static_key_enable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) > 0) { WARN_ON_ONCE(atomic_read(&key->enabled) != 1); return; } jump_label_lock(); if (atomic_read(&key->enabled) == 0) { atomic_set(&key->enabled, -1); jump_label_update(key); /* * See static_key_slow_inc(). */ atomic_set_release(&key->enabled, 1); } jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked); void static_key_enable(struct static_key *key) { cpus_read_lock(); static_key_enable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_enable); void static_key_disable_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); lockdep_assert_cpus_held(); if (atomic_read(&key->enabled) != 1) { WARN_ON_ONCE(atomic_read(&key->enabled) != 0); return; } jump_label_lock(); if (atomic_cmpxchg(&key->enabled, 1, 0)) jump_label_update(key); jump_label_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked); void static_key_disable(struct static_key *key) { cpus_read_lock(); static_key_disable_cpuslocked(key); cpus_read_unlock(); } EXPORT_SYMBOL_GPL(static_key_disable); static bool static_key_slow_try_dec(struct static_key *key) { int val; val = atomic_fetch_add_unless(&key->enabled, -1, 1); if (val == 1) return false; /* * The negative count check is valid even when a negative * key->enabled is in use by static_key_slow_inc(); a * __static_key_slow_dec() before the first static_key_slow_inc() * returns is unbalanced, because all other static_key_slow_inc() * instances block while the update is in progress. */ WARN(val < 0, "jump label: negative count!\n"); return true; } static void __static_key_slow_dec_cpuslocked(struct static_key *key) { lockdep_assert_cpus_held(); if (static_key_slow_try_dec(key)) return; jump_label_lock(); if (atomic_dec_and_test(&key->enabled)) jump_label_update(key); jump_label_unlock(); } static void __static_key_slow_dec(struct static_key *key) { cpus_read_lock(); __static_key_slow_dec_cpuslocked(key); cpus_read_unlock(); } void jump_label_update_timeout(struct work_struct *work) { struct static_key_deferred *key = container_of(work, struct static_key_deferred, work.work); __static_key_slow_dec(&key->key); } EXPORT_SYMBOL_GPL(jump_label_update_timeout); void static_key_slow_dec(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec(key); } EXPORT_SYMBOL_GPL(static_key_slow_dec); void static_key_slow_dec_cpuslocked(struct static_key *key) { STATIC_KEY_CHECK_USE(key); __static_key_slow_dec_cpuslocked(key); } void __static_key_slow_dec_deferred(struct static_key *key, struct delayed_work *work, unsigned long timeout) { STATIC_KEY_CHECK_USE(key); if (static_key_slow_try_dec(key)) return; schedule_delayed_work(work, timeout); } EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred); void __static_key_deferred_flush(void *key, struct delayed_work *work) { STATIC_KEY_CHECK_USE(key); flush_delayed_work(work); } EXPORT_SYMBOL_GPL(__static_key_deferred_flush); void jump_label_rate_limit(struct static_key_deferred *key, unsigned long rl) { STATIC_KEY_CHECK_USE(key); key->timeout = rl; INIT_DELAYED_WORK(&key->work, jump_label_update_timeout); } EXPORT_SYMBOL_GPL(jump_label_rate_limit); static int addr_conflict(struct jump_entry *entry, void *start, void *end) { if (jump_entry_code(entry) <= (unsigned long)end && jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start) return 1; return 0; } static int __jump_label_text_reserved(struct jump_entry *iter_start, struct jump_entry *iter_stop, void *start, void *end, bool init) { struct jump_entry *iter; iter = iter_start; while (iter < iter_stop) { if (init || !jump_entry_is_init(iter)) { if (addr_conflict(iter, start, end)) return 1; } iter++; } return 0; } #ifndef arch_jump_label_transform_static static void arch_jump_label_transform_static(struct jump_entry *entry, enum jump_label_type type) { /* nothing to do on most architectures */ } #endif static inline struct jump_entry *static_key_entries(struct static_key *key) { WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED); return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK); } static inline bool static_key_type(struct static_key *key) { return key->type & JUMP_TYPE_TRUE; } static inline bool static_key_linked(struct static_key *key) { return key->type & JUMP_TYPE_LINKED; } static inline void static_key_clear_linked(struct static_key *key) { key->type &= ~JUMP_TYPE_LINKED; } static inline void static_key_set_linked(struct static_key *key) { key->type |= JUMP_TYPE_LINKED; } /*** * A 'struct static_key' uses a union such that it either points directly * to a table of 'struct jump_entry' or to a linked list of modules which in * turn point to 'struct jump_entry' tables. * * The two lower bits of the pointer are used to keep track of which pointer * type is in use and to store the initial branch direction, we use an access * function which preserves these bits. */ static void static_key_set_entries(struct static_key *key, struct jump_entry *entries) { unsigned long type; WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->entries = entries; key->type |= type; } static enum jump_label_type jump_label_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool enabled = static_key_enabled(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return enabled ^ branch; } static bool jump_label_can_update(struct jump_entry *entry, bool init) { /* * Cannot update code that was in an init text area. */ if (!init && jump_entry_is_init(entry)) return false; if (!kernel_text_address(jump_entry_code(entry))) { /* * This skips patching built-in __exit, which * is part of init_section_contains() but is * not part of kernel_text_address(). * * Skipping built-in __exit is fine since it * will never be executed. */ WARN_ONCE(!jump_entry_is_init(entry), "can't patch jump_label at %pS", (void *)jump_entry_code(entry)); return false; } return true; } #ifndef HAVE_JUMP_LABEL_BATCH static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (jump_label_can_update(entry, init)) arch_jump_label_transform(entry, jump_label_type(entry)); } } #else static void __jump_label_update(struct static_key *key, struct jump_entry *entry, struct jump_entry *stop, bool init) { for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) { if (!jump_label_can_update(entry, init)) continue; if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) { /* * Queue is full: Apply the current queue and try again. */ arch_jump_label_transform_apply(); BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry))); } } arch_jump_label_transform_apply(); } #endif void __init jump_label_init(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct static_key *key = NULL; struct jump_entry *iter; /* * Since we are initializing the static_key.enabled field with * with the 'raw' int values (to avoid pulling in atomic.h) in * jump_label.h, let's make sure that is safe. There are only two * cases to check since we initialize to 0 or 1. */ BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0); BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1); if (static_key_initialized) return; cpus_read_lock(); jump_label_lock(); jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; /* rewrite NOPs */ if (jump_label_type(iter) == JUMP_LABEL_NOP) arch_jump_label_transform_static(iter, JUMP_LABEL_NOP); in_init = init_section_contains((void *)jump_entry_code(iter), 1); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; static_key_set_entries(key, iter); } static_key_initialized = true; jump_label_unlock(); cpus_read_unlock(); } static inline bool static_key_sealed(struct static_key *key) { return (key->type & JUMP_TYPE_LINKED) && !(key->type & ~JUMP_TYPE_MASK); } static inline void static_key_seal(struct static_key *key) { unsigned long type = key->type & JUMP_TYPE_TRUE; key->type = JUMP_TYPE_LINKED | type; } void jump_label_init_ro(void) { struct jump_entry *iter_start = __start___jump_table; struct jump_entry *iter_stop = __stop___jump_table; struct jump_entry *iter; if (WARN_ON_ONCE(!static_key_initialized)) return; cpus_read_lock(); jump_label_lock(); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk = jump_entry_key(iter); if (!is_kernel_ro_after_init((unsigned long)iterk)) continue; if (static_key_sealed(iterk)) continue; static_key_seal(iterk); } jump_label_unlock(); cpus_read_unlock(); } #ifdef CONFIG_MODULES enum jump_label_type jump_label_init_type(struct jump_entry *entry) { struct static_key *key = jump_entry_key(entry); bool type = static_key_type(key); bool branch = jump_entry_is_branch(entry); /* See the comment in linux/jump_label.h */ return type ^ branch; } struct static_key_mod { struct static_key_mod *next; struct jump_entry *entries; struct module *mod; }; static inline struct static_key_mod *static_key_mod(struct static_key *key) { WARN_ON_ONCE(!static_key_linked(key)); return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK); } /*** * key->type and key->next are the same via union. * This sets key->next and preserves the type bits. * * See additional comments above static_key_set_entries(). */ static void static_key_set_mod(struct static_key *key, struct static_key_mod *mod) { unsigned long type; WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK); type = key->type & JUMP_TYPE_MASK; key->next = mod; key->type |= type; } static int __jump_label_mod_text_reserved(void *start, void *end) { struct module *mod; int ret; preempt_disable(); mod = __module_text_address((unsigned long)start); WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod); if (!try_module_get(mod)) mod = NULL; preempt_enable(); if (!mod) return 0; ret = __jump_label_text_reserved(mod->jump_entries, mod->jump_entries + mod->num_jump_entries, start, end, mod->state == MODULE_STATE_COMING); module_put(mod); return ret; } static void __jump_label_mod_update(struct static_key *key) { struct static_key_mod *mod; for (mod = static_key_mod(key); mod; mod = mod->next) { struct jump_entry *stop; struct module *m; /* * NULL if the static_key is defined in a module * that does not use it */ if (!mod->entries) continue; m = mod->mod; if (!m) stop = __stop___jump_table; else stop = m->jump_entries + m->num_jump_entries; __jump_label_update(key, mod->entries, stop, m && m->state == MODULE_STATE_COMING); } } static int jump_label_add_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, *jlm2; /* if the module doesn't have jump label entries, just return */ if (iter_start == iter_stop) return 0; jump_label_sort_entries(iter_start, iter_stop); for (iter = iter_start; iter < iter_stop; iter++) { struct static_key *iterk; bool in_init; in_init = within_module_init(jump_entry_code(iter), mod); jump_entry_set_init(iter, in_init); iterk = jump_entry_key(iter); if (iterk == key) continue; key = iterk; if (within_module((unsigned long)key, mod)) { static_key_set_entries(key, iter); continue; } /* * If the key was sealed at init, then there's no need to keep a * reference to its module entries - just patch them now and be * done with it. */ if (static_key_sealed(key)) goto do_poke; jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm) return -ENOMEM; if (!static_key_linked(key)) { jlm2 = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL); if (!jlm2) { kfree(jlm); return -ENOMEM; } preempt_disable(); jlm2->mod = __module_address((unsigned long)key); preempt_enable(); jlm2->entries = static_key_entries(key); jlm2->next = NULL; static_key_set_mod(key, jlm2); static_key_set_linked(key); } jlm->mod = mod; jlm->entries = iter; jlm->next = static_key_mod(key); static_key_set_mod(key, jlm); static_key_set_linked(key); /* Only update if we've changed from our initial state */ do_poke: if (jump_label_type(iter) != jump_label_init_type(iter)) __jump_label_update(key, iter, iter_stop, true); } return 0; } static void jump_label_del_module(struct module *mod) { struct jump_entry *iter_start = mod->jump_entries; struct jump_entry *iter_stop = iter_start + mod->num_jump_entries; struct jump_entry *iter; struct static_key *key = NULL; struct static_key_mod *jlm, **prev; for (iter = iter_start; iter < iter_stop; iter++) { if (jump_entry_key(iter) == key) continue; key = jump_entry_key(iter); if (within_module((unsigned long)key, mod)) continue; /* No @jlm allocated because key was sealed at init. */ if (static_key_sealed(key)) continue; /* No memory during module load */ if (WARN_ON(!static_key_linked(key))) continue; prev = &key->next; jlm = static_key_mod(key); while (jlm && jlm->mod != mod) { prev = &jlm->next; jlm = jlm->next; } /* No memory during module load */ if (WARN_ON(!jlm)) continue; if (prev == &key->next) static_key_set_mod(key, jlm->next); else *prev = jlm->next; kfree(jlm); jlm = static_key_mod(key); /* if only one etry is left, fold it back into the static_key */ if (jlm->next == NULL) { static_key_set_entries(key, jlm->entries); static_key_clear_linked(key); kfree(jlm); } } } static int jump_label_module_notify(struct notifier_block *self, unsigned long val, void *data) { struct module *mod = data; int ret = 0; cpus_read_lock(); jump_label_lock(); switch (val) { case MODULE_STATE_COMING: ret = jump_label_add_module(mod); if (ret) { WARN(1, "Failed to allocate memory: jump_label may not work properly.\n"); jump_label_del_module(mod); } break; case MODULE_STATE_GOING: jump_label_del_module(mod); break; } jump_label_unlock(); cpus_read_unlock(); return notifier_from_errno(ret); } static struct notifier_block jump_label_module_nb = { .notifier_call = jump_label_module_notify, .priority = 1, /* higher than tracepoints */ }; static __init int jump_label_init_module(void) { return register_module_notifier(&jump_label_module_nb); } early_initcall(jump_label_init_module); #endif /* CONFIG_MODULES */ /*** * jump_label_text_reserved - check if addr range is reserved * @start: start text addr * @end: end text addr * * checks if the text addr located between @start and @end * overlaps with any of the jump label patch addresses. Code * that wants to modify kernel text should first verify that * it does not overlap with any of the jump label addresses. * Caller must hold jump_label_mutex. * * returns 1 if there is an overlap, 0 otherwise */ int jump_label_text_reserved(void *start, void *end) { bool init = system_state < SYSTEM_RUNNING; int ret = __jump_label_text_reserved(__start___jump_table, __stop___jump_table, start, end, init); if (ret) return ret; #ifdef CONFIG_MODULES ret = __jump_label_mod_text_reserved(start, end); #endif return ret; } static void jump_label_update(struct static_key *key) { struct jump_entry *stop = __stop___jump_table; bool init = system_state < SYSTEM_RUNNING; struct jump_entry *entry; #ifdef CONFIG_MODULES struct module *mod; if (static_key_linked(key)) { __jump_label_mod_update(key); return; } preempt_disable(); mod = __module_address((unsigned long)key); if (mod) { stop = mod->jump_entries + mod->num_jump_entries; init = mod->state == MODULE_STATE_COMING; } preempt_enable(); #endif entry = static_key_entries(key); /* if there are no users, entry can be NULL */ if (entry) __jump_label_update(key, entry, stop, init); } #ifdef CONFIG_STATIC_KEYS_SELFTEST static DEFINE_STATIC_KEY_TRUE(sk_true); static DEFINE_STATIC_KEY_FALSE(sk_false); static __init int jump_label_test(void) { int i; for (i = 0; i < 2; i++) { WARN_ON(static_key_enabled(&sk_true.key) != true); WARN_ON(static_key_enabled(&sk_false.key) != false); WARN_ON(!static_branch_likely(&sk_true)); WARN_ON(!static_branch_unlikely(&sk_true)); WARN_ON(static_branch_likely(&sk_false)); WARN_ON(static_branch_unlikely(&sk_false)); static_branch_disable(&sk_true); static_branch_enable(&sk_false); WARN_ON(static_key_enabled(&sk_true.key) == true); WARN_ON(static_key_enabled(&sk_false.key) == false); WARN_ON(static_branch_likely(&sk_true)); WARN_ON(static_branch_unlikely(&sk_true)); WARN_ON(!static_branch_likely(&sk_false)); WARN_ON(!static_branch_unlikely(&sk_false)); static_branch_enable(&sk_true); static_branch_disable(&sk_false); } return 0; } early_initcall(jump_label_test); #endif /* STATIC_KEYS_SELFTEST */ |
| 2 2 157 157 157 157 157 157 157 328 230 229 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 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 | // SPDX-License-Identifier: GPL-2.0 /* * Kernel timekeeping code and accessor functions. Based on code from * timer.c, moved in commit 8524070b7982. */ #include <linux/timekeeper_internal.h> #include <linux/module.h> #include <linux/interrupt.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/nmi.h> #include <linux/sched.h> #include <linux/sched/loadavg.h> #include <linux/sched/clock.h> #include <linux/syscore_ops.h> #include <linux/clocksource.h> #include <linux/jiffies.h> #include <linux/time.h> #include <linux/timex.h> #include <linux/tick.h> #include <linux/stop_machine.h> #include <linux/pvclock_gtod.h> #include <linux/compiler.h> #include <linux/audit.h> #include <linux/random.h> #include "tick-internal.h" #include "ntp_internal.h" #include "timekeeping_internal.h" #define TK_CLEAR_NTP (1 << 0) #define TK_MIRROR (1 << 1) #define TK_CLOCK_WAS_SET (1 << 2) enum timekeeping_adv_mode { /* Update timekeeper when a tick has passed */ TK_ADV_TICK, /* Update timekeeper on a direct frequency change */ TK_ADV_FREQ }; DEFINE_RAW_SPINLOCK(timekeeper_lock); /* * The most important data for readout fits into a single 64 byte * cache line. */ static struct { seqcount_raw_spinlock_t seq; struct timekeeper timekeeper; } tk_core ____cacheline_aligned = { .seq = SEQCNT_RAW_SPINLOCK_ZERO(tk_core.seq, &timekeeper_lock), }; static struct timekeeper shadow_timekeeper; /* flag for if timekeeping is suspended */ int __read_mostly timekeeping_suspended; /** * struct tk_fast - NMI safe timekeeper * @seq: Sequence counter for protecting updates. The lowest bit * is the index for the tk_read_base array * @base: tk_read_base array. Access is indexed by the lowest bit of * @seq. * * See @update_fast_timekeeper() below. */ struct tk_fast { seqcount_latch_t seq; struct tk_read_base base[2]; }; /* Suspend-time cycles value for halted fast timekeeper. */ static u64 cycles_at_suspend; static u64 dummy_clock_read(struct clocksource *cs) { if (timekeeping_suspended) return cycles_at_suspend; return local_clock(); } static struct clocksource dummy_clock = { .read = dummy_clock_read, }; /* * Boot time initialization which allows local_clock() to be utilized * during early boot when clocksources are not available. local_clock() * returns nanoseconds already so no conversion is required, hence mult=1 * and shift=0. When the first proper clocksource is installed then * the fast time keepers are updated with the correct values. */ #define FAST_TK_INIT \ { \ .clock = &dummy_clock, \ .mask = CLOCKSOURCE_MASK(64), \ .mult = 1, \ .shift = 0, \ } static struct tk_fast tk_fast_mono ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_mono.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static struct tk_fast tk_fast_raw ____cacheline_aligned = { .seq = SEQCNT_LATCH_ZERO(tk_fast_raw.seq), .base[0] = FAST_TK_INIT, .base[1] = FAST_TK_INIT, }; static inline void tk_normalize_xtime(struct timekeeper *tk) { while (tk->tkr_mono.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_mono.shift)) { tk->tkr_mono.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec++; } while (tk->tkr_raw.xtime_nsec >= ((u64)NSEC_PER_SEC << tk->tkr_raw.shift)) { tk->tkr_raw.xtime_nsec -= (u64)NSEC_PER_SEC << tk->tkr_raw.shift; tk->raw_sec++; } } static inline struct timespec64 tk_xtime(const struct timekeeper *tk) { struct timespec64 ts; ts.tv_sec = tk->xtime_sec; ts.tv_nsec = (long)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); return ts; } static void tk_set_xtime(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec = ts->tv_sec; tk->tkr_mono.xtime_nsec = (u64)ts->tv_nsec << tk->tkr_mono.shift; } static void tk_xtime_add(struct timekeeper *tk, const struct timespec64 *ts) { tk->xtime_sec += ts->tv_sec; tk->tkr_mono.xtime_nsec += (u64)ts->tv_nsec << tk->tkr_mono.shift; tk_normalize_xtime(tk); } static void tk_set_wall_to_mono(struct timekeeper *tk, struct timespec64 wtm) { struct timespec64 tmp; /* * Verify consistency of: offset_real = -wall_to_monotonic * before modifying anything */ set_normalized_timespec64(&tmp, -tk->wall_to_monotonic.tv_sec, -tk->wall_to_monotonic.tv_nsec); WARN_ON_ONCE(tk->offs_real != timespec64_to_ktime(tmp)); tk->wall_to_monotonic = wtm; set_normalized_timespec64(&tmp, -wtm.tv_sec, -wtm.tv_nsec); tk->offs_real = timespec64_to_ktime(tmp); tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tk->tai_offset, 0)); } static inline void tk_update_sleep_time(struct timekeeper *tk, ktime_t delta) { tk->offs_boot = ktime_add(tk->offs_boot, delta); /* * Timespec representation for VDSO update to avoid 64bit division * on every update. */ tk->monotonic_to_boot = ktime_to_timespec64(tk->offs_boot); } /* * tk_clock_read - atomic clocksource read() helper * * This helper is necessary to use in the read paths because, while the * seqcount ensures we don't return a bad value while structures are updated, * it doesn't protect from potential crashes. There is the possibility that * the tkr's clocksource may change between the read reference, and the * clock reference passed to the read function. This can cause crashes if * the wrong clocksource is passed to the wrong read function. * This isn't necessary to use when holding the timekeeper_lock or doing * a read of the fast-timekeeper tkrs (which is protected by its own locking * and update logic). */ static inline u64 tk_clock_read(const struct tk_read_base *tkr) { struct clocksource *clock = READ_ONCE(tkr->clock); return clock->read(clock); } #ifdef CONFIG_DEBUG_TIMEKEEPING #define WARNING_FREQ (HZ*300) /* 5 minute rate-limiting */ static void timekeeping_check_update(struct timekeeper *tk, u64 offset) { u64 max_cycles = tk->tkr_mono.clock->max_cycles; const char *name = tk->tkr_mono.clock->name; if (offset > max_cycles) { printk_deferred("WARNING: timekeeping: Cycle offset (%lld) is larger than allowed by the '%s' clock's max_cycles value (%lld): time overflow danger\n", offset, name, max_cycles); printk_deferred(" timekeeping: Your kernel is sick, but tries to cope by capping time updates\n"); } else { if (offset > (max_cycles >> 1)) { printk_deferred("INFO: timekeeping: Cycle offset (%lld) is larger than the '%s' clock's 50%% safety margin (%lld)\n", offset, name, max_cycles >> 1); printk_deferred(" timekeeping: Your kernel is still fine, but is feeling a bit nervous\n"); } } if (tk->underflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Underflow in clocksource '%s' observed, time update ignored.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->underflow_seen = 0; } if (tk->overflow_seen) { if (jiffies - tk->last_warning > WARNING_FREQ) { printk_deferred("WARNING: Overflow in clocksource '%s' observed, time update capped.\n", name); printk_deferred(" Please report this, consider using a different clocksource, if possible.\n"); printk_deferred(" Your kernel is probably still fine.\n"); tk->last_warning = jiffies; } tk->overflow_seen = 0; } } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles); static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { struct timekeeper *tk = &tk_core.timekeeper; u64 now, last, mask, max, delta; unsigned int seq; /* * Since we're called holding a seqcount, the data may shift * under us while we're doing the calculation. This can cause * false positives, since we'd note a problem but throw the * results away. So nest another seqcount here to atomically * grab the points we are checking with. */ do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(tkr); last = tkr->cycle_last; mask = tkr->mask; max = tkr->clock->max_cycles; } while (read_seqcount_retry(&tk_core.seq, seq)); delta = clocksource_delta(now, last, mask); /* * Try to catch underflows by checking if we are seeing small * mask-relative negative values. */ if (unlikely((~delta & mask) < (mask >> 3))) tk->underflow_seen = 1; /* Check for multiplication overflows */ if (unlikely(delta > max)) tk->overflow_seen = 1; /* timekeeping_cycles_to_ns() handles both under and overflow */ return timekeeping_cycles_to_ns(tkr, now); } #else static inline void timekeeping_check_update(struct timekeeper *tk, u64 offset) { } static inline u64 timekeeping_debug_get_ns(const struct tk_read_base *tkr) { BUG(); } #endif /** * tk_setup_internals - Set up internals to use clocksource clock. * * @tk: The target timekeeper to setup. * @clock: Pointer to clocksource. * * Calculates a fixed cycle/nsec interval for a given clocksource/adjustment * pair and interval request. * * Unless you're the timekeeping code, you should not be using this! */ static void tk_setup_internals(struct timekeeper *tk, struct clocksource *clock) { u64 interval; u64 tmp, ntpinterval; struct clocksource *old_clock; ++tk->cs_was_changed_seq; old_clock = tk->tkr_mono.clock; tk->tkr_mono.clock = clock; tk->tkr_mono.mask = clock->mask; tk->tkr_mono.cycle_last = tk_clock_read(&tk->tkr_mono); tk->tkr_raw.clock = clock; tk->tkr_raw.mask = clock->mask; tk->tkr_raw.cycle_last = tk->tkr_mono.cycle_last; /* Do the ns -> cycle conversion first, using original mult */ tmp = NTP_INTERVAL_LENGTH; tmp <<= clock->shift; ntpinterval = tmp; tmp += clock->mult/2; do_div(tmp, clock->mult); if (tmp == 0) tmp = 1; interval = (u64) tmp; tk->cycle_interval = interval; /* Go back from cycles -> shifted ns */ tk->xtime_interval = interval * clock->mult; tk->xtime_remainder = ntpinterval - tk->xtime_interval; tk->raw_interval = interval * clock->mult; /* if changing clocks, convert xtime_nsec shift units */ if (old_clock) { int shift_change = clock->shift - old_clock->shift; if (shift_change < 0) { tk->tkr_mono.xtime_nsec >>= -shift_change; tk->tkr_raw.xtime_nsec >>= -shift_change; } else { tk->tkr_mono.xtime_nsec <<= shift_change; tk->tkr_raw.xtime_nsec <<= shift_change; } } tk->tkr_mono.shift = clock->shift; tk->tkr_raw.shift = clock->shift; tk->ntp_error = 0; tk->ntp_error_shift = NTP_SCALE_SHIFT - clock->shift; tk->ntp_tick = ntpinterval << tk->ntp_error_shift; /* * The timekeeper keeps its own mult values for the currently * active clocksource. These value will be adjusted via NTP * to counteract clock drifting. */ tk->tkr_mono.mult = clock->mult; tk->tkr_raw.mult = clock->mult; tk->ntp_err_mult = 0; tk->skip_second_overflow = 0; } /* Timekeeper helper functions. */ static noinline u64 delta_to_ns_safe(const struct tk_read_base *tkr, u64 delta) { return mul_u64_u32_add_u64_shr(delta, tkr->mult, tkr->xtime_nsec, tkr->shift); } static inline u64 timekeeping_cycles_to_ns(const struct tk_read_base *tkr, u64 cycles) { /* Calculate the delta since the last update_wall_time() */ u64 mask = tkr->mask, delta = (cycles - tkr->cycle_last) & mask; /* * This detects both negative motion and the case where the delta * overflows the multiplication with tkr->mult. */ if (unlikely(delta > tkr->clock->max_cycles)) { /* * Handle clocksource inconsistency between CPUs to prevent * time from going backwards by checking for the MSB of the * mask being set in the delta. */ if (delta & ~(mask >> 1)) return tkr->xtime_nsec >> tkr->shift; return delta_to_ns_safe(tkr, delta); } return ((delta * tkr->mult) + tkr->xtime_nsec) >> tkr->shift; } static __always_inline u64 __timekeeping_get_ns(const struct tk_read_base *tkr) { return timekeeping_cycles_to_ns(tkr, tk_clock_read(tkr)); } static inline u64 timekeeping_get_ns(const struct tk_read_base *tkr) { if (IS_ENABLED(CONFIG_DEBUG_TIMEKEEPING)) return timekeeping_debug_get_ns(tkr); return __timekeeping_get_ns(tkr); } /** * update_fast_timekeeper - Update the fast and NMI safe monotonic timekeeper. * @tkr: Timekeeping readout base from which we take the update * @tkf: Pointer to NMI safe timekeeper * * We want to use this from any context including NMI and tracing / * instrumenting the timekeeping code itself. * * Employ the latch technique; see @raw_write_seqcount_latch. * * So if a NMI hits the update of base[0] then it will use base[1] * which is still consistent. In the worst case this can result is a * slightly wrong timestamp (a few nanoseconds). See * @ktime_get_mono_fast_ns. */ static void update_fast_timekeeper(const struct tk_read_base *tkr, struct tk_fast *tkf) { struct tk_read_base *base = tkf->base; /* Force readers off to base[1] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[0] */ memcpy(base, tkr, sizeof(*base)); /* Force readers back to base[0] */ raw_write_seqcount_latch(&tkf->seq); /* Update base[1] */ memcpy(base + 1, base, sizeof(*base)); } static __always_inline u64 __ktime_get_fast_ns(struct tk_fast *tkf) { struct tk_read_base *tkr; unsigned int seq; u64 now; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); now = ktime_to_ns(tkr->base); now += __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); return now; } /** * ktime_get_mono_fast_ns - Fast NMI safe access to clock monotonic * * This timestamp is not guaranteed to be monotonic across an update. * The timestamp is calculated by: * * now = base_mono + clock_delta * slope * * So if the update lowers the slope, readers who are forced to the * not yet updated second array are still using the old steeper slope. * * tmono * ^ * | o n * | o n * | u * | o * |o * |12345678---> reader order * * o = old slope * u = update * n = new slope * * So reader 6 will observe time going backwards versus reader 5. * * While other CPUs are likely to be able to observe that, the only way * for a CPU local observation is when an NMI hits in the middle of * the update. Timestamps taken from that NMI context might be ahead * of the following timestamps. Callers need to be aware of that and * deal with it. */ u64 notrace ktime_get_mono_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_mono); } EXPORT_SYMBOL_GPL(ktime_get_mono_fast_ns); /** * ktime_get_raw_fast_ns - Fast NMI safe access to clock monotonic raw * * Contrary to ktime_get_mono_fast_ns() this is always correct because the * conversion factor is not affected by NTP/PTP correction. */ u64 notrace ktime_get_raw_fast_ns(void) { return __ktime_get_fast_ns(&tk_fast_raw); } EXPORT_SYMBOL_GPL(ktime_get_raw_fast_ns); /** * ktime_get_boot_fast_ns - NMI safe and fast access to boot clock. * * To keep it NMI safe since we're accessing from tracing, we're not using a * separate timekeeper with updates to monotonic clock and boot offset * protected with seqcounts. This has the following minor side effects: * * (1) Its possible that a timestamp be taken after the boot offset is updated * but before the timekeeper is updated. If this happens, the new boot offset * is added to the old timekeeping making the clock appear to update slightly * earlier: * CPU 0 CPU 1 * timekeeping_inject_sleeptime64() * __timekeeping_inject_sleeptime(tk, delta); * timestamp(); * timekeeping_update(tk, TK_CLEAR_NTP...); * * (2) On 32-bit systems, the 64-bit boot offset (tk->offs_boot) may be * partially updated. Since the tk->offs_boot update is a rare event, this * should be a rare occurrence which postprocessing should be able to handle. * * The caveats vs. timestamp ordering as documented for ktime_get_mono_fast_ns() * apply as well. */ u64 notrace ktime_get_boot_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_boot))); } EXPORT_SYMBOL_GPL(ktime_get_boot_fast_ns); /** * ktime_get_tai_fast_ns - NMI safe and fast access to tai clock. * * The same limitations as described for ktime_get_boot_fast_ns() apply. The * mono time and the TAI offset are not read atomically which may yield wrong * readouts. However, an update of the TAI offset is an rare event e.g., caused * by settime or adjtimex with an offset. The user of this function has to deal * with the possibility of wrong timestamps in post processing. */ u64 notrace ktime_get_tai_fast_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; return (ktime_get_mono_fast_ns() + ktime_to_ns(data_race(tk->offs_tai))); } EXPORT_SYMBOL_GPL(ktime_get_tai_fast_ns); static __always_inline u64 __ktime_get_real_fast(struct tk_fast *tkf, u64 *mono) { struct tk_read_base *tkr; u64 basem, baser, delta; unsigned int seq; do { seq = raw_read_seqcount_latch(&tkf->seq); tkr = tkf->base + (seq & 0x01); basem = ktime_to_ns(tkr->base); baser = ktime_to_ns(tkr->base_real); delta = __timekeeping_get_ns(tkr); } while (raw_read_seqcount_latch_retry(&tkf->seq, seq)); if (mono) *mono = basem + delta; return baser + delta; } /** * ktime_get_real_fast_ns: - NMI safe and fast access to clock realtime. * * See ktime_get_mono_fast_ns() for documentation of the time stamp ordering. */ u64 ktime_get_real_fast_ns(void) { return __ktime_get_real_fast(&tk_fast_mono, NULL); } EXPORT_SYMBOL_GPL(ktime_get_real_fast_ns); /** * ktime_get_fast_timestamps: - NMI safe timestamps * @snapshot: Pointer to timestamp storage * * Stores clock monotonic, boottime and realtime timestamps. * * Boot time is a racy access on 32bit systems if the sleep time injection * happens late during resume and not in timekeeping_resume(). That could * be avoided by expanding struct tk_read_base with boot offset for 32bit * and adding more overhead to the update. As this is a hard to observe * once per resume event which can be filtered with reasonable effort using * the accurate mono/real timestamps, it's probably not worth the trouble. * * Aside of that it might be possible on 32 and 64 bit to observe the * following when the sleep time injection happens late: * * CPU 0 CPU 1 * timekeeping_resume() * ktime_get_fast_timestamps() * mono, real = __ktime_get_real_fast() * inject_sleep_time() * update boot offset * boot = mono + bootoffset; * * That means that boot time already has the sleep time adjustment, but * real time does not. On the next readout both are in sync again. * * Preventing this for 64bit is not really feasible without destroying the * careful cache layout of the timekeeper because the sequence count and * struct tk_read_base would then need two cache lines instead of one. * * Access to the time keeper clock source is disabled across the innermost * steps of suspend/resume. The accessors still work, but the timestamps * are frozen until time keeping is resumed which happens very early. * * For regular suspend/resume there is no observable difference vs. sched * clock, but it might affect some of the nasty low level debug printks. * * OTOH, access to sched clock is not guaranteed across suspend/resume on * all systems either so it depends on the hardware in use. * * If that turns out to be a real problem then this could be mitigated by * using sched clock in a similar way as during early boot. But it's not as * trivial as on early boot because it needs some careful protection * against the clock monotonic timestamp jumping backwards on resume. */ void ktime_get_fast_timestamps(struct ktime_timestamps *snapshot) { struct timekeeper *tk = &tk_core.timekeeper; snapshot->real = __ktime_get_real_fast(&tk_fast_mono, &snapshot->mono); snapshot->boot = snapshot->mono + ktime_to_ns(data_race(tk->offs_boot)); } /** * halt_fast_timekeeper - Prevent fast timekeeper from accessing clocksource. * @tk: Timekeeper to snapshot. * * It generally is unsafe to access the clocksource after timekeeping has been * suspended, so take a snapshot of the readout base of @tk and use it as the * fast timekeeper's readout base while suspended. It will return the same * number of cycles every time until timekeeping is resumed at which time the * proper readout base for the fast timekeeper will be restored automatically. */ static void halt_fast_timekeeper(const struct timekeeper *tk) { static struct tk_read_base tkr_dummy; const struct tk_read_base *tkr = &tk->tkr_mono; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); cycles_at_suspend = tk_clock_read(tkr); tkr_dummy.clock = &dummy_clock; tkr_dummy.base_real = tkr->base + tk->offs_real; update_fast_timekeeper(&tkr_dummy, &tk_fast_mono); tkr = &tk->tkr_raw; memcpy(&tkr_dummy, tkr, sizeof(tkr_dummy)); tkr_dummy.clock = &dummy_clock; update_fast_timekeeper(&tkr_dummy, &tk_fast_raw); } static RAW_NOTIFIER_HEAD(pvclock_gtod_chain); static void update_pvclock_gtod(struct timekeeper *tk, bool was_set) { raw_notifier_call_chain(&pvclock_gtod_chain, was_set, tk); } /** * pvclock_gtod_register_notifier - register a pvclock timedata update listener * @nb: Pointer to the notifier block to register */ int pvclock_gtod_register_notifier(struct notifier_block *nb) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_register(&pvclock_gtod_chain, nb); update_pvclock_gtod(tk, true); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_register_notifier); /** * pvclock_gtod_unregister_notifier - unregister a pvclock * timedata update listener * @nb: Pointer to the notifier block to unregister */ int pvclock_gtod_unregister_notifier(struct notifier_block *nb) { unsigned long flags; int ret; raw_spin_lock_irqsave(&timekeeper_lock, flags); ret = raw_notifier_chain_unregister(&pvclock_gtod_chain, nb); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return ret; } EXPORT_SYMBOL_GPL(pvclock_gtod_unregister_notifier); /* * tk_update_leap_state - helper to update the next_leap_ktime */ static inline void tk_update_leap_state(struct timekeeper *tk) { tk->next_leap_ktime = ntp_get_next_leap(); if (tk->next_leap_ktime != KTIME_MAX) /* Convert to monotonic time */ tk->next_leap_ktime = ktime_sub(tk->next_leap_ktime, tk->offs_real); } /* * Update the ktime_t based scalar nsec members of the timekeeper */ static inline void tk_update_ktime_data(struct timekeeper *tk) { u64 seconds; u32 nsec; /* * The xtime based monotonic readout is: * nsec = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec + now(); * The ktime based monotonic readout is: * nsec = base_mono + now(); * ==> base_mono = (xtime_sec + wtm_sec) * 1e9 + wtm_nsec */ seconds = (u64)(tk->xtime_sec + tk->wall_to_monotonic.tv_sec); nsec = (u32) tk->wall_to_monotonic.tv_nsec; tk->tkr_mono.base = ns_to_ktime(seconds * NSEC_PER_SEC + nsec); /* * The sum of the nanoseconds portions of xtime and * wall_to_monotonic can be greater/equal one second. Take * this into account before updating tk->ktime_sec. */ nsec += (u32)(tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift); if (nsec >= NSEC_PER_SEC) seconds++; tk->ktime_sec = seconds; /* Update the monotonic raw base */ tk->tkr_raw.base = ns_to_ktime(tk->raw_sec * NSEC_PER_SEC); } /* must hold timekeeper_lock */ static void timekeeping_update(struct timekeeper *tk, unsigned int action) { if (action & TK_CLEAR_NTP) { tk->ntp_error = 0; ntp_clear(); } tk_update_leap_state(tk); tk_update_ktime_data(tk); update_vsyscall(tk); update_pvclock_gtod(tk, action & TK_CLOCK_WAS_SET); tk->tkr_mono.base_real = tk->tkr_mono.base + tk->offs_real; update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono); update_fast_timekeeper(&tk->tkr_raw, &tk_fast_raw); if (action & TK_CLOCK_WAS_SET) tk->clock_was_set_seq++; /* * The mirroring of the data to the shadow-timekeeper needs * to happen last here to ensure we don't over-write the * timekeeper structure on the next update with stale data */ if (action & TK_MIRROR) memcpy(&shadow_timekeeper, &tk_core.timekeeper, sizeof(tk_core.timekeeper)); } /** * timekeeping_forward_now - update clock to the current time * @tk: Pointer to the timekeeper to update * * Forward the current clock to update its state since the last call to * update_wall_time(). This is useful before significant clock changes, * as it avoids having to deal with this time offset explicitly. */ static void timekeeping_forward_now(struct timekeeper *tk) { u64 cycle_now, delta; cycle_now = tk_clock_read(&tk->tkr_mono); delta = clocksource_delta(cycle_now, tk->tkr_mono.cycle_last, tk->tkr_mono.mask); tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; while (delta > 0) { u64 max = tk->tkr_mono.clock->max_cycles; u64 incr = delta < max ? delta : max; tk->tkr_mono.xtime_nsec += incr * tk->tkr_mono.mult; tk->tkr_raw.xtime_nsec += incr * tk->tkr_raw.mult; tk_normalize_xtime(tk); delta -= incr; } } /** * ktime_get_real_ts64 - Returns the time of day in a timespec64. * @ts: pointer to the timespec to be set * * Returns the time of day in a timespec64 (WARN if suspended). */ void ktime_get_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_real_ts64); ktime_t ktime_get(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get); u32 ktime_get_resolution_ns(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u32 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); nsecs = tk->tkr_mono.mult >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return nsecs; } EXPORT_SYMBOL_GPL(ktime_get_resolution_ns); static ktime_t *offsets[TK_OFFS_MAX] = { [TK_OFFS_REAL] = &tk_core.timekeeper.offs_real, [TK_OFFS_BOOT] = &tk_core.timekeeper.offs_boot, [TK_OFFS_TAI] = &tk_core.timekeeper.offs_tai, }; ktime_t ktime_get_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = timekeeping_get_ns(&tk->tkr_mono); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_with_offset); ktime_t ktime_get_coarse_with_offset(enum tk_offsets offs) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base, *offset = offsets[offs]; u64 nsecs; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); base = ktime_add(tk->tkr_mono.base, *offset); nsecs = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_coarse_with_offset); /** * ktime_mono_to_any() - convert monotonic time to any other time * @tmono: time to convert. * @offs: which offset to use */ ktime_t ktime_mono_to_any(ktime_t tmono, enum tk_offsets offs) { ktime_t *offset = offsets[offs]; unsigned int seq; ktime_t tconv; do { seq = read_seqcount_begin(&tk_core.seq); tconv = ktime_add(tmono, *offset); } while (read_seqcount_retry(&tk_core.seq, seq)); return tconv; } EXPORT_SYMBOL_GPL(ktime_mono_to_any); /** * ktime_get_raw - Returns the raw monotonic time in ktime_t format */ ktime_t ktime_get_raw(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_raw.base; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); return ktime_add_ns(base, nsecs); } EXPORT_SYMBOL_GPL(ktime_get_raw); /** * ktime_get_ts64 - get the monotonic clock in timespec64 format * @ts: pointer to timespec variable * * The function calculates the monotonic clock from the realtime * clock and the wall_to_monotonic offset and stores the result * in normalized timespec64 format in the variable pointed to by @ts. */ void ktime_get_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 tomono; unsigned int seq; u64 nsec; WARN_ON(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->xtime_sec; nsec = timekeeping_get_ns(&tk->tkr_mono); tomono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_sec += tomono.tv_sec; ts->tv_nsec = 0; timespec64_add_ns(ts, nsec + tomono.tv_nsec); } EXPORT_SYMBOL_GPL(ktime_get_ts64); /** * ktime_get_seconds - Get the seconds portion of CLOCK_MONOTONIC * * Returns the seconds portion of CLOCK_MONOTONIC with a single non * serialized read. tk->ktime_sec is of type 'unsigned long' so this * works on both 32 and 64 bit systems. On 32 bit systems the readout * covers ~136 years of uptime which should be enough to prevent * premature wrap arounds. */ time64_t ktime_get_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; WARN_ON(timekeeping_suspended); return tk->ktime_sec; } EXPORT_SYMBOL_GPL(ktime_get_seconds); /** * ktime_get_real_seconds - Get the seconds portion of CLOCK_REALTIME * * Returns the wall clock seconds since 1970. * * For 64bit systems the fast access to tk->xtime_sec is preserved. On * 32bit systems the access must be protected with the sequence * counter to provide "atomic" access to the 64bit tk->xtime_sec * value. */ time64_t ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; time64_t seconds; unsigned int seq; if (IS_ENABLED(CONFIG_64BIT)) return tk->xtime_sec; do { seq = read_seqcount_begin(&tk_core.seq); seconds = tk->xtime_sec; } while (read_seqcount_retry(&tk_core.seq, seq)); return seconds; } EXPORT_SYMBOL_GPL(ktime_get_real_seconds); /** * __ktime_get_real_seconds - The same as ktime_get_real_seconds * but without the sequence counter protect. This internal function * is called just when timekeeping lock is already held. */ noinstr time64_t __ktime_get_real_seconds(void) { struct timekeeper *tk = &tk_core.timekeeper; return tk->xtime_sec; } /** * ktime_get_snapshot - snapshots the realtime/monotonic raw clocks with counter * @systime_snapshot: pointer to struct receiving the system time snapshot */ void ktime_get_snapshot(struct system_time_snapshot *systime_snapshot) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base_raw; ktime_t base_real; u64 nsec_raw; u64 nsec_real; u64 now; WARN_ON_ONCE(timekeeping_suspended); do { seq = read_seqcount_begin(&tk_core.seq); now = tk_clock_read(&tk->tkr_mono); systime_snapshot->cs_id = tk->tkr_mono.clock->id; systime_snapshot->cs_was_changed_seq = tk->cs_was_changed_seq; systime_snapshot->clock_was_set_seq = tk->clock_was_set_seq; base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, now); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, now); } while (read_seqcount_retry(&tk_core.seq, seq)); systime_snapshot->cycles = now; systime_snapshot->real = ktime_add_ns(base_real, nsec_real); systime_snapshot->raw = ktime_add_ns(base_raw, nsec_raw); } EXPORT_SYMBOL_GPL(ktime_get_snapshot); /* Scale base by mult/div checking for overflow */ static int scale64_check_overflow(u64 mult, u64 div, u64 *base) { u64 tmp, rem; tmp = div64_u64_rem(*base, div, &rem); if (((int)sizeof(u64)*8 - fls64(mult) < fls64(tmp)) || ((int)sizeof(u64)*8 - fls64(mult) < fls64(rem))) return -EOVERFLOW; tmp *= mult; rem = div64_u64(rem * mult, div); *base = tmp + rem; return 0; } /** * adjust_historical_crosststamp - adjust crosstimestamp previous to current interval * @history: Snapshot representing start of history * @partial_history_cycles: Cycle offset into history (fractional part) * @total_history_cycles: Total history length in cycles * @discontinuity: True indicates clock was set on history period * @ts: Cross timestamp that should be adjusted using * partial/total ratio * * Helper function used by get_device_system_crosststamp() to correct the * crosstimestamp corresponding to the start of the current interval to the * system counter value (timestamp point) provided by the driver. The * total_history_* quantities are the total history starting at the provided * reference point and ending at the start of the current interval. The cycle * count between the driver timestamp point and the start of the current * interval is partial_history_cycles. */ static int adjust_historical_crosststamp(struct system_time_snapshot *history, u64 partial_history_cycles, u64 total_history_cycles, bool discontinuity, struct system_device_crosststamp *ts) { struct timekeeper *tk = &tk_core.timekeeper; u64 corr_raw, corr_real; bool interp_forward; int ret; if (total_history_cycles == 0 || partial_history_cycles == 0) return 0; /* Interpolate shortest distance from beginning or end of history */ interp_forward = partial_history_cycles > total_history_cycles / 2; partial_history_cycles = interp_forward ? total_history_cycles - partial_history_cycles : partial_history_cycles; /* * Scale the monotonic raw time delta by: * partial_history_cycles / total_history_cycles */ corr_raw = (u64)ktime_to_ns( ktime_sub(ts->sys_monoraw, history->raw)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_raw); if (ret) return ret; /* * If there is a discontinuity in the history, scale monotonic raw * correction by: * mult(real)/mult(raw) yielding the realtime correction * Otherwise, calculate the realtime correction similar to monotonic * raw calculation */ if (discontinuity) { corr_real = mul_u64_u32_div (corr_raw, tk->tkr_mono.mult, tk->tkr_raw.mult); } else { corr_real = (u64)ktime_to_ns( ktime_sub(ts->sys_realtime, history->real)); ret = scale64_check_overflow(partial_history_cycles, total_history_cycles, &corr_real); if (ret) return ret; } /* Fixup monotonic raw and real time time values */ if (interp_forward) { ts->sys_monoraw = ktime_add_ns(history->raw, corr_raw); ts->sys_realtime = ktime_add_ns(history->real, corr_real); } else { ts->sys_monoraw = ktime_sub_ns(ts->sys_monoraw, corr_raw); ts->sys_realtime = ktime_sub_ns(ts->sys_realtime, corr_real); } return 0; } /* * timestamp_in_interval - true if ts is chronologically in [start, end] * * True if ts occurs chronologically at or after start, and before or at end. */ static bool timestamp_in_interval(u64 start, u64 end, u64 ts) { if (ts >= start && ts <= end) return true; if (start > end && (ts >= start || ts <= end)) return true; return false; } /** * get_device_system_crosststamp - Synchronously capture system/device timestamp * @get_time_fn: Callback to get simultaneous device time and * system counter from the device driver * @ctx: Context passed to get_time_fn() * @history_begin: Historical reference point used to interpolate system * time when counter provided by the driver is before the current interval * @xtstamp: Receives simultaneously captured system and device time * * Reads a timestamp from a device and correlates it to system time */ int get_device_system_crosststamp(int (*get_time_fn) (ktime_t *device_time, struct system_counterval_t *sys_counterval, void *ctx), void *ctx, struct system_time_snapshot *history_begin, struct system_device_crosststamp *xtstamp) { struct system_counterval_t system_counterval; struct timekeeper *tk = &tk_core.timekeeper; u64 cycles, now, interval_start; unsigned int clock_was_set_seq = 0; ktime_t base_real, base_raw; u64 nsec_real, nsec_raw; u8 cs_was_changed_seq; unsigned int seq; bool do_interp; int ret; do { seq = read_seqcount_begin(&tk_core.seq); /* * Try to synchronously capture device time and a system * counter value calling back into the device driver */ ret = get_time_fn(&xtstamp->device, &system_counterval, ctx); if (ret) return ret; /* * Verify that the clocksource ID associated with the captured * system counter value is the same as for the currently * installed timekeeper clocksource */ if (system_counterval.cs_id == CSID_GENERIC || tk->tkr_mono.clock->id != system_counterval.cs_id) return -ENODEV; cycles = system_counterval.cycles; /* * Check whether the system counter value provided by the * device driver is on the current timekeeping interval. */ now = tk_clock_read(&tk->tkr_mono); interval_start = tk->tkr_mono.cycle_last; if (!timestamp_in_interval(interval_start, now, cycles)) { clock_was_set_seq = tk->clock_was_set_seq; cs_was_changed_seq = tk->cs_was_changed_seq; cycles = interval_start; do_interp = true; } else { do_interp = false; } base_real = ktime_add(tk->tkr_mono.base, tk_core.timekeeper.offs_real); base_raw = tk->tkr_raw.base; nsec_real = timekeeping_cycles_to_ns(&tk->tkr_mono, cycles); nsec_raw = timekeeping_cycles_to_ns(&tk->tkr_raw, cycles); } while (read_seqcount_retry(&tk_core.seq, seq)); xtstamp->sys_realtime = ktime_add_ns(base_real, nsec_real); xtstamp->sys_monoraw = ktime_add_ns(base_raw, nsec_raw); /* * Interpolate if necessary, adjusting back from the start of the * current interval */ if (do_interp) { u64 partial_history_cycles, total_history_cycles; bool discontinuity; /* * Check that the counter value is not before the provided * history reference and that the history doesn't cross a * clocksource change */ if (!history_begin || !timestamp_in_interval(history_begin->cycles, cycles, system_counterval.cycles) || history_begin->cs_was_changed_seq != cs_was_changed_seq) return -EINVAL; partial_history_cycles = cycles - system_counterval.cycles; total_history_cycles = cycles - history_begin->cycles; discontinuity = history_begin->clock_was_set_seq != clock_was_set_seq; ret = adjust_historical_crosststamp(history_begin, partial_history_cycles, total_history_cycles, discontinuity, xtstamp); if (ret) return ret; } return 0; } EXPORT_SYMBOL_GPL(get_device_system_crosststamp); /** * do_settimeofday64 - Sets the time of day. * @ts: pointer to the timespec64 variable containing the new time * * Sets the time of day to the new time and update NTP and notify hrtimers */ int do_settimeofday64(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 ts_delta, xt; unsigned long flags; int ret = 0; if (!timespec64_valid_settod(ts)) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); xt = tk_xtime(tk); ts_delta = timespec64_sub(*ts, xt); if (timespec64_compare(&tk->wall_to_monotonic, &ts_delta) > 0) { ret = -EINVAL; goto out; } tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts_delta)); tk_set_xtime(tk, ts); out: timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); if (!ret) { audit_tk_injoffset(ts_delta); add_device_randomness(ts, sizeof(*ts)); } return ret; } EXPORT_SYMBOL(do_settimeofday64); /** * timekeeping_inject_offset - Adds or subtracts from the current time. * @ts: Pointer to the timespec variable containing the offset * * Adds or subtracts an offset value from the current time. */ static int timekeeping_inject_offset(const struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 tmp; int ret = 0; if (ts->tv_nsec < 0 || ts->tv_nsec >= NSEC_PER_SEC) return -EINVAL; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); /* Make sure the proposed value is valid */ tmp = timespec64_add(tk_xtime(tk), *ts); if (timespec64_compare(&tk->wall_to_monotonic, ts) > 0 || !timespec64_valid_settod(&tmp)) { ret = -EINVAL; goto error; } tk_xtime_add(tk, ts); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *ts)); error: /* even if we error out, we forwarded the time, so call update */ timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL); return ret; } /* * Indicates if there is an offset between the system clock and the hardware * clock/persistent clock/rtc. */ int persistent_clock_is_local; /* * Adjust the time obtained from the CMOS to be UTC time instead of * local time. * * This is ugly, but preferable to the alternatives. Otherwise we * would either need to write a program to do it in /etc/rc (and risk * confusion if the program gets run more than once; it would also be * hard to make the program warp the clock precisely n hours) or * compile in the timezone information into the kernel. Bad, bad.... * * - TYT, 1992-01-01 * * The best thing to do is to keep the CMOS clock in universal time (UTC) * as real UNIX machines always do it. This avoids all headaches about * daylight saving times and warping kernel clocks. */ void timekeeping_warp_clock(void) { if (sys_tz.tz_minuteswest != 0) { struct timespec64 adjust; persistent_clock_is_local = 1; adjust.tv_sec = sys_tz.tz_minuteswest * 60; adjust.tv_nsec = 0; timekeeping_inject_offset(&adjust); } } /* * __timekeeping_set_tai_offset - Sets the TAI offset from UTC and monotonic */ static void __timekeeping_set_tai_offset(struct timekeeper *tk, s32 tai_offset) { tk->tai_offset = tai_offset; tk->offs_tai = ktime_add(tk->offs_real, ktime_set(tai_offset, 0)); } /* * change_clocksource - Swaps clocksources if a new one is available * * Accumulates current time interval and initializes new clocksource */ static int change_clocksource(void *data) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *new, *old = NULL; unsigned long flags; bool change = false; new = (struct clocksource *) data; /* * If the cs is in module, get a module reference. Succeeds * for built-in code (owner == NULL) as well. */ if (try_module_get(new->owner)) { if (!new->enable || new->enable(new) == 0) change = true; else module_put(new->owner); } raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); if (change) { old = tk->tkr_mono.clock; tk_setup_internals(tk, new); } timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); if (old) { if (old->disable) old->disable(old); module_put(old->owner); } return 0; } /** * timekeeping_notify - Install a new clock source * @clock: pointer to the clock source * * This function is called from clocksource.c after a new, better clock * source has been registered. The caller holds the clocksource_mutex. */ int timekeeping_notify(struct clocksource *clock) { struct timekeeper *tk = &tk_core.timekeeper; if (tk->tkr_mono.clock == clock) return 0; stop_machine(change_clocksource, clock, NULL); tick_clock_notify(); return tk->tkr_mono.clock == clock ? 0 : -1; } /** * ktime_get_raw_ts64 - Returns the raw monotonic time in a timespec * @ts: pointer to the timespec64 to be set * * Returns the raw monotonic time (completely un-modified by ntp) */ void ktime_get_raw_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); ts->tv_sec = tk->raw_sec; nsecs = timekeeping_get_ns(&tk->tkr_raw); } while (read_seqcount_retry(&tk_core.seq, seq)); ts->tv_nsec = 0; timespec64_add_ns(ts, nsecs); } EXPORT_SYMBOL(ktime_get_raw_ts64); /** * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres */ int timekeeping_valid_for_hres(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; int ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->flags & CLOCK_SOURCE_VALID_FOR_HRES; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * timekeeping_max_deferment - Returns max time the clocksource can be deferred */ u64 timekeeping_max_deferment(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; u64 ret; do { seq = read_seqcount_begin(&tk_core.seq); ret = tk->tkr_mono.clock->max_idle_ns; } while (read_seqcount_retry(&tk_core.seq, seq)); return ret; } /** * read_persistent_clock64 - Return time from the persistent clock. * @ts: Pointer to the storage for the readout value * * Weak dummy function for arches that do not yet support it. * Reads the time from the battery backed persistent clock. * Returns a timespec with tv_sec=0 and tv_nsec=0 if unsupported. * * XXX - Do be sure to remove it once all arches implement it. */ void __weak read_persistent_clock64(struct timespec64 *ts) { ts->tv_sec = 0; ts->tv_nsec = 0; } /** * read_persistent_wall_and_boot_offset - Read persistent clock, and also offset * from the boot. * @wall_time: current time as returned by persistent clock * @boot_offset: offset that is defined as wall_time - boot_time * * Weak dummy function for arches that do not yet support it. * * The default function calculates offset based on the current value of * local_clock(). This way architectures that support sched_clock() but don't * support dedicated boot time clock will provide the best estimate of the * boot time. */ void __weak __init read_persistent_wall_and_boot_offset(struct timespec64 *wall_time, struct timespec64 *boot_offset) { read_persistent_clock64(wall_time); *boot_offset = ns_to_timespec64(local_clock()); } /* * Flag reflecting whether timekeeping_resume() has injected sleeptime. * * The flag starts of false and is only set when a suspend reaches * timekeeping_suspend(), timekeeping_resume() sets it to false when the * timekeeper clocksource is not stopping across suspend and has been * used to update sleep time. If the timekeeper clocksource has stopped * then the flag stays true and is used by the RTC resume code to decide * whether sleeptime must be injected and if so the flag gets false then. * * If a suspend fails before reaching timekeeping_resume() then the flag * stays false and prevents erroneous sleeptime injection. */ static bool suspend_timing_needed; /* Flag for if there is a persistent clock on this platform */ static bool persistent_clock_exists; /* * timekeeping_init - Initializes the clocksource and common timekeeping values */ void __init timekeeping_init(void) { struct timespec64 wall_time, boot_offset, wall_to_mono; struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock; unsigned long flags; read_persistent_wall_and_boot_offset(&wall_time, &boot_offset); if (timespec64_valid_settod(&wall_time) && timespec64_to_ns(&wall_time) > 0) { persistent_clock_exists = true; } else if (timespec64_to_ns(&wall_time) != 0) { pr_warn("Persistent clock returned invalid value"); wall_time = (struct timespec64){0}; } if (timespec64_compare(&wall_time, &boot_offset) < 0) boot_offset = (struct timespec64){0}; /* * We want set wall_to_mono, so the following is true: * wall time + wall_to_mono = boot time */ wall_to_mono = timespec64_sub(boot_offset, wall_time); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); ntp_init(); clock = clocksource_default_clock(); if (clock->enable) clock->enable(clock); tk_setup_internals(tk, clock); tk_set_xtime(tk, &wall_time); tk->raw_sec = 0; tk_set_wall_to_mono(tk, wall_to_mono); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } /* time in seconds when suspend began for persistent clock */ static struct timespec64 timekeeping_suspend_time; /** * __timekeeping_inject_sleeptime - Internal function to add sleep interval * @tk: Pointer to the timekeeper to be updated * @delta: Pointer to the delta value in timespec64 format * * Takes a timespec offset measuring a suspend interval and properly * adds the sleep offset to the timekeeping variables. */ static void __timekeeping_inject_sleeptime(struct timekeeper *tk, const struct timespec64 *delta) { if (!timespec64_valid_strict(delta)) { printk_deferred(KERN_WARNING "__timekeeping_inject_sleeptime: Invalid " "sleep delta value!\n"); return; } tk_xtime_add(tk, delta); tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, *delta)); tk_update_sleep_time(tk, timespec64_to_ktime(*delta)); tk_debug_account_sleep_time(delta); } #if defined(CONFIG_PM_SLEEP) && defined(CONFIG_RTC_HCTOSYS_DEVICE) /* * We have three kinds of time sources to use for sleep time * injection, the preference order is: * 1) non-stop clocksource * 2) persistent clock (ie: RTC accessible when irqs are off) * 3) RTC * * 1) and 2) are used by timekeeping, 3) by RTC subsystem. * If system has neither 1) nor 2), 3) will be used finally. * * * If timekeeping has injected sleeptime via either 1) or 2), * 3) becomes needless, so in this case we don't need to call * rtc_resume(), and this is what timekeeping_rtc_skipresume() * means. */ bool timekeeping_rtc_skipresume(void) { return !suspend_timing_needed; } /* * 1) can be determined whether to use or not only when doing * timekeeping_resume() which is invoked after rtc_suspend(), * so we can't skip rtc_suspend() surely if system has 1). * * But if system has 2), 2) will definitely be used, so in this * case we don't need to call rtc_suspend(), and this is what * timekeeping_rtc_skipsuspend() means. */ bool timekeeping_rtc_skipsuspend(void) { return persistent_clock_exists; } /** * timekeeping_inject_sleeptime64 - Adds suspend interval to timeekeeping values * @delta: pointer to a timespec64 delta value * * This hook is for architectures that cannot support read_persistent_clock64 * because their RTC/persistent clock is only accessible when irqs are enabled. * and also don't have an effective nonstop clocksource. * * This function should only be called by rtc_resume(), and allows * a suspend offset to be injected into the timekeeping values. */ void timekeeping_inject_sleeptime64(const struct timespec64 *delta) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); suspend_timing_needed = false; timekeeping_forward_now(tk); __timekeeping_inject_sleeptime(tk, delta); timekeeping_update(tk, TK_CLEAR_NTP | TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); /* Signal hrtimers about time change */ clock_was_set(CLOCK_SET_WALL | CLOCK_SET_BOOT); } #endif /** * timekeeping_resume - Resumes the generic timekeeping subsystem. */ void timekeeping_resume(void) { struct timekeeper *tk = &tk_core.timekeeper; struct clocksource *clock = tk->tkr_mono.clock; unsigned long flags; struct timespec64 ts_new, ts_delta; u64 cycle_now, nsec; bool inject_sleeptime = false; read_persistent_clock64(&ts_new); clockevents_resume(); clocksource_resume(); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); /* * After system resumes, we need to calculate the suspended time and * compensate it for the OS time. There are 3 sources that could be * used: Nonstop clocksource during suspend, persistent clock and rtc * device. * * One specific platform may have 1 or 2 or all of them, and the * preference will be: * suspend-nonstop clocksource -> persistent clock -> rtc * The less preferred source will only be tried if there is no better * usable source. The rtc part is handled separately in rtc core code. */ cycle_now = tk_clock_read(&tk->tkr_mono); nsec = clocksource_stop_suspend_timing(clock, cycle_now); if (nsec > 0) { ts_delta = ns_to_timespec64(nsec); inject_sleeptime = true; } else if (timespec64_compare(&ts_new, &timekeeping_suspend_time) > 0) { ts_delta = timespec64_sub(ts_new, timekeeping_suspend_time); inject_sleeptime = true; } if (inject_sleeptime) { suspend_timing_needed = false; __timekeeping_inject_sleeptime(tk, &ts_delta); } /* Re-base the last cycle value */ tk->tkr_mono.cycle_last = cycle_now; tk->tkr_raw.cycle_last = cycle_now; tk->ntp_error = 0; timekeeping_suspended = 0; timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); touch_softlockup_watchdog(); /* Resume the clockevent device(s) and hrtimers */ tick_resume(); /* Notify timerfd as resume is equivalent to clock_was_set() */ timerfd_resume(); } int timekeeping_suspend(void) { struct timekeeper *tk = &tk_core.timekeeper; unsigned long flags; struct timespec64 delta, delta_delta; static struct timespec64 old_delta; struct clocksource *curr_clock; u64 cycle_now; read_persistent_clock64(&timekeeping_suspend_time); /* * On some systems the persistent_clock can not be detected at * timekeeping_init by its return value, so if we see a valid * value returned, update the persistent_clock_exists flag. */ if (timekeeping_suspend_time.tv_sec || timekeeping_suspend_time.tv_nsec) persistent_clock_exists = true; suspend_timing_needed = true; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); timekeeping_forward_now(tk); timekeeping_suspended = 1; /* * Since we've called forward_now, cycle_last stores the value * just read from the current clocksource. Save this to potentially * use in suspend timing. */ curr_clock = tk->tkr_mono.clock; cycle_now = tk->tkr_mono.cycle_last; clocksource_start_suspend_timing(curr_clock, cycle_now); if (persistent_clock_exists) { /* * To avoid drift caused by repeated suspend/resumes, * which each can add ~1 second drift error, * try to compensate so the difference in system time * and persistent_clock time stays close to constant. */ delta = timespec64_sub(tk_xtime(tk), timekeeping_suspend_time); delta_delta = timespec64_sub(delta, old_delta); if (abs(delta_delta.tv_sec) >= 2) { /* * if delta_delta is too large, assume time correction * has occurred and set old_delta to the current delta. */ old_delta = delta; } else { /* Otherwise try to adjust old_system to compensate */ timekeeping_suspend_time = timespec64_add(timekeeping_suspend_time, delta_delta); } } timekeeping_update(tk, TK_MIRROR); halt_fast_timekeeper(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); tick_suspend(); clocksource_suspend(); clockevents_suspend(); return 0; } /* sysfs resume/suspend bits for timekeeping */ static struct syscore_ops timekeeping_syscore_ops = { .resume = timekeeping_resume, .suspend = timekeeping_suspend, }; static int __init timekeeping_init_ops(void) { register_syscore_ops(&timekeeping_syscore_ops); return 0; } device_initcall(timekeeping_init_ops); /* * Apply a multiplier adjustment to the timekeeper */ static __always_inline void timekeeping_apply_adjustment(struct timekeeper *tk, s64 offset, s32 mult_adj) { s64 interval = tk->cycle_interval; if (mult_adj == 0) { return; } else if (mult_adj == -1) { interval = -interval; offset = -offset; } else if (mult_adj != 1) { interval *= mult_adj; offset *= mult_adj; } /* * So the following can be confusing. * * To keep things simple, lets assume mult_adj == 1 for now. * * When mult_adj != 1, remember that the interval and offset values * have been appropriately scaled so the math is the same. * * The basic idea here is that we're increasing the multiplier * by one, this causes the xtime_interval to be incremented by * one cycle_interval. This is because: * xtime_interval = cycle_interval * mult * So if mult is being incremented by one: * xtime_interval = cycle_interval * (mult + 1) * Its the same as: * xtime_interval = (cycle_interval * mult) + cycle_interval * Which can be shortened to: * xtime_interval += cycle_interval * * So offset stores the non-accumulated cycles. Thus the current * time (in shifted nanoseconds) is: * now = (offset * adj) + xtime_nsec * Now, even though we're adjusting the clock frequency, we have * to keep time consistent. In other words, we can't jump back * in time, and we also want to avoid jumping forward in time. * * So given the same offset value, we need the time to be the same * both before and after the freq adjustment. * now = (offset * adj_1) + xtime_nsec_1 * now = (offset * adj_2) + xtime_nsec_2 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_2) + xtime_nsec_2 * And we know: * adj_2 = adj_1 + 1 * So: * (offset * adj_1) + xtime_nsec_1 = * (offset * (adj_1+1)) + xtime_nsec_2 * (offset * adj_1) + xtime_nsec_1 = * (offset * adj_1) + offset + xtime_nsec_2 * Canceling the sides: * xtime_nsec_1 = offset + xtime_nsec_2 * Which gives us: * xtime_nsec_2 = xtime_nsec_1 - offset * Which simplifies to: * xtime_nsec -= offset */ if ((mult_adj > 0) && (tk->tkr_mono.mult + mult_adj < mult_adj)) { /* NTP adjustment caused clocksource mult overflow */ WARN_ON_ONCE(1); return; } tk->tkr_mono.mult += mult_adj; tk->xtime_interval += interval; tk->tkr_mono.xtime_nsec -= offset; } /* * Adjust the timekeeper's multiplier to the correct frequency * and also to reduce the accumulated error value. */ static void timekeeping_adjust(struct timekeeper *tk, s64 offset) { u32 mult; /* * Determine the multiplier from the current NTP tick length. * Avoid expensive division when the tick length doesn't change. */ if (likely(tk->ntp_tick == ntp_tick_length())) { mult = tk->tkr_mono.mult - tk->ntp_err_mult; } else { tk->ntp_tick = ntp_tick_length(); mult = div64_u64((tk->ntp_tick >> tk->ntp_error_shift) - tk->xtime_remainder, tk->cycle_interval); } /* * If the clock is behind the NTP time, increase the multiplier by 1 * to catch up with it. If it's ahead and there was a remainder in the * tick division, the clock will slow down. Otherwise it will stay * ahead until the tick length changes to a non-divisible value. */ tk->ntp_err_mult = tk->ntp_error > 0 ? 1 : 0; mult += tk->ntp_err_mult; timekeeping_apply_adjustment(tk, offset, mult - tk->tkr_mono.mult); if (unlikely(tk->tkr_mono.clock->maxadj && (abs(tk->tkr_mono.mult - tk->tkr_mono.clock->mult) > tk->tkr_mono.clock->maxadj))) { printk_once(KERN_WARNING "Adjusting %s more than 11%% (%ld vs %ld)\n", tk->tkr_mono.clock->name, (long)tk->tkr_mono.mult, (long)tk->tkr_mono.clock->mult + tk->tkr_mono.clock->maxadj); } /* * It may be possible that when we entered this function, xtime_nsec * was very small. Further, if we're slightly speeding the clocksource * in the code above, its possible the required corrective factor to * xtime_nsec could cause it to underflow. * * Now, since we have already accumulated the second and the NTP * subsystem has been notified via second_overflow(), we need to skip * the next update. */ if (unlikely((s64)tk->tkr_mono.xtime_nsec < 0)) { tk->tkr_mono.xtime_nsec += (u64)NSEC_PER_SEC << tk->tkr_mono.shift; tk->xtime_sec--; tk->skip_second_overflow = 1; } } /* * accumulate_nsecs_to_secs - Accumulates nsecs into secs * * Helper function that accumulates the nsecs greater than a second * from the xtime_nsec field to the xtime_secs field. * It also calls into the NTP code to handle leapsecond processing. */ static inline unsigned int accumulate_nsecs_to_secs(struct timekeeper *tk) { u64 nsecps = (u64)NSEC_PER_SEC << tk->tkr_mono.shift; unsigned int clock_set = 0; while (tk->tkr_mono.xtime_nsec >= nsecps) { int leap; tk->tkr_mono.xtime_nsec -= nsecps; tk->xtime_sec++; /* * Skip NTP update if this second was accumulated before, * i.e. xtime_nsec underflowed in timekeeping_adjust() */ if (unlikely(tk->skip_second_overflow)) { tk->skip_second_overflow = 0; continue; } /* Figure out if its a leap sec and apply if needed */ leap = second_overflow(tk->xtime_sec); if (unlikely(leap)) { struct timespec64 ts; tk->xtime_sec += leap; ts.tv_sec = leap; ts.tv_nsec = 0; tk_set_wall_to_mono(tk, timespec64_sub(tk->wall_to_monotonic, ts)); __timekeeping_set_tai_offset(tk, tk->tai_offset - leap); clock_set = TK_CLOCK_WAS_SET; } } return clock_set; } /* * logarithmic_accumulation - shifted accumulation of cycles * * This functions accumulates a shifted interval of cycles into * a shifted interval nanoseconds. Allows for O(log) accumulation * loop. * * Returns the unconsumed cycles. */ static u64 logarithmic_accumulation(struct timekeeper *tk, u64 offset, u32 shift, unsigned int *clock_set) { u64 interval = tk->cycle_interval << shift; u64 snsec_per_sec; /* If the offset is smaller than a shifted interval, do nothing */ if (offset < interval) return offset; /* Accumulate one shifted interval */ offset -= interval; tk->tkr_mono.cycle_last += interval; tk->tkr_raw.cycle_last += interval; tk->tkr_mono.xtime_nsec += tk->xtime_interval << shift; *clock_set |= accumulate_nsecs_to_secs(tk); /* Accumulate raw time */ tk->tkr_raw.xtime_nsec += tk->raw_interval << shift; snsec_per_sec = (u64)NSEC_PER_SEC << tk->tkr_raw.shift; while (tk->tkr_raw.xtime_nsec >= snsec_per_sec) { tk->tkr_raw.xtime_nsec -= snsec_per_sec; tk->raw_sec++; } /* Accumulate error between NTP and clock interval */ tk->ntp_error += tk->ntp_tick << shift; tk->ntp_error -= (tk->xtime_interval + tk->xtime_remainder) << (tk->ntp_error_shift + shift); return offset; } /* * timekeeping_advance - Updates the timekeeper to the current time and * current NTP tick length */ static bool timekeeping_advance(enum timekeeping_adv_mode mode) { struct timekeeper *real_tk = &tk_core.timekeeper; struct timekeeper *tk = &shadow_timekeeper; u64 offset; int shift = 0, maxshift; unsigned int clock_set = 0; unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); /* Make sure we're fully resumed: */ if (unlikely(timekeeping_suspended)) goto out; offset = clocksource_delta(tk_clock_read(&tk->tkr_mono), tk->tkr_mono.cycle_last, tk->tkr_mono.mask); /* Check if there's really nothing to do */ if (offset < real_tk->cycle_interval && mode == TK_ADV_TICK) goto out; /* Do some additional sanity checking */ timekeeping_check_update(tk, offset); /* * With NO_HZ we may have to accumulate many cycle_intervals * (think "ticks") worth of time at once. To do this efficiently, * we calculate the largest doubling multiple of cycle_intervals * that is smaller than the offset. We then accumulate that * chunk in one go, and then try to consume the next smaller * doubled multiple. */ shift = ilog2(offset) - ilog2(tk->cycle_interval); shift = max(0, shift); /* Bound shift to one less than what overflows tick_length */ maxshift = (64 - (ilog2(ntp_tick_length())+1)) - 1; shift = min(shift, maxshift); while (offset >= tk->cycle_interval) { offset = logarithmic_accumulation(tk, offset, shift, &clock_set); if (offset < tk->cycle_interval<<shift) shift--; } /* Adjust the multiplier to correct NTP error */ timekeeping_adjust(tk, offset); /* * Finally, make sure that after the rounding * xtime_nsec isn't larger than NSEC_PER_SEC */ clock_set |= accumulate_nsecs_to_secs(tk); write_seqcount_begin(&tk_core.seq); /* * Update the real timekeeper. * * We could avoid this memcpy by switching pointers, but that * requires changes to all other timekeeper usage sites as * well, i.e. move the timekeeper pointer getter into the * spinlocked/seqcount protected sections. And we trade this * memcpy under the tk_core.seq against one before we start * updating. */ timekeeping_update(tk, clock_set); memcpy(real_tk, tk, sizeof(*tk)); /* The memcpy must come last. Do not put anything here! */ write_seqcount_end(&tk_core.seq); out: raw_spin_unlock_irqrestore(&timekeeper_lock, flags); return !!clock_set; } /** * update_wall_time - Uses the current clocksource to increment the wall time * */ void update_wall_time(void) { if (timekeeping_advance(TK_ADV_TICK)) clock_was_set_delayed(); } /** * getboottime64 - Return the real time of system boot. * @ts: pointer to the timespec64 to be set * * Returns the wall-time of boot in a timespec64. * * This is based on the wall_to_monotonic offset and the total suspend * time. Calls to settimeofday will affect the value returned (which * basically means that however wrong your real time clock is at boot time, * you get the right time here). */ void getboottime64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; ktime_t t = ktime_sub(tk->offs_real, tk->offs_boot); *ts = ktime_to_timespec64(t); } EXPORT_SYMBOL_GPL(getboottime64); void ktime_get_coarse_real_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); *ts = tk_xtime(tk); } while (read_seqcount_retry(&tk_core.seq, seq)); } EXPORT_SYMBOL(ktime_get_coarse_real_ts64); void ktime_get_coarse_ts64(struct timespec64 *ts) { struct timekeeper *tk = &tk_core.timekeeper; struct timespec64 now, mono; unsigned int seq; do { seq = read_seqcount_begin(&tk_core.seq); now = tk_xtime(tk); mono = tk->wall_to_monotonic; } while (read_seqcount_retry(&tk_core.seq, seq)); set_normalized_timespec64(ts, now.tv_sec + mono.tv_sec, now.tv_nsec + mono.tv_nsec); } EXPORT_SYMBOL(ktime_get_coarse_ts64); /* * Must hold jiffies_lock */ void do_timer(unsigned long ticks) { jiffies_64 += ticks; calc_global_load(); } /** * ktime_get_update_offsets_now - hrtimer helper * @cwsseq: pointer to check and store the clock was set sequence number * @offs_real: pointer to storage for monotonic -> realtime offset * @offs_boot: pointer to storage for monotonic -> boottime offset * @offs_tai: pointer to storage for monotonic -> clock tai offset * * Returns current monotonic time and updates the offsets if the * sequence number in @cwsseq and timekeeper.clock_was_set_seq are * different. * * Called from hrtimer_interrupt() or retrigger_next_event() */ ktime_t ktime_get_update_offsets_now(unsigned int *cwsseq, ktime_t *offs_real, ktime_t *offs_boot, ktime_t *offs_tai) { struct timekeeper *tk = &tk_core.timekeeper; unsigned int seq; ktime_t base; u64 nsecs; do { seq = read_seqcount_begin(&tk_core.seq); base = tk->tkr_mono.base; nsecs = timekeeping_get_ns(&tk->tkr_mono); base = ktime_add_ns(base, nsecs); if (*cwsseq != tk->clock_was_set_seq) { *cwsseq = tk->clock_was_set_seq; *offs_real = tk->offs_real; *offs_boot = tk->offs_boot; *offs_tai = tk->offs_tai; } /* Handle leapsecond insertion adjustments */ if (unlikely(base >= tk->next_leap_ktime)) *offs_real = ktime_sub(tk->offs_real, ktime_set(1, 0)); } while (read_seqcount_retry(&tk_core.seq, seq)); return base; } /* * timekeeping_validate_timex - Ensures the timex is ok for use in do_adjtimex */ static int timekeeping_validate_timex(const struct __kernel_timex *txc) { if (txc->modes & ADJ_ADJTIME) { /* singleshot must not be used with any other mode bits */ if (!(txc->modes & ADJ_OFFSET_SINGLESHOT)) return -EINVAL; if (!(txc->modes & ADJ_OFFSET_READONLY) && !capable(CAP_SYS_TIME)) return -EPERM; } else { /* In order to modify anything, you gotta be super-user! */ if (txc->modes && !capable(CAP_SYS_TIME)) return -EPERM; /* * if the quartz is off by more than 10% then * something is VERY wrong! */ if (txc->modes & ADJ_TICK && (txc->tick < 900000/USER_HZ || txc->tick > 1100000/USER_HZ)) return -EINVAL; } if (txc->modes & ADJ_SETOFFSET) { /* In order to inject time, you gotta be super-user! */ if (!capable(CAP_SYS_TIME)) return -EPERM; /* * Validate if a timespec/timeval used to inject a time * offset is valid. Offsets can be positive or negative, so * we don't check tv_sec. The value of the timeval/timespec * is the sum of its fields,but *NOTE*: * The field tv_usec/tv_nsec must always be non-negative and * we can't have more nanoseconds/microseconds than a second. */ if (txc->time.tv_usec < 0) return -EINVAL; if (txc->modes & ADJ_NANO) { if (txc->time.tv_usec >= NSEC_PER_SEC) return -EINVAL; } else { if (txc->time.tv_usec >= USEC_PER_SEC) return -EINVAL; } } /* * Check for potential multiplication overflows that can * only happen on 64-bit systems: */ if ((txc->modes & ADJ_FREQUENCY) && (BITS_PER_LONG == 64)) { if (LLONG_MIN / PPM_SCALE > txc->freq) return -EINVAL; if (LLONG_MAX / PPM_SCALE < txc->freq) return -EINVAL; } return 0; } /** * random_get_entropy_fallback - Returns the raw clock source value, * used by random.c for platforms with no valid random_get_entropy(). */ unsigned long random_get_entropy_fallback(void) { struct tk_read_base *tkr = &tk_core.timekeeper.tkr_mono; struct clocksource *clock = READ_ONCE(tkr->clock); if (unlikely(timekeeping_suspended || !clock)) return 0; return clock->read(clock); } EXPORT_SYMBOL_GPL(random_get_entropy_fallback); /** * do_adjtimex() - Accessor function to NTP __do_adjtimex function */ int do_adjtimex(struct __kernel_timex *txc) { struct timekeeper *tk = &tk_core.timekeeper; struct audit_ntp_data ad; bool clock_set = false; struct timespec64 ts; unsigned long flags; s32 orig_tai, tai; int ret; /* Validate the data before disabling interrupts */ ret = timekeeping_validate_timex(txc); if (ret) return ret; add_device_randomness(txc, sizeof(*txc)); if (txc->modes & ADJ_SETOFFSET) { struct timespec64 delta; delta.tv_sec = txc->time.tv_sec; delta.tv_nsec = txc->time.tv_usec; if (!(txc->modes & ADJ_NANO)) delta.tv_nsec *= 1000; ret = timekeeping_inject_offset(&delta); if (ret) return ret; audit_tk_injoffset(delta); } audit_ntp_init(&ad); ktime_get_real_ts64(&ts); add_device_randomness(&ts, sizeof(ts)); raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); orig_tai = tai = tk->tai_offset; ret = __do_adjtimex(txc, &ts, &tai, &ad); if (tai != orig_tai) { __timekeeping_set_tai_offset(tk, tai); timekeeping_update(tk, TK_MIRROR | TK_CLOCK_WAS_SET); clock_set = true; } tk_update_leap_state(tk); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); audit_ntp_log(&ad); /* Update the multiplier immediately if frequency was set directly */ if (txc->modes & (ADJ_FREQUENCY | ADJ_TICK)) clock_set |= timekeeping_advance(TK_ADV_FREQ); if (clock_set) clock_was_set(CLOCK_REALTIME); ntp_notify_cmos_timer(); return ret; } #ifdef CONFIG_NTP_PPS /** * hardpps() - Accessor function to NTP __hardpps function */ void hardpps(const struct timespec64 *phase_ts, const struct timespec64 *raw_ts) { unsigned long flags; raw_spin_lock_irqsave(&timekeeper_lock, flags); write_seqcount_begin(&tk_core.seq); __hardpps(phase_ts, raw_ts); write_seqcount_end(&tk_core.seq); raw_spin_unlock_irqrestore(&timekeeper_lock, flags); } EXPORT_SYMBOL(hardpps); #endif /* CONFIG_NTP_PPS */ |
| 311 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __ASM_GENERIC_ACCESS_OK_H__ #define __ASM_GENERIC_ACCESS_OK_H__ /* * Checking whether a pointer is valid for user space access. * These definitions work on most architectures, but overrides can * be used where necessary. */ /* * architectures with compat tasks have a variable TASK_SIZE and should * override this to a constant. */ #ifndef TASK_SIZE_MAX #define TASK_SIZE_MAX TASK_SIZE #endif #ifndef __access_ok /* * 'size' is a compile-time constant for most callers, so optimize for * this case to turn the check into a single comparison against a constant * limit and catch all possible overflows. * On architectures with separate user address space (m68k, s390, parisc, * sparc64) or those without an MMU, this should always return true. * * This version was originally contributed by Jonas Bonn for the * OpenRISC architecture, and was found to be the most efficient * for constant 'size' and 'limit' values. */ static inline int __access_ok(const void __user *ptr, unsigned long size) { unsigned long limit = TASK_SIZE_MAX; unsigned long addr = (unsigned long)ptr; if (IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) || !IS_ENABLED(CONFIG_MMU)) return true; return (size <= limit) && (addr <= (limit - size)); } #endif #ifndef access_ok #define access_ok(addr, size) likely(__access_ok(addr, size)) #endif #endif |
| 10 10 10 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KERNEL_VTIME_H #define _LINUX_KERNEL_VTIME_H #include <linux/context_tracking_state.h> #include <linux/sched.h> /* * Common vtime APIs */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING extern void vtime_account_kernel(struct task_struct *tsk); extern void vtime_account_idle(struct task_struct *tsk); #endif /* !CONFIG_VIRT_CPU_ACCOUNTING */ #ifdef CONFIG_VIRT_CPU_ACCOUNTING_GEN extern void vtime_user_enter(struct task_struct *tsk); extern void vtime_user_exit(struct task_struct *tsk); extern void vtime_guest_enter(struct task_struct *tsk); extern void vtime_guest_exit(struct task_struct *tsk); extern void vtime_init_idle(struct task_struct *tsk, int cpu); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_GEN */ static inline void vtime_user_enter(struct task_struct *tsk) { } static inline void vtime_user_exit(struct task_struct *tsk) { } static inline void vtime_guest_enter(struct task_struct *tsk) { } static inline void vtime_guest_exit(struct task_struct *tsk) { } static inline void vtime_init_idle(struct task_struct *tsk, int cpu) { } #endif #ifdef CONFIG_VIRT_CPU_ACCOUNTING_NATIVE extern void vtime_account_irq(struct task_struct *tsk, unsigned int offset); extern void vtime_account_softirq(struct task_struct *tsk); extern void vtime_account_hardirq(struct task_struct *tsk); extern void vtime_flush(struct task_struct *tsk); #else /* !CONFIG_VIRT_CPU_ACCOUNTING_NATIVE */ static inline void vtime_account_irq(struct task_struct *tsk, unsigned int offset) { } static inline void vtime_account_softirq(struct task_struct *tsk) { } static inline void vtime_account_hardirq(struct task_struct *tsk) { } static inline void vtime_flush(struct task_struct *tsk) { } #endif /* * vtime_accounting_enabled_this_cpu() definitions/declarations */ #if defined(CONFIG_VIRT_CPU_ACCOUNTING_NATIVE) static inline bool vtime_accounting_enabled_this_cpu(void) { return true; } extern void vtime_task_switch(struct task_struct *prev); static __always_inline void vtime_account_guest_enter(void) { vtime_account_kernel(current); current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { vtime_account_kernel(current); current->flags &= ~PF_VCPU; } #elif defined(CONFIG_VIRT_CPU_ACCOUNTING_GEN) /* * Checks if vtime is enabled on some CPU. Cputime readers want to be careful * in that case and compute the tickless cputime. * For now vtime state is tied to context tracking. We might want to decouple * those later if necessary. */ static inline bool vtime_accounting_enabled(void) { return context_tracking_enabled(); } static inline bool vtime_accounting_enabled_cpu(int cpu) { return context_tracking_enabled_cpu(cpu); } static inline bool vtime_accounting_enabled_this_cpu(void) { return context_tracking_enabled_this_cpu(); } extern void vtime_task_switch_generic(struct task_struct *prev); static inline void vtime_task_switch(struct task_struct *prev) { if (vtime_accounting_enabled_this_cpu()) vtime_task_switch_generic(prev); } static __always_inline void vtime_account_guest_enter(void) { if (vtime_accounting_enabled_this_cpu()) vtime_guest_enter(current); else current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { if (vtime_accounting_enabled_this_cpu()) vtime_guest_exit(current); else current->flags &= ~PF_VCPU; } #else /* !CONFIG_VIRT_CPU_ACCOUNTING */ static inline bool vtime_accounting_enabled_this_cpu(void) { return false; } static inline void vtime_task_switch(struct task_struct *prev) { } static __always_inline void vtime_account_guest_enter(void) { current->flags |= PF_VCPU; } static __always_inline void vtime_account_guest_exit(void) { current->flags &= ~PF_VCPU; } #endif #ifdef CONFIG_IRQ_TIME_ACCOUNTING extern void irqtime_account_irq(struct task_struct *tsk, unsigned int offset); #else static inline void irqtime_account_irq(struct task_struct *tsk, unsigned int offset) { } #endif static inline void account_softirq_enter(struct task_struct *tsk) { vtime_account_irq(tsk, SOFTIRQ_OFFSET); irqtime_account_irq(tsk, SOFTIRQ_OFFSET); } static inline void account_softirq_exit(struct task_struct *tsk) { vtime_account_softirq(tsk); irqtime_account_irq(tsk, 0); } static inline void account_hardirq_enter(struct task_struct *tsk) { vtime_account_irq(tsk, HARDIRQ_OFFSET); irqtime_account_irq(tsk, HARDIRQ_OFFSET); } static inline void account_hardirq_exit(struct task_struct *tsk) { vtime_account_hardirq(tsk); irqtime_account_irq(tsk, 0); } #endif /* _LINUX_KERNEL_VTIME_H */ |
| 57 57 57 57 56 56 56 56 56 47 1 56 57 60 60 60 60 60 60 60 24 24 24 24 24 24 24 61 61 61 61 61 61 61 61 61 61 24 24 61 61 61 61 61 61 61 61 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* * hugetlbpage-backed filesystem. Based on ramfs. * * Nadia Yvette Chambers, 2002 * * Copyright (C) 2002 Linus Torvalds. * License: GPL */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/thread_info.h> #include <asm/current.h> #include <linux/falloc.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/file.h> #include <linux/kernel.h> #include <linux/writeback.h> #include <linux/pagemap.h> #include <linux/highmem.h> #include <linux/init.h> #include <linux/string.h> #include <linux/capability.h> #include <linux/ctype.h> #include <linux/backing-dev.h> #include <linux/hugetlb.h> #include <linux/pagevec.h> #include <linux/fs_parser.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/dnotify.h> #include <linux/statfs.h> #include <linux/security.h> #include <linux/magic.h> #include <linux/migrate.h> #include <linux/uio.h> #include <linux/uaccess.h> #include <linux/sched/mm.h> static const struct address_space_operations hugetlbfs_aops; static const struct file_operations hugetlbfs_file_operations; static const struct inode_operations hugetlbfs_dir_inode_operations; static const struct inode_operations hugetlbfs_inode_operations; enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT }; struct hugetlbfs_fs_context { struct hstate *hstate; unsigned long long max_size_opt; unsigned long long min_size_opt; long max_hpages; long nr_inodes; long min_hpages; enum hugetlbfs_size_type max_val_type; enum hugetlbfs_size_type min_val_type; kuid_t uid; kgid_t gid; umode_t mode; }; int sysctl_hugetlb_shm_group; enum hugetlb_param { Opt_gid, Opt_min_size, Opt_mode, Opt_nr_inodes, Opt_pagesize, Opt_size, Opt_uid, }; static const struct fs_parameter_spec hugetlb_fs_parameters[] = { fsparam_u32 ("gid", Opt_gid), fsparam_string("min_size", Opt_min_size), fsparam_u32oct("mode", Opt_mode), fsparam_string("nr_inodes", Opt_nr_inodes), fsparam_string("pagesize", Opt_pagesize), fsparam_string("size", Opt_size), fsparam_u32 ("uid", Opt_uid), {} }; /* * Mask used when checking the page offset value passed in via system * calls. This value will be converted to a loff_t which is signed. * Therefore, we want to check the upper PAGE_SHIFT + 1 bits of the * value. The extra bit (- 1 in the shift value) is to take the sign * bit into account. */ #define PGOFF_LOFFT_MAX \ (((1UL << (PAGE_SHIFT + 1)) - 1) << (BITS_PER_LONG - (PAGE_SHIFT + 1))) static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma) { struct inode *inode = file_inode(file); struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); loff_t len, vma_len; int ret; struct hstate *h = hstate_file(file); vm_flags_t vm_flags; /* * vma address alignment (but not the pgoff alignment) has * already been checked by prepare_hugepage_range. If you add * any error returns here, do so after setting VM_HUGETLB, so * is_vm_hugetlb_page tests below unmap_region go the right * way when do_mmap unwinds (may be important on powerpc * and ia64). */ vm_flags_set(vma, VM_HUGETLB | VM_DONTEXPAND); vma->vm_ops = &hugetlb_vm_ops; ret = seal_check_write(info->seals, vma); if (ret) return ret; /* * page based offset in vm_pgoff could be sufficiently large to * overflow a loff_t when converted to byte offset. This can * only happen on architectures where sizeof(loff_t) == * sizeof(unsigned long). So, only check in those instances. */ if (sizeof(unsigned long) == sizeof(loff_t)) { if (vma->vm_pgoff & PGOFF_LOFFT_MAX) return -EINVAL; } /* must be huge page aligned */ if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT)) return -EINVAL; vma_len = (loff_t)(vma->vm_end - vma->vm_start); len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); /* check for overflow */ if (len < vma_len) return -EINVAL; inode_lock(inode); file_accessed(file); ret = -ENOMEM; vm_flags = vma->vm_flags; /* * for SHM_HUGETLB, the pages are reserved in the shmget() call so skip * reserving here. Note: only for SHM hugetlbfs file, the inode * flag S_PRIVATE is set. */ if (inode->i_flags & S_PRIVATE) vm_flags |= VM_NORESERVE; if (!hugetlb_reserve_pages(inode, vma->vm_pgoff >> huge_page_order(h), len >> huge_page_shift(h), vma, vm_flags)) goto out; ret = 0; if (vma->vm_flags & VM_WRITE && inode->i_size < len) i_size_write(inode, len); out: inode_unlock(inode); return ret; } /* * Called under mmap_write_lock(mm). */ static unsigned long hugetlb_get_unmapped_area_bottomup(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); struct vm_unmapped_area_info info = {}; info.length = len; info.low_limit = current->mm->mmap_base; info.high_limit = arch_get_mmap_end(addr, len, flags); info.align_mask = PAGE_MASK & ~huge_page_mask(h); return vm_unmapped_area(&info); } static unsigned long hugetlb_get_unmapped_area_topdown(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct hstate *h = hstate_file(file); struct vm_unmapped_area_info info = {}; info.flags = VM_UNMAPPED_AREA_TOPDOWN; info.length = len; info.low_limit = PAGE_SIZE; info.high_limit = arch_get_mmap_base(addr, current->mm->mmap_base); info.align_mask = PAGE_MASK & ~huge_page_mask(h); addr = vm_unmapped_area(&info); /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario * can happen with large stack limits and large mmap() * allocations. */ if (unlikely(offset_in_page(addr))) { VM_BUG_ON(addr != -ENOMEM); info.flags = 0; info.low_limit = current->mm->mmap_base; info.high_limit = arch_get_mmap_end(addr, len, flags); addr = vm_unmapped_area(&info); } return addr; } unsigned long generic_hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma; struct hstate *h = hstate_file(file); const unsigned long mmap_end = arch_get_mmap_end(addr, len, flags); if (len & ~huge_page_mask(h)) return -EINVAL; if (len > TASK_SIZE) return -ENOMEM; if (flags & MAP_FIXED) { if (prepare_hugepage_range(file, addr, len)) return -EINVAL; return addr; } if (addr) { addr = ALIGN(addr, huge_page_size(h)); vma = find_vma(mm, addr); if (mmap_end - len >= addr && (!vma || addr + len <= vm_start_gap(vma))) return addr; } /* * Use MMF_TOPDOWN flag as a hint to use topdown routine. * If architectures have special needs, they should define their own * version of hugetlb_get_unmapped_area. */ if (test_bit(MMF_TOPDOWN, &mm->flags)) return hugetlb_get_unmapped_area_topdown(file, addr, len, pgoff, flags); return hugetlb_get_unmapped_area_bottomup(file, addr, len, pgoff, flags); } #ifndef HAVE_ARCH_HUGETLB_UNMAPPED_AREA static unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return generic_hugetlb_get_unmapped_area(file, addr, len, pgoff, flags); } #endif /* * Someone wants to read @bytes from a HWPOISON hugetlb @page from @offset. * Returns the maximum number of bytes one can read without touching the 1st raw * HWPOISON subpage. * * The implementation borrows the iteration logic from copy_page_to_iter*. */ static size_t adjust_range_hwpoison(struct page *page, size_t offset, size_t bytes) { size_t n = 0; size_t res = 0; /* First subpage to start the loop. */ page = nth_page(page, offset / PAGE_SIZE); offset %= PAGE_SIZE; while (1) { if (is_raw_hwpoison_page_in_hugepage(page)) break; /* Safe to read n bytes without touching HWPOISON subpage. */ n = min(bytes, (size_t)PAGE_SIZE - offset); res += n; bytes -= n; if (!bytes || !n) break; offset += n; if (offset == PAGE_SIZE) { page = nth_page(page, 1); offset = 0; } } return res; } /* * Support for read() - Find the page attached to f_mapping and copy out the * data. This provides functionality similar to filemap_read(). */ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to) { struct file *file = iocb->ki_filp; struct hstate *h = hstate_file(file); struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; unsigned long index = iocb->ki_pos >> huge_page_shift(h); unsigned long offset = iocb->ki_pos & ~huge_page_mask(h); unsigned long end_index; loff_t isize; ssize_t retval = 0; while (iov_iter_count(to)) { struct folio *folio; size_t nr, copied, want; /* nr is the maximum number of bytes to copy from this page */ nr = huge_page_size(h); isize = i_size_read(inode); if (!isize) break; end_index = (isize - 1) >> huge_page_shift(h); if (index > end_index) break; if (index == end_index) { nr = ((isize - 1) & ~huge_page_mask(h)) + 1; if (nr <= offset) break; } nr = nr - offset; /* Find the folio */ folio = filemap_lock_hugetlb_folio(h, mapping, index); if (IS_ERR(folio)) { /* * We have a HOLE, zero out the user-buffer for the * length of the hole or request. */ copied = iov_iter_zero(nr, to); } else { folio_unlock(folio); if (!folio_test_hwpoison(folio)) want = nr; else { /* * Adjust how many bytes safe to read without * touching the 1st raw HWPOISON subpage after * offset. */ want = adjust_range_hwpoison(&folio->page, offset, nr); if (want == 0) { folio_put(folio); retval = -EIO; break; } } /* * We have the folio, copy it to user space buffer. */ copied = copy_folio_to_iter(folio, offset, want, to); folio_put(folio); } offset += copied; retval += copied; if (copied != nr && iov_iter_count(to)) { if (!retval) retval = -EFAULT; break; } index += offset >> huge_page_shift(h); offset &= ~huge_page_mask(h); } iocb->ki_pos = ((loff_t)index << huge_page_shift(h)) + offset; return retval; } static int hugetlbfs_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, struct page **pagep, void **fsdata) { return -EINVAL; } static int hugetlbfs_write_end(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned copied, struct page *page, void *fsdata) { BUG(); return -EINVAL; } static void hugetlb_delete_from_page_cache(struct folio *folio) { folio_clear_dirty(folio); folio_clear_uptodate(folio); filemap_remove_folio(folio); } /* * Called with i_mmap_rwsem held for inode based vma maps. This makes * sure vma (and vm_mm) will not go away. We also hold the hugetlb fault * mutex for the page in the mapping. So, we can not race with page being * faulted into the vma. */ static bool hugetlb_vma_maps_page(struct vm_area_struct *vma, unsigned long addr, struct page *page) { pte_t *ptep, pte; ptep = hugetlb_walk(vma, addr, huge_page_size(hstate_vma(vma))); if (!ptep) return false; pte = huge_ptep_get(ptep); if (huge_pte_none(pte) || !pte_present(pte)) return false; if (pte_page(pte) == page) return true; return false; } /* * Can vma_offset_start/vma_offset_end overflow on 32-bit arches? * No, because the interval tree returns us only those vmas * which overlap the truncated area starting at pgoff, * and no vma on a 32-bit arch can span beyond the 4GB. */ static unsigned long vma_offset_start(struct vm_area_struct *vma, pgoff_t start) { unsigned long offset = 0; if (vma->vm_pgoff < start) offset = (start - vma->vm_pgoff) << PAGE_SHIFT; return vma->vm_start + offset; } static unsigned long vma_offset_end(struct vm_area_struct *vma, pgoff_t end) { unsigned long t_end; if (!end) return vma->vm_end; t_end = ((end - vma->vm_pgoff) << PAGE_SHIFT) + vma->vm_start; if (t_end > vma->vm_end) t_end = vma->vm_end; return t_end; } /* * Called with hugetlb fault mutex held. Therefore, no more mappings to * this folio can be created while executing the routine. */ static void hugetlb_unmap_file_folio(struct hstate *h, struct address_space *mapping, struct folio *folio, pgoff_t index) { struct rb_root_cached *root = &mapping->i_mmap; struct hugetlb_vma_lock *vma_lock; struct page *page = &folio->page; struct vm_area_struct *vma; unsigned long v_start; unsigned long v_end; pgoff_t start, end; start = index * pages_per_huge_page(h); end = (index + 1) * pages_per_huge_page(h); i_mmap_lock_write(mapping); retry: vma_lock = NULL; vma_interval_tree_foreach(vma, root, start, end - 1) { v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); if (!hugetlb_vma_maps_page(vma, v_start, page)) continue; if (!hugetlb_vma_trylock_write(vma)) { vma_lock = vma->vm_private_data; /* * If we can not get vma lock, we need to drop * immap_sema and take locks in order. First, * take a ref on the vma_lock structure so that * we can be guaranteed it will not go away when * dropping immap_sema. */ kref_get(&vma_lock->refs); break; } unmap_hugepage_range(vma, v_start, v_end, NULL, ZAP_FLAG_DROP_MARKER); hugetlb_vma_unlock_write(vma); } i_mmap_unlock_write(mapping); if (vma_lock) { /* * Wait on vma_lock. We know it is still valid as we have * a reference. We must 'open code' vma locking as we do * not know if vma_lock is still attached to vma. */ down_write(&vma_lock->rw_sema); i_mmap_lock_write(mapping); vma = vma_lock->vma; if (!vma) { /* * If lock is no longer attached to vma, then just * unlock, drop our reference and retry looking for * other vmas. */ up_write(&vma_lock->rw_sema); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); goto retry; } /* * vma_lock is still attached to vma. Check to see if vma * still maps page and if so, unmap. */ v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); if (hugetlb_vma_maps_page(vma, v_start, page)) unmap_hugepage_range(vma, v_start, v_end, NULL, ZAP_FLAG_DROP_MARKER); kref_put(&vma_lock->refs, hugetlb_vma_lock_release); hugetlb_vma_unlock_write(vma); goto retry; } } static void hugetlb_vmdelete_list(struct rb_root_cached *root, pgoff_t start, pgoff_t end, zap_flags_t zap_flags) { struct vm_area_struct *vma; /* * end == 0 indicates that the entire range after start should be * unmapped. Note, end is exclusive, whereas the interval tree takes * an inclusive "last". */ vma_interval_tree_foreach(vma, root, start, end ? end - 1 : ULONG_MAX) { unsigned long v_start; unsigned long v_end; if (!hugetlb_vma_trylock_write(vma)) continue; v_start = vma_offset_start(vma, start); v_end = vma_offset_end(vma, end); unmap_hugepage_range(vma, v_start, v_end, NULL, zap_flags); /* * Note that vma lock only exists for shared/non-private * vmas. Therefore, lock is not held when calling * unmap_hugepage_range for private vmas. */ hugetlb_vma_unlock_write(vma); } } /* * Called with hugetlb fault mutex held. * Returns true if page was actually removed, false otherwise. */ static bool remove_inode_single_folio(struct hstate *h, struct inode *inode, struct address_space *mapping, struct folio *folio, pgoff_t index, bool truncate_op) { bool ret = false; /* * If folio is mapped, it was faulted in after being * unmapped in caller. Unmap (again) while holding * the fault mutex. The mutex will prevent faults * until we finish removing the folio. */ if (unlikely(folio_mapped(folio))) hugetlb_unmap_file_folio(h, mapping, folio, index); folio_lock(folio); /* * We must remove the folio from page cache before removing * the region/ reserve map (hugetlb_unreserve_pages). In * rare out of memory conditions, removal of the region/reserve * map could fail. Correspondingly, the subpool and global * reserve usage count can need to be adjusted. */ VM_BUG_ON_FOLIO(folio_test_hugetlb_restore_reserve(folio), folio); hugetlb_delete_from_page_cache(folio); ret = true; if (!truncate_op) { if (unlikely(hugetlb_unreserve_pages(inode, index, index + 1, 1))) hugetlb_fix_reserve_counts(inode); } folio_unlock(folio); return ret; } /* * remove_inode_hugepages handles two distinct cases: truncation and hole * punch. There are subtle differences in operation for each case. * * truncation is indicated by end of range being LLONG_MAX * In this case, we first scan the range and release found pages. * After releasing pages, hugetlb_unreserve_pages cleans up region/reserve * maps and global counts. Page faults can race with truncation. * During faults, hugetlb_no_page() checks i_size before page allocation, * and again after obtaining page table lock. It will 'back out' * allocations in the truncated range. * hole punch is indicated if end is not LLONG_MAX * In the hole punch case we scan the range and release found pages. * Only when releasing a page is the associated region/reserve map * deleted. The region/reserve map for ranges without associated * pages are not modified. Page faults can race with hole punch. * This is indicated if we find a mapped page. * Note: If the passed end of range value is beyond the end of file, but * not LLONG_MAX this routine still performs a hole punch operation. */ static void remove_inode_hugepages(struct inode *inode, loff_t lstart, loff_t lend) { struct hstate *h = hstate_inode(inode); struct address_space *mapping = &inode->i_data; const pgoff_t end = lend >> PAGE_SHIFT; struct folio_batch fbatch; pgoff_t next, index; int i, freed = 0; bool truncate_op = (lend == LLONG_MAX); folio_batch_init(&fbatch); next = lstart >> PAGE_SHIFT; while (filemap_get_folios(mapping, &next, end - 1, &fbatch)) { for (i = 0; i < folio_batch_count(&fbatch); ++i) { struct folio *folio = fbatch.folios[i]; u32 hash = 0; index = folio->index >> huge_page_order(h); hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* * Remove folio that was part of folio_batch. */ if (remove_inode_single_folio(h, inode, mapping, folio, index, truncate_op)) freed++; mutex_unlock(&hugetlb_fault_mutex_table[hash]); } folio_batch_release(&fbatch); cond_resched(); } if (truncate_op) (void)hugetlb_unreserve_pages(inode, lstart >> huge_page_shift(h), LONG_MAX, freed); } static void hugetlbfs_evict_inode(struct inode *inode) { struct resv_map *resv_map; remove_inode_hugepages(inode, 0, LLONG_MAX); /* * Get the resv_map from the address space embedded in the inode. * This is the address space which points to any resv_map allocated * at inode creation time. If this is a device special inode, * i_mapping may not point to the original address space. */ resv_map = (struct resv_map *)(&inode->i_data)->i_private_data; /* Only regular and link inodes have associated reserve maps */ if (resv_map) resv_map_release(&resv_map->refs); clear_inode(inode); } static void hugetlb_vmtruncate(struct inode *inode, loff_t offset) { pgoff_t pgoff; struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); BUG_ON(offset & ~huge_page_mask(h)); pgoff = offset >> PAGE_SHIFT; i_size_write(inode, offset); i_mmap_lock_write(mapping); if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, pgoff, 0, ZAP_FLAG_DROP_MARKER); i_mmap_unlock_write(mapping); remove_inode_hugepages(inode, offset, LLONG_MAX); } static void hugetlbfs_zero_partial_page(struct hstate *h, struct address_space *mapping, loff_t start, loff_t end) { pgoff_t idx = start >> huge_page_shift(h); struct folio *folio; folio = filemap_lock_hugetlb_folio(h, mapping, idx); if (IS_ERR(folio)) return; start = start & ~huge_page_mask(h); end = end & ~huge_page_mask(h); if (!end) end = huge_page_size(h); folio_zero_segment(folio, (size_t)start, (size_t)end); folio_unlock(folio); folio_put(folio); } static long hugetlbfs_punch_hole(struct inode *inode, loff_t offset, loff_t len) { struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); loff_t hpage_size = huge_page_size(h); loff_t hole_start, hole_end; /* * hole_start and hole_end indicate the full pages within the hole. */ hole_start = round_up(offset, hpage_size); hole_end = round_down(offset + len, hpage_size); inode_lock(inode); /* protected by i_rwsem */ if (info->seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE)) { inode_unlock(inode); return -EPERM; } i_mmap_lock_write(mapping); /* If range starts before first full page, zero partial page. */ if (offset < hole_start) hugetlbfs_zero_partial_page(h, mapping, offset, min(offset + len, hole_start)); /* Unmap users of full pages in the hole. */ if (hole_end > hole_start) { if (!RB_EMPTY_ROOT(&mapping->i_mmap.rb_root)) hugetlb_vmdelete_list(&mapping->i_mmap, hole_start >> PAGE_SHIFT, hole_end >> PAGE_SHIFT, 0); } /* If range extends beyond last full page, zero partial page. */ if ((offset + len) > hole_end && (offset + len) > hole_start) hugetlbfs_zero_partial_page(h, mapping, hole_end, offset + len); i_mmap_unlock_write(mapping); /* Remove full pages from the file. */ if (hole_end > hole_start) remove_inode_hugepages(inode, hole_start, hole_end); inode_unlock(inode); return 0; } static long hugetlbfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); struct address_space *mapping = inode->i_mapping; struct hstate *h = hstate_inode(inode); struct vm_area_struct pseudo_vma; struct mm_struct *mm = current->mm; loff_t hpage_size = huge_page_size(h); unsigned long hpage_shift = huge_page_shift(h); pgoff_t start, index, end; int error; u32 hash; if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; if (mode & FALLOC_FL_PUNCH_HOLE) return hugetlbfs_punch_hole(inode, offset, len); /* * Default preallocate case. * For this range, start is rounded down and end is rounded up * as well as being converted to page offsets. */ start = offset >> hpage_shift; end = (offset + len + hpage_size - 1) >> hpage_shift; inode_lock(inode); /* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */ error = inode_newsize_ok(inode, offset + len); if (error) goto out; if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) { error = -EPERM; goto out; } /* * Initialize a pseudo vma as this is required by the huge page * allocation routines. */ vma_init(&pseudo_vma, mm); vm_flags_init(&pseudo_vma, VM_HUGETLB | VM_MAYSHARE | VM_SHARED); pseudo_vma.vm_file = file; for (index = start; index < end; index++) { /* * This is supposed to be the vaddr where the page is being * faulted in, but we have no vaddr here. */ struct folio *folio; unsigned long addr; cond_resched(); /* * fallocate(2) manpage permits EINTR; we may have been * interrupted because we are using up too much memory. */ if (signal_pending(current)) { error = -EINTR; break; } /* addr is the offset within the file (zero based) */ addr = index * hpage_size; /* mutex taken here, fault path and hole punch */ hash = hugetlb_fault_mutex_hash(mapping, index); mutex_lock(&hugetlb_fault_mutex_table[hash]); /* See if already present in mapping to avoid alloc/free */ folio = filemap_get_folio(mapping, index << huge_page_order(h)); if (!IS_ERR(folio)) { folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); continue; } /* * Allocate folio without setting the avoid_reserve argument. * There certainly are no reserves associated with the * pseudo_vma. However, there could be shared mappings with * reserves for the file at the inode level. If we fallocate * folios in these areas, we need to consume the reserves * to keep reservation accounting consistent. */ folio = alloc_hugetlb_folio(&pseudo_vma, addr, 0); if (IS_ERR(folio)) { mutex_unlock(&hugetlb_fault_mutex_table[hash]); error = PTR_ERR(folio); goto out; } clear_huge_page(&folio->page, addr, pages_per_huge_page(h)); __folio_mark_uptodate(folio); error = hugetlb_add_to_page_cache(folio, mapping, index); if (unlikely(error)) { restore_reserve_on_error(h, &pseudo_vma, addr, folio); folio_put(folio); mutex_unlock(&hugetlb_fault_mutex_table[hash]); goto out; } mutex_unlock(&hugetlb_fault_mutex_table[hash]); folio_set_hugetlb_migratable(folio); /* * folio_unlock because locked by hugetlb_add_to_page_cache() * folio_put() due to reference from alloc_hugetlb_folio() */ folio_unlock(folio); folio_put(folio); } if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size) i_size_write(inode, offset + len); inode_set_ctime_current(inode); out: inode_unlock(inode); return error; } static int hugetlbfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr) { struct inode *inode = d_inode(dentry); struct hstate *h = hstate_inode(inode); int error; unsigned int ia_valid = attr->ia_valid; struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); error = setattr_prepare(idmap, dentry, attr); if (error) return error; if (ia_valid & ATTR_SIZE) { loff_t oldsize = inode->i_size; loff_t newsize = attr->ia_size; if (newsize & ~huge_page_mask(h)) return -EINVAL; /* protected by i_rwsem */ if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) || (newsize > oldsize && (info->seals & F_SEAL_GROW))) return -EPERM; hugetlb_vmtruncate(inode, newsize); } setattr_copy(idmap, inode, attr); mark_inode_dirty(inode); return 0; } static struct inode *hugetlbfs_get_root(struct super_block *sb, struct hugetlbfs_fs_context *ctx) { struct inode *inode; inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); inode->i_mode = S_IFDIR | ctx->mode; inode->i_uid = ctx->uid; inode->i_gid = ctx->gid; simple_inode_init_ts(inode); inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); lockdep_annotate_inode_mutex_key(inode); } return inode; } /* * Hugetlbfs is not reclaimable; therefore its i_mmap_rwsem will never * be taken from reclaim -- unlike regular filesystems. This needs an * annotation because huge_pmd_share() does an allocation under hugetlb's * i_mmap_rwsem. */ static struct lock_class_key hugetlbfs_i_mmap_rwsem_key; static struct inode *hugetlbfs_get_inode(struct super_block *sb, struct mnt_idmap *idmap, struct inode *dir, umode_t mode, dev_t dev) { struct inode *inode; struct resv_map *resv_map = NULL; /* * Reserve maps are only needed for inodes that can have associated * page allocations. */ if (S_ISREG(mode) || S_ISLNK(mode)) { resv_map = resv_map_alloc(); if (!resv_map) return NULL; } inode = new_inode(sb); if (inode) { struct hugetlbfs_inode_info *info = HUGETLBFS_I(inode); inode->i_ino = get_next_ino(); inode_init_owner(idmap, inode, dir, mode); lockdep_set_class(&inode->i_mapping->i_mmap_rwsem, &hugetlbfs_i_mmap_rwsem_key); inode->i_mapping->a_ops = &hugetlbfs_aops; simple_inode_init_ts(inode); inode->i_mapping->i_private_data = resv_map; info->seals = F_SEAL_SEAL; switch (mode & S_IFMT) { default: init_special_inode(inode, mode, dev); break; case S_IFREG: inode->i_op = &hugetlbfs_inode_operations; inode->i_fop = &hugetlbfs_file_operations; break; case S_IFDIR: inode->i_op = &hugetlbfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); break; case S_IFLNK: inode->i_op = &page_symlink_inode_operations; inode_nohighmem(inode); break; } lockdep_annotate_inode_mutex_key(inode); } else { if (resv_map) kref_put(&resv_map->refs, resv_map_release); } return inode; } /* * File creation. Allocate an inode, and we're done.. */ static int hugetlbfs_mknod(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) { struct inode *inode; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, dev); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_instantiate(dentry, inode); dget(dentry);/* Extra count - pin the dentry in core */ return 0; } static int hugetlbfs_mkdir(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode) { int retval = hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFDIR, 0); if (!retval) inc_nlink(dir); return retval; } static int hugetlbfs_create(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, umode_t mode, bool excl) { return hugetlbfs_mknod(idmap, dir, dentry, mode | S_IFREG, 0); } static int hugetlbfs_tmpfile(struct mnt_idmap *idmap, struct inode *dir, struct file *file, umode_t mode) { struct inode *inode; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode | S_IFREG, 0); if (!inode) return -ENOSPC; inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); d_tmpfile(file, inode); return finish_open_simple(file, 0); } static int hugetlbfs_symlink(struct mnt_idmap *idmap, struct inode *dir, struct dentry *dentry, const char *symname) { const umode_t mode = S_IFLNK|S_IRWXUGO; struct inode *inode; int error = -ENOSPC; inode = hugetlbfs_get_inode(dir->i_sb, idmap, dir, mode, 0); if (inode) { int l = strlen(symname)+1; error = page_symlink(inode, symname, l); if (!error) { d_instantiate(dentry, inode); dget(dentry); } else iput(inode); } inode_set_mtime_to_ts(dir, inode_set_ctime_current(dir)); return error; } #ifdef CONFIG_MIGRATION static int hugetlbfs_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode) { int rc; rc = migrate_huge_page_move_mapping(mapping, dst, src); if (rc != MIGRATEPAGE_SUCCESS) return rc; if (hugetlb_folio_subpool(src)) { hugetlb_set_folio_subpool(dst, hugetlb_folio_subpool(src)); hugetlb_set_folio_subpool(src, NULL); } if (mode != MIGRATE_SYNC_NO_COPY) folio_migrate_copy(dst, src); else folio_migrate_flags(dst, src); return MIGRATEPAGE_SUCCESS; } #else #define hugetlbfs_migrate_folio NULL #endif static int hugetlbfs_error_remove_folio(struct address_space *mapping, struct folio *folio) { return 0; } /* * Display the mount options in /proc/mounts. */ static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb); struct hugepage_subpool *spool = sbinfo->spool; unsigned long hpage_size = huge_page_size(sbinfo->hstate); unsigned hpage_shift = huge_page_shift(sbinfo->hstate); char mod; if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, sbinfo->uid)); if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, sbinfo->gid)); if (sbinfo->mode != 0755) seq_printf(m, ",mode=%o", sbinfo->mode); if (sbinfo->max_inodes != -1) seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes); hpage_size /= 1024; mod = 'K'; if (hpage_size >= 1024) { hpage_size /= 1024; mod = 'M'; } seq_printf(m, ",pagesize=%lu%c", hpage_size, mod); if (spool) { if (spool->max_hpages != -1) seq_printf(m, ",size=%llu", (unsigned long long)spool->max_hpages << hpage_shift); if (spool->min_hpages != -1) seq_printf(m, ",min_size=%llu", (unsigned long long)spool->min_hpages << hpage_shift); } return 0; } static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb); struct hstate *h = hstate_inode(d_inode(dentry)); u64 id = huge_encode_dev(dentry->d_sb->s_dev); buf->f_fsid = u64_to_fsid(id); buf->f_type = HUGETLBFS_MAGIC; buf->f_bsize = huge_page_size(h); if (sbinfo) { spin_lock(&sbinfo->stat_lock); /* If no limits set, just report 0 or -1 for max/free/used * blocks, like simple_statfs() */ if (sbinfo->spool) { long free_pages; spin_lock_irq(&sbinfo->spool->lock); buf->f_blocks = sbinfo->spool->max_hpages; free_pages = sbinfo->spool->max_hpages - sbinfo->spool->used_hpages; buf->f_bavail = buf->f_bfree = free_pages; spin_unlock_irq(&sbinfo->spool->lock); buf->f_files = sbinfo->max_inodes; buf->f_ffree = sbinfo->free_inodes; } spin_unlock(&sbinfo->stat_lock); } buf->f_namelen = NAME_MAX; return 0; } static void hugetlbfs_put_super(struct super_block *sb) { struct hugetlbfs_sb_info *sbi = HUGETLBFS_SB(sb); if (sbi) { sb->s_fs_info = NULL; if (sbi->spool) hugepage_put_subpool(sbi->spool); kfree(sbi); } } static inline int hugetlbfs_dec_free_inodes(struct hugetlbfs_sb_info *sbinfo) { if (sbinfo->free_inodes >= 0) { spin_lock(&sbinfo->stat_lock); if (unlikely(!sbinfo->free_inodes)) { spin_unlock(&sbinfo->stat_lock); return 0; } sbinfo->free_inodes--; spin_unlock(&sbinfo->stat_lock); } return 1; } static void hugetlbfs_inc_free_inodes(struct hugetlbfs_sb_info *sbinfo) { if (sbinfo->free_inodes >= 0) { spin_lock(&sbinfo->stat_lock); sbinfo->free_inodes++; spin_unlock(&sbinfo->stat_lock); } } static struct kmem_cache *hugetlbfs_inode_cachep; static struct inode *hugetlbfs_alloc_inode(struct super_block *sb) { struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(sb); struct hugetlbfs_inode_info *p; if (unlikely(!hugetlbfs_dec_free_inodes(sbinfo))) return NULL; p = alloc_inode_sb(sb, hugetlbfs_inode_cachep, GFP_KERNEL); if (unlikely(!p)) { hugetlbfs_inc_free_inodes(sbinfo); return NULL; } return &p->vfs_inode; } static void hugetlbfs_free_inode(struct inode *inode) { kmem_cache_free(hugetlbfs_inode_cachep, HUGETLBFS_I(inode)); } static void hugetlbfs_destroy_inode(struct inode *inode) { hugetlbfs_inc_free_inodes(HUGETLBFS_SB(inode->i_sb)); } static const struct address_space_operations hugetlbfs_aops = { .write_begin = hugetlbfs_write_begin, .write_end = hugetlbfs_write_end, .dirty_folio = noop_dirty_folio, .migrate_folio = hugetlbfs_migrate_folio, .error_remove_folio = hugetlbfs_error_remove_folio, }; static void init_once(void *foo) { struct hugetlbfs_inode_info *ei = foo; inode_init_once(&ei->vfs_inode); } static const struct file_operations hugetlbfs_file_operations = { .read_iter = hugetlbfs_read_iter, .mmap = hugetlbfs_file_mmap, .fsync = noop_fsync, .get_unmapped_area = hugetlb_get_unmapped_area, .llseek = default_llseek, .fallocate = hugetlbfs_fallocate, .fop_flags = FOP_HUGE_PAGES, }; static const struct inode_operations hugetlbfs_dir_inode_operations = { .create = hugetlbfs_create, .lookup = simple_lookup, .link = simple_link, .unlink = simple_unlink, .symlink = hugetlbfs_symlink, .mkdir = hugetlbfs_mkdir, .rmdir = simple_rmdir, .mknod = hugetlbfs_mknod, .rename = simple_rename, .setattr = hugetlbfs_setattr, .tmpfile = hugetlbfs_tmpfile, }; static const struct inode_operations hugetlbfs_inode_operations = { .setattr = hugetlbfs_setattr, }; static const struct super_operations hugetlbfs_ops = { .alloc_inode = hugetlbfs_alloc_inode, .free_inode = hugetlbfs_free_inode, .destroy_inode = hugetlbfs_destroy_inode, .evict_inode = hugetlbfs_evict_inode, .statfs = hugetlbfs_statfs, .put_super = hugetlbfs_put_super, .show_options = hugetlbfs_show_options, }; /* * Convert size option passed from command line to number of huge pages * in the pool specified by hstate. Size option could be in bytes * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT). */ static long hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt, enum hugetlbfs_size_type val_type) { if (val_type == NO_SIZE) return -1; if (val_type == SIZE_PERCENT) { size_opt <<= huge_page_shift(h); size_opt *= h->max_huge_pages; do_div(size_opt, 100); } size_opt >>= huge_page_shift(h); return size_opt; } /* * Parse one mount parameter. */ static int hugetlbfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct fs_parse_result result; struct hstate *h; char *rest; unsigned long ps; int opt; opt = fs_parse(fc, hugetlb_fs_parameters, param, &result); if (opt < 0) return opt; switch (opt) { case Opt_uid: ctx->uid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(ctx->uid)) goto bad_val; return 0; case Opt_gid: ctx->gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(ctx->gid)) goto bad_val; return 0; case Opt_mode: ctx->mode = result.uint_32 & 01777U; return 0; case Opt_size: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->max_size_opt = memparse(param->string, &rest); ctx->max_val_type = SIZE_STD; if (*rest == '%') ctx->max_val_type = SIZE_PERCENT; return 0; case Opt_nr_inodes: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->nr_inodes = memparse(param->string, &rest); return 0; case Opt_pagesize: ps = memparse(param->string, &rest); h = size_to_hstate(ps); if (!h) { pr_err("Unsupported page size %lu MB\n", ps / SZ_1M); return -EINVAL; } ctx->hstate = h; return 0; case Opt_min_size: /* memparse() will accept a K/M/G without a digit */ if (!param->string || !isdigit(param->string[0])) goto bad_val; ctx->min_size_opt = memparse(param->string, &rest); ctx->min_val_type = SIZE_STD; if (*rest == '%') ctx->min_val_type = SIZE_PERCENT; return 0; default: return -EINVAL; } bad_val: return invalfc(fc, "Bad value '%s' for mount option '%s'\n", param->string, param->key); } /* * Validate the parsed options. */ static int hugetlbfs_validate(struct fs_context *fc) { struct hugetlbfs_fs_context *ctx = fc->fs_private; /* * Use huge page pool size (in hstate) to convert the size * options to number of huge pages. If NO_SIZE, -1 is returned. */ ctx->max_hpages = hugetlbfs_size_to_hpages(ctx->hstate, ctx->max_size_opt, ctx->max_val_type); ctx->min_hpages = hugetlbfs_size_to_hpages(ctx->hstate, ctx->min_size_opt, ctx->min_val_type); /* * If max_size was specified, then min_size must be smaller */ if (ctx->max_val_type > NO_SIZE && ctx->min_hpages > ctx->max_hpages) { pr_err("Minimum size can not be greater than maximum size\n"); return -EINVAL; } return 0; } static int hugetlbfs_fill_super(struct super_block *sb, struct fs_context *fc) { struct hugetlbfs_fs_context *ctx = fc->fs_private; struct hugetlbfs_sb_info *sbinfo; sbinfo = kmalloc(sizeof(struct hugetlbfs_sb_info), GFP_KERNEL); if (!sbinfo) return -ENOMEM; sb->s_fs_info = sbinfo; spin_lock_init(&sbinfo->stat_lock); sbinfo->hstate = ctx->hstate; sbinfo->max_inodes = ctx->nr_inodes; sbinfo->free_inodes = ctx->nr_inodes; sbinfo->spool = NULL; sbinfo->uid = ctx->uid; sbinfo->gid = ctx->gid; sbinfo->mode = ctx->mode; /* * Allocate and initialize subpool if maximum or minimum size is * specified. Any needed reservations (for minimum size) are taken * when the subpool is created. */ if (ctx->max_hpages != -1 || ctx->min_hpages != -1) { sbinfo->spool = hugepage_new_subpool(ctx->hstate, ctx->max_hpages, ctx->min_hpages); if (!sbinfo->spool) goto out_free; } sb->s_maxbytes = MAX_LFS_FILESIZE; sb->s_blocksize = huge_page_size(ctx->hstate); sb->s_blocksize_bits = huge_page_shift(ctx->hstate); sb->s_magic = HUGETLBFS_MAGIC; sb->s_op = &hugetlbfs_ops; sb->s_time_gran = 1; /* * Due to the special and limited functionality of hugetlbfs, it does * not work well as a stacking filesystem. */ sb->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH; sb->s_root = d_make_root(hugetlbfs_get_root(sb, ctx)); if (!sb->s_root) goto out_free; return 0; out_free: kfree(sbinfo->spool); kfree(sbinfo); return -ENOMEM; } static int hugetlbfs_get_tree(struct fs_context *fc) { int err = hugetlbfs_validate(fc); if (err) return err; return get_tree_nodev(fc, hugetlbfs_fill_super); } static void hugetlbfs_fs_context_free(struct fs_context *fc) { kfree(fc->fs_private); } static const struct fs_context_operations hugetlbfs_fs_context_ops = { .free = hugetlbfs_fs_context_free, .parse_param = hugetlbfs_parse_param, .get_tree = hugetlbfs_get_tree, }; static int hugetlbfs_init_fs_context(struct fs_context *fc) { struct hugetlbfs_fs_context *ctx; ctx = kzalloc(sizeof(struct hugetlbfs_fs_context), GFP_KERNEL); if (!ctx) return -ENOMEM; ctx->max_hpages = -1; /* No limit on size by default */ ctx->nr_inodes = -1; /* No limit on number of inodes by default */ ctx->uid = current_fsuid(); ctx->gid = current_fsgid(); ctx->mode = 0755; ctx->hstate = &default_hstate; ctx->min_hpages = -1; /* No default minimum size */ ctx->max_val_type = NO_SIZE; ctx->min_val_type = NO_SIZE; fc->fs_private = ctx; fc->ops = &hugetlbfs_fs_context_ops; return 0; } static struct file_system_type hugetlbfs_fs_type = { .name = "hugetlbfs", .init_fs_context = hugetlbfs_init_fs_context, .parameters = hugetlb_fs_parameters, .kill_sb = kill_litter_super, .fs_flags = FS_ALLOW_IDMAP, }; static struct vfsmount *hugetlbfs_vfsmount[HUGE_MAX_HSTATE]; static int can_do_hugetlb_shm(void) { kgid_t shm_group; shm_group = make_kgid(&init_user_ns, sysctl_hugetlb_shm_group); return capable(CAP_IPC_LOCK) || in_group_p(shm_group); } static int get_hstate_idx(int page_size_log) { struct hstate *h = hstate_sizelog(page_size_log); if (!h) return -1; return hstate_index(h); } /* * Note that size should be aligned to proper hugepage size in caller side, * otherwise hugetlb_reserve_pages reserves one less hugepages than intended. */ struct file *hugetlb_file_setup(const char *name, size_t size, vm_flags_t acctflag, int creat_flags, int page_size_log) { struct inode *inode; struct vfsmount *mnt; int hstate_idx; struct file *file; hstate_idx = get_hstate_idx(page_size_log); if (hstate_idx < 0) return ERR_PTR(-ENODEV); mnt = hugetlbfs_vfsmount[hstate_idx]; if (!mnt) return ERR_PTR(-ENOENT); if (creat_flags == HUGETLB_SHMFS_INODE && !can_do_hugetlb_shm()) { struct ucounts *ucounts = current_ucounts(); if (user_shm_lock(size, ucounts)) { pr_warn_once("%s (%d): Using mlock ulimits for SHM_HUGETLB is obsolete\n", current->comm, current->pid); user_shm_unlock(size, ucounts); } return ERR_PTR(-EPERM); } file = ERR_PTR(-ENOSPC); /* hugetlbfs_vfsmount[] mounts do not use idmapped mounts. */ inode = hugetlbfs_get_inode(mnt->mnt_sb, &nop_mnt_idmap, NULL, S_IFREG | S_IRWXUGO, 0); if (!inode) goto out; if (creat_flags == HUGETLB_SHMFS_INODE) inode->i_flags |= S_PRIVATE; inode->i_size = size; clear_nlink(inode); if (!hugetlb_reserve_pages(inode, 0, size >> huge_page_shift(hstate_inode(inode)), NULL, acctflag)) file = ERR_PTR(-ENOMEM); else file = alloc_file_pseudo(inode, mnt, name, O_RDWR, &hugetlbfs_file_operations); if (!IS_ERR(file)) return file; iput(inode); out: return file; } static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h) { struct fs_context *fc; struct vfsmount *mnt; fc = fs_context_for_mount(&hugetlbfs_fs_type, SB_KERNMOUNT); if (IS_ERR(fc)) { mnt = ERR_CAST(fc); } else { struct hugetlbfs_fs_context *ctx = fc->fs_private; ctx->hstate = h; mnt = fc_mount(fc); put_fs_context(fc); } if (IS_ERR(mnt)) pr_err("Cannot mount internal hugetlbfs for page size %luK", huge_page_size(h) / SZ_1K); return mnt; } static int __init init_hugetlbfs_fs(void) { struct vfsmount *mnt; struct hstate *h; int error; int i; if (!hugepages_supported()) { pr_info("disabling because there are no supported hugepage sizes\n"); return -ENOTSUPP; } error = -ENOMEM; hugetlbfs_inode_cachep = kmem_cache_create("hugetlbfs_inode_cache", sizeof(struct hugetlbfs_inode_info), 0, SLAB_ACCOUNT, init_once); if (hugetlbfs_inode_cachep == NULL) goto out; error = register_filesystem(&hugetlbfs_fs_type); if (error) goto out_free; /* default hstate mount is required */ mnt = mount_one_hugetlbfs(&default_hstate); if (IS_ERR(mnt)) { error = PTR_ERR(mnt); goto out_unreg; } hugetlbfs_vfsmount[default_hstate_idx] = mnt; /* other hstates are optional */ i = 0; for_each_hstate(h) { if (i == default_hstate_idx) { i++; continue; } mnt = mount_one_hugetlbfs(h); if (IS_ERR(mnt)) hugetlbfs_vfsmount[i] = NULL; else hugetlbfs_vfsmount[i] = mnt; i++; } return 0; out_unreg: (void)unregister_filesystem(&hugetlbfs_fs_type); out_free: kmem_cache_destroy(hugetlbfs_inode_cachep); out: return error; } fs_initcall(init_hugetlbfs_fs) |
| 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 | /* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */ #ifndef _LINUX_RSEQ_H #define _LINUX_RSEQ_H #ifdef CONFIG_RSEQ #include <linux/preempt.h> #include <linux/sched.h> /* * Map the event mask on the user-space ABI enum rseq_cs_flags * for direct mask checks. */ enum rseq_event_mask_bits { RSEQ_EVENT_PREEMPT_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT, RSEQ_EVENT_SIGNAL_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT, RSEQ_EVENT_MIGRATE_BIT = RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT, }; enum rseq_event_mask { RSEQ_EVENT_PREEMPT = (1U << RSEQ_EVENT_PREEMPT_BIT), RSEQ_EVENT_SIGNAL = (1U << RSEQ_EVENT_SIGNAL_BIT), RSEQ_EVENT_MIGRATE = (1U << RSEQ_EVENT_MIGRATE_BIT), }; static inline void rseq_set_notify_resume(struct task_struct *t) { if (t->rseq) set_tsk_thread_flag(t, TIF_NOTIFY_RESUME); } void __rseq_handle_notify_resume(struct ksignal *sig, struct pt_regs *regs); static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { if (current->rseq) __rseq_handle_notify_resume(ksig, regs); } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { preempt_disable(); __set_bit(RSEQ_EVENT_SIGNAL_BIT, ¤t->rseq_event_mask); preempt_enable(); rseq_handle_notify_resume(ksig, regs); } /* rseq_preempt() requires preemption to be disabled. */ static inline void rseq_preempt(struct task_struct *t) { __set_bit(RSEQ_EVENT_PREEMPT_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* rseq_migrate() requires preemption to be disabled. */ static inline void rseq_migrate(struct task_struct *t) { __set_bit(RSEQ_EVENT_MIGRATE_BIT, &t->rseq_event_mask); rseq_set_notify_resume(t); } /* * If parent process has a registered restartable sequences area, the * child inherits. Unregister rseq for a clone with CLONE_VM set. */ static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { if (clone_flags & CLONE_VM) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } else { t->rseq = current->rseq; t->rseq_len = current->rseq_len; t->rseq_sig = current->rseq_sig; t->rseq_event_mask = current->rseq_event_mask; } } static inline void rseq_execve(struct task_struct *t) { t->rseq = NULL; t->rseq_len = 0; t->rseq_sig = 0; t->rseq_event_mask = 0; } #else static inline void rseq_set_notify_resume(struct task_struct *t) { } static inline void rseq_handle_notify_resume(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { } static inline void rseq_preempt(struct task_struct *t) { } static inline void rseq_migrate(struct task_struct *t) { } static inline void rseq_fork(struct task_struct *t, unsigned long clone_flags) { } static inline void rseq_execve(struct task_struct *t) { } #endif #ifdef CONFIG_DEBUG_RSEQ void rseq_syscall(struct pt_regs *regs); #else static inline void rseq_syscall(struct pt_regs *regs) { } #endif #endif /* _LINUX_RSEQ_H */ |
| 14 14 9 9 5 5 5 5 5 14 14 14 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 | // SPDX-License-Identifier: GPL-2.0-only /* * common LSM auditing functions * * Based on code written for SELinux by : * Stephen Smalley, <sds@tycho.nsa.gov> * James Morris <jmorris@redhat.com> * Author : Etienne Basset, <etienne.basset@ensta.org> */ #include <linux/types.h> #include <linux/stddef.h> #include <linux/kernel.h> #include <linux/gfp.h> #include <linux/fs.h> #include <linux/init.h> #include <net/sock.h> #include <linux/un.h> #include <net/af_unix.h> #include <linux/audit.h> #include <linux/ipv6.h> #include <linux/ip.h> #include <net/ip.h> #include <net/ipv6.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/dccp.h> #include <linux/sctp.h> #include <linux/lsm_audit.h> #include <linux/security.h> /** * ipv4_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv4_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int ret = 0; struct iphdr *ih; ih = ip_hdr(skb); ad->u.net->v4info.saddr = ih->saddr; ad->u.net->v4info.daddr = ih->daddr; if (proto) *proto = ih->protocol; /* non initial fragment */ if (ntohs(ih->frag_off) & IP_OFFSET) return 0; switch (ih->protocol) { case IPPROTO_TCP: { struct tcphdr *th = tcp_hdr(skb); ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr *uh = udp_hdr(skb); ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr *dh = dccp_hdr(skb); ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } case IPPROTO_SCTP: { struct sctphdr *sh = sctp_hdr(skb); ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #if IS_ENABLED(CONFIG_IPV6) /** * ipv6_skb_to_auditdata : fill auditdata from skb * @skb : the skb * @ad : the audit data to fill * @proto : the layer 4 protocol * * return 0 on success */ int ipv6_skb_to_auditdata(struct sk_buff *skb, struct common_audit_data *ad, u8 *proto) { int offset, ret = 0; struct ipv6hdr *ip6; u8 nexthdr; __be16 frag_off; ip6 = ipv6_hdr(skb); ad->u.net->v6info.saddr = ip6->saddr; ad->u.net->v6info.daddr = ip6->daddr; /* IPv6 can have several extension header before the Transport header * skip them */ offset = skb_network_offset(skb); offset += sizeof(*ip6); nexthdr = ip6->nexthdr; offset = ipv6_skip_exthdr(skb, offset, &nexthdr, &frag_off); if (offset < 0) return 0; if (proto) *proto = nexthdr; switch (nexthdr) { case IPPROTO_TCP: { struct tcphdr _tcph, *th; th = skb_header_pointer(skb, offset, sizeof(_tcph), &_tcph); if (th == NULL) break; ad->u.net->sport = th->source; ad->u.net->dport = th->dest; break; } case IPPROTO_UDP: { struct udphdr _udph, *uh; uh = skb_header_pointer(skb, offset, sizeof(_udph), &_udph); if (uh == NULL) break; ad->u.net->sport = uh->source; ad->u.net->dport = uh->dest; break; } case IPPROTO_DCCP: { struct dccp_hdr _dccph, *dh; dh = skb_header_pointer(skb, offset, sizeof(_dccph), &_dccph); if (dh == NULL) break; ad->u.net->sport = dh->dccph_sport; ad->u.net->dport = dh->dccph_dport; break; } case IPPROTO_SCTP: { struct sctphdr _sctph, *sh; sh = skb_header_pointer(skb, offset, sizeof(_sctph), &_sctph); if (sh == NULL) break; ad->u.net->sport = sh->source; ad->u.net->dport = sh->dest; break; } default: ret = -EINVAL; } return ret; } #endif static inline void print_ipv6_addr(struct audit_buffer *ab, const struct in6_addr *addr, __be16 port, char *name1, char *name2) { if (!ipv6_addr_any(addr)) audit_log_format(ab, " %s=%pI6c", name1, addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } static inline void print_ipv4_addr(struct audit_buffer *ab, __be32 addr, __be16 port, char *name1, char *name2) { if (addr) audit_log_format(ab, " %s=%pI4", name1, &addr); if (port) audit_log_format(ab, " %s=%d", name2, ntohs(port)); } /** * dump_common_audit_data - helper to dump common audit data * @ab : the audit buffer * @a : common audit data * */ static void dump_common_audit_data(struct audit_buffer *ab, struct common_audit_data *a) { char comm[sizeof(current->comm)]; /* * To keep stack sizes in check force programmers to notice if they * start making this union too large! See struct lsm_network_audit * as an example of how to deal with large data. */ BUILD_BUG_ON(sizeof(a->u) > sizeof(void *)*2); audit_log_format(ab, " pid=%d comm=", task_tgid_nr(current)); audit_log_untrustedstring(ab, memcpy(comm, current->comm, sizeof(comm))); switch (a->type) { case LSM_AUDIT_DATA_NONE: return; case LSM_AUDIT_DATA_IPC: audit_log_format(ab, " ipc_key=%d ", a->u.ipc_id); break; case LSM_AUDIT_DATA_CAP: audit_log_format(ab, " capability=%d ", a->u.cap); break; case LSM_AUDIT_DATA_PATH: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.path); inode = d_backing_inode(a->u.path.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_FILE: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.file->f_path); inode = file_inode(a->u.file); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_IOCTL_OP: { struct inode *inode; audit_log_d_path(ab, " path=", &a->u.op->path); inode = a->u.op->path.dentry->d_inode; if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } audit_log_format(ab, " ioctlcmd=0x%hx", a->u.op->cmd); break; } case LSM_AUDIT_DATA_DENTRY: { struct inode *inode; audit_log_format(ab, " name="); spin_lock(&a->u.dentry->d_lock); audit_log_untrustedstring(ab, a->u.dentry->d_name.name); spin_unlock(&a->u.dentry->d_lock); inode = d_backing_inode(a->u.dentry); if (inode) { audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); } break; } case LSM_AUDIT_DATA_INODE: { struct dentry *dentry; struct inode *inode; rcu_read_lock(); inode = a->u.inode; dentry = d_find_alias_rcu(inode); if (dentry) { audit_log_format(ab, " name="); spin_lock(&dentry->d_lock); audit_log_untrustedstring(ab, dentry->d_name.name); spin_unlock(&dentry->d_lock); } audit_log_format(ab, " dev="); audit_log_untrustedstring(ab, inode->i_sb->s_id); audit_log_format(ab, " ino=%lu", inode->i_ino); rcu_read_unlock(); break; } case LSM_AUDIT_DATA_TASK: { struct task_struct *tsk = a->u.tsk; if (tsk) { pid_t pid = task_tgid_nr(tsk); if (pid) { char comm[sizeof(tsk->comm)]; audit_log_format(ab, " opid=%d ocomm=", pid); audit_log_untrustedstring(ab, memcpy(comm, tsk->comm, sizeof(comm))); } } break; } case LSM_AUDIT_DATA_NET: if (a->u.net->sk) { const struct sock *sk = a->u.net->sk; const struct unix_sock *u; struct unix_address *addr; int len = 0; char *p = NULL; switch (sk->sk_family) { case AF_INET: { const struct inet_sock *inet = inet_sk(sk); print_ipv4_addr(ab, inet->inet_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv4_addr(ab, inet->inet_daddr, inet->inet_dport, "faddr", "fport"); break; } #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: { const struct inet_sock *inet = inet_sk(sk); print_ipv6_addr(ab, &sk->sk_v6_rcv_saddr, inet->inet_sport, "laddr", "lport"); print_ipv6_addr(ab, &sk->sk_v6_daddr, inet->inet_dport, "faddr", "fport"); break; } #endif case AF_UNIX: u = unix_sk(sk); addr = smp_load_acquire(&u->addr); if (!addr) break; if (u->path.dentry) { audit_log_d_path(ab, " path=", &u->path); break; } len = addr->len-sizeof(short); p = &addr->name->sun_path[0]; audit_log_format(ab, " path="); if (*p) audit_log_untrustedstring(ab, p); else audit_log_n_hex(ab, p, len); break; } } switch (a->u.net->family) { case AF_INET: print_ipv4_addr(ab, a->u.net->v4info.saddr, a->u.net->sport, "saddr", "src"); print_ipv4_addr(ab, a->u.net->v4info.daddr, a->u.net->dport, "daddr", "dest"); break; case AF_INET6: print_ipv6_addr(ab, &a->u.net->v6info.saddr, a->u.net->sport, "saddr", "src"); print_ipv6_addr(ab, &a->u.net->v6info.daddr, a->u.net->dport, "daddr", "dest"); break; } if (a->u.net->netif > 0) { struct net_device *dev; /* NOTE: we always use init's namespace */ dev = dev_get_by_index(&init_net, a->u.net->netif); if (dev) { audit_log_format(ab, " netif=%s", dev->name); dev_put(dev); } } break; #ifdef CONFIG_KEYS case LSM_AUDIT_DATA_KEY: audit_log_format(ab, " key_serial=%u", a->u.key_struct.key); if (a->u.key_struct.key_desc) { audit_log_format(ab, " key_desc="); audit_log_untrustedstring(ab, a->u.key_struct.key_desc); } break; #endif case LSM_AUDIT_DATA_KMOD: audit_log_format(ab, " kmod="); audit_log_untrustedstring(ab, a->u.kmod_name); break; case LSM_AUDIT_DATA_IBPKEY: { struct in6_addr sbn_pfx; memset(&sbn_pfx.s6_addr, 0, sizeof(sbn_pfx.s6_addr)); memcpy(&sbn_pfx.s6_addr, &a->u.ibpkey->subnet_prefix, sizeof(a->u.ibpkey->subnet_prefix)); audit_log_format(ab, " pkey=0x%x subnet_prefix=%pI6c", a->u.ibpkey->pkey, &sbn_pfx); break; } case LSM_AUDIT_DATA_IBENDPORT: audit_log_format(ab, " device=%s port_num=%u", a->u.ibendport->dev_name, a->u.ibendport->port); break; case LSM_AUDIT_DATA_LOCKDOWN: audit_log_format(ab, " lockdown_reason=\"%s\"", lockdown_reasons[a->u.reason]); break; case LSM_AUDIT_DATA_ANONINODE: audit_log_format(ab, " anonclass=%s", a->u.anonclass); break; } /* switch (a->type) */ } /** * common_lsm_audit - generic LSM auditing function * @a: auxiliary audit data * @pre_audit: lsm-specific pre-audit callback * @post_audit: lsm-specific post-audit callback * * setup the audit buffer for common security information * uses callback to print LSM specific information */ void common_lsm_audit(struct common_audit_data *a, void (*pre_audit)(struct audit_buffer *, void *), void (*post_audit)(struct audit_buffer *, void *)) { struct audit_buffer *ab; if (a == NULL) return; /* we use GFP_ATOMIC so we won't sleep */ ab = audit_log_start(audit_context(), GFP_ATOMIC | __GFP_NOWARN, AUDIT_AVC); if (ab == NULL) return; if (pre_audit) pre_audit(ab, a); dump_common_audit_data(ab, a); if (post_audit) post_audit(ab, a); audit_log_end(ab); } |
| 70 70 83 83 83 70 70 70 83 69 28 27 28 28 17 17 17 58 57 58 58 58 58 104 104 104 104 104 104 104 132 103 133 178 159 133 177 178 178 178 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2009 Red Hat, Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/numa_balancing.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/shrinker.h> #include <linux/mm_inline.h> #include <linux/swapops.h> #include <linux/backing-dev.h> #include <linux/dax.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/pfn_t.h> #include <linux/mman.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/debugfs.h> #include <linux/migrate.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/shmem_fs.h> #include <linux/oom.h> #include <linux/numa.h> #include <linux/page_owner.h> #include <linux/sched/sysctl.h> #include <linux/memory-tiers.h> #include <linux/compat.h> #include <linux/pgalloc_tag.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "swap.h" #define CREATE_TRACE_POINTS #include <trace/events/thp.h> /* * By default, transparent hugepage support is disabled in order to avoid * risking an increased memory footprint for applications that are not * guaranteed to benefit from it. When transparent hugepage support is * enabled, it is for all mappings, and khugepaged scans all mappings. * Defrag is invoked by khugepaged hugepage allocations and by page faults * for all hugepage allocations. */ unsigned long transparent_hugepage_flags __read_mostly = #ifdef CONFIG_TRANSPARENT_HUGEPAGE_ALWAYS (1<<TRANSPARENT_HUGEPAGE_FLAG)| #endif #ifdef CONFIG_TRANSPARENT_HUGEPAGE_MADVISE (1<<TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG)| #endif (1<<TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG)| (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)| (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); static struct shrinker *deferred_split_shrinker; static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc); static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc); static atomic_t huge_zero_refcount; struct folio *huge_zero_folio __read_mostly; unsigned long huge_zero_pfn __read_mostly = ~0UL; unsigned long huge_anon_orders_always __read_mostly; unsigned long huge_anon_orders_madvise __read_mostly; unsigned long huge_anon_orders_inherit __read_mostly; unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma, unsigned long vm_flags, unsigned long tva_flags, unsigned long orders) { bool smaps = tva_flags & TVA_SMAPS; bool in_pf = tva_flags & TVA_IN_PF; bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS; /* Check the intersection of requested and supported orders. */ orders &= vma_is_anonymous(vma) ? THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE; if (!orders) return 0; if (!vma->vm_mm) /* vdso */ return 0; /* * Explicitly disabled through madvise or prctl, or some * architectures may disable THP for some mappings, for * example, s390 kvm. * */ if ((vm_flags & VM_NOHUGEPAGE) || test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags)) return 0; /* * If the hardware/firmware marked hugepage support disabled. */ if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED)) return 0; /* khugepaged doesn't collapse DAX vma, but page fault is fine. */ if (vma_is_dax(vma)) return in_pf ? orders : 0; /* * khugepaged special VMA and hugetlb VMA. * Must be checked after dax since some dax mappings may have * VM_MIXEDMAP set. */ if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED)) return 0; /* * Check alignment for file vma and size for both file and anon vma by * filtering out the unsuitable orders. * * Skip the check for page fault. Huge fault does the check in fault * handlers. */ if (!in_pf) { int order = highest_order(orders); unsigned long addr; while (orders) { addr = vma->vm_end - (PAGE_SIZE << order); if (thp_vma_suitable_order(vma, addr, order)) break; order = next_order(&orders, order); } if (!orders) return 0; } /* * Enabled via shmem mount options or sysfs settings. * Must be done before hugepage flags check since shmem has its * own flags. */ if (!in_pf && shmem_file(vma->vm_file)) return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff, !enforce_sysfs, vma->vm_mm, vm_flags) ? orders : 0; if (!vma_is_anonymous(vma)) { /* * Enforce sysfs THP requirements as necessary. Anonymous vmas * were already handled in thp_vma_allowable_orders(). */ if (enforce_sysfs && (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) && !hugepage_global_always()))) return 0; /* * Trust that ->huge_fault() handlers know what they are doing * in fault path. */ if (((in_pf || smaps)) && vma->vm_ops->huge_fault) return orders; /* Only regular file is valid in collapse path */ if (((!in_pf || smaps)) && file_thp_enabled(vma)) return orders; return 0; } if (vma_is_temporary_stack(vma)) return 0; /* * THPeligible bit of smaps should show 1 for proper VMAs even * though anon_vma is not initialized yet. * * Allow page fault since anon_vma may be not initialized until * the first page fault. */ if (!vma->anon_vma) return (smaps || in_pf) ? orders : 0; return orders; } static bool get_huge_zero_page(void) { struct folio *zero_folio; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) return true; zero_folio = folio_alloc((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_folio) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); return false; } preempt_disable(); if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) { preempt_enable(); folio_put(zero_folio); goto retry; } WRITE_ONCE(huge_zero_pfn, folio_pfn(zero_folio)); /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); count_vm_event(THP_ZERO_PAGE_ALLOC); return true; } static void put_huge_zero_page(void) { /* * Counter should never go to zero here. Only shrinker can put * last reference. */ BUG_ON(atomic_dec_and_test(&huge_zero_refcount)); } struct folio *mm_get_huge_zero_folio(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) return READ_ONCE(huge_zero_folio); if (!get_huge_zero_page()) return NULL; if (test_and_set_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); return READ_ONCE(huge_zero_folio); } void mm_put_huge_zero_folio(struct mm_struct *mm) { if (test_bit(MMF_HUGE_ZERO_PAGE, &mm->flags)) put_huge_zero_page(); } static unsigned long shrink_huge_zero_page_count(struct shrinker *shrink, struct shrink_control *sc) { /* we can free zero page only if last reference remains */ return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; } static unsigned long shrink_huge_zero_page_scan(struct shrinker *shrink, struct shrink_control *sc) { if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { struct folio *zero_folio = xchg(&huge_zero_folio, NULL); BUG_ON(zero_folio == NULL); WRITE_ONCE(huge_zero_pfn, ~0UL); folio_put(zero_folio); return HPAGE_PMD_NR; } return 0; } static struct shrinker *huge_zero_page_shrinker; #ifdef CONFIG_SYSFS static ssize_t enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (test_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags)) output = "[always] madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags)) output = "always [madvise] never"; else output = "always madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { ssize_t ret = count; if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); } else ret = -EINVAL; if (ret > 0) { int err = start_stop_khugepaged(); if (err) ret = err; } return ret; } static struct kobj_attribute enabled_attr = __ATTR_RW(enabled); ssize_t single_hugepage_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { return sysfs_emit(buf, "%d\n", !!test_bit(flag, &transparent_hugepage_flags)); } ssize_t single_hugepage_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) { unsigned long value; int ret; ret = kstrtoul(buf, 10, &value); if (ret < 0) return ret; if (value > 1) return -EINVAL; if (value) set_bit(flag, &transparent_hugepage_flags); else clear_bit(flag, &transparent_hugepage_flags); return count; } static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { const char *output; if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) output = "[always] defer defer+madvise madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) output = "always [defer] defer+madvise madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) output = "always defer [defer+madvise] madvise never"; else if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) output = "always defer defer+madvise [madvise] never"; else output = "always defer defer+madvise madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { if (sysfs_streq(buf, "always")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "defer+madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "defer")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); } else if (sysfs_streq(buf, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags); } else return -EINVAL; return count; } static struct kobj_attribute defrag_attr = __ATTR_RW(defrag); static ssize_t use_zero_page_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static ssize_t use_zero_page_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG); } static struct kobj_attribute use_zero_page_attr = __ATTR_RW(use_zero_page); static ssize_t hpage_pmd_size_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%lu\n", HPAGE_PMD_SIZE); } static struct kobj_attribute hpage_pmd_size_attr = __ATTR_RO(hpage_pmd_size); static struct attribute *hugepage_attr[] = { &enabled_attr.attr, &defrag_attr.attr, &use_zero_page_attr.attr, &hpage_pmd_size_attr.attr, #ifdef CONFIG_SHMEM &shmem_enabled_attr.attr, #endif NULL, }; static const struct attribute_group hugepage_attr_group = { .attrs = hugepage_attr, }; static void hugepage_exit_sysfs(struct kobject *hugepage_kobj); static void thpsize_release(struct kobject *kobj); static DEFINE_SPINLOCK(huge_anon_orders_lock); static LIST_HEAD(thpsize_list); struct thpsize { struct kobject kobj; struct list_head node; int order; }; #define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj) static ssize_t thpsize_enabled_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { int order = to_thpsize(kobj)->order; const char *output; if (test_bit(order, &huge_anon_orders_always)) output = "[always] inherit madvise never"; else if (test_bit(order, &huge_anon_orders_inherit)) output = "always [inherit] madvise never"; else if (test_bit(order, &huge_anon_orders_madvise)) output = "always inherit [madvise] never"; else output = "always inherit madvise [never]"; return sysfs_emit(buf, "%s\n", output); } static ssize_t thpsize_enabled_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int order = to_thpsize(kobj)->order; ssize_t ret = count; if (sysfs_streq(buf, "always")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_inherit); clear_bit(order, &huge_anon_orders_madvise); set_bit(order, &huge_anon_orders_always); spin_unlock(&huge_anon_orders_lock); } else if (sysfs_streq(buf, "inherit")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_always); clear_bit(order, &huge_anon_orders_madvise); set_bit(order, &huge_anon_orders_inherit); spin_unlock(&huge_anon_orders_lock); } else if (sysfs_streq(buf, "madvise")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_always); clear_bit(order, &huge_anon_orders_inherit); set_bit(order, &huge_anon_orders_madvise); spin_unlock(&huge_anon_orders_lock); } else if (sysfs_streq(buf, "never")) { spin_lock(&huge_anon_orders_lock); clear_bit(order, &huge_anon_orders_always); clear_bit(order, &huge_anon_orders_inherit); clear_bit(order, &huge_anon_orders_madvise); spin_unlock(&huge_anon_orders_lock); } else ret = -EINVAL; return ret; } static struct kobj_attribute thpsize_enabled_attr = __ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store); static struct attribute *thpsize_attrs[] = { &thpsize_enabled_attr.attr, NULL, }; static const struct attribute_group thpsize_attr_group = { .attrs = thpsize_attrs, }; static const struct kobj_type thpsize_ktype = { .release = &thpsize_release, .sysfs_ops = &kobj_sysfs_ops, }; DEFINE_PER_CPU(struct mthp_stat, mthp_stats) = {{{0}}}; static unsigned long sum_mthp_stat(int order, enum mthp_stat_item item) { unsigned long sum = 0; int cpu; for_each_possible_cpu(cpu) { struct mthp_stat *this = &per_cpu(mthp_stats, cpu); sum += this->stats[order][item]; } return sum; } #define DEFINE_MTHP_STAT_ATTR(_name, _index) \ static ssize_t _name##_show(struct kobject *kobj, \ struct kobj_attribute *attr, char *buf) \ { \ int order = to_thpsize(kobj)->order; \ \ return sysfs_emit(buf, "%lu\n", sum_mthp_stat(order, _index)); \ } \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) DEFINE_MTHP_STAT_ATTR(anon_fault_alloc, MTHP_STAT_ANON_FAULT_ALLOC); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK); DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT); DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK); static struct attribute *stats_attrs[] = { &anon_fault_alloc_attr.attr, &anon_fault_fallback_attr.attr, &anon_fault_fallback_charge_attr.attr, &swpout_attr.attr, &swpout_fallback_attr.attr, NULL, }; static struct attribute_group stats_attr_group = { .name = "stats", .attrs = stats_attrs, }; static struct thpsize *thpsize_create(int order, struct kobject *parent) { unsigned long size = (PAGE_SIZE << order) / SZ_1K; struct thpsize *thpsize; int ret; thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL); if (!thpsize) return ERR_PTR(-ENOMEM); ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent, "hugepages-%lukB", size); if (ret) { kfree(thpsize); return ERR_PTR(ret); } ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group); if (ret) { kobject_put(&thpsize->kobj); return ERR_PTR(ret); } ret = sysfs_create_group(&thpsize->kobj, &stats_attr_group); if (ret) { kobject_put(&thpsize->kobj); return ERR_PTR(ret); } thpsize->order = order; return thpsize; } static void thpsize_release(struct kobject *kobj) { kfree(to_thpsize(kobj)); } static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj) { int err; struct thpsize *thpsize; unsigned long orders; int order; /* * Default to setting PMD-sized THP to inherit the global setting and * disable all other sizes. powerpc's PMD_ORDER isn't a compile-time * constant so we have to do this here. */ huge_anon_orders_inherit = BIT(PMD_ORDER); *hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj); if (unlikely(!*hugepage_kobj)) { pr_err("failed to create transparent hugepage kobject\n"); return -ENOMEM; } err = sysfs_create_group(*hugepage_kobj, &hugepage_attr_group); if (err) { pr_err("failed to register transparent hugepage group\n"); goto delete_obj; } err = sysfs_create_group(*hugepage_kobj, &khugepaged_attr_group); if (err) { pr_err("failed to register transparent hugepage group\n"); goto remove_hp_group; } orders = THP_ORDERS_ALL_ANON; order = highest_order(orders); while (orders) { thpsize = thpsize_create(order, *hugepage_kobj); if (IS_ERR(thpsize)) { pr_err("failed to create thpsize for order %d\n", order); err = PTR_ERR(thpsize); goto remove_all; } list_add(&thpsize->node, &thpsize_list); order = next_order(&orders, order); } return 0; remove_all: hugepage_exit_sysfs(*hugepage_kobj); return err; remove_hp_group: sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group); delete_obj: kobject_put(*hugepage_kobj); return err; } static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj) { struct thpsize *thpsize, *tmp; list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) { list_del(&thpsize->node); kobject_put(&thpsize->kobj); } sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group); sysfs_remove_group(hugepage_kobj, &hugepage_attr_group); kobject_put(hugepage_kobj); } #else static inline int hugepage_init_sysfs(struct kobject **hugepage_kobj) { return 0; } static inline void hugepage_exit_sysfs(struct kobject *hugepage_kobj) { } #endif /* CONFIG_SYSFS */ static int __init thp_shrinker_init(void) { huge_zero_page_shrinker = shrinker_alloc(0, "thp-zero"); if (!huge_zero_page_shrinker) return -ENOMEM; deferred_split_shrinker = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE | SHRINKER_NONSLAB, "thp-deferred_split"); if (!deferred_split_shrinker) { shrinker_free(huge_zero_page_shrinker); return -ENOMEM; } huge_zero_page_shrinker->count_objects = shrink_huge_zero_page_count; huge_zero_page_shrinker->scan_objects = shrink_huge_zero_page_scan; shrinker_register(huge_zero_page_shrinker); deferred_split_shrinker->count_objects = deferred_split_count; deferred_split_shrinker->scan_objects = deferred_split_scan; shrinker_register(deferred_split_shrinker); return 0; } static void __init thp_shrinker_exit(void) { shrinker_free(huge_zero_page_shrinker); shrinker_free(deferred_split_shrinker); } static int __init hugepage_init(void) { int err; struct kobject *hugepage_kobj; if (!has_transparent_hugepage()) { transparent_hugepage_flags = 1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED; return -EINVAL; } /* * hugepages can't be allocated by the buddy allocator */ MAYBE_BUILD_BUG_ON(HPAGE_PMD_ORDER > MAX_PAGE_ORDER); err = hugepage_init_sysfs(&hugepage_kobj); if (err) goto err_sysfs; err = khugepaged_init(); if (err) goto err_slab; err = thp_shrinker_init(); if (err) goto err_shrinker; /* * By default disable transparent hugepages on smaller systems, * where the extra memory used could hurt more than TLB overhead * is likely to save. The admin can still enable it through /sys. */ if (totalram_pages() < (512 << (20 - PAGE_SHIFT))) { transparent_hugepage_flags = 0; return 0; } err = start_stop_khugepaged(); if (err) goto err_khugepaged; return 0; err_khugepaged: thp_shrinker_exit(); err_shrinker: khugepaged_destroy(); err_slab: hugepage_exit_sysfs(hugepage_kobj); err_sysfs: return err; } subsys_initcall(hugepage_init); static int __init setup_transparent_hugepage(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "always")) { set_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } else if (!strcmp(str, "madvise")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); set_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } else if (!strcmp(str, "never")) { clear_bit(TRANSPARENT_HUGEPAGE_FLAG, &transparent_hugepage_flags); clear_bit(TRANSPARENT_HUGEPAGE_REQ_MADV_FLAG, &transparent_hugepage_flags); ret = 1; } out: if (!ret) pr_warn("transparent_hugepage= cannot parse, ignored\n"); return ret; } __setup("transparent_hugepage=", setup_transparent_hugepage); pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pmd = pmd_mkwrite(pmd, vma); return pmd; } #ifdef CONFIG_MEMCG static inline struct deferred_split *get_deferred_split_queue(struct folio *folio) { struct mem_cgroup *memcg = folio_memcg(folio); struct pglist_data *pgdat = NODE_DATA(folio_nid(folio)); if (memcg) return &memcg->deferred_split_queue; else return &pgdat->deferred_split_queue; } #else static inline struct deferred_split *get_deferred_split_queue(struct folio *folio) { struct pglist_data *pgdat = NODE_DATA(folio_nid(folio)); return &pgdat->deferred_split_queue; } #endif static inline bool is_transparent_hugepage(const struct folio *folio) { if (!folio_test_large(folio)) return false; return is_huge_zero_folio(folio) || folio_test_large_rmappable(folio); } static unsigned long __thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, loff_t off, unsigned long flags, unsigned long size, vm_flags_t vm_flags) { loff_t off_end = off + len; loff_t off_align = round_up(off, size); unsigned long len_pad, ret, off_sub; if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall()) return 0; if (off_end <= off_align || (off_end - off_align) < size) return 0; len_pad = len + size; if (len_pad < len || (off + len_pad) < off) return 0; ret = mm_get_unmapped_area_vmflags(current->mm, filp, addr, len_pad, off >> PAGE_SHIFT, flags, vm_flags); /* * The failure might be due to length padding. The caller will retry * without the padding. */ if (IS_ERR_VALUE(ret)) return 0; /* * Do not try to align to THP boundary if allocation at the address * hint succeeds. */ if (ret == addr) return addr; off_sub = (off - ret) & (size - 1); if (test_bit(MMF_TOPDOWN, ¤t->mm->flags) && !off_sub) return ret + size; ret += off_sub; return ret; } unsigned long thp_get_unmapped_area_vmflags(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags, vm_flags_t vm_flags) { unsigned long ret; loff_t off = (loff_t)pgoff << PAGE_SHIFT; ret = __thp_get_unmapped_area(filp, addr, len, off, flags, PMD_SIZE, vm_flags); if (ret) return ret; return mm_get_unmapped_area_vmflags(current->mm, filp, addr, len, pgoff, flags, vm_flags); } unsigned long thp_get_unmapped_area(struct file *filp, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { return thp_get_unmapped_area_vmflags(filp, addr, len, pgoff, flags, 0); } EXPORT_SYMBOL_GPL(thp_get_unmapped_area); static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf, struct page *page, gfp_t gfp) { struct vm_area_struct *vma = vmf->vma; struct folio *folio = page_folio(page); pgtable_t pgtable; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret = 0; VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (mem_cgroup_charge(folio, vma->vm_mm, gfp)) { folio_put(folio); count_vm_event(THP_FAULT_FALLBACK); count_vm_event(THP_FAULT_FALLBACK_CHARGE); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE); return VM_FAULT_FALLBACK; } folio_throttle_swaprate(folio, gfp); pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) { ret = VM_FAULT_OOM; goto release; } clear_huge_page(page, vmf->address, HPAGE_PMD_NR); /* * The memory barrier inside __folio_mark_uptodate makes sure that * clear_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_none(*vmf->pmd))) { goto unlock_release; } else { pmd_t entry; ret = check_stable_address_space(vma->vm_mm); if (ret) goto unlock_release; /* Deliver the page fault to userland */ if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); folio_put(folio); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); return ret; } entry = mk_huge_pmd(page, vma->vm_page_prot); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); folio_add_new_anon_rmap(folio, vma, haddr); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(vma->vm_mm, vmf->pmd, pgtable); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, entry); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(vma->vm_mm); spin_unlock(vmf->ptl); count_vm_event(THP_FAULT_ALLOC); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC); count_memcg_event_mm(vma->vm_mm, THP_FAULT_ALLOC); } return 0; unlock_release: spin_unlock(vmf->ptl); release: if (pgtable) pte_free(vma->vm_mm, pgtable); folio_put(folio); return ret; } /* * always: directly stall for all thp allocations * defer: wake kswapd and fail if not immediately available * defer+madvise: wake kswapd and directly stall for MADV_HUGEPAGE, otherwise * fail if not immediately available * madvise: directly stall for MADV_HUGEPAGE, otherwise fail if not immediately * available * never: never stall for any thp allocation */ gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma) { const bool vma_madvised = vma && (vma->vm_flags & VM_HUGEPAGE); /* Always do synchronous compaction */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY); /* Kick kcompactd and fail quickly */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM; /* Synchronous compaction if madvised, otherwise kick kcompactd */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : __GFP_KSWAPD_RECLAIM); /* Only do synchronous compaction if madvised */ if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags)) return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM : 0); return GFP_TRANSHUGE_LIGHT; } /* Caller must hold page table lock. */ static void set_huge_zero_folio(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, struct folio *zero_folio) { pmd_t entry; if (!pmd_none(*pmd)) return; entry = mk_pmd(&zero_folio->page, vma->vm_page_prot); entry = pmd_mkhuge(entry); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); mm_inc_nr_ptes(mm); } vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; gfp_t gfp; struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; vm_fault_t ret; if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER)) return VM_FAULT_FALLBACK; ret = vmf_anon_prepare(vmf); if (ret) return ret; khugepaged_enter_vma(vma, vma->vm_flags); if (!(vmf->flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(vma->vm_mm) && transparent_hugepage_use_zero_page()) { pgtable_t pgtable; struct folio *zero_folio; vm_fault_t ret; pgtable = pte_alloc_one(vma->vm_mm); if (unlikely(!pgtable)) return VM_FAULT_OOM; zero_folio = mm_get_huge_zero_folio(vma->vm_mm); if (unlikely(!zero_folio)) { pte_free(vma->vm_mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); ret = 0; if (pmd_none(*vmf->pmd)) { ret = check_stable_address_space(vma->vm_mm); if (ret) { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); } else if (userfaultfd_missing(vma)) { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); ret = handle_userfault(vmf, VM_UFFD_MISSING); VM_BUG_ON(ret & VM_FAULT_FALLBACK); } else { set_huge_zero_folio(pgtable, vma->vm_mm, vma, haddr, vmf->pmd, zero_folio); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); } } else { spin_unlock(vmf->ptl); pte_free(vma->vm_mm, pgtable); } return ret; } gfp = vma_thp_gfp_mask(vma); folio = vma_alloc_folio(gfp, HPAGE_PMD_ORDER, vma, haddr, true); if (unlikely(!folio)) { count_vm_event(THP_FAULT_FALLBACK); count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_FALLBACK); return VM_FAULT_FALLBACK; } return __do_huge_pmd_anonymous_page(vmf, &folio->page, gfp); } static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, pgtable_t pgtable) { struct mm_struct *mm = vma->vm_mm; pmd_t entry; spinlock_t *ptl; ptl = pmd_lock(mm, pmd); if (!pmd_none(*pmd)) { if (write) { if (pmd_pfn(*pmd) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_huge_zero_pmd(*pmd)); goto out_unlock; } entry = pmd_mkyoung(*pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, addr, pmd, entry, 1)) update_mmu_cache_pmd(vma, addr, pmd); } goto out_unlock; } entry = pmd_mkhuge(pfn_t_pmd(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pmd_mkdevmap(entry); if (write) { entry = pmd_mkyoung(pmd_mkdirty(entry)); entry = maybe_pmd_mkwrite(entry, vma); } if (pgtable) { pgtable_trans_huge_deposit(mm, pmd, pgtable); mm_inc_nr_ptes(mm); pgtable = NULL; } set_pmd_at(mm, addr, pmd, entry); update_mmu_cache_pmd(vma, addr, pmd); out_unlock: spin_unlock(ptl); if (pgtable) pte_free(mm, pgtable); } /** * vmf_insert_pfn_pmd - insert a pmd size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @write: whether it's a write fault * * Insert a pmd size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write) { unsigned long addr = vmf->address & PMD_MASK; struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; pgtable_t pgtable = NULL; /* * If we had pmd_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; if (arch_needs_pgtable_deposit()) { pgtable = pte_alloc_one(vma->vm_mm); if (!pgtable) return VM_FAULT_OOM; } track_pfn_insert(vma, &pgprot, pfn); insert_pfn_pmd(vma, addr, vmf->pmd, pfn, pgprot, write, pgtable); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pmd); #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma) { if (likely(vma->vm_flags & VM_WRITE)) pud = pud_mkwrite(pud); return pud; } static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, pfn_t pfn, bool write) { struct mm_struct *mm = vma->vm_mm; pgprot_t prot = vma->vm_page_prot; pud_t entry; spinlock_t *ptl; ptl = pud_lock(mm, pud); if (!pud_none(*pud)) { if (write) { if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) { WARN_ON_ONCE(!is_huge_zero_pud(*pud)); goto out_unlock; } entry = pud_mkyoung(*pud); entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma); if (pudp_set_access_flags(vma, addr, pud, entry, 1)) update_mmu_cache_pud(vma, addr, pud); } goto out_unlock; } entry = pud_mkhuge(pfn_t_pud(pfn, prot)); if (pfn_t_devmap(pfn)) entry = pud_mkdevmap(entry); if (write) { entry = pud_mkyoung(pud_mkdirty(entry)); entry = maybe_pud_mkwrite(entry, vma); } set_pud_at(mm, addr, pud, entry); update_mmu_cache_pud(vma, addr, pud); out_unlock: spin_unlock(ptl); } /** * vmf_insert_pfn_pud - insert a pud size pfn * @vmf: Structure describing the fault * @pfn: pfn to insert * @write: whether it's a write fault * * Insert a pud size pfn. See vmf_insert_pfn() for additional info. * * Return: vm_fault_t value. */ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write) { unsigned long addr = vmf->address & PUD_MASK; struct vm_area_struct *vma = vmf->vma; pgprot_t pgprot = vma->vm_page_prot; /* * If we had pud_special, we could avoid all these restrictions, * but we need to be consistent with PTEs and architectures that * can't support a 'special' bit. */ BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) && !pfn_t_devmap(pfn)); BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) == (VM_PFNMAP|VM_MIXEDMAP)); BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags)); if (addr < vma->vm_start || addr >= vma->vm_end) return VM_FAULT_SIGBUS; track_pfn_insert(vma, &pgprot, pfn); insert_pfn_pud(vma, addr, vmf->pud, pfn, write); return VM_FAULT_NOPAGE; } EXPORT_SYMBOL_GPL(vmf_insert_pfn_pud); #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ void touch_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, bool write) { pmd_t _pmd; _pmd = pmd_mkyoung(*pmd); if (write) _pmd = pmd_mkdirty(_pmd); if (pmdp_set_access_flags(vma, addr & HPAGE_PMD_MASK, pmd, _pmd, write)) update_mmu_cache_pmd(vma, addr, pmd); } struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap) { unsigned long pfn = pmd_pfn(*pmd); struct mm_struct *mm = vma->vm_mm; struct page *page; int ret; assert_spin_locked(pmd_lockptr(mm, pmd)); if (flags & FOLL_WRITE && !pmd_write(*pmd)) return NULL; if (pmd_present(*pmd) && pmd_devmap(*pmd)) /* pass */; else return NULL; if (flags & FOLL_TOUCH) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); /* * device mapped pages can only be returned if the * caller will manage the page reference count. */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT; *pgmap = get_dev_pagemap(pfn, *pgmap); if (!*pgmap) return ERR_PTR(-EFAULT); page = pfn_to_page(pfn); ret = try_grab_page(page, flags); if (ret) page = ERR_PTR(ret); return page; } 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 *dst_vma, struct vm_area_struct *src_vma) { spinlock_t *dst_ptl, *src_ptl; struct page *src_page; struct folio *src_folio; pmd_t pmd; pgtable_t pgtable = NULL; int ret = -ENOMEM; /* Skip if can be re-fill on fault */ if (!vma_is_anonymous(dst_vma)) return 0; pgtable = pte_alloc_one(dst_mm); if (unlikely(!pgtable)) goto out; dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pmd = *src_pmd; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (unlikely(is_swap_pmd(pmd))) { swp_entry_t entry = pmd_to_swp_entry(pmd); VM_BUG_ON(!is_pmd_migration_entry(pmd)); if (!is_readable_migration_entry(entry)) { entry = make_readable_migration_entry( swp_offset(entry)); pmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*src_pmd)) pmd = pmd_swp_mksoft_dirty(pmd); if (pmd_swp_uffd_wp(*src_pmd)) pmd = pmd_swp_mkuffd_wp(pmd); set_pmd_at(src_mm, addr, src_pmd, pmd); } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); if (!userfaultfd_wp(dst_vma)) pmd = pmd_swp_clear_uffd_wp(pmd); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; goto out_unlock; } #endif if (unlikely(!pmd_trans_huge(pmd))) { pte_free(dst_mm, pgtable); goto out_unlock; } /* * When page table lock is held, the huge zero pmd should not be * under splitting since we don't split the page itself, only pmd to * a page table. */ if (is_huge_zero_pmd(pmd)) { /* * mm_get_huge_zero_folio() will never allocate a new * folio here, since we already have a zero page to * copy. It just takes a reference. */ mm_get_huge_zero_folio(dst_mm); goto out_zero_page; } src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); src_folio = page_folio(src_page); folio_get(src_folio); if (unlikely(folio_try_dup_anon_rmap_pmd(src_folio, src_page, src_vma))) { /* Page maybe pinned: split and retry the fault on PTEs. */ folio_put(src_folio); pte_free(dst_mm, pgtable); spin_unlock(src_ptl); spin_unlock(dst_ptl); __split_huge_pmd(src_vma, src_pmd, addr, false, NULL); return -EAGAIN; } add_mm_counter(dst_mm, MM_ANONPAGES, HPAGE_PMD_NR); out_zero_page: mm_inc_nr_ptes(dst_mm); pgtable_trans_huge_deposit(dst_mm, dst_pmd, pgtable); pmdp_set_wrprotect(src_mm, addr, src_pmd); if (!userfaultfd_wp(dst_vma)) pmd = pmd_clear_uffd_wp(pmd); pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); ret = 0; out_unlock: spin_unlock(src_ptl); spin_unlock(dst_ptl); out: return ret; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD void touch_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pud, bool write) { pud_t _pud; _pud = pud_mkyoung(*pud); if (write) _pud = pud_mkdirty(_pud); if (pudp_set_access_flags(vma, addr & HPAGE_PUD_MASK, pud, _pud, write)) update_mmu_cache_pud(vma, addr, pud); } 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) { spinlock_t *dst_ptl, *src_ptl; pud_t pud; int ret; dst_ptl = pud_lock(dst_mm, dst_pud); src_ptl = pud_lockptr(src_mm, src_pud); spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING); ret = -EAGAIN; pud = *src_pud; if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud))) goto out_unlock; /* * When page table lock is held, the huge zero pud should not be * under splitting since we don't split the page itself, only pud to * a page table. */ if (is_huge_zero_pud(pud)) { /* No huge zero pud yet */ } /* * TODO: once we support anonymous pages, use * folio_try_dup_anon_rmap_*() and split if duplicating fails. */ pudp_set_wrprotect(src_mm, addr, src_pud); pud = pud_mkold(pud_wrprotect(pud)); set_pud_at(dst_mm, addr, dst_pud, pud); ret = 0; out_unlock: spin_unlock(src_ptl); spin_unlock(dst_ptl); return ret; } void huge_pud_set_accessed(struct vm_fault *vmf, pud_t orig_pud) { bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pud_lock(vmf->vma->vm_mm, vmf->pud); if (unlikely(!pud_same(*vmf->pud, orig_pud))) goto unlock; touch_pud(vmf->vma, vmf->address, vmf->pud, write); unlock: spin_unlock(vmf->ptl); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ void huge_pmd_set_accessed(struct vm_fault *vmf) { bool write = vmf->flags & FAULT_FLAG_WRITE; vmf->ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(*vmf->pmd, vmf->orig_pmd))) goto unlock; touch_pmd(vmf->vma, vmf->address, vmf->pmd, write); unlock: spin_unlock(vmf->ptl); } vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf) { const bool unshare = vmf->flags & FAULT_FLAG_UNSHARE; struct vm_area_struct *vma = vmf->vma; struct folio *folio; struct page *page; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; pmd_t orig_pmd = vmf->orig_pmd; vmf->ptl = pmd_lockptr(vma->vm_mm, vmf->pmd); VM_BUG_ON_VMA(!vma->anon_vma, vma); if (is_huge_zero_pmd(orig_pmd)) goto fallback; spin_lock(vmf->ptl); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { spin_unlock(vmf->ptl); return 0; } page = pmd_page(orig_pmd); folio = page_folio(page); VM_BUG_ON_PAGE(!PageHead(page), page); /* Early check when only holding the PT lock. */ if (PageAnonExclusive(page)) goto reuse; if (!folio_trylock(folio)) { folio_get(folio); spin_unlock(vmf->ptl); folio_lock(folio); spin_lock(vmf->ptl); if (unlikely(!pmd_same(*vmf->pmd, orig_pmd))) { spin_unlock(vmf->ptl); folio_unlock(folio); folio_put(folio); return 0; } folio_put(folio); } /* Recheck after temporarily dropping the PT lock. */ if (PageAnonExclusive(page)) { folio_unlock(folio); goto reuse; } /* * See do_wp_page(): we can only reuse the folio exclusively if * there are no additional references. Note that we always drain * the LRU cache immediately after adding a THP. */ if (folio_ref_count(folio) > 1 + folio_test_swapcache(folio) * folio_nr_pages(folio)) goto unlock_fallback; if (folio_test_swapcache(folio)) folio_free_swap(folio); if (folio_ref_count(folio) == 1) { pmd_t entry; folio_move_anon_rmap(folio, vma); SetPageAnonExclusive(page); folio_unlock(folio); reuse: if (unlikely(unshare)) { spin_unlock(vmf->ptl); return 0; } entry = pmd_mkyoung(orig_pmd); entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); if (pmdp_set_access_flags(vma, haddr, vmf->pmd, entry, 1)) update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); return 0; } unlock_fallback: folio_unlock(folio); spin_unlock(vmf->ptl); fallback: __split_huge_pmd(vma, vmf->pmd, vmf->address, false, NULL); return VM_FAULT_FALLBACK; } static inline bool can_change_pmd_writable(struct vm_area_struct *vma, unsigned long addr, pmd_t pmd) { struct page *page; if (WARN_ON_ONCE(!(vma->vm_flags & VM_WRITE))) return false; /* Don't touch entries that are not even readable (NUMA hinting). */ if (pmd_protnone(pmd)) return false; /* Do we need write faults for softdirty tracking? */ if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) return false; /* Do we need write faults for uffd-wp tracking? */ if (userfaultfd_huge_pmd_wp(vma, pmd)) return false; if (!(vma->vm_flags & VM_SHARED)) { /* See can_change_pte_writable(). */ page = vm_normal_page_pmd(vma, addr, pmd); return page && PageAnon(page) && PageAnonExclusive(page); } /* See can_change_pte_writable(). */ return pmd_dirty(pmd); } /* NUMA hinting page fault entry point for trans huge pmds */ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf) { struct vm_area_struct *vma = vmf->vma; pmd_t oldpmd = vmf->orig_pmd; pmd_t pmd; struct folio *folio; unsigned long haddr = vmf->address & HPAGE_PMD_MASK; int nid = NUMA_NO_NODE; int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK); bool migrated = false, writable = false; int flags = 0; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); goto out; } pmd = pmd_modify(oldpmd, vma->vm_page_prot); /* * Detect now whether the PMD could be writable; this information * is only valid while holding the PT lock. */ writable = pmd_write(pmd); if (!writable && vma_wants_manual_pte_write_upgrade(vma) && can_change_pmd_writable(vma, vmf->address, pmd)) writable = true; folio = vm_normal_folio_pmd(vma, haddr, pmd); if (!folio) goto out_map; /* See similar comment in do_numa_page for explanation */ if (!writable) flags |= TNF_NO_GROUP; nid = folio_nid(folio); /* * For memory tiering mode, cpupid of slow memory page is used * to record page access time. So use default value. */ if (node_is_toptier(nid)) last_cpupid = folio_last_cpupid(folio); target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags); if (target_nid == NUMA_NO_NODE) { folio_put(folio); goto out_map; } spin_unlock(vmf->ptl); writable = false; migrated = migrate_misplaced_folio(folio, vma, target_nid); if (migrated) { flags |= TNF_MIGRATED; nid = target_nid; } else { flags |= TNF_MIGRATE_FAIL; vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd); if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) { spin_unlock(vmf->ptl); goto out; } goto out_map; } out: if (nid != NUMA_NO_NODE) task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags); return 0; out_map: /* Restore the PMD */ pmd = pmd_modify(oldpmd, vma->vm_page_prot); pmd = pmd_mkyoung(pmd); if (writable) pmd = pmd_mkwrite(pmd, vma); set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd); update_mmu_cache_pmd(vma, vmf->address, vmf->pmd); spin_unlock(vmf->ptl); goto out; } /* * Return true if we do MADV_FREE successfully on entire pmd page. * Otherwise, return false. */ bool madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long next) { spinlock_t *ptl; pmd_t orig_pmd; struct folio *folio; struct mm_struct *mm = tlb->mm; bool ret = false; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = pmd_trans_huge_lock(pmd, vma); if (!ptl) goto out_unlocked; orig_pmd = *pmd; if (is_huge_zero_pmd(orig_pmd)) goto out; if (unlikely(!pmd_present(orig_pmd))) { VM_BUG_ON(thp_migration_supported() && !is_pmd_migration_entry(orig_pmd)); goto out; } folio = pmd_folio(orig_pmd); /* * If other processes are mapping this folio, we couldn't discard * the folio unless they all do MADV_FREE so let's skip the folio. */ if (folio_likely_mapped_shared(folio)) goto out; if (!folio_trylock(folio)) goto out; /* * If user want to discard part-pages of THP, split it so MADV_FREE * will deactivate only them. */ if (next - addr != HPAGE_PMD_SIZE) { folio_get(folio); spin_unlock(ptl); split_folio(folio); folio_unlock(folio); folio_put(folio); goto out_unlocked; } if (folio_test_dirty(folio)) folio_clear_dirty(folio); folio_unlock(folio); if (pmd_young(orig_pmd) || pmd_dirty(orig_pmd)) { pmdp_invalidate(vma, addr, pmd); orig_pmd = pmd_mkold(orig_pmd); orig_pmd = pmd_mkclean(orig_pmd); set_pmd_at(mm, addr, pmd, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); } folio_mark_lazyfree(folio); ret = true; out: spin_unlock(ptl); out_unlocked: return ret; } static inline void zap_deposited_table(struct mm_struct *mm, pmd_t *pmd) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, pmd); pte_free(mm, pgtable); mm_dec_nr_ptes(mm); } int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr) { pmd_t orig_pmd; spinlock_t *ptl; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; /* * For architectures like ppc64 we look at deposited pgtable * when calling pmdp_huge_get_and_clear. So do the * pgtable_trans_huge_withdraw after finishing pmdp related * operations. */ orig_pmd = pmdp_huge_get_and_clear_full(vma, addr, pmd, tlb->fullmm); arch_check_zapped_pmd(vma, orig_pmd); tlb_remove_pmd_tlb_entry(tlb, pmd, addr); if (vma_is_special_huge(vma)) { if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else if (is_huge_zero_pmd(orig_pmd)) { zap_deposited_table(tlb->mm, pmd); spin_unlock(ptl); } else { struct folio *folio = NULL; int flush_needed = 1; if (pmd_present(orig_pmd)) { struct page *page = pmd_page(orig_pmd); folio = page_folio(page); folio_remove_rmap_pmd(folio, page, vma); WARN_ON_ONCE(folio_mapcount(folio) < 0); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { swp_entry_t entry; VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); folio = pfn_swap_entry_folio(entry); flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!"); if (folio_test_anon(folio)) { zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); } else { if (arch_needs_pgtable_deposit()) zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, mm_counter_file(folio), -HPAGE_PMD_NR); } spin_unlock(ptl); if (flush_needed) tlb_remove_page_size(tlb, &folio->page, HPAGE_PMD_SIZE); } return 1; } #ifndef pmd_move_must_withdraw static inline int pmd_move_must_withdraw(spinlock_t *new_pmd_ptl, spinlock_t *old_pmd_ptl, struct vm_area_struct *vma) { /* * With split pmd lock we also need to move preallocated * PTE page table if new_pmd is on different PMD page table. * * We also don't deposit and withdraw tables for file pages. */ return (new_pmd_ptl != old_pmd_ptl) && vma_is_anonymous(vma); } #endif static pmd_t move_soft_dirty_pmd(pmd_t pmd) { #ifdef CONFIG_MEM_SOFT_DIRTY if (unlikely(is_pmd_migration_entry(pmd))) pmd = pmd_swp_mksoft_dirty(pmd); else if (pmd_present(pmd)) pmd = pmd_mksoft_dirty(pmd); #endif return pmd; } bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr, unsigned long new_addr, pmd_t *old_pmd, pmd_t *new_pmd) { spinlock_t *old_ptl, *new_ptl; pmd_t pmd; struct mm_struct *mm = vma->vm_mm; bool force_flush = false; /* * The destination pmd shouldn't be established, free_pgtables() * should have released it; but move_page_tables() might have already * inserted a page table, if racing against shmem/file collapse. */ if (!pmd_none(*new_pmd)) { VM_BUG_ON(pmd_trans_huge(*new_pmd)); return false; } /* * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_lock prevents deadlock. */ old_ptl = __pmd_trans_huge_lock(old_pmd, vma); if (old_ptl) { new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); if (pmd_present(pmd)) force_flush = true; VM_BUG_ON(!pmd_none(*new_pmd)); if (pmd_move_must_withdraw(new_ptl, old_ptl, vma)) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); pgtable_trans_huge_deposit(mm, new_pmd, pgtable); } pmd = move_soft_dirty_pmd(pmd); set_pmd_at(mm, new_addr, new_pmd, pmd); if (force_flush) flush_pmd_tlb_range(vma, old_addr, old_addr + PMD_SIZE); if (new_ptl != old_ptl) spin_unlock(new_ptl); spin_unlock(old_ptl); return true; } return false; } /* * Returns * - 0 if PMD could not be locked * - 1 if PMD was locked but protections unchanged and TLB flush unnecessary * or if prot_numa but THP migration is not supported * - HPAGE_PMD_NR if protections changed and TLB flush necessary */ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, pgprot_t newprot, unsigned long cp_flags) { struct mm_struct *mm = vma->vm_mm; spinlock_t *ptl; pmd_t oldpmd, entry; bool prot_numa = cp_flags & MM_CP_PROT_NUMA; bool uffd_wp = cp_flags & MM_CP_UFFD_WP; bool uffd_wp_resolve = cp_flags & MM_CP_UFFD_WP_RESOLVE; int ret = 1; tlb_change_page_size(tlb, HPAGE_PMD_SIZE); if (prot_numa && !thp_migration_supported()) return 1; ptl = __pmd_trans_huge_lock(pmd, vma); if (!ptl) return 0; #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION if (is_swap_pmd(*pmd)) { swp_entry_t entry = pmd_to_swp_entry(*pmd); struct folio *folio = pfn_swap_entry_folio(entry); pmd_t newpmd; VM_BUG_ON(!is_pmd_migration_entry(*pmd)); if (is_writable_migration_entry(entry)) { /* * A protection check is difficult so * just be safe and disable write */ if (folio_test_anon(folio)) entry = make_readable_exclusive_migration_entry(swp_offset(entry)); else entry = make_readable_migration_entry(swp_offset(entry)); newpmd = swp_entry_to_pmd(entry); if (pmd_swp_soft_dirty(*pmd)) newpmd = pmd_swp_mksoft_dirty(newpmd); } else { newpmd = *pmd; } if (uffd_wp) newpmd = pmd_swp_mkuffd_wp(newpmd); else if (uffd_wp_resolve) newpmd = pmd_swp_clear_uffd_wp(newpmd); if (!pmd_same(*pmd, newpmd)) set_pmd_at(mm, addr, pmd, newpmd); goto unlock; } #endif if (prot_numa) { struct folio *folio; bool toptier; /* * Avoid trapping faults against the zero page. The read-only * data is likely to be read-cached on the local CPU and * local/remote hits to the zero page are not interesting. */ if (is_huge_zero_pmd(*pmd)) goto unlock; if (pmd_protnone(*pmd)) goto unlock; folio = pmd_folio(*pmd); toptier = node_is_toptier(folio_nid(folio)); /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && toptier) goto unlock; if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING && !toptier) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); } /* * In case prot_numa, we are under mmap_read_lock(mm). It's critical * to not clear pmd intermittently to avoid race with MADV_DONTNEED * which is also under mmap_read_lock(mm): * * CPU0: CPU1: * change_huge_pmd(prot_numa=1) * pmdp_huge_get_and_clear_notify() * madvise_dontneed() * zap_pmd_range() * pmd_trans_huge(*pmd) == 0 (without ptl) * // skip the pmd * set_pmd_at(); * // pmd is re-established * * The race makes MADV_DONTNEED miss the huge pmd and don't clear it * which may break userspace. * * pmdp_invalidate_ad() is required to make sure we don't miss * dirty/young flags set by hardware. */ oldpmd = pmdp_invalidate_ad(vma, addr, pmd); entry = pmd_modify(oldpmd, newprot); if (uffd_wp) entry = pmd_mkuffd_wp(entry); else if (uffd_wp_resolve) /* * Leave the write bit to be handled by PF interrupt * handler, then things like COW could be properly * handled. */ entry = pmd_clear_uffd_wp(entry); /* See change_pte_range(). */ if ((cp_flags & MM_CP_TRY_CHANGE_WRITABLE) && !pmd_write(entry) && can_change_pmd_writable(vma, addr, entry)) entry = pmd_mkwrite(entry, vma); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); if (huge_pmd_needs_flush(oldpmd, entry)) tlb_flush_pmd_range(tlb, addr, HPAGE_PMD_SIZE); unlock: spin_unlock(ptl); return ret; } #ifdef CONFIG_USERFAULTFD /* * The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by * the caller, but it must return after releasing the page_table_lock. * Just move the page from src_pmd to dst_pmd if possible. * Return zero if succeeded in moving the page, -EAGAIN if it needs to be * repeated by the caller, or other errors in case of failure. */ int move_pages_huge_pmd(struct mm_struct *mm, pmd_t *dst_pmd, pmd_t *src_pmd, pmd_t dst_pmdval, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma, unsigned long dst_addr, unsigned long src_addr) { pmd_t _dst_pmd, src_pmdval; struct page *src_page; struct folio *src_folio; struct anon_vma *src_anon_vma; spinlock_t *src_ptl, *dst_ptl; pgtable_t src_pgtable; struct mmu_notifier_range range; int err = 0; src_pmdval = *src_pmd; src_ptl = pmd_lockptr(mm, src_pmd); lockdep_assert_held(src_ptl); vma_assert_locked(src_vma); vma_assert_locked(dst_vma); /* Sanity checks before the operation */ if (WARN_ON_ONCE(!pmd_none(dst_pmdval)) || WARN_ON_ONCE(src_addr & ~HPAGE_PMD_MASK) || WARN_ON_ONCE(dst_addr & ~HPAGE_PMD_MASK)) { spin_unlock(src_ptl); return -EINVAL; } if (!pmd_trans_huge(src_pmdval)) { spin_unlock(src_ptl); if (is_pmd_migration_entry(src_pmdval)) { pmd_migration_entry_wait(mm, &src_pmdval); return -EAGAIN; } return -ENOENT; } src_page = pmd_page(src_pmdval); if (!is_huge_zero_pmd(src_pmdval)) { if (unlikely(!PageAnonExclusive(src_page))) { spin_unlock(src_ptl); return -EBUSY; } src_folio = page_folio(src_page); folio_get(src_folio); } else src_folio = NULL; spin_unlock(src_ptl); flush_cache_range(src_vma, src_addr, src_addr + HPAGE_PMD_SIZE); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, src_addr, src_addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); if (src_folio) { folio_lock(src_folio); /* * split_huge_page walks the anon_vma chain without the page * lock. Serialize against it with the anon_vma lock, the page * lock is not enough. */ src_anon_vma = folio_get_anon_vma(src_folio); if (!src_anon_vma) { err = -EAGAIN; goto unlock_folio; } anon_vma_lock_write(src_anon_vma); } else src_anon_vma = NULL; dst_ptl = pmd_lockptr(mm, dst_pmd); double_pt_lock(src_ptl, dst_ptl); if (unlikely(!pmd_same(*src_pmd, src_pmdval) || !pmd_same(*dst_pmd, dst_pmdval))) { err = -EAGAIN; goto unlock_ptls; } if (src_folio) { if (folio_maybe_dma_pinned(src_folio) || !PageAnonExclusive(&src_folio->page)) { err = -EBUSY; goto unlock_ptls; } if (WARN_ON_ONCE(!folio_test_head(src_folio)) || WARN_ON_ONCE(!folio_test_anon(src_folio))) { err = -EBUSY; goto unlock_ptls; } src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); /* Folio got pinned from under us. Put it back and fail the move. */ if (folio_maybe_dma_pinned(src_folio)) { set_pmd_at(mm, src_addr, src_pmd, src_pmdval); err = -EBUSY; goto unlock_ptls; } folio_move_anon_rmap(src_folio, dst_vma); src_folio->index = linear_page_index(dst_vma, dst_addr); _dst_pmd = mk_huge_pmd(&src_folio->page, dst_vma->vm_page_prot); /* Follow mremap() behavior and treat the entry dirty after the move */ _dst_pmd = pmd_mkwrite(pmd_mkdirty(_dst_pmd), dst_vma); } else { src_pmdval = pmdp_huge_clear_flush(src_vma, src_addr, src_pmd); _dst_pmd = mk_huge_pmd(src_page, dst_vma->vm_page_prot); } set_pmd_at(mm, dst_addr, dst_pmd, _dst_pmd); src_pgtable = pgtable_trans_huge_withdraw(mm, src_pmd); pgtable_trans_huge_deposit(mm, dst_pmd, src_pgtable); unlock_ptls: double_pt_unlock(src_ptl, dst_ptl); if (src_anon_vma) { anon_vma_unlock_write(src_anon_vma); put_anon_vma(src_anon_vma); } unlock_folio: /* unblock rmap walks */ if (src_folio) folio_unlock(src_folio); mmu_notifier_invalidate_range_end(&range); if (src_folio) folio_put(src_folio); return err; } #endif /* CONFIG_USERFAULTFD */ /* * Returns page table lock pointer if a given pmd maps a thp, NULL otherwise. * * Note that if it returns page table lock pointer, this routine returns without * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { spinlock_t *ptl; ptl = pmd_lock(vma->vm_mm, pmd); if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) return ptl; spin_unlock(ptl); return NULL; } /* * Returns page table lock pointer if a given pud maps a thp, NULL otherwise. * * Note that if it returns page table lock pointer, this routine returns without * unlocking page table lock. So callers must unlock it. */ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma) { spinlock_t *ptl; ptl = pud_lock(vma->vm_mm, pud); if (likely(pud_trans_huge(*pud) || pud_devmap(*pud))) return ptl; spin_unlock(ptl); return NULL; } #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma, pud_t *pud, unsigned long addr) { spinlock_t *ptl; ptl = __pud_trans_huge_lock(pud, vma); if (!ptl) return 0; pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm); tlb_remove_pud_tlb_entry(tlb, pud, addr); if (vma_is_special_huge(vma)) { spin_unlock(ptl); /* No zero page support yet */ } else { /* No support for anonymous PUD pages yet */ BUG(); } return 1; } static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud, unsigned long haddr) { VM_BUG_ON(haddr & ~HPAGE_PUD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma); VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud)); count_vm_event(THP_SPLIT_PUD); pudp_huge_clear_flush(vma, haddr, pud); } void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud, unsigned long address) { spinlock_t *ptl; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address & HPAGE_PUD_MASK, (address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE); mmu_notifier_invalidate_range_start(&range); ptl = pud_lock(vma->vm_mm, pud); if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud))) goto out; __split_huge_pud_locked(vma, pud, range.start); out: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); } #endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */ static void __split_huge_zero_page_pmd(struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd) { struct mm_struct *mm = vma->vm_mm; pgtable_t pgtable; pmd_t _pmd, old_pmd; unsigned long addr; pte_t *pte; int i; /* * Leave pmd empty until pte is filled note that it is fine to delay * notification until mmu_notifier_invalidate_range_end() as we are * replacing a zero pmd write protected page with a zero pte write * protected page. * * See Documentation/mm/mmu_notifier.rst */ old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte); for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry; entry = pfn_pte(my_zero_pfn(addr), vma->vm_page_prot); entry = pte_mkspecial(entry); if (pmd_uffd_wp(old_pmd)) entry = pte_mkuffd_wp(entry); VM_BUG_ON(!pte_none(ptep_get(pte))); set_pte_at(mm, addr, pte, entry); pte++; } pte_unmap(pte - 1); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); } static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, unsigned long haddr, bool freeze) { struct mm_struct *mm = vma->vm_mm; struct folio *folio; struct page *page; pgtable_t pgtable; pmd_t old_pmd, _pmd; bool young, write, soft_dirty, pmd_migration = false, uffd_wp = false; bool anon_exclusive = false, dirty = false; unsigned long addr; pte_t *pte; int i; VM_BUG_ON(haddr & ~HPAGE_PMD_MASK); VM_BUG_ON_VMA(vma->vm_start > haddr, vma); VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma); VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)); count_vm_event(THP_SPLIT_PMD); if (!vma_is_anonymous(vma)) { old_pmd = pmdp_huge_clear_flush(vma, haddr, pmd); /* * We are going to unmap this huge page. So * just go ahead and zap it */ if (arch_needs_pgtable_deposit()) zap_deposited_table(mm, pmd); if (vma_is_special_huge(vma)) return; if (unlikely(is_pmd_migration_entry(old_pmd))) { swp_entry_t entry; entry = pmd_to_swp_entry(old_pmd); folio = pfn_swap_entry_folio(entry); } else { page = pmd_page(old_pmd); folio = page_folio(page); if (!folio_test_dirty(folio) && pmd_dirty(old_pmd)) folio_mark_dirty(folio); if (!folio_test_referenced(folio) && pmd_young(old_pmd)) folio_set_referenced(folio); folio_remove_rmap_pmd(folio, page, vma); folio_put(folio); } add_mm_counter(mm, mm_counter_file(folio), -HPAGE_PMD_NR); return; } if (is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_arch_invalidate_secondary_tlbs() see comments below * inside __split_huge_pmd() ? * * We are going from a zero huge page write protected to zero * small page also write protected so it does not seems useful * to invalidate secondary mmu at this time. */ return __split_huge_zero_page_pmd(vma, haddr, pmd); } pmd_migration = is_pmd_migration_entry(*pmd); if (unlikely(pmd_migration)) { swp_entry_t entry; old_pmd = *pmd; entry = pmd_to_swp_entry(old_pmd); page = pfn_swap_entry_to_page(entry); write = is_writable_migration_entry(entry); if (PageAnon(page)) anon_exclusive = is_readable_exclusive_migration_entry(entry); young = is_migration_entry_young(entry); dirty = is_migration_entry_dirty(entry); soft_dirty = pmd_swp_soft_dirty(old_pmd); uffd_wp = pmd_swp_uffd_wp(old_pmd); } else { /* * Up to this point the pmd is present and huge and userland has * the whole access to the hugepage during the split (which * happens in place). If we overwrite the pmd with the not-huge * version pointing to the pte here (which of course we could if * all CPUs were bug free), userland could trigger a small page * size TLB miss on the small sized TLB while the hugepage TLB * entry is still established in the huge TLB. Some CPU doesn't * like that. See * http://support.amd.com/TechDocs/41322_10h_Rev_Gd.pdf, Erratum * 383 on page 105. Intel should be safe but is also warns that * it's only safe if the permission and cache attributes of the * two entries loaded in the two TLB is identical (which should * be the case here). But it is generally safer to never allow * small and huge TLB entries for the same virtual address to be * loaded simultaneously. So instead of doing "pmd_populate(); * flush_pmd_tlb_range();" we first mark the current pmd * notpresent (atomically because here the pmd_trans_huge must * remain set at all times on the pmd until the split is * complete for this pmd), then we flush the SMP TLB and finally * we write the non-huge version of the pmd entry with * pmd_populate. */ old_pmd = pmdp_invalidate(vma, haddr, pmd); page = pmd_page(old_pmd); folio = page_folio(page); if (pmd_dirty(old_pmd)) { dirty = true; folio_set_dirty(folio); } write = pmd_write(old_pmd); young = pmd_young(old_pmd); soft_dirty = pmd_soft_dirty(old_pmd); uffd_wp = pmd_uffd_wp(old_pmd); VM_WARN_ON_FOLIO(!folio_ref_count(folio), folio); VM_WARN_ON_FOLIO(!folio_test_anon(folio), folio); /* * Without "freeze", we'll simply split the PMD, propagating the * PageAnonExclusive() flag for each PTE by setting it for * each subpage -- no need to (temporarily) clear. * * With "freeze" we want to replace mapped pages by * migration entries right away. This is only possible if we * managed to clear PageAnonExclusive() -- see * set_pmd_migration_entry(). * * In case we cannot clear PageAnonExclusive(), split the PMD * only and let try_to_migrate_one() fail later. * * See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ anon_exclusive = PageAnonExclusive(page); if (freeze && anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) freeze = false; if (!freeze) { rmap_t rmap_flags = RMAP_NONE; folio_ref_add(folio, HPAGE_PMD_NR - 1); if (anon_exclusive) rmap_flags |= RMAP_EXCLUSIVE; folio_add_anon_rmap_ptes(folio, page, HPAGE_PMD_NR, vma, haddr, rmap_flags); } } /* * Withdraw the table only after we mark the pmd entry invalid. * This's critical for some architectures (Power). */ pgtable = pgtable_trans_huge_withdraw(mm, pmd); pmd_populate(mm, &_pmd, pgtable); pte = pte_offset_map(&_pmd, haddr); VM_BUG_ON(!pte); /* * Note that NUMA hinting access restrictions are not transferred to * avoid any possibility of altering permissions across VMAs. */ if (freeze || pmd_migration) { for (i = 0, addr = haddr; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE) { pte_t entry; swp_entry_t swp_entry; if (write) swp_entry = make_writable_migration_entry( page_to_pfn(page + i)); else if (anon_exclusive) swp_entry = make_readable_exclusive_migration_entry( page_to_pfn(page + i)); else swp_entry = make_readable_migration_entry( page_to_pfn(page + i)); if (young) swp_entry = make_migration_entry_young(swp_entry); if (dirty) swp_entry = make_migration_entry_dirty(swp_entry); entry = swp_entry_to_pte(swp_entry); if (soft_dirty) entry = pte_swp_mksoft_dirty(entry); if (uffd_wp) entry = pte_swp_mkuffd_wp(entry); VM_WARN_ON(!pte_none(ptep_get(pte + i))); set_pte_at(mm, addr, pte + i, entry); } } else { pte_t entry; entry = mk_pte(page, READ_ONCE(vma->vm_page_prot)); if (write) entry = pte_mkwrite(entry, vma); if (!young) entry = pte_mkold(entry); /* NOTE: this may set soft-dirty too on some archs */ if (dirty) entry = pte_mkdirty(entry); if (soft_dirty) entry = pte_mksoft_dirty(entry); if (uffd_wp) entry = pte_mkuffd_wp(entry); for (i = 0; i < HPAGE_PMD_NR; i++) VM_WARN_ON(!pte_none(ptep_get(pte + i))); set_ptes(mm, haddr, pte, entry, HPAGE_PMD_NR); } pte_unmap(pte); if (!pmd_migration) folio_remove_rmap_pmd(folio, page, vma); if (freeze) put_page(page); smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); } void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, unsigned long address, bool freeze, struct folio *folio) { spinlock_t *ptl; struct mmu_notifier_range range; mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, vma->vm_mm, address & HPAGE_PMD_MASK, (address & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); ptl = pmd_lock(vma->vm_mm, pmd); /* * If caller asks to setup a migration entry, we need a folio to check * pmd against. Otherwise we can end up replacing wrong folio. */ VM_BUG_ON(freeze && !folio); VM_WARN_ON_ONCE(folio && !folio_test_locked(folio)); if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) || is_pmd_migration_entry(*pmd)) { /* * It's safe to call pmd_page when folio is set because it's * guaranteed that pmd is present. */ if (folio && folio != pmd_folio(*pmd)) goto out; __split_huge_pmd_locked(vma, pmd, range.start, freeze); } out: spin_unlock(ptl); mmu_notifier_invalidate_range_end(&range); } void split_huge_pmd_address(struct vm_area_struct *vma, unsigned long address, bool freeze, struct folio *folio) { pmd_t *pmd = mm_find_pmd(vma->vm_mm, address); if (!pmd) return; __split_huge_pmd(vma, pmd, address, freeze, folio); } static inline void split_huge_pmd_if_needed(struct vm_area_struct *vma, unsigned long address) { /* * If the new address isn't hpage aligned and it could previously * contain an hugepage: check if we need to split an huge pmd. */ if (!IS_ALIGNED(address, HPAGE_PMD_SIZE) && range_in_vma(vma, ALIGN_DOWN(address, HPAGE_PMD_SIZE), ALIGN(address, HPAGE_PMD_SIZE))) split_huge_pmd_address(vma, address, false, NULL); } void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start, unsigned long end, long adjust_next) { /* Check if we need to split start first. */ split_huge_pmd_if_needed(vma, start); /* Check if we need to split end next. */ split_huge_pmd_if_needed(vma, end); /* * If we're also updating the next vma vm_start, * check if we need to split it. */ if (adjust_next > 0) { struct vm_area_struct *next = find_vma(vma->vm_mm, vma->vm_end); unsigned long nstart = next->vm_start; nstart += adjust_next; split_huge_pmd_if_needed(next, nstart); } } static void unmap_folio(struct folio *folio) { enum ttu_flags ttu_flags = TTU_RMAP_LOCKED | TTU_SYNC | TTU_BATCH_FLUSH; VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (folio_test_pmd_mappable(folio)) ttu_flags |= TTU_SPLIT_HUGE_PMD; /* * Anon pages need migration entries to preserve them, but file * pages can simply be left unmapped, then faulted back on demand. * If that is ever changed (perhaps for mlock), update remap_page(). */ if (folio_test_anon(folio)) try_to_migrate(folio, ttu_flags); else try_to_unmap(folio, ttu_flags | TTU_IGNORE_MLOCK); try_to_unmap_flush(); } static void remap_page(struct folio *folio, unsigned long nr) { int i = 0; /* If unmap_folio() uses try_to_migrate() on file, remove this check */ if (!folio_test_anon(folio)) return; for (;;) { remove_migration_ptes(folio, folio, true); i += folio_nr_pages(folio); if (i >= nr) break; folio = folio_next(folio); } } static void lru_add_page_tail(struct page *head, struct page *tail, struct lruvec *lruvec, struct list_head *list) { VM_BUG_ON_PAGE(!PageHead(head), head); VM_BUG_ON_PAGE(PageLRU(tail), head); lockdep_assert_held(&lruvec->lru_lock); if (list) { /* page reclaim is reclaiming a huge page */ VM_WARN_ON(PageLRU(head)); get_page(tail); list_add_tail(&tail->lru, list); } else { /* head is still on lru (and we have it frozen) */ VM_WARN_ON(!PageLRU(head)); if (PageUnevictable(tail)) tail->mlock_count = 0; else list_add_tail(&tail->lru, &head->lru); SetPageLRU(tail); } } static void __split_huge_page_tail(struct folio *folio, int tail, struct lruvec *lruvec, struct list_head *list, unsigned int new_order) { struct page *head = &folio->page; struct page *page_tail = head + tail; /* * Careful: new_folio is not a "real" folio before we cleared PageTail. * Don't pass it around before clear_compound_head(). */ struct folio *new_folio = (struct folio *)page_tail; VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail); /* * Clone page flags before unfreezing refcount. * * After successful get_page_unless_zero() might follow flags change, * for example lock_page() which set PG_waiters. * * Note that for mapped sub-pages of an anonymous THP, * PG_anon_exclusive has been cleared in unmap_folio() and is stored in * the migration entry instead from where remap_page() will restore it. * We can still have PG_anon_exclusive set on effectively unmapped and * unreferenced sub-pages of an anonymous THP: we can simply drop * PG_anon_exclusive (-> PG_mappedtodisk) for these here. */ page_tail->flags &= ~PAGE_FLAGS_CHECK_AT_PREP; page_tail->flags |= (head->flags & ((1L << PG_referenced) | (1L << PG_swapbacked) | (1L << PG_swapcache) | (1L << PG_mlocked) | (1L << PG_uptodate) | (1L << PG_active) | (1L << PG_workingset) | (1L << PG_locked) | (1L << PG_unevictable) | #ifdef CONFIG_ARCH_USES_PG_ARCH_X (1L << PG_arch_2) | (1L << PG_arch_3) | #endif (1L << PG_dirty) | LRU_GEN_MASK | LRU_REFS_MASK)); /* ->mapping in first and second tail page is replaced by other uses */ VM_BUG_ON_PAGE(tail > 2 && page_tail->mapping != TAIL_MAPPING, page_tail); page_tail->mapping = head->mapping; page_tail->index = head->index + tail; /* * page->private should not be set in tail pages. Fix up and warn once * if private is unexpectedly set. */ if (unlikely(page_tail->private)) { VM_WARN_ON_ONCE_PAGE(true, page_tail); page_tail->private = 0; } if (folio_test_swapcache(folio)) new_folio->swap.val = folio->swap.val + tail; /* Page flags must be visible before we make the page non-compound. */ smp_wmb(); /* * Clear PageTail before unfreezing page refcount. * * After successful get_page_unless_zero() might follow put_page() * which needs correct compound_head(). */ clear_compound_head(page_tail); if (new_order) { prep_compound_page(page_tail, new_order); folio_set_large_rmappable(new_folio); } /* Finally unfreeze refcount. Additional reference from page cache. */ page_ref_unfreeze(page_tail, 1 + ((!folio_test_anon(folio) || folio_test_swapcache(folio)) ? folio_nr_pages(new_folio) : 0)); if (folio_test_young(folio)) folio_set_young(new_folio); if (folio_test_idle(folio)) folio_set_idle(new_folio); folio_xchg_last_cpupid(new_folio, folio_last_cpupid(folio)); /* * always add to the tail because some iterators expect new * pages to show after the currently processed elements - e.g. * migrate_pages */ lru_add_page_tail(head, page_tail, lruvec, list); } static void __split_huge_page(struct page *page, struct list_head *list, pgoff_t end, unsigned int new_order) { struct folio *folio = page_folio(page); struct page *head = &folio->page; struct lruvec *lruvec; struct address_space *swap_cache = NULL; unsigned long offset = 0; int i, nr_dropped = 0; unsigned int new_nr = 1 << new_order; int order = folio_order(folio); unsigned int nr = 1 << order; /* complete memcg works before add pages to LRU */ split_page_memcg(head, order, new_order); if (folio_test_anon(folio) && folio_test_swapcache(folio)) { offset = swp_offset(folio->swap); swap_cache = swap_address_space(folio->swap); xa_lock(&swap_cache->i_pages); } /* lock lru list/PageCompound, ref frozen by page_ref_freeze */ lruvec = folio_lruvec_lock(folio); ClearPageHasHWPoisoned(head); for (i = nr - new_nr; i >= new_nr; i -= new_nr) { __split_huge_page_tail(folio, i, lruvec, list, new_order); /* Some pages can be beyond EOF: drop them from page cache */ if (head[i].index >= end) { struct folio *tail = page_folio(head + i); if (shmem_mapping(folio->mapping)) nr_dropped++; else if (folio_test_clear_dirty(tail)) folio_account_cleaned(tail, inode_to_wb(folio->mapping->host)); __filemap_remove_folio(tail, NULL); folio_put(tail); } else if (!PageAnon(page)) { __xa_store(&folio->mapping->i_pages, head[i].index, head + i, 0); } else if (swap_cache) { __xa_store(&swap_cache->i_pages, offset + i, head + i, 0); } } if (!new_order) ClearPageCompound(head); else { struct folio *new_folio = (struct folio *)head; folio_set_order(new_folio, new_order); } unlock_page_lruvec(lruvec); /* Caller disabled irqs, so they are still disabled here */ split_page_owner(head, order, new_order); pgalloc_tag_split(head, 1 << order); /* See comment in __split_huge_page_tail() */ if (folio_test_anon(folio)) { /* Additional pin to swap cache */ if (folio_test_swapcache(folio)) { folio_ref_add(folio, 1 + new_nr); xa_unlock(&swap_cache->i_pages); } else { folio_ref_inc(folio); } } else { /* Additional pin to page cache */ folio_ref_add(folio, 1 + new_nr); xa_unlock(&folio->mapping->i_pages); } local_irq_enable(); if (nr_dropped) shmem_uncharge(folio->mapping->host, nr_dropped); remap_page(folio, nr); /* * set page to its compound_head when split to non order-0 pages, so * we can skip unlocking it below, since PG_locked is transferred to * the compound_head of the page and the caller will unlock it. */ if (new_order) page = compound_head(page); for (i = 0; i < nr; i += new_nr) { struct page *subpage = head + i; struct folio *new_folio = page_folio(subpage); if (subpage == page) continue; folio_unlock(new_folio); /* * Subpages may be freed if there wasn't any mapping * like if add_to_swap() is running on a lru page that * had its mapping zapped. And freeing these pages * requires taking the lru_lock so we do the put_page * of the tail pages after the split is complete. */ free_page_and_swap_cache(subpage); } } /* Racy check whether the huge page can be split */ bool can_split_folio(struct folio *folio, int *pextra_pins) { int extra_pins; /* Additional pins from page cache */ if (folio_test_anon(folio)) extra_pins = folio_test_swapcache(folio) ? folio_nr_pages(folio) : 0; else extra_pins = folio_nr_pages(folio); if (pextra_pins) *pextra_pins = extra_pins; return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - 1; } /* * This function splits a large folio into smaller folios of order @new_order. * @page can point to any page of the large folio to split. The split operation * does not change the position of @page. * * Prerequisites: * * 1) The caller must hold a reference on the @page's owning folio, also known * as the large folio. * * 2) The large folio must be locked. * * 3) The folio must not be pinned. Any unexpected folio references, including * GUP pins, will result in the folio not getting split; instead, the caller * will receive an -EAGAIN. * * 4) @new_order > 1, usually. Splitting to order-1 anonymous folios is not * supported for non-file-backed folios, because folio->_deferred_list, which * is used by partially mapped folios, is stored in subpage 2, but an order-1 * folio only has subpages 0 and 1. File-backed order-1 folios are supported, * since they do not use _deferred_list. * * After splitting, the caller's folio reference will be transferred to @page, * resulting in a raised refcount of @page after this call. The other pages may * be freed if they are not mapped. * * If @list is null, tail pages will be added to LRU list, otherwise, to @list. * * Pages in @new_order will inherit the mapping, flags, and so on from the * huge page. * * Returns 0 if the huge page was split successfully. * * Returns -EAGAIN if the folio has unexpected reference (e.g., GUP) or if * the folio was concurrently removed from the page cache. * * Returns -EBUSY when trying to split the huge zeropage, if the folio is * under writeback, if fs-specific folio metadata cannot currently be * released, or if some unexpected race happened (e.g., anon VMA disappeared, * truncation). * * Returns -EINVAL when trying to split to an order that is incompatible * with the folio. Splitting to order 0 is compatible with all folios. */ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list, unsigned int new_order) { struct folio *folio = page_folio(page); struct deferred_split *ds_queue = get_deferred_split_queue(folio); /* reset xarray order to new order after split */ XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order); struct anon_vma *anon_vma = NULL; struct address_space *mapping = NULL; bool is_thp = folio_test_pmd_mappable(folio); int extra_pins, ret; pgoff_t end; bool is_hzp; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(!folio_test_large(folio), folio); if (new_order >= folio_order(folio)) return -EINVAL; if (folio_test_anon(folio)) { /* order-1 is not supported for anonymous THP. */ if (new_order == 1) { VM_WARN_ONCE(1, "Cannot split to order-1 folio"); return -EINVAL; } } else if (new_order) { /* Split shmem folio to non-zero order not supported */ if (shmem_mapping(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split shmem folio to non-0 order"); return -EINVAL; } /* * No split if the file system does not support large folio. * Note that we might still have THPs in such mappings due to * CONFIG_READ_ONLY_THP_FOR_FS. But in that case, the mapping * does not actually support large folios properly. */ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !mapping_large_folio_support(folio->mapping)) { VM_WARN_ONCE(1, "Cannot split file folio to non-0 order"); return -EINVAL; } } /* Only swapping a whole PMD-mapped folio is supported */ if (folio_test_swapcache(folio) && new_order) return -EINVAL; is_hzp = is_huge_zero_folio(folio); if (is_hzp) { pr_warn_ratelimited("Called split_huge_page for huge zero page\n"); return -EBUSY; } if (folio_test_writeback(folio)) return -EBUSY; if (folio_test_anon(folio)) { /* * The caller does not necessarily hold an mmap_lock that would * prevent the anon_vma disappearing so we first we take a * reference to it and then lock the anon_vma for write. This * is similar to folio_lock_anon_vma_read except the write lock * is taken to serialise against parallel split or collapse * operations. */ anon_vma = folio_get_anon_vma(folio); if (!anon_vma) { ret = -EBUSY; goto out; } end = -1; mapping = NULL; anon_vma_lock_write(anon_vma); } else { gfp_t gfp; mapping = folio->mapping; /* Truncated ? */ if (!mapping) { ret = -EBUSY; goto out; } gfp = current_gfp_context(mapping_gfp_mask(mapping) & GFP_RECLAIM_MASK); if (!filemap_release_folio(folio, gfp)) { ret = -EBUSY; goto out; } xas_split_alloc(&xas, folio, folio_order(folio), gfp); if (xas_error(&xas)) { ret = xas_error(&xas); goto out; } anon_vma = NULL; i_mmap_lock_read(mapping); /* *__split_huge_page() may need to trim off pages beyond EOF: * but on 32-bit, i_size_read() takes an irq-unsafe seqlock, * which cannot be nested inside the page tree lock. So note * end now: i_size itself may be changed at any moment, but * folio lock is good enough to serialize the trimming. */ end = DIV_ROUND_UP(i_size_read(mapping->host), PAGE_SIZE); if (shmem_mapping(mapping)) end = shmem_fallocend(mapping->host, end); } /* * Racy check if we can split the page, before unmap_folio() will * split PMDs */ if (!can_split_folio(folio, &extra_pins)) { ret = -EAGAIN; goto out_unlock; } unmap_folio(folio); /* block interrupt reentry in xa_lock and spinlock */ local_irq_disable(); if (mapping) { /* * Check if the folio is present in page cache. * We assume all tail are present too, if folio is there. */ xas_lock(&xas); xas_reset(&xas); if (xas_load(&xas) != folio) goto fail; } /* Prevent deferred_split_scan() touching ->_refcount */ spin_lock(&ds_queue->split_queue_lock); if (folio_ref_freeze(folio, 1 + extra_pins)) { if (folio_order(folio) > 1 && !list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; /* * Reinitialize page_deferred_list after removing the * page from the split_queue, otherwise a subsequent * split will see list corruption when checking the * page_deferred_list. */ list_del_init(&folio->_deferred_list); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { int nr = folio_nr_pages(folio); xas_split(&xas, folio, folio_order(folio)); if (folio_test_pmd_mappable(folio) && new_order < HPAGE_PMD_ORDER) { if (folio_test_swapbacked(folio)) { __lruvec_stat_mod_folio(folio, NR_SHMEM_THPS, -nr); } else { __lruvec_stat_mod_folio(folio, NR_FILE_THPS, -nr); filemap_nr_thps_dec(mapping); } } } __split_huge_page(page, list, end, new_order); ret = 0; } else { spin_unlock(&ds_queue->split_queue_lock); fail: if (mapping) xas_unlock(&xas); local_irq_enable(); remap_page(folio, folio_nr_pages(folio)); ret = -EAGAIN; } out_unlock: if (anon_vma) { anon_vma_unlock_write(anon_vma); put_anon_vma(anon_vma); } if (mapping) i_mmap_unlock_read(mapping); out: xas_destroy(&xas); if (is_thp) count_vm_event(!ret ? THP_SPLIT_PAGE : THP_SPLIT_PAGE_FAILED); return ret; } void folio_undo_large_rmappable(struct folio *folio) { struct deferred_split *ds_queue; unsigned long flags; if (folio_order(folio) <= 1) return; /* * At this point, there is no one trying to add the folio to * deferred_list. If folio is not in deferred_list, it's safe * to check without acquiring the split_queue_lock. */ if (data_race(list_empty(&folio->_deferred_list))) return; ds_queue = get_deferred_split_queue(folio); spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(&folio->_deferred_list)) { ds_queue->split_queue_len--; list_del_init(&folio->_deferred_list); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } void deferred_split_folio(struct folio *folio) { struct deferred_split *ds_queue = get_deferred_split_queue(folio); #ifdef CONFIG_MEMCG struct mem_cgroup *memcg = folio_memcg(folio); #endif unsigned long flags; /* * Order 1 folios have no space for a deferred list, but we also * won't waste much memory by not adding them to the deferred list. */ if (folio_order(folio) <= 1) return; /* * The try_to_unmap() in page reclaim path might reach here too, * this may cause a race condition to corrupt deferred split queue. * And, if page reclaim is already handling the same folio, it is * unnecessary to handle it again in shrinker. * * Check the swapcache flag to determine if the folio is being * handled by page reclaim since THP swap would add the folio into * swap cache before calling try_to_unmap(). */ if (folio_test_swapcache(folio)) return; if (!list_empty(&folio->_deferred_list)) return; spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (list_empty(&folio->_deferred_list)) { if (folio_test_pmd_mappable(folio)) count_vm_event(THP_DEFERRED_SPLIT_PAGE); list_add_tail(&folio->_deferred_list, &ds_queue->split_queue); ds_queue->split_queue_len++; #ifdef CONFIG_MEMCG if (memcg) set_shrinker_bit(memcg, folio_nid(folio), deferred_split_shrinker->id); #endif } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; #ifdef CONFIG_MEMCG if (sc->memcg) ds_queue = &sc->memcg->deferred_split_queue; #endif return READ_ONCE(ds_queue->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { struct pglist_data *pgdata = NODE_DATA(sc->nid); struct deferred_split *ds_queue = &pgdata->deferred_split_queue; unsigned long flags; LIST_HEAD(list); struct folio *folio, *next; int split = 0; #ifdef CONFIG_MEMCG if (sc->memcg) ds_queue = &sc->memcg->deferred_split_queue; #endif spin_lock_irqsave(&ds_queue->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ list_for_each_entry_safe(folio, next, &ds_queue->split_queue, _deferred_list) { if (folio_try_get(folio)) { list_move(&folio->_deferred_list, &list); } else { /* We lost race with folio_put() */ list_del_init(&folio->_deferred_list); ds_queue->split_queue_len--; } if (!--sc->nr_to_scan) break; } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); list_for_each_entry_safe(folio, next, &list, _deferred_list) { if (!folio_trylock(folio)) goto next; /* split_huge_page() removes page from list on success */ if (!split_folio(folio)) split++; folio_unlock(folio); next: folio_put(folio); } spin_lock_irqsave(&ds_queue->split_queue_lock, flags); list_splice_tail(&list, &ds_queue->split_queue); spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); /* * Stop shrinker if we didn't split any page, but the queue is empty. * This can happen if pages were freed under us. */ if (!split && list_empty(&ds_queue->split_queue)) return SHRINK_STOP; return split; } #ifdef CONFIG_DEBUG_FS static void split_huge_pages_all(void) { struct zone *zone; struct page *page; struct folio *folio; unsigned long pfn, max_zone_pfn; unsigned long total = 0, split = 0; pr_debug("Split all THPs\n"); for_each_zone(zone) { if (!managed_zone(zone)) continue; max_zone_pfn = zone_end_pfn(zone); for (pfn = zone->zone_start_pfn; pfn < max_zone_pfn; pfn++) { int nr_pages; page = pfn_to_online_page(pfn); if (!page || PageTail(page)) continue; folio = page_folio(page); if (!folio_try_get(folio)) continue; if (unlikely(page_folio(page) != folio)) goto next; if (zone != folio_zone(folio)) goto next; if (!folio_test_large(folio) || folio_test_hugetlb(folio) || !folio_test_lru(folio)) goto next; total++; folio_lock(folio); nr_pages = folio_nr_pages(folio); if (!split_folio(folio)) split++; pfn += nr_pages - 1; folio_unlock(folio); next: folio_put(folio); cond_resched(); } } pr_debug("%lu of %lu THP split\n", split, total); } static inline bool vma_not_suitable_for_thp_split(struct vm_area_struct *vma) { return vma_is_special_huge(vma) || (vma->vm_flags & VM_IO) || is_vm_hugetlb_page(vma); } static int split_huge_pages_pid(int pid, unsigned long vaddr_start, unsigned long vaddr_end, unsigned int new_order) { int ret = 0; struct task_struct *task; struct mm_struct *mm; unsigned long total = 0, split = 0; unsigned long addr; vaddr_start &= PAGE_MASK; vaddr_end &= PAGE_MASK; /* Find the task_struct from pid */ rcu_read_lock(); task = find_task_by_vpid(pid); if (!task) { rcu_read_unlock(); ret = -ESRCH; goto out; } get_task_struct(task); rcu_read_unlock(); /* Find the mm_struct */ mm = get_task_mm(task); put_task_struct(task); if (!mm) { ret = -EINVAL; goto out; } pr_debug("Split huge pages in pid: %d, vaddr: [0x%lx - 0x%lx]\n", pid, vaddr_start, vaddr_end); mmap_read_lock(mm); /* * always increase addr by PAGE_SIZE, since we could have a PTE page * table filled with PTE-mapped THPs, each of which is distinct. */ for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) { struct vm_area_struct *vma = vma_lookup(mm, addr); struct page *page; struct folio *folio; if (!vma) break; /* skip special VMA and hugetlb VMA */ if (vma_not_suitable_for_thp_split(vma)) { addr = vma->vm_end; continue; } /* FOLL_DUMP to ignore special (like zero) pages */ page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP); if (IS_ERR_OR_NULL(page)) continue; folio = page_folio(page); if (!is_transparent_hugepage(folio)) goto next; if (new_order >= folio_order(folio)) goto next; total++; /* * For folios with private, split_huge_page_to_list_to_order() * will try to drop it before split and then check if the folio * can be split or not. So skip the check here. */ if (!folio_test_private(folio) && !can_split_folio(folio, NULL)) goto next; if (!folio_trylock(folio)) goto next; if (!split_folio_to_order(folio, new_order)) split++; folio_unlock(folio); next: folio_put(folio); cond_resched(); } mmap_read_unlock(mm); mmput(mm); pr_debug("%lu of %lu THP split\n", split, total); out: return ret; } static int split_huge_pages_in_file(const char *file_path, pgoff_t off_start, pgoff_t off_end, unsigned int new_order) { struct filename *file; struct file *candidate; struct address_space *mapping; int ret = -EINVAL; pgoff_t index; int nr_pages = 1; unsigned long total = 0, split = 0; file = getname_kernel(file_path); if (IS_ERR(file)) return ret; candidate = file_open_name(file, O_RDONLY, 0); if (IS_ERR(candidate)) goto out; pr_debug("split file-backed THPs in file: %s, page offset: [0x%lx - 0x%lx]\n", file_path, off_start, off_end); mapping = candidate->f_mapping; for (index = off_start; index < off_end; index += nr_pages) { struct folio *folio = filemap_get_folio(mapping, index); nr_pages = 1; if (IS_ERR(folio)) continue; if (!folio_test_large(folio)) goto next; total++; nr_pages = folio_nr_pages(folio); if (new_order >= folio_order(folio)) goto next; if (!folio_trylock(folio)) goto next; if (!split_folio_to_order(folio, new_order)) split++; folio_unlock(folio); next: folio_put(folio); cond_resched(); } filp_close(candidate, NULL); ret = 0; pr_debug("%lu of %lu file-backed THP split\n", split, total); out: putname(file); return ret; } #define MAX_INPUT_BUF_SZ 255 static ssize_t split_huge_pages_write(struct file *file, const char __user *buf, size_t count, loff_t *ppops) { static DEFINE_MUTEX(split_debug_mutex); ssize_t ret; /* * hold pid, start_vaddr, end_vaddr, new_order or * file_path, off_start, off_end, new_order */ char input_buf[MAX_INPUT_BUF_SZ]; int pid; unsigned long vaddr_start, vaddr_end; unsigned int new_order = 0; ret = mutex_lock_interruptible(&split_debug_mutex); if (ret) return ret; ret = -EFAULT; memset(input_buf, 0, MAX_INPUT_BUF_SZ); if (copy_from_user(input_buf, buf, min_t(size_t, count, MAX_INPUT_BUF_SZ))) goto out; input_buf[MAX_INPUT_BUF_SZ - 1] = '\0'; if (input_buf[0] == '/') { char *tok; char *buf = input_buf; char file_path[MAX_INPUT_BUF_SZ]; pgoff_t off_start = 0, off_end = 0; size_t input_len = strlen(input_buf); tok = strsep(&buf, ","); if (tok) { strcpy(file_path, tok); } else { ret = -EINVAL; goto out; } ret = sscanf(buf, "0x%lx,0x%lx,%d", &off_start, &off_end, &new_order); if (ret != 2 && ret != 3) { ret = -EINVAL; goto out; } ret = split_huge_pages_in_file(file_path, off_start, off_end, new_order); if (!ret) ret = input_len; goto out; } ret = sscanf(input_buf, "%d,0x%lx,0x%lx,%d", &pid, &vaddr_start, &vaddr_end, &new_order); if (ret == 1 && pid == 1) { split_huge_pages_all(); ret = strlen(input_buf); goto out; } else if (ret != 3 && ret != 4) { ret = -EINVAL; goto out; } ret = split_huge_pages_pid(pid, vaddr_start, vaddr_end, new_order); if (!ret) ret = strlen(input_buf); out: mutex_unlock(&split_debug_mutex); return ret; } static const struct file_operations split_huge_pages_fops = { .owner = THIS_MODULE, .write = split_huge_pages_write, .llseek = no_llseek, }; static int __init split_huge_pages_debugfs(void) { debugfs_create_file("split_huge_pages", 0200, NULL, NULL, &split_huge_pages_fops); return 0; } late_initcall(split_huge_pages_debugfs); #endif #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION int set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw, struct page *page) { struct folio *folio = page_folio(page); struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; bool anon_exclusive; pmd_t pmdval; swp_entry_t entry; pmd_t pmdswp; if (!(pvmw->pmd && !pvmw->pte)) return 0; flush_cache_range(vma, address, address + HPAGE_PMD_SIZE); pmdval = pmdp_invalidate(vma, address, pvmw->pmd); /* See folio_try_share_anon_rmap_pmd(): invalidate PMD first. */ anon_exclusive = folio_test_anon(folio) && PageAnonExclusive(page); if (anon_exclusive && folio_try_share_anon_rmap_pmd(folio, page)) { set_pmd_at(mm, address, pvmw->pmd, pmdval); return -EBUSY; } if (pmd_dirty(pmdval)) folio_mark_dirty(folio); if (pmd_write(pmdval)) entry = make_writable_migration_entry(page_to_pfn(page)); else if (anon_exclusive) entry = make_readable_exclusive_migration_entry(page_to_pfn(page)); else entry = make_readable_migration_entry(page_to_pfn(page)); if (pmd_young(pmdval)) entry = make_migration_entry_young(entry); if (pmd_dirty(pmdval)) entry = make_migration_entry_dirty(entry); pmdswp = swp_entry_to_pmd(entry); if (pmd_soft_dirty(pmdval)) pmdswp = pmd_swp_mksoft_dirty(pmdswp); if (pmd_uffd_wp(pmdval)) pmdswp = pmd_swp_mkuffd_wp(pmdswp); set_pmd_at(mm, address, pvmw->pmd, pmdswp); folio_remove_rmap_pmd(folio, page, vma); folio_put(folio); trace_set_migration_pmd(address, pmd_val(pmdswp)); return 0; } void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) { struct folio *folio = page_folio(new); struct vm_area_struct *vma = pvmw->vma; struct mm_struct *mm = vma->vm_mm; unsigned long address = pvmw->address; unsigned long haddr = address & HPAGE_PMD_MASK; pmd_t pmde; swp_entry_t entry; if (!(pvmw->pmd && !pvmw->pte)) return; entry = pmd_to_swp_entry(*pvmw->pmd); folio_get(folio); pmde = mk_huge_pmd(new, READ_ONCE(vma->vm_page_prot)); if (pmd_swp_soft_dirty(*pvmw->pmd)) pmde = pmd_mksoft_dirty(pmde); if (is_writable_migration_entry(entry)) pmde = pmd_mkwrite(pmde, vma); if (pmd_swp_uffd_wp(*pvmw->pmd)) pmde = pmd_mkuffd_wp(pmde); if (!is_migration_entry_young(entry)) pmde = pmd_mkold(pmde); /* NOTE: this may contain setting soft-dirty on some archs */ if (folio_test_dirty(folio) && is_migration_entry_dirty(entry)) pmde = pmd_mkdirty(pmde); if (folio_test_anon(folio)) { rmap_t rmap_flags = RMAP_NONE; if (!is_readable_migration_entry(entry)) rmap_flags |= RMAP_EXCLUSIVE; folio_add_anon_rmap_pmd(folio, new, vma, haddr, rmap_flags); } else { folio_add_file_rmap_pmd(folio, new, vma); } VM_BUG_ON(pmd_write(pmde) && folio_test_anon(folio) && !PageAnonExclusive(new)); set_pmd_at(mm, haddr, pvmw->pmd, pmde); /* No need to invalidate - it was non-present before */ update_mmu_cache_pmd(vma, address, pvmw->pmd); trace_remove_migration_pmd(address, pmd_val(pmde)); } #endif |
| 402 190 4 301 181 313 337 83 285 295 62 384 205 23 405 404 405 51 4 154 403 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/atomic.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2002 Deep Blue Solutions Ltd. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_ATOMIC_LSE_H #define __ASM_ATOMIC_LSE_H #define ATOMIC_OP(op, asm_op) \ static __always_inline void \ __lse_atomic_##op(int i, atomic_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ " " #asm_op " %w[i], %[v]\n" \ : [v] "+Q" (v->counter) \ : [i] "r" (i)); \ } ATOMIC_OP(andnot, stclr) ATOMIC_OP(or, stset) ATOMIC_OP(xor, steor) ATOMIC_OP(add, stadd) static __always_inline void __lse_atomic_sub(int i, atomic_t *v) { __lse_atomic_add(-i, v); } #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, mb, op, asm_op, cl...) \ static __always_inline int \ __lse_atomic_fetch_##op##name(int i, atomic_t *v) \ { \ int old; \ \ asm volatile( \ __LSE_PREAMBLE \ " " #asm_op #mb " %w[i], %w[old], %[v]" \ : [v] "+Q" (v->counter), \ [old] "=r" (old) \ : [i] "r" (i) \ : cl); \ \ return old; \ } #define ATOMIC_FETCH_OPS(op, asm_op) \ ATOMIC_FETCH_OP(_relaxed, , op, asm_op) \ ATOMIC_FETCH_OP(_acquire, a, op, asm_op, "memory") \ ATOMIC_FETCH_OP(_release, l, op, asm_op, "memory") \ ATOMIC_FETCH_OP( , al, op, asm_op, "memory") ATOMIC_FETCH_OPS(andnot, ldclr) ATOMIC_FETCH_OPS(or, ldset) ATOMIC_FETCH_OPS(xor, ldeor) ATOMIC_FETCH_OPS(add, ldadd) #undef ATOMIC_FETCH_OP #undef ATOMIC_FETCH_OPS #define ATOMIC_FETCH_OP_SUB(name) \ static __always_inline int \ __lse_atomic_fetch_sub##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_add##name(-i, v); \ } ATOMIC_FETCH_OP_SUB(_relaxed) ATOMIC_FETCH_OP_SUB(_acquire) ATOMIC_FETCH_OP_SUB(_release) ATOMIC_FETCH_OP_SUB( ) #undef ATOMIC_FETCH_OP_SUB #define ATOMIC_OP_ADD_SUB_RETURN(name) \ static __always_inline int \ __lse_atomic_add_return##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_add##name(i, v) + i; \ } \ \ static __always_inline int \ __lse_atomic_sub_return##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_sub(i, v) - i; \ } ATOMIC_OP_ADD_SUB_RETURN(_relaxed) ATOMIC_OP_ADD_SUB_RETURN(_acquire) ATOMIC_OP_ADD_SUB_RETURN(_release) ATOMIC_OP_ADD_SUB_RETURN( ) #undef ATOMIC_OP_ADD_SUB_RETURN static __always_inline void __lse_atomic_and(int i, atomic_t *v) { return __lse_atomic_andnot(~i, v); } #define ATOMIC_FETCH_OP_AND(name, mb, cl...) \ static __always_inline int \ __lse_atomic_fetch_and##name(int i, atomic_t *v) \ { \ return __lse_atomic_fetch_andnot##name(~i, v); \ } ATOMIC_FETCH_OP_AND(_relaxed, ) ATOMIC_FETCH_OP_AND(_acquire, a, "memory") ATOMIC_FETCH_OP_AND(_release, l, "memory") ATOMIC_FETCH_OP_AND( , al, "memory") #undef ATOMIC_FETCH_OP_AND #define ATOMIC64_OP(op, asm_op) \ static __always_inline void \ __lse_atomic64_##op(s64 i, atomic64_t *v) \ { \ asm volatile( \ __LSE_PREAMBLE \ " " #asm_op " %[i], %[v]\n" \ : [v] "+Q" (v->counter) \ : [i] "r" (i)); \ } ATOMIC64_OP(andnot, stclr) ATOMIC64_OP(or, stset) ATOMIC64_OP(xor, steor) ATOMIC64_OP(add, stadd) static __always_inline void __lse_atomic64_sub(s64 i, atomic64_t *v) { __lse_atomic64_add(-i, v); } #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, mb, op, asm_op, cl...) \ static __always_inline long \ __lse_atomic64_fetch_##op##name(s64 i, atomic64_t *v) \ { \ s64 old; \ \ asm volatile( \ __LSE_PREAMBLE \ " " #asm_op #mb " %[i], %[old], %[v]" \ : [v] "+Q" (v->counter), \ [old] "=r" (old) \ : [i] "r" (i) \ : cl); \ \ return old; \ } #define ATOMIC64_FETCH_OPS(op, asm_op) \ ATOMIC64_FETCH_OP(_relaxed, , op, asm_op) \ ATOMIC64_FETCH_OP(_acquire, a, op, asm_op, "memory") \ ATOMIC64_FETCH_OP(_release, l, op, asm_op, "memory") \ ATOMIC64_FETCH_OP( , al, op, asm_op, "memory") ATOMIC64_FETCH_OPS(andnot, ldclr) ATOMIC64_FETCH_OPS(or, ldset) ATOMIC64_FETCH_OPS(xor, ldeor) ATOMIC64_FETCH_OPS(add, ldadd) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS #define ATOMIC64_FETCH_OP_SUB(name) \ static __always_inline long \ __lse_atomic64_fetch_sub##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_add##name(-i, v); \ } ATOMIC64_FETCH_OP_SUB(_relaxed) ATOMIC64_FETCH_OP_SUB(_acquire) ATOMIC64_FETCH_OP_SUB(_release) ATOMIC64_FETCH_OP_SUB( ) #undef ATOMIC64_FETCH_OP_SUB #define ATOMIC64_OP_ADD_SUB_RETURN(name) \ static __always_inline long \ __lse_atomic64_add_return##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_add##name(i, v) + i; \ } \ \ static __always_inline long \ __lse_atomic64_sub_return##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_sub##name(i, v) - i; \ } ATOMIC64_OP_ADD_SUB_RETURN(_relaxed) ATOMIC64_OP_ADD_SUB_RETURN(_acquire) ATOMIC64_OP_ADD_SUB_RETURN(_release) ATOMIC64_OP_ADD_SUB_RETURN( ) #undef ATOMIC64_OP_ADD_SUB_RETURN static __always_inline void __lse_atomic64_and(s64 i, atomic64_t *v) { return __lse_atomic64_andnot(~i, v); } #define ATOMIC64_FETCH_OP_AND(name, mb, cl...) \ static __always_inline long \ __lse_atomic64_fetch_and##name(s64 i, atomic64_t *v) \ { \ return __lse_atomic64_fetch_andnot##name(~i, v); \ } ATOMIC64_FETCH_OP_AND(_relaxed, ) ATOMIC64_FETCH_OP_AND(_acquire, a, "memory") ATOMIC64_FETCH_OP_AND(_release, l, "memory") ATOMIC64_FETCH_OP_AND( , al, "memory") #undef ATOMIC64_FETCH_OP_AND static __always_inline s64 __lse_atomic64_dec_if_positive(atomic64_t *v) { unsigned long tmp; asm volatile( __LSE_PREAMBLE "1: ldr %x[tmp], %[v]\n" " subs %[ret], %x[tmp], #1\n" " b.lt 2f\n" " casal %x[tmp], %[ret], %[v]\n" " sub %x[tmp], %x[tmp], #1\n" " sub %x[tmp], %x[tmp], %[ret]\n" " cbnz %x[tmp], 1b\n" "2:" : [ret] "+&r" (v), [v] "+Q" (v->counter), [tmp] "=&r" (tmp) : : "cc", "memory"); return (long)v; } #define __CMPXCHG_CASE(w, sfx, name, sz, mb, cl...) \ static __always_inline u##sz \ __lse__cmpxchg_case_##name##sz(volatile void *ptr, \ u##sz old, \ u##sz new) \ { \ asm volatile( \ __LSE_PREAMBLE \ " cas" #mb #sfx " %" #w "[old], %" #w "[new], %[v]\n" \ : [v] "+Q" (*(u##sz *)ptr), \ [old] "+r" (old) \ : [new] "rZ" (new) \ : cl); \ \ return old; \ } __CMPXCHG_CASE(w, b, , 8, ) __CMPXCHG_CASE(w, h, , 16, ) __CMPXCHG_CASE(w, , , 32, ) __CMPXCHG_CASE(x, , , 64, ) __CMPXCHG_CASE(w, b, acq_, 8, a, "memory") __CMPXCHG_CASE(w, h, acq_, 16, a, "memory") __CMPXCHG_CASE(w, , acq_, 32, a, "memory") __CMPXCHG_CASE(x, , acq_, 64, a, "memory") __CMPXCHG_CASE(w, b, rel_, 8, l, "memory") __CMPXCHG_CASE(w, h, rel_, 16, l, "memory") __CMPXCHG_CASE(w, , rel_, 32, l, "memory") __CMPXCHG_CASE(x, , rel_, 64, l, "memory") __CMPXCHG_CASE(w, b, mb_, 8, al, "memory") __CMPXCHG_CASE(w, h, mb_, 16, al, "memory") __CMPXCHG_CASE(w, , mb_, 32, al, "memory") __CMPXCHG_CASE(x, , mb_, 64, al, "memory") #undef __CMPXCHG_CASE #define __CMPXCHG128(name, mb, cl...) \ static __always_inline u128 \ __lse__cmpxchg128##name(volatile u128 *ptr, u128 old, u128 new) \ { \ union __u128_halves r, o = { .full = (old) }, \ n = { .full = (new) }; \ register unsigned long x0 asm ("x0") = o.low; \ register unsigned long x1 asm ("x1") = o.high; \ register unsigned long x2 asm ("x2") = n.low; \ register unsigned long x3 asm ("x3") = n.high; \ register unsigned long x4 asm ("x4") = (unsigned long)ptr; \ \ asm volatile( \ __LSE_PREAMBLE \ " casp" #mb "\t%[old1], %[old2], %[new1], %[new2], %[v]\n"\ : [old1] "+&r" (x0), [old2] "+&r" (x1), \ [v] "+Q" (*(u128 *)ptr) \ : [new1] "r" (x2), [new2] "r" (x3), [ptr] "r" (x4), \ [oldval1] "r" (o.low), [oldval2] "r" (o.high) \ : cl); \ \ r.low = x0; r.high = x1; \ \ return r.full; \ } __CMPXCHG128( , ) __CMPXCHG128(_mb, al, "memory") #undef __CMPXCHG128 #endif /* __ASM_ATOMIC_LSE_H */ |
| 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 */ /* * Linux Socket Filter Data Structures */ #ifndef __LINUX_FILTER_H__ #define __LINUX_FILTER_H__ #include <linux/atomic.h> #include <linux/bpf.h> #include <linux/refcount.h> #include <linux/compat.h> #include <linux/skbuff.h> #include <linux/linkage.h> #include <linux/printk.h> #include <linux/workqueue.h> #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/capability.h> #include <linux/set_memory.h> #include <linux/kallsyms.h> #include <linux/if_vlan.h> #include <linux/vmalloc.h> #include <linux/sockptr.h> #include <crypto/sha1.h> #include <linux/u64_stats_sync.h> #include <net/sch_generic.h> #include <asm/byteorder.h> #include <uapi/linux/filter.h> struct sk_buff; struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; struct xdp_buff; struct sock_reuseport; struct ctl_table; struct ctl_table_header; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function * calls in BPF_CALL instruction. */ #define BPF_REG_ARG1 BPF_REG_1 #define BPF_REG_ARG2 BPF_REG_2 #define BPF_REG_ARG3 BPF_REG_3 #define BPF_REG_ARG4 BPF_REG_4 #define BPF_REG_ARG5 BPF_REG_5 #define BPF_REG_CTX BPF_REG_6 #define BPF_REG_FP BPF_REG_10 /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 #define BPF_REG_TMP BPF_REG_2 /* scratch reg */ #define BPF_REG_D BPF_REG_8 /* data, callee-saved */ #define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register. */ #define BPF_REG_AX MAX_BPF_REG #define MAX_BPF_EXT_REG (MAX_BPF_REG + 1) #define MAX_BPF_JIT_REG MAX_BPF_EXT_REG /* unused opcode to mark special call to bpf_tail_call() helper */ #define BPF_TAIL_CALL 0xf0 /* unused opcode to mark special load instruction. Same as BPF_ABS */ #define BPF_PROBE_MEM 0x20 /* unused opcode to mark special ldsx instruction. Same as BPF_IND */ #define BPF_PROBE_MEMSX 0x40 /* unused opcode to mark special load instruction. Same as BPF_MSH */ #define BPF_PROBE_MEM32 0xa0 /* unused opcode to mark special atomic instruction */ #define BPF_PROBE_ATOMIC 0xe0 /* unused opcode to mark call to interpreter with arguments */ #define BPF_CALL_ARGS 0xe0 /* unused opcode to mark speculation barrier for mitigating * Speculative Store Bypass */ #define BPF_NOSPEC 0xc0 /* As per nm, we expose JITed images as text (code) section for * kallsyms. That way, tools like perf can find it to match * addresses. */ #define BPF_SYM_ELF_TYPE 't' /* BPF program can access up to 512 bytes of stack space. */ #define MAX_BPF_STACK 512 /* Helper macros for filter block array initializers. */ /* ALU ops on registers, bpf_add|sub|...: dst_reg += src_reg */ #define BPF_ALU64_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU64_REG(OP, DST, SRC) \ BPF_ALU64_REG_OFF(OP, DST, SRC, 0) #define BPF_ALU32_REG_OFF(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_ALU32_REG(OP, DST, SRC) \ BPF_ALU32_REG_OFF(OP, DST, SRC, 0) /* ALU ops on immediates, bpf_add|sub|...: dst_reg += imm32 */ #define BPF_ALU64_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU64_IMM(OP, DST, IMM) \ BPF_ALU64_IMM_OFF(OP, DST, IMM, 0) #define BPF_ALU32_IMM_OFF(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) #define BPF_ALU32_IMM(OP, DST, IMM) \ BPF_ALU32_IMM_OFF(OP, DST, IMM, 0) /* Endianess conversion, cpu_to_{l,b}e(), {l,b}e_to_cpu() */ #define BPF_ENDIAN(TYPE, DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_END | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Byte Swap, bswap16/32/64 */ #define BPF_BSWAP(DST, LEN) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_END | BPF_SRC(BPF_TO_LE), \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = LEN }) /* Short form of mov, dst_reg = src_reg */ #define BPF_MOV64_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) #define BPF_MOV32_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = 0 }) /* Special (internal-only) form of mov, used to resolve per-CPU addrs: * dst_reg = src_reg + <percpu_base_off> * BPF_ADDR_PERCPU is used as a special insn->off value. */ #define BPF_ADDR_PERCPU (-1) #define BPF_MOV64_PERCPU_REG(DST, SRC) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = BPF_ADDR_PERCPU, \ .imm = 0 }) static inline bool insn_is_mov_percpu_addr(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_PERCPU; } /* Short form of mov, dst_reg = imm32 */ #define BPF_MOV64_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_IMM(DST, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Short form of movsx, dst_reg = (s8,s16,s32)src_reg */ #define BPF_MOVSX64_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) #define BPF_MOVSX32_REG(DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Special form of mov32, used for doing explicit zero extension on dst. */ #define BPF_ZEXT_REG(DST) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_X, \ .dst_reg = DST, \ .src_reg = DST, \ .off = 0, \ .imm = 1 }) static inline bool insn_is_zext(const struct bpf_insn *insn) { return insn->code == (BPF_ALU | BPF_MOV | BPF_X) && insn->imm == 1; } /* addr_space_cast from as(0) to as(1) is for converting bpf arena pointers * to pointers in user vma. */ static inline bool insn_is_cast_user(const struct bpf_insn *insn) { return insn->code == (BPF_ALU64 | BPF_MOV | BPF_X) && insn->off == BPF_ADDR_SPACE_CAST && insn->imm == 1U << 16; } /* BPF_LD_IMM64 macro encodes single 'load 64-bit immediate' insn */ #define BPF_LD_IMM64(DST, IMM) \ BPF_LD_IMM64_RAW(DST, 0, IMM) #define BPF_LD_IMM64_RAW(DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_DW | BPF_IMM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = (__u32) (IMM) }), \ ((struct bpf_insn) { \ .code = 0, /* zero is reserved opcode */ \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = ((__u64) (IMM)) >> 32 }) /* pseudo BPF_LD_IMM64 insn used to refer to process-local map_fd */ #define BPF_LD_MAP_FD(DST, MAP_FD) \ BPF_LD_IMM64_RAW(DST, BPF_PSEUDO_MAP_FD, MAP_FD) /* Short form of mov based on type, BPF_X: dst_reg = src_reg, BPF_K: dst_reg = imm32 */ #define BPF_MOV64_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU64 | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) #define BPF_MOV32_RAW(TYPE, DST, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_ALU | BPF_MOV | BPF_SRC(TYPE), \ .dst_reg = DST, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Direct packet access, R0 = *(uint *) (skb->data + imm32) */ #define BPF_LD_ABS(SIZE, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_ABS, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = IMM }) /* Indirect packet access, R0 = *(uint *) (skb->data + src_reg + imm32) */ #define BPF_LD_IND(SIZE, SRC, IMM) \ ((struct bpf_insn) { \ .code = BPF_LD | BPF_SIZE(SIZE) | BPF_IND, \ .dst_reg = 0, \ .src_reg = SRC, \ .off = 0, \ .imm = IMM }) /* Memory load, dst_reg = *(uint *) (src_reg + off16) */ #define BPF_LDX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory load, dst_reg = *(signed size *) (src_reg + off16) */ #define BPF_LDX_MEMSX(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_LDX | BPF_SIZE(SIZE) | BPF_MEMSX, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Memory store, *(uint *) (dst_reg + off16) = src_reg */ #define BPF_STX_MEM(SIZE, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* * Atomic operations: * * BPF_ADD *(uint *) (dst_reg + off16) += src_reg * BPF_AND *(uint *) (dst_reg + off16) &= src_reg * BPF_OR *(uint *) (dst_reg + off16) |= src_reg * BPF_XOR *(uint *) (dst_reg + off16) ^= src_reg * BPF_ADD | BPF_FETCH src_reg = atomic_fetch_add(dst_reg + off16, src_reg); * BPF_AND | BPF_FETCH src_reg = atomic_fetch_and(dst_reg + off16, src_reg); * BPF_OR | BPF_FETCH src_reg = atomic_fetch_or(dst_reg + off16, src_reg); * BPF_XOR | BPF_FETCH src_reg = atomic_fetch_xor(dst_reg + off16, src_reg); * BPF_XCHG src_reg = atomic_xchg(dst_reg + off16, src_reg) * BPF_CMPXCHG r0 = atomic_cmpxchg(dst_reg + off16, r0, src_reg) */ #define BPF_ATOMIC_OP(SIZE, OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_STX | BPF_SIZE(SIZE) | BPF_ATOMIC, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = OP }) /* Legacy alias */ #define BPF_STX_XADD(SIZE, DST, SRC, OFF) BPF_ATOMIC_OP(SIZE, BPF_ADD, DST, SRC, OFF) /* Memory store, *(uint *) (dst_reg + off16) = imm32 */ #define BPF_ST_MEM(SIZE, DST, OFF, IMM) \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_SIZE(SIZE) | BPF_MEM, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Conditional jumps against registers, if (dst_reg 'op' src_reg) goto pc + off16 */ #define BPF_JMP_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Conditional jumps against immediates, if (dst_reg 'op' imm32) goto pc + off16 */ #define BPF_JMP_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Like BPF_JMP_REG, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_REG(OP, DST, SRC, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_X, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = 0 }) /* Like BPF_JMP_IMM, but with 32-bit wide operands for comparison. */ #define BPF_JMP32_IMM(OP, DST, IMM, OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP32 | BPF_OP(OP) | BPF_K, \ .dst_reg = DST, \ .src_reg = 0, \ .off = OFF, \ .imm = IMM }) /* Unconditional jumps, goto pc + off16 */ #define BPF_JMP_A(OFF) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_JA, \ .dst_reg = 0, \ .src_reg = 0, \ .off = OFF, \ .imm = 0 }) /* Relative call */ #define BPF_CALL_REL(TGT) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = BPF_PSEUDO_CALL, \ .off = 0, \ .imm = TGT }) /* Convert function address to BPF immediate */ #define BPF_CALL_IMM(x) ((void *)(x) - (void *)__bpf_call_base) #define BPF_EMIT_CALL(FUNC) \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_CALL, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = BPF_CALL_IMM(FUNC) }) /* Raw code statement block */ #define BPF_RAW_INSN(CODE, DST, SRC, OFF, IMM) \ ((struct bpf_insn) { \ .code = CODE, \ .dst_reg = DST, \ .src_reg = SRC, \ .off = OFF, \ .imm = IMM }) /* Program exit */ #define BPF_EXIT_INSN() \ ((struct bpf_insn) { \ .code = BPF_JMP | BPF_EXIT, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Speculation barrier */ #define BPF_ST_NOSPEC() \ ((struct bpf_insn) { \ .code = BPF_ST | BPF_NOSPEC, \ .dst_reg = 0, \ .src_reg = 0, \ .off = 0, \ .imm = 0 }) /* Internal classic blocks for direct assignment */ #define __BPF_STMT(CODE, K) \ ((struct sock_filter) BPF_STMT(CODE, K)) #define __BPF_JUMP(CODE, K, JT, JF) \ ((struct sock_filter) BPF_JUMP(CODE, K, JT, JF)) #define bytes_to_bpf_size(bytes) \ ({ \ int bpf_size = -EINVAL; \ \ if (bytes == sizeof(u8)) \ bpf_size = BPF_B; \ else if (bytes == sizeof(u16)) \ bpf_size = BPF_H; \ else if (bytes == sizeof(u32)) \ bpf_size = BPF_W; \ else if (bytes == sizeof(u64)) \ bpf_size = BPF_DW; \ \ bpf_size; \ }) #define bpf_size_to_bytes(bpf_size) \ ({ \ int bytes = -EINVAL; \ \ if (bpf_size == BPF_B) \ bytes = sizeof(u8); \ else if (bpf_size == BPF_H) \ bytes = sizeof(u16); \ else if (bpf_size == BPF_W) \ bytes = sizeof(u32); \ else if (bpf_size == BPF_DW) \ bytes = sizeof(u64); \ \ bytes; \ }) #define BPF_SIZEOF(type) \ ({ \ const int __size = bytes_to_bpf_size(sizeof(type)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_FIELD_SIZEOF(type, field) \ ({ \ const int __size = bytes_to_bpf_size(sizeof_field(type, field)); \ BUILD_BUG_ON(__size < 0); \ __size; \ }) #define BPF_LDST_BYTES(insn) \ ({ \ const int __size = bpf_size_to_bytes(BPF_SIZE((insn)->code)); \ WARN_ON(__size < 0); \ __size; \ }) #define __BPF_MAP_0(m, v, ...) v #define __BPF_MAP_1(m, v, t, a, ...) m(t, a) #define __BPF_MAP_2(m, v, t, a, ...) m(t, a), __BPF_MAP_1(m, v, __VA_ARGS__) #define __BPF_MAP_3(m, v, t, a, ...) m(t, a), __BPF_MAP_2(m, v, __VA_ARGS__) #define __BPF_MAP_4(m, v, t, a, ...) m(t, a), __BPF_MAP_3(m, v, __VA_ARGS__) #define __BPF_MAP_5(m, v, t, a, ...) m(t, a), __BPF_MAP_4(m, v, __VA_ARGS__) #define __BPF_REG_0(...) __BPF_PAD(5) #define __BPF_REG_1(...) __BPF_MAP(1, __VA_ARGS__), __BPF_PAD(4) #define __BPF_REG_2(...) __BPF_MAP(2, __VA_ARGS__), __BPF_PAD(3) #define __BPF_REG_3(...) __BPF_MAP(3, __VA_ARGS__), __BPF_PAD(2) #define __BPF_REG_4(...) __BPF_MAP(4, __VA_ARGS__), __BPF_PAD(1) #define __BPF_REG_5(...) __BPF_MAP(5, __VA_ARGS__) #define __BPF_MAP(n, ...) __BPF_MAP_##n(__VA_ARGS__) #define __BPF_REG(n, ...) __BPF_REG_##n(__VA_ARGS__) #define __BPF_CAST(t, a) \ (__force t) \ (__force \ typeof(__builtin_choose_expr(sizeof(t) == sizeof(unsigned long), \ (unsigned long)0, (t)0))) a #define __BPF_V void #define __BPF_N #define __BPF_DECL_ARGS(t, a) t a #define __BPF_DECL_REGS(t, a) u64 a #define __BPF_PAD(n) \ __BPF_MAP(n, __BPF_DECL_ARGS, __BPF_N, u64, __ur_1, u64, __ur_2, \ u64, __ur_3, u64, __ur_4, u64, __ur_5) #define BPF_CALL_x(x, attr, name, ...) \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ typedef u64 (*btf_##name)(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)); \ attr u64 name(__BPF_REG(x, __BPF_DECL_REGS, __BPF_N, __VA_ARGS__)) \ { \ return ((btf_##name)____##name)(__BPF_MAP(x,__BPF_CAST,__BPF_N,__VA_ARGS__));\ } \ static __always_inline \ u64 ____##name(__BPF_MAP(x, __BPF_DECL_ARGS, __BPF_V, __VA_ARGS__)) #define __NOATTR #define BPF_CALL_0(name, ...) BPF_CALL_x(0, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_1(name, ...) BPF_CALL_x(1, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_2(name, ...) BPF_CALL_x(2, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_3(name, ...) BPF_CALL_x(3, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_4(name, ...) BPF_CALL_x(4, __NOATTR, name, __VA_ARGS__) #define BPF_CALL_5(name, ...) BPF_CALL_x(5, __NOATTR, name, __VA_ARGS__) #define NOTRACE_BPF_CALL_1(name, ...) BPF_CALL_x(1, notrace, name, __VA_ARGS__) #define bpf_ctx_range(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #define bpf_ctx_range_till(TYPE, MEMBER1, MEMBER2) \ offsetof(TYPE, MEMBER1) ... offsetofend(TYPE, MEMBER2) - 1 #if BITS_PER_LONG == 64 # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetofend(TYPE, MEMBER) - 1 #else # define bpf_ctx_range_ptr(TYPE, MEMBER) \ offsetof(TYPE, MEMBER) ... offsetof(TYPE, MEMBER) + 8 - 1 #endif /* BITS_PER_LONG == 64 */ #define bpf_target_off(TYPE, MEMBER, SIZE, PTR_SIZE) \ ({ \ BUILD_BUG_ON(sizeof_field(TYPE, MEMBER) != (SIZE)); \ *(PTR_SIZE) = (SIZE); \ offsetof(TYPE, MEMBER); \ }) /* A struct sock_filter is architecture independent. */ struct compat_sock_fprog { u16 len; compat_uptr_t filter; /* struct sock_filter * */ }; struct sock_fprog_kern { u16 len; struct sock_filter *filter; }; /* Some arches need doubleword alignment for their instructions and/or data */ #define BPF_IMAGE_ALIGNMENT 8 struct bpf_binary_header { u32 size; u8 image[] __aligned(BPF_IMAGE_ALIGNMENT); }; struct bpf_prog_stats { u64_stats_t cnt; u64_stats_t nsecs; u64_stats_t misses; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); struct sk_filter { refcount_t refcnt; struct rcu_head rcu; struct bpf_prog *prog; }; DECLARE_STATIC_KEY_FALSE(bpf_stats_enabled_key); extern struct mutex nf_conn_btf_access_lock; extern int (*nfct_btf_struct_access)(struct bpf_verifier_log *log, const struct bpf_reg_state *reg, int off, int size); typedef unsigned int (*bpf_dispatcher_fn)(const void *ctx, const struct bpf_insn *insnsi, unsigned int (*bpf_func)(const void *, const struct bpf_insn *)); static __always_inline u32 __bpf_prog_run(const struct bpf_prog *prog, const void *ctx, bpf_dispatcher_fn dfunc) { u32 ret; cant_migrate(); if (static_branch_unlikely(&bpf_stats_enabled_key)) { struct bpf_prog_stats *stats; u64 duration, start = sched_clock(); unsigned long flags; ret = dfunc(ctx, prog->insnsi, prog->bpf_func); duration = sched_clock() - start; stats = this_cpu_ptr(prog->stats); flags = u64_stats_update_begin_irqsave(&stats->syncp); u64_stats_inc(&stats->cnt); u64_stats_add(&stats->nsecs, duration); u64_stats_update_end_irqrestore(&stats->syncp, flags); } else { ret = dfunc(ctx, prog->insnsi, prog->bpf_func); } return ret; } static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void *ctx) { return __bpf_prog_run(prog, ctx, bpf_dispatcher_nop_func); } /* * Use in preemptible and therefore migratable context to make sure that * the execution of the BPF program runs on one CPU. * * This uses migrate_disable/enable() explicitly to document that the * invocation of a BPF program does not require reentrancy protection * against a BPF program which is invoked from a preempting task. */ static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog, const void *ctx) { u32 ret; migrate_disable(); ret = bpf_prog_run(prog, ctx); migrate_enable(); return ret; } #define BPF_SKB_CB_LEN QDISC_CB_PRIV_LEN struct bpf_skb_data_end { struct qdisc_skb_cb qdisc_cb; void *data_meta; void *data_end; }; struct bpf_nh_params { u32 nh_family; union { u32 ipv4_nh; struct in6_addr ipv6_nh; }; }; struct bpf_redirect_info { u64 tgt_index; void *tgt_value; struct bpf_map *map; u32 flags; u32 kern_flags; u32 map_id; enum bpf_map_type map_type; struct bpf_nh_params nh; }; DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); /* flags for bpf_redirect_info kern_flags */ #define BPF_RI_F_RF_NO_DIRECT BIT(0) /* no napi_direct on return_frame */ /* Compute the linear packet data range [data, data_end) which * will be accessed by various program types (cls_bpf, act_bpf, * lwt, ...). Subsystems allowing direct data access must (!) * ensure that cb[] area can be written to when BPF program is * invoked (otherwise cb[] save/restore is necessary). */ static inline void bpf_compute_data_pointers(struct sk_buff *skb) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; BUILD_BUG_ON(sizeof(*cb) > sizeof_field(struct sk_buff, cb)); cb->data_meta = skb->data - skb_metadata_len(skb); cb->data_end = skb->data + skb_headlen(skb); } /* Similar to bpf_compute_data_pointers(), except that save orginal * data in cb->data and cb->meta_data for restore. */ static inline void bpf_compute_and_save_data_end( struct sk_buff *skb, void **saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; *saved_data_end = cb->data_end; cb->data_end = skb->data + skb_headlen(skb); } /* Restore data saved by bpf_compute_and_save_data_end(). */ static inline void bpf_restore_data_end( struct sk_buff *skb, void *saved_data_end) { struct bpf_skb_data_end *cb = (struct bpf_skb_data_end *)skb->cb; cb->data_end = saved_data_end; } static inline u8 *bpf_skb_cb(const struct sk_buff *skb) { /* eBPF programs may read/write skb->cb[] area to transfer meta * data between tail calls. Since this also needs to work with * tc, that scratch memory is mapped to qdisc_skb_cb's data area. * * In some socket filter cases, the cb unfortunately needs to be * saved/restored so that protocol specific skb->cb[] data won't * be lost. In any case, due to unpriviledged eBPF programs * attached to sockets, we need to clear the bpf_skb_cb() area * to not leak previous contents to user space. */ BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != BPF_SKB_CB_LEN); BUILD_BUG_ON(sizeof_field(struct __sk_buff, cb) != sizeof_field(struct qdisc_skb_cb, data)); return qdisc_skb_cb(skb)->data; } /* Must be invoked with migration disabled */ static inline u32 __bpf_prog_run_save_cb(const struct bpf_prog *prog, const void *ctx) { const struct sk_buff *skb = ctx; u8 *cb_data = bpf_skb_cb(skb); u8 cb_saved[BPF_SKB_CB_LEN]; u32 res; if (unlikely(prog->cb_access)) { memcpy(cb_saved, cb_data, sizeof(cb_saved)); memset(cb_data, 0, sizeof(cb_saved)); } res = bpf_prog_run(prog, skb); if (unlikely(prog->cb_access)) memcpy(cb_data, cb_saved, sizeof(cb_saved)); return res; } static inline u32 bpf_prog_run_save_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u32 res; migrate_disable(); res = __bpf_prog_run_save_cb(prog, skb); migrate_enable(); return res; } static inline u32 bpf_prog_run_clear_cb(const struct bpf_prog *prog, struct sk_buff *skb) { u8 *cb_data = bpf_skb_cb(skb); u32 res; if (unlikely(prog->cb_access)) memset(cb_data, 0, BPF_SKB_CB_LEN); res = bpf_prog_run_pin_on_cpu(prog, skb); return res; } DECLARE_BPF_DISPATCHER(xdp) DECLARE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key); u32 xdp_master_redirect(struct xdp_buff *xdp); void bpf_prog_change_xdp(struct bpf_prog *prev_prog, struct bpf_prog *prog); static inline u32 bpf_prog_insn_size(const struct bpf_prog *prog) { return prog->len * sizeof(struct bpf_insn); } static inline u32 bpf_prog_tag_scratch_size(const struct bpf_prog *prog) { return round_up(bpf_prog_insn_size(prog) + sizeof(__be64) + 1, SHA1_BLOCK_SIZE); } static inline unsigned int bpf_prog_size(unsigned int proglen) { return max(sizeof(struct bpf_prog), offsetof(struct bpf_prog, insns[proglen])); } static inline bool bpf_prog_was_classic(const struct bpf_prog *prog) { /* When classic BPF programs have been loaded and the arch * does not have a classic BPF JIT (anymore), they have been * converted via bpf_migrate_filter() to eBPF and thus always * have an unspec program type. */ return prog->type == BPF_PROG_TYPE_UNSPEC; } static inline u32 bpf_ctx_off_adjust_machine(u32 size) { const u32 size_machine = sizeof(unsigned long); if (size > size_machine && size % size_machine == 0) size = size_machine; return size; } static inline bool bpf_ctx_narrow_access_ok(u32 off, u32 size, u32 size_default) { return size <= size_default && (size & (size - 1)) == 0; } static inline u8 bpf_ctx_narrow_access_offset(u32 off, u32 size, u32 size_default) { u8 access_off = off & (size_default - 1); #ifdef __LITTLE_ENDIAN return access_off; #else return size_default - (access_off + size); #endif } #define bpf_ctx_wide_access_ok(off, size, type, field) \ (size == sizeof(__u64) && \ off >= offsetof(type, field) && \ off + sizeof(__u64) <= offsetofend(type, field) && \ off % sizeof(__u64) == 0) #define bpf_classic_proglen(fprog) (fprog->len * sizeof(fprog->filter[0])) static inline int __must_check bpf_prog_lock_ro(struct bpf_prog *fp) { #ifndef CONFIG_BPF_JIT_ALWAYS_ON if (!fp->jited) { set_vm_flush_reset_perms(fp); return set_memory_ro((unsigned long)fp, fp->pages); } #endif return 0; } static inline int __must_check bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr) { set_vm_flush_reset_perms(hdr); return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT); } int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap); static inline int sk_filter(struct sock *sk, struct sk_buff *skb) { return sk_filter_trim_cap(sk, skb, 1); } struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err); void bpf_prog_free(struct bpf_prog *fp); bool bpf_opcode_in_insntable(u8 code); void bpf_prog_fill_jited_linfo(struct bpf_prog *prog, const u32 *insn_to_jit_off); int bpf_prog_alloc_jited_linfo(struct bpf_prog *prog); void bpf_prog_jit_attempt_done(struct bpf_prog *prog); struct bpf_prog *bpf_prog_alloc(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flags); struct bpf_prog *bpf_prog_realloc(struct bpf_prog *fp_old, unsigned int size, gfp_t gfp_extra_flags); void __bpf_prog_free(struct bpf_prog *fp); static inline void bpf_prog_unlock_free(struct bpf_prog *fp) { __bpf_prog_free(fp); } typedef int (*bpf_aux_classic_check_t)(struct sock_filter *filter, unsigned int flen); int bpf_prog_create(struct bpf_prog **pfp, struct sock_fprog_kern *fprog); int bpf_prog_create_from_user(struct bpf_prog **pfp, struct sock_fprog *fprog, bpf_aux_classic_check_t trans, bool save_orig); void bpf_prog_destroy(struct bpf_prog *fp); int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_attach_bpf(u32 ufd, struct sock *sk); int sk_reuseport_attach_filter(struct sock_fprog *fprog, struct sock *sk); int sk_reuseport_attach_bpf(u32 ufd, struct sock *sk); void sk_reuseport_prog_free(struct bpf_prog *prog); int sk_detach_filter(struct sock *sk); int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len); bool sk_filter_charge(struct sock *sk, struct sk_filter *fp); void sk_filter_uncharge(struct sock *sk, struct sk_filter *fp); u64 __bpf_call_base(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); #define __bpf_call_base_args \ ((u64 (*)(u64, u64, u64, u64, u64, const struct bpf_insn *)) \ (void *)__bpf_call_base) struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog); void bpf_jit_compile(struct bpf_prog *prog); bool bpf_jit_needs_zext(void); bool bpf_jit_inlines_helper_call(s32 imm); bool bpf_jit_supports_subprog_tailcalls(void); bool bpf_jit_supports_percpu_insn(void); bool bpf_jit_supports_kfunc_call(void); bool bpf_jit_supports_far_kfunc_call(void); bool bpf_jit_supports_exceptions(void); bool bpf_jit_supports_ptr_xchg(void); bool bpf_jit_supports_arena(void); bool bpf_jit_supports_insn(struct bpf_insn *insn, bool in_arena); u64 bpf_arch_uaddress_limit(void); void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp), void *cookie); bool bpf_helper_changes_pkt_data(void *func); static inline bool bpf_dump_raw_ok(const struct cred *cred) { /* Reconstruction of call-sites is dependent on kallsyms, * thus make dump the same restriction. */ return kallsyms_show_value(cred); } struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, const struct bpf_insn *patch, u32 len); int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt); void bpf_clear_redirect_map(struct bpf_map *map); static inline bool xdp_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_set_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT; } static inline void xdp_clear_return_frame_no_direct(void) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT; } static inline int xdp_ok_fwd_dev(const struct net_device *fwd, unsigned int pktlen) { unsigned int len; if (unlikely(!(fwd->flags & IFF_UP))) return -ENETDOWN; len = fwd->mtu + fwd->hard_header_len + VLAN_HLEN; if (pktlen > len) return -EMSGSIZE; return 0; } /* The pair of xdp_do_redirect and xdp_do_flush MUST be called in the * same cpu context. Further for best results no more than a single map * for the do_redirect/do_flush pair should be used. This limitation is * because we only track one map and force a flush when the map changes. * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp, struct xdp_frame *xdpf, struct bpf_prog *prog); void xdp_do_flush(void); void bpf_warn_invalid_xdp_action(struct net_device *dev, struct bpf_prog *prog, u32 act); #ifdef CONFIG_INET struct sock *bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash); #else static inline struct sock * bpf_run_sk_reuseport(struct sock_reuseport *reuse, struct sock *sk, struct bpf_prog *prog, struct sk_buff *skb, struct sock *migrating_sk, u32 hash) { return NULL; } #endif #ifdef CONFIG_BPF_JIT extern int bpf_jit_enable; extern int bpf_jit_harden; extern int bpf_jit_kallsyms; extern long bpf_jit_limit; extern long bpf_jit_limit_max; typedef void (*bpf_jit_fill_hole_t)(void *area, unsigned int size); void bpf_jit_fill_hole_with_zero(void *area, unsigned int size); struct bpf_binary_header * bpf_jit_binary_alloc(unsigned int proglen, u8 **image_ptr, unsigned int alignment, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_jit_binary_free(struct bpf_binary_header *hdr); u64 bpf_jit_alloc_exec_limit(void); void *bpf_jit_alloc_exec(unsigned long size); void bpf_jit_free_exec(void *addr); void bpf_jit_free(struct bpf_prog *fp); struct bpf_binary_header * bpf_jit_binary_pack_hdr(const struct bpf_prog *fp); void *bpf_prog_pack_alloc(u32 size, bpf_jit_fill_hole_t bpf_fill_ill_insns); void bpf_prog_pack_free(void *ptr, u32 size); static inline bool bpf_prog_kallsyms_verify_off(const struct bpf_prog *fp) { return list_empty(&fp->aux->ksym.lnode) || fp->aux->ksym.lnode.prev == LIST_POISON2; } struct bpf_binary_header * bpf_jit_binary_pack_alloc(unsigned int proglen, u8 **ro_image, unsigned int alignment, struct bpf_binary_header **rw_hdr, u8 **rw_image, bpf_jit_fill_hole_t bpf_fill_ill_insns); int bpf_jit_binary_pack_finalize(struct bpf_prog *prog, struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); void bpf_jit_binary_pack_free(struct bpf_binary_header *ro_header, struct bpf_binary_header *rw_header); int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke); int bpf_jit_get_func_addr(const struct bpf_prog *prog, const struct bpf_insn *insn, bool extra_pass, u64 *func_addr, bool *func_addr_fixed); struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp); void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other); static inline void bpf_jit_dump(unsigned int flen, unsigned int proglen, u32 pass, void *image) { pr_err("flen=%u proglen=%u pass=%u image=%pK from=%s pid=%d\n", flen, proglen, pass, image, current->comm, task_pid_nr(current)); if (image) print_hex_dump(KERN_ERR, "JIT code: ", DUMP_PREFIX_OFFSET, 16, 1, image, proglen, false); } static inline bool bpf_jit_is_ebpf(void) { # ifdef CONFIG_HAVE_EBPF_JIT return true; # else return false; # endif } static inline bool ebpf_jit_enabled(void) { return bpf_jit_enable && bpf_jit_is_ebpf(); } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return fp->jited && bpf_jit_is_ebpf(); } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { /* These are the prerequisites, should someone ever have the * idea to call blinding outside of them, we make sure to * bail out. */ if (!bpf_jit_is_ebpf()) return false; if (!prog->jit_requested) return false; if (!bpf_jit_harden) return false; if (bpf_jit_harden == 1 && bpf_token_capable(prog->aux->token, CAP_BPF)) return false; return true; } static inline bool bpf_jit_kallsyms_enabled(void) { /* There are a couple of corner cases where kallsyms should * not be enabled f.e. on hardening. */ if (bpf_jit_harden) return false; if (!bpf_jit_kallsyms) return false; if (bpf_jit_kallsyms == 1) return true; return false; } int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym); bool is_bpf_text_address(unsigned long addr); int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym); struct bpf_prog *bpf_prog_ksym_find(unsigned long addr); static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { int ret = __bpf_address_lookup(addr, size, off, sym); if (ret && modname) *modname = NULL; return ret; } void bpf_prog_kallsyms_add(struct bpf_prog *fp); void bpf_prog_kallsyms_del(struct bpf_prog *fp); #else /* CONFIG_BPF_JIT */ static inline bool ebpf_jit_enabled(void) { return false; } static inline bool bpf_jit_blinding_enabled(struct bpf_prog *prog) { return false; } static inline bool bpf_prog_ebpf_jited(const struct bpf_prog *fp) { return false; } static inline int bpf_jit_add_poke_descriptor(struct bpf_prog *prog, struct bpf_jit_poke_descriptor *poke) { return -ENOTSUPP; } static inline void bpf_jit_free(struct bpf_prog *fp) { bpf_prog_unlock_free(fp); } static inline bool bpf_jit_kallsyms_enabled(void) { return false; } static inline int __bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char *sym) { return 0; } static inline bool is_bpf_text_address(unsigned long addr) { return false; } static inline int bpf_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *sym) { return -ERANGE; } static inline struct bpf_prog *bpf_prog_ksym_find(unsigned long addr) { return NULL; } static inline int bpf_address_lookup(unsigned long addr, unsigned long *size, unsigned long *off, char **modname, char *sym) { return 0; } static inline void bpf_prog_kallsyms_add(struct bpf_prog *fp) { } static inline void bpf_prog_kallsyms_del(struct bpf_prog *fp) { } #endif /* CONFIG_BPF_JIT */ void bpf_prog_kallsyms_del_all(struct bpf_prog *fp); #define BPF_ANC BIT(15) static inline bool bpf_needs_clear_a(const struct sock_filter *first) { switch (first->code) { case BPF_RET | BPF_K: case BPF_LD | BPF_W | BPF_LEN: return false; case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: if (first->k == SKF_AD_OFF + SKF_AD_ALU_XOR_X) return true; return false; default: return true; } } static inline u16 bpf_anc_helper(const struct sock_filter *ftest) { BUG_ON(ftest->code & BPF_ANC); switch (ftest->code) { case BPF_LD | BPF_W | BPF_ABS: case BPF_LD | BPF_H | BPF_ABS: case BPF_LD | BPF_B | BPF_ABS: #define BPF_ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ return BPF_ANC | SKF_AD_##CODE switch (ftest->k) { BPF_ANCILLARY(PROTOCOL); BPF_ANCILLARY(PKTTYPE); BPF_ANCILLARY(IFINDEX); BPF_ANCILLARY(NLATTR); BPF_ANCILLARY(NLATTR_NEST); BPF_ANCILLARY(MARK); BPF_ANCILLARY(QUEUE); BPF_ANCILLARY(HATYPE); BPF_ANCILLARY(RXHASH); BPF_ANCILLARY(CPU); BPF_ANCILLARY(ALU_XOR_X); BPF_ANCILLARY(VLAN_TAG); BPF_ANCILLARY(VLAN_TAG_PRESENT); BPF_ANCILLARY(PAY_OFFSET); BPF_ANCILLARY(RANDOM); BPF_ANCILLARY(VLAN_TPID); } fallthrough; default: return ftest->code; } } void *bpf_internal_load_pointer_neg_helper(const struct sk_buff *skb, int k, unsigned int size); static inline int bpf_tell_extensions(void) { return SKF_AD_MAX; } struct bpf_sock_addr_kern { struct sock *sk; struct sockaddr *uaddr; /* Temporary "register" to make indirect stores to nested structures * defined above. We need three registers to make such a store, but * only two (src and dst) are available at convert_ctx_access time */ u64 tmp_reg; void *t_ctx; /* Attach type specific context. */ u32 uaddrlen; }; struct bpf_sock_ops_kern { struct sock *sk; union { u32 args[4]; u32 reply; u32 replylong[4]; }; struct sk_buff *syn_skb; struct sk_buff *skb; void *skb_data_end; u8 op; u8 is_fullsock; u8 remaining_opt_len; u64 temp; /* temp and everything after is not * initialized to 0 before calling * the BPF program. New fields that * should be initialized to 0 should * be inserted before temp. * temp is scratch storage used by * sock_ops_convert_ctx_access * as temporary storage of a register. */ }; struct bpf_sysctl_kern { struct ctl_table_header *head; struct ctl_table *table; void *cur_val; size_t cur_len; void *new_val; size_t new_len; int new_updated; int write; loff_t *ppos; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; #define BPF_SOCKOPT_KERN_BUF_SIZE 32 struct bpf_sockopt_buf { u8 data[BPF_SOCKOPT_KERN_BUF_SIZE]; }; struct bpf_sockopt_kern { struct sock *sk; u8 *optval; u8 *optval_end; s32 level; s32 optname; s32 optlen; /* for retval in struct bpf_cg_run_ctx */ struct task_struct *current_task; /* Temporary "register" for indirect stores to ppos. */ u64 tmp_reg; }; int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len); struct bpf_sk_lookup_kern { u16 family; u16 protocol; __be16 sport; u16 dport; struct { __be32 saddr; __be32 daddr; } v4; struct { const struct in6_addr *saddr; const struct in6_addr *daddr; } v6; struct sock *selected_sk; u32 ingress_ifindex; bool no_reuseport; }; extern struct static_key_false bpf_sk_lookup_enabled; /* Runners for BPF_SK_LOOKUP programs to invoke on socket lookup. * * Allowed return values for a BPF SK_LOOKUP program are SK_PASS and * SK_DROP. Their meaning is as follows: * * SK_PASS && ctx.selected_sk != NULL: use selected_sk as lookup result * SK_PASS && ctx.selected_sk == NULL: continue to htable-based socket lookup * SK_DROP : terminate lookup with -ECONNREFUSED * * This macro aggregates return values and selected sockets from * multiple BPF programs according to following rules in order: * * 1. If any program returned SK_PASS and a non-NULL ctx.selected_sk, * macro result is SK_PASS and last ctx.selected_sk is used. * 2. If any program returned SK_DROP return value, * macro result is SK_DROP. * 3. Otherwise result is SK_PASS and ctx.selected_sk is NULL. * * Caller must ensure that the prog array is non-NULL, and that the * array as well as the programs it contains remain valid. */ #define BPF_PROG_SK_LOOKUP_RUN_ARRAY(array, ctx, func) \ ({ \ struct bpf_sk_lookup_kern *_ctx = &(ctx); \ struct bpf_prog_array_item *_item; \ struct sock *_selected_sk = NULL; \ bool _no_reuseport = false; \ struct bpf_prog *_prog; \ bool _all_pass = true; \ u32 _ret; \ \ migrate_disable(); \ _item = &(array)->items[0]; \ while ((_prog = READ_ONCE(_item->prog))) { \ /* restore most recent selection */ \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ \ _ret = func(_prog, _ctx); \ if (_ret == SK_PASS && _ctx->selected_sk) { \ /* remember last non-NULL socket */ \ _selected_sk = _ctx->selected_sk; \ _no_reuseport = _ctx->no_reuseport; \ } else if (_ret == SK_DROP && _all_pass) { \ _all_pass = false; \ } \ _item++; \ } \ _ctx->selected_sk = _selected_sk; \ _ctx->no_reuseport = _no_reuseport; \ migrate_enable(); \ _all_pass || _selected_sk ? SK_PASS : SK_DROP; \ }) static inline bool bpf_sk_lookup_run_v4(struct net *net, int protocol, const __be32 saddr, const __be16 sport, const __be32 daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET, .protocol = protocol, .v4.saddr = saddr, .v4.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #if IS_ENABLED(CONFIG_IPV6) static inline bool bpf_sk_lookup_run_v6(struct net *net, int protocol, const struct in6_addr *saddr, const __be16 sport, const struct in6_addr *daddr, const u16 dport, const int ifindex, struct sock **psk) { struct bpf_prog_array *run_array; struct sock *selected_sk = NULL; bool no_reuseport = false; rcu_read_lock(); run_array = rcu_dereference(net->bpf.run_array[NETNS_BPF_SK_LOOKUP]); if (run_array) { struct bpf_sk_lookup_kern ctx = { .family = AF_INET6, .protocol = protocol, .v6.saddr = saddr, .v6.daddr = daddr, .sport = sport, .dport = dport, .ingress_ifindex = ifindex, }; u32 act; act = BPF_PROG_SK_LOOKUP_RUN_ARRAY(run_array, ctx, bpf_prog_run); if (act == SK_PASS) { selected_sk = ctx.selected_sk; no_reuseport = ctx.no_reuseport; } else { selected_sk = ERR_PTR(-ECONNREFUSED); } } rcu_read_unlock(); *psk = selected_sk; return no_reuseport; } #endif /* IS_ENABLED(CONFIG_IPV6) */ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 index, u64 flags, const u64 flag_mask, void *lookup_elem(struct bpf_map *map, u32 key)) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX; /* Lower bits of the flags are used as return code on lookup failure */ if (unlikely(flags & ~(action_mask | flag_mask))) return XDP_ABORTED; ri->tgt_value = lookup_elem(map, index); if (unlikely(!ri->tgt_value) && !(flags & BPF_F_BROADCAST)) { /* If the lookup fails we want to clear out the state in the * redirect_info struct completely, so that if an eBPF program * performs multiple lookups, the last one always takes * precedence. */ ri->map_id = INT_MAX; /* Valid map id idr range: [1,INT_MAX[ */ ri->map_type = BPF_MAP_TYPE_UNSPEC; return flags & action_mask; } ri->tgt_index = index; ri->map_id = map->id; ri->map_type = map->map_type; if (flags & BPF_F_BROADCAST) { WRITE_ONCE(ri->map, map); ri->flags = flags; } else { WRITE_ONCE(ri->map, NULL); ri->flags = 0; } return XDP_REDIRECT; } #ifdef CONFIG_NET int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len); int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags); int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len); void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len); void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush); #else /* CONFIG_NET */ static inline int __bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) { return -EOPNOTSUPP; } static inline int __bpf_xdp_load_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline int __bpf_xdp_store_bytes(struct xdp_buff *xdp, u32 offset, void *buf, u32 len) { return -EOPNOTSUPP; } static inline void *bpf_xdp_pointer(struct xdp_buff *xdp, u32 offset, u32 len) { return NULL; } static inline void bpf_xdp_copy_buf(struct xdp_buff *xdp, unsigned long off, void *buf, unsigned long len, bool flush) { } #endif /* CONFIG_NET */ #endif /* __LINUX_FILTER_H__ */ |
| 152 152 152 152 152 158 148 158 158 158 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 | // SPDX-License-Identifier: GPL-2.0-only /* * lib/bitmap.c * Helper functions for bitmap.h. */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/ctype.h> #include <linux/device.h> #include <linux/export.h> #include <linux/slab.h> /** * DOC: bitmap introduction * * bitmaps provide an array of bits, implemented using an * array of unsigned longs. The number of valid bits in a * given bitmap does _not_ need to be an exact multiple of * BITS_PER_LONG. * * The possible unused bits in the last, partially used word * of a bitmap are 'don't care'. The implementation makes * no particular effort to keep them zero. It ensures that * their value will not affect the results of any operation. * The bitmap operations that return Boolean (bitmap_empty, * for example) or scalar (bitmap_weight, for example) results * carefully filter out these unused bits from impacting their * results. * * The byte ordering of bitmaps is more natural on little * endian architectures. See the big-endian headers * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h * for the best explanations of this ordering. */ bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] != bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_equal); bool __bitmap_or_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, const unsigned long *bitmap3, unsigned int bits) { unsigned int k, lim = bits / BITS_PER_LONG; unsigned long tmp; for (k = 0; k < lim; ++k) { if ((bitmap1[k] | bitmap2[k]) != bitmap3[k]) return false; } if (!(bits % BITS_PER_LONG)) return true; tmp = (bitmap1[k] | bitmap2[k]) ^ bitmap3[k]; return (tmp & BITMAP_LAST_WORD_MASK(bits)) == 0; } void __bitmap_complement(unsigned long *dst, const unsigned long *src, unsigned int bits) { unsigned int k, lim = BITS_TO_LONGS(bits); for (k = 0; k < lim; ++k) dst[k] = ~src[k]; } EXPORT_SYMBOL(__bitmap_complement); /** * __bitmap_shift_right - logical right shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting right (dividing) means moving bits in the MS -> LS bit * direction. Zeros are fed into the vacated MS positions and the * LS bits shifted off the bottom are lost. */ void __bitmap_shift_right(unsigned long *dst, const unsigned long *src, unsigned shift, unsigned nbits) { unsigned k, lim = BITS_TO_LONGS(nbits); unsigned off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; unsigned long mask = BITMAP_LAST_WORD_MASK(nbits); for (k = 0; off + k < lim; ++k) { unsigned long upper, lower; /* * If shift is not word aligned, take lower rem bits of * word above and make them the top rem bits of result. */ if (!rem || off + k + 1 >= lim) upper = 0; else { upper = src[off + k + 1]; if (off + k + 1 == lim - 1) upper &= mask; upper <<= (BITS_PER_LONG - rem); } lower = src[off + k]; if (off + k == lim - 1) lower &= mask; lower >>= rem; dst[k] = lower | upper; } if (off) memset(&dst[lim - off], 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_right); /** * __bitmap_shift_left - logical left shift of the bits in a bitmap * @dst : destination bitmap * @src : source bitmap * @shift : shift by this many bits * @nbits : bitmap size, in bits * * Shifting left (multiplying) means moving bits in the LS -> MS * direction. Zeros are fed into the vacated LS bit positions * and those MS bits shifted off the top are lost. */ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits) { int k; unsigned int lim = BITS_TO_LONGS(nbits); unsigned int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG; for (k = lim - off - 1; k >= 0; --k) { unsigned long upper, lower; /* * If shift is not word aligned, take upper rem bits of * word below and make them the bottom rem bits of result. */ if (rem && k > 0) lower = src[k - 1] >> (BITS_PER_LONG - rem); else lower = 0; upper = src[k] << rem; dst[k + off] = lower | upper; } if (off) memset(dst, 0, off*sizeof(unsigned long)); } EXPORT_SYMBOL(__bitmap_shift_left); /** * bitmap_cut() - remove bit region from bitmap and right shift remaining bits * @dst: destination bitmap, might overlap with src * @src: source bitmap * @first: start bit of region to be removed * @cut: number of bits to remove * @nbits: bitmap size, in bits * * Set the n-th bit of @dst iff the n-th bit of @src is set and * n is less than @first, or the m-th bit of @src is set for any * m such that @first <= n < nbits, and m = n + @cut. * * In pictures, example for a big-endian 32-bit architecture: * * The @src bitmap is:: * * 31 63 * | | * 10000000 11000001 11110010 00010101 10000000 11000001 01110010 00010101 * | | | | * 16 14 0 32 * * if @cut is 3, and @first is 14, bits 14-16 in @src are cut and @dst is:: * * 31 63 * | | * 10110000 00011000 00110010 00010101 00010000 00011000 00101110 01000010 * | | | * 14 (bit 17 0 32 * from @src) * * Note that @dst and @src might overlap partially or entirely. * * This is implemented in the obvious way, with a shift and carry * step for each moved bit. Optimisation is left as an exercise * for the compiler. */ void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits); unsigned long keep = 0, carry; int i; if (first % BITS_PER_LONG) { keep = src[first / BITS_PER_LONG] & (~0UL >> (BITS_PER_LONG - first % BITS_PER_LONG)); } memmove(dst, src, len * sizeof(*dst)); while (cut--) { for (i = first / BITS_PER_LONG; i < len; i++) { if (i < len - 1) carry = dst[i + 1] & 1UL; else carry = 0; dst[i] = (dst[i] >> 1) | (carry << (BITS_PER_LONG - 1)); } } dst[first / BITS_PER_LONG] &= ~0UL << (first % BITS_PER_LONG); dst[first / BITS_PER_LONG] |= keep; } EXPORT_SYMBOL(bitmap_cut); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_and); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] | bitmap2[k]; } EXPORT_SYMBOL(__bitmap_or); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(bits); for (k = 0; k < nr; k++) dst[k] = bitmap1[k] ^ bitmap2[k]; } EXPORT_SYMBOL(__bitmap_xor); bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; unsigned int lim = bits/BITS_PER_LONG; unsigned long result = 0; for (k = 0; k < lim; k++) result |= (dst[k] = bitmap1[k] & ~bitmap2[k]); if (bits % BITS_PER_LONG) result |= (dst[k] = bitmap1[k] & ~bitmap2[k] & BITMAP_LAST_WORD_MASK(bits)); return result != 0; } EXPORT_SYMBOL(__bitmap_andnot); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, const unsigned long *mask, unsigned int nbits) { unsigned int k; unsigned int nr = BITS_TO_LONGS(nbits); for (k = 0; k < nr; k++) dst[k] = (old[k] & ~mask[k]) | (new[k] & mask[k]); } EXPORT_SYMBOL(__bitmap_replace); bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & bitmap2[k]) return true; if (bits % BITS_PER_LONG) if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return true; return false; } EXPORT_SYMBOL(__bitmap_intersects); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; ++k) if (bitmap1[k] & ~bitmap2[k]) return false; if (bits % BITS_PER_LONG) if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits)) return false; return true; } EXPORT_SYMBOL(__bitmap_subset); #define BITMAP_WEIGHT(FETCH, bits) \ ({ \ unsigned int __bits = (bits), idx, w = 0; \ \ for (idx = 0; idx < __bits / BITS_PER_LONG; idx++) \ w += hweight_long(FETCH); \ \ if (__bits % BITS_PER_LONG) \ w += hweight_long((FETCH) & BITMAP_LAST_WORD_MASK(__bits)); \ \ w; \ }) unsigned int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { return BITMAP_WEIGHT(bitmap[idx], bits); } EXPORT_SYMBOL(__bitmap_weight); unsigned int __bitmap_weight_and(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_and); unsigned int __bitmap_weight_andnot(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { return BITMAP_WEIGHT(bitmap1[idx] & ~bitmap2[idx], bits); } EXPORT_SYMBOL(__bitmap_weight_andnot); void __bitmap_set(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_set >= 0) { *p |= mask_to_set; len -= bits_to_set; bits_to_set = BITS_PER_LONG; mask_to_set = ~0UL; p++; } if (len) { mask_to_set &= BITMAP_LAST_WORD_MASK(size); *p |= mask_to_set; } } EXPORT_SYMBOL(__bitmap_set); void __bitmap_clear(unsigned long *map, unsigned int start, int len) { unsigned long *p = map + BIT_WORD(start); const unsigned int size = start + len; int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG); unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start); while (len - bits_to_clear >= 0) { *p &= ~mask_to_clear; len -= bits_to_clear; bits_to_clear = BITS_PER_LONG; mask_to_clear = ~0UL; p++; } if (len) { mask_to_clear &= BITMAP_LAST_WORD_MASK(size); *p &= ~mask_to_clear; } } EXPORT_SYMBOL(__bitmap_clear); /** * bitmap_find_next_zero_area_off - find a contiguous aligned zero area * @map: The address to base the search on * @size: The bitmap size in bits * @start: The bitnumber to start searching at * @nr: The number of zeroed bits we're looking for * @align_mask: Alignment mask for zero area * @align_offset: Alignment offset for zero area. * * The @align_mask should be one less than a power of 2; the effect is that * the bit offset of all zero areas this function finds plus @align_offset * is multiple of that power of 2. */ unsigned long bitmap_find_next_zero_area_off(unsigned long *map, unsigned long size, unsigned long start, unsigned int nr, unsigned long align_mask, unsigned long align_offset) { unsigned long index, end, i; again: index = find_next_zero_bit(map, size, start); /* Align allocation */ index = __ALIGN_MASK(index + align_offset, align_mask) - align_offset; end = index + nr; if (end > size) return end; i = find_next_bit(map, end, index); if (i < end) { start = i + 1; goto again; } return index; } EXPORT_SYMBOL(bitmap_find_next_zero_area_off); /** * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap * @buf: pointer to a bitmap * @pos: a bit position in @buf (0 <= @pos < @nbits) * @nbits: number of valid bit positions in @buf * * Map the bit at position @pos in @buf (of length @nbits) to the * ordinal of which set bit it is. If it is not set or if @pos * is not a valid bit position, map to -1. * * If for example, just bits 4 through 7 are set in @buf, then @pos * values 4 through 7 will get mapped to 0 through 3, respectively, * and other @pos values will get mapped to -1. When @pos value 7 * gets mapped to (returns) @ord value 3 in this example, that means * that bit 7 is the 3rd (starting with 0th) set bit in @buf. * * The bit positions 0 through @bits are valid positions in @buf. */ static int bitmap_pos_to_ord(const unsigned long *buf, unsigned int pos, unsigned int nbits) { if (pos >= nbits || !test_bit(pos, buf)) return -1; return bitmap_weight(buf, pos); } /** * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap * @dst: remapped result * @src: subset to be remapped * @old: defines domain of map * @new: defines range of map * @nbits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * If either of the @old and @new bitmaps are empty, or if @src and * @dst point to the same location, then this routine copies @src * to @dst. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to @src, placing the result in * @dst, clearing any bits previously set in @dst. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @src comes into this routine * with bits 1, 5 and 7 set, then @dst should leave with bits 1, * 13 and 15 set. */ void bitmap_remap(unsigned long *dst, const unsigned long *src, const unsigned long *old, const unsigned long *new, unsigned int nbits) { unsigned int oldbit, w; if (dst == src) /* following doesn't handle inplace remaps */ return; bitmap_zero(dst, nbits); w = bitmap_weight(new, nbits); for_each_set_bit(oldbit, src, nbits) { int n = bitmap_pos_to_ord(old, oldbit, nbits); if (n < 0 || w == 0) set_bit(oldbit, dst); /* identity map */ else set_bit(find_nth_bit(new, nbits, n % w), dst); } } EXPORT_SYMBOL(bitmap_remap); /** * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit * @oldbit: bit position to be mapped * @old: defines domain of map * @new: defines range of map * @bits: number of bits in each of these bitmaps * * Let @old and @new define a mapping of bit positions, such that * whatever position is held by the n-th set bit in @old is mapped * to the n-th set bit in @new. In the more general case, allowing * for the possibility that the weight 'w' of @new is less than the * weight of @old, map the position of the n-th set bit in @old to * the position of the m-th set bit in @new, where m == n % w. * * The positions of unset bits in @old are mapped to themselves * (the identity map). * * Apply the above specified mapping to bit position @oldbit, returning * the new bit position. * * For example, lets say that @old has bits 4 through 7 set, and * @new has bits 12 through 15 set. This defines the mapping of bit * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other * bit positions unchanged. So if say @oldbit is 5, then this routine * returns 13. */ int bitmap_bitremap(int oldbit, const unsigned long *old, const unsigned long *new, int bits) { int w = bitmap_weight(new, bits); int n = bitmap_pos_to_ord(old, oldbit, bits); if (n < 0 || w == 0) return oldbit; else return find_nth_bit(new, bits, n % w); } EXPORT_SYMBOL(bitmap_bitremap); #ifdef CONFIG_NUMA /** * bitmap_onto - translate one bitmap relative to another * @dst: resulting translated bitmap * @orig: original untranslated bitmap * @relmap: bitmap relative to which translated * @bits: number of bits in each of these bitmaps * * Set the n-th bit of @dst iff there exists some m such that the * n-th bit of @relmap is set, the m-th bit of @orig is set, and * the n-th bit of @relmap is also the m-th _set_ bit of @relmap. * (If you understood the previous sentence the first time your * read it, you're overqualified for your current job.) * * In other words, @orig is mapped onto (surjectively) @dst, * using the map { <n, m> | the n-th bit of @relmap is the * m-th set bit of @relmap }. * * Any set bits in @orig above bit number W, where W is the * weight of (number of set bits in) @relmap are mapped nowhere. * In particular, if for all bits m set in @orig, m >= W, then * @dst will end up empty. In situations where the possibility * of such an empty result is not desired, one way to avoid it is * to use the bitmap_fold() operator, below, to first fold the * @orig bitmap over itself so that all its set bits x are in the * range 0 <= x < W. The bitmap_fold() operator does this by * setting the bit (m % W) in @dst, for each bit (m) set in @orig. * * Example [1] for bitmap_onto(): * Let's say @relmap has bits 30-39 set, and @orig has bits * 1, 3, 5, 7, 9 and 11 set. Then on return from this routine, * @dst will have bits 31, 33, 35, 37 and 39 set. * * When bit 0 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the first bit (if any) * that is turned on in @relmap. Since bit 0 was off in the * above example, we leave off that bit (bit 30) in @dst. * * When bit 1 is set in @orig (as in the above example), it * means turn on the bit in @dst corresponding to whatever * is the second bit that is turned on in @relmap. The second * bit in @relmap that was turned on in the above example was * bit 31, so we turned on bit 31 in @dst. * * Similarly, we turned on bits 33, 35, 37 and 39 in @dst, * because they were the 4th, 6th, 8th and 10th set bits * set in @relmap, and the 4th, 6th, 8th and 10th bits of * @orig (i.e. bits 3, 5, 7 and 9) were also set. * * When bit 11 is set in @orig, it means turn on the bit in * @dst corresponding to whatever is the twelfth bit that is * turned on in @relmap. In the above example, there were * only ten bits turned on in @relmap (30..39), so that bit * 11 was set in @orig had no affect on @dst. * * Example [2] for bitmap_fold() + bitmap_onto(): * Let's say @relmap has these ten bits set:: * * 40 41 42 43 45 48 53 61 74 95 * * (for the curious, that's 40 plus the first ten terms of the * Fibonacci sequence.) * * Further lets say we use the following code, invoking * bitmap_fold() then bitmap_onto, as suggested above to * avoid the possibility of an empty @dst result:: * * unsigned long *tmp; // a temporary bitmap's bits * * bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits); * bitmap_onto(dst, tmp, relmap, bits); * * Then this table shows what various values of @dst would be, for * various @orig's. I list the zero-based positions of each set bit. * The tmp column shows the intermediate result, as computed by * using bitmap_fold() to fold the @orig bitmap modulo ten * (the weight of @relmap): * * =============== ============== ================= * @orig tmp @dst * 0 0 40 * 1 1 41 * 9 9 95 * 10 0 40 [#f1]_ * 1 3 5 7 1 3 5 7 41 43 48 61 * 0 1 2 3 4 0 1 2 3 4 40 41 42 43 45 * 0 9 18 27 0 9 8 7 40 61 74 95 * 0 10 20 30 0 40 * 0 11 22 33 0 1 2 3 40 41 42 43 * 0 12 24 36 0 2 4 6 40 42 45 53 * 78 102 211 1 2 8 41 42 74 [#f1]_ * =============== ============== ================= * * .. [#f1] * * For these marked lines, if we hadn't first done bitmap_fold() * into tmp, then the @dst result would have been empty. * * If either of @orig or @relmap is empty (no set bits), then @dst * will be returned empty. * * If (as explained above) the only set bits in @orig are in positions * m where m >= W, (where W is the weight of @relmap) then @dst will * once again be returned empty. * * All bits in @dst not set by the above rule are cleared. */ void bitmap_onto(unsigned long *dst, const unsigned long *orig, const unsigned long *relmap, unsigned int bits) { unsigned int n, m; /* same meaning as in above comment */ if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, bits); /* * The following code is a more efficient, but less * obvious, equivalent to the loop: * for (m = 0; m < bitmap_weight(relmap, bits); m++) { * n = find_nth_bit(orig, bits, m); * if (test_bit(m, orig)) * set_bit(n, dst); * } */ m = 0; for_each_set_bit(n, relmap, bits) { /* m == bitmap_pos_to_ord(relmap, n, bits) */ if (test_bit(m, orig)) set_bit(n, dst); m++; } } /** * bitmap_fold - fold larger bitmap into smaller, modulo specified size * @dst: resulting smaller bitmap * @orig: original larger bitmap * @sz: specified size * @nbits: number of bits in each of these bitmaps * * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst. * Clear all other bits in @dst. See further the comment and * Example [2] for bitmap_onto() for why and how to use this. */ void bitmap_fold(unsigned long *dst, const unsigned long *orig, unsigned int sz, unsigned int nbits) { unsigned int oldbit; if (dst == orig) /* following doesn't handle inplace mappings */ return; bitmap_zero(dst, nbits); for_each_set_bit(oldbit, orig, nbits) set_bit(oldbit % sz, dst); } #endif /* CONFIG_NUMA */ unsigned long *bitmap_alloc(unsigned int nbits, gfp_t flags) { return kmalloc_array(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags); } EXPORT_SYMBOL(bitmap_alloc); unsigned long *bitmap_zalloc(unsigned int nbits, gfp_t flags) { return bitmap_alloc(nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL(bitmap_zalloc); unsigned long *bitmap_alloc_node(unsigned int nbits, gfp_t flags, int node) { return kmalloc_array_node(BITS_TO_LONGS(nbits), sizeof(unsigned long), flags, node); } EXPORT_SYMBOL(bitmap_alloc_node); unsigned long *bitmap_zalloc_node(unsigned int nbits, gfp_t flags, int node) { return bitmap_alloc_node(nbits, flags | __GFP_ZERO, node); } EXPORT_SYMBOL(bitmap_zalloc_node); void bitmap_free(const unsigned long *bitmap) { kfree(bitmap); } EXPORT_SYMBOL(bitmap_free); static void devm_bitmap_free(void *data) { unsigned long *bitmap = data; bitmap_free(bitmap); } unsigned long *devm_bitmap_alloc(struct device *dev, unsigned int nbits, gfp_t flags) { unsigned long *bitmap; int ret; bitmap = bitmap_alloc(nbits, flags); if (!bitmap) return NULL; ret = devm_add_action_or_reset(dev, devm_bitmap_free, bitmap); if (ret) return NULL; return bitmap; } EXPORT_SYMBOL_GPL(devm_bitmap_alloc); unsigned long *devm_bitmap_zalloc(struct device *dev, unsigned int nbits, gfp_t flags) { return devm_bitmap_alloc(dev, nbits, flags | __GFP_ZERO); } EXPORT_SYMBOL_GPL(devm_bitmap_zalloc); #if BITS_PER_LONG == 64 /** * bitmap_from_arr32 - copy the contents of u32 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u32 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr32(unsigned long *bitmap, const u32 *buf, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { bitmap[i/2] = (unsigned long) buf[i]; if (++i < halfwords) bitmap[i/2] |= ((unsigned long) buf[i]) << 32; } /* Clear tail bits in last word beyond nbits. */ if (nbits % BITS_PER_LONG) bitmap[(halfwords - 1) / 2] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr32); /** * bitmap_to_arr32 - copy the contents of bitmap to a u32 array of bits * @buf: array of u32 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr32(u32 *buf, const unsigned long *bitmap, unsigned int nbits) { unsigned int i, halfwords; halfwords = DIV_ROUND_UP(nbits, 32); for (i = 0; i < halfwords; i++) { buf[i] = (u32) (bitmap[i/2] & UINT_MAX); if (++i < halfwords) buf[i] = (u32) (bitmap[i/2] >> 32); } /* Clear tail bits in last element of array beyond nbits. */ if (nbits % BITS_PER_LONG) buf[halfwords - 1] &= (u32) (UINT_MAX >> ((-nbits) & 31)); } EXPORT_SYMBOL(bitmap_to_arr32); #endif #if BITS_PER_LONG == 32 /** * bitmap_from_arr64 - copy the contents of u64 array of bits to bitmap * @bitmap: array of unsigned longs, the destination bitmap * @buf: array of u64 (in host byte order), the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_from_arr64(unsigned long *bitmap, const u64 *buf, unsigned int nbits) { int n; for (n = nbits; n > 0; n -= 64) { u64 val = *buf++; *bitmap++ = val; if (n > 32) *bitmap++ = val >> 32; } /* * Clear tail bits in the last word beyond nbits. * * Negative index is OK because here we point to the word next * to the last word of the bitmap, except for nbits == 0, which * is tested implicitly. */ if (nbits % BITS_PER_LONG) bitmap[-1] &= BITMAP_LAST_WORD_MASK(nbits); } EXPORT_SYMBOL(bitmap_from_arr64); /** * bitmap_to_arr64 - copy the contents of bitmap to a u64 array of bits * @buf: array of u64 (in host byte order), the dest bitmap * @bitmap: array of unsigned longs, the source bitmap * @nbits: number of bits in @bitmap */ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits) { const unsigned long *end = bitmap + BITS_TO_LONGS(nbits); while (bitmap < end) { *buf = *bitmap++; if (bitmap < end) *buf |= (u64)(*bitmap++) << 32; buf++; } /* Clear tail bits in the last element of array beyond nbits. */ if (nbits % 64) buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0); } EXPORT_SYMBOL(bitmap_to_arr64); #endif |
| 49 49 40 384 173 19 40 20 40 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 | /* SPDX-License-Identifier: GPL-2.0 */ /* thread_info.h: common low-level thread information accessors * * Copyright (C) 2002 David Howells (dhowells@redhat.com) * - Incorporating suggestions made by Linus Torvalds */ #ifndef _LINUX_THREAD_INFO_H #define _LINUX_THREAD_INFO_H #include <linux/types.h> #include <linux/limits.h> #include <linux/bug.h> #include <linux/restart_block.h> #include <linux/errno.h> #ifdef CONFIG_THREAD_INFO_IN_TASK /* * For CONFIG_THREAD_INFO_IN_TASK kernels we need <asm/current.h> for the * definition of current, but for !CONFIG_THREAD_INFO_IN_TASK kernels, * including <asm/current.h> can cause a circular dependency on some platforms. */ #include <asm/current.h> #define current_thread_info() ((struct thread_info *)current) #endif #include <linux/bitops.h> /* * For per-arch arch_within_stack_frames() implementations, defined in * asm/thread_info.h. */ enum { BAD_STACK = -1, NOT_STACK = 0, GOOD_FRAME, GOOD_STACK, }; #ifdef CONFIG_GENERIC_ENTRY enum syscall_work_bit { SYSCALL_WORK_BIT_SECCOMP, SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT, SYSCALL_WORK_BIT_SYSCALL_TRACE, SYSCALL_WORK_BIT_SYSCALL_EMU, SYSCALL_WORK_BIT_SYSCALL_AUDIT, SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH, SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP, }; #define SYSCALL_WORK_SECCOMP BIT(SYSCALL_WORK_BIT_SECCOMP) #define SYSCALL_WORK_SYSCALL_TRACEPOINT BIT(SYSCALL_WORK_BIT_SYSCALL_TRACEPOINT) #define SYSCALL_WORK_SYSCALL_TRACE BIT(SYSCALL_WORK_BIT_SYSCALL_TRACE) #define SYSCALL_WORK_SYSCALL_EMU BIT(SYSCALL_WORK_BIT_SYSCALL_EMU) #define SYSCALL_WORK_SYSCALL_AUDIT BIT(SYSCALL_WORK_BIT_SYSCALL_AUDIT) #define SYSCALL_WORK_SYSCALL_USER_DISPATCH BIT(SYSCALL_WORK_BIT_SYSCALL_USER_DISPATCH) #define SYSCALL_WORK_SYSCALL_EXIT_TRAP BIT(SYSCALL_WORK_BIT_SYSCALL_EXIT_TRAP) #endif #include <asm/thread_info.h> #ifdef __KERNEL__ #ifndef arch_set_restart_data #define arch_set_restart_data(restart) do { } while (0) #endif static inline long set_restart_fn(struct restart_block *restart, long (*fn)(struct restart_block *)) { restart->fn = fn; arch_set_restart_data(restart); return -ERESTART_RESTARTBLOCK; } #ifndef THREAD_ALIGN #define THREAD_ALIGN THREAD_SIZE #endif #define THREADINFO_GFP (GFP_KERNEL_ACCOUNT | __GFP_ZERO) /* * flag set/clear/test wrappers * - pass TIF_xxxx constants to these functions */ static inline void set_ti_thread_flag(struct thread_info *ti, int flag) { set_bit(flag, (unsigned long *)&ti->flags); } static inline void clear_ti_thread_flag(struct thread_info *ti, int flag) { clear_bit(flag, (unsigned long *)&ti->flags); } static inline void update_ti_thread_flag(struct thread_info *ti, int flag, bool value) { if (value) set_ti_thread_flag(ti, flag); else clear_ti_thread_flag(ti, flag); } static inline int test_and_set_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_set_bit(flag, (unsigned long *)&ti->flags); } static inline int test_and_clear_ti_thread_flag(struct thread_info *ti, int flag) { return test_and_clear_bit(flag, (unsigned long *)&ti->flags); } static inline int test_ti_thread_flag(struct thread_info *ti, int flag) { return test_bit(flag, (unsigned long *)&ti->flags); } /* * This may be used in noinstr code, and needs to be __always_inline to prevent * inadvertent instrumentation. */ static __always_inline unsigned long read_ti_thread_flags(struct thread_info *ti) { return READ_ONCE(ti->flags); } #define set_thread_flag(flag) \ set_ti_thread_flag(current_thread_info(), flag) #define clear_thread_flag(flag) \ clear_ti_thread_flag(current_thread_info(), flag) #define update_thread_flag(flag, value) \ update_ti_thread_flag(current_thread_info(), flag, value) #define test_and_set_thread_flag(flag) \ test_and_set_ti_thread_flag(current_thread_info(), flag) #define test_and_clear_thread_flag(flag) \ test_and_clear_ti_thread_flag(current_thread_info(), flag) #define test_thread_flag(flag) \ test_ti_thread_flag(current_thread_info(), flag) #define read_thread_flags() \ read_ti_thread_flags(current_thread_info()) #define read_task_thread_flags(t) \ read_ti_thread_flags(task_thread_info(t)) #ifdef CONFIG_GENERIC_ENTRY #define set_syscall_work(fl) \ set_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define test_syscall_work(fl) \ test_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define clear_syscall_work(fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, ¤t_thread_info()->syscall_work) #define set_task_syscall_work(t, fl) \ set_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define test_task_syscall_work(t, fl) \ test_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #define clear_task_syscall_work(t, fl) \ clear_bit(SYSCALL_WORK_BIT_##fl, &task_thread_info(t)->syscall_work) #else /* CONFIG_GENERIC_ENTRY */ #define set_syscall_work(fl) \ set_ti_thread_flag(current_thread_info(), TIF_##fl) #define test_syscall_work(fl) \ test_ti_thread_flag(current_thread_info(), TIF_##fl) #define clear_syscall_work(fl) \ clear_ti_thread_flag(current_thread_info(), TIF_##fl) #define set_task_syscall_work(t, fl) \ set_ti_thread_flag(task_thread_info(t), TIF_##fl) #define test_task_syscall_work(t, fl) \ test_ti_thread_flag(task_thread_info(t), TIF_##fl) #define clear_task_syscall_work(t, fl) \ clear_ti_thread_flag(task_thread_info(t), TIF_##fl) #endif /* !CONFIG_GENERIC_ENTRY */ #ifdef _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H static __always_inline bool tif_need_resched(void) { return arch_test_bit(TIF_NEED_RESCHED, (unsigned long *)(¤t_thread_info()->flags)); } #else static __always_inline bool tif_need_resched(void) { return test_bit(TIF_NEED_RESCHED, (unsigned long *)(¤t_thread_info()->flags)); } #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ #ifndef CONFIG_HAVE_ARCH_WITHIN_STACK_FRAMES static inline int arch_within_stack_frames(const void * const stack, const void * const stackend, const void *obj, unsigned long len) { return 0; } #endif #ifdef CONFIG_HARDENED_USERCOPY extern void __check_object_size(const void *ptr, unsigned long n, bool to_user); static __always_inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { if (!__builtin_constant_p(n)) __check_object_size(ptr, n, to_user); } #else static inline void check_object_size(const void *ptr, unsigned long n, bool to_user) { } #endif /* CONFIG_HARDENED_USERCOPY */ extern void __compiletime_error("copy source size is too small") __bad_copy_from(void); extern void __compiletime_error("copy destination size is too small") __bad_copy_to(void); void __copy_overflow(int size, unsigned long count); static inline void copy_overflow(int size, unsigned long count) { if (IS_ENABLED(CONFIG_BUG)) __copy_overflow(size, count); } static __always_inline __must_check bool check_copy_size(const void *addr, size_t bytes, bool is_source) { int sz = __builtin_object_size(addr, 0); if (unlikely(sz >= 0 && sz < bytes)) { if (!__builtin_constant_p(bytes)) copy_overflow(sz, bytes); else if (is_source) __bad_copy_from(); else __bad_copy_to(); return false; } if (WARN_ON_ONCE(bytes > INT_MAX)) return false; check_object_size(addr, bytes, is_source); return true; } #ifndef arch_setup_new_exec static inline void arch_setup_new_exec(void) { } #endif void arch_task_cache_init(void); /* for CONFIG_SH */ void arch_release_task_struct(struct task_struct *tsk); int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src); #endif /* __KERNEL__ */ #endif /* _LINUX_THREAD_INFO_H */ |
| 27 27 27 2 27 38 38 8 26 27 27 27 27 27 8 27 3 3 3 20 27 27 27 27 8 26 27 4 27 35 27 27 37 27 27 38 38 11 35 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 38 11 27 5 38 38 38 38 38 38 13 5 13 26 19 19 38 38 38 38 38 38 38 38 38 38 38 27 38 27 27 27 27 2 2 2 27 38 38 2 2 2 2 2 2 1 2 2 2 2 2 90 90 90 90 90 90 90 36 36 36 36 90 90 90 90 90 90 1 1 90 90 90 68 25 90 90 90 2 2 2 2 2 2 2 2 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/kernel.h> #include <linux/errno.h> #include <linux/err.h> #include <linux/spinlock.h> #include <linux/mm.h> #include <linux/memremap.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/secretmem.h> #include <linux/sched/signal.h> #include <linux/rwsem.h> #include <linux/hugetlb.h> #include <linux/migrate.h> #include <linux/mm_inline.h> #include <linux/sched/mm.h> #include <linux/shmem_fs.h> #include <asm/mmu_context.h> #include <asm/tlbflush.h> #include "internal.h" struct follow_page_context { struct dev_pagemap *pgmap; unsigned int page_mask; }; static inline void sanity_check_pinned_pages(struct page **pages, unsigned long npages) { if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; /* * We only pin anonymous pages if they are exclusive. Once pinned, we * can no longer turn them possibly shared and PageAnonExclusive() will * stick around until the page is freed. * * We'd like to verify that our pinned anonymous pages are still mapped * exclusively. The issue with anon THP is that we don't know how * they are/were mapped when pinning them. However, for anon * THP we can assume that either the given page (PTE-mapped THP) or * the head page (PMD-mapped THP) should be PageAnonExclusive(). If * neither is the case, there is certainly something wrong. */ for (; npages; npages--, pages++) { struct page *page = *pages; struct folio *folio = page_folio(page); if (is_zero_page(page) || !folio_test_anon(folio)) continue; if (!folio_test_large(folio) || folio_test_hugetlb(folio)) VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page); else /* Either a PTE-mapped or a PMD-mapped THP. */ VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) && !PageAnonExclusive(page), page); } } /* * Return the folio with ref appropriately incremented, * or NULL if that failed. */ static inline struct folio *try_get_folio(struct page *page, int refs) { struct folio *folio; retry: folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) < 0)) return NULL; if (unlikely(!folio_ref_try_add_rcu(folio, refs))) return NULL; /* * At this point we have a stable reference to the folio; but it * could be that between calling page_folio() and the refcount * increment, the folio was split, in which case we'd end up * holding a reference on a folio that has nothing to do with the page * we were given anymore. * So now that the folio is stable, recheck that the page still * belongs to this folio. */ if (unlikely(page_folio(page) != folio)) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); goto retry; } return folio; } /** * try_grab_folio() - Attempt to get or pin a folio. * @page: pointer to page to be grabbed * @refs: the value to (effectively) add to the folio's refcount * @flags: gup flags: these are the FOLL_* flag values. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the folio's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) must be set, but not both at the * same time. (That's true throughout the get_user_pages*() and * pin_user_pages*() APIs.) Cases: * * FOLL_GET: folio's refcount will be incremented by @refs. * * FOLL_PIN on large folios: folio's refcount will be incremented by * @refs, and its pincount will be incremented by @refs. * * FOLL_PIN on single-page folios: folio's refcount will be incremented by * @refs * GUP_PIN_COUNTING_BIAS. * * Return: The folio containing @page (with refcount appropriately * incremented) for success, or NULL upon failure. If neither FOLL_GET * nor FOLL_PIN was set, that's considered failure, and furthermore, * a likely bug in the caller, so a warning is also emitted. */ struct folio *try_grab_folio(struct page *page, int refs, unsigned int flags) { struct folio *folio; if (WARN_ON_ONCE((flags & (FOLL_GET | FOLL_PIN)) == 0)) return NULL; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return NULL; if (flags & FOLL_GET) return try_get_folio(page, refs); /* FOLL_PIN is set */ /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return page_folio(page); folio = try_get_folio(page, refs); if (!folio) return NULL; /* * Can't do FOLL_LONGTERM + FOLL_PIN gup fast path if not in a * right zone, so fail and let the caller fall back to the slow * path. */ if (unlikely((flags & FOLL_LONGTERM) && !folio_is_longterm_pinnable(folio))) { if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); return NULL; } /* * When pinning a large folio, use an exact count to track it. * * However, be sure to *also* increment the normal folio * refcount field at least once, so that the folio really * is pinned. That's why the refcount from the earlier * try_get_folio() is left intact. */ if (folio_test_large(folio)) atomic_add(refs, &folio->_pincount); else folio_ref_add(folio, refs * (GUP_PIN_COUNTING_BIAS - 1)); /* * Adjust the pincount before re-checking the PTE for changes. * This is essentially a smp_mb() and is paired with a memory * barrier in folio_try_share_anon_rmap_*(). */ smp_mb__after_atomic(); node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, refs); return folio; } static void gup_put_folio(struct folio *folio, int refs, unsigned int flags) { if (flags & FOLL_PIN) { if (is_zero_folio(folio)) return; node_stat_mod_folio(folio, NR_FOLL_PIN_RELEASED, refs); if (folio_test_large(folio)) atomic_sub(refs, &folio->_pincount); else refs *= GUP_PIN_COUNTING_BIAS; } if (!put_devmap_managed_folio_refs(folio, refs)) folio_put_refs(folio, refs); } /** * try_grab_page() - elevate a page's refcount by a flag-dependent amount * @page: pointer to page to be grabbed * @flags: gup flags: these are the FOLL_* flag values. * * This might not do anything at all, depending on the flags argument. * * "grab" names in this file mean, "look at flags to decide whether to use * FOLL_PIN or FOLL_GET behavior, when incrementing the page's refcount. * * Either FOLL_PIN or FOLL_GET (or neither) may be set, but not both at the same * time. Cases: please see the try_grab_folio() documentation, with * "refs=1". * * Return: 0 for success, or if no action was required (if neither FOLL_PIN * nor FOLL_GET was set, nothing is done). A negative error code for failure: * * -ENOMEM FOLL_GET or FOLL_PIN was set, but the page could not * be grabbed. */ int __must_check try_grab_page(struct page *page, unsigned int flags) { struct folio *folio = page_folio(page); if (WARN_ON_ONCE(folio_ref_count(folio) <= 0)) return -ENOMEM; if (unlikely(!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page))) return -EREMOTEIO; if (flags & FOLL_GET) folio_ref_inc(folio); else if (flags & FOLL_PIN) { /* * Don't take a pin on the zero page - it's not going anywhere * and it is used in a *lot* of places. */ if (is_zero_page(page)) return 0; /* * Similar to try_grab_folio(): be sure to *also* * increment the normal page refcount field at least once, * so that the page really is pinned. */ if (folio_test_large(folio)) { folio_ref_add(folio, 1); atomic_add(1, &folio->_pincount); } else { folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } node_stat_mod_folio(folio, NR_FOLL_PIN_ACQUIRED, 1); } return 0; } /** * unpin_user_page() - release a dma-pinned page * @page: pointer to page to be released * * Pages that were pinned via pin_user_pages*() must be released via either * unpin_user_page(), or one of the unpin_user_pages*() routines. This is so * that such pages can be separately tracked and uniquely handled. In * particular, interactions with RDMA and filesystems need special handling. */ void unpin_user_page(struct page *page) { sanity_check_pinned_pages(&page, 1); gup_put_folio(page_folio(page), 1, FOLL_PIN); } EXPORT_SYMBOL(unpin_user_page); /** * folio_add_pin - Try to get an additional pin on a pinned folio * @folio: The folio to be pinned * * Get an additional pin on a folio we already have a pin on. Makes no change * if the folio is a zero_page. */ void folio_add_pin(struct folio *folio) { if (is_zero_folio(folio)) return; /* * Similar to try_grab_folio(): be sure to *also* increment the normal * page refcount field at least once, so that the page really is * pinned. */ if (folio_test_large(folio)) { WARN_ON_ONCE(atomic_read(&folio->_pincount) < 1); folio_ref_inc(folio); atomic_inc(&folio->_pincount); } else { WARN_ON_ONCE(folio_ref_count(folio) < GUP_PIN_COUNTING_BIAS); folio_ref_add(folio, GUP_PIN_COUNTING_BIAS); } } static inline struct folio *gup_folio_range_next(struct page *start, unsigned long npages, unsigned long i, unsigned int *ntails) { struct page *next = nth_page(start, i); struct folio *folio = page_folio(next); unsigned int nr = 1; if (folio_test_large(folio)) nr = min_t(unsigned int, npages - i, folio_nr_pages(folio) - folio_page_idx(folio, next)); *ntails = nr; return folio; } static inline struct folio *gup_folio_next(struct page **list, unsigned long npages, unsigned long i, unsigned int *ntails) { struct folio *folio = page_folio(list[i]); unsigned int nr; for (nr = i + 1; nr < npages; nr++) { if (page_folio(list[nr]) != folio) break; } *ntails = nr - i; return folio; } /** * unpin_user_pages_dirty_lock() - release and optionally dirty gup-pinned pages * @pages: array of pages to be maybe marked dirty, and definitely released. * @npages: number of pages in the @pages array. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page" refers to a page that has had one of the get_user_pages() * variants called on that page. * * For each page in the @pages array, make that page (or its head page, if a * compound page) dirty, if @make_dirty is true, and if the page was previously * listed as clean. In any case, releases all pages using unpin_user_page(), * possibly via unpin_user_pages(), for the non-dirty case. * * Please see the unpin_user_page() documentation for details. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_pages_dirty_lock(struct page **pages, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; if (!make_dirty) { unpin_user_pages(pages, npages); return; } sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); /* * Checking PageDirty at this point may race with * clear_page_dirty_for_io(), but that's OK. Two key * cases: * * 1) This code sees the page as already dirty, so it * skips the call to set_page_dirty(). That could happen * because clear_page_dirty_for_io() called * page_mkclean(), followed by set_page_dirty(). * However, now the page is going to get written back, * which meets the original intention of setting it * dirty, so all is well: clear_page_dirty_for_io() goes * on to call TestClearPageDirty(), and write the page * back. * * 2) This code sees the page as clean, so it calls * set_page_dirty(). The page stays dirty, despite being * written back, so it gets written back again in the * next writeback cycle. This is harmless. */ if (!folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages_dirty_lock); /** * unpin_user_page_range_dirty_lock() - release and optionally dirty * gup-pinned page range * * @page: the starting page of a range maybe marked dirty, and definitely released. * @npages: number of consecutive pages to release. * @make_dirty: whether to mark the pages dirty * * "gup-pinned page range" refers to a range of pages that has had one of the * pin_user_pages() variants called on that page. * * For the page ranges defined by [page .. page+npages], make that range (or * its head pages, if a compound page) dirty, if @make_dirty is true, and if the * page range was previously listed as clean. * * set_page_dirty_lock() is used internally. If instead, set_page_dirty() is * required, then the caller should a) verify that this is really correct, * because _lock() is usually required, and b) hand code it: * set_page_dirty_lock(), unpin_user_page(). * */ void unpin_user_page_range_dirty_lock(struct page *page, unsigned long npages, bool make_dirty) { unsigned long i; struct folio *folio; unsigned int nr; for (i = 0; i < npages; i += nr) { folio = gup_folio_range_next(page, npages, i, &nr); if (make_dirty && !folio_test_dirty(folio)) { folio_lock(folio); folio_mark_dirty(folio); folio_unlock(folio); } gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_page_range_dirty_lock); static void gup_fast_unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * Don't perform any sanity checks because we might have raced with * fork() and some anonymous pages might now actually be shared -- * which is why we're unpinning after all. */ for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } /** * unpin_user_pages() - release an array of gup-pinned pages. * @pages: array of pages to be marked dirty and released. * @npages: number of pages in the @pages array. * * For each page in the @pages array, release the page using unpin_user_page(). * * Please see the unpin_user_page() documentation for details. */ void unpin_user_pages(struct page **pages, unsigned long npages) { unsigned long i; struct folio *folio; unsigned int nr; /* * If this WARN_ON() fires, then the system *might* be leaking pages (by * leaving them pinned), but probably not. More likely, gup/pup returned * a hard -ERRNO error to the caller, who erroneously passed it here. */ if (WARN_ON(IS_ERR_VALUE(npages))) return; sanity_check_pinned_pages(pages, npages); for (i = 0; i < npages; i += nr) { folio = gup_folio_next(pages, npages, i, &nr); gup_put_folio(folio, nr, FOLL_PIN); } } EXPORT_SYMBOL(unpin_user_pages); /* * Set the MMF_HAS_PINNED if not set yet; after set it'll be there for the mm's * lifecycle. Avoid setting the bit unless necessary, or it might cause write * cache bouncing on large SMP machines for concurrent pinned gups. */ static inline void mm_set_has_pinned_flag(unsigned long *mm_flags) { if (!test_bit(MMF_HAS_PINNED, mm_flags)) set_bit(MMF_HAS_PINNED, mm_flags); } #ifdef CONFIG_MMU #if defined(CONFIG_ARCH_HAS_HUGEPD) || defined(CONFIG_HAVE_GUP_FAST) static int record_subpages(struct page *page, unsigned long sz, unsigned long addr, unsigned long end, struct page **pages) { struct page *start_page; int nr; start_page = nth_page(page, (addr & (sz - 1)) >> PAGE_SHIFT); for (nr = 0; addr != end; nr++, addr += PAGE_SIZE) pages[nr] = nth_page(start_page, nr); return nr; } #endif /* CONFIG_ARCH_HAS_HUGEPD || CONFIG_HAVE_GUP_FAST */ #ifdef CONFIG_ARCH_HAS_HUGEPD static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, unsigned long sz) { unsigned long __boundary = (addr + sz) & ~(sz-1); return (__boundary - 1 < end - 1) ? __boundary : end; } /* * Returns 1 if succeeded, 0 if failed, -EMLINK if unshare needed. * * NOTE: for the same entry, gup-fast and gup-slow can return different * results (0 v.s. -EMLINK) depending on whether vma is available. This is * the expected behavior, where we simply want gup-fast to fallback to * gup-slow to take the vma reference first. */ static int gup_hugepte(struct vm_area_struct *vma, pte_t *ptep, unsigned long sz, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long pte_end; struct page *page; struct folio *folio; pte_t pte; int refs; pte_end = (addr + sz) & ~(sz-1); if (pte_end < end) end = pte_end; pte = huge_ptep_get(ptep); if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; /* hugepages are never "special" */ VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); refs = record_subpages(page, sz, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, refs, flags); return 0; } if (!pte_write(pte) && gup_must_unshare(vma, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return -EMLINK; } *nr += refs; folio_set_referenced(folio); return 1; } /* * NOTE: currently GUP for a hugepd is only possible on hugetlbfs file * systems on Power, which does not have issue with folio writeback against * GUP updates. When hugepd will be extended to support non-hugetlbfs or * even anonymous memory, we need to do extra check as what we do with most * of the other folios. See writable_file_mapping_allowed() and * gup_fast_folio_allowed() for more information. */ static int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { pte_t *ptep; unsigned long sz = 1UL << hugepd_shift(hugepd); unsigned long next; int ret; ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); ret = gup_hugepte(vma, ptep, sz, addr, end, flags, pages, nr); if (ret != 1) return ret; } while (ptep++, addr = next, addr != end); return 1; } static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned int flags, struct follow_page_context *ctx) { struct page *page; struct hstate *h; spinlock_t *ptl; int nr = 0, ret; pte_t *ptep; /* Only hugetlb supports hugepd */ if (WARN_ON_ONCE(!is_vm_hugetlb_page(vma))) return ERR_PTR(-EFAULT); h = hstate_vma(vma); ptep = hugepte_offset(hugepd, addr, pdshift); ptl = huge_pte_lock(h, vma->vm_mm, ptep); ret = gup_hugepd(vma, hugepd, addr, pdshift, addr + PAGE_SIZE, flags, &page, &nr); spin_unlock(ptl); if (ret == 1) { /* GUP succeeded */ WARN_ON_ONCE(nr != 1); ctx->page_mask = (1U << huge_page_order(h)) - 1; return page; } /* ret can be either 0 (translates to NULL) or negative */ return ERR_PTR(ret); } #else /* CONFIG_ARCH_HAS_HUGEPD */ static inline int gup_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } static struct page *follow_hugepd(struct vm_area_struct *vma, hugepd_t hugepd, unsigned long addr, unsigned int pdshift, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_ARCH_HAS_HUGEPD */ static struct page *no_page_table(struct vm_area_struct *vma, unsigned int flags, unsigned long address) { if (!(flags & FOLL_DUMP)) return NULL; /* * When core dumping, we don't want to allocate unnecessary pages or * page tables. Return error instead of NULL to skip handle_mm_fault, * then get_dump_page() will return NULL to leave a hole in the dump. * But we can only make this optimization where a hole would surely * be zero-filled if handle_mm_fault() actually did handle it. */ if (is_vm_hugetlb_page(vma)) { struct hstate *h = hstate_vma(vma); if (!hugetlbfs_pagecache_present(h, vma, address)) return ERR_PTR(-EFAULT); } else if ((vma_is_anonymous(vma) || !vma->vm_ops->fault)) { return ERR_PTR(-EFAULT); } return NULL; } #ifdef CONFIG_PGTABLE_HAS_HUGE_LEAVES static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; struct page *page; pud_t pud = *pudp; unsigned long pfn = pud_pfn(pud); int ret; assert_spin_locked(pud_lockptr(mm, pudp)); if ((flags & FOLL_WRITE) && !pud_write(pud)) return NULL; if (!pud_present(pud)) return NULL; pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT; if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) && pud_devmap(pud)) { /* * device mapped pages can only be returned if the caller * will manage the page reference count. * * At least one of FOLL_GET | FOLL_PIN must be set, so * assert that here: */ if (!(flags & (FOLL_GET | FOLL_PIN))) return ERR_PTR(-EEXIST); if (flags & FOLL_TOUCH) touch_pud(vma, addr, pudp, flags & FOLL_WRITE); ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap); if (!ctx->pgmap) return ERR_PTR(-EFAULT); } page = pfn_to_page(pfn); if (!pud_devmap(pud) && !pud_write(pud) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); ret = try_grab_page(page, flags); if (ret) page = ERR_PTR(ret); else ctx->page_mask = HPAGE_PUD_NR - 1; return page; } /* FOLL_FORCE can write to even unwritable PMDs in COW mappings. */ static inline bool can_follow_write_pmd(pmd_t pmd, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pmd is writable, we can write to the page. */ if (pmd_write(pmd)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (vma_soft_dirty_enabled(vma) && !pmd_soft_dirty(pmd)) return false; return !userfaultfd_huge_pmd_wp(vma, pmd); } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { struct mm_struct *mm = vma->vm_mm; pmd_t pmdval = *pmd; struct page *page; int ret; assert_spin_locked(pmd_lockptr(mm, pmd)); page = pmd_page(pmdval); if ((flags & FOLL_WRITE) && !can_follow_write_pmd(pmdval, page, vma, flags)) return NULL; /* Avoid dumping huge zero page */ if ((flags & FOLL_DUMP) && is_huge_zero_pmd(pmdval)) return ERR_PTR(-EFAULT); if (pmd_protnone(*pmd) && !gup_can_follow_protnone(vma, flags)) return NULL; if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page)) return ERR_PTR(-EMLINK); VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); ret = try_grab_page(page, flags); if (ret) return ERR_PTR(ret); #ifdef CONFIG_TRANSPARENT_HUGEPAGE if (pmd_trans_huge(pmdval) && (flags & FOLL_TOUCH)) touch_pmd(vma, addr, pmd, flags & FOLL_WRITE); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ page += (addr & ~HPAGE_PMD_MASK) >> PAGE_SHIFT; ctx->page_mask = HPAGE_PMD_NR - 1; return page; } #else /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static struct page *follow_huge_pud(struct vm_area_struct *vma, unsigned long addr, pud_t *pudp, int flags, struct follow_page_context *ctx) { return NULL; } static struct page *follow_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, unsigned int flags, struct follow_page_context *ctx) { return NULL; } #endif /* CONFIG_PGTABLE_HAS_HUGE_LEAVES */ static int follow_pfn_pte(struct vm_area_struct *vma, unsigned long address, pte_t *pte, unsigned int flags) { if (flags & FOLL_TOUCH) { pte_t orig_entry = ptep_get(pte); pte_t entry = orig_entry; if (flags & FOLL_WRITE) entry = pte_mkdirty(entry); entry = pte_mkyoung(entry); if (!pte_same(orig_entry, entry)) { set_pte_at(vma->vm_mm, address, pte, entry); update_mmu_cache(vma, address, pte); } } /* Proper page table entry exists, but no corresponding struct page */ return -EEXIST; } /* FOLL_FORCE can write to even unwritable PTEs in COW mappings. */ static inline bool can_follow_write_pte(pte_t pte, struct page *page, struct vm_area_struct *vma, unsigned int flags) { /* If the pte is writable, we can write to the page. */ if (pte_write(pte)) return true; /* Maybe FOLL_FORCE is set to override it? */ if (!(flags & FOLL_FORCE)) return false; /* But FOLL_FORCE has no effect on shared mappings */ if (vma->vm_flags & (VM_MAYSHARE | VM_SHARED)) return false; /* ... or read-only private ones */ if (!(vma->vm_flags & VM_MAYWRITE)) return false; /* ... or already writable ones that just need to take a write fault */ if (vma->vm_flags & VM_WRITE) return false; /* * See can_change_pte_writable(): we broke COW and could map the page * writable if we have an exclusive anonymous page ... */ if (!page || !PageAnon(page) || !PageAnonExclusive(page)) return false; /* ... and a write-fault isn't required for other reasons. */ if (vma_soft_dirty_enabled(vma) && !pte_soft_dirty(pte)) return false; return !userfaultfd_pte_wp(vma, pte); } static struct page *follow_page_pte(struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags, struct dev_pagemap **pgmap) { struct mm_struct *mm = vma->vm_mm; struct page *page; spinlock_t *ptl; pte_t *ptep, pte; int ret; /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return ERR_PTR(-EINVAL); ptep = pte_offset_map_lock(mm, pmd, address, &ptl); if (!ptep) return no_page_table(vma, flags, address); pte = ptep_get(ptep); if (!pte_present(pte)) goto no_page; if (pte_protnone(pte) && !gup_can_follow_protnone(vma, flags)) goto no_page; page = vm_normal_page(vma, address, pte); /* * We only care about anon pages in can_follow_write_pte() and don't * have to worry about pte_devmap() because they are never anon. */ if ((flags & FOLL_WRITE) && !can_follow_write_pte(pte, page, vma, flags)) { page = NULL; goto out; } if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) { /* * Only return device mapping pages in the FOLL_GET or FOLL_PIN * case since they are only valid while holding the pgmap * reference. */ *pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap); if (*pgmap) page = pte_page(pte); else goto no_page; } else if (unlikely(!page)) { if (flags & FOLL_DUMP) { /* Avoid special (like zero) pages in core dumps */ page = ERR_PTR(-EFAULT); goto out; } if (is_zero_pfn(pte_pfn(pte))) { page = pte_page(pte); } else { ret = follow_pfn_pte(vma, address, ptep, flags); page = ERR_PTR(ret); goto out; } } if (!pte_write(pte) && gup_must_unshare(vma, flags, page)) { page = ERR_PTR(-EMLINK); goto out; } VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) && !PageAnonExclusive(page), page); /* try_grab_page() does nothing unless FOLL_GET or FOLL_PIN is set. */ ret = try_grab_page(page, flags); if (unlikely(ret)) { page = ERR_PTR(ret); goto out; } /* * We need to make the page accessible if and only if we are going * to access its content (the FOLL_PIN case). Please see * Documentation/core-api/pin_user_pages.rst for details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { unpin_user_page(page); page = ERR_PTR(ret); goto out; } } if (flags & FOLL_TOUCH) { if ((flags & FOLL_WRITE) && !pte_dirty(pte) && !PageDirty(page)) set_page_dirty(page); /* * pte_mkyoung() would be more correct here, but atomic care * is needed to avoid losing the dirty bit: it is easier to use * mark_page_accessed(). */ mark_page_accessed(page); } out: pte_unmap_unlock(ptep, ptl); return page; no_page: pte_unmap_unlock(ptep, ptl); if (!pte_none(pte)) return NULL; return no_page_table(vma, flags, address); } static struct page *follow_pmd_mask(struct vm_area_struct *vma, unsigned long address, pud_t *pudp, unsigned int flags, struct follow_page_context *ctx) { pmd_t *pmd, pmdval; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pmd = pmd_offset(pudp, address); pmdval = pmdp_get_lockless(pmd); if (pmd_none(pmdval)) return no_page_table(vma, flags, address); if (!pmd_present(pmdval)) return no_page_table(vma, flags, address); if (unlikely(is_hugepd(__hugepd(pmd_val(pmdval))))) return follow_hugepd(vma, __hugepd(pmd_val(pmdval)), address, PMD_SHIFT, flags, ctx); if (pmd_devmap(pmdval)) { ptl = pmd_lock(mm, pmd); page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (likely(!pmd_leaf(pmdval))) return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); if (pmd_protnone(pmdval) && !gup_can_follow_protnone(vma, flags)) return no_page_table(vma, flags, address); ptl = pmd_lock(mm, pmd); pmdval = *pmd; if (unlikely(!pmd_present(pmdval))) { spin_unlock(ptl); return no_page_table(vma, flags, address); } if (unlikely(!pmd_leaf(pmdval))) { spin_unlock(ptl); return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } if (pmd_trans_huge(pmdval) && (flags & FOLL_SPLIT_PMD)) { spin_unlock(ptl); split_huge_pmd(vma, pmd, address); /* If pmd was left empty, stuff a page table in there quickly */ return pte_alloc(mm, pmd) ? ERR_PTR(-ENOMEM) : follow_page_pte(vma, address, pmd, flags, &ctx->pgmap); } page = follow_huge_pmd(vma, address, pmd, flags, ctx); spin_unlock(ptl); return page; } static struct page *follow_pud_mask(struct vm_area_struct *vma, unsigned long address, p4d_t *p4dp, unsigned int flags, struct follow_page_context *ctx) { pud_t *pudp, pud; spinlock_t *ptl; struct page *page; struct mm_struct *mm = vma->vm_mm; pudp = pud_offset(p4dp, address); pud = READ_ONCE(*pudp); if (!pud_present(pud)) return no_page_table(vma, flags, address); if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) return follow_hugepd(vma, __hugepd(pud_val(pud)), address, PUD_SHIFT, flags, ctx); if (pud_leaf(pud)) { ptl = pud_lock(mm, pudp); page = follow_huge_pud(vma, address, pudp, flags, ctx); spin_unlock(ptl); if (page) return page; return no_page_table(vma, flags, address); } if (unlikely(pud_bad(pud))) return no_page_table(vma, flags, address); return follow_pmd_mask(vma, address, pudp, flags, ctx); } static struct page *follow_p4d_mask(struct vm_area_struct *vma, unsigned long address, pgd_t *pgdp, unsigned int flags, struct follow_page_context *ctx) { p4d_t *p4dp, p4d; p4dp = p4d_offset(pgdp, address); p4d = READ_ONCE(*p4dp); BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) return follow_hugepd(vma, __hugepd(p4d_val(p4d)), address, P4D_SHIFT, flags, ctx); if (!p4d_present(p4d) || p4d_bad(p4d)) return no_page_table(vma, flags, address); return follow_pud_mask(vma, address, p4dp, flags, ctx); } /** * follow_page_mask - look up a page descriptor from a user-virtual address * @vma: vm_area_struct mapping @address * @address: virtual address to look up * @flags: flags modifying lookup behaviour * @ctx: contains dev_pagemap for %ZONE_DEVICE memory pinning and a * pointer to output page_mask * * @flags can have FOLL_ flags set, defined in <linux/mm.h> * * When getting pages from ZONE_DEVICE memory, the @ctx->pgmap caches * the device's dev_pagemap metadata to avoid repeating expensive lookups. * * When getting an anonymous page and the caller has to trigger unsharing * of a shared anonymous page first, -EMLINK is returned. The caller should * trigger a fault with FAULT_FLAG_UNSHARE set. Note that unsharing is only * relevant with FOLL_PIN and !FOLL_WRITE. * * On output, the @ctx->page_mask is set according to the size of the page. * * Return: the mapped (struct page *), %NULL if no mapping exists, or * an error pointer if there is a mapping to something not represented * by a page descriptor (see also vm_normal_page()). */ static struct page *follow_page_mask(struct vm_area_struct *vma, unsigned long address, unsigned int flags, struct follow_page_context *ctx) { pgd_t *pgd; struct mm_struct *mm = vma->vm_mm; struct page *page; vma_pgtable_walk_begin(vma); ctx->page_mask = 0; pgd = pgd_offset(mm, address); if (unlikely(is_hugepd(__hugepd(pgd_val(*pgd))))) page = follow_hugepd(vma, __hugepd(pgd_val(*pgd)), address, PGDIR_SHIFT, flags, ctx); else if (pgd_none(*pgd) || unlikely(pgd_bad(*pgd))) page = no_page_table(vma, flags, address); else page = follow_p4d_mask(vma, address, pgd, flags, ctx); vma_pgtable_walk_end(vma); return page; } struct page *follow_page(struct vm_area_struct *vma, unsigned long address, unsigned int foll_flags) { struct follow_page_context ctx = { NULL }; struct page *page; if (vma_is_secretmem(vma)) return NULL; if (WARN_ON_ONCE(foll_flags & FOLL_PIN)) return NULL; /* * We never set FOLL_HONOR_NUMA_FAULT because callers don't expect * to fail on PROT_NONE-mapped pages. */ page = follow_page_mask(vma, address, foll_flags, &ctx); if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return page; } static int get_gate_page(struct mm_struct *mm, unsigned long address, unsigned int gup_flags, struct vm_area_struct **vma, struct page **page) { pgd_t *pgd; p4d_t *p4d; pud_t *pud; pmd_t *pmd; pte_t *pte; pte_t entry; int ret = -EFAULT; /* user gate pages are read-only */ if (gup_flags & FOLL_WRITE) return -EFAULT; if (address > TASK_SIZE) pgd = pgd_offset_k(address); else pgd = pgd_offset_gate(mm, address); if (pgd_none(*pgd)) return -EFAULT; p4d = p4d_offset(pgd, address); if (p4d_none(*p4d)) return -EFAULT; pud = pud_offset(p4d, address); if (pud_none(*pud)) return -EFAULT; pmd = pmd_offset(pud, address); if (!pmd_present(*pmd)) return -EFAULT; pte = pte_offset_map(pmd, address); if (!pte) return -EFAULT; entry = ptep_get(pte); if (pte_none(entry)) goto unmap; *vma = get_gate_vma(mm); if (!page) goto out; *page = vm_normal_page(*vma, address, entry); if (!*page) { if ((gup_flags & FOLL_DUMP) || !is_zero_pfn(pte_pfn(entry))) goto unmap; *page = pte_page(entry); } ret = try_grab_page(*page, gup_flags); if (unlikely(ret)) goto unmap; out: ret = 0; unmap: pte_unmap(pte); return ret; } /* * mmap_lock must be held on entry. If @flags has FOLL_UNLOCKABLE but not * FOLL_NOWAIT, the mmap_lock may be released. If it is, *@locked will be set * to 0 and -EBUSY returned. */ static int faultin_page(struct vm_area_struct *vma, unsigned long address, unsigned int *flags, bool unshare, int *locked) { unsigned int fault_flags = 0; vm_fault_t ret; if (*flags & FOLL_NOFAULT) return -EFAULT; if (*flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (*flags & FOLL_REMOTE) fault_flags |= FAULT_FLAG_REMOTE; if (*flags & FOLL_UNLOCKABLE) { fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; /* * FAULT_FLAG_INTERRUPTIBLE is opt-in. GUP callers must set * FOLL_INTERRUPTIBLE to enable FAULT_FLAG_INTERRUPTIBLE. * That's because some callers may not be prepared to * handle early exits caused by non-fatal signals. */ if (*flags & FOLL_INTERRUPTIBLE) fault_flags |= FAULT_FLAG_INTERRUPTIBLE; } if (*flags & FOLL_NOWAIT) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_RETRY_NOWAIT; if (*flags & FOLL_TRIED) { /* * Note: FAULT_FLAG_ALLOW_RETRY and FAULT_FLAG_TRIED * can co-exist */ fault_flags |= FAULT_FLAG_TRIED; } if (unshare) { fault_flags |= FAULT_FLAG_UNSHARE; /* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */ VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE); } ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * With FAULT_FLAG_RETRY_NOWAIT we'll never release the * mmap lock in the page fault handler. Sanity check this. */ WARN_ON_ONCE(fault_flags & FAULT_FLAG_RETRY_NOWAIT); *locked = 0; /* * We should do the same as VM_FAULT_RETRY, but let's not * return -EBUSY since that's not reflecting the reality of * what has happened - we've just fully completed a page * fault, with the mmap lock released. Use -EAGAIN to show * that we want to take the mmap lock _again_. */ return -EAGAIN; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, *flags); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { if (!(fault_flags & FAULT_FLAG_RETRY_NOWAIT)) *locked = 0; return -EBUSY; } return 0; } /* * Writing to file-backed mappings which require folio dirty tracking using GUP * is a fundamentally broken operation, as kernel write access to GUP mappings * do not adhere to the semantics expected by a file system. * * Consider the following scenario:- * * 1. A folio is written to via GUP which write-faults the memory, notifying * the file system and dirtying the folio. * 2. Later, writeback is triggered, resulting in the folio being cleaned and * the PTE being marked read-only. * 3. The GUP caller writes to the folio, as it is mapped read/write via the * direct mapping. * 4. The GUP caller, now done with the page, unpins it and sets it dirty * (though it does not have to). * * This results in both data being written to a folio without writenotify, and * the folio being dirtied unexpectedly (if the caller decides to do so). */ static bool writable_file_mapping_allowed(struct vm_area_struct *vma, unsigned long gup_flags) { /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the case we disallow. */ if ((gup_flags & (FOLL_PIN | FOLL_LONGTERM)) != (FOLL_PIN | FOLL_LONGTERM)) return true; /* * If the VMA does not require dirty tracking then no problematic write * can occur either. */ return !vma_needs_dirty_tracking(vma); } static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) { vm_flags_t vm_flags = vma->vm_flags; int write = (gup_flags & FOLL_WRITE); int foreign = (gup_flags & FOLL_REMOTE); bool vma_anon = vma_is_anonymous(vma); if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; if ((gup_flags & FOLL_ANON) && !vma_anon) return -EFAULT; if ((gup_flags & FOLL_LONGTERM) && vma_is_fsdax(vma)) return -EOPNOTSUPP; if (vma_is_secretmem(vma)) return -EFAULT; if (write) { if (!vma_anon && !writable_file_mapping_allowed(vma, gup_flags)) return -EFAULT; if (!(vm_flags & VM_WRITE) || (vm_flags & VM_SHADOW_STACK)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* hugetlb does not support FOLL_FORCE|FOLL_WRITE. */ if (is_vm_hugetlb_page(vma)) return -EFAULT; /* * We used to let the write,force case do COW in a * VM_MAYWRITE VM_SHARED !VM_WRITE vma, so ptrace could * set a breakpoint in a read-only mapping of an * executable, without corrupting the file (yet only * when that file had been opened for writing!). * Anon pages in shared mappings are surprising: now * just reject it. */ if (!is_cow_mapping(vm_flags)) return -EFAULT; } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) return -EFAULT; /* * Is there actually any vma we can reach here which does not * have VM_MAYREAD set? */ if (!(vm_flags & VM_MAYREAD)) return -EFAULT; } /* * gups are always data accesses, not instruction * fetches, so execute=false here */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return -EFAULT; return 0; } /* * This is "vma_lookup()", but with a warning if we would have * historically expanded the stack in the GUP code. */ static struct vm_area_struct *gup_vma_lookup(struct mm_struct *mm, unsigned long addr) { #ifdef CONFIG_STACK_GROWSUP return vma_lookup(mm, addr); #else static volatile unsigned long next_warn; struct vm_area_struct *vma; unsigned long now, next; vma = find_vma(mm, addr); if (!vma || (addr >= vma->vm_start)) return vma; /* Only warn for half-way relevant accesses */ if (!(vma->vm_flags & VM_GROWSDOWN)) return NULL; if (vma->vm_start - addr > 65536) return NULL; /* Let's not warn more than once an hour.. */ now = jiffies; next = next_warn; if (next && time_before(now, next)) return NULL; next_warn = now + 60*60*HZ; /* Let people know things may have changed. */ pr_warn("GUP no longer grows the stack in %s (%d): %lx-%lx (%lx)\n", current->comm, task_pid_nr(current), vma->vm_start, vma->vm_end, addr); dump_stack(); return NULL; #endif } /** * __get_user_pages() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: whether we're still with the mmap_lock held * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * -- 0 return value is possible when the fault would need to be retried. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held. It may be released. See below. * * __get_user_pages walks a process's page tables and takes a reference to * each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * __get_user_pages returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If @gup_flags & FOLL_WRITE == 0, the page must not be written to. If * the page is written to, set_page_dirty (or set_page_dirty_lock, as * appropriate) must be called after the page is finished with, and * before put_page is called. * * If FOLL_UNLOCKABLE is set without FOLL_NOWAIT then the mmap_lock may * be released. If this happens *@locked will be set to 0 on return. * * A caller using such a combination of @gup_flags must therefore hold the * mmap_lock for reading only, and recognize when it's been released. Otherwise, * it must be held for either reading or writing and will not be released. * * In most cases, get_user_pages or get_user_pages_fast should be used * instead of __get_user_pages. __get_user_pages should be used only if * you need some special @gup_flags. */ static long __get_user_pages(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { long ret = 0, i = 0; struct vm_area_struct *vma = NULL; struct follow_page_context ctx = { NULL }; if (!nr_pages) return 0; start = untagged_addr_remote(mm, start); VM_BUG_ON(!!pages != !!(gup_flags & (FOLL_GET | FOLL_PIN))); do { struct page *page; unsigned int foll_flags = gup_flags; unsigned int page_increm; /* first iteration or cross vma bound */ if (!vma || start >= vma->vm_end) { /* * MADV_POPULATE_(READ|WRITE) wants to handle VMA * lookups+error reporting differently. */ if (gup_flags & FOLL_MADV_POPULATE) { vma = vma_lookup(mm, start); if (!vma) { ret = -ENOMEM; goto out; } if (check_vma_flags(vma, gup_flags)) { ret = -EINVAL; goto out; } goto retry; } vma = gup_vma_lookup(mm, start); if (!vma && in_gate_area(mm, start)) { ret = get_gate_page(mm, start & PAGE_MASK, gup_flags, &vma, pages ? &page : NULL); if (ret) goto out; ctx.page_mask = 0; goto next_page; } if (!vma) { ret = -EFAULT; goto out; } ret = check_vma_flags(vma, gup_flags); if (ret) goto out; } retry: /* * If we have a pending SIGKILL, don't keep faulting pages and * potentially allocating memory. */ if (fatal_signal_pending(current)) { ret = -EINTR; goto out; } cond_resched(); page = follow_page_mask(vma, start, foll_flags, &ctx); if (!page || PTR_ERR(page) == -EMLINK) { ret = faultin_page(vma, start, &foll_flags, PTR_ERR(page) == -EMLINK, locked); switch (ret) { case 0: goto retry; case -EBUSY: case -EAGAIN: ret = 0; fallthrough; case -EFAULT: case -ENOMEM: case -EHWPOISON: goto out; } BUG(); } else if (PTR_ERR(page) == -EEXIST) { /* * Proper page table entry exists, but no corresponding * struct page. If the caller expects **pages to be * filled in, bail out now, because that can't be done * for this page. */ if (pages) { ret = PTR_ERR(page); goto out; } } else if (IS_ERR(page)) { ret = PTR_ERR(page); goto out; } next_page: page_increm = 1 + (~(start >> PAGE_SHIFT) & ctx.page_mask); if (page_increm > nr_pages) page_increm = nr_pages; if (pages) { struct page *subpage; unsigned int j; /* * This must be a large folio (and doesn't need to * be the whole folio; it can be part of it), do * the refcount work for all the subpages too. * * NOTE: here the page may not be the head page * e.g. when start addr is not thp-size aligned. * try_grab_folio() should have taken care of tail * pages. */ if (page_increm > 1) { struct folio *folio; /* * Since we already hold refcount on the * large folio, this should never fail. */ folio = try_grab_folio(page, page_increm - 1, foll_flags); if (WARN_ON_ONCE(!folio)) { /* * Release the 1st page ref if the * folio is problematic, fail hard. */ gup_put_folio(page_folio(page), 1, foll_flags); ret = -EFAULT; goto out; } } for (j = 0; j < page_increm; j++) { subpage = nth_page(page, j); pages[i + j] = subpage; flush_anon_page(vma, subpage, start + j * PAGE_SIZE); flush_dcache_page(subpage); } } i += page_increm; start += page_increm * PAGE_SIZE; nr_pages -= page_increm; } while (nr_pages); out: if (ctx.pgmap) put_dev_pagemap(ctx.pgmap); return i ? i : ret; } static bool vma_permits_fault(struct vm_area_struct *vma, unsigned int fault_flags) { bool write = !!(fault_flags & FAULT_FLAG_WRITE); bool foreign = !!(fault_flags & FAULT_FLAG_REMOTE); vm_flags_t vm_flags = write ? VM_WRITE : VM_READ; if (!(vm_flags & vma->vm_flags)) return false; /* * The architecture might have a hardware protection * mechanism other than read/write that can deny access. * * gup always represents data access, not instruction * fetches, so execute=false here: */ if (!arch_vma_access_permitted(vma, write, false, foreign)) return false; return true; } /** * fixup_user_fault() - manually resolve a user page fault * @mm: mm_struct of target mm * @address: user address * @fault_flags:flags to pass down to handle_mm_fault() * @unlocked: did we unlock the mmap_lock while retrying, maybe NULL if caller * does not allow retry. If NULL, the caller must guarantee * that fault_flags does not contain FAULT_FLAG_ALLOW_RETRY. * * This is meant to be called in the specific scenario where for locking reasons * we try to access user memory in atomic context (within a pagefault_disable() * section), this returns -EFAULT, and we want to resolve the user fault before * trying again. * * Typically this is meant to be used by the futex code. * * The main difference with get_user_pages() is that this function will * unconditionally call handle_mm_fault() which will in turn perform all the * necessary SW fixup of the dirty and young bits in the PTE, while * get_user_pages() only guarantees to update these in the struct page. * * This is important for some architectures where those bits also gate the * access permission to the page because they are maintained in software. On * such architectures, gup() will not be enough to make a subsequent access * succeed. * * This function will not return with an unlocked mmap_lock. So it has not the * same semantics wrt the @mm->mmap_lock as does filemap_fault(). */ int fixup_user_fault(struct mm_struct *mm, unsigned long address, unsigned int fault_flags, bool *unlocked) { struct vm_area_struct *vma; vm_fault_t ret; address = untagged_addr_remote(mm, address); if (unlocked) fault_flags |= FAULT_FLAG_ALLOW_RETRY | FAULT_FLAG_KILLABLE; retry: vma = gup_vma_lookup(mm, address); if (!vma) return -EFAULT; if (!vma_permits_fault(vma, fault_flags)) return -EFAULT; if ((fault_flags & FAULT_FLAG_KILLABLE) && fatal_signal_pending(current)) return -EINTR; ret = handle_mm_fault(vma, address, fault_flags, NULL); if (ret & VM_FAULT_COMPLETED) { /* * NOTE: it's a pity that we need to retake the lock here * to pair with the unlock() in the callers. Ideally we * could tell the callers so they do not need to unlock. */ mmap_read_lock(mm); *unlocked = true; return 0; } if (ret & VM_FAULT_ERROR) { int err = vm_fault_to_errno(ret, 0); if (err) return err; BUG(); } if (ret & VM_FAULT_RETRY) { mmap_read_lock(mm); *unlocked = true; fault_flags |= FAULT_FLAG_TRIED; goto retry; } return 0; } EXPORT_SYMBOL_GPL(fixup_user_fault); /* * GUP always responds to fatal signals. When FOLL_INTERRUPTIBLE is * specified, it'll also respond to generic signals. The caller of GUP * that has FOLL_INTERRUPTIBLE should take care of the GUP interruption. */ static bool gup_signal_pending(unsigned int flags) { if (fatal_signal_pending(current)) return true; if (!(flags & FOLL_INTERRUPTIBLE)) return false; return signal_pending(current); } /* * Locking: (*locked == 1) means that the mmap_lock has already been acquired by * the caller. This function may drop the mmap_lock. If it does so, then it will * set (*locked = 0). * * (*locked == 0) means that the caller expects this function to acquire and * drop the mmap_lock. Therefore, the value of *locked will still be zero when * the function returns, even though it may have changed temporarily during * function execution. * * Please note that this function, unlike __get_user_pages(), will not return 0 * for nr_pages > 0, unless FOLL_NOWAIT is used. */ static __always_inline long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int flags) { long ret, pages_done; bool must_unlock = false; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } else mmap_assert_locked(mm); if (flags & FOLL_PIN) mm_set_has_pinned_flag(&mm->flags); /* * FOLL_PIN and FOLL_GET are mutually exclusive. Traditional behavior * is to set FOLL_GET if the caller wants pages[] filled in (but has * carelessly failed to specify FOLL_GET), so keep doing that, but only * for FOLL_GET, not for the newer FOLL_PIN. * * FOLL_PIN always expects pages to be non-null, but no need to assert * that here, as any failures will be obvious enough. */ if (pages && !(flags & FOLL_PIN)) flags |= FOLL_GET; pages_done = 0; for (;;) { ret = __get_user_pages(mm, start, nr_pages, flags, pages, locked); if (!(flags & FOLL_UNLOCKABLE)) { /* VM_FAULT_RETRY couldn't trigger, bypass */ pages_done = ret; break; } /* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */ if (!*locked) { BUG_ON(ret < 0); BUG_ON(ret >= nr_pages); } if (ret > 0) { nr_pages -= ret; pages_done += ret; if (!nr_pages) break; } if (*locked) { /* * VM_FAULT_RETRY didn't trigger or it was a * FOLL_NOWAIT. */ if (!pages_done) pages_done = ret; break; } /* * VM_FAULT_RETRY triggered, so seek to the faulting offset. * For the prefault case (!pages) we only update counts. */ if (likely(pages)) pages += ret; start += ret << PAGE_SHIFT; /* The lock was temporarily dropped, so we must unlock later */ must_unlock = true; retry: /* * Repeat on the address that fired VM_FAULT_RETRY * with both FAULT_FLAG_ALLOW_RETRY and * FAULT_FLAG_TRIED. Note that GUP can be interrupted * by fatal signals of even common signals, depending on * the caller's request. So we need to check it before we * start trying again otherwise it can loop forever. */ if (gup_signal_pending(flags)) { if (!pages_done) pages_done = -EINTR; break; } ret = mmap_read_lock_killable(mm); if (ret) { BUG_ON(ret > 0); if (!pages_done) pages_done = ret; break; } *locked = 1; ret = __get_user_pages(mm, start, 1, flags | FOLL_TRIED, pages, locked); if (!*locked) { /* Continue to retry until we succeeded */ BUG_ON(ret != 0); goto retry; } if (ret != 1) { BUG_ON(ret > 1); if (!pages_done) pages_done = ret; break; } nr_pages--; pages_done++; if (!nr_pages) break; if (likely(pages)) pages++; start += PAGE_SIZE; } if (must_unlock && *locked) { /* * We either temporarily dropped the lock, or the caller * requested that we both acquire and drop the lock. Either way, * we must now unlock, and notify the caller of that state. */ mmap_read_unlock(mm); *locked = 0; } /* * Failing to pin anything implies something has gone wrong (except when * FOLL_NOWAIT is specified). */ if (WARN_ON_ONCE(pages_done == 0 && !(flags & FOLL_NOWAIT))) return -EFAULT; return pages_done; } /** * populate_vma_page_range() - populate a range of pages in the vma. * @vma: target vma * @start: start address * @end: end address * @locked: whether the mmap_lock is still held * * This takes care of mlocking the pages too if VM_LOCKED is set. * * Return either number of pages pinned in the vma, or a negative error * code on error. * * vma->vm_mm->mmap_lock must be held. * * If @locked is NULL, it may be held for read or write and will * be unperturbed. * * If @locked is non-NULL, it must held for read only and may be * released. If it's released, *@locked will be set to 0. */ long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked) { struct mm_struct *mm = vma->vm_mm; unsigned long nr_pages = (end - start) / PAGE_SIZE; int local_locked = 1; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); VM_BUG_ON_VMA(start < vma->vm_start, vma); VM_BUG_ON_VMA(end > vma->vm_end, vma); mmap_assert_locked(mm); /* * Rightly or wrongly, the VM_LOCKONFAULT case has never used * faultin_page() to break COW, so it has no work to do here. */ if (vma->vm_flags & VM_LOCKONFAULT) return nr_pages; /* ... similarly, we've never faulted in PROT_NONE pages */ if (!vma_is_accessible(vma)) return -EFAULT; gup_flags = FOLL_TOUCH; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW * and we would not want to dirty them for nothing. * * Otherwise, do a read fault, and use FOLL_FORCE in case it's not * readable (ie write-only or executable). */ if ((vma->vm_flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) gup_flags |= FOLL_WRITE; else gup_flags |= FOLL_FORCE; if (locked) gup_flags |= FOLL_UNLOCKABLE; /* * We made sure addr is within a VMA, so the following will * not result in a stack expansion that recurses back here. */ ret = __get_user_pages(mm, start, nr_pages, gup_flags, NULL, locked ? locked : &local_locked); lru_add_drain(); return ret; } /* * faultin_page_range() - populate (prefault) page tables inside the * given range readable/writable * * This takes care of mlocking the pages, too, if VM_LOCKED is set. * * @mm: the mm to populate page tables in * @start: start address * @end: end address * @write: whether to prefault readable or writable * @locked: whether the mmap_lock is still held * * Returns either number of processed pages in the MM, or a negative error * code on error (see __get_user_pages()). Note that this function reports * errors related to VMAs, such as incompatible mappings, as expected by * MADV_POPULATE_(READ|WRITE). * * The range must be page-aligned. * * mm->mmap_lock must be held. If it's released, *@locked will be set to 0. */ long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked) { unsigned long nr_pages = (end - start) / PAGE_SIZE; int gup_flags; long ret; VM_BUG_ON(!PAGE_ALIGNED(start)); VM_BUG_ON(!PAGE_ALIGNED(end)); mmap_assert_locked(mm); /* * FOLL_TOUCH: Mark page accessed and thereby young; will also mark * the page dirty with FOLL_WRITE -- which doesn't make a * difference with !FOLL_FORCE, because the page is writable * in the page table. * FOLL_HWPOISON: Return -EHWPOISON instead of -EFAULT when we hit * a poisoned page. * !FOLL_FORCE: Require proper access permissions. */ gup_flags = FOLL_TOUCH | FOLL_HWPOISON | FOLL_UNLOCKABLE | FOLL_MADV_POPULATE; if (write) gup_flags |= FOLL_WRITE; ret = __get_user_pages_locked(mm, start, nr_pages, NULL, locked, gup_flags); lru_add_drain(); return ret; } /* * __mm_populate - populate and/or mlock pages within a range of address space. * * This is used to implement mlock() and the MAP_POPULATE / MAP_LOCKED mmap * flags. VMAs must be already marked with the desired vm_flags, and * mmap_lock must not be held. */ int __mm_populate(unsigned long start, unsigned long len, int ignore_errors) { struct mm_struct *mm = current->mm; unsigned long end, nstart, nend; struct vm_area_struct *vma = NULL; int locked = 0; long ret = 0; end = start + len; for (nstart = start; nstart < end; nstart = nend) { /* * We want to fault in pages for [nstart; end) address range. * Find first corresponding VMA. */ if (!locked) { locked = 1; mmap_read_lock(mm); vma = find_vma_intersection(mm, nstart, end); } else if (nstart >= vma->vm_end) vma = find_vma_intersection(mm, vma->vm_end, end); if (!vma) break; /* * Set [nstart; nend) to intersection of desired address * range with the first VMA. Also, skip undesirable VMA types. */ nend = min(end, vma->vm_end); if (vma->vm_flags & (VM_IO | VM_PFNMAP)) continue; if (nstart < vma->vm_start) nstart = vma->vm_start; /* * Now fault in a range of pages. populate_vma_page_range() * double checks the vma flags, so that it won't mlock pages * if the vma was already munlocked. */ ret = populate_vma_page_range(vma, nstart, nend, &locked); if (ret < 0) { if (ignore_errors) { ret = 0; continue; /* continue at next VMA */ } break; } nend = nstart + ret * PAGE_SIZE; ret = 0; } if (locked) mmap_read_unlock(mm); return ret; /* 0 or negative error code */ } #else /* CONFIG_MMU */ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int foll_flags) { struct vm_area_struct *vma; bool must_unlock = false; unsigned long vm_flags; long i; if (!nr_pages) return 0; /* * The internal caller expects GUP to manage the lock internally and the * lock must be released when this returns. */ if (!*locked) { if (mmap_read_lock_killable(mm)) return -EAGAIN; must_unlock = true; *locked = 1; } /* calculate required read or write permissions. * If FOLL_FORCE is set, we only require the "MAY" flags. */ vm_flags = (foll_flags & FOLL_WRITE) ? (VM_WRITE | VM_MAYWRITE) : (VM_READ | VM_MAYREAD); vm_flags &= (foll_flags & FOLL_FORCE) ? (VM_MAYREAD | VM_MAYWRITE) : (VM_READ | VM_WRITE); for (i = 0; i < nr_pages; i++) { vma = find_vma(mm, start); if (!vma) break; /* protect what we can, including chardevs */ if ((vma->vm_flags & (VM_IO | VM_PFNMAP)) || !(vm_flags & vma->vm_flags)) break; if (pages) { pages[i] = virt_to_page((void *)start); if (pages[i]) get_page(pages[i]); } start = (start + PAGE_SIZE) & PAGE_MASK; } if (must_unlock && *locked) { mmap_read_unlock(mm); *locked = 0; } return i ? : -EFAULT; } #endif /* !CONFIG_MMU */ /** * fault_in_writeable - fault in userspace address range for writing * @uaddr: start of address range * @size: size of address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_writeable(char __user *uaddr, size_t size) { char __user *start = uaddr, *end; if (unlikely(size == 0)) return 0; if (!user_write_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_put_user(0, uaddr, out); uaddr = (char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_put_user(0, uaddr, out); uaddr += PAGE_SIZE; } out: user_write_access_end(); if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_writeable); /** * fault_in_subpage_writeable - fault in an address range for writing * @uaddr: start of address range * @size: size of address range * * Fault in a user address range for writing while checking for permissions at * sub-page granularity (e.g. arm64 MTE). This function should be used when * the caller cannot guarantee forward progress of a copy_to_user() loop. * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_subpage_writeable(char __user *uaddr, size_t size) { size_t faulted_in; /* * Attempt faulting in at page granularity first for page table * permission checking. The arch-specific probe_subpage_writeable() * functions may not check for this. */ faulted_in = size - fault_in_writeable(uaddr, size); if (faulted_in) faulted_in -= probe_subpage_writeable(uaddr, faulted_in); return size - faulted_in; } EXPORT_SYMBOL(fault_in_subpage_writeable); /* * fault_in_safe_writeable - fault in an address range for writing * @uaddr: start of address range * @size: length of address range * * Faults in an address range for writing. This is primarily useful when we * already know that some or all of the pages in the address range aren't in * memory. * * Unlike fault_in_writeable(), this function is non-destructive. * * Note that we don't pin or otherwise hold the pages referenced that we fault * in. There's no guarantee that they'll stay in memory for any duration of * time. * * Returns the number of bytes not faulted in, like copy_to_user() and * copy_from_user(). */ size_t fault_in_safe_writeable(const char __user *uaddr, size_t size) { unsigned long start = (unsigned long)uaddr, end; struct mm_struct *mm = current->mm; bool unlocked = false; if (unlikely(size == 0)) return 0; end = PAGE_ALIGN(start + size); if (end < start) end = 0; mmap_read_lock(mm); do { if (fixup_user_fault(mm, start, FAULT_FLAG_WRITE, &unlocked)) break; start = (start + PAGE_SIZE) & PAGE_MASK; } while (start != end); mmap_read_unlock(mm); if (size > (unsigned long)uaddr - start) return size - ((unsigned long)uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_safe_writeable); /** * fault_in_readable - fault in userspace address range for reading * @uaddr: start of user address range * @size: size of user address range * * Returns the number of bytes not faulted in (like copy_to_user() and * copy_from_user()). */ size_t fault_in_readable(const char __user *uaddr, size_t size) { const char __user *start = uaddr, *end; volatile char c; if (unlikely(size == 0)) return 0; if (!user_read_access_begin(uaddr, size)) return size; if (!PAGE_ALIGNED(uaddr)) { unsafe_get_user(c, uaddr, out); uaddr = (const char __user *)PAGE_ALIGN((unsigned long)uaddr); } end = (const char __user *)PAGE_ALIGN((unsigned long)start + size); if (unlikely(end < start)) end = NULL; while (uaddr != end) { unsafe_get_user(c, uaddr, out); uaddr += PAGE_SIZE; } out: user_read_access_end(); (void)c; if (size > uaddr - start) return size - (uaddr - start); return 0; } EXPORT_SYMBOL(fault_in_readable); /** * get_dump_page() - pin user page in memory while writing it to core dump * @addr: user address * * Returns struct page pointer of user page pinned for dump, * to be freed afterwards by put_page(). * * Returns NULL on any kind of failure - a hole must then be inserted into * the corefile, to preserve alignment with its headers; and also returns * NULL wherever the ZERO_PAGE, or an anonymous pte_none, has been found - * allowing a hole to be left in the corefile to save disk space. * * Called without mmap_lock (takes and releases the mmap_lock by itself). */ #ifdef CONFIG_ELF_CORE struct page *get_dump_page(unsigned long addr) { struct page *page; int locked = 0; int ret; ret = __get_user_pages_locked(current->mm, addr, 1, &page, &locked, FOLL_FORCE | FOLL_DUMP | FOLL_GET); return (ret == 1) ? page : NULL; } #endif /* CONFIG_ELF_CORE */ #ifdef CONFIG_MIGRATION /* * Returns the number of collected pages. Return value is always >= 0. */ static unsigned long collect_longterm_unpinnable_pages( struct list_head *movable_page_list, unsigned long nr_pages, struct page **pages) { unsigned long i, collected = 0; struct folio *prev_folio = NULL; bool drain_allow = true; for (i = 0; i < nr_pages; i++) { struct folio *folio = page_folio(pages[i]); if (folio == prev_folio) continue; prev_folio = folio; if (folio_is_longterm_pinnable(folio)) continue; collected++; if (folio_is_device_coherent(folio)) continue; if (folio_test_hugetlb(folio)) { isolate_hugetlb(folio, movable_page_list); continue; } if (!folio_test_lru(folio) && drain_allow) { lru_add_drain_all(); drain_allow = false; } if (!folio_isolate_lru(folio)) continue; list_add_tail(&folio->lru, movable_page_list); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } return collected; } /* * Unpins all pages and migrates device coherent pages and movable_page_list. * Returns -EAGAIN if all pages were successfully migrated or -errno for failure * (or partial success). */ static int migrate_longterm_unpinnable_pages( struct list_head *movable_page_list, unsigned long nr_pages, struct page **pages) { int ret; unsigned long i; for (i = 0; i < nr_pages; i++) { struct folio *folio = page_folio(pages[i]); if (folio_is_device_coherent(folio)) { /* * Migration will fail if the page is pinned, so convert * the pin on the source page to a normal reference. */ pages[i] = NULL; folio_get(folio); gup_put_folio(folio, 1, FOLL_PIN); if (migrate_device_coherent_page(&folio->page)) { ret = -EBUSY; goto err; } continue; } /* * We can't migrate pages with unexpected references, so drop * the reference obtained by __get_user_pages_locked(). * Migrating pages have been added to movable_page_list after * calling folio_isolate_lru() which takes a reference so the * page won't be freed if it's migrating. */ unpin_user_page(pages[i]); pages[i] = NULL; } if (!list_empty(movable_page_list)) { struct migration_target_control mtc = { .nid = NUMA_NO_NODE, .gfp_mask = GFP_USER | __GFP_NOWARN, .reason = MR_LONGTERM_PIN, }; if (migrate_pages(movable_page_list, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_LONGTERM_PIN, NULL)) { ret = -ENOMEM; goto err; } } putback_movable_pages(movable_page_list); return -EAGAIN; err: for (i = 0; i < nr_pages; i++) if (pages[i]) unpin_user_page(pages[i]); putback_movable_pages(movable_page_list); return ret; } /* * Check whether all pages are *allowed* to be pinned. Rather confusingly, all * pages in the range are required to be pinned via FOLL_PIN, before calling * this routine. * * If any pages in the range are not allowed to be pinned, then this routine * will migrate those pages away, unpin all the pages in the range and return * -EAGAIN. The caller should re-pin the entire range with FOLL_PIN and then * call this routine again. * * If an error other than -EAGAIN occurs, this indicates a migration failure. * The caller should give up, and propagate the error back up the call stack. * * If everything is OK and all pages in the range are allowed to be pinned, then * this routine leaves all pages pinned and returns zero for success. */ static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { unsigned long collected; LIST_HEAD(movable_page_list); collected = collect_longterm_unpinnable_pages(&movable_page_list, nr_pages, pages); if (!collected) return 0; return migrate_longterm_unpinnable_pages(&movable_page_list, nr_pages, pages); } #else static long check_and_migrate_movable_pages(unsigned long nr_pages, struct page **pages) { return 0; } #endif /* CONFIG_MIGRATION */ /* * __gup_longterm_locked() is a wrapper for __get_user_pages_locked which * allows us to process the FOLL_LONGTERM flag. */ static long __gup_longterm_locked(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, struct page **pages, int *locked, unsigned int gup_flags) { unsigned int flags; long rc, nr_pinned_pages; if (!(gup_flags & FOLL_LONGTERM)) return __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); flags = memalloc_pin_save(); do { nr_pinned_pages = __get_user_pages_locked(mm, start, nr_pages, pages, locked, gup_flags); if (nr_pinned_pages <= 0) { rc = nr_pinned_pages; break; } /* FOLL_LONGTERM implies FOLL_PIN */ rc = check_and_migrate_movable_pages(nr_pinned_pages, pages); } while (rc == -EAGAIN); memalloc_pin_restore(flags); return rc ? rc : nr_pinned_pages; } /* * Check that the given flags are valid for the exported gup/pup interface, and * update them with the required flags that the caller must have set. */ static bool is_valid_gup_args(struct page **pages, int *locked, unsigned int *gup_flags_p, unsigned int to_set) { unsigned int gup_flags = *gup_flags_p; /* * These flags not allowed to be specified externally to the gup * interfaces: * - FOLL_TOUCH/FOLL_PIN/FOLL_TRIED/FOLL_FAST_ONLY are internal only * - FOLL_REMOTE is internal only and used on follow_page() * - FOLL_UNLOCKABLE is internal only and used if locked is !NULL */ if (WARN_ON_ONCE(gup_flags & INTERNAL_GUP_FLAGS)) return false; gup_flags |= to_set; if (locked) { /* At the external interface locked must be set */ if (WARN_ON_ONCE(*locked != 1)) return false; gup_flags |= FOLL_UNLOCKABLE; } /* FOLL_GET and FOLL_PIN are mutually exclusive. */ if (WARN_ON_ONCE((gup_flags & (FOLL_PIN | FOLL_GET)) == (FOLL_PIN | FOLL_GET))) return false; /* LONGTERM can only be specified when pinning */ if (WARN_ON_ONCE(!(gup_flags & FOLL_PIN) && (gup_flags & FOLL_LONGTERM))) return false; /* Pages input must be given if using GET/PIN */ if (WARN_ON_ONCE((gup_flags & (FOLL_GET | FOLL_PIN)) && !pages)) return false; /* We want to allow the pgmap to be hot-unplugged at all times */ if (WARN_ON_ONCE((gup_flags & FOLL_LONGTERM) && (gup_flags & FOLL_PCI_P2PDMA))) return false; *gup_flags_p = gup_flags; return true; } #ifdef CONFIG_MMU /** * get_user_pages_remote() - pin user pages in memory * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Returns either number of pages pinned (which may be less than the * number requested), or an error. Details about the return value: * * -- If nr_pages is 0, returns 0. * -- If nr_pages is >0, but no pages were pinned, returns -errno. * -- If nr_pages is >0, and some pages were pinned, returns the number of * pages pinned. Again, this may be less than nr_pages. * * The caller is responsible for releasing returned @pages, via put_page(). * * Must be called with mmap_lock held for read or write. * * get_user_pages_remote walks a process's page tables and takes a reference * to each struct page that each user address corresponds to at a given * instant. That is, it takes the page that would be accessed if a user * thread accesses the given user virtual address at that instant. * * This does not guarantee that the page exists in the user mappings when * get_user_pages_remote returns, and there may even be a completely different * page there in some cases (eg. if mmapped pagecache has been invalidated * and subsequently re-faulted). However it does guarantee that the page * won't be freed completely. And mostly callers simply care that the page * contains data that was valid *at some point in time*. Typically, an IO * or similar operation cannot guarantee anything stronger anyway because * locks can't be held over the syscall boundary. * * If gup_flags & FOLL_WRITE == 0, the page must not be written to. If the page * is written to, set_page_dirty (or set_page_dirty_lock, as appropriate) must * be called after the page is finished with, and before put_page is called. * * get_user_pages_remote is typically used for fewer-copy IO operations, * to get a handle on the memory by some means other than accesses * via the user virtual addresses. The pages may be submitted for * DMA to devices or accessed via their kernel linear mapping (via the * kmap APIs). Care should be taken to use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. * * get_user_pages_remote should be phased out in favor of * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing * should use get_user_pages_remote because it cannot pass * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_TOUCH | FOLL_REMOTE)) return -EINVAL; return __get_user_pages_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_remote); #else /* CONFIG_MMU */ long get_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { return 0; } #endif /* !CONFIG_MMU */ /** * get_user_pages() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. Or NULL, if caller * only intends to ensure the pages are faulted in. * * This is the same as get_user_pages_remote(), just with a less-flexible * calling convention where we assume that the mm being operated on belongs to * the current task, and doesn't allow passing of a locked parameter. We also * obviously don't pass FOLL_REMOTE in here. */ long get_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages); /* * get_user_pages_unlocked() is suitable to replace the form: * * mmap_read_lock(mm); * get_user_pages(mm, ..., pages, NULL); * mmap_read_unlock(mm); * * with: * * get_user_pages_unlocked(mm, ..., pages); * * It is functionally equivalent to get_user_pages_fast so * get_user_pages_fast should be used instead if specific gup_flags * (e.g. FOLL_FORCE) are not required. */ long get_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_TOUCH | FOLL_UNLOCKABLE)) return -EINVAL; return __get_user_pages_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(get_user_pages_unlocked); /* * GUP-fast * * get_user_pages_fast attempts to pin user pages by walking the page * tables directly and avoids taking locks. Thus the walker needs to be * protected from page table pages being freed from under it, and should * block any THP splits. * * One way to achieve this is to have the walker disable interrupts, and * rely on IPIs from the TLB flushing code blocking before the page table * pages are freed. This is unsuitable for architectures that do not need * to broadcast an IPI when invalidating TLBs. * * Another way to achieve this is to batch up page table containing pages * belonging to more than one mm_user, then rcu_sched a callback to free those * pages. Disabling interrupts will allow the gup_fast() walker to both block * the rcu_sched callback, and an IPI that we broadcast for splitting THPs * (which is a relatively rare event). The code below adopts this strategy. * * Before activating this code, please be aware that the following assumptions * are currently made: * * *) Either MMU_GATHER_RCU_TABLE_FREE is enabled, and tlb_remove_table() is used to * free pages containing page tables or TLB flushing requires IPI broadcast. * * *) ptes can be read atomically by the architecture. * * *) access_ok is sufficient to validate userspace address ranges. * * The last two assumptions can be relaxed by the addition of helper functions. * * This code is based heavily on the PowerPC implementation by Nick Piggin. */ #ifdef CONFIG_HAVE_GUP_FAST /* * Used in the GUP-fast path to determine whether GUP is permitted to work on * a specific folio. * * This call assumes the caller has pinned the folio, that the lowest page table * level still points to this folio, and that interrupts have been disabled. * * GUP-fast must reject all secretmem folios. * * Writing to pinned file-backed dirty tracked folios is inherently problematic * (see comment describing the writable_file_mapping_allowed() function). We * therefore try to avoid the most egregious case of a long-term mapping doing * so. * * This function cannot be as thorough as that one as the VMA is not available * in the fast path, so instead we whitelist known good cases and if in doubt, * fall back to the slow path. */ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags) { bool reject_file_backed = false; struct address_space *mapping; bool check_secretmem = false; unsigned long mapping_flags; /* * If we aren't pinning then no problematic write can occur. A long term * pin is the most egregious case so this is the one we disallow. */ if ((flags & (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) == (FOLL_PIN | FOLL_LONGTERM | FOLL_WRITE)) reject_file_backed = true; /* We hold a folio reference, so we can safely access folio fields. */ /* secretmem folios are always order-0 folios. */ if (IS_ENABLED(CONFIG_SECRETMEM) && !folio_test_large(folio)) check_secretmem = true; if (!reject_file_backed && !check_secretmem) return true; if (WARN_ON_ONCE(folio_test_slab(folio))) return false; /* hugetlb neither requires dirty-tracking nor can be secretmem. */ if (folio_test_hugetlb(folio)) return true; /* * GUP-fast disables IRQs. When IRQS are disabled, RCU grace periods * cannot proceed, which means no actions performed under RCU can * proceed either. * * inodes and thus their mappings are freed under RCU, which means the * mapping cannot be freed beneath us and thus we can safely dereference * it. */ lockdep_assert_irqs_disabled(); /* * However, there may be operations which _alter_ the mapping, so ensure * we read it once and only once. */ mapping = READ_ONCE(folio->mapping); /* * The mapping may have been truncated, in any case we cannot determine * if this mapping is safe - fall back to slow path to determine how to * proceed. */ if (!mapping) return false; /* Anonymous folios pose no problem. */ mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS; if (mapping_flags) return mapping_flags & PAGE_MAPPING_ANON; /* * At this point, we know the mapping is non-null and points to an * address_space object. */ if (check_secretmem && secretmem_mapping(mapping)) return false; /* The only remaining allowed file system is shmem. */ return !reject_file_backed || shmem_mapping(mapping); } static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start, unsigned int flags, struct page **pages) { while ((*nr) - nr_start) { struct folio *folio = page_folio(pages[--(*nr)]); folio_clear_referenced(folio); gup_put_folio(folio, 1, flags); } } #ifdef CONFIG_ARCH_HAS_PTE_SPECIAL /* * GUP-fast relies on pte change detection to avoid concurrent pgtable * operations. * * To pin the page, GUP-fast needs to do below in order: * (1) pin the page (by prefetching pte), then (2) check pte not changed. * * For the rest of pgtable operations where pgtable updates can be racy * with GUP-fast, we need to do (1) clear pte, then (2) check whether page * is pinned. * * Above will work for all pte-level operations, including THP split. * * For THP collapse, it's a bit more complicated because GUP-fast may be * walking a pgtable page that is being freed (pte is still valid but pmd * can be cleared already). To avoid race in such condition, we need to * also check pmd here to make sure pmd doesn't change (corresponds to * pmdp_collapse_flush() in the THP collapse code path). */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct dev_pagemap *pgmap = NULL; int nr_start = *nr, ret = 0; pte_t *ptep, *ptem; ptem = ptep = pte_offset_map(&pmd, addr); if (!ptep) return 0; do { pte_t pte = ptep_get_lockless(ptep); struct page *page; struct folio *folio; /* * Always fallback to ordinary GUP on PROT_NONE-mapped pages: * pte_access_permitted() better should reject these pages * either way: otherwise, GUP-fast might succeed in * cases where ordinary GUP would fail due to VMA access * permissions. */ if (pte_protnone(pte)) goto pte_unmap; if (!pte_access_permitted(pte, flags & FOLL_WRITE)) goto pte_unmap; if (pte_devmap(pte)) { if (unlikely(flags & FOLL_LONGTERM)) goto pte_unmap; pgmap = get_dev_pagemap(pte_pfn(pte), pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); goto pte_unmap; } } else if (pte_special(pte)) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); page = pte_page(pte); folio = try_grab_folio(page, 1, flags); if (!folio) goto pte_unmap; if (unlikely(pmd_val(pmd) != pmd_val(*pmdp)) || unlikely(pte_val(pte) != pte_val(ptep_get(ptep)))) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } if (!pte_write(pte) && gup_must_unshare(NULL, flags, page)) { gup_put_folio(folio, 1, flags); goto pte_unmap; } /* * We need to make the page accessible if and only if we are * going to access its content (the FOLL_PIN case). Please * see Documentation/core-api/pin_user_pages.rst for * details. */ if (flags & FOLL_PIN) { ret = arch_make_page_accessible(page); if (ret) { gup_put_folio(folio, 1, flags); goto pte_unmap; } } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; } while (ptep++, addr += PAGE_SIZE, addr != end); ret = 1; pte_unmap: if (pgmap) put_dev_pagemap(pgmap); pte_unmap(ptem); return ret; } #else /* * If we can't determine whether or not a pte is special, then fail immediately * for ptes. Note, we can still pin HugeTLB and THP as these are guaranteed not * to be special. * * For a futex to be placed on a THP tail page, get_futex_key requires a * get_user_pages_fast_only implementation that can pin pages. Thus it's still * useful to have gup_fast_pmd_leaf even if we can't operate on ptes. */ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; } #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */ #if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE) static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int nr_start = *nr; struct dev_pagemap *pgmap = NULL; do { struct folio *folio; struct page *page = pfn_to_page(pfn); pgmap = get_dev_pagemap(pfn, pgmap); if (unlikely(!pgmap)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } if (!(flags & FOLL_PCI_P2PDMA) && is_pci_p2pdma_page(page)) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio = try_grab_folio(page, 1, flags); if (!folio) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); break; } folio_set_referenced(folio); pages[*nr] = page; (*nr)++; pfn++; } while (addr += PAGE_SIZE, addr != end); put_dev_pagemap(pgmap); return addr == end; } static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long fault_pfn; int nr_start = *nr; fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT); if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr)) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages); return 0; } return 1; } #else static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { BUILD_BUG(); return 0; } #endif static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pmd_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pmd_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags, pages, nr); } page = pmd_page(orig); refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { struct page *page; struct folio *folio; int refs; if (!pud_access_permitted(orig, flags & FOLL_WRITE)) return 0; if (pud_devmap(orig)) { if (unlikely(flags & FOLL_LONGTERM)) return 0; return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags, pages, nr); } page = pud_page(orig); refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pud_val(orig) != pud_val(*pudp))) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } if (!pud_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pgd_leaf(pgd_t orig, pgd_t *pgdp, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { int refs; struct page *page; struct folio *folio; if (!pgd_access_permitted(orig, flags & FOLL_WRITE)) return 0; BUILD_BUG_ON(pgd_devmap(orig)); page = pgd_page(orig); refs = record_subpages(page, PGDIR_SIZE, addr, end, pages + *nr); folio = try_grab_folio(page, refs, flags); if (!folio) return 0; if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) { gup_put_folio(folio, refs, flags); return 0; } if (!pgd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) { gup_put_folio(folio, refs, flags); return 0; } if (!gup_fast_folio_allowed(folio, flags)) { gup_put_folio(folio, refs, flags); return 0; } *nr += refs; folio_set_referenced(folio); return 1; } static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = pmdp_get_lockless(pmdp); next = pmd_addr_end(addr, end); if (!pmd_present(pmd)) return 0; if (unlikely(pmd_leaf(pmd))) { /* See gup_fast_pte_range() */ if (pmd_protnone(pmd)) return 0; if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pmd_val(pmd))))) { /* * architecture have different format for hugetlbfs * pmd format and THP pmd format */ if (gup_hugepd(NULL, __hugepd(pmd_val(pmd)), addr, PMD_SHIFT, next, flags, pages, nr) != 1) return 0; } else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages, nr)) return 0; } while (pmdp++, addr = next, addr != end); return 1; } static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); next = pud_addr_end(addr, end); if (unlikely(!pud_present(pud))) return 0; if (unlikely(pud_leaf(pud))) { if (!gup_fast_pud_leaf(pud, pudp, addr, next, flags, pages, nr)) return 0; } else if (unlikely(is_hugepd(__hugepd(pud_val(pud))))) { if (gup_hugepd(NULL, __hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr) != 1) return 0; } else if (!gup_fast_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } static int gup_fast_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); next = p4d_addr_end(addr, end); if (!p4d_present(p4d)) return 0; BUILD_BUG_ON(p4d_leaf(p4d)); if (unlikely(is_hugepd(__hugepd(p4d_val(p4d))))) { if (gup_hugepd(NULL, __hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr) != 1) return 0; } else if (!gup_fast_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); return 1; } static void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pgd_t *pgdp; pgdp = pgd_offset(current->mm, addr); do { pgd_t pgd = READ_ONCE(*pgdp); next = pgd_addr_end(addr, end); if (pgd_none(pgd)) return; if (unlikely(pgd_leaf(pgd))) { if (!gup_fast_pgd_leaf(pgd, pgdp, addr, next, flags, pages, nr)) return; } else if (unlikely(is_hugepd(__hugepd(pgd_val(pgd))))) { if (gup_hugepd(NULL, __hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr) != 1) return; } else if (!gup_fast_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } #else static inline void gup_fast_pgd_range(unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { } #endif /* CONFIG_HAVE_GUP_FAST */ #ifndef gup_fast_permitted /* * Check if it's allowed to use get_user_pages_fast_only() for the range, or * we need to fall back to the slow version: */ static bool gup_fast_permitted(unsigned long start, unsigned long end) { return true; } #endif static unsigned long gup_fast(unsigned long start, unsigned long end, unsigned int gup_flags, struct page **pages) { unsigned long flags; int nr_pinned = 0; unsigned seq; if (!IS_ENABLED(CONFIG_HAVE_GUP_FAST) || !gup_fast_permitted(start, end)) return 0; if (gup_flags & FOLL_PIN) { seq = raw_read_seqcount(¤t->mm->write_protect_seq); if (seq & 1) return 0; } /* * Disable interrupts. The nested form is used, in order to allow full, * general purpose use of this routine. * * With interrupts disabled, we block page table pages from being freed * from under us. See struct mmu_table_batch comments in * include/asm-generic/tlb.h for more details. * * We do not adopt an rcu_read_lock() here as we also want to block IPIs * that come from THPs splitting. */ local_irq_save(flags); gup_fast_pgd_range(start, end, gup_flags, pages, &nr_pinned); local_irq_restore(flags); /* * When pinning pages for DMA there could be a concurrent write protect * from fork() via copy_page_range(), in this case always fail GUP-fast. */ if (gup_flags & FOLL_PIN) { if (read_seqcount_retry(¤t->mm->write_protect_seq, seq)) { gup_fast_unpin_user_pages(pages, nr_pinned); return 0; } else { sanity_check_pinned_pages(pages, nr_pinned); } } return nr_pinned; } static int gup_fast_fallback(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { unsigned long len, end; unsigned long nr_pinned; int locked = 0; int ret; if (WARN_ON_ONCE(gup_flags & ~(FOLL_WRITE | FOLL_LONGTERM | FOLL_FORCE | FOLL_PIN | FOLL_GET | FOLL_FAST_ONLY | FOLL_NOFAULT | FOLL_PCI_P2PDMA | FOLL_HONOR_NUMA_FAULT))) return -EINVAL; if (gup_flags & FOLL_PIN) mm_set_has_pinned_flag(¤t->mm->flags); if (!(gup_flags & FOLL_FAST_ONLY)) might_lock_read(¤t->mm->mmap_lock); start = untagged_addr(start) & PAGE_MASK; len = nr_pages << PAGE_SHIFT; if (check_add_overflow(start, len, &end)) return -EOVERFLOW; if (end > TASK_SIZE_MAX) return -EFAULT; if (unlikely(!access_ok((void __user *)start, len))) return -EFAULT; nr_pinned = gup_fast(start, end, gup_flags, pages); if (nr_pinned == nr_pages || gup_flags & FOLL_FAST_ONLY) return nr_pinned; /* Slow path: try to get the remaining pages with get_user_pages */ start += nr_pinned << PAGE_SHIFT; pages += nr_pinned; ret = __gup_longterm_locked(current->mm, start, nr_pages - nr_pinned, pages, &locked, gup_flags | FOLL_TOUCH | FOLL_UNLOCKABLE); if (ret < 0) { /* * The caller has to unpin the pages we already pinned so * returning -errno is not an option */ if (nr_pinned) return nr_pinned; return ret; } return ret + nr_pinned; } /** * get_user_pages_fast_only() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Like get_user_pages_fast() except it's IRQ-safe in that it won't fall back to * the regular GUP. * * If the architecture does not support this function, simply return with no * pages pinned. * * Careful, careful! COW breaking can go either way, so a non-write * access can get ambiguous page results. If you call this function without * 'write' set, you'd better be sure that you're ok with that ambiguity. */ int get_user_pages_fast_only(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * Internally (within mm/gup.c), gup fast variants must set FOLL_GET, * because gup fast is always a "pin with a +1 page refcount" request. * * FOLL_FAST_ONLY is required in order to match the API description of * this routine: no fall back to regular ("slow") GUP. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET | FOLL_FAST_ONLY)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast_only); /** * get_user_pages_fast() - pin user pages in memory * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Attempt to pin user pages in memory without taking mm->mmap_lock. * If not successful, it will fall back to taking the lock and * calling get_user_pages(). * * Returns number of pages pinned. This may be fewer than the number requested. * If nr_pages is 0 or negative, returns 0. If no pages were pinned, returns * -errno. */ int get_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { /* * The caller may or may not have explicitly set FOLL_GET; either way is * OK. However, internally (within mm/gup.c), gup fast variants must set * FOLL_GET, because gup fast is always a "pin with a +1 page refcount" * request. */ if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_GET)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); /** * pin_user_pages_fast() - pin user pages in memory without taking locks * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying pin behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages_fast(), except that FOLL_PIN is set. See * get_user_pages_fast() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for further details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page() will not remove pins from it. */ int pin_user_pages_fast(unsigned long start, int nr_pages, unsigned int gup_flags, struct page **pages) { if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return -EINVAL; return gup_fast_fallback(start, nr_pages, gup_flags, pages); } EXPORT_SYMBOL_GPL(pin_user_pages_fast); /** * pin_user_pages_remote() - pin pages of a remote process * * @mm: mm_struct of target mm * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * @locked: pointer to lock flag indicating whether lock is held and * subsequently whether VM_FAULT_RETRY functionality can be * utilised. Lock must initially be held. * * Nearly the same as get_user_pages_remote(), except that FOLL_PIN is set. See * get_user_pages_remote() for documentation on the function arguments, because * the arguments here are identical. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_remote(struct mm_struct *mm, unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages, int *locked) { int local_locked = 1; if (!is_valid_gup_args(pages, locked, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_REMOTE)) return 0; return __gup_longterm_locked(mm, start, nr_pages, pages, locked ? locked : &local_locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_remote); /** * pin_user_pages() - pin user pages in memory for use by other devices * * @start: starting user address * @nr_pages: number of pages from start to pin * @gup_flags: flags modifying lookup behaviour * @pages: array that receives pointers to the pages pinned. * Should be at least nr_pages long. * * Nearly the same as get_user_pages(), except that FOLL_TOUCH is not set, and * FOLL_PIN is set. * * FOLL_PIN means that the pages must be released via unpin_user_page(). Please * see Documentation/core-api/pin_user_pages.rst for details. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages(unsigned long start, unsigned long nr_pages, unsigned int gup_flags, struct page **pages) { int locked = 1; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages); /* * pin_user_pages_unlocked() is the FOLL_PIN variant of * get_user_pages_unlocked(). Behavior is the same, except that this one sets * FOLL_PIN and rejects FOLL_GET. * * Note that if a zero_page is amongst the returned pages, it will not have * pins in it and unpin_user_page*() will not remove pins from it. */ long pin_user_pages_unlocked(unsigned long start, unsigned long nr_pages, struct page **pages, unsigned int gup_flags) { int locked = 0; if (!is_valid_gup_args(pages, NULL, &gup_flags, FOLL_PIN | FOLL_TOUCH | FOLL_UNLOCKABLE)) return 0; return __gup_longterm_locked(current->mm, start, nr_pages, pages, &locked, gup_flags); } EXPORT_SYMBOL(pin_user_pages_unlocked); |
| 2 2 2 2 61 61 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 | // SPDX-License-Identifier: GPL-2.0 /* * Implementation of the multi-level security (MLS) policy. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the MLS label from NetLabel * Copyright (C) Hewlett-Packard Development Company, L.P., 2006 */ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <net/netlabel.h> #include "sidtab.h" #include "mls.h" #include "policydb.h" #include "services.h" /* * Return the length in bytes for the MLS fields of the * security context string representation of `context'. */ int mls_compute_context_len(struct policydb *p, struct context *context) { int i, l, len, head, prev; char *nm; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return 0; len = 1; /* for the beginning ":" */ for (l = 0; l < 2; l++) { u32 index_sens = context->range.level[l].sens; len += strlen(sym_name(p, SYM_LEVELS, index_sens - 1)); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (head != prev) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } nm = sym_name(p, SYM_CATS, i); len += strlen(nm) + 1; head = i; } prev = i; } if (prev != head) { nm = sym_name(p, SYM_CATS, prev); len += strlen(nm) + 1; } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else len++; } } return len; } /* * Write the security context string representation of * the MLS fields of `context' into the string `*scontext'. * Update `*scontext' to point to the end of the MLS fields. */ void mls_sid_to_context(struct policydb *p, struct context *context, char **scontext) { char *scontextp, *nm; int i, l, head, prev; struct ebitmap *e; struct ebitmap_node *node; if (!p->mls_enabled) return; scontextp = *scontext; *scontextp = ':'; scontextp++; for (l = 0; l < 2; l++) { strcpy(scontextp, sym_name(p, SYM_LEVELS, context->range.level[l].sens - 1)); scontextp += strlen(scontextp); /* categories */ head = -2; prev = -2; e = &context->range.level[l].cat; ebitmap_for_each_positive_bit(e, node, i) { if (i - prev > 1) { /* one or more negative bits are skipped */ if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (prev < 0) *scontextp++ = ':'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, i); strcpy(scontextp, nm); scontextp += strlen(nm); head = i; } prev = i; } if (prev != head) { if (prev - head > 1) *scontextp++ = '.'; else *scontextp++ = ','; nm = sym_name(p, SYM_CATS, prev); strcpy(scontextp, nm); scontextp += strlen(nm); } if (l == 0) { if (mls_level_eq(&context->range.level[0], &context->range.level[1])) break; else *scontextp++ = '-'; } } *scontext = scontextp; } int mls_level_isvalid(struct policydb *p, struct mls_level *l) { struct level_datum *levdatum; if (!l->sens || l->sens > p->p_levels.nprim) return 0; levdatum = symtab_search(&p->p_levels, sym_name(p, SYM_LEVELS, l->sens - 1)); if (!levdatum) return 0; /* * Return 1 iff all the bits set in l->cat are also be set in * levdatum->level->cat and no bit in l->cat is larger than * p->p_cats.nprim. */ return ebitmap_contains(&levdatum->level->cat, &l->cat, p->p_cats.nprim); } int mls_range_isvalid(struct policydb *p, struct mls_range *r) { return (mls_level_isvalid(p, &r->level[0]) && mls_level_isvalid(p, &r->level[1]) && mls_level_dom(&r->level[1], &r->level[0])); } /* * Return 1 if the MLS fields in the security context * structure `c' are valid. Return 0 otherwise. */ int mls_context_isvalid(struct policydb *p, struct context *c) { struct user_datum *usrdatum; if (!p->mls_enabled) return 1; if (!mls_range_isvalid(p, &c->range)) return 0; if (c->role == OBJECT_R_VAL) return 1; /* * User must be authorized for the MLS range. */ if (!c->user || c->user > p->p_users.nprim) return 0; usrdatum = p->user_val_to_struct[c->user - 1]; if (!mls_range_contains(usrdatum->range, c->range)) return 0; /* user may not be associated with range */ return 1; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `scontext'. * * This function modifies the string in place, inserting * NULL characters to terminate the MLS fields. * * If a def_sid is provided and no MLS field is present, * copy the MLS field of the associated default context. * Used for upgraded to MLS systems where objects may lack * MLS fields. * * Policy read-lock must be held for sidtab lookup. * */ int mls_context_to_sid(struct policydb *pol, char oldc, char *scontext, struct context *context, struct sidtab *s, u32 def_sid) { char *sensitivity, *cur_cat, *next_cat, *rngptr; struct level_datum *levdatum; struct cat_datum *catdatum, *rngdatum; u32 i; int l, rc; char *rangep[2]; if (!pol->mls_enabled) { /* * With no MLS, only return -EINVAL if there is a MLS field * and it did not come from an xattr. */ if (oldc && def_sid == SECSID_NULL) return -EINVAL; return 0; } /* * No MLS component to the security context, try and map to * default if provided. */ if (!oldc) { struct context *defcon; if (def_sid == SECSID_NULL) return -EINVAL; defcon = sidtab_search(s, def_sid); if (!defcon) return -EINVAL; return mls_context_cpy(context, defcon); } /* * If we're dealing with a range, figure out where the two parts * of the range begin. */ rangep[0] = scontext; rangep[1] = strchr(scontext, '-'); if (rangep[1]) { rangep[1][0] = '\0'; rangep[1]++; } /* For each part of the range: */ for (l = 0; l < 2; l++) { /* Split sensitivity and category set. */ sensitivity = rangep[l]; if (sensitivity == NULL) break; next_cat = strchr(sensitivity, ':'); if (next_cat) *(next_cat++) = '\0'; /* Parse sensitivity. */ levdatum = symtab_search(&pol->p_levels, sensitivity); if (!levdatum) return -EINVAL; context->range.level[l].sens = levdatum->level->sens; /* Extract category set. */ while (next_cat != NULL) { cur_cat = next_cat; next_cat = strchr(next_cat, ','); if (next_cat != NULL) *(next_cat++) = '\0'; /* Separate into range if exists */ rngptr = strchr(cur_cat, '.'); if (rngptr != NULL) { /* Remove '.' */ *rngptr++ = '\0'; } catdatum = symtab_search(&pol->p_cats, cur_cat); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&context->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; /* If range, set all categories in range */ if (rngptr == NULL) continue; rngdatum = symtab_search(&pol->p_cats, rngptr); if (!rngdatum) return -EINVAL; if (catdatum->value >= rngdatum->value) return -EINVAL; for (i = catdatum->value; i < rngdatum->value; i++) { rc = ebitmap_set_bit( &context->range.level[l].cat, i, 1); if (rc) return rc; } } } /* If we didn't see a '-', the range start is also the range end. */ if (rangep[1] == NULL) { context->range.level[1].sens = context->range.level[0].sens; rc = ebitmap_cpy(&context->range.level[1].cat, &context->range.level[0].cat); if (rc) return rc; } return 0; } /* * Set the MLS fields in the security context structure * `context' based on the string representation in * the string `str'. This function will allocate temporary memory with the * given constraints of gfp_mask. */ int mls_from_string(struct policydb *p, char *str, struct context *context, gfp_t gfp_mask) { char *tmpstr; int rc; if (!p->mls_enabled) return -EINVAL; tmpstr = kstrdup(str, gfp_mask); if (!tmpstr) { rc = -ENOMEM; } else { rc = mls_context_to_sid(p, ':', tmpstr, context, NULL, SECSID_NULL); kfree(tmpstr); } return rc; } /* * Copies the MLS range `range' into `context'. */ int mls_range_set(struct context *context, struct mls_range *range) { int l, rc = 0; /* Copy the MLS range into the context */ for (l = 0; l < 2; l++) { context->range.level[l].sens = range->level[l].sens; rc = ebitmap_cpy(&context->range.level[l].cat, &range->level[l].cat); if (rc) break; } return rc; } int mls_setup_user_range(struct policydb *p, struct context *fromcon, struct user_datum *user, struct context *usercon) { if (p->mls_enabled) { struct mls_level *fromcon_sen = &(fromcon->range.level[0]); struct mls_level *fromcon_clr = &(fromcon->range.level[1]); struct mls_level *user_low = &(user->range.level[0]); struct mls_level *user_clr = &(user->range.level[1]); struct mls_level *user_def = &(user->dfltlevel); struct mls_level *usercon_sen = &(usercon->range.level[0]); struct mls_level *usercon_clr = &(usercon->range.level[1]); /* Honor the user's default level if we can */ if (mls_level_between(user_def, fromcon_sen, fromcon_clr)) *usercon_sen = *user_def; else if (mls_level_between(fromcon_sen, user_def, user_clr)) *usercon_sen = *fromcon_sen; else if (mls_level_between(fromcon_clr, user_low, user_def)) *usercon_sen = *user_low; else return -EINVAL; /* Lower the clearance of available contexts if the clearance of "fromcon" is lower than that of the user's default clearance (but only if the "fromcon" clearance dominates the user's computed sensitivity level) */ if (mls_level_dom(user_clr, fromcon_clr)) *usercon_clr = *fromcon_clr; else if (mls_level_dom(fromcon_clr, user_clr)) *usercon_clr = *user_clr; else return -EINVAL; } return 0; } /* * Convert the MLS fields in the security context * structure `oldc' from the values specified in the * policy `oldp' to the values specified in the policy `newp', * storing the resulting context in `newc'. */ int mls_convert_context(struct policydb *oldp, struct policydb *newp, struct context *oldc, struct context *newc) { struct level_datum *levdatum; struct cat_datum *catdatum; struct ebitmap_node *node; u32 i; int l; if (!oldp->mls_enabled || !newp->mls_enabled) return 0; for (l = 0; l < 2; l++) { char *name = sym_name(oldp, SYM_LEVELS, oldc->range.level[l].sens - 1); levdatum = symtab_search(&newp->p_levels, name); if (!levdatum) return -EINVAL; newc->range.level[l].sens = levdatum->level->sens; ebitmap_for_each_positive_bit(&oldc->range.level[l].cat, node, i) { int rc; catdatum = symtab_search(&newp->p_cats, sym_name(oldp, SYM_CATS, i)); if (!catdatum) return -EINVAL; rc = ebitmap_set_bit(&newc->range.level[l].cat, catdatum->value - 1, 1); if (rc) return rc; } } return 0; } int mls_compute_sid(struct policydb *p, struct context *scontext, struct context *tcontext, u16 tclass, u32 specified, struct context *newcontext, bool sock) { struct range_trans rtr; struct mls_range *r; struct class_datum *cladatum; char default_range = 0; if (!p->mls_enabled) return 0; switch (specified) { case AVTAB_TRANSITION: /* Look for a range transition rule. */ rtr.source_type = scontext->type; rtr.target_type = tcontext->type; rtr.target_class = tclass; r = policydb_rangetr_search(p, &rtr); if (r) return mls_range_set(newcontext, r); if (tclass && tclass <= p->p_classes.nprim) { cladatum = p->class_val_to_struct[tclass - 1]; if (cladatum) default_range = cladatum->default_range; } switch (default_range) { case DEFAULT_SOURCE_LOW: return mls_context_cpy_low(newcontext, scontext); case DEFAULT_SOURCE_HIGH: return mls_context_cpy_high(newcontext, scontext); case DEFAULT_SOURCE_LOW_HIGH: return mls_context_cpy(newcontext, scontext); case DEFAULT_TARGET_LOW: return mls_context_cpy_low(newcontext, tcontext); case DEFAULT_TARGET_HIGH: return mls_context_cpy_high(newcontext, tcontext); case DEFAULT_TARGET_LOW_HIGH: return mls_context_cpy(newcontext, tcontext); case DEFAULT_GLBLUB: return mls_context_glblub(newcontext, scontext, tcontext); } fallthrough; case AVTAB_CHANGE: if ((tclass == p->process_class) || sock) /* Use the process MLS attributes. */ return mls_context_cpy(newcontext, scontext); else /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); case AVTAB_MEMBER: /* Use the process effective MLS attributes. */ return mls_context_cpy_low(newcontext, scontext); } return -EINVAL; } #ifdef CONFIG_NETLABEL /** * mls_export_netlbl_lvl - Export the MLS sensitivity levels to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS sensitivity level into the * NetLabel MLS sensitivity level field. * */ void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; secattr->attr.mls.lvl = context->range.level[0].sens - 1; secattr->flags |= NETLBL_SECATTR_MLS_LVL; } /** * mls_import_netlbl_lvl - Import the NetLabel MLS sensitivity levels * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context and the NetLabel security attributes, copy the * NetLabel MLS sensitivity level into the context. * */ void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { if (!p->mls_enabled) return; context->range.level[0].sens = secattr->attr.mls.lvl + 1; context->range.level[1].sens = context->range.level[0].sens; } /** * mls_export_netlbl_cat - Export the MLS categories to NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Given the security context copy the low MLS categories into the NetLabel * MLS category field. Returns zero on success, negative values on failure. * */ int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_export(&context->range.level[0].cat, &secattr->attr.mls.cat); if (rc == 0 && secattr->attr.mls.cat != NULL) secattr->flags |= NETLBL_SECATTR_MLS_CAT; return rc; } /** * mls_import_netlbl_cat - Import the MLS categories from NetLabel * @p: the policy * @context: the security context * @secattr: the NetLabel security attributes * * Description: * Copy the NetLabel security attributes into the SELinux context; since the * NetLabel security attribute only contains a single MLS category use it for * both the low and high categories of the context. Returns zero on success, * negative values on failure. * */ int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { int rc; if (!p->mls_enabled) return 0; rc = ebitmap_netlbl_import(&context->range.level[0].cat, secattr->attr.mls.cat); if (rc) goto import_netlbl_cat_failure; memcpy(&context->range.level[1].cat, &context->range.level[0].cat, sizeof(context->range.level[0].cat)); return 0; import_netlbl_cat_failure: ebitmap_destroy(&context->range.level[0].cat); return rc; } #endif /* CONFIG_NETLABEL */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NF_CONNTRACK_COMMON_H #define _NF_CONNTRACK_COMMON_H #include <linux/refcount.h> #include <uapi/linux/netfilter/nf_conntrack_common.h> struct ip_conntrack_stat { unsigned int found; unsigned int invalid; unsigned int insert; unsigned int insert_failed; unsigned int clash_resolve; unsigned int drop; unsigned int early_drop; unsigned int error; unsigned int expect_new; unsigned int expect_create; unsigned int expect_delete; unsigned int search_restart; unsigned int chaintoolong; }; #define NFCT_INFOMASK 7UL #define NFCT_PTRMASK ~(NFCT_INFOMASK) struct nf_conntrack { refcount_t use; }; void nf_conntrack_destroy(struct nf_conntrack *nfct); /* like nf_ct_put, but without module dependency on nf_conntrack */ static inline void nf_conntrack_put(struct nf_conntrack *nfct) { if (nfct && refcount_dec_and_test(&nfct->use)) nf_conntrack_destroy(nfct); } static inline void nf_conntrack_get(struct nf_conntrack *nfct) { if (nfct) refcount_inc(&nfct->use); } #endif /* _NF_CONNTRACK_COMMON_H */ |
| 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 | // SPDX-License-Identifier: GPL-2.0 /* * kernel userspace event delivery * * Copyright (C) 2004 Red Hat, Inc. All rights reserved. * Copyright (C) 2004 Novell, Inc. All rights reserved. * Copyright (C) 2004 IBM, Inc. All rights reserved. * * Authors: * Robert Love <rml@novell.com> * Kay Sievers <kay.sievers@vrfy.org> * Arjan van de Ven <arjanv@redhat.com> * Greg Kroah-Hartman <greg@kroah.com> */ #include <linux/spinlock.h> #include <linux/string.h> #include <linux/kobject.h> #include <linux/export.h> #include <linux/kmod.h> #include <linux/slab.h> #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> #include <linux/uidgid.h> #include <linux/uuid.h> #include <linux/ctype.h> #include <net/sock.h> #include <net/netlink.h> #include <net/net_namespace.h> atomic64_t uevent_seqnum; #ifdef CONFIG_UEVENT_HELPER char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH; #endif struct uevent_sock { struct list_head list; struct sock *sk; }; #ifdef CONFIG_NET static LIST_HEAD(uevent_sock_list); /* This lock protects uevent_sock_list */ static DEFINE_MUTEX(uevent_sock_mutex); #endif /* the strings here must match the enum in include/linux/kobject.h */ static const char *kobject_actions[] = { [KOBJ_ADD] = "add", [KOBJ_REMOVE] = "remove", [KOBJ_CHANGE] = "change", [KOBJ_MOVE] = "move", [KOBJ_ONLINE] = "online", [KOBJ_OFFLINE] = "offline", [KOBJ_BIND] = "bind", [KOBJ_UNBIND] = "unbind", }; static int kobject_action_type(const char *buf, size_t count, enum kobject_action *type, const char **args) { enum kobject_action action; size_t count_first; const char *args_start; int ret = -EINVAL; if (count && (buf[count-1] == '\n' || buf[count-1] == '\0')) count--; if (!count) goto out; args_start = strnchr(buf, count, ' '); if (args_start) { count_first = args_start - buf; args_start = args_start + 1; } else count_first = count; for (action = 0; action < ARRAY_SIZE(kobject_actions); action++) { if (strncmp(kobject_actions[action], buf, count_first) != 0) continue; if (kobject_actions[action][count_first] != '\0') continue; if (args) *args = args_start; *type = action; ret = 0; break; } out: return ret; } static const char *action_arg_word_end(const char *buf, const char *buf_end, char delim) { const char *next = buf; while (next <= buf_end && *next != delim) if (!isalnum(*next++)) return NULL; if (next == buf) return NULL; return next; } static int kobject_action_args(const char *buf, size_t count, struct kobj_uevent_env **ret_env) { struct kobj_uevent_env *env = NULL; const char *next, *buf_end, *key; int key_len; int r = -EINVAL; if (count && (buf[count - 1] == '\n' || buf[count - 1] == '\0')) count--; if (!count) return -EINVAL; env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return -ENOMEM; /* first arg is UUID */ if (count < UUID_STRING_LEN || !uuid_is_valid(buf) || add_uevent_var(env, "SYNTH_UUID=%.*s", UUID_STRING_LEN, buf)) goto out; /* * the rest are custom environment variables in KEY=VALUE * format with ' ' delimiter between each KEY=VALUE pair */ next = buf + UUID_STRING_LEN; buf_end = buf + count - 1; while (next <= buf_end) { if (*next != ' ') goto out; /* skip the ' ', key must follow */ key = ++next; if (key > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, '='); if (!next || next > buf_end || *next != '=') goto out; key_len = next - buf; /* skip the '=', value must follow */ if (++next > buf_end) goto out; buf = next; next = action_arg_word_end(buf, buf_end, ' '); if (!next) goto out; if (add_uevent_var(env, "SYNTH_ARG_%.*s=%.*s", key_len, key, (int) (next - buf), buf)) goto out; } r = 0; out: if (r) kfree(env); else *ret_env = env; return r; } /** * kobject_synth_uevent - send synthetic uevent with arguments * * @kobj: struct kobject for which synthetic uevent is to be generated * @buf: buffer containing action type and action args, newline is ignored * @count: length of buffer * * Returns 0 if kobject_synthetic_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_synth_uevent(struct kobject *kobj, const char *buf, size_t count) { char *no_uuid_envp[] = { "SYNTH_UUID=0", NULL }; enum kobject_action action; const char *action_args; struct kobj_uevent_env *env; const char *msg = NULL, *devpath; int r; r = kobject_action_type(buf, count, &action, &action_args); if (r) { msg = "unknown uevent action string"; goto out; } if (!action_args) { r = kobject_uevent_env(kobj, action, no_uuid_envp); goto out; } r = kobject_action_args(action_args, count - (action_args - buf), &env); if (r == -EINVAL) { msg = "incorrect uevent action arguments"; goto out; } if (r) goto out; r = kobject_uevent_env(kobj, action, env->envp); kfree(env); out: if (r) { devpath = kobject_get_path(kobj, GFP_KERNEL); pr_warn("synth uevent: %s: %s\n", devpath ?: "unknown device", msg ?: "failed to send uevent"); kfree(devpath); } return r; } #ifdef CONFIG_UEVENT_HELPER static int kobj_usermode_filter(struct kobject *kobj) { const struct kobj_ns_type_operations *ops; ops = kobj_ns_ops(kobj); if (ops) { const void *init_ns, *ns; ns = kobj->ktype->namespace(kobj); init_ns = ops->initial_ns(); return ns != init_ns; } return 0; } static int init_uevent_argv(struct kobj_uevent_env *env, const char *subsystem) { int buffer_size = sizeof(env->buf) - env->buflen; int len; len = strscpy(&env->buf[env->buflen], subsystem, buffer_size); if (len < 0) { pr_warn("%s: insufficient buffer space (%u left) for %s\n", __func__, buffer_size, subsystem); return -ENOMEM; } env->argv[0] = uevent_helper; env->argv[1] = &env->buf[env->buflen]; env->argv[2] = NULL; env->buflen += len + 1; return 0; } static void cleanup_uevent_env(struct subprocess_info *info) { kfree(info->data); } #endif #ifdef CONFIG_NET static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct netlink_skb_parms *parms; struct sk_buff *skb = NULL; char *scratch; size_t len; /* allocate message with maximum possible size */ len = strlen(action_string) + strlen(devpath) + 2; skb = alloc_skb(len + env->buflen, GFP_KERNEL); if (!skb) return NULL; /* add header */ scratch = skb_put(skb, len); sprintf(scratch, "%s@%s", action_string, devpath); skb_put_data(skb, env->buf, env->buflen); parms = &NETLINK_CB(skb); parms->creds.uid = GLOBAL_ROOT_UID; parms->creds.gid = GLOBAL_ROOT_GID; parms->dst_group = 1; parms->portid = 0; return skb; } static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct sk_buff *skb = NULL; struct uevent_sock *ue_sk; int retval = 0; /* send netlink message */ mutex_lock(&uevent_sock_mutex); list_for_each_entry(ue_sk, &uevent_sock_list, list) { struct sock *uevent_sock = ue_sk->sk; if (!netlink_has_listeners(uevent_sock, 1)) continue; if (!skb) { retval = -ENOMEM; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) continue; } retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } mutex_unlock(&uevent_sock_mutex); consume_skb(skb); return retval; } static int uevent_net_broadcast_tagged(struct sock *usk, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { struct user_namespace *owning_user_ns = sock_net(usk)->user_ns; struct sk_buff *skb = NULL; int ret = 0; skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) return -ENOMEM; /* fix credentials */ if (owning_user_ns != &init_user_ns) { struct netlink_skb_parms *parms = &NETLINK_CB(skb); kuid_t root_uid; kgid_t root_gid; /* fix uid */ root_uid = make_kuid(owning_user_ns, 0); if (uid_valid(root_uid)) parms->creds.uid = root_uid; /* fix gid */ root_gid = make_kgid(owning_user_ns, 0); if (gid_valid(root_gid)) parms->creds.gid = root_gid; } ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } #endif static int kobject_uevent_net_broadcast(struct kobject *kobj, struct kobj_uevent_env *env, const char *action_string, const char *devpath) { int ret = 0; #ifdef CONFIG_NET const struct kobj_ns_type_operations *ops; const struct net *net = NULL; ops = kobj_ns_ops(kobj); if (!ops && kobj->kset) { struct kobject *ksobj = &kobj->kset->kobj; if (ksobj->parent != NULL) ops = kobj_ns_ops(ksobj->parent); } /* kobjects currently only carry network namespace tags and they * are the only tag relevant here since we want to decide which * network namespaces to broadcast the uevent into. */ if (ops && ops->netlink_ns && kobj->ktype->namespace) if (ops->type == KOBJ_NS_TYPE_NET) net = kobj->ktype->namespace(kobj); if (!net) ret = uevent_net_broadcast_untagged(env, action_string, devpath); else ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, action_string, devpath); #endif return ret; } static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; size_t len; int i, j; for (i = 0; i < env->envp_idx;) { if (strncmp(env->envp[i], modalias_prefix, sizeof(modalias_prefix) - 1)) { i++; continue; } len = strlen(env->envp[i]) + 1; if (i != env->envp_idx - 1) { memmove(env->envp[i], env->envp[i + 1], env->buflen - len); for (j = i; j < env->envp_idx - 1; j++) env->envp[j] = env->envp[j + 1] - len; } env->envp_idx--; env->buflen -= len; } } /** * kobject_uevent_env - send an uevent with environmental data * * @kobj: struct kobject that the action is happening to * @action: action that is happening * @envp_ext: pointer to environmental data * * Returns 0 if kobject_uevent_env() is completed with success or the * corresponding error when it fails. */ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action, char *envp_ext[]) { struct kobj_uevent_env *env; const char *action_string = kobject_actions[action]; const char *devpath = NULL; const char *subsystem; struct kobject *top_kobj; struct kset *kset; const struct kset_uevent_ops *uevent_ops; int i = 0; int retval = 0; /* * Mark "remove" event done regardless of result, for some subsystems * do not want to re-trigger "remove" event via automatic cleanup. */ if (action == KOBJ_REMOVE) kobj->state_remove_uevent_sent = 1; pr_debug("kobject: '%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); /* search the kset we belong to */ top_kobj = kobj; while (!top_kobj->kset && top_kobj->parent) top_kobj = top_kobj->parent; if (!top_kobj->kset) { pr_debug("kobject: '%s' (%p): %s: attempted to send uevent " "without kset!\n", kobject_name(kobj), kobj, __func__); return -EINVAL; } kset = top_kobj->kset; uevent_ops = kset->uevent_ops; /* skip the event, if uevent_suppress is set*/ if (kobj->uevent_suppress) { pr_debug("kobject: '%s' (%p): %s: uevent_suppress " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* skip the event, if the filter returns zero. */ if (uevent_ops && uevent_ops->filter) if (!uevent_ops->filter(kobj)) { pr_debug("kobject: '%s' (%p): %s: filter function " "caused the event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* originating subsystem */ if (uevent_ops && uevent_ops->name) subsystem = uevent_ops->name(kobj); else subsystem = kobject_name(&kset->kobj); if (!subsystem) { pr_debug("kobject: '%s' (%p): %s: unset subsystem caused the " "event to drop!\n", kobject_name(kobj), kobj, __func__); return 0; } /* environment buffer */ env = kzalloc(sizeof(struct kobj_uevent_env), GFP_KERNEL); if (!env) return -ENOMEM; /* complete object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { retval = -ENOENT; goto exit; } /* default keys */ retval = add_uevent_var(env, "ACTION=%s", action_string); if (retval) goto exit; retval = add_uevent_var(env, "DEVPATH=%s", devpath); if (retval) goto exit; retval = add_uevent_var(env, "SUBSYSTEM=%s", subsystem); if (retval) goto exit; /* keys passed in from the caller */ if (envp_ext) { for (i = 0; envp_ext[i]; i++) { retval = add_uevent_var(env, "%s", envp_ext[i]); if (retval) goto exit; } } /* let the kset specific function add its stuff */ if (uevent_ops && uevent_ops->uevent) { retval = uevent_ops->uevent(kobj, env); if (retval) { pr_debug("kobject: '%s' (%p): %s: uevent() returned " "%d\n", kobject_name(kobj), kobj, __func__, retval); goto exit; } } switch (action) { case KOBJ_ADD: /* * Mark "add" event so we can make sure we deliver "remove" * event to userspace during automatic cleanup. If * the object did send an "add" event, "remove" will * automatically generated by the core, if not already done * by the caller. */ kobj->state_add_uevent_sent = 1; break; case KOBJ_UNBIND: zap_modalias_env(env); break; default: break; } /* we will send an event, so request a new sequence number */ retval = add_uevent_var(env, "SEQNUM=%llu", atomic64_inc_return(&uevent_seqnum)); if (retval) goto exit; retval = kobject_uevent_net_broadcast(kobj, env, action_string, devpath); #ifdef CONFIG_UEVENT_HELPER /* call uevent_helper, usually only enabled during early boot */ if (uevent_helper[0] && !kobj_usermode_filter(kobj)) { struct subprocess_info *info; retval = add_uevent_var(env, "HOME=/"); if (retval) goto exit; retval = add_uevent_var(env, "PATH=/sbin:/bin:/usr/sbin:/usr/bin"); if (retval) goto exit; retval = init_uevent_argv(env, subsystem); if (retval) goto exit; retval = -ENOMEM; info = call_usermodehelper_setup(env->argv[0], env->argv, env->envp, GFP_KERNEL, NULL, cleanup_uevent_env, env); if (info) { retval = call_usermodehelper_exec(info, UMH_NO_WAIT); env = NULL; /* freed by cleanup_uevent_env */ } } #endif exit: kfree(devpath); kfree(env); return retval; } EXPORT_SYMBOL_GPL(kobject_uevent_env); /** * kobject_uevent - notify userspace by sending an uevent * * @kobj: struct kobject that the action is happening to * @action: action that is happening * * Returns 0 if kobject_uevent() is completed with success or the * corresponding error when it fails. */ int kobject_uevent(struct kobject *kobj, enum kobject_action action) { return kobject_uevent_env(kobj, action, NULL); } EXPORT_SYMBOL_GPL(kobject_uevent); /** * add_uevent_var - add key value string to the environment buffer * @env: environment buffer structure * @format: printf format for the key=value pair * * Returns 0 if environment variable was added successfully or -ENOMEM * if no space was available. */ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...) { va_list args; int len; if (env->envp_idx >= ARRAY_SIZE(env->envp)) { WARN(1, KERN_ERR "add_uevent_var: too many keys\n"); return -ENOMEM; } va_start(args, format); len = vsnprintf(&env->buf[env->buflen], sizeof(env->buf) - env->buflen, format, args); va_end(args); if (len >= (sizeof(env->buf) - env->buflen)) { WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n"); return -ENOMEM; } env->envp[env->envp_idx++] = &env->buf[env->buflen]; env->buflen += len + 1; return 0; } EXPORT_SYMBOL_GPL(add_uevent_var); #if defined(CONFIG_NET) static int uevent_net_broadcast(struct sock *usk, struct sk_buff *skb, struct netlink_ext_ack *extack) { /* u64 to chars: 2^64 - 1 = 21 chars */ char buf[sizeof("SEQNUM=") + 21]; struct sk_buff *skbc; int ret; /* bump and prepare sequence number */ ret = snprintf(buf, sizeof(buf), "SEQNUM=%llu", atomic64_inc_return(&uevent_seqnum)); if (ret < 0 || (size_t)ret >= sizeof(buf)) return -ENOMEM; ret++; /* verify message does not overflow */ if ((skb->len + ret) > UEVENT_BUFFER_SIZE) { NL_SET_ERR_MSG(extack, "uevent message too big"); return -EINVAL; } /* copy skb and extend to accommodate sequence number */ skbc = skb_copy_expand(skb, 0, ret, GFP_KERNEL); if (!skbc) return -ENOMEM; /* append sequence number */ skb_put_data(skbc, buf, ret); /* remove msg header */ skb_pull(skbc, NLMSG_HDRLEN); /* set portid 0 to inform userspace message comes from kernel */ NETLINK_CB(skbc).portid = 0; NETLINK_CB(skbc).dst_group = 1; ret = netlink_broadcast(usk, skbc, 0, 1, GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (ret == -ENOBUFS || ret == -ESRCH) ret = 0; return ret; } static int uevent_net_rcv_skb(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net; int ret; if (!nlmsg_data(nlh)) return -EINVAL; /* * Verify that we are allowed to send messages to the target * network namespace. The caller must have CAP_SYS_ADMIN in the * owning user namespace of the target network namespace. */ net = sock_net(NETLINK_CB(skb).sk); if (!netlink_ns_capable(skb, net->user_ns, CAP_SYS_ADMIN)) { NL_SET_ERR_MSG(extack, "missing CAP_SYS_ADMIN capability"); return -EPERM; } ret = uevent_net_broadcast(net->uevent_sock->sk, skb, extack); return ret; } static void uevent_net_rcv(struct sk_buff *skb) { netlink_rcv_skb(skb, &uevent_net_rcv_skb); } static int uevent_net_init(struct net *net) { struct uevent_sock *ue_sk; struct netlink_kernel_cfg cfg = { .groups = 1, .input = uevent_net_rcv, .flags = NL_CFG_F_NONROOT_RECV }; ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL); if (!ue_sk) return -ENOMEM; ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg); if (!ue_sk->sk) { pr_err("kobject_uevent: unable to create netlink socket!\n"); kfree(ue_sk); return -ENODEV; } net->uevent_sock = ue_sk; /* Restrict uevents to initial user namespace. */ if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_add_tail(&ue_sk->list, &uevent_sock_list); mutex_unlock(&uevent_sock_mutex); } return 0; } static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk = net->uevent_sock; if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { mutex_lock(&uevent_sock_mutex); list_del(&ue_sk->list); mutex_unlock(&uevent_sock_mutex); } netlink_kernel_release(ue_sk->sk); kfree(ue_sk); } static struct pernet_operations uevent_net_ops = { .init = uevent_net_init, .exit = uevent_net_exit, }; static int __init kobject_uevent_init(void) { return register_pernet_subsys(&uevent_net_ops); } postcore_initcall(kobject_uevent_init); #endif |
| 15 60 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _ASM_GENERIC_HUGETLB_H #define _ASM_GENERIC_HUGETLB_H #include <linux/swap.h> #include <linux/swapops.h> static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) { return mk_pte(page, pgprot); } static inline unsigned long huge_pte_write(pte_t pte) { return pte_write(pte); } static inline unsigned long huge_pte_dirty(pte_t pte) { return pte_dirty(pte); } static inline pte_t huge_pte_mkwrite(pte_t pte) { return pte_mkwrite_novma(pte); } #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT static inline pte_t huge_pte_wrprotect(pte_t pte) { return pte_wrprotect(pte); } #endif static inline pte_t huge_pte_mkdirty(pte_t pte) { return pte_mkdirty(pte); } static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) { return pte_modify(pte, newprot); } static inline pte_t huge_pte_mkuffd_wp(pte_t pte) { return huge_pte_wrprotect(pte_mkuffd_wp(pte)); } static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) { return pte_clear_uffd_wp(pte); } static inline int huge_pte_uffd_wp(pte_t pte) { return pte_uffd_wp(pte); } #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { pte_clear(mm, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr, unsigned long end, unsigned long floor, unsigned long ceiling) { free_pgd_range(tlb, addr, end, floor, ceiling); } #endif #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { set_pte_at(mm, addr, ptep, pte); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { return ptep_get_and_clear(mm, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return ptep_clear_flush(vma, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_PTE_NONE static inline int huge_pte_none(pte_t pte) { return pte_none(pte); } #endif /* Please refer to comments above pte_none_mostly() for the usage */ static inline int huge_pte_none_mostly(pte_t pte) { return huge_pte_none(pte) || is_pte_marker(pte); } #ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE static inline int prepare_hugepage_range(struct file *file, unsigned long addr, unsigned long len) { struct hstate *h = hstate_file(file); if (len & ~huge_page_mask(h)) return -EINVAL; if (addr & ~huge_page_mask(h)) return -EINVAL; return 0; } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT static inline void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { ptep_set_wrprotect(mm, addr, ptep); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { return ptep_set_access_flags(vma, addr, ptep, pte, dirty); } #endif #ifndef __HAVE_ARCH_HUGE_PTEP_GET static inline pte_t huge_ptep_get(pte_t *ptep) { return ptep_get(ptep); } #endif #ifndef __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED static inline bool gigantic_page_runtime_supported(void) { return IS_ENABLED(CONFIG_ARCH_HAS_GIGANTIC_PAGE); } #endif /* __HAVE_ARCH_GIGANTIC_PAGE_RUNTIME_SUPPORTED */ #endif /* _ASM_GENERIC_HUGETLB_H */ |
| 117 117 117 117 117 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/mmu_notifier.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/mm_inline.h> #include <linux/kthread.h> #include <linux/khugepaged.h> #include <linux/freezer.h> #include <linux/mman.h> #include <linux/hashtable.h> #include <linux/userfaultfd_k.h> #include <linux/page_idle.h> #include <linux/page_table_check.h> #include <linux/rcupdate_wait.h> #include <linux/swapops.h> #include <linux/shmem_fs.h> #include <linux/ksm.h> #include <asm/tlb.h> #include <asm/pgalloc.h> #include "internal.h" #include "mm_slot.h" enum scan_result { SCAN_FAIL, SCAN_SUCCEED, SCAN_PMD_NULL, SCAN_PMD_NONE, SCAN_PMD_MAPPED, SCAN_EXCEED_NONE_PTE, SCAN_EXCEED_SWAP_PTE, SCAN_EXCEED_SHARED_PTE, SCAN_PTE_NON_PRESENT, SCAN_PTE_UFFD_WP, SCAN_PTE_MAPPED_HUGEPAGE, SCAN_PAGE_RO, SCAN_LACK_REFERENCED_PAGE, SCAN_PAGE_NULL, SCAN_SCAN_ABORT, SCAN_PAGE_COUNT, SCAN_PAGE_LRU, SCAN_PAGE_LOCK, SCAN_PAGE_ANON, SCAN_PAGE_COMPOUND, SCAN_ANY_PROCESS, SCAN_VMA_NULL, SCAN_VMA_CHECK, SCAN_ADDRESS_RANGE, SCAN_DEL_PAGE_LRU, SCAN_ALLOC_HUGE_PAGE_FAIL, SCAN_CGROUP_CHARGE_FAIL, SCAN_TRUNCATED, SCAN_PAGE_HAS_PRIVATE, SCAN_STORE_FAILED, SCAN_COPY_MC, SCAN_PAGE_FILLED, }; #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> static struct task_struct *khugepaged_thread __read_mostly; static DEFINE_MUTEX(khugepaged_mutex); /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; static unsigned int khugepaged_full_scans; static unsigned int khugepaged_scan_sleep_millisecs __read_mostly = 10000; /* during fragmentation poll the hugepage allocator once every minute */ static unsigned int khugepaged_alloc_sleep_millisecs __read_mostly = 60000; static unsigned long khugepaged_sleep_expire; static DEFINE_SPINLOCK(khugepaged_mm_lock); static DECLARE_WAIT_QUEUE_HEAD(khugepaged_wait); /* * default collapse hugepages if there is at least one pte mapped like * it would have happened if the vma was large enough during page * fault. * * Note that these are only respected if collapse was initiated by khugepaged. */ static unsigned int khugepaged_max_ptes_none __read_mostly; static unsigned int khugepaged_max_ptes_swap __read_mostly; static unsigned int khugepaged_max_ptes_shared __read_mostly; #define MM_SLOTS_HASH_BITS 10 static DEFINE_READ_MOSTLY_HASHTABLE(mm_slots_hash, MM_SLOTS_HASH_BITS); static struct kmem_cache *mm_slot_cache __ro_after_init; struct collapse_control { bool is_khugepaged; /* Num pages scanned per node */ u32 node_load[MAX_NUMNODES]; /* nodemask for allocation fallback */ nodemask_t alloc_nmask; }; /** * struct khugepaged_mm_slot - khugepaged information per mm that is being scanned * @slot: hash lookup from mm to mm_slot */ struct khugepaged_mm_slot { struct mm_slot slot; }; /** * struct khugepaged_scan - cursor for scanning * @mm_head: the head of the mm list to scan * @mm_slot: the current mm_slot we are scanning * @address: the next address inside that to be scanned * * There is only the one khugepaged_scan instance of this cursor structure. */ struct khugepaged_scan { struct list_head mm_head; struct khugepaged_mm_slot *mm_slot; unsigned long address; }; static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; #ifdef CONFIG_SYSFS static ssize_t scan_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_scan_sleep_millisecs); } static ssize_t scan_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_scan_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute scan_sleep_millisecs_attr = __ATTR_RW(scan_sleep_millisecs); static ssize_t alloc_sleep_millisecs_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_alloc_sleep_millisecs); } static ssize_t alloc_sleep_millisecs_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int msecs; int err; err = kstrtouint(buf, 10, &msecs); if (err) return -EINVAL; khugepaged_alloc_sleep_millisecs = msecs; khugepaged_sleep_expire = 0; wake_up_interruptible(&khugepaged_wait); return count; } static struct kobj_attribute alloc_sleep_millisecs_attr = __ATTR_RW(alloc_sleep_millisecs); static ssize_t pages_to_scan_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_to_scan); } static ssize_t pages_to_scan_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { unsigned int pages; int err; err = kstrtouint(buf, 10, &pages); if (err || !pages) return -EINVAL; khugepaged_pages_to_scan = pages; return count; } static struct kobj_attribute pages_to_scan_attr = __ATTR_RW(pages_to_scan); static ssize_t pages_collapsed_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_pages_collapsed); } static struct kobj_attribute pages_collapsed_attr = __ATTR_RO(pages_collapsed); static ssize_t full_scans_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_full_scans); } static struct kobj_attribute full_scans_attr = __ATTR_RO(full_scans); static ssize_t defrag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return single_hugepage_flag_show(kobj, attr, buf, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static ssize_t defrag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { return single_hugepage_flag_store(kobj, attr, buf, count, TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG); } static struct kobj_attribute khugepaged_defrag_attr = __ATTR_RW(defrag); /* * max_ptes_none controls if khugepaged should collapse hugepages over * any unmapped ptes in turn potentially increasing the memory * footprint of the vmas. When max_ptes_none is 0 khugepaged will not * reduce the available free memory in the system as it * runs. Increasing max_ptes_none will instead potentially reduce the * free memory in the system during the khugepaged scan. */ static ssize_t max_ptes_none_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_none); } static ssize_t max_ptes_none_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_none; err = kstrtoul(buf, 10, &max_ptes_none); if (err || max_ptes_none > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_none = max_ptes_none; return count; } static struct kobj_attribute khugepaged_max_ptes_none_attr = __ATTR_RW(max_ptes_none); static ssize_t max_ptes_swap_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_swap); } static ssize_t max_ptes_swap_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_swap; err = kstrtoul(buf, 10, &max_ptes_swap); if (err || max_ptes_swap > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_swap = max_ptes_swap; return count; } static struct kobj_attribute khugepaged_max_ptes_swap_attr = __ATTR_RW(max_ptes_swap); static ssize_t max_ptes_shared_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { return sysfs_emit(buf, "%u\n", khugepaged_max_ptes_shared); } static ssize_t max_ptes_shared_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { int err; unsigned long max_ptes_shared; err = kstrtoul(buf, 10, &max_ptes_shared); if (err || max_ptes_shared > HPAGE_PMD_NR - 1) return -EINVAL; khugepaged_max_ptes_shared = max_ptes_shared; return count; } static struct kobj_attribute khugepaged_max_ptes_shared_attr = __ATTR_RW(max_ptes_shared); static struct attribute *khugepaged_attr[] = { &khugepaged_defrag_attr.attr, &khugepaged_max_ptes_none_attr.attr, &khugepaged_max_ptes_swap_attr.attr, &khugepaged_max_ptes_shared_attr.attr, &pages_to_scan_attr.attr, &pages_collapsed_attr.attr, &full_scans_attr.attr, &scan_sleep_millisecs_attr.attr, &alloc_sleep_millisecs_attr.attr, NULL, }; struct attribute_group khugepaged_attr_group = { .attrs = khugepaged_attr, .name = "khugepaged", }; #endif /* CONFIG_SYSFS */ int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { switch (advice) { case MADV_HUGEPAGE: #ifdef CONFIG_S390 /* * qemu blindly sets MADV_HUGEPAGE on all allocations, but s390 * can't handle this properly after s390_enable_sie, so we simply * ignore the madvise to prevent qemu from causing a SIGSEGV. */ if (mm_has_pgste(vma->vm_mm)) return 0; #endif *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; /* * If the vma become good for khugepaged to scan, * register it here without waiting a page fault that * may not happen any time soon. */ khugepaged_enter_vma(vma, *vm_flags); break; case MADV_NOHUGEPAGE: *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; /* * Setting VM_NOHUGEPAGE will prevent khugepaged from scanning * this vma even if we leave the mm registered in khugepaged if * it got registered before VM_NOHUGEPAGE was set. */ break; } return 0; } int __init khugepaged_init(void) { mm_slot_cache = kmem_cache_create("khugepaged_mm_slot", sizeof(struct khugepaged_mm_slot), __alignof__(struct khugepaged_mm_slot), 0, NULL); if (!mm_slot_cache) return -ENOMEM; khugepaged_pages_to_scan = HPAGE_PMD_NR * 8; khugepaged_max_ptes_none = HPAGE_PMD_NR - 1; khugepaged_max_ptes_swap = HPAGE_PMD_NR / 8; khugepaged_max_ptes_shared = HPAGE_PMD_NR / 2; return 0; } void __init khugepaged_destroy(void) { kmem_cache_destroy(mm_slot_cache); } static inline int hpage_collapse_test_exit(struct mm_struct *mm) { return atomic_read(&mm->mm_users) == 0; } static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm) { return hpage_collapse_test_exit(mm) || test_bit(MMF_DISABLE_THP, &mm->flags); } void __khugepaged_enter(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int wakeup; /* __khugepaged_exit() must not run from under us */ VM_BUG_ON_MM(hpage_collapse_test_exit(mm), mm); if (unlikely(test_and_set_bit(MMF_VM_HUGEPAGE, &mm->flags))) return; mm_slot = mm_slot_alloc(mm_slot_cache); if (!mm_slot) return; slot = &mm_slot->slot; spin_lock(&khugepaged_mm_lock); mm_slot_insert(mm_slots_hash, mm, slot); /* * Insert just behind the scanning cursor, to let the area settle * down a little. */ wakeup = list_empty(&khugepaged_scan.mm_head); list_add_tail(&slot->mm_node, &khugepaged_scan.mm_head); spin_unlock(&khugepaged_mm_lock); mmgrab(mm); if (wakeup) wake_up_interruptible(&khugepaged_wait); } void khugepaged_enter_vma(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) && hugepage_flags_enabled()) { if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) __khugepaged_enter(vma->vm_mm); } } void __khugepaged_exit(struct mm_struct *mm) { struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; int free = 0; spin_lock(&khugepaged_mm_lock); slot = mm_slot_lookup(mm_slots_hash, mm); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); if (mm_slot && khugepaged_scan.mm_slot != mm_slot) { hash_del(&slot->hash); list_del(&slot->mm_node); free = 1; } spin_unlock(&khugepaged_mm_lock); if (free) { clear_bit(MMF_VM_HUGEPAGE, &mm->flags); mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } else if (mm_slot) { /* * This is required to serialize against * hpage_collapse_test_exit() (which is guaranteed to run * under mmap sem read mode). Stop here (after we return all * pagetables will be destroyed) until khugepaged has finished * working on the pagetables under the mmap_lock. */ mmap_write_lock(mm); mmap_write_unlock(mm); } } static void release_pte_folio(struct folio *folio) { node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), -folio_nr_pages(folio)); folio_unlock(folio); folio_putback_lru(folio); } static void release_pte_pages(pte_t *pte, pte_t *_pte, struct list_head *compound_pagelist) { struct folio *folio, *tmp; while (--_pte >= pte) { pte_t pteval = ptep_get(_pte); unsigned long pfn; if (pte_none(pteval)) continue; pfn = pte_pfn(pteval); if (is_zero_pfn(pfn)) continue; folio = pfn_folio(pfn); if (folio_test_large(folio)) continue; release_pte_folio(folio); } list_for_each_entry_safe(folio, tmp, compound_pagelist, lru) { list_del(&folio->lru); release_pte_folio(folio); } } static bool is_refcount_suitable(struct folio *folio) { int expected_refcount; expected_refcount = folio_mapcount(folio); if (folio_test_swapcache(folio)) expected_refcount += folio_nr_pages(folio); return folio_ref_count(folio) == expected_refcount; } static int __collapse_huge_page_isolate(struct vm_area_struct *vma, unsigned long address, pte_t *pte, struct collapse_control *cc, struct list_head *compound_pagelist) { struct page *page = NULL; struct folio *folio = NULL; pte_t *_pte; int none_or_zero = 0, shared = 0, result = SCAN_FAIL, referenced = 0; bool writable = false; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (pte_none(pteval) || (pte_present(pteval) && is_zero_pfn(pte_pfn(pteval)))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out; } } if (!pte_present(pteval)) { result = SCAN_PTE_NON_PRESENT; goto out; } if (pte_uffd_wp(pteval)) { result = SCAN_PTE_UFFD_WP; goto out; } page = vm_normal_page(vma, address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out; } folio = page_folio(page); VM_BUG_ON_FOLIO(!folio_test_anon(folio), folio); /* See hpage_collapse_scan_pmd(). */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out; } } if (folio_test_large(folio)) { struct folio *f; /* * Check if we have dealt with the compound page * already */ list_for_each_entry(f, compound_pagelist, lru) { if (folio == f) goto next; } } /* * We can do it before isolate_lru_page because the * page can't be freed from under us. NOTE: PG_lock * is needed to serialize against split_huge_page * when invoked from the VM. */ if (!folio_trylock(folio)) { result = SCAN_PAGE_LOCK; goto out; } /* * Check if the page has any GUP (or other external) pins. * * The page table that maps the page has been already unlinked * from the page table tree and this process cannot get * an additional pin on the page. * * New pins can come later if the page is shared across fork, * but not from this process. The other process cannot write to * the page, only trigger CoW. */ if (!is_refcount_suitable(folio)) { folio_unlock(folio); result = SCAN_PAGE_COUNT; goto out; } /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. */ if (!folio_isolate_lru(folio)) { folio_unlock(folio); result = SCAN_DEL_PAGE_LRU; goto out; } node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); VM_BUG_ON_FOLIO(folio_test_lru(folio), folio); if (folio_test_large(folio)) list_add_tail(&folio->lru, compound_pagelist); next: /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; if (pte_write(pteval)) writable = true; } if (unlikely(!writable)) { result = SCAN_PAGE_RO; } else if (unlikely(cc->is_khugepaged && !referenced)) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } out: release_pte_pages(pte, _pte, compound_pagelist); trace_mm_collapse_huge_page_isolate(&folio->page, none_or_zero, referenced, writable, result); return result; } static void __collapse_huge_page_copy_succeeded(pte_t *pte, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { struct folio *src, *tmp; pte_t *_pte; pte_t pteval; for (_pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pteval = ptep_get(_pte); if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { add_mm_counter(vma->vm_mm, MM_ANONPAGES, 1); if (is_zero_pfn(pte_pfn(pteval))) { /* * ptl mostly unnecessary. */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); spin_unlock(ptl); ksm_might_unmap_zero_page(vma->vm_mm, pteval); } } else { struct page *src_page = pte_page(pteval); src = page_folio(src_page); if (!folio_test_large(src)) release_pte_folio(src); /* * ptl mostly unnecessary, but preempt has to * be disabled to update the per-cpu stats * inside folio_remove_rmap_pte(). */ spin_lock(ptl); ptep_clear(vma->vm_mm, address, _pte); folio_remove_rmap_pte(src, src_page, vma); spin_unlock(ptl); free_page_and_swap_cache(src_page); } } list_for_each_entry_safe(src, tmp, compound_pagelist, lru) { list_del(&src->lru); node_stat_sub_folio(src, NR_ISOLATED_ANON + folio_is_file_lru(src)); folio_unlock(src); free_swap_cache(src); folio_putback_lru(src); } } static void __collapse_huge_page_copy_failed(pte_t *pte, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, struct list_head *compound_pagelist) { spinlock_t *pmd_ptl; /* * Re-establish the PMD to point to the original page table * entry. Restoring PMD needs to be done prior to releasing * pages. Since pages are still isolated and locked here, * acquiring anon_vma_lock_write is unnecessary. */ pmd_ptl = pmd_lock(vma->vm_mm, pmd); pmd_populate(vma->vm_mm, pmd, pmd_pgtable(orig_pmd)); spin_unlock(pmd_ptl); /* * Release both raw and compound pages isolated * in __collapse_huge_page_isolate. */ release_pte_pages(pte, pte + HPAGE_PMD_NR, compound_pagelist); } /* * __collapse_huge_page_copy - attempts to copy memory contents from raw * pages to a hugepage. Cleans up the raw pages if copying succeeds; * otherwise restores the original page table and releases isolated raw pages. * Returns SCAN_SUCCEED if copying succeeds, otherwise returns SCAN_COPY_MC. * * @pte: starting of the PTEs to copy from * @folio: the new hugepage to copy contents to * @pmd: pointer to the new hugepage's PMD * @orig_pmd: the original raw pages' PMD * @vma: the original raw pages' virtual memory area * @address: starting address to copy * @ptl: lock on raw pages' PTEs * @compound_pagelist: list that stores compound pages */ static int __collapse_huge_page_copy(pte_t *pte, struct folio *folio, pmd_t *pmd, pmd_t orig_pmd, struct vm_area_struct *vma, unsigned long address, spinlock_t *ptl, struct list_head *compound_pagelist) { unsigned int i; int result = SCAN_SUCCEED; /* * Copying pages' contents is subject to memory poison at any iteration. */ for (i = 0; i < HPAGE_PMD_NR; i++) { pte_t pteval = ptep_get(pte + i); struct page *page = folio_page(folio, i); unsigned long src_addr = address + i * PAGE_SIZE; struct page *src_page; if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { clear_user_highpage(page, src_addr); continue; } src_page = pte_page(pteval); if (copy_mc_user_highpage(page, src_page, src_addr, vma) > 0) { result = SCAN_COPY_MC; break; } } if (likely(result == SCAN_SUCCEED)) __collapse_huge_page_copy_succeeded(pte, vma, address, ptl, compound_pagelist); else __collapse_huge_page_copy_failed(pte, pmd, orig_pmd, vma, compound_pagelist); return result; } static void khugepaged_alloc_sleep(void) { DEFINE_WAIT(wait); add_wait_queue(&khugepaged_wait, &wait); __set_current_state(TASK_INTERRUPTIBLE|TASK_FREEZABLE); schedule_timeout(msecs_to_jiffies(khugepaged_alloc_sleep_millisecs)); remove_wait_queue(&khugepaged_wait, &wait); } struct collapse_control khugepaged_collapse_control = { .is_khugepaged = true, }; static bool hpage_collapse_scan_abort(int nid, struct collapse_control *cc) { int i; /* * If node_reclaim_mode is disabled, then no extra effort is made to * allocate memory locally. */ if (!node_reclaim_enabled()) return false; /* If there is a count for this node already, it must be acceptable */ if (cc->node_load[nid]) return false; for (i = 0; i < MAX_NUMNODES; i++) { if (!cc->node_load[i]) continue; if (node_distance(nid, i) > node_reclaim_distance) return true; } return false; } #define khugepaged_defrag() \ (transparent_hugepage_flags & \ (1<<TRANSPARENT_HUGEPAGE_DEFRAG_KHUGEPAGED_FLAG)) /* Defrag for khugepaged will enter direct reclaim/compaction if necessary */ static inline gfp_t alloc_hugepage_khugepaged_gfpmask(void) { return khugepaged_defrag() ? GFP_TRANSHUGE : GFP_TRANSHUGE_LIGHT; } #ifdef CONFIG_NUMA static int hpage_collapse_find_target_node(struct collapse_control *cc) { int nid, target_node = 0, max_value = 0; /* find first node with max normal pages hit */ for (nid = 0; nid < MAX_NUMNODES; nid++) if (cc->node_load[nid] > max_value) { max_value = cc->node_load[nid]; target_node = nid; } for_each_online_node(nid) { if (max_value == cc->node_load[nid]) node_set(nid, cc->alloc_nmask); } return target_node; } #else static int hpage_collapse_find_target_node(struct collapse_control *cc) { return 0; } #endif /* * If mmap_lock temporarily dropped, revalidate vma * before taking mmap_lock. * Returns enum scan_result value. */ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address, bool expect_anon, struct vm_area_struct **vmap, struct collapse_control *cc) { struct vm_area_struct *vma; unsigned long tva_flags = cc->is_khugepaged ? TVA_ENFORCE_SYSFS : 0; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) return SCAN_ANY_PROCESS; *vmap = vma = find_vma(mm, address); if (!vma) return SCAN_VMA_NULL; if (!thp_vma_suitable_order(vma, address, PMD_ORDER)) return SCAN_ADDRESS_RANGE; if (!thp_vma_allowable_order(vma, vma->vm_flags, tva_flags, PMD_ORDER)) return SCAN_VMA_CHECK; /* * Anon VMA expected, the address may be unmapped then * remapped to file after khugepaged reaquired the mmap_lock. * * thp_vma_allowable_order may return true for qualified file * vmas. */ if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap))) return SCAN_PAGE_ANON; return SCAN_SUCCEED; } static int find_pmd_or_thp_or_none(struct mm_struct *mm, unsigned long address, pmd_t **pmd) { pmd_t pmde; *pmd = mm_find_pmd(mm, address); if (!*pmd) return SCAN_PMD_NULL; pmde = pmdp_get_lockless(*pmd); if (pmd_none(pmde)) return SCAN_PMD_NONE; if (!pmd_present(pmde)) return SCAN_PMD_NULL; if (pmd_trans_huge(pmde)) return SCAN_PMD_MAPPED; if (pmd_devmap(pmde)) return SCAN_PMD_NULL; if (pmd_bad(pmde)) return SCAN_PMD_NULL; return SCAN_SUCCEED; } static int check_pmd_still_valid(struct mm_struct *mm, unsigned long address, pmd_t *pmd) { pmd_t *new_pmd; int result = find_pmd_or_thp_or_none(mm, address, &new_pmd); if (result != SCAN_SUCCEED) return result; if (new_pmd != pmd) return SCAN_FAIL; return SCAN_SUCCEED; } /* * Bring missing pages in from swap, to complete THP collapse. * Only done if hpage_collapse_scan_pmd believes it is worthwhile. * * Called and returns without pte mapped or spinlocks held. * Returns result: if not SCAN_SUCCEED, mmap_lock has been released. */ static int __collapse_huge_page_swapin(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, int referenced) { int swapped_in = 0; vm_fault_t ret = 0; unsigned long address, end = haddr + (HPAGE_PMD_NR * PAGE_SIZE); int result; pte_t *pte = NULL; spinlock_t *ptl; for (address = haddr; address < end; address += PAGE_SIZE) { struct vm_fault vmf = { .vma = vma, .address = address, .pgoff = linear_page_index(vma, address), .flags = FAULT_FLAG_ALLOW_RETRY, .pmd = pmd, }; if (!pte++) { pte = pte_offset_map_nolock(mm, pmd, address, &ptl); if (!pte) { mmap_read_unlock(mm); result = SCAN_PMD_NULL; goto out; } } vmf.orig_pte = ptep_get_lockless(pte); if (!is_swap_pte(vmf.orig_pte)) continue; vmf.pte = pte; vmf.ptl = ptl; ret = do_swap_page(&vmf); /* Which unmaps pte (after perhaps re-checking the entry) */ pte = NULL; /* * do_swap_page returns VM_FAULT_RETRY with released mmap_lock. * Note we treat VM_FAULT_RETRY as VM_FAULT_ERROR here because * we do not retry here and swap entry will remain in pagetable * resulting in later failure. */ if (ret & VM_FAULT_RETRY) { /* Likely, but not guaranteed, that page lock failed */ result = SCAN_PAGE_LOCK; goto out; } if (ret & VM_FAULT_ERROR) { mmap_read_unlock(mm); result = SCAN_FAIL; goto out; } swapped_in++; } if (pte) pte_unmap(pte); /* Drain LRU cache to remove extra pin on the swapped in pages */ if (swapped_in) lru_add_drain(); result = SCAN_SUCCEED; out: trace_mm_collapse_huge_page_swapin(mm, swapped_in, referenced, result); return result; } static int alloc_charge_folio(struct folio **foliop, struct mm_struct *mm, struct collapse_control *cc) { gfp_t gfp = (cc->is_khugepaged ? alloc_hugepage_khugepaged_gfpmask() : GFP_TRANSHUGE); int node = hpage_collapse_find_target_node(cc); struct folio *folio; folio = __folio_alloc(gfp, HPAGE_PMD_ORDER, node, &cc->alloc_nmask); if (!folio) { *foliop = NULL; count_vm_event(THP_COLLAPSE_ALLOC_FAILED); return SCAN_ALLOC_HUGE_PAGE_FAIL; } count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_charge(folio, mm, gfp))) { folio_put(folio); *foliop = NULL; return SCAN_CGROUP_CHARGE_FAIL; } count_memcg_folio_events(folio, THP_COLLAPSE_ALLOC, 1); *foliop = folio; return SCAN_SUCCEED; } static int collapse_huge_page(struct mm_struct *mm, unsigned long address, int referenced, int unmapped, struct collapse_control *cc) { LIST_HEAD(compound_pagelist); pmd_t *pmd, _pmd; pte_t *pte; pgtable_t pgtable; struct folio *folio; spinlock_t *pmd_ptl, *pte_ptl; int result = SCAN_FAIL; struct vm_area_struct *vma; struct mmu_notifier_range range; VM_BUG_ON(address & ~HPAGE_PMD_MASK); /* * Before allocating the hugepage, release the mmap_lock read lock. * The allocation can take potentially a long time if it involves * sync compaction, and we do not need to hold the mmap_lock during * that. We will recheck the vma after taking it again in write mode. */ mmap_read_unlock(mm); result = alloc_charge_folio(&folio, mm, cc); if (result != SCAN_SUCCEED) goto out_nolock; mmap_read_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) { mmap_read_unlock(mm); goto out_nolock; } if (unmapped) { /* * __collapse_huge_page_swapin will return with mmap_lock * released when it fails. So we jump out_nolock directly in * that case. Continuing to collapse causes inconsistency. */ result = __collapse_huge_page_swapin(mm, vma, address, pmd, referenced); if (result != SCAN_SUCCEED) goto out_nolock; } mmap_read_unlock(mm); /* * Prevent all access to pagetables with the exception of * gup_fast later handled by the ptep_clear_flush and the VM * handled by the anon_vma lock + PG_lock. * * UFFDIO_MOVE is prevented to race as well thanks to the * mmap_lock. */ mmap_write_lock(mm); result = hugepage_vma_revalidate(mm, address, true, &vma, cc); if (result != SCAN_SUCCEED) goto out_up_write; /* check if the pmd is still valid */ result = check_pmd_still_valid(mm, address, pmd); if (result != SCAN_SUCCEED) goto out_up_write; vma_start_write(vma); anon_vma_lock_write(vma->anon_vma); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * This removes any huge TLB entry from the CPU so we won't allow * huge and small TLB entries for the same virtual address to * avoid the risk of CPU bugs in that area. * * Parallel GUP-fast is fine since GUP-fast will back off when * it detects PMD is changed. */ _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(&range); tlb_remove_table_sync_one(); pte = pte_offset_map_lock(mm, &_pmd, address, &pte_ptl); if (pte) { result = __collapse_huge_page_isolate(vma, address, pte, cc, &compound_pagelist); spin_unlock(pte_ptl); } else { result = SCAN_PMD_NULL; } if (unlikely(result != SCAN_SUCCEED)) { if (pte) pte_unmap(pte); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); /* * We can only use set_pmd_at when establishing * hugepmds and never for establishing regular pmds that * points to regular pagetables. Use pmd_populate for that */ pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(pmd_ptl); anon_vma_unlock_write(vma->anon_vma); goto out_up_write; } /* * All pages are isolated and locked so anon_vma rmap * can't run anymore. */ anon_vma_unlock_write(vma->anon_vma); result = __collapse_huge_page_copy(pte, folio, pmd, _pmd, vma, address, pte_ptl, &compound_pagelist); pte_unmap(pte); if (unlikely(result != SCAN_SUCCEED)) goto out_up_write; /* * The smp_wmb() inside __folio_mark_uptodate() ensures the * copy_huge_page writes become visible before the set_pmd_at() * write. */ __folio_mark_uptodate(folio); pgtable = pmd_pgtable(_pmd); _pmd = mk_huge_pmd(&folio->page, vma->vm_page_prot); _pmd = maybe_pmd_mkwrite(pmd_mkdirty(_pmd), vma); spin_lock(pmd_ptl); BUG_ON(!pmd_none(*pmd)); folio_add_new_anon_rmap(folio, vma, address); folio_add_lru_vma(folio, vma); pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache_pmd(vma, address, pmd); spin_unlock(pmd_ptl); folio = NULL; result = SCAN_SUCCEED; out_up_write: mmap_write_unlock(mm); out_nolock: if (folio) folio_put(folio); trace_mm_collapse_huge_page(mm, result == SCAN_SUCCEED, result); return result; } static int hpage_collapse_scan_pmd(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, bool *mmap_locked, struct collapse_control *cc) { pmd_t *pmd; pte_t *pte, *_pte; int result = SCAN_FAIL, referenced = 0; int none_or_zero = 0, shared = 0; struct page *page = NULL; struct folio *folio = NULL; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE, unmapped = 0; bool writable = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); result = find_pmd_or_thp_or_none(mm, address, &pmd); if (result != SCAN_SUCCEED) goto out; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (!pte) { result = SCAN_PMD_NULL; goto out; } for (_address = address, _pte = pte; _pte < pte + HPAGE_PMD_NR; _pte++, _address += PAGE_SIZE) { pte_t pteval = ptep_get(_pte); if (is_swap_pte(pteval)) { ++unmapped; if (!cc->is_khugepaged || unmapped <= khugepaged_max_ptes_swap) { /* * Always be strict with uffd-wp * enabled swap entries. Please see * comment below for pte_uffd_wp(). */ if (pte_swp_uffd_wp_any(pteval)) { result = SCAN_PTE_UFFD_WP; goto out_unmap; } continue; } else { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); goto out_unmap; } } if (pte_none(pteval) || is_zero_pfn(pte_pfn(pteval))) { ++none_or_zero; if (!userfaultfd_armed(vma) && (!cc->is_khugepaged || none_or_zero <= khugepaged_max_ptes_none)) { continue; } else { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); goto out_unmap; } } if (pte_uffd_wp(pteval)) { /* * Don't collapse the page if any of the small * PTEs are armed with uffd write protection. * Here we can also mark the new huge pmd as * write protected if any of the small ones is * marked but that could bring unknown * userfault messages that falls outside of * the registered range. So, just be simple. */ result = SCAN_PTE_UFFD_WP; goto out_unmap; } if (pte_write(pteval)) writable = true; page = vm_normal_page(vma, _address, pteval); if (unlikely(!page) || unlikely(is_zone_device_page(page))) { result = SCAN_PAGE_NULL; goto out_unmap; } folio = page_folio(page); if (!folio_test_anon(folio)) { result = SCAN_PAGE_ANON; goto out_unmap; } /* * We treat a single page as shared if any part of the THP * is shared. "False negatives" from * folio_likely_mapped_shared() are not expected to matter * much in practice. */ if (folio_likely_mapped_shared(folio)) { ++shared; if (cc->is_khugepaged && shared > khugepaged_max_ptes_shared) { result = SCAN_EXCEED_SHARED_PTE; count_vm_event(THP_SCAN_EXCEED_SHARED_PTE); goto out_unmap; } } /* * Record which node the original page is from and save this * information to cc->node_load[]. * Khugepaged will allocate hugepage from the node has the max * hit record. */ node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; goto out_unmap; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; goto out_unmap; } if (folio_test_locked(folio)) { result = SCAN_PAGE_LOCK; goto out_unmap; } /* * Check if the page has any GUP (or other external) pins. * * Here the check may be racy: * it may see folio_mapcount() > folio_ref_count(). * But such case is ephemeral we could always retry collapse * later. However it may report false positive if the page * has excessive GUP pins (i.e. 512). Anyway the same check * will be done again later the risk seems low. */ if (!is_refcount_suitable(folio)) { result = SCAN_PAGE_COUNT; goto out_unmap; } /* * If collapse was initiated by khugepaged, check that there is * enough young pte to justify collapsing the page */ if (cc->is_khugepaged && (pte_young(pteval) || folio_test_young(folio) || folio_test_referenced(folio) || mmu_notifier_test_young(vma->vm_mm, address))) referenced++; } if (!writable) { result = SCAN_PAGE_RO; } else if (cc->is_khugepaged && (!referenced || (unmapped && referenced < HPAGE_PMD_NR / 2))) { result = SCAN_LACK_REFERENCED_PAGE; } else { result = SCAN_SUCCEED; } out_unmap: pte_unmap_unlock(pte, ptl); if (result == SCAN_SUCCEED) { result = collapse_huge_page(mm, address, referenced, unmapped, cc); /* collapse_huge_page will return with the mmap_lock released */ *mmap_locked = false; } out: trace_mm_khugepaged_scan_pmd(mm, &folio->page, writable, referenced, none_or_zero, result, unmapped); return result; } static void collect_mm_slot(struct khugepaged_mm_slot *mm_slot) { struct mm_slot *slot = &mm_slot->slot; struct mm_struct *mm = slot->mm; lockdep_assert_held(&khugepaged_mm_lock); if (hpage_collapse_test_exit(mm)) { /* free mm_slot */ hash_del(&slot->hash); list_del(&slot->mm_node); /* * Not strictly needed because the mm exited already. * * clear_bit(MMF_VM_HUGEPAGE, &mm->flags); */ /* khugepaged_mm_lock actually not necessary for the below */ mm_slot_free(mm_slot_cache, mm_slot); mmdrop(mm); } } #ifdef CONFIG_SHMEM /* hpage must be locked, and mmap_lock must be held */ static int set_huge_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmdp, struct page *hpage) { struct vm_fault vmf = { .vma = vma, .address = addr, .flags = 0, .pmd = pmdp, }; VM_BUG_ON(!PageTransHuge(hpage)); mmap_assert_locked(vma->vm_mm); if (do_set_pmd(&vmf, hpage)) return SCAN_FAIL; get_page(hpage); return SCAN_SUCCEED; } /** * collapse_pte_mapped_thp - Try to collapse a pte-mapped THP for mm at * address haddr. * * @mm: process address space where collapse happens * @addr: THP collapse address * @install_pmd: If a huge PMD should be installed * * This function checks whether all the PTEs in the PMD are pointing to the * right THP. If so, retract the page table so the THP can refault in with * as pmd-mapped. Possibly install a huge PMD mapping the THP. */ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr, bool install_pmd) { struct mmu_notifier_range range; bool notified = false; unsigned long haddr = addr & HPAGE_PMD_MASK; struct vm_area_struct *vma = vma_lookup(mm, haddr); struct folio *folio; pte_t *start_pte, *pte; pmd_t *pmd, pgt_pmd; spinlock_t *pml = NULL, *ptl; int nr_ptes = 0, result = SCAN_FAIL; int i; mmap_assert_locked(mm); /* First check VMA found, in case page tables are being torn down */ if (!vma || !vma->vm_file || !range_in_vma(vma, haddr, haddr + HPAGE_PMD_SIZE)) return SCAN_VMA_CHECK; /* Fast check before locking page if already PMD-mapped */ result = find_pmd_or_thp_or_none(mm, haddr, &pmd); if (result == SCAN_PMD_MAPPED) return result; /* * If we are here, we've succeeded in replacing all the native pages * in the page cache with a single hugepage. If a mm were to fault-in * this memory (mapped by a suitably aligned VMA), we'd get the hugepage * and map it by a PMD, regardless of sysfs THP settings. As such, let's * analogously elide sysfs THP settings here. */ if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return SCAN_VMA_CHECK; /* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */ if (userfaultfd_wp(vma)) return SCAN_PTE_UFFD_WP; folio = filemap_lock_folio(vma->vm_file->f_mapping, linear_page_index(vma, haddr)); if (IS_ERR(folio)) return SCAN_PAGE_NULL; if (folio_order(folio) != HPAGE_PMD_ORDER) { result = SCAN_PAGE_COMPOUND; goto drop_folio; } result = find_pmd_or_thp_or_none(mm, haddr, &pmd); switch (result) { case SCAN_SUCCEED: break; case SCAN_PMD_NONE: /* * All pte entries have been removed and pmd cleared. * Skip all the pte checks and just update the pmd mapping. */ goto maybe_install_pmd; default: goto drop_folio; } result = SCAN_FAIL; start_pte = pte_offset_map_lock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto drop_folio; /* step 1: check all mapped PTEs are to the right huge page */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); /* empty pte, skip */ if (pte_none(ptent)) continue; /* page swapped out, abort */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (WARN_ON_ONCE(page && is_zone_device_page(page))) page = NULL; /* * Note that uprobe, debugger, or MAP_PRIVATE may change the * page table, but the new page will not be a subpage of hpage. */ if (folio_page(folio, i) != page) goto abort; } pte_unmap_unlock(start_pte, ptl); mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, haddr, haddr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); notified = true; /* * pmd_lock covers a wider range than ptl, and (if split from mm's * page_table_lock) ptl nests inside pml. The less time we hold pml, * the better; but userfaultfd's mfill_atomic_pte() on a private VMA * inserts a valid as-if-COWed PTE without even looking up page cache. * So page lock of folio does not protect from it, so we must not drop * ptl before pgt_pmd is removed, so uffd private needs pml taken now. */ if (userfaultfd_armed(vma) && !(vma->vm_flags & VM_SHARED)) pml = pmd_lock(mm, pmd); start_pte = pte_offset_map_nolock(mm, pmd, haddr, &ptl); if (!start_pte) /* mmap_lock + page lock should prevent this */ goto abort; if (!pml) spin_lock(ptl); else if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* step 2: clear page table and adjust rmap */ for (i = 0, addr = haddr, pte = start_pte; i < HPAGE_PMD_NR; i++, addr += PAGE_SIZE, pte++) { struct page *page; pte_t ptent = ptep_get(pte); if (pte_none(ptent)) continue; /* * We dropped ptl after the first scan, to do the mmu_notifier: * page lock stops more PTEs of the folio being faulted in, but * does not stop write faults COWing anon copies from existing * PTEs; and does not stop those being swapped out or migrated. */ if (!pte_present(ptent)) { result = SCAN_PTE_NON_PRESENT; goto abort; } page = vm_normal_page(vma, addr, ptent); if (folio_page(folio, i) != page) goto abort; /* * Must clear entry, or a racing truncate may re-remove it. * TLB flush can be left until pmdp_collapse_flush() does it. * PTE dirty? Shmem page is already dirty; file is read-only. */ ptep_clear(mm, addr, pte); folio_remove_rmap_pte(folio, page, vma); nr_ptes++; } pte_unmap(start_pte); if (!pml) spin_unlock(ptl); /* step 3: set proper refcount and mm_counters. */ if (nr_ptes) { folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } /* step 4: remove empty page table */ if (!pml) { pml = pmd_lock(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); } pgt_pmd = pmdp_collapse_flush(vma, haddr, pmd); pmdp_get_lockless_sync(); if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, haddr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); maybe_install_pmd: /* step 5: install pmd entry */ result = install_pmd ? set_huge_pmd(vma, haddr, pmd, &folio->page) : SCAN_SUCCEED; goto drop_folio; abort: if (nr_ptes) { flush_tlb_mm(mm); folio_ref_sub(folio, nr_ptes); add_mm_counter(mm, mm_counter_file(folio), -nr_ptes); } if (start_pte) pte_unmap_unlock(start_pte, ptl); if (pml && pml != ptl) spin_unlock(pml); if (notified) mmu_notifier_invalidate_range_end(&range); drop_folio: folio_unlock(folio); folio_put(folio); return result; } static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) { struct vm_area_struct *vma; i_mmap_lock_read(mapping); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { struct mmu_notifier_range range; struct mm_struct *mm; unsigned long addr; pmd_t *pmd, pgt_pmd; spinlock_t *pml; spinlock_t *ptl; bool skipped_uffd = false; /* * Check vma->anon_vma to exclude MAP_PRIVATE mappings that * got written to. These VMAs are likely not worth removing * page tables from, as PMD-mapping is likely to be split later. */ if (READ_ONCE(vma->anon_vma)) continue; addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); if (addr & ~HPAGE_PMD_MASK || vma->vm_end < addr + HPAGE_PMD_SIZE) continue; mm = vma->vm_mm; if (find_pmd_or_thp_or_none(mm, addr, &pmd) != SCAN_SUCCEED) continue; if (hpage_collapse_test_exit(mm)) continue; /* * When a vma is registered with uffd-wp, we cannot recycle * the page table because there may be pte markers installed. * Other vmas can still have the same file mapped hugely, but * skip this one: it will always be mapped in small page size * for uffd-wp registered ranges. */ if (userfaultfd_wp(vma)) continue; /* PTEs were notified when unmapped; but now for the PMD? */ mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, addr, addr + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); pml = pmd_lock(mm, pmd); ptl = pte_lockptr(mm, pmd); if (ptl != pml) spin_lock_nested(ptl, SINGLE_DEPTH_NESTING); /* * Huge page lock is still held, so normally the page table * must remain empty; and we have already skipped anon_vma * and userfaultfd_wp() vmas. But since the mmap_lock is not * held, it is still possible for a racing userfaultfd_ioctl() * to have inserted ptes or markers. Now that we hold ptlock, * repeating the anon_vma check protects from one category, * and repeating the userfaultfd_wp() check from another. */ if (unlikely(vma->anon_vma || userfaultfd_wp(vma))) { skipped_uffd = true; } else { pgt_pmd = pmdp_collapse_flush(vma, addr, pmd); pmdp_get_lockless_sync(); } if (ptl != pml) spin_unlock(ptl); spin_unlock(pml); mmu_notifier_invalidate_range_end(&range); if (!skipped_uffd) { mm_dec_nr_ptes(mm); page_table_check_pte_clear_range(mm, addr, pgt_pmd); pte_free_defer(mm, pmd_pgtable(pgt_pmd)); } } i_mmap_unlock_read(mapping); } /** * collapse_file - collapse filemap/tmpfs/shmem pages into huge one. * * @mm: process address space where collapse happens * @addr: virtual collapse start address * @file: file that collapse on * @start: collapse start address * @cc: collapse context and scratchpad * * Basic scheme is simple, details are more complex: * - allocate and lock a new huge page; * - scan page cache, locking old pages * + swap/gup in pages if necessary; * - copy data to new page * - handle shmem holes * + re-validate that holes weren't filled by someone else * + check for userfaultfd * - finalize updates to the page cache; * - if replacing succeeds: * + unlock huge page; * + free old pages; * - if replacing failed; * + unlock old pages * + unlock and free huge page; */ static int collapse_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct address_space *mapping = file->f_mapping; struct page *dst; struct folio *folio, *tmp, *new_folio; pgoff_t index = 0, end = start + HPAGE_PMD_NR; LIST_HEAD(pagelist); XA_STATE_ORDER(xas, &mapping->i_pages, start, HPAGE_PMD_ORDER); int nr_none = 0, result = SCAN_SUCCEED; bool is_shmem = shmem_file(file); VM_BUG_ON(!IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) && !is_shmem); VM_BUG_ON(start & (HPAGE_PMD_NR - 1)); result = alloc_charge_folio(&new_folio, mm, cc); if (result != SCAN_SUCCEED) goto out; __folio_set_locked(new_folio); if (is_shmem) __folio_set_swapbacked(new_folio); new_folio->index = start; new_folio->mapping = mapping; /* * Ensure we have slots for all the pages in the range. This is * almost certainly a no-op because most of the pages must be present */ do { xas_lock_irq(&xas); xas_create_range(&xas); if (!xas_error(&xas)) break; xas_unlock_irq(&xas); if (!xas_nomem(&xas, GFP_KERNEL)) { result = SCAN_FAIL; goto rollback; } } while (1); for (index = start; index < end; index++) { xas_set(&xas, index); folio = xas_load(&xas); VM_BUG_ON(index != xas.xa_index); if (is_shmem) { if (!folio) { /* * Stop if extent has been truncated or * hole-punched, and is now completely * empty. */ if (index == start) { if (!xas_next_entry(&xas, end - 1)) { result = SCAN_TRUNCATED; goto xa_locked; } } nr_none++; continue; } if (xa_is_value(folio) || !folio_test_uptodate(folio)) { xas_unlock_irq(&xas); /* swap in or instantiate fallocated page */ if (shmem_get_folio(mapping->host, index, &folio, SGP_NOALLOC)) { result = SCAN_FAIL; goto xa_unlocked; } /* drain lru cache to help isolate_lru_page() */ lru_add_drain(); } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } else { /* !is_shmem */ if (!folio || xa_is_value(folio)) { xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, end - index); /* drain lru cache to help isolate_lru_page() */ lru_add_drain(); folio = filemap_lock_folio(mapping, index); if (IS_ERR(folio)) { result = SCAN_FAIL; goto xa_unlocked; } } else if (folio_test_dirty(folio)) { /* * khugepaged only works on read-only fd, * so this page is dirty because it hasn't * been flushed since first write. There * won't be new dirty pages. * * Trigger async flush here and hope the * writeback is done when khugepaged * revisits this page. * * This is a one-off situation. We are not * forcing writeback in loop. */ xas_unlock_irq(&xas); filemap_flush(mapping); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_test_writeback(folio)) { xas_unlock_irq(&xas); result = SCAN_FAIL; goto xa_unlocked; } else if (folio_trylock(folio)) { folio_get(folio); xas_unlock_irq(&xas); } else { result = SCAN_PAGE_LOCK; goto xa_locked; } } /* * The folio must be locked, so we can drop the i_pages lock * without racing with truncate. */ VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); /* make sure the folio is up to date */ if (unlikely(!folio_test_uptodate(folio))) { result = SCAN_FAIL; goto out_unlock; } /* * If file was truncated then extended, or hole-punched, before * we locked the first folio, then a THP might be there already. * This will be discovered on the first iteration. */ if (folio_test_large(folio)) { result = folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start /* Maybe PMD-mapped */ ? SCAN_PTE_MAPPED_HUGEPAGE : SCAN_PAGE_COMPOUND; goto out_unlock; } if (folio_mapping(folio) != mapping) { result = SCAN_TRUNCATED; goto out_unlock; } if (!is_shmem && (folio_test_dirty(folio) || folio_test_writeback(folio))) { /* * khugepaged only works on read-only fd, so this * folio is dirty because it hasn't been flushed * since first write. */ result = SCAN_FAIL; goto out_unlock; } if (!folio_isolate_lru(folio)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; } if (!filemap_release_folio(folio, GFP_KERNEL)) { result = SCAN_PAGE_HAS_PRIVATE; folio_putback_lru(folio); goto out_unlock; } if (folio_mapped(folio)) try_to_unmap(folio, TTU_IGNORE_MLOCK | TTU_BATCH_FLUSH); xas_lock_irq(&xas); VM_BUG_ON_FOLIO(folio != xa_load(xas.xa, index), folio); /* * We control three references to the folio: * - we hold a pin on it; * - one reference from page cache; * - one from lru_isolate_folio; * If those are the only references, then any new usage * of the folio will have to fetch it from the page * cache. That requires locking the folio to handle * truncate, so any new usage will be blocked until we * unlock folio after collapse/during rollback. */ if (folio_ref_count(folio) != 3) { result = SCAN_PAGE_COUNT; xas_unlock_irq(&xas); folio_putback_lru(folio); goto out_unlock; } /* * Accumulate the folios that are being collapsed. */ list_add_tail(&folio->lru, &pagelist); continue; out_unlock: folio_unlock(folio); folio_put(folio); goto xa_unlocked; } if (!is_shmem) { filemap_nr_thps_inc(mapping); /* * Paired with smp_mb() in do_dentry_open() to ensure * i_writecount is up to date and the update to nr_thps is * visible. Ensures the page cache will be truncated if the * file is opened writable. */ smp_mb(); if (inode_is_open_for_write(mapping->host)) { result = SCAN_FAIL; filemap_nr_thps_dec(mapping); } } xa_locked: xas_unlock_irq(&xas); xa_unlocked: /* * If collapse is successful, flush must be done now before copying. * If collapse is unsuccessful, does flush actually need to be done? * Do it anyway, to clear the state. */ try_to_unmap_flush(); if (result == SCAN_SUCCEED && nr_none && !shmem_charge(mapping->host, nr_none)) result = SCAN_FAIL; if (result != SCAN_SUCCEED) { nr_none = 0; goto rollback; } /* * The old folios are locked, so they won't change anymore. */ index = start; dst = folio_page(new_folio, 0); list_for_each_entry(folio, &pagelist, lru) { while (index < folio->index) { clear_highpage(dst); index++; dst++; } if (copy_mc_highpage(dst, folio_page(folio, 0)) > 0) { result = SCAN_COPY_MC; goto rollback; } index++; dst++; } while (index < end) { clear_highpage(dst); index++; dst++; } if (nr_none) { struct vm_area_struct *vma; int nr_none_check = 0; i_mmap_lock_read(mapping); xas_lock_irq(&xas); xas_set(&xas, start); for (index = start; index < end; index++) { if (!xas_next(&xas)) { xas_store(&xas, XA_RETRY_ENTRY); if (xas_error(&xas)) { result = SCAN_STORE_FAILED; goto immap_locked; } nr_none_check++; } } if (nr_none != nr_none_check) { result = SCAN_PAGE_FILLED; goto immap_locked; } /* * If userspace observed a missing page in a VMA with * a MODE_MISSING userfaultfd, then it might expect a * UFFD_EVENT_PAGEFAULT for that page. If so, we need to * roll back to avoid suppressing such an event. Since * wp/minor userfaultfds don't give userspace any * guarantees that the kernel doesn't fill a missing * page with a zero page, so they don't matter here. * * Any userfaultfds registered after this point will * not be able to observe any missing pages due to the * previously inserted retry entries. */ vma_interval_tree_foreach(vma, &mapping->i_mmap, start, end) { if (userfaultfd_missing(vma)) { result = SCAN_EXCEED_NONE_PTE; goto immap_locked; } } immap_locked: i_mmap_unlock_read(mapping); if (result != SCAN_SUCCEED) { xas_set(&xas, start); for (index = start; index < end; index++) { if (xas_next(&xas) == XA_RETRY_ENTRY) xas_store(&xas, NULL); } xas_unlock_irq(&xas); goto rollback; } } else { xas_lock_irq(&xas); } if (is_shmem) __lruvec_stat_mod_folio(new_folio, NR_SHMEM_THPS, HPAGE_PMD_NR); else __lruvec_stat_mod_folio(new_folio, NR_FILE_THPS, HPAGE_PMD_NR); if (nr_none) { __lruvec_stat_mod_folio(new_folio, NR_FILE_PAGES, nr_none); /* nr_none is always 0 for non-shmem. */ __lruvec_stat_mod_folio(new_folio, NR_SHMEM, nr_none); } /* * Mark new_folio as uptodate before inserting it into the * page cache so that it isn't mistaken for an fallocated but * unwritten page. */ folio_mark_uptodate(new_folio); folio_ref_add(new_folio, HPAGE_PMD_NR - 1); if (is_shmem) folio_mark_dirty(new_folio); folio_add_lru(new_folio); /* Join all the small entries into a single multi-index entry. */ xas_set_order(&xas, start, HPAGE_PMD_ORDER); xas_store(&xas, new_folio); WARN_ON_ONCE(xas_error(&xas)); xas_unlock_irq(&xas); /* * Remove pte page tables, so we can re-fault the page as huge. * If MADV_COLLAPSE, adjust result to call collapse_pte_mapped_thp(). */ retract_page_tables(mapping, start); if (cc && !cc->is_khugepaged) result = SCAN_PTE_MAPPED_HUGEPAGE; folio_unlock(new_folio); /* * The collapse has succeeded, so free the old folios. */ list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio->mapping = NULL; folio_clear_active(folio); folio_clear_unevictable(folio); folio_unlock(folio); folio_put_refs(folio, 3); } goto out; rollback: /* Something went wrong: roll back page cache changes */ if (nr_none) { xas_lock_irq(&xas); mapping->nrpages -= nr_none; xas_unlock_irq(&xas); shmem_uncharge(mapping->host, nr_none); } list_for_each_entry_safe(folio, tmp, &pagelist, lru) { list_del(&folio->lru); folio_unlock(folio); folio_putback_lru(folio); folio_put(folio); } /* * Undo the updates of filemap_nr_thps_inc for non-SHMEM * file only. This undo is not needed unless failure is * due to SCAN_COPY_MC. */ if (!is_shmem && result == SCAN_COPY_MC) { filemap_nr_thps_dec(mapping); /* * Paired with smp_mb() in do_dentry_open() to * ensure the update to nr_thps is visible. */ smp_mb(); } new_folio->mapping = NULL; folio_unlock(new_folio); folio_put(new_folio); out: VM_BUG_ON(!list_empty(&pagelist)); trace_mm_khugepaged_collapse_file(mm, new_folio, index, is_shmem, addr, file, HPAGE_PMD_NR, result); return result; } static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { struct folio *folio = NULL; struct address_space *mapping = file->f_mapping; XA_STATE(xas, &mapping->i_pages, start); int present, swap; int node = NUMA_NO_NODE; int result = SCAN_SUCCEED; present = 0; swap = 0; memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); rcu_read_lock(); xas_for_each(&xas, folio, start + HPAGE_PMD_NR - 1) { if (xas_retry(&xas, folio)) continue; if (xa_is_value(folio)) { ++swap; if (cc->is_khugepaged && swap > khugepaged_max_ptes_swap) { result = SCAN_EXCEED_SWAP_PTE; count_vm_event(THP_SCAN_EXCEED_SWAP_PTE); break; } continue; } /* * TODO: khugepaged should compact smaller compound pages * into a PMD sized page */ if (folio_test_large(folio)) { result = folio_order(folio) == HPAGE_PMD_ORDER && folio->index == start /* Maybe PMD-mapped */ ? SCAN_PTE_MAPPED_HUGEPAGE : SCAN_PAGE_COMPOUND; /* * For SCAN_PTE_MAPPED_HUGEPAGE, further processing * by the caller won't touch the page cache, and so * it's safe to skip LRU and refcount checks before * returning. */ break; } node = folio_nid(folio); if (hpage_collapse_scan_abort(node, cc)) { result = SCAN_SCAN_ABORT; break; } cc->node_load[node]++; if (!folio_test_lru(folio)) { result = SCAN_PAGE_LRU; break; } if (folio_ref_count(folio) != 1 + folio_mapcount(folio) + folio_test_private(folio)) { result = SCAN_PAGE_COUNT; break; } /* * We probably should check if the folio is referenced * here, but nobody would transfer pte_young() to * folio_test_referenced() for us. And rmap walk here * is just too costly... */ present++; if (need_resched()) { xas_pause(&xas); cond_resched_rcu(); } } rcu_read_unlock(); if (result == SCAN_SUCCEED) { if (cc->is_khugepaged && present < HPAGE_PMD_NR - khugepaged_max_ptes_none) { result = SCAN_EXCEED_NONE_PTE; count_vm_event(THP_SCAN_EXCEED_NONE_PTE); } else { result = collapse_file(mm, addr, file, start, cc); } } trace_mm_khugepaged_scan_file(mm, folio, file, present, swap, result); return result; } #else static int hpage_collapse_scan_file(struct mm_struct *mm, unsigned long addr, struct file *file, pgoff_t start, struct collapse_control *cc) { BUILD_BUG(); } #endif static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result, struct collapse_control *cc) __releases(&khugepaged_mm_lock) __acquires(&khugepaged_mm_lock) { struct vma_iterator vmi; struct khugepaged_mm_slot *mm_slot; struct mm_slot *slot; struct mm_struct *mm; struct vm_area_struct *vma; int progress = 0; VM_BUG_ON(!pages); lockdep_assert_held(&khugepaged_mm_lock); *result = SCAN_FAIL; if (khugepaged_scan.mm_slot) { mm_slot = khugepaged_scan.mm_slot; slot = &mm_slot->slot; } else { slot = list_entry(khugepaged_scan.mm_head.next, struct mm_slot, mm_node); mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; khugepaged_scan.mm_slot = mm_slot; } spin_unlock(&khugepaged_mm_lock); mm = slot->mm; /* * Don't wait for semaphore (to avoid long wait times). Just move to * the next mm on the list. */ vma = NULL; if (unlikely(!mmap_read_trylock(mm))) goto breakouterloop_mmap_lock; progress++; if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; vma_iter_init(&vmi, mm, khugepaged_scan.address); for_each_vma(vmi, vma) { unsigned long hstart, hend; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) { progress++; break; } if (!thp_vma_allowable_order(vma, vma->vm_flags, TVA_ENFORCE_SYSFS, PMD_ORDER)) { skip: progress++; continue; } hstart = round_up(vma->vm_start, HPAGE_PMD_SIZE); hend = round_down(vma->vm_end, HPAGE_PMD_SIZE); if (khugepaged_scan.address > hend) goto skip; if (khugepaged_scan.address < hstart) khugepaged_scan.address = hstart; VM_BUG_ON(khugepaged_scan.address & ~HPAGE_PMD_MASK); while (khugepaged_scan.address < hend) { bool mmap_locked = true; cond_resched(); if (unlikely(hpage_collapse_test_exit_or_disable(mm))) goto breakouterloop; VM_BUG_ON(khugepaged_scan.address < hstart || khugepaged_scan.address + HPAGE_PMD_SIZE > hend); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, khugepaged_scan.address); mmap_read_unlock(mm); mmap_locked = false; *result = hpage_collapse_scan_file(mm, khugepaged_scan.address, file, pgoff, cc); fput(file); if (*result == SCAN_PTE_MAPPED_HUGEPAGE) { mmap_read_lock(mm); if (hpage_collapse_test_exit_or_disable(mm)) goto breakouterloop; *result = collapse_pte_mapped_thp(mm, khugepaged_scan.address, false); if (*result == SCAN_PMD_MAPPED) *result = SCAN_SUCCEED; mmap_read_unlock(mm); } } else { *result = hpage_collapse_scan_pmd(mm, vma, khugepaged_scan.address, &mmap_locked, cc); } if (*result == SCAN_SUCCEED) ++khugepaged_pages_collapsed; /* move to next address */ khugepaged_scan.address += HPAGE_PMD_SIZE; progress += HPAGE_PMD_NR; if (!mmap_locked) /* * We released mmap_lock so break loop. Note * that we drop mmap_lock before all hugepage * allocations, so if allocation fails, we are * guaranteed to break here and report the * correct result back to caller. */ goto breakouterloop_mmap_lock; if (progress >= pages) goto breakouterloop; } } breakouterloop: mmap_read_unlock(mm); /* exit_mmap will destroy ptes after this */ breakouterloop_mmap_lock: spin_lock(&khugepaged_mm_lock); VM_BUG_ON(khugepaged_scan.mm_slot != mm_slot); /* * Release the current mm_slot if this mm is about to die, or * if we scanned all vmas of this mm. */ if (hpage_collapse_test_exit(mm) || !vma) { /* * Make sure that if mm_users is reaching zero while * khugepaged runs here, khugepaged_exit will find * mm_slot not pointing to the exiting mm. */ if (slot->mm_node.next != &khugepaged_scan.mm_head) { slot = list_entry(slot->mm_node.next, struct mm_slot, mm_node); khugepaged_scan.mm_slot = mm_slot_entry(slot, struct khugepaged_mm_slot, slot); khugepaged_scan.address = 0; } else { khugepaged_scan.mm_slot = NULL; khugepaged_full_scans++; } collect_mm_slot(mm_slot); } return progress; } static int khugepaged_has_work(void) { return !list_empty(&khugepaged_scan.mm_head) && hugepage_flags_enabled(); } static int khugepaged_wait_event(void) { return !list_empty(&khugepaged_scan.mm_head) || kthread_should_stop(); } static void khugepaged_do_scan(struct collapse_control *cc) { unsigned int progress = 0, pass_through_head = 0; unsigned int pages = READ_ONCE(khugepaged_pages_to_scan); bool wait = true; int result = SCAN_SUCCEED; lru_add_drain_all(); while (true) { cond_resched(); if (unlikely(kthread_should_stop())) break; spin_lock(&khugepaged_mm_lock); if (!khugepaged_scan.mm_slot) pass_through_head++; if (khugepaged_has_work() && pass_through_head < 2) progress += khugepaged_scan_mm_slot(pages - progress, &result, cc); else progress = pages; spin_unlock(&khugepaged_mm_lock); if (progress >= pages) break; if (result == SCAN_ALLOC_HUGE_PAGE_FAIL) { /* * If fail to allocate the first time, try to sleep for * a while. When hit again, cancel the scan. */ if (!wait) break; wait = false; khugepaged_alloc_sleep(); } } } static bool khugepaged_should_wakeup(void) { return kthread_should_stop() || time_after_eq(jiffies, khugepaged_sleep_expire); } static void khugepaged_wait_work(void) { if (khugepaged_has_work()) { const unsigned long scan_sleep_jiffies = msecs_to_jiffies(khugepaged_scan_sleep_millisecs); if (!scan_sleep_jiffies) return; khugepaged_sleep_expire = jiffies + scan_sleep_jiffies; wait_event_freezable_timeout(khugepaged_wait, khugepaged_should_wakeup(), scan_sleep_jiffies); return; } if (hugepage_flags_enabled()) wait_event_freezable(khugepaged_wait, khugepaged_wait_event()); } static int khugepaged(void *none) { struct khugepaged_mm_slot *mm_slot; set_freezable(); set_user_nice(current, MAX_NICE); while (!kthread_should_stop()) { khugepaged_do_scan(&khugepaged_collapse_control); khugepaged_wait_work(); } spin_lock(&khugepaged_mm_lock); mm_slot = khugepaged_scan.mm_slot; khugepaged_scan.mm_slot = NULL; if (mm_slot) collect_mm_slot(mm_slot); spin_unlock(&khugepaged_mm_lock); return 0; } static void set_recommended_min_free_kbytes(void) { struct zone *zone; int nr_zones = 0; unsigned long recommended_min; if (!hugepage_flags_enabled()) { calculate_min_free_kbytes(); goto update_wmarks; } for_each_populated_zone(zone) { /* * We don't need to worry about fragmentation of * ZONE_MOVABLE since it only has movable pages. */ if (zone_idx(zone) > gfp_zone(GFP_USER)) continue; nr_zones++; } /* Ensure 2 pageblocks are free to assist fragmentation avoidance */ recommended_min = pageblock_nr_pages * nr_zones * 2; /* * Make sure that on average at least two pageblocks are almost free * of another type, one for a migratetype to fall back to and a * second to avoid subsequent fallbacks of other types There are 3 * MIGRATE_TYPES we care about. */ recommended_min += pageblock_nr_pages * nr_zones * MIGRATE_PCPTYPES * MIGRATE_PCPTYPES; /* don't ever allow to reserve more than 5% of the lowmem */ recommended_min = min(recommended_min, (unsigned long) nr_free_buffer_pages() / 20); recommended_min <<= (PAGE_SHIFT-10); if (recommended_min > min_free_kbytes) { if (user_min_free_kbytes >= 0) pr_info("raising min_free_kbytes from %d to %lu to help transparent hugepage allocations\n", min_free_kbytes, recommended_min); min_free_kbytes = recommended_min; } update_wmarks: setup_per_zone_wmarks(); } int start_stop_khugepaged(void) { int err = 0; mutex_lock(&khugepaged_mutex); if (hugepage_flags_enabled()) { if (!khugepaged_thread) khugepaged_thread = kthread_run(khugepaged, NULL, "khugepaged"); if (IS_ERR(khugepaged_thread)) { pr_err("khugepaged: kthread_run(khugepaged) failed\n"); err = PTR_ERR(khugepaged_thread); khugepaged_thread = NULL; goto fail; } if (!list_empty(&khugepaged_scan.mm_head)) wake_up_interruptible(&khugepaged_wait); } else if (khugepaged_thread) { kthread_stop(khugepaged_thread); khugepaged_thread = NULL; } set_recommended_min_free_kbytes(); fail: mutex_unlock(&khugepaged_mutex); return err; } void khugepaged_min_free_kbytes_update(void) { mutex_lock(&khugepaged_mutex); if (hugepage_flags_enabled() && khugepaged_thread) set_recommended_min_free_kbytes(); mutex_unlock(&khugepaged_mutex); } bool current_is_khugepaged(void) { return kthread_func(current) == khugepaged; } static int madvise_collapse_errno(enum scan_result r) { /* * MADV_COLLAPSE breaks from existing madvise(2) conventions to provide * actionable feedback to caller, so they may take an appropriate * fallback measure depending on the nature of the failure. */ switch (r) { case SCAN_ALLOC_HUGE_PAGE_FAIL: return -ENOMEM; case SCAN_CGROUP_CHARGE_FAIL: case SCAN_EXCEED_NONE_PTE: return -EBUSY; /* Resource temporary unavailable - trying again might succeed */ case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: case SCAN_PAGE_FILLED: return -EAGAIN; /* * Other: Trying again likely not to succeed / error intrinsic to * specified memory range. khugepaged likely won't be able to collapse * either. */ default: return -EINVAL; } } int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end) { struct collapse_control *cc; struct mm_struct *mm = vma->vm_mm; unsigned long hstart, hend, addr; int thps = 0, last_fail = SCAN_FAIL; bool mmap_locked = true; BUG_ON(vma->vm_start > start); BUG_ON(vma->vm_end < end); *prev = vma; if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER)) return -EINVAL; cc = kmalloc(sizeof(*cc), GFP_KERNEL); if (!cc) return -ENOMEM; cc->is_khugepaged = false; mmgrab(mm); lru_add_drain_all(); hstart = (start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = end & HPAGE_PMD_MASK; for (addr = hstart; addr < hend; addr += HPAGE_PMD_SIZE) { int result = SCAN_FAIL; if (!mmap_locked) { cond_resched(); mmap_read_lock(mm); mmap_locked = true; result = hugepage_vma_revalidate(mm, addr, false, &vma, cc); if (result != SCAN_SUCCEED) { last_fail = result; goto out_nolock; } hend = min(hend, vma->vm_end & HPAGE_PMD_MASK); } mmap_assert_locked(mm); memset(cc->node_load, 0, sizeof(cc->node_load)); nodes_clear(cc->alloc_nmask); if (IS_ENABLED(CONFIG_SHMEM) && vma->vm_file) { struct file *file = get_file(vma->vm_file); pgoff_t pgoff = linear_page_index(vma, addr); mmap_read_unlock(mm); mmap_locked = false; result = hpage_collapse_scan_file(mm, addr, file, pgoff, cc); fput(file); } else { result = hpage_collapse_scan_pmd(mm, vma, addr, &mmap_locked, cc); } if (!mmap_locked) *prev = NULL; /* Tell caller we dropped mmap_lock */ handle_result: switch (result) { case SCAN_SUCCEED: case SCAN_PMD_MAPPED: ++thps; break; case SCAN_PTE_MAPPED_HUGEPAGE: BUG_ON(mmap_locked); BUG_ON(*prev); mmap_read_lock(mm); result = collapse_pte_mapped_thp(mm, addr, true); mmap_read_unlock(mm); goto handle_result; /* Whitelisted set of results where continuing OK */ case SCAN_PMD_NULL: case SCAN_PTE_NON_PRESENT: case SCAN_PTE_UFFD_WP: case SCAN_PAGE_RO: case SCAN_LACK_REFERENCED_PAGE: case SCAN_PAGE_NULL: case SCAN_PAGE_COUNT: case SCAN_PAGE_LOCK: case SCAN_PAGE_COMPOUND: case SCAN_PAGE_LRU: case SCAN_DEL_PAGE_LRU: last_fail = result; break; default: last_fail = result; /* Other error, exit */ goto out_maybelock; } } out_maybelock: /* Caller expects us to hold mmap_lock on return */ if (!mmap_locked) mmap_read_lock(mm); out_nolock: mmap_assert_locked(mm); mmdrop(mm); kfree(cc); return thps == ((hend - hstart) >> HPAGE_PMD_SHIFT) ? 0 : madvise_collapse_errno(last_fail); } |
| 150 148 22 2 2 2 2 2 2 22 2 22 2 22 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2020 Google LLC * Author: Will Deacon <will@kernel.org> */ #ifndef __ARM64_KVM_PGTABLE_H__ #define __ARM64_KVM_PGTABLE_H__ #include <linux/bits.h> #include <linux/kvm_host.h> #include <linux/types.h> #define KVM_PGTABLE_FIRST_LEVEL -1 #define KVM_PGTABLE_LAST_LEVEL 3 /* * The largest supported block sizes for KVM (no 52-bit PA support): * - 4K (level 1): 1GB * - 16K (level 2): 32MB * - 64K (level 2): 512MB */ #ifdef CONFIG_ARM64_4K_PAGES #define KVM_PGTABLE_MIN_BLOCK_LEVEL 1 #else #define KVM_PGTABLE_MIN_BLOCK_LEVEL 2 #endif #define kvm_lpa2_is_enabled() system_supports_lpa2() static inline u64 kvm_get_parange_max(void) { if (kvm_lpa2_is_enabled() || (IS_ENABLED(CONFIG_ARM64_PA_BITS_52) && PAGE_SHIFT == 16)) return ID_AA64MMFR0_EL1_PARANGE_52; else return ID_AA64MMFR0_EL1_PARANGE_48; } static inline u64 kvm_get_parange(u64 mmfr0) { u64 parange_max = kvm_get_parange_max(); u64 parange = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_PARANGE_SHIFT); if (parange > parange_max) parange = parange_max; return parange; } typedef u64 kvm_pte_t; #define KVM_PTE_VALID BIT(0) #define KVM_PTE_ADDR_MASK GENMASK(47, PAGE_SHIFT) #define KVM_PTE_ADDR_51_48 GENMASK(15, 12) #define KVM_PTE_ADDR_MASK_LPA2 GENMASK(49, PAGE_SHIFT) #define KVM_PTE_ADDR_51_50_LPA2 GENMASK(9, 8) #define KVM_PHYS_INVALID (-1ULL) static inline bool kvm_pte_valid(kvm_pte_t pte) { return pte & KVM_PTE_VALID; } static inline u64 kvm_pte_to_phys(kvm_pte_t pte) { u64 pa; if (kvm_lpa2_is_enabled()) { pa = pte & KVM_PTE_ADDR_MASK_LPA2; pa |= FIELD_GET(KVM_PTE_ADDR_51_50_LPA2, pte) << 50; } else { pa = pte & KVM_PTE_ADDR_MASK; if (PAGE_SHIFT == 16) pa |= FIELD_GET(KVM_PTE_ADDR_51_48, pte) << 48; } return pa; } static inline kvm_pte_t kvm_phys_to_pte(u64 pa) { kvm_pte_t pte; if (kvm_lpa2_is_enabled()) { pte = pa & KVM_PTE_ADDR_MASK_LPA2; pa &= GENMASK(51, 50); pte |= FIELD_PREP(KVM_PTE_ADDR_51_50_LPA2, pa >> 50); } else { pte = pa & KVM_PTE_ADDR_MASK; if (PAGE_SHIFT == 16) { pa &= GENMASK(51, 48); pte |= FIELD_PREP(KVM_PTE_ADDR_51_48, pa >> 48); } } return pte; } static inline kvm_pfn_t kvm_pte_to_pfn(kvm_pte_t pte) { return __phys_to_pfn(kvm_pte_to_phys(pte)); } static inline u64 kvm_granule_shift(s8 level) { /* Assumes KVM_PGTABLE_LAST_LEVEL is 3 */ return ARM64_HW_PGTABLE_LEVEL_SHIFT(level); } static inline u64 kvm_granule_size(s8 level) { return BIT(kvm_granule_shift(level)); } static inline bool kvm_level_supports_block_mapping(s8 level) { return level >= KVM_PGTABLE_MIN_BLOCK_LEVEL; } static inline u32 kvm_supported_block_sizes(void) { s8 level = KVM_PGTABLE_MIN_BLOCK_LEVEL; u32 r = 0; for (; level <= KVM_PGTABLE_LAST_LEVEL; level++) r |= BIT(kvm_granule_shift(level)); return r; } static inline bool kvm_is_block_size_supported(u64 size) { bool is_power_of_two = IS_ALIGNED(size, size); return is_power_of_two && (size & kvm_supported_block_sizes()); } /** * struct kvm_pgtable_mm_ops - Memory management callbacks. * @zalloc_page: Allocate a single zeroed memory page. * The @arg parameter can be used by the walker * to pass a memcache. The initial refcount of * the page is 1. * @zalloc_pages_exact: Allocate an exact number of zeroed memory pages. * The @size parameter is in bytes, and is rounded * up to the next page boundary. The resulting * allocation is physically contiguous. * @free_pages_exact: Free an exact number of memory pages previously * allocated by zalloc_pages_exact. * @free_unlinked_table: Free an unlinked paging structure by unlinking and * dropping references. * @get_page: Increment the refcount on a page. * @put_page: Decrement the refcount on a page. When the * refcount reaches 0 the page is automatically * freed. * @page_count: Return the refcount of a page. * @phys_to_virt: Convert a physical address into a virtual * address mapped in the current context. * @virt_to_phys: Convert a virtual address mapped in the current * context into a physical address. * @dcache_clean_inval_poc: Clean and invalidate the data cache to the PoC * for the specified memory address range. * @icache_inval_pou: Invalidate the instruction cache to the PoU * for the specified memory address range. */ struct kvm_pgtable_mm_ops { void* (*zalloc_page)(void *arg); void* (*zalloc_pages_exact)(size_t size); void (*free_pages_exact)(void *addr, size_t size); void (*free_unlinked_table)(void *addr, s8 level); void (*get_page)(void *addr); void (*put_page)(void *addr); int (*page_count)(void *addr); void* (*phys_to_virt)(phys_addr_t phys); phys_addr_t (*virt_to_phys)(void *addr); void (*dcache_clean_inval_poc)(void *addr, size_t size); void (*icache_inval_pou)(void *addr, size_t size); }; /** * enum kvm_pgtable_stage2_flags - Stage-2 page-table flags. * @KVM_PGTABLE_S2_NOFWB: Don't enforce Normal-WB even if the CPUs have * ARM64_HAS_STAGE2_FWB. * @KVM_PGTABLE_S2_IDMAP: Only use identity mappings. */ enum kvm_pgtable_stage2_flags { KVM_PGTABLE_S2_NOFWB = BIT(0), KVM_PGTABLE_S2_IDMAP = BIT(1), }; /** * enum kvm_pgtable_prot - Page-table permissions and attributes. * @KVM_PGTABLE_PROT_X: Execute permission. * @KVM_PGTABLE_PROT_W: Write permission. * @KVM_PGTABLE_PROT_R: Read permission. * @KVM_PGTABLE_PROT_DEVICE: Device attributes. * @KVM_PGTABLE_PROT_NORMAL_NC: Normal noncacheable attributes. * @KVM_PGTABLE_PROT_SW0: Software bit 0. * @KVM_PGTABLE_PROT_SW1: Software bit 1. * @KVM_PGTABLE_PROT_SW2: Software bit 2. * @KVM_PGTABLE_PROT_SW3: Software bit 3. */ enum kvm_pgtable_prot { KVM_PGTABLE_PROT_X = BIT(0), KVM_PGTABLE_PROT_W = BIT(1), KVM_PGTABLE_PROT_R = BIT(2), KVM_PGTABLE_PROT_DEVICE = BIT(3), KVM_PGTABLE_PROT_NORMAL_NC = BIT(4), KVM_PGTABLE_PROT_SW0 = BIT(55), KVM_PGTABLE_PROT_SW1 = BIT(56), KVM_PGTABLE_PROT_SW2 = BIT(57), KVM_PGTABLE_PROT_SW3 = BIT(58), }; #define KVM_PGTABLE_PROT_RW (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_W) #define KVM_PGTABLE_PROT_RWX (KVM_PGTABLE_PROT_RW | KVM_PGTABLE_PROT_X) #define PKVM_HOST_MEM_PROT KVM_PGTABLE_PROT_RWX #define PKVM_HOST_MMIO_PROT KVM_PGTABLE_PROT_RW #define PAGE_HYP KVM_PGTABLE_PROT_RW #define PAGE_HYP_EXEC (KVM_PGTABLE_PROT_R | KVM_PGTABLE_PROT_X) #define PAGE_HYP_RO (KVM_PGTABLE_PROT_R) #define PAGE_HYP_DEVICE (PAGE_HYP | KVM_PGTABLE_PROT_DEVICE) typedef bool (*kvm_pgtable_force_pte_cb_t)(u64 addr, u64 end, enum kvm_pgtable_prot prot); /** * enum kvm_pgtable_walk_flags - Flags to control a depth-first page-table walk. * @KVM_PGTABLE_WALK_LEAF: Visit leaf entries, including invalid * entries. * @KVM_PGTABLE_WALK_TABLE_PRE: Visit table entries before their * children. * @KVM_PGTABLE_WALK_TABLE_POST: Visit table entries after their * children. * @KVM_PGTABLE_WALK_SHARED: Indicates the page-tables may be shared * with other software walkers. * @KVM_PGTABLE_WALK_HANDLE_FAULT: Indicates the page-table walk was * invoked from a fault handler. * @KVM_PGTABLE_WALK_SKIP_BBM_TLBI: Visit and update table entries * without Break-before-make's * TLB invalidation. * @KVM_PGTABLE_WALK_SKIP_CMO: Visit and update table entries * without Cache maintenance * operations required. */ enum kvm_pgtable_walk_flags { KVM_PGTABLE_WALK_LEAF = BIT(0), KVM_PGTABLE_WALK_TABLE_PRE = BIT(1), KVM_PGTABLE_WALK_TABLE_POST = BIT(2), KVM_PGTABLE_WALK_SHARED = BIT(3), KVM_PGTABLE_WALK_HANDLE_FAULT = BIT(4), KVM_PGTABLE_WALK_SKIP_BBM_TLBI = BIT(5), KVM_PGTABLE_WALK_SKIP_CMO = BIT(6), }; struct kvm_pgtable_visit_ctx { kvm_pte_t *ptep; kvm_pte_t old; void *arg; struct kvm_pgtable_mm_ops *mm_ops; u64 start; u64 addr; u64 end; s8 level; enum kvm_pgtable_walk_flags flags; }; typedef int (*kvm_pgtable_visitor_fn_t)(const struct kvm_pgtable_visit_ctx *ctx, enum kvm_pgtable_walk_flags visit); static inline bool kvm_pgtable_walk_shared(const struct kvm_pgtable_visit_ctx *ctx) { return ctx->flags & KVM_PGTABLE_WALK_SHARED; } /** * struct kvm_pgtable_walker - Hook into a page-table walk. * @cb: Callback function to invoke during the walk. * @arg: Argument passed to the callback function. * @flags: Bitwise-OR of flags to identify the entry types on which to * invoke the callback function. */ struct kvm_pgtable_walker { const kvm_pgtable_visitor_fn_t cb; void * const arg; const enum kvm_pgtable_walk_flags flags; }; /* * RCU cannot be used in a non-kernel context such as the hyp. As such, page * table walkers used in hyp do not call into RCU and instead use other * synchronization mechanisms (such as a spinlock). */ #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) typedef kvm_pte_t *kvm_pteref_t; static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, kvm_pteref_t pteref) { return pteref; } static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { /* * Due to the lack of RCU (or a similar protection scheme), only * non-shared table walkers are allowed in the hypervisor. */ if (walker->flags & KVM_PGTABLE_WALK_SHARED) return -EPERM; return 0; } static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) {} static inline bool kvm_pgtable_walk_lock_held(void) { return true; } #else typedef kvm_pte_t __rcu *kvm_pteref_t; static inline kvm_pte_t *kvm_dereference_pteref(struct kvm_pgtable_walker *walker, kvm_pteref_t pteref) { return rcu_dereference_check(pteref, !(walker->flags & KVM_PGTABLE_WALK_SHARED)); } static inline int kvm_pgtable_walk_begin(struct kvm_pgtable_walker *walker) { if (walker->flags & KVM_PGTABLE_WALK_SHARED) rcu_read_lock(); return 0; } static inline void kvm_pgtable_walk_end(struct kvm_pgtable_walker *walker) { if (walker->flags & KVM_PGTABLE_WALK_SHARED) rcu_read_unlock(); } static inline bool kvm_pgtable_walk_lock_held(void) { return rcu_read_lock_held(); } #endif /** * struct kvm_pgtable - KVM page-table. * @ia_bits: Maximum input address size, in bits. * @start_level: Level at which the page-table walk starts. * @pgd: Pointer to the first top-level entry of the page-table. * @mm_ops: Memory management callbacks. * @mmu: Stage-2 KVM MMU struct. Unused for stage-1 page-tables. * @flags: Stage-2 page-table flags. * @force_pte_cb: Function that returns true if page level mappings must * be used instead of block mappings. */ struct kvm_pgtable { u32 ia_bits; s8 start_level; kvm_pteref_t pgd; struct kvm_pgtable_mm_ops *mm_ops; /* Stage-2 only */ struct kvm_s2_mmu *mmu; enum kvm_pgtable_stage2_flags flags; kvm_pgtable_force_pte_cb_t force_pte_cb; }; /** * kvm_pgtable_hyp_init() - Initialise a hypervisor stage-1 page-table. * @pgt: Uninitialised page-table structure to initialise. * @va_bits: Maximum virtual address bits. * @mm_ops: Memory management callbacks. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_hyp_init(struct kvm_pgtable *pgt, u32 va_bits, struct kvm_pgtable_mm_ops *mm_ops); /** * kvm_pgtable_hyp_destroy() - Destroy an unused hypervisor stage-1 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). * * The page-table is assumed to be unreachable by any hardware walkers prior * to freeing and therefore no TLB invalidation is performed. */ void kvm_pgtable_hyp_destroy(struct kvm_pgtable *pgt); /** * kvm_pgtable_hyp_map() - Install a mapping in a hypervisor stage-1 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). * @addr: Virtual address at which to place the mapping. * @size: Size of the mapping. * @phys: Physical address of the memory to map. * @prot: Permissions and attributes for the mapping. * * The offset of @addr within a page is ignored, @size is rounded-up to * the next page boundary and @phys is rounded-down to the previous page * boundary. * * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. Attempts to install a new mapping * for a virtual address that is already mapped will be rejected with an * error and a WARN(). * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_hyp_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot); /** * kvm_pgtable_hyp_unmap() - Remove a mapping from a hypervisor stage-1 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_hyp_init(). * @addr: Virtual address from which to remove the mapping. * @size: Size of the mapping. * * The offset of @addr within a page is ignored, @size is rounded-up to * the next page boundary and @phys is rounded-down to the previous page * boundary. * * TLB invalidation is performed for each page-table entry cleared during the * unmapping operation and the reference count for the page-table page * containing the cleared entry is decremented, with unreferenced pages being * freed. The unmapping operation will stop early if it encounters either an * invalid page-table entry or a valid block mapping which maps beyond the range * being unmapped. * * Return: Number of bytes unmapped, which may be 0. */ u64 kvm_pgtable_hyp_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_get_vtcr() - Helper to construct VTCR_EL2 * @mmfr0: Sanitized value of SYS_ID_AA64MMFR0_EL1 register. * @mmfr1: Sanitized value of SYS_ID_AA64MMFR1_EL1 register. * @phys_shfit: Value to set in VTCR_EL2.T0SZ. * * The VTCR value is common across all the physical CPUs on the system. * We use system wide sanitised values to fill in different fields, * except for Hardware Management of Access Flags. HA Flag is set * unconditionally on all CPUs, as it is safe to run with or without * the feature and the bit is RES0 on CPUs that don't support it. * * Return: VTCR_EL2 value */ u64 kvm_get_vtcr(u64 mmfr0, u64 mmfr1, u32 phys_shift); /** * kvm_pgtable_stage2_pgd_size() - Helper to compute size of a stage-2 PGD * @vtcr: Content of the VTCR register. * * Return: the size (in bytes) of the stage-2 PGD */ size_t kvm_pgtable_stage2_pgd_size(u64 vtcr); /** * __kvm_pgtable_stage2_init() - Initialise a guest stage-2 page-table. * @pgt: Uninitialised page-table structure to initialise. * @mmu: S2 MMU context for this S2 translation * @mm_ops: Memory management callbacks. * @flags: Stage-2 configuration flags. * @force_pte_cb: Function that returns true if page level mappings must * be used instead of block mappings. * * Return: 0 on success, negative error code on failure. */ int __kvm_pgtable_stage2_init(struct kvm_pgtable *pgt, struct kvm_s2_mmu *mmu, struct kvm_pgtable_mm_ops *mm_ops, enum kvm_pgtable_stage2_flags flags, kvm_pgtable_force_pte_cb_t force_pte_cb); #define kvm_pgtable_stage2_init(pgt, mmu, mm_ops) \ __kvm_pgtable_stage2_init(pgt, mmu, mm_ops, 0, NULL) /** * kvm_pgtable_stage2_destroy() - Destroy an unused guest stage-2 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * * The page-table is assumed to be unreachable by any hardware walkers prior * to freeing and therefore no TLB invalidation is performed. */ void kvm_pgtable_stage2_destroy(struct kvm_pgtable *pgt); /** * kvm_pgtable_stage2_free_unlinked() - Free an unlinked stage-2 paging structure. * @mm_ops: Memory management callbacks. * @pgtable: Unlinked stage-2 paging structure to be freed. * @level: Level of the stage-2 paging structure to be freed. * * The page-table is assumed to be unreachable by any hardware walkers prior to * freeing and therefore no TLB invalidation is performed. */ void kvm_pgtable_stage2_free_unlinked(struct kvm_pgtable_mm_ops *mm_ops, void *pgtable, s8 level); /** * kvm_pgtable_stage2_create_unlinked() - Create an unlinked stage-2 paging structure. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @phys: Physical address of the memory to map. * @level: Starting level of the stage-2 paging structure to be created. * @prot: Permissions and attributes for the mapping. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * @force_pte: Force mappings to PAGE_SIZE granularity. * * Returns an unlinked page-table tree. This new page-table tree is * not reachable (i.e., it is unlinked) from the root pgd and it's * therefore unreachableby the hardware page-table walker. No TLB * invalidation or CMOs are performed. * * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. * * Return: The fully populated (unlinked) stage-2 paging structure, or * an ERR_PTR(error) on failure. */ kvm_pte_t *kvm_pgtable_stage2_create_unlinked(struct kvm_pgtable *pgt, u64 phys, s8 level, enum kvm_pgtable_prot prot, void *mc, bool force_pte); /** * kvm_pgtable_stage2_map() - Install a mapping in a guest stage-2 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address at which to place the mapping. * @size: Size of the mapping. * @phys: Physical address of the memory to map. * @prot: Permissions and attributes for the mapping. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * @flags: Flags to control the page-table walk (ex. a shared walk) * * The offset of @addr within a page is ignored, @size is rounded-up to * the next page boundary and @phys is rounded-down to the previous page * boundary. * * If device attributes are not explicitly requested in @prot, then the * mapping will be normal, cacheable. * * Note that the update of a valid leaf PTE in this function will be aborted, * if it's trying to recreate the exact same mapping or only change the access * permissions. Instead, the vCPU will exit one more time from guest if still * needed and then go through the path of relaxing permissions. * * Note that this function will both coalesce existing table entries and split * existing block mappings, relying on page-faults to fault back areas outside * of the new mapping lazily. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_map(struct kvm_pgtable *pgt, u64 addr, u64 size, u64 phys, enum kvm_pgtable_prot prot, void *mc, enum kvm_pgtable_walk_flags flags); /** * kvm_pgtable_stage2_set_owner() - Unmap and annotate pages in the IPA space to * track ownership. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Base intermediate physical address to annotate. * @size: Size of the annotated range. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * @owner_id: Unique identifier for the owner of the page. * * By default, all page-tables are owned by identifier 0. This function can be * used to mark portions of the IPA space as owned by other entities. When a * stage 2 is used with identity-mappings, these annotations allow to use the * page-table data structure as a simple rmap. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_set_owner(struct kvm_pgtable *pgt, u64 addr, u64 size, void *mc, u8 owner_id); /** * kvm_pgtable_stage2_unmap() - Remove a mapping from a guest stage-2 page-table. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address from which to remove the mapping. * @size: Size of the mapping. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * TLB invalidation is performed for each page-table entry cleared during the * unmapping operation and the reference count for the page-table page * containing the cleared entry is decremented, with unreferenced pages being * freed. Unmapping a cacheable page will ensure that it is clean to the PoC if * FWB is not supported by the CPU. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_unmap(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_pgtable_stage2_wrprotect() - Write-protect guest stage-2 address range * without TLB invalidation. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address from which to write-protect, * @size: Size of the range. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * Note that it is the caller's responsibility to invalidate the TLB after * calling this function to ensure that the updated permissions are visible * to the CPUs. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_wrprotect(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_pgtable_stage2_mkyoung() - Set the access flag in a page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * * The offset of @addr within a page is ignored. * * If there is a valid, leaf page-table entry used to translate @addr, then * set the access flag in that entry. * * Return: The old page-table entry prior to setting the flag, 0 on failure. */ kvm_pte_t kvm_pgtable_stage2_mkyoung(struct kvm_pgtable *pgt, u64 addr); /** * kvm_pgtable_stage2_test_clear_young() - Test and optionally clear the access * flag in a page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * @size: Size of the address range to visit. * @mkold: True if the access flag should be cleared. * * The offset of @addr within a page is ignored. * * Tests and conditionally clears the access flag for every valid, leaf * page-table entry used to translate the range [@addr, @addr + @size). * * Note that it is the caller's responsibility to invalidate the TLB after * calling this function to ensure that the updated permissions are visible * to the CPUs. * * Return: True if any of the visited PTEs had the access flag set. */ bool kvm_pgtable_stage2_test_clear_young(struct kvm_pgtable *pgt, u64 addr, u64 size, bool mkold); /** * kvm_pgtable_stage2_relax_perms() - Relax the permissions enforced by a * page-table entry. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address to identify the page-table entry. * @prot: Additional permissions to grant for the mapping. * * The offset of @addr within a page is ignored. * * If there is a valid, leaf page-table entry used to translate @addr, then * relax the permissions in that entry according to the read, write and * execute permissions specified by @prot. No permissions are removed, and * TLB invalidation is performed after updating the entry. Software bits cannot * be set or cleared using kvm_pgtable_stage2_relax_perms(). * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_relax_perms(struct kvm_pgtable *pgt, u64 addr, enum kvm_pgtable_prot prot); /** * kvm_pgtable_stage2_flush_range() - Clean and invalidate data cache to Point * of Coherency for guest stage-2 address * range. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init*(). * @addr: Intermediate physical address from which to flush. * @size: Size of the range. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_stage2_flush(struct kvm_pgtable *pgt, u64 addr, u64 size); /** * kvm_pgtable_stage2_split() - Split a range of huge pages into leaf PTEs pointing * to PAGE_SIZE guest pages. * @pgt: Page-table structure initialised by kvm_pgtable_stage2_init(). * @addr: Intermediate physical address from which to split. * @size: Size of the range. * @mc: Cache of pre-allocated and zeroed memory from which to allocate * page-table pages. * * The function tries to split any level 1 or 2 entry that overlaps * with the input range (given by @addr and @size). * * Return: 0 on success, negative error code on failure. Note that * kvm_pgtable_stage2_split() is best effort: it tries to break as many * blocks in the input range as allowed by @mc_capacity. */ int kvm_pgtable_stage2_split(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_mmu_memory_cache *mc); /** * kvm_pgtable_walk() - Walk a page-table. * @pgt: Page-table structure initialised by kvm_pgtable_*_init(). * @addr: Input address for the start of the walk. * @size: Size of the range to walk. * @walker: Walker callback description. * * The offset of @addr within a page is ignored and @size is rounded-up to * the next page boundary. * * The walker will walk the page-table entries corresponding to the input * address range specified, visiting entries according to the walker flags. * Invalid entries are treated as leaf entries. The visited page table entry is * reloaded after invoking the walker callback, allowing the walker to descend * into a newly installed table. * * Returning a negative error code from the walker callback function will * terminate the walk immediately with the same error code. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_walk(struct kvm_pgtable *pgt, u64 addr, u64 size, struct kvm_pgtable_walker *walker); /** * kvm_pgtable_get_leaf() - Walk a page-table and retrieve the leaf entry * with its level. * @pgt: Page-table structure initialised by kvm_pgtable_*_init() * or a similar initialiser. * @addr: Input address for the start of the walk. * @ptep: Pointer to storage for the retrieved PTE. * @level: Pointer to storage for the level of the retrieved PTE. * * The offset of @addr within a page is ignored. * * The walker will walk the page-table entries corresponding to the input * address specified, retrieving the leaf corresponding to this address. * Invalid entries are treated as leaf entries. * * Return: 0 on success, negative error code on failure. */ int kvm_pgtable_get_leaf(struct kvm_pgtable *pgt, u64 addr, kvm_pte_t *ptep, s8 *level); /** * kvm_pgtable_stage2_pte_prot() - Retrieve the protection attributes of a * stage-2 Page-Table Entry. * @pte: Page-table entry * * Return: protection attributes of the page-table entry in the enum * kvm_pgtable_prot format. */ enum kvm_pgtable_prot kvm_pgtable_stage2_pte_prot(kvm_pte_t pte); /** * kvm_pgtable_hyp_pte_prot() - Retrieve the protection attributes of a stage-1 * Page-Table Entry. * @pte: Page-table entry * * Return: protection attributes of the page-table entry in the enum * kvm_pgtable_prot format. */ enum kvm_pgtable_prot kvm_pgtable_hyp_pte_prot(kvm_pte_t pte); /** * kvm_tlb_flush_vmid_range() - Invalidate/flush a range of TLB entries * * @mmu: Stage-2 KVM MMU struct * @addr: The base Intermediate physical address from which to invalidate * @size: Size of the range from the base to invalidate */ void kvm_tlb_flush_vmid_range(struct kvm_s2_mmu *mmu, phys_addr_t addr, size_t size); #endif /* __ARM64_KVM_PGTABLE_H__ */ |
| 10 10 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* I/O iterator iteration building functions. * * Copyright (C) 2023 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef _LINUX_IOV_ITER_H #define _LINUX_IOV_ITER_H #include <linux/uio.h> #include <linux/bvec.h> typedef size_t (*iov_step_f)(void *iter_base, size_t progress, size_t len, void *priv, void *priv2); typedef size_t (*iov_ustep_f)(void __user *iter_base, size_t progress, size_t len, void *priv, void *priv2); /* * Handle ITER_UBUF. */ static __always_inline size_t iterate_ubuf(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { void __user *base = iter->ubuf; size_t progress = 0, remain; remain = step(base + iter->iov_offset, 0, len, priv, priv2); progress = len - remain; iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_IOVEC. */ static __always_inline size_t iterate_iovec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f step) { const struct iovec *p = iter->__iov; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->__iov; iter->__iov = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_KVEC. */ static __always_inline size_t iterate_kvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct kvec *p = iter->kvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t part = min(len, p->iov_len - skip); if (likely(part)) { remain = step(p->iov_base + skip, progress, part, priv, priv2); consumed = part - remain; progress += consumed; skip += consumed; len -= consumed; if (skip < p->iov_len) break; } p++; skip = 0; } while (len); iter->nr_segs -= p - iter->kvec; iter->kvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_BVEC. */ static __always_inline size_t iterate_bvec(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { const struct bio_vec *p = iter->bvec; size_t progress = 0, skip = iter->iov_offset; do { size_t remain, consumed; size_t offset = p->bv_offset + skip, part; void *kaddr = kmap_local_page(p->bv_page + offset / PAGE_SIZE); part = min3(len, (size_t)(p->bv_len - skip), (size_t)(PAGE_SIZE - offset % PAGE_SIZE)); remain = step(kaddr + offset % PAGE_SIZE, progress, part, priv, priv2); kunmap_local(kaddr); consumed = part - remain; len -= consumed; progress += consumed; skip += consumed; if (skip >= p->bv_len) { skip = 0; p++; } if (remain) break; } while (len); iter->nr_segs -= p - iter->bvec; iter->bvec = p; iter->iov_offset = skip; iter->count -= progress; return progress; } /* * Handle ITER_XARRAY. */ static __always_inline size_t iterate_xarray(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { struct folio *folio; size_t progress = 0; loff_t start = iter->xarray_start + iter->iov_offset; pgoff_t index = start / PAGE_SIZE; XA_STATE(xas, iter->xarray, index); rcu_read_lock(); xas_for_each(&xas, folio, ULONG_MAX) { size_t remain, consumed, offset, part, flen; if (xas_retry(&xas, folio)) continue; if (WARN_ON(xa_is_value(folio))) break; if (WARN_ON(folio_test_hugetlb(folio))) break; offset = offset_in_folio(folio, start + progress); flen = min(folio_size(folio) - offset, len); while (flen) { void *base = kmap_local_folio(folio, offset); part = min_t(size_t, flen, PAGE_SIZE - offset_in_page(offset)); remain = step(base, progress, part, priv, priv2); kunmap_local(base); consumed = part - remain; progress += consumed; len -= consumed; if (remain || len == 0) goto out; flen -= consumed; offset += consumed; } } out: rcu_read_unlock(); iter->iov_offset += progress; iter->count -= progress; return progress; } /* * Handle ITER_DISCARD. */ static __always_inline size_t iterate_discard(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_step_f step) { size_t progress = len; iter->count -= progress; return progress; } /** * iterate_and_advance2 - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @priv2: More data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * Iterate over the next part of an iterator, up to the specified length. The * buffer is presented in segments, which for kernel iteration are broken up by * physical pages and mapped, with the mapped address being presented. * * Two step functions, @step and @ustep, must be provided, one for handling * mapped kernel addresses and the other is given user addresses which have the * potential to fault since no pinning is performed. * * The step functions are passed the address and length of the segment, @priv, * @priv2 and the amount of data so far iterated over (which can, for example, * be added to @priv to point to the right part of a second buffer). The step * functions should return the amount of the segment they didn't process (ie. 0 * indicates complete processsing). * * This function returns the amount of data processed (ie. 0 means nothing was * processed and the value of @len means processes to completion). */ static __always_inline size_t iterate_and_advance2(struct iov_iter *iter, size_t len, void *priv, void *priv2, iov_ustep_f ustep, iov_step_f step) { if (unlikely(iter->count < len)) len = iter->count; if (unlikely(!len)) return 0; if (likely(iter_is_ubuf(iter))) return iterate_ubuf(iter, len, priv, priv2, ustep); if (likely(iter_is_iovec(iter))) return iterate_iovec(iter, len, priv, priv2, ustep); if (iov_iter_is_bvec(iter)) return iterate_bvec(iter, len, priv, priv2, step); if (iov_iter_is_kvec(iter)) return iterate_kvec(iter, len, priv, priv2, step); if (iov_iter_is_xarray(iter)) return iterate_xarray(iter, len, priv, priv2, step); return iterate_discard(iter, len, priv, priv2, step); } /** * iterate_and_advance - Iterate over an iterator * @iter: The iterator to iterate over. * @len: The amount to iterate over. * @priv: Data for the step functions. * @ustep: Function for UBUF/IOVEC iterators; given __user addresses. * @step: Function for other iterators; given kernel addresses. * * As iterate_and_advance2(), but priv2 is always NULL. */ static __always_inline size_t iterate_and_advance(struct iov_iter *iter, size_t len, void *priv, iov_ustep_f ustep, iov_step_f step) { return iterate_and_advance2(iter, len, priv, NULL, ustep, step); } #endif /* _LINUX_IOV_ITER_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (c) 2014-2015, The Linux Foundation. All rights reserved. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM clk #if !defined(_TRACE_CLK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CLK_H #include <linux/tracepoint.h> struct clk_core; DECLARE_EVENT_CLASS(clk, TP_PROTO(struct clk_core *core), TP_ARGS(core), TP_STRUCT__entry( __string( name, core->name ) ), TP_fast_assign( __assign_str(name); ), TP_printk("%s", __get_str(name)) ); DEFINE_EVENT(clk, clk_enable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_enable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_disable_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_prepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DEFINE_EVENT(clk, clk_unprepare_complete, TP_PROTO(struct clk_core *core), TP_ARGS(core) ); DECLARE_EVENT_CLASS(clk_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, rate ) ), TP_fast_assign( __assign_str(name); __entry->rate = rate; ), TP_printk("%s %lu", __get_str(name), (unsigned long)__entry->rate) ); DEFINE_EVENT(clk_rate, clk_set_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_rate_complete, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_min_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DEFINE_EVENT(clk_rate, clk_set_max_rate, TP_PROTO(struct clk_core *core, unsigned long rate), TP_ARGS(core, rate) ); DECLARE_EVENT_CLASS(clk_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max), TP_STRUCT__entry( __string( name, core->name ) __field(unsigned long, min ) __field(unsigned long, max ) ), TP_fast_assign( __assign_str(name); __entry->min = min; __entry->max = max; ), TP_printk("%s min %lu max %lu", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max) ); DEFINE_EVENT(clk_rate_range, clk_set_rate_range, TP_PROTO(struct clk_core *core, unsigned long min, unsigned long max), TP_ARGS(core, min, max) ); DECLARE_EVENT_CLASS(clk_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent), TP_STRUCT__entry( __string( name, core->name ) __string( pname, parent ? parent->name : "none" ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); ), TP_printk("%s %s", __get_str(name), __get_str(pname)) ); DEFINE_EVENT(clk_parent, clk_set_parent, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DEFINE_EVENT(clk_parent, clk_set_parent_complete, TP_PROTO(struct clk_core *core, struct clk_core *parent), TP_ARGS(core, parent) ); DECLARE_EVENT_CLASS(clk_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase), TP_STRUCT__entry( __string( name, core->name ) __field( int, phase ) ), TP_fast_assign( __assign_str(name); __entry->phase = phase; ), TP_printk("%s %d", __get_str(name), (int)__entry->phase) ); DEFINE_EVENT(clk_phase, clk_set_phase, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DEFINE_EVENT(clk_phase, clk_set_phase_complete, TP_PROTO(struct clk_core *core, int phase), TP_ARGS(core, phase) ); DECLARE_EVENT_CLASS(clk_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty), TP_STRUCT__entry( __string( name, core->name ) __field( unsigned int, num ) __field( unsigned int, den ) ), TP_fast_assign( __assign_str(name); __entry->num = duty->num; __entry->den = duty->den; ), TP_printk("%s %u/%u", __get_str(name), (unsigned int)__entry->num, (unsigned int)__entry->den) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DEFINE_EVENT(clk_duty_cycle, clk_set_duty_cycle_complete, TP_PROTO(struct clk_core *core, struct clk_duty *duty), TP_ARGS(core, duty) ); DECLARE_EVENT_CLASS(clk_rate_request, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req), TP_STRUCT__entry( __string( name, req->core ? req->core->name : "none") __string( pname, req->best_parent_hw ? clk_hw_get_name(req->best_parent_hw) : "none" ) __field(unsigned long, min ) __field(unsigned long, max ) __field(unsigned long, prate ) ), TP_fast_assign( __assign_str(name); __assign_str(pname); __entry->min = req->min_rate; __entry->max = req->max_rate; __entry->prate = req->best_parent_rate; ), TP_printk("%s min %lu max %lu, parent %s (%lu)", __get_str(name), (unsigned long)__entry->min, (unsigned long)__entry->max, __get_str(pname), (unsigned long)__entry->prate) ); DEFINE_EVENT(clk_rate_request, clk_rate_request_start, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req) ); DEFINE_EVENT(clk_rate_request, clk_rate_request_done, TP_PROTO(struct clk_rate_request *req), TP_ARGS(req) ); #endif /* _TRACE_CLK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 | /* SPDX-License-Identifier: GPL-2.0 */ /* * An extensible bitmap is a bitmap that supports an * arbitrary number of bits. Extensible bitmaps are * used to represent sets of values, such as types, * roles, categories, and classes. * * Each extensible bitmap is implemented as a linked * list of bitmap nodes, where each bitmap node has * an explicitly specified starting bit position within * the total bitmap. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ #ifndef _SS_EBITMAP_H_ #define _SS_EBITMAP_H_ #include <net/netlabel.h> #ifdef CONFIG_64BIT #define EBITMAP_NODE_SIZE 64 #else #define EBITMAP_NODE_SIZE 32 #endif #define EBITMAP_UNIT_NUMS \ ((EBITMAP_NODE_SIZE - sizeof(void *) - sizeof(u32)) / \ sizeof(unsigned long)) #define EBITMAP_UNIT_SIZE BITS_PER_LONG #define EBITMAP_SIZE (EBITMAP_UNIT_NUMS * EBITMAP_UNIT_SIZE) #define EBITMAP_BIT 1ULL #define EBITMAP_SHIFT_UNIT_SIZE(x) \ (((x) >> EBITMAP_UNIT_SIZE / 2) >> EBITMAP_UNIT_SIZE / 2) struct ebitmap_node { struct ebitmap_node *next; unsigned long maps[EBITMAP_UNIT_NUMS]; u32 startbit; }; struct ebitmap { struct ebitmap_node *node; /* first node in the bitmap */ u32 highbit; /* highest position in the total bitmap */ }; #define ebitmap_length(e) ((e)->highbit) static inline u32 ebitmap_start_positive(const struct ebitmap *e, struct ebitmap_node **n) { u32 ofs; for (*n = e->node; *n; *n = (*n)->next) { ofs = find_first_bit((*n)->maps, EBITMAP_SIZE); if (ofs < EBITMAP_SIZE) return (*n)->startbit + ofs; } return ebitmap_length(e); } static inline void ebitmap_init(struct ebitmap *e) { memset(e, 0, sizeof(*e)); } static inline u32 ebitmap_next_positive(const struct ebitmap *e, struct ebitmap_node **n, u32 bit) { u32 ofs; ofs = find_next_bit((*n)->maps, EBITMAP_SIZE, bit - (*n)->startbit + 1); if (ofs < EBITMAP_SIZE) return ofs + (*n)->startbit; for (*n = (*n)->next; *n; *n = (*n)->next) { ofs = find_first_bit((*n)->maps, EBITMAP_SIZE); if (ofs < EBITMAP_SIZE) return ofs + (*n)->startbit; } return ebitmap_length(e); } #define EBITMAP_NODE_INDEX(node, bit) \ (((bit) - (node)->startbit) / EBITMAP_UNIT_SIZE) #define EBITMAP_NODE_OFFSET(node, bit) \ (((bit) - (node)->startbit) % EBITMAP_UNIT_SIZE) static inline int ebitmap_node_get_bit(const struct ebitmap_node *n, u32 bit) { u32 index = EBITMAP_NODE_INDEX(n, bit); u32 ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); if ((n->maps[index] & (EBITMAP_BIT << ofs))) return 1; return 0; } static inline void ebitmap_node_set_bit(struct ebitmap_node *n, u32 bit) { u32 index = EBITMAP_NODE_INDEX(n, bit); u32 ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); n->maps[index] |= (EBITMAP_BIT << ofs); } static inline void ebitmap_node_clr_bit(struct ebitmap_node *n, u32 bit) { u32 index = EBITMAP_NODE_INDEX(n, bit); u32 ofs = EBITMAP_NODE_OFFSET(n, bit); BUG_ON(index >= EBITMAP_UNIT_NUMS); n->maps[index] &= ~(EBITMAP_BIT << ofs); } #define ebitmap_for_each_positive_bit(e, n, bit) \ for ((bit) = ebitmap_start_positive(e, &(n)); \ (bit) < ebitmap_length(e); \ (bit) = ebitmap_next_positive(e, &(n), bit)) int ebitmap_cmp(const struct ebitmap *e1, const struct ebitmap *e2); int ebitmap_cpy(struct ebitmap *dst, const struct ebitmap *src); int ebitmap_and(struct ebitmap *dst, const struct ebitmap *e1, const struct ebitmap *e2); int ebitmap_contains(const struct ebitmap *e1, const struct ebitmap *e2, u32 last_e2bit); int ebitmap_get_bit(const struct ebitmap *e, u32 bit); int ebitmap_set_bit(struct ebitmap *e, u32 bit, int value); void ebitmap_destroy(struct ebitmap *e); int ebitmap_read(struct ebitmap *e, void *fp); int ebitmap_write(const struct ebitmap *e, void *fp); u32 ebitmap_hash(const struct ebitmap *e, u32 hash); #ifdef CONFIG_NETLABEL int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap); int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap); #else static inline int ebitmap_netlbl_export(struct ebitmap *ebmap, struct netlbl_lsm_catmap **catmap) { return -ENOMEM; } static inline int ebitmap_netlbl_import(struct ebitmap *ebmap, struct netlbl_lsm_catmap *catmap) { return -ENOMEM; } #endif #endif /* _SS_EBITMAP_H_ */ |
| 412 411 413 413 412 413 412 413 411 411 412 412 413 411 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Common arm64 stack unwinder code. * * See: arch/arm64/kernel/stacktrace.c for the reference implementation. * * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_STACKTRACE_COMMON_H #define __ASM_STACKTRACE_COMMON_H #include <linux/types.h> struct stack_info { unsigned long low; unsigned long high; }; /** * struct unwind_state - state used for robust unwinding. * * @fp: The fp value in the frame record (or the real fp) * @pc: The lr value in the frame record (or the real lr) * * @stack: The stack currently being unwound. * @stacks: An array of stacks which can be unwound. * @nr_stacks: The number of stacks in @stacks. */ struct unwind_state { unsigned long fp; unsigned long pc; struct stack_info stack; struct stack_info *stacks; int nr_stacks; }; static inline struct stack_info stackinfo_get_unknown(void) { return (struct stack_info) { .low = 0, .high = 0, }; } static inline bool stackinfo_on_stack(const struct stack_info *info, unsigned long sp, unsigned long size) { if (!info->low) return false; if (sp < info->low || sp + size < sp || sp + size > info->high) return false; return true; } static inline void unwind_init_common(struct unwind_state *state) { state->stack = stackinfo_get_unknown(); } static struct stack_info *unwind_find_next_stack(const struct unwind_state *state, unsigned long sp, unsigned long size) { for (int i = 0; i < state->nr_stacks; i++) { struct stack_info *info = &state->stacks[i]; if (stackinfo_on_stack(info, sp, size)) return info; } return NULL; } /** * unwind_consume_stack() - Check if an object is on an accessible stack, * updating stack boundaries so that future unwind steps cannot consume this * object again. * * @state: the current unwind state. * @sp: the base address of the object. * @size: the size of the object. * * Return: 0 upon success, an error code otherwise. */ static inline int unwind_consume_stack(struct unwind_state *state, unsigned long sp, unsigned long size) { struct stack_info *next; if (stackinfo_on_stack(&state->stack, sp, size)) goto found; next = unwind_find_next_stack(state, sp, size); if (!next) return -EINVAL; /* * Stack transitions are strictly one-way, and once we've * transitioned from one stack to another, it's never valid to * unwind back to the old stack. * * Remove the current stack from the list of stacks so that it cannot * be found on a subsequent transition. * * Note that stacks can nest in several valid orders, e.g. * * TASK -> IRQ -> OVERFLOW -> SDEI_NORMAL * TASK -> SDEI_NORMAL -> SDEI_CRITICAL -> OVERFLOW * HYP -> OVERFLOW * * ... so we do not check the specific order of stack * transitions. */ state->stack = *next; *next = stackinfo_get_unknown(); found: /* * Future unwind steps can only consume stack above this frame record. * Update the current stack to start immediately above it. */ state->stack.low = sp + size; return 0; } /** * unwind_next_frame_record() - Unwind to the next frame record. * * @state: the current unwind state. * * Return: 0 upon success, an error code otherwise. */ static inline int unwind_next_frame_record(struct unwind_state *state) { unsigned long fp = state->fp; int err; if (fp & 0x7) return -EINVAL; err = unwind_consume_stack(state, fp, 16); if (err) return err; /* * Record this frame record's values. */ state->fp = READ_ONCE(*(unsigned long *)(fp)); state->pc = READ_ONCE(*(unsigned long *)(fp + 8)); return 0; } #endif /* __ASM_STACKTRACE_COMMON_H */ |
| 135 60 136 105 104 60 60 49 49 1 1 49 1 1 1 136 136 136 136 136 136 136 87 95 136 1 136 136 81 37 1 37 35 37 2 2 114 69 4 68 68 68 94 98 47 48 1 47 48 48 60 136 134 134 134 1 135 136 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/fault.c * * Copyright (C) 1995 Linus Torvalds * Copyright (C) 1995-2004 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/acpi.h> #include <linux/bitfield.h> #include <linux/extable.h> #include <linux/kfence.h> #include <linux/signal.h> #include <linux/mm.h> #include <linux/hardirq.h> #include <linux/init.h> #include <linux/kasan.h> #include <linux/kprobes.h> #include <linux/uaccess.h> #include <linux/page-flags.h> #include <linux/sched/signal.h> #include <linux/sched/debug.h> #include <linux/highmem.h> #include <linux/perf_event.h> #include <linux/preempt.h> #include <linux/hugetlb.h> #include <asm/acpi.h> #include <asm/bug.h> #include <asm/cmpxchg.h> #include <asm/cpufeature.h> #include <asm/efi.h> #include <asm/exception.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/esr.h> #include <asm/kprobes.h> #include <asm/mte.h> #include <asm/processor.h> #include <asm/sysreg.h> #include <asm/system_misc.h> #include <asm/tlbflush.h> #include <asm/traps.h> struct fault_info { int (*fn)(unsigned long far, unsigned long esr, struct pt_regs *regs); int sig; int code; const char *name; }; static const struct fault_info fault_info[]; static struct fault_info debug_fault_info[]; static inline const struct fault_info *esr_to_fault_info(unsigned long esr) { return fault_info + (esr & ESR_ELx_FSC); } static inline const struct fault_info *esr_to_debug_fault_info(unsigned long esr) { return debug_fault_info + DBG_ESR_EVT(esr); } static void data_abort_decode(unsigned long esr) { unsigned long iss2 = ESR_ELx_ISS2(esr); pr_alert("Data abort info:\n"); if (esr & ESR_ELx_ISV) { pr_alert(" Access size = %u byte(s)\n", 1U << ((esr & ESR_ELx_SAS) >> ESR_ELx_SAS_SHIFT)); pr_alert(" SSE = %lu, SRT = %lu\n", (esr & ESR_ELx_SSE) >> ESR_ELx_SSE_SHIFT, (esr & ESR_ELx_SRT_MASK) >> ESR_ELx_SRT_SHIFT); pr_alert(" SF = %lu, AR = %lu\n", (esr & ESR_ELx_SF) >> ESR_ELx_SF_SHIFT, (esr & ESR_ELx_AR) >> ESR_ELx_AR_SHIFT); } else { pr_alert(" ISV = 0, ISS = 0x%08lx, ISS2 = 0x%08lx\n", esr & ESR_ELx_ISS_MASK, iss2); } pr_alert(" CM = %lu, WnR = %lu, TnD = %lu, TagAccess = %lu\n", (esr & ESR_ELx_CM) >> ESR_ELx_CM_SHIFT, (esr & ESR_ELx_WNR) >> ESR_ELx_WNR_SHIFT, (iss2 & ESR_ELx_TnD) >> ESR_ELx_TnD_SHIFT, (iss2 & ESR_ELx_TagAccess) >> ESR_ELx_TagAccess_SHIFT); pr_alert(" GCS = %ld, Overlay = %lu, DirtyBit = %lu, Xs = %llu\n", (iss2 & ESR_ELx_GCS) >> ESR_ELx_GCS_SHIFT, (iss2 & ESR_ELx_Overlay) >> ESR_ELx_Overlay_SHIFT, (iss2 & ESR_ELx_DirtyBit) >> ESR_ELx_DirtyBit_SHIFT, (iss2 & ESR_ELx_Xs_MASK) >> ESR_ELx_Xs_SHIFT); } static void mem_abort_decode(unsigned long esr) { pr_alert("Mem abort info:\n"); pr_alert(" ESR = 0x%016lx\n", esr); pr_alert(" EC = 0x%02lx: %s, IL = %u bits\n", ESR_ELx_EC(esr), esr_get_class_string(esr), (esr & ESR_ELx_IL) ? 32 : 16); pr_alert(" SET = %lu, FnV = %lu\n", (esr & ESR_ELx_SET_MASK) >> ESR_ELx_SET_SHIFT, (esr & ESR_ELx_FnV) >> ESR_ELx_FnV_SHIFT); pr_alert(" EA = %lu, S1PTW = %lu\n", (esr & ESR_ELx_EA) >> ESR_ELx_EA_SHIFT, (esr & ESR_ELx_S1PTW) >> ESR_ELx_S1PTW_SHIFT); pr_alert(" FSC = 0x%02lx: %s\n", (esr & ESR_ELx_FSC), esr_to_fault_info(esr)->name); if (esr_is_data_abort(esr)) data_abort_decode(esr); } static inline unsigned long mm_to_pgd_phys(struct mm_struct *mm) { /* Either init_pg_dir or swapper_pg_dir */ if (mm == &init_mm) return __pa_symbol(mm->pgd); return (unsigned long)virt_to_phys(mm->pgd); } /* * Dump out the page tables associated with 'addr' in the currently active mm. */ static void show_pte(unsigned long addr) { struct mm_struct *mm; pgd_t *pgdp; pgd_t pgd; if (is_ttbr0_addr(addr)) { /* TTBR0 */ mm = current->active_mm; if (mm == &init_mm) { pr_alert("[%016lx] user address but active_mm is swapper\n", addr); return; } } else if (is_ttbr1_addr(addr)) { /* TTBR1 */ mm = &init_mm; } else { pr_alert("[%016lx] address between user and kernel address ranges\n", addr); return; } pr_alert("%s pgtable: %luk pages, %llu-bit VAs, pgdp=%016lx\n", mm == &init_mm ? "swapper" : "user", PAGE_SIZE / SZ_1K, vabits_actual, mm_to_pgd_phys(mm)); pgdp = pgd_offset(mm, addr); pgd = READ_ONCE(*pgdp); pr_alert("[%016lx] pgd=%016llx", addr, pgd_val(pgd)); do { p4d_t *p4dp, p4d; pud_t *pudp, pud; pmd_t *pmdp, pmd; pte_t *ptep, pte; if (pgd_none(pgd) || pgd_bad(pgd)) break; p4dp = p4d_offset(pgdp, addr); p4d = READ_ONCE(*p4dp); pr_cont(", p4d=%016llx", p4d_val(p4d)); if (p4d_none(p4d) || p4d_bad(p4d)) break; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); pr_cont(", pud=%016llx", pud_val(pud)); if (pud_none(pud) || pud_bad(pud)) break; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); pr_cont(", pmd=%016llx", pmd_val(pmd)); if (pmd_none(pmd) || pmd_bad(pmd)) break; ptep = pte_offset_map(pmdp, addr); if (!ptep) break; pte = __ptep_get(ptep); pr_cont(", pte=%016llx", pte_val(pte)); pte_unmap(ptep); } while(0); pr_cont("\n"); } /* * This function sets the access flags (dirty, accessed), as well as write * permission, and only to a more permissive setting. * * It needs to cope with hardware update of the accessed/dirty state by other * agents in the system and can safely skip the __sync_icache_dcache() call as, * like __set_ptes(), the PTE is never changed from no-exec to exec here. * * Returns whether or not the PTE actually changed. */ int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty) { pteval_t old_pteval, pteval; pte_t pte = __ptep_get(ptep); if (pte_same(pte, entry)) return 0; /* only preserve the access flags and write permission */ pte_val(entry) &= PTE_RDONLY | PTE_AF | PTE_WRITE | PTE_DIRTY; /* * Setting the flags must be done atomically to avoid racing with the * hardware update of the access/dirty state. The PTE_RDONLY bit must * be set to the most permissive (lowest value) of *ptep and entry * (calculated as: a & b == ~(~a | ~b)). */ pte_val(entry) ^= PTE_RDONLY; pteval = pte_val(pte); do { old_pteval = pteval; pteval ^= PTE_RDONLY; pteval |= pte_val(entry); pteval ^= PTE_RDONLY; pteval = cmpxchg_relaxed(&pte_val(*ptep), old_pteval, pteval); } while (pteval != old_pteval); /* Invalidate a stale read-only entry */ if (dirty) flush_tlb_page(vma, address); return 1; } static bool is_el1_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_CUR; } static bool is_el1_data_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_DABT_CUR; } static inline bool is_el1_permission_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { if (!is_el1_data_abort(esr) && !is_el1_instruction_abort(esr)) return false; if (esr_fsc_is_permission_fault(esr)) return true; if (is_ttbr0_addr(addr) && system_uses_ttbr0_pan()) return esr_fsc_is_translation_fault(esr) && (regs->pstate & PSR_PAN_BIT); return false; } static bool __kprobes is_spurious_el1_translation_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { unsigned long flags; u64 par, dfsc; if (!is_el1_data_abort(esr) || !esr_fsc_is_translation_fault(esr)) return false; local_irq_save(flags); asm volatile("at s1e1r, %0" :: "r" (addr)); isb(); par = read_sysreg_par(); local_irq_restore(flags); /* * If we now have a valid translation, treat the translation fault as * spurious. */ if (!(par & SYS_PAR_EL1_F)) return true; /* * If we got a different type of fault from the AT instruction, * treat the translation fault as spurious. */ dfsc = FIELD_GET(SYS_PAR_EL1_FST, par); return !esr_fsc_is_translation_fault(dfsc); } static void die_kernel_fault(const char *msg, unsigned long addr, unsigned long esr, struct pt_regs *regs) { bust_spinlocks(1); pr_alert("Unable to handle kernel %s at virtual address %016lx\n", msg, addr); kasan_non_canonical_hook(addr); mem_abort_decode(esr); show_pte(addr); die("Oops", regs, esr); bust_spinlocks(0); make_task_dead(SIGKILL); } #ifdef CONFIG_KASAN_HW_TAGS static void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { /* * SAS bits aren't set for all faults reported in EL1, so we can't * find out access size. */ bool is_write = !!(esr & ESR_ELx_WNR); kasan_report((void *)addr, 0, is_write, regs->pc); } #else /* Tag faults aren't enabled without CONFIG_KASAN_HW_TAGS. */ static inline void report_tag_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { } #endif static void do_tag_recovery(unsigned long addr, unsigned long esr, struct pt_regs *regs) { report_tag_fault(addr, esr, regs); /* * Disable MTE Tag Checking on the local CPU for the current EL. * It will be done lazily on the other CPUs when they will hit a * tag fault. */ sysreg_clear_set(sctlr_el1, SCTLR_EL1_TCF_MASK, SYS_FIELD_PREP_ENUM(SCTLR_EL1, TCF, NONE)); isb(); } static bool is_el1_mte_sync_tag_check_fault(unsigned long esr) { unsigned long fsc = esr & ESR_ELx_FSC; if (!is_el1_data_abort(esr)) return false; if (fsc == ESR_ELx_FSC_MTE) return true; return false; } static void __do_kernel_fault(unsigned long addr, unsigned long esr, struct pt_regs *regs) { const char *msg; /* * Are we prepared to handle this kernel fault? * We are almost certainly not prepared to handle instruction faults. */ if (!is_el1_instruction_abort(esr) && fixup_exception(regs)) return; if (WARN_RATELIMIT(is_spurious_el1_translation_fault(addr, esr, regs), "Ignoring spurious kernel translation fault at virtual address %016lx\n", addr)) return; if (is_el1_mte_sync_tag_check_fault(esr)) { do_tag_recovery(addr, esr, regs); return; } if (is_el1_permission_fault(addr, esr, regs)) { if (esr & ESR_ELx_WNR) msg = "write to read-only memory"; else if (is_el1_instruction_abort(esr)) msg = "execute from non-executable memory"; else msg = "read from unreadable memory"; } else if (addr < PAGE_SIZE) { msg = "NULL pointer dereference"; } else { if (esr_fsc_is_translation_fault(esr) && kfence_handle_page_fault(addr, esr & ESR_ELx_WNR, regs)) return; msg = "paging request"; } if (efi_runtime_fixup_exception(regs, msg)) return; die_kernel_fault(msg, addr, esr, regs); } static void set_thread_esr(unsigned long address, unsigned long esr) { current->thread.fault_address = address; /* * If the faulting address is in the kernel, we must sanitize the ESR. * From userspace's point of view, kernel-only mappings don't exist * at all, so we report them as level 0 translation faults. * (This is not quite the way that "no mapping there at all" behaves: * an alignment fault not caused by the memory type would take * precedence over translation fault for a real access to empty * space. Unfortunately we can't easily distinguish "alignment fault * not caused by memory type" from "alignment fault caused by memory * type", so we ignore this wrinkle and just return the translation * fault.) */ if (!is_ttbr0_addr(current->thread.fault_address)) { switch (ESR_ELx_EC(esr)) { case ESR_ELx_EC_DABT_LOW: /* * These bits provide only information about the * faulting instruction, which userspace knows already. * We explicitly clear bits which are architecturally * RES0 in case they are given meanings in future. * We always report the ESR as if the fault was taken * to EL1 and so ISV and the bits in ISS[23:14] are * clear. (In fact it always will be a fault to EL1.) */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL | ESR_ELx_CM | ESR_ELx_WNR; esr |= ESR_ELx_FSC_FAULT; break; case ESR_ELx_EC_IABT_LOW: /* * Claim a level 0 translation fault. * All other bits are architecturally RES0 for faults * reported with that DFSC value, so we clear them. */ esr &= ESR_ELx_EC_MASK | ESR_ELx_IL; esr |= ESR_ELx_FSC_FAULT; break; default: /* * This should never happen (entry.S only brings us * into this code for insn and data aborts from a lower * exception level). Fail safe by not providing an ESR * context record at all. */ WARN(1, "ESR 0x%lx is not DABT or IABT from EL0\n", esr); esr = 0; break; } } current->thread.fault_code = esr; } static void do_bad_area(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (user_mode(regs)) { const struct fault_info *inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); arm64_force_sig_fault(inf->sig, inf->code, far, inf->name); } else { __do_kernel_fault(addr, esr, regs); } } static bool is_el0_instruction_abort(unsigned long esr) { return ESR_ELx_EC(esr) == ESR_ELx_EC_IABT_LOW; } /* * Note: not valid for EL1 DC IVAC, but we never use that such that it * should fault. EL0 cannot issue DC IVAC (undef). */ static bool is_write_abort(unsigned long esr) { return (esr & ESR_ELx_WNR) && !(esr & ESR_ELx_CM); } static int __kprobes do_page_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; struct mm_struct *mm = current->mm; vm_fault_t fault; unsigned long vm_flags; unsigned int mm_flags = FAULT_FLAG_DEFAULT; unsigned long addr = untagged_addr(far); struct vm_area_struct *vma; int si_code; if (kprobe_page_fault(regs, esr)) return 0; /* * If we're in an interrupt or have no user context, we must not take * the fault. */ if (faulthandler_disabled() || !mm) goto no_context; if (user_mode(regs)) mm_flags |= FAULT_FLAG_USER; /* * vm_flags tells us what bits we must have in vma->vm_flags * for the fault to be benign, __do_page_fault() would check * vma->vm_flags & vm_flags and returns an error if the * intersection is empty */ if (is_el0_instruction_abort(esr)) { /* It was exec fault */ vm_flags = VM_EXEC; mm_flags |= FAULT_FLAG_INSTRUCTION; } else if (is_write_abort(esr)) { /* It was write fault */ vm_flags = VM_WRITE; mm_flags |= FAULT_FLAG_WRITE; } else { /* It was read fault */ vm_flags = VM_READ; /* Write implies read */ vm_flags |= VM_WRITE; /* If EPAN is absent then exec implies read */ if (!alternative_has_cap_unlikely(ARM64_HAS_EPAN)) vm_flags |= VM_EXEC; } if (is_ttbr0_addr(addr) && is_el1_permission_fault(addr, esr, regs)) { if (is_el1_instruction_abort(esr)) die_kernel_fault("execution of user memory", addr, esr, regs); if (!search_exception_tables(regs->pc)) die_kernel_fault("access to user memory outside uaccess routines", addr, esr, regs); } perf_sw_event(PERF_COUNT_SW_PAGE_FAULTS, 1, regs, addr); if (!(mm_flags & FAULT_FLAG_USER)) goto lock_mmap; vma = lock_vma_under_rcu(mm, addr); if (!vma) goto lock_mmap; if (!(vma->vm_flags & vm_flags)) { vma_end_read(vma); fault = 0; si_code = SEGV_ACCERR; count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags | FAULT_FLAG_VMA_LOCK, regs); if (!(fault & (VM_FAULT_RETRY | VM_FAULT_COMPLETED))) vma_end_read(vma); if (!(fault & VM_FAULT_RETRY)) { count_vm_vma_lock_event(VMA_LOCK_SUCCESS); goto done; } count_vm_vma_lock_event(VMA_LOCK_RETRY); if (fault & VM_FAULT_MAJOR) mm_flags |= FAULT_FLAG_TRIED; /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } lock_mmap: retry: vma = lock_mm_and_find_vma(mm, addr, regs); if (unlikely(!vma)) { fault = 0; si_code = SEGV_MAPERR; goto bad_area; } if (!(vma->vm_flags & vm_flags)) { mmap_read_unlock(mm); fault = 0; si_code = SEGV_ACCERR; goto bad_area; } fault = handle_mm_fault(vma, addr, mm_flags, regs); /* Quick path to respond to signals */ if (fault_signal_pending(fault, regs)) { if (!user_mode(regs)) goto no_context; return 0; } /* The fault is fully completed (including releasing mmap lock) */ if (fault & VM_FAULT_COMPLETED) return 0; if (fault & VM_FAULT_RETRY) { mm_flags |= FAULT_FLAG_TRIED; goto retry; } mmap_read_unlock(mm); done: /* Handle the "normal" (no error) case first. */ if (likely(!(fault & VM_FAULT_ERROR))) return 0; si_code = SEGV_MAPERR; bad_area: /* * If we are in kernel mode at this point, we have no context to * handle this fault with. */ if (!user_mode(regs)) goto no_context; if (fault & VM_FAULT_OOM) { /* * We ran out of memory, call the OOM killer, and return to * userspace (which will retry the fault, or kill us if we got * oom-killed). */ pagefault_out_of_memory(); return 0; } inf = esr_to_fault_info(esr); set_thread_esr(addr, esr); if (fault & VM_FAULT_SIGBUS) { /* * We had some memory, but were unable to successfully fix up * this page fault. */ arm64_force_sig_fault(SIGBUS, BUS_ADRERR, far, inf->name); } else if (fault & (VM_FAULT_HWPOISON_LARGE | VM_FAULT_HWPOISON)) { unsigned int lsb; lsb = PAGE_SHIFT; if (fault & VM_FAULT_HWPOISON_LARGE) lsb = hstate_index_to_shift(VM_FAULT_GET_HINDEX(fault)); arm64_force_sig_mceerr(BUS_MCEERR_AR, far, lsb, inf->name); } else { /* Something tried to access memory that out of memory map */ arm64_force_sig_fault(SIGSEGV, si_code, far, inf->name); } return 0; no_context: __do_kernel_fault(addr, esr, regs); return 0; } static int __kprobes do_translation_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { unsigned long addr = untagged_addr(far); if (is_ttbr0_addr(addr)) return do_page_fault(far, esr, regs); do_bad_area(far, esr, regs); return 0; } static int do_alignment_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { if (IS_ENABLED(CONFIG_COMPAT_ALIGNMENT_FIXUPS) && compat_user_mode(regs)) return do_compat_alignment_fixup(far, regs); do_bad_area(far, esr, regs); return 0; } static int do_bad(unsigned long far, unsigned long esr, struct pt_regs *regs) { return 1; /* "fault" */ } static int do_sea(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf; unsigned long siaddr; inf = esr_to_fault_info(esr); if (user_mode(regs) && apei_claim_sea(regs) == 0) { /* * APEI claimed this as a firmware-first notification. * Some processing deferred to task_work before ret_to_user(). */ return 0; } if (esr & ESR_ELx_FnV) { siaddr = 0; } else { /* * The architecture specifies that the tag bits of FAR_EL1 are * UNKNOWN for synchronous external aborts. Mask them out now * so that userspace doesn't see them. */ siaddr = untagged_addr(far); } arm64_notify_die(inf->name, regs, inf->sig, inf->code, siaddr, esr); return 0; } static int do_tag_check_fault(unsigned long far, unsigned long esr, struct pt_regs *regs) { /* * The architecture specifies that bits 63:60 of FAR_EL1 are UNKNOWN * for tag check faults. Set them to corresponding bits in the untagged * address. */ far = (__untagged_addr(far) & ~MTE_TAG_MASK) | (far & MTE_TAG_MASK); do_bad_area(far, esr, regs); return 0; } static const struct fault_info fault_info[] = { { do_bad, SIGKILL, SI_KERNEL, "ttbr address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 2 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "level 3 address size fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 0 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 1 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 2 translation fault" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level 3 translation fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 access flag fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 0 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 1 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 2 permission fault" }, { do_page_fault, SIGSEGV, SEGV_ACCERR, "level 3 permission fault" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous external abort" }, { do_tag_check_fault, SIGSEGV, SEGV_MTESERR, "synchronous tag check fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 18" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 0 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 1 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 2 (translation table walk)" }, { do_sea, SIGKILL, SI_KERNEL, "level 3 (translation table walk)" }, { do_sea, SIGBUS, BUS_OBJERR, "synchronous parity or ECC error" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 25" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 26" }, { do_sea, SIGKILL, SI_KERNEL, "level -1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 0 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 1 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 2 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_sea, SIGKILL, SI_KERNEL, "level 3 synchronous parity error (translation table walk)" }, // Reserved when RAS is implemented { do_bad, SIGKILL, SI_KERNEL, "unknown 32" }, { do_alignment_fault, SIGBUS, BUS_ADRALN, "alignment fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 34" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 35" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 36" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 37" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 38" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 39" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 40" }, { do_bad, SIGKILL, SI_KERNEL, "level -1 address size fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 42" }, { do_translation_fault, SIGSEGV, SEGV_MAPERR, "level -1 translation fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 44" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 45" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 46" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 47" }, { do_bad, SIGKILL, SI_KERNEL, "TLB conflict abort" }, { do_bad, SIGKILL, SI_KERNEL, "Unsupported atomic hardware update fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 50" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 51" }, { do_bad, SIGKILL, SI_KERNEL, "implementation fault (lockdown abort)" }, { do_bad, SIGBUS, BUS_OBJERR, "implementation fault (unsupported exclusive)" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 54" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 55" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 56" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 57" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 58" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 59" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 60" }, { do_bad, SIGKILL, SI_KERNEL, "section domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "page domain fault" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 63" }, }; void do_mem_abort(unsigned long far, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_fault_info(esr); unsigned long addr = untagged_addr(far); if (!inf->fn(far, esr, regs)) return; if (!user_mode(regs)) die_kernel_fault(inf->name, addr, esr, regs); /* * At this point we have an unrecognized fault type whose tag bits may * have been defined as UNKNOWN. Therefore we only expose the untagged * address to the signal handler. */ arm64_notify_die(inf->name, regs, inf->sig, inf->code, addr, esr); } NOKPROBE_SYMBOL(do_mem_abort); void do_sp_pc_abort(unsigned long addr, unsigned long esr, struct pt_regs *regs) { arm64_notify_die("SP/PC alignment exception", regs, SIGBUS, BUS_ADRALN, addr, esr); } NOKPROBE_SYMBOL(do_sp_pc_abort); /* * __refdata because early_brk64 is __init, but the reference to it is * clobbered at arch_initcall time. * See traps.c and debug-monitors.c:debug_traps_init(). */ static struct fault_info __refdata debug_fault_info[] = { { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware breakpoint" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware single-step" }, { do_bad, SIGTRAP, TRAP_HWBKPT, "hardware watchpoint" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 3" }, { do_bad, SIGTRAP, TRAP_BRKPT, "aarch32 BKPT" }, { do_bad, SIGKILL, SI_KERNEL, "aarch32 vector catch" }, { early_brk64, SIGTRAP, TRAP_BRKPT, "aarch64 BRK" }, { do_bad, SIGKILL, SI_KERNEL, "unknown 7" }, }; void __init hook_debug_fault_code(int nr, int (*fn)(unsigned long, unsigned long, struct pt_regs *), int sig, int code, const char *name) { BUG_ON(nr < 0 || nr >= ARRAY_SIZE(debug_fault_info)); debug_fault_info[nr].fn = fn; debug_fault_info[nr].sig = sig; debug_fault_info[nr].code = code; debug_fault_info[nr].name = name; } /* * In debug exception context, we explicitly disable preemption despite * having interrupts disabled. * This serves two purposes: it makes it much less likely that we would * accidentally schedule in exception context and it will force a warning * if we somehow manage to schedule by accident. */ static void debug_exception_enter(struct pt_regs *regs) { preempt_disable(); /* This code is a bit fragile. Test it. */ RCU_LOCKDEP_WARN(!rcu_is_watching(), "exception_enter didn't work"); } NOKPROBE_SYMBOL(debug_exception_enter); static void debug_exception_exit(struct pt_regs *regs) { preempt_enable_no_resched(); } NOKPROBE_SYMBOL(debug_exception_exit); void do_debug_exception(unsigned long addr_if_watchpoint, unsigned long esr, struct pt_regs *regs) { const struct fault_info *inf = esr_to_debug_fault_info(esr); unsigned long pc = instruction_pointer(regs); debug_exception_enter(regs); if (user_mode(regs) && !is_ttbr0_addr(pc)) arm64_apply_bp_hardening(); if (inf->fn(addr_if_watchpoint, esr, regs)) { arm64_notify_die(inf->name, regs, inf->sig, inf->code, pc, esr); } debug_exception_exit(regs); } NOKPROBE_SYMBOL(do_debug_exception); /* * Used during anonymous page fault handling. */ struct folio *vma_alloc_zeroed_movable_folio(struct vm_area_struct *vma, unsigned long vaddr) { gfp_t flags = GFP_HIGHUSER_MOVABLE | __GFP_ZERO; /* * If the page is mapped with PROT_MTE, initialise the tags at the * point of allocation and page zeroing as this is usually faster than * separate DC ZVA and STGM. */ if (vma->vm_flags & VM_MTE) flags |= __GFP_ZEROTAGS; return vma_alloc_folio(flags, 0, vma, vaddr, false); } void tag_clear_highpage(struct page *page) { /* Newly allocated page, shouldn't have been tagged yet */ WARN_ON_ONCE(!try_page_mte_tagging(page)); mte_zero_clear_page_tags(page_address(page)); set_page_mte_tagged(page); } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Dynamic loading of modules into the kernel. * * Rewritten by Richard Henderson <rth@tamu.edu> Dec 1996 * Rewritten again by Rusty Russell, 2002 */ #ifndef _LINUX_MODULE_H #define _LINUX_MODULE_H #include <linux/list.h> #include <linux/stat.h> #include <linux/buildid.h> #include <linux/compiler.h> #include <linux/cache.h> #include <linux/kmod.h> #include <linux/init.h> #include <linux/elf.h> #include <linux/stringify.h> #include <linux/kobject.h> #include <linux/moduleparam.h> #include <linux/jump_label.h> #include <linux/export.h> #include <linux/rbtree_latch.h> #include <linux/error-injection.h> #include <linux/tracepoint-defs.h> #include <linux/srcu.h> #include <linux/static_call_types.h> #include <linux/dynamic_debug.h> #include <linux/percpu.h> #include <asm/module.h> #define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN struct modversion_info { unsigned long crc; char name[MODULE_NAME_LEN]; }; struct module; struct exception_table_entry; struct module_kobject { struct kobject kobj; struct module *mod; struct kobject *drivers_dir; struct module_param_attrs *mp; struct completion *kobj_completion; } __randomize_layout; struct module_attribute { struct attribute attr; ssize_t (*show)(struct module_attribute *, struct module_kobject *, char *); ssize_t (*store)(struct module_attribute *, struct module_kobject *, const char *, size_t count); void (*setup)(struct module *, const char *); int (*test)(struct module *); void (*free)(struct module *); }; struct module_version_attribute { struct module_attribute mattr; const char *module_name; const char *version; }; extern ssize_t __modver_version_show(struct module_attribute *, struct module_kobject *, char *); extern struct module_attribute module_uevent; /* These are either module local, or the kernel's dummy ones. */ extern int init_module(void); extern void cleanup_module(void); #ifndef MODULE /** * module_init() - driver initialization entry point * @x: function to be run at kernel boot time or module insertion * * module_init() will either be called during do_initcalls() (if * builtin) or at module insertion time (if a module). There can only * be one per module. */ #define module_init(x) __initcall(x); /** * module_exit() - driver exit entry point * @x: function to be run when driver is removed * * module_exit() will wrap the driver clean-up code * with cleanup_module() when used with rmmod when * the driver is a module. If the driver is statically * compiled into the kernel, module_exit() has no effect. * There can only be one per module. */ #define module_exit(x) __exitcall(x); #else /* MODULE */ /* * In most cases loadable modules do not need custom * initcall levels. There are still some valid cases where * a driver may be needed early if built in, and does not * matter when built as a loadable module. Like bus * snooping debug drivers. */ #define early_initcall(fn) module_init(fn) #define core_initcall(fn) module_init(fn) #define core_initcall_sync(fn) module_init(fn) #define postcore_initcall(fn) module_init(fn) #define postcore_initcall_sync(fn) module_init(fn) #define arch_initcall(fn) module_init(fn) #define subsys_initcall(fn) module_init(fn) #define subsys_initcall_sync(fn) module_init(fn) #define fs_initcall(fn) module_init(fn) #define fs_initcall_sync(fn) module_init(fn) #define rootfs_initcall(fn) module_init(fn) #define device_initcall(fn) module_init(fn) #define device_initcall_sync(fn) module_init(fn) #define late_initcall(fn) module_init(fn) #define late_initcall_sync(fn) module_init(fn) #define console_initcall(fn) module_init(fn) /* Each module must use one module_init(). */ #define module_init(initfn) \ static inline initcall_t __maybe_unused __inittest(void) \ { return initfn; } \ int init_module(void) __copy(initfn) \ __attribute__((alias(#initfn))); \ ___ADDRESSABLE(init_module, __initdata); /* This is only required if you want to be unloadable. */ #define module_exit(exitfn) \ static inline exitcall_t __maybe_unused __exittest(void) \ { return exitfn; } \ void cleanup_module(void) __copy(exitfn) \ __attribute__((alias(#exitfn))); \ ___ADDRESSABLE(cleanup_module, __exitdata); #endif /* This means "can be init if no module support, otherwise module load may call it." */ #ifdef CONFIG_MODULES #define __init_or_module #define __initdata_or_module #define __initconst_or_module #define __INIT_OR_MODULE .text #define __INITDATA_OR_MODULE .data #define __INITRODATA_OR_MODULE .section ".rodata","a",%progbits #else #define __init_or_module __init #define __initdata_or_module __initdata #define __initconst_or_module __initconst #define __INIT_OR_MODULE __INIT #define __INITDATA_OR_MODULE __INITDATA #define __INITRODATA_OR_MODULE __INITRODATA #endif /*CONFIG_MODULES*/ /* Generic info of form tag = "info" */ #define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info) /* For userspace: you can also call me... */ #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias) /* Soft module dependencies. See man modprobe.d for details. * Example: MODULE_SOFTDEP("pre: module-foo module-bar post: module-baz") */ #define MODULE_SOFTDEP(_softdep) MODULE_INFO(softdep, _softdep) /* * MODULE_FILE is used for generating modules.builtin * So, make it no-op when this is being built as a module */ #ifdef MODULE #define MODULE_FILE #else #define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE); #endif /* * The following license idents are currently accepted as indicating free * software modules * * "GPL" [GNU Public License v2] * "GPL v2" [GNU Public License v2] * "GPL and additional rights" [GNU Public License v2 rights and more] * "Dual BSD/GPL" [GNU Public License v2 * or BSD license choice] * "Dual MIT/GPL" [GNU Public License v2 * or MIT license choice] * "Dual MPL/GPL" [GNU Public License v2 * or Mozilla license choice] * * The following other idents are available * * "Proprietary" [Non free products] * * Both "GPL v2" and "GPL" (the latter also in dual licensed strings) are * merely stating that the module is licensed under the GPL v2, but are not * telling whether "GPL v2 only" or "GPL v2 or later". The reason why there * are two variants is a historic and failed attempt to convey more * information in the MODULE_LICENSE string. For module loading the * "only/or later" distinction is completely irrelevant and does neither * replace the proper license identifiers in the corresponding source file * nor amends them in any way. The sole purpose is to make the * 'Proprietary' flagging work and to refuse to bind symbols which are * exported with EXPORT_SYMBOL_GPL when a non free module is loaded. * * In the same way "BSD" is not a clear license information. It merely * states, that the module is licensed under one of the compatible BSD * license variants. The detailed and correct license information is again * to be found in the corresponding source files. * * There are dual licensed components, but when running with Linux it is the * GPL that is relevant so this is a non issue. Similarly LGPL linked with GPL * is a GPL combined work. * * This exists for several reasons * 1. So modinfo can show license info for users wanting to vet their setup * is free * 2. So the community can ignore bug reports including proprietary modules * 3. So vendors can do likewise based on their own policies */ #define MODULE_LICENSE(_license) MODULE_FILE MODULE_INFO(license, _license) /* * Author(s), use "Name <email>" or just "Name", for multiple * authors use multiple MODULE_AUTHOR() statements/lines. */ #define MODULE_AUTHOR(_author) MODULE_INFO(author, _author) /* What your module does. */ #define MODULE_DESCRIPTION(_description) MODULE_INFO(description, _description) #ifdef MODULE /* Creates an alias so file2alias.c can find device table. */ #define MODULE_DEVICE_TABLE(type, name) \ extern typeof(name) __mod_##type##__##name##_device_table \ __attribute__ ((unused, alias(__stringify(name)))) #else /* !MODULE */ #define MODULE_DEVICE_TABLE(type, name) #endif /* Version of form [<epoch>:]<version>[-<extra-version>]. * Or for CVS/RCS ID version, everything but the number is stripped. * <epoch>: A (small) unsigned integer which allows you to start versions * anew. If not mentioned, it's zero. eg. "2:1.0" is after * "1:2.0". * <version>: The <version> may contain only alphanumerics and the * character `.'. Ordered by numeric sort for numeric parts, * ascii sort for ascii parts (as per RPM or DEB algorithm). * <extraversion>: Like <version>, but inserted for local * customizations, eg "rh3" or "rusty1". * Using this automatically adds a checksum of the .c files and the * local headers in "srcversion". */ #if defined(MODULE) || !defined(CONFIG_SYSFS) #define MODULE_VERSION(_version) MODULE_INFO(version, _version) #else #define MODULE_VERSION(_version) \ MODULE_INFO(version, _version); \ static struct module_version_attribute __modver_attr \ __used __section("__modver") \ __aligned(__alignof__(struct module_version_attribute)) \ = { \ .mattr = { \ .attr = { \ .name = "version", \ .mode = S_IRUGO, \ }, \ .show = __modver_version_show, \ }, \ .module_name = KBUILD_MODNAME, \ .version = _version, \ } #endif /* Optional firmware file (or files) needed by the module * format is simply firmware file name. Multiple firmware * files require multiple MODULE_FIRMWARE() specifiers */ #define MODULE_FIRMWARE(_firmware) MODULE_INFO(firmware, _firmware) #define MODULE_IMPORT_NS(ns) MODULE_INFO(import_ns, __stringify(ns)) struct notifier_block; #ifdef CONFIG_MODULES extern int modules_disabled; /* for sysctl */ /* Get/put a kernel symbol (calls must be symmetric) */ void *__symbol_get(const char *symbol); void *__symbol_get_gpl(const char *symbol); #define symbol_get(x) ((typeof(&x))(__symbol_get(__stringify(x)))) /* modules using other modules: kdb wants to see this. */ struct module_use { struct list_head source_list; struct list_head target_list; struct module *source, *target; }; enum module_state { MODULE_STATE_LIVE, /* Normal state. */ MODULE_STATE_COMING, /* Full formed, running module_init. */ MODULE_STATE_GOING, /* Going away. */ MODULE_STATE_UNFORMED, /* Still setting it up. */ }; struct mod_tree_node { struct module *mod; struct latch_tree_node node; }; enum mod_mem_type { MOD_TEXT = 0, MOD_DATA, MOD_RODATA, MOD_RO_AFTER_INIT, MOD_INIT_TEXT, MOD_INIT_DATA, MOD_INIT_RODATA, MOD_MEM_NUM_TYPES, MOD_INVALID = -1, }; #define mod_mem_type_is_init(type) \ ((type) == MOD_INIT_TEXT || \ (type) == MOD_INIT_DATA || \ (type) == MOD_INIT_RODATA) #define mod_mem_type_is_core(type) (!mod_mem_type_is_init(type)) #define mod_mem_type_is_text(type) \ ((type) == MOD_TEXT || \ (type) == MOD_INIT_TEXT) #define mod_mem_type_is_data(type) (!mod_mem_type_is_text(type)) #define mod_mem_type_is_core_data(type) \ (mod_mem_type_is_core(type) && \ mod_mem_type_is_data(type)) #define for_each_mod_mem_type(type) \ for (enum mod_mem_type (type) = 0; \ (type) < MOD_MEM_NUM_TYPES; (type)++) #define for_class_mod_mem_type(type, class) \ for_each_mod_mem_type(type) \ if (mod_mem_type_is_##class(type)) struct module_memory { void *base; unsigned int size; #ifdef CONFIG_MODULES_TREE_LOOKUP struct mod_tree_node mtn; #endif }; #ifdef CONFIG_MODULES_TREE_LOOKUP /* Only touch one cacheline for common rbtree-for-core-layout case. */ #define __module_memory_align ____cacheline_aligned #else #define __module_memory_align #endif struct mod_kallsyms { Elf_Sym *symtab; unsigned int num_symtab; char *strtab; char *typetab; }; #ifdef CONFIG_LIVEPATCH /** * struct klp_modinfo - ELF information preserved from the livepatch module * * @hdr: ELF header * @sechdrs: Section header table * @secstrings: String table for the section headers * @symndx: The symbol table section index */ struct klp_modinfo { Elf_Ehdr hdr; Elf_Shdr *sechdrs; char *secstrings; unsigned int symndx; }; #endif struct module { enum module_state state; /* Member of list of modules */ struct list_head list; /* Unique handle for this module */ char name[MODULE_NAME_LEN]; #ifdef CONFIG_STACKTRACE_BUILD_ID /* Module build ID */ unsigned char build_id[BUILD_ID_SIZE_MAX]; #endif /* Sysfs stuff. */ struct module_kobject mkobj; struct module_attribute *modinfo_attrs; const char *version; const char *srcversion; struct kobject *holders_dir; /* Exported symbols */ const struct kernel_symbol *syms; const s32 *crcs; unsigned int num_syms; #ifdef CONFIG_ARCH_USES_CFI_TRAPS s32 *kcfi_traps; s32 *kcfi_traps_end; #endif /* Kernel parameters. */ #ifdef CONFIG_SYSFS struct mutex param_lock; #endif struct kernel_param *kp; unsigned int num_kp; /* GPL-only exported symbols. */ unsigned int num_gpl_syms; const struct kernel_symbol *gpl_syms; const s32 *gpl_crcs; bool using_gplonly_symbols; #ifdef CONFIG_MODULE_SIG /* Signature was verified. */ bool sig_ok; #endif bool async_probe_requested; /* Exception table */ unsigned int num_exentries; struct exception_table_entry *extable; /* Startup function. */ int (*init)(void); struct module_memory mem[MOD_MEM_NUM_TYPES] __module_memory_align; /* Arch-specific module values */ struct mod_arch_specific arch; unsigned long taints; /* same bits as kernel:taint_flags */ #ifdef CONFIG_GENERIC_BUG /* Support for BUG */ unsigned num_bugs; struct list_head bug_list; struct bug_entry *bug_table; #endif #ifdef CONFIG_KALLSYMS /* Protected by RCU and/or module_mutex: use rcu_dereference() */ struct mod_kallsyms __rcu *kallsyms; struct mod_kallsyms core_kallsyms; /* Section attributes */ struct module_sect_attrs *sect_attrs; /* Notes attributes */ struct module_notes_attrs *notes_attrs; #endif /* The command line arguments (may be mangled). People like keeping pointers to this stuff */ char *args; #ifdef CONFIG_SMP /* Per-cpu data. */ void __percpu *percpu; unsigned int percpu_size; #endif void *noinstr_text_start; unsigned int noinstr_text_size; #ifdef CONFIG_TRACEPOINTS unsigned int num_tracepoints; tracepoint_ptr_t *tracepoints_ptrs; #endif #ifdef CONFIG_TREE_SRCU unsigned int num_srcu_structs; struct srcu_struct **srcu_struct_ptrs; #endif #ifdef CONFIG_BPF_EVENTS unsigned int num_bpf_raw_events; struct bpf_raw_event_map *bpf_raw_events; #endif #ifdef CONFIG_DEBUG_INFO_BTF_MODULES unsigned int btf_data_size; void *btf_data; #endif #ifdef CONFIG_JUMP_LABEL struct jump_entry *jump_entries; unsigned int num_jump_entries; #endif #ifdef CONFIG_TRACING unsigned int num_trace_bprintk_fmt; const char **trace_bprintk_fmt_start; #endif #ifdef CONFIG_EVENT_TRACING struct trace_event_call **trace_events; unsigned int num_trace_events; struct trace_eval_map **trace_evals; unsigned int num_trace_evals; #endif #ifdef CONFIG_FTRACE_MCOUNT_RECORD unsigned int num_ftrace_callsites; unsigned long *ftrace_callsites; #endif #ifdef CONFIG_KPROBES void *kprobes_text_start; unsigned int kprobes_text_size; unsigned long *kprobe_blacklist; unsigned int num_kprobe_blacklist; #endif #ifdef CONFIG_HAVE_STATIC_CALL_INLINE int num_static_call_sites; struct static_call_site *static_call_sites; #endif #if IS_ENABLED(CONFIG_KUNIT) int num_kunit_init_suites; struct kunit_suite **kunit_init_suites; int num_kunit_suites; struct kunit_suite **kunit_suites; #endif #ifdef CONFIG_LIVEPATCH bool klp; /* Is this a livepatch module? */ bool klp_alive; /* ELF information */ struct klp_modinfo *klp_info; #endif #ifdef CONFIG_PRINTK_INDEX unsigned int printk_index_size; struct pi_entry **printk_index_start; #endif #ifdef CONFIG_MODULE_UNLOAD /* What modules depend on me? */ struct list_head source_list; /* What modules do I depend on? */ struct list_head target_list; /* Destruction function. */ void (*exit)(void); atomic_t refcnt; #endif #ifdef CONFIG_CONSTRUCTORS /* Constructor functions. */ ctor_fn_t *ctors; unsigned int num_ctors; #endif #ifdef CONFIG_FUNCTION_ERROR_INJECTION struct error_injection_entry *ei_funcs; unsigned int num_ei_funcs; #endif #ifdef CONFIG_DYNAMIC_DEBUG_CORE struct _ddebug_info dyndbg_info; #endif } ____cacheline_aligned __randomize_layout; #ifndef MODULE_ARCH_INIT #define MODULE_ARCH_INIT {} #endif #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym) { return sym->st_value; } #endif /* FIXME: It'd be nice to isolate modules during init, too, so they aren't used before they (may) fail. But presently too much code (IDE & SCSI) require entry into the module during init.*/ static inline bool module_is_live(struct module *mod) { return mod->state != MODULE_STATE_GOING; } static inline bool module_is_coming(struct module *mod) { return mod->state == MODULE_STATE_COMING; } struct module *__module_text_address(unsigned long addr); struct module *__module_address(unsigned long addr); bool is_module_address(unsigned long addr); bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr); bool is_module_percpu_address(unsigned long addr); bool is_module_text_address(unsigned long addr); static inline bool within_module_mem_type(unsigned long addr, const struct module *mod, enum mod_mem_type type) { unsigned long base, size; base = (unsigned long)mod->mem[type].base; size = mod->mem[type].size; return addr - base < size; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { for_class_mod_mem_type(type, core) { if (within_module_mem_type(addr, mod, type)) return true; } return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { for_class_mod_mem_type(type, init) { if (within_module_mem_type(addr, mod, type)) return true; } return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return within_module_init(addr, mod) || within_module_core(addr, mod); } /* Search for module by name: must be in a RCU-sched critical section. */ struct module *find_module(const char *name); extern void __noreturn __module_put_and_kthread_exit(struct module *mod, long code); #define module_put_and_kthread_exit(code) __module_put_and_kthread_exit(THIS_MODULE, code) #ifdef CONFIG_MODULE_UNLOAD int module_refcount(struct module *mod); void __symbol_put(const char *symbol); #define symbol_put(x) __symbol_put(__stringify(x)) void symbol_put_addr(void *addr); /* Sometimes we know we already have a refcount, and it's easier not to handle the error case (which only happens with rmmod --wait). */ extern void __module_get(struct module *module); /** * try_module_get() - take module refcount unless module is being removed * @module: the module we should check for * * Only try to get a module reference count if the module is not being removed. * This call will fail if the module is in the process of being removed. * * Care must also be taken to ensure the module exists and is alive prior to * usage of this call. This can be gauranteed through two means: * * 1) Direct protection: you know an earlier caller must have increased the * module reference through __module_get(). This can typically be achieved * by having another entity other than the module itself increment the * module reference count. * * 2) Implied protection: there is an implied protection against module * removal. An example of this is the implied protection used by kernfs / * sysfs. The sysfs store / read file operations are guaranteed to exist * through the use of kernfs's active reference (see kernfs_active()) and a * sysfs / kernfs file removal cannot happen unless the same file is not * active. Therefore, if a sysfs file is being read or written to the module * which created it must still exist. It is therefore safe to use * try_module_get() on module sysfs store / read ops. * * One of the real values to try_module_get() is the module_is_live() check * which ensures that the caller of try_module_get() can yield to userspace * module removal requests and gracefully fail if the module is on its way out. * * Returns true if the reference count was successfully incremented. */ extern bool try_module_get(struct module *module); /** * module_put() - release a reference count to a module * @module: the module we should release a reference count for * * If you successfully bump a reference count to a module with try_module_get(), * when you are finished you must call module_put() to release that reference * count. */ extern void module_put(struct module *module); #else /*!CONFIG_MODULE_UNLOAD*/ static inline bool try_module_get(struct module *module) { return !module || module_is_live(module); } static inline void module_put(struct module *module) { } static inline void __module_get(struct module *module) { } #define symbol_put(x) do { } while (0) #define symbol_put_addr(p) do { } while (0) #endif /* CONFIG_MODULE_UNLOAD */ /* This is a #define so the string doesn't get put in every .o file */ #define module_name(mod) \ ({ \ struct module *__mod = (mod); \ __mod ? __mod->name : "kernel"; \ }) /* Dereference module function descriptor */ void *dereference_module_function_descriptor(struct module *mod, void *ptr); int register_module_notifier(struct notifier_block *nb); int unregister_module_notifier(struct notifier_block *nb); extern void print_modules(void); static inline bool module_requested_async_probing(struct module *module) { return module && module->async_probe_requested; } static inline bool is_livepatch_module(struct module *mod) { #ifdef CONFIG_LIVEPATCH return mod->klp; #else return false; #endif } void set_module_sig_enforced(void); #else /* !CONFIG_MODULES... */ static inline struct module *__module_address(unsigned long addr) { return NULL; } static inline struct module *__module_text_address(unsigned long addr) { return NULL; } static inline bool is_module_address(unsigned long addr) { return false; } static inline bool is_module_percpu_address(unsigned long addr) { return false; } static inline bool __is_module_percpu_address(unsigned long addr, unsigned long *can_addr) { return false; } static inline bool is_module_text_address(unsigned long addr) { return false; } static inline bool within_module_core(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module_init(unsigned long addr, const struct module *mod) { return false; } static inline bool within_module(unsigned long addr, const struct module *mod) { return false; } /* Get/put a kernel symbol (calls should be symmetric) */ #define symbol_get(x) ({ extern typeof(x) x __attribute__((weak,visibility("hidden"))); &(x); }) #define symbol_put(x) do { } while (0) #define symbol_put_addr(x) do { } while (0) static inline void __module_get(struct module *module) { } static inline bool try_module_get(struct module *module) { return true; } static inline void module_put(struct module *module) { } #define module_name(mod) "kernel" static inline int register_module_notifier(struct notifier_block *nb) { /* no events will happen anyway, so this can always succeed */ return 0; } static inline int unregister_module_notifier(struct notifier_block *nb) { return 0; } #define module_put_and_kthread_exit(code) kthread_exit(code) static inline void print_modules(void) { } static inline bool module_requested_async_probing(struct module *module) { return false; } static inline void set_module_sig_enforced(void) { } /* Dereference module function descriptor */ static inline void *dereference_module_function_descriptor(struct module *mod, void *ptr) { return ptr; } static inline bool module_is_coming(struct module *mod) { return false; } #endif /* CONFIG_MODULES */ #ifdef CONFIG_SYSFS extern struct kset *module_kset; extern const struct kobj_type module_ktype; #endif /* CONFIG_SYSFS */ #define symbol_request(x) try_then_request_module(symbol_get(x), "symbol:" #x) /* BELOW HERE ALL THESE ARE OBSOLETE AND WILL VANISH */ #define __MODULE_STRING(x) __stringify(x) #ifdef CONFIG_GENERIC_BUG void module_bug_finalize(const Elf_Ehdr *, const Elf_Shdr *, struct module *); void module_bug_cleanup(struct module *); #else /* !CONFIG_GENERIC_BUG */ static inline void module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mod) { } static inline void module_bug_cleanup(struct module *mod) {} #endif /* CONFIG_GENERIC_BUG */ #ifdef CONFIG_MITIGATION_RETPOLINE extern bool retpoline_module_ok(bool has_retpoline); #else static inline bool retpoline_module_ok(bool has_retpoline) { return true; } #endif #ifdef CONFIG_MODULE_SIG bool is_module_sig_enforced(void); static inline bool module_sig_ok(struct module *module) { return module->sig_ok; } #else /* !CONFIG_MODULE_SIG */ static inline bool is_module_sig_enforced(void) { return false; } static inline bool module_sig_ok(struct module *module) { return true; } #endif /* CONFIG_MODULE_SIG */ #if defined(CONFIG_MODULES) && defined(CONFIG_KALLSYMS) int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data); /* For kallsyms to ask for address resolution. namebuf should be at * least KSYM_NAME_LEN long: a pointer to namebuf is returned if * found, otherwise NULL. */ int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf); int lookup_module_symbol_name(unsigned long addr, char *symname); int lookup_module_symbol_attrs(unsigned long addr, unsigned long *size, unsigned long *offset, char *modname, char *name); /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if * symnum out of range. */ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported); /* Look for this name: can be of form module:name. */ unsigned long module_kallsyms_lookup_name(const char *name); unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name); #else /* CONFIG_MODULES && CONFIG_KALLSYMS */ static inline int module_kallsyms_on_each_symbol(const char *modname, int (*fn)(void *, const char *, unsigned long), void *data) { return -EOPNOTSUPP; } /* For kallsyms to ask for address resolution. NULL means not found. */ static inline int module_address_lookup(unsigned long addr, unsigned long *symbolsize, unsigned long *offset, char **modname, const unsigned char **modbuildid, char *namebuf) { return 0; } static inline int lookup_module_symbol_name(unsigned long addr, char *symname) { return -ERANGE; } static inline int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type, char *name, char *module_name, int *exported) { return -ERANGE; } static inline unsigned long module_kallsyms_lookup_name(const char *name) { return 0; } static inline unsigned long find_kallsyms_symbol_value(struct module *mod, const char *name) { return 0; } #endif /* CONFIG_MODULES && CONFIG_KALLSYMS */ #endif /* _LINUX_MODULE_H */ |
| 1 115 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_KVM_MAIN_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_KVM_MAIN_H #include <linux/tracepoint.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm #define ERSN(x) { KVM_EXIT_##x, "KVM_EXIT_" #x } #define kvm_trace_exit_reason \ ERSN(UNKNOWN), ERSN(EXCEPTION), ERSN(IO), ERSN(HYPERCALL), \ ERSN(DEBUG), ERSN(HLT), ERSN(MMIO), ERSN(IRQ_WINDOW_OPEN), \ ERSN(SHUTDOWN), ERSN(FAIL_ENTRY), ERSN(INTR), ERSN(SET_TPR), \ ERSN(TPR_ACCESS), ERSN(S390_SIEIC), ERSN(S390_RESET), ERSN(DCR),\ ERSN(NMI), ERSN(INTERNAL_ERROR), ERSN(OSI), ERSN(PAPR_HCALL), \ ERSN(S390_UCONTROL), ERSN(WATCHDOG), ERSN(S390_TSCH), ERSN(EPR),\ ERSN(SYSTEM_EVENT), ERSN(S390_STSI), ERSN(IOAPIC_EOI), \ ERSN(HYPERV), ERSN(ARM_NISV), ERSN(X86_RDMSR), ERSN(X86_WRMSR) TRACE_EVENT(kvm_userspace_exit, TP_PROTO(__u32 reason, int errno), TP_ARGS(reason, errno), TP_STRUCT__entry( __field( __u32, reason ) __field( int, errno ) ), TP_fast_assign( __entry->reason = reason; __entry->errno = errno; ), TP_printk("reason %s (%d)", __entry->errno < 0 ? (__entry->errno == -EINTR ? "restart" : "error") : __print_symbolic(__entry->reason, kvm_trace_exit_reason), __entry->errno < 0 ? -__entry->errno : __entry->reason) ); TRACE_EVENT(kvm_vcpu_wakeup, TP_PROTO(__u64 ns, bool waited, bool valid), TP_ARGS(ns, waited, valid), TP_STRUCT__entry( __field( __u64, ns ) __field( bool, waited ) __field( bool, valid ) ), TP_fast_assign( __entry->ns = ns; __entry->waited = waited; __entry->valid = valid; ), TP_printk("%s time %lld ns, polling %s", __entry->waited ? "wait" : "poll", __entry->ns, __entry->valid ? "valid" : "invalid") ); #if defined(CONFIG_HAVE_KVM_IRQCHIP) TRACE_EVENT(kvm_set_irq, TP_PROTO(unsigned int gsi, int level, int irq_source_id), TP_ARGS(gsi, level, irq_source_id), TP_STRUCT__entry( __field( unsigned int, gsi ) __field( int, level ) __field( int, irq_source_id ) ), TP_fast_assign( __entry->gsi = gsi; __entry->level = level; __entry->irq_source_id = irq_source_id; ), TP_printk("gsi %u level %d source %d", __entry->gsi, __entry->level, __entry->irq_source_id) ); #endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ #if defined(__KVM_HAVE_IOAPIC) #define kvm_deliver_mode \ {0x0, "Fixed"}, \ {0x1, "LowPrio"}, \ {0x2, "SMI"}, \ {0x3, "Res3"}, \ {0x4, "NMI"}, \ {0x5, "INIT"}, \ {0x6, "SIPI"}, \ {0x7, "ExtINT"} TRACE_EVENT(kvm_ioapic_set_irq, TP_PROTO(__u64 e, int pin, bool coalesced), TP_ARGS(e, pin, coalesced), TP_STRUCT__entry( __field( __u64, e ) __field( int, pin ) __field( bool, coalesced ) ), TP_fast_assign( __entry->e = e; __entry->pin = pin; __entry->coalesced = coalesced; ), TP_printk("pin %u dst %x vec %u (%s|%s|%s%s)%s", __entry->pin, (u8)(__entry->e >> 56), (u8)__entry->e, __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), (__entry->e & (1<<11)) ? "logical" : "physical", (__entry->e & (1<<15)) ? "level" : "edge", (__entry->e & (1<<16)) ? "|masked" : "", __entry->coalesced ? " (coalesced)" : "") ); TRACE_EVENT(kvm_ioapic_delayed_eoi_inj, TP_PROTO(__u64 e), TP_ARGS(e), TP_STRUCT__entry( __field( __u64, e ) ), TP_fast_assign( __entry->e = e; ), TP_printk("dst %x vec %u (%s|%s|%s%s)", (u8)(__entry->e >> 56), (u8)__entry->e, __print_symbolic((__entry->e >> 8 & 0x7), kvm_deliver_mode), (__entry->e & (1<<11)) ? "logical" : "physical", (__entry->e & (1<<15)) ? "level" : "edge", (__entry->e & (1<<16)) ? "|masked" : "") ); TRACE_EVENT(kvm_msi_set_irq, TP_PROTO(__u64 address, __u64 data), TP_ARGS(address, data), TP_STRUCT__entry( __field( __u64, address ) __field( __u64, data ) ), TP_fast_assign( __entry->address = address; __entry->data = data; ), TP_printk("dst %llx vec %u (%s|%s|%s%s)", (u8)(__entry->address >> 12) | ((__entry->address >> 32) & 0xffffff00), (u8)__entry->data, __print_symbolic((__entry->data >> 8 & 0x7), kvm_deliver_mode), (__entry->address & (1<<2)) ? "logical" : "physical", (__entry->data & (1<<15)) ? "level" : "edge", (__entry->address & (1<<3)) ? "|rh" : "") ); #define kvm_irqchips \ {KVM_IRQCHIP_PIC_MASTER, "PIC master"}, \ {KVM_IRQCHIP_PIC_SLAVE, "PIC slave"}, \ {KVM_IRQCHIP_IOAPIC, "IOAPIC"} #endif /* defined(__KVM_HAVE_IOAPIC) */ #if defined(CONFIG_HAVE_KVM_IRQCHIP) #ifdef kvm_irqchips #define kvm_ack_irq_string "irqchip %s pin %u" #define kvm_ack_irq_parm __print_symbolic(__entry->irqchip, kvm_irqchips), __entry->pin #else #define kvm_ack_irq_string "irqchip %d pin %u" #define kvm_ack_irq_parm __entry->irqchip, __entry->pin #endif TRACE_EVENT(kvm_ack_irq, TP_PROTO(unsigned int irqchip, unsigned int pin), TP_ARGS(irqchip, pin), TP_STRUCT__entry( __field( unsigned int, irqchip ) __field( unsigned int, pin ) ), TP_fast_assign( __entry->irqchip = irqchip; __entry->pin = pin; ), TP_printk(kvm_ack_irq_string, kvm_ack_irq_parm) ); #endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */ #define KVM_TRACE_MMIO_READ_UNSATISFIED 0 #define KVM_TRACE_MMIO_READ 1 #define KVM_TRACE_MMIO_WRITE 2 #define kvm_trace_symbol_mmio \ { KVM_TRACE_MMIO_READ_UNSATISFIED, "unsatisfied-read" }, \ { KVM_TRACE_MMIO_READ, "read" }, \ { KVM_TRACE_MMIO_WRITE, "write" } TRACE_EVENT(kvm_mmio, TP_PROTO(int type, int len, u64 gpa, void *val), TP_ARGS(type, len, gpa, val), TP_STRUCT__entry( __field( u32, type ) __field( u32, len ) __field( u64, gpa ) __field( u64, val ) ), TP_fast_assign( __entry->type = type; __entry->len = len; __entry->gpa = gpa; __entry->val = 0; if (val) memcpy(&__entry->val, val, min_t(u32, sizeof(__entry->val), len)); ), TP_printk("mmio %s len %u gpa 0x%llx val 0x%llx", __print_symbolic(__entry->type, kvm_trace_symbol_mmio), __entry->len, __entry->gpa, __entry->val) ); #define kvm_fpu_load_symbol \ {0, "unload"}, \ {1, "load"} TRACE_EVENT(kvm_fpu, TP_PROTO(int load), TP_ARGS(load), TP_STRUCT__entry( __field( u32, load ) ), TP_fast_assign( __entry->load = load; ), TP_printk("%s", __print_symbolic(__entry->load, kvm_fpu_load_symbol)) ); #ifdef CONFIG_KVM_ASYNC_PF DECLARE_EVENT_CLASS(kvm_async_get_page_class, TP_PROTO(u64 gva, u64 gfn), TP_ARGS(gva, gfn), TP_STRUCT__entry( __field(__u64, gva) __field(u64, gfn) ), TP_fast_assign( __entry->gva = gva; __entry->gfn = gfn; ), TP_printk("gva = %#llx, gfn = %#llx", __entry->gva, __entry->gfn) ); DEFINE_EVENT(kvm_async_get_page_class, kvm_try_async_get_page, TP_PROTO(u64 gva, u64 gfn), TP_ARGS(gva, gfn) ); DEFINE_EVENT(kvm_async_get_page_class, kvm_async_pf_repeated_fault, TP_PROTO(u64 gva, u64 gfn), TP_ARGS(gva, gfn) ); DECLARE_EVENT_CLASS(kvm_async_pf_nopresent_ready, TP_PROTO(u64 token, u64 gva), TP_ARGS(token, gva), TP_STRUCT__entry( __field(__u64, token) __field(__u64, gva) ), TP_fast_assign( __entry->token = token; __entry->gva = gva; ), TP_printk("token %#llx gva %#llx", __entry->token, __entry->gva) ); DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_not_present, TP_PROTO(u64 token, u64 gva), TP_ARGS(token, gva) ); DEFINE_EVENT(kvm_async_pf_nopresent_ready, kvm_async_pf_ready, TP_PROTO(u64 token, u64 gva), TP_ARGS(token, gva) ); TRACE_EVENT( kvm_async_pf_completed, TP_PROTO(unsigned long address, u64 gva), TP_ARGS(address, gva), TP_STRUCT__entry( __field(unsigned long, address) __field(u64, gva) ), TP_fast_assign( __entry->address = address; __entry->gva = gva; ), TP_printk("gva %#llx address %#lx", __entry->gva, __entry->address) ); #endif TRACE_EVENT(kvm_halt_poll_ns, TP_PROTO(bool grow, unsigned int vcpu_id, unsigned int new, unsigned int old), TP_ARGS(grow, vcpu_id, new, old), TP_STRUCT__entry( __field(bool, grow) __field(unsigned int, vcpu_id) __field(unsigned int, new) __field(unsigned int, old) ), TP_fast_assign( __entry->grow = grow; __entry->vcpu_id = vcpu_id; __entry->new = new; __entry->old = old; ), TP_printk("vcpu %u: halt_poll_ns %u (%s %u)", __entry->vcpu_id, __entry->new, __entry->grow ? "grow" : "shrink", __entry->old) ); #define trace_kvm_halt_poll_ns_grow(vcpu_id, new, old) \ trace_kvm_halt_poll_ns(true, vcpu_id, new, old) #define trace_kvm_halt_poll_ns_shrink(vcpu_id, new, old) \ trace_kvm_halt_poll_ns(false, vcpu_id, new, old) TRACE_EVENT(kvm_dirty_ring_push, TP_PROTO(struct kvm_dirty_ring *ring, u32 slot, u64 offset), TP_ARGS(ring, slot, offset), TP_STRUCT__entry( __field(int, index) __field(u32, dirty_index) __field(u32, reset_index) __field(u32, slot) __field(u64, offset) ), TP_fast_assign( __entry->index = ring->index; __entry->dirty_index = ring->dirty_index; __entry->reset_index = ring->reset_index; __entry->slot = slot; __entry->offset = offset; ), TP_printk("ring %d: dirty 0x%x reset 0x%x " "slot %u offset 0x%llx (used %u)", __entry->index, __entry->dirty_index, __entry->reset_index, __entry->slot, __entry->offset, __entry->dirty_index - __entry->reset_index) ); TRACE_EVENT(kvm_dirty_ring_reset, TP_PROTO(struct kvm_dirty_ring *ring), TP_ARGS(ring), TP_STRUCT__entry( __field(int, index) __field(u32, dirty_index) __field(u32, reset_index) ), TP_fast_assign( __entry->index = ring->index; __entry->dirty_index = ring->dirty_index; __entry->reset_index = ring->reset_index; ), TP_printk("ring %d: dirty 0x%x reset 0x%x (used %u)", __entry->index, __entry->dirty_index, __entry->reset_index, __entry->dirty_index - __entry->reset_index) ); TRACE_EVENT(kvm_dirty_ring_exit, TP_PROTO(struct kvm_vcpu *vcpu), TP_ARGS(vcpu), TP_STRUCT__entry( __field(int, vcpu_id) ), TP_fast_assign( __entry->vcpu_id = vcpu->vcpu_id; ), TP_printk("vcpu %d", __entry->vcpu_id) ); TRACE_EVENT(kvm_unmap_hva_range, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), TP_STRUCT__entry( __field( unsigned long, start ) __field( unsigned long, end ) ), TP_fast_assign( __entry->start = start; __entry->end = end; ), TP_printk("mmu notifier unmap range: %#016lx -- %#016lx", __entry->start, __entry->end) ); TRACE_EVENT(kvm_age_hva, TP_PROTO(unsigned long start, unsigned long end), TP_ARGS(start, end), TP_STRUCT__entry( __field( unsigned long, start ) __field( unsigned long, end ) ), TP_fast_assign( __entry->start = start; __entry->end = end; ), TP_printk("mmu notifier age hva: %#016lx -- %#016lx", __entry->start, __entry->end) ); TRACE_EVENT(kvm_test_age_hva, TP_PROTO(unsigned long hva), TP_ARGS(hva), TP_STRUCT__entry( __field( unsigned long, hva ) ), TP_fast_assign( __entry->hva = hva; ), TP_printk("mmu notifier test age hva: %#016lx", __entry->hva) ); #endif /* _TRACE_KVM_MAIN_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 11 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #ifndef __ASM_ARM_KVM_ARCH_TIMER_H #define __ASM_ARM_KVM_ARCH_TIMER_H #include <linux/clocksource.h> #include <linux/hrtimer.h> enum kvm_arch_timers { TIMER_PTIMER, TIMER_VTIMER, NR_KVM_EL0_TIMERS, TIMER_HVTIMER = NR_KVM_EL0_TIMERS, TIMER_HPTIMER, NR_KVM_TIMERS }; enum kvm_arch_timer_regs { TIMER_REG_CNT, TIMER_REG_CVAL, TIMER_REG_TVAL, TIMER_REG_CTL, TIMER_REG_VOFF, }; struct arch_timer_offset { /* * If set, pointer to one of the offsets in the kvm's offset * structure. If NULL, assume a zero offset. */ u64 *vm_offset; /* * If set, pointer to one of the offsets in the vcpu's sysreg * array. If NULL, assume a zero offset. */ u64 *vcpu_offset; }; struct arch_timer_vm_data { /* Offset applied to the virtual timer/counter */ u64 voffset; /* Offset applied to the physical timer/counter */ u64 poffset; /* The PPI for each timer, global to the VM */ u8 ppi[NR_KVM_TIMERS]; }; struct arch_timer_context { struct kvm_vcpu *vcpu; /* Emulated Timer (may be unused) */ struct hrtimer hrtimer; u64 ns_frac; /* Offset for this counter/timer */ struct arch_timer_offset offset; /* * We have multiple paths which can save/restore the timer state onto * the hardware, so we need some way of keeping track of where the * latest state is. */ bool loaded; /* Output level of the timer IRQ */ struct { bool level; } irq; /* Duplicated state from arch_timer.c for convenience */ u32 host_timer_irq; }; struct timer_map { struct arch_timer_context *direct_vtimer; struct arch_timer_context *direct_ptimer; struct arch_timer_context *emul_vtimer; struct arch_timer_context *emul_ptimer; }; void get_timer_map(struct kvm_vcpu *vcpu, struct timer_map *map); struct arch_timer_cpu { struct arch_timer_context timers[NR_KVM_TIMERS]; /* Background timer used when the guest is not running */ struct hrtimer bg_timer; /* Is the timer enabled */ bool enabled; }; int __init kvm_timer_hyp_init(bool has_gic); int kvm_timer_enable(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_reset(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_init(struct kvm_vcpu *vcpu); void kvm_timer_sync_user(struct kvm_vcpu *vcpu); bool kvm_timer_should_notify_user(struct kvm_vcpu *vcpu); void kvm_timer_update_run(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_terminate(struct kvm_vcpu *vcpu); void kvm_timer_init_vm(struct kvm *kvm); u64 kvm_arm_timer_get_reg(struct kvm_vcpu *, u64 regid); int kvm_arm_timer_set_reg(struct kvm_vcpu *, u64 regid, u64 value); int kvm_arm_timer_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_timer_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); u64 kvm_phys_timer_read(void); void kvm_timer_vcpu_load(struct kvm_vcpu *vcpu); void kvm_timer_vcpu_put(struct kvm_vcpu *vcpu); void kvm_timer_init_vhe(void); #define vcpu_timer(v) (&(v)->arch.timer_cpu) #define vcpu_get_timer(v,t) (&vcpu_timer(v)->timers[(t)]) #define vcpu_vtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_VTIMER]) #define vcpu_ptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_PTIMER]) #define vcpu_hvtimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HVTIMER]) #define vcpu_hptimer(v) (&(v)->arch.timer_cpu.timers[TIMER_HPTIMER]) #define arch_timer_ctx_index(ctx) ((ctx) - vcpu_timer((ctx)->vcpu)->timers) #define timer_vm_data(ctx) (&(ctx)->vcpu->kvm->arch.timer_data) #define timer_irq(ctx) (timer_vm_data(ctx)->ppi[arch_timer_ctx_index(ctx)]) u64 kvm_arm_timer_read_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg); void kvm_arm_timer_write_sysreg(struct kvm_vcpu *vcpu, enum kvm_arch_timers tmr, enum kvm_arch_timer_regs treg, u64 val); /* Needed for tracing */ u32 timer_get_ctl(struct arch_timer_context *ctxt); u64 timer_get_cval(struct arch_timer_context *ctxt); /* CPU HP callbacks */ void kvm_timer_cpu_up(void); void kvm_timer_cpu_down(void); static inline bool has_cntpoff(void) { return (has_vhe() && cpus_have_final_cap(ARM64_HAS_ECV_CNTPOFF)); } #endif |
| 183 183 183 183 183 183 183 182 183 183 19 20 173 173 173 171 2 2 2 183 184 184 183 182 183 183 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 | // SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure * and overwrite under many unintended conditions. This code is based * on PAX_USERCOPY, which is: * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> #include <linux/highmem.h> #include <linux/kstrtox.h> #include <linux/slab.h> #include <linux/sched.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/thread_info.h> #include <linux/vmalloc.h> #include <linux/atomic.h> #include <linux/jump_label.h> #include <asm/sections.h> #include "slab.h" /* * Checks if a given pointer and length is contained by the current * stack frame (if possible). * * Returns: * NOT_STACK: not at all on the stack * GOOD_FRAME: fully within a valid stack frame * GOOD_STACK: within the current stack (when can't frame-check exactly) * BAD_STACK: error condition (invalid stack position or bad stack frame) */ static noinline int check_stack_object(const void *obj, unsigned long len) { const void * const stack = task_stack_page(current); const void * const stackend = stack + THREAD_SIZE; int ret; /* Object is not on the stack at all. */ if (obj + len <= stack || stackend <= obj) return NOT_STACK; /* * Reject: object partially overlaps the stack (passing the * check above means at least one end is within the stack, * so if this check fails, the other end is outside the stack). */ if (obj < stack || stackend < obj + len) return BAD_STACK; /* Check if object is safely within a valid frame. */ ret = arch_within_stack_frames(stack, stackend, obj, len); if (ret) return ret; /* Finally, check stack depth if possible. */ #ifdef CONFIG_ARCH_HAS_CURRENT_STACK_POINTER if (IS_ENABLED(CONFIG_STACK_GROWSUP)) { if ((void *)current_stack_pointer < obj + len) return BAD_STACK; } else { if (obj < (void *)current_stack_pointer) return BAD_STACK; } #endif return GOOD_STACK; } /* * If these functions are reached, then CONFIG_HARDENED_USERCOPY has found * an unexpected state during a copy_from_user() or copy_to_user() call. * There are several checks being performed on the buffer by the * __check_object_size() function. Normal stack buffer usage should never * trip the checks, and kernel text addressing will always trip the check. * For cache objects, it is checking that only the whitelisted range of * bytes for a given cache is being accessed (via the cache's usersize and * useroffset fields). To adjust a cache whitelist, use the usercopy-aware * kmem_cache_create_usercopy() function to create the cache (and * carefully audit the whitelist range). */ void __noreturn usercopy_abort(const char *name, const char *detail, bool to_user, unsigned long offset, unsigned long len) { pr_emerg("Kernel memory %s attempt detected %s %s%s%s%s (offset %lu, size %lu)!\n", to_user ? "exposure" : "overwrite", to_user ? "from" : "to", name ? : "unknown?!", detail ? " '" : "", detail ? : "", detail ? "'" : "", offset, len); /* * For greater effect, it would be nice to do do_group_exit(), * but BUG() actually hooks all the lock-breaking and per-arch * Oops code, so that is used here instead. */ BUG(); } /* Returns true if any portion of [ptr,ptr+n) over laps with [low,high). */ static bool overlaps(const unsigned long ptr, unsigned long n, unsigned long low, unsigned long high) { const unsigned long check_low = ptr; unsigned long check_high = check_low + n; /* Does not overlap if entirely above or entirely below. */ if (check_low >= high || check_high <= low) return false; return true; } /* Is this address range in the kernel text area? */ static inline void check_kernel_text_object(const unsigned long ptr, unsigned long n, bool to_user) { unsigned long textlow = (unsigned long)_stext; unsigned long texthigh = (unsigned long)_etext; unsigned long textlow_linear, texthigh_linear; if (overlaps(ptr, n, textlow, texthigh)) usercopy_abort("kernel text", NULL, to_user, ptr - textlow, n); /* * Some architectures have virtual memory mappings with a secondary * mapping of the kernel text, i.e. there is more than one virtual * kernel address that points to the kernel image. It is usually * when there is a separate linear physical memory mapping, in that * __pa() is not just the reverse of __va(). This can be detected * and checked: */ textlow_linear = (unsigned long)lm_alias(textlow); /* No different mapping: we're done. */ if (textlow_linear == textlow) return; /* Check the secondary mapping... */ texthigh_linear = (unsigned long)lm_alias(texthigh); if (overlaps(ptr, n, textlow_linear, texthigh_linear)) usercopy_abort("linear kernel text", NULL, to_user, ptr - textlow_linear, n); } static inline void check_bogus_address(const unsigned long ptr, unsigned long n, bool to_user) { /* Reject if object wraps past end of memory. */ if (ptr + (n - 1) < ptr) usercopy_abort("wrapped address", NULL, to_user, 0, ptr + n); /* Reject if NULL or ZERO-allocation. */ if (ZERO_OR_NULL_PTR(ptr)) usercopy_abort("null address", NULL, to_user, ptr, n); } static inline void check_heap_object(const void *ptr, unsigned long n, bool to_user) { unsigned long addr = (unsigned long)ptr; unsigned long offset; struct folio *folio; if (is_kmap_addr(ptr)) { offset = offset_in_page(ptr); if (n > PAGE_SIZE - offset) usercopy_abort("kmap", NULL, to_user, offset, n); return; } if (is_vmalloc_addr(ptr) && !pagefault_disabled()) { struct vmap_area *area = find_vmap_area(addr); if (!area) usercopy_abort("vmalloc", "no area", to_user, 0, n); if (n > area->va_end - addr) { offset = addr - area->va_start; usercopy_abort("vmalloc", NULL, to_user, offset, n); } return; } if (!virt_addr_valid(ptr)) return; folio = virt_to_folio(ptr); if (folio_test_slab(folio)) { /* Check slab allocator for flags and size. */ __check_heap_object(ptr, n, folio_slab(folio), to_user); } else if (folio_test_large(folio)) { offset = ptr - folio_address(folio); if (n > folio_size(folio) - offset) usercopy_abort("page alloc", NULL, to_user, offset, n); } } static DEFINE_STATIC_KEY_FALSE_RO(bypass_usercopy_checks); /* * Validates that the given object is: * - not bogus address * - fully contained by stack (or stack frame, when available) * - fully within SLAB object (or object whitelist area, when available) * - not in kernel text */ void __check_object_size(const void *ptr, unsigned long n, bool to_user) { if (static_branch_unlikely(&bypass_usercopy_checks)) return; /* Skip all tests if size is zero. */ if (!n) return; /* Check for invalid addresses. */ check_bogus_address((const unsigned long)ptr, n, to_user); /* Check for bad stack object. */ switch (check_stack_object(ptr, n)) { case NOT_STACK: /* Object is not touching the current process stack. */ break; case GOOD_FRAME: case GOOD_STACK: /* * Object is either in the correct frame (when it * is possible to check) or just generally on the * process stack (when frame checking not available). */ return; default: usercopy_abort("process stack", NULL, to_user, #ifdef CONFIG_ARCH_HAS_CURRENT_STACK_POINTER IS_ENABLED(CONFIG_STACK_GROWSUP) ? ptr - (void *)current_stack_pointer : (void *)current_stack_pointer - ptr, #else 0, #endif n); } /* Check for bad heap object. */ check_heap_object(ptr, n, to_user); /* Check for object in kernel to avoid text exposure. */ check_kernel_text_object((const unsigned long)ptr, n, to_user); } EXPORT_SYMBOL(__check_object_size); static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { if (kstrtobool(str, &enable_checks)) pr_warn("Invalid option string for hardened_usercopy: '%s'\n", str); return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); static int __init set_hardened_usercopy(void) { if (enable_checks == false) static_branch_enable(&bypass_usercopy_checks); return 1; } late_initcall(set_hardened_usercopy); |
| 61 61 150 150 131 131 71 10 71 10 145 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Integrity Measurement Architecture * * Copyright (C) 2005,2006,2007,2008 IBM Corporation * * Authors: * Reiner Sailer <sailer@watson.ibm.com> * Serge Hallyn <serue@us.ibm.com> * Kylene Hall <kylene@us.ibm.com> * Mimi Zohar <zohar@us.ibm.com> * * File: ima_main.c * implements the IMA hooks: ima_bprm_check, ima_file_mmap, * and ima_file_check. */ #include <linux/module.h> #include <linux/file.h> #include <linux/binfmts.h> #include <linux/kernel_read_file.h> #include <linux/mount.h> #include <linux/mman.h> #include <linux/slab.h> #include <linux/xattr.h> #include <linux/ima.h> #include <linux/fs.h> #include <linux/iversion.h> #include <linux/evm.h> #include "ima.h" #ifdef CONFIG_IMA_APPRAISE int ima_appraise = IMA_APPRAISE_ENFORCE; #else int ima_appraise; #endif int __ro_after_init ima_hash_algo = HASH_ALGO_SHA1; static int hash_setup_done; static struct notifier_block ima_lsm_policy_notifier = { .notifier_call = ima_lsm_policy_change, }; static int __init hash_setup(char *str) { struct ima_template_desc *template_desc = ima_template_desc_current(); int i; if (hash_setup_done) return 1; if (strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) == 0) { if (strncmp(str, "sha1", 4) == 0) { ima_hash_algo = HASH_ALGO_SHA1; } else if (strncmp(str, "md5", 3) == 0) { ima_hash_algo = HASH_ALGO_MD5; } else { pr_err("invalid hash algorithm \"%s\" for template \"%s\"", str, IMA_TEMPLATE_IMA_NAME); return 1; } goto out; } i = match_string(hash_algo_name, HASH_ALGO__LAST, str); if (i < 0) { pr_err("invalid hash algorithm \"%s\"", str); return 1; } ima_hash_algo = i; out: hash_setup_done = 1; return 1; } __setup("ima_hash=", hash_setup); enum hash_algo ima_get_current_hash_algo(void) { return ima_hash_algo; } /* Prevent mmap'ing a file execute that is already mmap'ed write */ static int mmap_violation_check(enum ima_hooks func, struct file *file, char **pathbuf, const char **pathname, char *filename) { struct inode *inode; int rc = 0; if ((func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && mapping_writably_mapped(file->f_mapping)) { rc = -ETXTBSY; inode = file_inode(file); if (!*pathbuf) /* ima_rdwr_violation possibly pre-fetched */ *pathname = ima_d_path(&file->f_path, pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, *pathname, "mmap_file", "mmapped_writers", rc, 0); } return rc; } /* * ima_rdwr_violation_check * * Only invalidate the PCR for measured files: * - Opening a file for write when already open for read, * results in a time of measure, time of use (ToMToU) error. * - Opening a file for read when already open for write, * could result in a file measurement error. * */ static void ima_rdwr_violation_check(struct file *file, struct ima_iint_cache *iint, int must_measure, char **pathbuf, const char **pathname, char *filename) { struct inode *inode = file_inode(file); fmode_t mode = file->f_mode; bool send_tomtou = false, send_writers = false; if (mode & FMODE_WRITE) { if (atomic_read(&inode->i_readcount) && IS_IMA(inode)) { if (!iint) iint = ima_iint_find(inode); /* IMA_MEASURE is set from reader side */ if (iint && test_bit(IMA_MUST_MEASURE, &iint->atomic_flags)) send_tomtou = true; } } else { if (must_measure) set_bit(IMA_MUST_MEASURE, &iint->atomic_flags); if (inode_is_open_for_write(inode) && must_measure) send_writers = true; } if (!send_tomtou && !send_writers) return; *pathname = ima_d_path(&file->f_path, pathbuf, filename); if (send_tomtou) ima_add_violation(file, *pathname, iint, "invalid_pcr", "ToMToU"); if (send_writers) ima_add_violation(file, *pathname, iint, "invalid_pcr", "open_writers"); } static void ima_check_last_writer(struct ima_iint_cache *iint, struct inode *inode, struct file *file) { fmode_t mode = file->f_mode; bool update; if (!(mode & FMODE_WRITE)) return; mutex_lock(&iint->mutex); if (atomic_read(&inode->i_writecount) == 1) { struct kstat stat; update = test_and_clear_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); if ((iint->flags & IMA_NEW_FILE) || vfs_getattr_nosec(&file->f_path, &stat, STATX_CHANGE_COOKIE, AT_STATX_SYNC_AS_STAT) || !(stat.result_mask & STATX_CHANGE_COOKIE) || stat.change_cookie != iint->real_inode.version) { iint->flags &= ~(IMA_DONE_MASK | IMA_NEW_FILE); iint->measured_pcrs = 0; if (update) ima_update_xattr(iint, file); } } mutex_unlock(&iint->mutex); } /** * ima_file_free - called on __fput() * @file: pointer to file structure being freed * * Flag files that changed, based on i_version */ static void ima_file_free(struct file *file) { struct inode *inode = file_inode(file); struct ima_iint_cache *iint; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; iint = ima_iint_find(inode); if (!iint) return; ima_check_last_writer(iint, inode, file); } static int process_measurement(struct file *file, const struct cred *cred, u32 secid, char *buf, loff_t size, int mask, enum ima_hooks func) { struct inode *real_inode, *inode = file_inode(file); struct ima_iint_cache *iint = NULL; struct ima_template_desc *template_desc = NULL; struct inode *metadata_inode; char *pathbuf = NULL; char filename[NAME_MAX]; const char *pathname = NULL; int rc = 0, action, must_appraise = 0; int pcr = CONFIG_IMA_MEASURE_PCR_IDX; struct evm_ima_xattr_data *xattr_value = NULL; struct modsig *modsig = NULL; int xattr_len = 0; bool violation_check; enum hash_algo hash_algo; unsigned int allowed_algos = 0; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return 0; /* Return an IMA_MEASURE, IMA_APPRAISE, IMA_AUDIT action * bitmask based on the appraise/audit/measurement policy. * Included is the appraise submask. */ action = ima_get_action(file_mnt_idmap(file), inode, cred, secid, mask, func, &pcr, &template_desc, NULL, &allowed_algos); violation_check = ((func == FILE_CHECK || func == MMAP_CHECK || func == MMAP_CHECK_REQPROT) && (ima_policy_flag & IMA_MEASURE)); if (!action && !violation_check) return 0; must_appraise = action & IMA_APPRAISE; /* Is the appraise rule hook specific? */ if (action & IMA_FILE_APPRAISE) func = FILE_CHECK; inode_lock(inode); if (action) { iint = ima_inode_get(inode); if (!iint) rc = -ENOMEM; } if (!rc && violation_check) ima_rdwr_violation_check(file, iint, action & IMA_MEASURE, &pathbuf, &pathname, filename); inode_unlock(inode); if (rc) goto out; if (!action) goto out; mutex_lock(&iint->mutex); if (test_and_clear_bit(IMA_CHANGE_ATTR, &iint->atomic_flags)) /* reset appraisal flags if ima_inode_post_setattr was called */ iint->flags &= ~(IMA_APPRAISE | IMA_APPRAISED | IMA_APPRAISE_SUBMASK | IMA_APPRAISED_SUBMASK | IMA_NONACTION_FLAGS); /* * Re-evaulate the file if either the xattr has changed or the * kernel has no way of detecting file change on the filesystem. * (Limited to privileged mounted filesystems.) */ if (test_and_clear_bit(IMA_CHANGE_XATTR, &iint->atomic_flags) || ((inode->i_sb->s_iflags & SB_I_IMA_UNVERIFIABLE_SIGNATURE) && !(inode->i_sb->s_iflags & SB_I_UNTRUSTED_MOUNTER) && !(action & IMA_FAIL_UNVERIFIABLE_SIGS))) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * On stacked filesystems, detect and re-evaluate file data and * metadata changes. */ real_inode = d_real_inode(file_dentry(file)); if (real_inode != inode && (action & IMA_DO_MASK) && (iint->flags & IMA_DONE_MASK)) { if (!IS_I_VERSION(real_inode) || integrity_inode_attrs_changed(&iint->real_inode, real_inode)) { iint->flags &= ~IMA_DONE_MASK; iint->measured_pcrs = 0; } /* * Reset the EVM status when metadata changed. */ metadata_inode = d_inode(d_real(file_dentry(file), D_REAL_METADATA)); if (evm_metadata_changed(inode, metadata_inode)) iint->flags &= ~(IMA_APPRAISED | IMA_APPRAISED_SUBMASK); } /* Determine if already appraised/measured based on bitmask * (IMA_MEASURE, IMA_MEASURED, IMA_XXXX_APPRAISE, IMA_XXXX_APPRAISED, * IMA_AUDIT, IMA_AUDITED) */ iint->flags |= action; action &= IMA_DO_MASK; action &= ~((iint->flags & (IMA_DONE_MASK ^ IMA_MEASURED)) >> 1); /* If target pcr is already measured, unset IMA_MEASURE action */ if ((action & IMA_MEASURE) && (iint->measured_pcrs & (0x1 << pcr))) action ^= IMA_MEASURE; /* HASH sets the digital signature and update flags, nothing else */ if ((action & IMA_HASH) && !(test_bit(IMA_DIGSIG, &iint->atomic_flags))) { xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); if ((xattr_value && xattr_len > 2) && (xattr_value->type == EVM_IMA_XATTR_DIGSIG)) set_bit(IMA_DIGSIG, &iint->atomic_flags); iint->flags |= IMA_HASHED; action ^= IMA_HASH; set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } /* Nothing to do, just return existing appraised status */ if (!action) { if (must_appraise) { rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); if (!rc) rc = ima_get_cache_status(iint, func); } goto out_locked; } if ((action & IMA_APPRAISE_SUBMASK) || strcmp(template_desc->name, IMA_TEMPLATE_IMA_NAME) != 0) { /* read 'security.ima' */ xattr_len = ima_read_xattr(file_dentry(file), &xattr_value, xattr_len); /* * Read the appended modsig if allowed by the policy, and allow * an additional measurement list entry, if needed, based on the * template format and whether the file was already measured. */ if (iint->flags & IMA_MODSIG_ALLOWED) { rc = ima_read_modsig(func, buf, size, &modsig); if (!rc && ima_template_has_modsig(template_desc) && iint->flags & IMA_MEASURED) action |= IMA_MEASURE; } } hash_algo = ima_get_hash_algo(xattr_value, xattr_len); rc = ima_collect_measurement(iint, file, buf, size, hash_algo, modsig); if (rc != 0 && rc != -EBADF && rc != -EINVAL) goto out_locked; if (!pathbuf) /* ima_rdwr_violation possibly pre-fetched */ pathname = ima_d_path(&file->f_path, &pathbuf, filename); if (action & IMA_MEASURE) ima_store_measurement(iint, file, pathname, xattr_value, xattr_len, modsig, pcr, template_desc); if (rc == 0 && (action & IMA_APPRAISE_SUBMASK)) { rc = ima_check_blacklist(iint, modsig, pcr); if (rc != -EPERM) { inode_lock(inode); rc = ima_appraise_measurement(func, iint, file, pathname, xattr_value, xattr_len, modsig); inode_unlock(inode); } if (!rc) rc = mmap_violation_check(func, file, &pathbuf, &pathname, filename); } if (action & IMA_AUDIT) ima_audit_measurement(iint, pathname); if ((file->f_flags & O_DIRECT) && (iint->flags & IMA_PERMIT_DIRECTIO)) rc = 0; /* Ensure the digest was generated using an allowed algorithm */ if (rc == 0 && must_appraise && allowed_algos != 0 && (allowed_algos & (1U << hash_algo)) == 0) { rc = -EACCES; integrity_audit_msg(AUDIT_INTEGRITY_DATA, file_inode(file), pathname, "collect_data", "denied-hash-algorithm", rc, 0); } out_locked: if ((mask & MAY_WRITE) && test_bit(IMA_DIGSIG, &iint->atomic_flags) && !(iint->flags & IMA_NEW_FILE)) rc = -EACCES; mutex_unlock(&iint->mutex); kfree(xattr_value); ima_free_modsig(modsig); out: if (pathbuf) __putname(pathbuf); if (must_appraise) { if (rc && (ima_appraise & IMA_APPRAISE_ENFORCE)) return -EACCES; if (file->f_mode & FMODE_WRITE) set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); } return 0; } /** * ima_file_mmap - based on policy, collect/store measurement. * @file: pointer to the file to be measured (May be NULL) * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * @flags: operational flags * * Measure files being mmapped executable based on the ima_must_measure() * policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_mmap(struct file *file, unsigned long reqprot, unsigned long prot, unsigned long flags) { u32 secid; int ret; if (!file) return 0; security_current_getsecid_subj(&secid); if (reqprot & PROT_EXEC) { ret = process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK_REQPROT); if (ret) return ret; } if (prot & PROT_EXEC) return process_measurement(file, current_cred(), secid, NULL, 0, MAY_EXEC, MMAP_CHECK); return 0; } /** * ima_file_mprotect - based on policy, limit mprotect change * @vma: vm_area_struct protection is set to * @reqprot: protection requested by the application * @prot: protection that will be applied by the kernel * * Files can be mmap'ed read/write and later changed to execute to circumvent * IMA's mmap appraisal policy rules. Due to locking issues (mmap semaphore * would be taken before i_mutex), files can not be measured or appraised at * this point. Eliminate this integrity gap by denying the mprotect * PROT_EXECUTE change, if an mmap appraise policy rule exists. * * On mprotect change success, return 0. On failure, return -EACESS. */ static int ima_file_mprotect(struct vm_area_struct *vma, unsigned long reqprot, unsigned long prot) { struct ima_template_desc *template = NULL; struct file *file; char filename[NAME_MAX]; char *pathbuf = NULL; const char *pathname = NULL; struct inode *inode; int result = 0; int action; u32 secid; int pcr; /* Is mprotect making an mmap'ed file executable? */ if (!(ima_policy_flag & IMA_APPRAISE) || !vma->vm_file || !(prot & PROT_EXEC) || (vma->vm_flags & VM_EXEC)) return 0; security_current_getsecid_subj(&secid); inode = file_inode(vma->vm_file); action = ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK, &pcr, &template, NULL, NULL); action |= ima_get_action(file_mnt_idmap(vma->vm_file), inode, current_cred(), secid, MAY_EXEC, MMAP_CHECK_REQPROT, &pcr, &template, NULL, NULL); /* Is the mmap'ed file in policy? */ if (!(action & (IMA_MEASURE | IMA_APPRAISE_SUBMASK))) return 0; if (action & IMA_APPRAISE_SUBMASK) result = -EPERM; file = vma->vm_file; pathname = ima_d_path(&file->f_path, &pathbuf, filename); integrity_audit_msg(AUDIT_INTEGRITY_DATA, inode, pathname, "collect_data", "failed-mprotect", result, 0); if (pathbuf) __putname(pathbuf); return result; } /** * ima_bprm_check - based on policy, collect/store measurement. * @bprm: contains the linux_binprm structure * * The OS protects against an executable file, already open for write, * from being executed in deny_write_access() and an executable file, * already open for execute, from being modified in get_write_access(). * So we can be certain that what we verify and measure here is actually * what is being executed. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_bprm_check(struct linux_binprm *bprm) { int ret; u32 secid; security_current_getsecid_subj(&secid); ret = process_measurement(bprm->file, current_cred(), secid, NULL, 0, MAY_EXEC, BPRM_CHECK); if (ret) return ret; security_cred_getsecid(bprm->cred, &secid); return process_measurement(bprm->file, bprm->cred, secid, NULL, 0, MAY_EXEC, CREDS_CHECK); } /** * ima_file_check - based on policy, collect/store measurement. * @file: pointer to the file to be measured * @mask: contains MAY_READ, MAY_WRITE, MAY_EXEC or MAY_APPEND * * Measure files based on the ima_must_measure() policy decision. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_file_check(struct file *file, int mask) { u32 secid; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, mask & (MAY_READ | MAY_WRITE | MAY_EXEC | MAY_APPEND), FILE_CHECK); } static int __ima_inode_hash(struct inode *inode, struct file *file, char *buf, size_t buf_size) { struct ima_iint_cache *iint = NULL, tmp_iint; int rc, hash_algo; if (ima_policy_flag) { iint = ima_iint_find(inode); if (iint) mutex_lock(&iint->mutex); } if ((!iint || !(iint->flags & IMA_COLLECTED)) && file) { if (iint) mutex_unlock(&iint->mutex); memset(&tmp_iint, 0, sizeof(tmp_iint)); mutex_init(&tmp_iint.mutex); rc = ima_collect_measurement(&tmp_iint, file, NULL, 0, ima_hash_algo, NULL); if (rc < 0) { /* ima_hash could be allocated in case of failure. */ if (rc != -ENOMEM) kfree(tmp_iint.ima_hash); return -EOPNOTSUPP; } iint = &tmp_iint; mutex_lock(&iint->mutex); } if (!iint) return -EOPNOTSUPP; /* * ima_file_hash can be called when ima_collect_measurement has still * not been called, we might not always have a hash. */ if (!iint->ima_hash || !(iint->flags & IMA_COLLECTED)) { mutex_unlock(&iint->mutex); return -EOPNOTSUPP; } if (buf) { size_t copied_size; copied_size = min_t(size_t, iint->ima_hash->length, buf_size); memcpy(buf, iint->ima_hash->digest, copied_size); } hash_algo = iint->ima_hash->algo; mutex_unlock(&iint->mutex); if (iint == &tmp_iint) kfree(iint->ima_hash); return hash_algo; } /** * ima_file_hash - return a measurement of the file * @file: pointer to the file * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The file hash returned is based on the entire file, including the appended * signature. * * If the measurement cannot be performed, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_file_hash(struct file *file, char *buf, size_t buf_size) { if (!file) return -EINVAL; return __ima_inode_hash(file_inode(file), file, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_file_hash); /** * ima_inode_hash - return the stored measurement if the inode has been hashed * and is in the iint cache. * @inode: pointer to the inode * @buf: buffer in which to store the hash * @buf_size: length of the buffer * * On success, return the hash algorithm (as defined in the enum hash_algo). * If buf is not NULL, this function also outputs the hash into buf. * If the hash is larger than buf_size, then only buf_size bytes will be copied. * It generally just makes sense to pass a buffer capable of holding the largest * possible hash: IMA_MAX_DIGEST_SIZE. * The hash returned is based on the entire contents, including the appended * signature. * * If IMA is disabled or if no measurement is available, return -EOPNOTSUPP. * If the parameters are incorrect, return -EINVAL. */ int ima_inode_hash(struct inode *inode, char *buf, size_t buf_size) { if (!inode) return -EINVAL; return __ima_inode_hash(inode, NULL, buf, buf_size); } EXPORT_SYMBOL_GPL(ima_inode_hash); /** * ima_post_create_tmpfile - mark newly created tmpfile as new * @idmap: idmap of the mount the inode was found from * @inode: inode of the newly created tmpfile * * No measuring, appraising or auditing of newly created tmpfiles is needed. * Skip calling process_measurement(), but indicate which newly, created * tmpfiles are in policy. */ static void ima_post_create_tmpfile(struct mnt_idmap *idmap, struct inode *inode) { struct ima_iint_cache *iint; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for writing the security xattrs */ set_bit(IMA_UPDATE_XATTR, &iint->atomic_flags); iint->ima_file_status = INTEGRITY_PASS; } /** * ima_post_path_mknod - mark as a new inode * @idmap: idmap of the mount the inode was found from * @dentry: newly created dentry * * Mark files created via the mknodat syscall as new, so that the * file data can be written later. */ static void ima_post_path_mknod(struct mnt_idmap *idmap, struct dentry *dentry) { struct ima_iint_cache *iint; struct inode *inode = dentry->d_inode; int must_appraise; if (!ima_policy_flag || !S_ISREG(inode->i_mode)) return; must_appraise = ima_must_appraise(idmap, inode, MAY_ACCESS, FILE_CHECK); if (!must_appraise) return; /* Nothing to do if we can't allocate memory */ iint = ima_inode_get(inode); if (!iint) return; /* needed for re-opening empty files */ iint->flags |= IMA_NEW_FILE; } /** * ima_read_file - pre-measure/appraise hook decision based on policy * @file: pointer to the file to be measured/appraised/audit * @read_id: caller identifier * @contents: whether a subsequent call will be made to ima_post_read_file() * * Permit reading a file based on policy. The policy rules are written * in terms of the policy identifier. Appraising the integrity of * a file requires a file descriptor. * * For permission return 0, otherwise return -EACCES. */ static int ima_read_file(struct file *file, enum kernel_read_file_id read_id, bool contents) { enum ima_hooks func; u32 secid; /* * Do devices using pre-allocated memory run the risk of the * firmware being accessible to the device prior to the completion * of IMA's signature verification any more than when using two * buffers? It may be desirable to include the buffer address * in this API and walk all the dma_map_single() mappings to check. */ /* * There will be a call made to ima_post_read_file() with * a filled buffer, so we don't need to perform an extra * read early here. */ if (contents) return 0; /* Read entire file for all partial reads. */ func = read_idmap[read_id] ?: FILE_CHECK; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, NULL, 0, MAY_READ, func); } const int read_idmap[READING_MAX_ID] = { [READING_FIRMWARE] = FIRMWARE_CHECK, [READING_MODULE] = MODULE_CHECK, [READING_KEXEC_IMAGE] = KEXEC_KERNEL_CHECK, [READING_KEXEC_INITRAMFS] = KEXEC_INITRAMFS_CHECK, [READING_POLICY] = POLICY_CHECK }; /** * ima_post_read_file - in memory collect/appraise/audit measurement * @file: pointer to the file to be measured/appraised/audit * @buf: pointer to in memory file contents * @size: size of in memory file contents * @read_id: caller identifier * * Measure/appraise/audit in memory file based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_read_file(struct file *file, char *buf, loff_t size, enum kernel_read_file_id read_id) { enum ima_hooks func; u32 secid; /* permit signed certs */ if (!file && read_id == READING_X509_CERTIFICATE) return 0; if (!file || !buf || size == 0) { /* should never happen */ if (ima_appraise & IMA_APPRAISE_ENFORCE) return -EACCES; return 0; } func = read_idmap[read_id] ?: FILE_CHECK; security_current_getsecid_subj(&secid); return process_measurement(file, current_cred(), secid, buf, size, MAY_READ, func); } /** * ima_load_data - appraise decision based on policy * @id: kernel load data caller identifier * @contents: whether the full contents will be available in a later * call to ima_post_load_data(). * * Callers of this LSM hook can not measure, appraise, or audit the * data provided by userspace. Enforce policy rules requiring a file * signature (eg. kexec'ed kernel image). * * For permission return 0, otherwise return -EACCES. */ static int ima_load_data(enum kernel_load_data_id id, bool contents) { bool ima_enforce, sig_enforce; ima_enforce = (ima_appraise & IMA_APPRAISE_ENFORCE) == IMA_APPRAISE_ENFORCE; switch (id) { case LOADING_KEXEC_IMAGE: if (IS_ENABLED(CONFIG_KEXEC_SIG) && arch_ima_get_secureboot()) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; } if (ima_enforce && (ima_appraise & IMA_APPRAISE_KEXEC)) { pr_err("impossible to appraise a kernel image without a file descriptor; try using kexec_file_load syscall.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_FIRMWARE: if (ima_enforce && (ima_appraise & IMA_APPRAISE_FIRMWARE) && !contents) { pr_err("Prevent firmware sysfs fallback loading.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; case LOADING_MODULE: sig_enforce = is_module_sig_enforced(); if (ima_enforce && (!sig_enforce && (ima_appraise & IMA_APPRAISE_MODULES))) { pr_err("impossible to appraise a module without a file descriptor. sig_enforce kernel parameter might help\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } break; default: break; } return 0; } /** * ima_post_load_data - appraise decision based on policy * @buf: pointer to in memory file contents * @size: size of in memory file contents * @load_id: kernel load data caller identifier * @description: @load_id-specific description of contents * * Measure/appraise/audit in memory buffer based on policy. Policy rules * are written in terms of a policy identifier. * * On success return 0. On integrity appraisal error, assuming the file * is in policy and IMA-appraisal is in enforcing mode, return -EACCES. */ static int ima_post_load_data(char *buf, loff_t size, enum kernel_load_data_id load_id, char *description) { if (load_id == LOADING_FIRMWARE) { if ((ima_appraise & IMA_APPRAISE_FIRMWARE) && (ima_appraise & IMA_APPRAISE_ENFORCE)) { pr_err("Prevent firmware loading_store.\n"); return -EACCES; /* INTEGRITY_UNKNOWN */ } return 0; } /* * Measure the init_module syscall buffer containing the ELF image. */ if (load_id == LOADING_MODULE) ima_measure_critical_data("modules", "init_module", buf, size, true, NULL, 0); return 0; } /** * process_buffer_measurement - Measure the buffer or the buffer data hash * @idmap: idmap of the mount the inode was found from * @inode: inode associated with the object being measured (NULL for KEY_CHECK) * @buf: pointer to the buffer that needs to be added to the log. * @size: size of buffer(in bytes). * @eventname: event name to be used for the buffer entry. * @func: IMA hook * @pcr: pcr to extend the measurement * @func_data: func specific data, may be NULL * @buf_hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Based on policy, either the buffer data or buffer data hash is measured * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int process_buffer_measurement(struct mnt_idmap *idmap, struct inode *inode, const void *buf, int size, const char *eventname, enum ima_hooks func, int pcr, const char *func_data, bool buf_hash, u8 *digest, size_t digest_len) { int ret = 0; const char *audit_cause = "ENOMEM"; struct ima_template_entry *entry = NULL; struct ima_iint_cache iint = {}; struct ima_event_data event_data = {.iint = &iint, .filename = eventname, .buf = buf, .buf_len = size}; struct ima_template_desc *template; struct ima_max_digest_data hash; struct ima_digest_data *hash_hdr = container_of(&hash.hdr, struct ima_digest_data, hdr); char digest_hash[IMA_MAX_DIGEST_SIZE]; int digest_hash_len = hash_digest_size[ima_hash_algo]; int violation = 0; int action = 0; u32 secid; if (digest && digest_len < digest_hash_len) return -EINVAL; if (!ima_policy_flag && !digest) return -ENOENT; template = ima_template_desc_buf(); if (!template) { ret = -EINVAL; audit_cause = "ima_template_desc_buf"; goto out; } /* * Both LSM hooks and auxilary based buffer measurements are * based on policy. To avoid code duplication, differentiate * between the LSM hooks and auxilary buffer measurements, * retrieving the policy rule information only for the LSM hook * buffer measurements. */ if (func) { security_current_getsecid_subj(&secid); action = ima_get_action(idmap, inode, current_cred(), secid, 0, func, &pcr, &template, func_data, NULL); if (!(action & IMA_MEASURE) && !digest) return -ENOENT; } if (!pcr) pcr = CONFIG_IMA_MEASURE_PCR_IDX; iint.ima_hash = hash_hdr; iint.ima_hash->algo = ima_hash_algo; iint.ima_hash->length = hash_digest_size[ima_hash_algo]; ret = ima_calc_buffer_hash(buf, size, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } if (buf_hash) { memcpy(digest_hash, hash_hdr->digest, digest_hash_len); ret = ima_calc_buffer_hash(digest_hash, digest_hash_len, iint.ima_hash); if (ret < 0) { audit_cause = "hashing_error"; goto out; } event_data.buf = digest_hash; event_data.buf_len = digest_hash_len; } if (digest) memcpy(digest, iint.ima_hash->digest, digest_hash_len); if (!ima_policy_flag || (func && !(action & IMA_MEASURE))) return 1; ret = ima_alloc_init_template(&event_data, &entry, template); if (ret < 0) { audit_cause = "alloc_entry"; goto out; } ret = ima_store_template(entry, violation, NULL, event_data.buf, pcr); if (ret < 0) { audit_cause = "store_entry"; ima_free_template_entry(entry); } out: if (ret < 0) integrity_audit_message(AUDIT_INTEGRITY_PCR, NULL, eventname, func_measure_str(func), audit_cause, ret, 0, ret); return ret; } /** * ima_kexec_cmdline - measure kexec cmdline boot args * @kernel_fd: file descriptor of the kexec kernel being loaded * @buf: pointer to buffer * @size: size of buffer * * Buffers can only be measured, not appraised. */ void ima_kexec_cmdline(int kernel_fd, const void *buf, int size) { struct fd f; if (!buf || !size) return; f = fdget(kernel_fd); if (!f.file) return; process_buffer_measurement(file_mnt_idmap(f.file), file_inode(f.file), buf, size, "kexec-cmdline", KEXEC_CMDLINE, 0, NULL, false, NULL, 0); fdput(f); } /** * ima_measure_critical_data - measure kernel integrity critical data * @event_label: unique event label for grouping and limiting critical data * @event_name: event name for the record in the IMA measurement list * @buf: pointer to buffer data * @buf_len: length of buffer data (in bytes) * @hash: measure buffer data hash * @digest: buffer digest will be written to * @digest_len: buffer length * * Measure data critical to the integrity of the kernel into the IMA log * and extend the pcr. Examples of critical data could be various data * structures, policies, and states stored in kernel memory that can * impact the integrity of the system. * * Return: 0 if the buffer has been successfully measured, 1 if the digest * has been written to the passed location but not added to a measurement entry, * a negative value otherwise. */ int ima_measure_critical_data(const char *event_label, const char *event_name, const void *buf, size_t buf_len, bool hash, u8 *digest, size_t digest_len) { if (!event_name || !event_label || !buf || !buf_len) return -ENOPARAM; return process_buffer_measurement(&nop_mnt_idmap, NULL, buf, buf_len, event_name, CRITICAL_DATA, 0, event_label, hash, digest, digest_len); } EXPORT_SYMBOL_GPL(ima_measure_critical_data); #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS /** * ima_kernel_module_request - Prevent crypto-pkcs1pad(rsa,*) requests * @kmod_name: kernel module name * * Avoid a verification loop where verifying the signature of the modprobe * binary requires executing modprobe itself. Since the modprobe iint->mutex * is already held when the signature verification is performed, a deadlock * occurs as soon as modprobe is executed within the critical region, since * the same lock cannot be taken again. * * This happens when public_key_verify_signature(), in case of RSA algorithm, * use alg_name to store internal information in order to construct an * algorithm on the fly, but crypto_larval_lookup() will try to use alg_name * in order to load a kernel module with same name. * * Since we don't have any real "crypto-pkcs1pad(rsa,*)" kernel modules, * we are safe to fail such module request from crypto_larval_lookup(), and * avoid the verification loop. * * Return: Zero if it is safe to load the kernel module, -EINVAL otherwise. */ static int ima_kernel_module_request(char *kmod_name) { if (strncmp(kmod_name, "crypto-pkcs1pad(rsa,", 20) == 0) return -EINVAL; return 0; } #endif /* CONFIG_INTEGRITY_ASYMMETRIC_KEYS */ static int __init init_ima(void) { int error; ima_appraise_parse_cmdline(); ima_init_template_list(); hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); if (error && strcmp(hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH) != 0) { pr_info("Allocating %s failed, going to use default hash algorithm %s\n", hash_algo_name[ima_hash_algo], CONFIG_IMA_DEFAULT_HASH); hash_setup_done = 0; hash_setup(CONFIG_IMA_DEFAULT_HASH); error = ima_init(); } if (error) return error; error = register_blocking_lsm_notifier(&ima_lsm_policy_notifier); if (error) pr_warn("Couldn't register LSM notifier, error %d\n", error); if (!error) ima_update_policy_flags(); return error; } static struct security_hook_list ima_hooks[] __ro_after_init = { LSM_HOOK_INIT(bprm_check_security, ima_bprm_check), LSM_HOOK_INIT(file_post_open, ima_file_check), LSM_HOOK_INIT(inode_post_create_tmpfile, ima_post_create_tmpfile), LSM_HOOK_INIT(file_release, ima_file_free), LSM_HOOK_INIT(mmap_file, ima_file_mmap), LSM_HOOK_INIT(file_mprotect, ima_file_mprotect), LSM_HOOK_INIT(kernel_load_data, ima_load_data), LSM_HOOK_INIT(kernel_post_load_data, ima_post_load_data), LSM_HOOK_INIT(kernel_read_file, ima_read_file), LSM_HOOK_INIT(kernel_post_read_file, ima_post_read_file), LSM_HOOK_INIT(path_post_mknod, ima_post_path_mknod), #ifdef CONFIG_IMA_MEASURE_ASYMMETRIC_KEYS LSM_HOOK_INIT(key_post_create_or_update, ima_post_key_create_or_update), #endif #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request), #endif LSM_HOOK_INIT(inode_free_security, ima_inode_free), }; static const struct lsm_id ima_lsmid = { .name = "ima", .id = LSM_ID_IMA, }; static int __init init_ima_lsm(void) { ima_iintcache_init(); security_add_hooks(ima_hooks, ARRAY_SIZE(ima_hooks), &ima_lsmid); init_ima_appraise_lsm(&ima_lsmid); return 0; } struct lsm_blob_sizes ima_blob_sizes __ro_after_init = { .lbs_inode = sizeof(struct ima_iint_cache *), }; DEFINE_LSM(ima) = { .name = "ima", .init = init_ima_lsm, .order = LSM_ORDER_LAST, .blobs = &ima_blob_sizes, }; late_initcall(init_ima); /* Start IMA after the TPM is available */ |
| 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/signal.c * * Copyright (C) 1995-2009 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/cache.h> #include <linux/compat.h> #include <linux/errno.h> #include <linux/kernel.h> #include <linux/signal.h> #include <linux/freezer.h> #include <linux/stddef.h> #include <linux/uaccess.h> #include <linux/sizes.h> #include <linux/string.h> #include <linux/ratelimit.h> #include <linux/rseq.h> #include <linux/syscalls.h> #include <asm/daifflags.h> #include <asm/debug-monitors.h> #include <asm/elf.h> #include <asm/exception.h> #include <asm/cacheflush.h> #include <asm/ucontext.h> #include <asm/unistd.h> #include <asm/fpsimd.h> #include <asm/ptrace.h> #include <asm/syscall.h> #include <asm/signal32.h> #include <asm/traps.h> #include <asm/vdso.h> /* * Do a signal return; undo the signal stack. These are aligned to 128-bit. */ struct rt_sigframe { struct siginfo info; struct ucontext uc; }; struct frame_record { u64 fp; u64 lr; }; struct rt_sigframe_user_layout { struct rt_sigframe __user *sigframe; struct frame_record __user *next_frame; unsigned long size; /* size of allocated sigframe data */ unsigned long limit; /* largest allowed size */ unsigned long fpsimd_offset; unsigned long esr_offset; unsigned long sve_offset; unsigned long tpidr2_offset; unsigned long za_offset; unsigned long zt_offset; unsigned long fpmr_offset; unsigned long extra_offset; unsigned long end_offset; }; #define BASE_SIGFRAME_SIZE round_up(sizeof(struct rt_sigframe), 16) #define TERMINATOR_SIZE round_up(sizeof(struct _aarch64_ctx), 16) #define EXTRA_CONTEXT_SIZE round_up(sizeof(struct extra_context), 16) static void init_user_layout(struct rt_sigframe_user_layout *user) { const size_t reserved_size = sizeof(user->sigframe->uc.uc_mcontext.__reserved); memset(user, 0, sizeof(*user)); user->size = offsetof(struct rt_sigframe, uc.uc_mcontext.__reserved); user->limit = user->size + reserved_size; user->limit -= TERMINATOR_SIZE; user->limit -= EXTRA_CONTEXT_SIZE; /* Reserve space for extension and terminator ^ */ } static size_t sigframe_size(struct rt_sigframe_user_layout const *user) { return round_up(max(user->size, sizeof(struct rt_sigframe)), 16); } /* * Sanity limit on the approximate maximum size of signal frame we'll * try to generate. Stack alignment padding and the frame record are * not taken into account. This limit is not a guarantee and is * NOT ABI. */ #define SIGFRAME_MAXSZ SZ_256K static int __sigframe_alloc(struct rt_sigframe_user_layout *user, unsigned long *offset, size_t size, bool extend) { size_t padded_size = round_up(size, 16); if (padded_size > user->limit - user->size && !user->extra_offset && extend) { int ret; user->limit += EXTRA_CONTEXT_SIZE; ret = __sigframe_alloc(user, &user->extra_offset, sizeof(struct extra_context), false); if (ret) { user->limit -= EXTRA_CONTEXT_SIZE; return ret; } /* Reserve space for the __reserved[] terminator */ user->size += TERMINATOR_SIZE; /* * Allow expansion up to SIGFRAME_MAXSZ, ensuring space for * the terminator: */ user->limit = SIGFRAME_MAXSZ - TERMINATOR_SIZE; } /* Still not enough space? Bad luck! */ if (padded_size > user->limit - user->size) return -ENOMEM; *offset = user->size; user->size += padded_size; return 0; } /* * Allocate space for an optional record of <size> bytes in the user * signal frame. The offset from the signal frame base address to the * allocated block is assigned to *offset. */ static int sigframe_alloc(struct rt_sigframe_user_layout *user, unsigned long *offset, size_t size) { return __sigframe_alloc(user, offset, size, true); } /* Allocate the null terminator record and prevent further allocations */ static int sigframe_alloc_end(struct rt_sigframe_user_layout *user) { int ret; /* Un-reserve the space reserved for the terminator: */ user->limit += TERMINATOR_SIZE; ret = sigframe_alloc(user, &user->end_offset, sizeof(struct _aarch64_ctx)); if (ret) return ret; /* Prevent further allocation: */ user->limit = user->size; return 0; } static void __user *apply_user_offset( struct rt_sigframe_user_layout const *user, unsigned long offset) { char __user *base = (char __user *)user->sigframe; return base + offset; } struct user_ctxs { struct fpsimd_context __user *fpsimd; u32 fpsimd_size; struct sve_context __user *sve; u32 sve_size; struct tpidr2_context __user *tpidr2; u32 tpidr2_size; struct za_context __user *za; u32 za_size; struct zt_context __user *zt; u32 zt_size; struct fpmr_context __user *fpmr; u32 fpmr_size; }; static int preserve_fpsimd_context(struct fpsimd_context __user *ctx) { struct user_fpsimd_state const *fpsimd = ¤t->thread.uw.fpsimd_state; int err; /* copy the FP and status/control registers */ err = __copy_to_user(ctx->vregs, fpsimd->vregs, sizeof(fpsimd->vregs)); __put_user_error(fpsimd->fpsr, &ctx->fpsr, err); __put_user_error(fpsimd->fpcr, &ctx->fpcr, err); /* copy the magic/size information */ __put_user_error(FPSIMD_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(struct fpsimd_context), &ctx->head.size, err); return err ? -EFAULT : 0; } static int restore_fpsimd_context(struct user_ctxs *user) { struct user_fpsimd_state fpsimd; int err = 0; /* check the size information */ if (user->fpsimd_size != sizeof(struct fpsimd_context)) return -EINVAL; /* copy the FP and status/control registers */ err = __copy_from_user(fpsimd.vregs, &(user->fpsimd->vregs), sizeof(fpsimd.vregs)); __get_user_error(fpsimd.fpsr, &(user->fpsimd->fpsr), err); __get_user_error(fpsimd.fpcr, &(user->fpsimd->fpcr), err); clear_thread_flag(TIF_SVE); current->thread.fp_type = FP_STATE_FPSIMD; /* load the hardware registers from the fpsimd_state structure */ if (!err) fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } static int preserve_fpmr_context(struct fpmr_context __user *ctx) { int err = 0; current->thread.uw.fpmr = read_sysreg_s(SYS_FPMR); __put_user_error(FPMR_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(current->thread.uw.fpmr, &ctx->fpmr, err); return err; } static int restore_fpmr_context(struct user_ctxs *user) { u64 fpmr; int err = 0; if (user->fpmr_size != sizeof(*user->fpmr)) return -EINVAL; __get_user_error(fpmr, &user->fpmr->fpmr, err); if (!err) write_sysreg_s(fpmr, SYS_FPMR); return err; } #ifdef CONFIG_ARM64_SVE static int preserve_sve_context(struct sve_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; u16 flags = 0; unsigned int vl = task_get_sve_vl(current); unsigned int vq = 0; if (thread_sm_enabled(¤t->thread)) { vl = task_get_sme_vl(current); vq = sve_vq_from_vl(vl); flags |= SVE_SIG_FLAG_SM; } else if (current->thread.fp_type == FP_STATE_SVE) { vq = sve_vq_from_vl(vl); } memset(reserved, 0, sizeof(reserved)); __put_user_error(SVE_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(SVE_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); __put_user_error(flags, &ctx->flags, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) { /* * This assumes that the SVE state has already been saved to * the task struct by calling the function * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + SVE_SIG_REGS_OFFSET, current->thread.sve_state, SVE_SIG_REGS_SIZE(vq)); } return err ? -EFAULT : 0; } static int restore_sve_fpsimd_context(struct user_ctxs *user) { int err = 0; unsigned int vl, vq; struct user_fpsimd_state fpsimd; u16 user_vl, flags; if (user->sve_size < sizeof(*user->sve)) return -EINVAL; __get_user_error(user_vl, &(user->sve->vl), err); __get_user_error(flags, &(user->sve->flags), err); if (err) return err; if (flags & SVE_SIG_FLAG_SM) { if (!system_supports_sme()) return -EINVAL; vl = task_get_sme_vl(current); } else { /* * A SME only system use SVE for streaming mode so can * have a SVE formatted context with a zero VL and no * payload data. */ if (!system_supports_sve() && !system_supports_sme()) return -EINVAL; vl = task_get_sve_vl(current); } if (user_vl != vl) return -EINVAL; if (user->sve_size == sizeof(*user->sve)) { clear_thread_flag(TIF_SVE); current->thread.svcr &= ~SVCR_SM_MASK; current->thread.fp_type = FP_STATE_FPSIMD; goto fpsimd_only; } vq = sve_vq_from_vl(vl); if (user->sve_size < SVE_SIG_CONTEXT_SIZE(vq)) return -EINVAL; /* * Careful: we are about __copy_from_user() directly into * thread.sve_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ sve_alloc(current, true); if (!current->thread.sve_state) { clear_thread_flag(TIF_SVE); return -ENOMEM; } err = __copy_from_user(current->thread.sve_state, (char __user const *)user->sve + SVE_SIG_REGS_OFFSET, SVE_SIG_REGS_SIZE(vq)); if (err) return -EFAULT; if (flags & SVE_SIG_FLAG_SM) current->thread.svcr |= SVCR_SM_MASK; else set_thread_flag(TIF_SVE); current->thread.fp_type = FP_STATE_SVE; fpsimd_only: /* copy the FP and status/control registers */ /* restore_sigframe() already checked that user->fpsimd != NULL. */ err = __copy_from_user(fpsimd.vregs, user->fpsimd->vregs, sizeof(fpsimd.vregs)); __get_user_error(fpsimd.fpsr, &user->fpsimd->fpsr, err); __get_user_error(fpsimd.fpcr, &user->fpsimd->fpcr, err); /* load the hardware registers from the fpsimd_state structure */ if (!err) fpsimd_update_current_state(&fpsimd); return err ? -EFAULT : 0; } #else /* ! CONFIG_ARM64_SVE */ static int restore_sve_fpsimd_context(struct user_ctxs *user) { WARN_ON_ONCE(1); return -EINVAL; } /* Turn any non-optimised out attempts to use this into a link error: */ extern int preserve_sve_context(void __user *ctx); #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int preserve_tpidr2_context(struct tpidr2_context __user *ctx) { int err = 0; current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0); __put_user_error(TPIDR2_MAGIC, &ctx->head.magic, err); __put_user_error(sizeof(*ctx), &ctx->head.size, err); __put_user_error(current->thread.tpidr2_el0, &ctx->tpidr2, err); return err; } static int restore_tpidr2_context(struct user_ctxs *user) { u64 tpidr2_el0; int err = 0; if (user->tpidr2_size != sizeof(*user->tpidr2)) return -EINVAL; __get_user_error(tpidr2_el0, &user->tpidr2->tpidr2, err); if (!err) write_sysreg_s(tpidr2_el0, SYS_TPIDR2_EL0); return err; } static int preserve_za_context(struct za_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; unsigned int vl = task_get_sme_vl(current); unsigned int vq; if (thread_za_enabled(¤t->thread)) vq = sve_vq_from_vl(vl); else vq = 0; memset(reserved, 0, sizeof(reserved)); __put_user_error(ZA_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(ZA_SIG_CONTEXT_SIZE(vq), 16), &ctx->head.size, err); __put_user_error(vl, &ctx->vl, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); if (vq) { /* * This assumes that the ZA state has already been saved to * the task struct by calling the function * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + ZA_SIG_REGS_OFFSET, current->thread.sme_state, ZA_SIG_REGS_SIZE(vq)); } return err ? -EFAULT : 0; } static int restore_za_context(struct user_ctxs *user) { int err = 0; unsigned int vq; u16 user_vl; if (user->za_size < sizeof(*user->za)) return -EINVAL; __get_user_error(user_vl, &(user->za->vl), err); if (err) return err; if (user_vl != task_get_sme_vl(current)) return -EINVAL; if (user->za_size == sizeof(*user->za)) { current->thread.svcr &= ~SVCR_ZA_MASK; return 0; } vq = sve_vq_from_vl(user_vl); if (user->za_size < ZA_SIG_CONTEXT_SIZE(vq)) return -EINVAL; /* * Careful: we are about __copy_from_user() directly into * thread.sme_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch thread.sve_state */ sme_alloc(current, true); if (!current->thread.sme_state) { current->thread.svcr &= ~SVCR_ZA_MASK; clear_thread_flag(TIF_SME); return -ENOMEM; } err = __copy_from_user(current->thread.sme_state, (char __user const *)user->za + ZA_SIG_REGS_OFFSET, ZA_SIG_REGS_SIZE(vq)); if (err) return -EFAULT; set_thread_flag(TIF_SME); current->thread.svcr |= SVCR_ZA_MASK; return 0; } static int preserve_zt_context(struct zt_context __user *ctx) { int err = 0; u16 reserved[ARRAY_SIZE(ctx->__reserved)]; if (WARN_ON(!thread_za_enabled(¤t->thread))) return -EINVAL; memset(reserved, 0, sizeof(reserved)); __put_user_error(ZT_MAGIC, &ctx->head.magic, err); __put_user_error(round_up(ZT_SIG_CONTEXT_SIZE(1), 16), &ctx->head.size, err); __put_user_error(1, &ctx->nregs, err); BUILD_BUG_ON(sizeof(ctx->__reserved) != sizeof(reserved)); err |= __copy_to_user(&ctx->__reserved, reserved, sizeof(reserved)); /* * This assumes that the ZT state has already been saved to * the task struct by calling the function * fpsimd_signal_preserve_current_state(). */ err |= __copy_to_user((char __user *)ctx + ZT_SIG_REGS_OFFSET, thread_zt_state(¤t->thread), ZT_SIG_REGS_SIZE(1)); return err ? -EFAULT : 0; } static int restore_zt_context(struct user_ctxs *user) { int err; u16 nregs; /* ZA must be restored first for this check to be valid */ if (!thread_za_enabled(¤t->thread)) return -EINVAL; if (user->zt_size != ZT_SIG_CONTEXT_SIZE(1)) return -EINVAL; if (__copy_from_user(&nregs, &(user->zt->nregs), sizeof(nregs))) return -EFAULT; if (nregs != 1) return -EINVAL; /* * Careful: we are about __copy_from_user() directly into * thread.zt_state with preemption enabled, so protection is * needed to prevent a racing context switch from writing stale * registers back over the new data. */ fpsimd_flush_task_state(current); /* From now, fpsimd_thread_switch() won't touch ZT in thread state */ err = __copy_from_user(thread_zt_state(¤t->thread), (char __user const *)user->zt + ZT_SIG_REGS_OFFSET, ZT_SIG_REGS_SIZE(1)); if (err) return -EFAULT; return 0; } #else /* ! CONFIG_ARM64_SME */ /* Turn any non-optimised out attempts to use these into a link error: */ extern int preserve_tpidr2_context(void __user *ctx); extern int restore_tpidr2_context(struct user_ctxs *user); extern int preserve_za_context(void __user *ctx); extern int restore_za_context(struct user_ctxs *user); extern int preserve_zt_context(void __user *ctx); extern int restore_zt_context(struct user_ctxs *user); #endif /* ! CONFIG_ARM64_SME */ static int parse_user_sigframe(struct user_ctxs *user, struct rt_sigframe __user *sf) { struct sigcontext __user *const sc = &sf->uc.uc_mcontext; struct _aarch64_ctx __user *head; char __user *base = (char __user *)&sc->__reserved; size_t offset = 0; size_t limit = sizeof(sc->__reserved); bool have_extra_context = false; char const __user *const sfp = (char const __user *)sf; user->fpsimd = NULL; user->sve = NULL; user->tpidr2 = NULL; user->za = NULL; user->zt = NULL; user->fpmr = NULL; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; while (1) { int err = 0; u32 magic, size; char const __user *userp; struct extra_context const __user *extra; u64 extra_datap; u32 extra_size; struct _aarch64_ctx const __user *end; u32 end_magic, end_size; if (limit - offset < sizeof(*head)) goto invalid; if (!IS_ALIGNED(offset, 16)) goto invalid; head = (struct _aarch64_ctx __user *)(base + offset); __get_user_error(magic, &head->magic, err); __get_user_error(size, &head->size, err); if (err) return err; if (limit - offset < size) goto invalid; switch (magic) { case 0: if (size) goto invalid; goto done; case FPSIMD_MAGIC: if (!system_supports_fpsimd()) goto invalid; if (user->fpsimd) goto invalid; user->fpsimd = (struct fpsimd_context __user *)head; user->fpsimd_size = size; break; case ESR_MAGIC: /* ignore */ break; case SVE_MAGIC: if (!system_supports_sve() && !system_supports_sme()) goto invalid; if (user->sve) goto invalid; user->sve = (struct sve_context __user *)head; user->sve_size = size; break; case TPIDR2_MAGIC: if (!system_supports_tpidr2()) goto invalid; if (user->tpidr2) goto invalid; user->tpidr2 = (struct tpidr2_context __user *)head; user->tpidr2_size = size; break; case ZA_MAGIC: if (!system_supports_sme()) goto invalid; if (user->za) goto invalid; user->za = (struct za_context __user *)head; user->za_size = size; break; case ZT_MAGIC: if (!system_supports_sme2()) goto invalid; if (user->zt) goto invalid; user->zt = (struct zt_context __user *)head; user->zt_size = size; break; case FPMR_MAGIC: if (!system_supports_fpmr()) goto invalid; if (user->fpmr) goto invalid; user->fpmr = (struct fpmr_context __user *)head; user->fpmr_size = size; break; case EXTRA_MAGIC: if (have_extra_context) goto invalid; if (size < sizeof(*extra)) goto invalid; userp = (char const __user *)head; extra = (struct extra_context const __user *)userp; userp += size; __get_user_error(extra_datap, &extra->datap, err); __get_user_error(extra_size, &extra->size, err); if (err) return err; /* Check for the dummy terminator in __reserved[]: */ if (limit - offset - size < TERMINATOR_SIZE) goto invalid; end = (struct _aarch64_ctx const __user *)userp; userp += TERMINATOR_SIZE; __get_user_error(end_magic, &end->magic, err); __get_user_error(end_size, &end->size, err); if (err) return err; if (end_magic || end_size) goto invalid; /* Prevent looping/repeated parsing of extra_context */ have_extra_context = true; base = (__force void __user *)extra_datap; if (!IS_ALIGNED((unsigned long)base, 16)) goto invalid; if (!IS_ALIGNED(extra_size, 16)) goto invalid; if (base != userp) goto invalid; /* Reject "unreasonably large" frames: */ if (extra_size > sfp + SIGFRAME_MAXSZ - userp) goto invalid; /* * Ignore trailing terminator in __reserved[] * and start parsing extra data: */ offset = 0; limit = extra_size; if (!access_ok(base, limit)) goto invalid; continue; default: goto invalid; } if (size < sizeof(*head)) goto invalid; if (limit - offset < size) goto invalid; offset += size; } done: return 0; invalid: return -EINVAL; } static int restore_sigframe(struct pt_regs *regs, struct rt_sigframe __user *sf) { sigset_t set; int i, err; struct user_ctxs user; err = __copy_from_user(&set, &sf->uc.uc_sigmask, sizeof(set)); if (err == 0) set_current_blocked(&set); for (i = 0; i < 31; i++) __get_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i], err); __get_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err); __get_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err); __get_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err); /* * Avoid sys_rt_sigreturn() restarting. */ forget_syscall(regs); err |= !valid_user_regs(®s->user_regs, current); if (err == 0) err = parse_user_sigframe(&user, sf); if (err == 0 && system_supports_fpsimd()) { if (!user.fpsimd) return -EINVAL; if (user.sve) err = restore_sve_fpsimd_context(&user); else err = restore_fpsimd_context(&user); } if (err == 0 && system_supports_tpidr2() && user.tpidr2) err = restore_tpidr2_context(&user); if (err == 0 && system_supports_fpmr() && user.fpmr) err = restore_fpmr_context(&user); if (err == 0 && system_supports_sme() && user.za) err = restore_za_context(&user); if (err == 0 && system_supports_sme2() && user.zt) err = restore_zt_context(&user); return err; } SYSCALL_DEFINE0(rt_sigreturn) { struct pt_regs *regs = current_pt_regs(); struct rt_sigframe __user *frame; /* Always make any pending restarted system calls return -EINTR */ current->restart_block.fn = do_no_restart_syscall; /* * Since we stacked the signal on a 128-bit boundary, then 'sp' should * be word aligned here. */ if (regs->sp & 15) goto badframe; frame = (struct rt_sigframe __user *)regs->sp; if (!access_ok(frame, sizeof (*frame))) goto badframe; if (restore_sigframe(regs, frame)) goto badframe; if (restore_altstack(&frame->uc.uc_stack)) goto badframe; return regs->regs[0]; badframe: arm64_notify_segfault(regs->sp); return 0; } /* * Determine the layout of optional records in the signal frame * * add_all: if true, lays out the biggest possible signal frame for * this task; otherwise, generates a layout for the current state * of the task. */ static int setup_sigframe_layout(struct rt_sigframe_user_layout *user, bool add_all) { int err; if (system_supports_fpsimd()) { err = sigframe_alloc(user, &user->fpsimd_offset, sizeof(struct fpsimd_context)); if (err) return err; } /* fault information, if valid */ if (add_all || current->thread.fault_code) { err = sigframe_alloc(user, &user->esr_offset, sizeof(struct esr_context)); if (err) return err; } if (system_supports_sve() || system_supports_sme()) { unsigned int vq = 0; if (add_all || current->thread.fp_type == FP_STATE_SVE || thread_sm_enabled(¤t->thread)) { int vl = max(sve_max_vl(), sme_max_vl()); if (!add_all) vl = thread_get_cur_vl(¤t->thread); vq = sve_vq_from_vl(vl); } err = sigframe_alloc(user, &user->sve_offset, SVE_SIG_CONTEXT_SIZE(vq)); if (err) return err; } if (system_supports_tpidr2()) { err = sigframe_alloc(user, &user->tpidr2_offset, sizeof(struct tpidr2_context)); if (err) return err; } if (system_supports_sme()) { unsigned int vl; unsigned int vq = 0; if (add_all) vl = sme_max_vl(); else vl = task_get_sme_vl(current); if (thread_za_enabled(¤t->thread)) vq = sve_vq_from_vl(vl); err = sigframe_alloc(user, &user->za_offset, ZA_SIG_CONTEXT_SIZE(vq)); if (err) return err; } if (system_supports_sme2()) { if (add_all || thread_za_enabled(¤t->thread)) { err = sigframe_alloc(user, &user->zt_offset, ZT_SIG_CONTEXT_SIZE(1)); if (err) return err; } } if (system_supports_fpmr()) { err = sigframe_alloc(user, &user->fpmr_offset, sizeof(struct fpmr_context)); if (err) return err; } return sigframe_alloc_end(user); } static int setup_sigframe(struct rt_sigframe_user_layout *user, struct pt_regs *regs, sigset_t *set) { int i, err = 0; struct rt_sigframe __user *sf = user->sigframe; /* set up the stack frame for unwinding */ __put_user_error(regs->regs[29], &user->next_frame->fp, err); __put_user_error(regs->regs[30], &user->next_frame->lr, err); for (i = 0; i < 31; i++) __put_user_error(regs->regs[i], &sf->uc.uc_mcontext.regs[i], err); __put_user_error(regs->sp, &sf->uc.uc_mcontext.sp, err); __put_user_error(regs->pc, &sf->uc.uc_mcontext.pc, err); __put_user_error(regs->pstate, &sf->uc.uc_mcontext.pstate, err); __put_user_error(current->thread.fault_address, &sf->uc.uc_mcontext.fault_address, err); err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); if (err == 0 && system_supports_fpsimd()) { struct fpsimd_context __user *fpsimd_ctx = apply_user_offset(user, user->fpsimd_offset); err |= preserve_fpsimd_context(fpsimd_ctx); } /* fault information, if valid */ if (err == 0 && user->esr_offset) { struct esr_context __user *esr_ctx = apply_user_offset(user, user->esr_offset); __put_user_error(ESR_MAGIC, &esr_ctx->head.magic, err); __put_user_error(sizeof(*esr_ctx), &esr_ctx->head.size, err); __put_user_error(current->thread.fault_code, &esr_ctx->esr, err); } /* Scalable Vector Extension state (including streaming), if present */ if ((system_supports_sve() || system_supports_sme()) && err == 0 && user->sve_offset) { struct sve_context __user *sve_ctx = apply_user_offset(user, user->sve_offset); err |= preserve_sve_context(sve_ctx); } /* TPIDR2 if supported */ if (system_supports_tpidr2() && err == 0) { struct tpidr2_context __user *tpidr2_ctx = apply_user_offset(user, user->tpidr2_offset); err |= preserve_tpidr2_context(tpidr2_ctx); } /* FPMR if supported */ if (system_supports_fpmr() && err == 0) { struct fpmr_context __user *fpmr_ctx = apply_user_offset(user, user->fpmr_offset); err |= preserve_fpmr_context(fpmr_ctx); } /* ZA state if present */ if (system_supports_sme() && err == 0 && user->za_offset) { struct za_context __user *za_ctx = apply_user_offset(user, user->za_offset); err |= preserve_za_context(za_ctx); } /* ZT state if present */ if (system_supports_sme2() && err == 0 && user->zt_offset) { struct zt_context __user *zt_ctx = apply_user_offset(user, user->zt_offset); err |= preserve_zt_context(zt_ctx); } if (err == 0 && user->extra_offset) { char __user *sfp = (char __user *)user->sigframe; char __user *userp = apply_user_offset(user, user->extra_offset); struct extra_context __user *extra; struct _aarch64_ctx __user *end; u64 extra_datap; u32 extra_size; extra = (struct extra_context __user *)userp; userp += EXTRA_CONTEXT_SIZE; end = (struct _aarch64_ctx __user *)userp; userp += TERMINATOR_SIZE; /* * extra_datap is just written to the signal frame. * The value gets cast back to a void __user * * during sigreturn. */ extra_datap = (__force u64)userp; extra_size = sfp + round_up(user->size, 16) - userp; __put_user_error(EXTRA_MAGIC, &extra->head.magic, err); __put_user_error(EXTRA_CONTEXT_SIZE, &extra->head.size, err); __put_user_error(extra_datap, &extra->datap, err); __put_user_error(extra_size, &extra->size, err); /* Add the terminator */ __put_user_error(0, &end->magic, err); __put_user_error(0, &end->size, err); } /* set the "end" magic */ if (err == 0) { struct _aarch64_ctx __user *end = apply_user_offset(user, user->end_offset); __put_user_error(0, &end->magic, err); __put_user_error(0, &end->size, err); } return err; } static int get_sigframe(struct rt_sigframe_user_layout *user, struct ksignal *ksig, struct pt_regs *regs) { unsigned long sp, sp_top; int err; init_user_layout(user); err = setup_sigframe_layout(user, false); if (err) return err; sp = sp_top = sigsp(regs->sp, ksig); sp = round_down(sp - sizeof(struct frame_record), 16); user->next_frame = (struct frame_record __user *)sp; sp = round_down(sp, 16) - sigframe_size(user); user->sigframe = (struct rt_sigframe __user *)sp; /* * Check that we can actually write to the signal frame. */ if (!access_ok(user->sigframe, sp_top - sp)) return -EFAULT; return 0; } static void setup_return(struct pt_regs *regs, struct k_sigaction *ka, struct rt_sigframe_user_layout *user, int usig) { __sigrestore_t sigtramp; regs->regs[0] = usig; regs->sp = (unsigned long)user->sigframe; regs->regs[29] = (unsigned long)&user->next_frame->fp; regs->pc = (unsigned long)ka->sa.sa_handler; /* * Signal delivery is a (wacky) indirect function call in * userspace, so simulate the same setting of BTYPE as a BLR * <register containing the signal handler entry point>. * Signal delivery to a location in a PROT_BTI guarded page * that is not a function entry point will now trigger a * SIGILL in userspace. * * If the signal handler entry point is not in a PROT_BTI * guarded page, this is harmless. */ if (system_supports_bti()) { regs->pstate &= ~PSR_BTYPE_MASK; regs->pstate |= PSR_BTYPE_C; } /* TCO (Tag Check Override) always cleared for signal handlers */ regs->pstate &= ~PSR_TCO_BIT; /* Signal handlers are invoked with ZA and streaming mode disabled */ if (system_supports_sme()) { /* * If we were in streaming mode the saved register * state was SVE but we will exit SM and use the * FPSIMD register state - flush the saved FPSIMD * register state in case it gets loaded. */ if (current->thread.svcr & SVCR_SM_MASK) { memset(¤t->thread.uw.fpsimd_state, 0, sizeof(current->thread.uw.fpsimd_state)); current->thread.fp_type = FP_STATE_FPSIMD; } current->thread.svcr &= ~(SVCR_ZA_MASK | SVCR_SM_MASK); sme_smstop(); } if (ka->sa.sa_flags & SA_RESTORER) sigtramp = ka->sa.sa_restorer; else sigtramp = VDSO_SYMBOL(current->mm->context.vdso, sigtramp); regs->regs[30] = (unsigned long)sigtramp; } static int setup_rt_frame(int usig, struct ksignal *ksig, sigset_t *set, struct pt_regs *regs) { struct rt_sigframe_user_layout user; struct rt_sigframe __user *frame; int err = 0; fpsimd_signal_preserve_current_state(); if (get_sigframe(&user, ksig, regs)) return 1; frame = user.sigframe; __put_user_error(0, &frame->uc.uc_flags, err); __put_user_error(NULL, &frame->uc.uc_link, err); err |= __save_altstack(&frame->uc.uc_stack, regs->sp); err |= setup_sigframe(&user, regs, set); if (err == 0) { setup_return(regs, &ksig->ka, &user, usig); if (ksig->ka.sa.sa_flags & SA_SIGINFO) { err |= copy_siginfo_to_user(&frame->info, &ksig->info); regs->regs[1] = (unsigned long)&frame->info; regs->regs[2] = (unsigned long)&frame->uc; } } return err; } static void setup_restart_syscall(struct pt_regs *regs) { if (is_compat_task()) compat_setup_restart_syscall(regs); else regs->regs[8] = __NR_restart_syscall; } /* * OK, we're invoking a handler */ static void handle_signal(struct ksignal *ksig, struct pt_regs *regs) { sigset_t *oldset = sigmask_to_save(); int usig = ksig->sig; int ret; rseq_signal_deliver(ksig, regs); /* * Set up the stack frame */ if (is_compat_task()) { if (ksig->ka.sa.sa_flags & SA_SIGINFO) ret = compat_setup_rt_frame(usig, ksig, oldset, regs); else ret = compat_setup_frame(usig, ksig, oldset, regs); } else { ret = setup_rt_frame(usig, ksig, oldset, regs); } /* * Check that the resulting registers are actually sane. */ ret |= !valid_user_regs(®s->user_regs, current); /* Step into the signal handler if we are stepping */ signal_setup_done(ret, ksig, test_thread_flag(TIF_SINGLESTEP)); } /* * Note that 'init' is a special process: it doesn't get signals it doesn't * want to handle. Thus you cannot kill init even with a SIGKILL even by * mistake. * * Note that we go through the signals twice: once to check the signals that * the kernel can handle, and then we build all the user-level signal handling * stack-frames in one go after that. */ void do_signal(struct pt_regs *regs) { unsigned long continue_addr = 0, restart_addr = 0; int retval = 0; struct ksignal ksig; bool syscall = in_syscall(regs); /* * If we were from a system call, check for system call restarting... */ if (syscall) { continue_addr = regs->pc; restart_addr = continue_addr - (compat_thumb_mode(regs) ? 2 : 4); retval = regs->regs[0]; /* * Avoid additional syscall restarting via ret_to_user. */ forget_syscall(regs); /* * Prepare for system call restart. We do this here so that a * debugger will see the already changed PC. */ switch (retval) { case -ERESTARTNOHAND: case -ERESTARTSYS: case -ERESTARTNOINTR: case -ERESTART_RESTARTBLOCK: regs->regs[0] = regs->orig_x0; regs->pc = restart_addr; break; } } /* * Get the signal to deliver. When running under ptrace, at this point * the debugger may change all of our registers. */ if (get_signal(&ksig)) { /* * Depending on the signal settings, we may need to revert the * decision to restart the system call, but skip this if a * debugger has chosen to restart at a different PC. */ if (regs->pc == restart_addr && (retval == -ERESTARTNOHAND || retval == -ERESTART_RESTARTBLOCK || (retval == -ERESTARTSYS && !(ksig.ka.sa.sa_flags & SA_RESTART)))) { syscall_set_return_value(current, regs, -EINTR, 0); regs->pc = continue_addr; } handle_signal(&ksig, regs); return; } /* * Handle restarting a different system call. As above, if a debugger * has chosen to restart at a different PC, ignore the restart. */ if (syscall && regs->pc == restart_addr) { if (retval == -ERESTART_RESTARTBLOCK) setup_restart_syscall(regs); user_rewind_single_step(current); } restore_saved_sigmask(); } unsigned long __ro_after_init signal_minsigstksz; /* * Determine the stack space required for guaranteed signal devliery. * This function is used to populate AT_MINSIGSTKSZ at process startup. * cpufeatures setup is assumed to be complete. */ void __init minsigstksz_setup(void) { struct rt_sigframe_user_layout user; init_user_layout(&user); /* * If this fails, SIGFRAME_MAXSZ needs to be enlarged. It won't * be big enough, but it's our best guess: */ if (WARN_ON(setup_sigframe_layout(&user, true))) return; signal_minsigstksz = sigframe_size(&user) + round_up(sizeof(struct frame_record), 16) + 16; /* max alignment padding */ } /* * Compile-time assertions for siginfo_t offsets. Check NSIG* as well, as * changes likely come with new fields that should be added below. */ static_assert(NSIGILL == 11); static_assert(NSIGFPE == 15); static_assert(NSIGSEGV == 10); static_assert(NSIGBUS == 5); static_assert(NSIGTRAP == 6); static_assert(NSIGCHLD == 6); static_assert(NSIGSYS == 2); static_assert(sizeof(siginfo_t) == 128); static_assert(__alignof__(siginfo_t) == 8); static_assert(offsetof(siginfo_t, si_signo) == 0x00); static_assert(offsetof(siginfo_t, si_errno) == 0x04); static_assert(offsetof(siginfo_t, si_code) == 0x08); static_assert(offsetof(siginfo_t, si_pid) == 0x10); static_assert(offsetof(siginfo_t, si_uid) == 0x14); static_assert(offsetof(siginfo_t, si_tid) == 0x10); static_assert(offsetof(siginfo_t, si_overrun) == 0x14); static_assert(offsetof(siginfo_t, si_status) == 0x18); static_assert(offsetof(siginfo_t, si_utime) == 0x20); static_assert(offsetof(siginfo_t, si_stime) == 0x28); static_assert(offsetof(siginfo_t, si_value) == 0x18); static_assert(offsetof(siginfo_t, si_int) == 0x18); static_assert(offsetof(siginfo_t, si_ptr) == 0x18); static_assert(offsetof(siginfo_t, si_addr) == 0x10); static_assert(offsetof(siginfo_t, si_addr_lsb) == 0x18); static_assert(offsetof(siginfo_t, si_lower) == 0x20); static_assert(offsetof(siginfo_t, si_upper) == 0x28); static_assert(offsetof(siginfo_t, si_pkey) == 0x20); static_assert(offsetof(siginfo_t, si_perf_data) == 0x18); static_assert(offsetof(siginfo_t, si_perf_type) == 0x20); static_assert(offsetof(siginfo_t, si_perf_flags) == 0x24); static_assert(offsetof(siginfo_t, si_band) == 0x10); static_assert(offsetof(siginfo_t, si_fd) == 0x18); static_assert(offsetof(siginfo_t, si_call_addr) == 0x10); static_assert(offsetof(siginfo_t, si_syscall) == 0x18); static_assert(offsetof(siginfo_t, si_arch) == 0x1c); |
| 33 156 33 33 33 33 32 33 33 33 33 33 32 150 150 150 150 150 150 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2001 Momchil Velikov * Portions Copyright (C) 2001 Christoph Hellwig * Copyright (C) 2005 SGI, Christoph Lameter * Copyright (C) 2006 Nick Piggin * Copyright (C) 2012 Konstantin Khlebnikov * Copyright (C) 2016 Intel, Matthew Wilcox * Copyright (C) 2016 Intel, Ross Zwisler */ #include <linux/bitmap.h> #include <linux/bitops.h> #include <linux/bug.h> #include <linux/cpu.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/idr.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kmemleak.h> #include <linux/percpu.h> #include <linux/preempt.h> /* in_interrupt() */ #include <linux/radix-tree.h> #include <linux/rcupdate.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/xarray.h> #include "radix-tree.h" /* * Radix tree node cache. */ struct kmem_cache *radix_tree_node_cachep; /* * The radix tree is variable-height, so an insert operation not only has * to build the branch to its corresponding item, it also has to build the * branch to existing items if the size has to be increased (by * radix_tree_extend). * * The worst case is a zero height tree with just a single item at index 0, * and then inserting an item at index ULONG_MAX. This requires 2 new branches * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared. * Hence: */ #define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1) /* * The IDR does not have to be as high as the radix tree since it uses * signed integers, not unsigned longs. */ #define IDR_INDEX_BITS (8 /* CHAR_BIT */ * sizeof(int) - 1) #define IDR_MAX_PATH (DIV_ROUND_UP(IDR_INDEX_BITS, \ RADIX_TREE_MAP_SHIFT)) #define IDR_PRELOAD_SIZE (IDR_MAX_PATH * 2 - 1) /* * Per-cpu pool of preloaded nodes */ DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { .lock = INIT_LOCAL_LOCK(lock), }; EXPORT_PER_CPU_SYMBOL_GPL(radix_tree_preloads); static inline struct radix_tree_node *entry_to_node(void *ptr) { return (void *)((unsigned long)ptr & ~RADIX_TREE_INTERNAL_NODE); } static inline void *node_to_entry(void *ptr) { return (void *)((unsigned long)ptr | RADIX_TREE_INTERNAL_NODE); } #define RADIX_TREE_RETRY XA_RETRY_ENTRY static inline unsigned long get_slot_offset(const struct radix_tree_node *parent, void __rcu **slot) { return parent ? slot - parent->slots : 0; } static unsigned int radix_tree_descend(const struct radix_tree_node *parent, struct radix_tree_node **nodep, unsigned long index) { unsigned int offset = (index >> parent->shift) & RADIX_TREE_MAP_MASK; void __rcu **entry = rcu_dereference_raw(parent->slots[offset]); *nodep = (void *)entry; return offset; } static inline gfp_t root_gfp_mask(const struct radix_tree_root *root) { return root->xa_flags & (__GFP_BITS_MASK & ~GFP_ZONEMASK); } static inline void tag_set(struct radix_tree_node *node, unsigned int tag, int offset) { __set_bit(offset, node->tags[tag]); } static inline void tag_clear(struct radix_tree_node *node, unsigned int tag, int offset) { __clear_bit(offset, node->tags[tag]); } static inline int tag_get(const struct radix_tree_node *node, unsigned int tag, int offset) { return test_bit(offset, node->tags[tag]); } static inline void root_tag_set(struct radix_tree_root *root, unsigned tag) { root->xa_flags |= (__force gfp_t)(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear(struct radix_tree_root *root, unsigned tag) { root->xa_flags &= (__force gfp_t)~(1 << (tag + ROOT_TAG_SHIFT)); } static inline void root_tag_clear_all(struct radix_tree_root *root) { root->xa_flags &= (__force gfp_t)((1 << ROOT_TAG_SHIFT) - 1); } static inline int root_tag_get(const struct radix_tree_root *root, unsigned tag) { return (__force int)root->xa_flags & (1 << (tag + ROOT_TAG_SHIFT)); } static inline unsigned root_tags_get(const struct radix_tree_root *root) { return (__force unsigned)root->xa_flags >> ROOT_TAG_SHIFT; } static inline bool is_idr(const struct radix_tree_root *root) { return !!(root->xa_flags & ROOT_IS_IDR); } /* * Returns 1 if any slot in the node has this tag set. * Otherwise returns 0. */ static inline int any_tag_set(const struct radix_tree_node *node, unsigned int tag) { unsigned idx; for (idx = 0; idx < RADIX_TREE_TAG_LONGS; idx++) { if (node->tags[tag][idx]) return 1; } return 0; } static inline void all_tag_set(struct radix_tree_node *node, unsigned int tag) { bitmap_fill(node->tags[tag], RADIX_TREE_MAP_SIZE); } /** * radix_tree_find_next_bit - find the next set bit in a memory region * * @node: where to begin the search * @tag: the tag index * @offset: the bitnumber to start searching at * * Unrollable variant of find_next_bit() for constant size arrays. * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero. * Returns next bit offset, or size if nothing found. */ static __always_inline unsigned long radix_tree_find_next_bit(struct radix_tree_node *node, unsigned int tag, unsigned long offset) { const unsigned long *addr = node->tags[tag]; if (offset < RADIX_TREE_MAP_SIZE) { unsigned long tmp; addr += offset / BITS_PER_LONG; tmp = *addr >> (offset % BITS_PER_LONG); if (tmp) return __ffs(tmp) + offset; offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1); while (offset < RADIX_TREE_MAP_SIZE) { tmp = *++addr; if (tmp) return __ffs(tmp) + offset; offset += BITS_PER_LONG; } } return RADIX_TREE_MAP_SIZE; } static unsigned int iter_offset(const struct radix_tree_iter *iter) { return iter->index & RADIX_TREE_MAP_MASK; } /* * The maximum index which can be stored in a radix tree */ static inline unsigned long shift_maxindex(unsigned int shift) { return (RADIX_TREE_MAP_SIZE << shift) - 1; } static inline unsigned long node_maxindex(const struct radix_tree_node *node) { return shift_maxindex(node->shift); } static unsigned long next_index(unsigned long index, const struct radix_tree_node *node, unsigned long offset) { return (index & ~node_maxindex(node)) + (offset << node->shift); } /* * This assumes that the caller has performed appropriate preallocation, and * that the caller has pinned this thread of control to the current CPU. */ static struct radix_tree_node * radix_tree_node_alloc(gfp_t gfp_mask, struct radix_tree_node *parent, struct radix_tree_root *root, unsigned int shift, unsigned int offset, unsigned int count, unsigned int nr_values) { struct radix_tree_node *ret = NULL; /* * Preload code isn't irq safe and it doesn't make sense to use * preloading during an interrupt anyway as all the allocations have * to be atomic. So just do normal allocation when in interrupt. */ if (!gfpflags_allow_blocking(gfp_mask) && !in_interrupt()) { struct radix_tree_preload *rtp; /* * Even if the caller has preloaded, try to allocate from the * cache first for the new node to get accounted to the memory * cgroup. */ ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask | __GFP_NOWARN); if (ret) goto out; /* * Provided the caller has preloaded here, we will always * succeed in getting a node here (and never reach * kmem_cache_alloc) */ rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr) { ret = rtp->nodes; rtp->nodes = ret->parent; rtp->nr--; } /* * Update the allocation stack trace as this is more useful * for debugging. */ kmemleak_update_trace(ret); goto out; } ret = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); out: BUG_ON(radix_tree_is_internal_node(ret)); if (ret) { ret->shift = shift; ret->offset = offset; ret->count = count; ret->nr_values = nr_values; ret->parent = parent; ret->array = root; } return ret; } void radix_tree_node_rcu_free(struct rcu_head *head) { struct radix_tree_node *node = container_of(head, struct radix_tree_node, rcu_head); /* * Must only free zeroed nodes into the slab. We can be left with * non-NULL entries by radix_tree_free_nodes, so clear the entries * and tags here. */ memset(node->slots, 0, sizeof(node->slots)); memset(node->tags, 0, sizeof(node->tags)); INIT_LIST_HEAD(&node->private_list); kmem_cache_free(radix_tree_node_cachep, node); } static inline void radix_tree_node_free(struct radix_tree_node *node) { call_rcu(&node->rcu_head, radix_tree_node_rcu_free); } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ static __must_check int __radix_tree_preload(gfp_t gfp_mask, unsigned nr) { struct radix_tree_preload *rtp; struct radix_tree_node *node; int ret = -ENOMEM; /* * Nodes preloaded by one cgroup can be used by another cgroup, so * they should never be accounted to any particular memory cgroup. */ gfp_mask &= ~__GFP_ACCOUNT; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); while (rtp->nr < nr) { local_unlock(&radix_tree_preloads.lock); node = kmem_cache_alloc(radix_tree_node_cachep, gfp_mask); if (node == NULL) goto out; local_lock(&radix_tree_preloads.lock); rtp = this_cpu_ptr(&radix_tree_preloads); if (rtp->nr < nr) { node->parent = rtp->nodes; rtp->nodes = node; rtp->nr++; } else { kmem_cache_free(radix_tree_node_cachep, node); } } ret = 0; out: return ret; } /* * Load up this CPU's radix_tree_node buffer with sufficient objects to * ensure that the addition of a single element in the tree cannot fail. On * success, return zero, with preemption disabled. On error, return -ENOMEM * with preemption not disabled. * * To make use of this facility, the radix tree must be initialised without * __GFP_DIRECT_RECLAIM being passed to INIT_RADIX_TREE(). */ int radix_tree_preload(gfp_t gfp_mask) { /* Warn on non-sensical use... */ WARN_ON_ONCE(!gfpflags_allow_blocking(gfp_mask)); return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); } EXPORT_SYMBOL(radix_tree_preload); /* * The same as above function, except we don't guarantee preloading happens. * We do it, if we decide it helps. On success, return zero with preemption * disabled. On error, return -ENOMEM with preemption not disabled. */ int radix_tree_maybe_preload(gfp_t gfp_mask) { if (gfpflags_allow_blocking(gfp_mask)) return __radix_tree_preload(gfp_mask, RADIX_TREE_PRELOAD_SIZE); /* Preloading doesn't help anything with this gfp mask, skip it */ local_lock(&radix_tree_preloads.lock); return 0; } EXPORT_SYMBOL(radix_tree_maybe_preload); static unsigned radix_tree_load_root(const struct radix_tree_root *root, struct radix_tree_node **nodep, unsigned long *maxindex) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); *nodep = node; if (likely(radix_tree_is_internal_node(node))) { node = entry_to_node(node); *maxindex = node_maxindex(node); return node->shift + RADIX_TREE_MAP_SHIFT; } *maxindex = 0; return 0; } /* * Extend a radix tree so it can store key @index. */ static int radix_tree_extend(struct radix_tree_root *root, gfp_t gfp, unsigned long index, unsigned int shift) { void *entry; unsigned int maxshift; int tag; /* Figure out what the shift should be. */ maxshift = shift; while (index > shift_maxindex(maxshift)) maxshift += RADIX_TREE_MAP_SHIFT; entry = rcu_dereference_raw(root->xa_head); if (!entry && (!is_idr(root) || root_tag_get(root, IDR_FREE))) goto out; do { struct radix_tree_node *node = radix_tree_node_alloc(gfp, NULL, root, shift, 0, 1, 0); if (!node) return -ENOMEM; if (is_idr(root)) { all_tag_set(node, IDR_FREE); if (!root_tag_get(root, IDR_FREE)) { tag_clear(node, IDR_FREE, 0); root_tag_set(root, IDR_FREE); } } else { /* Propagate the aggregated tag info to the new child */ for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) { if (root_tag_get(root, tag)) tag_set(node, tag, 0); } } BUG_ON(shift > BITS_PER_LONG); if (radix_tree_is_internal_node(entry)) { entry_to_node(entry)->parent = node; } else if (xa_is_value(entry)) { /* Moving a value entry root->xa_head to a node */ node->nr_values = 1; } /* * entry was already in the radix tree, so we do not need * rcu_assign_pointer here */ node->slots[0] = (void __rcu *)entry; entry = node_to_entry(node); rcu_assign_pointer(root->xa_head, entry); shift += RADIX_TREE_MAP_SHIFT; } while (shift <= maxshift); out: return maxshift + RADIX_TREE_MAP_SHIFT; } /** * radix_tree_shrink - shrink radix tree to minimum height * @root: radix tree root */ static inline bool radix_tree_shrink(struct radix_tree_root *root) { bool shrunk = false; for (;;) { struct radix_tree_node *node = rcu_dereference_raw(root->xa_head); struct radix_tree_node *child; if (!radix_tree_is_internal_node(node)) break; node = entry_to_node(node); /* * The candidate node has more than one child, or its child * is not at the leftmost slot, we cannot shrink. */ if (node->count != 1) break; child = rcu_dereference_raw(node->slots[0]); if (!child) break; /* * For an IDR, we must not shrink entry 0 into the root in * case somebody calls idr_replace() with a pointer that * appears to be an internal entry */ if (!node->shift && is_idr(root)) break; if (radix_tree_is_internal_node(child)) entry_to_node(child)->parent = NULL; /* * We don't need rcu_assign_pointer(), since we are simply * moving the node from one part of the tree to another: if it * was safe to dereference the old pointer to it * (node->slots[0]), it will be safe to dereference the new * one (root->xa_head) as far as dependent read barriers go. */ root->xa_head = (void __rcu *)child; if (is_idr(root) && !tag_get(node, IDR_FREE, 0)) root_tag_clear(root, IDR_FREE); /* * We have a dilemma here. The node's slot[0] must not be * NULLed in case there are concurrent lookups expecting to * find the item. However if this was a bottom-level node, * then it may be subject to the slot pointer being visible * to callers dereferencing it. If item corresponding to * slot[0] is subsequently deleted, these callers would expect * their slot to become empty sooner or later. * * For example, lockless pagecache will look up a slot, deref * the page pointer, and if the page has 0 refcount it means it * was concurrently deleted from pagecache so try the deref * again. Fortunately there is already a requirement for logic * to retry the entire slot lookup -- the indirect pointer * problem (replacing direct root node with an indirect pointer * also results in a stale slot). So tag the slot as indirect * to force callers to retry. */ node->count = 0; if (!radix_tree_is_internal_node(child)) { node->slots[0] = (void __rcu *)RADIX_TREE_RETRY; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); shrunk = true; } return shrunk; } static bool delete_node(struct radix_tree_root *root, struct radix_tree_node *node) { bool deleted = false; do { struct radix_tree_node *parent; if (node->count) { if (node_to_entry(node) == rcu_dereference_raw(root->xa_head)) deleted |= radix_tree_shrink(root); return deleted; } parent = node->parent; if (parent) { parent->slots[node->offset] = NULL; parent->count--; } else { /* * Shouldn't the tags already have all been cleared * by the caller? */ if (!is_idr(root)) root_tag_clear_all(root); root->xa_head = NULL; } WARN_ON_ONCE(!list_empty(&node->private_list)); radix_tree_node_free(node); deleted = true; node = parent; } while (node); return deleted; } /** * __radix_tree_create - create a slot in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Create, if necessary, and return the node and slot for an item * at position @index in the radix tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. * * Returns -ENOMEM, or 0 for success. */ static int __radix_tree_create(struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex; unsigned int shift, offset = 0; unsigned long max = index; gfp_t gfp = root_gfp_mask(root); shift = radix_tree_load_root(root, &child, &maxindex); /* Make sure the tree is high enough. */ if (max > maxindex) { int error = radix_tree_extend(root, gfp, max, shift); if (error < 0) return error; shift = error; child = rcu_dereference_raw(root->xa_head); } while (shift > 0) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return -ENOMEM; rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; /* Go a level down */ node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); slot = &node->slots[offset]; } if (nodep) *nodep = node; if (slotp) *slotp = slot; return 0; } /* * Free any nodes below this node. The tree is presumed to not need * shrinking, and any user data in the tree is presumed to not need a * destructor called on it. If we need to add a destructor, we can * add that functionality later. Note that we may not clear tags or * slots from the tree as an RCU walker may still have a pointer into * this subtree. We could replace the entries with RADIX_TREE_RETRY, * but we'll still have to clear those in rcu_free. */ static void radix_tree_free_nodes(struct radix_tree_node *node) { unsigned offset = 0; struct radix_tree_node *child = entry_to_node(node); for (;;) { void *entry = rcu_dereference_raw(child->slots[offset]); if (xa_is_node(entry) && child->shift) { child = entry_to_node(entry); offset = 0; continue; } offset++; while (offset == RADIX_TREE_MAP_SIZE) { struct radix_tree_node *old = child; offset = child->offset + 1; child = child->parent; WARN_ON_ONCE(!list_empty(&old->private_list)); radix_tree_node_free(old); if (old == entry_to_node(node)) return; } } } static inline int insert_entries(struct radix_tree_node *node, void __rcu **slot, void *item) { if (*slot) return -EEXIST; rcu_assign_pointer(*slot, item); if (node) { node->count++; if (xa_is_value(item)) node->nr_values++; } return 1; } /** * radix_tree_insert - insert into a radix tree * @root: radix tree root * @index: index key * @item: item to insert * * Insert an item into the radix tree at position @index. */ int radix_tree_insert(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node; void __rcu **slot; int error; BUG_ON(radix_tree_is_internal_node(item)); error = __radix_tree_create(root, index, &node, &slot); if (error) return error; error = insert_entries(node, slot, item); if (error < 0) return error; if (node) { unsigned offset = get_slot_offset(node, slot); BUG_ON(tag_get(node, 0, offset)); BUG_ON(tag_get(node, 1, offset)); BUG_ON(tag_get(node, 2, offset)); } else { BUG_ON(root_tags_get(root)); } return 0; } EXPORT_SYMBOL(radix_tree_insert); /** * __radix_tree_lookup - lookup an item in a radix tree * @root: radix tree root * @index: index key * @nodep: returns node * @slotp: returns slot * * Lookup and return the item at position @index in the radix * tree @root. * * Until there is more than one item in the tree, no nodes are * allocated and @root->xa_head is used as a direct slot instead of * pointing to a node, in which case *@nodep will be NULL. */ void *__radix_tree_lookup(const struct radix_tree_root *root, unsigned long index, struct radix_tree_node **nodep, void __rcu ***slotp) { struct radix_tree_node *node, *parent; unsigned long maxindex; void __rcu **slot; restart: parent = NULL; slot = (void __rcu **)&root->xa_head; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); slot = parent->slots + offset; if (node == RADIX_TREE_RETRY) goto restart; if (parent->shift == 0) break; } if (nodep) *nodep = parent; if (slotp) *slotp = slot; return node; } /** * radix_tree_lookup_slot - lookup a slot in a radix tree * @root: radix tree root * @index: index key * * Returns: the slot corresponding to the position @index in the * radix tree @root. This is useful for update-if-exists operations. * * This function can be called under rcu_read_lock iff the slot is not * modified by radix_tree_replace_slot, otherwise it must be called * exclusive from other writers. Any dereference of the slot must be done * using radix_tree_deref_slot. */ void __rcu **radix_tree_lookup_slot(const struct radix_tree_root *root, unsigned long index) { void __rcu **slot; if (!__radix_tree_lookup(root, index, NULL, &slot)) return NULL; return slot; } EXPORT_SYMBOL(radix_tree_lookup_slot); /** * radix_tree_lookup - perform lookup operation on a radix tree * @root: radix tree root * @index: index key * * Lookup the item at the position @index in the radix tree @root. * * This function can be called under rcu_read_lock, however the caller * must manage lifetimes of leaf nodes (eg. RCU may also be used to free * them safely). No RCU barriers are required to access or modify the * returned item, however. */ void *radix_tree_lookup(const struct radix_tree_root *root, unsigned long index) { return __radix_tree_lookup(root, index, NULL, NULL); } EXPORT_SYMBOL(radix_tree_lookup); static void replace_slot(void __rcu **slot, void *item, struct radix_tree_node *node, int count, int values) { if (node && (count || values)) { node->count += count; node->nr_values += values; } rcu_assign_pointer(*slot, item); } static bool node_tag_get(const struct radix_tree_root *root, const struct radix_tree_node *node, unsigned int tag, unsigned int offset) { if (node) return tag_get(node, tag, offset); return root_tag_get(root, tag); } /* * IDR users want to be able to store NULL in the tree, so if the slot isn't * free, don't adjust the count, even if it's transitioning between NULL and * non-NULL. For the IDA, we mark slots as being IDR_FREE while they still * have empty bits, but it only stores NULL in slots when they're being * deleted. */ static int calculate_count(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item, void *old) { if (is_idr(root)) { unsigned offset = get_slot_offset(node, slot); bool free = node_tag_get(root, node, IDR_FREE, offset); if (!free) return 0; if (!old) return 1; } return !!item - !!old; } /** * __radix_tree_replace - replace item in a slot * @root: radix tree root * @node: pointer to tree node * @slot: pointer to slot in @node * @item: new item to store in the slot. * * For use with __radix_tree_lookup(). Caller must hold tree write locked * across slot lookup and replacement. */ void __radix_tree_replace(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot, void *item) { void *old = rcu_dereference_raw(*slot); int values = !!xa_is_value(item) - !!xa_is_value(old); int count = calculate_count(root, node, slot, item, old); /* * This function supports replacing value entries and * deleting entries, but that needs accounting against the * node unless the slot is root->xa_head. */ WARN_ON_ONCE(!node && (slot != (void __rcu **)&root->xa_head) && (count || values)); replace_slot(slot, item, node, count, values); if (!node) return; delete_node(root, node); } /** * radix_tree_replace_slot - replace item in a slot * @root: radix tree root * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_lookup_slot() and * radix_tree_gang_lookup_tag_slot(). Caller must hold tree write locked * across slot lookup and replacement. * * NOTE: This cannot be used to switch between non-entries (empty slots), * regular entries, and value entries, as that requires accounting * inside the radix tree node. When switching from one type of entry or * deleting, use __radix_tree_lookup() and __radix_tree_replace() or * radix_tree_iter_replace(). */ void radix_tree_replace_slot(struct radix_tree_root *root, void __rcu **slot, void *item) { __radix_tree_replace(root, NULL, slot, item); } EXPORT_SYMBOL(radix_tree_replace_slot); /** * radix_tree_iter_replace - replace item in a slot * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * @item: new item to store in the slot. * * For use with radix_tree_for_each_slot(). * Caller must hold tree write locked. */ void radix_tree_iter_replace(struct radix_tree_root *root, const struct radix_tree_iter *iter, void __rcu **slot, void *item) { __radix_tree_replace(root, iter->node, slot, item); } static void node_tag_set(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (tag_get(node, tag, offset)) return; tag_set(node, tag, offset); offset = node->offset; node = node->parent; } if (!root_tag_get(root, tag)) root_tag_set(root, tag); } /** * radix_tree_tag_set - set a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Set the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. From * the root all the way down to the leaf node. * * Returns the address of the tagged item. Setting a tag on a not-present * item is a bug. */ void *radix_tree_tag_set(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; radix_tree_load_root(root, &node, &maxindex); BUG_ON(index > maxindex); while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); BUG_ON(!node); if (!tag_get(parent, tag, offset)) tag_set(parent, tag, offset); } /* set the root's tag bit */ if (!root_tag_get(root, tag)) root_tag_set(root, tag); return node; } EXPORT_SYMBOL(radix_tree_tag_set); static void node_tag_clear(struct radix_tree_root *root, struct radix_tree_node *node, unsigned int tag, unsigned int offset) { while (node) { if (!tag_get(node, tag, offset)) return; tag_clear(node, tag, offset); if (any_tag_set(node, tag)) return; offset = node->offset; node = node->parent; } /* clear the root's tag bit */ if (root_tag_get(root, tag)) root_tag_clear(root, tag); } /** * radix_tree_tag_clear - clear a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index * * Clear the search tag (which must be < RADIX_TREE_MAX_TAGS) * corresponding to @index in the radix tree. If this causes * the leaf node to have no tags set then clear the tag in the * next-to-leaf node, etc. * * Returns the address of the tagged item on success, else NULL. ie: * has the same return value and semantics as radix_tree_lookup(). */ void *radix_tree_tag_clear(struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; int offset = 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return NULL; parent = NULL; while (radix_tree_is_internal_node(node)) { parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); } if (node) node_tag_clear(root, parent, tag, offset); return node; } EXPORT_SYMBOL(radix_tree_tag_clear); /** * radix_tree_iter_tag_clear - clear a tag on the current iterator entry * @root: radix tree root * @iter: iterator state * @tag: tag to clear */ void radix_tree_iter_tag_clear(struct radix_tree_root *root, const struct radix_tree_iter *iter, unsigned int tag) { node_tag_clear(root, iter->node, tag, iter_offset(iter)); } /** * radix_tree_tag_get - get a tag on a radix tree node * @root: radix tree root * @index: index key * @tag: tag index (< RADIX_TREE_MAX_TAGS) * * Return values: * * 0: tag not present or not set * 1: tag set * * Note that the return value of this function may not be relied on, even if * the RCU lock is held, unless tag modification and node deletion are excluded * from concurrency. */ int radix_tree_tag_get(const struct radix_tree_root *root, unsigned long index, unsigned int tag) { struct radix_tree_node *node, *parent; unsigned long maxindex; if (!root_tag_get(root, tag)) return 0; radix_tree_load_root(root, &node, &maxindex); if (index > maxindex) return 0; while (radix_tree_is_internal_node(node)) { unsigned offset; parent = entry_to_node(node); offset = radix_tree_descend(parent, &node, index); if (!tag_get(parent, tag, offset)) return 0; if (node == RADIX_TREE_RETRY) break; } return 1; } EXPORT_SYMBOL(radix_tree_tag_get); /* Construct iter->tags bit-mask from node->tags[tag] array */ static void set_iter_tags(struct radix_tree_iter *iter, struct radix_tree_node *node, unsigned offset, unsigned tag) { unsigned tag_long = offset / BITS_PER_LONG; unsigned tag_bit = offset % BITS_PER_LONG; if (!node) { iter->tags = 1; return; } iter->tags = node->tags[tag][tag_long] >> tag_bit; /* This never happens if RADIX_TREE_TAG_LONGS == 1 */ if (tag_long < RADIX_TREE_TAG_LONGS - 1) { /* Pick tags from next element */ if (tag_bit) iter->tags |= node->tags[tag][tag_long + 1] << (BITS_PER_LONG - tag_bit); /* Clip chunk size, here only BITS_PER_LONG tags */ iter->next_index = __radix_tree_iter_add(iter, BITS_PER_LONG); } } void __rcu **radix_tree_iter_resume(void __rcu **slot, struct radix_tree_iter *iter) { iter->index = __radix_tree_iter_add(iter, 1); iter->next_index = iter->index; iter->tags = 0; return NULL; } EXPORT_SYMBOL(radix_tree_iter_resume); /** * radix_tree_next_chunk - find next chunk of slots for iteration * * @root: radix tree root * @iter: iterator state * @flags: RADIX_TREE_ITER_* flags and tag index * Returns: pointer to chunk first slot, or NULL if iteration is over */ void __rcu **radix_tree_next_chunk(const struct radix_tree_root *root, struct radix_tree_iter *iter, unsigned flags) { unsigned tag = flags & RADIX_TREE_ITER_TAG_MASK; struct radix_tree_node *node, *child; unsigned long index, offset, maxindex; if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag)) return NULL; /* * Catch next_index overflow after ~0UL. iter->index never overflows * during iterating; it can be zero only at the beginning. * And we cannot overflow iter->next_index in a single step, * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG. * * This condition also used by radix_tree_next_slot() to stop * contiguous iterating, and forbid switching to the next chunk. */ index = iter->next_index; if (!index && iter->index) return NULL; restart: radix_tree_load_root(root, &child, &maxindex); if (index > maxindex) return NULL; if (!child) return NULL; if (!radix_tree_is_internal_node(child)) { /* Single-slot tree */ iter->index = index; iter->next_index = maxindex + 1; iter->tags = 1; iter->node = NULL; return (void __rcu **)&root->xa_head; } do { node = entry_to_node(child); offset = radix_tree_descend(node, &child, index); if ((flags & RADIX_TREE_ITER_TAGGED) ? !tag_get(node, tag, offset) : !child) { /* Hole detected */ if (flags & RADIX_TREE_ITER_CONTIG) return NULL; if (flags & RADIX_TREE_ITER_TAGGED) offset = radix_tree_find_next_bit(node, tag, offset + 1); else while (++offset < RADIX_TREE_MAP_SIZE) { void *slot = rcu_dereference_raw( node->slots[offset]); if (slot) break; } index &= ~node_maxindex(node); index += offset << node->shift; /* Overflow after ~0UL */ if (!index) return NULL; if (offset == RADIX_TREE_MAP_SIZE) goto restart; child = rcu_dereference_raw(node->slots[offset]); } if (!child) goto restart; if (child == RADIX_TREE_RETRY) break; } while (node->shift && radix_tree_is_internal_node(child)); /* Update the iterator state */ iter->index = (index &~ node_maxindex(node)) | offset; iter->next_index = (index | node_maxindex(node)) + 1; iter->node = node; if (flags & RADIX_TREE_ITER_TAGGED) set_iter_tags(iter, node, offset, tag); return node->slots + offset; } EXPORT_SYMBOL(radix_tree_next_chunk); /** * radix_tree_gang_lookup - perform multiple lookup on a radix tree * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * * Performs an index-ascending scan of the tree for present items. Places * them at *@results and returns the number of items which were placed at * *@results. * * The implementation is naive. * * Like radix_tree_lookup, radix_tree_gang_lookup may be called under * rcu_read_lock. In this case, rather than the returned results being * an atomic snapshot of the tree at a single point in time, the * semantics of an RCU protected gang lookup are as though multiple * radix_tree_lookups have been issued in individual locks, and results * stored in 'results'. */ unsigned int radix_tree_gang_lookup(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_slot(slot, root, &iter, first_index) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup); /** * radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree * based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the items at *@results and * returns the number of items which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag(const struct radix_tree_root *root, void **results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = rcu_dereference_raw(*slot); if (!results[ret]) continue; if (radix_tree_is_internal_node(results[ret])) { slot = radix_tree_iter_retry(&iter); continue; } if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag); /** * radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a * radix tree based on a tag * @root: radix tree root * @results: where the results of the lookup are placed * @first_index: start the lookup from this key * @max_items: place up to this many items at *results * @tag: the tag index (< RADIX_TREE_MAX_TAGS) * * Performs an index-ascending scan of the tree for present items which * have the tag indexed by @tag set. Places the slots at *@results and * returns the number of slots which were placed at *@results. */ unsigned int radix_tree_gang_lookup_tag_slot(const struct radix_tree_root *root, void __rcu ***results, unsigned long first_index, unsigned int max_items, unsigned int tag) { struct radix_tree_iter iter; void __rcu **slot; unsigned int ret = 0; if (unlikely(!max_items)) return 0; radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) { results[ret] = slot; if (++ret == max_items) break; } return ret; } EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot); static bool __radix_tree_delete(struct radix_tree_root *root, struct radix_tree_node *node, void __rcu **slot) { void *old = rcu_dereference_raw(*slot); int values = xa_is_value(old) ? -1 : 0; unsigned offset = get_slot_offset(node, slot); int tag; if (is_idr(root)) node_tag_set(root, node, IDR_FREE, offset); else for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) node_tag_clear(root, node, tag, offset); replace_slot(slot, NULL, node, -1, values); return node && delete_node(root, node); } /** * radix_tree_iter_delete - delete the entry at this iterator position * @root: radix tree root * @iter: iterator state * @slot: pointer to slot * * Delete the entry at the position currently pointed to by the iterator. * This may result in the current node being freed; if it is, the iterator * is advanced so that it will not reference the freed memory. This * function may be called without any locking if there are no other threads * which can access this tree. */ void radix_tree_iter_delete(struct radix_tree_root *root, struct radix_tree_iter *iter, void __rcu **slot) { if (__radix_tree_delete(root, iter->node, slot)) iter->index = iter->next_index; } EXPORT_SYMBOL(radix_tree_iter_delete); /** * radix_tree_delete_item - delete an item from a radix tree * @root: radix tree root * @index: index key * @item: expected item * * Remove @item at @index from the radix tree rooted at @root. * * Return: the deleted entry, or %NULL if it was not present * or the entry at the given @index was not @item. */ void *radix_tree_delete_item(struct radix_tree_root *root, unsigned long index, void *item) { struct radix_tree_node *node = NULL; void __rcu **slot = NULL; void *entry; entry = __radix_tree_lookup(root, index, &node, &slot); if (!slot) return NULL; if (!entry && (!is_idr(root) || node_tag_get(root, node, IDR_FREE, get_slot_offset(node, slot)))) return NULL; if (item && entry != item) return NULL; __radix_tree_delete(root, node, slot); return entry; } EXPORT_SYMBOL(radix_tree_delete_item); /** * radix_tree_delete - delete an entry from a radix tree * @root: radix tree root * @index: index key * * Remove the entry at @index from the radix tree rooted at @root. * * Return: The deleted entry, or %NULL if it was not present. */ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index) { return radix_tree_delete_item(root, index, NULL); } EXPORT_SYMBOL(radix_tree_delete); /** * radix_tree_tagged - test whether any items in the tree are tagged * @root: radix tree root * @tag: tag to test */ int radix_tree_tagged(const struct radix_tree_root *root, unsigned int tag) { return root_tag_get(root, tag); } EXPORT_SYMBOL(radix_tree_tagged); /** * idr_preload - preload for idr_alloc() * @gfp_mask: allocation mask to use for preloading * * Preallocate memory to use for the next call to idr_alloc(). This function * returns with preemption disabled. It will be enabled by idr_preload_end(). */ void idr_preload(gfp_t gfp_mask) { if (__radix_tree_preload(gfp_mask, IDR_PRELOAD_SIZE)) local_lock(&radix_tree_preloads.lock); } EXPORT_SYMBOL(idr_preload); void __rcu **idr_get_free(struct radix_tree_root *root, struct radix_tree_iter *iter, gfp_t gfp, unsigned long max) { struct radix_tree_node *node = NULL, *child; void __rcu **slot = (void __rcu **)&root->xa_head; unsigned long maxindex, start = iter->next_index; unsigned int shift, offset = 0; grow: shift = radix_tree_load_root(root, &child, &maxindex); if (!radix_tree_tagged(root, IDR_FREE)) start = max(start, maxindex + 1); if (start > max) return ERR_PTR(-ENOSPC); if (start > maxindex) { int error = radix_tree_extend(root, gfp, start, shift); if (error < 0) return ERR_PTR(error); shift = error; child = rcu_dereference_raw(root->xa_head); } if (start == 0 && shift == 0) shift = RADIX_TREE_MAP_SHIFT; while (shift) { shift -= RADIX_TREE_MAP_SHIFT; if (child == NULL) { /* Have to add a child node. */ child = radix_tree_node_alloc(gfp, node, root, shift, offset, 0, 0); if (!child) return ERR_PTR(-ENOMEM); all_tag_set(child, IDR_FREE); rcu_assign_pointer(*slot, node_to_entry(child)); if (node) node->count++; } else if (!radix_tree_is_internal_node(child)) break; node = entry_to_node(child); offset = radix_tree_descend(node, &child, start); if (!tag_get(node, IDR_FREE, offset)) { offset = radix_tree_find_next_bit(node, IDR_FREE, offset + 1); start = next_index(start, node, offset); if (start > max || start == 0) return ERR_PTR(-ENOSPC); while (offset == RADIX_TREE_MAP_SIZE) { offset = node->offset + 1; node = node->parent; if (!node) goto grow; shift = node->shift; } child = rcu_dereference_raw(node->slots[offset]); } slot = &node->slots[offset]; } iter->index = start; if (node) iter->next_index = 1 + min(max, (start | node_maxindex(node))); else iter->next_index = 1; iter->node = node; set_iter_tags(iter, node, offset, IDR_FREE); return slot; } /** * idr_destroy - release all internal memory from an IDR * @idr: idr handle * * After this function is called, the IDR is empty, and may be reused or * the data structure containing it may be freed. * * A typical clean-up sequence for objects stored in an idr tree will use * idr_for_each() to free all objects, if necessary, then idr_destroy() to * free the memory used to keep track of those objects. */ void idr_destroy(struct idr *idr) { struct radix_tree_node *node = rcu_dereference_raw(idr->idr_rt.xa_head); if (radix_tree_is_internal_node(node)) radix_tree_free_nodes(node); idr->idr_rt.xa_head = NULL; root_tag_set(&idr->idr_rt, IDR_FREE); } EXPORT_SYMBOL(idr_destroy); static void radix_tree_node_ctor(void *arg) { struct radix_tree_node *node = arg; memset(node, 0, sizeof(*node)); INIT_LIST_HEAD(&node->private_list); } static int radix_tree_cpu_dead(unsigned int cpu) { struct radix_tree_preload *rtp; struct radix_tree_node *node; /* Free per-cpu pool of preloaded nodes */ rtp = &per_cpu(radix_tree_preloads, cpu); while (rtp->nr) { node = rtp->nodes; rtp->nodes = node->parent; kmem_cache_free(radix_tree_node_cachep, node); rtp->nr--; } return 0; } void __init radix_tree_init(void) { int ret; BUILD_BUG_ON(RADIX_TREE_MAX_TAGS + __GFP_BITS_SHIFT > 32); BUILD_BUG_ON(ROOT_IS_IDR & ~GFP_ZONEMASK); BUILD_BUG_ON(XA_CHUNK_SIZE > 255); radix_tree_node_cachep = kmem_cache_create("radix_tree_node", sizeof(struct radix_tree_node), 0, SLAB_PANIC | SLAB_RECLAIM_ACCOUNT, radix_tree_node_ctor); ret = cpuhp_setup_state_nocalls(CPUHP_RADIX_DEAD, "lib/radix:dead", NULL, radix_tree_cpu_dead); WARN_ON(ret < 0); } |
| 83 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 | /* SPDX-License-Identifier: GPL-2.0 */ /* * * Definitions for mount interface. This describes the in the kernel build * linkedlist with mounted filesystems. * * Author: Marco van Wieringen <mvw@planets.elm.net> * */ #ifndef _LINUX_MOUNT_H #define _LINUX_MOUNT_H #include <linux/types.h> #include <asm/barrier.h> struct super_block; struct dentry; struct user_namespace; struct mnt_idmap; struct file_system_type; struct fs_context; struct file; struct path; #define MNT_NOSUID 0x01 #define MNT_NODEV 0x02 #define MNT_NOEXEC 0x04 #define MNT_NOATIME 0x08 #define MNT_NODIRATIME 0x10 #define MNT_RELATIME 0x20 #define MNT_READONLY 0x40 /* does the user want this to be r/o? */ #define MNT_NOSYMFOLLOW 0x80 #define MNT_SHRINKABLE 0x100 #define MNT_WRITE_HOLD 0x200 #define MNT_SHARED 0x1000 /* if the vfsmount is a shared mount */ #define MNT_UNBINDABLE 0x2000 /* if the vfsmount is a unbindable mount */ /* * MNT_SHARED_MASK is the set of flags that should be cleared when a * mount becomes shared. Currently, this is only the flag that says a * mount cannot be bind mounted, since this is how we create a mount * that shares events with another mount. If you add a new MNT_* * flag, consider how it interacts with shared mounts. */ #define MNT_SHARED_MASK (MNT_UNBINDABLE) #define MNT_USER_SETTABLE_MASK (MNT_NOSUID | MNT_NODEV | MNT_NOEXEC \ | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME \ | MNT_READONLY | MNT_NOSYMFOLLOW) #define MNT_ATIME_MASK (MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME ) #define MNT_INTERNAL_FLAGS (MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL | \ MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED | MNT_ONRB) #define MNT_INTERNAL 0x4000 #define MNT_LOCK_ATIME 0x040000 #define MNT_LOCK_NOEXEC 0x080000 #define MNT_LOCK_NOSUID 0x100000 #define MNT_LOCK_NODEV 0x200000 #define MNT_LOCK_READONLY 0x400000 #define MNT_LOCKED 0x800000 #define MNT_DOOMED 0x1000000 #define MNT_SYNC_UMOUNT 0x2000000 #define MNT_MARKED 0x4000000 #define MNT_UMOUNT 0x8000000 #define MNT_ONRB 0x10000000 struct vfsmount { struct dentry *mnt_root; /* root of the mounted tree */ struct super_block *mnt_sb; /* pointer to superblock */ int mnt_flags; struct mnt_idmap *mnt_idmap; } __randomize_layout; static inline struct mnt_idmap *mnt_idmap(const struct vfsmount *mnt) { /* Pairs with smp_store_release() in do_idmap_mount(). */ return smp_load_acquire(&mnt->mnt_idmap); } extern int mnt_want_write(struct vfsmount *mnt); extern int mnt_want_write_file(struct file *file); extern void mnt_drop_write(struct vfsmount *mnt); extern void mnt_drop_write_file(struct file *file); extern void mntput(struct vfsmount *mnt); extern struct vfsmount *mntget(struct vfsmount *mnt); extern void mnt_make_shortterm(struct vfsmount *mnt); extern struct vfsmount *mnt_clone_internal(const struct path *path); extern bool __mnt_is_readonly(struct vfsmount *mnt); extern bool mnt_may_suid(struct vfsmount *mnt); extern struct vfsmount *clone_private_mount(const struct path *path); int mnt_get_write_access(struct vfsmount *mnt); void mnt_put_write_access(struct vfsmount *mnt); extern struct vfsmount *fc_mount(struct fs_context *fc); extern struct vfsmount *vfs_create_mount(struct fs_context *fc); extern struct vfsmount *vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void *data); extern struct vfsmount *vfs_submount(const struct dentry *mountpoint, struct file_system_type *type, const char *name, void *data); extern void mnt_set_expiry(struct vfsmount *mnt, struct list_head *expiry_list); extern void mark_mounts_for_expiry(struct list_head *mounts); extern bool path_is_mountpoint(const struct path *path); extern bool our_mnt(struct vfsmount *mnt); extern struct vfsmount *kern_mount(struct file_system_type *); extern void kern_unmount(struct vfsmount *mnt); extern int may_umount_tree(struct vfsmount *); extern int may_umount(struct vfsmount *); extern long do_mount(const char *, const char __user *, const char *, unsigned long, void *); extern struct vfsmount *collect_mounts(const struct path *); extern void drop_collected_mounts(struct vfsmount *); extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *, struct vfsmount *); extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num); extern int cifs_root_data(char **dev, char **opts); #endif /* _LINUX_MOUNT_H */ |
| 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2017 ARM Ltd. */ #ifndef __ASM_DAIFFLAGS_H #define __ASM_DAIFFLAGS_H #include <linux/irqflags.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/ptrace.h> #define DAIF_PROCCTX 0 #define DAIF_PROCCTX_NOIRQ (PSR_I_BIT | PSR_F_BIT) #define DAIF_ERRCTX (PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) #define DAIF_MASK (PSR_D_BIT | PSR_A_BIT | PSR_I_BIT | PSR_F_BIT) /* mask/save/unmask/restore all exceptions, including interrupts. */ static inline void local_daif_mask(void) { WARN_ON(system_has_prio_mask_debugging() && (read_sysreg_s(SYS_ICC_PMR_EL1) == (GIC_PRIO_IRQOFF | GIC_PRIO_PSR_I_SET))); asm volatile( "msr daifset, #0xf // local_daif_mask\n" : : : "memory"); /* Don't really care for a dsb here, we don't intend to enable IRQs */ if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); trace_hardirqs_off(); } static inline unsigned long local_daif_save_flags(void) { unsigned long flags; flags = read_sysreg(daif); if (system_uses_irq_prio_masking()) { /* If IRQs are masked with PMR, reflect it in the flags */ if (read_sysreg_s(SYS_ICC_PMR_EL1) != GIC_PRIO_IRQON) flags |= PSR_I_BIT | PSR_F_BIT; } return flags; } static inline unsigned long local_daif_save(void) { unsigned long flags; flags = local_daif_save_flags(); local_daif_mask(); return flags; } static inline void local_daif_restore(unsigned long flags) { bool irq_disabled = flags & PSR_I_BIT; WARN_ON(system_has_prio_mask_debugging() && (read_sysreg(daif) & (PSR_I_BIT | PSR_F_BIT)) != (PSR_I_BIT | PSR_F_BIT)); if (!irq_disabled) { trace_hardirqs_on(); if (system_uses_irq_prio_masking()) { gic_write_pmr(GIC_PRIO_IRQON); pmr_sync(); } } else if (system_uses_irq_prio_masking()) { u64 pmr; if (!(flags & PSR_A_BIT)) { /* * If interrupts are disabled but we can take * asynchronous errors, we can take NMIs */ flags &= ~(PSR_I_BIT | PSR_F_BIT); pmr = GIC_PRIO_IRQOFF; } else { pmr = GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET; } /* * There has been concern that the write to daif * might be reordered before this write to PMR. * From the ARM ARM DDI 0487D.a, section D1.7.1 * "Accessing PSTATE fields": * Writes to the PSTATE fields have side-effects on * various aspects of the PE operation. All of these * side-effects are guaranteed: * - Not to be visible to earlier instructions in * the execution stream. * - To be visible to later instructions in the * execution stream * * Also, writes to PMR are self-synchronizing, so no * interrupts with a lower priority than PMR is signaled * to the PE after the write. * * So we don't need additional synchronization here. */ gic_write_pmr(pmr); } write_sysreg(flags, daif); if (irq_disabled) trace_hardirqs_off(); } /* * Called by synchronous exception handlers to restore the DAIF bits that were * modified by taking an exception. */ static inline void local_daif_inherit(struct pt_regs *regs) { unsigned long flags = regs->pstate & DAIF_MASK; if (interrupts_enabled(regs)) trace_hardirqs_on(); if (system_uses_irq_prio_masking()) gic_write_pmr(regs->pmr_save); /* * We can't use local_daif_restore(regs->pstate) here as * system_has_prio_mask_debugging() won't restore the I bit if it can * use the pmr instead. */ write_sysreg(flags, daif); } #endif |
| 155 155 154 155 119 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_BIT_SPINLOCK_H #define __LINUX_BIT_SPINLOCK_H #include <linux/kernel.h> #include <linux/preempt.h> #include <linux/atomic.h> #include <linux/bug.h> /* * bit-based spin_lock() * * Don't use this unless you really need to: spin_lock() and spin_unlock() * are significantly faster. */ static inline void bit_spin_lock(int bitnum, unsigned long *addr) { /* * Assuming the lock is uncontended, this never enters * the body of the outer loop. If it is contended, then * within the inner loop a non-atomic test is used to * busywait with less bus contention for a good time to * attempt to acquire the lock bit. */ preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) while (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); do { cpu_relax(); } while (test_bit(bitnum, addr)); preempt_disable(); } #endif __acquire(bitlock); } /* * Return true if it was acquired */ static inline int bit_spin_trylock(int bitnum, unsigned long *addr) { preempt_disable(); #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) if (unlikely(test_and_set_bit_lock(bitnum, addr))) { preempt_enable(); return 0; } #endif __acquire(bitlock); return 1; } /* * bit-based spin_unlock() */ static inline void bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * bit-based spin_unlock() * non-atomic version, which can be used eg. if the bit lock itself is * protecting the rest of the flags in the word. */ static inline void __bit_spin_unlock(int bitnum, unsigned long *addr) { #ifdef CONFIG_DEBUG_SPINLOCK BUG_ON(!test_bit(bitnum, addr)); #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) __clear_bit_unlock(bitnum, addr); #endif preempt_enable(); __release(bitlock); } /* * Return true if the lock is held. */ static inline int bit_spin_is_locked(int bitnum, unsigned long *addr) { #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) return test_bit(bitnum, addr); #elif defined CONFIG_PREEMPT_COUNT return preempt_count(); #else return 1; #endif } #endif /* __LINUX_BIT_SPINLOCK_H */ |
| 336 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CTYPE_H #define _LINUX_CTYPE_H #include <linux/compiler.h> /* * NOTE! This ctype does not handle EOF like the standard C * library is required to. */ #define _U 0x01 /* upper */ #define _L 0x02 /* lower */ #define _D 0x04 /* digit */ #define _C 0x08 /* cntrl */ #define _P 0x10 /* punct */ #define _S 0x20 /* white space (space/lf/tab) */ #define _X 0x40 /* hex digit */ #define _SP 0x80 /* hard space (0x20) */ extern const unsigned char _ctype[]; #define __ismask(x) (_ctype[(int)(unsigned char)(x)]) #define isalnum(c) ((__ismask(c)&(_U|_L|_D)) != 0) #define isalpha(c) ((__ismask(c)&(_U|_L)) != 0) #define iscntrl(c) ((__ismask(c)&(_C)) != 0) #define isgraph(c) ((__ismask(c)&(_P|_U|_L|_D)) != 0) #define islower(c) ((__ismask(c)&(_L)) != 0) #define isprint(c) ((__ismask(c)&(_P|_U|_L|_D|_SP)) != 0) #define ispunct(c) ((__ismask(c)&(_P)) != 0) /* Note: isspace() must return false for %NUL-terminator */ #define isspace(c) ((__ismask(c)&(_S)) != 0) #define isupper(c) ((__ismask(c)&(_U)) != 0) #define isxdigit(c) ((__ismask(c)&(_D|_X)) != 0) #define isascii(c) (((unsigned char)(c))<=0x7f) #define toascii(c) (((unsigned char)(c))&0x7f) #if __has_builtin(__builtin_isdigit) #define isdigit(c) __builtin_isdigit(c) #else static inline int isdigit(int c) { return '0' <= c && c <= '9'; } #endif static inline unsigned char __tolower(unsigned char c) { if (isupper(c)) c -= 'A'-'a'; return c; } static inline unsigned char __toupper(unsigned char c) { if (islower(c)) c -= 'a'-'A'; return c; } #define tolower(c) __tolower(c) #define toupper(c) __toupper(c) /* * Fast implementation of tolower() for internal usage. Do not use in your * code. */ static inline char _tolower(const char c) { return c | 0x20; } /* Fast check for octal digit */ static inline int isodigit(const char c) { return c >= '0' && c <= '7'; } #endif |
| 57 49 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/writeback.h */ #ifndef WRITEBACK_H #define WRITEBACK_H #include <linux/sched.h> #include <linux/workqueue.h> #include <linux/fs.h> #include <linux/flex_proportions.h> #include <linux/backing-dev-defs.h> #include <linux/blk_types.h> #include <linux/pagevec.h> struct bio; DECLARE_PER_CPU(int, dirty_throttle_leaks); /* * The global dirty threshold is normally equal to the global dirty limit, * except when the system suddenly allocates a lot of anonymous memory and * knocks down the global dirty threshold quickly, in which case the global * dirty limit will follow down slowly to prevent livelocking all dirtier tasks. */ #define DIRTY_SCOPE 8 struct backing_dev_info; /* * fs/fs-writeback.c */ enum writeback_sync_modes { WB_SYNC_NONE, /* Don't wait on anything */ WB_SYNC_ALL, /* Wait on every mapping */ }; /* * A control structure which tells the writeback code what to do. These are * always on the stack, and hence need no locking. They are always initialised * in a manner such that unspecified fields are set to zero. */ struct writeback_control { /* public fields that can be set and/or consumed by the caller: */ long nr_to_write; /* Write this many pages, and decrement this for each page written */ long pages_skipped; /* Pages which were not written */ /* * For a_ops->writepages(): if start or end are non-zero then this is * a hint that the filesystem need only write out the pages inside that * byterange. The byte at `end' is included in the writeout request. */ loff_t range_start; loff_t range_end; enum writeback_sync_modes sync_mode; unsigned for_kupdate:1; /* A kupdate writeback */ unsigned for_background:1; /* A background writeback */ unsigned tagged_writepages:1; /* tag-and-write to avoid livelock */ unsigned for_reclaim:1; /* Invoked from the page allocator */ unsigned range_cyclic:1; /* range_start is cyclic */ unsigned for_sync:1; /* sync(2) WB_SYNC_ALL writeback */ unsigned unpinned_netfs_wb:1; /* Cleared I_PINNING_NETFS_WB */ /* * When writeback IOs are bounced through async layers, only the * initial synchronous phase should be accounted towards inode * cgroup ownership arbitration to avoid confusion. Later stages * can set the following flag to disable the accounting. */ unsigned no_cgroup_owner:1; /* To enable batching of swap writes to non-block-device backends, * "plug" can be set point to a 'struct swap_iocb *'. When all swap * writes have been submitted, if with swap_iocb is not NULL, * swap_write_unplug() should be called. */ struct swap_iocb **swap_plug; /* internal fields used by the ->writepages implementation: */ struct folio_batch fbatch; pgoff_t index; int saved_err; #ifdef CONFIG_CGROUP_WRITEBACK struct bdi_writeback *wb; /* wb this writeback is issued under */ struct inode *inode; /* inode being written out */ /* foreign inode detection, see wbc_detach_inode() */ int wb_id; /* current wb id */ int wb_lcand_id; /* last foreign candidate wb id */ int wb_tcand_id; /* this foreign candidate wb id */ size_t wb_bytes; /* bytes written by current wb */ size_t wb_lcand_bytes; /* bytes written by last candidate */ size_t wb_tcand_bytes; /* bytes written by this candidate */ #endif }; static inline blk_opf_t wbc_to_write_flags(struct writeback_control *wbc) { blk_opf_t flags = 0; if (wbc->sync_mode == WB_SYNC_ALL) flags |= REQ_SYNC; else if (wbc->for_kupdate || wbc->for_background) flags |= REQ_BACKGROUND; return flags; } #ifdef CONFIG_CGROUP_WRITEBACK #define wbc_blkcg_css(wbc) \ ((wbc)->wb ? (wbc)->wb->blkcg_css : blkcg_root_css) #else #define wbc_blkcg_css(wbc) (blkcg_root_css) #endif /* CONFIG_CGROUP_WRITEBACK */ /* * A wb_domain represents a domain that wb's (bdi_writeback's) belong to * and are measured against each other in. There always is one global * domain, global_wb_domain, that every wb in the system is a member of. * This allows measuring the relative bandwidth of each wb to distribute * dirtyable memory accordingly. */ struct wb_domain { spinlock_t lock; /* * Scale the writeback cache size proportional to the relative * writeout speed. * * We do this by keeping a floating proportion between BDIs, based * on page writeback completions [end_page_writeback()]. Those * devices that write out pages fastest will get the larger share, * while the slower will get a smaller share. * * We use page writeout completions because we are interested in * getting rid of dirty pages. Having them written out is the * primary goal. * * We introduce a concept of time, a period over which we measure * these events, because demand can/will vary over time. The length * of this period itself is measured in page writeback completions. */ struct fprop_global completions; struct timer_list period_timer; /* timer for aging of completions */ unsigned long period_time; /* * The dirtyable memory and dirty threshold could be suddenly * knocked down by a large amount (eg. on the startup of KVM in a * swapless system). This may throw the system into deep dirty * exceeded state and throttle heavy/light dirtiers alike. To * retain good responsiveness, maintain global_dirty_limit for * tracking slowly down to the knocked down dirty threshold. * * Both fields are protected by ->lock. */ unsigned long dirty_limit_tstamp; unsigned long dirty_limit; }; /** * wb_domain_size_changed - memory available to a wb_domain has changed * @dom: wb_domain of interest * * This function should be called when the amount of memory available to * @dom has changed. It resets @dom's dirty limit parameters to prevent * the past values which don't match the current configuration from skewing * dirty throttling. Without this, when memory size of a wb_domain is * greatly reduced, the dirty throttling logic may allow too many pages to * be dirtied leading to consecutive unnecessary OOMs and may get stuck in * that situation. */ static inline void wb_domain_size_changed(struct wb_domain *dom) { spin_lock(&dom->lock); dom->dirty_limit_tstamp = jiffies; dom->dirty_limit = 0; spin_unlock(&dom->lock); } /* * fs/fs-writeback.c */ struct bdi_writeback; void writeback_inodes_sb(struct super_block *, enum wb_reason reason); void writeback_inodes_sb_nr(struct super_block *, unsigned long nr, enum wb_reason reason); void try_to_writeback_inodes_sb(struct super_block *sb, enum wb_reason reason); void sync_inodes_sb(struct super_block *); void wakeup_flusher_threads(enum wb_reason reason); void wakeup_flusher_threads_bdi(struct backing_dev_info *bdi, enum wb_reason reason); void inode_wait_for_writeback(struct inode *inode); void inode_io_list_del(struct inode *inode); /* writeback.h requires fs.h; it, too, is not included from here. */ static inline void wait_on_inode(struct inode *inode) { wait_on_bit(&inode->i_state, __I_NEW, TASK_UNINTERRUPTIBLE); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/cgroup.h> #include <linux/bio.h> void __inode_attach_wb(struct inode *inode, struct folio *folio); void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock); void wbc_detach_inode(struct writeback_control *wbc); void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes); int cgroup_writeback_by_id(u64 bdi_id, int memcg_id, enum wb_reason reason, struct wb_completion *done); void cgroup_writeback_umount(void); bool cleanup_offline_cgwb(struct bdi_writeback *wb); /** * inode_attach_wb - associate an inode with its wb * @inode: inode of interest * @folio: folio being dirtied (may be NULL) * * If @inode doesn't have its wb, associate it with the wb matching the * memcg of @folio or, if @folio is NULL, %current. May be called w/ or w/o * @inode->i_lock. */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { if (!inode->i_wb) __inode_attach_wb(inode, folio); } /** * inode_detach_wb - disassociate an inode from its wb * @inode: inode of interest * * @inode is being freed. Detach from its wb. */ static inline void inode_detach_wb(struct inode *inode) { if (inode->i_wb) { WARN_ON_ONCE(!(inode->i_state & I_CLEAR)); wb_put(inode->i_wb); inode->i_wb = NULL; } } /** * wbc_attach_fdatawrite_inode - associate wbc and inode for fdatawrite * @wbc: writeback_control of interest * @inode: target inode * * This function is to be used by __filemap_fdatawrite_range(), which is an * alternative entry point into writeback code, and first ensures @inode is * associated with a bdi_writeback and attaches it to @wbc. */ static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { spin_lock(&inode->i_lock); inode_attach_wb(inode, NULL); wbc_attach_and_unlock_inode(wbc, inode); } /** * wbc_init_bio - writeback specific initializtion of bio * @wbc: writeback_control for the writeback in progress * @bio: bio to be initialized * * @bio is a part of the writeback in progress controlled by @wbc. Perform * writeback specific initialization. This is used to apply the cgroup * writeback context. Must be called after the bio has been associated with * a device. */ static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { /* * 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) bio_associate_blkg_from_css(bio, wbc->wb->blkcg_css); } #else /* CONFIG_CGROUP_WRITEBACK */ static inline void inode_attach_wb(struct inode *inode, struct folio *folio) { } static inline void inode_detach_wb(struct inode *inode) { } static inline void wbc_attach_and_unlock_inode(struct writeback_control *wbc, struct inode *inode) __releases(&inode->i_lock) { spin_unlock(&inode->i_lock); } static inline void wbc_attach_fdatawrite_inode(struct writeback_control *wbc, struct inode *inode) { } static inline void wbc_detach_inode(struct writeback_control *wbc) { } static inline void wbc_init_bio(struct writeback_control *wbc, struct bio *bio) { } static inline void wbc_account_cgroup_owner(struct writeback_control *wbc, struct page *page, size_t bytes) { } static inline void cgroup_writeback_umount(void) { } #endif /* CONFIG_CGROUP_WRITEBACK */ /* * mm/page-writeback.c */ void laptop_io_completion(struct backing_dev_info *info); void laptop_sync_completion(void); void laptop_mode_timer_fn(struct timer_list *t); bool node_dirty_ok(struct pglist_data *pgdat); int wb_domain_init(struct wb_domain *dom, gfp_t gfp); #ifdef CONFIG_CGROUP_WRITEBACK void wb_domain_exit(struct wb_domain *dom); #endif extern struct wb_domain global_wb_domain; /* These are exported to sysctl. */ extern unsigned int dirty_writeback_interval; extern unsigned int dirty_expire_interval; extern unsigned int dirtytime_expire_interval; extern int laptop_mode; int dirtytime_interval_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos); void global_dirty_limits(unsigned long *pbackground, unsigned long *pdirty); unsigned long wb_calc_thresh(struct bdi_writeback *wb, unsigned long thresh); unsigned long cgwb_calc_thresh(struct bdi_writeback *wb); void wb_update_bandwidth(struct bdi_writeback *wb); /* Invoke balance dirty pages in async mode. */ #define BDP_ASYNC 0x0001 void balance_dirty_pages_ratelimited(struct address_space *mapping); int balance_dirty_pages_ratelimited_flags(struct address_space *mapping, unsigned int flags); bool wb_over_bg_thresh(struct bdi_writeback *wb); struct folio *writeback_iter(struct address_space *mapping, struct writeback_control *wbc, struct folio *folio, int *error); typedef int (*writepage_t)(struct folio *folio, struct writeback_control *wbc, void *data); int write_cache_pages(struct address_space *mapping, struct writeback_control *wbc, writepage_t writepage, void *data); int do_writepages(struct address_space *mapping, struct writeback_control *wbc); void writeback_set_ratelimit(void); void tag_pages_for_writeback(struct address_space *mapping, pgoff_t start, pgoff_t end); bool filemap_dirty_folio(struct address_space *mapping, struct folio *folio); bool folio_redirty_for_writepage(struct writeback_control *, struct folio *); bool redirty_page_for_writepage(struct writeback_control *, struct page *); void sb_mark_inode_writeback(struct inode *inode); void sb_clear_inode_writeback(struct inode *inode); #endif /* WRITEBACK_H */ |
| 8 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | /* SPDX-License-Identifier: GPL-2.0-only */ #ifndef __KVM_IODEV_H__ #define __KVM_IODEV_H__ #include <linux/kvm_types.h> #include <linux/errno.h> struct kvm_io_device; struct kvm_vcpu; /** * kvm_io_device_ops are called under kvm slots_lock. * read and write handlers return 0 if the transaction has been handled, * or non-zero to have it passed to the next device. **/ struct kvm_io_device_ops { int (*read)(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, void *val); int (*write)(struct kvm_vcpu *vcpu, struct kvm_io_device *this, gpa_t addr, int len, const void *val); void (*destructor)(struct kvm_io_device *this); }; struct kvm_io_device { const struct kvm_io_device_ops *ops; }; static inline void kvm_iodevice_init(struct kvm_io_device *dev, const struct kvm_io_device_ops *ops) { dev->ops = ops; } static inline int kvm_iodevice_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int l, void *v) { return dev->ops->read ? dev->ops->read(vcpu, dev, addr, l, v) : -EOPNOTSUPP; } static inline int kvm_iodevice_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int l, const void *v) { return dev->ops->write ? dev->ops->write(vcpu, dev, addr, l, v) : -EOPNOTSUPP; } #endif /* __KVM_IODEV_H__ */ |
| 27 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 | /* * Compatibility functions which bloat the callers too much to make inline. * All of the callers of these functions should be converted to use folios * eventually. */ #include <linux/migrate.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include "internal.h" struct address_space *page_mapping(struct page *page) { return folio_mapping(page_folio(page)); } EXPORT_SYMBOL(page_mapping); void unlock_page(struct page *page) { return folio_unlock(page_folio(page)); } EXPORT_SYMBOL(unlock_page); void end_page_writeback(struct page *page) { return folio_end_writeback(page_folio(page)); } EXPORT_SYMBOL(end_page_writeback); void wait_on_page_writeback(struct page *page) { return folio_wait_writeback(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_on_page_writeback); void wait_for_stable_page(struct page *page) { return folio_wait_stable(page_folio(page)); } EXPORT_SYMBOL_GPL(wait_for_stable_page); void mark_page_accessed(struct page *page) { folio_mark_accessed(page_folio(page)); } EXPORT_SYMBOL(mark_page_accessed); void set_page_writeback(struct page *page) { folio_start_writeback(page_folio(page)); } EXPORT_SYMBOL(set_page_writeback); bool set_page_dirty(struct page *page) { return folio_mark_dirty(page_folio(page)); } EXPORT_SYMBOL(set_page_dirty); bool clear_page_dirty_for_io(struct page *page) { return folio_clear_dirty_for_io(page_folio(page)); } EXPORT_SYMBOL(clear_page_dirty_for_io); bool redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { return folio_redirty_for_writepage(wbc, page_folio(page)); } EXPORT_SYMBOL(redirty_page_for_writepage); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp) { return filemap_add_folio(mapping, page_folio(page), index, gfp); } EXPORT_SYMBOL(add_to_page_cache_lru); noinline struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp) { struct folio *folio; folio = __filemap_get_folio(mapping, index, fgp_flags, gfp); if (IS_ERR(folio)) return NULL; return folio_file_page(folio, index); } EXPORT_SYMBOL(pagecache_get_page); struct page *grab_cache_page_write_begin(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_WRITEBEGIN, mapping_gfp_mask(mapping)); } EXPORT_SYMBOL(grab_cache_page_write_begin); bool isolate_lru_page(struct page *page) { if (WARN_RATELIMIT(PageTail(page), "trying to isolate tail page")) return false; return folio_isolate_lru((struct folio *)page); } void putback_lru_page(struct page *page) { folio_putback_lru(page_folio(page)); } |
| 139 139 139 133 139 11 139 139 11 139 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar * Copyright (C) 2005-2006, Thomas Gleixner, Russell King * * This file contains the interrupt descriptor management code. Detailed * information is available in Documentation/core-api/genericirq.rst * */ #include <linux/irq.h> #include <linux/slab.h> #include <linux/export.h> #include <linux/interrupt.h> #include <linux/kernel_stat.h> #include <linux/maple_tree.h> #include <linux/irqdomain.h> #include <linux/sysfs.h> #include "internals.h" /* * lockdep: we want to handle all irq_desc locks as a single lock-class: */ static struct lock_class_key irq_desc_lock_class; #if defined(CONFIG_SMP) static int __init irq_affinity_setup(char *str) { alloc_bootmem_cpumask_var(&irq_default_affinity); cpulist_parse(str, irq_default_affinity); /* * Set at least the boot cpu. We don't want to end up with * bugreports caused by random commandline masks */ cpumask_set_cpu(smp_processor_id(), irq_default_affinity); return 1; } __setup("irqaffinity=", irq_affinity_setup); static void __init init_irq_default_affinity(void) { if (!cpumask_available(irq_default_affinity)) zalloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT); if (cpumask_empty(irq_default_affinity)) cpumask_setall(irq_default_affinity); } #else static void __init init_irq_default_affinity(void) { } #endif #ifdef CONFIG_SMP static int alloc_masks(struct irq_desc *desc, int node) { if (!zalloc_cpumask_var_node(&desc->irq_common_data.affinity, GFP_KERNEL, node)) return -ENOMEM; #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK if (!zalloc_cpumask_var_node(&desc->irq_common_data.effective_affinity, GFP_KERNEL, node)) { free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif #ifdef CONFIG_GENERIC_PENDING_IRQ if (!zalloc_cpumask_var_node(&desc->pending_mask, GFP_KERNEL, node)) { #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif free_cpumask_var(desc->irq_common_data.affinity); return -ENOMEM; } #endif return 0; } static void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { if (!affinity) affinity = irq_default_affinity; cpumask_copy(desc->irq_common_data.affinity, affinity); #ifdef CONFIG_GENERIC_PENDING_IRQ cpumask_clear(desc->pending_mask); #endif #ifdef CONFIG_NUMA desc->irq_common_data.node = node; #endif } static void free_masks(struct irq_desc *desc) { #ifdef CONFIG_GENERIC_PENDING_IRQ free_cpumask_var(desc->pending_mask); #endif free_cpumask_var(desc->irq_common_data.affinity); #ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK free_cpumask_var(desc->irq_common_data.effective_affinity); #endif } #else static inline int alloc_masks(struct irq_desc *desc, int node) { return 0; } static inline void desc_smp_init(struct irq_desc *desc, int node, const struct cpumask *affinity) { } static inline void free_masks(struct irq_desc *desc) { } #endif static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node, const struct cpumask *affinity, struct module *owner) { int cpu; desc->irq_common_data.handler_data = NULL; desc->irq_common_data.msi_desc = NULL; desc->irq_data.common = &desc->irq_common_data; desc->irq_data.irq = irq; desc->irq_data.chip = &no_irq_chip; desc->irq_data.chip_data = NULL; irq_settings_clr_and_set(desc, ~0, _IRQ_DEFAULT_INIT_FLAGS); irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED); irqd_set(&desc->irq_data, IRQD_IRQ_MASKED); desc->handle_irq = handle_bad_irq; desc->depth = 1; desc->irq_count = 0; desc->irqs_unhandled = 0; desc->tot_count = 0; desc->name = NULL; desc->owner = owner; for_each_possible_cpu(cpu) *per_cpu_ptr(desc->kstat_irqs, cpu) = (struct irqstat) { }; desc_smp_init(desc, node, affinity); } int nr_irqs = NR_IRQS; EXPORT_SYMBOL_GPL(nr_irqs); static DEFINE_MUTEX(sparse_irq_lock); static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs, MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | MT_FLAGS_USE_RCU, sparse_irq_lock); static int irq_find_free_area(unsigned int from, unsigned int cnt) { MA_STATE(mas, &sparse_irqs, 0, 0); if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt)) return -ENOSPC; return mas.index; } static unsigned int irq_find_at_or_after(unsigned int offset) { unsigned long index = offset; struct irq_desc *desc; guard(rcu)(); desc = mt_find(&sparse_irqs, &index, nr_irqs); return desc ? irq_desc_get_irq(desc) : nr_irqs; } static void irq_insert_desc(unsigned int irq, struct irq_desc *desc) { MA_STATE(mas, &sparse_irqs, irq, irq); WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0); } static void delete_irq_desc(unsigned int irq) { MA_STATE(mas, &sparse_irqs, irq, irq); mas_erase(&mas); } #ifdef CONFIG_SPARSE_IRQ static const struct kobj_type irq_kobj_type; #endif static int init_desc(struct irq_desc *desc, int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { desc->kstat_irqs = alloc_percpu(struct irqstat); if (!desc->kstat_irqs) return -ENOMEM; if (alloc_masks(desc, node)) { free_percpu(desc->kstat_irqs); return -ENOMEM; } raw_spin_lock_init(&desc->lock); lockdep_set_class(&desc->lock, &irq_desc_lock_class); mutex_init(&desc->request_mutex); init_waitqueue_head(&desc->wait_for_threads); desc_set_defaults(irq, desc, node, affinity, owner); irqd_set(&desc->irq_data, flags); irq_resend_init(desc); #ifdef CONFIG_SPARSE_IRQ kobject_init(&desc->kobj, &irq_kobj_type); init_rcu_head(&desc->rcu); #endif return 0; } #ifdef CONFIG_SPARSE_IRQ static void irq_kobj_release(struct kobject *kobj); #ifdef CONFIG_SYSFS static struct kobject *irq_kobj_base; #define IRQ_ATTR_RO(_name) \ static struct kobj_attribute _name##_attr = __ATTR_RO(_name) static ssize_t per_cpu_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; char *p = ""; int cpu; for_each_possible_cpu(cpu) { unsigned int c = irq_desc_kstat_cpu(desc, cpu); ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%u", p, c); p = ","; } ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); return ret; } IRQ_ATTR_RO(per_cpu_count); static ssize_t chip_name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->irq_data.chip && desc->irq_data.chip->name) { ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->irq_data.chip->name); } raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(chip_name); static ssize_t hwirq_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->irq_data.domain) ret = sprintf(buf, "%lu\n", desc->irq_data.hwirq); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(hwirq); static ssize_t type_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); ret = sprintf(buf, "%s\n", irqd_is_level_type(&desc->irq_data) ? "level" : "edge"); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(type); static ssize_t wakeup_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); ret = sprintf(buf, "%s\n", irqd_is_wakeup_set(&desc->irq_data) ? "enabled" : "disabled"); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(wakeup); static ssize_t name_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); ssize_t ret = 0; raw_spin_lock_irq(&desc->lock); if (desc->name) ret = scnprintf(buf, PAGE_SIZE, "%s\n", desc->name); raw_spin_unlock_irq(&desc->lock); return ret; } IRQ_ATTR_RO(name); static ssize_t actions_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); struct irqaction *action; ssize_t ret = 0; char *p = ""; raw_spin_lock_irq(&desc->lock); for_each_action_of_desc(desc, action) { ret += scnprintf(buf + ret, PAGE_SIZE - ret, "%s%s", p, action->name); p = ","; } raw_spin_unlock_irq(&desc->lock); if (ret) ret += scnprintf(buf + ret, PAGE_SIZE - ret, "\n"); return ret; } IRQ_ATTR_RO(actions); static struct attribute *irq_attrs[] = { &per_cpu_count_attr.attr, &chip_name_attr.attr, &hwirq_attr.attr, &type_attr.attr, &wakeup_attr.attr, &name_attr.attr, &actions_attr.attr, NULL }; ATTRIBUTE_GROUPS(irq); static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, .sysfs_ops = &kobj_sysfs_ops, .default_groups = irq_groups, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) { if (irq_kobj_base) { /* * Continue even in case of failure as this is nothing * crucial and failures in the late irq_sysfs_init() * cannot be rolled back. */ if (kobject_add(&desc->kobj, irq_kobj_base, "%d", irq)) pr_warn("Failed to add kobject for irq %d\n", irq); else desc->istate |= IRQS_SYSFS; } } static void irq_sysfs_del(struct irq_desc *desc) { /* * Only invoke kobject_del() when kobject_add() was successfully * invoked for the descriptor. This covers both early boot, where * sysfs is not initialized yet, and the case of a failed * kobject_add() invocation. */ if (desc->istate & IRQS_SYSFS) kobject_del(&desc->kobj); } static int __init irq_sysfs_init(void) { struct irq_desc *desc; int irq; /* Prevent concurrent irq alloc/free */ irq_lock_sparse(); irq_kobj_base = kobject_create_and_add("irq", kernel_kobj); if (!irq_kobj_base) { irq_unlock_sparse(); return -ENOMEM; } /* Add the already allocated interrupts */ for_each_irq_desc(irq, desc) irq_sysfs_add(irq, desc); irq_unlock_sparse(); return 0; } postcore_initcall(irq_sysfs_init); #else /* !CONFIG_SYSFS */ static const struct kobj_type irq_kobj_type = { .release = irq_kobj_release, }; static void irq_sysfs_add(int irq, struct irq_desc *desc) {} static void irq_sysfs_del(struct irq_desc *desc) {} #endif /* CONFIG_SYSFS */ struct irq_desc *irq_to_desc(unsigned int irq) { return mtree_load(&sparse_irqs, irq); } #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE EXPORT_SYMBOL_GPL(irq_to_desc); #endif void irq_lock_sparse(void) { mutex_lock(&sparse_irq_lock); } void irq_unlock_sparse(void) { mutex_unlock(&sparse_irq_lock); } static struct irq_desc *alloc_desc(int irq, int node, unsigned int flags, const struct cpumask *affinity, struct module *owner) { struct irq_desc *desc; int ret; desc = kzalloc_node(sizeof(*desc), GFP_KERNEL, node); if (!desc) return NULL; ret = init_desc(desc, irq, node, flags, affinity, owner); if (unlikely(ret)) { kfree(desc); return NULL; } return desc; } static void irq_kobj_release(struct kobject *kobj) { struct irq_desc *desc = container_of(kobj, struct irq_desc, kobj); free_masks(desc); free_percpu(desc->kstat_irqs); kfree(desc); } static void delayed_free_desc(struct rcu_head *rhp) { struct irq_desc *desc = container_of(rhp, struct irq_desc, rcu); kobject_put(&desc->kobj); } static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); irq_remove_debugfs_entry(desc); unregister_irq_proc(irq, desc); /* * sparse_irq_lock protects also show_interrupts() and * kstat_irq_usr(). Once we deleted the descriptor from the * sparse tree we can free it. Access in proc will fail to * lookup the descriptor. * * The sysfs entry must be serialized against a concurrent * irq_sysfs_init() as well. */ irq_sysfs_del(desc); delete_irq_desc(irq); /* * We free the descriptor, masks and stat fields via RCU. That * allows demultiplex interrupts to do rcu based management of * the child interrupts. * This also allows us to use rcu in kstat_irqs_usr(). */ call_rcu(&desc->rcu, delayed_free_desc); } static int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { struct irq_desc *desc; int i; /* Validate affinity mask(s) */ if (affinity) { for (i = 0; i < cnt; i++) { if (cpumask_empty(&affinity[i].mask)) return -EINVAL; } } for (i = 0; i < cnt; i++) { const struct cpumask *mask = NULL; unsigned int flags = 0; if (affinity) { if (affinity->is_managed) { flags = IRQD_AFFINITY_MANAGED | IRQD_MANAGED_SHUTDOWN; } mask = &affinity->mask; node = cpu_to_node(cpumask_first(mask)); affinity++; } desc = alloc_desc(start + i, node, flags, mask, owner); if (!desc) goto err; irq_insert_desc(start + i, desc); irq_sysfs_add(start + i, desc); irq_add_debugfs_entry(start + i, desc); } return start; err: for (i--; i >= 0; i--) free_desc(start + i); return -ENOMEM; } static int irq_expand_nr_irqs(unsigned int nr) { if (nr > MAX_SPARSE_IRQS) return -ENOMEM; nr_irqs = nr; return 0; } int __init early_irq_init(void) { int i, initcnt, node = first_online_node; struct irq_desc *desc; init_irq_default_affinity(); /* Let arch update nr_irqs and return the nr of preallocated irqs */ initcnt = arch_probe_nr_irqs(); printk(KERN_INFO "NR_IRQS: %d, nr_irqs: %d, preallocated irqs: %d\n", NR_IRQS, nr_irqs, initcnt); if (WARN_ON(nr_irqs > MAX_SPARSE_IRQS)) nr_irqs = MAX_SPARSE_IRQS; if (WARN_ON(initcnt > MAX_SPARSE_IRQS)) initcnt = MAX_SPARSE_IRQS; if (initcnt > nr_irqs) nr_irqs = initcnt; for (i = 0; i < initcnt; i++) { desc = alloc_desc(i, node, 0, NULL, NULL); irq_insert_desc(i, desc); } return arch_early_irq_init(); } #else /* !CONFIG_SPARSE_IRQ */ struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = { [0 ... NR_IRQS-1] = { .handle_irq = handle_bad_irq, .depth = 1, .lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock), } }; int __init early_irq_init(void) { int count, i, node = first_online_node; int ret; init_irq_default_affinity(); printk(KERN_INFO "NR_IRQS: %d\n", NR_IRQS); count = ARRAY_SIZE(irq_desc); for (i = 0; i < count; i++) { ret = init_desc(irq_desc + i, i, node, 0, NULL, NULL); if (unlikely(ret)) goto __free_desc_res; } return arch_early_irq_init(); __free_desc_res: while (--i >= 0) { free_masks(irq_desc + i); free_percpu(irq_desc[i].kstat_irqs); } return ret; } struct irq_desc *irq_to_desc(unsigned int irq) { return (irq < NR_IRQS) ? irq_desc + irq : NULL; } EXPORT_SYMBOL(irq_to_desc); static void free_desc(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); unsigned long flags; raw_spin_lock_irqsave(&desc->lock, flags); desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL); raw_spin_unlock_irqrestore(&desc->lock, flags); delete_irq_desc(irq); } static inline int alloc_descs(unsigned int start, unsigned int cnt, int node, const struct irq_affinity_desc *affinity, struct module *owner) { u32 i; for (i = 0; i < cnt; i++) { struct irq_desc *desc = irq_to_desc(start + i); desc->owner = owner; irq_insert_desc(start + i, desc); } return start; } static int irq_expand_nr_irqs(unsigned int nr) { return -ENOMEM; } void irq_mark_irq(unsigned int irq) { mutex_lock(&sparse_irq_lock); irq_insert_desc(irq, irq_desc + irq); mutex_unlock(&sparse_irq_lock); } #ifdef CONFIG_GENERIC_IRQ_LEGACY void irq_init_desc(unsigned int irq) { free_desc(irq); } #endif #endif /* !CONFIG_SPARSE_IRQ */ int handle_irq_desc(struct irq_desc *desc) { struct irq_data *data; if (!desc) return -EINVAL; data = irq_desc_get_irq_data(desc); if (WARN_ON_ONCE(!in_hardirq() && handle_enforce_irqctx(data))) return -EPERM; generic_handle_irq_desc(desc); return 0; } /** * generic_handle_irq - Invoke the handler for a particular irq * @irq: The irq number to handle * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_irq(unsigned int irq) { return handle_irq_desc(irq_to_desc(irq)); } EXPORT_SYMBOL_GPL(generic_handle_irq); /** * generic_handle_irq_safe - Invoke the handler for a particular irq from any * context. * @irq: The irq number to handle * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process context). It * will report an error if not invoked from IRQ context and the irq has been * marked to enforce IRQ-context only. */ int generic_handle_irq_safe(unsigned int irq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_to_desc(irq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_irq_safe); #ifdef CONFIG_IRQ_DOMAIN /** * generic_handle_domain_irq - Invoke the handler for a HW irq belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an IRQ context with irq regs * initialized. */ int generic_handle_domain_irq(struct irq_domain *domain, unsigned int hwirq) { return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } EXPORT_SYMBOL_GPL(generic_handle_domain_irq); /** * generic_handle_irq_safe - Invoke the handler for a HW irq belonging * to a domain from any context. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, a negative value on error. * * This function can be called from any context (IRQ or process * context). If the interrupt is marked as 'enforce IRQ-context only' then * the function must be invoked from hard interrupt context. */ int generic_handle_domain_irq_safe(struct irq_domain *domain, unsigned int hwirq) { unsigned long flags; int ret; local_irq_save(flags); ret = handle_irq_desc(irq_resolve_mapping(domain, hwirq)); local_irq_restore(flags); return ret; } EXPORT_SYMBOL_GPL(generic_handle_domain_irq_safe); /** * generic_handle_domain_nmi - Invoke the handler for a HW nmi belonging * to a domain. * @domain: The domain where to perform the lookup * @hwirq: The HW irq number to convert to a logical one * * Returns: 0 on success, or -EINVAL if conversion has failed * * This function must be called from an NMI context with irq regs * initialized. **/ int generic_handle_domain_nmi(struct irq_domain *domain, unsigned int hwirq) { WARN_ON_ONCE(!in_nmi()); return handle_irq_desc(irq_resolve_mapping(domain, hwirq)); } #endif /* Dynamic interrupt handling */ /** * irq_free_descs - free irq descriptors * @from: Start of descriptor range * @cnt: Number of consecutive irqs to free */ void irq_free_descs(unsigned int from, unsigned int cnt) { int i; if (from >= nr_irqs || (from + cnt) > nr_irqs) return; mutex_lock(&sparse_irq_lock); for (i = 0; i < cnt; i++) free_desc(from + i); mutex_unlock(&sparse_irq_lock); } EXPORT_SYMBOL_GPL(irq_free_descs); /** * __irq_alloc_descs - allocate and initialize a range of irq descriptors * @irq: Allocate for specific irq number if irq >= 0 * @from: Start the search from this irq number * @cnt: Number of consecutive irqs to allocate. * @node: Preferred node on which the irq descriptor should be allocated * @owner: Owning module (can be NULL) * @affinity: Optional pointer to an affinity mask array of size @cnt which * hints where the irq descriptors should be allocated and which * default affinities to use * * Returns the first irq number or error code */ int __ref __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node, struct module *owner, const struct irq_affinity_desc *affinity) { int start, ret; if (!cnt) return -EINVAL; if (irq >= 0) { if (from > irq) return -EINVAL; from = irq; } else { /* * For interrupts which are freely allocated the * architecture can force a lower bound to the @from * argument. x86 uses this to exclude the GSI space. */ from = arch_dynirq_lower_bound(from); } mutex_lock(&sparse_irq_lock); start = irq_find_free_area(from, cnt); ret = -EEXIST; if (irq >=0 && start != irq) goto unlock; if (start + cnt > nr_irqs) { ret = irq_expand_nr_irqs(start + cnt); if (ret) goto unlock; } ret = alloc_descs(start, cnt, node, affinity, owner); unlock: mutex_unlock(&sparse_irq_lock); return ret; } EXPORT_SYMBOL_GPL(__irq_alloc_descs); /** * irq_get_next_irq - get next allocated irq number * @offset: where to start the search * * Returns next irq number after offset or nr_irqs if none is found. */ unsigned int irq_get_next_irq(unsigned int offset) { return irq_find_at_or_after(offset); } struct irq_desc * __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus, unsigned int check) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { if (check & _IRQ_DESC_CHECK) { if ((check & _IRQ_DESC_PERCPU) && !irq_settings_is_per_cpu_devid(desc)) return NULL; if (!(check & _IRQ_DESC_PERCPU) && irq_settings_is_per_cpu_devid(desc)) return NULL; } if (bus) chip_bus_lock(desc); raw_spin_lock_irqsave(&desc->lock, *flags); } return desc; } void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus) __releases(&desc->lock) { raw_spin_unlock_irqrestore(&desc->lock, flags); if (bus) chip_bus_sync_unlock(desc); } int irq_set_percpu_devid_partition(unsigned int irq, const struct cpumask *affinity) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || desc->percpu_enabled) return -EINVAL; desc->percpu_enabled = kzalloc(sizeof(*desc->percpu_enabled), GFP_KERNEL); if (!desc->percpu_enabled) return -ENOMEM; desc->percpu_affinity = affinity ? : cpu_possible_mask; irq_set_percpu_devid_flags(irq); return 0; } int irq_set_percpu_devid(unsigned int irq) { return irq_set_percpu_devid_partition(irq, NULL); } int irq_get_percpu_devid_partition(unsigned int irq, struct cpumask *affinity) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->percpu_enabled) return -EINVAL; if (affinity) cpumask_copy(affinity, desc->percpu_affinity); return 0; } EXPORT_SYMBOL_GPL(irq_get_percpu_devid_partition); void kstat_incr_irq_this_cpu(unsigned int irq) { kstat_incr_irqs_this_cpu(irq_to_desc(irq)); } /** * kstat_irqs_cpu - Get the statistics for an interrupt on a cpu * @irq: The interrupt number * @cpu: The cpu number * * Returns the sum of interrupt counts on @cpu since boot for * @irq. The caller must ensure that the interrupt is not removed * concurrently. */ unsigned int kstat_irqs_cpu(unsigned int irq, int cpu) { struct irq_desc *desc = irq_to_desc(irq); return desc && desc->kstat_irqs ? per_cpu(desc->kstat_irqs->cnt, cpu) : 0; } unsigned int kstat_irqs_desc(struct irq_desc *desc, const struct cpumask *cpumask) { unsigned int sum = 0; int cpu; if (!irq_settings_is_per_cpu_devid(desc) && !irq_settings_is_per_cpu(desc) && !irq_is_nmi(desc)) return data_race(desc->tot_count); for_each_cpu(cpu, cpumask) sum += data_race(per_cpu(desc->kstat_irqs->cnt, cpu)); return sum; } static unsigned int kstat_irqs(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return kstat_irqs_desc(desc, cpu_possible_mask); } #ifdef CONFIG_GENERIC_IRQ_STAT_SNAPSHOT void kstat_snapshot_irqs(void) { struct irq_desc *desc; unsigned int irq; for_each_irq_desc(irq, desc) { if (!desc->kstat_irqs) continue; this_cpu_write(desc->kstat_irqs->ref, this_cpu_read(desc->kstat_irqs->cnt)); } } unsigned int kstat_get_irq_since_snapshot(unsigned int irq) { struct irq_desc *desc = irq_to_desc(irq); if (!desc || !desc->kstat_irqs) return 0; return this_cpu_read(desc->kstat_irqs->cnt) - this_cpu_read(desc->kstat_irqs->ref); } #endif /** * kstat_irqs_usr - Get the statistics for an interrupt from thread context * @irq: The interrupt number * * Returns the sum of interrupt counts on all cpus since boot for @irq. * * It uses rcu to protect the access since a concurrent removal of an * interrupt descriptor is observing an rcu grace period before * delayed_free_desc()/irq_kobj_release(). */ unsigned int kstat_irqs_usr(unsigned int irq) { unsigned int sum; rcu_read_lock(); sum = kstat_irqs(irq); rcu_read_unlock(); return sum; } #ifdef CONFIG_LOCKDEP void __irq_set_lockdep_class(unsigned int irq, struct lock_class_key *lock_class, struct lock_class_key *request_class) { struct irq_desc *desc = irq_to_desc(irq); if (desc) { lockdep_set_class(&desc->lock, lock_class); lockdep_set_class(&desc->request_mutex, request_class); } } EXPORT_SYMBOL_GPL(__irq_set_lockdep_class); #endif |
| 162 162 147 147 1 147 29 29 147 163 162 163 163 162 161 162 162 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 | // SPDX-License-Identifier: GPL-2.0 #include <linux/compiler.h> #include <linux/export.h> #include <linux/fault-inject-usercopy.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 __always_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, mask; /* 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); /* * Note that we mask out the bytes following the NUL. This is * important to do because string oblivious code may read past * the NUL. For those routines, we don't want to give them * potentially random bytes after the NUL in `src`. * * One example of such code is BPF map keys. BPF treats map keys * as an opaque set of bytes. Without the post-NUL mask, any BPF * maps keyed by strings returned from strncpy_from_user() may * have multiple entries for semantically identical strings. */ if (has_zero(c, &data, &constants)) { data = prep_zero_mask(c, data, &constants); data = create_zero_mask(data); mask = zero_bytemask(data); *(unsigned long *)(dst+res) = c & mask; return res + find_zero(data); } *(unsigned long *)(dst+res) = c; 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; might_fault(); if (should_fail_usercopy()) return -EFAULT; if (unlikely(count <= 0)) return 0; max_addr = TASK_SIZE_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_read_access_begin(src, max)) { retval = do_strncpy_from_user(dst, src, count, max); user_read_access_end(); return retval; } } return -EFAULT; } EXPORT_SYMBOL(strncpy_from_user); |
| 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Multi-level security (MLS) policy operations. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2006 Trusted Computer Solutions, Inc. * * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support to import/export the MLS label from NetLabel * Copyright (X) Hewlett-Packard Development Company, L.P., 2006 */ #ifndef _SS_MLS_H_ #define _SS_MLS_H_ #include <linux/jhash.h> #include "context.h" #include "ebitmap.h" #include "policydb.h" int mls_compute_context_len(struct policydb *p, struct context *context); void mls_sid_to_context(struct policydb *p, struct context *context, char **scontext); int mls_context_isvalid(struct policydb *p, struct context *c); int mls_range_isvalid(struct policydb *p, struct mls_range *r); int mls_level_isvalid(struct policydb *p, struct mls_level *l); int mls_context_to_sid(struct policydb *p, char oldc, char *scontext, struct context *context, struct sidtab *s, u32 def_sid); int mls_from_string(struct policydb *p, char *str, struct context *context, gfp_t gfp_mask); int mls_range_set(struct context *context, struct mls_range *range); int mls_convert_context(struct policydb *oldp, struct policydb *newp, struct context *oldc, struct context *newc); int mls_compute_sid(struct policydb *p, struct context *scontext, struct context *tcontext, u16 tclass, u32 specified, struct context *newcontext, bool sock); int mls_setup_user_range(struct policydb *p, struct context *fromcon, struct user_datum *user, struct context *usercon); #ifdef CONFIG_NETLABEL void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr); void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr); int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr); int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr); #else static inline void mls_export_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { return; } static inline void mls_import_netlbl_lvl(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { return; } static inline int mls_export_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { return -ENOMEM; } static inline int mls_import_netlbl_cat(struct policydb *p, struct context *context, struct netlbl_lsm_secattr *secattr) { return -ENOMEM; } #endif static inline u32 mls_range_hash(const struct mls_range *r, u32 hash) { hash = jhash_2words(r->level[0].sens, r->level[1].sens, hash); hash = ebitmap_hash(&r->level[0].cat, hash); hash = ebitmap_hash(&r->level[1].cat, hash); return hash; } #endif /* _SS_MLS_H */ |
| 1 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2016 Linaro * Author: Christoffer Dall <christoffer.dall@linaro.org> */ #include <linux/cpu.h> #include <linux/debugfs.h> #include <linux/interrupt.h> #include <linux/kvm_host.h> #include <linux/seq_file.h> #include <kvm/arm_vgic.h> #include <asm/kvm_mmu.h> #include "vgic.h" /* * Structure to control looping through the entire vgic state. We start at * zero for each field and move upwards. So, if dist_id is 0 we print the * distributor info. When dist_id is 1, we have already printed it and move * on. * * When vcpu_id < nr_cpus we print the vcpu info until vcpu_id == nr_cpus and * so on. */ struct vgic_state_iter { int nr_cpus; int nr_spis; int nr_lpis; int dist_id; int vcpu_id; unsigned long intid; int lpi_idx; }; static void iter_next(struct kvm *kvm, struct vgic_state_iter *iter) { struct vgic_dist *dist = &kvm->arch.vgic; if (iter->dist_id == 0) { iter->dist_id++; return; } /* * Let the xarray drive the iterator after the last SPI, as the iterator * has exhausted the sequentially-allocated INTID space. */ if (iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS - 1)) { if (iter->lpi_idx < iter->nr_lpis) xa_find_after(&dist->lpi_xa, &iter->intid, VGIC_LPI_MAX_INTID, LPI_XA_MARK_DEBUG_ITER); iter->lpi_idx++; return; } iter->intid++; if (iter->intid == VGIC_NR_PRIVATE_IRQS && ++iter->vcpu_id < iter->nr_cpus) iter->intid = 0; } static int iter_mark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; int nr_lpis = 0; xa_for_each(&dist->lpi_xa, intid, irq) { if (!vgic_try_get_irq_kref(irq)) continue; xa_set_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); nr_lpis++; } return nr_lpis; } static void iter_unmark_lpis(struct kvm *kvm) { struct vgic_dist *dist = &kvm->arch.vgic; struct vgic_irq *irq; unsigned long intid; xa_for_each(&dist->lpi_xa, intid, irq) { xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER); vgic_put_irq(kvm, irq); } } static void iter_init(struct kvm *kvm, struct vgic_state_iter *iter, loff_t pos) { int nr_cpus = atomic_read(&kvm->online_vcpus); memset(iter, 0, sizeof(*iter)); iter->nr_cpus = nr_cpus; iter->nr_spis = kvm->arch.vgic.nr_spis; if (kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3) iter->nr_lpis = iter_mark_lpis(kvm); /* Fast forward to the right position if needed */ while (pos--) iter_next(kvm, iter); } static bool end_of_vgic(struct vgic_state_iter *iter) { return iter->dist_id > 0 && iter->vcpu_id == iter->nr_cpus && iter->intid >= (iter->nr_spis + VGIC_NR_PRIVATE_IRQS) && iter->lpi_idx > iter->nr_lpis; } static void *vgic_debug_start(struct seq_file *s, loff_t *pos) { struct kvm *kvm = s->private; struct vgic_state_iter *iter; mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; if (iter) { iter = ERR_PTR(-EBUSY); goto out; } iter = kmalloc(sizeof(*iter), GFP_KERNEL); if (!iter) { iter = ERR_PTR(-ENOMEM); goto out; } iter_init(kvm, iter, *pos); kvm->arch.vgic.iter = iter; if (end_of_vgic(iter)) iter = NULL; out: mutex_unlock(&kvm->arch.config_lock); return iter; } static void *vgic_debug_next(struct seq_file *s, void *v, loff_t *pos) { struct kvm *kvm = s->private; struct vgic_state_iter *iter = kvm->arch.vgic.iter; ++*pos; iter_next(kvm, iter); if (end_of_vgic(iter)) iter = NULL; return iter; } static void vgic_debug_stop(struct seq_file *s, void *v) { struct kvm *kvm = s->private; struct vgic_state_iter *iter; /* * If the seq file wasn't properly opened, there's nothing to clearn * up. */ if (IS_ERR(v)) return; mutex_lock(&kvm->arch.config_lock); iter = kvm->arch.vgic.iter; iter_unmark_lpis(kvm); kfree(iter); kvm->arch.vgic.iter = NULL; mutex_unlock(&kvm->arch.config_lock); } static void print_dist_state(struct seq_file *s, struct vgic_dist *dist, struct vgic_state_iter *iter) { bool v3 = dist->vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3; seq_printf(s, "Distributor\n"); seq_printf(s, "===========\n"); seq_printf(s, "vgic_model:\t%s\n", v3 ? "GICv3" : "GICv2"); seq_printf(s, "nr_spis:\t%d\n", dist->nr_spis); if (v3) seq_printf(s, "nr_lpis:\t%d\n", iter->nr_lpis); seq_printf(s, "enabled:\t%d\n", dist->enabled); seq_printf(s, "\n"); seq_printf(s, "P=pending_latch, L=line_level, A=active\n"); seq_printf(s, "E=enabled, H=hw, C=config (level=1, edge=0)\n"); seq_printf(s, "G=group\n"); } static void print_header(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { int id = 0; char *hdr = "SPI "; if (vcpu) { hdr = "VCPU"; id = vcpu->vcpu_idx; } seq_printf(s, "\n"); seq_printf(s, "%s%2d TYP ID TGT_ID PLAEHCG HWID TARGET SRC PRI VCPU_ID\n", hdr, id); seq_printf(s, "----------------------------------------------------------------\n"); } static void print_irq_state(struct seq_file *s, struct vgic_irq *irq, struct kvm_vcpu *vcpu) { char *type; bool pending; if (irq->intid < VGIC_NR_SGIS) type = "SGI"; else if (irq->intid < VGIC_NR_PRIVATE_IRQS) type = "PPI"; else if (irq->intid < VGIC_MAX_SPI) type = "SPI"; else type = "LPI"; if (irq->intid ==0 || irq->intid == VGIC_NR_PRIVATE_IRQS) print_header(s, irq, vcpu); pending = irq->pending_latch; if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; err = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &pending); WARN_ON_ONCE(err); } seq_printf(s, " %s %4d " " %2d " "%d%d%d%d%d%d%d " "%8d " "%8x " " %2x " "%3d " " %2d " "\n", type, irq->intid, (irq->target_vcpu) ? irq->target_vcpu->vcpu_idx : -1, pending, irq->line_level, irq->active, irq->enabled, irq->hw, irq->config == VGIC_CONFIG_LEVEL, irq->group, irq->hwintid, irq->mpidr, irq->source, irq->priority, (irq->vcpu) ? irq->vcpu->vcpu_idx : -1); } static int vgic_debug_show(struct seq_file *s, void *v) { struct kvm *kvm = s->private; struct vgic_state_iter *iter = v; struct vgic_irq *irq; struct kvm_vcpu *vcpu = NULL; unsigned long flags; if (iter->dist_id == 0) { print_dist_state(s, &kvm->arch.vgic, iter); return 0; } if (!kvm->arch.vgic.initialized) return 0; if (iter->vcpu_id < iter->nr_cpus) vcpu = kvm_get_vcpu(kvm, iter->vcpu_id); /* * Expect this to succeed, as iter_mark_lpis() takes a reference on * every LPI to be visited. */ irq = vgic_get_irq(kvm, vcpu, iter->intid); if (WARN_ON_ONCE(!irq)) return -EINVAL; raw_spin_lock_irqsave(&irq->irq_lock, flags); print_irq_state(s, irq, vcpu); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(kvm, irq); return 0; } static const struct seq_operations vgic_debug_sops = { .start = vgic_debug_start, .next = vgic_debug_next, .stop = vgic_debug_stop, .show = vgic_debug_show }; DEFINE_SEQ_ATTRIBUTE(vgic_debug); void vgic_debug_init(struct kvm *kvm) { debugfs_create_file("vgic-state", 0444, kvm->debugfs_dentry, kvm, &vgic_debug_fops); } void vgic_debug_destroy(struct kvm *kvm) { } |
| 150 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 | // SPDX-License-Identifier: GPL-2.0 #include <linux/kernel.h> #include <linux/of.h> #include <linux/of_device.h> #include <linux/of_address.h> #include <linux/of_iommu.h> #include <linux/of_reserved_mem.h> #include <linux/dma-direct.h> /* for bus_dma_region */ #include <linux/dma-map-ops.h> #include <linux/init.h> #include <linux/mod_devicetable.h> #include <linux/slab.h> #include <linux/platform_device.h> #include <asm/errno.h> #include "of_private.h" /** * of_match_device - Tell if a struct device matches an of_device_id list * @matches: array of of device match structures to search in * @dev: the of device structure to match against * * Used by a driver to check whether an platform_device present in the * system is in its list of supported devices. */ const struct of_device_id *of_match_device(const struct of_device_id *matches, const struct device *dev) { if (!matches || !dev->of_node || dev->of_node_reused) return NULL; return of_match_node(matches, dev->of_node); } EXPORT_SYMBOL(of_match_device); static void of_dma_set_restricted_buffer(struct device *dev, struct device_node *np) { struct device_node *node, *of_node = dev->of_node; int count, i; if (!IS_ENABLED(CONFIG_DMA_RESTRICTED_POOL)) return; count = of_property_count_elems_of_size(of_node, "memory-region", sizeof(u32)); /* * If dev->of_node doesn't exist or doesn't contain memory-region, try * the OF node having DMA configuration. */ if (count <= 0) { of_node = np; count = of_property_count_elems_of_size( of_node, "memory-region", sizeof(u32)); } for (i = 0; i < count; i++) { node = of_parse_phandle(of_node, "memory-region", i); /* * There might be multiple memory regions, but only one * restricted-dma-pool region is allowed. */ if (of_device_is_compatible(node, "restricted-dma-pool") && of_device_is_available(node)) { of_node_put(node); break; } of_node_put(node); } /* * Attempt to initialize a restricted-dma-pool region if one was found. * Note that count can hold a negative error code. */ if (i < count && of_reserved_mem_device_init_by_idx(dev, of_node, i)) dev_warn(dev, "failed to initialise \"restricted-dma-pool\" memory node\n"); } /** * of_dma_configure_id - Setup DMA configuration * @dev: Device to apply DMA configuration * @np: Pointer to OF node having DMA configuration * @force_dma: Whether device is to be set up by of_dma_configure() even if * DMA capability is not explicitly described by firmware. * @id: Optional const pointer value input id * * Try to get devices's DMA configuration from DT and update it * accordingly. * * If platform code needs to use its own special DMA configuration, it * can use a platform bus notifier and handle BUS_NOTIFY_ADD_DEVICE events * to fix up DMA configuration. */ int of_dma_configure_id(struct device *dev, struct device_node *np, bool force_dma, const u32 *id) { const struct bus_dma_region *map = NULL; struct device_node *bus_np; u64 mask, end = 0; bool coherent; int iommu_ret; int ret; if (np == dev->of_node) bus_np = __of_get_dma_parent(np); else bus_np = of_node_get(np); ret = of_dma_get_range(bus_np, &map); of_node_put(bus_np); if (ret < 0) { /* * For legacy reasons, we have to assume some devices need * DMA configuration regardless of whether "dma-ranges" is * correctly specified or not. */ if (!force_dma) return ret == -ENODEV ? 0 : ret; } else { /* Determine the overall bounds of all DMA regions */ end = dma_range_map_max(map); } /* * If @dev is expected to be DMA-capable then the bus code that created * it should have initialised its dma_mask pointer by this point. For * now, we'll continue the legacy behaviour of coercing it to the * coherent mask if not, but we'll no longer do so quietly. */ if (!dev->dma_mask) { dev_warn(dev, "DMA mask not set\n"); dev->dma_mask = &dev->coherent_dma_mask; } if (!end && dev->coherent_dma_mask) end = dev->coherent_dma_mask; else if (!end) end = (1ULL << 32) - 1; /* * Limit coherent and dma mask based on size and default mask * set by the driver. */ mask = DMA_BIT_MASK(ilog2(end) + 1); dev->coherent_dma_mask &= mask; *dev->dma_mask &= mask; /* ...but only set bus limit and range map if we found valid dma-ranges earlier */ if (!ret) { dev->bus_dma_limit = end; dev->dma_range_map = map; } coherent = of_dma_is_coherent(np); dev_dbg(dev, "device is%sdma coherent\n", coherent ? " " : " not "); iommu_ret = of_iommu_configure(dev, np, id); if (iommu_ret == -EPROBE_DEFER) { /* Don't touch range map if it wasn't set from a valid dma-ranges */ if (!ret) dev->dma_range_map = NULL; kfree(map); return -EPROBE_DEFER; } else if (iommu_ret == -ENODEV) { dev_dbg(dev, "device is not behind an iommu\n"); } else if (iommu_ret) { dev_err(dev, "iommu configuration for device failed with %pe\n", ERR_PTR(iommu_ret)); /* * Historically this routine doesn't fail driver probing * due to errors in of_iommu_configure() */ } else dev_dbg(dev, "device is behind an iommu\n"); arch_setup_dma_ops(dev, coherent); if (iommu_ret) of_dma_set_restricted_buffer(dev, np); return 0; } EXPORT_SYMBOL_GPL(of_dma_configure_id); const void *of_device_get_match_data(const struct device *dev) { const struct of_device_id *match; match = of_match_device(dev->driver->of_match_table, dev); if (!match) return NULL; return match->data; } EXPORT_SYMBOL(of_device_get_match_data); /** * of_device_modalias - Fill buffer with newline terminated modalias string * @dev: Calling device * @str: Modalias string * @len: Size of @str */ ssize_t of_device_modalias(struct device *dev, char *str, ssize_t len) { ssize_t sl; if (!dev || !dev->of_node || dev->of_node_reused) return -ENODEV; sl = of_modalias(dev->of_node, str, len - 2); if (sl < 0) return sl; if (sl > len - 2) return -ENOMEM; str[sl++] = '\n'; str[sl] = 0; return sl; } EXPORT_SYMBOL_GPL(of_device_modalias); /** * of_device_uevent - Display OF related uevent information * @dev: Device to display the uevent information for * @env: Kernel object's userspace event reference to fill up */ void of_device_uevent(const struct device *dev, struct kobj_uevent_env *env) { const char *compat, *type; struct alias_prop *app; struct property *p; int seen = 0; if ((!dev) || (!dev->of_node)) return; add_uevent_var(env, "OF_NAME=%pOFn", dev->of_node); add_uevent_var(env, "OF_FULLNAME=%pOF", dev->of_node); type = of_node_get_device_type(dev->of_node); if (type) add_uevent_var(env, "OF_TYPE=%s", type); /* Since the compatible field can contain pretty much anything * it's not really legal to split it out with commas. We split it * up using a number of environment variables instead. */ of_property_for_each_string(dev->of_node, "compatible", p, compat) { add_uevent_var(env, "OF_COMPATIBLE_%d=%s", seen, compat); seen++; } add_uevent_var(env, "OF_COMPATIBLE_N=%d", seen); seen = 0; mutex_lock(&of_mutex); list_for_each_entry(app, &aliases_lookup, link) { if (dev->of_node == app->np) { add_uevent_var(env, "OF_ALIAS_%d=%s", seen, app->alias); seen++; } } mutex_unlock(&of_mutex); } EXPORT_SYMBOL_GPL(of_device_uevent); int of_device_uevent_modalias(const struct device *dev, struct kobj_uevent_env *env) { int sl; if ((!dev) || (!dev->of_node) || dev->of_node_reused) return -ENODEV; /* Devicetree modalias is tricky, we add it in 2 steps */ if (add_uevent_var(env, "MODALIAS=")) return -ENOMEM; sl = of_modalias(dev->of_node, &env->buf[env->buflen-1], sizeof(env->buf) - env->buflen); if (sl < 0) return sl; if (sl >= (sizeof(env->buf) - env->buflen)) return -ENOMEM; env->buflen += sl; return 0; } EXPORT_SYMBOL_GPL(of_device_uevent_modalias); /** * of_device_make_bus_id - Use the device node data to assign a unique name * @dev: pointer to device structure that is linked to a device tree node * * This routine will first try using the translated bus address to * derive a unique name. If it cannot, then it will prepend names from * parent nodes until a unique name can be derived. */ void of_device_make_bus_id(struct device *dev) { struct device_node *node = dev->of_node; const __be32 *reg; u64 addr; u32 mask; /* Construct the name, using parent nodes if necessary to ensure uniqueness */ while (node->parent) { /* * If the address can be translated, then that is as much * uniqueness as we need. Make it the first component and return */ reg = of_get_property(node, "reg", NULL); if (reg && (addr = of_translate_address(node, reg)) != OF_BAD_ADDR) { if (!of_property_read_u32(node, "mask", &mask)) dev_set_name(dev, dev_name(dev) ? "%llx.%x.%pOFn:%s" : "%llx.%x.%pOFn", addr, ffs(mask) - 1, node, dev_name(dev)); else dev_set_name(dev, dev_name(dev) ? "%llx.%pOFn:%s" : "%llx.%pOFn", addr, node, dev_name(dev)); return; } /* format arguments only used if dev_name() resolves to NULL */ dev_set_name(dev, dev_name(dev) ? "%s:%s" : "%s", kbasename(node->full_name), dev_name(dev)); node = node->parent; } } EXPORT_SYMBOL_GPL(of_device_make_bus_id); |
| 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 | #ifndef _LINUX_HASH_H #define _LINUX_HASH_H /* Fast hashing routine for ints, longs and pointers. (C) 2002 Nadia Yvette Chambers, IBM */ #include <asm/types.h> #include <linux/compiler.h> /* * The "GOLDEN_RATIO_PRIME" is used in ifs/btrfs/brtfs_inode.h and * fs/inode.c. It's not actually prime any more (the previous primes * were actively bad for hashing), but the name remains. */ #if BITS_PER_LONG == 32 #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_32 #define hash_long(val, bits) hash_32(val, bits) #elif BITS_PER_LONG == 64 #define hash_long(val, bits) hash_64(val, bits) #define GOLDEN_RATIO_PRIME GOLDEN_RATIO_64 #else #error Wordsize not 32 or 64 #endif /* * This hash multiplies the input by a large odd number and takes the * high bits. Since multiplication propagates changes to the most * significant end only, it is essential that the high bits of the * product be used for the hash value. * * Chuck Lever verified the effectiveness of this technique: * http://www.citi.umich.edu/techreports/reports/citi-tr-00-1.pdf * * Although a random odd number will do, it turns out that the golden * ratio phi = (sqrt(5)-1)/2, or its negative, has particularly nice * properties. (See Knuth vol 3, section 6.4, exercise 9.) * * These are the negative, (1 - phi) = phi**2 = (3 - sqrt(5))/2, * which is very slightly easier to multiply by and makes no * difference to the hash distribution. */ #define GOLDEN_RATIO_32 0x61C88647 #define GOLDEN_RATIO_64 0x61C8864680B583EBull #ifdef CONFIG_HAVE_ARCH_HASH /* This header may use the GOLDEN_RATIO_xx constants */ #include <asm/hash.h> #endif /* * The _generic versions exist only so lib/test_hash.c can compare * the arch-optimized versions with the generic. * * Note that if you change these, any <asm/hash.h> that aren't updated * to match need to have their HAVE_ARCH_* define values updated so the * self-test will not false-positive. */ #ifndef HAVE_ARCH__HASH_32 #define __hash_32 __hash_32_generic #endif static inline u32 __hash_32_generic(u32 val) { return val * GOLDEN_RATIO_32; } static inline u32 hash_32(u32 val, unsigned int bits) { /* High bits are more random, so use them. */ return __hash_32(val) >> (32 - bits); } #ifndef HAVE_ARCH_HASH_64 #define hash_64 hash_64_generic #endif static __always_inline u32 hash_64_generic(u64 val, unsigned int bits) { #if BITS_PER_LONG == 64 /* 64x64-bit multiply is efficient on all 64-bit processors */ return val * GOLDEN_RATIO_64 >> (64 - bits); #else /* Hash 64 bits using only 32x32-bit multiply. */ return hash_32((u32)val ^ __hash_32(val >> 32), bits); #endif } static inline u32 hash_ptr(const void *ptr, unsigned int bits) { return hash_long((unsigned long)ptr, bits); } /* This really should be called fold32_ptr; it does no hashing to speak of. */ static inline u32 hash32_ptr(const void *ptr) { unsigned long val = (unsigned long)ptr; #if BITS_PER_LONG == 64 val ^= (val >> 32); #endif return (u32)val; } #endif /* _LINUX_HASH_H */ |
| 61 61 61 61 61 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Implementation of the policy database. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* * Updated: Trusted Computer Solutions, Inc. <dgoeddel@trustedcs.com> * Support for enhanced MLS infrastructure. * Copyright (C) 2004-2005 Trusted Computer Solutions, Inc. * * Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003-2004 Tresys Technology, LLC * * Updated: Hewlett-Packard <paul@paul-moore.com> * Added support for the policy capability bitmap * Copyright (C) 2007 Hewlett-Packard Development Company, L.P. * * Update: Mellanox Techonologies * Added Infiniband support * Copyright (C) 2016 Mellanox Techonologies */ #include <linux/kernel.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/errno.h> #include <linux/audit.h> #include "security.h" #include "policydb.h" #include "conditional.h" #include "mls.h" #include "services.h" #ifdef CONFIG_SECURITY_SELINUX_DEBUG /* clang-format off */ static const char *const symtab_name[SYM_NUM] = { "common prefixes", "classes", "roles", "types", "users", "bools", "levels", "categories", }; /* clang-format off */ #endif struct policydb_compat_info { unsigned int version; unsigned int sym_num; unsigned int ocon_num; }; /* These need to be updated if SYM_NUM or OCON_NUM changes */ static const struct policydb_compat_info policydb_compat[] = { { .version = POLICYDB_VERSION_BASE, .sym_num = SYM_NUM - 3, .ocon_num = OCON_NUM - 3, }, { .version = POLICYDB_VERSION_BOOL, .sym_num = SYM_NUM - 2, .ocon_num = OCON_NUM - 3, }, { .version = POLICYDB_VERSION_IPV6, .sym_num = SYM_NUM - 2, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_NLCLASS, .sym_num = SYM_NUM - 2, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_MLS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_AVTAB, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_RANGETRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_POLCAP, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_PERMISSIVE, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_BOUNDARY, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_FILENAME_TRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_ROLETRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_NEW_OBJECT_DEFAULTS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_DEFAULT_TYPE, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_CONSTRAINT_NAMES, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_XPERMS_IOCTL, .sym_num = SYM_NUM, .ocon_num = OCON_NUM - 2, }, { .version = POLICYDB_VERSION_INFINIBAND, .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, { .version = POLICYDB_VERSION_GLBLUB, .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, { .version = POLICYDB_VERSION_COMP_FTRANS, .sym_num = SYM_NUM, .ocon_num = OCON_NUM, }, }; static const struct policydb_compat_info * policydb_lookup_compat(unsigned int version) { unsigned int i; for (i = 0; i < ARRAY_SIZE(policydb_compat); i++) { if (policydb_compat[i].version == version) return &policydb_compat[i]; } return NULL; } /* * The following *_destroy functions are used to * free any memory allocated for each kind of * symbol data in the policy database. */ static int perm_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static int common_destroy(void *key, void *datum, void *p) { struct common_datum *comdatum; kfree(key); if (datum) { comdatum = datum; hashtab_map(&comdatum->permissions.table, perm_destroy, NULL); hashtab_destroy(&comdatum->permissions.table); } kfree(datum); return 0; } static void constraint_expr_destroy(struct constraint_expr *expr) { if (expr) { ebitmap_destroy(&expr->names); if (expr->type_names) { ebitmap_destroy(&expr->type_names->types); ebitmap_destroy(&expr->type_names->negset); kfree(expr->type_names); } kfree(expr); } } static int cls_destroy(void *key, void *datum, void *p) { struct class_datum *cladatum; struct constraint_node *constraint, *ctemp; struct constraint_expr *e, *etmp; kfree(key); if (datum) { cladatum = datum; hashtab_map(&cladatum->permissions.table, perm_destroy, NULL); hashtab_destroy(&cladatum->permissions.table); constraint = cladatum->constraints; while (constraint) { e = constraint->expr; while (e) { etmp = e; e = e->next; constraint_expr_destroy(etmp); } ctemp = constraint; constraint = constraint->next; kfree(ctemp); } constraint = cladatum->validatetrans; while (constraint) { e = constraint->expr; while (e) { etmp = e; e = e->next; constraint_expr_destroy(etmp); } ctemp = constraint; constraint = constraint->next; kfree(ctemp); } kfree(cladatum->comkey); } kfree(datum); return 0; } static int role_destroy(void *key, void *datum, void *p) { struct role_datum *role; kfree(key); if (datum) { role = datum; ebitmap_destroy(&role->dominates); ebitmap_destroy(&role->types); } kfree(datum); return 0; } static int type_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static int user_destroy(void *key, void *datum, void *p) { struct user_datum *usrdatum; kfree(key); if (datum) { usrdatum = datum; ebitmap_destroy(&usrdatum->roles); ebitmap_destroy(&usrdatum->range.level[0].cat); ebitmap_destroy(&usrdatum->range.level[1].cat); ebitmap_destroy(&usrdatum->dfltlevel.cat); } kfree(datum); return 0; } static int sens_destroy(void *key, void *datum, void *p) { struct level_datum *levdatum; kfree(key); if (datum) { levdatum = datum; if (levdatum->level) ebitmap_destroy(&levdatum->level->cat); kfree(levdatum->level); } kfree(datum); return 0; } static int cat_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } /* clang-format off */ static int (*const destroy_f[SYM_NUM])(void *key, void *datum, void *datap) = { common_destroy, cls_destroy, role_destroy, type_destroy, user_destroy, cond_destroy_bool, sens_destroy, cat_destroy, }; /* clang-format on */ static int filenametr_destroy(void *key, void *datum, void *p) { struct filename_trans_key *ft = key; struct filename_trans_datum *next, *d = datum; kfree(ft->name); kfree(key); do { ebitmap_destroy(&d->stypes); next = d->next; kfree(d); d = next; } while (unlikely(d)); cond_resched(); return 0; } static int range_tr_destroy(void *key, void *datum, void *p) { struct mls_range *rt = datum; kfree(key); ebitmap_destroy(&rt->level[0].cat); ebitmap_destroy(&rt->level[1].cat); kfree(datum); cond_resched(); return 0; } static int role_tr_destroy(void *key, void *datum, void *p) { kfree(key); kfree(datum); return 0; } static void ocontext_destroy(struct ocontext *c, unsigned int i) { if (!c) return; context_destroy(&c->context[0]); context_destroy(&c->context[1]); if (i == OCON_ISID || i == OCON_FS || i == OCON_NETIF || i == OCON_FSUSE) kfree(c->u.name); kfree(c); } /* * Initialize the role table. */ static int roles_init(struct policydb *p) { char *key = NULL; int rc; struct role_datum *role; role = kzalloc(sizeof(*role), GFP_KERNEL); if (!role) return -ENOMEM; rc = -EINVAL; role->value = ++p->p_roles.nprim; if (role->value != OBJECT_R_VAL) goto out; rc = -ENOMEM; key = kstrdup(OBJECT_R, GFP_KERNEL); if (!key) goto out; rc = symtab_insert(&p->p_roles, key, role); if (rc) goto out; return 0; out: kfree(key); kfree(role); return rc; } static u32 filenametr_hash(const void *k) { const struct filename_trans_key *ft = k; unsigned long salt = ft->ttype ^ ft->tclass; return full_name_hash((void *)salt, ft->name, strlen(ft->name)); } static int filenametr_cmp(const void *k1, const void *k2) { const struct filename_trans_key *ft1 = k1; const struct filename_trans_key *ft2 = k2; int v; v = ft1->ttype - ft2->ttype; if (v) return v; v = ft1->tclass - ft2->tclass; if (v) return v; return strcmp(ft1->name, ft2->name); } static const struct hashtab_key_params filenametr_key_params = { .hash = filenametr_hash, .cmp = filenametr_cmp, }; struct filename_trans_datum * policydb_filenametr_search(struct policydb *p, struct filename_trans_key *key) { return hashtab_search(&p->filename_trans, key, filenametr_key_params); } static u32 rangetr_hash(const void *k) { const struct range_trans *key = k; return key->source_type + (key->target_type << 3) + (key->target_class << 5); } static int rangetr_cmp(const void *k1, const void *k2) { const struct range_trans *key1 = k1, *key2 = k2; int v; v = key1->source_type - key2->source_type; if (v) return v; v = key1->target_type - key2->target_type; if (v) return v; v = key1->target_class - key2->target_class; return v; } static const struct hashtab_key_params rangetr_key_params = { .hash = rangetr_hash, .cmp = rangetr_cmp, }; struct mls_range *policydb_rangetr_search(struct policydb *p, struct range_trans *key) { return hashtab_search(&p->range_tr, key, rangetr_key_params); } static u32 role_trans_hash(const void *k) { const struct role_trans_key *key = k; return jhash_3words(key->role, key->type, (u32)key->tclass << 16 | key->tclass, 0); } static int role_trans_cmp(const void *k1, const void *k2) { const struct role_trans_key *key1 = k1, *key2 = k2; int v; v = key1->role - key2->role; if (v) return v; v = key1->type - key2->type; if (v) return v; return key1->tclass - key2->tclass; } static const struct hashtab_key_params roletr_key_params = { .hash = role_trans_hash, .cmp = role_trans_cmp, }; struct role_trans_datum *policydb_roletr_search(struct policydb *p, struct role_trans_key *key) { return hashtab_search(&p->role_tr, key, roletr_key_params); } /* * Initialize a policy database structure. */ static void policydb_init(struct policydb *p) { memset(p, 0, sizeof(*p)); avtab_init(&p->te_avtab); cond_policydb_init(p); ebitmap_init(&p->filename_trans_ttypes); ebitmap_init(&p->policycaps); ebitmap_init(&p->permissive_map); } /* * The following *_index functions are used to * define the val_to_name and val_to_struct arrays * in a policy database structure. The val_to_name * arrays are used when converting security context * structures into string representations. The * val_to_struct arrays are used when the attributes * of a class, role, or user are needed. */ static int common_index(void *key, void *datum, void *datap) { struct policydb *p; struct common_datum *comdatum; comdatum = datum; p = datap; if (!comdatum->value || comdatum->value > p->p_commons.nprim) return -EINVAL; p->sym_val_to_name[SYM_COMMONS][comdatum->value - 1] = key; return 0; } static int class_index(void *key, void *datum, void *datap) { struct policydb *p; struct class_datum *cladatum; cladatum = datum; p = datap; if (!cladatum->value || cladatum->value > p->p_classes.nprim) return -EINVAL; p->sym_val_to_name[SYM_CLASSES][cladatum->value - 1] = key; p->class_val_to_struct[cladatum->value - 1] = cladatum; return 0; } static int role_index(void *key, void *datum, void *datap) { struct policydb *p; struct role_datum *role; role = datum; p = datap; if (!role->value || role->value > p->p_roles.nprim || role->bounds > p->p_roles.nprim) return -EINVAL; p->sym_val_to_name[SYM_ROLES][role->value - 1] = key; p->role_val_to_struct[role->value - 1] = role; return 0; } static int type_index(void *key, void *datum, void *datap) { struct policydb *p; struct type_datum *typdatum; typdatum = datum; p = datap; if (typdatum->primary) { if (!typdatum->value || typdatum->value > p->p_types.nprim || typdatum->bounds > p->p_types.nprim) return -EINVAL; p->sym_val_to_name[SYM_TYPES][typdatum->value - 1] = key; p->type_val_to_struct[typdatum->value - 1] = typdatum; } return 0; } static int user_index(void *key, void *datum, void *datap) { struct policydb *p; struct user_datum *usrdatum; usrdatum = datum; p = datap; if (!usrdatum->value || usrdatum->value > p->p_users.nprim || usrdatum->bounds > p->p_users.nprim) return -EINVAL; p->sym_val_to_name[SYM_USERS][usrdatum->value - 1] = key; p->user_val_to_struct[usrdatum->value - 1] = usrdatum; return 0; } static int sens_index(void *key, void *datum, void *datap) { struct policydb *p; struct level_datum *levdatum; levdatum = datum; p = datap; if (!levdatum->isalias) { if (!levdatum->level->sens || levdatum->level->sens > p->p_levels.nprim) return -EINVAL; p->sym_val_to_name[SYM_LEVELS][levdatum->level->sens - 1] = key; } return 0; } static int cat_index(void *key, void *datum, void *datap) { struct policydb *p; struct cat_datum *catdatum; catdatum = datum; p = datap; if (!catdatum->isalias) { if (!catdatum->value || catdatum->value > p->p_cats.nprim) return -EINVAL; p->sym_val_to_name[SYM_CATS][catdatum->value - 1] = key; } return 0; } /* clang-format off */ static int (*const index_f[SYM_NUM])(void *key, void *datum, void *datap) = { common_index, class_index, role_index, type_index, user_index, cond_index_bool, sens_index, cat_index, }; /* clang-format on */ #ifdef CONFIG_SECURITY_SELINUX_DEBUG static void hash_eval(struct hashtab *h, const char *hash_name, const char *hash_details) { struct hashtab_info info; hashtab_stat(h, &info); pr_debug( "SELinux: %s%s%s: %d entries and %d/%d buckets used, longest chain length %d, sum of chain length^2 %llu\n", hash_name, hash_details ? "@" : "", hash_details ?: "", h->nel, info.slots_used, h->size, info.max_chain_len, info.chain2_len_sum); } static void symtab_hash_eval(struct symtab *s) { int i; for (i = 0; i < SYM_NUM; i++) hash_eval(&s[i].table, symtab_name[i], NULL); } #else static inline void hash_eval(struct hashtab *h, const char *hash_name, const char *hash_details) { } static inline void symtab_hash_eval(struct symtab *s) { } #endif /* CONFIG_SECURITY_SELINUX_DEBUG */ /* * Define the other val_to_name and val_to_struct arrays * in a policy database structure. * * Caller must clean up on failure. */ static int policydb_index(struct policydb *p) { int i, rc; if (p->mls_enabled) pr_debug( "SELinux: %d users, %d roles, %d types, %d bools, %d sens, %d cats\n", p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim, p->p_bools.nprim, p->p_levels.nprim, p->p_cats.nprim); else pr_debug("SELinux: %d users, %d roles, %d types, %d bools\n", p->p_users.nprim, p->p_roles.nprim, p->p_types.nprim, p->p_bools.nprim); pr_debug("SELinux: %d classes, %d rules\n", p->p_classes.nprim, p->te_avtab.nel); avtab_hash_eval(&p->te_avtab, "rules"); symtab_hash_eval(p->symtab); p->class_val_to_struct = kcalloc(p->p_classes.nprim, sizeof(*p->class_val_to_struct), GFP_KERNEL); if (!p->class_val_to_struct) return -ENOMEM; p->role_val_to_struct = kcalloc( p->p_roles.nprim, sizeof(*p->role_val_to_struct), GFP_KERNEL); if (!p->role_val_to_struct) return -ENOMEM; p->user_val_to_struct = kcalloc( p->p_users.nprim, sizeof(*p->user_val_to_struct), GFP_KERNEL); if (!p->user_val_to_struct) return -ENOMEM; p->type_val_to_struct = kvcalloc( p->p_types.nprim, sizeof(*p->type_val_to_struct), GFP_KERNEL); if (!p->type_val_to_struct) return -ENOMEM; rc = cond_init_bool_indexes(p); if (rc) goto out; for (i = 0; i < SYM_NUM; i++) { p->sym_val_to_name[i] = kvcalloc(p->symtab[i].nprim, sizeof(char *), GFP_KERNEL); if (!p->sym_val_to_name[i]) return -ENOMEM; rc = hashtab_map(&p->symtab[i].table, index_f[i], p); if (rc) goto out; } rc = 0; out: return rc; } /* * Free any memory allocated by a policy database structure. */ void policydb_destroy(struct policydb *p) { struct ocontext *c, *ctmp; struct genfs *g, *gtmp; u32 i; struct role_allow *ra, *lra = NULL; for (i = 0; i < SYM_NUM; i++) { cond_resched(); hashtab_map(&p->symtab[i].table, destroy_f[i], NULL); hashtab_destroy(&p->symtab[i].table); } for (i = 0; i < SYM_NUM; i++) kvfree(p->sym_val_to_name[i]); kfree(p->class_val_to_struct); kfree(p->role_val_to_struct); kfree(p->user_val_to_struct); kvfree(p->type_val_to_struct); avtab_destroy(&p->te_avtab); for (i = 0; i < OCON_NUM; i++) { cond_resched(); c = p->ocontexts[i]; while (c) { ctmp = c; c = c->next; ocontext_destroy(ctmp, i); } p->ocontexts[i] = NULL; } g = p->genfs; while (g) { cond_resched(); kfree(g->fstype); c = g->head; while (c) { ctmp = c; c = c->next; ocontext_destroy(ctmp, OCON_FSUSE); } gtmp = g; g = g->next; kfree(gtmp); } p->genfs = NULL; cond_policydb_destroy(p); hashtab_map(&p->role_tr, role_tr_destroy, NULL); hashtab_destroy(&p->role_tr); for (ra = p->role_allow; ra; ra = ra->next) { cond_resched(); kfree(lra); lra = ra; } kfree(lra); hashtab_map(&p->filename_trans, filenametr_destroy, NULL); hashtab_destroy(&p->filename_trans); hashtab_map(&p->range_tr, range_tr_destroy, NULL); hashtab_destroy(&p->range_tr); if (p->type_attr_map_array) { for (i = 0; i < p->p_types.nprim; i++) ebitmap_destroy(&p->type_attr_map_array[i]); kvfree(p->type_attr_map_array); } ebitmap_destroy(&p->filename_trans_ttypes); ebitmap_destroy(&p->policycaps); ebitmap_destroy(&p->permissive_map); } /* * Load the initial SIDs specified in a policy database * structure into a SID table. */ int policydb_load_isids(struct policydb *p, struct sidtab *s) { struct ocontext *head, *c; bool isid_init; int rc; rc = sidtab_init(s); if (rc) { pr_err("SELinux: out of memory on SID table init\n"); return rc; } isid_init = ebitmap_get_bit(&p->policycaps, POLICYDB_CAP_USERSPACE_INITIAL_CONTEXT); head = p->ocontexts[OCON_ISID]; for (c = head; c; c = c->next) { u32 sid = c->sid[0]; const char *name = security_get_initial_sid_context(sid); if (sid == SECSID_NULL) { pr_err("SELinux: SID 0 was assigned a context.\n"); sidtab_destroy(s); return -EINVAL; } /* Ignore initial SIDs unused by this kernel. */ if (!name) continue; /* * Also ignore SECINITSID_INIT if the policy doesn't declare * support for it */ if (sid == SECINITSID_INIT && !isid_init) continue; rc = sidtab_set_initial(s, sid, &c->context[0]); if (rc) { pr_err("SELinux: unable to load initial SID %s.\n", name); sidtab_destroy(s); return rc; } /* * If the policy doesn't support the "userspace_initial_context" * capability, set SECINITSID_INIT to the same context as * SECINITSID_KERNEL. This ensures the same behavior as before * the reintroduction of SECINITSID_INIT, where all tasks * started before policy load would initially get the context * corresponding to SECINITSID_KERNEL. */ if (sid == SECINITSID_KERNEL && !isid_init) { rc = sidtab_set_initial(s, SECINITSID_INIT, &c->context[0]); if (rc) { pr_err("SELinux: unable to load initial SID %s.\n", name); sidtab_destroy(s); return rc; } } } return 0; } int policydb_class_isvalid(struct policydb *p, unsigned int class) { if (!class || class > p->p_classes.nprim) return 0; return 1; } int policydb_role_isvalid(struct policydb *p, unsigned int role) { if (!role || role > p->p_roles.nprim) return 0; return 1; } int policydb_type_isvalid(struct policydb *p, unsigned int type) { if (!type || type > p->p_types.nprim) return 0; return 1; } /* * Return 1 if the fields in the security context * structure `c' are valid. Return 0 otherwise. */ int policydb_context_isvalid(struct policydb *p, struct context *c) { struct role_datum *role; struct user_datum *usrdatum; if (!c->role || c->role > p->p_roles.nprim) return 0; if (!c->user || c->user > p->p_users.nprim) return 0; if (!c->type || c->type > p->p_types.nprim) return 0; if (c->role != OBJECT_R_VAL) { /* * Role must be authorized for the type. */ role = p->role_val_to_struct[c->role - 1]; if (!role || !ebitmap_get_bit(&role->types, c->type - 1)) /* role may not be associated with type */ return 0; /* * User must be authorized for the role. */ usrdatum = p->user_val_to_struct[c->user - 1]; if (!usrdatum) return 0; if (!ebitmap_get_bit(&usrdatum->roles, c->role - 1)) /* user may not be associated with role */ return 0; } if (!mls_context_isvalid(p, c)) return 0; return 1; } /* * Read a MLS range structure from a policydb binary * representation file. */ static int mls_read_range_helper(struct mls_range *r, void *fp) { __le32 buf[2]; u32 items; int rc; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; rc = -EINVAL; items = le32_to_cpu(buf[0]); if (items > ARRAY_SIZE(buf)) { pr_err("SELinux: mls: range overflow\n"); goto out; } rc = next_entry(buf, fp, sizeof(u32) * items); if (rc) { pr_err("SELinux: mls: truncated range\n"); goto out; } r->level[0].sens = le32_to_cpu(buf[0]); if (items > 1) r->level[1].sens = le32_to_cpu(buf[1]); else r->level[1].sens = r->level[0].sens; rc = ebitmap_read(&r->level[0].cat, fp); if (rc) { pr_err("SELinux: mls: error reading low categories\n"); goto out; } if (items > 1) { rc = ebitmap_read(&r->level[1].cat, fp); if (rc) { pr_err("SELinux: mls: error reading high categories\n"); goto bad_high; } } else { rc = ebitmap_cpy(&r->level[1].cat, &r->level[0].cat); if (rc) { pr_err("SELinux: mls: out of memory\n"); goto bad_high; } } return 0; bad_high: ebitmap_destroy(&r->level[0].cat); out: return rc; } /* * Read and validate a security context structure * from a policydb binary representation file. */ static int context_read_and_validate(struct context *c, struct policydb *p, void *fp) { __le32 buf[3]; int rc; rc = next_entry(buf, fp, sizeof buf); if (rc) { pr_err("SELinux: context truncated\n"); goto out; } c->user = le32_to_cpu(buf[0]); c->role = le32_to_cpu(buf[1]); c->type = le32_to_cpu(buf[2]); if (p->policyvers >= POLICYDB_VERSION_MLS) { rc = mls_read_range_helper(&c->range, fp); if (rc) { pr_err("SELinux: error reading MLS range of context\n"); goto out; } } rc = -EINVAL; if (!policydb_context_isvalid(p, c)) { pr_err("SELinux: invalid security context\n"); context_destroy(c); goto out; } rc = 0; out: return rc; } /* * The following *_read functions are used to * read the symbol data from a policy database * binary representation file. */ static int str_read(char **strp, gfp_t flags, void *fp, u32 len) { int rc; char *str; if ((len == 0) || (len == (u32)-1)) return -EINVAL; str = kmalloc(len + 1, flags | __GFP_NOWARN); if (!str) return -ENOMEM; rc = next_entry(str, fp, len); if (rc) { kfree(str); return rc; } str[len] = '\0'; *strp = str; return 0; } static int perm_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct perm_datum *perdatum; int rc; __le32 buf[2]; u32 len; perdatum = kzalloc(sizeof(*perdatum), GFP_KERNEL); if (!perdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); perdatum->value = le32_to_cpu(buf[1]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = symtab_insert(s, key, perdatum); if (rc) goto bad; return 0; bad: perm_destroy(key, perdatum, NULL); return rc; } static int common_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct common_datum *comdatum; __le32 buf[4]; u32 i, len, nel; int rc; comdatum = kzalloc(sizeof(*comdatum), GFP_KERNEL); if (!comdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); comdatum->value = le32_to_cpu(buf[1]); nel = le32_to_cpu(buf[3]); rc = symtab_init(&comdatum->permissions, nel); if (rc) goto bad; comdatum->permissions.nprim = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = perm_read(p, &comdatum->permissions, fp); if (rc) goto bad; } hash_eval(&comdatum->permissions.table, "common_permissions", key); rc = symtab_insert(s, key, comdatum); if (rc) goto bad; return 0; bad: common_destroy(key, comdatum, NULL); return rc; } static void type_set_init(struct type_set *t) { ebitmap_init(&t->types); ebitmap_init(&t->negset); } static int type_set_read(struct type_set *t, void *fp) { __le32 buf[1]; int rc; if (ebitmap_read(&t->types, fp)) return -EINVAL; if (ebitmap_read(&t->negset, fp)) return -EINVAL; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) return -EINVAL; t->flags = le32_to_cpu(buf[0]); return 0; } static int read_cons_helper(struct policydb *p, struct constraint_node **nodep, u32 ncons, int allowxtarget, void *fp) { struct constraint_node *c, *lc; struct constraint_expr *e, *le; __le32 buf[3]; u32 i, j, nexpr; int rc, depth; lc = NULL; for (i = 0; i < ncons; i++) { c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) return -ENOMEM; if (lc) lc->next = c; else *nodep = c; rc = next_entry(buf, fp, (sizeof(u32) * 2)); if (rc) return rc; c->permissions = le32_to_cpu(buf[0]); nexpr = le32_to_cpu(buf[1]); le = NULL; depth = -1; for (j = 0; j < nexpr; j++) { e = kzalloc(sizeof(*e), GFP_KERNEL); if (!e) return -ENOMEM; if (le) le->next = e; else c->expr = e; rc = next_entry(buf, fp, (sizeof(u32) * 3)); if (rc) return rc; e->expr_type = le32_to_cpu(buf[0]); e->attr = le32_to_cpu(buf[1]); e->op = le32_to_cpu(buf[2]); switch (e->expr_type) { case CEXPR_NOT: if (depth < 0) return -EINVAL; break; case CEXPR_AND: case CEXPR_OR: if (depth < 1) return -EINVAL; depth--; break; case CEXPR_ATTR: if (depth == (CEXPR_MAXDEPTH - 1)) return -EINVAL; depth++; break; case CEXPR_NAMES: if (!allowxtarget && (e->attr & CEXPR_XTARGET)) return -EINVAL; if (depth == (CEXPR_MAXDEPTH - 1)) return -EINVAL; depth++; rc = ebitmap_read(&e->names, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_CONSTRAINT_NAMES) { e->type_names = kzalloc(sizeof(*e->type_names), GFP_KERNEL); if (!e->type_names) return -ENOMEM; type_set_init(e->type_names); rc = type_set_read(e->type_names, fp); if (rc) return rc; } break; default: return -EINVAL; } le = e; } if (depth != 0) return -EINVAL; lc = c; } return 0; } static int class_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct class_datum *cladatum; __le32 buf[6]; u32 i, len, len2, ncons, nel; int rc; cladatum = kzalloc(sizeof(*cladatum), GFP_KERNEL); if (!cladatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof(u32) * 6); if (rc) goto bad; len = le32_to_cpu(buf[0]); len2 = le32_to_cpu(buf[1]); cladatum->value = le32_to_cpu(buf[2]); nel = le32_to_cpu(buf[4]); rc = symtab_init(&cladatum->permissions, nel); if (rc) goto bad; cladatum->permissions.nprim = le32_to_cpu(buf[3]); ncons = le32_to_cpu(buf[5]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; if (len2) { rc = str_read(&cladatum->comkey, GFP_KERNEL, fp, len2); if (rc) goto bad; rc = -EINVAL; cladatum->comdatum = symtab_search(&p->p_commons, cladatum->comkey); if (!cladatum->comdatum) { pr_err("SELinux: unknown common %s\n", cladatum->comkey); goto bad; } } for (i = 0; i < nel; i++) { rc = perm_read(p, &cladatum->permissions, fp); if (rc) goto bad; } hash_eval(&cladatum->permissions.table, "class_permissions", key); rc = read_cons_helper(p, &cladatum->constraints, ncons, 0, fp); if (rc) goto bad; if (p->policyvers >= POLICYDB_VERSION_VALIDATETRANS) { /* grab the validatetrans rules */ rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; ncons = le32_to_cpu(buf[0]); rc = read_cons_helper(p, &cladatum->validatetrans, ncons, 1, fp); if (rc) goto bad; } if (p->policyvers >= POLICYDB_VERSION_NEW_OBJECT_DEFAULTS) { rc = next_entry(buf, fp, sizeof(u32) * 3); if (rc) goto bad; cladatum->default_user = le32_to_cpu(buf[0]); cladatum->default_role = le32_to_cpu(buf[1]); cladatum->default_range = le32_to_cpu(buf[2]); } if (p->policyvers >= POLICYDB_VERSION_DEFAULT_TYPE) { rc = next_entry(buf, fp, sizeof(u32) * 1); if (rc) goto bad; cladatum->default_type = le32_to_cpu(buf[0]); } rc = symtab_insert(s, key, cladatum); if (rc) goto bad; return 0; bad: cls_destroy(key, cladatum, NULL); return rc; } static int role_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct role_datum *role; int rc; unsigned int to_read = 2; __le32 buf[3]; u32 len; role = kzalloc(sizeof(*role), GFP_KERNEL); if (!role) return -ENOMEM; if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) to_read = 3; rc = next_entry(buf, fp, sizeof(buf[0]) * to_read); if (rc) goto bad; len = le32_to_cpu(buf[0]); role->value = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) role->bounds = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = ebitmap_read(&role->dominates, fp); if (rc) goto bad; rc = ebitmap_read(&role->types, fp); if (rc) goto bad; if (strcmp(key, OBJECT_R) == 0) { rc = -EINVAL; if (role->value != OBJECT_R_VAL) { pr_err("SELinux: Role %s has wrong value %d\n", OBJECT_R, role->value); goto bad; } rc = 0; goto bad; } rc = symtab_insert(s, key, role); if (rc) goto bad; return 0; bad: role_destroy(key, role, NULL); return rc; } static int type_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct type_datum *typdatum; int rc; unsigned int to_read = 3; __le32 buf[4]; u32 len; typdatum = kzalloc(sizeof(*typdatum), GFP_KERNEL); if (!typdatum) return -ENOMEM; if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) to_read = 4; rc = next_entry(buf, fp, sizeof(buf[0]) * to_read); if (rc) goto bad; len = le32_to_cpu(buf[0]); typdatum->value = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) { u32 prop = le32_to_cpu(buf[2]); if (prop & TYPEDATUM_PROPERTY_PRIMARY) typdatum->primary = 1; if (prop & TYPEDATUM_PROPERTY_ATTRIBUTE) typdatum->attribute = 1; typdatum->bounds = le32_to_cpu(buf[3]); } else { typdatum->primary = le32_to_cpu(buf[2]); } rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = symtab_insert(s, key, typdatum); if (rc) goto bad; return 0; bad: type_destroy(key, typdatum, NULL); return rc; } /* * Read a MLS level structure from a policydb binary * representation file. */ static int mls_read_level(struct mls_level *lp, void *fp) { __le32 buf[1]; int rc; memset(lp, 0, sizeof(*lp)); rc = next_entry(buf, fp, sizeof buf); if (rc) { pr_err("SELinux: mls: truncated level\n"); return rc; } lp->sens = le32_to_cpu(buf[0]); rc = ebitmap_read(&lp->cat, fp); if (rc) { pr_err("SELinux: mls: error reading level categories\n"); return rc; } return 0; } static int user_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct user_datum *usrdatum; int rc; unsigned int to_read = 2; __le32 buf[3]; u32 len; usrdatum = kzalloc(sizeof(*usrdatum), GFP_KERNEL); if (!usrdatum) return -ENOMEM; if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) to_read = 3; rc = next_entry(buf, fp, sizeof(buf[0]) * to_read); if (rc) goto bad; len = le32_to_cpu(buf[0]); usrdatum->value = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) usrdatum->bounds = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = ebitmap_read(&usrdatum->roles, fp); if (rc) goto bad; if (p->policyvers >= POLICYDB_VERSION_MLS) { rc = mls_read_range_helper(&usrdatum->range, fp); if (rc) goto bad; rc = mls_read_level(&usrdatum->dfltlevel, fp); if (rc) goto bad; } rc = symtab_insert(s, key, usrdatum); if (rc) goto bad; return 0; bad: user_destroy(key, usrdatum, NULL); return rc; } static int sens_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct level_datum *levdatum; int rc; __le32 buf[2]; u32 len; levdatum = kzalloc(sizeof(*levdatum), GFP_KERNEL); if (!levdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); levdatum->isalias = le32_to_cpu(buf[1]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = -ENOMEM; levdatum->level = kmalloc(sizeof(*levdatum->level), GFP_KERNEL); if (!levdatum->level) goto bad; rc = mls_read_level(levdatum->level, fp); if (rc) goto bad; rc = symtab_insert(s, key, levdatum); if (rc) goto bad; return 0; bad: sens_destroy(key, levdatum, NULL); return rc; } static int cat_read(struct policydb *p, struct symtab *s, void *fp) { char *key = NULL; struct cat_datum *catdatum; int rc; __le32 buf[3]; u32 len; catdatum = kzalloc(sizeof(*catdatum), GFP_KERNEL); if (!catdatum) return -ENOMEM; rc = next_entry(buf, fp, sizeof buf); if (rc) goto bad; len = le32_to_cpu(buf[0]); catdatum->value = le32_to_cpu(buf[1]); catdatum->isalias = le32_to_cpu(buf[2]); rc = str_read(&key, GFP_KERNEL, fp, len); if (rc) goto bad; rc = symtab_insert(s, key, catdatum); if (rc) goto bad; return 0; bad: cat_destroy(key, catdatum, NULL); return rc; } /* clang-format off */ static int (*const read_f[SYM_NUM])(struct policydb *p, struct symtab *s, void *fp) = { common_read, class_read, role_read, type_read, user_read, cond_read_bool, sens_read, cat_read, }; /* clang-format on */ static int user_bounds_sanity_check(void *key, void *datum, void *datap) { struct user_datum *upper, *user; struct policydb *p = datap; int depth = 0; upper = user = datum; while (upper->bounds) { struct ebitmap_node *node; u32 bit; if (++depth == POLICYDB_BOUNDS_MAXDEPTH) { pr_err("SELinux: user %s: " "too deep or looped boundary\n", (char *)key); return -EINVAL; } upper = p->user_val_to_struct[upper->bounds - 1]; ebitmap_for_each_positive_bit(&user->roles, node, bit) { if (ebitmap_get_bit(&upper->roles, bit)) continue; pr_err("SELinux: boundary violated policy: " "user=%s role=%s bounds=%s\n", sym_name(p, SYM_USERS, user->value - 1), sym_name(p, SYM_ROLES, bit), sym_name(p, SYM_USERS, upper->value - 1)); return -EINVAL; } } return 0; } static int role_bounds_sanity_check(void *key, void *datum, void *datap) { struct role_datum *upper, *role; struct policydb *p = datap; int depth = 0; upper = role = datum; while (upper->bounds) { struct ebitmap_node *node; u32 bit; if (++depth == POLICYDB_BOUNDS_MAXDEPTH) { pr_err("SELinux: role %s: " "too deep or looped bounds\n", (char *)key); return -EINVAL; } upper = p->role_val_to_struct[upper->bounds - 1]; ebitmap_for_each_positive_bit(&role->types, node, bit) { if (ebitmap_get_bit(&upper->types, bit)) continue; pr_err("SELinux: boundary violated policy: " "role=%s type=%s bounds=%s\n", sym_name(p, SYM_ROLES, role->value - 1), sym_name(p, SYM_TYPES, bit), sym_name(p, SYM_ROLES, upper->value - 1)); return -EINVAL; } } return 0; } static int type_bounds_sanity_check(void *key, void *datum, void *datap) { struct type_datum *upper; struct policydb *p = datap; int depth = 0; upper = datum; while (upper->bounds) { if (++depth == POLICYDB_BOUNDS_MAXDEPTH) { pr_err("SELinux: type %s: " "too deep or looped boundary\n", (char *)key); return -EINVAL; } upper = p->type_val_to_struct[upper->bounds - 1]; BUG_ON(!upper); if (upper->attribute) { pr_err("SELinux: type %s: " "bounded by attribute %s\n", (char *)key, sym_name(p, SYM_TYPES, upper->value - 1)); return -EINVAL; } } return 0; } static int policydb_bounds_sanity_check(struct policydb *p) { int rc; if (p->policyvers < POLICYDB_VERSION_BOUNDARY) return 0; rc = hashtab_map(&p->p_users.table, user_bounds_sanity_check, p); if (rc) return rc; rc = hashtab_map(&p->p_roles.table, role_bounds_sanity_check, p); if (rc) return rc; rc = hashtab_map(&p->p_types.table, type_bounds_sanity_check, p); if (rc) return rc; return 0; } u16 string_to_security_class(struct policydb *p, const char *name) { struct class_datum *cladatum; cladatum = symtab_search(&p->p_classes, name); if (!cladatum) return 0; return cladatum->value; } u32 string_to_av_perm(struct policydb *p, u16 tclass, const char *name) { struct class_datum *cladatum; struct perm_datum *perdatum = NULL; struct common_datum *comdatum; if (!tclass || tclass > p->p_classes.nprim) return 0; cladatum = p->class_val_to_struct[tclass - 1]; comdatum = cladatum->comdatum; if (comdatum) perdatum = symtab_search(&comdatum->permissions, name); if (!perdatum) perdatum = symtab_search(&cladatum->permissions, name); if (!perdatum) return 0; return 1U << (perdatum->value - 1); } static int range_read(struct policydb *p, void *fp) { struct range_trans *rt = NULL; struct mls_range *r = NULL; int rc; __le32 buf[2]; u32 i, nel; if (p->policyvers < POLICYDB_VERSION_MLS) return 0; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; nel = le32_to_cpu(buf[0]); rc = hashtab_init(&p->range_tr, nel); if (rc) return rc; for (i = 0; i < nel; i++) { rc = -ENOMEM; rt = kzalloc(sizeof(*rt), GFP_KERNEL); if (!rt) goto out; rc = next_entry(buf, fp, (sizeof(u32) * 2)); if (rc) goto out; rt->source_type = le32_to_cpu(buf[0]); rt->target_type = le32_to_cpu(buf[1]); if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; rt->target_class = le32_to_cpu(buf[0]); } else rt->target_class = p->process_class; rc = -EINVAL; if (!policydb_type_isvalid(p, rt->source_type) || !policydb_type_isvalid(p, rt->target_type) || !policydb_class_isvalid(p, rt->target_class)) goto out; rc = -ENOMEM; r = kzalloc(sizeof(*r), GFP_KERNEL); if (!r) goto out; rc = mls_read_range_helper(r, fp); if (rc) goto out; rc = -EINVAL; if (!mls_range_isvalid(p, r)) { pr_warn("SELinux: rangetrans: invalid range\n"); goto out; } rc = hashtab_insert(&p->range_tr, rt, r, rangetr_key_params); if (rc) goto out; rt = NULL; r = NULL; } hash_eval(&p->range_tr, "rangetr", NULL); rc = 0; out: kfree(rt); kfree(r); return rc; } static int filename_trans_read_helper_compat(struct policydb *p, void *fp) { struct filename_trans_key key, *ft = NULL; struct filename_trans_datum *last, *datum = NULL; char *name = NULL; u32 len, stype, otype; __le32 buf[4]; int rc; /* length of the path component string */ rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; len = le32_to_cpu(buf[0]); /* path component string */ rc = str_read(&name, GFP_KERNEL, fp, len); if (rc) return rc; rc = next_entry(buf, fp, sizeof(u32) * 4); if (rc) goto out; stype = le32_to_cpu(buf[0]); key.ttype = le32_to_cpu(buf[1]); key.tclass = le32_to_cpu(buf[2]); key.name = name; otype = le32_to_cpu(buf[3]); last = NULL; datum = policydb_filenametr_search(p, &key); while (datum) { if (unlikely(ebitmap_get_bit(&datum->stypes, stype - 1))) { /* conflicting/duplicate rules are ignored */ datum = NULL; rc = 0; goto out; } if (likely(datum->otype == otype)) break; last = datum; datum = datum->next; } if (!datum) { rc = -ENOMEM; datum = kmalloc(sizeof(*datum), GFP_KERNEL); if (!datum) goto out; ebitmap_init(&datum->stypes); datum->otype = otype; datum->next = NULL; if (unlikely(last)) { last->next = datum; } else { rc = -ENOMEM; ft = kmemdup(&key, sizeof(key), GFP_KERNEL); if (!ft) goto out; rc = hashtab_insert(&p->filename_trans, ft, datum, filenametr_key_params); if (rc) goto out; name = NULL; rc = ebitmap_set_bit(&p->filename_trans_ttypes, key.ttype, 1); if (rc) return rc; } } kfree(name); return ebitmap_set_bit(&datum->stypes, stype - 1, 1); out: kfree(ft); kfree(name); kfree(datum); return rc; } static int filename_trans_read_helper(struct policydb *p, void *fp) { struct filename_trans_key *ft = NULL; struct filename_trans_datum **dst, *datum, *first = NULL; char *name = NULL; u32 len, ttype, tclass, ndatum, i; __le32 buf[3]; int rc; /* length of the path component string */ rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; len = le32_to_cpu(buf[0]); /* path component string */ rc = str_read(&name, GFP_KERNEL, fp, len); if (rc) return rc; rc = next_entry(buf, fp, sizeof(u32) * 3); if (rc) goto out; ttype = le32_to_cpu(buf[0]); tclass = le32_to_cpu(buf[1]); ndatum = le32_to_cpu(buf[2]); if (ndatum == 0) { pr_err("SELinux: Filename transition key with no datum\n"); rc = -ENOENT; goto out; } dst = &first; for (i = 0; i < ndatum; i++) { rc = -ENOMEM; datum = kmalloc(sizeof(*datum), GFP_KERNEL); if (!datum) goto out; datum->next = NULL; *dst = datum; /* ebitmap_read() will at least init the bitmap */ rc = ebitmap_read(&datum->stypes, fp); if (rc) goto out; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; datum->otype = le32_to_cpu(buf[0]); dst = &datum->next; } rc = -ENOMEM; ft = kmalloc(sizeof(*ft), GFP_KERNEL); if (!ft) goto out; ft->ttype = ttype; ft->tclass = tclass; ft->name = name; rc = hashtab_insert(&p->filename_trans, ft, first, filenametr_key_params); if (rc == -EEXIST) pr_err("SELinux: Duplicate filename transition key\n"); if (rc) goto out; return ebitmap_set_bit(&p->filename_trans_ttypes, ttype, 1); out: kfree(ft); kfree(name); while (first) { datum = first; first = first->next; ebitmap_destroy(&datum->stypes); kfree(datum); } return rc; } static int filename_trans_read(struct policydb *p, void *fp) { u32 nel, i; __le32 buf[1]; int rc; if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS) return 0; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; nel = le32_to_cpu(buf[0]); if (p->policyvers < POLICYDB_VERSION_COMP_FTRANS) { p->compat_filename_trans_count = nel; rc = hashtab_init(&p->filename_trans, (1 << 11)); if (rc) return rc; for (i = 0; i < nel; i++) { rc = filename_trans_read_helper_compat(p, fp); if (rc) return rc; } } else { rc = hashtab_init(&p->filename_trans, nel); if (rc) return rc; for (i = 0; i < nel; i++) { rc = filename_trans_read_helper(p, fp); if (rc) return rc; } } hash_eval(&p->filename_trans, "filenametr", NULL); return 0; } static int genfs_read(struct policydb *p, void *fp) { int rc; u32 i, j, nel, nel2, len, len2; __le32 buf[1]; struct ocontext *l, *c; struct ocontext *newc = NULL; struct genfs *genfs_p, *genfs; struct genfs *newgenfs = NULL; rc = next_entry(buf, fp, sizeof(u32)); if (rc) return rc; nel = le32_to_cpu(buf[0]); for (i = 0; i < nel; i++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = -ENOMEM; newgenfs = kzalloc(sizeof(*newgenfs), GFP_KERNEL); if (!newgenfs) goto out; rc = str_read(&newgenfs->fstype, GFP_KERNEL, fp, len); if (rc) goto out; for (genfs_p = NULL, genfs = p->genfs; genfs; genfs_p = genfs, genfs = genfs->next) { rc = -EINVAL; if (strcmp(newgenfs->fstype, genfs->fstype) == 0) { pr_err("SELinux: dup genfs fstype %s\n", newgenfs->fstype); goto out; } if (strcmp(newgenfs->fstype, genfs->fstype) < 0) break; } newgenfs->next = genfs; if (genfs_p) genfs_p->next = newgenfs; else p->genfs = newgenfs; genfs = newgenfs; newgenfs = NULL; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; nel2 = le32_to_cpu(buf[0]); for (j = 0; j < nel2; j++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = -ENOMEM; newc = kzalloc(sizeof(*newc), GFP_KERNEL); if (!newc) goto out; rc = str_read(&newc->u.name, GFP_KERNEL, fp, len); if (rc) goto out; rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; newc->v.sclass = le32_to_cpu(buf[0]); rc = context_read_and_validate(&newc->context[0], p, fp); if (rc) goto out; for (l = NULL, c = genfs->head; c; l = c, c = c->next) { rc = -EINVAL; if (!strcmp(newc->u.name, c->u.name) && (!c->v.sclass || !newc->v.sclass || newc->v.sclass == c->v.sclass)) { pr_err("SELinux: dup genfs entry (%s,%s)\n", genfs->fstype, c->u.name); goto out; } len = strlen(newc->u.name); len2 = strlen(c->u.name); if (len > len2) break; } newc->next = c; if (l) l->next = newc; else genfs->head = newc; newc = NULL; } } rc = 0; out: if (newgenfs) { kfree(newgenfs->fstype); kfree(newgenfs); } ocontext_destroy(newc, OCON_FSUSE); return rc; } static int ocontext_read(struct policydb *p, const struct policydb_compat_info *info, void *fp) { int rc; unsigned int i; u32 j, nel, len; __be64 prefixbuf[1]; __le32 buf[3]; struct ocontext *l, *c; u32 nodebuf[8]; for (i = 0; i < info->ocon_num; i++) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; nel = le32_to_cpu(buf[0]); l = NULL; for (j = 0; j < nel; j++) { rc = -ENOMEM; c = kzalloc(sizeof(*c), GFP_KERNEL); if (!c) goto out; if (l) l->next = c; else p->ocontexts[i] = c; l = c; switch (i) { case OCON_ISID: rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; c->sid[0] = le32_to_cpu(buf[0]); rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_FS: case OCON_NETIF: rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = str_read(&c->u.name, GFP_KERNEL, fp, len); if (rc) goto out; if (i == OCON_FS) pr_warn("SELinux: void and deprecated fs ocon %s\n", c->u.name); rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; rc = context_read_and_validate(&c->context[1], p, fp); if (rc) goto out; break; case OCON_PORT: rc = next_entry(buf, fp, sizeof(u32) * 3); if (rc) goto out; c->u.port.protocol = le32_to_cpu(buf[0]); c->u.port.low_port = le32_to_cpu(buf[1]); c->u.port.high_port = le32_to_cpu(buf[2]); rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_NODE: rc = next_entry(nodebuf, fp, sizeof(u32) * 2); if (rc) goto out; c->u.node.addr = nodebuf[0]; /* network order */ c->u.node.mask = nodebuf[1]; /* network order */ rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_FSUSE: rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto out; rc = -EINVAL; c->v.behavior = le32_to_cpu(buf[0]); /* Determined at runtime, not in policy DB. */ if (c->v.behavior == SECURITY_FS_USE_MNTPOINT) goto out; if (c->v.behavior > SECURITY_FS_USE_MAX) goto out; len = le32_to_cpu(buf[1]); rc = str_read(&c->u.name, GFP_KERNEL, fp, len); if (rc) goto out; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; case OCON_NODE6: { int k; rc = next_entry(nodebuf, fp, sizeof(u32) * 8); if (rc) goto out; for (k = 0; k < 4; k++) c->u.node6.addr[k] = nodebuf[k]; for (k = 0; k < 4; k++) c->u.node6.mask[k] = nodebuf[k + 4]; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; } case OCON_IBPKEY: { u32 pkey_lo, pkey_hi; rc = next_entry(prefixbuf, fp, sizeof(u64)); if (rc) goto out; /* we need to have subnet_prefix in CPU order */ c->u.ibpkey.subnet_prefix = be64_to_cpu(prefixbuf[0]); rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto out; pkey_lo = le32_to_cpu(buf[0]); pkey_hi = le32_to_cpu(buf[1]); if (pkey_lo > U16_MAX || pkey_hi > U16_MAX) { rc = -EINVAL; goto out; } c->u.ibpkey.low_pkey = pkey_lo; c->u.ibpkey.high_pkey = pkey_hi; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; } case OCON_IBENDPORT: { u32 port; rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto out; len = le32_to_cpu(buf[0]); rc = str_read(&c->u.ibendport.dev_name, GFP_KERNEL, fp, len); if (rc) goto out; port = le32_to_cpu(buf[1]); if (port > U8_MAX || port == 0) { rc = -EINVAL; goto out; } c->u.ibendport.port = port; rc = context_read_and_validate(&c->context[0], p, fp); if (rc) goto out; break; } /* end case */ } /* end switch */ } } rc = 0; out: return rc; } /* * Read the configuration data from a policy database binary * representation file into a policy database structure. */ int policydb_read(struct policydb *p, void *fp) { struct role_allow *ra, *lra; struct role_trans_key *rtk = NULL; struct role_trans_datum *rtd = NULL; int rc; __le32 buf[4]; u32 i, j, len, nprim, nel, perm; char *policydb_str; const struct policydb_compat_info *info; policydb_init(p); /* Read the magic number and string length. */ rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto bad; rc = -EINVAL; if (le32_to_cpu(buf[0]) != POLICYDB_MAGIC) { pr_err("SELinux: policydb magic number 0x%x does " "not match expected magic number 0x%x\n", le32_to_cpu(buf[0]), POLICYDB_MAGIC); goto bad; } rc = -EINVAL; len = le32_to_cpu(buf[1]); if (len != strlen(POLICYDB_STRING)) { pr_err("SELinux: policydb string length %d does not " "match expected length %zu\n", len, strlen(POLICYDB_STRING)); goto bad; } rc = -ENOMEM; policydb_str = kmalloc(len + 1, GFP_KERNEL); if (!policydb_str) { pr_err("SELinux: unable to allocate memory for policydb " "string of length %d\n", len); goto bad; } rc = next_entry(policydb_str, fp, len); if (rc) { pr_err("SELinux: truncated policydb string identifier\n"); kfree(policydb_str); goto bad; } rc = -EINVAL; policydb_str[len] = '\0'; if (strcmp(policydb_str, POLICYDB_STRING)) { pr_err("SELinux: policydb string %s does not match " "my string %s\n", policydb_str, POLICYDB_STRING); kfree(policydb_str); goto bad; } /* Done with policydb_str. */ kfree(policydb_str); policydb_str = NULL; /* Read the version and table sizes. */ rc = next_entry(buf, fp, sizeof(u32) * 4); if (rc) goto bad; rc = -EINVAL; p->policyvers = le32_to_cpu(buf[0]); if (p->policyvers < POLICYDB_VERSION_MIN || p->policyvers > POLICYDB_VERSION_MAX) { pr_err("SELinux: policydb version %d does not match " "my version range %d-%d\n", le32_to_cpu(buf[0]), POLICYDB_VERSION_MIN, POLICYDB_VERSION_MAX); goto bad; } if ((le32_to_cpu(buf[1]) & POLICYDB_CONFIG_MLS)) { p->mls_enabled = 1; rc = -EINVAL; if (p->policyvers < POLICYDB_VERSION_MLS) { pr_err("SELinux: security policydb version %d " "(MLS) not backwards compatible\n", p->policyvers); goto bad; } } p->reject_unknown = !!(le32_to_cpu(buf[1]) & REJECT_UNKNOWN); p->allow_unknown = !!(le32_to_cpu(buf[1]) & ALLOW_UNKNOWN); if (p->policyvers >= POLICYDB_VERSION_POLCAP) { rc = ebitmap_read(&p->policycaps, fp); if (rc) goto bad; } if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) { rc = ebitmap_read(&p->permissive_map, fp); if (rc) goto bad; } rc = -EINVAL; info = policydb_lookup_compat(p->policyvers); if (!info) { pr_err("SELinux: unable to find policy compat info " "for version %d\n", p->policyvers); goto bad; } rc = -EINVAL; if (le32_to_cpu(buf[2]) != info->sym_num || le32_to_cpu(buf[3]) != info->ocon_num) { pr_err("SELinux: policydb table sizes (%d,%d) do " "not match mine (%d,%d)\n", le32_to_cpu(buf[2]), le32_to_cpu(buf[3]), info->sym_num, info->ocon_num); goto bad; } for (i = 0; i < info->sym_num; i++) { rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto bad; nprim = le32_to_cpu(buf[0]); nel = le32_to_cpu(buf[1]); rc = symtab_init(&p->symtab[i], nel); if (rc) goto out; if (i == SYM_ROLES) { rc = roles_init(p); if (rc) goto out; } for (j = 0; j < nel; j++) { rc = read_f[i](p, &p->symtab[i], fp); if (rc) goto bad; } p->symtab[i].nprim = nprim; } rc = -EINVAL; p->process_class = string_to_security_class(p, "process"); if (!p->process_class) { pr_err("SELinux: process class is required, not defined in policy\n"); goto bad; } rc = avtab_read(&p->te_avtab, fp, p); if (rc) goto bad; if (p->policyvers >= POLICYDB_VERSION_BOOL) { rc = cond_read_list(p, fp); if (rc) goto bad; } rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; nel = le32_to_cpu(buf[0]); rc = hashtab_init(&p->role_tr, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = -ENOMEM; rtk = kmalloc(sizeof(*rtk), GFP_KERNEL); if (!rtk) goto bad; rc = -ENOMEM; rtd = kmalloc(sizeof(*rtd), GFP_KERNEL); if (!rtd) goto bad; rc = next_entry(buf, fp, sizeof(u32) * 3); if (rc) goto bad; rtk->role = le32_to_cpu(buf[0]); rtk->type = le32_to_cpu(buf[1]); rtd->new_role = le32_to_cpu(buf[2]); if (p->policyvers >= POLICYDB_VERSION_ROLETRANS) { rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; rtk->tclass = le32_to_cpu(buf[0]); } else rtk->tclass = p->process_class; rc = -EINVAL; if (!policydb_role_isvalid(p, rtk->role) || !policydb_type_isvalid(p, rtk->type) || !policydb_class_isvalid(p, rtk->tclass) || !policydb_role_isvalid(p, rtd->new_role)) goto bad; rc = hashtab_insert(&p->role_tr, rtk, rtd, roletr_key_params); if (rc) goto bad; rtk = NULL; rtd = NULL; } hash_eval(&p->role_tr, "roletr", NULL); rc = next_entry(buf, fp, sizeof(u32)); if (rc) goto bad; nel = le32_to_cpu(buf[0]); lra = NULL; for (i = 0; i < nel; i++) { rc = -ENOMEM; ra = kzalloc(sizeof(*ra), GFP_KERNEL); if (!ra) goto bad; if (lra) lra->next = ra; else p->role_allow = ra; rc = next_entry(buf, fp, sizeof(u32) * 2); if (rc) goto bad; rc = -EINVAL; ra->role = le32_to_cpu(buf[0]); ra->new_role = le32_to_cpu(buf[1]); if (!policydb_role_isvalid(p, ra->role) || !policydb_role_isvalid(p, ra->new_role)) goto bad; lra = ra; } rc = filename_trans_read(p, fp); if (rc) goto bad; rc = policydb_index(p); if (rc) goto bad; rc = -EINVAL; perm = string_to_av_perm(p, p->process_class, "transition"); if (!perm) { pr_err("SELinux: process transition permission is required, not defined in policy\n"); goto bad; } p->process_trans_perms = perm; perm = string_to_av_perm(p, p->process_class, "dyntransition"); if (!perm) { pr_err("SELinux: process dyntransition permission is required, not defined in policy\n"); goto bad; } p->process_trans_perms |= perm; rc = ocontext_read(p, info, fp); if (rc) goto bad; rc = genfs_read(p, fp); if (rc) goto bad; rc = range_read(p, fp); if (rc) goto bad; rc = -ENOMEM; p->type_attr_map_array = kvcalloc( p->p_types.nprim, sizeof(*p->type_attr_map_array), GFP_KERNEL); if (!p->type_attr_map_array) goto bad; /* just in case ebitmap_init() becomes more than just a memset(0): */ for (i = 0; i < p->p_types.nprim; i++) ebitmap_init(&p->type_attr_map_array[i]); for (i = 0; i < p->p_types.nprim; i++) { struct ebitmap *e = &p->type_attr_map_array[i]; if (p->policyvers >= POLICYDB_VERSION_AVTAB) { rc = ebitmap_read(e, fp); if (rc) goto bad; } /* add the type itself as the degenerate case */ rc = ebitmap_set_bit(e, i, 1); if (rc) goto bad; } rc = policydb_bounds_sanity_check(p); if (rc) goto bad; rc = 0; out: return rc; bad: kfree(rtk); kfree(rtd); policydb_destroy(p); goto out; } /* * Write a MLS level structure to a policydb binary * representation file. */ static int mls_write_level(struct mls_level *l, void *fp) { __le32 buf[1]; int rc; buf[0] = cpu_to_le32(l->sens); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = ebitmap_write(&l->cat, fp); if (rc) return rc; return 0; } /* * Write a MLS range structure to a policydb binary * representation file. */ static int mls_write_range_helper(struct mls_range *r, void *fp) { __le32 buf[3]; size_t items; int rc, eq; eq = mls_level_eq(&r->level[1], &r->level[0]); if (eq) items = 2; else items = 3; buf[0] = cpu_to_le32(items - 1); buf[1] = cpu_to_le32(r->level[0].sens); if (!eq) buf[2] = cpu_to_le32(r->level[1].sens); BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = ebitmap_write(&r->level[0].cat, fp); if (rc) return rc; if (!eq) { rc = ebitmap_write(&r->level[1].cat, fp); if (rc) return rc; } return 0; } static int sens_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct level_datum *levdatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[2]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(levdatum->isalias); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = mls_write_level(levdatum->level, fp); if (rc) return rc; return 0; } static int cat_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct cat_datum *catdatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[3]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(catdatum->value); buf[2] = cpu_to_le32(catdatum->isalias); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } static int role_trans_write_one(void *key, void *datum, void *ptr) { struct role_trans_key *rtk = key; struct role_trans_datum *rtd = datum; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; __le32 buf[3]; int rc; buf[0] = cpu_to_le32(rtk->role); buf[1] = cpu_to_le32(rtk->type); buf[2] = cpu_to_le32(rtd->new_role); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_ROLETRANS) { buf[0] = cpu_to_le32(rtk->tclass); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; } return 0; } static int role_trans_write(struct policydb *p, void *fp) { struct policy_data pd = { .p = p, .fp = fp }; __le32 buf[1]; int rc; buf[0] = cpu_to_le32(p->role_tr.nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; return hashtab_map(&p->role_tr, role_trans_write_one, &pd); } static int role_allow_write(struct role_allow *r, void *fp) { struct role_allow *ra; __le32 buf[2]; size_t nel; int rc; nel = 0; for (ra = r; ra; ra = ra->next) nel++; buf[0] = cpu_to_le32(nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (ra = r; ra; ra = ra->next) { buf[0] = cpu_to_le32(ra->role); buf[1] = cpu_to_le32(ra->new_role); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; } return 0; } /* * Write a security context structure * to a policydb binary representation file. */ static int context_write(struct policydb *p, struct context *c, void *fp) { int rc; __le32 buf[3]; buf[0] = cpu_to_le32(c->user); buf[1] = cpu_to_le32(c->role); buf[2] = cpu_to_le32(c->type); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = mls_write_range_helper(&c->range, fp); if (rc) return rc; return 0; } /* * The following *_write functions are used to * write the symbol data to a policy database * binary representation file. */ static int perm_write(void *vkey, void *datum, void *fp) { char *key = vkey; struct perm_datum *perdatum = datum; __le32 buf[2]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(perdatum->value); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } static int common_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct common_datum *comdatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; __le32 buf[4]; size_t len; int rc; len = strlen(key); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(comdatum->value); buf[2] = cpu_to_le32(comdatum->permissions.nprim); buf[3] = cpu_to_le32(comdatum->permissions.table.nel); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = hashtab_map(&comdatum->permissions.table, perm_write, fp); if (rc) return rc; return 0; } static int type_set_write(struct type_set *t, void *fp) { int rc; __le32 buf[1]; if (ebitmap_write(&t->types, fp)) return -EINVAL; if (ebitmap_write(&t->negset, fp)) return -EINVAL; buf[0] = cpu_to_le32(t->flags); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return -EINVAL; return 0; } static int write_cons_helper(struct policydb *p, struct constraint_node *node, void *fp) { struct constraint_node *c; struct constraint_expr *e; __le32 buf[3]; u32 nel; int rc; for (c = node; c; c = c->next) { nel = 0; for (e = c->expr; e; e = e->next) nel++; buf[0] = cpu_to_le32(c->permissions); buf[1] = cpu_to_le32(nel); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; for (e = c->expr; e; e = e->next) { buf[0] = cpu_to_le32(e->expr_type); buf[1] = cpu_to_le32(e->attr); buf[2] = cpu_to_le32(e->op); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; switch (e->expr_type) { case CEXPR_NAMES: rc = ebitmap_write(&e->names, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_CONSTRAINT_NAMES) { rc = type_set_write(e->type_names, fp); if (rc) return rc; } break; default: break; } } } return 0; } static int class_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct class_datum *cladatum = datum; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; struct constraint_node *c; __le32 buf[6]; u32 ncons; size_t len, len2; int rc; len = strlen(key); if (cladatum->comkey) len2 = strlen(cladatum->comkey); else len2 = 0; ncons = 0; for (c = cladatum->constraints; c; c = c->next) ncons++; buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(len2); buf[2] = cpu_to_le32(cladatum->value); buf[3] = cpu_to_le32(cladatum->permissions.nprim); buf[4] = cpu_to_le32(cladatum->permissions.table.nel); buf[5] = cpu_to_le32(ncons); rc = put_entry(buf, sizeof(u32), 6, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; if (cladatum->comkey) { rc = put_entry(cladatum->comkey, 1, len2, fp); if (rc) return rc; } rc = hashtab_map(&cladatum->permissions.table, perm_write, fp); if (rc) return rc; rc = write_cons_helper(p, cladatum->constraints, fp); if (rc) return rc; /* write out the validatetrans rule */ ncons = 0; for (c = cladatum->validatetrans; c; c = c->next) ncons++; buf[0] = cpu_to_le32(ncons); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = write_cons_helper(p, cladatum->validatetrans, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_NEW_OBJECT_DEFAULTS) { buf[0] = cpu_to_le32(cladatum->default_user); buf[1] = cpu_to_le32(cladatum->default_role); buf[2] = cpu_to_le32(cladatum->default_range); rc = put_entry(buf, sizeof(uint32_t), 3, fp); if (rc) return rc; } if (p->policyvers >= POLICYDB_VERSION_DEFAULT_TYPE) { buf[0] = cpu_to_le32(cladatum->default_type); rc = put_entry(buf, sizeof(uint32_t), 1, fp); if (rc) return rc; } return 0; } static int role_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct role_datum *role = datum; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; __le32 buf[3]; size_t items, len; int rc; len = strlen(key); items = 0; buf[items++] = cpu_to_le32(len); buf[items++] = cpu_to_le32(role->value); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) buf[items++] = cpu_to_le32(role->bounds); BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = ebitmap_write(&role->dominates, fp); if (rc) return rc; rc = ebitmap_write(&role->types, fp); if (rc) return rc; return 0; } static int type_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct type_datum *typdatum = datum; struct policy_data *pd = ptr; struct policydb *p = pd->p; void *fp = pd->fp; __le32 buf[4]; int rc; size_t items, len; len = strlen(key); items = 0; buf[items++] = cpu_to_le32(len); buf[items++] = cpu_to_le32(typdatum->value); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) { u32 properties = 0; if (typdatum->primary) properties |= TYPEDATUM_PROPERTY_PRIMARY; if (typdatum->attribute) properties |= TYPEDATUM_PROPERTY_ATTRIBUTE; buf[items++] = cpu_to_le32(properties); buf[items++] = cpu_to_le32(typdatum->bounds); } else { buf[items++] = cpu_to_le32(typdatum->primary); } BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; return 0; } static int user_write(void *vkey, void *datum, void *ptr) { char *key = vkey; struct user_datum *usrdatum = datum; struct policy_data *pd = ptr; struct policydb *p = pd->p; void *fp = pd->fp; __le32 buf[3]; size_t items, len; int rc; len = strlen(key); items = 0; buf[items++] = cpu_to_le32(len); buf[items++] = cpu_to_le32(usrdatum->value); if (p->policyvers >= POLICYDB_VERSION_BOUNDARY) buf[items++] = cpu_to_le32(usrdatum->bounds); BUG_ON(items > ARRAY_SIZE(buf)); rc = put_entry(buf, sizeof(u32), items, fp); if (rc) return rc; rc = put_entry(key, 1, len, fp); if (rc) return rc; rc = ebitmap_write(&usrdatum->roles, fp); if (rc) return rc; rc = mls_write_range_helper(&usrdatum->range, fp); if (rc) return rc; rc = mls_write_level(&usrdatum->dfltlevel, fp); if (rc) return rc; return 0; } /* clang-format off */ static int (*const write_f[SYM_NUM])(void *key, void *datum, void *datap) = { common_write, class_write, role_write, type_write, user_write, cond_write_bool, sens_write, cat_write, }; /* clang-format on */ static int ocontext_write(struct policydb *p, const struct policydb_compat_info *info, void *fp) { unsigned int i, j; int rc; size_t nel, len; __be64 prefixbuf[1]; __le32 buf[3]; u32 nodebuf[8]; struct ocontext *c; for (i = 0; i < info->ocon_num; i++) { nel = 0; for (c = p->ocontexts[i]; c; c = c->next) nel++; buf[0] = cpu_to_le32(nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (c = p->ocontexts[i]; c; c = c->next) { switch (i) { case OCON_ISID: buf[0] = cpu_to_le32(c->sid[0]); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_FS: case OCON_NETIF: len = strlen(c->u.name); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(c->u.name, 1, len, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; rc = context_write(p, &c->context[1], fp); if (rc) return rc; break; case OCON_PORT: buf[0] = cpu_to_le32(c->u.port.protocol); buf[1] = cpu_to_le32(c->u.port.low_port); buf[2] = cpu_to_le32(c->u.port.high_port); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_NODE: nodebuf[0] = c->u.node.addr; /* network order */ nodebuf[1] = c->u.node.mask; /* network order */ rc = put_entry(nodebuf, sizeof(u32), 2, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_FSUSE: buf[0] = cpu_to_le32(c->v.behavior); len = strlen(c->u.name); buf[1] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(c->u.name, 1, len, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_NODE6: for (j = 0; j < 4; j++) nodebuf[j] = c->u.node6.addr [j]; /* network order */ for (j = 0; j < 4; j++) nodebuf[j + 4] = c->u.node6.mask [j]; /* network order */ rc = put_entry(nodebuf, sizeof(u32), 8, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_IBPKEY: /* subnet_prefix is in CPU order */ prefixbuf[0] = cpu_to_be64(c->u.ibpkey.subnet_prefix); rc = put_entry(prefixbuf, sizeof(u64), 1, fp); if (rc) return rc; buf[0] = cpu_to_le32(c->u.ibpkey.low_pkey); buf[1] = cpu_to_le32(c->u.ibpkey.high_pkey); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; case OCON_IBENDPORT: len = strlen(c->u.ibendport.dev_name); buf[0] = cpu_to_le32(len); buf[1] = cpu_to_le32(c->u.ibendport.port); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(c->u.ibendport.dev_name, 1, len, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; break; } } } return 0; } static int genfs_write(struct policydb *p, void *fp) { struct genfs *genfs; struct ocontext *c; size_t len; __le32 buf[1]; int rc; len = 0; for (genfs = p->genfs; genfs; genfs = genfs->next) len++; buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (genfs = p->genfs; genfs; genfs = genfs->next) { len = strlen(genfs->fstype); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(genfs->fstype, 1, len, fp); if (rc) return rc; len = 0; for (c = genfs->head; c; c = c->next) len++; buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (c = genfs->head; c; c = c->next) { len = strlen(c->u.name); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(c->u.name, 1, len, fp); if (rc) return rc; buf[0] = cpu_to_le32(c->v.sclass); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = context_write(p, &c->context[0], fp); if (rc) return rc; } } return 0; } static int range_write_helper(void *key, void *data, void *ptr) { __le32 buf[2]; struct range_trans *rt = key; struct mls_range *r = data; struct policy_data *pd = ptr; void *fp = pd->fp; struct policydb *p = pd->p; int rc; buf[0] = cpu_to_le32(rt->source_type); buf[1] = cpu_to_le32(rt->target_type); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_RANGETRANS) { buf[0] = cpu_to_le32(rt->target_class); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; } rc = mls_write_range_helper(r, fp); if (rc) return rc; return 0; } static int range_write(struct policydb *p, void *fp) { __le32 buf[1]; int rc; struct policy_data pd; pd.p = p; pd.fp = fp; buf[0] = cpu_to_le32(p->range_tr.nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; /* actually write all of the entries */ rc = hashtab_map(&p->range_tr, range_write_helper, &pd); if (rc) return rc; return 0; } static int filename_write_helper_compat(void *key, void *data, void *ptr) { struct filename_trans_key *ft = key; struct filename_trans_datum *datum = data; struct ebitmap_node *node; void *fp = ptr; __le32 buf[4]; int rc; u32 bit, len = strlen(ft->name); do { ebitmap_for_each_positive_bit(&datum->stypes, node, bit) { buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(ft->name, sizeof(char), len, fp); if (rc) return rc; buf[0] = cpu_to_le32(bit + 1); buf[1] = cpu_to_le32(ft->ttype); buf[2] = cpu_to_le32(ft->tclass); buf[3] = cpu_to_le32(datum->otype); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) return rc; } datum = datum->next; } while (unlikely(datum)); return 0; } static int filename_write_helper(void *key, void *data, void *ptr) { struct filename_trans_key *ft = key; struct filename_trans_datum *datum; void *fp = ptr; __le32 buf[3]; int rc; u32 ndatum, len = strlen(ft->name); buf[0] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = put_entry(ft->name, sizeof(char), len, fp); if (rc) return rc; ndatum = 0; datum = data; do { ndatum++; datum = datum->next; } while (unlikely(datum)); buf[0] = cpu_to_le32(ft->ttype); buf[1] = cpu_to_le32(ft->tclass); buf[2] = cpu_to_le32(ndatum); rc = put_entry(buf, sizeof(u32), 3, fp); if (rc) return rc; datum = data; do { rc = ebitmap_write(&datum->stypes, fp); if (rc) return rc; buf[0] = cpu_to_le32(datum->otype); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; datum = datum->next; } while (unlikely(datum)); return 0; } static int filename_trans_write(struct policydb *p, void *fp) { __le32 buf[1]; int rc; if (p->policyvers < POLICYDB_VERSION_FILENAME_TRANS) return 0; if (p->policyvers < POLICYDB_VERSION_COMP_FTRANS) { buf[0] = cpu_to_le32(p->compat_filename_trans_count); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = hashtab_map(&p->filename_trans, filename_write_helper_compat, fp); } else { buf[0] = cpu_to_le32(p->filename_trans.nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; rc = hashtab_map(&p->filename_trans, filename_write_helper, fp); } return rc; } /* * Write the configuration data in a policy database * structure to a policy database binary representation * file. */ int policydb_write(struct policydb *p, void *fp) { unsigned int num_syms; int rc; __le32 buf[4]; u32 config, i; size_t len; const struct policydb_compat_info *info; /* * refuse to write policy older than compressed avtab * to simplify the writer. There are other tests dropped * since we assume this throughout the writer code. Be * careful if you ever try to remove this restriction */ if (p->policyvers < POLICYDB_VERSION_AVTAB) { pr_err("SELinux: refusing to write policy version %d." " Because it is less than version %d\n", p->policyvers, POLICYDB_VERSION_AVTAB); return -EINVAL; } config = 0; if (p->mls_enabled) config |= POLICYDB_CONFIG_MLS; if (p->reject_unknown) config |= REJECT_UNKNOWN; if (p->allow_unknown) config |= ALLOW_UNKNOWN; /* Write the magic number and string identifiers. */ buf[0] = cpu_to_le32(POLICYDB_MAGIC); len = strlen(POLICYDB_STRING); buf[1] = cpu_to_le32(len); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = put_entry(POLICYDB_STRING, 1, len, fp); if (rc) return rc; /* Write the version, config, and table sizes. */ info = policydb_lookup_compat(p->policyvers); if (!info) { pr_err("SELinux: compatibility lookup failed for policy " "version %d\n", p->policyvers); return -EINVAL; } buf[0] = cpu_to_le32(p->policyvers); buf[1] = cpu_to_le32(config); buf[2] = cpu_to_le32(info->sym_num); buf[3] = cpu_to_le32(info->ocon_num); rc = put_entry(buf, sizeof(u32), 4, fp); if (rc) return rc; if (p->policyvers >= POLICYDB_VERSION_POLCAP) { rc = ebitmap_write(&p->policycaps, fp); if (rc) return rc; } if (p->policyvers >= POLICYDB_VERSION_PERMISSIVE) { rc = ebitmap_write(&p->permissive_map, fp); if (rc) return rc; } num_syms = info->sym_num; for (i = 0; i < num_syms; i++) { struct policy_data pd; pd.fp = fp; pd.p = p; buf[0] = cpu_to_le32(p->symtab[i].nprim); buf[1] = cpu_to_le32(p->symtab[i].table.nel); rc = put_entry(buf, sizeof(u32), 2, fp); if (rc) return rc; rc = hashtab_map(&p->symtab[i].table, write_f[i], &pd); if (rc) return rc; } rc = avtab_write(p, &p->te_avtab, fp); if (rc) return rc; rc = cond_write_list(p, fp); if (rc) return rc; rc = role_trans_write(p, fp); if (rc) return rc; rc = role_allow_write(p->role_allow, fp); if (rc) return rc; rc = filename_trans_write(p, fp); if (rc) return rc; rc = ocontext_write(p, info, fp); if (rc) return rc; rc = genfs_write(p, fp); if (rc) return rc; rc = range_write(p, fp); if (rc) return rc; for (i = 0; i < p->p_types.nprim; i++) { struct ebitmap *e = &p->type_attr_map_array[i]; rc = ebitmap_write(e, fp); if (rc) return rc; } return 0; } |
| 398 190 4 180 181 227 313 81 285 290 62 384 205 23 64 332 404 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/atomic.h * * Copyright (C) 1996 Russell King. * Copyright (C) 2002 Deep Blue Solutions Ltd. * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_ATOMIC_H #define __ASM_ATOMIC_H #include <linux/compiler.h> #include <linux/types.h> #include <asm/barrier.h> #include <asm/cmpxchg.h> #include <asm/lse.h> #define ATOMIC_OP(op) \ static __always_inline void arch_##op(int i, atomic_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } ATOMIC_OP(atomic_andnot) ATOMIC_OP(atomic_or) ATOMIC_OP(atomic_xor) ATOMIC_OP(atomic_add) ATOMIC_OP(atomic_and) ATOMIC_OP(atomic_sub) #undef ATOMIC_OP #define ATOMIC_FETCH_OP(name, op) \ static __always_inline int arch_##op##name(int i, atomic_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } #define ATOMIC_FETCH_OPS(op) \ ATOMIC_FETCH_OP(_relaxed, op) \ ATOMIC_FETCH_OP(_acquire, op) \ ATOMIC_FETCH_OP(_release, op) \ ATOMIC_FETCH_OP( , op) ATOMIC_FETCH_OPS(atomic_fetch_andnot) ATOMIC_FETCH_OPS(atomic_fetch_or) ATOMIC_FETCH_OPS(atomic_fetch_xor) ATOMIC_FETCH_OPS(atomic_fetch_add) ATOMIC_FETCH_OPS(atomic_fetch_and) ATOMIC_FETCH_OPS(atomic_fetch_sub) ATOMIC_FETCH_OPS(atomic_add_return) ATOMIC_FETCH_OPS(atomic_sub_return) #undef ATOMIC_FETCH_OP #undef ATOMIC_FETCH_OPS #define ATOMIC64_OP(op) \ static __always_inline void arch_##op(long i, atomic64_t *v) \ { \ __lse_ll_sc_body(op, i, v); \ } ATOMIC64_OP(atomic64_andnot) ATOMIC64_OP(atomic64_or) ATOMIC64_OP(atomic64_xor) ATOMIC64_OP(atomic64_add) ATOMIC64_OP(atomic64_and) ATOMIC64_OP(atomic64_sub) #undef ATOMIC64_OP #define ATOMIC64_FETCH_OP(name, op) \ static __always_inline long arch_##op##name(long i, atomic64_t *v) \ { \ return __lse_ll_sc_body(op##name, i, v); \ } #define ATOMIC64_FETCH_OPS(op) \ ATOMIC64_FETCH_OP(_relaxed, op) \ ATOMIC64_FETCH_OP(_acquire, op) \ ATOMIC64_FETCH_OP(_release, op) \ ATOMIC64_FETCH_OP( , op) ATOMIC64_FETCH_OPS(atomic64_fetch_andnot) ATOMIC64_FETCH_OPS(atomic64_fetch_or) ATOMIC64_FETCH_OPS(atomic64_fetch_xor) ATOMIC64_FETCH_OPS(atomic64_fetch_add) ATOMIC64_FETCH_OPS(atomic64_fetch_and) ATOMIC64_FETCH_OPS(atomic64_fetch_sub) ATOMIC64_FETCH_OPS(atomic64_add_return) ATOMIC64_FETCH_OPS(atomic64_sub_return) #undef ATOMIC64_FETCH_OP #undef ATOMIC64_FETCH_OPS static __always_inline long arch_atomic64_dec_if_positive(atomic64_t *v) { return __lse_ll_sc_body(atomic64_dec_if_positive, v); } #define arch_atomic_read(v) __READ_ONCE((v)->counter) #define arch_atomic_set(v, i) __WRITE_ONCE(((v)->counter), (i)) #define arch_atomic_add_return_relaxed arch_atomic_add_return_relaxed #define arch_atomic_add_return_acquire arch_atomic_add_return_acquire #define arch_atomic_add_return_release arch_atomic_add_return_release #define arch_atomic_add_return arch_atomic_add_return #define arch_atomic_sub_return_relaxed arch_atomic_sub_return_relaxed #define arch_atomic_sub_return_acquire arch_atomic_sub_return_acquire #define arch_atomic_sub_return_release arch_atomic_sub_return_release #define arch_atomic_sub_return arch_atomic_sub_return #define arch_atomic_fetch_add_relaxed arch_atomic_fetch_add_relaxed #define arch_atomic_fetch_add_acquire arch_atomic_fetch_add_acquire #define arch_atomic_fetch_add_release arch_atomic_fetch_add_release #define arch_atomic_fetch_add arch_atomic_fetch_add #define arch_atomic_fetch_sub_relaxed arch_atomic_fetch_sub_relaxed #define arch_atomic_fetch_sub_acquire arch_atomic_fetch_sub_acquire #define arch_atomic_fetch_sub_release arch_atomic_fetch_sub_release #define arch_atomic_fetch_sub arch_atomic_fetch_sub #define arch_atomic_fetch_and_relaxed arch_atomic_fetch_and_relaxed #define arch_atomic_fetch_and_acquire arch_atomic_fetch_and_acquire #define arch_atomic_fetch_and_release arch_atomic_fetch_and_release #define arch_atomic_fetch_and arch_atomic_fetch_and #define arch_atomic_fetch_andnot_relaxed arch_atomic_fetch_andnot_relaxed #define arch_atomic_fetch_andnot_acquire arch_atomic_fetch_andnot_acquire #define arch_atomic_fetch_andnot_release arch_atomic_fetch_andnot_release #define arch_atomic_fetch_andnot arch_atomic_fetch_andnot #define arch_atomic_fetch_or_relaxed arch_atomic_fetch_or_relaxed #define arch_atomic_fetch_or_acquire arch_atomic_fetch_or_acquire #define arch_atomic_fetch_or_release arch_atomic_fetch_or_release #define arch_atomic_fetch_or arch_atomic_fetch_or #define arch_atomic_fetch_xor_relaxed arch_atomic_fetch_xor_relaxed #define arch_atomic_fetch_xor_acquire arch_atomic_fetch_xor_acquire #define arch_atomic_fetch_xor_release arch_atomic_fetch_xor_release #define arch_atomic_fetch_xor arch_atomic_fetch_xor #define arch_atomic_andnot arch_atomic_andnot /* * 64-bit arch_atomic operations. */ #define ATOMIC64_INIT ATOMIC_INIT #define arch_atomic64_read arch_atomic_read #define arch_atomic64_set arch_atomic_set #define arch_atomic64_add_return_relaxed arch_atomic64_add_return_relaxed #define arch_atomic64_add_return_acquire arch_atomic64_add_return_acquire #define arch_atomic64_add_return_release arch_atomic64_add_return_release #define arch_atomic64_add_return arch_atomic64_add_return #define arch_atomic64_sub_return_relaxed arch_atomic64_sub_return_relaxed #define arch_atomic64_sub_return_acquire arch_atomic64_sub_return_acquire #define arch_atomic64_sub_return_release arch_atomic64_sub_return_release #define arch_atomic64_sub_return arch_atomic64_sub_return #define arch_atomic64_fetch_add_relaxed arch_atomic64_fetch_add_relaxed #define arch_atomic64_fetch_add_acquire arch_atomic64_fetch_add_acquire #define arch_atomic64_fetch_add_release arch_atomic64_fetch_add_release #define arch_atomic64_fetch_add arch_atomic64_fetch_add #define arch_atomic64_fetch_sub_relaxed arch_atomic64_fetch_sub_relaxed #define arch_atomic64_fetch_sub_acquire arch_atomic64_fetch_sub_acquire #define arch_atomic64_fetch_sub_release arch_atomic64_fetch_sub_release #define arch_atomic64_fetch_sub arch_atomic64_fetch_sub #define arch_atomic64_fetch_and_relaxed arch_atomic64_fetch_and_relaxed #define arch_atomic64_fetch_and_acquire arch_atomic64_fetch_and_acquire #define arch_atomic64_fetch_and_release arch_atomic64_fetch_and_release #define arch_atomic64_fetch_and arch_atomic64_fetch_and #define arch_atomic64_fetch_andnot_relaxed arch_atomic64_fetch_andnot_relaxed #define arch_atomic64_fetch_andnot_acquire arch_atomic64_fetch_andnot_acquire #define arch_atomic64_fetch_andnot_release arch_atomic64_fetch_andnot_release #define arch_atomic64_fetch_andnot arch_atomic64_fetch_andnot #define arch_atomic64_fetch_or_relaxed arch_atomic64_fetch_or_relaxed #define arch_atomic64_fetch_or_acquire arch_atomic64_fetch_or_acquire #define arch_atomic64_fetch_or_release arch_atomic64_fetch_or_release #define arch_atomic64_fetch_or arch_atomic64_fetch_or #define arch_atomic64_fetch_xor_relaxed arch_atomic64_fetch_xor_relaxed #define arch_atomic64_fetch_xor_acquire arch_atomic64_fetch_xor_acquire #define arch_atomic64_fetch_xor_release arch_atomic64_fetch_xor_release #define arch_atomic64_fetch_xor arch_atomic64_fetch_xor #define arch_atomic64_andnot arch_atomic64_andnot #define arch_atomic64_dec_if_positive arch_atomic64_dec_if_positive #endif /* __ASM_ATOMIC_H */ |
| 17 222 248 151 17 17 17 21 17 3 155 17 228 4 17 17 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_DCACHE_H #define __LINUX_DCACHE_H #include <linux/atomic.h> #include <linux/list.h> #include <linux/math.h> #include <linux/rculist.h> #include <linux/rculist_bl.h> #include <linux/spinlock.h> #include <linux/seqlock.h> #include <linux/cache.h> #include <linux/rcupdate.h> #include <linux/lockref.h> #include <linux/stringhash.h> #include <linux/wait.h> struct path; struct file; struct vfsmount; /* * linux/include/linux/dcache.h * * Dirent cache data structures * * (C) Copyright 1997 Thomas Schoebel-Theuer, * with heavy changes by Linus Torvalds */ #define IS_ROOT(x) ((x) == (x)->d_parent) /* The hash is always the low bits of hash_len */ #ifdef __LITTLE_ENDIAN #define HASH_LEN_DECLARE u32 hash; u32 len #define bytemask_from_count(cnt) (~(~0ul << (cnt)*8)) #else #define HASH_LEN_DECLARE u32 len; u32 hash #define bytemask_from_count(cnt) (~(~0ul >> (cnt)*8)) #endif /* * "quick string" -- eases parameter passing, but more importantly * saves "metadata" about the string (ie length and the hash). * * hash comes first so it snuggles against d_parent in the * dentry. */ struct qstr { union { struct { HASH_LEN_DECLARE; }; u64 hash_len; }; const unsigned char *name; }; #define QSTR_INIT(n,l) { { { .len = l } }, .name = n } extern const struct qstr empty_name; extern const struct qstr slash_name; extern const struct qstr dotdot_name; /* * Try to keep struct dentry aligned on 64 byte cachelines (this will * give reasonable cacheline footprint with larger lines without the * large memory footprint increase). */ #ifdef CONFIG_64BIT # define DNAME_INLINE_LEN 40 /* 192 bytes */ #else # ifdef CONFIG_SMP # define DNAME_INLINE_LEN 40 /* 128 bytes */ # else # define DNAME_INLINE_LEN 44 /* 128 bytes */ # endif #endif #define d_lock d_lockref.lock struct dentry { /* RCU lookup touched fields */ unsigned int d_flags; /* protected by d_lock */ seqcount_spinlock_t d_seq; /* per dentry seqlock */ struct hlist_bl_node d_hash; /* lookup hash list */ struct dentry *d_parent; /* parent directory */ struct qstr d_name; struct inode *d_inode; /* Where the name belongs to - NULL is * negative */ unsigned char d_iname[DNAME_INLINE_LEN]; /* small names */ /* Ref lookup also touches following */ struct lockref d_lockref; /* per-dentry lock and refcount */ const struct dentry_operations *d_op; struct super_block *d_sb; /* The root of the dentry tree */ unsigned long d_time; /* used by d_revalidate */ void *d_fsdata; /* fs-specific data */ union { struct list_head d_lru; /* LRU list */ wait_queue_head_t *d_wait; /* in-lookup ones only */ }; struct hlist_node d_sib; /* child of parent list */ struct hlist_head d_children; /* our children */ /* * d_alias and d_rcu can share memory */ union { struct hlist_node d_alias; /* inode alias list */ struct hlist_bl_node d_in_lookup_hash; /* only for in-lookup ones */ struct rcu_head d_rcu; } d_u; }; /* * dentry->d_lock spinlock nesting subclasses: * * 0: normal * 1: nested */ enum dentry_d_lock_class { DENTRY_D_LOCK_NORMAL, /* implicitly used by plain spin_lock() APIs. */ DENTRY_D_LOCK_NESTED }; enum d_real_type { D_REAL_DATA, D_REAL_METADATA, }; struct dentry_operations { int (*d_revalidate)(struct dentry *, unsigned int); int (*d_weak_revalidate)(struct dentry *, unsigned int); int (*d_hash)(const struct dentry *, struct qstr *); int (*d_compare)(const struct dentry *, unsigned int, const char *, const struct qstr *); int (*d_delete)(const struct dentry *); int (*d_init)(struct dentry *); void (*d_release)(struct dentry *); void (*d_prune)(struct dentry *); void (*d_iput)(struct dentry *, struct inode *); char *(*d_dname)(struct dentry *, char *, int); struct vfsmount *(*d_automount)(struct path *); int (*d_manage)(const struct path *, bool); struct dentry *(*d_real)(struct dentry *, enum d_real_type type); } ____cacheline_aligned; /* * Locking rules for dentry_operations callbacks are to be found in * Documentation/filesystems/locking.rst. Keep it updated! * * FUrther descriptions are found in Documentation/filesystems/vfs.rst. * Keep it updated too! */ /* d_flags entries */ #define DCACHE_OP_HASH BIT(0) #define DCACHE_OP_COMPARE BIT(1) #define DCACHE_OP_REVALIDATE BIT(2) #define DCACHE_OP_DELETE BIT(3) #define DCACHE_OP_PRUNE BIT(4) #define DCACHE_DISCONNECTED BIT(5) /* This dentry is possibly not currently connected to the dcache tree, in * which case its parent will either be itself, or will have this flag as * well. nfsd will not use a dentry with this bit set, but will first * endeavour to clear the bit either by discovering that it is connected, * or by performing lookup operations. Any filesystem which supports * nfsd_operations MUST have a lookup function which, if it finds a * directory inode with a DCACHE_DISCONNECTED dentry, will d_move that * dentry into place and return that dentry rather than the passed one, * typically using d_splice_alias. */ #define DCACHE_REFERENCED BIT(6) /* Recently used, don't discard. */ #define DCACHE_DONTCACHE BIT(7) /* Purge from memory on final dput() */ #define DCACHE_CANT_MOUNT BIT(8) #define DCACHE_GENOCIDE BIT(9) #define DCACHE_SHRINK_LIST BIT(10) #define DCACHE_OP_WEAK_REVALIDATE BIT(11) #define DCACHE_NFSFS_RENAMED BIT(12) /* this dentry has been "silly renamed" and has to be deleted on the last * dput() */ #define DCACHE_FSNOTIFY_PARENT_WATCHED BIT(14) /* Parent inode is watched by some fsnotify listener */ #define DCACHE_DENTRY_KILLED BIT(15) #define DCACHE_MOUNTED BIT(16) /* is a mountpoint */ #define DCACHE_NEED_AUTOMOUNT BIT(17) /* handle automount on this dir */ #define DCACHE_MANAGE_TRANSIT BIT(18) /* manage transit from this dirent */ #define DCACHE_MANAGED_DENTRY \ (DCACHE_MOUNTED|DCACHE_NEED_AUTOMOUNT|DCACHE_MANAGE_TRANSIT) #define DCACHE_LRU_LIST BIT(19) #define DCACHE_ENTRY_TYPE (7 << 20) /* bits 20..22 are for storing type: */ #define DCACHE_MISS_TYPE (0 << 20) /* Negative dentry */ #define DCACHE_WHITEOUT_TYPE (1 << 20) /* Whiteout dentry (stop pathwalk) */ #define DCACHE_DIRECTORY_TYPE (2 << 20) /* Normal directory */ #define DCACHE_AUTODIR_TYPE (3 << 20) /* Lookupless directory (presumed automount) */ #define DCACHE_REGULAR_TYPE (4 << 20) /* Regular file type */ #define DCACHE_SPECIAL_TYPE (5 << 20) /* Other file type */ #define DCACHE_SYMLINK_TYPE (6 << 20) /* Symlink */ #define DCACHE_NOKEY_NAME BIT(25) /* Encrypted name encoded without key */ #define DCACHE_OP_REAL BIT(26) #define DCACHE_PAR_LOOKUP BIT(28) /* being looked up (with parent locked shared) */ #define DCACHE_DENTRY_CURSOR BIT(29) #define DCACHE_NORCU BIT(30) /* No RCU delay for freeing */ extern seqlock_t rename_lock; /* * These are the low-level FS interfaces to the dcache.. */ extern void d_instantiate(struct dentry *, struct inode *); extern void d_instantiate_new(struct dentry *, struct inode *); extern void __d_drop(struct dentry *dentry); extern void d_drop(struct dentry *dentry); extern void d_delete(struct dentry *); extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op); /* allocate/de-allocate */ extern struct dentry * d_alloc(struct dentry *, const struct qstr *); extern struct dentry * d_alloc_anon(struct super_block *); extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *, wait_queue_head_t *); extern struct dentry * d_splice_alias(struct inode *, struct dentry *); extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *); extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent, const struct qstr *name); extern struct dentry * d_exact_alias(struct dentry *, struct inode *); extern struct dentry *d_find_any_alias(struct inode *inode); extern struct dentry * d_obtain_alias(struct inode *); extern struct dentry * d_obtain_root(struct inode *); extern void shrink_dcache_sb(struct super_block *); extern void shrink_dcache_parent(struct dentry *); extern void d_invalidate(struct dentry *); /* only used at mount-time */ extern struct dentry * d_make_root(struct inode *); extern void d_mark_tmpfile(struct file *, struct inode *); extern void d_tmpfile(struct file *, struct inode *); extern struct dentry *d_find_alias(struct inode *); extern void d_prune_aliases(struct inode *); extern struct dentry *d_find_alias_rcu(struct inode *); /* test whether we have any submounts in a subdir tree */ extern int path_has_submounts(const struct path *); /* * This adds the entry to the hash queues. */ extern void d_rehash(struct dentry *); extern void d_add(struct dentry *, struct inode *); /* used for rename() and baskets */ extern void d_move(struct dentry *, struct dentry *); extern void d_exchange(struct dentry *, struct dentry *); extern struct dentry *d_ancestor(struct dentry *, struct dentry *); extern struct dentry *d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); static inline unsigned d_count(const struct dentry *dentry) { return dentry->d_lockref.count; } /* * helper function for dentry_operations.d_dname() members */ extern __printf(3, 4) char *dynamic_dname(char *, int, const char *, ...); extern char *__d_path(const struct path *, const struct path *, char *, int); extern char *d_absolute_path(const struct path *, char *, int); extern char *d_path(const struct path *, char *, int); extern char *dentry_path_raw(const struct dentry *, char *, int); extern char *dentry_path(const struct dentry *, char *, int); /* Allocation counts.. */ /** * dget_dlock - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a live dentry, increment the reference count and return the dentry. * Caller must hold @dentry->d_lock. Making sure that dentry is alive is * caller's resonsibility. There are many conditions sufficient to guarantee * that; e.g. anything with non-negative refcount is alive, so's anything * hashed, anything positive, anyone's parent, etc. */ static inline struct dentry *dget_dlock(struct dentry *dentry) { dentry->d_lockref.count++; return dentry; } /** * dget - get a reference to a dentry * @dentry: dentry to get a reference to * * Given a dentry or %NULL pointer increment the reference count * if appropriate and return the dentry. A dentry will not be * destroyed when it has references. Conversely, a dentry with * no references can disappear for any number of reasons, starting * with memory pressure. In other words, that primitive is * used to clone an existing reference; using it on something with * zero refcount is a bug. * * NOTE: it will spin if @dentry->d_lock is held. From the deadlock * avoidance point of view it is equivalent to spin_lock()/increment * refcount/spin_unlock(), so calling it under @dentry->d_lock is * always a bug; so's calling it under ->d_lock on any of its descendents. * */ static inline struct dentry *dget(struct dentry *dentry) { if (dentry) lockref_get(&dentry->d_lockref); return dentry; } extern struct dentry *dget_parent(struct dentry *dentry); /** * d_unhashed - is dentry hashed * @dentry: entry to check * * Returns true if the dentry passed is not currently hashed. */ static inline int d_unhashed(const struct dentry *dentry) { return hlist_bl_unhashed(&dentry->d_hash); } static inline int d_unlinked(const struct dentry *dentry) { return d_unhashed(dentry) && !IS_ROOT(dentry); } static inline int cant_mount(const struct dentry *dentry) { return (dentry->d_flags & DCACHE_CANT_MOUNT); } static inline void dont_mount(struct dentry *dentry) { spin_lock(&dentry->d_lock); dentry->d_flags |= DCACHE_CANT_MOUNT; spin_unlock(&dentry->d_lock); } extern void __d_lookup_unhash_wake(struct dentry *dentry); static inline int d_in_lookup(const struct dentry *dentry) { return dentry->d_flags & DCACHE_PAR_LOOKUP; } static inline void d_lookup_done(struct dentry *dentry) { if (unlikely(d_in_lookup(dentry))) __d_lookup_unhash_wake(dentry); } extern void dput(struct dentry *); static inline bool d_managed(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MANAGED_DENTRY; } static inline bool d_mountpoint(const struct dentry *dentry) { return dentry->d_flags & DCACHE_MOUNTED; } /* * Directory cache entry type accessor functions. */ static inline unsigned __d_entry_type(const struct dentry *dentry) { return dentry->d_flags & DCACHE_ENTRY_TYPE; } static inline bool d_is_miss(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_MISS_TYPE; } static inline bool d_is_whiteout(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_WHITEOUT_TYPE; } static inline bool d_can_lookup(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_DIRECTORY_TYPE; } static inline bool d_is_autodir(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_AUTODIR_TYPE; } static inline bool d_is_dir(const struct dentry *dentry) { return d_can_lookup(dentry) || d_is_autodir(dentry); } static inline bool d_is_symlink(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SYMLINK_TYPE; } static inline bool d_is_reg(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_REGULAR_TYPE; } static inline bool d_is_special(const struct dentry *dentry) { return __d_entry_type(dentry) == DCACHE_SPECIAL_TYPE; } static inline bool d_is_file(const struct dentry *dentry) { return d_is_reg(dentry) || d_is_special(dentry); } static inline bool d_is_negative(const struct dentry *dentry) { // TODO: check d_is_whiteout(dentry) also. return d_is_miss(dentry); } static inline bool d_flags_negative(unsigned flags) { return (flags & DCACHE_ENTRY_TYPE) == DCACHE_MISS_TYPE; } static inline bool d_is_positive(const struct dentry *dentry) { return !d_is_negative(dentry); } /** * d_really_is_negative - Determine if a dentry is really negative (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents either an absent name or a name that * doesn't map to an inode (ie. ->d_inode is NULL). The dentry could represent * a true miss, a whiteout that isn't represented by a 0,0 chardev or a * fallthrough marker in an opaque directory. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. (3) The dentry may have something attached to ->d_lower and the * type field of the flags may be set to something other than miss or whiteout. */ static inline bool d_really_is_negative(const struct dentry *dentry) { return dentry->d_inode == NULL; } /** * d_really_is_positive - Determine if a dentry is really positive (ignoring fallthroughs) * @dentry: The dentry in question * * Returns true if the dentry represents a name that maps to an inode * (ie. ->d_inode is not NULL). The dentry might still represent a whiteout if * that is represented on medium as a 0,0 chardev. * * Note! (1) This should be used *only* by a filesystem to examine its own * dentries. It should not be used to look at some other filesystem's * dentries. (2) It should also be used in combination with d_inode() to get * the inode. */ static inline bool d_really_is_positive(const struct dentry *dentry) { return dentry->d_inode != NULL; } static inline int simple_positive(const struct dentry *dentry) { return d_really_is_positive(dentry) && !d_unhashed(dentry); } extern int sysctl_vfs_cache_pressure; static inline unsigned long vfs_pressure_ratio(unsigned long val) { return mult_frac(val, sysctl_vfs_cache_pressure, 100); } /** * d_inode - Get the actual inode of this dentry * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode(const struct dentry *dentry) { return dentry->d_inode; } /** * d_inode_rcu - Get the actual inode of this dentry with READ_ONCE() * @dentry: The dentry to query * * This is the helper normal filesystems should use to get at their own inodes * in their own dentries and ignore the layering superimposed upon them. */ static inline struct inode *d_inode_rcu(const struct dentry *dentry) { return READ_ONCE(dentry->d_inode); } /** * d_backing_inode - Get upper or lower inode we should be using * @upper: The upper layer * * This is the helper that should be used to get at the inode that will be used * if this dentry were to be opened as a file. The inode may be on the upper * dentry or it may be on a lower dentry pinned by the upper. * * Normal filesystems should not use this to access their own inodes. */ static inline struct inode *d_backing_inode(const struct dentry *upper) { struct inode *inode = upper->d_inode; return inode; } /** * d_real - Return the real dentry * @dentry: the dentry to query * @type: the type of real dentry (data or metadata) * * If dentry is on a union/overlay, then return the underlying, real dentry. * Otherwise return the dentry itself. * * See also: Documentation/filesystems/vfs.rst */ static inline struct dentry *d_real(struct dentry *dentry, enum d_real_type type) { if (unlikely(dentry->d_flags & DCACHE_OP_REAL)) return dentry->d_op->d_real(dentry, type); else return dentry; } /** * d_real_inode - Return the real inode hosting the data * @dentry: The dentry to query * * If dentry is on a union/overlay, then return the underlying, real inode. * Otherwise return d_inode(). */ static inline struct inode *d_real_inode(const struct dentry *dentry) { /* This usage of d_real() results in const dentry */ return d_inode(d_real((struct dentry *) dentry, D_REAL_DATA)); } struct name_snapshot { struct qstr name; unsigned char inline_name[DNAME_INLINE_LEN]; }; void take_dentry_name_snapshot(struct name_snapshot *, struct dentry *); void release_dentry_name_snapshot(struct name_snapshot *); static inline struct dentry *d_first_child(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_children.first, struct dentry, d_sib); } static inline struct dentry *d_next_sibling(const struct dentry *dentry) { return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib); } #endif /* __LINUX_DCACHE_H */ |
| 101 101 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | /* SPDX-License-Identifier: GPL-2.0 */ /* * NUMA memory policies for Linux. * Copyright 2003,2004 Andi Kleen SuSE Labs */ #ifndef _LINUX_MEMPOLICY_H #define _LINUX_MEMPOLICY_H 1 #include <linux/sched.h> #include <linux/mmzone.h> #include <linux/slab.h> #include <linux/rbtree.h> #include <linux/spinlock.h> #include <linux/nodemask.h> #include <linux/pagemap.h> #include <uapi/linux/mempolicy.h> struct mm_struct; #define NO_INTERLEAVE_INDEX (-1UL) /* use task il_prev for interleaving */ #ifdef CONFIG_NUMA /* * Describe a memory policy. * * A mempolicy can be either associated with a process or with a VMA. * For VMA related allocations the VMA policy is preferred, otherwise * the process policy is used. Interrupts ignore the memory policy * of the current process. * * Locking policy for interleave: * In process context there is no locking because only the process accesses * its own state. All vma manipulation is somewhat protected by a down_read on * mmap_lock. * * Freeing policy: * Mempolicy objects are reference counted. A mempolicy will be freed when * mpol_put() decrements the reference count to zero. * * Duplicating policy objects: * mpol_dup() allocates a new mempolicy and copies the specified mempolicy * to the new storage. The reference count of the new object is initialized * to 1, representing the caller of mpol_dup(). */ struct mempolicy { atomic_t refcnt; unsigned short mode; /* See MPOL_* above */ unsigned short flags; /* See set_mempolicy() MPOL_F_* above */ nodemask_t nodes; /* interleave/bind/perfer */ int home_node; /* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */ union { nodemask_t cpuset_mems_allowed; /* relative to these nodes */ nodemask_t user_nodemask; /* nodemask passed by user */ } w; }; /* * Support for managing mempolicy data objects (clone, copy, destroy) * The default fast path of a NULL MPOL_DEFAULT policy is always inlined. */ extern void __mpol_put(struct mempolicy *pol); static inline void mpol_put(struct mempolicy *pol) { if (pol) __mpol_put(pol); } /* * Does mempolicy pol need explicit unref after use? * Currently only needed for shared policies. */ static inline int mpol_needs_cond_ref(struct mempolicy *pol) { return (pol && (pol->flags & MPOL_F_SHARED)); } static inline void mpol_cond_put(struct mempolicy *pol) { if (mpol_needs_cond_ref(pol)) __mpol_put(pol); } extern struct mempolicy *__mpol_dup(struct mempolicy *pol); static inline struct mempolicy *mpol_dup(struct mempolicy *pol) { if (pol) pol = __mpol_dup(pol); return pol; } static inline void mpol_get(struct mempolicy *pol) { if (pol) atomic_inc(&pol->refcnt); } extern bool __mpol_equal(struct mempolicy *a, struct mempolicy *b); static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (a == b) return true; return __mpol_equal(a, b); } /* * Tree of shared policies for a shared memory region. */ struct shared_policy { struct rb_root root; rwlock_t lock; }; struct sp_node { struct rb_node nd; pgoff_t start, end; struct mempolicy *policy; }; int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst); void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *mpol); void mpol_free_shared_policy(struct shared_policy *sp); struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx); struct mempolicy *get_task_policy(struct task_struct *p); struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx); struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx); bool vma_policy_mof(struct vm_area_struct *vma); extern void numa_default_policy(void); extern void numa_policy_init(void); extern void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new); extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new); extern int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask); extern bool init_nodemask_of_mempolicy(nodemask_t *mask); extern bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask); extern unsigned int mempolicy_slab_node(void); extern enum zone_type policy_zone; static inline void check_highest_zone(enum zone_type k) { if (k > policy_zone && k != ZONE_MOVABLE) policy_zone = k; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags); #ifdef CONFIG_TMPFS extern int mpol_parse_str(char *str, struct mempolicy **mpol); #endif extern void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol); /* Check if a vma is migratable */ extern bool vma_migratable(struct vm_area_struct *vma); int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr); extern void mpol_put_task_policy(struct task_struct *); static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return (pol->mode == MPOL_PREFERRED_MANY); } extern bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone); #else struct mempolicy {}; static inline struct mempolicy *get_task_policy(struct task_struct *p) { return NULL; } static inline bool mpol_equal(struct mempolicy *a, struct mempolicy *b) { return true; } static inline void mpol_put(struct mempolicy *pol) { } static inline void mpol_cond_put(struct mempolicy *pol) { } static inline void mpol_get(struct mempolicy *pol) { } struct shared_policy {}; static inline void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { } static inline void mpol_free_shared_policy(struct shared_policy *sp) { } static inline struct mempolicy * mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { return NULL; } static inline struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { *ilx = 0; return NULL; } static inline int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { return 0; } static inline void numa_policy_init(void) { } static inline void numa_default_policy(void) { } static inline void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { } static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { } static inline int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { *mpol = NULL; *nodemask = NULL; return 0; } static inline bool init_nodemask_of_mempolicy(nodemask_t *m) { return false; } static inline int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return 0; } static inline void check_highest_zone(int k) { } #ifdef CONFIG_TMPFS static inline int mpol_parse_str(char *str, struct mempolicy **mpol) { return 1; /* error */ } #endif static inline int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long address) { return -1; /* no node preference */ } static inline void mpol_put_task_policy(struct task_struct *task) { } static inline bool mpol_is_preferred_many(struct mempolicy *pol) { return false; } #endif /* CONFIG_NUMA */ #endif |
| 150 150 150 150 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // 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 <linux/cookie.h> #include <linux/proc_fs.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; 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; DEFINE_COOKIE(net_cookie); 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) 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_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) kfree(net_generic(net, *ops->id)); } } /* 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 */ static int __peernet2id(const struct net *net, struct net *peer) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); /* Magic value for id 0. */ if (id == NET_ID_ZERO) return 0; if (id > 0) return id; return NETNSA_NSID_NOT_ASSIGNED; } 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) { int id; if (refcount_read(&net->ns.count) == 0) return NETNSA_NSID_NOT_ASSIGNED; spin_lock_bh(&net->nsid_lock); id = __peernet2id(net, peer); if (id >= 0) { spin_unlock_bh(&net->nsid_lock); return id; } /* 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)) { spin_unlock_bh(&net->nsid_lock); return NETNSA_NSID_NOT_ASSIGNED; } id = alloc_netid(net, peer, -1); spin_unlock_bh(&net->nsid_lock); put_net(peer); if (id < 0) return NETNSA_NSID_NOT_ASSIGNED; rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ int peernet2id(const 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(const struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } struct net *get_net_ns_by_id(const 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; } EXPORT_SYMBOL_GPL(get_net_ns_by_id); /* init code that must occur even if setup_net() is not called. */ static __net_init void preinit_net(struct net *net) { ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt"); } /* * 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; LIST_HEAD(net_exit_list); LIST_HEAD(dev_kill_list); int error = 0; refcount_set(&net->ns.count, 1); ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt"); refcount_set(&net->passive, 1); get_random_bytes(&net->hash_mix, sizeof(u32)); preempt_disable(); net->net_cookie = gen_cookie_next(&net_cookie); preempt_enable(); 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; rtnl_lock(); list_for_each_entry_continue_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); 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; /* Limits per socket sk_omem_alloc usage. * TCP zerocopy regular usage needs 128 KB. */ net->core.sysctl_optmem_max = 128 * 1024; net->core.sysctl_txrehash = SOCK_TXREHASH_ENABLED; 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) { if (refcount_dec_and_test(&net->passive)) { kfree(rcu_access_pointer(net->gen)); /* There should not be any trackers left there. */ ref_tracker_dir_exit(&net->notrefcnt_tracker); kmem_cache_free(net_cachep, net); } } void net_drop_ns(void *p) { struct net *net = (struct net *)p; if (net) net_free(net); } 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; } preinit_net(net); 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_free(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); LIST_HEAD(dev_kill_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_expedited(); rtnl_lock(); list_for_each_entry_reverse(ops, &pernet_list, list) { if (ops->exit_batch_rtnl) ops->exit_batch_rtnl(&net_exit_list, &dev_kill_list); } unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); /* 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_free(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) { ref_tracker_dir_exit(&net->refcnt_tracker); /* 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 fd f = fdget(fd); struct net *net = ERR_PTR(-EINVAL); if (!f.file) return ERR_PTR(-EBADF); if (proc_ns_file(f.file)) { struct ns_common *ns = get_proc_ns(file_inode(f.file)); if (ns->ops == &netns_operations) net = get_net(container_of(ns, struct net, ns)); } fdput(f); return net; } EXPORT_SYMBOL_GPL(get_net_ns_by_fd); #endif 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; } 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); } #ifdef CONFIG_NET_NS static void __init netns_ipv4_struct_check(void) { /* TX readonly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_early_retrans); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_tso_win_divisor); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_tso_rtt_log); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_autocorking); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_min_snd_mss); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_notsent_lowat); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_limit_output_bytes); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_min_rtt_wlen); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_tcp_wmem); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_tx, sysctl_ip_fwd_use_pmtu); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_tx, 33); /* TXRX readonly hotpath cache lines */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_txrx, sysctl_tcp_moderate_rcvbuf); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_txrx, 1); /* RX readonly hotpath cache line */ CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_ip_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_early_demux); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_reordering); CACHELINE_ASSERT_GROUP_MEMBER(struct netns_ipv4, netns_ipv4_read_rx, sysctl_tcp_rmem); CACHELINE_ASSERT_GROUP_SIZE(struct netns_ipv4, netns_ipv4_read_rx, 18); } #endif void __init net_ns_init(void) { struct net_generic *ng; #ifdef CONFIG_NET_NS netns_ipv4_struct_check(); 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); #ifdef CONFIG_KEYS init_net.key_domain = &init_net_key_domain; #endif down_write(&pernet_ops_rwsem); preinit_net(&init_net); 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 | RTNL_FLAG_DUMP_UNLOCKED); } static void free_exit_list(struct pernet_operations *ops, struct list_head *net_exit_list) { ops_pre_exit_list(ops, net_exit_list); synchronize_rcu(); if (ops->exit_batch_rtnl) { LIST_HEAD(dev_kill_list); rtnl_lock(); ops->exit_batch_rtnl(net_exit_list, &dev_kill_list); unregister_netdevice_many(&dev_kill_list); rtnl_unlock(); } ops_exit_list(ops, net_exit_list); ops_free_list(ops, net_exit_list); } #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); free_exit_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); free_exit_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); free_exit_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 nsset *nsset, struct ns_common *ns) { struct nsproxy *nsproxy = nsset->nsproxy; struct net *net = to_net_ns(ns); if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) || !ns_capable(nsset->cred->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 |
| 153 153 153 153 153 153 | 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PGALLOC_TRACK_H #define _LINUX_PGALLOC_TRACK_H #if defined(CONFIG_MMU) static inline p4d_t *p4d_alloc_track(struct mm_struct *mm, pgd_t *pgd, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pgd_none(*pgd))) { if (__p4d_alloc(mm, pgd, address)) return NULL; *mod_mask |= PGTBL_PGD_MODIFIED; } return p4d_offset(pgd, address); } static inline pud_t *pud_alloc_track(struct mm_struct *mm, p4d_t *p4d, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(p4d_none(*p4d))) { if (__pud_alloc(mm, p4d, address)) return NULL; *mod_mask |= PGTBL_P4D_MODIFIED; } return pud_offset(p4d, address); } static inline pmd_t *pmd_alloc_track(struct mm_struct *mm, pud_t *pud, unsigned long address, pgtbl_mod_mask *mod_mask) { if (unlikely(pud_none(*pud))) { if (__pmd_alloc(mm, pud, address)) return NULL; *mod_mask |= PGTBL_PUD_MODIFIED; } return pmd_offset(pud, address); } #endif /* CONFIG_MMU */ #define pte_alloc_kernel_track(pmd, address, mask) \ ((unlikely(pmd_none(*(pmd))) && \ (__pte_alloc_kernel(pmd) || ({*(mask)|=PGTBL_PMD_MODIFIED;0;})))?\ NULL: pte_offset_kernel(pmd, address)) #endif /* _LINUX_PGALLOC_TRACK_H */ |
| 61 61 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Implementations of the security context functions. * * Author: Ondrej Mosnacek <omosnacek@gmail.com> * Copyright (C) 2020 Red Hat, Inc. */ #include <linux/jhash.h> #include "context.h" #include "mls.h" u32 context_compute_hash(const struct context *c) { u32 hash = 0; /* * If a context is invalid, it will always be represented by a * context struct with only the len & str set (and vice versa) * under a given policy. Since context structs from different * policies should never meet, it is safe to hash valid and * invalid contexts differently. The context_cmp() function * already operates under the same assumption. */ if (c->len) return full_name_hash(NULL, c->str, c->len); hash = jhash_3words(c->user, c->role, c->type, hash); hash = mls_range_hash(&c->range, hash); return hash; } |
| 133 133 133 133 133 133 133 133 133 133 133 133 133 133 133 133 51 133 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Generic helpers for smp ipi calls * * (C) Jens Axboe <jens.axboe@oracle.com> 2008 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/irq_work.h> #include <linux/rcupdate.h> #include <linux/rculist.h> #include <linux/kernel.h> #include <linux/export.h> #include <linux/percpu.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/gfp.h> #include <linux/smp.h> #include <linux/cpu.h> #include <linux/sched.h> #include <linux/sched/idle.h> #include <linux/hypervisor.h> #include <linux/sched/clock.h> #include <linux/nmi.h> #include <linux/sched/debug.h> #include <linux/jump_label.h> #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/csd.h> #undef CREATE_TRACE_POINTS #include "smpboot.h" #include "sched/smp.h" #define CSD_TYPE(_csd) ((_csd)->node.u_flags & CSD_FLAG_TYPE_MASK) struct call_function_data { call_single_data_t __percpu *csd; cpumask_var_t cpumask; cpumask_var_t cpumask_ipi; }; static DEFINE_PER_CPU_ALIGNED(struct call_function_data, cfd_data); static DEFINE_PER_CPU_SHARED_ALIGNED(struct llist_head, call_single_queue); static DEFINE_PER_CPU(atomic_t, trigger_backtrace) = ATOMIC_INIT(1); static void __flush_smp_call_function_queue(bool warn_cpu_offline); int smpcfd_prepare_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); if (!zalloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL, cpu_to_node(cpu))) return -ENOMEM; if (!zalloc_cpumask_var_node(&cfd->cpumask_ipi, GFP_KERNEL, cpu_to_node(cpu))) { free_cpumask_var(cfd->cpumask); return -ENOMEM; } cfd->csd = alloc_percpu(call_single_data_t); if (!cfd->csd) { free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); return -ENOMEM; } return 0; } int smpcfd_dead_cpu(unsigned int cpu) { struct call_function_data *cfd = &per_cpu(cfd_data, cpu); free_cpumask_var(cfd->cpumask); free_cpumask_var(cfd->cpumask_ipi); free_percpu(cfd->csd); return 0; } int smpcfd_dying_cpu(unsigned int cpu) { /* * The IPIs for the smp-call-function callbacks queued by other * CPUs might arrive late, either due to hardware latencies or * because this CPU disabled interrupts (inside stop-machine) * before the IPIs were sent. So flush out any pending callbacks * explicitly (without waiting for the IPIs to arrive), to * ensure that the outgoing CPU doesn't go offline with work * still pending. */ __flush_smp_call_function_queue(false); irq_work_run(); return 0; } void __init call_function_init(void) { int i; for_each_possible_cpu(i) init_llist_head(&per_cpu(call_single_queue, i)); smpcfd_prepare_cpu(smp_processor_id()); } static __always_inline void send_call_function_single_ipi(int cpu) { if (call_function_single_prep_ipi(cpu)) { trace_ipi_send_cpu(cpu, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_single_ipi(cpu); } } static __always_inline void send_call_function_ipi_mask(struct cpumask *mask) { trace_ipi_send_cpumask(mask, _RET_IP_, generic_smp_call_function_single_interrupt); arch_send_call_function_ipi_mask(mask); } static __always_inline void csd_do_func(smp_call_func_t func, void *info, call_single_data_t *csd) { trace_csd_function_entry(func, csd); func(info); trace_csd_function_exit(func, csd); } #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG static DEFINE_STATIC_KEY_MAYBE(CONFIG_CSD_LOCK_WAIT_DEBUG_DEFAULT, csdlock_debug_enabled); /* * Parse the csdlock_debug= kernel boot parameter. * * If you need to restore the old "ext" value that once provided * additional debugging information, reapply the following commits: * * de7b09ef658d ("locking/csd_lock: Prepare more CSD lock debugging") * a5aabace5fb8 ("locking/csd_lock: Add more data to CSD lock debugging") */ static int __init csdlock_debug(char *str) { int ret; unsigned int val = 0; ret = get_option(&str, &val); if (ret) { if (val) static_branch_enable(&csdlock_debug_enabled); else static_branch_disable(&csdlock_debug_enabled); } return 1; } __setup("csdlock_debug=", csdlock_debug); static DEFINE_PER_CPU(call_single_data_t *, cur_csd); static DEFINE_PER_CPU(smp_call_func_t, cur_csd_func); static DEFINE_PER_CPU(void *, cur_csd_info); static ulong csd_lock_timeout = 5000; /* CSD lock timeout in milliseconds. */ module_param(csd_lock_timeout, ulong, 0444); static int panic_on_ipistall; /* CSD panic timeout in milliseconds, 300000 for five minutes. */ module_param(panic_on_ipistall, int, 0444); static atomic_t csd_bug_count = ATOMIC_INIT(0); /* Record current CSD work for current CPU, NULL to erase. */ static void __csd_lock_record(call_single_data_t *csd) { if (!csd) { smp_mb(); /* NULL cur_csd after unlock. */ __this_cpu_write(cur_csd, NULL); return; } __this_cpu_write(cur_csd_func, csd->func); __this_cpu_write(cur_csd_info, csd->info); smp_wmb(); /* func and info before csd. */ __this_cpu_write(cur_csd, csd); smp_mb(); /* Update cur_csd before function call. */ /* Or before unlock, as the case may be. */ } static __always_inline void csd_lock_record(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) __csd_lock_record(csd); } static int csd_lock_wait_getcpu(call_single_data_t *csd) { unsigned int csd_type; csd_type = CSD_TYPE(csd); if (csd_type == CSD_TYPE_ASYNC || csd_type == CSD_TYPE_SYNC) return csd->node.dst; /* Other CSD_TYPE_ values might not have ->dst. */ return -1; } /* * Complain if too much time spent waiting. Note that only * the CSD_TYPE_SYNC/ASYNC types provide the destination CPU, * so waiting on other types gets much less information. */ static bool csd_lock_wait_toolong(call_single_data_t *csd, u64 ts0, u64 *ts1, int *bug_id) { int cpu = -1; int cpux; bool firsttime; u64 ts2, ts_delta; call_single_data_t *cpu_cur_csd; unsigned int flags = READ_ONCE(csd->node.u_flags); unsigned long long csd_lock_timeout_ns = csd_lock_timeout * NSEC_PER_MSEC; if (!(flags & CSD_FLAG_LOCK)) { if (!unlikely(*bug_id)) return true; cpu = csd_lock_wait_getcpu(csd); pr_alert("csd: CSD lock (#%d) got unstuck on CPU#%02d, CPU#%02d released the lock.\n", *bug_id, raw_smp_processor_id(), cpu); return true; } ts2 = sched_clock(); /* How long since we last checked for a stuck CSD lock.*/ ts_delta = ts2 - *ts1; if (likely(ts_delta <= csd_lock_timeout_ns || csd_lock_timeout_ns == 0)) return false; firsttime = !*bug_id; if (firsttime) *bug_id = atomic_inc_return(&csd_bug_count); cpu = csd_lock_wait_getcpu(csd); if (WARN_ONCE(cpu < 0 || cpu >= nr_cpu_ids, "%s: cpu = %d\n", __func__, cpu)) cpux = 0; else cpux = cpu; cpu_cur_csd = smp_load_acquire(&per_cpu(cur_csd, cpux)); /* Before func and info. */ /* How long since this CSD lock was stuck. */ ts_delta = ts2 - ts0; pr_alert("csd: %s non-responsive CSD lock (#%d) on CPU#%d, waiting %llu ns for CPU#%02d %pS(%ps).\n", firsttime ? "Detected" : "Continued", *bug_id, raw_smp_processor_id(), ts_delta, cpu, csd->func, csd->info); /* * If the CSD lock is still stuck after 5 minutes, it is unlikely * to become unstuck. Use a signed comparison to avoid triggering * on underflows when the TSC is out of sync between sockets. */ BUG_ON(panic_on_ipistall > 0 && (s64)ts_delta > ((s64)panic_on_ipistall * NSEC_PER_MSEC)); if (cpu_cur_csd && csd != cpu_cur_csd) { pr_alert("\tcsd: CSD lock (#%d) handling prior %pS(%ps) request.\n", *bug_id, READ_ONCE(per_cpu(cur_csd_func, cpux)), READ_ONCE(per_cpu(cur_csd_info, cpux))); } else { pr_alert("\tcsd: CSD lock (#%d) %s.\n", *bug_id, !cpu_cur_csd ? "unresponsive" : "handling this request"); } if (cpu >= 0) { if (atomic_cmpxchg_acquire(&per_cpu(trigger_backtrace, cpu), 1, 0)) dump_cpu_task(cpu); if (!cpu_cur_csd) { pr_alert("csd: Re-sending CSD lock (#%d) IPI from CPU#%02d to CPU#%02d\n", *bug_id, raw_smp_processor_id(), cpu); arch_send_call_function_single_ipi(cpu); } } if (firsttime) dump_stack(); *ts1 = ts2; return false; } /* * csd_lock/csd_unlock used to serialize access to per-cpu csd resources * * For non-synchronous ipi calls the csd can still be in use by the * previous function call. For multi-cpu calls its even more interesting * as we'll have to ensure no other cpu is observing our csd. */ static void __csd_lock_wait(call_single_data_t *csd) { int bug_id = 0; u64 ts0, ts1; ts1 = ts0 = sched_clock(); for (;;) { if (csd_lock_wait_toolong(csd, ts0, &ts1, &bug_id)) break; cpu_relax(); } smp_acquire__after_ctrl_dep(); } static __always_inline void csd_lock_wait(call_single_data_t *csd) { if (static_branch_unlikely(&csdlock_debug_enabled)) { __csd_lock_wait(csd); return; } smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #else static void csd_lock_record(call_single_data_t *csd) { } static __always_inline void csd_lock_wait(call_single_data_t *csd) { smp_cond_load_acquire(&csd->node.u_flags, !(VAL & CSD_FLAG_LOCK)); } #endif static __always_inline void csd_lock(call_single_data_t *csd) { csd_lock_wait(csd); csd->node.u_flags |= CSD_FLAG_LOCK; /* * prevent CPU from reordering the above assignment * to ->flags with any subsequent assignments to other * fields of the specified call_single_data_t structure: */ smp_wmb(); } static __always_inline void csd_unlock(call_single_data_t *csd) { WARN_ON(!(csd->node.u_flags & CSD_FLAG_LOCK)); /* * ensure we're all done before releasing data: */ smp_store_release(&csd->node.u_flags, 0); } static DEFINE_PER_CPU_SHARED_ALIGNED(call_single_data_t, csd_data); void __smp_call_single_queue(int cpu, struct llist_node *node) { /* * We have to check the type of the CSD before queueing it, because * once queued it can have its flags cleared by * flush_smp_call_function_queue() * even if we haven't sent the smp_call IPI yet (e.g. the stopper * executes migration_cpu_stop() on the remote CPU). */ if (trace_csd_queue_cpu_enabled()) { call_single_data_t *csd; smp_call_func_t func; csd = container_of(node, call_single_data_t, node.llist); func = CSD_TYPE(csd) == CSD_TYPE_TTWU ? sched_ttwu_pending : csd->func; trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); } /* * The list addition should be visible to the target CPU when it pops * the head of the list to pull the entry off it in the IPI handler * because of normal cache coherency rules implied by the underlying * llist ops. * * If IPIs can go out of order to the cache coherency protocol * in an architecture, sufficient synchronisation should be added * to arch code to make it appear to obey cache coherency WRT * locking and barrier primitives. Generic code isn't really * equipped to do the right thing... */ if (llist_add(node, &per_cpu(call_single_queue, cpu))) send_call_function_single_ipi(cpu); } /* * Insert a previously allocated call_single_data_t element * for execution on the given CPU. data must already have * ->func, ->info, and ->flags set. */ static int generic_exec_single(int cpu, call_single_data_t *csd) { if (cpu == smp_processor_id()) { smp_call_func_t func = csd->func; void *info = csd->info; unsigned long flags; /* * We can unlock early even for the synchronous on-stack case, * since we're doing this from the same CPU.. */ csd_lock_record(csd); csd_unlock(csd); local_irq_save(flags); csd_do_func(func, info, NULL); csd_lock_record(NULL); local_irq_restore(flags); return 0; } if ((unsigned)cpu >= nr_cpu_ids || !cpu_online(cpu)) { csd_unlock(csd); return -ENXIO; } __smp_call_single_queue(cpu, &csd->node.llist); return 0; } /** * generic_smp_call_function_single_interrupt - Execute SMP IPI callbacks * * Invoked by arch to handle an IPI for call function single. * Must be called with interrupts disabled. */ void generic_smp_call_function_single_interrupt(void) { __flush_smp_call_function_queue(true); } /** * __flush_smp_call_function_queue - Flush pending smp-call-function callbacks * * @warn_cpu_offline: If set to 'true', warn if callbacks were queued on an * offline CPU. Skip this check if set to 'false'. * * Flush any pending smp-call-function callbacks queued on this CPU. This is * invoked by the generic IPI handler, as well as by a CPU about to go offline, * to ensure that all pending IPI callbacks are run before it goes completely * offline. * * Loop through the call_single_queue and run all the queued callbacks. * Must be called with interrupts disabled. */ static void __flush_smp_call_function_queue(bool warn_cpu_offline) { call_single_data_t *csd, *csd_next; struct llist_node *entry, *prev; struct llist_head *head; static bool warned; atomic_t *tbt; lockdep_assert_irqs_disabled(); /* Allow waiters to send backtrace NMI from here onwards */ tbt = this_cpu_ptr(&trigger_backtrace); atomic_set_release(tbt, 1); head = this_cpu_ptr(&call_single_queue); entry = llist_del_all(head); entry = llist_reverse_order(entry); /* There shouldn't be any pending callbacks on an offline CPU. */ if (unlikely(warn_cpu_offline && !cpu_online(smp_processor_id()) && !warned && entry != NULL)) { warned = true; WARN(1, "IPI on offline CPU %d\n", smp_processor_id()); /* * We don't have to use the _safe() variant here * because we are not invoking the IPI handlers yet. */ llist_for_each_entry(csd, entry, node.llist) { switch (CSD_TYPE(csd)) { case CSD_TYPE_ASYNC: case CSD_TYPE_SYNC: case CSD_TYPE_IRQ_WORK: pr_warn("IPI callback %pS sent to offline CPU\n", csd->func); break; case CSD_TYPE_TTWU: pr_warn("IPI task-wakeup sent to offline CPU\n"); break; default: pr_warn("IPI callback, unknown type %d, sent to offline CPU\n", CSD_TYPE(csd)); break; } } } /* * First; run all SYNC callbacks, people are waiting for us. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { /* Do we wait until *after* callback? */ if (CSD_TYPE(csd) == CSD_TYPE_SYNC) { smp_call_func_t func = csd->func; void *info = csd->info; if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } csd_lock_record(csd); csd_do_func(func, info, csd); csd_unlock(csd); csd_lock_record(NULL); } else { prev = &csd->node.llist; } } if (!entry) return; /* * Second; run all !SYNC callbacks. */ prev = NULL; llist_for_each_entry_safe(csd, csd_next, entry, node.llist) { int type = CSD_TYPE(csd); if (type != CSD_TYPE_TTWU) { if (prev) { prev->next = &csd_next->node.llist; } else { entry = &csd_next->node.llist; } if (type == CSD_TYPE_ASYNC) { smp_call_func_t func = csd->func; void *info = csd->info; csd_lock_record(csd); csd_unlock(csd); csd_do_func(func, info, csd); csd_lock_record(NULL); } else if (type == CSD_TYPE_IRQ_WORK) { irq_work_single(csd); } } else { prev = &csd->node.llist; } } /* * Third; only CSD_TYPE_TTWU is left, issue those. */ if (entry) { csd = llist_entry(entry, typeof(*csd), node.llist); csd_do_func(sched_ttwu_pending, entry, csd); } } /** * flush_smp_call_function_queue - Flush pending smp-call-function callbacks * from task context (idle, migration thread) * * When TIF_POLLING_NRFLAG is supported and a CPU is in idle and has it * set, then remote CPUs can avoid sending IPIs and wake the idle CPU by * setting TIF_NEED_RESCHED. The idle task on the woken up CPU has to * handle queued SMP function calls before scheduling. * * The migration thread has to ensure that an eventually pending wakeup has * been handled before it migrates a task. */ void flush_smp_call_function_queue(void) { unsigned int was_pending; unsigned long flags; if (llist_empty(this_cpu_ptr(&call_single_queue))) return; local_irq_save(flags); /* Get the already pending soft interrupts for RT enabled kernels */ was_pending = local_softirq_pending(); __flush_smp_call_function_queue(true); if (local_softirq_pending()) do_softirq_post_smp_call_flush(was_pending); local_irq_restore(flags); } /* * smp_call_function_single - Run a function on a specific CPU * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed on other CPUs. * * Returns 0 on success, else a negative status code. */ int smp_call_function_single(int cpu, smp_call_func_t func, void *info, int wait) { call_single_data_t *csd; call_single_data_t csd_stack = { .node = { .u_flags = CSD_FLAG_LOCK | CSD_TYPE_SYNC, }, }; int this_cpu; int err; /* * prevent preemption and reschedule on another processor, * as well as CPU removal */ this_cpu = get_cpu(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ WARN_ON_ONCE(cpu_online(this_cpu) && irqs_disabled() && !oops_in_progress); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); csd = &csd_stack; if (!wait) { csd = this_cpu_ptr(&csd_data); csd_lock(csd); } csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif err = generic_exec_single(cpu, csd); if (wait) csd_lock_wait(csd); put_cpu(); return err; } EXPORT_SYMBOL(smp_call_function_single); /** * smp_call_function_single_async() - Run an asynchronous function on a * specific CPU. * @cpu: The CPU to run on. * @csd: Pre-allocated and setup data structure * * Like smp_call_function_single(), but the call is asynchonous and * can thus be done from contexts with disabled interrupts. * * The caller passes his own pre-allocated data structure * (ie: embedded in an object) and is responsible for synchronizing it * such that the IPIs performed on the @csd are strictly serialized. * * If the function is called with one csd which has not yet been * processed by previous call to smp_call_function_single_async(), the * function will return immediately with -EBUSY showing that the csd * object is still in progress. * * NOTE: Be careful, there is unfortunately no current debugging facility to * validate the correctness of this serialization. * * Return: %0 on success or negative errno value on error */ int smp_call_function_single_async(int cpu, call_single_data_t *csd) { int err = 0; preempt_disable(); if (csd->node.u_flags & CSD_FLAG_LOCK) { err = -EBUSY; goto out; } csd->node.u_flags = CSD_FLAG_LOCK; smp_wmb(); err = generic_exec_single(cpu, csd); out: preempt_enable(); return err; } EXPORT_SYMBOL_GPL(smp_call_function_single_async); /* * smp_call_function_any - Run a function on any of the given cpus * @mask: The mask of cpus it can run on. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait until function has completed. * * Returns 0 on success, else a negative status code (if no cpus were online). * * Selection preference: * 1) current cpu if in @mask * 2) any cpu of current node if in @mask * 3) any other online cpu in @mask */ int smp_call_function_any(const struct cpumask *mask, smp_call_func_t func, void *info, int wait) { unsigned int cpu; const struct cpumask *nodemask; int ret; /* Try for same CPU (cheapest) */ cpu = get_cpu(); if (cpumask_test_cpu(cpu, mask)) goto call; /* Try for same node. */ nodemask = cpumask_of_node(cpu_to_node(cpu)); for (cpu = cpumask_first_and(nodemask, mask); cpu < nr_cpu_ids; cpu = cpumask_next_and(cpu, nodemask, mask)) { if (cpu_online(cpu)) goto call; } /* Any online will do: smp_call_function_single handles nr_cpu_ids. */ cpu = cpumask_any_and(mask, cpu_online_mask); call: ret = smp_call_function_single(cpu, func, info, wait); put_cpu(); return ret; } EXPORT_SYMBOL_GPL(smp_call_function_any); /* * Flags to be used as scf_flags argument of smp_call_function_many_cond(). * * %SCF_WAIT: Wait until function execution is completed * %SCF_RUN_LOCAL: Run also locally if local cpu is set in cpumask */ #define SCF_WAIT (1U << 0) #define SCF_RUN_LOCAL (1U << 1) static void smp_call_function_many_cond(const struct cpumask *mask, smp_call_func_t func, void *info, unsigned int scf_flags, smp_cond_func_t cond_func) { int cpu, last_cpu, this_cpu = smp_processor_id(); struct call_function_data *cfd; bool wait = scf_flags & SCF_WAIT; int nr_cpus = 0; bool run_remote = false; bool run_local = false; lockdep_assert_preemption_disabled(); /* * Can deadlock when called with interrupts disabled. * We allow cpu's that are not yet online though, as no one else can * send smp call function interrupt to this cpu and as such deadlocks * can't happen. */ if (cpu_online(this_cpu) && !oops_in_progress && !early_boot_irqs_disabled) lockdep_assert_irqs_enabled(); /* * When @wait we can deadlock when we interrupt between llist_add() and * arch_send_call_function_ipi*(); when !@wait we can deadlock due to * csd_lock() on because the interrupt context uses the same csd * storage. */ WARN_ON_ONCE(!in_task()); /* Check if we need local execution. */ if ((scf_flags & SCF_RUN_LOCAL) && cpumask_test_cpu(this_cpu, mask)) run_local = true; /* Check if we need remote execution, i.e., any CPU excluding this one. */ cpu = cpumask_first_and(mask, cpu_online_mask); if (cpu == this_cpu) cpu = cpumask_next_and(cpu, mask, cpu_online_mask); if (cpu < nr_cpu_ids) run_remote = true; if (run_remote) { cfd = this_cpu_ptr(&cfd_data); cpumask_and(cfd->cpumask, mask, cpu_online_mask); __cpumask_clear_cpu(this_cpu, cfd->cpumask); cpumask_clear(cfd->cpumask_ipi); for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd = per_cpu_ptr(cfd->csd, cpu); if (cond_func && !cond_func(cpu, info)) { __cpumask_clear_cpu(cpu, cfd->cpumask); continue; } csd_lock(csd); if (wait) csd->node.u_flags |= CSD_TYPE_SYNC; csd->func = func; csd->info = info; #ifdef CONFIG_CSD_LOCK_WAIT_DEBUG csd->node.src = smp_processor_id(); csd->node.dst = cpu; #endif trace_csd_queue_cpu(cpu, _RET_IP_, func, csd); if (llist_add(&csd->node.llist, &per_cpu(call_single_queue, cpu))) { __cpumask_set_cpu(cpu, cfd->cpumask_ipi); nr_cpus++; last_cpu = cpu; } } /* * Choose the most efficient way to send an IPI. Note that the * number of CPUs might be zero due to concurrent changes to the * provided mask. */ if (nr_cpus == 1) send_call_function_single_ipi(last_cpu); else if (likely(nr_cpus > 1)) send_call_function_ipi_mask(cfd->cpumask_ipi); } if (run_local && (!cond_func || cond_func(this_cpu, info))) { unsigned long flags; local_irq_save(flags); csd_do_func(func, info, NULL); local_irq_restore(flags); } if (run_remote && wait) { for_each_cpu(cpu, cfd->cpumask) { call_single_data_t *csd; csd = per_cpu_ptr(cfd->csd, cpu); csd_lock_wait(csd); } } } /** * smp_call_function_many(): Run a function on a set of CPUs. * @mask: The set of cpus to run on (only runs on online subset). * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: Bitmask that controls the operation. If %SCF_WAIT is set, wait * (atomically) until function has completed on other CPUs. If * %SCF_RUN_LOCAL is set, the function will also be run locally * if the local CPU is set in the @cpumask. * * If @wait is true, then returns once @func has returned. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. Preemption * must be disabled when calling this function. */ void smp_call_function_many(const struct cpumask *mask, smp_call_func_t func, void *info, bool wait) { smp_call_function_many_cond(mask, func, info, wait * SCF_WAIT, NULL); } EXPORT_SYMBOL(smp_call_function_many); /** * smp_call_function(): Run a function on all other CPUs. * @func: The function to run. This must be fast and non-blocking. * @info: An arbitrary pointer to pass to the function. * @wait: If true, wait (atomically) until function has completed * on other CPUs. * * Returns 0. * * If @wait is true, then returns once @func has returned; otherwise * it returns just before the target cpu calls @func. * * You must not call this function with disabled interrupts or from a * hardware interrupt handler or from a bottom half handler. */ void smp_call_function(smp_call_func_t func, void *info, int wait) { preempt_disable(); smp_call_function_many(cpu_online_mask, func, info, wait); preempt_enable(); } EXPORT_SYMBOL(smp_call_function); /* Setup configured maximum number of CPUs to activate */ unsigned int setup_max_cpus = NR_CPUS; EXPORT_SYMBOL(setup_max_cpus); /* * Setup routine for controlling SMP activation * * Command-line option of "nosmp" or "maxcpus=0" will disable SMP * activation entirely (the MPS table probe still happens, though). * * Command-line option of "maxcpus=<NUM>", where <NUM> is an integer * greater than 0, limits the maximum number of CPUs activated in * SMP mode to <NUM>. */ void __weak __init arch_disable_smp_support(void) { } static int __init nosmp(char *str) { setup_max_cpus = 0; arch_disable_smp_support(); return 0; } early_param("nosmp", nosmp); /* this is hard limit */ static int __init nrcpus(char *str) { int nr_cpus; if (get_option(&str, &nr_cpus) && nr_cpus > 0 && nr_cpus < nr_cpu_ids) set_nr_cpu_ids(nr_cpus); return 0; } early_param("nr_cpus", nrcpus); static int __init maxcpus(char *str) { get_option(&str, &setup_max_cpus); if (setup_max_cpus == 0) arch_disable_smp_support(); return 0; } early_param("maxcpus", maxcpus); #if (NR_CPUS > 1) && !defined(CONFIG_FORCE_NR_CPUS) /* Setup number of possible processor ids */ unsigned int nr_cpu_ids __read_mostly = NR_CPUS; EXPORT_SYMBOL(nr_cpu_ids); #endif /* An arch may set nr_cpu_ids earlier if needed, so this would be redundant */ void __init setup_nr_cpu_ids(void) { set_nr_cpu_ids(find_last_bit(cpumask_bits(cpu_possible_mask), NR_CPUS) + 1); } /* Called by boot processor to activate the rest. */ void __init smp_init(void) { int num_nodes, num_cpus; idle_threads_init(); cpuhp_threads_init(); pr_info("Bringing up secondary CPUs ...\n"); bringup_nonboot_cpus(setup_max_cpus); num_nodes = num_online_nodes(); num_cpus = num_online_cpus(); pr_info("Brought up %d node%s, %d CPU%s\n", num_nodes, (num_nodes > 1 ? "s" : ""), num_cpus, (num_cpus > 1 ? "s" : "")); /* Any cleanup work */ smp_cpus_done(setup_max_cpus); } /* * on_each_cpu_cond(): Call a function on each processor for which * the supplied function cond_func returns true, optionally waiting * for all the required CPUs to finish. This may include the local * processor. * @cond_func: A callback function that is passed a cpu id and * the info parameter. The function is called * with preemption disabled. The function should * return a blooean value indicating whether to IPI * the specified CPU. * @func: The function to run on all applicable CPUs. * This must be fast and non-blocking. * @info: An arbitrary pointer to pass to both functions. * @wait: If true, wait (atomically) until function has * completed on other CPUs. * * Preemption is disabled to protect against CPUs going offline but not online. * CPUs going online during the call will not be seen or sent an IPI. * * You must not call this function with disabled interrupts or * from a hardware interrupt handler or from a bottom half handler. */ void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func, void *info, bool wait, const struct cpumask *mask) { unsigned int scf_flags = SCF_RUN_LOCAL; if (wait) scf_flags |= SCF_WAIT; preempt_disable(); smp_call_function_many_cond(mask, func, info, scf_flags, cond_func); preempt_enable(); } EXPORT_SYMBOL(on_each_cpu_cond_mask); static void do_nothing(void *unused) { } /** * kick_all_cpus_sync - Force all cpus out of idle * * Used to synchronize the update of pm_idle function pointer. It's * called after the pointer is updated and returns after the dummy * callback function has been executed on all cpus. The execution of * the function can only happen on the remote cpus after they have * left the idle function which had been called via pm_idle function * pointer. So it's guaranteed that nothing uses the previous pointer * anymore. */ void kick_all_cpus_sync(void) { /* Make sure the change is visible before we kick the cpus */ smp_mb(); smp_call_function(do_nothing, NULL, 1); } EXPORT_SYMBOL_GPL(kick_all_cpus_sync); /** * wake_up_all_idle_cpus - break all cpus out of idle * wake_up_all_idle_cpus try to break all cpus which is in idle state even * including idle polling cpus, for non-idle cpus, we will do nothing * for them. */ void wake_up_all_idle_cpus(void) { int cpu; for_each_possible_cpu(cpu) { preempt_disable(); if (cpu != smp_processor_id() && cpu_online(cpu)) wake_up_if_idle(cpu); preempt_enable(); } } EXPORT_SYMBOL_GPL(wake_up_all_idle_cpus); /** * struct smp_call_on_cpu_struct - Call a function on a specific CPU * @work: &work_struct * @done: &completion to signal * @func: function to call * @data: function's data argument * @ret: return value from @func * @cpu: target CPU (%-1 for any CPU) * * Used to call a function on a specific cpu and wait for it to return. * Optionally make sure the call is done on a specified physical cpu via vcpu * pinning in order to support virtualized environments. */ struct smp_call_on_cpu_struct { struct work_struct work; struct completion done; int (*func)(void *); void *data; int ret; int cpu; }; static void smp_call_on_cpu_callback(struct work_struct *work) { struct smp_call_on_cpu_struct *sscs; sscs = container_of(work, struct smp_call_on_cpu_struct, work); if (sscs->cpu >= 0) hypervisor_pin_vcpu(sscs->cpu); sscs->ret = sscs->func(sscs->data); if (sscs->cpu >= 0) hypervisor_pin_vcpu(-1); complete(&sscs->done); } int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys) { struct smp_call_on_cpu_struct sscs = { .done = COMPLETION_INITIALIZER_ONSTACK(sscs.done), .func = func, .data = par, .cpu = phys ? cpu : -1, }; INIT_WORK_ONSTACK(&sscs.work, smp_call_on_cpu_callback); if (cpu >= nr_cpu_ids || !cpu_online(cpu)) return -ENXIO; queue_work_on(cpu, system_wq, &sscs.work); wait_for_completion(&sscs.done); return sscs.ret; } EXPORT_SYMBOL_GPL(smp_call_on_cpu); |
| 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/super.c * * Copyright (C) 1991, 1992 Linus Torvalds * * super.c contains code to handle: - mount structures * - super-block tables * - filesystem drivers list * - mount system call * - umount system call * - ustat system call * * GK 2/5/95 - Changed to support mounting the root fs via NFS * * Added kerneld support: Jacques Gelinas and Bjorn Ekwall * Added change_root: Werner Almesberger & Hans Lermen, Feb '96 * Added options to /proc/mounts: * Torbjörn Lindh (torbjorn.lindh@gopta.se), April 14, 1996. * Added devfs support: Richard Gooch <rgooch@atnf.csiro.au>, 13-JAN-1998 * Heavily rewritten for 'one fs - one tree' dcache architecture. AV, Mar 2000 */ #include <linux/export.h> #include <linux/slab.h> #include <linux/blkdev.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/writeback.h> /* for the emergency remount stuff */ #include <linux/idr.h> #include <linux/mutex.h> #include <linux/backing-dev.h> #include <linux/rculist_bl.h> #include <linux/fscrypt.h> #include <linux/fsnotify.h> #include <linux/lockdep.h> #include <linux/user_namespace.h> #include <linux/fs_context.h> #include <uapi/linux/mount.h> #include "internal.h" static int thaw_super_locked(struct super_block *sb, enum freeze_holder who); static LIST_HEAD(super_blocks); static DEFINE_SPINLOCK(sb_lock); static char *sb_writers_name[SB_FREEZE_LEVELS] = { "sb_writers", "sb_pagefaults", "sb_internal", }; static inline void __super_lock(struct super_block *sb, bool excl) { if (excl) down_write(&sb->s_umount); else down_read(&sb->s_umount); } static inline void super_unlock(struct super_block *sb, bool excl) { if (excl) up_write(&sb->s_umount); else up_read(&sb->s_umount); } static inline void __super_lock_excl(struct super_block *sb) { __super_lock(sb, true); } static inline void super_unlock_excl(struct super_block *sb) { super_unlock(sb, true); } static inline void super_unlock_shared(struct super_block *sb) { super_unlock(sb, false); } static bool super_flags(const struct super_block *sb, unsigned int flags) { /* * Pairs with smp_store_release() in super_wake() and ensures * that we see @flags after we're woken. */ return smp_load_acquire(&sb->s_flags) & flags; } /** * super_lock - wait for superblock to become ready and lock it * @sb: superblock to wait for * @excl: whether exclusive access is required * * If the superblock has neither passed through vfs_get_tree() or * generic_shutdown_super() yet wait for it to happen. Either superblock * creation will succeed and SB_BORN is set by vfs_get_tree() or we're * woken and we'll see SB_DYING. * * The caller must have acquired a temporary reference on @sb->s_count. * * Return: The function returns true if SB_BORN was set and with * s_umount held. The function returns false if SB_DYING was * set and without s_umount held. */ static __must_check bool super_lock(struct super_block *sb, bool excl) { lockdep_assert_not_held(&sb->s_umount); /* wait until the superblock is ready or dying */ wait_var_event(&sb->s_flags, super_flags(sb, SB_BORN | SB_DYING)); /* Don't pointlessly acquire s_umount. */ if (super_flags(sb, SB_DYING)) return false; __super_lock(sb, excl); /* * Has gone through generic_shutdown_super() in the meantime. * @sb->s_root is NULL and @sb->s_active is 0. No one needs to * grab a reference to this. Tell them so. */ if (sb->s_flags & SB_DYING) { super_unlock(sb, excl); return false; } WARN_ON_ONCE(!(sb->s_flags & SB_BORN)); return true; } /* wait and try to acquire read-side of @sb->s_umount */ static inline bool super_lock_shared(struct super_block *sb) { return super_lock(sb, false); } /* wait and try to acquire write-side of @sb->s_umount */ static inline bool super_lock_excl(struct super_block *sb) { return super_lock(sb, true); } /* wake waiters */ #define SUPER_WAKE_FLAGS (SB_BORN | SB_DYING | SB_DEAD) static void super_wake(struct super_block *sb, unsigned int flag) { WARN_ON_ONCE((flag & ~SUPER_WAKE_FLAGS)); WARN_ON_ONCE(hweight32(flag & SUPER_WAKE_FLAGS) > 1); /* * Pairs with smp_load_acquire() in super_lock() to make sure * all initializations in the superblock are seen by the user * seeing SB_BORN sent. */ smp_store_release(&sb->s_flags, sb->s_flags | flag); /* * Pairs with the barrier in prepare_to_wait_event() to make sure * ___wait_var_event() either sees SB_BORN set or * waitqueue_active() check in wake_up_var() sees the waiter. */ smp_mb(); wake_up_var(&sb->s_flags); } /* * One thing we have to be careful of with a per-sb shrinker is that we don't * drop the last active reference to the superblock from within the shrinker. * If that happens we could trigger unregistering the shrinker from within the * shrinker path and that leads to deadlock on the shrinker_mutex. Hence we * take a passive reference to the superblock to avoid this from occurring. */ static unsigned long super_cache_scan(struct shrinker *shrink, struct shrink_control *sc) { struct super_block *sb; long fs_objects = 0; long total_objects; long freed = 0; long dentries; long inodes; sb = shrink->private_data; /* * Deadlock avoidance. We may hold various FS locks, and we don't want * to recurse into the FS that called us in clear_inode() and friends.. */ if (!(sc->gfp_mask & __GFP_FS)) return SHRINK_STOP; if (!super_trylock_shared(sb)) return SHRINK_STOP; if (sb->s_op->nr_cached_objects) fs_objects = sb->s_op->nr_cached_objects(sb, sc); inodes = list_lru_shrink_count(&sb->s_inode_lru, sc); dentries = list_lru_shrink_count(&sb->s_dentry_lru, sc); total_objects = dentries + inodes + fs_objects + 1; if (!total_objects) total_objects = 1; /* proportion the scan between the caches */ dentries = mult_frac(sc->nr_to_scan, dentries, total_objects); inodes = mult_frac(sc->nr_to_scan, inodes, total_objects); fs_objects = mult_frac(sc->nr_to_scan, fs_objects, total_objects); /* * prune the dcache first as the icache is pinned by it, then * prune the icache, followed by the filesystem specific caches * * Ensure that we always scan at least one object - memcg kmem * accounting uses this to fully empty the caches. */ sc->nr_to_scan = dentries + 1; freed = prune_dcache_sb(sb, sc); sc->nr_to_scan = inodes + 1; freed += prune_icache_sb(sb, sc); if (fs_objects) { sc->nr_to_scan = fs_objects + 1; freed += sb->s_op->free_cached_objects(sb, sc); } super_unlock_shared(sb); return freed; } static unsigned long super_cache_count(struct shrinker *shrink, struct shrink_control *sc) { struct super_block *sb; long total_objects = 0; sb = shrink->private_data; /* * We don't call super_trylock_shared() here as it is a scalability * bottleneck, so we're exposed to partial setup state. The shrinker * rwsem does not protect filesystem operations backing * list_lru_shrink_count() or s_op->nr_cached_objects(). Counts can * change between super_cache_count and super_cache_scan, so we really * don't need locks here. * * However, if we are currently mounting the superblock, the underlying * filesystem might be in a state of partial construction and hence it * is dangerous to access it. super_trylock_shared() uses a SB_BORN check * to avoid this situation, so do the same here. The memory barrier is * matched with the one in mount_fs() as we don't hold locks here. */ if (!(sb->s_flags & SB_BORN)) return 0; smp_rmb(); if (sb->s_op && sb->s_op->nr_cached_objects) total_objects = sb->s_op->nr_cached_objects(sb, sc); total_objects += list_lru_shrink_count(&sb->s_dentry_lru, sc); total_objects += list_lru_shrink_count(&sb->s_inode_lru, sc); if (!total_objects) return SHRINK_EMPTY; total_objects = vfs_pressure_ratio(total_objects); return total_objects; } static void destroy_super_work(struct work_struct *work) { struct super_block *s = container_of(work, struct super_block, destroy_work); fsnotify_sb_free(s); security_sb_free(s); put_user_ns(s->s_user_ns); kfree(s->s_subtype); for (int i = 0; i < SB_FREEZE_LEVELS; i++) percpu_free_rwsem(&s->s_writers.rw_sem[i]); kfree(s); } static void destroy_super_rcu(struct rcu_head *head) { struct super_block *s = container_of(head, struct super_block, rcu); INIT_WORK(&s->destroy_work, destroy_super_work); schedule_work(&s->destroy_work); } /* Free a superblock that has never been seen by anyone */ static void destroy_unused_super(struct super_block *s) { if (!s) return; super_unlock_excl(s); list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); shrinker_free(s->s_shrink); /* no delays needed */ destroy_super_work(&s->destroy_work); } /** * alloc_super - create new superblock * @type: filesystem type superblock should belong to * @flags: the mount flags * @user_ns: User namespace for the super_block * * Allocates and initializes a new &struct super_block. alloc_super() * returns a pointer new superblock or %NULL if allocation had failed. */ static struct super_block *alloc_super(struct file_system_type *type, int flags, struct user_namespace *user_ns) { struct super_block *s = kzalloc(sizeof(struct super_block), GFP_KERNEL); static const struct super_operations default_op; int i; if (!s) return NULL; INIT_LIST_HEAD(&s->s_mounts); s->s_user_ns = get_user_ns(user_ns); init_rwsem(&s->s_umount); lockdep_set_class(&s->s_umount, &type->s_umount_key); /* * sget() can have s_umount recursion. * * When it cannot find a suitable sb, it allocates a new * one (this one), and tries again to find a suitable old * one. * * In case that succeeds, it will acquire the s_umount * lock of the old one. Since these are clearly distrinct * locks, and this object isn't exposed yet, there's no * risk of deadlocks. * * Annotate this by putting this lock in a different * subclass. */ down_write_nested(&s->s_umount, SINGLE_DEPTH_NESTING); if (security_sb_alloc(s)) goto fail; for (i = 0; i < SB_FREEZE_LEVELS; i++) { if (__percpu_init_rwsem(&s->s_writers.rw_sem[i], sb_writers_name[i], &type->s_writers_key[i])) goto fail; } s->s_bdi = &noop_backing_dev_info; s->s_flags = flags; if (s->s_user_ns != &init_user_ns) s->s_iflags |= SB_I_NODEV; INIT_HLIST_NODE(&s->s_instances); INIT_HLIST_BL_HEAD(&s->s_roots); mutex_init(&s->s_sync_lock); INIT_LIST_HEAD(&s->s_inodes); spin_lock_init(&s->s_inode_list_lock); INIT_LIST_HEAD(&s->s_inodes_wb); spin_lock_init(&s->s_inode_wblist_lock); s->s_count = 1; atomic_set(&s->s_active, 1); mutex_init(&s->s_vfs_rename_mutex); lockdep_set_class(&s->s_vfs_rename_mutex, &type->s_vfs_rename_key); init_rwsem(&s->s_dquot.dqio_sem); s->s_maxbytes = MAX_NON_LFS; s->s_op = &default_op; s->s_time_gran = 1000000000; s->s_time_min = TIME64_MIN; s->s_time_max = TIME64_MAX; s->s_shrink = shrinker_alloc(SHRINKER_NUMA_AWARE | SHRINKER_MEMCG_AWARE, "sb-%s", type->name); if (!s->s_shrink) goto fail; s->s_shrink->scan_objects = super_cache_scan; s->s_shrink->count_objects = super_cache_count; s->s_shrink->batch = 1024; s->s_shrink->private_data = s; if (list_lru_init_memcg(&s->s_dentry_lru, s->s_shrink)) goto fail; if (list_lru_init_memcg(&s->s_inode_lru, s->s_shrink)) goto fail; return s; fail: destroy_unused_super(s); return NULL; } /* Superblock refcounting */ /* * Drop a superblock's refcount. The caller must hold sb_lock. */ static void __put_super(struct super_block *s) { if (!--s->s_count) { list_del_init(&s->s_list); WARN_ON(s->s_dentry_lru.node); WARN_ON(s->s_inode_lru.node); WARN_ON(!list_empty(&s->s_mounts)); call_rcu(&s->rcu, destroy_super_rcu); } } /** * put_super - drop a temporary reference to superblock * @sb: superblock in question * * Drops a temporary reference, frees superblock if there's no * references left. */ void put_super(struct super_block *sb) { spin_lock(&sb_lock); __put_super(sb); spin_unlock(&sb_lock); } static void kill_super_notify(struct super_block *sb) { lockdep_assert_not_held(&sb->s_umount); /* already notified earlier */ if (sb->s_flags & SB_DEAD) return; /* * Remove it from @fs_supers so it isn't found by new * sget{_fc}() walkers anymore. Any concurrent mounter still * managing to grab a temporary reference is guaranteed to * already see SB_DYING and will wait until we notify them about * SB_DEAD. */ spin_lock(&sb_lock); hlist_del_init(&sb->s_instances); spin_unlock(&sb_lock); /* * Let concurrent mounts know that this thing is really dead. * We don't need @sb->s_umount here as every concurrent caller * will see SB_DYING and either discard the superblock or wait * for SB_DEAD. */ super_wake(sb, SB_DEAD); } /** * deactivate_locked_super - drop an active reference to superblock * @s: superblock to deactivate * * Drops an active reference to superblock, converting it into a temporary * one if there is no other active references left. In that case we * tell fs driver to shut it down and drop the temporary reference we * had just acquired. * * Caller holds exclusive lock on superblock; that lock is released. */ void deactivate_locked_super(struct super_block *s) { struct file_system_type *fs = s->s_type; if (atomic_dec_and_test(&s->s_active)) { shrinker_free(s->s_shrink); fs->kill_sb(s); kill_super_notify(s); /* * Since list_lru_destroy() may sleep, we cannot call it from * put_super(), where we hold the sb_lock. Therefore we destroy * the lru lists right now. */ list_lru_destroy(&s->s_dentry_lru); list_lru_destroy(&s->s_inode_lru); put_filesystem(fs); put_super(s); } else { super_unlock_excl(s); } } EXPORT_SYMBOL(deactivate_locked_super); /** * deactivate_super - drop an active reference to superblock * @s: superblock to deactivate * * Variant of deactivate_locked_super(), except that superblock is *not* * locked by caller. If we are going to drop the final active reference, * lock will be acquired prior to that. */ void deactivate_super(struct super_block *s) { if (!atomic_add_unless(&s->s_active, -1, 1)) { __super_lock_excl(s); deactivate_locked_super(s); } } EXPORT_SYMBOL(deactivate_super); /** * grab_super - acquire an active reference to a superblock * @sb: superblock to acquire * * Acquire a temporary reference on a superblock and try to trade it for * an active reference. This is used in sget{_fc}() to wait for a * superblock to either become SB_BORN or for it to pass through * sb->kill() and be marked as SB_DEAD. * * Return: This returns true if an active reference could be acquired, * false if not. */ static bool grab_super(struct super_block *sb) { bool locked; sb->s_count++; spin_unlock(&sb_lock); locked = super_lock_excl(sb); if (locked) { if (atomic_inc_not_zero(&sb->s_active)) { put_super(sb); return true; } super_unlock_excl(sb); } wait_var_event(&sb->s_flags, super_flags(sb, SB_DEAD)); put_super(sb); return false; } /* * super_trylock_shared - try to grab ->s_umount shared * @sb: reference we are trying to grab * * Try to prevent fs shutdown. This is used in places where we * cannot take an active reference but we need to ensure that the * filesystem is not shut down while we are working on it. It returns * false if we cannot acquire s_umount or if we lose the race and * filesystem already got into shutdown, and returns true with the s_umount * lock held in read mode in case of success. On successful return, * the caller must drop the s_umount lock when done. * * Note that unlike get_super() et.al. this one does *not* bump ->s_count. * The reason why it's safe is that we are OK with doing trylock instead * of down_read(). There's a couple of places that are OK with that, but * it's very much not a general-purpose interface. */ bool super_trylock_shared(struct super_block *sb) { if (down_read_trylock(&sb->s_umount)) { if (!(sb->s_flags & SB_DYING) && sb->s_root && (sb->s_flags & SB_BORN)) return true; super_unlock_shared(sb); } return false; } /** * retire_super - prevents superblock from being reused * @sb: superblock to retire * * The function marks superblock to be ignored in superblock test, which * prevents it from being reused for any new mounts. If the superblock has * a private bdi, it also unregisters it, but doesn't reduce the refcount * of the superblock to prevent potential races. The refcount is reduced * by generic_shutdown_super(). The function can not be called * concurrently with generic_shutdown_super(). It is safe to call the * function multiple times, subsequent calls have no effect. * * The marker will affect the re-use only for block-device-based * superblocks. Other superblocks will still get marked if this function * is used, but that will not affect their reusability. */ void retire_super(struct super_block *sb) { WARN_ON(!sb->s_bdev); __super_lock_excl(sb); if (sb->s_iflags & SB_I_PERSB_BDI) { bdi_unregister(sb->s_bdi); sb->s_iflags &= ~SB_I_PERSB_BDI; } sb->s_iflags |= SB_I_RETIRED; super_unlock_excl(sb); } EXPORT_SYMBOL(retire_super); /** * generic_shutdown_super - common helper for ->kill_sb() * @sb: superblock to kill * * generic_shutdown_super() does all fs-independent work on superblock * shutdown. Typical ->kill_sb() should pick all fs-specific objects * that need destruction out of superblock, call generic_shutdown_super() * and release aforementioned objects. Note: dentries and inodes _are_ * taken care of and do not need specific handling. * * Upon calling this function, the filesystem may no longer alter or * rearrange the set of dentries belonging to this super_block, nor may it * change the attachments of dentries to inodes. */ void generic_shutdown_super(struct super_block *sb) { const struct super_operations *sop = sb->s_op; if (sb->s_root) { shrink_dcache_for_umount(sb); sync_filesystem(sb); sb->s_flags &= ~SB_ACTIVE; cgroup_writeback_umount(); /* Evict all inodes with zero refcount. */ evict_inodes(sb); /* * Clean up and evict any inodes that still have references due * to fsnotify or the security policy. */ fsnotify_sb_delete(sb); security_sb_delete(sb); if (sb->s_dio_done_wq) { destroy_workqueue(sb->s_dio_done_wq); sb->s_dio_done_wq = NULL; } if (sop->put_super) sop->put_super(sb); /* * Now that all potentially-encrypted inodes have been evicted, * the fscrypt keyring can be destroyed. */ fscrypt_destroy_keyring(sb); if (CHECK_DATA_CORRUPTION(!list_empty(&sb->s_inodes), "VFS: Busy inodes after unmount of %s (%s)", sb->s_id, sb->s_type->name)) { /* * Adding a proper bailout path here would be hard, but * we can at least make it more likely that a later * iput_final() or such crashes cleanly. */ struct inode *inode; spin_lock(&sb->s_inode_list_lock); list_for_each_entry(inode, &sb->s_inodes, i_sb_list) { inode->i_op = VFS_PTR_POISON; inode->i_sb = VFS_PTR_POISON; inode->i_mapping = VFS_PTR_POISON; } spin_unlock(&sb->s_inode_list_lock); } } /* * Broadcast to everyone that grabbed a temporary reference to this * superblock before we removed it from @fs_supers that the superblock * is dying. Every walker of @fs_supers outside of sget{_fc}() will now * discard this superblock and treat it as dead. * * We leave the superblock on @fs_supers so it can be found by * sget{_fc}() until we passed sb->kill_sb(). */ super_wake(sb, SB_DYING); super_unlock_excl(sb); if (sb->s_bdi != &noop_backing_dev_info) { if (sb->s_iflags & SB_I_PERSB_BDI) bdi_unregister(sb->s_bdi); bdi_put(sb->s_bdi); sb->s_bdi = &noop_backing_dev_info; } } EXPORT_SYMBOL(generic_shutdown_super); bool mount_capable(struct fs_context *fc) { if (!(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) return capable(CAP_SYS_ADMIN); else return ns_capable(fc->user_ns, CAP_SYS_ADMIN); } /** * sget_fc - Find or create a superblock * @fc: Filesystem context. * @test: Comparison callback * @set: Setup callback * * Create a new superblock or find an existing one. * * The @test callback is used to find a matching existing superblock. * Whether or not the requested parameters in @fc are taken into account * is specific to the @test callback that is used. They may even be * completely ignored. * * If an extant superblock is matched, it will be returned unless: * * (1) the namespace the filesystem context @fc and the extant * superblock's namespace differ * * (2) the filesystem context @fc has requested that reusing an extant * superblock is not allowed * * In both cases EBUSY will be returned. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info and s_id will be * set and the @set callback will be invoked), the superblock will be * published and it will be returned in a partially constructed state * with SB_BORN and SB_ACTIVE as yet unset. * * Return: On success, an extant or newly created superblock is * returned. On failure an error pointer is returned. */ struct super_block *sget_fc(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*set)(struct super_block *, struct fs_context *)) { struct super_block *s = NULL; struct super_block *old; struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns; int err; retry: spin_lock(&sb_lock); if (test) { hlist_for_each_entry(old, &fc->fs_type->fs_supers, s_instances) { if (test(old, fc)) goto share_extant_sb; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(fc->fs_type, fc->sb_flags, user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } s->s_fs_info = fc->s_fs_info; err = set(s, fc); if (err) { s->s_fs_info = NULL; spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(err); } fc->s_fs_info = NULL; s->s_type = fc->fs_type; s->s_iflags |= fc->s_iflags; strscpy(s->s_id, s->s_type->name, sizeof(s->s_id)); /* * Make the superblock visible on @super_blocks and @fs_supers. * It's in a nascent state and users should wait on SB_BORN or * SB_DYING to be set. */ list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &s->s_type->fs_supers); spin_unlock(&sb_lock); get_filesystem(s->s_type); shrinker_register(s->s_shrink); return s; share_extant_sb: if (user_ns != old->s_user_ns || fc->exclusive) { spin_unlock(&sb_lock); destroy_unused_super(s); if (fc->exclusive) warnfc(fc, "reusing existing filesystem not allowed"); else warnfc(fc, "reusing existing filesystem in another namespace not allowed"); return ERR_PTR(-EBUSY); } if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; } EXPORT_SYMBOL(sget_fc); /** * sget - find or create a superblock * @type: filesystem type superblock should belong to * @test: comparison callback * @set: setup callback * @flags: mount flags * @data: argument to each of them */ struct super_block *sget(struct file_system_type *type, int (*test)(struct super_block *,void *), int (*set)(struct super_block *,void *), int flags, void *data) { struct user_namespace *user_ns = current_user_ns(); struct super_block *s = NULL; struct super_block *old; int err; /* We don't yet pass the user namespace of the parent * mount through to here so always use &init_user_ns * until that changes. */ if (flags & SB_SUBMOUNT) user_ns = &init_user_ns; retry: spin_lock(&sb_lock); if (test) { hlist_for_each_entry(old, &type->fs_supers, s_instances) { if (!test(old, data)) continue; if (user_ns != old->s_user_ns) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(-EBUSY); } if (!grab_super(old)) goto retry; destroy_unused_super(s); return old; } } if (!s) { spin_unlock(&sb_lock); s = alloc_super(type, (flags & ~SB_SUBMOUNT), user_ns); if (!s) return ERR_PTR(-ENOMEM); goto retry; } err = set(s, data); if (err) { spin_unlock(&sb_lock); destroy_unused_super(s); return ERR_PTR(err); } s->s_type = type; strscpy(s->s_id, type->name, sizeof(s->s_id)); list_add_tail(&s->s_list, &super_blocks); hlist_add_head(&s->s_instances, &type->fs_supers); spin_unlock(&sb_lock); get_filesystem(type); shrinker_register(s->s_shrink); return s; } EXPORT_SYMBOL(sget); void drop_super(struct super_block *sb) { super_unlock_shared(sb); put_super(sb); } EXPORT_SYMBOL(drop_super); void drop_super_exclusive(struct super_block *sb) { super_unlock_excl(sb); put_super(sb); } EXPORT_SYMBOL(drop_super_exclusive); static void __iterate_supers(void (*f)(struct super_block *)) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (super_flags(sb, SB_DYING)) continue; sb->s_count++; spin_unlock(&sb_lock); f(sb); spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } /** * iterate_supers - call function for all active superblocks * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers(void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { bool locked; sb->s_count++; spin_unlock(&sb_lock); locked = super_lock_shared(sb); if (locked) { if (sb->s_root) f(sb, arg); super_unlock_shared(sb); } spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } /** * iterate_supers_type - call function for superblocks of given type * @type: fs type * @f: function to call * @arg: argument to pass to it * * Scans the superblock list and calls given function, passing it * locked superblock and given argument. */ void iterate_supers_type(struct file_system_type *type, void (*f)(struct super_block *, void *), void *arg) { struct super_block *sb, *p = NULL; spin_lock(&sb_lock); hlist_for_each_entry(sb, &type->fs_supers, s_instances) { bool locked; sb->s_count++; spin_unlock(&sb_lock); locked = super_lock_shared(sb); if (locked) { if (sb->s_root) f(sb, arg); super_unlock_shared(sb); } spin_lock(&sb_lock); if (p) __put_super(p); p = sb; } if (p) __put_super(p); spin_unlock(&sb_lock); } EXPORT_SYMBOL(iterate_supers_type); struct super_block *user_get_super(dev_t dev, bool excl) { struct super_block *sb; spin_lock(&sb_lock); list_for_each_entry(sb, &super_blocks, s_list) { if (sb->s_dev == dev) { bool locked; sb->s_count++; spin_unlock(&sb_lock); /* still alive? */ locked = super_lock(sb, excl); if (locked) { if (sb->s_root) return sb; super_unlock(sb, excl); } /* nope, got unmounted */ spin_lock(&sb_lock); __put_super(sb); break; } } spin_unlock(&sb_lock); return NULL; } /** * reconfigure_super - asks filesystem to change superblock parameters * @fc: The superblock and configuration * * Alters the configuration parameters of a live superblock. */ int reconfigure_super(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; int retval; bool remount_ro = false; bool remount_rw = false; bool force = fc->sb_flags & SB_FORCE; if (fc->sb_flags_mask & ~MS_RMT_MASK) return -EINVAL; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; retval = security_sb_remount(sb, fc->security); if (retval) return retval; if (fc->sb_flags_mask & SB_RDONLY) { #ifdef CONFIG_BLOCK if (!(fc->sb_flags & SB_RDONLY) && sb->s_bdev && bdev_read_only(sb->s_bdev)) return -EACCES; #endif remount_rw = !(fc->sb_flags & SB_RDONLY) && sb_rdonly(sb); remount_ro = (fc->sb_flags & SB_RDONLY) && !sb_rdonly(sb); } if (remount_ro) { if (!hlist_empty(&sb->s_pins)) { super_unlock_excl(sb); group_pin_kill(&sb->s_pins); __super_lock_excl(sb); if (!sb->s_root) return 0; if (sb->s_writers.frozen != SB_UNFROZEN) return -EBUSY; remount_ro = !sb_rdonly(sb); } } shrink_dcache_sb(sb); /* If we are reconfiguring to RDONLY and current sb is read/write, * make sure there are no files open for writing. */ if (remount_ro) { if (force) { sb_start_ro_state_change(sb); } else { retval = sb_prepare_remount_readonly(sb); if (retval) return retval; } } else if (remount_rw) { /* * Protect filesystem's reconfigure code from writes from * userspace until reconfigure finishes. */ sb_start_ro_state_change(sb); } if (fc->ops->reconfigure) { retval = fc->ops->reconfigure(fc); if (retval) { if (!force) goto cancel_readonly; /* If forced remount, go ahead despite any errors */ WARN(1, "forced remount of a %s fs returned %i\n", sb->s_type->name, retval); } } WRITE_ONCE(sb->s_flags, ((sb->s_flags & ~fc->sb_flags_mask) | (fc->sb_flags & fc->sb_flags_mask))); sb_end_ro_state_change(sb); /* * Some filesystems modify their metadata via some other path than the * bdev buffer cache (eg. use a private mapping, or directories in * pagecache, etc). Also file data modifications go via their own * mappings. So If we try to mount readonly then copy the filesystem * from bdev, we could get stale data, so invalidate it to give a best * effort at coherency. */ if (remount_ro && sb->s_bdev) invalidate_bdev(sb->s_bdev); return 0; cancel_readonly: sb_end_ro_state_change(sb); return retval; } static void do_emergency_remount_callback(struct super_block *sb) { bool locked = super_lock_excl(sb); if (locked && sb->s_root && sb->s_bdev && !sb_rdonly(sb)) { struct fs_context *fc; fc = fs_context_for_reconfigure(sb->s_root, SB_RDONLY | SB_FORCE, SB_RDONLY); if (!IS_ERR(fc)) { if (parse_monolithic_mount_data(fc, NULL) == 0) (void)reconfigure_super(fc); put_fs_context(fc); } } if (locked) super_unlock_excl(sb); } static void do_emergency_remount(struct work_struct *work) { __iterate_supers(do_emergency_remount_callback); kfree(work); printk("Emergency Remount complete\n"); } void emergency_remount(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_emergency_remount); schedule_work(work); } } static void do_thaw_all_callback(struct super_block *sb) { bool locked = super_lock_excl(sb); if (locked && sb->s_root) { if (IS_ENABLED(CONFIG_BLOCK)) while (sb->s_bdev && !bdev_thaw(sb->s_bdev)) pr_warn("Emergency Thaw on %pg\n", sb->s_bdev); thaw_super_locked(sb, FREEZE_HOLDER_USERSPACE); return; } if (locked) super_unlock_excl(sb); } static void do_thaw_all(struct work_struct *work) { __iterate_supers(do_thaw_all_callback); kfree(work); printk(KERN_WARNING "Emergency Thaw complete\n"); } /** * emergency_thaw_all -- forcibly thaw every frozen filesystem * * Used for emergency unfreeze of all filesystems via SysRq */ void emergency_thaw_all(void) { struct work_struct *work; work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) { INIT_WORK(work, do_thaw_all); schedule_work(work); } } static DEFINE_IDA(unnamed_dev_ida); /** * get_anon_bdev - Allocate a block device for filesystems which don't have one. * @p: Pointer to a dev_t. * * Filesystems which don't use real block devices can call this function * to allocate a virtual block device. * * Context: Any context. Frequently called while holding sb_lock. * Return: 0 on success, -EMFILE if there are no anonymous bdevs left * or -ENOMEM if memory allocation failed. */ int get_anon_bdev(dev_t *p) { int dev; /* * Many userspace utilities consider an FSID of 0 invalid. * Always return at least 1 from get_anon_bdev. */ dev = ida_alloc_range(&unnamed_dev_ida, 1, (1 << MINORBITS) - 1, GFP_ATOMIC); if (dev == -ENOSPC) dev = -EMFILE; if (dev < 0) return dev; *p = MKDEV(0, dev); return 0; } EXPORT_SYMBOL(get_anon_bdev); void free_anon_bdev(dev_t dev) { ida_free(&unnamed_dev_ida, MINOR(dev)); } EXPORT_SYMBOL(free_anon_bdev); int set_anon_super(struct super_block *s, void *data) { return get_anon_bdev(&s->s_dev); } EXPORT_SYMBOL(set_anon_super); void kill_anon_super(struct super_block *sb) { dev_t dev = sb->s_dev; generic_shutdown_super(sb); kill_super_notify(sb); free_anon_bdev(dev); } EXPORT_SYMBOL(kill_anon_super); void kill_litter_super(struct super_block *sb) { if (sb->s_root) d_genocide(sb->s_root); kill_anon_super(sb); } EXPORT_SYMBOL(kill_litter_super); int set_anon_super_fc(struct super_block *sb, struct fs_context *fc) { return set_anon_super(sb, NULL); } EXPORT_SYMBOL(set_anon_super_fc); static int test_keyed_super(struct super_block *sb, struct fs_context *fc) { return sb->s_fs_info == fc->s_fs_info; } static int test_single_super(struct super_block *s, struct fs_context *fc) { return 1; } static int vfs_get_super(struct fs_context *fc, int (*test)(struct super_block *, struct fs_context *), int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { struct super_block *sb; int err; sb = sget_fc(fc, test, set_anon_super_fc); if (IS_ERR(sb)) return PTR_ERR(sb); if (!sb->s_root) { err = fill_super(sb, fc); if (err) goto error; sb->s_flags |= SB_ACTIVE; } fc->root = dget(sb->s_root); return 0; error: deactivate_locked_super(sb); return err; } int get_tree_nodev(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, NULL, fill_super); } EXPORT_SYMBOL(get_tree_nodev); int get_tree_single(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc)) { return vfs_get_super(fc, test_single_super, fill_super); } EXPORT_SYMBOL(get_tree_single); int get_tree_keyed(struct fs_context *fc, int (*fill_super)(struct super_block *sb, struct fs_context *fc), void *key) { fc->s_fs_info = key; return vfs_get_super(fc, test_keyed_super, fill_super); } EXPORT_SYMBOL(get_tree_keyed); static int set_bdev_super(struct super_block *s, void *data) { s->s_dev = *(dev_t *)data; return 0; } static int super_s_dev_set(struct super_block *s, struct fs_context *fc) { return set_bdev_super(s, fc->sget_key); } static int super_s_dev_test(struct super_block *s, struct fs_context *fc) { return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)fc->sget_key; } /** * sget_dev - Find or create a superblock by device number * @fc: Filesystem context. * @dev: device number * * Find or create a superblock using the provided device number that * will be stored in fc->sget_key. * * If an extant superblock is matched, then that will be returned with * an elevated reference count that the caller must transfer or discard. * * If no match is made, a new superblock will be allocated and basic * initialisation will be performed (s_type, s_fs_info, s_id, s_dev will * be set). The superblock will be published and it will be returned in * a partially constructed state with SB_BORN and SB_ACTIVE as yet * unset. * * Return: an existing or newly created superblock on success, an error * pointer on failure. */ struct super_block *sget_dev(struct fs_context *fc, dev_t dev) { fc->sget_key = &dev; return sget_fc(fc, super_s_dev_test, super_s_dev_set); } EXPORT_SYMBOL(sget_dev); #ifdef CONFIG_BLOCK /* * Lock the superblock that is holder of the bdev. Returns the superblock * pointer if we successfully locked the superblock and it is alive. Otherwise * we return NULL and just unlock bdev->bd_holder_lock. * * The function must be called with bdev->bd_holder_lock and releases it. */ static struct super_block *bdev_super_lock(struct block_device *bdev, bool excl) __releases(&bdev->bd_holder_lock) { struct super_block *sb = bdev->bd_holder; bool locked; lockdep_assert_held(&bdev->bd_holder_lock); lockdep_assert_not_held(&sb->s_umount); lockdep_assert_not_held(&bdev->bd_disk->open_mutex); /* Make sure sb doesn't go away from under us */ spin_lock(&sb_lock); sb->s_count++; spin_unlock(&sb_lock); mutex_unlock(&bdev->bd_holder_lock); locked = super_lock(sb, excl); /* * If the superblock wasn't already SB_DYING then we hold * s_umount and can safely drop our temporary reference. */ put_super(sb); if (!locked) return NULL; if (!sb->s_root || !(sb->s_flags & SB_ACTIVE)) { super_unlock(sb, excl); return NULL; } return sb; } static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise) { struct super_block *sb; sb = bdev_super_lock(bdev, false); if (!sb) return; if (!surprise) sync_filesystem(sb); shrink_dcache_sb(sb); invalidate_inodes(sb); if (sb->s_op->shutdown) sb->s_op->shutdown(sb); super_unlock_shared(sb); } static void fs_bdev_sync(struct block_device *bdev) { struct super_block *sb; sb = bdev_super_lock(bdev, false); if (!sb) return; sync_filesystem(sb); super_unlock_shared(sb); } static struct super_block *get_bdev_super(struct block_device *bdev) { bool active = false; struct super_block *sb; sb = bdev_super_lock(bdev, true); if (sb) { active = atomic_inc_not_zero(&sb->s_active); super_unlock_excl(sb); } if (!active) return NULL; return sb; } /** * fs_bdev_freeze - freeze owning filesystem of block device * @bdev: block device * * Freeze the filesystem that owns this block device if it is still * active. * * A filesystem that owns multiple block devices may be frozen from each * block device and won't be unfrozen until all block devices are * unfrozen. Each block device can only freeze the filesystem once as we * nest freezes for block devices in the block layer. * * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ static int fs_bdev_freeze(struct block_device *bdev) { struct super_block *sb; int error = 0; lockdep_assert_held(&bdev->bd_fsfreeze_mutex); sb = get_bdev_super(bdev); if (!sb) return -EINVAL; if (sb->s_op->freeze_super) error = sb->s_op->freeze_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); else error = freeze_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); if (!error) error = sync_blockdev(bdev); deactivate_super(sb); return error; } /** * fs_bdev_thaw - thaw owning filesystem of block device * @bdev: block device * * Thaw the filesystem that owns this block device. * * A filesystem that owns multiple block devices may be frozen from each * block device and won't be unfrozen until all block devices are * unfrozen. Each block device can only freeze the filesystem once as we * nest freezes for block devices in the block layer. * * Return: If the thaw was successful zero is returned. If the thaw * failed a negative error code is returned. If this function * returns zero it doesn't mean that the filesystem is unfrozen * as it may have been frozen multiple times (kernel may hold a * freeze or might be frozen from other block devices). */ static int fs_bdev_thaw(struct block_device *bdev) { struct super_block *sb; int error; lockdep_assert_held(&bdev->bd_fsfreeze_mutex); sb = get_bdev_super(bdev); if (WARN_ON_ONCE(!sb)) return -EINVAL; if (sb->s_op->thaw_super) error = sb->s_op->thaw_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); else error = thaw_super(sb, FREEZE_MAY_NEST | FREEZE_HOLDER_USERSPACE); deactivate_super(sb); return error; } const struct blk_holder_ops fs_holder_ops = { .mark_dead = fs_bdev_mark_dead, .sync = fs_bdev_sync, .freeze = fs_bdev_freeze, .thaw = fs_bdev_thaw, }; EXPORT_SYMBOL_GPL(fs_holder_ops); int setup_bdev_super(struct super_block *sb, int sb_flags, struct fs_context *fc) { blk_mode_t mode = sb_open_mode(sb_flags); struct file *bdev_file; struct block_device *bdev; bdev_file = bdev_file_open_by_dev(sb->s_dev, mode, sb, &fs_holder_ops); if (IS_ERR(bdev_file)) { if (fc) errorf(fc, "%s: Can't open blockdev", fc->source); return PTR_ERR(bdev_file); } bdev = file_bdev(bdev_file); /* * This really should be in blkdev_get_by_dev, but right now can't due * to legacy issues that require us to allow opening a block device node * writable from userspace even for a read-only block device. */ if ((mode & BLK_OPEN_WRITE) && bdev_read_only(bdev)) { bdev_fput(bdev_file); return -EACCES; } /* * It is enough to check bdev was not frozen before we set * s_bdev as freezing will wait until SB_BORN is set. */ if (atomic_read(&bdev->bd_fsfreeze_count) > 0) { if (fc) warnf(fc, "%pg: Can't mount, blockdev is frozen", bdev); bdev_fput(bdev_file); return -EBUSY; } spin_lock(&sb_lock); sb->s_bdev_file = bdev_file; sb->s_bdev = bdev; sb->s_bdi = bdi_get(bdev->bd_disk->bdi); if (bdev_stable_writes(bdev)) sb->s_iflags |= SB_I_STABLE_WRITES; spin_unlock(&sb_lock); snprintf(sb->s_id, sizeof(sb->s_id), "%pg", bdev); shrinker_debugfs_rename(sb->s_shrink, "sb-%s:%s", sb->s_type->name, sb->s_id); sb_set_blocksize(sb, block_size(bdev)); return 0; } EXPORT_SYMBOL_GPL(setup_bdev_super); /** * get_tree_bdev - Get a superblock based on a single block device * @fc: The filesystem context holding the parameters * @fill_super: Helper to initialise a new superblock */ int get_tree_bdev(struct fs_context *fc, int (*fill_super)(struct super_block *, struct fs_context *)) { struct super_block *s; int error = 0; dev_t dev; if (!fc->source) return invalf(fc, "No source specified"); error = lookup_bdev(fc->source, &dev); if (error) { errorf(fc, "%s: Can't lookup blockdev", fc->source); return error; } fc->sb_flags |= SB_NOSEC; s = sget_dev(fc, dev); if (IS_ERR(s)) return PTR_ERR(s); if (s->s_root) { /* Don't summarily change the RO/RW state. */ if ((fc->sb_flags ^ s->s_flags) & SB_RDONLY) { warnf(fc, "%pg: Can't mount, would change RO state", s->s_bdev); deactivate_locked_super(s); return -EBUSY; } } else { error = setup_bdev_super(s, fc->sb_flags, fc); if (!error) error = fill_super(s, fc); if (error) { deactivate_locked_super(s); return error; } s->s_flags |= SB_ACTIVE; } BUG_ON(fc->root); fc->root = dget(s->s_root); return 0; } EXPORT_SYMBOL(get_tree_bdev); static int test_bdev_super(struct super_block *s, void *data) { return !(s->s_iflags & SB_I_RETIRED) && s->s_dev == *(dev_t *)data; } struct dentry *mount_bdev(struct file_system_type *fs_type, int flags, const char *dev_name, void *data, int (*fill_super)(struct super_block *, void *, int)) { struct super_block *s; int error; dev_t dev; error = lookup_bdev(dev_name, &dev); if (error) return ERR_PTR(error); flags |= SB_NOSEC; s = sget(fs_type, test_bdev_super, set_bdev_super, flags, &dev); if (IS_ERR(s)) return ERR_CAST(s); if (s->s_root) { if ((flags ^ s->s_flags) & SB_RDONLY) { deactivate_locked_super(s); return ERR_PTR(-EBUSY); } } else { error = setup_bdev_super(s, flags, NULL); if (!error) error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); return ERR_PTR(error); } s->s_flags |= SB_ACTIVE; } return dget(s->s_root); } EXPORT_SYMBOL(mount_bdev); void kill_block_super(struct super_block *sb) { struct block_device *bdev = sb->s_bdev; generic_shutdown_super(sb); if (bdev) { sync_blockdev(bdev); bdev_fput(sb->s_bdev_file); } } EXPORT_SYMBOL(kill_block_super); #endif struct dentry *mount_nodev(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)) { int error; struct super_block *s = sget(fs_type, NULL, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (error) { deactivate_locked_super(s); return ERR_PTR(error); } s->s_flags |= SB_ACTIVE; return dget(s->s_root); } EXPORT_SYMBOL(mount_nodev); int reconfigure_single(struct super_block *s, int flags, void *data) { struct fs_context *fc; int ret; /* The caller really need to be passing fc down into mount_single(), * then a chunk of this can be removed. [Bollocks -- AV] * Better yet, reconfiguration shouldn't happen, but rather the second * mount should be rejected if the parameters are not compatible. */ fc = fs_context_for_reconfigure(s->s_root, flags, MS_RMT_MASK); if (IS_ERR(fc)) return PTR_ERR(fc); ret = parse_monolithic_mount_data(fc, data); if (ret < 0) goto out; ret = reconfigure_super(fc); out: put_fs_context(fc); return ret; } static int compare_single(struct super_block *s, void *p) { return 1; } struct dentry *mount_single(struct file_system_type *fs_type, int flags, void *data, int (*fill_super)(struct super_block *, void *, int)) { struct super_block *s; int error; s = sget(fs_type, compare_single, set_anon_super, flags, NULL); if (IS_ERR(s)) return ERR_CAST(s); if (!s->s_root) { error = fill_super(s, data, flags & SB_SILENT ? 1 : 0); if (!error) s->s_flags |= SB_ACTIVE; } else { error = reconfigure_single(s, flags, data); } if (unlikely(error)) { deactivate_locked_super(s); return ERR_PTR(error); } return dget(s->s_root); } EXPORT_SYMBOL(mount_single); /** * vfs_get_tree - Get the mountable root * @fc: The superblock configuration context. * * The filesystem is invoked to get or create a superblock which can then later * be used for mounting. The filesystem places a pointer to the root to be * used for mounting in @fc->root. */ int vfs_get_tree(struct fs_context *fc) { struct super_block *sb; int error; if (fc->root) return -EBUSY; /* Get the mountable root in fc->root, with a ref on the root and a ref * on the superblock. */ error = fc->ops->get_tree(fc); if (error < 0) return error; if (!fc->root) { pr_err("Filesystem %s get_tree() didn't set fc->root\n", fc->fs_type->name); /* We don't know what the locking state of the superblock is - * if there is a superblock. */ BUG(); } sb = fc->root->d_sb; WARN_ON(!sb->s_bdi); /* * super_wake() contains a memory barrier which also care of * ordering for super_cache_count(). We place it before setting * SB_BORN as the data dependency between the two functions is * the superblock structure contents that we just set up, not * the SB_BORN flag. */ super_wake(sb, SB_BORN); error = security_sb_set_mnt_opts(sb, fc->security, 0, NULL); if (unlikely(error)) { fc_drop_locked(fc); return error; } /* * filesystems should never set s_maxbytes larger than MAX_LFS_FILESIZE * but s_maxbytes was an unsigned long long for many releases. Throw * this warning for a little while to try and catch filesystems that * violate this rule. */ WARN((sb->s_maxbytes < 0), "%s set sb->s_maxbytes to " "negative value (%lld)\n", fc->fs_type->name, sb->s_maxbytes); return 0; } EXPORT_SYMBOL(vfs_get_tree); /* * Setup private BDI for given superblock. It gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi_name(struct super_block *sb, char *fmt, ...) { struct backing_dev_info *bdi; int err; va_list args; bdi = bdi_alloc(NUMA_NO_NODE); if (!bdi) return -ENOMEM; va_start(args, fmt); err = bdi_register_va(bdi, fmt, args); va_end(args); if (err) { bdi_put(bdi); return err; } WARN_ON(sb->s_bdi != &noop_backing_dev_info); sb->s_bdi = bdi; sb->s_iflags |= SB_I_PERSB_BDI; return 0; } EXPORT_SYMBOL(super_setup_bdi_name); /* * Setup private BDI for given superblock. I gets automatically cleaned up * in generic_shutdown_super(). */ int super_setup_bdi(struct super_block *sb) { static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name, atomic_long_inc_return(&bdi_seq)); } EXPORT_SYMBOL(super_setup_bdi); /** * sb_wait_write - wait until all writers to given file system finish * @sb: the super for which we wait * @level: type of writers we wait for (normal vs page fault) * * This function waits until there are no writers of given type to given file * system. */ static void sb_wait_write(struct super_block *sb, int level) { percpu_down_write(sb->s_writers.rw_sem + level-1); } /* * We are going to return to userspace and forget about these locks, the * ownership goes to the caller of thaw_super() which does unlock(). */ static void lockdep_sb_freeze_release(struct super_block *sb) { int level; for (level = SB_FREEZE_LEVELS - 1; level >= 0; level--) percpu_rwsem_release(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } /* * Tell lockdep we are holding these locks before we call ->unfreeze_fs(sb). */ static void lockdep_sb_freeze_acquire(struct super_block *sb) { int level; for (level = 0; level < SB_FREEZE_LEVELS; ++level) percpu_rwsem_acquire(sb->s_writers.rw_sem + level, 0, _THIS_IP_); } static void sb_freeze_unlock(struct super_block *sb, int level) { for (level--; level >= 0; level--) percpu_up_write(sb->s_writers.rw_sem + level); } static int wait_for_partially_frozen(struct super_block *sb) { int ret = 0; do { unsigned short old = sb->s_writers.frozen; up_write(&sb->s_umount); ret = wait_var_event_killable(&sb->s_writers.frozen, sb->s_writers.frozen != old); down_write(&sb->s_umount); } while (ret == 0 && sb->s_writers.frozen != SB_UNFROZEN && sb->s_writers.frozen != SB_FREEZE_COMPLETE); return ret; } #define FREEZE_HOLDERS (FREEZE_HOLDER_KERNEL | FREEZE_HOLDER_USERSPACE) #define FREEZE_FLAGS (FREEZE_HOLDERS | FREEZE_MAY_NEST) static inline int freeze_inc(struct super_block *sb, enum freeze_holder who) { WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if (who & FREEZE_HOLDER_KERNEL) ++sb->s_writers.freeze_kcount; if (who & FREEZE_HOLDER_USERSPACE) ++sb->s_writers.freeze_ucount; return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; } static inline int freeze_dec(struct super_block *sb, enum freeze_holder who) { WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if ((who & FREEZE_HOLDER_KERNEL) && sb->s_writers.freeze_kcount) --sb->s_writers.freeze_kcount; if ((who & FREEZE_HOLDER_USERSPACE) && sb->s_writers.freeze_ucount) --sb->s_writers.freeze_ucount; return sb->s_writers.freeze_kcount + sb->s_writers.freeze_ucount; } static inline bool may_freeze(struct super_block *sb, enum freeze_holder who) { WARN_ON_ONCE((who & ~FREEZE_FLAGS)); WARN_ON_ONCE(hweight32(who & FREEZE_HOLDERS) > 1); if (who & FREEZE_HOLDER_KERNEL) return (who & FREEZE_MAY_NEST) || sb->s_writers.freeze_kcount == 0; if (who & FREEZE_HOLDER_USERSPACE) return (who & FREEZE_MAY_NEST) || sb->s_writers.freeze_ucount == 0; return false; } /** * freeze_super - lock the filesystem and force it into a consistent state * @sb: the super to lock * @who: context that wants to freeze * * Syncs the super to make sure the filesystem is consistent and calls the fs's * freeze_fs. Subsequent calls to this without first thawing the fs may return * -EBUSY. * * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to freeze the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to freeze the fs. * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed. * * The @who argument distinguishes between the kernel and userspace trying to * freeze the filesystem. Although there cannot be multiple kernel freezes or * multiple userspace freezes in effect at any given time, the kernel and * userspace can both hold a filesystem frozen. The filesystem remains frozen * until there are no kernel or userspace freezes in effect. * * A filesystem may hold multiple devices and thus a filesystems may be * frozen through the block layer via multiple block devices. In this * case the request is marked as being allowed to nest by passing * FREEZE_MAY_NEST. The filesystem remains frozen until all block * devices are unfrozen. If multiple freezes are attempted without * FREEZE_MAY_NEST -EBUSY will be returned. * * During this function, sb->s_writers.frozen goes through these values: * * SB_UNFROZEN: File system is normal, all writes progress as usual. * * SB_FREEZE_WRITE: The file system is in the process of being frozen. New * writes should be blocked, though page faults are still allowed. We wait for * all writes to complete and then proceed to the next stage. * * SB_FREEZE_PAGEFAULT: Freezing continues. Now also page faults are blocked * but internal fs threads can still modify the filesystem (although they * should not dirty new pages or inodes), writeback can run etc. After waiting * for all running page faults we sync the filesystem which will clean all * dirty pages and inodes (no new dirty pages or inodes can be created when * sync is running). * * SB_FREEZE_FS: The file system is frozen. Now all internal sources of fs * modification are blocked (e.g. XFS preallocation truncation on inode * reclaim). This is usually implemented by blocking new transactions for * filesystems that have them and need this additional guard. After all * internal writers are finished we call ->freeze_fs() to finish filesystem * freezing. Then we transition to SB_FREEZE_COMPLETE state. This state is * mostly auxiliary for filesystems to verify they do not modify frozen fs. * * sb->s_writers.frozen is protected by sb->s_umount. * * Return: If the freeze was successful zero is returned. If the freeze * failed a negative error code is returned. */ int freeze_super(struct super_block *sb, enum freeze_holder who) { int ret; if (!super_lock_excl(sb)) { WARN_ON_ONCE("Dying superblock while freezing!"); return -EINVAL; } atomic_inc(&sb->s_active); retry: if (sb->s_writers.frozen == SB_FREEZE_COMPLETE) { if (may_freeze(sb, who)) ret = !!WARN_ON_ONCE(freeze_inc(sb, who) == 1); else ret = -EBUSY; /* All freezers share a single active reference. */ deactivate_locked_super(sb); return ret; } if (sb->s_writers.frozen != SB_UNFROZEN) { ret = wait_for_partially_frozen(sb); if (ret) { deactivate_locked_super(sb); return ret; } goto retry; } if (sb_rdonly(sb)) { /* Nothing to do really... */ WARN_ON_ONCE(freeze_inc(sb, who) > 1); sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); super_unlock_excl(sb); return 0; } sb->s_writers.frozen = SB_FREEZE_WRITE; /* Release s_umount to preserve sb_start_write -> s_umount ordering */ super_unlock_excl(sb); sb_wait_write(sb, SB_FREEZE_WRITE); __super_lock_excl(sb); /* Now we go and block page faults... */ sb->s_writers.frozen = SB_FREEZE_PAGEFAULT; sb_wait_write(sb, SB_FREEZE_PAGEFAULT); /* All writers are done so after syncing there won't be dirty data */ ret = sync_filesystem(sb); if (ret) { sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_PAGEFAULT); wake_up_var(&sb->s_writers.frozen); deactivate_locked_super(sb); return ret; } /* Now wait for internal filesystem counter */ sb->s_writers.frozen = SB_FREEZE_FS; sb_wait_write(sb, SB_FREEZE_FS); if (sb->s_op->freeze_fs) { ret = sb->s_op->freeze_fs(sb); if (ret) { printk(KERN_ERR "VFS:Filesystem freeze failed\n"); sb->s_writers.frozen = SB_UNFROZEN; sb_freeze_unlock(sb, SB_FREEZE_FS); wake_up_var(&sb->s_writers.frozen); deactivate_locked_super(sb); return ret; } } /* * For debugging purposes so that fs can warn if it sees write activity * when frozen is set to SB_FREEZE_COMPLETE, and for thaw_super(). */ WARN_ON_ONCE(freeze_inc(sb, who) > 1); sb->s_writers.frozen = SB_FREEZE_COMPLETE; wake_up_var(&sb->s_writers.frozen); lockdep_sb_freeze_release(sb); super_unlock_excl(sb); return 0; } EXPORT_SYMBOL(freeze_super); /* * Undoes the effect of a freeze_super_locked call. If the filesystem is * frozen both by userspace and the kernel, a thaw call from either source * removes that state without releasing the other state or unlocking the * filesystem. */ static int thaw_super_locked(struct super_block *sb, enum freeze_holder who) { int error = -EINVAL; if (sb->s_writers.frozen != SB_FREEZE_COMPLETE) goto out_unlock; /* * All freezers share a single active reference. * So just unlock in case there are any left. */ if (freeze_dec(sb, who)) goto out_unlock; if (sb_rdonly(sb)) { sb->s_writers.frozen = SB_UNFROZEN; wake_up_var(&sb->s_writers.frozen); goto out_deactivate; } lockdep_sb_freeze_acquire(sb); if (sb->s_op->unfreeze_fs) { error = sb->s_op->unfreeze_fs(sb); if (error) { pr_err("VFS: Filesystem thaw failed\n"); freeze_inc(sb, who); lockdep_sb_freeze_release(sb); goto out_unlock; } } sb->s_writers.frozen = SB_UNFROZEN; wake_up_var(&sb->s_writers.frozen); sb_freeze_unlock(sb, SB_FREEZE_FS); out_deactivate: deactivate_locked_super(sb); return 0; out_unlock: super_unlock_excl(sb); return error; } /** * thaw_super -- unlock filesystem * @sb: the super to thaw * @who: context that wants to freeze * * Unlocks the filesystem and marks it writeable again after freeze_super() * if there are no remaining freezes on the filesystem. * * @who should be: * * %FREEZE_HOLDER_USERSPACE if userspace wants to thaw the fs; * * %FREEZE_HOLDER_KERNEL if the kernel wants to thaw the fs. * * %FREEZE_MAY_NEST whether nesting freeze and thaw requests is allowed * * A filesystem may hold multiple devices and thus a filesystems may * have been frozen through the block layer via multiple block devices. * The filesystem remains frozen until all block devices are unfrozen. */ int thaw_super(struct super_block *sb, enum freeze_holder who) { if (!super_lock_excl(sb)) { WARN_ON_ONCE("Dying superblock while thawing!"); return -EINVAL; } return thaw_super_locked(sb, who); } EXPORT_SYMBOL(thaw_super); /* * Create workqueue for deferred direct IO completions. We allocate the * workqueue when it's first needed. This avoids creating workqueue for * filesystems that don't need it and also allows us to create the workqueue * late enough so the we can include s_id in the name of the workqueue. */ int sb_init_dio_done_wq(struct super_block *sb) { struct workqueue_struct *old; struct workqueue_struct *wq = alloc_workqueue("dio/%s", WQ_MEM_RECLAIM, 0, sb->s_id); if (!wq) return -ENOMEM; /* * This has to be atomic as more DIOs can race to create the workqueue */ old = cmpxchg(&sb->s_dio_done_wq, NULL, wq); /* Someone created workqueue before us? Free ours... */ if (old) destroy_workqueue(wq); return 0; } EXPORT_SYMBOL_GPL(sb_init_dio_done_wq); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_MMU_H #define __ASM_MMU_H #include <asm/cputype.h> #define MMCF_AARCH32 0x1 /* mm context flag for AArch32 executables */ #define USER_ASID_BIT 48 #define USER_ASID_FLAG (UL(1) << USER_ASID_BIT) #define TTBR_ASID_MASK (UL(0xffff) << 48) #ifndef __ASSEMBLY__ #include <linux/refcount.h> #include <asm/cpufeature.h> typedef struct { atomic64_t id; #ifdef CONFIG_COMPAT void *sigpage; #endif refcount_t pinned; void *vdso; unsigned long flags; } mm_context_t; /* * We use atomic64_read() here because the ASID for an 'mm_struct' can * be reallocated when scheduling one of its threads following a * rollover event (see new_context() and flush_context()). In this case, * a concurrent TLBI (e.g. via try_to_unmap_one() and ptep_clear_flush()) * may use a stale ASID. This is fine in principle as the new ASID is * guaranteed to be clean in the TLB, but the TLBI routines have to take * care to handle the following race: * * CPU 0 CPU 1 CPU 2 * * // ptep_clear_flush(mm) * xchg_relaxed(pte, 0) * DSB ISHST * old = ASID(mm) * | <rollover> * | new = new_context(mm) * \-----------------> atomic_set(mm->context.id, new) * cpu_switch_mm(mm) * // Hardware walk of pte using new ASID * TLBI(old) * * In this scenario, the barrier on CPU 0 and the dependency on CPU 1 * ensure that the page-table walker on CPU 1 *must* see the invalid PTE * written by CPU 0. */ #define ASID(mm) (atomic64_read(&(mm)->context.id) & 0xffff) static inline bool arm64_kernel_unmapped_at_el0(void) { return alternative_has_cap_unlikely(ARM64_UNMAP_KERNEL_AT_EL0); } extern void arm64_memblock_init(void); extern void paging_init(void); extern void bootmem_init(void); extern void __iomem *early_io_map(phys_addr_t phys, unsigned long virt); extern void create_mapping_noalloc(phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot); extern void create_pgd_mapping(struct mm_struct *mm, phys_addr_t phys, unsigned long virt, phys_addr_t size, pgprot_t prot, bool page_mappings_only); extern void *fixmap_remap_fdt(phys_addr_t dt_phys, int *size, pgprot_t prot); extern void mark_linear_text_alias_ro(void); /* * This check is triggered during the early boot before the cpufeature * is initialised. Checking the status on the local CPU allows the boot * CPU to detect the need for non-global mappings and thus avoiding a * pagetable re-write after all the CPUs are booted. This check will be * anyway run on individual CPUs, allowing us to get the consistent * state once the SMP CPUs are up and thus make the switch to non-global * mappings if required. */ static inline bool kaslr_requires_kpti(void) { /* * E0PD does a similar job to KPTI so can be used instead * where available. */ if (IS_ENABLED(CONFIG_ARM64_E0PD)) { u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); if (cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_E0PD_SHIFT)) return false; } /* * Systems affected by Cavium erratum 24756 are incompatible * with KPTI. */ if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { extern const struct midr_range cavium_erratum_27456_cpus[]; if (is_midr_in_range_list(read_cpuid_id(), cavium_erratum_27456_cpus)) return false; } return true; } #define INIT_MM_CONTEXT(name) \ .pgd = swapper_pg_dir, #endif /* !__ASSEMBLY__ */ #endif |
| 14 14 14 7 7 1 1 14 14 1 131 132 132 131 132 90 17 2 2 2 15 17 47 21 47 46 2 2 182 182 182 143 180 59 59 59 59 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/mm.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/compiler.h> #include <linux/export.h> #include <linux/err.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/security.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/mman.h> #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> #include <linux/elf.h> #include <linux/elf-randomize.h> #include <linux/personality.h> #include <linux/random.h> #include <linux/processor.h> #include <linux/sizes.h> #include <linux/compat.h> #include <linux/uaccess.h> #include "internal.h" #include "swap.h" /** * kfree_const - conditionally free memory * @x: pointer to the memory * * Function calls kfree only if @x is not in .rodata section. */ void kfree_const(const void *x) { if (!is_kernel_rodata((unsigned long)x)) kfree(x); } EXPORT_SYMBOL(kfree_const); /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s or %NULL in case of error */ noinline char *kstrdup(const char *s, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strlen(s) + 1; buf = kmalloc_track_caller(len, gfp); if (buf) memcpy(buf, s, len); return buf; } EXPORT_SYMBOL(kstrdup); /** * kstrdup_const - conditionally duplicate an existing const string * @s: the string to duplicate * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Strings allocated by kstrdup_const should be freed by kfree_const and * must not be passed to krealloc(). * * Return: source string if it is in .rodata section otherwise * fallback to kstrdup. */ const char *kstrdup_const(const char *s, gfp_t gfp) { if (is_kernel_rodata((unsigned long)s)) return s; return kstrdup(s, gfp); } EXPORT_SYMBOL(kstrdup_const); /** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Note: Use kmemdup_nul() instead if the size is known exactly. * * Return: newly allocated copy of @s or %NULL in case of error */ char *kstrndup(const char *s, size_t max, gfp_t gfp) { size_t len; char *buf; if (!s) return NULL; len = strnlen(s, max); buf = kmalloc_track_caller(len+1, gfp); if (buf) { memcpy(buf, s, len); buf[len] = '\0'; } return buf; } EXPORT_SYMBOL(kstrndup); /** * kmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_noprof(const void *src, size_t len, gfp_t gfp) { void *p; p = kmalloc_node_track_caller_noprof(len, gfp, NUMA_NO_NODE, _RET_IP_); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kmemdup_noprof); /** * kmemdup_array - duplicate a given array. * * @src: array to duplicate. * @count: number of elements to duplicate from array. * @element_size: size of each element of array. * @gfp: GFP mask to use. * * Return: duplicated array of @src or %NULL in case of error, * result is physically contiguous. Use kfree() to free. */ void *kmemdup_array(const void *src, size_t count, size_t element_size, gfp_t gfp) { return kmemdup(src, size_mul(element_size, count), gfp); } EXPORT_SYMBOL(kmemdup_array); /** * kvmemdup - duplicate region of memory * * @src: memory region to duplicate * @len: memory region length * @gfp: GFP mask to use * * Return: newly allocated copy of @src or %NULL in case of error, * result may be not physically contiguous. Use kvfree() to free. */ void *kvmemdup(const void *src, size_t len, gfp_t gfp) { void *p; p = kvmalloc(len, gfp); if (p) memcpy(p, src, len); return p; } EXPORT_SYMBOL(kvmemdup); /** * kmemdup_nul - Create a NUL-terminated string from unterminated data * @s: The data to stringify * @len: The size of the data * @gfp: the GFP mask used in the kmalloc() call when allocating memory * * Return: newly allocated copy of @s with NUL-termination or %NULL in * case of error */ char *kmemdup_nul(const char *s, size_t len, gfp_t gfp) { char *buf; if (!s) return NULL; buf = kmalloc_track_caller(len + 1, gfp); if (buf) { memcpy(buf, s, len); buf[len] = '\0'; } return buf; } EXPORT_SYMBOL(kmemdup_nul); /** * memdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result is physically * contiguous, to be freed by kfree(). */ void *memdup_user(const void __user *src, size_t len) { void *p; p = kmalloc_track_caller(len, GFP_USER | __GFP_NOWARN); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(memdup_user); /** * vmemdup_user - duplicate memory region from user space * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. Result may be not * physically contiguous. Use kvfree() to free. */ void *vmemdup_user(const void __user *src, size_t len) { void *p; p = kvmalloc(len, GFP_USER); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kvfree(p); return ERR_PTR(-EFAULT); } return p; } EXPORT_SYMBOL(vmemdup_user); /** * strndup_user - duplicate an existing string from user space * @s: The string to duplicate * @n: Maximum number of bytes to copy, including the trailing NUL. * * Return: newly allocated copy of @s or an ERR_PTR() in case of error */ char *strndup_user(const char __user *s, long n) { char *p; long length; length = strnlen_user(s, n); if (!length) return ERR_PTR(-EFAULT); if (length > n) return ERR_PTR(-EINVAL); p = memdup_user(s, length); if (IS_ERR(p)) return p; p[length - 1] = '\0'; return p; } EXPORT_SYMBOL(strndup_user); /** * memdup_user_nul - duplicate memory region from user space and NUL-terminate * * @src: source address in user space * @len: number of bytes to copy * * Return: an ERR_PTR() on failure. */ void *memdup_user_nul(const void __user *src, size_t len) { char *p; /* * Always use GFP_KERNEL, since copy_from_user() can sleep and * cause pagefault, which makes it pointless to use GFP_NOFS * or GFP_ATOMIC. */ p = kmalloc_track_caller(len + 1, GFP_KERNEL); if (!p) return ERR_PTR(-ENOMEM); if (copy_from_user(p, src, len)) { kfree(p); return ERR_PTR(-EFAULT); } p[len] = '\0'; return p; } EXPORT_SYMBOL(memdup_user_nul); /* Check if the vma is being used as a stack by this task */ int vma_is_stack_for_current(struct vm_area_struct *vma) { struct task_struct * __maybe_unused t = current; return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } /* * Change backing file, only valid to use during initial VMA setup. */ void vma_set_file(struct vm_area_struct *vma, struct file *file) { /* Changing an anonymous vma with this is illegal */ get_file(file); swap(vma->vm_file, file); fput(file); } EXPORT_SYMBOL(vma_set_file); #ifndef STACK_RND_MASK #define STACK_RND_MASK (0x7ff >> (PAGE_SHIFT - 12)) /* 8MB of VA */ #endif unsigned long randomize_stack_top(unsigned long stack_top) { unsigned long random_variable = 0; if (current->flags & PF_RANDOMIZE) { random_variable = get_random_long(); random_variable &= STACK_RND_MASK; random_variable <<= PAGE_SHIFT; } #ifdef CONFIG_STACK_GROWSUP return PAGE_ALIGN(stack_top) + random_variable; #else return PAGE_ALIGN(stack_top) - random_variable; #endif } /** * randomize_page - Generate a random, page aligned address * @start: The smallest acceptable address the caller will take. * @range: The size of the area, starting at @start, within which the * random address must fall. * * If @start + @range would overflow, @range is capped. * * NOTE: Historical use of randomize_range, which this replaces, presumed that * @start was already page aligned. We now align it regardless. * * Return: A page aligned address within [start, start + range). On error, * @start is returned. */ unsigned long randomize_page(unsigned long start, unsigned long range) { if (!PAGE_ALIGNED(start)) { range -= PAGE_ALIGN(start) - start; start = PAGE_ALIGN(start); } if (start > ULONG_MAX - range) range = ULONG_MAX - start; range >>= PAGE_SHIFT; if (range == 0) return start; return start + (get_random_long() % range << PAGE_SHIFT); } #ifdef CONFIG_ARCH_WANT_DEFAULT_TOPDOWN_MMAP_LAYOUT unsigned long __weak arch_randomize_brk(struct mm_struct *mm) { /* Is the current task 32bit ? */ if (!IS_ENABLED(CONFIG_64BIT) || is_compat_task()) return randomize_page(mm->brk, SZ_32M); return randomize_page(mm->brk, SZ_1G); } unsigned long arch_mmap_rnd(void) { unsigned long rnd; #ifdef CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS if (is_compat_task()) rnd = get_random_long() & ((1UL << mmap_rnd_compat_bits) - 1); else #endif /* CONFIG_HAVE_ARCH_MMAP_RND_COMPAT_BITS */ rnd = get_random_long() & ((1UL << mmap_rnd_bits) - 1); return rnd << PAGE_SHIFT; } static int mmap_is_legacy(struct rlimit *rlim_stack) { if (current->personality & ADDR_COMPAT_LAYOUT) return 1; /* On parisc the stack always grows up - so a unlimited stack should * not be an indicator to use the legacy memory layout. */ if (rlim_stack->rlim_cur == RLIM_INFINITY && !IS_ENABLED(CONFIG_STACK_GROWSUP)) return 1; return sysctl_legacy_va_layout; } /* * Leave enough space between the mmap area and the stack to honour ulimit in * the face of randomisation. */ #define MIN_GAP (SZ_128M) #define MAX_GAP (STACK_TOP / 6 * 5) static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack) { #ifdef CONFIG_STACK_GROWSUP /* * For an upwards growing stack the calculation is much simpler. * Memory for the maximum stack size is reserved at the top of the * task. mmap_base starts directly below the stack and grows * downwards. */ return PAGE_ALIGN_DOWN(mmap_upper_limit(rlim_stack) - rnd); #else unsigned long gap = rlim_stack->rlim_cur; unsigned long pad = stack_guard_gap; /* Account for stack randomization if necessary */ if (current->flags & PF_RANDOMIZE) pad += (STACK_RND_MASK << PAGE_SHIFT); /* Values close to RLIM_INFINITY can overflow. */ if (gap + pad > gap) gap += pad; if (gap < MIN_GAP) gap = MIN_GAP; else if (gap > MAX_GAP) gap = MAX_GAP; return PAGE_ALIGN(STACK_TOP - gap - rnd); #endif } void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { unsigned long random_factor = 0UL; if (current->flags & PF_RANDOMIZE) random_factor = arch_mmap_rnd(); if (mmap_is_legacy(rlim_stack)) { mm->mmap_base = TASK_UNMAPPED_BASE + random_factor; clear_bit(MMF_TOPDOWN, &mm->flags); } else { mm->mmap_base = mmap_base(random_factor, rlim_stack); set_bit(MMF_TOPDOWN, &mm->flags); } } #elif defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { mm->mmap_base = TASK_UNMAPPED_BASE; clear_bit(MMF_TOPDOWN, &mm->flags); } #endif /** * __account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * @task: task used to check RLIMIT_MEMLOCK * @bypass_rlim: %true if checking RLIMIT_MEMLOCK should be skipped * * Assumes @task and @mm are valid (i.e. at least one reference on each), and * that mmap_lock is held as writer. * * Return: * * 0 on success * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int __account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc, struct task_struct *task, bool bypass_rlim) { unsigned long locked_vm, limit; int ret = 0; mmap_assert_write_locked(mm); locked_vm = mm->locked_vm; if (inc) { if (!bypass_rlim) { limit = task_rlimit(task, RLIMIT_MEMLOCK) >> PAGE_SHIFT; if (locked_vm + pages > limit) ret = -ENOMEM; } if (!ret) mm->locked_vm = locked_vm + pages; } else { WARN_ON_ONCE(pages > locked_vm); mm->locked_vm = locked_vm - pages; } pr_debug("%s: [%d] caller %ps %c%lu %lu/%lu%s\n", __func__, task->pid, (void *)_RET_IP_, (inc) ? '+' : '-', pages << PAGE_SHIFT, locked_vm << PAGE_SHIFT, task_rlimit(task, RLIMIT_MEMLOCK), ret ? " - exceeded" : ""); return ret; } EXPORT_SYMBOL_GPL(__account_locked_vm); /** * account_locked_vm - account locked pages to an mm's locked_vm * @mm: mm to account against, may be NULL * @pages: number of pages to account * @inc: %true if @pages should be considered positive, %false if not * * Assumes a non-NULL @mm is valid (i.e. at least one reference on it). * * Return: * * 0 on success, or if mm is NULL * * -ENOMEM if RLIMIT_MEMLOCK would be exceeded. */ int account_locked_vm(struct mm_struct *mm, unsigned long pages, bool inc) { int ret; if (pages == 0 || !mm) return 0; mmap_write_lock(mm); ret = __account_locked_vm(mm, pages, inc, current, capable(CAP_IPC_LOCK)); mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL_GPL(account_locked_vm); unsigned long vm_mmap_pgoff(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long pgoff) { unsigned long ret; struct mm_struct *mm = current->mm; unsigned long populate; LIST_HEAD(uf); ret = security_mmap_file(file, prot, flag); if (!ret) { if (mmap_write_lock_killable(mm)) return -EINTR; ret = do_mmap(file, addr, len, prot, flag, 0, pgoff, &populate, &uf); mmap_write_unlock(mm); userfaultfd_unmap_complete(mm, &uf); if (populate) mm_populate(ret, populate); } return ret; } unsigned long vm_mmap(struct file *file, unsigned long addr, unsigned long len, unsigned long prot, unsigned long flag, unsigned long offset) { if (unlikely(offset + PAGE_ALIGN(len) < offset)) return -EINVAL; if (unlikely(offset_in_page(offset))) return -EINVAL; return vm_mmap_pgoff(file, addr, len, prot, flag, offset >> PAGE_SHIFT); } EXPORT_SYMBOL(vm_mmap); /** * kvmalloc_node - attempt to allocate physically contiguous memory, but upon * failure, fall back to non-contiguous (vmalloc) allocation. * @size: size of the request. * @flags: gfp mask for the allocation - must be compatible (superset) with GFP_KERNEL. * @node: numa node to allocate from * * Uses kmalloc to get the memory but if the allocation fails then falls back * to the vmalloc allocator. Use kvfree for freeing the memory. * * GFP_NOWAIT and GFP_ATOMIC are not supported, neither is the __GFP_NORETRY modifier. * __GFP_RETRY_MAYFAIL is supported, and it should be used only if kmalloc is * preferable to the vmalloc fallback, due to visible performance drawbacks. * * Return: pointer to the allocated memory of %NULL in case of failure */ void *kvmalloc_node_noprof(size_t size, gfp_t flags, int node) { gfp_t kmalloc_flags = flags; void *ret; /* * We want to attempt a large physically contiguous block first because * it is less likely to fragment multiple larger blocks and therefore * contribute to a long term fragmentation less than vmalloc fallback. * However make sure that larger requests are not too disruptive - no * OOM killer and no allocation failure warnings as we have a fallback. */ if (size > PAGE_SIZE) { kmalloc_flags |= __GFP_NOWARN; if (!(kmalloc_flags & __GFP_RETRY_MAYFAIL)) kmalloc_flags |= __GFP_NORETRY; /* nofail semantic is implemented by the vmalloc fallback */ kmalloc_flags &= ~__GFP_NOFAIL; } ret = kmalloc_node_noprof(size, kmalloc_flags, node); /* * It doesn't really make sense to fallback to vmalloc for sub page * requests */ if (ret || size <= PAGE_SIZE) return ret; /* non-sleeping allocations are not supported by vmalloc */ if (!gfpflags_allow_blocking(flags)) return NULL; /* Don't even allow crazy sizes */ if (unlikely(size > INT_MAX)) { WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; } /* * kvmalloc() can always use VM_ALLOW_HUGE_VMAP, * since the callers already cannot assume anything * about the resulting pointer, and cannot play * protection games. */ return __vmalloc_node_range_noprof(size, 1, VMALLOC_START, VMALLOC_END, flags, PAGE_KERNEL, VM_ALLOW_HUGE_VMAP, node, __builtin_return_address(0)); } EXPORT_SYMBOL(kvmalloc_node_noprof); /** * kvfree() - Free memory. * @addr: Pointer to allocated memory. * * kvfree frees memory allocated by any of vmalloc(), kmalloc() or kvmalloc(). * It is slightly more efficient to use kfree() or vfree() if you are certain * that you know which one to use. * * Context: Either preemptible task context or not-NMI interrupt. */ void kvfree(const void *addr) { if (is_vmalloc_addr(addr)) vfree(addr); else kfree(addr); } EXPORT_SYMBOL(kvfree); /** * kvfree_sensitive - Free a data object containing sensitive information. * @addr: address of the data object to be freed. * @len: length of the data object. * * Use the special memzero_explicit() function to clear the content of a * kvmalloc'ed object containing sensitive data to make sure that the * compiler won't optimize out the data clearing. */ void kvfree_sensitive(const void *addr, size_t len) { if (likely(!ZERO_OR_NULL_PTR(addr))) { memzero_explicit((void *)addr, len); kvfree(addr); } } EXPORT_SYMBOL(kvfree_sensitive); void *kvrealloc_noprof(const void *p, size_t oldsize, size_t newsize, gfp_t flags) { void *newp; if (oldsize >= newsize) return (void *)p; newp = kvmalloc_noprof(newsize, flags); if (!newp) return NULL; memcpy(newp, p, oldsize); kvfree(p); return newp; } EXPORT_SYMBOL(kvrealloc_noprof); /** * __vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) { size_t bytes; if (unlikely(check_mul_overflow(n, size, &bytes))) return NULL; return __vmalloc_noprof(bytes, flags); } EXPORT_SYMBOL(__vmalloc_array_noprof); /** * vmalloc_array - allocate memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vmalloc_array_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL); } EXPORT_SYMBOL(vmalloc_array_noprof); /** * __vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. * @flags: the type of memory to allocate (see kmalloc). */ void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) { return __vmalloc_array_noprof(n, size, flags | __GFP_ZERO); } EXPORT_SYMBOL(__vcalloc_noprof); /** * vcalloc - allocate and zero memory for a virtually contiguous array. * @n: number of elements. * @size: element size. */ void *vcalloc_noprof(size_t n, size_t size) { return __vmalloc_array_noprof(n, size, GFP_KERNEL | __GFP_ZERO); } EXPORT_SYMBOL(vcalloc_noprof); struct anon_vma *folio_anon_vma(struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON) return NULL; return (void *)(mapping - PAGE_MAPPING_ANON); } /** * folio_mapping - Find the mapping where this folio is stored. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Folios in the swap cache return the swap mapping * this page is stored in (which is different from the mapping for the * swap file or swap device where the data is stored). * * You can call this for folios which aren't in the swap cache or page * cache and it will return NULL. */ struct address_space *folio_mapping(struct folio *folio) { struct address_space *mapping; /* This happens if someone calls flush_dcache_page on slab page */ if (unlikely(folio_test_slab(folio))) return NULL; if (unlikely(folio_test_swapcache(folio))) return swap_address_space(folio->swap); mapping = folio->mapping; if ((unsigned long)mapping & PAGE_MAPPING_FLAGS) return NULL; return mapping; } EXPORT_SYMBOL(folio_mapping); /** * folio_copy - Copy the contents of one folio to another. * @dst: Folio to copy to. * @src: Folio to copy from. * * The bytes in the folio represented by @src are copied to @dst. * Assumes the caller has validated that @dst is at least as large as @src. * Can be called in atomic context for order-0 folios, but if the folio is * larger, it may sleep. */ void folio_copy(struct folio *dst, struct folio *src) { long i = 0; long nr = folio_nr_pages(src); for (;;) { copy_highpage(folio_page(dst, i), folio_page(src, i)); if (++i == nr) break; cond_resched(); } } EXPORT_SYMBOL(folio_copy); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; int sysctl_overcommit_ratio __read_mostly = 50; unsigned long sysctl_overcommit_kbytes __read_mostly; int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int overcommit_ratio_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_dointvec(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_kbytes = 0; return ret; } static void sync_overcommit_as(struct work_struct *dummy) { percpu_counter_sync(&vm_committed_as); } int overcommit_policy_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { struct ctl_table t; int new_policy = -1; int ret; /* * The deviation of sync_overcommit_as could be big with loose policy * like OVERCOMMIT_ALWAYS/OVERCOMMIT_GUESS. When changing policy to * strict OVERCOMMIT_NEVER, we need to reduce the deviation to comply * with the strict "NEVER", and to avoid possible race condition (even * though user usually won't too frequently do the switching to policy * OVERCOMMIT_NEVER), the switch is done in the following order: * 1. changing the batch * 2. sync percpu count on each CPU * 3. switch the policy */ if (write) { t = *table; t.data = &new_policy; ret = proc_dointvec_minmax(&t, write, buffer, lenp, ppos); if (ret || new_policy == -1) return ret; mm_compute_batch(new_policy); if (new_policy == OVERCOMMIT_NEVER) schedule_on_each_cpu(sync_overcommit_as); sysctl_overcommit_memory = new_policy; } else { ret = proc_dointvec_minmax(table, write, buffer, lenp, ppos); } return ret; } int overcommit_kbytes_handler(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int ret; ret = proc_doulongvec_minmax(table, write, buffer, lenp, ppos); if (ret == 0 && write) sysctl_overcommit_ratio = 0; return ret; } /* * Committed memory limit enforced when OVERCOMMIT_NEVER policy is used */ unsigned long vm_commit_limit(void) { unsigned long allowed; if (sysctl_overcommit_kbytes) allowed = sysctl_overcommit_kbytes >> (PAGE_SHIFT - 10); else allowed = ((totalram_pages() - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100); allowed += total_swap_pages; return allowed; } /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. */ struct percpu_counter vm_committed_as ____cacheline_aligned_in_smp; /* * The global memory commitment made in the system can be a metric * that can be used to drive ballooning decisions when Linux is hosted * as a guest. On Hyper-V, the host implements a policy engine for dynamically * balancing memory across competing virtual machines that are hosted. * Several metrics drive this policy engine including the guest reported * memory commitment. * * The time cost of this is very low for small platforms, and for big * platform like a 2S/36C/72T Skylake server, in worst case where * vm_committed_as's spinlock is under severe contention, the time cost * could be about 30~40 microseconds. */ unsigned long vm_memory_committed(void) { return percpu_counter_sum_positive(&vm_committed_as); } EXPORT_SYMBOL_GPL(vm_memory_committed); /* * Check that a process has enough memory to allocate a new virtual * mapping. 0 means there is enough memory for the allocation to * succeed and -ENOMEM implies there is not. * * We currently support three overcommit policies, which are set via the * vm.overcommit_memory sysctl. See Documentation/mm/overcommit-accounting.rst * * Strict overcommit modes added 2002 Feb 26 by Alan Cox. * Additional code 2002 Jul 20 by Robert Love. * * cap_sys_admin is 1 if the process has admin privileges, 0 otherwise. * * Note this is a helper function intended to be used by LSMs which * wish to use this logic. */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { long allowed; unsigned long bytes_failed; vm_acct_memory(pages); /* * Sometimes we want to use more memory than we have */ if (sysctl_overcommit_memory == OVERCOMMIT_ALWAYS) return 0; if (sysctl_overcommit_memory == OVERCOMMIT_GUESS) { if (pages > totalram_pages() + total_swap_pages) goto error; return 0; } allowed = vm_commit_limit(); /* * Reserve some for root */ if (!cap_sys_admin) allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); /* * Don't let a single process grow so big a user can't recover */ if (mm) { long reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; error: bytes_failed = pages << PAGE_SHIFT; pr_warn_ratelimited("%s: pid: %d, comm: %s, bytes: %lu not enough memory for the allocation\n", __func__, current->pid, current->comm, bytes_failed); vm_unacct_memory(pages); return -ENOMEM; } /** * get_cmdline() - copy the cmdline value to a buffer. * @task: the task whose cmdline value to copy. * @buffer: the buffer to copy to. * @buflen: the length of the buffer. Larger cmdline values are truncated * to this length. * * Return: the size of the cmdline field copied. Note that the copy does * not guarantee an ending NULL byte. */ int get_cmdline(struct task_struct *task, char *buffer, int buflen) { int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ spin_lock(&mm->arg_lock); arg_start = mm->arg_start; arg_end = mm->arg_end; env_start = mm->env_start; env_end = mm->env_end; spin_unlock(&mm->arg_lock); len = arg_end - arg_start; if (len > buflen) len = buflen; res = access_process_vm(task, arg_start, buffer, len, FOLL_FORCE); /* * If the nul at the end of args has been overwritten, then * assume application is using setproctitle(3). */ if (res > 0 && buffer[res-1] != '\0' && len < buflen) { len = strnlen(buffer, res); if (len < res) { res = len; } else { len = env_end - env_start; if (len > buflen - res) len = buflen - res; res += access_process_vm(task, env_start, buffer+res, len, FOLL_FORCE); res = strnlen(buffer, res); } } out_mm: mmput(mm); out: return res; } int __weak memcmp_pages(struct page *page1, struct page *page2) { char *addr1, *addr2; int ret; addr1 = kmap_local_page(page1); addr2 = kmap_local_page(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); kunmap_local(addr2); kunmap_local(addr1); return ret; } #ifdef CONFIG_PRINTK /** * mem_dump_obj - Print available provenance information * @object: object for which to find provenance information. * * This function uses pr_cont(), so that the caller is expected to have * printed out whatever preamble is appropriate. The provenance information * depends on the type of object and on how much debugging is enabled. * For example, for a slab-cache object, the slab name is printed, and, * if available, the return address and stack trace from the allocation * and last free path of that object. */ void mem_dump_obj(void *object) { const char *type; if (kmem_dump_obj(object)) return; if (vmalloc_dump_obj(object)) return; if (is_vmalloc_addr(object)) type = "vmalloc memory"; else if (virt_addr_valid(object)) type = "non-slab/vmalloc memory"; else if (object == NULL) type = "NULL pointer"; else if (object == ZERO_SIZE_PTR) type = "zero-size pointer"; else type = "non-paged memory"; pr_cont(" %s\n", type); } EXPORT_SYMBOL_GPL(mem_dump_obj); #endif /* * A driver might set a page logically offline -- PageOffline() -- and * turn the page inaccessible in the hypervisor; after that, access to page * content can be fatal. * * Some special PFN walkers -- i.e., /proc/kcore -- read content of random * pages after checking PageOffline(); however, these PFN walkers can race * with drivers that set PageOffline(). * * page_offline_freeze()/page_offline_thaw() allows for a subsystem to * synchronize with such drivers, achieving that a page cannot be set * PageOffline() while frozen. * * page_offline_begin()/page_offline_end() is used by drivers that care about * such races when setting a page PageOffline(). */ static DECLARE_RWSEM(page_offline_rwsem); void page_offline_freeze(void) { down_read(&page_offline_rwsem); } void page_offline_thaw(void) { up_read(&page_offline_rwsem); } void page_offline_begin(void) { down_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_begin); void page_offline_end(void) { up_write(&page_offline_rwsem); } EXPORT_SYMBOL(page_offline_end); #ifndef flush_dcache_folio void flush_dcache_folio(struct folio *folio) { long i, nr = folio_nr_pages(folio); for (i = 0; i < nr; i++) flush_dcache_page(folio_page(folio, i)); } EXPORT_SYMBOL(flush_dcache_folio); #endif |
| 18 18 18 18 18 18 18 18 18 18 18 18 18 18 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 | // SPDX-License-Identifier: GPL-2.0-or-later /* * lib/plist.c * * Descending-priority-sorted double-linked list * * (C) 2002-2003 Intel Corp * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>. * * 2001-2005 (c) MontaVista Software, Inc. * Daniel Walker <dwalker@mvista.com> * * (C) 2005 Thomas Gleixner <tglx@linutronix.de> * * Simplifications of the original code by * Oleg Nesterov <oleg@tv-sign.ru> * * Based on simple lists (include/linux/list.h). * * This file contains the add / del functions which are considered to * be too large to inline. See include/linux/plist.h for further * information. */ #include <linux/bug.h> #include <linux/plist.h> #ifdef CONFIG_DEBUG_PLIST static struct plist_head test_head; static void plist_check_prev_next(struct list_head *t, struct list_head *p, struct list_head *n) { WARN(n->prev != p || p->next != n, "top: %p, n: %p, p: %p\n" "prev: %p, n: %p, p: %p\n" "next: %p, n: %p, p: %p\n", t, t->next, t->prev, p, p->next, p->prev, n, n->next, n->prev); } static void plist_check_list(struct list_head *top) { struct list_head *prev = top, *next = top->next; plist_check_prev_next(top, prev, next); while (next != top) { prev = next; next = prev->next; plist_check_prev_next(top, prev, next); } } static void plist_check_head(struct plist_head *head) { if (!plist_head_empty(head)) plist_check_list(&plist_first(head)->prio_list); plist_check_list(&head->node_list); } #else # define plist_check_head(h) do { } while (0) #endif /** * plist_add - add @node to @head * * @node: &struct plist_node pointer * @head: &struct plist_head pointer */ void plist_add(struct plist_node *node, struct plist_head *head) { struct plist_node *first, *iter, *prev = NULL; struct list_head *node_next = &head->node_list; plist_check_head(head); WARN_ON(!plist_node_empty(node)); WARN_ON(!list_empty(&node->prio_list)); if (plist_head_empty(head)) goto ins_node; first = iter = plist_first(head); do { if (node->prio < iter->prio) { node_next = &iter->node_list; break; } prev = iter; iter = list_entry(iter->prio_list.next, struct plist_node, prio_list); } while (iter != first); if (!prev || prev->prio != node->prio) list_add_tail(&node->prio_list, &iter->prio_list); ins_node: list_add_tail(&node->node_list, node_next); plist_check_head(head); } /** * plist_del - Remove a @node from plist. * * @node: &struct plist_node pointer - entry to be removed * @head: &struct plist_head pointer - list head */ void plist_del(struct plist_node *node, struct plist_head *head) { plist_check_head(head); if (!list_empty(&node->prio_list)) { if (node->node_list.next != &head->node_list) { struct plist_node *next; next = list_entry(node->node_list.next, struct plist_node, node_list); /* add the next plist_node into prio_list */ if (list_empty(&next->prio_list)) list_add(&next->prio_list, &node->prio_list); } list_del_init(&node->prio_list); } list_del_init(&node->node_list); plist_check_head(head); } /** * plist_requeue - Requeue @node at end of same-prio entries. * * This is essentially an optimized plist_del() followed by * plist_add(). It moves an entry already in the plist to * after any other same-priority entries. * * @node: &struct plist_node pointer - entry to be moved * @head: &struct plist_head pointer - list head */ void plist_requeue(struct plist_node *node, struct plist_head *head) { struct plist_node *iter; struct list_head *node_next = &head->node_list; plist_check_head(head); BUG_ON(plist_head_empty(head)); BUG_ON(plist_node_empty(node)); if (node == plist_last(head)) return; iter = plist_next(node); if (node->prio != iter->prio) return; plist_del(node, head); plist_for_each_continue(iter, head) { if (node->prio != iter->prio) { node_next = &iter->node_list; break; } } list_add_tail(&node->node_list, node_next); plist_check_head(head); } #ifdef CONFIG_DEBUG_PLIST #include <linux/sched.h> #include <linux/sched/clock.h> #include <linux/module.h> #include <linux/init.h> static struct plist_node __initdata test_node[241]; static void __init plist_test_check(int nr_expect) { struct plist_node *first, *prio_pos, *node_pos; if (plist_head_empty(&test_head)) { BUG_ON(nr_expect != 0); return; } prio_pos = first = plist_first(&test_head); plist_for_each(node_pos, &test_head) { if (nr_expect-- < 0) break; if (node_pos == first) continue; if (node_pos->prio == prio_pos->prio) { BUG_ON(!list_empty(&node_pos->prio_list)); continue; } BUG_ON(prio_pos->prio > node_pos->prio); BUG_ON(prio_pos->prio_list.next != &node_pos->prio_list); prio_pos = node_pos; } BUG_ON(nr_expect != 0); BUG_ON(prio_pos->prio_list.next != &first->prio_list); } static void __init plist_test_requeue(struct plist_node *node) { plist_requeue(node, &test_head); if (node != plist_last(&test_head)) BUG_ON(node->prio == plist_next(node)->prio); } static int __init plist_test(void) { int nr_expect = 0, i, loop; unsigned int r = local_clock(); printk(KERN_DEBUG "start plist test\n"); plist_head_init(&test_head); for (i = 0; i < ARRAY_SIZE(test_node); i++) plist_node_init(test_node + i, 0); for (loop = 0; loop < 1000; loop++) { r = r * 193939 % 47629; i = r % ARRAY_SIZE(test_node); if (plist_node_empty(test_node + i)) { r = r * 193939 % 47629; test_node[i].prio = r % 99; plist_add(test_node + i, &test_head); nr_expect++; } else { plist_del(test_node + i, &test_head); nr_expect--; } plist_test_check(nr_expect); if (!plist_node_empty(test_node + i)) { plist_test_requeue(test_node + i); plist_test_check(nr_expect); } } for (i = 0; i < ARRAY_SIZE(test_node); i++) { if (plist_node_empty(test_node + i)) continue; plist_del(test_node + i, &test_head); nr_expect--; plist_test_check(nr_expect); } printk(KERN_DEBUG "end plist test\n"); return 0; } module_init(plist_test); #endif |
| 260 289 96 84 85 84 85 2 19 109 160 132 160 160 224 109 153 109 200 32 200 200 200 200 153 200 29 136 219 219 260 260 289 289 289 288 289 288 289 289 289 117 39 39 14 11 33 136 83 2 84 19 108 200 33 14 14 11 10 11 11 21 23 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_PGTABLE_H #define __ASM_PGTABLE_H #include <asm/bug.h> #include <asm/proc-fns.h> #include <asm/memory.h> #include <asm/mte.h> #include <asm/pgtable-hwdef.h> #include <asm/pgtable-prot.h> #include <asm/tlbflush.h> /* * VMALLOC range. * * VMALLOC_START: beginning of the kernel vmalloc space * VMALLOC_END: extends to the available space below vmemmap */ #define VMALLOC_START (MODULES_END) #if VA_BITS == VA_BITS_MIN #define VMALLOC_END (VMEMMAP_START - SZ_8M) #else #define VMEMMAP_UNUSED_NPAGES ((_PAGE_OFFSET(vabits_actual) - PAGE_OFFSET) >> PAGE_SHIFT) #define VMALLOC_END (VMEMMAP_START + VMEMMAP_UNUSED_NPAGES * sizeof(struct page) - SZ_8M) #endif #define vmemmap ((struct page *)VMEMMAP_START - (memstart_addr >> PAGE_SHIFT)) #ifndef __ASSEMBLY__ #include <asm/cmpxchg.h> #include <asm/fixmap.h> #include <linux/mmdebug.h> #include <linux/mm_types.h> #include <linux/sched.h> #include <linux/page_table_check.h> #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE /* Set stride and tlb_level in flush_*_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PMD_SIZE, false, 2) #define flush_pud_tlb_range(vma, addr, end) \ __flush_tlb_range(vma, addr, end, PUD_SIZE, false, 1) #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ /* * Outside of a few very special situations (e.g. hibernation), we always * use broadcast TLB invalidation instructions, therefore a spurious page * fault on one CPU which has been handled concurrently by another CPU * does not need to perform additional invalidation. */ #define flush_tlb_fix_spurious_fault(vma, address, ptep) do { } while (0) /* * ZERO_PAGE is a global shared page that is always zero: used * for zero-mapped memory areas etc.. */ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)]; #define ZERO_PAGE(vaddr) phys_to_page(__pa_symbol(empty_zero_page)) #define pte_ERROR(e) \ pr_err("%s:%d: bad pte %016llx.\n", __FILE__, __LINE__, pte_val(e)) /* * Macros to convert between a physical address and its placement in a * page table entry, taking care of 52-bit addresses. */ #ifdef CONFIG_ARM64_PA_BITS_52 static inline phys_addr_t __pte_to_phys(pte_t pte) { pte_val(pte) &= ~PTE_MAYBE_SHARED; return (pte_val(pte) & PTE_ADDR_LOW) | ((pte_val(pte) & PTE_ADDR_HIGH) << PTE_ADDR_HIGH_SHIFT); } static inline pteval_t __phys_to_pte_val(phys_addr_t phys) { return (phys | (phys >> PTE_ADDR_HIGH_SHIFT)) & PHYS_TO_PTE_ADDR_MASK; } #else #define __pte_to_phys(pte) (pte_val(pte) & PTE_ADDR_LOW) #define __phys_to_pte_val(phys) (phys) #endif #define pte_pfn(pte) (__pte_to_phys(pte) >> PAGE_SHIFT) #define pfn_pte(pfn,prot) \ __pte(__phys_to_pte_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define pte_none(pte) (!pte_val(pte)) #define __pte_clear(mm, addr, ptep) \ __set_pte(ptep, __pte(0)) #define pte_page(pte) (pfn_to_page(pte_pfn(pte))) /* * The following only work if pte_present(). Undefined behaviour otherwise. */ #define pte_present(pte) (pte_valid(pte) || pte_present_invalid(pte)) #define pte_young(pte) (!!(pte_val(pte) & PTE_AF)) #define pte_special(pte) (!!(pte_val(pte) & PTE_SPECIAL)) #define pte_write(pte) (!!(pte_val(pte) & PTE_WRITE)) #define pte_rdonly(pte) (!!(pte_val(pte) & PTE_RDONLY)) #define pte_user(pte) (!!(pte_val(pte) & PTE_USER)) #define pte_user_exec(pte) (!(pte_val(pte) & PTE_UXN)) #define pte_cont(pte) (!!(pte_val(pte) & PTE_CONT)) #define pte_devmap(pte) (!!(pte_val(pte) & PTE_DEVMAP)) #define pte_tagged(pte) ((pte_val(pte) & PTE_ATTRINDX_MASK) == \ PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pte_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PTE_SIZE) & CONT_PTE_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pmd_cont_addr_end(addr, end) \ ({ unsigned long __boundary = ((addr) + CONT_PMD_SIZE) & CONT_PMD_MASK; \ (__boundary - 1 < (end) - 1) ? __boundary : (end); \ }) #define pte_hw_dirty(pte) (pte_write(pte) && !pte_rdonly(pte)) #define pte_sw_dirty(pte) (!!(pte_val(pte) & PTE_DIRTY)) #define pte_dirty(pte) (pte_sw_dirty(pte) || pte_hw_dirty(pte)) #define pte_valid(pte) (!!(pte_val(pte) & PTE_VALID)) #define pte_present_invalid(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_PRESENT_INVALID)) == PTE_PRESENT_INVALID) /* * Execute-only user mappings do not have the PTE_USER bit set. All valid * kernel mappings have the PTE_UXN bit set. */ #define pte_valid_not_user(pte) \ ((pte_val(pte) & (PTE_VALID | PTE_USER | PTE_UXN)) == (PTE_VALID | PTE_UXN)) /* * Returns true if the pte is valid and has the contiguous bit set. */ #define pte_valid_cont(pte) (pte_valid(pte) && pte_cont(pte)) /* * Could the pte be present in the TLB? We must check mm_tlb_flush_pending * so that we don't erroneously return false for pages that have been * remapped as PROT_NONE but are yet to be flushed from the TLB. * Note that we can't make any assumptions based on the state of the access * flag, since __ptep_clear_flush_young() elides a DSB when invalidating the * TLB. */ #define pte_accessible(mm, pte) \ (mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte)) /* * p??_access_permitted() is true for valid user mappings (PTE_USER * bit set, subject to the write permission check). For execute-only * mappings, like PROT_EXEC with EPAN (both PTE_USER and PTE_UXN bits * not set) must return false. PROT_NONE mappings do not have the * PTE_VALID bit set. */ #define pte_access_permitted(pte, write) \ (((pte_val(pte) & (PTE_VALID | PTE_USER)) == (PTE_VALID | PTE_USER)) && (!(write) || pte_write(pte))) #define pmd_access_permitted(pmd, write) \ (pte_access_permitted(pmd_pte(pmd), (write))) #define pud_access_permitted(pud, write) \ (pte_access_permitted(pud_pte(pud), (write))) static inline pte_t clear_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) &= ~pgprot_val(prot); return pte; } static inline pte_t set_pte_bit(pte_t pte, pgprot_t prot) { pte_val(pte) |= pgprot_val(prot); return pte; } static inline pmd_t clear_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) &= ~pgprot_val(prot); return pmd; } static inline pmd_t set_pmd_bit(pmd_t pmd, pgprot_t prot) { pmd_val(pmd) |= pgprot_val(prot); return pmd; } static inline pte_t pte_mkwrite_novma(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_WRITE)); pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkclean(pte_t pte) { pte = clear_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkdirty(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); if (pte_write(pte)) pte = clear_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_wrprotect(pte_t pte) { /* * If hardware-dirty (PTE_WRITE/DBM bit set and PTE_RDONLY * clear), set the PTE_DIRTY bit. */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte = clear_pte_bit(pte, __pgprot(PTE_WRITE)); pte = set_pte_bit(pte, __pgprot(PTE_RDONLY)); return pte; } static inline pte_t pte_mkold(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkyoung(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_AF)); } static inline pte_t pte_mkspecial(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SPECIAL)); } static inline pte_t pte_mkcont(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_CONT)); return set_pte_bit(pte, __pgprot(PTE_TYPE_PAGE)); } static inline pte_t pte_mknoncont(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_CONT)); } static inline pte_t pte_mkpresent(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_VALID)); } static inline pte_t pte_mkinvalid(pte_t pte) { pte = set_pte_bit(pte, __pgprot(PTE_PRESENT_INVALID)); pte = clear_pte_bit(pte, __pgprot(PTE_VALID)); return pte; } static inline pmd_t pmd_mkcont(pmd_t pmd) { return __pmd(pmd_val(pmd) | PMD_SECT_CONT); } static inline pte_t pte_mkdevmap(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline int pte_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_UFFD_WP); } static inline pte_t pte_mkuffd_wp(pte_t pte) { return pte_wrprotect(set_pte_bit(pte, __pgprot(PTE_UFFD_WP))); } static inline pte_t pte_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ static inline void __set_pte_nosync(pte_t *ptep, pte_t pte) { WRITE_ONCE(*ptep, pte); } static inline void __set_pte(pte_t *ptep, pte_t pte) { __set_pte_nosync(ptep, pte); /* * Only if the new pte is valid and kernel, otherwise TLB maintenance * or update_mmu_cache() have the necessary barriers. */ if (pte_valid_not_user(pte)) { dsb(ishst); isb(); } } static inline pte_t __ptep_get(pte_t *ptep) { return READ_ONCE(*ptep); } extern void __sync_icache_dcache(pte_t pteval); bool pgattr_change_is_safe(u64 old, u64 new); /* * PTE bits configuration in the presence of hardware Dirty Bit Management * (PTE_WRITE == PTE_DBM): * * Dirty Writable | PTE_RDONLY PTE_WRITE PTE_DIRTY (sw) * 0 0 | 1 0 0 * 0 1 | 1 1 0 * 1 0 | 1 0 1 * 1 1 | 0 1 x * * When hardware DBM is not present, the sofware PTE_DIRTY bit is updated via * the page fault mechanism. Checking the dirty status of a pte becomes: * * PTE_DIRTY || (PTE_WRITE && !PTE_RDONLY) */ static inline void __check_safe_pte_update(struct mm_struct *mm, pte_t *ptep, pte_t pte) { pte_t old_pte; if (!IS_ENABLED(CONFIG_DEBUG_VM)) return; old_pte = __ptep_get(ptep); if (!pte_valid(old_pte) || !pte_valid(pte)) return; if (mm != current->active_mm && atomic_read(&mm->mm_users) <= 1) return; /* * Check for potential race with hardware updates of the pte * (__ptep_set_access_flags safely changes valid ptes without going * through an invalid entry). */ VM_WARN_ONCE(!pte_young(pte), "%s: racy access flag clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(pte_write(old_pte) && !pte_dirty(pte), "%s: racy dirty state clearing: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); VM_WARN_ONCE(!pgattr_change_is_safe(pte_val(old_pte), pte_val(pte)), "%s: unsafe attribute change: 0x%016llx -> 0x%016llx", __func__, pte_val(old_pte), pte_val(pte)); } static inline void __sync_cache_and_tags(pte_t pte, unsigned int nr_pages) { if (pte_present(pte) && pte_user_exec(pte) && !pte_special(pte)) __sync_icache_dcache(pte); /* * If the PTE would provide user space access to the tags associated * with it then ensure that the MTE tags are synchronised. Although * pte_access_permitted() returns false for exec only mappings, they * don't expose tags (instruction fetches don't check tags). */ if (system_supports_mte() && pte_access_permitted(pte, false) && !pte_special(pte) && pte_tagged(pte)) mte_sync_tags(pte, nr_pages); } /* * Select all bits except the pfn */ static inline pgprot_t pte_pgprot(pte_t pte) { unsigned long pfn = pte_pfn(pte); return __pgprot(pte_val(pfn_pte(pfn, __pgprot(0))) ^ pte_val(pte)); } #define pte_advance_pfn pte_advance_pfn static inline pte_t pte_advance_pfn(pte_t pte, unsigned long nr) { return pfn_pte(pte_pfn(pte) + nr, pte_pgprot(pte)); } static inline void __set_ptes(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { page_table_check_ptes_set(mm, ptep, pte, nr); __sync_cache_and_tags(pte, nr); for (;;) { __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); if (--nr == 0) break; ptep++; pte = pte_advance_pfn(pte, 1); } } /* * Huge pte definitions. */ #define pte_mkhuge(pte) (__pte(pte_val(pte) & ~PTE_TABLE_BIT)) /* * Hugetlb definitions. */ #define HUGE_MAX_HSTATE 4 #define HPAGE_SHIFT PMD_SHIFT #define HPAGE_SIZE (_AC(1, UL) << HPAGE_SHIFT) #define HPAGE_MASK (~(HPAGE_SIZE - 1)) #define HUGETLB_PAGE_ORDER (HPAGE_SHIFT - PAGE_SHIFT) static inline pte_t pgd_pte(pgd_t pgd) { return __pte(pgd_val(pgd)); } static inline pte_t p4d_pte(p4d_t p4d) { return __pte(p4d_val(p4d)); } static inline pte_t pud_pte(pud_t pud) { return __pte(pud_val(pud)); } static inline pud_t pte_pud(pte_t pte) { return __pud(pte_val(pte)); } static inline pmd_t pud_pmd(pud_t pud) { return __pmd(pud_val(pud)); } static inline pte_t pmd_pte(pmd_t pmd) { return __pte(pmd_val(pmd)); } static inline pmd_t pte_pmd(pte_t pte) { return __pmd(pte_val(pte)); } static inline pgprot_t mk_pud_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PUD_TABLE_BIT) | PUD_TYPE_SECT); } static inline pgprot_t mk_pmd_sect_prot(pgprot_t prot) { return __pgprot((pgprot_val(prot) & ~PMD_TABLE_BIT) | PMD_TYPE_SECT); } static inline pte_t pte_swp_mkexclusive(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } static inline int pte_swp_exclusive(pte_t pte) { return pte_val(pte) & PTE_SWP_EXCLUSIVE; } static inline pte_t pte_swp_clear_exclusive(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_EXCLUSIVE)); } #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP static inline pte_t pte_swp_mkuffd_wp(pte_t pte) { return set_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } static inline int pte_swp_uffd_wp(pte_t pte) { return !!(pte_val(pte) & PTE_SWP_UFFD_WP); } static inline pte_t pte_swp_clear_uffd_wp(pte_t pte) { return clear_pte_bit(pte, __pgprot(PTE_SWP_UFFD_WP)); } #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #ifdef CONFIG_NUMA_BALANCING /* * See the comment in include/linux/pgtable.h */ static inline int pte_protnone(pte_t pte) { /* * pte_present_invalid() tells us that the pte is invalid from HW * perspective but present from SW perspective, so the fields are to be * interpretted as per the HW layout. The second 2 checks are the unique * encoding that we use for PROT_NONE. It is insufficient to only use * the first check because we share the same encoding scheme with pmds * which support pmd_mkinvalid(), so can be present-invalid without * being PROT_NONE. */ return pte_present_invalid(pte) && !pte_user(pte) && !pte_user_exec(pte); } static inline int pmd_protnone(pmd_t pmd) { return pte_protnone(pmd_pte(pmd)); } #endif #define pmd_present(pmd) pte_present(pmd_pte(pmd)) /* * THP definitions. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline int pmd_trans_huge(pmd_t pmd) { return pmd_val(pmd) && pmd_present(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ #define pmd_dirty(pmd) pte_dirty(pmd_pte(pmd)) #define pmd_young(pmd) pte_young(pmd_pte(pmd)) #define pmd_valid(pmd) pte_valid(pmd_pte(pmd)) #define pmd_user(pmd) pte_user(pmd_pte(pmd)) #define pmd_user_exec(pmd) pte_user_exec(pmd_pte(pmd)) #define pmd_cont(pmd) pte_cont(pmd_pte(pmd)) #define pmd_wrprotect(pmd) pte_pmd(pte_wrprotect(pmd_pte(pmd))) #define pmd_mkold(pmd) pte_pmd(pte_mkold(pmd_pte(pmd))) #define pmd_mkwrite_novma(pmd) pte_pmd(pte_mkwrite_novma(pmd_pte(pmd))) #define pmd_mkclean(pmd) pte_pmd(pte_mkclean(pmd_pte(pmd))) #define pmd_mkdirty(pmd) pte_pmd(pte_mkdirty(pmd_pte(pmd))) #define pmd_mkyoung(pmd) pte_pmd(pte_mkyoung(pmd_pte(pmd))) #define pmd_mkinvalid(pmd) pte_pmd(pte_mkinvalid(pmd_pte(pmd))) #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP #define pmd_uffd_wp(pmd) pte_uffd_wp(pmd_pte(pmd)) #define pmd_mkuffd_wp(pmd) pte_pmd(pte_mkuffd_wp(pmd_pte(pmd))) #define pmd_clear_uffd_wp(pmd) pte_pmd(pte_clear_uffd_wp(pmd_pte(pmd))) #define pmd_swp_uffd_wp(pmd) pte_swp_uffd_wp(pmd_pte(pmd)) #define pmd_swp_mkuffd_wp(pmd) pte_pmd(pte_swp_mkuffd_wp(pmd_pte(pmd))) #define pmd_swp_clear_uffd_wp(pmd) \ pte_pmd(pte_swp_clear_uffd_wp(pmd_pte(pmd))) #endif /* CONFIG_HAVE_ARCH_USERFAULTFD_WP */ #define pmd_write(pmd) pte_write(pmd_pte(pmd)) #define pmd_mkhuge(pmd) (__pmd(pmd_val(pmd) & ~PMD_TABLE_BIT)) #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define pmd_devmap(pmd) pte_devmap(pmd_pte(pmd)) #endif static inline pmd_t pmd_mkdevmap(pmd_t pmd) { return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP))); } #define __pmd_to_phys(pmd) __pte_to_phys(pmd_pte(pmd)) #define __phys_to_pmd_val(phys) __phys_to_pte_val(phys) #define pmd_pfn(pmd) ((__pmd_to_phys(pmd) & PMD_MASK) >> PAGE_SHIFT) #define pfn_pmd(pfn,prot) __pmd(__phys_to_pmd_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) #define mk_pmd(page,prot) pfn_pmd(page_to_pfn(page),prot) #define pud_young(pud) pte_young(pud_pte(pud)) #define pud_mkyoung(pud) pte_pud(pte_mkyoung(pud_pte(pud))) #define pud_write(pud) pte_write(pud_pte(pud)) #define pud_mkhuge(pud) (__pud(pud_val(pud) & ~PUD_TABLE_BIT)) #define __pud_to_phys(pud) __pte_to_phys(pud_pte(pud)) #define __phys_to_pud_val(phys) __phys_to_pte_val(phys) #define pud_pfn(pud) ((__pud_to_phys(pud) & PUD_MASK) >> PAGE_SHIFT) #define pfn_pud(pfn,prot) __pud(__phys_to_pud_val((phys_addr_t)(pfn) << PAGE_SHIFT) | pgprot_val(prot)) static inline void __set_pte_at(struct mm_struct *mm, unsigned long __always_unused addr, pte_t *ptep, pte_t pte, unsigned int nr) { __sync_cache_and_tags(pte, nr); __check_safe_pte_update(mm, ptep, pte); __set_pte(ptep, pte); } static inline void set_pmd_at(struct mm_struct *mm, unsigned long addr, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(mm, pmdp, pmd); return __set_pte_at(mm, addr, (pte_t *)pmdp, pmd_pte(pmd), PMD_SIZE >> PAGE_SHIFT); } static inline void set_pud_at(struct mm_struct *mm, unsigned long addr, pud_t *pudp, pud_t pud) { page_table_check_pud_set(mm, pudp, pud); return __set_pte_at(mm, addr, (pte_t *)pudp, pud_pte(pud), PUD_SIZE >> PAGE_SHIFT); } #define __p4d_to_phys(p4d) __pte_to_phys(p4d_pte(p4d)) #define __phys_to_p4d_val(phys) __phys_to_pte_val(phys) #define __pgd_to_phys(pgd) __pte_to_phys(pgd_pte(pgd)) #define __phys_to_pgd_val(phys) __phys_to_pte_val(phys) #define __pgprot_modify(prot,mask,bits) \ __pgprot((pgprot_val(prot) & ~(mask)) | (bits)) #define pgprot_nx(prot) \ __pgprot_modify(prot, PTE_MAYBE_GP, PTE_PXN) /* * Mark the prot value as uncacheable and unbufferable. */ #define pgprot_noncached(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRnE) | PTE_PXN | PTE_UXN) #define pgprot_writecombine(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define pgprot_device(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_DEVICE_nGnRE) | PTE_PXN | PTE_UXN) #define pgprot_tagged(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, PTE_ATTRINDX(MT_NORMAL_TAGGED)) #define pgprot_mhp pgprot_tagged /* * DMA allocations for non-coherent devices use what the Arm architecture calls * "Normal non-cacheable" memory, which permits speculation, unaligned accesses * and merging of writes. This is different from "Device-nGnR[nE]" memory which * is intended for MMIO and thus forbids speculation, preserves access size, * requires strict alignment and can also force write responses to come from the * endpoint. */ #define pgprot_dmacoherent(prot) \ __pgprot_modify(prot, PTE_ATTRINDX_MASK, \ PTE_ATTRINDX(MT_NORMAL_NC) | PTE_PXN | PTE_UXN) #define __HAVE_PHYS_MEM_ACCESS_PROT struct file; extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot); #define pmd_none(pmd) (!pmd_val(pmd)) #define pmd_table(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_TABLE) #define pmd_sect(pmd) ((pmd_val(pmd) & PMD_TYPE_MASK) == \ PMD_TYPE_SECT) #define pmd_leaf(pmd) (pmd_present(pmd) && !pmd_table(pmd)) #define pmd_bad(pmd) (!pmd_table(pmd)) #define pmd_leaf_size(pmd) (pmd_cont(pmd) ? CONT_PMD_SIZE : PMD_SIZE) #define pte_leaf_size(pte) (pte_cont(pte) ? CONT_PTE_SIZE : PAGE_SIZE) #if defined(CONFIG_ARM64_64K_PAGES) || CONFIG_PGTABLE_LEVELS < 3 static inline bool pud_sect(pud_t pud) { return false; } static inline bool pud_table(pud_t pud) { return true; } #else #define pud_sect(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_SECT) #define pud_table(pud) ((pud_val(pud) & PUD_TYPE_MASK) == \ PUD_TYPE_TABLE) #endif extern pgd_t init_pg_dir[]; extern pgd_t init_pg_end[]; extern pgd_t swapper_pg_dir[]; extern pgd_t idmap_pg_dir[]; extern pgd_t tramp_pg_dir[]; extern pgd_t reserved_pg_dir[]; extern void set_swapper_pgd(pgd_t *pgdp, pgd_t pgd); static inline bool in_swapper_pgdir(void *addr) { return ((unsigned long)addr & PAGE_MASK) == ((unsigned long)swapper_pg_dir & PAGE_MASK); } static inline void set_pmd(pmd_t *pmdp, pmd_t pmd) { #ifdef __PAGETABLE_PMD_FOLDED if (in_swapper_pgdir(pmdp)) { set_swapper_pgd((pgd_t *)pmdp, __pgd(pmd_val(pmd))); return; } #endif /* __PAGETABLE_PMD_FOLDED */ WRITE_ONCE(*pmdp, pmd); if (pmd_valid(pmd)) { dsb(ishst); isb(); } } static inline void pmd_clear(pmd_t *pmdp) { set_pmd(pmdp, __pmd(0)); } static inline phys_addr_t pmd_page_paddr(pmd_t pmd) { return __pmd_to_phys(pmd); } static inline unsigned long pmd_page_vaddr(pmd_t pmd) { return (unsigned long)__va(pmd_page_paddr(pmd)); } /* Find an entry in the third-level page table. */ #define pte_offset_phys(dir,addr) (pmd_page_paddr(READ_ONCE(*(dir))) + pte_index(addr) * sizeof(pte_t)) #define pte_set_fixmap(addr) ((pte_t *)set_fixmap_offset(FIX_PTE, addr)) #define pte_set_fixmap_offset(pmd, addr) pte_set_fixmap(pte_offset_phys(pmd, addr)) #define pte_clear_fixmap() clear_fixmap(FIX_PTE) #define pmd_page(pmd) phys_to_page(__pmd_to_phys(pmd)) /* use ONLY for statically allocated translation tables */ #define pte_offset_kimg(dir,addr) ((pte_t *)__phys_to_kimg(pte_offset_phys((dir), (addr)))) /* * Conversion functions: convert a page and protection to a page entry, * and a page entry and page directory to the page they refer to. */ #define mk_pte(page,prot) pfn_pte(page_to_pfn(page),prot) #if CONFIG_PGTABLE_LEVELS > 2 #define pmd_ERROR(e) \ pr_err("%s:%d: bad pmd %016llx.\n", __FILE__, __LINE__, pmd_val(e)) #define pud_none(pud) (!pud_val(pud)) #define pud_bad(pud) (!pud_table(pud)) #define pud_present(pud) pte_present(pud_pte(pud)) #ifndef __PAGETABLE_PMD_FOLDED #define pud_leaf(pud) (pud_present(pud) && !pud_table(pud)) #else #define pud_leaf(pud) false #endif #define pud_valid(pud) pte_valid(pud_pte(pud)) #define pud_user(pud) pte_user(pud_pte(pud)) #define pud_user_exec(pud) pte_user_exec(pud_pte(pud)) static inline bool pgtable_l4_enabled(void); static inline void set_pud(pud_t *pudp, pud_t pud) { if (!pgtable_l4_enabled() && in_swapper_pgdir(pudp)) { set_swapper_pgd((pgd_t *)pudp, __pgd(pud_val(pud))); return; } WRITE_ONCE(*pudp, pud); if (pud_valid(pud)) { dsb(ishst); isb(); } } static inline void pud_clear(pud_t *pudp) { set_pud(pudp, __pud(0)); } static inline phys_addr_t pud_page_paddr(pud_t pud) { return __pud_to_phys(pud); } static inline pmd_t *pud_pgtable(pud_t pud) { return (pmd_t *)__va(pud_page_paddr(pud)); } /* Find an entry in the second-level page table. */ #define pmd_offset_phys(dir, addr) (pud_page_paddr(READ_ONCE(*(dir))) + pmd_index(addr) * sizeof(pmd_t)) #define pmd_set_fixmap(addr) ((pmd_t *)set_fixmap_offset(FIX_PMD, addr)) #define pmd_set_fixmap_offset(pud, addr) pmd_set_fixmap(pmd_offset_phys(pud, addr)) #define pmd_clear_fixmap() clear_fixmap(FIX_PMD) #define pud_page(pud) phys_to_page(__pud_to_phys(pud)) /* use ONLY for statically allocated translation tables */ #define pmd_offset_kimg(dir,addr) ((pmd_t *)__phys_to_kimg(pmd_offset_phys((dir), (addr)))) #else #define pud_valid(pud) false #define pud_page_paddr(pud) ({ BUILD_BUG(); 0; }) #define pud_user_exec(pud) pud_user(pud) /* Always 0 with folding */ /* Match pmd_offset folding in <asm/generic/pgtable-nopmd.h> */ #define pmd_set_fixmap(addr) NULL #define pmd_set_fixmap_offset(pudp, addr) ((pmd_t *)pudp) #define pmd_clear_fixmap() #define pmd_offset_kimg(dir,addr) ((pmd_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 2 */ #if CONFIG_PGTABLE_LEVELS > 3 static __always_inline bool pgtable_l4_enabled(void) { if (CONFIG_PGTABLE_LEVELS > 4 || !IS_ENABLED(CONFIG_ARM64_LPA2)) return true; if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_pud_folded(const struct mm_struct *mm) { return !pgtable_l4_enabled(); } #define mm_pud_folded mm_pud_folded #define pud_ERROR(e) \ pr_err("%s:%d: bad pud %016llx.\n", __FILE__, __LINE__, pud_val(e)) #define p4d_none(p4d) (pgtable_l4_enabled() && !p4d_val(p4d)) #define p4d_bad(p4d) (pgtable_l4_enabled() && !(p4d_val(p4d) & 2)) #define p4d_present(p4d) (!p4d_none(p4d)) static inline void set_p4d(p4d_t *p4dp, p4d_t p4d) { if (in_swapper_pgdir(p4dp)) { set_swapper_pgd((pgd_t *)p4dp, __pgd(p4d_val(p4d))); return; } WRITE_ONCE(*p4dp, p4d); dsb(ishst); isb(); } static inline void p4d_clear(p4d_t *p4dp) { if (pgtable_l4_enabled()) set_p4d(p4dp, __p4d(0)); } static inline phys_addr_t p4d_page_paddr(p4d_t p4d) { return __p4d_to_phys(p4d); } #define pud_index(addr) (((addr) >> PUD_SHIFT) & (PTRS_PER_PUD - 1)) static inline pud_t *p4d_to_folded_pud(p4d_t *p4dp, unsigned long addr) { return (pud_t *)PTR_ALIGN_DOWN(p4dp, PAGE_SIZE) + pud_index(addr); } static inline pud_t *p4d_pgtable(p4d_t p4d) { return (pud_t *)__va(p4d_page_paddr(p4d)); } static inline phys_addr_t pud_offset_phys(p4d_t *p4dp, unsigned long addr) { BUG_ON(!pgtable_l4_enabled()); return p4d_page_paddr(READ_ONCE(*p4dp)) + pud_index(addr) * sizeof(pud_t); } static inline pud_t *pud_offset_lockless(p4d_t *p4dp, p4d_t p4d, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__va(p4d_page_paddr(p4d)) + pud_index(addr); } #define pud_offset_lockless pud_offset_lockless static inline pud_t *pud_offset(p4d_t *p4dp, unsigned long addr) { return pud_offset_lockless(p4dp, READ_ONCE(*p4dp), addr); } #define pud_offset pud_offset static inline pud_t *pud_set_fixmap(unsigned long addr) { if (!pgtable_l4_enabled()) return NULL; return (pud_t *)set_fixmap_offset(FIX_PUD, addr); } static inline pud_t *pud_set_fixmap_offset(p4d_t *p4dp, unsigned long addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return pud_set_fixmap(pud_offset_phys(p4dp, addr)); } static inline void pud_clear_fixmap(void) { if (pgtable_l4_enabled()) clear_fixmap(FIX_PUD); } /* use ONLY for statically allocated translation tables */ static inline pud_t *pud_offset_kimg(p4d_t *p4dp, u64 addr) { if (!pgtable_l4_enabled()) return p4d_to_folded_pud(p4dp, addr); return (pud_t *)__phys_to_kimg(pud_offset_phys(p4dp, addr)); } #define p4d_page(p4d) pfn_to_page(__phys_to_pfn(__p4d_to_phys(p4d))) #else static inline bool pgtable_l4_enabled(void) { return false; } #define p4d_page_paddr(p4d) ({ BUILD_BUG(); 0;}) /* Match pud_offset folding in <asm/generic/pgtable-nopud.h> */ #define pud_set_fixmap(addr) NULL #define pud_set_fixmap_offset(pgdp, addr) ((pud_t *)pgdp) #define pud_clear_fixmap() #define pud_offset_kimg(dir,addr) ((pud_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #if CONFIG_PGTABLE_LEVELS > 4 static __always_inline bool pgtable_l5_enabled(void) { if (!alternative_has_cap_likely(ARM64_ALWAYS_BOOT)) return vabits_actual == VA_BITS; return alternative_has_cap_unlikely(ARM64_HAS_VA52); } static inline bool mm_p4d_folded(const struct mm_struct *mm) { return !pgtable_l5_enabled(); } #define mm_p4d_folded mm_p4d_folded #define p4d_ERROR(e) \ pr_err("%s:%d: bad p4d %016llx.\n", __FILE__, __LINE__, p4d_val(e)) #define pgd_none(pgd) (pgtable_l5_enabled() && !pgd_val(pgd)) #define pgd_bad(pgd) (pgtable_l5_enabled() && !(pgd_val(pgd) & 2)) #define pgd_present(pgd) (!pgd_none(pgd)) static inline void set_pgd(pgd_t *pgdp, pgd_t pgd) { if (in_swapper_pgdir(pgdp)) { set_swapper_pgd(pgdp, __pgd(pgd_val(pgd))); return; } WRITE_ONCE(*pgdp, pgd); dsb(ishst); isb(); } static inline void pgd_clear(pgd_t *pgdp) { if (pgtable_l5_enabled()) set_pgd(pgdp, __pgd(0)); } static inline phys_addr_t pgd_page_paddr(pgd_t pgd) { return __pgd_to_phys(pgd); } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) static inline p4d_t *pgd_to_folded_p4d(pgd_t *pgdp, unsigned long addr) { return (p4d_t *)PTR_ALIGN_DOWN(pgdp, PAGE_SIZE) + p4d_index(addr); } static inline phys_addr_t p4d_offset_phys(pgd_t *pgdp, unsigned long addr) { BUG_ON(!pgtable_l5_enabled()); return pgd_page_paddr(READ_ONCE(*pgdp)) + p4d_index(addr) * sizeof(p4d_t); } static inline p4d_t *p4d_offset_lockless(pgd_t *pgdp, pgd_t pgd, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__va(pgd_page_paddr(pgd)) + p4d_index(addr); } #define p4d_offset_lockless p4d_offset_lockless static inline p4d_t *p4d_offset(pgd_t *pgdp, unsigned long addr) { return p4d_offset_lockless(pgdp, READ_ONCE(*pgdp), addr); } static inline p4d_t *p4d_set_fixmap(unsigned long addr) { if (!pgtable_l5_enabled()) return NULL; return (p4d_t *)set_fixmap_offset(FIX_P4D, addr); } static inline p4d_t *p4d_set_fixmap_offset(pgd_t *pgdp, unsigned long addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return p4d_set_fixmap(p4d_offset_phys(pgdp, addr)); } static inline void p4d_clear_fixmap(void) { if (pgtable_l5_enabled()) clear_fixmap(FIX_P4D); } /* use ONLY for statically allocated translation tables */ static inline p4d_t *p4d_offset_kimg(pgd_t *pgdp, u64 addr) { if (!pgtable_l5_enabled()) return pgd_to_folded_p4d(pgdp, addr); return (p4d_t *)__phys_to_kimg(p4d_offset_phys(pgdp, addr)); } #define pgd_page(pgd) pfn_to_page(__phys_to_pfn(__pgd_to_phys(pgd))) #else static inline bool pgtable_l5_enabled(void) { return false; } #define p4d_index(addr) (((addr) >> P4D_SHIFT) & (PTRS_PER_P4D - 1)) /* Match p4d_offset folding in <asm/generic/pgtable-nop4d.h> */ #define p4d_set_fixmap(addr) NULL #define p4d_set_fixmap_offset(p4dp, addr) ((p4d_t *)p4dp) #define p4d_clear_fixmap() #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir) #endif /* CONFIG_PGTABLE_LEVELS > 4 */ #define pgd_ERROR(e) \ pr_err("%s:%d: bad pgd %016llx.\n", __FILE__, __LINE__, pgd_val(e)) #define pgd_set_fixmap(addr) ((pgd_t *)set_fixmap_offset(FIX_PGD, addr)) #define pgd_clear_fixmap() clear_fixmap(FIX_PGD) static inline pte_t pte_modify(pte_t pte, pgprot_t newprot) { /* * Normal and Normal-Tagged are two different memory types and indices * in MAIR_EL1. The mask below has to include PTE_ATTRINDX_MASK. */ const pteval_t mask = PTE_USER | PTE_PXN | PTE_UXN | PTE_RDONLY | PTE_PRESENT_INVALID | PTE_VALID | PTE_WRITE | PTE_GP | PTE_ATTRINDX_MASK; /* preserve the hardware dirty information */ if (pte_hw_dirty(pte)) pte = set_pte_bit(pte, __pgprot(PTE_DIRTY)); pte_val(pte) = (pte_val(pte) & ~mask) | (pgprot_val(newprot) & mask); /* * If we end up clearing hw dirtiness for a sw-dirty PTE, set hardware * dirtiness again. */ if (pte_sw_dirty(pte)) pte = pte_mkdirty(pte); return pte; } static inline pmd_t pmd_modify(pmd_t pmd, pgprot_t newprot) { return pte_pmd(pte_modify(pmd_pte(pmd), newprot)); } extern int __ptep_set_access_flags(struct vm_area_struct *vma, unsigned long address, pte_t *ptep, pte_t entry, int dirty); #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_ACCESS_FLAGS static inline int pmdp_set_access_flags(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t entry, int dirty) { return __ptep_set_access_flags(vma, address, (pte_t *)pmdp, pmd_pte(entry), dirty); } static inline int pud_devmap(pud_t pud) { return 0; } static inline int pgd_devmap(pgd_t pgd) { return 0; } #endif #ifdef CONFIG_PAGE_TABLE_CHECK static inline bool pte_user_accessible_page(pte_t pte) { return pte_valid(pte) && (pte_user(pte) || pte_user_exec(pte)); } static inline bool pmd_user_accessible_page(pmd_t pmd) { return pmd_valid(pmd) && !pmd_table(pmd) && (pmd_user(pmd) || pmd_user_exec(pmd)); } static inline bool pud_user_accessible_page(pud_t pud) { return pud_valid(pud) && !pud_table(pud) && (pud_user(pud) || pud_user_exec(pud)); } #endif /* * Atomic pte/pmd modifications. */ static inline int __ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { pte_t old_pte, pte; pte = __ptep_get(ptep); do { old_pte = pte; pte = pte_mkold(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); return pte_young(pte); } static inline int __ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pte_t *ptep) { int young = __ptep_test_and_clear_young(vma, address, ptep); if (young) { /* * We can elide the trailing DSB here since the worst that can * happen is that a CPU continues to use the young entry in its * TLB and we mistakenly reclaim the associated page. The * window for such an event is bounded by the next * context-switch, which provides a DSB to complete the TLB * invalidation. */ flush_tlb_page_nosync(vma, address); } return young; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_TEST_AND_CLEAR_YOUNG static inline int pmdp_test_and_clear_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { return __ptep_test_and_clear_young(vma, address, (pte_t *)pmdp); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline pte_t __ptep_get_and_clear(struct mm_struct *mm, unsigned long address, pte_t *ptep) { pte_t pte = __pte(xchg_relaxed(&pte_val(*ptep), 0)); page_table_check_pte_clear(mm, pte); return pte; } static inline void __clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { for (;;) { __ptep_get_and_clear(mm, addr, ptep); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } static inline pte_t __get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte, tmp_pte; pte = __ptep_get_and_clear(mm, addr, ptep); while (--nr) { ptep++; addr += PAGE_SIZE; tmp_pte = __ptep_get_and_clear(mm, addr, ptep); if (pte_dirty(tmp_pte)) pte = pte_mkdirty(pte); if (pte_young(tmp_pte)) pte = pte_mkyoung(pte); } return pte; } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_HUGE_GET_AND_CLEAR static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { pmd_t pmd = __pmd(xchg_relaxed(&pmd_val(*pmdp), 0)); page_table_check_pmd_clear(mm, pmd); return pmd; } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ static inline void ___ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep, pte_t pte) { pte_t old_pte; do { old_pte = pte; pte = pte_wrprotect(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } /* * __ptep_set_wrprotect - mark read-only while trasferring potential hardware * dirty status (PTE_DBM && !PTE_RDONLY) to the software PTE_DIRTY bit. */ static inline void __ptep_set_wrprotect(struct mm_struct *mm, unsigned long address, pte_t *ptep) { ___ptep_set_wrprotect(mm, address, ptep, __ptep_get(ptep)); } static inline void __wrprotect_ptes(struct mm_struct *mm, unsigned long address, pte_t *ptep, unsigned int nr) { unsigned int i; for (i = 0; i < nr; i++, address += PAGE_SIZE, ptep++) __ptep_set_wrprotect(mm, address, ptep); } static inline void __clear_young_dirty_pte(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, cydp_t flags) { pte_t old_pte; do { old_pte = pte; if (flags & CYDP_CLEAR_YOUNG) pte = pte_mkold(pte); if (flags & CYDP_CLEAR_DIRTY) pte = pte_mkclean(pte); pte_val(pte) = cmpxchg_relaxed(&pte_val(*ptep), pte_val(old_pte), pte_val(pte)); } while (pte_val(pte) != pte_val(old_pte)); } static inline void __clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { pte_t pte; for (;;) { pte = __ptep_get(ptep); if (flags == (CYDP_CLEAR_YOUNG | CYDP_CLEAR_DIRTY)) __set_pte(ptep, pte_mkclean(pte_mkold(pte))); else __clear_young_dirty_pte(vma, addr, ptep, pte, flags); if (--nr == 0) break; ptep++; addr += PAGE_SIZE; } } #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define __HAVE_ARCH_PMDP_SET_WRPROTECT static inline void pmdp_set_wrprotect(struct mm_struct *mm, unsigned long address, pmd_t *pmdp) { __ptep_set_wrprotect(mm, address, (pte_t *)pmdp); } #define pmdp_establish pmdp_establish static inline pmd_t pmdp_establish(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp, pmd_t pmd) { page_table_check_pmd_set(vma->vm_mm, pmdp, pmd); return __pmd(xchg_relaxed(&pmd_val(*pmdp), pmd_val(pmd))); } #endif /* * Encode and decode a swap entry: * bits 0-1: present (must be zero) * bits 2: remember PG_anon_exclusive * bit 3: remember uffd-wp state * bits 6-10: swap type * bit 11: PTE_PRESENT_INVALID (must be zero) * bits 12-61: swap offset */ #define __SWP_TYPE_SHIFT 6 #define __SWP_TYPE_BITS 5 #define __SWP_TYPE_MASK ((1 << __SWP_TYPE_BITS) - 1) #define __SWP_OFFSET_SHIFT 12 #define __SWP_OFFSET_BITS 50 #define __SWP_OFFSET_MASK ((1UL << __SWP_OFFSET_BITS) - 1) #define __swp_type(x) (((x).val >> __SWP_TYPE_SHIFT) & __SWP_TYPE_MASK) #define __swp_offset(x) (((x).val >> __SWP_OFFSET_SHIFT) & __SWP_OFFSET_MASK) #define __swp_entry(type,offset) ((swp_entry_t) { ((type) << __SWP_TYPE_SHIFT) | ((offset) << __SWP_OFFSET_SHIFT) }) #define __pte_to_swp_entry(pte) ((swp_entry_t) { pte_val(pte) }) #define __swp_entry_to_pte(swp) ((pte_t) { (swp).val }) #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION #define __pmd_to_swp_entry(pmd) ((swp_entry_t) { pmd_val(pmd) }) #define __swp_entry_to_pmd(swp) __pmd((swp).val) #endif /* CONFIG_ARCH_ENABLE_THP_MIGRATION */ /* * Ensure that there are not more swap files than can be encoded in the kernel * PTEs. */ #define MAX_SWAPFILES_CHECK() BUILD_BUG_ON(MAX_SWAPFILES_SHIFT > __SWP_TYPE_BITS) #ifdef CONFIG_ARM64_MTE #define __HAVE_ARCH_PREPARE_TO_SWAP extern int arch_prepare_to_swap(struct folio *folio); #define __HAVE_ARCH_SWAP_INVALIDATE static inline void arch_swap_invalidate_page(int type, pgoff_t offset) { if (system_supports_mte()) mte_invalidate_tags(type, offset); } static inline void arch_swap_invalidate_area(int type) { if (system_supports_mte()) mte_invalidate_tags_area(type); } #define __HAVE_ARCH_SWAP_RESTORE extern void arch_swap_restore(swp_entry_t entry, struct folio *folio); #endif /* CONFIG_ARM64_MTE */ /* * On AArch64, the cache coherency is handled via the __set_ptes() function. */ static inline void update_mmu_cache_range(struct vm_fault *vmf, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr) { /* * We don't do anything here, so there's a very small chance of * us retaking a user fault which we just fixed up. The alternative * is doing a dsb(ishst), but that penalises the fastpath. */ } #define update_mmu_cache(vma, addr, ptep) \ update_mmu_cache_range(NULL, vma, addr, ptep, 1) #define update_mmu_cache_pmd(vma, address, pmd) do { } while (0) #ifdef CONFIG_ARM64_PA_BITS_52 #define phys_to_ttbr(addr) (((addr) | ((addr) >> 46)) & TTBR_BADDR_MASK_52) #else #define phys_to_ttbr(addr) (addr) #endif /* * On arm64 without hardware Access Flag, copying from user will fail because * the pte is old and cannot be marked young. So we always end up with zeroed * page after fork() + CoW for pfn mappings. We don't always have a * hardware-managed access flag on arm64. */ #define arch_has_hw_pte_young cpu_has_hw_af /* * Experimentally, it's cheap to set the access flag in hardware and we * benefit from prefaulting mappings as 'old' to start with. */ #define arch_wants_old_prefaulted_pte cpu_has_hw_af static inline bool pud_sect_supported(void) { return PAGE_SIZE == SZ_4K; } #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION #define ptep_modify_prot_start ptep_modify_prot_start extern pte_t ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); #define ptep_modify_prot_commit ptep_modify_prot_commit extern void ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t new_pte); #ifdef CONFIG_ARM64_CONTPTE /* * The contpte APIs are used to transparently manage the contiguous bit in ptes * where it is possible and makes sense to do so. The PTE_CONT bit is considered * a private implementation detail of the public ptep API (see below). */ extern void __contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern void __contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte); extern pte_t contpte_ptep_get(pte_t *ptep, pte_t orig_pte); extern pte_t contpte_ptep_get_lockless(pte_t *orig_ptep); extern void contpte_set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr); extern void contpte_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern pte_t contpte_get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full); extern int contpte_ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern int contpte_ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); extern void contpte_wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr); extern int contpte_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty); extern void contpte_clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags); static __always_inline void contpte_try_fold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { /* * Only bother trying if both the virtual and physical addresses are * aligned and correspond to the last entry in a contig range. The core * code mostly modifies ranges from low to high, so this is the likely * the last modification in the contig range, so a good time to fold. * We can't fold special mappings, because there is no associated folio. */ const unsigned long contmask = CONT_PTES - 1; bool valign = ((addr >> PAGE_SHIFT) & contmask) == contmask; if (unlikely(valign)) { bool palign = (pte_pfn(pte) & contmask) == contmask; if (unlikely(palign && pte_valid(pte) && !pte_cont(pte) && !pte_special(pte))) __contpte_try_fold(mm, addr, ptep, pte); } } static __always_inline void contpte_try_unfold(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte) { if (unlikely(pte_valid_cont(pte))) __contpte_try_unfold(mm, addr, ptep, pte); } #define pte_batch_hint pte_batch_hint static inline unsigned int pte_batch_hint(pte_t *ptep, pte_t pte) { if (!pte_valid_cont(pte)) return 1; return CONT_PTES - (((unsigned long)ptep >> 3) & (CONT_PTES - 1)); } /* * The below functions constitute the public API that arm64 presents to the * core-mm to manipulate PTE entries within their page tables (or at least this * is the subset of the API that arm64 needs to implement). These public * versions will automatically and transparently apply the contiguous bit where * it makes sense to do so. Therefore any users that are contig-aware (e.g. * hugetlb, kernel mapper) should NOT use these APIs, but instead use the * private versions, which are prefixed with double underscore. All of these * APIs except for ptep_get_lockless() are expected to be called with the PTL * held. Although the contiguous bit is considered private to the * implementation, it is deliberately allowed to leak through the getters (e.g. * ptep_get()), back to core code. This is required so that pte_leaf_size() can * provide an accurate size for perf_get_pgtable_size(). But this leakage means * its possible a pte will be passed to a setter with the contiguous bit set, so * we explicitly clear the contiguous bit in those cases to prevent accidentally * setting it in the pgtable. */ #define ptep_get ptep_get static inline pte_t ptep_get(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get(ptep, pte); } #define ptep_get_lockless ptep_get_lockless static inline pte_t ptep_get_lockless(pte_t *ptep) { pte_t pte = __ptep_get(ptep); if (likely(!pte_valid_cont(pte))) return pte; return contpte_ptep_get_lockless(ptep); } static inline void set_pte(pte_t *ptep, pte_t pte) { /* * We don't have the mm or vaddr so cannot unfold contig entries (since * it requires tlb maintenance). set_pte() is not used in core code, so * this should never even be called. Regardless do our best to service * any call and emit a warning if there is any attempt to set a pte on * top of an existing contig range. */ pte_t orig_pte = __ptep_get(ptep); WARN_ON_ONCE(pte_valid_cont(orig_pte)); __set_pte(ptep, pte_mknoncont(pte)); } #define set_ptes set_ptes static __always_inline void set_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned int nr) { pte = pte_mknoncont(pte); if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __set_ptes(mm, addr, ptep, pte, 1); contpte_try_fold(mm, addr, ptep, pte); } else { contpte_set_ptes(mm, addr, ptep, pte, nr); } } static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __pte_clear(mm, addr, ptep); } #define clear_full_ptes clear_full_ptes static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); __clear_full_ptes(mm, addr, ptep, nr, full); } else { contpte_clear_full_ptes(mm, addr, ptep, nr, full); } } #define get_and_clear_full_ptes get_and_clear_full_ptes static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr, int full) { pte_t pte; if (likely(nr == 1)) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); pte = __get_and_clear_full_ptes(mm, addr, ptep, nr, full); } else { pte = contpte_get_and_clear_full_ptes(mm, addr, ptep, nr, full); } return pte; } #define __HAVE_ARCH_PTEP_GET_AND_CLEAR static inline pte_t ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { contpte_try_unfold(mm, addr, ptep, __ptep_get(ptep)); return __ptep_get_and_clear(mm, addr, ptep); } #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG static inline int ptep_test_and_clear_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_test_and_clear_young(vma, addr, ptep); return contpte_ptep_test_and_clear_young(vma, addr, ptep); } #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH static inline int ptep_clear_flush_young(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { pte_t orig_pte = __ptep_get(ptep); if (likely(!pte_valid_cont(orig_pte))) return __ptep_clear_flush_young(vma, addr, ptep); return contpte_ptep_clear_flush_young(vma, addr, ptep); } #define wrprotect_ptes wrprotect_ptes static __always_inline void wrprotect_ptes(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned int nr) { if (likely(nr == 1)) { /* * Optimization: wrprotect_ptes() can only be called for present * ptes so we only need to check contig bit as condition for * unfold, and we can remove the contig bit from the pte we read * to avoid re-reading. This speeds up fork() which is sensitive * for order-0 folios. Equivalent to contpte_try_unfold(). */ pte_t orig_pte = __ptep_get(ptep); if (unlikely(pte_cont(orig_pte))) { __contpte_try_unfold(mm, addr, ptep, orig_pte); orig_pte = pte_mknoncont(orig_pte); } ___ptep_set_wrprotect(mm, addr, ptep, orig_pte); } else { contpte_wrprotect_ptes(mm, addr, ptep, nr); } } #define __HAVE_ARCH_PTEP_SET_WRPROTECT static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { wrprotect_ptes(mm, addr, ptep, 1); } #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS static inline int ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t entry, int dirty) { pte_t orig_pte = __ptep_get(ptep); entry = pte_mknoncont(entry); if (likely(!pte_valid_cont(orig_pte))) return __ptep_set_access_flags(vma, addr, ptep, entry, dirty); return contpte_ptep_set_access_flags(vma, addr, ptep, entry, dirty); } #define clear_young_dirty_ptes clear_young_dirty_ptes static inline void clear_young_dirty_ptes(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, unsigned int nr, cydp_t flags) { if (likely(nr == 1 && !pte_cont(__ptep_get(ptep)))) __clear_young_dirty_ptes(vma, addr, ptep, nr, flags); else contpte_clear_young_dirty_ptes(vma, addr, ptep, nr, flags); } #else /* CONFIG_ARM64_CONTPTE */ #define ptep_get __ptep_get #define set_pte __set_pte #define set_ptes __set_ptes #define pte_clear __pte_clear #define clear_full_ptes __clear_full_ptes #define get_and_clear_full_ptes __get_and_clear_full_ptes #define __HAVE_ARCH_PTEP_GET_AND_CLEAR #define ptep_get_and_clear __ptep_get_and_clear #define __HAVE_ARCH_PTEP_TEST_AND_CLEAR_YOUNG #define ptep_test_and_clear_young __ptep_test_and_clear_young #define __HAVE_ARCH_PTEP_CLEAR_YOUNG_FLUSH #define ptep_clear_flush_young __ptep_clear_flush_young #define __HAVE_ARCH_PTEP_SET_WRPROTECT #define ptep_set_wrprotect __ptep_set_wrprotect #define wrprotect_ptes __wrprotect_ptes #define __HAVE_ARCH_PTEP_SET_ACCESS_FLAGS #define ptep_set_access_flags __ptep_set_access_flags #define clear_young_dirty_ptes __clear_young_dirty_ptes #endif /* CONFIG_ARM64_CONTPTE */ #endif /* !__ASSEMBLY__ */ #endif /* __ASM_PGTABLE_H */ |
| 204 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | /* SPDX-License-Identifier: GPL-2.0+ */ /* * RCU-based infrastructure for lightweight reader-writer locking * * Copyright (c) 2015, Red Hat, Inc. * * Author: Oleg Nesterov <oleg@redhat.com> */ #ifndef _LINUX_RCU_SYNC_H_ #define _LINUX_RCU_SYNC_H_ #include <linux/wait.h> #include <linux/rcupdate.h> /* Structure to mediate between updaters and fastpath-using readers. */ struct rcu_sync { int gp_state; int gp_count; wait_queue_head_t gp_wait; struct rcu_head cb_head; }; /** * rcu_sync_is_idle() - Are readers permitted to use their fastpaths? * @rsp: Pointer to rcu_sync structure to use for synchronization * * Returns true if readers are permitted to use their fastpaths. Must be * invoked within some flavor of RCU read-side critical section. */ static inline bool rcu_sync_is_idle(struct rcu_sync *rsp) { RCU_LOCKDEP_WARN(!rcu_read_lock_any_held(), "suspicious rcu_sync_is_idle() usage"); return !READ_ONCE(rsp->gp_state); /* GP_IDLE */ } extern void rcu_sync_init(struct rcu_sync *); extern void rcu_sync_enter(struct rcu_sync *); extern void rcu_sync_exit(struct rcu_sync *); extern void rcu_sync_dtor(struct rcu_sync *); #define __RCU_SYNC_INITIALIZER(name) { \ .gp_state = 0, \ .gp_count = 0, \ .gp_wait = __WAIT_QUEUE_HEAD_INITIALIZER(name.gp_wait), \ } #define DEFINE_RCU_SYNC(name) \ struct rcu_sync name = __RCU_SYNC_INITIALIZER(name) #endif /* _LINUX_RCU_SYNC_H_ */ |
| 149 154 152 154 148 148 148 3 148 149 149 149 149 149 149 149 149 149 149 149 149 149 149 149 149 149 149 149 148 148 148 148 148 17 17 17 17 17 17 14 149 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 | // SPDX-License-Identifier: GPL-2.0 /* * inode.c - part of debugfs, a tiny little debug file system * * Copyright (C) 2004,2019 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Inc. * Copyright (C) 2019 Linux Foundation <gregkh@linuxfoundation.org> * * debugfs is for people to use instead of /proc or /sys. * See ./Documentation/core-api/kernel-api.rst for more details. */ #define pr_fmt(fmt) "debugfs: " fmt #include <linux/module.h> #include <linux/fs.h> #include <linux/fs_context.h> #include <linux/fs_parser.h> #include <linux/pagemap.h> #include <linux/init.h> #include <linux/kobject.h> #include <linux/namei.h> #include <linux/debugfs.h> #include <linux/fsnotify.h> #include <linux/string.h> #include <linux/seq_file.h> #include <linux/magic.h> #include <linux/slab.h> #include <linux/security.h> #include "internal.h" #define DEBUGFS_DEFAULT_MODE 0700 static struct vfsmount *debugfs_mount; static int debugfs_mount_count; static bool debugfs_registered; static unsigned int debugfs_allow __ro_after_init = DEFAULT_DEBUGFS_ALLOW_BITS; /* * Don't allow access attributes to be changed whilst the kernel is locked down * so that we can use the file mode as part of a heuristic to determine whether * to lock down individual files. */ static int debugfs_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *ia) { int ret; if (ia->ia_valid & (ATTR_MODE | ATTR_UID | ATTR_GID)) { ret = security_locked_down(LOCKDOWN_DEBUGFS); if (ret) return ret; } return simple_setattr(&nop_mnt_idmap, dentry, ia); } static const struct inode_operations debugfs_file_inode_operations = { .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_dir_inode_operations = { .lookup = simple_lookup, .setattr = debugfs_setattr, }; static const struct inode_operations debugfs_symlink_inode_operations = { .get_link = simple_get_link, .setattr = debugfs_setattr, }; static struct inode *debugfs_get_inode(struct super_block *sb) { struct inode *inode = new_inode(sb); if (inode) { inode->i_ino = get_next_ino(); simple_inode_init_ts(inode); } return inode; } struct debugfs_fs_info { kuid_t uid; kgid_t gid; umode_t mode; /* Opt_* bitfield. */ unsigned int opts; }; enum { Opt_uid, Opt_gid, Opt_mode, }; static const struct fs_parameter_spec debugfs_param_specs[] = { fsparam_u32 ("gid", Opt_gid), fsparam_u32oct ("mode", Opt_mode), fsparam_u32 ("uid", Opt_uid), {} }; static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param) { struct debugfs_fs_info *opts = fc->s_fs_info; struct fs_parse_result result; kuid_t uid; kgid_t gid; int opt; opt = fs_parse(fc, debugfs_param_specs, param, &result); if (opt < 0) { /* * We might like to report bad mount options here; but * traditionally debugfs has ignored all mount options */ if (opt == -ENOPARAM) return 0; return opt; } switch (opt) { case Opt_uid: uid = make_kuid(current_user_ns(), result.uint_32); if (!uid_valid(uid)) return invalf(fc, "Unknown uid"); opts->uid = uid; break; case Opt_gid: gid = make_kgid(current_user_ns(), result.uint_32); if (!gid_valid(gid)) return invalf(fc, "Unknown gid"); opts->gid = gid; break; case Opt_mode: opts->mode = result.uint_32 & S_IALLUGO; break; /* * We might like to report bad mount options here; * but traditionally debugfs has ignored all mount options */ } opts->opts |= BIT(opt); return 0; } static void _debugfs_apply_options(struct super_block *sb, bool remount) { struct debugfs_fs_info *fsi = sb->s_fs_info; struct inode *inode = d_inode(sb->s_root); /* * On remount, only reset mode/uid/gid if they were provided as mount * options. */ if (!remount || fsi->opts & BIT(Opt_mode)) { inode->i_mode &= ~S_IALLUGO; inode->i_mode |= fsi->mode; } if (!remount || fsi->opts & BIT(Opt_uid)) inode->i_uid = fsi->uid; if (!remount || fsi->opts & BIT(Opt_gid)) inode->i_gid = fsi->gid; } static void debugfs_apply_options(struct super_block *sb) { _debugfs_apply_options(sb, false); } static void debugfs_apply_options_remount(struct super_block *sb) { _debugfs_apply_options(sb, true); } static int debugfs_reconfigure(struct fs_context *fc) { struct super_block *sb = fc->root->d_sb; struct debugfs_fs_info *sb_opts = sb->s_fs_info; struct debugfs_fs_info *new_opts = fc->s_fs_info; sync_filesystem(sb); /* structure copy of new mount options to sb */ *sb_opts = *new_opts; debugfs_apply_options_remount(sb); return 0; } static int debugfs_show_options(struct seq_file *m, struct dentry *root) { struct debugfs_fs_info *fsi = root->d_sb->s_fs_info; if (!uid_eq(fsi->uid, GLOBAL_ROOT_UID)) seq_printf(m, ",uid=%u", from_kuid_munged(&init_user_ns, fsi->uid)); if (!gid_eq(fsi->gid, GLOBAL_ROOT_GID)) seq_printf(m, ",gid=%u", from_kgid_munged(&init_user_ns, fsi->gid)); if (fsi->mode != DEBUGFS_DEFAULT_MODE) seq_printf(m, ",mode=%o", fsi->mode); return 0; } static void debugfs_free_inode(struct inode *inode) { if (S_ISLNK(inode->i_mode)) kfree(inode->i_link); free_inode_nonrcu(inode); } static const struct super_operations debugfs_super_operations = { .statfs = simple_statfs, .show_options = debugfs_show_options, .free_inode = debugfs_free_inode, }; static void debugfs_release_dentry(struct dentry *dentry) { struct debugfs_fsdata *fsd = dentry->d_fsdata; if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) return; /* check it wasn't a dir (no fsdata) or automount (no real_fops) */ if (fsd && fsd->real_fops) { WARN_ON(!list_empty(&fsd->cancellations)); mutex_destroy(&fsd->cancellations_mtx); } kfree(fsd); } static struct vfsmount *debugfs_automount(struct path *path) { struct debugfs_fsdata *fsd = path->dentry->d_fsdata; return fsd->automount(path->dentry, d_inode(path->dentry)->i_private); } static const struct dentry_operations debugfs_dops = { .d_delete = always_delete_dentry, .d_release = debugfs_release_dentry, .d_automount = debugfs_automount, }; static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc) { static const struct tree_descr debug_files[] = {{""}}; int err; err = simple_fill_super(sb, DEBUGFS_MAGIC, debug_files); if (err) return err; sb->s_op = &debugfs_super_operations; sb->s_d_op = &debugfs_dops; debugfs_apply_options(sb); return 0; } static int debugfs_get_tree(struct fs_context *fc) { if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return -EPERM; return get_tree_single(fc, debugfs_fill_super); } static void debugfs_free_fc(struct fs_context *fc) { kfree(fc->s_fs_info); } static const struct fs_context_operations debugfs_context_ops = { .free = debugfs_free_fc, .parse_param = debugfs_parse_param, .get_tree = debugfs_get_tree, .reconfigure = debugfs_reconfigure, }; static int debugfs_init_fs_context(struct fs_context *fc) { struct debugfs_fs_info *fsi; fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL); if (!fsi) return -ENOMEM; fsi->mode = DEBUGFS_DEFAULT_MODE; fc->s_fs_info = fsi; fc->ops = &debugfs_context_ops; return 0; } static struct file_system_type debug_fs_type = { .owner = THIS_MODULE, .name = "debugfs", .init_fs_context = debugfs_init_fs_context, .parameters = debugfs_param_specs, .kill_sb = kill_litter_super, }; MODULE_ALIAS_FS("debugfs"); /** * debugfs_lookup() - look up an existing debugfs file * @name: a pointer to a string containing the name of the file to look up. * @parent: a pointer to the parent dentry of the file. * * This function will return a pointer to a dentry if it succeeds. If the file * doesn't exist or an error occurs, %NULL will be returned. The returned * dentry must be passed to dput() when it is no longer needed. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_lookup(const char *name, struct dentry *parent) { struct dentry *dentry; if (!debugfs_initialized() || IS_ERR_OR_NULL(name) || IS_ERR(parent)) return NULL; if (!parent) parent = debugfs_mount->mnt_root; dentry = lookup_positive_unlocked(name, parent, strlen(name)); if (IS_ERR(dentry)) return NULL; return dentry; } EXPORT_SYMBOL_GPL(debugfs_lookup); static struct dentry *start_creating(const char *name, struct dentry *parent) { struct dentry *dentry; int error; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) return ERR_PTR(-EPERM); if (!debugfs_initialized()) return ERR_PTR(-ENOENT); pr_debug("creating file '%s'\n", name); if (IS_ERR(parent)) return parent; error = simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); if (error) { pr_err("Unable to pin filesystem for file '%s'\n", name); return ERR_PTR(error); } /* If the parent is not specified, we create it in the root. * We need the root dentry to do this, which is in the super * block. A pointer to that is in the struct vfsmount that we * have around. */ if (!parent) parent = debugfs_mount->mnt_root; inode_lock(d_inode(parent)); if (unlikely(IS_DEADDIR(d_inode(parent)))) dentry = ERR_PTR(-ENOENT); else dentry = lookup_one_len(name, parent, strlen(name)); if (!IS_ERR(dentry) && d_really_is_positive(dentry)) { if (d_is_dir(dentry)) pr_err("Directory '%s' with parent '%s' already present!\n", name, parent->d_name.name); else pr_err("File '%s' in directory '%s' already present!\n", name, parent->d_name.name); dput(dentry); dentry = ERR_PTR(-EEXIST); } if (IS_ERR(dentry)) { inode_unlock(d_inode(parent)); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } return dentry; } static struct dentry *failed_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); dput(dentry); simple_release_fs(&debugfs_mount, &debugfs_mount_count); return ERR_PTR(-ENOMEM); } static struct dentry *end_creating(struct dentry *dentry) { inode_unlock(d_inode(dentry->d_parent)); return dentry; } static struct dentry *__debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *proxy_fops, const struct file_operations *real_fops) { struct dentry *dentry; struct inode *inode; if (!(mode & S_IFMT)) mode |= S_IFREG; BUG_ON(!S_ISREG(mode)); dentry = start_creating(name, parent); if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create file '%s'\n", name); return failed_creating(dentry); } inode->i_mode = mode; inode->i_private = data; inode->i_op = &debugfs_file_inode_operations; inode->i_fop = proxy_fops; dentry->d_fsdata = (void *)((unsigned long)real_fops | DEBUGFS_FSDATA_IS_REAL_FOPS_BIT); d_instantiate(dentry, inode); fsnotify_create(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } /** * debugfs_create_file - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_file(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, fops ? &debugfs_full_proxy_file_operations : &debugfs_noop_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file); /** * debugfs_create_file_unsafe - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * * debugfs_create_file_unsafe() is completely analogous to * debugfs_create_file(), the only difference being that the fops * handed it will not get protected against file removals by the * debugfs core. * * It is your responsibility to protect your struct file_operation * methods against file removals by means of debugfs_file_get() * and debugfs_file_put(). ->open() is still protected by * debugfs though. * * Any struct file_operations defined by means of * DEFINE_DEBUGFS_ATTRIBUTE() is protected against file removals and * thus, may be used here. */ struct dentry *debugfs_create_file_unsafe(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops) { return __debugfs_create_file(name, mode, parent, data, fops ? &debugfs_open_proxy_file_operations : &debugfs_noop_file_operations, fops); } EXPORT_SYMBOL_GPL(debugfs_create_file_unsafe); /** * debugfs_create_file_size - create a file in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @mode: the permission that the file should have. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @data: a pointer to something that the caller will want to get to later * on. The inode.i_private pointer will point to this value on * the open() call. * @fops: a pointer to a struct file_operations that should be used for * this file. * @file_size: initial file size * * This is the basic "create a file" function for debugfs. It allows for a * wide range of flexibility in creating a file, or a directory (if you want * to create a directory, the debugfs_create_dir() function is * recommended to be used instead.) */ void debugfs_create_file_size(const char *name, umode_t mode, struct dentry *parent, void *data, const struct file_operations *fops, loff_t file_size) { struct dentry *de = debugfs_create_file(name, mode, parent, data, fops); if (!IS_ERR(de)) d_inode(de)->i_size = file_size; } EXPORT_SYMBOL_GPL(debugfs_create_file_size); /** * debugfs_create_dir - create a directory in the debugfs filesystem * @name: a pointer to a string containing the name of the directory to * create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * directory will be created in the root of the debugfs filesystem. * * This function creates a directory in debugfs with the given name. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the file is * to be removed (no automatic cleanup happens if your module is unloaded, * you are responsible here.) If an error occurs, ERR_PTR(-ERROR) will be * returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. * * NOTE: it's expected that most callers should _ignore_ the errors returned * by this function. Other debugfs functions handle the fact that the "dentry" * passed to them could be an error and they don't crash in that case. * Drivers should generally work fine even if debugfs fails to init anyway. */ struct dentry *debugfs_create_dir(const char *name, struct dentry *parent) { struct dentry *dentry = start_creating(name, parent); struct inode *inode; if (IS_ERR(dentry)) return dentry; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create directory '%s'\n", name); return failed_creating(dentry); } inode->i_mode = S_IFDIR | S_IRWXU | S_IRUGO | S_IXUGO; inode->i_op = &debugfs_dir_inode_operations; inode->i_fop = &simple_dir_operations; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_dir); /** * debugfs_create_automount - create automount point in the debugfs filesystem * @name: a pointer to a string containing the name of the file to create. * @parent: a pointer to the parent dentry for this file. This should be a * directory dentry if set. If this parameter is NULL, then the * file will be created in the root of the debugfs filesystem. * @f: function to be called when pathname resolution steps on that one. * @data: opaque argument to pass to f(). * * @f should return what ->d_automount() would. */ struct dentry *debugfs_create_automount(const char *name, struct dentry *parent, debugfs_automount_t f, void *data) { struct dentry *dentry = start_creating(name, parent); struct debugfs_fsdata *fsd; struct inode *inode; if (IS_ERR(dentry)) return dentry; fsd = kzalloc(sizeof(*fsd), GFP_KERNEL); if (!fsd) { failed_creating(dentry); return ERR_PTR(-ENOMEM); } fsd->automount = f; if (!(debugfs_allow & DEBUGFS_ALLOW_API)) { failed_creating(dentry); kfree(fsd); return ERR_PTR(-EPERM); } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create automount '%s'\n", name); kfree(fsd); return failed_creating(dentry); } make_empty_dir_inode(inode); inode->i_flags |= S_AUTOMOUNT; inode->i_private = data; dentry->d_fsdata = fsd; /* directory inodes start off with i_nlink == 2 (for "." entry) */ inc_nlink(inode); d_instantiate(dentry, inode); inc_nlink(d_inode(dentry->d_parent)); fsnotify_mkdir(d_inode(dentry->d_parent), dentry); return end_creating(dentry); } EXPORT_SYMBOL(debugfs_create_automount); /** * debugfs_create_symlink- create a symbolic link in the debugfs filesystem * @name: a pointer to a string containing the name of the symbolic link to * create. * @parent: a pointer to the parent dentry for this symbolic link. This * should be a directory dentry if set. If this parameter is NULL, * then the symbolic link will be created in the root of the debugfs * filesystem. * @target: a pointer to a string containing the path to the target of the * symbolic link. * * This function creates a symbolic link with the given name in debugfs that * links to the given target path. * * This function will return a pointer to a dentry if it succeeds. This * pointer must be passed to the debugfs_remove() function when the symbolic * link is to be removed (no automatic cleanup happens if your module is * unloaded, you are responsible here.) If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_create_symlink(const char *name, struct dentry *parent, const char *target) { struct dentry *dentry; struct inode *inode; char *link = kstrdup(target, GFP_KERNEL); if (!link) return ERR_PTR(-ENOMEM); dentry = start_creating(name, parent); if (IS_ERR(dentry)) { kfree(link); return dentry; } inode = debugfs_get_inode(dentry->d_sb); if (unlikely(!inode)) { pr_err("out of free dentries, can not create symlink '%s'\n", name); kfree(link); return failed_creating(dentry); } inode->i_mode = S_IFLNK | S_IRWXUGO; inode->i_op = &debugfs_symlink_inode_operations; inode->i_link = link; d_instantiate(dentry, inode); return end_creating(dentry); } EXPORT_SYMBOL_GPL(debugfs_create_symlink); static void __debugfs_file_removed(struct dentry *dentry) { struct debugfs_fsdata *fsd; /* * Paired with the closing smp_mb() implied by a successful * cmpxchg() in debugfs_file_get(): either * debugfs_file_get() must see a dead dentry or we must see a * debugfs_fsdata instance at ->d_fsdata here (or both). */ smp_mb(); fsd = READ_ONCE(dentry->d_fsdata); if ((unsigned long)fsd & DEBUGFS_FSDATA_IS_REAL_FOPS_BIT) return; /* if this was the last reference, we're done */ if (refcount_dec_and_test(&fsd->active_users)) return; /* * If there's still a reference, the code that obtained it can * be in different states: * - The common case of not using cancellations, or already * after debugfs_leave_cancellation(), where we just need * to wait for debugfs_file_put() which signals the completion; * - inside a cancellation section, i.e. between * debugfs_enter_cancellation() and debugfs_leave_cancellation(), * in which case we need to trigger the ->cancel() function, * and then wait for debugfs_file_put() just like in the * previous case; * - before debugfs_enter_cancellation() (but obviously after * debugfs_file_get()), in which case we may not see the * cancellation in the list on the first round of the loop, * but debugfs_enter_cancellation() signals the completion * after adding it, so this code gets woken up to call the * ->cancel() function. */ while (refcount_read(&fsd->active_users)) { struct debugfs_cancellation *c; /* * Lock the cancellations. Note that the cancellations * structs are meant to be on the stack, so we need to * ensure we either use them here or don't touch them, * and debugfs_leave_cancellation() will wait for this * to be finished processing before exiting one. It may * of course win and remove the cancellation, but then * chances are we never even got into this bit, we only * do if the refcount isn't zero already. */ mutex_lock(&fsd->cancellations_mtx); while ((c = list_first_entry_or_null(&fsd->cancellations, typeof(*c), list))) { list_del_init(&c->list); c->cancel(dentry, c->cancel_data); } mutex_unlock(&fsd->cancellations_mtx); wait_for_completion(&fsd->active_users_drained); } } static void remove_one(struct dentry *victim) { if (d_is_reg(victim)) __debugfs_file_removed(victim); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } /** * debugfs_remove - recursively removes a directory * @dentry: a pointer to a the dentry of the directory to be removed. If this * parameter is NULL or an error value, nothing will be done. * * This function recursively removes a directory tree in debugfs that * was previously created with a call to another debugfs function * (like debugfs_create_file() or variants thereof.) * * This function is required to be called in order for the file to be * removed, no automatic cleanup of files will happen when a module is * removed, you are responsible here. */ void debugfs_remove(struct dentry *dentry) { if (IS_ERR_OR_NULL(dentry)) return; simple_pin_fs(&debug_fs_type, &debugfs_mount, &debugfs_mount_count); simple_recursive_removal(dentry, remove_one); simple_release_fs(&debugfs_mount, &debugfs_mount_count); } EXPORT_SYMBOL_GPL(debugfs_remove); /** * debugfs_lookup_and_remove - lookup a directory or file and recursively remove it * @name: a pointer to a string containing the name of the item to look up. * @parent: a pointer to the parent dentry of the item. * * This is the equlivant of doing something like * debugfs_remove(debugfs_lookup(..)) but with the proper reference counting * handled for the directory being looked up. */ void debugfs_lookup_and_remove(const char *name, struct dentry *parent) { struct dentry *dentry; dentry = debugfs_lookup(name, parent); if (!dentry) return; debugfs_remove(dentry); dput(dentry); } EXPORT_SYMBOL_GPL(debugfs_lookup_and_remove); /** * debugfs_rename - rename a file/directory in the debugfs filesystem * @old_dir: a pointer to the parent dentry for the renamed object. This * should be a directory dentry. * @old_dentry: dentry of an object to be renamed. * @new_dir: a pointer to the parent dentry where the object should be * moved. This should be a directory dentry. * @new_name: a pointer to a string containing the target name. * * This function renames a file/directory in debugfs. The target must not * exist for rename to succeed. * * This function will return a pointer to old_dentry (which is updated to * reflect renaming) if it succeeds. If an error occurs, ERR_PTR(-ERROR) * will be returned. * * If debugfs is not enabled in the kernel, the value -%ENODEV will be * returned. */ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry, struct dentry *new_dir, const char *new_name) { int error; struct dentry *dentry = NULL, *trap; struct name_snapshot old_name; if (IS_ERR(old_dir)) return old_dir; if (IS_ERR(new_dir)) return new_dir; if (IS_ERR_OR_NULL(old_dentry)) return old_dentry; trap = lock_rename(new_dir, old_dir); /* Source or destination directories don't exist? */ if (d_really_is_negative(old_dir) || d_really_is_negative(new_dir)) goto exit; /* Source does not exist, cyclic rename, or mountpoint? */ if (d_really_is_negative(old_dentry) || old_dentry == trap || d_mountpoint(old_dentry)) goto exit; dentry = lookup_one_len(new_name, new_dir, strlen(new_name)); /* Lookup failed, cyclic rename or target exists? */ if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry)) goto exit; take_dentry_name_snapshot(&old_name, old_dentry); error = simple_rename(&nop_mnt_idmap, d_inode(old_dir), old_dentry, d_inode(new_dir), dentry, 0); if (error) { release_dentry_name_snapshot(&old_name); goto exit; } d_move(old_dentry, dentry); fsnotify_move(d_inode(old_dir), d_inode(new_dir), &old_name.name, d_is_dir(old_dentry), NULL, old_dentry); release_dentry_name_snapshot(&old_name); unlock_rename(new_dir, old_dir); dput(dentry); return old_dentry; exit: if (dentry && !IS_ERR(dentry)) dput(dentry); unlock_rename(new_dir, old_dir); if (IS_ERR(dentry)) return dentry; return ERR_PTR(-EINVAL); } EXPORT_SYMBOL_GPL(debugfs_rename); /** * debugfs_initialized - Tells whether debugfs has been registered */ bool debugfs_initialized(void) { return debugfs_registered; } EXPORT_SYMBOL_GPL(debugfs_initialized); static int __init debugfs_kernel(char *str) { if (str) { if (!strcmp(str, "on")) debugfs_allow = DEBUGFS_ALLOW_API | DEBUGFS_ALLOW_MOUNT; else if (!strcmp(str, "no-mount")) debugfs_allow = DEBUGFS_ALLOW_API; else if (!strcmp(str, "off")) debugfs_allow = 0; } return 0; } early_param("debugfs", debugfs_kernel); static int __init debugfs_init(void) { int retval; if (!(debugfs_allow & DEBUGFS_ALLOW_MOUNT)) return -EPERM; retval = sysfs_create_mount_point(kernel_kobj, "debug"); if (retval) return retval; retval = register_filesystem(&debug_fs_type); if (retval) sysfs_remove_mount_point(kernel_kobj, "debug"); else debugfs_registered = true; return retval; } core_initcall(debugfs_init); |
| 158 158 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM cgroup #if !defined(_TRACE_CGROUP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_CGROUP_H #include <linux/cgroup.h> #include <linux/tracepoint.h> DECLARE_EVENT_CLASS(cgroup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root), TP_STRUCT__entry( __field( int, root ) __field( u16, ss_mask ) __string( name, root->name ) ), TP_fast_assign( __entry->root = root->hierarchy_id; __entry->ss_mask = root->subsys_mask; __assign_str(name); ), TP_printk("root=%d ss_mask=%#x name=%s", __entry->root, __entry->ss_mask, __get_str(name)) ); DEFINE_EVENT(cgroup_root, cgroup_setup_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_destroy_root, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DEFINE_EVENT(cgroup_root, cgroup_remount, TP_PROTO(struct cgroup_root *root), TP_ARGS(root) ); DECLARE_EVENT_CLASS(cgroup, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); ), TP_printk("root=%d id=%llu level=%d path=%s", __entry->root, __entry->id, __entry->level, __get_str(path)) ); DEFINE_EVENT(cgroup, cgroup_mkdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rmdir, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_release, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_rename, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_freeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DEFINE_EVENT(cgroup, cgroup_unfreeze, TP_PROTO(struct cgroup *cgrp, const char *path), TP_ARGS(cgrp, path) ); DECLARE_EVENT_CLASS(cgroup_migrate, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup), TP_STRUCT__entry( __field( int, dst_root ) __field( int, dst_level ) __field( u64, dst_id ) __field( int, pid ) __string( dst_path, path ) __string( comm, task->comm ) ), TP_fast_assign( __entry->dst_root = dst_cgrp->root->hierarchy_id; __entry->dst_id = cgroup_id(dst_cgrp); __entry->dst_level = dst_cgrp->level; __assign_str(dst_path); __entry->pid = task->pid; __assign_str(comm); ), TP_printk("dst_root=%d dst_id=%llu dst_level=%d dst_path=%s pid=%d comm=%s", __entry->dst_root, __entry->dst_id, __entry->dst_level, __get_str(dst_path), __entry->pid, __get_str(comm)) ); DEFINE_EVENT(cgroup_migrate, cgroup_attach_task, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DEFINE_EVENT(cgroup_migrate, cgroup_transfer_tasks, TP_PROTO(struct cgroup *dst_cgrp, const char *path, struct task_struct *task, bool threadgroup), TP_ARGS(dst_cgrp, path, task, threadgroup) ); DECLARE_EVENT_CLASS(cgroup_event, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __string( path, path ) __field( int, val ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __assign_str(path); __entry->val = val; ), TP_printk("root=%d id=%llu level=%d path=%s val=%d", __entry->root, __entry->id, __entry->level, __get_str(path), __entry->val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_populated, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DEFINE_EVENT(cgroup_event, cgroup_notify_frozen, TP_PROTO(struct cgroup *cgrp, const char *path, int val), TP_ARGS(cgrp, path, val) ); DECLARE_EVENT_CLASS(cgroup_rstat, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended), TP_STRUCT__entry( __field( int, root ) __field( int, level ) __field( u64, id ) __field( int, cpu ) __field( bool, contended ) ), TP_fast_assign( __entry->root = cgrp->root->hierarchy_id; __entry->id = cgroup_id(cgrp); __entry->level = cgrp->level; __entry->cpu = cpu; __entry->contended = contended; ), TP_printk("root=%d id=%llu level=%d cpu=%d lock contended:%d", __entry->root, __entry->id, __entry->level, __entry->cpu, __entry->contended) ); /* Related to global: cgroup_rstat_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); /* Related to per CPU: cgroup_rstat_cpu_lock */ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath, TP_PROTO(struct cgroup *cgrp, int cpu, bool contended), TP_ARGS(cgrp, cpu, contended) ); #endif /* _TRACE_CGROUP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 178 98 178 13 110 104 96 142 192 146 52 172 172 130 117 154 19 14 19 151 127 57 57 57 151 69 151 151 13 147 147 191 192 191 43 128 148 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* Red Black Trees (C) 1999 Andrea Arcangeli <andrea@suse.de> (C) 2002 David Woodhouse <dwmw2@infradead.org> (C) 2012 Michel Lespinasse <walken@google.com> linux/include/linux/rbtree_augmented.h */ #ifndef _LINUX_RBTREE_AUGMENTED_H #define _LINUX_RBTREE_AUGMENTED_H #include <linux/compiler.h> #include <linux/rbtree.h> #include <linux/rcupdate.h> /* * Please note - only struct rb_augment_callbacks and the prototypes for * rb_insert_augmented() and rb_erase_augmented() are intended to be public. * The rest are implementation details you are not expected to depend on. * * See Documentation/core-api/rbtree.rst for documentation and samples. */ struct rb_augment_callbacks { void (*propagate)(struct rb_node *node, struct rb_node *stop); void (*copy)(struct rb_node *old, struct rb_node *new); void (*rotate)(struct rb_node *old, struct rb_node *new); }; extern void __rb_insert_augmented(struct rb_node *node, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); /* * Fixup the rbtree and update the augmented information when rebalancing. * * On insertion, the user must update the augmented information on the path * leading to the inserted node, then call rb_link_node() as usual and * rb_insert_augmented() instead of the usual rb_insert_color() call. * If rb_insert_augmented() rebalances the rbtree, it will callback into * a user provided function to update the augmented information on the * affected subtrees. */ static inline void rb_insert_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { __rb_insert_augmented(node, root, augment->rotate); } static inline void rb_insert_augmented_cached(struct rb_node *node, struct rb_root_cached *root, bool newleft, const struct rb_augment_callbacks *augment) { if (newleft) root->rb_leftmost = node; rb_insert_augmented(node, &root->rb_root, augment); } static __always_inline struct rb_node * rb_add_augmented_cached(struct rb_node *node, struct rb_root_cached *tree, bool (*less)(struct rb_node *, const struct rb_node *), const struct rb_augment_callbacks *augment) { struct rb_node **link = &tree->rb_root.rb_node; struct rb_node *parent = NULL; bool leftmost = true; while (*link) { parent = *link; if (less(node, parent)) { link = &parent->rb_left; } else { link = &parent->rb_right; leftmost = false; } } rb_link_node(node, parent, link); augment->propagate(parent, NULL); /* suboptimal */ rb_insert_augmented_cached(node, tree, leftmost, augment); return leftmost ? node : NULL; } /* * Template for declaring augmented rbtree callbacks (generic case) * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBAUGMENTED: name of field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that recomputes the RBAUGMENTED data */ #define RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBCOMPUTE) \ static inline void \ RBNAME ## _propagate(struct rb_node *rb, struct rb_node *stop) \ { \ while (rb != stop) { \ RBSTRUCT *node = rb_entry(rb, RBSTRUCT, RBFIELD); \ if (RBCOMPUTE(node, true)) \ break; \ rb = rb_parent(&node->RBFIELD); \ } \ } \ static inline void \ RBNAME ## _copy(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ } \ static void \ RBNAME ## _rotate(struct rb_node *rb_old, struct rb_node *rb_new) \ { \ RBSTRUCT *old = rb_entry(rb_old, RBSTRUCT, RBFIELD); \ RBSTRUCT *new = rb_entry(rb_new, RBSTRUCT, RBFIELD); \ new->RBAUGMENTED = old->RBAUGMENTED; \ RBCOMPUTE(old, false); \ } \ RBSTATIC const struct rb_augment_callbacks RBNAME = { \ .propagate = RBNAME ## _propagate, \ .copy = RBNAME ## _copy, \ .rotate = RBNAME ## _rotate \ }; /* * Template for declaring augmented rbtree callbacks, * computing RBAUGMENTED scalar as max(RBCOMPUTE(node)) for all subtree nodes. * * RBSTATIC: 'static' or empty * RBNAME: name of the rb_augment_callbacks structure * RBSTRUCT: struct type of the tree nodes * RBFIELD: name of struct rb_node field within RBSTRUCT * RBTYPE: type of the RBAUGMENTED field * RBAUGMENTED: name of RBTYPE field within RBSTRUCT holding data for subtree * RBCOMPUTE: name of function that returns the per-node RBTYPE scalar */ #define RB_DECLARE_CALLBACKS_MAX(RBSTATIC, RBNAME, RBSTRUCT, RBFIELD, \ RBTYPE, RBAUGMENTED, RBCOMPUTE) \ static inline bool RBNAME ## _compute_max(RBSTRUCT *node, bool exit) \ { \ RBSTRUCT *child; \ RBTYPE max = RBCOMPUTE(node); \ if (node->RBFIELD.rb_left) { \ child = rb_entry(node->RBFIELD.rb_left, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (node->RBFIELD.rb_right) { \ child = rb_entry(node->RBFIELD.rb_right, RBSTRUCT, RBFIELD); \ if (child->RBAUGMENTED > max) \ max = child->RBAUGMENTED; \ } \ if (exit && node->RBAUGMENTED == max) \ return true; \ node->RBAUGMENTED = max; \ return false; \ } \ RB_DECLARE_CALLBACKS(RBSTATIC, RBNAME, \ RBSTRUCT, RBFIELD, RBAUGMENTED, RBNAME ## _compute_max) #define RB_RED 0 #define RB_BLACK 1 #define __rb_parent(pc) ((struct rb_node *)(pc & ~3)) #define __rb_color(pc) ((pc) & 1) #define __rb_is_black(pc) __rb_color(pc) #define __rb_is_red(pc) (!__rb_color(pc)) #define rb_color(rb) __rb_color((rb)->__rb_parent_color) #define rb_is_red(rb) __rb_is_red((rb)->__rb_parent_color) #define rb_is_black(rb) __rb_is_black((rb)->__rb_parent_color) static inline void rb_set_parent(struct rb_node *rb, struct rb_node *p) { rb->__rb_parent_color = rb_color(rb) + (unsigned long)p; } static inline void rb_set_parent_color(struct rb_node *rb, struct rb_node *p, int color) { rb->__rb_parent_color = (unsigned long)p + color; } static inline void __rb_change_child(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) WRITE_ONCE(parent->rb_left, new); else WRITE_ONCE(parent->rb_right, new); } else WRITE_ONCE(root->rb_node, new); } static inline void __rb_change_child_rcu(struct rb_node *old, struct rb_node *new, struct rb_node *parent, struct rb_root *root) { if (parent) { if (parent->rb_left == old) rcu_assign_pointer(parent->rb_left, new); else rcu_assign_pointer(parent->rb_right, new); } else rcu_assign_pointer(root->rb_node, new); } extern void __rb_erase_color(struct rb_node *parent, struct rb_root *root, void (*augment_rotate)(struct rb_node *old, struct rb_node *new)); static __always_inline struct rb_node * __rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *child = node->rb_right; struct rb_node *tmp = node->rb_left; struct rb_node *parent, *rebalance; unsigned long pc; if (!tmp) { /* * Case 1: node to erase has no more than 1 child (easy!) * * Note that if there is one child it must be red due to 5) * and node must be black due to 4). We adjust colors locally * so as to bypass __rb_erase_color() later on. */ pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, child, parent, root); if (child) { child->__rb_parent_color = pc; rebalance = NULL; } else rebalance = __rb_is_black(pc) ? parent : NULL; tmp = parent; } else if (!child) { /* Still case 1, but this time the child is node->rb_left */ tmp->__rb_parent_color = pc = node->__rb_parent_color; parent = __rb_parent(pc); __rb_change_child(node, tmp, parent, root); rebalance = NULL; tmp = parent; } else { struct rb_node *successor = child, *child2; tmp = child->rb_left; if (!tmp) { /* * Case 2: node's successor is its right child * * (n) (s) * / \ / \ * (x) (s) -> (x) (c) * \ * (c) */ parent = successor; child2 = successor->rb_right; augment->copy(node, successor); } else { /* * Case 3: node's successor is leftmost under * node's right child subtree * * (n) (s) * / \ / \ * (x) (y) -> (x) (y) * / / * (p) (p) * / / * (s) (c) * \ * (c) */ do { parent = successor; successor = tmp; tmp = tmp->rb_left; } while (tmp); child2 = successor->rb_right; WRITE_ONCE(parent->rb_left, child2); WRITE_ONCE(successor->rb_right, child); rb_set_parent(child, successor); augment->copy(node, successor); augment->propagate(parent, successor); } tmp = node->rb_left; WRITE_ONCE(successor->rb_left, tmp); rb_set_parent(tmp, successor); pc = node->__rb_parent_color; tmp = __rb_parent(pc); __rb_change_child(node, successor, tmp, root); if (child2) { rb_set_parent_color(child2, parent, RB_BLACK); rebalance = NULL; } else { rebalance = rb_is_black(successor) ? parent : NULL; } successor->__rb_parent_color = pc; tmp = successor; } augment->propagate(tmp, NULL); return rebalance; } static __always_inline void rb_erase_augmented(struct rb_node *node, struct rb_root *root, const struct rb_augment_callbacks *augment) { struct rb_node *rebalance = __rb_erase_augmented(node, root, augment); if (rebalance) __rb_erase_color(rebalance, root, augment->rotate); } static __always_inline void rb_erase_augmented_cached(struct rb_node *node, struct rb_root_cached *root, const struct rb_augment_callbacks *augment) { if (root->rb_leftmost == node) root->rb_leftmost = rb_next(node); rb_erase_augmented(node, &root->rb_root, augment); } #endif /* _LINUX_RBTREE_AUGMENTED_H */ |
| 6 6 4 4 6 10 1 1 1 11 2 3 9 11 10 1 1 1 1 5 5 5 1 1 1 1 1 4 1 16 8 11 3 3 2 1 5 3 1 1 1 1 4 5 3 1 15 1 8 7 8 1 7 8 3 3 2 2 2 2 2 2 3 2 19 2 17 1 6 1 5 10 1 5 5 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC: KVM DEVICE API * * Copyright (C) 2015 ARM Ltd. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <linux/kvm_host.h> #include <kvm/arm_vgic.h> #include <linux/uaccess.h> #include <asm/kvm_mmu.h> #include <asm/cputype.h> #include "vgic.h" /* common helpers */ int vgic_check_iorange(struct kvm *kvm, phys_addr_t ioaddr, phys_addr_t addr, phys_addr_t alignment, phys_addr_t size) { if (!IS_VGIC_ADDR_UNDEF(ioaddr)) return -EEXIST; if (!IS_ALIGNED(addr, alignment) || !IS_ALIGNED(size, alignment)) return -EINVAL; if (addr + size < addr) return -EINVAL; if (addr & ~kvm_phys_mask(&kvm->arch.mmu) || (addr + size) > kvm_phys_size(&kvm->arch.mmu)) return -E2BIG; return 0; } static int vgic_check_type(struct kvm *kvm, int type_needed) { if (kvm->arch.vgic.vgic_model != type_needed) return -ENODEV; else return 0; } int kvm_set_legacy_vgic_v2_addr(struct kvm *kvm, struct kvm_arm_device_addr *dev_addr) { struct vgic_dist *vgic = &kvm->arch.vgic; int r; mutex_lock(&kvm->arch.config_lock); switch (FIELD_GET(KVM_ARM_DEVICE_TYPE_MASK, dev_addr->id)) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_dist_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_DIST_SIZE); if (!r) vgic->vgic_dist_base = dev_addr->addr; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); if (!r) r = vgic_check_iorange(kvm, vgic->vgic_cpu_base, dev_addr->addr, SZ_4K, KVM_VGIC_V2_CPU_SIZE); if (!r) vgic->vgic_cpu_base = dev_addr->addr; break; default: r = -ENODEV; } mutex_unlock(&kvm->arch.config_lock); return r; } /** * kvm_vgic_addr - set or get vgic VM base addresses * @kvm: pointer to the vm struct * @attr: pointer to the attribute being retrieved/updated * @write: if true set the address in the VM address space, if false read the * address * * Set or get the vgic base addresses for the distributor and the virtual CPU * interface in the VM physical address space. These addresses are properties * of the emulated core/SoC and therefore user space initially knows this * information. * Check them for sanity (alignment, double assignment). We can't check for * overlapping regions in case of a virtual GICv3 here, since we don't know * the number of VCPUs yet, so we defer this check to map_resources(). */ static int kvm_vgic_addr(struct kvm *kvm, struct kvm_device_attr *attr, bool write) { u64 __user *uaddr = (u64 __user *)attr->addr; struct vgic_dist *vgic = &kvm->arch.vgic; phys_addr_t *addr_ptr, alignment, size; u64 undef_value = VGIC_ADDR_UNDEF; u64 addr; int r; /* Reading a redistributor region addr implies getting the index */ if (write || attr->attr == KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION) if (get_user(addr, uaddr)) return -EFAULT; /* * Since we can't hold config_lock while registering the redistributor * iodevs, take the slots_lock immediately. */ mutex_lock(&kvm->slots_lock); switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_4K; size = KVM_VGIC_V2_DIST_SIZE; break; case KVM_VGIC_V2_ADDR_TYPE_CPU: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V2); addr_ptr = &vgic->vgic_cpu_base; alignment = SZ_4K; size = KVM_VGIC_V2_CPU_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_DIST: r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); addr_ptr = &vgic->vgic_dist_base; alignment = SZ_64K; size = KVM_VGIC_V3_DIST_SIZE; break; case KVM_VGIC_V3_ADDR_TYPE_REDIST: { struct vgic_redist_region *rdreg; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; if (write) { r = vgic_v3_set_redist_base(kvm, 0, addr, 0); goto out; } rdreg = list_first_entry_or_null(&vgic->rd_regions, struct vgic_redist_region, list); if (!rdreg) addr_ptr = &undef_value; else addr_ptr = &rdreg->base; break; } case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: { struct vgic_redist_region *rdreg; u8 index; r = vgic_check_type(kvm, KVM_DEV_TYPE_ARM_VGIC_V3); if (r) break; index = addr & KVM_VGIC_V3_RDIST_INDEX_MASK; if (write) { gpa_t base = addr & KVM_VGIC_V3_RDIST_BASE_MASK; u32 count = FIELD_GET(KVM_VGIC_V3_RDIST_COUNT_MASK, addr); u8 flags = FIELD_GET(KVM_VGIC_V3_RDIST_FLAGS_MASK, addr); if (!count || flags) r = -EINVAL; else r = vgic_v3_set_redist_base(kvm, index, base, count); goto out; } rdreg = vgic_v3_rdist_region_from_index(kvm, index); if (!rdreg) { r = -ENOENT; goto out; } addr = index; addr |= rdreg->base; addr |= (u64)rdreg->count << KVM_VGIC_V3_RDIST_COUNT_SHIFT; goto out; } default: r = -ENODEV; } if (r) goto out; mutex_lock(&kvm->arch.config_lock); if (write) { r = vgic_check_iorange(kvm, *addr_ptr, addr, alignment, size); if (!r) *addr_ptr = addr; } else { addr = *addr_ptr; } mutex_unlock(&kvm->arch.config_lock); out: mutex_unlock(&kvm->slots_lock); if (!r && !write) r = put_user(addr, uaddr); return r; } static int vgic_set_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, true); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; u32 val; int ret = 0; if (get_user(val, uaddr)) return -EFAULT; /* * We require: * - at least 32 SPIs on top of the 16 SGIs and 16 PPIs * - at most 1024 interrupts * - a multiple of 32 interrupts */ if (val < (VGIC_NR_PRIVATE_IRQS + 32) || val > VGIC_MAX_RESERVED || (val & 31)) return -EINVAL; mutex_lock(&dev->kvm->arch.config_lock); if (vgic_ready(dev->kvm) || dev->kvm->arch.vgic.nr_spis) ret = -EBUSY; else dev->kvm->arch.vgic.nr_spis = val - VGIC_NR_PRIVATE_IRQS; mutex_unlock(&dev->kvm->arch.config_lock); return ret; } case KVM_DEV_ARM_VGIC_GRP_CTRL: { switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: mutex_lock(&dev->kvm->arch.config_lock); r = vgic_init(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); return r; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: /* * OK, this one isn't common at all, but we * want to handle all control group attributes * in a single place. */ if (vgic_check_type(dev->kvm, KVM_DEV_TYPE_ARM_VGIC_V3)) return -ENXIO; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); r = vgic_v3_save_pending_tables(dev->kvm); mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); return r; } break; } } return -ENXIO; } static int vgic_get_common_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { int r = -ENXIO; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: r = kvm_vgic_addr(dev->kvm, attr, false); return (r == -ENODEV) ? -ENXIO : r; case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: { u32 __user *uaddr = (u32 __user *)(long)attr->addr; r = put_user(dev->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS, uaddr); break; } } return r; } static int vgic_create(struct kvm_device *dev, u32 type) { return kvm_vgic_create(dev->kvm, type); } static void vgic_destroy(struct kvm_device *dev) { kfree(dev); } int kvm_register_vgic_device(unsigned long type) { int ret = -ENODEV; switch (type) { case KVM_DEV_TYPE_ARM_VGIC_V2: ret = kvm_register_device_ops(&kvm_arm_vgic_v2_ops, KVM_DEV_TYPE_ARM_VGIC_V2); break; case KVM_DEV_TYPE_ARM_VGIC_V3: ret = kvm_register_device_ops(&kvm_arm_vgic_v3_ops, KVM_DEV_TYPE_ARM_VGIC_V3); if (ret) break; ret = kvm_vgic_register_its_device(); break; } return ret; } int vgic_v2_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { int cpuid = FIELD_GET(KVM_DEV_ARM_VGIC_CPUID_MASK, attr->attr); reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; reg_attr->vcpu = kvm_get_vcpu_by_id(dev->kvm, cpuid); if (!reg_attr->vcpu) return -EINVAL; return 0; } /** * vgic_v2_attr_regs_access - allows user space to access VGIC v2 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v2_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; int ret; u32 val; ret = vgic_v2_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; if (is_write) if (get_user(val, uaddr)) return -EFAULT; mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); ret = vgic_init(dev->kvm); if (ret) goto out; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: ret = vgic_v2_cpuif_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v2_dist_uaccess(vcpu, is_write, addr, &val); break; default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && !is_write) ret = put_user(val, uaddr); return ret; } static int vgic_v2_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v2_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v2_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V2_ADDR_TYPE_DIST: case KVM_VGIC_V2_ADDR_TYPE_CPU: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_REGS: return vgic_v2_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v2_ops = { .name = "kvm-arm-vgic-v2", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v2_set_attr, .get_attr = vgic_v2_get_attr, .has_attr = vgic_v2_has_attr, }; int vgic_v3_parse_attr(struct kvm_device *dev, struct kvm_device_attr *attr, struct vgic_reg_attr *reg_attr) { unsigned long vgic_mpidr, mpidr_reg; /* * For KVM_DEV_ARM_VGIC_GRP_DIST_REGS group, * attr might not hold MPIDR. Hence assume vcpu0. */ if (attr->group != KVM_DEV_ARM_VGIC_GRP_DIST_REGS) { vgic_mpidr = (attr->attr & KVM_DEV_ARM_VGIC_V3_MPIDR_MASK) >> KVM_DEV_ARM_VGIC_V3_MPIDR_SHIFT; mpidr_reg = VGIC_TO_MPIDR(vgic_mpidr); reg_attr->vcpu = kvm_mpidr_to_vcpu(dev->kvm, mpidr_reg); } else { reg_attr->vcpu = kvm_get_vcpu(dev->kvm, 0); } if (!reg_attr->vcpu) return -EINVAL; reg_attr->addr = attr->attr & KVM_DEV_ARM_VGIC_OFFSET_MASK; return 0; } /* * vgic_v3_attr_regs_access - allows user space to access VGIC v3 state * * @dev: kvm device handle * @attr: kvm device attribute * @is_write: true if userspace is writing a register */ static int vgic_v3_attr_regs_access(struct kvm_device *dev, struct kvm_device_attr *attr, bool is_write) { struct vgic_reg_attr reg_attr; gpa_t addr; struct kvm_vcpu *vcpu; bool uaccess; u32 val; int ret; ret = vgic_v3_parse_attr(dev, attr, ®_attr); if (ret) return ret; vcpu = reg_attr.vcpu; addr = reg_attr.addr; switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: /* Sysregs uaccess is performed by the sysreg handling code */ uaccess = false; break; default: uaccess = true; } if (uaccess && is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; if (get_user(val, uaddr)) return -EFAULT; } mutex_lock(&dev->kvm->lock); if (!lock_all_vcpus(dev->kvm)) { mutex_unlock(&dev->kvm->lock); return -EBUSY; } mutex_lock(&dev->kvm->arch.config_lock); if (unlikely(!vgic_initialized(dev->kvm))) { ret = -EBUSY; goto out; } switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: ret = vgic_v3_dist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: ret = vgic_v3_redist_uaccess(vcpu, is_write, addr, &val); break; case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: ret = vgic_v3_cpu_sysregs_uaccess(vcpu, attr, is_write); break; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { unsigned int info, intid; info = (attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT; if (info == VGIC_LEVEL_INFO_LINE_LEVEL) { intid = attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INTID_MASK; ret = vgic_v3_line_level_info_uaccess(vcpu, is_write, intid, &val); } else { ret = -EINVAL; } break; } default: ret = -EINVAL; break; } out: mutex_unlock(&dev->kvm->arch.config_lock); unlock_all_vcpus(dev->kvm); mutex_unlock(&dev->kvm->lock); if (!ret && uaccess && !is_write) { u32 __user *uaddr = (u32 __user *)(unsigned long)attr->addr; ret = put_user(val, uaddr); } return ret; } static int vgic_v3_set_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, true); default: return vgic_set_common_attr(dev, attr); } } static int vgic_v3_get_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: return vgic_v3_attr_regs_access(dev, attr, false); default: return vgic_get_common_attr(dev, attr); } } static int vgic_v3_has_attr(struct kvm_device *dev, struct kvm_device_attr *attr) { switch (attr->group) { case KVM_DEV_ARM_VGIC_GRP_ADDR: switch (attr->attr) { case KVM_VGIC_V3_ADDR_TYPE_DIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST: case KVM_VGIC_V3_ADDR_TYPE_REDIST_REGION: return 0; } break; case KVM_DEV_ARM_VGIC_GRP_DIST_REGS: case KVM_DEV_ARM_VGIC_GRP_REDIST_REGS: case KVM_DEV_ARM_VGIC_GRP_CPU_SYSREGS: return vgic_v3_has_attr_regs(dev, attr); case KVM_DEV_ARM_VGIC_GRP_NR_IRQS: return 0; case KVM_DEV_ARM_VGIC_GRP_LEVEL_INFO: { if (((attr->attr & KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_MASK) >> KVM_DEV_ARM_VGIC_LINE_LEVEL_INFO_SHIFT) == VGIC_LEVEL_INFO_LINE_LEVEL) return 0; break; } case KVM_DEV_ARM_VGIC_GRP_CTRL: switch (attr->attr) { case KVM_DEV_ARM_VGIC_CTRL_INIT: return 0; case KVM_DEV_ARM_VGIC_SAVE_PENDING_TABLES: return 0; } } return -ENXIO; } struct kvm_device_ops kvm_arm_vgic_v3_ops = { .name = "kvm-arm-vgic-v3", .create = vgic_create, .destroy = vgic_destroy, .set_attr = vgic_v3_set_attr, .get_attr = vgic_v3_get_attr, .has_attr = vgic_v3_has_attr, }; |
| 69 8 39 6 145 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 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-only */ /* * kref.h - library routines for handling generic reference counted objects * * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com> * Copyright (C) 2004 IBM Corp. * * based on kobject.h which was: * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (C) 2002-2003 Open Source Development Labs */ #ifndef _KREF_H_ #define _KREF_H_ #include <linux/spinlock.h> #include <linux/refcount.h> struct kref { refcount_t refcount; }; #define KREF_INIT(n) { .refcount = REFCOUNT_INIT(n), } /** * kref_init - initialize object. * @kref: object in question. */ static inline void kref_init(struct kref *kref) { refcount_set(&kref->refcount, 1); } static inline unsigned int kref_read(const struct kref *kref) { return refcount_read(&kref->refcount); } /** * kref_get - increment refcount for object. * @kref: object. */ static inline void kref_get(struct kref *kref) { refcount_inc(&kref->refcount); } /** * kref_put - decrement refcount for object. * @kref: object. * @release: pointer to the function that will clean up the object when the * last reference to the object is released. * This pointer is required, and it is not acceptable to pass kfree * in as this function. * * Decrement the refcount, and if 0, call release(). * Return 1 if the object was removed, otherwise return 0. Beware, if this * function returns 0, you still can not count on the kref from remaining in * memory. Only use the return value if you want to see if the kref is now * gone, not present. */ static inline int kref_put(struct kref *kref, void (*release)(struct kref *kref)) { if (refcount_dec_and_test(&kref->refcount)) { release(kref); return 1; } return 0; } static inline int kref_put_mutex(struct kref *kref, void (*release)(struct kref *kref), struct mutex *lock) { if (refcount_dec_and_mutex_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } static inline int kref_put_lock(struct kref *kref, void (*release)(struct kref *kref), spinlock_t *lock) { if (refcount_dec_and_lock(&kref->refcount, lock)) { release(kref); return 1; } return 0; } /** * kref_get_unless_zero - Increment refcount for object unless it is zero. * @kref: object. * * Return non-zero if the increment succeeded. Otherwise return 0. * * This function is intended to simplify locking around refcounting for * objects that can be looked up from a lookup structure, and which are * removed from that lookup structure in the object destructor. * Operations on such objects require at least a read lock around * lookup + kref_get, and a write lock around kref_put + remove from lookup * structure. Furthermore, RCU implementations become extremely tricky. * With a lookup followed by a kref_get_unless_zero *with return value check* * locking in the kref_put path can be deferred to the actual removal from * the lookup structure and RCU lookups become trivial. */ static inline int __must_check kref_get_unless_zero(struct kref *kref) { return refcount_inc_not_zero(&kref->refcount); } #endif /* _KREF_H_ */ |
| 247 247 68 68 86 86 86 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2022 Christian Brauner <brauner@kernel.org> */ #include <linux/cred.h> #include <linux/fs.h> #include <linux/mnt_idmapping.h> #include <linux/slab.h> #include <linux/user_namespace.h> #include "internal.h" /* * Outside of this file vfs{g,u}id_t are always created from k{g,u}id_t, * never from raw values. These are just internal helpers. */ #define VFSUIDT_INIT_RAW(val) (vfsuid_t){ val } #define VFSGIDT_INIT_RAW(val) (vfsgid_t){ val } struct mnt_idmap { struct uid_gid_map uid_map; struct uid_gid_map gid_map; refcount_t count; }; /* * Carries the initial idmapping of 0:0:4294967295 which is an identity * mapping. This means that {g,u}id 0 is mapped to {g,u}id 0, {g,u}id 1 is * mapped to {g,u}id 1, [...], {g,u}id 1000 to {g,u}id 1000, [...]. */ struct mnt_idmap nop_mnt_idmap = { .count = REFCOUNT_INIT(1), }; EXPORT_SYMBOL_GPL(nop_mnt_idmap); /** * initial_idmapping - check whether this is the initial mapping * @ns: idmapping to check * * Check whether this is the initial mapping, mapping 0 to 0, 1 to 1, * [...], 1000 to 1000 [...]. * * Return: true if this is the initial mapping, false if not. */ static inline bool initial_idmapping(const struct user_namespace *ns) { return ns == &init_user_ns; } /** * make_vfsuid - map a filesystem kuid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kuid : kuid to be mapped * * Take a @kuid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kuid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kuid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kuid won't change when calling * from_kuid() so we can simply retrieve the value via __kuid_val() * directly. * * Return: @kuid mapped according to @idmap. * If @kuid has no mapping in either @idmap or @fs_userns INVALID_UID is * returned. */ vfsuid_t make_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kuid_t kuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return VFSUIDT_INIT(kuid); if (initial_idmapping(fs_userns)) uid = __kuid_val(kuid); else uid = from_kuid(fs_userns, kuid); if (uid == (uid_t)-1) return INVALID_VFSUID; return VFSUIDT_INIT_RAW(map_id_down(&idmap->uid_map, uid)); } EXPORT_SYMBOL_GPL(make_vfsuid); /** * make_vfsgid - map a filesystem kgid according to an idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @kgid : kgid to be mapped * * Take a @kgid and remap it from @fs_userns into @idmap. Use this * function when preparing a @kgid to be reported to userspace. * * If initial_idmapping() determines that this is not an idmapped mount * we can simply return @kgid unchanged. * If initial_idmapping() tells us that the filesystem is not mounted with an * idmapping we know the value of @kgid won't change when calling * from_kgid() so we can simply retrieve the value via __kgid_val() * directly. * * Return: @kgid mapped according to @idmap. * If @kgid has no mapping in either @idmap or @fs_userns INVALID_GID is * returned. */ vfsgid_t make_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, kgid_t kgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return VFSGIDT_INIT(kgid); if (initial_idmapping(fs_userns)) gid = __kgid_val(kgid); else gid = from_kgid(fs_userns, kgid); if (gid == (gid_t)-1) return INVALID_VFSGID; return VFSGIDT_INIT_RAW(map_id_down(&idmap->gid_map, gid)); } EXPORT_SYMBOL_GPL(make_vfsgid); /** * from_vfsuid - map a vfsuid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsuid : vfsuid to be mapped * * Map @vfsuid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsuid to inode->i_uid. * * Return: @vfsuid mapped into the filesystem idmapping */ kuid_t from_vfsuid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsuid_t vfsuid) { uid_t uid; if (idmap == &nop_mnt_idmap) return AS_KUIDT(vfsuid); uid = map_id_up(&idmap->uid_map, __vfsuid_val(vfsuid)); if (uid == (uid_t)-1) return INVALID_UID; if (initial_idmapping(fs_userns)) return KUIDT_INIT(uid); return make_kuid(fs_userns, uid); } EXPORT_SYMBOL_GPL(from_vfsuid); /** * from_vfsgid - map a vfsgid into the filesystem idmapping * @idmap: the mount's idmapping * @fs_userns: the filesystem's idmapping * @vfsgid : vfsgid to be mapped * * Map @vfsgid into the filesystem idmapping. This function has to be used in * order to e.g. write @vfsgid to inode->i_gid. * * Return: @vfsgid mapped into the filesystem idmapping */ kgid_t from_vfsgid(struct mnt_idmap *idmap, struct user_namespace *fs_userns, vfsgid_t vfsgid) { gid_t gid; if (idmap == &nop_mnt_idmap) return AS_KGIDT(vfsgid); gid = map_id_up(&idmap->gid_map, __vfsgid_val(vfsgid)); if (gid == (gid_t)-1) return INVALID_GID; if (initial_idmapping(fs_userns)) return KGIDT_INIT(gid); return make_kgid(fs_userns, gid); } EXPORT_SYMBOL_GPL(from_vfsgid); #ifdef CONFIG_MULTIUSER /** * vfsgid_in_group_p() - check whether a vfsuid matches the caller's groups * @vfsgid: the mnt gid to match * * This function can be used to determine whether @vfsuid matches any of the * caller's groups. * * Return: 1 if vfsuid matches caller's groups, 0 if not. */ int vfsgid_in_group_p(vfsgid_t vfsgid) { return in_group_p(AS_KGIDT(vfsgid)); } #else int vfsgid_in_group_p(vfsgid_t vfsgid) { return 1; } #endif EXPORT_SYMBOL_GPL(vfsgid_in_group_p); static int copy_mnt_idmap(struct uid_gid_map *map_from, struct uid_gid_map *map_to) { struct uid_gid_extent *forward, *reverse; u32 nr_extents = READ_ONCE(map_from->nr_extents); /* Pairs with smp_wmb() when writing the idmapping. */ smp_rmb(); /* * Don't blindly copy @map_to into @map_from if nr_extents is * smaller or equal to UID_GID_MAP_MAX_BASE_EXTENTS. Since we * read @nr_extents someone could have written an idmapping and * then we might end up with inconsistent data. So just don't do * anything at all. */ if (nr_extents == 0) return -EINVAL; /* * Here we know that nr_extents is greater than zero which means * a map has been written. Since idmappings can't be changed * once they have been written we know that we can safely copy * from @map_to into @map_from. */ if (nr_extents <= UID_GID_MAP_MAX_BASE_EXTENTS) { *map_to = *map_from; return 0; } forward = kmemdup(map_from->forward, nr_extents * sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!forward) return -ENOMEM; reverse = kmemdup(map_from->reverse, nr_extents * sizeof(struct uid_gid_extent), GFP_KERNEL_ACCOUNT); if (!reverse) { kfree(forward); return -ENOMEM; } /* * The idmapping isn't exposed anywhere so we don't need to care * about ordering between extent pointers and @nr_extents * initialization. */ map_to->forward = forward; map_to->reverse = reverse; map_to->nr_extents = nr_extents; return 0; } static void free_mnt_idmap(struct mnt_idmap *idmap) { if (idmap->uid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->uid_map.forward); kfree(idmap->uid_map.reverse); } if (idmap->gid_map.nr_extents > UID_GID_MAP_MAX_BASE_EXTENTS) { kfree(idmap->gid_map.forward); kfree(idmap->gid_map.reverse); } kfree(idmap); } struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns) { struct mnt_idmap *idmap; int ret; idmap = kzalloc(sizeof(struct mnt_idmap), GFP_KERNEL_ACCOUNT); if (!idmap) return ERR_PTR(-ENOMEM); refcount_set(&idmap->count, 1); ret = copy_mnt_idmap(&mnt_userns->uid_map, &idmap->uid_map); if (!ret) ret = copy_mnt_idmap(&mnt_userns->gid_map, &idmap->gid_map); if (ret) { free_mnt_idmap(idmap); idmap = ERR_PTR(ret); } return idmap; } /** * mnt_idmap_get - get a reference to an idmapping * @idmap: the idmap to bump the reference on * * If @idmap is not the @nop_mnt_idmap bump the reference count. * * Return: @idmap with reference count bumped if @not_mnt_idmap isn't passed. */ struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap) refcount_inc(&idmap->count); return idmap; } EXPORT_SYMBOL_GPL(mnt_idmap_get); /** * mnt_idmap_put - put a reference to an idmapping * @idmap: the idmap to put the reference on * * If this is a non-initial idmapping, put the reference count when a mount is * released and free it if we're the last user. */ void mnt_idmap_put(struct mnt_idmap *idmap) { if (idmap != &nop_mnt_idmap && refcount_dec_and_test(&idmap->count)) free_mnt_idmap(idmap); } EXPORT_SYMBOL_GPL(mnt_idmap_put); |
| 150 150 150 150 150 150 150 150 150 150 150 145 145 10 10 10 10 150 150 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * kobject.c - library routines for handling generic kernel objects * * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org> * Copyright (c) 2006-2007 Greg Kroah-Hartman <greg@kroah.com> * Copyright (c) 2006-2007 Novell Inc. * * Please see the file Documentation/core-api/kobject.rst for critical information * about using the kobject interface. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kobject.h> #include <linux/string.h> #include <linux/export.h> #include <linux/stat.h> #include <linux/slab.h> #include <linux/random.h> /** * kobject_namespace() - Return @kobj's namespace tag. * @kobj: kobject in question * * Returns namespace tag of @kobj if its parent has namespace ops enabled * and thus @kobj should have a namespace tag associated with it. Returns * %NULL otherwise. */ const void *kobject_namespace(const struct kobject *kobj) { const struct kobj_ns_type_operations *ns_ops = kobj_ns_ops(kobj); if (!ns_ops || ns_ops->type == KOBJ_NS_TYPE_NONE) return NULL; return kobj->ktype->namespace(kobj); } /** * kobject_get_ownership() - Get sysfs ownership data for @kobj. * @kobj: kobject in question * @uid: kernel user ID for sysfs objects * @gid: kernel group ID for sysfs objects * * Returns initial uid/gid pair that should be used when creating sysfs * representation of given kobject. Normally used to adjust ownership of * objects in a container. */ void kobject_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { *uid = GLOBAL_ROOT_UID; *gid = GLOBAL_ROOT_GID; if (kobj->ktype->get_ownership) kobj->ktype->get_ownership(kobj, uid, gid); } static bool kobj_ns_type_is_valid(enum kobj_ns_type type) { if ((type <= KOBJ_NS_TYPE_NONE) || (type >= KOBJ_NS_TYPES)) return false; return true; } static int create_dir(struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); const struct kobj_ns_type_operations *ops; int error; error = sysfs_create_dir_ns(kobj, kobject_namespace(kobj)); if (error) return error; if (ktype) { error = sysfs_create_groups(kobj, ktype->default_groups); if (error) { sysfs_remove_dir(kobj); return error; } } /* * @kobj->sd may be deleted by an ancestor going away. Hold an * extra reference so that it stays until @kobj is gone. */ sysfs_get(kobj->sd); /* * If @kobj has ns_ops, its children need to be filtered based on * their namespace tags. Enable namespace support on @kobj->sd. */ ops = kobj_child_ns_ops(kobj); if (ops) { BUG_ON(!kobj_ns_type_is_valid(ops->type)); BUG_ON(!kobj_ns_type_registered(ops->type)); sysfs_enable_ns(kobj->sd); } return 0; } static int get_kobj_path_length(const struct kobject *kobj) { int length = 1; const struct kobject *parent = kobj; /* walk up the ancestors until we hit the one pointing to the * root. * Add 1 to strlen for leading '/' of each level. */ do { if (kobject_name(parent) == NULL) return 0; length += strlen(kobject_name(parent)) + 1; parent = parent->parent; } while (parent); return length; } static int fill_kobj_path(const struct kobject *kobj, char *path, int length) { const struct kobject *parent; --length; for (parent = kobj; parent; parent = parent->parent) { int cur = strlen(kobject_name(parent)); /* back up enough to print this name with '/' */ length -= cur; if (length <= 0) return -EINVAL; memcpy(path + length, kobject_name(parent), cur); *(path + --length) = '/'; } pr_debug("'%s' (%p): %s: path = '%s'\n", kobject_name(kobj), kobj, __func__, path); return 0; } /** * kobject_get_path() - Allocate memory and fill in the path for @kobj. * @kobj: kobject in question, with which to build the path * @gfp_mask: the allocation type used to allocate the path * * Return: The newly allocated memory, caller must free with kfree(). */ char *kobject_get_path(const struct kobject *kobj, gfp_t gfp_mask) { char *path; int len; retry: len = get_kobj_path_length(kobj); if (len == 0) return NULL; path = kzalloc(len, gfp_mask); if (!path) return NULL; if (fill_kobj_path(kobj, path, len)) { kfree(path); goto retry; } return path; } EXPORT_SYMBOL_GPL(kobject_get_path); /* add the kobject to its kset's list */ static void kobj_kset_join(struct kobject *kobj) { if (!kobj->kset) return; kset_get(kobj->kset); spin_lock(&kobj->kset->list_lock); list_add_tail(&kobj->entry, &kobj->kset->list); spin_unlock(&kobj->kset->list_lock); } /* remove the kobject from its kset's list */ static void kobj_kset_leave(struct kobject *kobj) { if (!kobj->kset) return; spin_lock(&kobj->kset->list_lock); list_del_init(&kobj->entry); spin_unlock(&kobj->kset->list_lock); kset_put(kobj->kset); } static void kobject_init_internal(struct kobject *kobj) { if (!kobj) return; kref_init(&kobj->kref); INIT_LIST_HEAD(&kobj->entry); kobj->state_in_sysfs = 0; kobj->state_add_uevent_sent = 0; kobj->state_remove_uevent_sent = 0; kobj->state_initialized = 1; } static int kobject_add_internal(struct kobject *kobj) { int error = 0; struct kobject *parent; if (!kobj) return -ENOENT; if (!kobj->name || !kobj->name[0]) { WARN(1, "kobject: (%p): attempted to be registered with empty name!\n", kobj); return -EINVAL; } parent = kobject_get(kobj->parent); /* join kset if set, use it as parent if we do not already have one */ if (kobj->kset) { if (!parent) parent = kobject_get(&kobj->kset->kobj); kobj_kset_join(kobj); kobj->parent = parent; } pr_debug("'%s' (%p): %s: parent: '%s', set: '%s'\n", kobject_name(kobj), kobj, __func__, parent ? kobject_name(parent) : "<NULL>", kobj->kset ? kobject_name(&kobj->kset->kobj) : "<NULL>"); error = create_dir(kobj); if (error) { kobj_kset_leave(kobj); kobject_put(parent); kobj->parent = NULL; /* be noisy on error issues */ if (error == -EEXIST) pr_err("%s failed for %s with -EEXIST, don't try to register things with the same name in the same directory.\n", __func__, kobject_name(kobj)); else pr_err("%s failed for %s (error: %d parent: %s)\n", __func__, kobject_name(kobj), error, parent ? kobject_name(parent) : "'none'"); } else kobj->state_in_sysfs = 1; return error; } /** * kobject_set_name_vargs() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * @vargs: vargs to format the string. */ int kobject_set_name_vargs(struct kobject *kobj, const char *fmt, va_list vargs) { const char *s; if (kobj->name && !fmt) return 0; s = kvasprintf_const(GFP_KERNEL, fmt, vargs); if (!s) return -ENOMEM; /* * ewww... some of these buggers have '/' in the name ... If * that's the case, we need to make sure we have an actual * allocated copy to modify, since kvasprintf_const may have * returned something from .rodata. */ if (strchr(s, '/')) { char *t; t = kstrdup(s, GFP_KERNEL); kfree_const(s); if (!t) return -ENOMEM; s = strreplace(t, '/', '!'); } kfree_const(kobj->name); kobj->name = s; return 0; } /** * kobject_set_name() - Set the name of a kobject. * @kobj: struct kobject to set the name of * @fmt: format string used to build the name * * This sets the name of the kobject. If you have already added the * kobject to the system, you must call kobject_rename() in order to * change the name of the kobject. */ int kobject_set_name(struct kobject *kobj, const char *fmt, ...) { va_list vargs; int retval; va_start(vargs, fmt); retval = kobject_set_name_vargs(kobj, fmt, vargs); va_end(vargs); return retval; } EXPORT_SYMBOL(kobject_set_name); /** * kobject_init() - Initialize a kobject structure. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * * This function will properly initialize a kobject such that it can then * be passed to the kobject_add() call. * * After this function is called, the kobject MUST be cleaned up by a call * to kobject_put(), not by a call to kfree directly to ensure that all of * the memory is cleaned up properly. */ void kobject_init(struct kobject *kobj, const struct kobj_type *ktype) { char *err_str; if (!kobj) { err_str = "invalid kobject pointer!"; goto error; } if (!ktype) { err_str = "must have a ktype to be initialized properly!\n"; goto error; } if (kobj->state_initialized) { /* do not error out as sometimes we can recover */ pr_err("kobject (%p): tried to init an initialized object, something is seriously wrong.\n", kobj); dump_stack_lvl(KERN_ERR); } kobject_init_internal(kobj); kobj->ktype = ktype; return; error: pr_err("kobject (%p): %s\n", kobj, err_str); dump_stack_lvl(KERN_ERR); } EXPORT_SYMBOL(kobject_init); static __printf(3, 0) int kobject_add_varg(struct kobject *kobj, struct kobject *parent, const char *fmt, va_list vargs) { int retval; retval = kobject_set_name_vargs(kobj, fmt, vargs); if (retval) { pr_err("can not set name properly!\n"); return retval; } kobj->parent = parent; return kobject_add_internal(kobj); } /** * kobject_add() - The main kobject add function. * @kobj: the kobject to add * @parent: pointer to the parent of the kobject. * @fmt: format to name the kobject with. * * The kobject name is set and added to the kobject hierarchy in this * function. * * If @parent is set, then the parent of the @kobj will be set to it. * If @parent is NULL, then the parent of the @kobj will be set to the * kobject associated with the kset assigned to this kobject. If no kset * is assigned to the kobject, then the kobject will be located in the * root of the sysfs tree. * * Note, no "add" uevent will be created with this call, the caller should set * up all of the necessary sysfs files for the object and then call * kobject_uevent() with the UEVENT_ADD parameter to ensure that * userspace is properly notified of this kobject's creation. * * Return: If this function returns an error, kobject_put() must be * called to properly clean up the memory associated with the * object. Under no instance should the kobject that is passed * to this function be directly freed with a call to kfree(), * that can leak memory. * * If this function returns success, kobject_put() must also be called * in order to properly clean up the memory associated with the object. * * In short, once this function is called, kobject_put() MUST be called * when the use of the object is finished in order to properly free * everything. */ int kobject_add(struct kobject *kobj, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; if (!kobj) return -EINVAL; if (!kobj->state_initialized) { pr_err("kobject '%s' (%p): tried to add an uninitialized object, something is seriously wrong.\n", kobject_name(kobj), kobj); dump_stack_lvl(KERN_ERR); return -EINVAL; } va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL(kobject_add); /** * kobject_init_and_add() - Initialize a kobject structure and add it to * the kobject hierarchy. * @kobj: pointer to the kobject to initialize * @ktype: pointer to the ktype for this kobject. * @parent: pointer to the parent of this kobject. * @fmt: the name of the kobject. * * This function combines the call to kobject_init() and kobject_add(). * * If this function returns an error, kobject_put() must be called to * properly clean up the memory associated with the object. This is the * same type of error handling after a call to kobject_add() and kobject * lifetime rules are the same here. */ int kobject_init_and_add(struct kobject *kobj, const struct kobj_type *ktype, struct kobject *parent, const char *fmt, ...) { va_list args; int retval; kobject_init(kobj, ktype); va_start(args, fmt); retval = kobject_add_varg(kobj, parent, fmt, args); va_end(args); return retval; } EXPORT_SYMBOL_GPL(kobject_init_and_add); /** * kobject_rename() - Change the name of an object. * @kobj: object in question. * @new_name: object's new name * * It is the responsibility of the caller to provide mutual * exclusion between two different calls of kobject_rename * on the same kobject and to ensure that new_name is valid and * won't conflict with other kobjects. */ int kobject_rename(struct kobject *kobj, const char *new_name) { int error = 0; const char *devpath = NULL; const char *dup_name = NULL, *name; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; if (!kobj->parent) { kobject_put(kobj); return -EINVAL; } devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; name = dup_name = kstrdup_const(new_name, GFP_KERNEL); if (!name) { error = -ENOMEM; goto out; } error = sysfs_rename_dir_ns(kobj, new_name, kobject_namespace(kobj)); if (error) goto out; /* Install the new kobject name */ dup_name = kobj->name; kobj->name = name; /* This function is mostly/only used for network interface. * Some hotplug package track interfaces by their name and * therefore want to know when the name is changed by the user. */ kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kfree_const(dup_name); kfree(devpath_string); kfree(devpath); kobject_put(kobj); return error; } EXPORT_SYMBOL_GPL(kobject_rename); /** * kobject_move() - Move object to another parent. * @kobj: object in question. * @new_parent: object's new parent (can be NULL) */ int kobject_move(struct kobject *kobj, struct kobject *new_parent) { int error; struct kobject *old_parent; const char *devpath = NULL; char *devpath_string = NULL; char *envp[2]; kobj = kobject_get(kobj); if (!kobj) return -EINVAL; new_parent = kobject_get(new_parent); if (!new_parent) { if (kobj->kset) new_parent = kobject_get(&kobj->kset->kobj); } /* old object path */ devpath = kobject_get_path(kobj, GFP_KERNEL); if (!devpath) { error = -ENOMEM; goto out; } devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL); if (!devpath_string) { error = -ENOMEM; goto out; } sprintf(devpath_string, "DEVPATH_OLD=%s", devpath); envp[0] = devpath_string; envp[1] = NULL; error = sysfs_move_dir_ns(kobj, new_parent, kobject_namespace(kobj)); if (error) goto out; old_parent = kobj->parent; kobj->parent = new_parent; new_parent = NULL; kobject_put(old_parent); kobject_uevent_env(kobj, KOBJ_MOVE, envp); out: kobject_put(new_parent); kobject_put(kobj); kfree(devpath_string); kfree(devpath); return error; } EXPORT_SYMBOL_GPL(kobject_move); static void __kobject_del(struct kobject *kobj) { struct kernfs_node *sd; const struct kobj_type *ktype; sd = kobj->sd; ktype = get_ktype(kobj); if (ktype) sysfs_remove_groups(kobj, ktype->default_groups); /* send "remove" if the caller did not do it but sent "add" */ if (kobj->state_add_uevent_sent && !kobj->state_remove_uevent_sent) { pr_debug("'%s' (%p): auto cleanup 'remove' event\n", kobject_name(kobj), kobj); kobject_uevent(kobj, KOBJ_REMOVE); } sysfs_remove_dir(kobj); sysfs_put(sd); kobj->state_in_sysfs = 0; kobj_kset_leave(kobj); kobj->parent = NULL; } /** * kobject_del() - Unlink kobject from hierarchy. * @kobj: object. * * This is the function that should be called to delete an object * successfully added via kobject_add(). */ void kobject_del(struct kobject *kobj) { struct kobject *parent; if (!kobj) return; parent = kobj->parent; __kobject_del(kobj); kobject_put(parent); } EXPORT_SYMBOL(kobject_del); /** * kobject_get() - Increment refcount for object. * @kobj: object. */ struct kobject *kobject_get(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_get() is being called.\n", kobject_name(kobj), kobj); kref_get(&kobj->kref); } return kobj; } EXPORT_SYMBOL(kobject_get); struct kobject * __must_check kobject_get_unless_zero(struct kobject *kobj) { if (!kobj) return NULL; if (!kref_get_unless_zero(&kobj->kref)) kobj = NULL; return kobj; } EXPORT_SYMBOL(kobject_get_unless_zero); /* * kobject_cleanup - free kobject resources. * @kobj: object to cleanup */ static void kobject_cleanup(struct kobject *kobj) { struct kobject *parent = kobj->parent; const struct kobj_type *t = get_ktype(kobj); const char *name = kobj->name; pr_debug("'%s' (%p): %s, parent %p\n", kobject_name(kobj), kobj, __func__, kobj->parent); if (t && !t->release) pr_debug("'%s' (%p): does not have a release() function, it is broken and must be fixed. See Documentation/core-api/kobject.rst.\n", kobject_name(kobj), kobj); /* remove from sysfs if the caller did not do it */ if (kobj->state_in_sysfs) { pr_debug("'%s' (%p): auto cleanup kobject_del\n", kobject_name(kobj), kobj); __kobject_del(kobj); } else { /* avoid dropping the parent reference unnecessarily */ parent = NULL; } if (t && t->release) { pr_debug("'%s' (%p): calling ktype release\n", kobject_name(kobj), kobj); t->release(kobj); } /* free name if we allocated it */ if (name) { pr_debug("'%s': free name\n", name); kfree_const(name); } kobject_put(parent); } #ifdef CONFIG_DEBUG_KOBJECT_RELEASE static void kobject_delayed_cleanup(struct work_struct *work) { kobject_cleanup(container_of(to_delayed_work(work), struct kobject, release)); } #endif static void kobject_release(struct kref *kref) { struct kobject *kobj = container_of(kref, struct kobject, kref); #ifdef CONFIG_DEBUG_KOBJECT_RELEASE unsigned long delay = HZ + HZ * get_random_u32_below(4); pr_info("'%s' (%p): %s, parent %p (delayed %ld)\n", kobject_name(kobj), kobj, __func__, kobj->parent, delay); INIT_DELAYED_WORK(&kobj->release, kobject_delayed_cleanup); schedule_delayed_work(&kobj->release, delay); #else kobject_cleanup(kobj); #endif } /** * kobject_put() - Decrement refcount for object. * @kobj: object. * * Decrement the refcount, and if 0, call kobject_cleanup(). */ void kobject_put(struct kobject *kobj) { if (kobj) { if (!kobj->state_initialized) WARN(1, KERN_WARNING "kobject: '%s' (%p): is not initialized, yet kobject_put() is being called.\n", kobject_name(kobj), kobj); kref_put(&kobj->kref, kobject_release); } } EXPORT_SYMBOL(kobject_put); static void dynamic_kobj_release(struct kobject *kobj) { pr_debug("(%p): %s\n", kobj, __func__); kfree(kobj); } static const struct kobj_type dynamic_kobj_ktype = { .release = dynamic_kobj_release, .sysfs_ops = &kobj_sysfs_ops, }; /** * kobject_create() - Create a struct kobject dynamically. * * This function creates a kobject structure dynamically and sets it up * to be a "dynamic" kobject with a default release function set up. * * If the kobject was not able to be created, NULL will be returned. * The kobject structure returned from here must be cleaned up with a * call to kobject_put() and not kfree(), as kobject_init() has * already been called on this structure. */ static struct kobject *kobject_create(void) { struct kobject *kobj; kobj = kzalloc(sizeof(*kobj), GFP_KERNEL); if (!kobj) return NULL; kobject_init(kobj, &dynamic_kobj_ktype); return kobj; } /** * kobject_create_and_add() - Create a struct kobject dynamically and * register it with sysfs. * @name: the name for the kobject * @parent: the parent kobject of this kobject, if any. * * This function creates a kobject structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kobject_put() and the structure will be dynamically freed when * it is no longer being used. * * If the kobject was not able to be created, NULL will be returned. */ struct kobject *kobject_create_and_add(const char *name, struct kobject *parent) { struct kobject *kobj; int retval; kobj = kobject_create(); if (!kobj) return NULL; retval = kobject_add(kobj, parent, "%s", name); if (retval) { pr_warn("%s: kobject_add error: %d\n", __func__, retval); kobject_put(kobj); kobj = NULL; } return kobj; } EXPORT_SYMBOL_GPL(kobject_create_and_add); /** * kset_init() - Initialize a kset for use. * @k: kset */ void kset_init(struct kset *k) { kobject_init_internal(&k->kobj); INIT_LIST_HEAD(&k->list); spin_lock_init(&k->list_lock); } /* default kobject attribute operations */ static ssize_t kobj_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->show) ret = kattr->show(kobj, kattr, buf); return ret; } static ssize_t kobj_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct kobj_attribute *kattr; ssize_t ret = -EIO; kattr = container_of(attr, struct kobj_attribute, attr); if (kattr->store) ret = kattr->store(kobj, kattr, buf, count); return ret; } const struct sysfs_ops kobj_sysfs_ops = { .show = kobj_attr_show, .store = kobj_attr_store, }; EXPORT_SYMBOL_GPL(kobj_sysfs_ops); /** * kset_register() - Initialize and add a kset. * @k: kset. * * NOTE: On error, the kset.kobj.name allocated by() kobj_set_name() * is freed, it can not be used any more. */ int kset_register(struct kset *k) { int err; if (!k) return -EINVAL; if (!k->kobj.ktype) { pr_err("must have a ktype to be initialized properly!\n"); return -EINVAL; } kset_init(k); err = kobject_add_internal(&k->kobj); if (err) { kfree_const(k->kobj.name); /* Set it to NULL to avoid accessing bad pointer in callers. */ k->kobj.name = NULL; return err; } kobject_uevent(&k->kobj, KOBJ_ADD); return 0; } EXPORT_SYMBOL(kset_register); /** * kset_unregister() - Remove a kset. * @k: kset. */ void kset_unregister(struct kset *k) { if (!k) return; kobject_del(&k->kobj); kobject_put(&k->kobj); } EXPORT_SYMBOL(kset_unregister); /** * kset_find_obj() - Search for object in kset. * @kset: kset we're looking in. * @name: object's name. * * Lock kset via @kset->subsys, and iterate over @kset->list, * looking for a matching kobject. If matching object is found * take a reference and return the object. */ struct kobject *kset_find_obj(struct kset *kset, const char *name) { struct kobject *k; struct kobject *ret = NULL; spin_lock(&kset->list_lock); list_for_each_entry(k, &kset->list, entry) { if (kobject_name(k) && !strcmp(kobject_name(k), name)) { ret = kobject_get_unless_zero(k); break; } } spin_unlock(&kset->list_lock); return ret; } EXPORT_SYMBOL_GPL(kset_find_obj); static void kset_release(struct kobject *kobj) { struct kset *kset = container_of(kobj, struct kset, kobj); pr_debug("'%s' (%p): %s\n", kobject_name(kobj), kobj, __func__); kfree(kset); } static void kset_get_ownership(const struct kobject *kobj, kuid_t *uid, kgid_t *gid) { if (kobj->parent) kobject_get_ownership(kobj->parent, uid, gid); } static const struct kobj_type kset_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = kset_release, .get_ownership = kset_get_ownership, }; /** * kset_create() - Create a struct kset dynamically. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically. This structure can * then be registered with the system and show up in sysfs with a call to * kset_register(). When you are finished with this structure, if * kset_register() has been called, call kset_unregister() and the * structure will be dynamically freed when it is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ static struct kset *kset_create(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int retval; kset = kzalloc(sizeof(*kset), GFP_KERNEL); if (!kset) return NULL; retval = kobject_set_name(&kset->kobj, "%s", name); if (retval) { kfree(kset); return NULL; } kset->uevent_ops = uevent_ops; kset->kobj.parent = parent_kobj; /* * The kobject of this kset will have a type of kset_ktype and belong to * no kset itself. That way we can properly free it when it is * finished being used. */ kset->kobj.ktype = &kset_ktype; kset->kobj.kset = NULL; return kset; } /** * kset_create_and_add() - Create a struct kset dynamically and add it to sysfs. * * @name: the name for the kset * @uevent_ops: a struct kset_uevent_ops for the kset * @parent_kobj: the parent kobject of this kset, if any. * * This function creates a kset structure dynamically and registers it * with sysfs. When you are finished with this structure, call * kset_unregister() and the structure will be dynamically freed when it * is no longer being used. * * If the kset was not able to be created, NULL will be returned. */ struct kset *kset_create_and_add(const char *name, const struct kset_uevent_ops *uevent_ops, struct kobject *parent_kobj) { struct kset *kset; int error; kset = kset_create(name, uevent_ops, parent_kobj); if (!kset) return NULL; error = kset_register(kset); if (error) { kfree(kset); return NULL; } return kset; } EXPORT_SYMBOL_GPL(kset_create_and_add); static DEFINE_SPINLOCK(kobj_ns_type_lock); static const struct kobj_ns_type_operations *kobj_ns_ops_tbl[KOBJ_NS_TYPES]; int kobj_ns_type_register(const struct kobj_ns_type_operations *ops) { enum kobj_ns_type type = ops->type; int error; spin_lock(&kobj_ns_type_lock); error = -EINVAL; if (!kobj_ns_type_is_valid(type)) goto out; error = -EBUSY; if (kobj_ns_ops_tbl[type]) goto out; error = 0; kobj_ns_ops_tbl[type] = ops; out: spin_unlock(&kobj_ns_type_lock); return error; } int kobj_ns_type_registered(enum kobj_ns_type type) { int registered = 0; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type)) registered = kobj_ns_ops_tbl[type] != NULL; spin_unlock(&kobj_ns_type_lock); return registered; } const struct kobj_ns_type_operations *kobj_child_ns_ops(const struct kobject *parent) { const struct kobj_ns_type_operations *ops = NULL; if (parent && parent->ktype && parent->ktype->child_ns_type) ops = parent->ktype->child_ns_type(parent); return ops; } const struct kobj_ns_type_operations *kobj_ns_ops(const struct kobject *kobj) { return kobj_child_ns_ops(kobj->parent); } bool kobj_ns_current_may_mount(enum kobj_ns_type type) { bool may_mount = true; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) may_mount = kobj_ns_ops_tbl[type]->current_may_mount(); spin_unlock(&kobj_ns_type_lock); return may_mount; } void *kobj_ns_grab_current(enum kobj_ns_type type) { void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->grab_current_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } EXPORT_SYMBOL_GPL(kobj_ns_grab_current); const void *kobj_ns_netlink(enum kobj_ns_type type, struct sock *sk) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->netlink_ns(sk); spin_unlock(&kobj_ns_type_lock); return ns; } const void *kobj_ns_initial(enum kobj_ns_type type) { const void *ns = NULL; spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type]) ns = kobj_ns_ops_tbl[type]->initial_ns(); spin_unlock(&kobj_ns_type_lock); return ns; } void kobj_ns_drop(enum kobj_ns_type type, void *ns) { spin_lock(&kobj_ns_type_lock); if (kobj_ns_type_is_valid(type) && kobj_ns_ops_tbl[type] && kobj_ns_ops_tbl[type]->drop_ns) kobj_ns_ops_tbl[type]->drop_ns(ns); spin_unlock(&kobj_ns_type_lock); } EXPORT_SYMBOL_GPL(kobj_ns_drop); |
| 11 253 11 11 253 269 1 155 155 13 13 13 385 388 385 49 49 383 11 11 271 163 22 151 151 19 148 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org> */ #ifndef __ASM_CPUFEATURE_H #define __ASM_CPUFEATURE_H #include <asm/alternative-macros.h> #include <asm/cpucaps.h> #include <asm/cputype.h> #include <asm/hwcap.h> #include <asm/sysreg.h> #define MAX_CPU_FEATURES 128 #define cpu_feature(x) KERNEL_HWCAP_ ## x #define ARM64_SW_FEATURE_OVERRIDE_NOKASLR 0 #define ARM64_SW_FEATURE_OVERRIDE_HVHE 4 #define ARM64_SW_FEATURE_OVERRIDE_RODATA_OFF 8 #ifndef __ASSEMBLY__ #include <linux/bug.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/cpumask.h> /* * CPU feature register tracking * * The safe value of a CPUID feature field is dependent on the implications * of the values assigned to it by the architecture. Based on the relationship * between the values, the features are classified into 3 types - LOWER_SAFE, * HIGHER_SAFE and EXACT. * * The lowest value of all the CPUs is chosen for LOWER_SAFE and highest * for HIGHER_SAFE. It is expected that all CPUs have the same value for * a field when EXACT is specified, failing which, the safe value specified * in the table is chosen. */ enum ftr_type { FTR_EXACT, /* Use a predefined safe value */ FTR_LOWER_SAFE, /* Smaller value is safe */ FTR_HIGHER_SAFE, /* Bigger value is safe */ FTR_HIGHER_OR_ZERO_SAFE, /* Bigger value is safe, but 0 is biggest */ }; #define FTR_STRICT true /* SANITY check strict matching required */ #define FTR_NONSTRICT false /* SANITY check ignored */ #define FTR_SIGNED true /* Value should be treated as signed */ #define FTR_UNSIGNED false /* Value should be treated as unsigned */ #define FTR_VISIBLE true /* Feature visible to the user space */ #define FTR_HIDDEN false /* Feature is hidden from the user */ #define FTR_VISIBLE_IF_IS_ENABLED(config) \ (IS_ENABLED(config) ? FTR_VISIBLE : FTR_HIDDEN) struct arm64_ftr_bits { bool sign; /* Value is signed ? */ bool visible; bool strict; /* CPU Sanity check: strict matching required ? */ enum ftr_type type; u8 shift; u8 width; s64 safe_val; /* safe value for FTR_EXACT features */ }; /* * Describe the early feature override to the core override code: * * @val Values that are to be merged into the final * sanitised value of the register. Only the bitfields * set to 1 in @mask are valid * @mask Mask of the features that are overridden by @val * * A @mask field set to full-1 indicates that the corresponding field * in @val is a valid override. * * A @mask field set to full-0 with the corresponding @val field set * to full-0 denotes that this field has no override * * A @mask field set to full-0 with the corresponding @val field set * to full-1 denotes that this field has an invalid override. */ struct arm64_ftr_override { u64 val; u64 mask; }; /* * @arm64_ftr_reg - Feature register * @strict_mask Bits which should match across all CPUs for sanity. * @sys_val Safe value across the CPUs (system view) */ struct arm64_ftr_reg { const char *name; u64 strict_mask; u64 user_mask; u64 sys_val; u64 user_val; struct arm64_ftr_override *override; const struct arm64_ftr_bits *ftr_bits; }; extern struct arm64_ftr_reg arm64_ftr_reg_ctrel0; /* * CPU capabilities: * * We use arm64_cpu_capabilities to represent system features, errata work * arounds (both used internally by kernel and tracked in system_cpucaps) and * ELF HWCAPs (which are exposed to user). * * To support systems with heterogeneous CPUs, we need to make sure that we * detect the capabilities correctly on the system and take appropriate * measures to ensure there are no incompatibilities. * * This comment tries to explain how we treat the capabilities. * Each capability has the following list of attributes : * * 1) Scope of Detection : The system detects a given capability by * performing some checks at runtime. This could be, e.g, checking the * value of a field in CPU ID feature register or checking the cpu * model. The capability provides a call back ( @matches() ) to * perform the check. Scope defines how the checks should be performed. * There are three cases: * * a) SCOPE_LOCAL_CPU: check all the CPUs and "detect" if at least one * matches. This implies, we have to run the check on all the * booting CPUs, until the system decides that state of the * capability is finalised. (See section 2 below) * Or * b) SCOPE_SYSTEM: check all the CPUs and "detect" if all the CPUs * matches. This implies, we run the check only once, when the * system decides to finalise the state of the capability. If the * capability relies on a field in one of the CPU ID feature * registers, we use the sanitised value of the register from the * CPU feature infrastructure to make the decision. * Or * c) SCOPE_BOOT_CPU: Check only on the primary boot CPU to detect the * feature. This category is for features that are "finalised" * (or used) by the kernel very early even before the SMP cpus * are brought up. * * The process of detection is usually denoted by "update" capability * state in the code. * * 2) Finalise the state : The kernel should finalise the state of a * capability at some point during its execution and take necessary * actions if any. Usually, this is done, after all the boot-time * enabled CPUs are brought up by the kernel, so that it can make * better decision based on the available set of CPUs. However, there * are some special cases, where the action is taken during the early * boot by the primary boot CPU. (e.g, running the kernel at EL2 with * Virtualisation Host Extensions). The kernel usually disallows any * changes to the state of a capability once it finalises the capability * and takes any action, as it may be impossible to execute the actions * safely. A CPU brought up after a capability is "finalised" is * referred to as "Late CPU" w.r.t the capability. e.g, all secondary * CPUs are treated "late CPUs" for capabilities determined by the boot * CPU. * * At the moment there are two passes of finalising the capabilities. * a) Boot CPU scope capabilities - Finalised by primary boot CPU via * setup_boot_cpu_capabilities(). * b) Everything except (a) - Run via setup_system_capabilities(). * * 3) Verification: When a CPU is brought online (e.g, by user or by the * kernel), the kernel should make sure that it is safe to use the CPU, * by verifying that the CPU is compliant with the state of the * capabilities finalised already. This happens via : * * secondary_start_kernel()-> check_local_cpu_capabilities() * * As explained in (2) above, capabilities could be finalised at * different points in the execution. Each newly booted CPU is verified * against the capabilities that have been finalised by the time it * boots. * * a) SCOPE_BOOT_CPU : All CPUs are verified against the capability * except for the primary boot CPU. * * b) SCOPE_LOCAL_CPU, SCOPE_SYSTEM: All CPUs hotplugged on by the * user after the kernel boot are verified against the capability. * * If there is a conflict, the kernel takes an action, based on the * severity (e.g, a CPU could be prevented from booting or cause a * kernel panic). The CPU is allowed to "affect" the state of the * capability, if it has not been finalised already. See section 5 * for more details on conflicts. * * 4) Action: As mentioned in (2), the kernel can take an action for each * detected capability, on all CPUs on the system. Appropriate actions * include, turning on an architectural feature, modifying the control * registers (e.g, SCTLR, TCR etc.) or patching the kernel via * alternatives. The kernel patching is batched and performed at later * point. The actions are always initiated only after the capability * is finalised. This is usally denoted by "enabling" the capability. * The actions are initiated as follows : * a) Action is triggered on all online CPUs, after the capability is * finalised, invoked within the stop_machine() context from * enable_cpu_capabilitie(). * * b) Any late CPU, brought up after (1), the action is triggered via: * * check_local_cpu_capabilities() -> verify_local_cpu_capabilities() * * 5) Conflicts: Based on the state of the capability on a late CPU vs. * the system state, we could have the following combinations : * * x-----------------------------x * | Type | System | Late CPU | * |-----------------------------| * | a | y | n | * |-----------------------------| * | b | n | y | * x-----------------------------x * * Two separate flag bits are defined to indicate whether each kind of * conflict can be allowed: * ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU - Case(a) is allowed * ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU - Case(b) is allowed * * Case (a) is not permitted for a capability that the system requires * all CPUs to have in order for the capability to be enabled. This is * typical for capabilities that represent enhanced functionality. * * Case (b) is not permitted for a capability that must be enabled * during boot if any CPU in the system requires it in order to run * safely. This is typical for erratum work arounds that cannot be * enabled after the corresponding capability is finalised. * * In some non-typical cases either both (a) and (b), or neither, * should be permitted. This can be described by including neither * or both flags in the capability's type field. * * In case of a conflict, the CPU is prevented from booting. If the * ARM64_CPUCAP_PANIC_ON_CONFLICT flag is specified for the capability, * then a kernel panic is triggered. */ /* * Decide how the capability is detected. * On any local CPU vs System wide vs the primary boot CPU */ #define ARM64_CPUCAP_SCOPE_LOCAL_CPU ((u16)BIT(0)) #define ARM64_CPUCAP_SCOPE_SYSTEM ((u16)BIT(1)) /* * The capabilitiy is detected on the Boot CPU and is used by kernel * during early boot. i.e, the capability should be "detected" and * "enabled" as early as possibly on all booting CPUs. */ #define ARM64_CPUCAP_SCOPE_BOOT_CPU ((u16)BIT(2)) #define ARM64_CPUCAP_SCOPE_MASK \ (ARM64_CPUCAP_SCOPE_SYSTEM | \ ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_SCOPE_BOOT_CPU) #define SCOPE_SYSTEM ARM64_CPUCAP_SCOPE_SYSTEM #define SCOPE_LOCAL_CPU ARM64_CPUCAP_SCOPE_LOCAL_CPU #define SCOPE_BOOT_CPU ARM64_CPUCAP_SCOPE_BOOT_CPU #define SCOPE_ALL ARM64_CPUCAP_SCOPE_MASK /* * Is it permitted for a late CPU to have this capability when system * hasn't already enabled it ? */ #define ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU ((u16)BIT(4)) /* Is it safe for a late CPU to miss this capability when system has it */ #define ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU ((u16)BIT(5)) /* Panic when a conflict is detected */ #define ARM64_CPUCAP_PANIC_ON_CONFLICT ((u16)BIT(6)) /* * CPU errata workarounds that need to be enabled at boot time if one or * more CPUs in the system requires it. When one of these capabilities * has been enabled, it is safe to allow any CPU to boot that doesn't * require the workaround. However, it is not safe if a "late" CPU * requires a workaround and the system hasn't enabled it already. */ #define ARM64_CPUCAP_LOCAL_CPU_ERRATUM \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) /* * CPU feature detected at boot time based on system-wide value of a * feature. It is safe for a late CPU to have this feature even though * the system hasn't enabled it, although the feature will not be used * by Linux in this case. If the system has enabled this feature already, * then every late CPU must have it. */ #define ARM64_CPUCAP_SYSTEM_FEATURE \ (ARM64_CPUCAP_SCOPE_SYSTEM | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) /* * CPU feature detected at boot time based on feature of one or more CPUs. * All possible conflicts for a late CPU are ignored. * NOTE: this means that a late CPU with the feature will *not* cause the * capability to be advertised by cpus_have_*cap()! */ #define ARM64_CPUCAP_WEAK_LOCAL_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU | \ ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) /* * CPU feature detected at boot time, on one or more CPUs. A late CPU * is not allowed to have the capability when the system doesn't have it. * It is Ok for a late CPU to miss the feature. */ #define ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE \ (ARM64_CPUCAP_SCOPE_LOCAL_CPU | \ ARM64_CPUCAP_OPTIONAL_FOR_LATE_CPU) /* * CPU feature used early in the boot based on the boot CPU. All secondary * CPUs must match the state of the capability as detected by the boot CPU. In * case of a conflict, a kernel panic is triggered. */ #define ARM64_CPUCAP_STRICT_BOOT_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PANIC_ON_CONFLICT) /* * CPU feature used early in the boot based on the boot CPU. It is safe for a * late CPU to have this feature even though the boot CPU hasn't enabled it, * although the feature will not be used by Linux in this case. If the boot CPU * has enabled this feature already, then every late CPU must have it. */ #define ARM64_CPUCAP_BOOT_CPU_FEATURE \ (ARM64_CPUCAP_SCOPE_BOOT_CPU | ARM64_CPUCAP_PERMITTED_FOR_LATE_CPU) struct arm64_cpu_capabilities { const char *desc; u16 capability; u16 type; bool (*matches)(const struct arm64_cpu_capabilities *caps, int scope); /* * Take the appropriate actions to configure this capability * for this CPU. If the capability is detected by the kernel * this will be called on all the CPUs in the system, * including the hotplugged CPUs, regardless of whether the * capability is available on that specific CPU. This is * useful for some capabilities (e.g, working around CPU * errata), where all the CPUs must take some action (e.g, * changing system control/configuration). Thus, if an action * is required only if the CPU has the capability, then the * routine must check it before taking any action. */ void (*cpu_enable)(const struct arm64_cpu_capabilities *cap); union { struct { /* To be used for erratum handling only */ struct midr_range midr_range; const struct arm64_midr_revidr { u32 midr_rv; /* revision/variant */ u32 revidr_mask; } * const fixed_revs; }; const struct midr_range *midr_range_list; struct { /* Feature register checking */ u32 sys_reg; u8 field_pos; u8 field_width; u8 min_field_value; u8 max_field_value; u8 hwcap_type; bool sign; unsigned long hwcap; }; }; /* * An optional list of "matches/cpu_enable" pair for the same * "capability" of the same "type" as described by the parent. * Only matches(), cpu_enable() and fields relevant to these * methods are significant in the list. The cpu_enable is * invoked only if the corresponding entry "matches()". * However, if a cpu_enable() method is associated * with multiple matches(), care should be taken that either * the match criteria are mutually exclusive, or that the * method is robust against being called multiple times. */ const struct arm64_cpu_capabilities *match_list; const struct cpumask *cpus; }; static inline int cpucap_default_scope(const struct arm64_cpu_capabilities *cap) { return cap->type & ARM64_CPUCAP_SCOPE_MASK; } /* * Generic helper for handling capabilities with multiple (match,enable) pairs * of call backs, sharing the same capability bit. * Iterate over each entry to see if at least one matches. */ static inline bool cpucap_multi_entry_cap_matches(const struct arm64_cpu_capabilities *entry, int scope) { const struct arm64_cpu_capabilities *caps; for (caps = entry->match_list; caps->matches; caps++) if (caps->matches(caps, scope)) return true; return false; } static __always_inline bool is_vhe_hyp_code(void) { /* Only defined for code run in VHE hyp context */ return __is_defined(__KVM_VHE_HYPERVISOR__); } static __always_inline bool is_nvhe_hyp_code(void) { /* Only defined for code run in NVHE hyp context */ return __is_defined(__KVM_NVHE_HYPERVISOR__); } static __always_inline bool is_hyp_code(void) { return is_vhe_hyp_code() || is_nvhe_hyp_code(); } extern DECLARE_BITMAP(system_cpucaps, ARM64_NCAPS); extern DECLARE_BITMAP(boot_cpucaps, ARM64_NCAPS); #define for_each_available_cap(cap) \ for_each_set_bit(cap, system_cpucaps, ARM64_NCAPS) bool this_cpu_has_cap(unsigned int cap); void cpu_set_feature(unsigned int num); bool cpu_have_feature(unsigned int num); unsigned long cpu_get_elf_hwcap(void); unsigned long cpu_get_elf_hwcap2(void); #define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name)) #define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name)) static __always_inline bool boot_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_BOOT); } static __always_inline bool system_capabilities_finalized(void) { return alternative_has_cap_likely(ARM64_ALWAYS_SYSTEM); } /* * Test for a capability with a runtime check. * * Before the capability is detected, this returns false. */ static __always_inline bool cpus_have_cap(unsigned int num) { if (__builtin_constant_p(num) && !cpucap_is_possible(num)) return false; if (num >= ARM64_NCAPS) return false; return arch_test_bit(num, system_cpucaps); } /* * Test for a capability without a runtime check. * * Before boot capabilities are finalized, this will BUG(). * After boot capabilities are finalized, this is patched to avoid a runtime * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_boot_cap(int num) { if (boot_capabilities_finalized()) return alternative_has_cap_unlikely(num); else BUG(); } /* * Test for a capability without a runtime check. * * Before system capabilities are finalized, this will BUG(). * After system capabilities are finalized, this is patched to avoid a runtime * check. * * @num must be a compile-time constant. */ static __always_inline bool cpus_have_final_cap(int num) { if (system_capabilities_finalized()) return alternative_has_cap_unlikely(num); else BUG(); } static inline int __attribute_const__ cpuid_feature_extract_signed_field_width(u64 features, int field, int width) { return (s64)(features << (64 - width - field)) >> (64 - width); } static inline int __attribute_const__ cpuid_feature_extract_signed_field(u64 features, int field) { return cpuid_feature_extract_signed_field_width(features, field, 4); } static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field_width(u64 features, int field, int width) { return (u64)(features << (64 - width - field)) >> (64 - width); } static __always_inline unsigned int __attribute_const__ cpuid_feature_extract_unsigned_field(u64 features, int field) { return cpuid_feature_extract_unsigned_field_width(features, field, 4); } /* * Fields that identify the version of the Performance Monitors Extension do * not follow the standard ID scheme. See ARM DDI 0487E.a page D13-2825, * "Alternative ID scheme used for the Performance Monitors Extension version". */ static inline u64 __attribute_const__ cpuid_feature_cap_perfmon_field(u64 features, int field, u64 cap) { u64 val = cpuid_feature_extract_unsigned_field(features, field); u64 mask = GENMASK_ULL(field + 3, field); /* Treat IMPLEMENTATION DEFINED functionality as unimplemented */ if (val == ID_AA64DFR0_EL1_PMUVer_IMP_DEF) val = 0; if (val > cap) { features &= ~mask; features |= (cap << field) & mask; } return features; } static inline u64 arm64_ftr_mask(const struct arm64_ftr_bits *ftrp) { return (u64)GENMASK(ftrp->shift + ftrp->width - 1, ftrp->shift); } static inline u64 arm64_ftr_reg_user_value(const struct arm64_ftr_reg *reg) { return (reg->user_val | (reg->sys_val & reg->user_mask)); } static inline int __attribute_const__ cpuid_feature_extract_field_width(u64 features, int field, int width, bool sign) { if (WARN_ON_ONCE(!width)) width = 4; return (sign) ? cpuid_feature_extract_signed_field_width(features, field, width) : cpuid_feature_extract_unsigned_field_width(features, field, width); } static inline int __attribute_const__ cpuid_feature_extract_field(u64 features, int field, bool sign) { return cpuid_feature_extract_field_width(features, field, 4, sign); } static inline s64 arm64_ftr_value(const struct arm64_ftr_bits *ftrp, u64 val) { return (s64)cpuid_feature_extract_field_width(val, ftrp->shift, ftrp->width, ftrp->sign); } static inline bool id_aa64mmfr0_mixed_endian_el0(u64 mmfr0) { return cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT) == 0x1 || cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGENDEL0_SHIFT) == 0x1; } static inline bool id_aa64pfr0_32bit_el1(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL1_SHIFT); return val == ID_AA64PFR0_EL1_ELx_32BIT_64BIT; } static inline bool id_aa64pfr0_32bit_el0(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_EL0_SHIFT); return val == ID_AA64PFR0_EL1_ELx_32BIT_64BIT; } static inline bool id_aa64pfr0_sve(u64 pfr0) { u32 val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_SVE_SHIFT); return val > 0; } static inline bool id_aa64pfr1_sme(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_SME_SHIFT); return val > 0; } static inline bool id_aa64pfr1_mte(u64 pfr1) { u32 val = cpuid_feature_extract_unsigned_field(pfr1, ID_AA64PFR1_EL1_MTE_SHIFT); return val >= ID_AA64PFR1_EL1_MTE_MTE2; } void __init setup_boot_cpu_features(void); void __init setup_system_features(void); void __init setup_user_features(void); void check_local_cpu_capabilities(void); u64 read_sanitised_ftr_reg(u32 id); u64 __read_sysreg_by_encoding(u32 sys_id); static inline bool cpu_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_cpuid(ID_AA64MMFR0_EL1)); } static inline bool supports_csv2p3(int scope) { u64 pfr0; u8 csv2_val; if (scope == SCOPE_LOCAL_CPU) pfr0 = read_sysreg_s(SYS_ID_AA64PFR0_EL1); else pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); csv2_val = cpuid_feature_extract_unsigned_field(pfr0, ID_AA64PFR0_EL1_CSV2_SHIFT); return csv2_val == 3; } static inline bool supports_clearbhb(int scope) { u64 isar2; if (scope == SCOPE_LOCAL_CPU) isar2 = read_sysreg_s(SYS_ID_AA64ISAR2_EL1); else isar2 = read_sanitised_ftr_reg(SYS_ID_AA64ISAR2_EL1); return cpuid_feature_extract_unsigned_field(isar2, ID_AA64ISAR2_EL1_CLRBHB_SHIFT); } const struct cpumask *system_32bit_el0_cpumask(void); DECLARE_STATIC_KEY_FALSE(arm64_mismatched_32bit_el0); static inline bool system_supports_32bit_el0(void) { u64 pfr0 = read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1); return static_branch_unlikely(&arm64_mismatched_32bit_el0) || id_aa64pfr0_32bit_el0(pfr0); } static inline bool system_supports_4kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN4_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN4_SUPPORTED_MAX); } static inline bool system_supports_64kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN64_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN64_SUPPORTED_MAX); } static inline bool system_supports_16kb_granule(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN16_SHIFT); return (val >= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MIN) && (val <= ID_AA64MMFR0_EL1_TGRAN16_SUPPORTED_MAX); } static inline bool system_supports_mixed_endian_el0(void) { return id_aa64mmfr0_mixed_endian_el0(read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1)); } static inline bool system_supports_mixed_endian(void) { u64 mmfr0; u32 val; mmfr0 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR0_EL1); val = cpuid_feature_extract_unsigned_field(mmfr0, ID_AA64MMFR0_EL1_BIGEND_SHIFT); return val == 0x1; } static __always_inline bool system_supports_fpsimd(void) { return alternative_has_cap_likely(ARM64_HAS_FPSIMD); } static inline bool system_uses_hw_pan(void) { return alternative_has_cap_unlikely(ARM64_HAS_PAN); } static inline bool system_uses_ttbr0_pan(void) { return IS_ENABLED(CONFIG_ARM64_SW_TTBR0_PAN) && !system_uses_hw_pan(); } static __always_inline bool system_supports_sve(void) { return alternative_has_cap_unlikely(ARM64_SVE); } static __always_inline bool system_supports_sme(void) { return alternative_has_cap_unlikely(ARM64_SME); } static __always_inline bool system_supports_sme2(void) { return alternative_has_cap_unlikely(ARM64_SME2); } static __always_inline bool system_supports_fa64(void) { return alternative_has_cap_unlikely(ARM64_SME_FA64); } static __always_inline bool system_supports_tpidr2(void) { return system_supports_sme(); } static __always_inline bool system_supports_fpmr(void) { return alternative_has_cap_unlikely(ARM64_HAS_FPMR); } static __always_inline bool system_supports_cnp(void) { return alternative_has_cap_unlikely(ARM64_HAS_CNP); } static inline bool system_supports_address_auth(void) { return cpus_have_final_boot_cap(ARM64_HAS_ADDRESS_AUTH); } static inline bool system_supports_generic_auth(void) { return alternative_has_cap_unlikely(ARM64_HAS_GENERIC_AUTH); } static inline bool system_has_full_ptr_auth(void) { return system_supports_address_auth() && system_supports_generic_auth(); } static __always_inline bool system_uses_irq_prio_masking(void) { return alternative_has_cap_unlikely(ARM64_HAS_GIC_PRIO_MASKING); } static inline bool system_supports_mte(void) { return alternative_has_cap_unlikely(ARM64_MTE); } static inline bool system_has_prio_mask_debugging(void) { return IS_ENABLED(CONFIG_ARM64_DEBUG_PRIORITY_MASKING) && system_uses_irq_prio_masking(); } static inline bool system_supports_bti(void) { return cpus_have_final_cap(ARM64_BTI); } static inline bool system_supports_bti_kernel(void) { return IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) && cpus_have_final_boot_cap(ARM64_BTI); } static inline bool system_supports_tlb_range(void) { return alternative_has_cap_unlikely(ARM64_HAS_TLB_RANGE); } static inline bool system_supports_lpa2(void) { return cpus_have_final_cap(ARM64_HAS_LPA2); } int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt); bool try_emulate_mrs(struct pt_regs *regs, u32 isn); static inline u32 id_aa64mmfr0_parange_to_phys_shift(int parange) { switch (parange) { case ID_AA64MMFR0_EL1_PARANGE_32: return 32; case ID_AA64MMFR0_EL1_PARANGE_36: return 36; case ID_AA64MMFR0_EL1_PARANGE_40: return 40; case ID_AA64MMFR0_EL1_PARANGE_42: return 42; case ID_AA64MMFR0_EL1_PARANGE_44: return 44; case ID_AA64MMFR0_EL1_PARANGE_48: return 48; case ID_AA64MMFR0_EL1_PARANGE_52: return 52; /* * A future PE could use a value unknown to the kernel. * However, by the "D10.1.4 Principles of the ID scheme * for fields in ID registers", ARM DDI 0487C.a, any new * value is guaranteed to be higher than what we know already. * As a safe limit, we return the limit supported by the kernel. */ default: return CONFIG_ARM64_PA_BITS; } } /* Check whether hardware update of the Access flag is supported */ static inline bool cpu_has_hw_af(void) { u64 mmfr1; if (!IS_ENABLED(CONFIG_ARM64_HW_AFDBM)) return false; /* * Use cached version to avoid emulated msr operation on KVM * guests. */ mmfr1 = read_sanitised_ftr_reg(SYS_ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_HAFDBS_SHIFT); } static inline bool cpu_has_pan(void) { u64 mmfr1 = read_cpuid(ID_AA64MMFR1_EL1); return cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_PAN_SHIFT); } #ifdef CONFIG_ARM64_AMU_EXTN /* Check whether the cpu supports the Activity Monitors Unit (AMU) */ extern bool cpu_has_amu_feat(int cpu); #else static inline bool cpu_has_amu_feat(int cpu) { return false; } #endif /* Get a cpu that supports the Activity Monitors Unit (AMU) */ extern int get_cpu_with_amu_feat(void); static inline unsigned int get_vmid_bits(u64 mmfr1) { int vmid_bits; vmid_bits = cpuid_feature_extract_unsigned_field(mmfr1, ID_AA64MMFR1_EL1_VMIDBits_SHIFT); if (vmid_bits == ID_AA64MMFR1_EL1_VMIDBits_16) return 16; /* * Return the default here even if any reserved * value is fetched from the system register. */ return 8; } s64 arm64_ftr_safe_value(const struct arm64_ftr_bits *ftrp, s64 new, s64 cur); struct arm64_ftr_reg *get_arm64_ftr_reg(u32 sys_id); extern struct arm64_ftr_override id_aa64mmfr0_override; extern struct arm64_ftr_override id_aa64mmfr1_override; extern struct arm64_ftr_override id_aa64mmfr2_override; extern struct arm64_ftr_override id_aa64pfr0_override; extern struct arm64_ftr_override id_aa64pfr1_override; extern struct arm64_ftr_override id_aa64zfr0_override; extern struct arm64_ftr_override id_aa64smfr0_override; extern struct arm64_ftr_override id_aa64isar1_override; extern struct arm64_ftr_override id_aa64isar2_override; extern struct arm64_ftr_override arm64_sw_feature_override; static inline u64 arm64_apply_feature_override(u64 val, int feat, int width, const struct arm64_ftr_override *override) { u64 oval = override->val; /* * When it encounters an invalid override (e.g., an override that * cannot be honoured due to a missing CPU feature), the early idreg * override code will set the mask to 0x0 and the value to non-zero for * the field in question. In order to determine whether the override is * valid or not for the field we are interested in, we first need to * disregard bits belonging to other fields. */ oval &= GENMASK_ULL(feat + width - 1, feat); /* * The override is valid if all value bits are accounted for in the * mask. If so, replace the masked bits with the override value. */ if (oval == (oval & override->mask)) { val &= ~override->mask; val |= oval; } /* Extract the field from the updated value */ return cpuid_feature_extract_unsigned_field(val, feat); } static inline bool arm64_test_sw_feature_override(int feat) { /* * Software features are pseudo CPU features that have no underlying * CPUID system register value to apply the override to. */ return arm64_apply_feature_override(0, feat, 4, &arm64_sw_feature_override); } static inline bool kaslr_disabled_cmdline(void) { return arm64_test_sw_feature_override(ARM64_SW_FEATURE_OVERRIDE_NOKASLR); } u32 get_kvm_ipa_limit(void); void dump_cpu_features(void); static inline bool cpu_has_bti(void) { if (!IS_ENABLED(CONFIG_ARM64_BTI)) return false; return arm64_apply_feature_override(read_cpuid(ID_AA64PFR1_EL1), ID_AA64PFR1_EL1_BT_SHIFT, 4, &id_aa64pfr1_override); } static inline bool cpu_has_pac(void) { u64 isar1, isar2; if (!IS_ENABLED(CONFIG_ARM64_PTR_AUTH)) return false; isar1 = read_cpuid(ID_AA64ISAR1_EL1); isar2 = read_cpuid(ID_AA64ISAR2_EL1); if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_APA_SHIFT, 4, &id_aa64isar1_override)) return true; if (arm64_apply_feature_override(isar1, ID_AA64ISAR1_EL1_API_SHIFT, 4, &id_aa64isar1_override)) return true; return arm64_apply_feature_override(isar2, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, &id_aa64isar2_override); } static inline bool cpu_has_lva(void) { u64 mmfr2; mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); mmfr2 &= ~id_aa64mmfr2_override.mask; mmfr2 |= id_aa64mmfr2_override.val; return cpuid_feature_extract_unsigned_field(mmfr2, ID_AA64MMFR2_EL1_VARange_SHIFT); } static inline bool cpu_has_lpa2(void) { #ifdef CONFIG_ARM64_LPA2 u64 mmfr0; int feat; mmfr0 = read_sysreg(id_aa64mmfr0_el1); mmfr0 &= ~id_aa64mmfr0_override.mask; mmfr0 |= id_aa64mmfr0_override.val; feat = cpuid_feature_extract_signed_field(mmfr0, ID_AA64MMFR0_EL1_TGRAN_SHIFT); return feat >= ID_AA64MMFR0_EL1_TGRAN_LPA2; #else return false; #endif } #endif /* __ASSEMBLY__ */ #endif |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM filemap #if !defined(_TRACE_FILEMAP_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_FILEMAP_H #include <linux/types.h> #include <linux/tracepoint.h> #include <linux/mm.h> #include <linux/memcontrol.h> #include <linux/device.h> #include <linux/kdev_t.h> #include <linux/errseq.h> DECLARE_EVENT_CLASS(mm_filemap_op_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio), TP_STRUCT__entry( __field(unsigned long, pfn) __field(unsigned long, i_ino) __field(unsigned long, index) __field(dev_t, s_dev) __field(unsigned char, order) ), TP_fast_assign( __entry->pfn = folio_pfn(folio); __entry->i_ino = folio->mapping->host->i_ino; __entry->index = folio->index; if (folio->mapping->host->i_sb) __entry->s_dev = folio->mapping->host->i_sb->s_dev; else __entry->s_dev = folio->mapping->host->i_rdev; __entry->order = folio_order(folio); ), TP_printk("dev %d:%d ino %lx pfn=0x%lx ofs=%lu order=%u", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->pfn, __entry->index << PAGE_SHIFT, __entry->order) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_delete_from_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); DEFINE_EVENT(mm_filemap_op_page_cache, mm_filemap_add_to_page_cache, TP_PROTO(struct folio *folio), TP_ARGS(folio) ); TRACE_EVENT(filemap_set_wb_err, TP_PROTO(struct address_space *mapping, errseq_t eseq), TP_ARGS(mapping, eseq), TP_STRUCT__entry( __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, errseq) ), TP_fast_assign( __entry->i_ino = mapping->host->i_ino; __entry->errseq = eseq; if (mapping->host->i_sb) __entry->s_dev = mapping->host->i_sb->s_dev; else __entry->s_dev = mapping->host->i_rdev; ), TP_printk("dev=%d:%d ino=0x%lx errseq=0x%x", MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->errseq) ); TRACE_EVENT(file_check_and_advance_wb_err, TP_PROTO(struct file *file, errseq_t old), TP_ARGS(file, old), TP_STRUCT__entry( __field(struct file *, file) __field(unsigned long, i_ino) __field(dev_t, s_dev) __field(errseq_t, old) __field(errseq_t, new) ), TP_fast_assign( __entry->file = file; __entry->i_ino = file->f_mapping->host->i_ino; if (file->f_mapping->host->i_sb) __entry->s_dev = file->f_mapping->host->i_sb->s_dev; else __entry->s_dev = file->f_mapping->host->i_rdev; __entry->old = old; __entry->new = file->f_wb_err; ), TP_printk("file=%p dev=%d:%d ino=0x%lx old=0x%x new=0x%x", __entry->file, MAJOR(__entry->s_dev), MINOR(__entry->s_dev), __entry->i_ino, __entry->old, __entry->new) ); #endif /* _TRACE_FILEMAP_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 187 316 56 104 322 17 79 42 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_SPINLOCK_H #define __LINUX_SPINLOCK_H #define __LINUX_INSIDE_SPINLOCK_H /* * include/linux/spinlock.h - generic spinlock/rwlock declarations * * here's the role of the various spinlock/rwlock related include files: * * on SMP builds: * * asm/spinlock_types.h: contains the arch_spinlock_t/arch_rwlock_t and the * initializers * * linux/spinlock_types_raw: * The raw types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * asm/spinlock.h: contains the arch_spin_*()/etc. lowlevel * implementations, mostly inline assembly code * * (also included on UP-debug builds:) * * linux/spinlock_api_smp.h: * contains the prototypes for the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. * * on UP builds: * * linux/spinlock_type_up.h: * contains the generic, simplified UP spinlock type. * (which is an empty structure on non-debug builds) * * linux/spinlock_types_raw: * The raw RT types and initializers * linux/spinlock_types.h: * defines the generic type and initializers * * linux/spinlock_up.h: * contains the arch_spin_*()/etc. version of UP * builds. (which are NOPs on non-debug, non-preempt * builds) * * (included on UP-non-debug builds:) * * linux/spinlock_api_up.h: * builds the _spin_*() APIs. * * linux/spinlock.h: builds the final spin_*() APIs. */ #include <linux/typecheck.h> #include <linux/preempt.h> #include <linux/linkage.h> #include <linux/compiler.h> #include <linux/irqflags.h> #include <linux/thread_info.h> #include <linux/stringify.h> #include <linux/bottom_half.h> #include <linux/lockdep.h> #include <linux/cleanup.h> #include <asm/barrier.h> #include <asm/mmiowb.h> /* * Must define these before including other files, inline functions need them */ #define LOCK_SECTION_NAME ".text..lock."KBUILD_BASENAME #define LOCK_SECTION_START(extra) \ ".subsection 1\n\t" \ extra \ ".ifndef " LOCK_SECTION_NAME "\n\t" \ LOCK_SECTION_NAME ":\n\t" \ ".endif\n" #define LOCK_SECTION_END \ ".previous\n\t" #define __lockfunc __section(".spinlock.text") /* * Pull the arch_spinlock_t and arch_rwlock_t definitions: */ #include <linux/spinlock_types.h> /* * Pull the arch_spin*() functions/declarations (UP-nondebug doesn't need them): */ #ifdef CONFIG_SMP # include <asm/spinlock.h> #else # include <linux/spinlock_up.h> #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name, struct lock_class_key *key, short inner); # define raw_spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init((lock), #lock, &__key, LD_WAIT_SPIN); \ } while (0) #else # define raw_spin_lock_init(lock) \ do { *(lock) = __RAW_SPIN_LOCK_UNLOCKED(lock); } while (0) #endif #define raw_spin_is_locked(lock) arch_spin_is_locked(&(lock)->raw_lock) #ifdef arch_spin_is_contended #define raw_spin_is_contended(lock) arch_spin_is_contended(&(lock)->raw_lock) #else #define raw_spin_is_contended(lock) (((void)(lock), 0)) #endif /*arch_spin_is_contended*/ /* * smp_mb__after_spinlock() provides the equivalent of a full memory barrier * between program-order earlier lock acquisitions and program-order later * memory accesses. * * This guarantees that the following two properties hold: * * 1) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 * * WRITE_ONCE(X, 1); WRITE_ONCE(Y, 1); * spin_lock(S); smp_mb(); * smp_mb__after_spinlock(); r1 = READ_ONCE(X); * r0 = READ_ONCE(Y); * spin_unlock(S); * * it is forbidden that CPU0 does not observe CPU1's store to Y (r0 = 0) * and CPU1 does not observe CPU0's store to X (r1 = 0); see the comments * preceding the call to smp_mb__after_spinlock() in __schedule() and in * try_to_wake_up(). * * 2) Given the snippet: * * { X = 0; Y = 0; } * * CPU0 CPU1 CPU2 * * spin_lock(S); spin_lock(S); r1 = READ_ONCE(Y); * WRITE_ONCE(X, 1); smp_mb__after_spinlock(); smp_rmb(); * spin_unlock(S); r0 = READ_ONCE(X); r2 = READ_ONCE(X); * WRITE_ONCE(Y, 1); * spin_unlock(S); * * it is forbidden that CPU0's critical section executes before CPU1's * critical section (r0 = 1), CPU2 observes CPU1's store to Y (r1 = 1) * and CPU2 does not observe CPU0's store to X (r2 = 0); see the comments * preceding the calls to smp_rmb() in try_to_wake_up() for similar * snippets but "projected" onto two CPUs. * * Property (2) upgrades the lock to an RCsc lock. * * Since most load-store architectures implement ACQUIRE with an smp_mb() after * the LL/SC loop, they need no further barriers. Similarly all our TSO * architectures imply an smp_mb() for each atomic instruction and equally don't * need more. * * Architectures that can implement ACQUIRE better need to take care. */ #ifndef smp_mb__after_spinlock #define smp_mb__after_spinlock() kcsan_mb() #endif #ifdef CONFIG_DEBUG_SPINLOCK extern void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock); extern int do_raw_spin_trylock(raw_spinlock_t *lock); extern void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock); #else static inline void do_raw_spin_lock(raw_spinlock_t *lock) __acquires(lock) { __acquire(lock); arch_spin_lock(&lock->raw_lock); mmiowb_spin_lock(); } static inline int do_raw_spin_trylock(raw_spinlock_t *lock) { int ret = arch_spin_trylock(&(lock)->raw_lock); if (ret) mmiowb_spin_lock(); return ret; } static inline void do_raw_spin_unlock(raw_spinlock_t *lock) __releases(lock) { mmiowb_spin_unlock(); arch_spin_unlock(&lock->raw_lock); __release(lock); } #endif /* * Define the various spin_lock methods. Note we define these * regardless of whether CONFIG_SMP or CONFIG_PREEMPTION are set. The * various methods are defined as nops in the case they are not * required. */ #define raw_spin_trylock(lock) __cond_lock(lock, _raw_spin_trylock(lock)) #define raw_spin_lock(lock) _raw_spin_lock(lock) #ifdef CONFIG_DEBUG_LOCK_ALLOC # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock_nested(lock, subclass) # define raw_spin_lock_nest_lock(lock, nest_lock) \ do { \ typecheck(struct lockdep_map *, &(nest_lock)->dep_map);\ _raw_spin_lock_nest_lock(lock, &(nest_lock)->dep_map); \ } while (0) #else /* * Always evaluate the 'subclass' argument to avoid that the compiler * warns about set-but-not-used variables when building with * CONFIG_DEBUG_LOCK_ALLOC=n and with W=1. */ # define raw_spin_lock_nested(lock, subclass) \ _raw_spin_lock(((void)(subclass), (lock))) # define raw_spin_lock_nest_lock(lock, nest_lock) _raw_spin_lock(lock) #endif #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #ifdef CONFIG_DEBUG_LOCK_ALLOC #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave_nested(lock, subclass); \ } while (0) #else #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ typecheck(unsigned long, flags); \ flags = _raw_spin_lock_irqsave(lock); \ } while (0) #endif #else #define raw_spin_lock_irqsave(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_lock_irqsave(lock, flags); \ } while (0) #define raw_spin_lock_irqsave_nested(lock, flags, subclass) \ raw_spin_lock_irqsave(lock, flags) #endif #define raw_spin_lock_irq(lock) _raw_spin_lock_irq(lock) #define raw_spin_lock_bh(lock) _raw_spin_lock_bh(lock) #define raw_spin_unlock(lock) _raw_spin_unlock(lock) #define raw_spin_unlock_irq(lock) _raw_spin_unlock_irq(lock) #define raw_spin_unlock_irqrestore(lock, flags) \ do { \ typecheck(unsigned long, flags); \ _raw_spin_unlock_irqrestore(lock, flags); \ } while (0) #define raw_spin_unlock_bh(lock) _raw_spin_unlock_bh(lock) #define raw_spin_trylock_bh(lock) \ __cond_lock(lock, _raw_spin_trylock_bh(lock)) #define raw_spin_trylock_irq(lock) \ ({ \ local_irq_disable(); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_enable(); 0; }); \ }) #define raw_spin_trylock_irqsave(lock, flags) \ ({ \ local_irq_save(flags); \ raw_spin_trylock(lock) ? \ 1 : ({ local_irq_restore(flags); 0; }); \ }) #ifndef CONFIG_PREEMPT_RT /* Include rwlock functions for !RT */ #include <linux/rwlock.h> #endif /* * Pull the _spin_*()/_read_*()/_write_*() functions/declarations: */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) # include <linux/spinlock_api_smp.h> #else # include <linux/spinlock_api_up.h> #endif /* Non PREEMPT_RT kernel, map to raw spinlocks: */ #ifndef CONFIG_PREEMPT_RT /* * Map the spin_lock functions to the raw variants for PREEMPT_RT=n */ static __always_inline raw_spinlock_t *spinlock_check(spinlock_t *lock) { return &lock->rlock; } #ifdef CONFIG_DEBUG_SPINLOCK # define spin_lock_init(lock) \ do { \ static struct lock_class_key __key; \ \ __raw_spin_lock_init(spinlock_check(lock), \ #lock, &__key, LD_WAIT_CONFIG); \ } while (0) #else # define spin_lock_init(_lock) \ do { \ spinlock_check(_lock); \ *(_lock) = __SPIN_LOCK_UNLOCKED(_lock); \ } while (0) #endif static __always_inline void spin_lock(spinlock_t *lock) { raw_spin_lock(&lock->rlock); } static __always_inline void spin_lock_bh(spinlock_t *lock) { raw_spin_lock_bh(&lock->rlock); } static __always_inline int spin_trylock(spinlock_t *lock) { return raw_spin_trylock(&lock->rlock); } #define spin_lock_nested(lock, subclass) \ do { \ raw_spin_lock_nested(spinlock_check(lock), subclass); \ } while (0) #define spin_lock_nest_lock(lock, nest_lock) \ do { \ raw_spin_lock_nest_lock(spinlock_check(lock), nest_lock); \ } while (0) static __always_inline void spin_lock_irq(spinlock_t *lock) { raw_spin_lock_irq(&lock->rlock); } #define spin_lock_irqsave(lock, flags) \ do { \ raw_spin_lock_irqsave(spinlock_check(lock), flags); \ } while (0) #define spin_lock_irqsave_nested(lock, flags, subclass) \ do { \ raw_spin_lock_irqsave_nested(spinlock_check(lock), flags, subclass); \ } while (0) static __always_inline void spin_unlock(spinlock_t *lock) { raw_spin_unlock(&lock->rlock); } static __always_inline void spin_unlock_bh(spinlock_t *lock) { raw_spin_unlock_bh(&lock->rlock); } static __always_inline void spin_unlock_irq(spinlock_t *lock) { raw_spin_unlock_irq(&lock->rlock); } static __always_inline void spin_unlock_irqrestore(spinlock_t *lock, unsigned long flags) { raw_spin_unlock_irqrestore(&lock->rlock, flags); } static __always_inline int spin_trylock_bh(spinlock_t *lock) { return raw_spin_trylock_bh(&lock->rlock); } static __always_inline int spin_trylock_irq(spinlock_t *lock) { return raw_spin_trylock_irq(&lock->rlock); } #define spin_trylock_irqsave(lock, flags) \ ({ \ raw_spin_trylock_irqsave(spinlock_check(lock), flags); \ }) /** * spin_is_locked() - Check whether a spinlock is locked. * @lock: Pointer to the spinlock. * * This function is NOT required to provide any memory ordering * guarantees; it could be used for debugging purposes or, when * additional synchronization is needed, accompanied with other * constructs (memory barriers) enforcing the synchronization. * * Returns: 1 if @lock is locked, 0 otherwise. * * Note that the function only tells you that the spinlock is * seen to be locked, not that it is locked on your CPU. * * Further, on CONFIG_SMP=n builds with CONFIG_DEBUG_SPINLOCK=n, * the return value is always 0 (see include/linux/spinlock_up.h). * Therefore you should not rely heavily on the return value. */ static __always_inline int spin_is_locked(spinlock_t *lock) { return raw_spin_is_locked(&lock->rlock); } static __always_inline int spin_is_contended(spinlock_t *lock) { return raw_spin_is_contended(&lock->rlock); } #define assert_spin_locked(lock) assert_raw_spin_locked(&(lock)->rlock) #else /* !CONFIG_PREEMPT_RT */ # include <linux/spinlock_rt.h> #endif /* CONFIG_PREEMPT_RT */ /* * Does a critical section need to be broken due to another * task waiting?: (technically does not depend on CONFIG_PREEMPTION, * but a general need for low latency) */ static inline int spin_needbreak(spinlock_t *lock) { #ifdef CONFIG_PREEMPTION return spin_is_contended(lock); #else return 0; #endif } /* * Check if a rwlock is contended. * Returns non-zero if there is another task waiting on the rwlock. * Returns zero if the lock is not contended or the system / underlying * rwlock implementation does not support contention detection. * Technically does not depend on CONFIG_PREEMPTION, but a general need * for low latency. */ static inline int rwlock_needbreak(rwlock_t *lock) { #ifdef CONFIG_PREEMPTION return rwlock_is_contended(lock); #else return 0; #endif } /* * Pull the atomic_t declaration: * (asm-mips/atomic.h needs above definitions) */ #include <linux/atomic.h> /** * atomic_dec_and_lock - lock on reaching reference count zero * @atomic: the atomic counter * @lock: the spinlock in question * * Decrements @atomic by 1. If the result is 0, returns true and locks * @lock. Returns false for all other cases. */ extern int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock); #define atomic_dec_and_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_lock(atomic, lock)) extern int _atomic_dec_and_lock_irqsave(atomic_t *atomic, spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_lock_irqsave(atomic, lock, &(flags))) extern int _atomic_dec_and_raw_lock(atomic_t *atomic, raw_spinlock_t *lock); #define atomic_dec_and_raw_lock(atomic, lock) \ __cond_lock(lock, _atomic_dec_and_raw_lock(atomic, lock)) extern int _atomic_dec_and_raw_lock_irqsave(atomic_t *atomic, raw_spinlock_t *lock, unsigned long *flags); #define atomic_dec_and_raw_lock_irqsave(atomic, lock, flags) \ __cond_lock(lock, _atomic_dec_and_raw_lock_irqsave(atomic, lock, &(flags))) int __alloc_bucket_spinlocks(spinlock_t **locks, unsigned int *lock_mask, size_t max_size, unsigned int cpu_mult, gfp_t gfp, const char *name, struct lock_class_key *key); #define alloc_bucket_spinlocks(locks, lock_mask, max_size, cpu_mult, gfp) \ ({ \ static struct lock_class_key key; \ int ret; \ \ ret = __alloc_bucket_spinlocks(locks, lock_mask, max_size, \ cpu_mult, gfp, #locks, &key); \ ret; \ }) void free_bucket_spinlocks(spinlock_t *locks); DEFINE_LOCK_GUARD_1(raw_spinlock, raw_spinlock_t, raw_spin_lock(_T->lock), raw_spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(raw_spinlock, _try, raw_spin_trylock(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_nested, raw_spinlock_t, raw_spin_lock_nested(_T->lock, SINGLE_DEPTH_NESTING), raw_spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_irq, raw_spinlock_t, raw_spin_lock_irq(_T->lock), raw_spin_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irq, _try, raw_spin_trylock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(raw_spinlock_irqsave, raw_spinlock_t, raw_spin_lock_irqsave(_T->lock, _T->flags), raw_spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1_COND(raw_spinlock_irqsave, _try, raw_spin_trylock_irqsave(_T->lock, _T->flags)) DEFINE_LOCK_GUARD_1(spinlock, spinlock_t, spin_lock(_T->lock), spin_unlock(_T->lock)) DEFINE_LOCK_GUARD_1_COND(spinlock, _try, spin_trylock(_T->lock)) DEFINE_LOCK_GUARD_1(spinlock_irq, spinlock_t, spin_lock_irq(_T->lock), spin_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1_COND(spinlock_irq, _try, spin_trylock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(spinlock_irqsave, spinlock_t, spin_lock_irqsave(_T->lock, _T->flags), spin_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1_COND(spinlock_irqsave, _try, spin_trylock_irqsave(_T->lock, _T->flags)) DEFINE_LOCK_GUARD_1(read_lock, rwlock_t, read_lock(_T->lock), read_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(read_lock_irq, rwlock_t, read_lock_irq(_T->lock), read_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(read_lock_irqsave, rwlock_t, read_lock_irqsave(_T->lock, _T->flags), read_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) DEFINE_LOCK_GUARD_1(write_lock, rwlock_t, write_lock(_T->lock), write_unlock(_T->lock)) DEFINE_LOCK_GUARD_1(write_lock_irq, rwlock_t, write_lock_irq(_T->lock), write_unlock_irq(_T->lock)) DEFINE_LOCK_GUARD_1(write_lock_irqsave, rwlock_t, write_lock_irqsave(_T->lock, _T->flags), write_unlock_irqrestore(_T->lock, _T->flags), unsigned long flags) #undef __LINUX_INSIDE_SPINLOCK_H #endif /* __LINUX_SPINLOCK_H */ |
| 145 19 2 2 2 2 2 11 7 11 1 1 2 2 2 3 3 3 3 3 3 3 3 3 3 3 3 3 3 28 28 2 2 2 2 3 16 3 16 120 115 115 115 115 3 3 3 3 114 3 115 3 3 3 3 3 3 3 3 3 115 115 115 115 3 115 3 3 3 3 115 115 115 115 115 115 115 16 16 16 1 1 1 1 16 16 16 19 17 14 14 16 148 148 3 3 148 148 148 148 148 148 148 148 148 148 148 141 141 16 152 152 152 152 152 152 152 152 152 152 152 152 148 148 148 141 141 141 141 4 4 4 4 4 4 4 2 19 19 19 16 16 16 16 16 16 16 16 16 2 16 16 16 16 16 16 49 22 18 18 16 2 11 11 11 11 1 1 1 7 7 7 7 7 11 11 11 1 11 11 1 1 1 1 11 11 1 1 11 11 17 11 11 11 1 11 12 10 2 2 2 2 12 1 11 11 1 1 11 11 2 2 11 1 1 1 11 1 12 12 1 1 12 1 1 11 11 1 1 11 12 12 12 2 17 16 16 16 15 15 14 14 13 13 12 12 12 12 12 1 1 2 1 12 2 12 2 2 12 12 12 12 1 1 18 17 18 19 18 2 1 1 1 1 2 2 2 4 3 3 3 3 3 4 4 4 10 3 3 10 2 3 3 10 3 3 10 2 2 1 1 1 1 2 2 2 2 1 2 2 2 2 2 2 2 2 1 2 2 2 2 2 2 2 2 2 2 10 10 1 1 6 6 6 6 6 6 3 3 3 3 4 4 4 4 4 4 4 33 34 34 34 34 34 34 34 34 33 33 33 33 33 33 33 3 3 3 3 3 1 1 1 1 1 58 58 58 56 55 12 11 11 11 11 11 1 1 1 1 2 1 1 1 1 1 1 1 1 2 2 2 2 2 2 1 4 4 4 4 5 2 1 1 1 1 1 1 9 31 51 55 1 1 1 56 55 58 58 58 9 57 1 56 5 2 2 5 4 23 22 20 20 2 19 19 19 19 19 22 1 19 1 7 2 2 1 2 1 1 2 1 1 1 1 149 148 149 34 8 8 7 3 20 18 20 20 18 19 2 2 149 2 4 4 4 2 2 2 3 3 3 5 5 4 13 13 13 5 5 5 12 12 11 6 1 16 16 16 16 16 15 14 1 14 23 23 23 20 26 2 149 1 20 7 152 152 152 145 4 141 141 141 141 4 4 172 2 152 19 167 8 130 130 130 130 130 130 9 9 9 9 16 16 9 16 148 148 130 148 7 16 5 5 16 5 2 1 5 2 2 2 10 10 10 10 10 10 5 10 10 3 3 3 3 3 2 3 2 2 2 2 2 2 2 2 2 150 150 141 19 150 150 148 148 148 148 150 150 11 11 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 | // SPDX-License-Identifier: GPL-2.0-only /* * Kernel-based Virtual Machine driver for Linux * * This module enables machines with Intel VT-x extensions to run virtual * machines without emulation or binary translation. * * Copyright (C) 2006 Qumranet, Inc. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * * Authors: * Avi Kivity <avi@qumranet.com> * Yaniv Kamay <yaniv@qumranet.com> */ #include <kvm/iodev.h> #include <linux/kvm_host.h> #include <linux/kvm.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/percpu.h> #include <linux/mm.h> #include <linux/miscdevice.h> #include <linux/vmalloc.h> #include <linux/reboot.h> #include <linux/debugfs.h> #include <linux/highmem.h> #include <linux/file.h> #include <linux/syscore_ops.h> #include <linux/cpu.h> #include <linux/sched/signal.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/cpumask.h> #include <linux/smp.h> #include <linux/anon_inodes.h> #include <linux/profile.h> #include <linux/kvm_para.h> #include <linux/pagemap.h> #include <linux/mman.h> #include <linux/swap.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/compat.h> #include <linux/srcu.h> #include <linux/hugetlb.h> #include <linux/slab.h> #include <linux/sort.h> #include <linux/bsearch.h> #include <linux/io.h> #include <linux/lockdep.h> #include <linux/kthread.h> #include <linux/suspend.h> #include <asm/processor.h> #include <asm/ioctl.h> #include <linux/uaccess.h> #include "coalesced_mmio.h" #include "async_pf.h" #include "kvm_mm.h" #include "vfio.h" #include <trace/events/ipi.h> #define CREATE_TRACE_POINTS #include <trace/events/kvm.h> #include <linux/kvm_dirty_ring.h> /* Worst case buffer size needed for holding an integer. */ #define ITOA_MAX_LEN 12 MODULE_AUTHOR("Qumranet"); MODULE_LICENSE("GPL"); /* Architectures should define their poll value according to the halt latency */ unsigned int halt_poll_ns = KVM_HALT_POLL_NS_DEFAULT; module_param(halt_poll_ns, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns); /* Default doubles per-vcpu halt_poll_ns. */ unsigned int halt_poll_ns_grow = 2; module_param(halt_poll_ns_grow, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow); /* The start value to grow halt_poll_ns from */ unsigned int halt_poll_ns_grow_start = 10000; /* 10us */ module_param(halt_poll_ns_grow_start, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_grow_start); /* Default resets per-vcpu halt_poll_ns . */ unsigned int halt_poll_ns_shrink; module_param(halt_poll_ns_shrink, uint, 0644); EXPORT_SYMBOL_GPL(halt_poll_ns_shrink); /* * Ordering of locks: * * kvm->lock --> kvm->slots_lock --> kvm->irq_lock */ DEFINE_MUTEX(kvm_lock); LIST_HEAD(vm_list); static struct kmem_cache *kvm_vcpu_cache; static __read_mostly struct preempt_ops kvm_preempt_ops; static DEFINE_PER_CPU(struct kvm_vcpu *, kvm_running_vcpu); struct dentry *kvm_debugfs_dir; EXPORT_SYMBOL_GPL(kvm_debugfs_dir); static const struct file_operations stat_fops_per_vm; static long kvm_vcpu_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg); #define KVM_COMPAT(c) .compat_ioctl = (c) #else /* * For architectures that don't implement a compat infrastructure, * adopt a double line of defense: * - Prevent a compat task from opening /dev/kvm * - If the open has been done by a 64bit task, and the KVM fd * passed to a compat task, let the ioctls fail. */ static long kvm_no_compat_ioctl(struct file *file, unsigned int ioctl, unsigned long arg) { return -EINVAL; } static int kvm_no_compat_open(struct inode *inode, struct file *file) { return is_compat_task() ? -ENODEV : 0; } #define KVM_COMPAT(c) .compat_ioctl = kvm_no_compat_ioctl, \ .open = kvm_no_compat_open #endif static int hardware_enable_all(void); static void hardware_disable_all(void); static void kvm_io_bus_destroy(struct kvm_io_bus *bus); #define KVM_EVENT_CREATE_VM 0 #define KVM_EVENT_DESTROY_VM 1 static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm); static unsigned long long kvm_createvm_count; static unsigned long long kvm_active_vms; static DEFINE_PER_CPU(cpumask_var_t, cpu_kick_mask); __weak void kvm_arch_guest_memory_reclaimed(struct kvm *kvm) { } bool kvm_is_zone_device_page(struct page *page) { /* * The metadata used by is_zone_device_page() to determine whether or * not a page is ZONE_DEVICE is guaranteed to be valid if and only if * the device has been pinned, e.g. by get_user_pages(). WARN if the * page_count() is zero to help detect bad usage of this helper. */ if (WARN_ON_ONCE(!page_count(page))) return false; return is_zone_device_page(page); } /* * Returns a 'struct page' if the pfn is "valid" and backed by a refcounted * page, NULL otherwise. Note, the list of refcounted PG_reserved page types * is likely incomplete, it has been compiled purely through people wanting to * back guest with a certain type of memory and encountering issues. */ struct page *kvm_pfn_to_refcounted_page(kvm_pfn_t pfn) { struct page *page; if (!pfn_valid(pfn)) return NULL; page = pfn_to_page(pfn); if (!PageReserved(page)) return page; /* The ZERO_PAGE(s) is marked PG_reserved, but is refcounted. */ if (is_zero_pfn(pfn)) return page; /* * ZONE_DEVICE pages currently set PG_reserved, but from a refcounting * perspective they are "normal" pages, albeit with slightly different * usage rules. */ if (kvm_is_zone_device_page(page)) return page; return NULL; } /* * Switches to specified vcpu, until a matching vcpu_put() */ void vcpu_load(struct kvm_vcpu *vcpu) { int cpu = get_cpu(); __this_cpu_write(kvm_running_vcpu, vcpu); preempt_notifier_register(&vcpu->preempt_notifier); kvm_arch_vcpu_load(vcpu, cpu); put_cpu(); } EXPORT_SYMBOL_GPL(vcpu_load); void vcpu_put(struct kvm_vcpu *vcpu) { preempt_disable(); kvm_arch_vcpu_put(vcpu); preempt_notifier_unregister(&vcpu->preempt_notifier); __this_cpu_write(kvm_running_vcpu, NULL); preempt_enable(); } EXPORT_SYMBOL_GPL(vcpu_put); /* TODO: merge with kvm_arch_vcpu_should_kick */ static bool kvm_request_needs_ipi(struct kvm_vcpu *vcpu, unsigned req) { int mode = kvm_vcpu_exiting_guest_mode(vcpu); /* * We need to wait for the VCPU to reenable interrupts and get out of * READING_SHADOW_PAGE_TABLES mode. */ if (req & KVM_REQUEST_WAIT) return mode != OUTSIDE_GUEST_MODE; /* * Need to kick a running VCPU, but otherwise there is nothing to do. */ return mode == IN_GUEST_MODE; } static void ack_kick(void *_completed) { } static inline bool kvm_kick_many_cpus(struct cpumask *cpus, bool wait) { if (cpumask_empty(cpus)) return false; smp_call_function_many(cpus, ack_kick, NULL, wait); return true; } static void kvm_make_vcpu_request(struct kvm_vcpu *vcpu, unsigned int req, struct cpumask *tmp, int current_cpu) { int cpu; if (likely(!(req & KVM_REQUEST_NO_ACTION))) __kvm_make_request(req, vcpu); if (!(req & KVM_REQUEST_NO_WAKEUP) && kvm_vcpu_wake_up(vcpu)) return; /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_request_needs_ipi(), which could result in sending an IPI * to the previous pCPU. But, that's OK because the purpose of the IPI * is to ensure the vCPU returns to OUTSIDE_GUEST_MODE, which is * satisfied if the vCPU migrates. Entering READING_SHADOW_PAGE_TABLES * after this point is also OK, as the requirement is only that KVM wait * for vCPUs that were reading SPTEs _before_ any changes were * finalized. See kvm_vcpu_kick() for more details on handling requests. */ if (kvm_request_needs_ipi(vcpu, req)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != -1 && cpu != current_cpu) __cpumask_set_cpu(cpu, tmp); } } bool kvm_make_vcpus_request_mask(struct kvm *kvm, unsigned int req, unsigned long *vcpu_bitmap) { struct kvm_vcpu *vcpu; struct cpumask *cpus; int i, me; bool called; me = get_cpu(); cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); cpumask_clear(cpus); for_each_set_bit(i, vcpu_bitmap, KVM_MAX_VCPUS) { vcpu = kvm_get_vcpu(kvm, i); if (!vcpu) continue; kvm_make_vcpu_request(vcpu, req, cpus, me); } called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req) { struct kvm_vcpu *vcpu; struct cpumask *cpus; unsigned long i; bool called; int me; me = get_cpu(); cpus = this_cpu_cpumask_var_ptr(cpu_kick_mask); cpumask_clear(cpus); kvm_for_each_vcpu(i, vcpu, kvm) kvm_make_vcpu_request(vcpu, req, cpus, me); called = kvm_kick_many_cpus(cpus, !!(req & KVM_REQUEST_WAIT)); put_cpu(); return called; } EXPORT_SYMBOL_GPL(kvm_make_all_cpus_request); void kvm_flush_remote_tlbs(struct kvm *kvm) { ++kvm->stat.generic.remote_tlb_flush_requests; /* * We want to publish modifications to the page tables before reading * mode. Pairs with a memory barrier in arch-specific code. * - x86: smp_mb__after_srcu_read_unlock in vcpu_enter_guest * and smp_mb in walk_shadow_page_lockless_begin/end. * - powerpc: smp_mb in kvmppc_prepare_to_enter. * * There is already an smp_mb__after_atomic() before * kvm_make_all_cpus_request() reads vcpu->mode. We reuse that * barrier here. */ if (!kvm_arch_flush_remote_tlbs(kvm) || kvm_make_all_cpus_request(kvm, KVM_REQ_TLB_FLUSH)) ++kvm->stat.generic.remote_tlb_flush; } EXPORT_SYMBOL_GPL(kvm_flush_remote_tlbs); void kvm_flush_remote_tlbs_range(struct kvm *kvm, gfn_t gfn, u64 nr_pages) { if (!kvm_arch_flush_remote_tlbs_range(kvm, gfn, nr_pages)) return; /* * Fall back to a flushing entire TLBs if the architecture range-based * TLB invalidation is unsupported or can't be performed for whatever * reason. */ kvm_flush_remote_tlbs(kvm); } void kvm_flush_remote_tlbs_memslot(struct kvm *kvm, const struct kvm_memory_slot *memslot) { /* * All current use cases for flushing the TLBs for a specific memslot * are related to dirty logging, and many do the TLB flush out of * mmu_lock. The interaction between the various operations on memslot * must be serialized by slots_locks to ensure the TLB flush from one * operation is observed by any other operation on the same memslot. */ lockdep_assert_held(&kvm->slots_lock); kvm_flush_remote_tlbs_range(kvm, memslot->base_gfn, memslot->npages); } static void kvm_flush_shadow_all(struct kvm *kvm) { kvm_arch_flush_shadow_all(kvm); kvm_arch_guest_memory_reclaimed(kvm); } #ifdef KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE static inline void *mmu_memory_cache_alloc_obj(struct kvm_mmu_memory_cache *mc, gfp_t gfp_flags) { void *page; gfp_flags |= mc->gfp_zero; if (mc->kmem_cache) return kmem_cache_alloc(mc->kmem_cache, gfp_flags); page = (void *)__get_free_page(gfp_flags); if (page && mc->init_value) memset64(page, mc->init_value, PAGE_SIZE / sizeof(u64)); return page; } int __kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int capacity, int min) { gfp_t gfp = mc->gfp_custom ? mc->gfp_custom : GFP_KERNEL_ACCOUNT; void *obj; if (mc->nobjs >= min) return 0; if (unlikely(!mc->objects)) { if (WARN_ON_ONCE(!capacity)) return -EIO; /* * Custom init values can be used only for page allocations, * and obviously conflict with __GFP_ZERO. */ if (WARN_ON_ONCE(mc->init_value && (mc->kmem_cache || mc->gfp_zero))) return -EIO; mc->objects = kvmalloc_array(capacity, sizeof(void *), gfp); if (!mc->objects) return -ENOMEM; mc->capacity = capacity; } /* It is illegal to request a different capacity across topups. */ if (WARN_ON_ONCE(mc->capacity != capacity)) return -EIO; while (mc->nobjs < mc->capacity) { obj = mmu_memory_cache_alloc_obj(mc, gfp); if (!obj) return mc->nobjs >= min ? 0 : -ENOMEM; mc->objects[mc->nobjs++] = obj; } return 0; } int kvm_mmu_topup_memory_cache(struct kvm_mmu_memory_cache *mc, int min) { return __kvm_mmu_topup_memory_cache(mc, KVM_ARCH_NR_OBJS_PER_MEMORY_CACHE, min); } int kvm_mmu_memory_cache_nr_free_objects(struct kvm_mmu_memory_cache *mc) { return mc->nobjs; } void kvm_mmu_free_memory_cache(struct kvm_mmu_memory_cache *mc) { while (mc->nobjs) { if (mc->kmem_cache) kmem_cache_free(mc->kmem_cache, mc->objects[--mc->nobjs]); else free_page((unsigned long)mc->objects[--mc->nobjs]); } kvfree(mc->objects); mc->objects = NULL; mc->capacity = 0; } void *kvm_mmu_memory_cache_alloc(struct kvm_mmu_memory_cache *mc) { void *p; if (WARN_ON(!mc->nobjs)) p = mmu_memory_cache_alloc_obj(mc, GFP_ATOMIC | __GFP_ACCOUNT); else p = mc->objects[--mc->nobjs]; BUG_ON(!p); return p; } #endif static void kvm_vcpu_init(struct kvm_vcpu *vcpu, struct kvm *kvm, unsigned id) { mutex_init(&vcpu->mutex); vcpu->cpu = -1; vcpu->kvm = kvm; vcpu->vcpu_id = id; vcpu->pid = NULL; #ifndef __KVM_HAVE_ARCH_WQP rcuwait_init(&vcpu->wait); #endif kvm_async_pf_vcpu_init(vcpu); kvm_vcpu_set_in_spin_loop(vcpu, false); kvm_vcpu_set_dy_eligible(vcpu, false); vcpu->preempted = false; vcpu->ready = false; preempt_notifier_init(&vcpu->preempt_notifier, &kvm_preempt_ops); vcpu->last_used_slot = NULL; /* Fill the stats id string for the vcpu */ snprintf(vcpu->stats_id, sizeof(vcpu->stats_id), "kvm-%d/vcpu-%d", task_pid_nr(current), id); } static void kvm_vcpu_destroy(struct kvm_vcpu *vcpu) { kvm_arch_vcpu_destroy(vcpu); kvm_dirty_ring_free(&vcpu->dirty_ring); /* * No need for rcu_read_lock as VCPU_RUN is the only place that changes * the vcpu->pid pointer, and at destruction time all file descriptors * are already gone. */ put_pid(rcu_dereference_protected(vcpu->pid, 1)); free_page((unsigned long)vcpu->run); kmem_cache_free(kvm_vcpu_cache, vcpu); } void kvm_destroy_vcpus(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) { kvm_vcpu_destroy(vcpu); xa_erase(&kvm->vcpu_array, i); } atomic_set(&kvm->online_vcpus, 0); } EXPORT_SYMBOL_GPL(kvm_destroy_vcpus); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER static inline struct kvm *mmu_notifier_to_kvm(struct mmu_notifier *mn) { return container_of(mn, struct kvm, mmu_notifier); } typedef bool (*gfn_handler_t)(struct kvm *kvm, struct kvm_gfn_range *range); typedef void (*on_lock_fn_t)(struct kvm *kvm); struct kvm_mmu_notifier_range { /* * 64-bit addresses, as KVM notifiers can operate on host virtual * addresses (unsigned long) and guest physical addresses (64-bit). */ u64 start; u64 end; union kvm_mmu_notifier_arg arg; gfn_handler_t handler; on_lock_fn_t on_lock; bool flush_on_ret; bool may_block; }; /* * The inner-most helper returns a tuple containing the return value from the * arch- and action-specific handler, plus a flag indicating whether or not at * least one memslot was found, i.e. if the handler found guest memory. * * Note, most notifiers are averse to booleans, so even though KVM tracks the * return from arch code as a bool, outer helpers will cast it to an int. :-( */ typedef struct kvm_mmu_notifier_return { bool ret; bool found_memslot; } kvm_mn_ret_t; /* * Use a dedicated stub instead of NULL to indicate that there is no callback * function/handler. The compiler technically can't guarantee that a real * function will have a non-zero address, and so it will generate code to * check for !NULL, whereas comparing against a stub will be elided at compile * time (unless the compiler is getting long in the tooth, e.g. gcc 4.9). */ static void kvm_null_fn(void) { } #define IS_KVM_NULL_FN(fn) ((fn) == (void *)kvm_null_fn) /* Iterate over each memslot intersecting [start, last] (inclusive) range */ #define kvm_for_each_memslot_in_hva_range(node, slots, start, last) \ for (node = interval_tree_iter_first(&slots->hva_tree, start, last); \ node; \ node = interval_tree_iter_next(node, start, last)) \ static __always_inline kvm_mn_ret_t __kvm_handle_hva_range(struct kvm *kvm, const struct kvm_mmu_notifier_range *range) { struct kvm_mmu_notifier_return r = { .ret = false, .found_memslot = false, }; struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; int i, idx; if (WARN_ON_ONCE(range->end <= range->start)) return r; /* A null handler is allowed if and only if on_lock() is provided. */ if (WARN_ON_ONCE(IS_KVM_NULL_FN(range->on_lock) && IS_KVM_NULL_FN(range->handler))) return r; idx = srcu_read_lock(&kvm->srcu); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { struct interval_tree_node *node; slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_hva_range(node, slots, range->start, range->end - 1) { unsigned long hva_start, hva_end; slot = container_of(node, struct kvm_memory_slot, hva_node[slots->node_idx]); hva_start = max_t(unsigned long, range->start, slot->userspace_addr); hva_end = min_t(unsigned long, range->end, slot->userspace_addr + (slot->npages << PAGE_SHIFT)); /* * To optimize for the likely case where the address * range is covered by zero or one memslots, don't * bother making these conditional (to avoid writes on * the second or later invocation of the handler). */ gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; /* * {gfn(page) | page intersects with [hva_start, hva_end)} = * {gfn_start, gfn_start+1, ..., gfn_end-1}. */ gfn_range.start = hva_to_gfn_memslot(hva_start, slot); gfn_range.end = hva_to_gfn_memslot(hva_end + PAGE_SIZE - 1, slot); gfn_range.slot = slot; if (!r.found_memslot) { r.found_memslot = true; KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) range->on_lock(kvm); if (IS_KVM_NULL_FN(range->handler)) goto mmu_unlock; } r.ret |= range->handler(kvm, &gfn_range); } } if (range->flush_on_ret && r.ret) kvm_flush_remote_tlbs(kvm); mmu_unlock: if (r.found_memslot) KVM_MMU_UNLOCK(kvm); srcu_read_unlock(&kvm->srcu, idx); return r; } static __always_inline int kvm_handle_hva_range(struct mmu_notifier *mn, unsigned long start, unsigned long end, gfn_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .handler = handler, .on_lock = (void *)kvm_null_fn, .flush_on_ret = true, .may_block = false, }; return __kvm_handle_hva_range(kvm, &range).ret; } static __always_inline int kvm_handle_hva_range_no_flush(struct mmu_notifier *mn, unsigned long start, unsigned long end, gfn_handler_t handler) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range range = { .start = start, .end = end, .handler = handler, .on_lock = (void *)kvm_null_fn, .flush_on_ret = false, .may_block = false, }; return __kvm_handle_hva_range(kvm, &range).ret; } void kvm_mmu_invalidate_begin(struct kvm *kvm) { lockdep_assert_held_write(&kvm->mmu_lock); /* * The count increase must become visible at unlock time as no * spte can be established without taking the mmu_lock and * count is also read inside the mmu_lock critical section. */ kvm->mmu_invalidate_in_progress++; if (likely(kvm->mmu_invalidate_in_progress == 1)) { kvm->mmu_invalidate_range_start = INVALID_GPA; kvm->mmu_invalidate_range_end = INVALID_GPA; } } void kvm_mmu_invalidate_range_add(struct kvm *kvm, gfn_t start, gfn_t end) { lockdep_assert_held_write(&kvm->mmu_lock); WARN_ON_ONCE(!kvm->mmu_invalidate_in_progress); if (likely(kvm->mmu_invalidate_range_start == INVALID_GPA)) { kvm->mmu_invalidate_range_start = start; kvm->mmu_invalidate_range_end = end; } else { /* * Fully tracking multiple concurrent ranges has diminishing * returns. Keep things simple and just find the minimal range * which includes the current and new ranges. As there won't be * enough information to subtract a range after its invalidate * completes, any ranges invalidated concurrently will * accumulate and persist until all outstanding invalidates * complete. */ kvm->mmu_invalidate_range_start = min(kvm->mmu_invalidate_range_start, start); kvm->mmu_invalidate_range_end = max(kvm->mmu_invalidate_range_end, end); } } bool kvm_mmu_unmap_gfn_range(struct kvm *kvm, struct kvm_gfn_range *range) { kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_unmap_gfn_range(kvm, range); } static int kvm_mmu_notifier_invalidate_range_start(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = kvm_mmu_unmap_gfn_range, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, .may_block = mmu_notifier_range_blockable(range), }; trace_kvm_unmap_hva_range(range->start, range->end); /* * Prevent memslot modification between range_start() and range_end() * so that conditionally locking provides the same result in both * functions. Without that guarantee, the mmu_invalidate_in_progress * adjustments will be imbalanced. * * Pairs with the decrement in range_end(). */ spin_lock(&kvm->mn_invalidate_lock); kvm->mn_active_invalidate_count++; spin_unlock(&kvm->mn_invalidate_lock); /* * Invalidate pfn caches _before_ invalidating the secondary MMUs, i.e. * before acquiring mmu_lock, to avoid holding mmu_lock while acquiring * each cache's lock. There are relatively few caches in existence at * any given time, and the caches themselves can check for hva overlap, * i.e. don't need to rely on memslot overlap checks for performance. * Because this runs without holding mmu_lock, the pfn caches must use * mn_active_invalidate_count (see above) instead of * mmu_invalidate_in_progress. */ gfn_to_pfn_cache_invalidate_start(kvm, range->start, range->end); /* * If one or more memslots were found and thus zapped, notify arch code * that guest memory has been reclaimed. This needs to be done *after* * dropping mmu_lock, as x86's reclaim path is slooooow. */ if (__kvm_handle_hva_range(kvm, &hva_range).found_memslot) kvm_arch_guest_memory_reclaimed(kvm); return 0; } void kvm_mmu_invalidate_end(struct kvm *kvm) { lockdep_assert_held_write(&kvm->mmu_lock); /* * This sequence increase will notify the kvm page fault that * the page that is going to be mapped in the spte could have * been freed. */ kvm->mmu_invalidate_seq++; smp_wmb(); /* * The above sequence increase must be visible before the * below count decrease, which is ensured by the smp_wmb above * in conjunction with the smp_rmb in mmu_invalidate_retry(). */ kvm->mmu_invalidate_in_progress--; KVM_BUG_ON(kvm->mmu_invalidate_in_progress < 0, kvm); /* * Assert that at least one range was added between start() and end(). * Not adding a range isn't fatal, but it is a KVM bug. */ WARN_ON_ONCE(kvm->mmu_invalidate_range_start == INVALID_GPA); } static void kvm_mmu_notifier_invalidate_range_end(struct mmu_notifier *mn, const struct mmu_notifier_range *range) { struct kvm *kvm = mmu_notifier_to_kvm(mn); const struct kvm_mmu_notifier_range hva_range = { .start = range->start, .end = range->end, .handler = (void *)kvm_null_fn, .on_lock = kvm_mmu_invalidate_end, .flush_on_ret = false, .may_block = mmu_notifier_range_blockable(range), }; bool wake; __kvm_handle_hva_range(kvm, &hva_range); /* Pairs with the increment in range_start(). */ spin_lock(&kvm->mn_invalidate_lock); if (!WARN_ON_ONCE(!kvm->mn_active_invalidate_count)) --kvm->mn_active_invalidate_count; wake = !kvm->mn_active_invalidate_count; spin_unlock(&kvm->mn_invalidate_lock); /* * There can only be one waiter, since the wait happens under * slots_lock. */ if (wake) rcuwait_wake_up(&kvm->mn_memslots_update_rcuwait); } static int kvm_mmu_notifier_clear_flush_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { trace_kvm_age_hva(start, end); return kvm_handle_hva_range(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_clear_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long start, unsigned long end) { trace_kvm_age_hva(start, end); /* * Even though we do not flush TLB, this will still adversely * affect performance on pre-Haswell Intel EPT, where there is * no EPT Access Bit to clear so that we have to tear down EPT * tables instead. If we find this unacceptable, we can always * add a parameter to kvm_age_hva so that it effectively doesn't * do anything on clear_young. * * Also note that currently we never issue secondary TLB flushes * from clear_young, leaving this job up to the regular system * cadence. If we find this inaccurate, we might come up with a * more sophisticated heuristic later. */ return kvm_handle_hva_range_no_flush(mn, start, end, kvm_age_gfn); } static int kvm_mmu_notifier_test_young(struct mmu_notifier *mn, struct mm_struct *mm, unsigned long address) { trace_kvm_test_age_hva(address); return kvm_handle_hva_range_no_flush(mn, address, address + 1, kvm_test_age_gfn); } static void kvm_mmu_notifier_release(struct mmu_notifier *mn, struct mm_struct *mm) { struct kvm *kvm = mmu_notifier_to_kvm(mn); int idx; idx = srcu_read_lock(&kvm->srcu); kvm_flush_shadow_all(kvm); srcu_read_unlock(&kvm->srcu, idx); } static const struct mmu_notifier_ops kvm_mmu_notifier_ops = { .invalidate_range_start = kvm_mmu_notifier_invalidate_range_start, .invalidate_range_end = kvm_mmu_notifier_invalidate_range_end, .clear_flush_young = kvm_mmu_notifier_clear_flush_young, .clear_young = kvm_mmu_notifier_clear_young, .test_young = kvm_mmu_notifier_test_young, .release = kvm_mmu_notifier_release, }; static int kvm_init_mmu_notifier(struct kvm *kvm) { kvm->mmu_notifier.ops = &kvm_mmu_notifier_ops; return mmu_notifier_register(&kvm->mmu_notifier, current->mm); } #else /* !CONFIG_KVM_GENERIC_MMU_NOTIFIER */ static int kvm_init_mmu_notifier(struct kvm *kvm) { return 0; } #endif /* CONFIG_KVM_GENERIC_MMU_NOTIFIER */ #ifdef CONFIG_HAVE_KVM_PM_NOTIFIER static int kvm_pm_notifier_call(struct notifier_block *bl, unsigned long state, void *unused) { struct kvm *kvm = container_of(bl, struct kvm, pm_notifier); return kvm_arch_pm_notifier(kvm, state); } static void kvm_init_pm_notifier(struct kvm *kvm) { kvm->pm_notifier.notifier_call = kvm_pm_notifier_call; /* Suspend KVM before we suspend ftrace, RCU, etc. */ kvm->pm_notifier.priority = INT_MAX; register_pm_notifier(&kvm->pm_notifier); } static void kvm_destroy_pm_notifier(struct kvm *kvm) { unregister_pm_notifier(&kvm->pm_notifier); } #else /* !CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_init_pm_notifier(struct kvm *kvm) { } static void kvm_destroy_pm_notifier(struct kvm *kvm) { } #endif /* CONFIG_HAVE_KVM_PM_NOTIFIER */ static void kvm_destroy_dirty_bitmap(struct kvm_memory_slot *memslot) { if (!memslot->dirty_bitmap) return; vfree(memslot->dirty_bitmap); memslot->dirty_bitmap = NULL; } /* This does not remove the slot from struct kvm_memslots data structures */ static void kvm_free_memslot(struct kvm *kvm, struct kvm_memory_slot *slot) { if (slot->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(slot); kvm_destroy_dirty_bitmap(slot); kvm_arch_free_memslot(kvm, slot); kfree(slot); } static void kvm_free_memslots(struct kvm *kvm, struct kvm_memslots *slots) { struct hlist_node *idnode; struct kvm_memory_slot *memslot; int bkt; /* * The same memslot objects live in both active and inactive sets, * arbitrarily free using index '1' so the second invocation of this * function isn't operating over a structure with dangling pointers * (even though this function isn't actually touching them). */ if (!slots->node_idx) return; hash_for_each_safe(slots->id_hash, bkt, idnode, memslot, id_node[1]) kvm_free_memslot(kvm, memslot); } static umode_t kvm_stats_debugfs_mode(const struct _kvm_stats_desc *pdesc) { switch (pdesc->desc.flags & KVM_STATS_TYPE_MASK) { case KVM_STATS_TYPE_INSTANT: return 0444; case KVM_STATS_TYPE_CUMULATIVE: case KVM_STATS_TYPE_PEAK: default: return 0644; } } static void kvm_destroy_vm_debugfs(struct kvm *kvm) { int i; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; if (IS_ERR(kvm->debugfs_dentry)) return; debugfs_remove_recursive(kvm->debugfs_dentry); if (kvm->debugfs_stat_data) { for (i = 0; i < kvm_debugfs_num_entries; i++) kfree(kvm->debugfs_stat_data[i]); kfree(kvm->debugfs_stat_data); } } static int kvm_create_vm_debugfs(struct kvm *kvm, const char *fdname) { static DEFINE_MUTEX(kvm_debugfs_lock); struct dentry *dent; char dir_name[ITOA_MAX_LEN * 2]; struct kvm_stat_data *stat_data; const struct _kvm_stats_desc *pdesc; int i, ret = -ENOMEM; int kvm_debugfs_num_entries = kvm_vm_stats_header.num_desc + kvm_vcpu_stats_header.num_desc; if (!debugfs_initialized()) return 0; snprintf(dir_name, sizeof(dir_name), "%d-%s", task_pid_nr(current), fdname); mutex_lock(&kvm_debugfs_lock); dent = debugfs_lookup(dir_name, kvm_debugfs_dir); if (dent) { pr_warn_ratelimited("KVM: debugfs: duplicate directory %s\n", dir_name); dput(dent); mutex_unlock(&kvm_debugfs_lock); return 0; } dent = debugfs_create_dir(dir_name, kvm_debugfs_dir); mutex_unlock(&kvm_debugfs_lock); if (IS_ERR(dent)) return 0; kvm->debugfs_dentry = dent; kvm->debugfs_stat_data = kcalloc(kvm_debugfs_num_entries, sizeof(*kvm->debugfs_stat_data), GFP_KERNEL_ACCOUNT); if (!kvm->debugfs_stat_data) goto out_err; for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { pdesc = &kvm_vm_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) goto out_err; stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VM; kvm->debugfs_stat_data[i] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { pdesc = &kvm_vcpu_stats_desc[i]; stat_data = kzalloc(sizeof(*stat_data), GFP_KERNEL_ACCOUNT); if (!stat_data) goto out_err; stat_data->kvm = kvm; stat_data->desc = pdesc; stat_data->kind = KVM_STAT_VCPU; kvm->debugfs_stat_data[i + kvm_vm_stats_header.num_desc] = stat_data; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm->debugfs_dentry, stat_data, &stat_fops_per_vm); } kvm_arch_create_vm_debugfs(kvm); return 0; out_err: kvm_destroy_vm_debugfs(kvm); return ret; } /* * Called after the VM is otherwise initialized, but just before adding it to * the vm_list. */ int __weak kvm_arch_post_init_vm(struct kvm *kvm) { return 0; } /* * Called just after removing the VM from the vm_list, but before doing any * other destruction. */ void __weak kvm_arch_pre_destroy_vm(struct kvm *kvm) { } /* * Called after per-vm debugfs created. When called kvm->debugfs_dentry should * be setup already, so we can create arch-specific debugfs entries under it. * Cleanup should be automatic done in kvm_destroy_vm_debugfs() recursively, so * a per-arch destroy interface is not needed. */ void __weak kvm_arch_create_vm_debugfs(struct kvm *kvm) { } static struct kvm *kvm_create_vm(unsigned long type, const char *fdname) { struct kvm *kvm = kvm_arch_alloc_vm(); struct kvm_memslots *slots; int r = -ENOMEM; int i, j; if (!kvm) return ERR_PTR(-ENOMEM); KVM_MMU_LOCK_INIT(kvm); mmgrab(current->mm); kvm->mm = current->mm; kvm_eventfd_init(kvm); mutex_init(&kvm->lock); mutex_init(&kvm->irq_lock); mutex_init(&kvm->slots_lock); mutex_init(&kvm->slots_arch_lock); spin_lock_init(&kvm->mn_invalidate_lock); rcuwait_init(&kvm->mn_memslots_update_rcuwait); xa_init(&kvm->vcpu_array); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_init(&kvm->mem_attr_array); #endif INIT_LIST_HEAD(&kvm->gpc_list); spin_lock_init(&kvm->gpc_lock); INIT_LIST_HEAD(&kvm->devices); kvm->max_vcpus = KVM_MAX_VCPUS; BUILD_BUG_ON(KVM_MEM_SLOTS_NUM > SHRT_MAX); /* * Force subsequent debugfs file creations to fail if the VM directory * is not created (by kvm_create_vm_debugfs()). */ kvm->debugfs_dentry = ERR_PTR(-ENOENT); snprintf(kvm->stats_id, sizeof(kvm->stats_id), "kvm-%d", task_pid_nr(current)); if (init_srcu_struct(&kvm->srcu)) goto out_err_no_srcu; if (init_srcu_struct(&kvm->irq_srcu)) goto out_err_no_irq_srcu; refcount_set(&kvm->users_count, 1); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { for (j = 0; j < 2; j++) { slots = &kvm->__memslots[i][j]; atomic_long_set(&slots->last_used_slot, (unsigned long)NULL); slots->hva_tree = RB_ROOT_CACHED; slots->gfn_tree = RB_ROOT; hash_init(slots->id_hash); slots->node_idx = j; /* Generations must be different for each address space. */ slots->generation = i; } rcu_assign_pointer(kvm->memslots[i], &kvm->__memslots[i][0]); } for (i = 0; i < KVM_NR_BUSES; i++) { rcu_assign_pointer(kvm->buses[i], kzalloc(sizeof(struct kvm_io_bus), GFP_KERNEL_ACCOUNT)); if (!kvm->buses[i]) goto out_err_no_arch_destroy_vm; } r = kvm_arch_init_vm(kvm, type); if (r) goto out_err_no_arch_destroy_vm; r = hardware_enable_all(); if (r) goto out_err_no_disable; #ifdef CONFIG_HAVE_KVM_IRQCHIP INIT_HLIST_HEAD(&kvm->irq_ack_notifier_list); #endif r = kvm_init_mmu_notifier(kvm); if (r) goto out_err_no_mmu_notifier; r = kvm_coalesced_mmio_init(kvm); if (r < 0) goto out_no_coalesced_mmio; r = kvm_create_vm_debugfs(kvm, fdname); if (r) goto out_err_no_debugfs; r = kvm_arch_post_init_vm(kvm); if (r) goto out_err; mutex_lock(&kvm_lock); list_add(&kvm->vm_list, &vm_list); mutex_unlock(&kvm_lock); preempt_notifier_inc(); kvm_init_pm_notifier(kvm); return kvm; out_err: kvm_destroy_vm_debugfs(kvm); out_err_no_debugfs: kvm_coalesced_mmio_free(kvm); out_no_coalesced_mmio: #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER if (kvm->mmu_notifier.ops) mmu_notifier_unregister(&kvm->mmu_notifier, current->mm); #endif out_err_no_mmu_notifier: hardware_disable_all(); out_err_no_disable: kvm_arch_destroy_vm(kvm); out_err_no_arch_destroy_vm: WARN_ON_ONCE(!refcount_dec_and_test(&kvm->users_count)); for (i = 0; i < KVM_NR_BUSES; i++) kfree(kvm_get_bus(kvm, i)); cleanup_srcu_struct(&kvm->irq_srcu); out_err_no_irq_srcu: cleanup_srcu_struct(&kvm->srcu); out_err_no_srcu: kvm_arch_free_vm(kvm); mmdrop(current->mm); return ERR_PTR(r); } static void kvm_destroy_devices(struct kvm *kvm) { struct kvm_device *dev, *tmp; /* * We do not need to take the kvm->lock here, because nobody else * has a reference to the struct kvm at this point and therefore * cannot access the devices list anyhow. * * The device list is generally managed as an rculist, but list_del() * is used intentionally here. If a bug in KVM introduced a reader that * was not backed by a reference on the kvm struct, the hope is that * it'd consume the poisoned forward pointer instead of suffering a * use-after-free, even though this cannot be guaranteed. */ list_for_each_entry_safe(dev, tmp, &kvm->devices, vm_node) { list_del(&dev->vm_node); dev->ops->destroy(dev); } } static void kvm_destroy_vm(struct kvm *kvm) { int i; struct mm_struct *mm = kvm->mm; kvm_destroy_pm_notifier(kvm); kvm_uevent_notify_change(KVM_EVENT_DESTROY_VM, kvm); kvm_destroy_vm_debugfs(kvm); kvm_arch_sync_events(kvm); mutex_lock(&kvm_lock); list_del(&kvm->vm_list); mutex_unlock(&kvm_lock); kvm_arch_pre_destroy_vm(kvm); kvm_free_irq_routing(kvm); for (i = 0; i < KVM_NR_BUSES; i++) { struct kvm_io_bus *bus = kvm_get_bus(kvm, i); if (bus) kvm_io_bus_destroy(bus); kvm->buses[i] = NULL; } kvm_coalesced_mmio_free(kvm); #ifdef CONFIG_KVM_GENERIC_MMU_NOTIFIER mmu_notifier_unregister(&kvm->mmu_notifier, kvm->mm); /* * At this point, pending calls to invalidate_range_start() * have completed but no more MMU notifiers will run, so * mn_active_invalidate_count may remain unbalanced. * No threads can be waiting in kvm_swap_active_memslots() as the * last reference on KVM has been dropped, but freeing * memslots would deadlock without this manual intervention. * * If the count isn't unbalanced, i.e. KVM did NOT unregister its MMU * notifier between a start() and end(), then there shouldn't be any * in-progress invalidations. */ WARN_ON(rcuwait_active(&kvm->mn_memslots_update_rcuwait)); if (kvm->mn_active_invalidate_count) kvm->mn_active_invalidate_count = 0; else WARN_ON(kvm->mmu_invalidate_in_progress); #else kvm_flush_shadow_all(kvm); #endif kvm_arch_destroy_vm(kvm); kvm_destroy_devices(kvm); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { kvm_free_memslots(kvm, &kvm->__memslots[i][0]); kvm_free_memslots(kvm, &kvm->__memslots[i][1]); } cleanup_srcu_struct(&kvm->irq_srcu); cleanup_srcu_struct(&kvm->srcu); #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES xa_destroy(&kvm->mem_attr_array); #endif kvm_arch_free_vm(kvm); preempt_notifier_dec(); hardware_disable_all(); mmdrop(mm); } void kvm_get_kvm(struct kvm *kvm) { refcount_inc(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm); /* * Make sure the vm is not during destruction, which is a safe version of * kvm_get_kvm(). Return true if kvm referenced successfully, false otherwise. */ bool kvm_get_kvm_safe(struct kvm *kvm) { return refcount_inc_not_zero(&kvm->users_count); } EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); void kvm_put_kvm(struct kvm *kvm) { if (refcount_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm); } EXPORT_SYMBOL_GPL(kvm_put_kvm); /* * Used to put a reference that was taken on behalf of an object associated * with a user-visible file descriptor, e.g. a vcpu or device, if installation * of the new file descriptor fails and the reference cannot be transferred to * its final owner. In such cases, the caller is still actively using @kvm and * will fail miserably if the refcount unexpectedly hits zero. */ void kvm_put_kvm_no_destroy(struct kvm *kvm) { WARN_ON(refcount_dec_and_test(&kvm->users_count)); } EXPORT_SYMBOL_GPL(kvm_put_kvm_no_destroy); static int kvm_vm_release(struct inode *inode, struct file *filp) { struct kvm *kvm = filp->private_data; kvm_irqfd_release(kvm); kvm_put_kvm(kvm); return 0; } /* * Allocation size is twice as large as the actual dirty bitmap size. * See kvm_vm_ioctl_get_dirty_log() why this is needed. */ static int kvm_alloc_dirty_bitmap(struct kvm_memory_slot *memslot) { unsigned long dirty_bytes = kvm_dirty_bitmap_bytes(memslot); memslot->dirty_bitmap = __vcalloc(2, dirty_bytes, GFP_KERNEL_ACCOUNT); if (!memslot->dirty_bitmap) return -ENOMEM; return 0; } static struct kvm_memslots *kvm_get_inactive_memslots(struct kvm *kvm, int as_id) { struct kvm_memslots *active = __kvm_memslots(kvm, as_id); int node_idx_inactive = active->node_idx ^ 1; return &kvm->__memslots[as_id][node_idx_inactive]; } /* * Helper to get the address space ID when one of memslot pointers may be NULL. * This also serves as a sanity that at least one of the pointers is non-NULL, * and that their address space IDs don't diverge. */ static int kvm_memslots_get_as_id(struct kvm_memory_slot *a, struct kvm_memory_slot *b) { if (WARN_ON_ONCE(!a && !b)) return 0; if (!a) return b->as_id; if (!b) return a->as_id; WARN_ON_ONCE(a->as_id != b->as_id); return a->as_id; } static void kvm_insert_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *slot) { struct rb_root *gfn_tree = &slots->gfn_tree; struct rb_node **node, *parent; int idx = slots->node_idx; parent = NULL; for (node = &gfn_tree->rb_node; *node; ) { struct kvm_memory_slot *tmp; tmp = container_of(*node, struct kvm_memory_slot, gfn_node[idx]); parent = *node; if (slot->base_gfn < tmp->base_gfn) node = &(*node)->rb_left; else if (slot->base_gfn > tmp->base_gfn) node = &(*node)->rb_right; else BUG(); } rb_link_node(&slot->gfn_node[idx], parent, node); rb_insert_color(&slot->gfn_node[idx], gfn_tree); } static void kvm_erase_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *slot) { rb_erase(&slot->gfn_node[slots->node_idx], &slots->gfn_tree); } static void kvm_replace_gfn_node(struct kvm_memslots *slots, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int idx = slots->node_idx; WARN_ON_ONCE(old->base_gfn != new->base_gfn); rb_replace_node(&old->gfn_node[idx], &new->gfn_node[idx], &slots->gfn_tree); } /* * Replace @old with @new in the inactive memslots. * * With NULL @old this simply adds @new. * With NULL @new this simply removes @old. * * If @new is non-NULL its hva_node[slots_idx] range has to be set * appropriately. */ static void kvm_replace_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int as_id = kvm_memslots_get_as_id(old, new); struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); int idx = slots->node_idx; if (old) { hash_del(&old->id_node[idx]); interval_tree_remove(&old->hva_node[idx], &slots->hva_tree); if ((long)old == atomic_long_read(&slots->last_used_slot)) atomic_long_set(&slots->last_used_slot, (long)new); if (!new) { kvm_erase_gfn_node(slots, old); return; } } /* * Initialize @new's hva range. Do this even when replacing an @old * slot, kvm_copy_memslot() deliberately does not touch node data. */ new->hva_node[idx].start = new->userspace_addr; new->hva_node[idx].last = new->userspace_addr + (new->npages << PAGE_SHIFT) - 1; /* * (Re)Add the new memslot. There is no O(1) interval_tree_replace(), * hva_node needs to be swapped with remove+insert even though hva can't * change when replacing an existing slot. */ hash_add(slots->id_hash, &new->id_node[idx], new->id); interval_tree_insert(&new->hva_node[idx], &slots->hva_tree); /* * If the memslot gfn is unchanged, rb_replace_node() can be used to * switch the node in the gfn tree instead of removing the old and * inserting the new as two separate operations. Replacement is a * single O(1) operation versus two O(log(n)) operations for * remove+insert. */ if (old && old->base_gfn == new->base_gfn) { kvm_replace_gfn_node(slots, old, new); } else { if (old) kvm_erase_gfn_node(slots, old); kvm_insert_gfn_node(slots, new); } } /* * Flags that do not access any of the extra space of struct * kvm_userspace_memory_region2. KVM_SET_USER_MEMORY_REGION_V1_FLAGS * only allows these. */ #define KVM_SET_USER_MEMORY_REGION_V1_FLAGS \ (KVM_MEM_LOG_DIRTY_PAGES | KVM_MEM_READONLY) static int check_memory_region_flags(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { u32 valid_flags = KVM_MEM_LOG_DIRTY_PAGES; if (kvm_arch_has_private_mem(kvm)) valid_flags |= KVM_MEM_GUEST_MEMFD; /* Dirty logging private memory is not currently supported. */ if (mem->flags & KVM_MEM_GUEST_MEMFD) valid_flags &= ~KVM_MEM_LOG_DIRTY_PAGES; #ifdef CONFIG_HAVE_KVM_READONLY_MEM /* * GUEST_MEMFD is incompatible with read-only memslots, as writes to * read-only memslots have emulated MMIO, not page fault, semantics, * and KVM doesn't allow emulated MMIO for private memory. */ if (!(mem->flags & KVM_MEM_GUEST_MEMFD)) valid_flags |= KVM_MEM_READONLY; #endif if (mem->flags & ~valid_flags) return -EINVAL; return 0; } static void kvm_swap_active_memslots(struct kvm *kvm, int as_id) { struct kvm_memslots *slots = kvm_get_inactive_memslots(kvm, as_id); /* Grab the generation from the activate memslots. */ u64 gen = __kvm_memslots(kvm, as_id)->generation; WARN_ON(gen & KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS); slots->generation = gen | KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; /* * Do not store the new memslots while there are invalidations in * progress, otherwise the locking in invalidate_range_start and * invalidate_range_end will be unbalanced. */ spin_lock(&kvm->mn_invalidate_lock); prepare_to_rcuwait(&kvm->mn_memslots_update_rcuwait); while (kvm->mn_active_invalidate_count) { set_current_state(TASK_UNINTERRUPTIBLE); spin_unlock(&kvm->mn_invalidate_lock); schedule(); spin_lock(&kvm->mn_invalidate_lock); } finish_rcuwait(&kvm->mn_memslots_update_rcuwait); rcu_assign_pointer(kvm->memslots[as_id], slots); spin_unlock(&kvm->mn_invalidate_lock); /* * Acquired in kvm_set_memslot. Must be released before synchronize * SRCU below in order to avoid deadlock with another thread * acquiring the slots_arch_lock in an srcu critical section. */ mutex_unlock(&kvm->slots_arch_lock); synchronize_srcu_expedited(&kvm->srcu); /* * Increment the new memslot generation a second time, dropping the * update in-progress flag and incrementing the generation based on * the number of address spaces. This provides a unique and easily * identifiable generation number while the memslots are in flux. */ gen = slots->generation & ~KVM_MEMSLOT_GEN_UPDATE_IN_PROGRESS; /* * Generations must be unique even across address spaces. We do not need * a global counter for that, instead the generation space is evenly split * across address spaces. For example, with two address spaces, address * space 0 will use generations 0, 2, 4, ... while address space 1 will * use generations 1, 3, 5, ... */ gen += kvm_arch_nr_memslot_as_ids(kvm); kvm_arch_memslots_updated(kvm, gen); slots->generation = gen; } static int kvm_prepare_memory_region(struct kvm *kvm, const struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { int r; /* * If dirty logging is disabled, nullify the bitmap; the old bitmap * will be freed on "commit". If logging is enabled in both old and * new, reuse the existing bitmap. If logging is enabled only in the * new and KVM isn't using a ring buffer, allocate and initialize a * new bitmap. */ if (change != KVM_MR_DELETE) { if (!(new->flags & KVM_MEM_LOG_DIRTY_PAGES)) new->dirty_bitmap = NULL; else if (old && old->dirty_bitmap) new->dirty_bitmap = old->dirty_bitmap; else if (kvm_use_dirty_bitmap(kvm)) { r = kvm_alloc_dirty_bitmap(new); if (r) return r; if (kvm_dirty_log_manual_protect_and_init_set(kvm)) bitmap_set(new->dirty_bitmap, 0, new->npages); } } r = kvm_arch_prepare_memory_region(kvm, old, new, change); /* Free the bitmap on failure if it was allocated above. */ if (r && new && new->dirty_bitmap && (!old || !old->dirty_bitmap)) kvm_destroy_dirty_bitmap(new); return r; } static void kvm_commit_memory_region(struct kvm *kvm, struct kvm_memory_slot *old, const struct kvm_memory_slot *new, enum kvm_mr_change change) { int old_flags = old ? old->flags : 0; int new_flags = new ? new->flags : 0; /* * Update the total number of memslot pages before calling the arch * hook so that architectures can consume the result directly. */ if (change == KVM_MR_DELETE) kvm->nr_memslot_pages -= old->npages; else if (change == KVM_MR_CREATE) kvm->nr_memslot_pages += new->npages; if ((old_flags ^ new_flags) & KVM_MEM_LOG_DIRTY_PAGES) { int change = (new_flags & KVM_MEM_LOG_DIRTY_PAGES) ? 1 : -1; atomic_set(&kvm->nr_memslots_dirty_logging, atomic_read(&kvm->nr_memslots_dirty_logging) + change); } kvm_arch_commit_memory_region(kvm, old, new, change); switch (change) { case KVM_MR_CREATE: /* Nothing more to do. */ break; case KVM_MR_DELETE: /* Free the old memslot and all its metadata. */ kvm_free_memslot(kvm, old); break; case KVM_MR_MOVE: case KVM_MR_FLAGS_ONLY: /* * Free the dirty bitmap as needed; the below check encompasses * both the flags and whether a ring buffer is being used) */ if (old->dirty_bitmap && !new->dirty_bitmap) kvm_destroy_dirty_bitmap(old); /* * The final quirk. Free the detached, old slot, but only its * memory, not any metadata. Metadata, including arch specific * data, may be reused by @new. */ kfree(old); break; default: BUG(); } } /* * Activate @new, which must be installed in the inactive slots by the caller, * by swapping the active slots and then propagating @new to @old once @old is * unreachable and can be safely modified. * * With NULL @old this simply adds @new to @active (while swapping the sets). * With NULL @new this simply removes @old from @active and frees it * (while also swapping the sets). */ static void kvm_activate_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { int as_id = kvm_memslots_get_as_id(old, new); kvm_swap_active_memslots(kvm, as_id); /* Propagate the new memslot to the now inactive memslots. */ kvm_replace_memslot(kvm, old, new); } static void kvm_copy_memslot(struct kvm_memory_slot *dest, const struct kvm_memory_slot *src) { dest->base_gfn = src->base_gfn; dest->npages = src->npages; dest->dirty_bitmap = src->dirty_bitmap; dest->arch = src->arch; dest->userspace_addr = src->userspace_addr; dest->flags = src->flags; dest->id = src->id; dest->as_id = src->as_id; } static void kvm_invalidate_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *invalid_slot) { /* * Mark the current slot INVALID. As with all memslot modifications, * this must be done on an unreachable slot to avoid modifying the * current slot in the active tree. */ kvm_copy_memslot(invalid_slot, old); invalid_slot->flags |= KVM_MEMSLOT_INVALID; kvm_replace_memslot(kvm, old, invalid_slot); /* * Activate the slot that is now marked INVALID, but don't propagate * the slot to the now inactive slots. The slot is either going to be * deleted or recreated as a new slot. */ kvm_swap_active_memslots(kvm, old->as_id); /* * From this point no new shadow pages pointing to a deleted, or moved, * memslot will be created. Validation of sp->gfn happens in: * - gfn_to_hva (kvm_read_guest, gfn_to_pfn) * - kvm_is_visible_gfn (mmu_check_root) */ kvm_arch_flush_shadow_memslot(kvm, old); kvm_arch_guest_memory_reclaimed(kvm); /* Was released by kvm_swap_active_memslots(), reacquire. */ mutex_lock(&kvm->slots_arch_lock); /* * Copy the arch-specific field of the newly-installed slot back to the * old slot as the arch data could have changed between releasing * slots_arch_lock in kvm_swap_active_memslots() and re-acquiring the lock * above. Writers are required to retrieve memslots *after* acquiring * slots_arch_lock, thus the active slot's data is guaranteed to be fresh. */ old->arch = invalid_slot->arch; } static void kvm_create_memslot(struct kvm *kvm, struct kvm_memory_slot *new) { /* Add the new memslot to the inactive set and activate. */ kvm_replace_memslot(kvm, NULL, new); kvm_activate_memslot(kvm, NULL, new); } static void kvm_delete_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *invalid_slot) { /* * Remove the old memslot (in the inactive memslots) by passing NULL as * the "new" slot, and for the invalid version in the active slots. */ kvm_replace_memslot(kvm, old, NULL); kvm_activate_memslot(kvm, invalid_slot, NULL); } static void kvm_move_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, struct kvm_memory_slot *invalid_slot) { /* * Replace the old memslot in the inactive slots, and then swap slots * and replace the current INVALID with the new as well. */ kvm_replace_memslot(kvm, old, new); kvm_activate_memslot(kvm, invalid_slot, new); } static void kvm_update_flags_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new) { /* * Similar to the MOVE case, but the slot doesn't need to be zapped as * an intermediate step. Instead, the old memslot is simply replaced * with a new, updated copy in both memslot sets. */ kvm_replace_memslot(kvm, old, new); kvm_activate_memslot(kvm, old, new); } static int kvm_set_memslot(struct kvm *kvm, struct kvm_memory_slot *old, struct kvm_memory_slot *new, enum kvm_mr_change change) { struct kvm_memory_slot *invalid_slot; int r; /* * Released in kvm_swap_active_memslots(). * * Must be held from before the current memslots are copied until after * the new memslots are installed with rcu_assign_pointer, then * released before the synchronize srcu in kvm_swap_active_memslots(). * * When modifying memslots outside of the slots_lock, must be held * before reading the pointer to the current memslots until after all * changes to those memslots are complete. * * These rules ensure that installing new memslots does not lose * changes made to the previous memslots. */ mutex_lock(&kvm->slots_arch_lock); /* * Invalidate the old slot if it's being deleted or moved. This is * done prior to actually deleting/moving the memslot to allow vCPUs to * continue running by ensuring there are no mappings or shadow pages * for the memslot when it is deleted/moved. Without pre-invalidation * (and without a lock), a window would exist between effecting the * delete/move and committing the changes in arch code where KVM or a * guest could access a non-existent memslot. * * Modifications are done on a temporary, unreachable slot. The old * slot needs to be preserved in case a later step fails and the * invalidation needs to be reverted. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { invalid_slot = kzalloc(sizeof(*invalid_slot), GFP_KERNEL_ACCOUNT); if (!invalid_slot) { mutex_unlock(&kvm->slots_arch_lock); return -ENOMEM; } kvm_invalidate_memslot(kvm, old, invalid_slot); } r = kvm_prepare_memory_region(kvm, old, new, change); if (r) { /* * For DELETE/MOVE, revert the above INVALID change. No * modifications required since the original slot was preserved * in the inactive slots. Changing the active memslots also * release slots_arch_lock. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) { kvm_activate_memslot(kvm, invalid_slot, old); kfree(invalid_slot); } else { mutex_unlock(&kvm->slots_arch_lock); } return r; } /* * For DELETE and MOVE, the working slot is now active as the INVALID * version of the old slot. MOVE is particularly special as it reuses * the old slot and returns a copy of the old slot (in working_slot). * For CREATE, there is no old slot. For DELETE and FLAGS_ONLY, the * old slot is detached but otherwise preserved. */ if (change == KVM_MR_CREATE) kvm_create_memslot(kvm, new); else if (change == KVM_MR_DELETE) kvm_delete_memslot(kvm, old, invalid_slot); else if (change == KVM_MR_MOVE) kvm_move_memslot(kvm, old, new, invalid_slot); else if (change == KVM_MR_FLAGS_ONLY) kvm_update_flags_memslot(kvm, old, new); else BUG(); /* Free the temporary INVALID slot used for DELETE and MOVE. */ if (change == KVM_MR_DELETE || change == KVM_MR_MOVE) kfree(invalid_slot); /* * No need to refresh new->arch, changes after dropping slots_arch_lock * will directly hit the final, active memslot. Architectures are * responsible for knowing that new->arch may be stale. */ kvm_commit_memory_region(kvm, old, new, change); return 0; } static bool kvm_check_memslot_overlap(struct kvm_memslots *slots, int id, gfn_t start, gfn_t end) { struct kvm_memslot_iter iter; kvm_for_each_memslot_in_gfn_range(&iter, slots, start, end) { if (iter.slot->id != id) return true; } return false; } /* * Allocate some memory and give it an address in the guest physical address * space. * * Discontiguous memory is allowed, mostly for framebuffers. * * Must be called holding kvm->slots_lock for write. */ int __kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { struct kvm_memory_slot *old, *new; struct kvm_memslots *slots; enum kvm_mr_change change; unsigned long npages; gfn_t base_gfn; int as_id, id; int r; r = check_memory_region_flags(kvm, mem); if (r) return r; as_id = mem->slot >> 16; id = (u16)mem->slot; /* General sanity checks */ if ((mem->memory_size & (PAGE_SIZE - 1)) || (mem->memory_size != (unsigned long)mem->memory_size)) return -EINVAL; if (mem->guest_phys_addr & (PAGE_SIZE - 1)) return -EINVAL; /* We can read the guest memory with __xxx_user() later on. */ if ((mem->userspace_addr & (PAGE_SIZE - 1)) || (mem->userspace_addr != untagged_addr(mem->userspace_addr)) || !access_ok((void __user *)(unsigned long)mem->userspace_addr, mem->memory_size)) return -EINVAL; if (mem->flags & KVM_MEM_GUEST_MEMFD && (mem->guest_memfd_offset & (PAGE_SIZE - 1) || mem->guest_memfd_offset + mem->memory_size < mem->guest_memfd_offset)) return -EINVAL; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_MEM_SLOTS_NUM) return -EINVAL; if (mem->guest_phys_addr + mem->memory_size < mem->guest_phys_addr) return -EINVAL; if ((mem->memory_size >> PAGE_SHIFT) > KVM_MEM_MAX_NR_PAGES) return -EINVAL; slots = __kvm_memslots(kvm, as_id); /* * Note, the old memslot (and the pointer itself!) may be invalidated * and/or destroyed by kvm_set_memslot(). */ old = id_to_memslot(slots, id); if (!mem->memory_size) { if (!old || !old->npages) return -EINVAL; if (WARN_ON_ONCE(kvm->nr_memslot_pages < old->npages)) return -EIO; return kvm_set_memslot(kvm, old, NULL, KVM_MR_DELETE); } base_gfn = (mem->guest_phys_addr >> PAGE_SHIFT); npages = (mem->memory_size >> PAGE_SHIFT); if (!old || !old->npages) { change = KVM_MR_CREATE; /* * To simplify KVM internals, the total number of pages across * all memslots must fit in an unsigned long. */ if ((kvm->nr_memslot_pages + npages) < kvm->nr_memslot_pages) return -EINVAL; } else { /* Modify an existing slot. */ /* Private memslots are immutable, they can only be deleted. */ if (mem->flags & KVM_MEM_GUEST_MEMFD) return -EINVAL; if ((mem->userspace_addr != old->userspace_addr) || (npages != old->npages) || ((mem->flags ^ old->flags) & KVM_MEM_READONLY)) return -EINVAL; if (base_gfn != old->base_gfn) change = KVM_MR_MOVE; else if (mem->flags != old->flags) change = KVM_MR_FLAGS_ONLY; else /* Nothing to change. */ return 0; } if ((change == KVM_MR_CREATE || change == KVM_MR_MOVE) && kvm_check_memslot_overlap(slots, id, base_gfn, base_gfn + npages)) return -EEXIST; /* Allocate a slot that will persist in the memslot. */ new = kzalloc(sizeof(*new), GFP_KERNEL_ACCOUNT); if (!new) return -ENOMEM; new->as_id = as_id; new->id = id; new->base_gfn = base_gfn; new->npages = npages; new->flags = mem->flags; new->userspace_addr = mem->userspace_addr; if (mem->flags & KVM_MEM_GUEST_MEMFD) { r = kvm_gmem_bind(kvm, new, mem->guest_memfd, mem->guest_memfd_offset); if (r) goto out; } r = kvm_set_memslot(kvm, old, new, change); if (r) goto out_unbind; return 0; out_unbind: if (mem->flags & KVM_MEM_GUEST_MEMFD) kvm_gmem_unbind(new); out: kfree(new); return r; } EXPORT_SYMBOL_GPL(__kvm_set_memory_region); int kvm_set_memory_region(struct kvm *kvm, const struct kvm_userspace_memory_region2 *mem) { int r; mutex_lock(&kvm->slots_lock); r = __kvm_set_memory_region(kvm, mem); mutex_unlock(&kvm->slots_lock); return r; } EXPORT_SYMBOL_GPL(kvm_set_memory_region); static int kvm_vm_ioctl_set_memory_region(struct kvm *kvm, struct kvm_userspace_memory_region2 *mem) { if ((u16)mem->slot >= KVM_USER_MEM_SLOTS) return -EINVAL; return kvm_set_memory_region(kvm, mem); } #ifndef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT /** * kvm_get_dirty_log - get a snapshot of dirty pages * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * @is_dirty: set to '1' if any dirty pages were found * @memslot: set to the associated memslot, always valid on success */ int kvm_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log, int *is_dirty, struct kvm_memory_slot **memslot) { struct kvm_memslots *slots; int i, as_id, id; unsigned long n; unsigned long any = 0; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; *memslot = NULL; *is_dirty = 0; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); *memslot = id_to_memslot(slots, id); if (!(*memslot) || !(*memslot)->dirty_bitmap) return -ENOENT; kvm_arch_sync_dirty_log(kvm, *memslot); n = kvm_dirty_bitmap_bytes(*memslot); for (i = 0; !any && i < n/sizeof(long); ++i) any = (*memslot)->dirty_bitmap[i]; if (copy_to_user(log->dirty_bitmap, (*memslot)->dirty_bitmap, n)) return -EFAULT; if (any) *is_dirty = 1; return 0; } EXPORT_SYMBOL_GPL(kvm_get_dirty_log); #else /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ /** * kvm_get_dirty_log_protect - get a snapshot of dirty pages * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address to which we copy the log * * We need to keep it in mind that VCPU threads can write to the bitmap * concurrently. So, to avoid losing track of dirty pages we keep the * following order: * * 1. Take a snapshot of the bit and clear it if needed. * 2. Write protect the corresponding page. * 3. Copy the snapshot to the userspace. * 4. Upon return caller flushes TLB's if needed. * * Between 2 and 4, the guest may write to the page using the remaining TLB * entry. This is not a problem because the page is reported dirty using * the snapshot taken before and step 4 ensures that writes done after * exiting to userspace will be logged for the next call. * */ static int kvm_get_dirty_log_protect(struct kvm *kvm, struct kvm_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int i, as_id, id; unsigned long n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; bool flush; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap) return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; kvm_arch_sync_dirty_log(kvm, memslot); n = kvm_dirty_bitmap_bytes(memslot); flush = false; if (kvm->manual_dirty_log_protect) { /* * Unlike kvm_get_dirty_log, we always return false in *flush, * because no flush is needed until KVM_CLEAR_DIRTY_LOG. There * is some code duplication between this function and * kvm_get_dirty_log, but hopefully all architecture * transition to kvm_get_dirty_log_protect and kvm_get_dirty_log * can be eliminated. */ dirty_bitmap_buffer = dirty_bitmap; } else { dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); memset(dirty_bitmap_buffer, 0, n); KVM_MMU_LOCK(kvm); for (i = 0; i < n / sizeof(long); i++) { unsigned long mask; gfn_t offset; if (!dirty_bitmap[i]) continue; flush = true; mask = xchg(&dirty_bitmap[i], 0); dirty_bitmap_buffer[i] = mask; offset = i * BITS_PER_LONG; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } KVM_MMU_UNLOCK(kvm); } if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); if (copy_to_user(log->dirty_bitmap, dirty_bitmap_buffer, n)) return -EFAULT; return 0; } /** * kvm_vm_ioctl_get_dirty_log - get and clear the log of dirty pages in a slot * @kvm: kvm instance * @log: slot id and address to which we copy the log * * Steps 1-4 below provide general overview of dirty page logging. See * kvm_get_dirty_log_protect() function description for additional details. * * We call kvm_get_dirty_log_protect() to handle steps 1-3, upon return we * always flush the TLB (step 4) even if previous step failed and the dirty * bitmap may be corrupt. Regardless of previous outcome the KVM logging API * does not preclude user space subsequent dirty log read. Flushing TLB ensures * writes will be marked dirty for next log read. * * 1. Take a snapshot of the bit and clear it if needed. * 2. Write protect the corresponding page. * 3. Copy the snapshot to the userspace. * 4. Flush TLB's if needed. */ static int kvm_vm_ioctl_get_dirty_log(struct kvm *kvm, struct kvm_dirty_log *log) { int r; mutex_lock(&kvm->slots_lock); r = kvm_get_dirty_log_protect(kvm, log); mutex_unlock(&kvm->slots_lock); return r; } /** * kvm_clear_dirty_log_protect - clear dirty bits in the bitmap * and reenable dirty page tracking for the corresponding pages. * @kvm: pointer to kvm instance * @log: slot id and address from which to fetch the bitmap of dirty pages */ static int kvm_clear_dirty_log_protect(struct kvm *kvm, struct kvm_clear_dirty_log *log) { struct kvm_memslots *slots; struct kvm_memory_slot *memslot; int as_id, id; gfn_t offset; unsigned long i, n; unsigned long *dirty_bitmap; unsigned long *dirty_bitmap_buffer; bool flush; /* Dirty ring tracking may be exclusive to dirty log tracking */ if (!kvm_use_dirty_bitmap(kvm)) return -ENXIO; as_id = log->slot >> 16; id = (u16)log->slot; if (as_id >= kvm_arch_nr_memslot_as_ids(kvm) || id >= KVM_USER_MEM_SLOTS) return -EINVAL; if (log->first_page & 63) return -EINVAL; slots = __kvm_memslots(kvm, as_id); memslot = id_to_memslot(slots, id); if (!memslot || !memslot->dirty_bitmap) return -ENOENT; dirty_bitmap = memslot->dirty_bitmap; n = ALIGN(log->num_pages, BITS_PER_LONG) / 8; if (log->first_page > memslot->npages || log->num_pages > memslot->npages - log->first_page || (log->num_pages < memslot->npages - log->first_page && (log->num_pages & 63))) return -EINVAL; kvm_arch_sync_dirty_log(kvm, memslot); flush = false; dirty_bitmap_buffer = kvm_second_dirty_bitmap(memslot); if (copy_from_user(dirty_bitmap_buffer, log->dirty_bitmap, n)) return -EFAULT; KVM_MMU_LOCK(kvm); for (offset = log->first_page, i = offset / BITS_PER_LONG, n = DIV_ROUND_UP(log->num_pages, BITS_PER_LONG); n--; i++, offset += BITS_PER_LONG) { unsigned long mask = *dirty_bitmap_buffer++; atomic_long_t *p = (atomic_long_t *) &dirty_bitmap[i]; if (!mask) continue; mask &= atomic_long_fetch_andnot(mask, p); /* * mask contains the bits that really have been cleared. This * never includes any bits beyond the length of the memslot (if * the length is not aligned to 64 pages), therefore it is not * a problem if userspace sets them in log->dirty_bitmap. */ if (mask) { flush = true; kvm_arch_mmu_enable_log_dirty_pt_masked(kvm, memslot, offset, mask); } } KVM_MMU_UNLOCK(kvm); if (flush) kvm_flush_remote_tlbs_memslot(kvm, memslot); return 0; } static int kvm_vm_ioctl_clear_dirty_log(struct kvm *kvm, struct kvm_clear_dirty_log *log) { int r; mutex_lock(&kvm->slots_lock); r = kvm_clear_dirty_log_protect(kvm, log); mutex_unlock(&kvm->slots_lock); return r; } #endif /* CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES /* * Returns true if _all_ gfns in the range [@start, @end) have attributes * matching @attrs. */ bool kvm_range_has_memory_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long attrs) { XA_STATE(xas, &kvm->mem_attr_array, start); unsigned long index; bool has_attrs; void *entry; rcu_read_lock(); if (!attrs) { has_attrs = !xas_find(&xas, end - 1); goto out; } has_attrs = true; for (index = start; index < end; index++) { do { entry = xas_next(&xas); } while (xas_retry(&xas, entry)); if (xas.xa_index != index || xa_to_value(entry) != attrs) { has_attrs = false; break; } } out: rcu_read_unlock(); return has_attrs; } static u64 kvm_supported_mem_attributes(struct kvm *kvm) { if (!kvm || kvm_arch_has_private_mem(kvm)) return KVM_MEMORY_ATTRIBUTE_PRIVATE; return 0; } static __always_inline void kvm_handle_gfn_range(struct kvm *kvm, struct kvm_mmu_notifier_range *range) { struct kvm_gfn_range gfn_range; struct kvm_memory_slot *slot; struct kvm_memslots *slots; struct kvm_memslot_iter iter; bool found_memslot = false; bool ret = false; int i; gfn_range.arg = range->arg; gfn_range.may_block = range->may_block; for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { slots = __kvm_memslots(kvm, i); kvm_for_each_memslot_in_gfn_range(&iter, slots, range->start, range->end) { slot = iter.slot; gfn_range.slot = slot; gfn_range.start = max(range->start, slot->base_gfn); gfn_range.end = min(range->end, slot->base_gfn + slot->npages); if (gfn_range.start >= gfn_range.end) continue; if (!found_memslot) { found_memslot = true; KVM_MMU_LOCK(kvm); if (!IS_KVM_NULL_FN(range->on_lock)) range->on_lock(kvm); } ret |= range->handler(kvm, &gfn_range); } } if (range->flush_on_ret && ret) kvm_flush_remote_tlbs(kvm); if (found_memslot) KVM_MMU_UNLOCK(kvm); } static bool kvm_pre_set_memory_attributes(struct kvm *kvm, struct kvm_gfn_range *range) { /* * Unconditionally add the range to the invalidation set, regardless of * whether or not the arch callback actually needs to zap SPTEs. E.g. * if KVM supports RWX attributes in the future and the attributes are * going from R=>RW, zapping isn't strictly necessary. Unconditionally * adding the range allows KVM to require that MMU invalidations add at * least one range between begin() and end(), e.g. allows KVM to detect * bugs where the add() is missed. Relaxing the rule *might* be safe, * but it's not obvious that allowing new mappings while the attributes * are in flux is desirable or worth the complexity. */ kvm_mmu_invalidate_range_add(kvm, range->start, range->end); return kvm_arch_pre_set_memory_attributes(kvm, range); } /* Set @attributes for the gfn range [@start, @end). */ static int kvm_vm_set_mem_attributes(struct kvm *kvm, gfn_t start, gfn_t end, unsigned long attributes) { struct kvm_mmu_notifier_range pre_set_range = { .start = start, .end = end, .handler = kvm_pre_set_memory_attributes, .on_lock = kvm_mmu_invalidate_begin, .flush_on_ret = true, .may_block = true, }; struct kvm_mmu_notifier_range post_set_range = { .start = start, .end = end, .arg.attributes = attributes, .handler = kvm_arch_post_set_memory_attributes, .on_lock = kvm_mmu_invalidate_end, .may_block = true, }; unsigned long i; void *entry; int r = 0; entry = attributes ? xa_mk_value(attributes) : NULL; mutex_lock(&kvm->slots_lock); /* Nothing to do if the entire range as the desired attributes. */ if (kvm_range_has_memory_attributes(kvm, start, end, attributes)) goto out_unlock; /* * Reserve memory ahead of time to avoid having to deal with failures * partway through setting the new attributes. */ for (i = start; i < end; i++) { r = xa_reserve(&kvm->mem_attr_array, i, GFP_KERNEL_ACCOUNT); if (r) goto out_unlock; } kvm_handle_gfn_range(kvm, &pre_set_range); for (i = start; i < end; i++) { r = xa_err(xa_store(&kvm->mem_attr_array, i, entry, GFP_KERNEL_ACCOUNT)); KVM_BUG_ON(r, kvm); } kvm_handle_gfn_range(kvm, &post_set_range); out_unlock: mutex_unlock(&kvm->slots_lock); return r; } static int kvm_vm_ioctl_set_mem_attributes(struct kvm *kvm, struct kvm_memory_attributes *attrs) { gfn_t start, end; /* flags is currently not used. */ if (attrs->flags) return -EINVAL; if (attrs->attributes & ~kvm_supported_mem_attributes(kvm)) return -EINVAL; if (attrs->size == 0 || attrs->address + attrs->size < attrs->address) return -EINVAL; if (!PAGE_ALIGNED(attrs->address) || !PAGE_ALIGNED(attrs->size)) return -EINVAL; start = attrs->address >> PAGE_SHIFT; end = (attrs->address + attrs->size) >> PAGE_SHIFT; /* * xarray tracks data using "unsigned long", and as a result so does * KVM. For simplicity, supports generic attributes only on 64-bit * architectures. */ BUILD_BUG_ON(sizeof(attrs->attributes) != sizeof(unsigned long)); return kvm_vm_set_mem_attributes(kvm, start, end, attrs->attributes); } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ struct kvm_memory_slot *gfn_to_memslot(struct kvm *kvm, gfn_t gfn) { return __gfn_to_memslot(kvm_memslots(kvm), gfn); } EXPORT_SYMBOL_GPL(gfn_to_memslot); struct kvm_memory_slot *kvm_vcpu_gfn_to_memslot(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memslots *slots = kvm_vcpu_memslots(vcpu); u64 gen = slots->generation; struct kvm_memory_slot *slot; /* * This also protects against using a memslot from a different address space, * since different address spaces have different generation numbers. */ if (unlikely(gen != vcpu->last_used_slot_gen)) { vcpu->last_used_slot = NULL; vcpu->last_used_slot_gen = gen; } slot = try_get_memslot(vcpu->last_used_slot, gfn); if (slot) return slot; /* * Fall back to searching all memslots. We purposely use * search_memslots() instead of __gfn_to_memslot() to avoid * thrashing the VM-wide last_used_slot in kvm_memslots. */ slot = search_memslots(slots, gfn, false); if (slot) { vcpu->last_used_slot = slot; return slot; } return NULL; } bool kvm_is_visible_gfn(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot = gfn_to_memslot(kvm, gfn); return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_is_visible_gfn); bool kvm_vcpu_is_visible_gfn(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memory_slot *memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return kvm_is_visible_memslot(memslot); } EXPORT_SYMBOL_GPL(kvm_vcpu_is_visible_gfn); unsigned long kvm_host_page_size(struct kvm_vcpu *vcpu, gfn_t gfn) { struct vm_area_struct *vma; unsigned long addr, size; size = PAGE_SIZE; addr = kvm_vcpu_gfn_to_hva_prot(vcpu, gfn, NULL); if (kvm_is_error_hva(addr)) return PAGE_SIZE; mmap_read_lock(current->mm); vma = find_vma(current->mm, addr); if (!vma) goto out; size = vma_kernel_pagesize(vma); out: mmap_read_unlock(current->mm); return size; } static bool memslot_is_readonly(const struct kvm_memory_slot *slot) { return slot->flags & KVM_MEM_READONLY; } static unsigned long __gfn_to_hva_many(const struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages, bool write) { if (!slot || slot->flags & KVM_MEMSLOT_INVALID) return KVM_HVA_ERR_BAD; if (memslot_is_readonly(slot) && write) return KVM_HVA_ERR_RO_BAD; if (nr_pages) *nr_pages = slot->npages - (gfn - slot->base_gfn); return __gfn_to_hva_memslot(slot, gfn); } static unsigned long gfn_to_hva_many(struct kvm_memory_slot *slot, gfn_t gfn, gfn_t *nr_pages) { return __gfn_to_hva_many(slot, gfn, nr_pages, true); } unsigned long gfn_to_hva_memslot(struct kvm_memory_slot *slot, gfn_t gfn) { return gfn_to_hva_many(slot, gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva_memslot); unsigned long gfn_to_hva(struct kvm *kvm, gfn_t gfn) { return gfn_to_hva_many(gfn_to_memslot(kvm, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(gfn_to_hva); unsigned long kvm_vcpu_gfn_to_hva(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_hva_many(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn, NULL); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_hva); /* * Return the hva of a @gfn and the R/W attribute if possible. * * @slot: the kvm_memory_slot which contains @gfn * @gfn: the gfn to be translated * @writable: used to return the read/write attribute of the @slot if the hva * is valid and @writable is not NULL */ unsigned long gfn_to_hva_memslot_prot(struct kvm_memory_slot *slot, gfn_t gfn, bool *writable) { unsigned long hva = __gfn_to_hva_many(slot, gfn, NULL, false); if (!kvm_is_error_hva(hva) && writable) *writable = !memslot_is_readonly(slot); return hva; } unsigned long gfn_to_hva_prot(struct kvm *kvm, gfn_t gfn, bool *writable) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return gfn_to_hva_memslot_prot(slot, gfn, writable); } unsigned long kvm_vcpu_gfn_to_hva_prot(struct kvm_vcpu *vcpu, gfn_t gfn, bool *writable) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return gfn_to_hva_memslot_prot(slot, gfn, writable); } static inline int check_user_page_hwpoison(unsigned long addr) { int rc, flags = FOLL_HWPOISON | FOLL_WRITE; rc = get_user_pages(addr, 1, flags, NULL); return rc == -EHWPOISON; } /* * The fast path to get the writable pfn which will be stored in @pfn, * true indicates success, otherwise false is returned. It's also the * only part that runs if we can in atomic context. */ static bool hva_to_pfn_fast(unsigned long addr, bool write_fault, bool *writable, kvm_pfn_t *pfn) { struct page *page[1]; /* * Fast pin a writable pfn only if it is a write fault request * or the caller allows to map a writable pfn for a read fault * request. */ if (!(write_fault || writable)) return false; if (get_user_page_fast_only(addr, FOLL_WRITE, page)) { *pfn = page_to_pfn(page[0]); if (writable) *writable = true; return true; } return false; } /* * The slow path to get the pfn of the specified host virtual address, * 1 indicates success, -errno is returned if error is detected. */ static int hva_to_pfn_slow(unsigned long addr, bool *async, bool write_fault, bool interruptible, bool *writable, kvm_pfn_t *pfn) { /* * When a VCPU accesses a page that is not mapped into the secondary * MMU, we lookup the page using GUP to map it, so the guest VCPU can * make progress. We always want to honor NUMA hinting faults in that * case, because GUP usage corresponds to memory accesses from the VCPU. * Otherwise, we'd not trigger NUMA hinting faults once a page is * mapped into the secondary MMU and gets accessed by a VCPU. * * Note that get_user_page_fast_only() and FOLL_WRITE for now * implicitly honor NUMA hinting faults and don't need this flag. */ unsigned int flags = FOLL_HWPOISON | FOLL_HONOR_NUMA_FAULT; struct page *page; int npages; might_sleep(); if (writable) *writable = write_fault; if (write_fault) flags |= FOLL_WRITE; if (async) flags |= FOLL_NOWAIT; if (interruptible) flags |= FOLL_INTERRUPTIBLE; npages = get_user_pages_unlocked(addr, 1, &page, flags); if (npages != 1) return npages; /* map read fault as writable if possible */ if (unlikely(!write_fault) && writable) { struct page *wpage; if (get_user_page_fast_only(addr, FOLL_WRITE, &wpage)) { *writable = true; put_page(page); page = wpage; } } *pfn = page_to_pfn(page); return npages; } static bool vma_is_valid(struct vm_area_struct *vma, bool write_fault) { if (unlikely(!(vma->vm_flags & VM_READ))) return false; if (write_fault && (unlikely(!(vma->vm_flags & VM_WRITE)))) return false; return true; } static int kvm_try_get_pfn(kvm_pfn_t pfn) { struct page *page = kvm_pfn_to_refcounted_page(pfn); if (!page) return 1; return get_page_unless_zero(page); } static int hva_to_pfn_remapped(struct vm_area_struct *vma, unsigned long addr, bool write_fault, bool *writable, kvm_pfn_t *p_pfn) { kvm_pfn_t pfn; pte_t *ptep; pte_t pte; spinlock_t *ptl; int r; r = follow_pte(vma, addr, &ptep, &ptl); if (r) { /* * get_user_pages fails for VM_IO and VM_PFNMAP vmas and does * not call the fault handler, so do it here. */ bool unlocked = false; r = fixup_user_fault(current->mm, addr, (write_fault ? FAULT_FLAG_WRITE : 0), &unlocked); if (unlocked) return -EAGAIN; if (r) return r; r = follow_pte(vma, addr, &ptep, &ptl); if (r) return r; } pte = ptep_get(ptep); if (write_fault && !pte_write(pte)) { pfn = KVM_PFN_ERR_RO_FAULT; goto out; } if (writable) *writable = pte_write(pte); pfn = pte_pfn(pte); /* * Get a reference here because callers of *hva_to_pfn* and * *gfn_to_pfn* ultimately call kvm_release_pfn_clean on the * returned pfn. This is only needed if the VMA has VM_MIXEDMAP * set, but the kvm_try_get_pfn/kvm_release_pfn_clean pair will * simply do nothing for reserved pfns. * * Whoever called remap_pfn_range is also going to call e.g. * unmap_mapping_range before the underlying pages are freed, * causing a call to our MMU notifier. * * Certain IO or PFNMAP mappings can be backed with valid * struct pages, but be allocated without refcounting e.g., * tail pages of non-compound higher order allocations, which * would then underflow the refcount when the caller does the * required put_page. Don't allow those pages here. */ if (!kvm_try_get_pfn(pfn)) r = -EFAULT; out: pte_unmap_unlock(ptep, ptl); *p_pfn = pfn; return r; } /* * Pin guest page in memory and return its pfn. * @addr: host virtual address which maps memory to the guest * @atomic: whether this function is forbidden from sleeping * @interruptible: whether the process can be interrupted by non-fatal signals * @async: whether this function need to wait IO complete if the * host page is not in the memory * @write_fault: whether we should get a writable host page * @writable: whether it allows to map a writable host page for !@write_fault * * The function will map a writable host page for these two cases: * 1): @write_fault = true * 2): @write_fault = false && @writable, @writable will tell the caller * whether the mapping is writable. */ kvm_pfn_t hva_to_pfn(unsigned long addr, bool atomic, bool interruptible, bool *async, bool write_fault, bool *writable) { struct vm_area_struct *vma; kvm_pfn_t pfn; int npages, r; /* we can do it either atomically or asynchronously, not both */ BUG_ON(atomic && async); if (hva_to_pfn_fast(addr, write_fault, writable, &pfn)) return pfn; if (atomic) return KVM_PFN_ERR_FAULT; npages = hva_to_pfn_slow(addr, async, write_fault, interruptible, writable, &pfn); if (npages == 1) return pfn; if (npages == -EINTR) return KVM_PFN_ERR_SIGPENDING; mmap_read_lock(current->mm); if (npages == -EHWPOISON || (!async && check_user_page_hwpoison(addr))) { pfn = KVM_PFN_ERR_HWPOISON; goto exit; } retry: vma = vma_lookup(current->mm, addr); if (vma == NULL) pfn = KVM_PFN_ERR_FAULT; else if (vma->vm_flags & (VM_IO | VM_PFNMAP)) { r = hva_to_pfn_remapped(vma, addr, write_fault, writable, &pfn); if (r == -EAGAIN) goto retry; if (r < 0) pfn = KVM_PFN_ERR_FAULT; } else { if (async && vma_is_valid(vma, write_fault)) *async = true; pfn = KVM_PFN_ERR_FAULT; } exit: mmap_read_unlock(current->mm); return pfn; } kvm_pfn_t __gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn, bool atomic, bool interruptible, bool *async, bool write_fault, bool *writable, hva_t *hva) { unsigned long addr = __gfn_to_hva_many(slot, gfn, NULL, write_fault); if (hva) *hva = addr; if (kvm_is_error_hva(addr)) { if (writable) *writable = false; return addr == KVM_HVA_ERR_RO_BAD ? KVM_PFN_ERR_RO_FAULT : KVM_PFN_NOSLOT; } /* Do not map writable pfn in the readonly memslot. */ if (writable && memslot_is_readonly(slot)) { *writable = false; writable = NULL; } return hva_to_pfn(addr, atomic, interruptible, async, write_fault, writable); } EXPORT_SYMBOL_GPL(__gfn_to_pfn_memslot); kvm_pfn_t gfn_to_pfn_prot(struct kvm *kvm, gfn_t gfn, bool write_fault, bool *writable) { return __gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn, false, false, NULL, write_fault, writable, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_prot); kvm_pfn_t gfn_to_pfn_memslot(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, false, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot); kvm_pfn_t gfn_to_pfn_memslot_atomic(const struct kvm_memory_slot *slot, gfn_t gfn) { return __gfn_to_pfn_memslot(slot, gfn, true, false, NULL, true, NULL, NULL); } EXPORT_SYMBOL_GPL(gfn_to_pfn_memslot_atomic); kvm_pfn_t kvm_vcpu_gfn_to_pfn_atomic(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot_atomic(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn_atomic); kvm_pfn_t gfn_to_pfn(struct kvm *kvm, gfn_t gfn) { return gfn_to_pfn_memslot(gfn_to_memslot(kvm, gfn), gfn); } EXPORT_SYMBOL_GPL(gfn_to_pfn); kvm_pfn_t kvm_vcpu_gfn_to_pfn(struct kvm_vcpu *vcpu, gfn_t gfn) { return gfn_to_pfn_memslot(kvm_vcpu_gfn_to_memslot(vcpu, gfn), gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_gfn_to_pfn); int gfn_to_page_many_atomic(struct kvm_memory_slot *slot, gfn_t gfn, struct page **pages, int nr_pages) { unsigned long addr; gfn_t entry = 0; addr = gfn_to_hva_many(slot, gfn, &entry); if (kvm_is_error_hva(addr)) return -1; if (entry < nr_pages) return 0; return get_user_pages_fast_only(addr, nr_pages, FOLL_WRITE, pages); } EXPORT_SYMBOL_GPL(gfn_to_page_many_atomic); /* * Do not use this helper unless you are absolutely certain the gfn _must_ be * backed by 'struct page'. A valid example is if the backing memslot is * controlled by KVM. Note, if the returned page is valid, it's refcount has * been elevated by gfn_to_pfn(). */ struct page *gfn_to_page(struct kvm *kvm, gfn_t gfn) { struct page *page; kvm_pfn_t pfn; pfn = gfn_to_pfn(kvm, gfn); if (is_error_noslot_pfn(pfn)) return KVM_ERR_PTR_BAD_PAGE; page = kvm_pfn_to_refcounted_page(pfn); if (!page) return KVM_ERR_PTR_BAD_PAGE; return page; } EXPORT_SYMBOL_GPL(gfn_to_page); void kvm_release_pfn(kvm_pfn_t pfn, bool dirty) { if (dirty) kvm_release_pfn_dirty(pfn); else kvm_release_pfn_clean(pfn); } int kvm_vcpu_map(struct kvm_vcpu *vcpu, gfn_t gfn, struct kvm_host_map *map) { kvm_pfn_t pfn; void *hva = NULL; struct page *page = KVM_UNMAPPED_PAGE; if (!map) return -EINVAL; pfn = gfn_to_pfn(vcpu->kvm, gfn); if (is_error_noslot_pfn(pfn)) return -EINVAL; if (pfn_valid(pfn)) { page = pfn_to_page(pfn); hva = kmap(page); #ifdef CONFIG_HAS_IOMEM } else { hva = memremap(pfn_to_hpa(pfn), PAGE_SIZE, MEMREMAP_WB); #endif } if (!hva) return -EFAULT; map->page = page; map->hva = hva; map->pfn = pfn; map->gfn = gfn; return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_map); void kvm_vcpu_unmap(struct kvm_vcpu *vcpu, struct kvm_host_map *map, bool dirty) { if (!map) return; if (!map->hva) return; if (map->page != KVM_UNMAPPED_PAGE) kunmap(map->page); #ifdef CONFIG_HAS_IOMEM else memunmap(map->hva); #endif if (dirty) kvm_vcpu_mark_page_dirty(vcpu, map->gfn); kvm_release_pfn(map->pfn, dirty); map->hva = NULL; map->page = NULL; } EXPORT_SYMBOL_GPL(kvm_vcpu_unmap); static bool kvm_is_ad_tracked_page(struct page *page) { /* * Per page-flags.h, pages tagged PG_reserved "should in general not be * touched (e.g. set dirty) except by its owner". */ return !PageReserved(page); } static void kvm_set_page_dirty(struct page *page) { if (kvm_is_ad_tracked_page(page)) SetPageDirty(page); } static void kvm_set_page_accessed(struct page *page) { if (kvm_is_ad_tracked_page(page)) mark_page_accessed(page); } void kvm_release_page_clean(struct page *page) { WARN_ON(is_error_page(page)); kvm_set_page_accessed(page); put_page(page); } EXPORT_SYMBOL_GPL(kvm_release_page_clean); void kvm_release_pfn_clean(kvm_pfn_t pfn) { struct page *page; if (is_error_noslot_pfn(pfn)) return; page = kvm_pfn_to_refcounted_page(pfn); if (!page) return; kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_pfn_clean); void kvm_release_page_dirty(struct page *page) { WARN_ON(is_error_page(page)); kvm_set_page_dirty(page); kvm_release_page_clean(page); } EXPORT_SYMBOL_GPL(kvm_release_page_dirty); void kvm_release_pfn_dirty(kvm_pfn_t pfn) { struct page *page; if (is_error_noslot_pfn(pfn)) return; page = kvm_pfn_to_refcounted_page(pfn); if (!page) return; kvm_release_page_dirty(page); } EXPORT_SYMBOL_GPL(kvm_release_pfn_dirty); /* * Note, checking for an error/noslot pfn is the caller's responsibility when * directly marking a page dirty/accessed. Unlike the "release" helpers, the * "set" helpers are not to be used when the pfn might point at garbage. */ void kvm_set_pfn_dirty(kvm_pfn_t pfn) { if (WARN_ON(is_error_noslot_pfn(pfn))) return; if (pfn_valid(pfn)) kvm_set_page_dirty(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_dirty); void kvm_set_pfn_accessed(kvm_pfn_t pfn) { if (WARN_ON(is_error_noslot_pfn(pfn))) return; if (pfn_valid(pfn)) kvm_set_page_accessed(pfn_to_page(pfn)); } EXPORT_SYMBOL_GPL(kvm_set_pfn_accessed); static int next_segment(unsigned long len, int offset) { if (len > PAGE_SIZE - offset) return PAGE_SIZE - offset; else return len; } /* Copy @len bytes from guest memory at '(@gfn * PAGE_SIZE) + @offset' to @data */ static int __kvm_read_guest_page(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, int len) { int r; unsigned long addr; addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_from_user(data, (void __user *)addr + offset, len); if (r) return -EFAULT; return 0; } int kvm_read_guest_page(struct kvm *kvm, gfn_t gfn, void *data, int offset, int len) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return __kvm_read_guest_page(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_page); int kvm_vcpu_read_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, void *data, int offset, int len) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return __kvm_read_guest_page(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_page); int kvm_read_guest(struct kvm *kvm, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_read_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest); int kvm_vcpu_read_guest(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_vcpu_read_guest_page(vcpu, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest); static int __kvm_read_guest_atomic(struct kvm_memory_slot *slot, gfn_t gfn, void *data, int offset, unsigned long len) { int r; unsigned long addr; addr = gfn_to_hva_memslot_prot(slot, gfn, NULL); if (kvm_is_error_hva(addr)) return -EFAULT; pagefault_disable(); r = __copy_from_user_inatomic(data, (void __user *)addr + offset, len); pagefault_enable(); if (r) return -EFAULT; return 0; } int kvm_vcpu_read_guest_atomic(struct kvm_vcpu *vcpu, gpa_t gpa, void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); int offset = offset_in_page(gpa); return __kvm_read_guest_atomic(slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_read_guest_atomic); /* Copy @len bytes from @data into guest memory at '(@gfn * PAGE_SIZE) + @offset' */ static int __kvm_write_guest_page(struct kvm *kvm, struct kvm_memory_slot *memslot, gfn_t gfn, const void *data, int offset, int len) { int r; unsigned long addr; addr = gfn_to_hva_memslot(memslot, gfn); if (kvm_is_error_hva(addr)) return -EFAULT; r = __copy_to_user((void __user *)addr + offset, data, len); if (r) return -EFAULT; mark_page_dirty_in_slot(kvm, memslot, gfn); return 0; } int kvm_write_guest_page(struct kvm *kvm, gfn_t gfn, const void *data, int offset, int len) { struct kvm_memory_slot *slot = gfn_to_memslot(kvm, gfn); return __kvm_write_guest_page(kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_page); int kvm_vcpu_write_guest_page(struct kvm_vcpu *vcpu, gfn_t gfn, const void *data, int offset, int len) { struct kvm_memory_slot *slot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); return __kvm_write_guest_page(vcpu->kvm, slot, gfn, data, offset, len); } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest_page); int kvm_write_guest(struct kvm *kvm, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest); int kvm_vcpu_write_guest(struct kvm_vcpu *vcpu, gpa_t gpa, const void *data, unsigned long len) { gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_vcpu_write_guest_page(vcpu, gfn, data, offset, seg); if (ret < 0) return ret; offset = 0; len -= seg; data += seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_vcpu_write_guest); static int __kvm_gfn_to_hva_cache_init(struct kvm_memslots *slots, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { int offset = offset_in_page(gpa); gfn_t start_gfn = gpa >> PAGE_SHIFT; gfn_t end_gfn = (gpa + len - 1) >> PAGE_SHIFT; gfn_t nr_pages_needed = end_gfn - start_gfn + 1; gfn_t nr_pages_avail; /* Update ghc->generation before performing any error checks. */ ghc->generation = slots->generation; if (start_gfn > end_gfn) { ghc->hva = KVM_HVA_ERR_BAD; return -EINVAL; } /* * If the requested region crosses two memslots, we still * verify that the entire region is valid here. */ for ( ; start_gfn <= end_gfn; start_gfn += nr_pages_avail) { ghc->memslot = __gfn_to_memslot(slots, start_gfn); ghc->hva = gfn_to_hva_many(ghc->memslot, start_gfn, &nr_pages_avail); if (kvm_is_error_hva(ghc->hva)) return -EFAULT; } /* Use the slow path for cross page reads and writes. */ if (nr_pages_needed == 1) ghc->hva += offset; else ghc->memslot = NULL; ghc->gpa = gpa; ghc->len = len; return 0; } int kvm_gfn_to_hva_cache_init(struct kvm *kvm, struct gfn_to_hva_cache *ghc, gpa_t gpa, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); return __kvm_gfn_to_hva_cache_init(slots, ghc, gpa, len); } EXPORT_SYMBOL_GPL(kvm_gfn_to_hva_cache_init); int kvm_write_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; gpa_t gpa = ghc->gpa + offset; if (WARN_ON_ONCE(len + offset > ghc->len)) return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) return -EFAULT; } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; if (unlikely(!ghc->memslot)) return kvm_write_guest(kvm, gpa, data, len); r = __copy_to_user((void __user *)ghc->hva + offset, data, len); if (r) return -EFAULT; mark_page_dirty_in_slot(kvm, ghc->memslot, gpa >> PAGE_SHIFT); return 0; } EXPORT_SYMBOL_GPL(kvm_write_guest_offset_cached); int kvm_write_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { return kvm_write_guest_offset_cached(kvm, ghc, data, 0, len); } EXPORT_SYMBOL_GPL(kvm_write_guest_cached); int kvm_read_guest_offset_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned int offset, unsigned long len) { struct kvm_memslots *slots = kvm_memslots(kvm); int r; gpa_t gpa = ghc->gpa + offset; if (WARN_ON_ONCE(len + offset > ghc->len)) return -EINVAL; if (slots->generation != ghc->generation) { if (__kvm_gfn_to_hva_cache_init(slots, ghc, ghc->gpa, ghc->len)) return -EFAULT; } if (kvm_is_error_hva(ghc->hva)) return -EFAULT; if (unlikely(!ghc->memslot)) return kvm_read_guest(kvm, gpa, data, len); r = __copy_from_user(data, (void __user *)ghc->hva + offset, len); if (r) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(kvm_read_guest_offset_cached); int kvm_read_guest_cached(struct kvm *kvm, struct gfn_to_hva_cache *ghc, void *data, unsigned long len) { return kvm_read_guest_offset_cached(kvm, ghc, data, 0, len); } EXPORT_SYMBOL_GPL(kvm_read_guest_cached); int kvm_clear_guest(struct kvm *kvm, gpa_t gpa, unsigned long len) { const void *zero_page = (const void *) __va(page_to_phys(ZERO_PAGE(0))); gfn_t gfn = gpa >> PAGE_SHIFT; int seg; int offset = offset_in_page(gpa); int ret; while ((seg = next_segment(len, offset)) != 0) { ret = kvm_write_guest_page(kvm, gfn, zero_page, offset, len); if (ret < 0) return ret; offset = 0; len -= seg; ++gfn; } return 0; } EXPORT_SYMBOL_GPL(kvm_clear_guest); void mark_page_dirty_in_slot(struct kvm *kvm, const struct kvm_memory_slot *memslot, gfn_t gfn) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); #ifdef CONFIG_HAVE_KVM_DIRTY_RING if (WARN_ON_ONCE(vcpu && vcpu->kvm != kvm)) return; WARN_ON_ONCE(!vcpu && !kvm_arch_allow_write_without_running_vcpu(kvm)); #endif if (memslot && kvm_slot_dirty_track_enabled(memslot)) { unsigned long rel_gfn = gfn - memslot->base_gfn; u32 slot = (memslot->as_id << 16) | memslot->id; if (kvm->dirty_ring_size && vcpu) kvm_dirty_ring_push(vcpu, slot, rel_gfn); else if (memslot->dirty_bitmap) set_bit_le(rel_gfn, memslot->dirty_bitmap); } } EXPORT_SYMBOL_GPL(mark_page_dirty_in_slot); void mark_page_dirty(struct kvm *kvm, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = gfn_to_memslot(kvm, gfn); mark_page_dirty_in_slot(kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(mark_page_dirty); void kvm_vcpu_mark_page_dirty(struct kvm_vcpu *vcpu, gfn_t gfn) { struct kvm_memory_slot *memslot; memslot = kvm_vcpu_gfn_to_memslot(vcpu, gfn); mark_page_dirty_in_slot(vcpu->kvm, memslot, gfn); } EXPORT_SYMBOL_GPL(kvm_vcpu_mark_page_dirty); void kvm_sigset_activate(struct kvm_vcpu *vcpu) { if (!vcpu->sigset_active) return; /* * This does a lockless modification of ->real_blocked, which is fine * because, only current can change ->real_blocked and all readers of * ->real_blocked don't care as long ->real_blocked is always a subset * of ->blocked. */ sigprocmask(SIG_SETMASK, &vcpu->sigset, ¤t->real_blocked); } void kvm_sigset_deactivate(struct kvm_vcpu *vcpu) { if (!vcpu->sigset_active) return; sigprocmask(SIG_SETMASK, ¤t->real_blocked, NULL); sigemptyset(¤t->real_blocked); } static void grow_halt_poll_ns(struct kvm_vcpu *vcpu) { unsigned int old, val, grow, grow_start; old = val = vcpu->halt_poll_ns; grow_start = READ_ONCE(halt_poll_ns_grow_start); grow = READ_ONCE(halt_poll_ns_grow); if (!grow) goto out; val *= grow; if (val < grow_start) val = grow_start; vcpu->halt_poll_ns = val; out: trace_kvm_halt_poll_ns_grow(vcpu->vcpu_id, val, old); } static void shrink_halt_poll_ns(struct kvm_vcpu *vcpu) { unsigned int old, val, shrink, grow_start; old = val = vcpu->halt_poll_ns; shrink = READ_ONCE(halt_poll_ns_shrink); grow_start = READ_ONCE(halt_poll_ns_grow_start); if (shrink == 0) val = 0; else val /= shrink; if (val < grow_start) val = 0; vcpu->halt_poll_ns = val; trace_kvm_halt_poll_ns_shrink(vcpu->vcpu_id, val, old); } static int kvm_vcpu_check_block(struct kvm_vcpu *vcpu) { int ret = -EINTR; int idx = srcu_read_lock(&vcpu->kvm->srcu); if (kvm_arch_vcpu_runnable(vcpu)) goto out; if (kvm_cpu_has_pending_timer(vcpu)) goto out; if (signal_pending(current)) goto out; if (kvm_check_request(KVM_REQ_UNBLOCK, vcpu)) goto out; ret = 0; out: srcu_read_unlock(&vcpu->kvm->srcu, idx); return ret; } /* * Block the vCPU until the vCPU is runnable, an event arrives, or a signal is * pending. This is mostly used when halting a vCPU, but may also be used * directly for other vCPU non-runnable states, e.g. x86's Wait-For-SIPI. */ bool kvm_vcpu_block(struct kvm_vcpu *vcpu) { struct rcuwait *wait = kvm_arch_vcpu_get_wait(vcpu); bool waited = false; vcpu->stat.generic.blocking = 1; preempt_disable(); kvm_arch_vcpu_blocking(vcpu); prepare_to_rcuwait(wait); preempt_enable(); for (;;) { set_current_state(TASK_INTERRUPTIBLE); if (kvm_vcpu_check_block(vcpu) < 0) break; waited = true; schedule(); } preempt_disable(); finish_rcuwait(wait); kvm_arch_vcpu_unblocking(vcpu); preempt_enable(); vcpu->stat.generic.blocking = 0; return waited; } static inline void update_halt_poll_stats(struct kvm_vcpu *vcpu, ktime_t start, ktime_t end, bool success) { struct kvm_vcpu_stat_generic *stats = &vcpu->stat.generic; u64 poll_ns = ktime_to_ns(ktime_sub(end, start)); ++vcpu->stat.generic.halt_attempted_poll; if (success) { ++vcpu->stat.generic.halt_successful_poll; if (!vcpu_valid_wakeup(vcpu)) ++vcpu->stat.generic.halt_poll_invalid; stats->halt_poll_success_ns += poll_ns; KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_success_hist, poll_ns); } else { stats->halt_poll_fail_ns += poll_ns; KVM_STATS_LOG_HIST_UPDATE(stats->halt_poll_fail_hist, poll_ns); } } static unsigned int kvm_vcpu_max_halt_poll_ns(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; if (kvm->override_halt_poll_ns) { /* * Ensure kvm->max_halt_poll_ns is not read before * kvm->override_halt_poll_ns. * * Pairs with the smp_wmb() when enabling KVM_CAP_HALT_POLL. */ smp_rmb(); return READ_ONCE(kvm->max_halt_poll_ns); } return READ_ONCE(halt_poll_ns); } /* * Emulate a vCPU halt condition, e.g. HLT on x86, WFI on arm, etc... If halt * polling is enabled, busy wait for a short time before blocking to avoid the * expensive block+unblock sequence if a wake event arrives soon after the vCPU * is halted. */ void kvm_vcpu_halt(struct kvm_vcpu *vcpu) { unsigned int max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); bool halt_poll_allowed = !kvm_arch_no_poll(vcpu); ktime_t start, cur, poll_end; bool waited = false; bool do_halt_poll; u64 halt_ns; if (vcpu->halt_poll_ns > max_halt_poll_ns) vcpu->halt_poll_ns = max_halt_poll_ns; do_halt_poll = halt_poll_allowed && vcpu->halt_poll_ns; start = cur = poll_end = ktime_get(); if (do_halt_poll) { ktime_t stop = ktime_add_ns(start, vcpu->halt_poll_ns); do { if (kvm_vcpu_check_block(vcpu) < 0) goto out; cpu_relax(); poll_end = cur = ktime_get(); } while (kvm_vcpu_can_poll(cur, stop)); } waited = kvm_vcpu_block(vcpu); cur = ktime_get(); if (waited) { vcpu->stat.generic.halt_wait_ns += ktime_to_ns(cur) - ktime_to_ns(poll_end); KVM_STATS_LOG_HIST_UPDATE(vcpu->stat.generic.halt_wait_hist, ktime_to_ns(cur) - ktime_to_ns(poll_end)); } out: /* The total time the vCPU was "halted", including polling time. */ halt_ns = ktime_to_ns(cur) - ktime_to_ns(start); /* * Note, halt-polling is considered successful so long as the vCPU was * never actually scheduled out, i.e. even if the wake event arrived * after of the halt-polling loop itself, but before the full wait. */ if (do_halt_poll) update_halt_poll_stats(vcpu, start, poll_end, !waited); if (halt_poll_allowed) { /* Recompute the max halt poll time in case it changed. */ max_halt_poll_ns = kvm_vcpu_max_halt_poll_ns(vcpu); if (!vcpu_valid_wakeup(vcpu)) { shrink_halt_poll_ns(vcpu); } else if (max_halt_poll_ns) { if (halt_ns <= vcpu->halt_poll_ns) ; /* we had a long block, shrink polling */ else if (vcpu->halt_poll_ns && halt_ns > max_halt_poll_ns) shrink_halt_poll_ns(vcpu); /* we had a short halt and our poll time is too small */ else if (vcpu->halt_poll_ns < max_halt_poll_ns && halt_ns < max_halt_poll_ns) grow_halt_poll_ns(vcpu); } else { vcpu->halt_poll_ns = 0; } } trace_kvm_vcpu_wakeup(halt_ns, waited, vcpu_valid_wakeup(vcpu)); } EXPORT_SYMBOL_GPL(kvm_vcpu_halt); bool kvm_vcpu_wake_up(struct kvm_vcpu *vcpu) { if (__kvm_vcpu_wake_up(vcpu)) { WRITE_ONCE(vcpu->ready, true); ++vcpu->stat.generic.halt_wakeup; return true; } return false; } EXPORT_SYMBOL_GPL(kvm_vcpu_wake_up); #ifndef CONFIG_S390 /* * Kick a sleeping VCPU, or a guest VCPU in guest mode, into host kernel mode. */ void kvm_vcpu_kick(struct kvm_vcpu *vcpu) { int me, cpu; if (kvm_vcpu_wake_up(vcpu)) return; me = get_cpu(); /* * The only state change done outside the vcpu mutex is IN_GUEST_MODE * to EXITING_GUEST_MODE. Therefore the moderately expensive "should * kick" check does not need atomic operations if kvm_vcpu_kick is used * within the vCPU thread itself. */ if (vcpu == __this_cpu_read(kvm_running_vcpu)) { if (vcpu->mode == IN_GUEST_MODE) WRITE_ONCE(vcpu->mode, EXITING_GUEST_MODE); goto out; } /* * Note, the vCPU could get migrated to a different pCPU at any point * after kvm_arch_vcpu_should_kick(), which could result in sending an * IPI to the previous pCPU. But, that's ok because the purpose of the * IPI is to force the vCPU to leave IN_GUEST_MODE, and migrating the * vCPU also requires it to leave IN_GUEST_MODE. */ if (kvm_arch_vcpu_should_kick(vcpu)) { cpu = READ_ONCE(vcpu->cpu); if (cpu != me && (unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) smp_send_reschedule(cpu); } out: put_cpu(); } EXPORT_SYMBOL_GPL(kvm_vcpu_kick); #endif /* !CONFIG_S390 */ int kvm_vcpu_yield_to(struct kvm_vcpu *target) { struct pid *pid; struct task_struct *task = NULL; int ret = 0; rcu_read_lock(); pid = rcu_dereference(target->pid); if (pid) task = get_pid_task(pid, PIDTYPE_PID); rcu_read_unlock(); if (!task) return ret; ret = yield_to(task, 1); put_task_struct(task); return ret; } EXPORT_SYMBOL_GPL(kvm_vcpu_yield_to); /* * Helper that checks whether a VCPU is eligible for directed yield. * Most eligible candidate to yield is decided by following heuristics: * * (a) VCPU which has not done pl-exit or cpu relax intercepted recently * (preempted lock holder), indicated by @in_spin_loop. * Set at the beginning and cleared at the end of interception/PLE handler. * * (b) VCPU which has done pl-exit/ cpu relax intercepted but did not get * chance last time (mostly it has become eligible now since we have probably * yielded to lockholder in last iteration. This is done by toggling * @dy_eligible each time a VCPU checked for eligibility.) * * Yielding to a recently pl-exited/cpu relax intercepted VCPU before yielding * to preempted lock-holder could result in wrong VCPU selection and CPU * burning. Giving priority for a potential lock-holder increases lock * progress. * * Since algorithm is based on heuristics, accessing another VCPU data without * locking does not harm. It may result in trying to yield to same VCPU, fail * and continue with next VCPU and so on. */ static bool kvm_vcpu_eligible_for_directed_yield(struct kvm_vcpu *vcpu) { #ifdef CONFIG_HAVE_KVM_CPU_RELAX_INTERCEPT bool eligible; eligible = !vcpu->spin_loop.in_spin_loop || vcpu->spin_loop.dy_eligible; if (vcpu->spin_loop.in_spin_loop) kvm_vcpu_set_dy_eligible(vcpu, !vcpu->spin_loop.dy_eligible); return eligible; #else return true; #endif } /* * Unlike kvm_arch_vcpu_runnable, this function is called outside * a vcpu_load/vcpu_put pair. However, for most architectures * kvm_arch_vcpu_runnable does not require vcpu_load. */ bool __weak kvm_arch_dy_runnable(struct kvm_vcpu *vcpu) { return kvm_arch_vcpu_runnable(vcpu); } static bool vcpu_dy_runnable(struct kvm_vcpu *vcpu) { if (kvm_arch_dy_runnable(vcpu)) return true; #ifdef CONFIG_KVM_ASYNC_PF if (!list_empty_careful(&vcpu->async_pf.done)) return true; #endif return false; } /* * By default, simply query the target vCPU's current mode when checking if a * vCPU was preempted in kernel mode. All architectures except x86 (or more * specifical, except VMX) allow querying whether or not a vCPU is in kernel * mode even if the vCPU is NOT loaded, i.e. using kvm_arch_vcpu_in_kernel() * directly for cross-vCPU checks is functionally correct and accurate. */ bool __weak kvm_arch_vcpu_preempted_in_kernel(struct kvm_vcpu *vcpu) { return kvm_arch_vcpu_in_kernel(vcpu); } bool __weak kvm_arch_dy_has_pending_interrupt(struct kvm_vcpu *vcpu) { return false; } void kvm_vcpu_on_spin(struct kvm_vcpu *me, bool yield_to_kernel_mode) { struct kvm *kvm = me->kvm; struct kvm_vcpu *vcpu; int last_boosted_vcpu; unsigned long i; int yielded = 0; int try = 3; int pass; last_boosted_vcpu = READ_ONCE(kvm->last_boosted_vcpu); kvm_vcpu_set_in_spin_loop(me, true); /* * We boost the priority of a VCPU that is runnable but not * currently running, because it got preempted by something * else and called schedule in __vcpu_run. Hopefully that * VCPU is holding the lock that we need and will release it. * We approximate round-robin by starting at the last boosted VCPU. */ for (pass = 0; pass < 2 && !yielded && try; pass++) { kvm_for_each_vcpu(i, vcpu, kvm) { if (!pass && i <= last_boosted_vcpu) { i = last_boosted_vcpu; continue; } else if (pass && i > last_boosted_vcpu) break; if (!READ_ONCE(vcpu->ready)) continue; if (vcpu == me) continue; if (kvm_vcpu_is_blocking(vcpu) && !vcpu_dy_runnable(vcpu)) continue; /* * Treat the target vCPU as being in-kernel if it has a * pending interrupt, as the vCPU trying to yield may * be spinning waiting on IPI delivery, i.e. the target * vCPU is in-kernel for the purposes of directed yield. */ if (READ_ONCE(vcpu->preempted) && yield_to_kernel_mode && !kvm_arch_dy_has_pending_interrupt(vcpu) && !kvm_arch_vcpu_preempted_in_kernel(vcpu)) continue; if (!kvm_vcpu_eligible_for_directed_yield(vcpu)) continue; yielded = kvm_vcpu_yield_to(vcpu); if (yielded > 0) { WRITE_ONCE(kvm->last_boosted_vcpu, i); break; } else if (yielded < 0) { try--; if (!try) break; } } } kvm_vcpu_set_in_spin_loop(me, false); /* Ensure vcpu is not eligible during next spinloop */ kvm_vcpu_set_dy_eligible(me, false); } EXPORT_SYMBOL_GPL(kvm_vcpu_on_spin); static bool kvm_page_in_dirty_ring(struct kvm *kvm, unsigned long pgoff) { #ifdef CONFIG_HAVE_KVM_DIRTY_RING return (pgoff >= KVM_DIRTY_LOG_PAGE_OFFSET) && (pgoff < KVM_DIRTY_LOG_PAGE_OFFSET + kvm->dirty_ring_size / PAGE_SIZE); #else return false; #endif } static vm_fault_t kvm_vcpu_fault(struct vm_fault *vmf) { struct kvm_vcpu *vcpu = vmf->vma->vm_file->private_data; struct page *page; if (vmf->pgoff == 0) page = virt_to_page(vcpu->run); #ifdef CONFIG_X86 else if (vmf->pgoff == KVM_PIO_PAGE_OFFSET) page = virt_to_page(vcpu->arch.pio_data); #endif #ifdef CONFIG_KVM_MMIO else if (vmf->pgoff == KVM_COALESCED_MMIO_PAGE_OFFSET) page = virt_to_page(vcpu->kvm->coalesced_mmio_ring); #endif else if (kvm_page_in_dirty_ring(vcpu->kvm, vmf->pgoff)) page = kvm_dirty_ring_get_page( &vcpu->dirty_ring, vmf->pgoff - KVM_DIRTY_LOG_PAGE_OFFSET); else return kvm_arch_vcpu_fault(vcpu, vmf); get_page(page); vmf->page = page; return 0; } static const struct vm_operations_struct kvm_vcpu_vm_ops = { .fault = kvm_vcpu_fault, }; static int kvm_vcpu_mmap(struct file *file, struct vm_area_struct *vma) { struct kvm_vcpu *vcpu = file->private_data; unsigned long pages = vma_pages(vma); if ((kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff) || kvm_page_in_dirty_ring(vcpu->kvm, vma->vm_pgoff + pages - 1)) && ((vma->vm_flags & VM_EXEC) || !(vma->vm_flags & VM_SHARED))) return -EINVAL; vma->vm_ops = &kvm_vcpu_vm_ops; return 0; } static int kvm_vcpu_release(struct inode *inode, struct file *filp) { struct kvm_vcpu *vcpu = filp->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static struct file_operations kvm_vcpu_fops = { .release = kvm_vcpu_release, .unlocked_ioctl = kvm_vcpu_ioctl, .mmap = kvm_vcpu_mmap, .llseek = noop_llseek, KVM_COMPAT(kvm_vcpu_compat_ioctl), }; /* * Allocates an inode for the vcpu. */ static int create_vcpu_fd(struct kvm_vcpu *vcpu) { char name[8 + 1 + ITOA_MAX_LEN + 1]; snprintf(name, sizeof(name), "kvm-vcpu:%d", vcpu->vcpu_id); return anon_inode_getfd(name, &kvm_vcpu_fops, vcpu, O_RDWR | O_CLOEXEC); } #ifdef __KVM_HAVE_ARCH_VCPU_DEBUGFS static int vcpu_get_pid(void *data, u64 *val) { struct kvm_vcpu *vcpu = data; rcu_read_lock(); *val = pid_nr(rcu_dereference(vcpu->pid)); rcu_read_unlock(); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_get_pid_fops, vcpu_get_pid, NULL, "%llu\n"); static void kvm_create_vcpu_debugfs(struct kvm_vcpu *vcpu) { struct dentry *debugfs_dentry; char dir_name[ITOA_MAX_LEN * 2]; if (!debugfs_initialized()) return; snprintf(dir_name, sizeof(dir_name), "vcpu%d", vcpu->vcpu_id); debugfs_dentry = debugfs_create_dir(dir_name, vcpu->kvm->debugfs_dentry); debugfs_create_file("pid", 0444, debugfs_dentry, vcpu, &vcpu_get_pid_fops); kvm_arch_create_vcpu_debugfs(vcpu, debugfs_dentry); } #endif /* * Creates some virtual cpus. Good luck creating more than one. */ static int kvm_vm_ioctl_create_vcpu(struct kvm *kvm, u32 id) { int r; struct kvm_vcpu *vcpu; struct page *page; if (id >= KVM_MAX_VCPU_IDS) return -EINVAL; mutex_lock(&kvm->lock); if (kvm->created_vcpus >= kvm->max_vcpus) { mutex_unlock(&kvm->lock); return -EINVAL; } r = kvm_arch_vcpu_precreate(kvm, id); if (r) { mutex_unlock(&kvm->lock); return r; } kvm->created_vcpus++; mutex_unlock(&kvm->lock); vcpu = kmem_cache_zalloc(kvm_vcpu_cache, GFP_KERNEL_ACCOUNT); if (!vcpu) { r = -ENOMEM; goto vcpu_decrement; } BUILD_BUG_ON(sizeof(struct kvm_run) > PAGE_SIZE); page = alloc_page(GFP_KERNEL_ACCOUNT | __GFP_ZERO); if (!page) { r = -ENOMEM; goto vcpu_free; } vcpu->run = page_address(page); kvm_vcpu_init(vcpu, kvm, id); r = kvm_arch_vcpu_create(vcpu); if (r) goto vcpu_free_run_page; if (kvm->dirty_ring_size) { r = kvm_dirty_ring_alloc(&vcpu->dirty_ring, id, kvm->dirty_ring_size); if (r) goto arch_vcpu_destroy; } mutex_lock(&kvm->lock); #ifdef CONFIG_LOCKDEP /* Ensure that lockdep knows vcpu->mutex is taken *inside* kvm->lock */ mutex_lock(&vcpu->mutex); mutex_unlock(&vcpu->mutex); #endif if (kvm_get_vcpu_by_id(kvm, id)) { r = -EEXIST; goto unlock_vcpu_destroy; } vcpu->vcpu_idx = atomic_read(&kvm->online_vcpus); r = xa_reserve(&kvm->vcpu_array, vcpu->vcpu_idx, GFP_KERNEL_ACCOUNT); if (r) goto unlock_vcpu_destroy; /* Now it's all set up, let userspace reach it */ kvm_get_kvm(kvm); r = create_vcpu_fd(vcpu); if (r < 0) goto kvm_put_xa_release; if (KVM_BUG_ON(xa_store(&kvm->vcpu_array, vcpu->vcpu_idx, vcpu, 0), kvm)) { r = -EINVAL; goto kvm_put_xa_release; } /* * Pairs with smp_rmb() in kvm_get_vcpu. Store the vcpu * pointer before kvm->online_vcpu's incremented value. */ smp_wmb(); atomic_inc(&kvm->online_vcpus); mutex_unlock(&kvm->lock); kvm_arch_vcpu_postcreate(vcpu); kvm_create_vcpu_debugfs(vcpu); return r; kvm_put_xa_release: kvm_put_kvm_no_destroy(kvm); xa_release(&kvm->vcpu_array, vcpu->vcpu_idx); unlock_vcpu_destroy: mutex_unlock(&kvm->lock); kvm_dirty_ring_free(&vcpu->dirty_ring); arch_vcpu_destroy: kvm_arch_vcpu_destroy(vcpu); vcpu_free_run_page: free_page((unsigned long)vcpu->run); vcpu_free: kmem_cache_free(kvm_vcpu_cache, vcpu); vcpu_decrement: mutex_lock(&kvm->lock); kvm->created_vcpus--; mutex_unlock(&kvm->lock); return r; } static int kvm_vcpu_ioctl_set_sigmask(struct kvm_vcpu *vcpu, sigset_t *sigset) { if (sigset) { sigdelsetmask(sigset, sigmask(SIGKILL)|sigmask(SIGSTOP)); vcpu->sigset_active = 1; vcpu->sigset = *sigset; } else vcpu->sigset_active = 0; return 0; } static ssize_t kvm_vcpu_stats_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset) { struct kvm_vcpu *vcpu = file->private_data; return kvm_stats_read(vcpu->stats_id, &kvm_vcpu_stats_header, &kvm_vcpu_stats_desc[0], &vcpu->stat, sizeof(vcpu->stat), user_buffer, size, offset); } static int kvm_vcpu_stats_release(struct inode *inode, struct file *file) { struct kvm_vcpu *vcpu = file->private_data; kvm_put_kvm(vcpu->kvm); return 0; } static const struct file_operations kvm_vcpu_stats_fops = { .owner = THIS_MODULE, .read = kvm_vcpu_stats_read, .release = kvm_vcpu_stats_release, .llseek = noop_llseek, }; static int kvm_vcpu_ioctl_get_stats_fd(struct kvm_vcpu *vcpu) { int fd; struct file *file; char name[15 + ITOA_MAX_LEN + 1]; snprintf(name, sizeof(name), "kvm-vcpu-stats:%d", vcpu->vcpu_id); fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile(name, &kvm_vcpu_stats_fops, vcpu, O_RDONLY); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } kvm_get_kvm(vcpu->kvm); file->f_mode |= FMODE_PREAD; fd_install(fd, file); return fd; } static long kvm_vcpu_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = (void __user *)arg; int r; struct kvm_fpu *fpu = NULL; struct kvm_sregs *kvm_sregs = NULL; if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; if (unlikely(_IOC_TYPE(ioctl) != KVMIO)) return -EINVAL; /* * Some architectures have vcpu ioctls that are asynchronous to vcpu * execution; mutex_lock() would break them. */ r = kvm_arch_vcpu_async_ioctl(filp, ioctl, arg); if (r != -ENOIOCTLCMD) return r; if (mutex_lock_killable(&vcpu->mutex)) return -EINTR; switch (ioctl) { case KVM_RUN: { struct pid *oldpid; r = -EINVAL; if (arg) goto out; oldpid = rcu_access_pointer(vcpu->pid); if (unlikely(oldpid != task_pid(current))) { /* The thread running this VCPU changed. */ struct pid *newpid; r = kvm_arch_vcpu_run_pid_change(vcpu); if (r) break; newpid = get_task_pid(current, PIDTYPE_PID); rcu_assign_pointer(vcpu->pid, newpid); if (oldpid) synchronize_rcu(); put_pid(oldpid); } r = kvm_arch_vcpu_ioctl_run(vcpu); trace_kvm_userspace_exit(vcpu->run->exit_reason, r); break; } case KVM_GET_REGS: { struct kvm_regs *kvm_regs; r = -ENOMEM; kvm_regs = kzalloc(sizeof(struct kvm_regs), GFP_KERNEL); if (!kvm_regs) goto out; r = kvm_arch_vcpu_ioctl_get_regs(vcpu, kvm_regs); if (r) goto out_free1; r = -EFAULT; if (copy_to_user(argp, kvm_regs, sizeof(struct kvm_regs))) goto out_free1; r = 0; out_free1: kfree(kvm_regs); break; } case KVM_SET_REGS: { struct kvm_regs *kvm_regs; kvm_regs = memdup_user(argp, sizeof(*kvm_regs)); if (IS_ERR(kvm_regs)) { r = PTR_ERR(kvm_regs); goto out; } r = kvm_arch_vcpu_ioctl_set_regs(vcpu, kvm_regs); kfree(kvm_regs); break; } case KVM_GET_SREGS: { kvm_sregs = kzalloc(sizeof(struct kvm_sregs), GFP_KERNEL); r = -ENOMEM; if (!kvm_sregs) goto out; r = kvm_arch_vcpu_ioctl_get_sregs(vcpu, kvm_sregs); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, kvm_sregs, sizeof(struct kvm_sregs))) goto out; r = 0; break; } case KVM_SET_SREGS: { kvm_sregs = memdup_user(argp, sizeof(*kvm_sregs)); if (IS_ERR(kvm_sregs)) { r = PTR_ERR(kvm_sregs); kvm_sregs = NULL; goto out; } r = kvm_arch_vcpu_ioctl_set_sregs(vcpu, kvm_sregs); break; } case KVM_GET_MP_STATE: { struct kvm_mp_state mp_state; r = kvm_arch_vcpu_ioctl_get_mpstate(vcpu, &mp_state); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &mp_state, sizeof(mp_state))) goto out; r = 0; break; } case KVM_SET_MP_STATE: { struct kvm_mp_state mp_state; r = -EFAULT; if (copy_from_user(&mp_state, argp, sizeof(mp_state))) goto out; r = kvm_arch_vcpu_ioctl_set_mpstate(vcpu, &mp_state); break; } case KVM_TRANSLATE: { struct kvm_translation tr; r = -EFAULT; if (copy_from_user(&tr, argp, sizeof(tr))) goto out; r = kvm_arch_vcpu_ioctl_translate(vcpu, &tr); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &tr, sizeof(tr))) goto out; r = 0; break; } case KVM_SET_GUEST_DEBUG: { struct kvm_guest_debug dbg; r = -EFAULT; if (copy_from_user(&dbg, argp, sizeof(dbg))) goto out; r = kvm_arch_vcpu_ioctl_set_guest_debug(vcpu, &dbg); break; } case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset, *p; p = NULL; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof(kvm_sigmask))) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof(sigset)) goto out; r = -EFAULT; if (copy_from_user(&sigset, sigmask_arg->sigset, sizeof(sigset))) goto out; p = &sigset; } r = kvm_vcpu_ioctl_set_sigmask(vcpu, p); break; } case KVM_GET_FPU: { fpu = kzalloc(sizeof(struct kvm_fpu), GFP_KERNEL); r = -ENOMEM; if (!fpu) goto out; r = kvm_arch_vcpu_ioctl_get_fpu(vcpu, fpu); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, fpu, sizeof(struct kvm_fpu))) goto out; r = 0; break; } case KVM_SET_FPU: { fpu = memdup_user(argp, sizeof(*fpu)); if (IS_ERR(fpu)) { r = PTR_ERR(fpu); fpu = NULL; goto out; } r = kvm_arch_vcpu_ioctl_set_fpu(vcpu, fpu); break; } case KVM_GET_STATS_FD: { r = kvm_vcpu_ioctl_get_stats_fd(vcpu); break; } default: r = kvm_arch_vcpu_ioctl(filp, ioctl, arg); } out: mutex_unlock(&vcpu->mutex); kfree(fpu); kfree(kvm_sregs); return r; } #ifdef CONFIG_KVM_COMPAT static long kvm_vcpu_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_vcpu *vcpu = filp->private_data; void __user *argp = compat_ptr(arg); int r; if (vcpu->kvm->mm != current->mm || vcpu->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_SIGNAL_MASK: { struct kvm_signal_mask __user *sigmask_arg = argp; struct kvm_signal_mask kvm_sigmask; sigset_t sigset; if (argp) { r = -EFAULT; if (copy_from_user(&kvm_sigmask, argp, sizeof(kvm_sigmask))) goto out; r = -EINVAL; if (kvm_sigmask.len != sizeof(compat_sigset_t)) goto out; r = -EFAULT; if (get_compat_sigset(&sigset, (compat_sigset_t __user *)sigmask_arg->sigset)) goto out; r = kvm_vcpu_ioctl_set_sigmask(vcpu, &sigset); } else r = kvm_vcpu_ioctl_set_sigmask(vcpu, NULL); break; } default: r = kvm_vcpu_ioctl(filp, ioctl, arg); } out: return r; } #endif static int kvm_device_mmap(struct file *filp, struct vm_area_struct *vma) { struct kvm_device *dev = filp->private_data; if (dev->ops->mmap) return dev->ops->mmap(dev, vma); return -ENODEV; } static int kvm_device_ioctl_attr(struct kvm_device *dev, int (*accessor)(struct kvm_device *dev, struct kvm_device_attr *attr), unsigned long arg) { struct kvm_device_attr attr; if (!accessor) return -EPERM; if (copy_from_user(&attr, (void __user *)arg, sizeof(attr))) return -EFAULT; return accessor(dev, &attr); } static long kvm_device_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm_device *dev = filp->private_data; if (dev->kvm->mm != current->mm || dev->kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_SET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->set_attr, arg); case KVM_GET_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->get_attr, arg); case KVM_HAS_DEVICE_ATTR: return kvm_device_ioctl_attr(dev, dev->ops->has_attr, arg); default: if (dev->ops->ioctl) return dev->ops->ioctl(dev, ioctl, arg); return -ENOTTY; } } static int kvm_device_release(struct inode *inode, struct file *filp) { struct kvm_device *dev = filp->private_data; struct kvm *kvm = dev->kvm; if (dev->ops->release) { mutex_lock(&kvm->lock); list_del_rcu(&dev->vm_node); synchronize_rcu(); dev->ops->release(dev); mutex_unlock(&kvm->lock); } kvm_put_kvm(kvm); return 0; } static struct file_operations kvm_device_fops = { .unlocked_ioctl = kvm_device_ioctl, .release = kvm_device_release, KVM_COMPAT(kvm_device_ioctl), .mmap = kvm_device_mmap, }; struct kvm_device *kvm_device_from_filp(struct file *filp) { if (filp->f_op != &kvm_device_fops) return NULL; return filp->private_data; } static const struct kvm_device_ops *kvm_device_ops_table[KVM_DEV_TYPE_MAX] = { #ifdef CONFIG_KVM_MPIC [KVM_DEV_TYPE_FSL_MPIC_20] = &kvm_mpic_ops, [KVM_DEV_TYPE_FSL_MPIC_42] = &kvm_mpic_ops, #endif }; int kvm_register_device_ops(const struct kvm_device_ops *ops, u32 type) { if (type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENOSPC; if (kvm_device_ops_table[type] != NULL) return -EEXIST; kvm_device_ops_table[type] = ops; return 0; } void kvm_unregister_device_ops(u32 type) { if (kvm_device_ops_table[type] != NULL) kvm_device_ops_table[type] = NULL; } static int kvm_ioctl_create_device(struct kvm *kvm, struct kvm_create_device *cd) { const struct kvm_device_ops *ops; struct kvm_device *dev; bool test = cd->flags & KVM_CREATE_DEVICE_TEST; int type; int ret; if (cd->type >= ARRAY_SIZE(kvm_device_ops_table)) return -ENODEV; type = array_index_nospec(cd->type, ARRAY_SIZE(kvm_device_ops_table)); ops = kvm_device_ops_table[type]; if (ops == NULL) return -ENODEV; if (test) return 0; dev = kzalloc(sizeof(*dev), GFP_KERNEL_ACCOUNT); if (!dev) return -ENOMEM; dev->ops = ops; dev->kvm = kvm; mutex_lock(&kvm->lock); ret = ops->create(dev, type); if (ret < 0) { mutex_unlock(&kvm->lock); kfree(dev); return ret; } list_add_rcu(&dev->vm_node, &kvm->devices); mutex_unlock(&kvm->lock); if (ops->init) ops->init(dev); kvm_get_kvm(kvm); ret = anon_inode_getfd(ops->name, &kvm_device_fops, dev, O_RDWR | O_CLOEXEC); if (ret < 0) { kvm_put_kvm_no_destroy(kvm); mutex_lock(&kvm->lock); list_del_rcu(&dev->vm_node); synchronize_rcu(); if (ops->release) ops->release(dev); mutex_unlock(&kvm->lock); if (ops->destroy) ops->destroy(dev); return ret; } cd->fd = ret; return 0; } static int kvm_vm_ioctl_check_extension_generic(struct kvm *kvm, long arg) { switch (arg) { case KVM_CAP_USER_MEMORY: case KVM_CAP_USER_MEMORY2: case KVM_CAP_DESTROY_MEMORY_REGION_WORKS: case KVM_CAP_JOIN_MEMORY_REGIONS_WORKS: case KVM_CAP_INTERNAL_ERROR_DATA: #ifdef CONFIG_HAVE_KVM_MSI case KVM_CAP_SIGNAL_MSI: #endif #ifdef CONFIG_HAVE_KVM_IRQCHIP case KVM_CAP_IRQFD: #endif case KVM_CAP_IOEVENTFD_ANY_LENGTH: case KVM_CAP_CHECK_EXTENSION_VM: case KVM_CAP_ENABLE_CAP_VM: case KVM_CAP_HALT_POLL: return 1; #ifdef CONFIG_KVM_MMIO case KVM_CAP_COALESCED_MMIO: return KVM_COALESCED_MMIO_PAGE_OFFSET; case KVM_CAP_COALESCED_PIO: return 1; #endif #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: return KVM_DIRTY_LOG_MANUAL_CAPS; #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_CAP_IRQ_ROUTING: return KVM_MAX_IRQ_ROUTES; #endif #if KVM_MAX_NR_ADDRESS_SPACES > 1 case KVM_CAP_MULTI_ADDRESS_SPACE: if (kvm) return kvm_arch_nr_memslot_as_ids(kvm); return KVM_MAX_NR_ADDRESS_SPACES; #endif case KVM_CAP_NR_MEMSLOTS: return KVM_USER_MEM_SLOTS; case KVM_CAP_DIRTY_LOG_RING: #ifdef CONFIG_HAVE_KVM_DIRTY_RING_TSO return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; #endif case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: #ifdef CONFIG_HAVE_KVM_DIRTY_RING_ACQ_REL return KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn); #else return 0; #endif #ifdef CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: #endif case KVM_CAP_BINARY_STATS_FD: case KVM_CAP_SYSTEM_EVENT_DATA: case KVM_CAP_DEVICE_CTRL: return 1; #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_CAP_MEMORY_ATTRIBUTES: return kvm_supported_mem_attributes(kvm); #endif #ifdef CONFIG_KVM_PRIVATE_MEM case KVM_CAP_GUEST_MEMFD: return !kvm || kvm_arch_has_private_mem(kvm); #endif default: break; } return kvm_vm_ioctl_check_extension(kvm, arg); } static int kvm_vm_ioctl_enable_dirty_log_ring(struct kvm *kvm, u32 size) { int r; if (!KVM_DIRTY_LOG_PAGE_OFFSET) return -EINVAL; /* the size should be power of 2 */ if (!size || (size & (size - 1))) return -EINVAL; /* Should be bigger to keep the reserved entries, or a page */ if (size < kvm_dirty_ring_get_rsvd_entries() * sizeof(struct kvm_dirty_gfn) || size < PAGE_SIZE) return -EINVAL; if (size > KVM_DIRTY_RING_MAX_ENTRIES * sizeof(struct kvm_dirty_gfn)) return -E2BIG; /* We only allow it to set once */ if (kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->lock); if (kvm->created_vcpus) { /* We don't allow to change this value after vcpu created */ r = -EINVAL; } else { kvm->dirty_ring_size = size; r = 0; } mutex_unlock(&kvm->lock); return r; } static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm) { unsigned long i; struct kvm_vcpu *vcpu; int cleared = 0; if (!kvm->dirty_ring_size) return -EINVAL; mutex_lock(&kvm->slots_lock); kvm_for_each_vcpu(i, vcpu, kvm) cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring); mutex_unlock(&kvm->slots_lock); if (cleared) kvm_flush_remote_tlbs(kvm); return cleared; } int __attribute__((weak)) kvm_vm_ioctl_enable_cap(struct kvm *kvm, struct kvm_enable_cap *cap) { return -EINVAL; } bool kvm_are_all_memslots_empty(struct kvm *kvm) { int i; lockdep_assert_held(&kvm->slots_lock); for (i = 0; i < kvm_arch_nr_memslot_as_ids(kvm); i++) { if (!kvm_memslots_empty(__kvm_memslots(kvm, i))) return false; } return true; } EXPORT_SYMBOL_GPL(kvm_are_all_memslots_empty); static int kvm_vm_ioctl_enable_cap_generic(struct kvm *kvm, struct kvm_enable_cap *cap) { switch (cap->cap) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CAP_MANUAL_DIRTY_LOG_PROTECT2: { u64 allowed_options = KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE; if (cap->args[0] & KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE) allowed_options = KVM_DIRTY_LOG_MANUAL_CAPS; if (cap->flags || (cap->args[0] & ~allowed_options)) return -EINVAL; kvm->manual_dirty_log_protect = cap->args[0]; return 0; } #endif case KVM_CAP_HALT_POLL: { if (cap->flags || cap->args[0] != (unsigned int)cap->args[0]) return -EINVAL; kvm->max_halt_poll_ns = cap->args[0]; /* * Ensure kvm->override_halt_poll_ns does not become visible * before kvm->max_halt_poll_ns. * * Pairs with the smp_rmb() in kvm_vcpu_max_halt_poll_ns(). */ smp_wmb(); kvm->override_halt_poll_ns = true; return 0; } case KVM_CAP_DIRTY_LOG_RING: case KVM_CAP_DIRTY_LOG_RING_ACQ_REL: if (!kvm_vm_ioctl_check_extension_generic(kvm, cap->cap)) return -EINVAL; return kvm_vm_ioctl_enable_dirty_log_ring(kvm, cap->args[0]); case KVM_CAP_DIRTY_LOG_RING_WITH_BITMAP: { int r = -EINVAL; if (!IS_ENABLED(CONFIG_NEED_KVM_DIRTY_RING_WITH_BITMAP) || !kvm->dirty_ring_size || cap->flags) return r; mutex_lock(&kvm->slots_lock); /* * For simplicity, allow enabling ring+bitmap if and only if * there are no memslots, e.g. to ensure all memslots allocate * a bitmap after the capability is enabled. */ if (kvm_are_all_memslots_empty(kvm)) { kvm->dirty_ring_with_bitmap = true; r = 0; } mutex_unlock(&kvm->slots_lock); return r; } default: return kvm_vm_ioctl_enable_cap(kvm, cap); } } static ssize_t kvm_vm_stats_read(struct file *file, char __user *user_buffer, size_t size, loff_t *offset) { struct kvm *kvm = file->private_data; return kvm_stats_read(kvm->stats_id, &kvm_vm_stats_header, &kvm_vm_stats_desc[0], &kvm->stat, sizeof(kvm->stat), user_buffer, size, offset); } static int kvm_vm_stats_release(struct inode *inode, struct file *file) { struct kvm *kvm = file->private_data; kvm_put_kvm(kvm); return 0; } static const struct file_operations kvm_vm_stats_fops = { .owner = THIS_MODULE, .read = kvm_vm_stats_read, .release = kvm_vm_stats_release, .llseek = noop_llseek, }; static int kvm_vm_ioctl_get_stats_fd(struct kvm *kvm) { int fd; struct file *file; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; file = anon_inode_getfile("kvm-vm-stats", &kvm_vm_stats_fops, kvm, O_RDONLY); if (IS_ERR(file)) { put_unused_fd(fd); return PTR_ERR(file); } kvm_get_kvm(kvm); file->f_mode |= FMODE_PREAD; fd_install(fd, file); return fd; } #define SANITY_CHECK_MEM_REGION_FIELD(field) \ do { \ BUILD_BUG_ON(offsetof(struct kvm_userspace_memory_region, field) != \ offsetof(struct kvm_userspace_memory_region2, field)); \ BUILD_BUG_ON(sizeof_field(struct kvm_userspace_memory_region, field) != \ sizeof_field(struct kvm_userspace_memory_region2, field)); \ } while (0) static long kvm_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; void __user *argp = (void __user *)arg; int r; if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; switch (ioctl) { case KVM_CREATE_VCPU: r = kvm_vm_ioctl_create_vcpu(kvm, arg); break; case KVM_ENABLE_CAP: { struct kvm_enable_cap cap; r = -EFAULT; if (copy_from_user(&cap, argp, sizeof(cap))) goto out; r = kvm_vm_ioctl_enable_cap_generic(kvm, &cap); break; } case KVM_SET_USER_MEMORY_REGION2: case KVM_SET_USER_MEMORY_REGION: { struct kvm_userspace_memory_region2 mem; unsigned long size; if (ioctl == KVM_SET_USER_MEMORY_REGION) { /* * Fields beyond struct kvm_userspace_memory_region shouldn't be * accessed, but avoid leaking kernel memory in case of a bug. */ memset(&mem, 0, sizeof(mem)); size = sizeof(struct kvm_userspace_memory_region); } else { size = sizeof(struct kvm_userspace_memory_region2); } /* Ensure the common parts of the two structs are identical. */ SANITY_CHECK_MEM_REGION_FIELD(slot); SANITY_CHECK_MEM_REGION_FIELD(flags); SANITY_CHECK_MEM_REGION_FIELD(guest_phys_addr); SANITY_CHECK_MEM_REGION_FIELD(memory_size); SANITY_CHECK_MEM_REGION_FIELD(userspace_addr); r = -EFAULT; if (copy_from_user(&mem, argp, size)) goto out; r = -EINVAL; if (ioctl == KVM_SET_USER_MEMORY_REGION && (mem.flags & ~KVM_SET_USER_MEMORY_REGION_V1_FLAGS)) goto out; r = kvm_vm_ioctl_set_memory_region(kvm, &mem); break; } case KVM_GET_DIRTY_LOG: { struct kvm_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { struct kvm_clear_dirty_log log; r = -EFAULT; if (copy_from_user(&log, argp, sizeof(log))) goto out; r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); break; } #endif #ifdef CONFIG_KVM_MMIO case KVM_REGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_register_coalesced_mmio(kvm, &zone); break; } case KVM_UNREGISTER_COALESCED_MMIO: { struct kvm_coalesced_mmio_zone zone; r = -EFAULT; if (copy_from_user(&zone, argp, sizeof(zone))) goto out; r = kvm_vm_ioctl_unregister_coalesced_mmio(kvm, &zone); break; } #endif case KVM_IRQFD: { struct kvm_irqfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_irqfd(kvm, &data); break; } case KVM_IOEVENTFD: { struct kvm_ioeventfd data; r = -EFAULT; if (copy_from_user(&data, argp, sizeof(data))) goto out; r = kvm_ioeventfd(kvm, &data); break; } #ifdef CONFIG_HAVE_KVM_MSI case KVM_SIGNAL_MSI: { struct kvm_msi msi; r = -EFAULT; if (copy_from_user(&msi, argp, sizeof(msi))) goto out; r = kvm_send_userspace_msi(kvm, &msi); break; } #endif #ifdef __KVM_HAVE_IRQ_LINE case KVM_IRQ_LINE_STATUS: case KVM_IRQ_LINE: { struct kvm_irq_level irq_event; r = -EFAULT; if (copy_from_user(&irq_event, argp, sizeof(irq_event))) goto out; r = kvm_vm_ioctl_irq_line(kvm, &irq_event, ioctl == KVM_IRQ_LINE_STATUS); if (r) goto out; r = -EFAULT; if (ioctl == KVM_IRQ_LINE_STATUS) { if (copy_to_user(argp, &irq_event, sizeof(irq_event))) goto out; } r = 0; break; } #endif #ifdef CONFIG_HAVE_KVM_IRQ_ROUTING case KVM_SET_GSI_ROUTING: { struct kvm_irq_routing routing; struct kvm_irq_routing __user *urouting; struct kvm_irq_routing_entry *entries = NULL; r = -EFAULT; if (copy_from_user(&routing, argp, sizeof(routing))) goto out; r = -EINVAL; if (!kvm_arch_can_set_irq_routing(kvm)) goto out; if (routing.nr > KVM_MAX_IRQ_ROUTES) goto out; if (routing.flags) goto out; if (routing.nr) { urouting = argp; entries = vmemdup_array_user(urouting->entries, routing.nr, sizeof(*entries)); if (IS_ERR(entries)) { r = PTR_ERR(entries); goto out; } } r = kvm_set_irq_routing(kvm, entries, routing.nr, routing.flags); kvfree(entries); break; } #endif /* CONFIG_HAVE_KVM_IRQ_ROUTING */ #ifdef CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES case KVM_SET_MEMORY_ATTRIBUTES: { struct kvm_memory_attributes attrs; r = -EFAULT; if (copy_from_user(&attrs, argp, sizeof(attrs))) goto out; r = kvm_vm_ioctl_set_mem_attributes(kvm, &attrs); break; } #endif /* CONFIG_KVM_GENERIC_MEMORY_ATTRIBUTES */ case KVM_CREATE_DEVICE: { struct kvm_create_device cd; r = -EFAULT; if (copy_from_user(&cd, argp, sizeof(cd))) goto out; r = kvm_ioctl_create_device(kvm, &cd); if (r) goto out; r = -EFAULT; if (copy_to_user(argp, &cd, sizeof(cd))) goto out; r = 0; break; } case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(kvm, arg); break; case KVM_RESET_DIRTY_RINGS: r = kvm_vm_ioctl_reset_dirty_pages(kvm); break; case KVM_GET_STATS_FD: r = kvm_vm_ioctl_get_stats_fd(kvm); break; #ifdef CONFIG_KVM_PRIVATE_MEM case KVM_CREATE_GUEST_MEMFD: { struct kvm_create_guest_memfd guest_memfd; r = -EFAULT; if (copy_from_user(&guest_memfd, argp, sizeof(guest_memfd))) goto out; r = kvm_gmem_create(kvm, &guest_memfd); break; } #endif default: r = kvm_arch_vm_ioctl(filp, ioctl, arg); } out: return r; } #ifdef CONFIG_KVM_COMPAT struct compat_kvm_dirty_log { __u32 slot; __u32 padding1; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; struct compat_kvm_clear_dirty_log { __u32 slot; __u32 num_pages; __u64 first_page; union { compat_uptr_t dirty_bitmap; /* one bit per page */ __u64 padding2; }; }; long __weak kvm_arch_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { return -ENOTTY; } static long kvm_vm_compat_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { struct kvm *kvm = filp->private_data; int r; if (kvm->mm != current->mm || kvm->vm_dead) return -EIO; r = kvm_arch_vm_compat_ioctl(filp, ioctl, arg); if (r != -ENOTTY) return r; switch (ioctl) { #ifdef CONFIG_KVM_GENERIC_DIRTYLOG_READ_PROTECT case KVM_CLEAR_DIRTY_LOG: { struct compat_kvm_clear_dirty_log compat_log; struct kvm_clear_dirty_log log; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) return -EFAULT; log.slot = compat_log.slot; log.num_pages = compat_log.num_pages; log.first_page = compat_log.first_page; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_clear_dirty_log(kvm, &log); break; } #endif case KVM_GET_DIRTY_LOG: { struct compat_kvm_dirty_log compat_log; struct kvm_dirty_log log; if (copy_from_user(&compat_log, (void __user *)arg, sizeof(compat_log))) return -EFAULT; log.slot = compat_log.slot; log.padding1 = compat_log.padding1; log.padding2 = compat_log.padding2; log.dirty_bitmap = compat_ptr(compat_log.dirty_bitmap); r = kvm_vm_ioctl_get_dirty_log(kvm, &log); break; } default: r = kvm_vm_ioctl(filp, ioctl, arg); } return r; } #endif static struct file_operations kvm_vm_fops = { .release = kvm_vm_release, .unlocked_ioctl = kvm_vm_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_vm_compat_ioctl), }; bool file_is_kvm(struct file *file) { return file && file->f_op == &kvm_vm_fops; } EXPORT_SYMBOL_GPL(file_is_kvm); static int kvm_dev_ioctl_create_vm(unsigned long type) { char fdname[ITOA_MAX_LEN + 1]; int r, fd; struct kvm *kvm; struct file *file; fd = get_unused_fd_flags(O_CLOEXEC); if (fd < 0) return fd; snprintf(fdname, sizeof(fdname), "%d", fd); kvm = kvm_create_vm(type, fdname); if (IS_ERR(kvm)) { r = PTR_ERR(kvm); goto put_fd; } file = anon_inode_getfile("kvm-vm", &kvm_vm_fops, kvm, O_RDWR); if (IS_ERR(file)) { r = PTR_ERR(file); goto put_kvm; } /* * Don't call kvm_put_kvm anymore at this point; file->f_op is * already set, with ->release() being kvm_vm_release(). In error * cases it will be called by the final fput(file) and will take * care of doing kvm_put_kvm(kvm). */ kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); fd_install(fd, file); return fd; put_kvm: kvm_put_kvm(kvm); put_fd: put_unused_fd(fd); return r; } static long kvm_dev_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg) { int r = -EINVAL; switch (ioctl) { case KVM_GET_API_VERSION: if (arg) goto out; r = KVM_API_VERSION; break; case KVM_CREATE_VM: r = kvm_dev_ioctl_create_vm(arg); break; case KVM_CHECK_EXTENSION: r = kvm_vm_ioctl_check_extension_generic(NULL, arg); break; case KVM_GET_VCPU_MMAP_SIZE: if (arg) goto out; r = PAGE_SIZE; /* struct kvm_run */ #ifdef CONFIG_X86 r += PAGE_SIZE; /* pio data page */ #endif #ifdef CONFIG_KVM_MMIO r += PAGE_SIZE; /* coalesced mmio ring page */ #endif break; default: return kvm_arch_dev_ioctl(filp, ioctl, arg); } out: return r; } static struct file_operations kvm_chardev_ops = { .unlocked_ioctl = kvm_dev_ioctl, .llseek = noop_llseek, KVM_COMPAT(kvm_dev_ioctl), }; static struct miscdevice kvm_dev = { KVM_MINOR, "kvm", &kvm_chardev_ops, }; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING __visible bool kvm_rebooting; EXPORT_SYMBOL_GPL(kvm_rebooting); static DEFINE_PER_CPU(bool, hardware_enabled); static int kvm_usage_count; static int __hardware_enable_nolock(void) { if (__this_cpu_read(hardware_enabled)) return 0; if (kvm_arch_hardware_enable()) { pr_info("kvm: enabling virtualization on CPU%d failed\n", raw_smp_processor_id()); return -EIO; } __this_cpu_write(hardware_enabled, true); return 0; } static void hardware_enable_nolock(void *failed) { if (__hardware_enable_nolock()) atomic_inc(failed); } static int kvm_online_cpu(unsigned int cpu) { int ret = 0; /* * Abort the CPU online process if hardware virtualization cannot * be enabled. Otherwise running VMs would encounter unrecoverable * errors when scheduled to this CPU. */ mutex_lock(&kvm_lock); if (kvm_usage_count) ret = __hardware_enable_nolock(); mutex_unlock(&kvm_lock); return ret; } static void hardware_disable_nolock(void *junk) { /* * Note, hardware_disable_all_nolock() tells all online CPUs to disable * hardware, not just CPUs that successfully enabled hardware! */ if (!__this_cpu_read(hardware_enabled)) return; kvm_arch_hardware_disable(); __this_cpu_write(hardware_enabled, false); } static int kvm_offline_cpu(unsigned int cpu) { mutex_lock(&kvm_lock); if (kvm_usage_count) hardware_disable_nolock(NULL); mutex_unlock(&kvm_lock); return 0; } static void hardware_disable_all_nolock(void) { BUG_ON(!kvm_usage_count); kvm_usage_count--; if (!kvm_usage_count) on_each_cpu(hardware_disable_nolock, NULL, 1); } static void hardware_disable_all(void) { cpus_read_lock(); mutex_lock(&kvm_lock); hardware_disable_all_nolock(); mutex_unlock(&kvm_lock); cpus_read_unlock(); } static int hardware_enable_all(void) { atomic_t failed = ATOMIC_INIT(0); int r; /* * Do not enable hardware virtualization if the system is going down. * If userspace initiated a forced reboot, e.g. reboot -f, then it's * possible for an in-flight KVM_CREATE_VM to trigger hardware enabling * after kvm_reboot() is called. Note, this relies on system_state * being set _before_ kvm_reboot(), which is why KVM uses a syscore ops * hook instead of registering a dedicated reboot notifier (the latter * runs before system_state is updated). */ if (system_state == SYSTEM_HALT || system_state == SYSTEM_POWER_OFF || system_state == SYSTEM_RESTART) return -EBUSY; /* * When onlining a CPU, cpu_online_mask is set before kvm_online_cpu() * is called, and so on_each_cpu() between them includes the CPU that * is being onlined. As a result, hardware_enable_nolock() may get * invoked before kvm_online_cpu(), which also enables hardware if the * usage count is non-zero. Disable CPU hotplug to avoid attempting to * enable hardware multiple times. */ cpus_read_lock(); mutex_lock(&kvm_lock); r = 0; kvm_usage_count++; if (kvm_usage_count == 1) { on_each_cpu(hardware_enable_nolock, &failed, 1); if (atomic_read(&failed)) { hardware_disable_all_nolock(); r = -EBUSY; } } mutex_unlock(&kvm_lock); cpus_read_unlock(); return r; } static void kvm_shutdown(void) { /* * Disable hardware virtualization and set kvm_rebooting to indicate * that KVM has asynchronously disabled hardware virtualization, i.e. * that relevant errors and exceptions aren't entirely unexpected. * Some flavors of hardware virtualization need to be disabled before * transferring control to firmware (to perform shutdown/reboot), e.g. * on x86, virtualization can block INIT interrupts, which are used by * firmware to pull APs back under firmware control. Note, this path * is used for both shutdown and reboot scenarios, i.e. neither name is * 100% comprehensive. */ pr_info("kvm: exiting hardware virtualization\n"); kvm_rebooting = true; on_each_cpu(hardware_disable_nolock, NULL, 1); } static int kvm_suspend(void) { /* * Secondary CPUs and CPU hotplug are disabled across the suspend/resume * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count * is stable. Assert that kvm_lock is not held to ensure the system * isn't suspended while KVM is enabling hardware. Hardware enabling * can be preempted, but the task cannot be frozen until it has dropped * all locks (userspace tasks are frozen via a fake signal). */ lockdep_assert_not_held(&kvm_lock); lockdep_assert_irqs_disabled(); if (kvm_usage_count) hardware_disable_nolock(NULL); return 0; } static void kvm_resume(void) { lockdep_assert_not_held(&kvm_lock); lockdep_assert_irqs_disabled(); if (kvm_usage_count) WARN_ON_ONCE(__hardware_enable_nolock()); } static struct syscore_ops kvm_syscore_ops = { .suspend = kvm_suspend, .resume = kvm_resume, .shutdown = kvm_shutdown, }; #else /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static int hardware_enable_all(void) { return 0; } static void hardware_disable_all(void) { } #endif /* CONFIG_KVM_GENERIC_HARDWARE_ENABLING */ static void kvm_iodevice_destructor(struct kvm_io_device *dev) { if (dev->ops->destructor) dev->ops->destructor(dev); } static void kvm_io_bus_destroy(struct kvm_io_bus *bus) { int i; for (i = 0; i < bus->dev_count; i++) { struct kvm_io_device *pos = bus->range[i].dev; kvm_iodevice_destructor(pos); } kfree(bus); } static inline int kvm_io_bus_cmp(const struct kvm_io_range *r1, const struct kvm_io_range *r2) { gpa_t addr1 = r1->addr; gpa_t addr2 = r2->addr; if (addr1 < addr2) return -1; /* If r2->len == 0, match the exact address. If r2->len != 0, * accept any overlapping write. Any order is acceptable for * overlapping ranges, because kvm_io_bus_get_first_dev ensures * we process all of them. */ if (r2->len) { addr1 += r1->len; addr2 += r2->len; } if (addr1 > addr2) return 1; return 0; } static int kvm_io_bus_sort_cmp(const void *p1, const void *p2) { return kvm_io_bus_cmp(p1, p2); } static int kvm_io_bus_get_first_dev(struct kvm_io_bus *bus, gpa_t addr, int len) { struct kvm_io_range *range, key; int off; key = (struct kvm_io_range) { .addr = addr, .len = len, }; range = bsearch(&key, bus->range, bus->dev_count, sizeof(struct kvm_io_range), kvm_io_bus_sort_cmp); if (range == NULL) return -ENOENT; off = range - bus->range; while (off > 0 && kvm_io_bus_cmp(&key, &bus->range[off-1]) == 0) off--; return off; } static int __kvm_io_bus_write(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, const void *val) { int idx; idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_write(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; } return -EOPNOTSUPP; } /* kvm_io_bus_write - called under kvm->slots_lock */ int kvm_io_bus_write(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val) { struct kvm_io_bus *bus; struct kvm_io_range range; int r; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; r = __kvm_io_bus_write(vcpu, bus, &range, val); return r < 0 ? r : 0; } EXPORT_SYMBOL_GPL(kvm_io_bus_write); /* kvm_io_bus_write_cookie - called under kvm->slots_lock */ int kvm_io_bus_write_cookie(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, const void *val, long cookie) { struct kvm_io_bus *bus; struct kvm_io_range range; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; /* First try the device referenced by cookie. */ if ((cookie >= 0) && (cookie < bus->dev_count) && (kvm_io_bus_cmp(&range, &bus->range[cookie]) == 0)) if (!kvm_iodevice_write(vcpu, bus->range[cookie].dev, addr, len, val)) return cookie; /* * cookie contained garbage; fall back to search and return the * correct cookie value. */ return __kvm_io_bus_write(vcpu, bus, &range, val); } static int __kvm_io_bus_read(struct kvm_vcpu *vcpu, struct kvm_io_bus *bus, struct kvm_io_range *range, void *val) { int idx; idx = kvm_io_bus_get_first_dev(bus, range->addr, range->len); if (idx < 0) return -EOPNOTSUPP; while (idx < bus->dev_count && kvm_io_bus_cmp(range, &bus->range[idx]) == 0) { if (!kvm_iodevice_read(vcpu, bus->range[idx].dev, range->addr, range->len, val)) return idx; idx++; } return -EOPNOTSUPP; } /* kvm_io_bus_read - called under kvm->slots_lock */ int kvm_io_bus_read(struct kvm_vcpu *vcpu, enum kvm_bus bus_idx, gpa_t addr, int len, void *val) { struct kvm_io_bus *bus; struct kvm_io_range range; int r; range = (struct kvm_io_range) { .addr = addr, .len = len, }; bus = srcu_dereference(vcpu->kvm->buses[bus_idx], &vcpu->kvm->srcu); if (!bus) return -ENOMEM; r = __kvm_io_bus_read(vcpu, bus, &range, val); return r < 0 ? r : 0; } int kvm_io_bus_register_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr, int len, struct kvm_io_device *dev) { int i; struct kvm_io_bus *new_bus, *bus; struct kvm_io_range range; lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus) return -ENOMEM; /* exclude ioeventfd which is limited by maximum fd */ if (bus->dev_count - bus->ioeventfd_count > NR_IOBUS_DEVS - 1) return -ENOSPC; new_bus = kmalloc(struct_size(bus, range, bus->dev_count + 1), GFP_KERNEL_ACCOUNT); if (!new_bus) return -ENOMEM; range = (struct kvm_io_range) { .addr = addr, .len = len, .dev = dev, }; for (i = 0; i < bus->dev_count; i++) if (kvm_io_bus_cmp(&bus->range[i], &range) > 0) break; memcpy(new_bus, bus, sizeof(*bus) + i * sizeof(struct kvm_io_range)); new_bus->dev_count++; new_bus->range[i] = range; memcpy(new_bus->range + i + 1, bus->range + i, (bus->dev_count - i) * sizeof(struct kvm_io_range)); rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); kfree(bus); return 0; } int kvm_io_bus_unregister_dev(struct kvm *kvm, enum kvm_bus bus_idx, struct kvm_io_device *dev) { int i; struct kvm_io_bus *new_bus, *bus; lockdep_assert_held(&kvm->slots_lock); bus = kvm_get_bus(kvm, bus_idx); if (!bus) return 0; for (i = 0; i < bus->dev_count; i++) { if (bus->range[i].dev == dev) { break; } } if (i == bus->dev_count) return 0; new_bus = kmalloc(struct_size(bus, range, bus->dev_count - 1), GFP_KERNEL_ACCOUNT); if (new_bus) { memcpy(new_bus, bus, struct_size(bus, range, i)); new_bus->dev_count--; memcpy(new_bus->range + i, bus->range + i + 1, flex_array_size(new_bus, range, new_bus->dev_count - i)); } rcu_assign_pointer(kvm->buses[bus_idx], new_bus); synchronize_srcu_expedited(&kvm->srcu); /* * If NULL bus is installed, destroy the old bus, including all the * attached devices. Otherwise, destroy the caller's device only. */ if (!new_bus) { pr_err("kvm: failed to shrink bus, removing it completely\n"); kvm_io_bus_destroy(bus); return -ENOMEM; } kvm_iodevice_destructor(dev); kfree(bus); return 0; } struct kvm_io_device *kvm_io_bus_get_dev(struct kvm *kvm, enum kvm_bus bus_idx, gpa_t addr) { struct kvm_io_bus *bus; int dev_idx, srcu_idx; struct kvm_io_device *iodev = NULL; srcu_idx = srcu_read_lock(&kvm->srcu); bus = srcu_dereference(kvm->buses[bus_idx], &kvm->srcu); if (!bus) goto out_unlock; dev_idx = kvm_io_bus_get_first_dev(bus, addr, 1); if (dev_idx < 0) goto out_unlock; iodev = bus->range[dev_idx].dev; out_unlock: srcu_read_unlock(&kvm->srcu, srcu_idx); return iodev; } EXPORT_SYMBOL_GPL(kvm_io_bus_get_dev); static int kvm_debugfs_open(struct inode *inode, struct file *file, int (*get)(void *, u64 *), int (*set)(void *, u64), const char *fmt) { int ret; struct kvm_stat_data *stat_data = inode->i_private; /* * The debugfs files are a reference to the kvm struct which * is still valid when kvm_destroy_vm is called. kvm_get_kvm_safe * avoids the race between open and the removal of the debugfs directory. */ if (!kvm_get_kvm_safe(stat_data->kvm)) return -ENOENT; ret = simple_attr_open(inode, file, get, kvm_stats_debugfs_mode(stat_data->desc) & 0222 ? set : NULL, fmt); if (ret) kvm_put_kvm(stat_data->kvm); return ret; } static int kvm_debugfs_release(struct inode *inode, struct file *file) { struct kvm_stat_data *stat_data = inode->i_private; simple_attr_release(inode, file); kvm_put_kvm(stat_data->kvm); return 0; } static int kvm_get_stat_per_vm(struct kvm *kvm, size_t offset, u64 *val) { *val = *(u64 *)((void *)(&kvm->stat) + offset); return 0; } static int kvm_clear_stat_per_vm(struct kvm *kvm, size_t offset) { *(u64 *)((void *)(&kvm->stat) + offset) = 0; return 0; } static int kvm_get_stat_per_vcpu(struct kvm *kvm, size_t offset, u64 *val) { unsigned long i; struct kvm_vcpu *vcpu; *val = 0; kvm_for_each_vcpu(i, vcpu, kvm) *val += *(u64 *)((void *)(&vcpu->stat) + offset); return 0; } static int kvm_clear_stat_per_vcpu(struct kvm *kvm, size_t offset) { unsigned long i; struct kvm_vcpu *vcpu; kvm_for_each_vcpu(i, vcpu, kvm) *(u64 *)((void *)(&vcpu->stat) + offset) = 0; return 0; } static int kvm_stat_data_get(void *data, u64 *val) { int r = -EFAULT; struct kvm_stat_data *stat_data = data; switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_get_stat_per_vm(stat_data->kvm, stat_data->desc->desc.offset, val); break; case KVM_STAT_VCPU: r = kvm_get_stat_per_vcpu(stat_data->kvm, stat_data->desc->desc.offset, val); break; } return r; } static int kvm_stat_data_clear(void *data, u64 val) { int r = -EFAULT; struct kvm_stat_data *stat_data = data; if (val) return -EINVAL; switch (stat_data->kind) { case KVM_STAT_VM: r = kvm_clear_stat_per_vm(stat_data->kvm, stat_data->desc->desc.offset); break; case KVM_STAT_VCPU: r = kvm_clear_stat_per_vcpu(stat_data->kvm, stat_data->desc->desc.offset); break; } return r; } static int kvm_stat_data_open(struct inode *inode, struct file *file) { __simple_attr_check_format("%llu\n", 0ull); return kvm_debugfs_open(inode, file, kvm_stat_data_get, kvm_stat_data_clear, "%llu\n"); } static const struct file_operations stat_fops_per_vm = { .owner = THIS_MODULE, .open = kvm_stat_data_open, .release = kvm_debugfs_release, .read = simple_attr_read, .write = simple_attr_write, .llseek = no_llseek, }; static int vm_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_get_stat_per_vm(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); return 0; } static int vm_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_clear_stat_per_vm(kvm, offset); } mutex_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vm_stat_fops, vm_stat_get, vm_stat_clear, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(vm_stat_readonly_fops, vm_stat_get, NULL, "%llu\n"); static int vcpu_stat_get(void *_offset, u64 *val) { unsigned offset = (long)_offset; struct kvm *kvm; u64 tmp_val; *val = 0; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_get_stat_per_vcpu(kvm, offset, &tmp_val); *val += tmp_val; } mutex_unlock(&kvm_lock); return 0; } static int vcpu_stat_clear(void *_offset, u64 val) { unsigned offset = (long)_offset; struct kvm *kvm; if (val) return -EINVAL; mutex_lock(&kvm_lock); list_for_each_entry(kvm, &vm_list, vm_list) { kvm_clear_stat_per_vcpu(kvm, offset); } mutex_unlock(&kvm_lock); return 0; } DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_fops, vcpu_stat_get, vcpu_stat_clear, "%llu\n"); DEFINE_SIMPLE_ATTRIBUTE(vcpu_stat_readonly_fops, vcpu_stat_get, NULL, "%llu\n"); static void kvm_uevent_notify_change(unsigned int type, struct kvm *kvm) { struct kobj_uevent_env *env; unsigned long long created, active; if (!kvm_dev.this_device || !kvm) return; mutex_lock(&kvm_lock); if (type == KVM_EVENT_CREATE_VM) { kvm_createvm_count++; kvm_active_vms++; } else if (type == KVM_EVENT_DESTROY_VM) { kvm_active_vms--; } created = kvm_createvm_count; active = kvm_active_vms; mutex_unlock(&kvm_lock); env = kzalloc(sizeof(*env), GFP_KERNEL); if (!env) return; add_uevent_var(env, "CREATED=%llu", created); add_uevent_var(env, "COUNT=%llu", active); if (type == KVM_EVENT_CREATE_VM) { add_uevent_var(env, "EVENT=create"); kvm->userspace_pid = task_pid_nr(current); } else if (type == KVM_EVENT_DESTROY_VM) { add_uevent_var(env, "EVENT=destroy"); } add_uevent_var(env, "PID=%d", kvm->userspace_pid); if (!IS_ERR(kvm->debugfs_dentry)) { char *tmp, *p = kmalloc(PATH_MAX, GFP_KERNEL); if (p) { tmp = dentry_path_raw(kvm->debugfs_dentry, p, PATH_MAX); if (!IS_ERR(tmp)) add_uevent_var(env, "STATS_PATH=%s", tmp); kfree(p); } } /* no need for checks, since we are adding at most only 5 keys */ env->envp[env->envp_idx++] = NULL; kobject_uevent_env(&kvm_dev.this_device->kobj, KOBJ_CHANGE, env->envp); kfree(env); } static void kvm_init_debug(void) { const struct file_operations *fops; const struct _kvm_stats_desc *pdesc; int i; kvm_debugfs_dir = debugfs_create_dir("kvm", NULL); for (i = 0; i < kvm_vm_stats_header.num_desc; ++i) { pdesc = &kvm_vm_stats_desc[i]; if (kvm_stats_debugfs_mode(pdesc) & 0222) fops = &vm_stat_fops; else fops = &vm_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, (void *)(long)pdesc->desc.offset, fops); } for (i = 0; i < kvm_vcpu_stats_header.num_desc; ++i) { pdesc = &kvm_vcpu_stats_desc[i]; if (kvm_stats_debugfs_mode(pdesc) & 0222) fops = &vcpu_stat_fops; else fops = &vcpu_stat_readonly_fops; debugfs_create_file(pdesc->name, kvm_stats_debugfs_mode(pdesc), kvm_debugfs_dir, (void *)(long)pdesc->desc.offset, fops); } } static inline struct kvm_vcpu *preempt_notifier_to_vcpu(struct preempt_notifier *pn) { return container_of(pn, struct kvm_vcpu, preempt_notifier); } static void kvm_sched_in(struct preempt_notifier *pn, int cpu) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); WRITE_ONCE(vcpu->preempted, false); WRITE_ONCE(vcpu->ready, false); __this_cpu_write(kvm_running_vcpu, vcpu); kvm_arch_sched_in(vcpu, cpu); kvm_arch_vcpu_load(vcpu, cpu); } static void kvm_sched_out(struct preempt_notifier *pn, struct task_struct *next) { struct kvm_vcpu *vcpu = preempt_notifier_to_vcpu(pn); if (current->on_rq) { WRITE_ONCE(vcpu->preempted, true); WRITE_ONCE(vcpu->ready, true); } kvm_arch_vcpu_put(vcpu); __this_cpu_write(kvm_running_vcpu, NULL); } /** * kvm_get_running_vcpu - get the vcpu running on the current CPU. * * We can disable preemption locally around accessing the per-CPU variable, * and use the resolved vcpu pointer after enabling preemption again, * because even if the current thread is migrated to another CPU, reading * the per-CPU value later will give us the same value as we update the * per-CPU variable in the preempt notifier handlers. */ struct kvm_vcpu *kvm_get_running_vcpu(void) { struct kvm_vcpu *vcpu; preempt_disable(); vcpu = __this_cpu_read(kvm_running_vcpu); preempt_enable(); return vcpu; } EXPORT_SYMBOL_GPL(kvm_get_running_vcpu); /** * kvm_get_running_vcpus - get the per-CPU array of currently running vcpus. */ struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void) { return &kvm_running_vcpu; } #ifdef CONFIG_GUEST_PERF_EVENTS static unsigned int kvm_guest_state(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); unsigned int state; if (!kvm_arch_pmi_in_guest(vcpu)) return 0; state = PERF_GUEST_ACTIVE; if (!kvm_arch_vcpu_in_kernel(vcpu)) state |= PERF_GUEST_USER; return state; } static unsigned long kvm_guest_get_ip(void) { struct kvm_vcpu *vcpu = kvm_get_running_vcpu(); /* Retrieving the IP must be guarded by a call to kvm_guest_state(). */ if (WARN_ON_ONCE(!kvm_arch_pmi_in_guest(vcpu))) return 0; return kvm_arch_vcpu_get_ip(vcpu); } static struct perf_guest_info_callbacks kvm_guest_cbs = { .state = kvm_guest_state, .get_ip = kvm_guest_get_ip, .handle_intel_pt_intr = NULL, }; void kvm_register_perf_callbacks(unsigned int (*pt_intr_handler)(void)) { kvm_guest_cbs.handle_intel_pt_intr = pt_intr_handler; perf_register_guest_info_callbacks(&kvm_guest_cbs); } void kvm_unregister_perf_callbacks(void) { perf_unregister_guest_info_callbacks(&kvm_guest_cbs); } #endif int kvm_init(unsigned vcpu_size, unsigned vcpu_align, struct module *module) { int r; int cpu; #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING r = cpuhp_setup_state_nocalls(CPUHP_AP_KVM_ONLINE, "kvm/cpu:online", kvm_online_cpu, kvm_offline_cpu); if (r) return r; register_syscore_ops(&kvm_syscore_ops); #endif /* A kmem cache lets us meet the alignment requirements of fx_save. */ if (!vcpu_align) vcpu_align = __alignof__(struct kvm_vcpu); kvm_vcpu_cache = kmem_cache_create_usercopy("kvm_vcpu", vcpu_size, vcpu_align, SLAB_ACCOUNT, offsetof(struct kvm_vcpu, arch), offsetofend(struct kvm_vcpu, stats_id) - offsetof(struct kvm_vcpu, arch), NULL); if (!kvm_vcpu_cache) { r = -ENOMEM; goto err_vcpu_cache; } for_each_possible_cpu(cpu) { if (!alloc_cpumask_var_node(&per_cpu(cpu_kick_mask, cpu), GFP_KERNEL, cpu_to_node(cpu))) { r = -ENOMEM; goto err_cpu_kick_mask; } } r = kvm_irqfd_init(); if (r) goto err_irqfd; r = kvm_async_pf_init(); if (r) goto err_async_pf; kvm_chardev_ops.owner = module; kvm_vm_fops.owner = module; kvm_vcpu_fops.owner = module; kvm_device_fops.owner = module; kvm_preempt_ops.sched_in = kvm_sched_in; kvm_preempt_ops.sched_out = kvm_sched_out; kvm_init_debug(); r = kvm_vfio_ops_init(); if (WARN_ON_ONCE(r)) goto err_vfio; kvm_gmem_init(module); /* * Registration _must_ be the very last thing done, as this exposes * /dev/kvm to userspace, i.e. all infrastructure must be setup! */ r = misc_register(&kvm_dev); if (r) { pr_err("kvm: misc device register failed\n"); goto err_register; } return 0; err_register: kvm_vfio_ops_exit(); err_vfio: kvm_async_pf_deinit(); err_async_pf: kvm_irqfd_exit(); err_irqfd: err_cpu_kick_mask: for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); err_vcpu_cache: #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif return r; } EXPORT_SYMBOL_GPL(kvm_init); void kvm_exit(void) { int cpu; /* * Note, unregistering /dev/kvm doesn't strictly need to come first, * fops_get(), a.k.a. try_module_get(), prevents acquiring references * to KVM while the module is being stopped. */ misc_deregister(&kvm_dev); debugfs_remove_recursive(kvm_debugfs_dir); for_each_possible_cpu(cpu) free_cpumask_var(per_cpu(cpu_kick_mask, cpu)); kmem_cache_destroy(kvm_vcpu_cache); kvm_vfio_ops_exit(); kvm_async_pf_deinit(); #ifdef CONFIG_KVM_GENERIC_HARDWARE_ENABLING unregister_syscore_ops(&kvm_syscore_ops); cpuhp_remove_state_nocalls(CPUHP_AP_KVM_ONLINE); #endif kvm_irqfd_exit(); } EXPORT_SYMBOL_GPL(kvm_exit); struct kvm_vm_worker_thread_context { struct kvm *kvm; struct task_struct *parent; struct completion init_done; kvm_vm_thread_fn_t thread_fn; uintptr_t data; int err; }; static int kvm_vm_worker_thread(void *context) { /* * The init_context is allocated on the stack of the parent thread, so * we have to locally copy anything that is needed beyond initialization */ struct kvm_vm_worker_thread_context *init_context = context; struct task_struct *parent; struct kvm *kvm = init_context->kvm; kvm_vm_thread_fn_t thread_fn = init_context->thread_fn; uintptr_t data = init_context->data; int err; err = kthread_park(current); /* kthread_park(current) is never supposed to return an error */ WARN_ON(err != 0); if (err) goto init_complete; err = cgroup_attach_task_all(init_context->parent, current); if (err) { kvm_err("%s: cgroup_attach_task_all failed with err %d\n", __func__, err); goto init_complete; } set_user_nice(current, task_nice(init_context->parent)); init_complete: init_context->err = err; complete(&init_context->init_done); init_context = NULL; if (err) goto out; /* Wait to be woken up by the spawner before proceeding. */ kthread_parkme(); if (!kthread_should_stop()) err = thread_fn(kvm, data); out: /* * Move kthread back to its original cgroup to prevent it lingering in * the cgroup of the VM process, after the latter finishes its * execution. * * kthread_stop() waits on the 'exited' completion condition which is * set in exit_mm(), via mm_release(), in do_exit(). However, the * kthread is removed from the cgroup in the cgroup_exit() which is * called after the exit_mm(). This causes the kthread_stop() to return * before the kthread actually quits the cgroup. */ rcu_read_lock(); parent = rcu_dereference(current->real_parent); get_task_struct(parent); rcu_read_unlock(); cgroup_attach_task_all(parent, current); put_task_struct(parent); return err; } int kvm_vm_create_worker_thread(struct kvm *kvm, kvm_vm_thread_fn_t thread_fn, uintptr_t data, const char *name, struct task_struct **thread_ptr) { struct kvm_vm_worker_thread_context init_context = {}; struct task_struct *thread; *thread_ptr = NULL; init_context.kvm = kvm; init_context.parent = current; init_context.thread_fn = thread_fn; init_context.data = data; init_completion(&init_context.init_done); thread = kthread_run(kvm_vm_worker_thread, &init_context, "%s-%d", name, task_pid_nr(current)); if (IS_ERR(thread)) return PTR_ERR(thread); /* kthread_run is never supposed to return NULL */ WARN_ON(thread == NULL); wait_for_completion(&init_context.init_done); if (!init_context.err) *thread_ptr = thread; return init_context.err; } |
| 54 68 25 4 2 38 24 255 6 255 255 255 119 24 241 255 255 240 239 33 241 254 255 241 241 255 57 25 25 25 33 33 33 38 38 38 38 38 38 38 61 37 34 1 1 4 4 4 1 1 61 58 5 37 33 37 1 1 1 1 1 1 1 1 1 1 37 67 61 58 61 37 58 61 17 17 17 67 39 37 37 37 67 33 39 77 51 77 4 77 77 67 67 17 77 77 77 77 77 17 77 33 77 51 47 4 4 4 77 6 6 6 6 25 25 4 24 25 25 6 25 25 9 114 114 15 114 9 113 114 106 2 2 2 2 2 2 2 2 2 114 2 2 9 9 9 9 9 9 9 9 9 16 16 16 16 16 237 237 237 237 237 33 36 3 3 3 33 33 33 33 33 33 33 33 33 33 33 33 76 76 76 76 76 76 20 76 8 8 16 16 16 16 16 8 8 16 16 16 16 16 16 16 16 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 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 | // 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> #include "radix-tree.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_next_offset(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 __always_inline 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; while (xa_is_sibling(entry)) { offset = xa_to_sibling(entry); entry = xa_entry(xas->xa, node, offset); if (node->shift && xa_is_node(entry)) entry = XA_RETRY_ENTRY; } 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); #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. * * Most users will not need to call this function; it is called for you * by xas_nomem(). */ 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_lru(radix_tree_node_cachep, xas->xa_lru, 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_lru(radix_tree_node_cachep, xas->xa_lru, gfp); xas_lock_type(xas, lock_type); } else { xas->xa_alloc = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, 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_lru(radix_tree_node_cachep, xas->xa_lru, 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 + 1UL) << 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 inline void node_mark_slots(struct xa_node *node, unsigned int sibs, xa_mark_t mark) { int i; if (sibs == 0) node_mark_all(node, mark); else { for (i = 0; i < XA_CHUNK_SIZE; i += sibs + 1) node_set_mark(node, i, mark); } } static void node_set_marks(struct xa_node *node, unsigned int offset, struct xa_node *child, unsigned int sibs, 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_slots(child, sibs, 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: Current 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 = NULL; struct xa_node *node; node = kmem_cache_alloc_lru(radix_tree_node_cachep, xas->xa_lru, 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(i); } 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: Current entry order. * * The size of the new entries is set in @xas. The value in @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, xas->xa_sibs, 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, 0, 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_next_offset(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_next_offset(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); /** * xas_get_order() - Get the order of an entry. * @xas: XArray operation state. * * Called after xas_load, the xas should not be in an error state. * * Return: A number between 0 and 63 indicating the order of the entry. */ int xas_get_order(struct xa_state *xas) { int order = 0; if (!xas->xa_node) return 0; for (;;) { unsigned int slot = xas->xa_offset + (1 << order); if (slot >= XA_CHUNK_SIZE) break; if (!xa_is_sibling(xa_entry(xas->xa, xas->xa_node, slot))) break; order++; } order += xas->xa_node->shift; return order; } EXPORT_SYMBOL_GPL(xas_get_order); /** * 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); int order = 0; void *entry; rcu_read_lock(); entry = xas_load(&xas); if (entry) order = xas_get_order(&xas); 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. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * 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. * * Must only be operated on an xarray initialized with flag XA_FLAGS_ALLOC set * in xa_init_flags(). * * 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 (!IS_ENABLED(CONFIG_XARRAY_MULTI) || !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_delete_node() - Private interface for workingset code. * @node: Node to be removed from the tree. * @update: Function to call to update ancestor nodes. * * Context: xa_lock must be held on entry and will not be released. */ void xa_delete_node(struct xa_node *node, xa_update_node_t update) { struct xa_state xas = { .xa = node->array, .xa_index = (unsigned long)node->offset << (node->shift + XA_CHUNK_SHIFT), .xa_shift = node->shift + XA_CHUNK_SHIFT, .xa_offset = node->offset, .xa_node = xa_parent_locked(node->array, node), .xa_update = update, }; xas_store(&xas, NULL); } EXPORT_SYMBOL_GPL(xa_delete_node); /* For the benefit of the test suite */ /** * 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 |
| 1 1 1 144 144 10 14 10 10 10 4 4 10 10 4 10 10 6 10 6 4 10 130 10 10 10 10 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012,2013 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> * * Derived from arch/arm/include/asm/kvm_host.h: * Copyright (C) 2012 - Virtual Open Systems and Columbia University * Author: Christoffer Dall <c.dall@virtualopensystems.com> */ #ifndef __ARM64_KVM_HOST_H__ #define __ARM64_KVM_HOST_H__ #include <linux/arm-smccc.h> #include <linux/bitmap.h> #include <linux/types.h> #include <linux/jump_label.h> #include <linux/kvm_types.h> #include <linux/maple_tree.h> #include <linux/percpu.h> #include <linux/psci.h> #include <asm/arch_gicv3.h> #include <asm/barrier.h> #include <asm/cpufeature.h> #include <asm/cputype.h> #include <asm/daifflags.h> #include <asm/fpsimd.h> #include <asm/kvm.h> #include <asm/kvm_asm.h> #include <asm/vncr_mapping.h> #define __KVM_HAVE_ARCH_INTC_INITIALIZED #define KVM_HALT_POLL_NS_DEFAULT 500000 #include <kvm/arm_vgic.h> #include <kvm/arm_arch_timer.h> #include <kvm/arm_pmu.h> #define KVM_MAX_VCPUS VGIC_V3_MAX_CPUS #define KVM_VCPU_MAX_FEATURES 7 #define KVM_VCPU_VALID_FEATURES (BIT(KVM_VCPU_MAX_FEATURES) - 1) #define KVM_REQ_SLEEP \ KVM_ARCH_REQ_FLAGS(0, KVM_REQUEST_WAIT | KVM_REQUEST_NO_WAKEUP) #define KVM_REQ_IRQ_PENDING KVM_ARCH_REQ(1) #define KVM_REQ_VCPU_RESET KVM_ARCH_REQ(2) #define KVM_REQ_RECORD_STEAL KVM_ARCH_REQ(3) #define KVM_REQ_RELOAD_GICv4 KVM_ARCH_REQ(4) #define KVM_REQ_RELOAD_PMU KVM_ARCH_REQ(5) #define KVM_REQ_SUSPEND KVM_ARCH_REQ(6) #define KVM_REQ_RESYNC_PMU_EL0 KVM_ARCH_REQ(7) #define KVM_DIRTY_LOG_MANUAL_CAPS (KVM_DIRTY_LOG_MANUAL_PROTECT_ENABLE | \ KVM_DIRTY_LOG_INITIALLY_SET) #define KVM_HAVE_MMU_RWLOCK /* * Mode of operation configurable with kvm-arm.mode early param. * See Documentation/admin-guide/kernel-parameters.txt for more information. */ enum kvm_mode { KVM_MODE_DEFAULT, KVM_MODE_PROTECTED, KVM_MODE_NV, KVM_MODE_NONE, }; #ifdef CONFIG_KVM enum kvm_mode kvm_get_mode(void); #else static inline enum kvm_mode kvm_get_mode(void) { return KVM_MODE_NONE; }; #endif DECLARE_STATIC_KEY_FALSE(userspace_irqchip_in_use); extern unsigned int __ro_after_init kvm_sve_max_vl; extern unsigned int __ro_after_init kvm_host_sve_max_vl; int __init kvm_arm_init_sve(void); u32 __attribute_const__ kvm_target_cpu(void); void kvm_reset_vcpu(struct kvm_vcpu *vcpu); void kvm_arm_vcpu_destroy(struct kvm_vcpu *vcpu); struct kvm_hyp_memcache { phys_addr_t head; unsigned long nr_pages; }; static inline void push_hyp_memcache(struct kvm_hyp_memcache *mc, phys_addr_t *p, phys_addr_t (*to_pa)(void *virt)) { *p = mc->head; mc->head = to_pa(p); mc->nr_pages++; } static inline void *pop_hyp_memcache(struct kvm_hyp_memcache *mc, void *(*to_va)(phys_addr_t phys)) { phys_addr_t *p = to_va(mc->head); if (!mc->nr_pages) return NULL; mc->head = *p; mc->nr_pages--; return p; } static inline int __topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages, void *(*alloc_fn)(void *arg), phys_addr_t (*to_pa)(void *virt), void *arg) { while (mc->nr_pages < min_pages) { phys_addr_t *p = alloc_fn(arg); if (!p) return -ENOMEM; push_hyp_memcache(mc, p, to_pa); } return 0; } static inline void __free_hyp_memcache(struct kvm_hyp_memcache *mc, void (*free_fn)(void *virt, void *arg), void *(*to_va)(phys_addr_t phys), void *arg) { while (mc->nr_pages) free_fn(pop_hyp_memcache(mc, to_va), arg); } void free_hyp_memcache(struct kvm_hyp_memcache *mc); int topup_hyp_memcache(struct kvm_hyp_memcache *mc, unsigned long min_pages); struct kvm_vmid { atomic64_t id; }; struct kvm_s2_mmu { struct kvm_vmid vmid; /* * stage2 entry level table * * Two kvm_s2_mmu structures in the same VM can point to the same * pgd here. This happens when running a guest using a * translation regime that isn't affected by its own stage-2 * translation, such as a non-VHE hypervisor running at vEL2, or * for vEL1/EL0 with vHCR_EL2.VM == 0. In that case, we use the * canonical stage-2 page tables. */ phys_addr_t pgd_phys; struct kvm_pgtable *pgt; /* * VTCR value used on the host. For a non-NV guest (or a NV * guest that runs in a context where its own S2 doesn't * apply), its T0SZ value reflects that of the IPA size. * * For a shadow S2 MMU, T0SZ reflects the PARange exposed to * the guest. */ u64 vtcr; /* The last vcpu id that ran on each physical CPU */ int __percpu *last_vcpu_ran; #define KVM_ARM_EAGER_SPLIT_CHUNK_SIZE_DEFAULT 0 /* * Memory cache used to split * KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE worth of huge pages. It * is used to allocate stage2 page tables while splitting huge * pages. The choice of KVM_CAP_ARM_EAGER_SPLIT_CHUNK_SIZE * influences both the capacity of the split page cache, and * how often KVM reschedules. Be wary of raising CHUNK_SIZE * too high. * * Protected by kvm->slots_lock. */ struct kvm_mmu_memory_cache split_page_cache; uint64_t split_page_chunk_size; struct kvm_arch *arch; /* * For a shadow stage-2 MMU, the virtual vttbr used by the * host to parse the guest S2. * This either contains: * - the virtual VTTBR programmed by the guest hypervisor with * CnP cleared * - The value 1 (VMID=0, BADDR=0, CnP=1) if invalid * * We also cache the full VTCR which gets used for TLB invalidation, * taking the ARM ARM's "Any of the bits in VTCR_EL2 are permitted * to be cached in a TLB" to the letter. */ u64 tlb_vttbr; u64 tlb_vtcr; /* * true when this represents a nested context where virtual * HCR_EL2.VM == 1 */ bool nested_stage2_enabled; /* * 0: Nobody is currently using this, check vttbr for validity * >0: Somebody is actively using this. */ atomic_t refcnt; }; struct kvm_arch_memory_slot { }; /** * struct kvm_smccc_features: Descriptor of the hypercall services exposed to the guests * * @std_bmap: Bitmap of standard secure service calls * @std_hyp_bmap: Bitmap of standard hypervisor service calls * @vendor_hyp_bmap: Bitmap of vendor specific hypervisor service calls */ struct kvm_smccc_features { unsigned long std_bmap; unsigned long std_hyp_bmap; unsigned long vendor_hyp_bmap; }; typedef unsigned int pkvm_handle_t; struct kvm_protected_vm { pkvm_handle_t handle; struct kvm_hyp_memcache teardown_mc; bool enabled; }; struct kvm_mpidr_data { u64 mpidr_mask; DECLARE_FLEX_ARRAY(u16, cmpidr_to_idx); }; static inline u16 kvm_mpidr_index(struct kvm_mpidr_data *data, u64 mpidr) { unsigned long index = 0, mask = data->mpidr_mask; unsigned long aff = mpidr & MPIDR_HWID_BITMASK; bitmap_gather(&index, &aff, &mask, fls(mask)); return index; } struct kvm_sysreg_masks; enum fgt_group_id { __NO_FGT_GROUP__, HFGxTR_GROUP, HDFGRTR_GROUP, HDFGWTR_GROUP = HDFGRTR_GROUP, HFGITR_GROUP, HAFGRTR_GROUP, /* Must be last */ __NR_FGT_GROUP_IDS__ }; struct kvm_arch { struct kvm_s2_mmu mmu; /* * Fine-Grained UNDEF, mimicking the FGT layout defined by the * architecture. We track them globally, as we present the * same feature-set to all vcpus. * * Index 0 is currently spare. */ u64 fgu[__NR_FGT_GROUP_IDS__]; /* * Stage 2 paging state for VMs with nested S2 using a virtual * VMID. */ struct kvm_s2_mmu *nested_mmus; size_t nested_mmus_size; int nested_mmus_next; /* Interrupt controller */ struct vgic_dist vgic; /* Timers */ struct arch_timer_vm_data timer_data; /* Mandated version of PSCI */ u32 psci_version; /* Protects VM-scoped configuration data */ struct mutex config_lock; /* * If we encounter a data abort without valid instruction syndrome * information, report this to user space. User space can (and * should) opt in to this feature if KVM_CAP_ARM_NISV_TO_USER is * supported. */ #define KVM_ARCH_FLAG_RETURN_NISV_IO_ABORT_TO_USER 0 /* Memory Tagging Extension enabled for the guest */ #define KVM_ARCH_FLAG_MTE_ENABLED 1 /* At least one vCPU has ran in the VM */ #define KVM_ARCH_FLAG_HAS_RAN_ONCE 2 /* The vCPU feature set for the VM is configured */ #define KVM_ARCH_FLAG_VCPU_FEATURES_CONFIGURED 3 /* PSCI SYSTEM_SUSPEND enabled for the guest */ #define KVM_ARCH_FLAG_SYSTEM_SUSPEND_ENABLED 4 /* VM counter offset */ #define KVM_ARCH_FLAG_VM_COUNTER_OFFSET 5 /* Timer PPIs made immutable */ #define KVM_ARCH_FLAG_TIMER_PPIS_IMMUTABLE 6 /* Initial ID reg values loaded */ #define KVM_ARCH_FLAG_ID_REGS_INITIALIZED 7 /* Fine-Grained UNDEF initialised */ #define KVM_ARCH_FLAG_FGU_INITIALIZED 8 unsigned long flags; /* VM-wide vCPU feature set */ DECLARE_BITMAP(vcpu_features, KVM_VCPU_MAX_FEATURES); /* MPIDR to vcpu index mapping, optional */ struct kvm_mpidr_data *mpidr_data; /* * VM-wide PMU filter, implemented as a bitmap and big enough for * up to 2^10 events (ARMv8.0) or 2^16 events (ARMv8.1+). */ unsigned long *pmu_filter; struct arm_pmu *arm_pmu; cpumask_var_t supported_cpus; /* PMCR_EL0.N value for the guest */ u8 pmcr_n; /* Iterator for idreg debugfs */ u8 idreg_debugfs_iter; /* Hypercall features firmware registers' descriptor */ struct kvm_smccc_features smccc_feat; struct maple_tree smccc_filter; /* * Emulated CPU ID registers per VM * (Op0, Op1, CRn, CRm, Op2) of the ID registers to be saved in it * is (3, 0, 0, crm, op2), where 1<=crm<8, 0<=op2<8. * * These emulated idregs are VM-wide, but accessed from the context of a vCPU. * Atomic access to multiple idregs are guarded by kvm_arch.config_lock. */ #define IDREG_IDX(id) (((sys_reg_CRm(id) - 1) << 3) | sys_reg_Op2(id)) #define KVM_ARM_ID_REG_NUM (IDREG_IDX(sys_reg(3, 0, 0, 7, 7)) + 1) u64 id_regs[KVM_ARM_ID_REG_NUM]; u64 ctr_el0; /* Masks for VNCR-baked sysregs */ struct kvm_sysreg_masks *sysreg_masks; /* * For an untrusted host VM, 'pkvm.handle' is used to lookup * the associated pKVM instance in the hypervisor. */ struct kvm_protected_vm pkvm; }; struct kvm_vcpu_fault_info { u64 esr_el2; /* Hyp Syndrom Register */ u64 far_el2; /* Hyp Fault Address Register */ u64 hpfar_el2; /* Hyp IPA Fault Address Register */ u64 disr_el1; /* Deferred [SError] Status Register */ }; /* * VNCR() just places the VNCR_capable registers in the enum after * __VNCR_START__, and the value (after correction) to be an 8-byte offset * from the VNCR base. As we don't require the enum to be otherwise ordered, * we need the terrible hack below to ensure that we correctly size the * sys_regs array, no matter what. * * The __MAX__ macro has been lifted from Sean Eron Anderson's wonderful * treasure trove of bit hacks: * https://graphics.stanford.edu/~seander/bithacks.html#IntegerMinOrMax */ #define __MAX__(x,y) ((x) ^ (((x) ^ (y)) & -((x) < (y)))) #define VNCR(r) \ __before_##r, \ r = __VNCR_START__ + ((VNCR_ ## r) / 8), \ __after_##r = __MAX__(__before_##r - 1, r) enum vcpu_sysreg { __INVALID_SYSREG__, /* 0 is reserved as an invalid value */ MPIDR_EL1, /* MultiProcessor Affinity Register */ CLIDR_EL1, /* Cache Level ID Register */ CSSELR_EL1, /* Cache Size Selection Register */ TPIDR_EL0, /* Thread ID, User R/W */ TPIDRRO_EL0, /* Thread ID, User R/O */ TPIDR_EL1, /* Thread ID, Privileged */ CNTKCTL_EL1, /* Timer Control Register (EL1) */ PAR_EL1, /* Physical Address Register */ MDCCINT_EL1, /* Monitor Debug Comms Channel Interrupt Enable Reg */ OSLSR_EL1, /* OS Lock Status Register */ DISR_EL1, /* Deferred Interrupt Status Register */ /* Performance Monitors Registers */ PMCR_EL0, /* Control Register */ PMSELR_EL0, /* Event Counter Selection Register */ PMEVCNTR0_EL0, /* Event Counter Register (0-30) */ PMEVCNTR30_EL0 = PMEVCNTR0_EL0 + 30, PMCCNTR_EL0, /* Cycle Counter Register */ PMEVTYPER0_EL0, /* Event Type Register (0-30) */ PMEVTYPER30_EL0 = PMEVTYPER0_EL0 + 30, PMCCFILTR_EL0, /* Cycle Count Filter Register */ PMCNTENSET_EL0, /* Count Enable Set Register */ PMINTENSET_EL1, /* Interrupt Enable Set Register */ PMOVSSET_EL0, /* Overflow Flag Status Set Register */ PMUSERENR_EL0, /* User Enable Register */ /* Pointer Authentication Registers in a strict increasing order. */ APIAKEYLO_EL1, APIAKEYHI_EL1, APIBKEYLO_EL1, APIBKEYHI_EL1, APDAKEYLO_EL1, APDAKEYHI_EL1, APDBKEYLO_EL1, APDBKEYHI_EL1, APGAKEYLO_EL1, APGAKEYHI_EL1, /* Memory Tagging Extension registers */ RGSR_EL1, /* Random Allocation Tag Seed Register */ GCR_EL1, /* Tag Control Register */ TFSRE0_EL1, /* Tag Fault Status Register (EL0) */ /* 32bit specific registers. */ DACR32_EL2, /* Domain Access Control Register */ IFSR32_EL2, /* Instruction Fault Status Register */ FPEXC32_EL2, /* Floating-Point Exception Control Register */ DBGVCR32_EL2, /* Debug Vector Catch Register */ /* EL2 registers */ SCTLR_EL2, /* System Control Register (EL2) */ ACTLR_EL2, /* Auxiliary Control Register (EL2) */ MDCR_EL2, /* Monitor Debug Configuration Register (EL2) */ CPTR_EL2, /* Architectural Feature Trap Register (EL2) */ HACR_EL2, /* Hypervisor Auxiliary Control Register */ ZCR_EL2, /* SVE Control Register (EL2) */ TTBR0_EL2, /* Translation Table Base Register 0 (EL2) */ TTBR1_EL2, /* Translation Table Base Register 1 (EL2) */ TCR_EL2, /* Translation Control Register (EL2) */ SPSR_EL2, /* EL2 saved program status register */ ELR_EL2, /* EL2 exception link register */ AFSR0_EL2, /* Auxiliary Fault Status Register 0 (EL2) */ AFSR1_EL2, /* Auxiliary Fault Status Register 1 (EL2) */ ESR_EL2, /* Exception Syndrome Register (EL2) */ FAR_EL2, /* Fault Address Register (EL2) */ HPFAR_EL2, /* Hypervisor IPA Fault Address Register */ MAIR_EL2, /* Memory Attribute Indirection Register (EL2) */ AMAIR_EL2, /* Auxiliary Memory Attribute Indirection Register (EL2) */ VBAR_EL2, /* Vector Base Address Register (EL2) */ RVBAR_EL2, /* Reset Vector Base Address Register */ CONTEXTIDR_EL2, /* Context ID Register (EL2) */ CNTHCTL_EL2, /* Counter-timer Hypervisor Control register */ SP_EL2, /* EL2 Stack Pointer */ CNTHP_CTL_EL2, CNTHP_CVAL_EL2, CNTHV_CTL_EL2, CNTHV_CVAL_EL2, __VNCR_START__, /* Any VNCR-capable reg goes after this point */ VNCR(SCTLR_EL1),/* System Control Register */ VNCR(ACTLR_EL1),/* Auxiliary Control Register */ VNCR(CPACR_EL1),/* Coprocessor Access Control */ VNCR(ZCR_EL1), /* SVE Control */ VNCR(TTBR0_EL1),/* Translation Table Base Register 0 */ VNCR(TTBR1_EL1),/* Translation Table Base Register 1 */ VNCR(TCR_EL1), /* Translation Control Register */ VNCR(TCR2_EL1), /* Extended Translation Control Register */ VNCR(ESR_EL1), /* Exception Syndrome Register */ VNCR(AFSR0_EL1),/* Auxiliary Fault Status Register 0 */ VNCR(AFSR1_EL1),/* Auxiliary Fault Status Register 1 */ VNCR(FAR_EL1), /* Fault Address Register */ VNCR(MAIR_EL1), /* Memory Attribute Indirection Register */ VNCR(VBAR_EL1), /* Vector Base Address Register */ VNCR(CONTEXTIDR_EL1), /* Context ID Register */ VNCR(AMAIR_EL1),/* Aux Memory Attribute Indirection Register */ VNCR(MDSCR_EL1),/* Monitor Debug System Control Register */ VNCR(ELR_EL1), VNCR(SP_EL1), VNCR(SPSR_EL1), VNCR(TFSR_EL1), /* Tag Fault Status Register (EL1) */ VNCR(VPIDR_EL2),/* Virtualization Processor ID Register */ VNCR(VMPIDR_EL2),/* Virtualization Multiprocessor ID Register */ VNCR(HCR_EL2), /* Hypervisor Configuration Register */ VNCR(HSTR_EL2), /* Hypervisor System Trap Register */ VNCR(VTTBR_EL2),/* Virtualization Translation Table Base Register */ VNCR(VTCR_EL2), /* Virtualization Translation Control Register */ VNCR(TPIDR_EL2),/* EL2 Software Thread ID Register */ VNCR(HCRX_EL2), /* Extended Hypervisor Configuration Register */ /* Permission Indirection Extension registers */ VNCR(PIR_EL1), /* Permission Indirection Register 1 (EL1) */ VNCR(PIRE0_EL1), /* Permission Indirection Register 0 (EL1) */ VNCR(HFGRTR_EL2), VNCR(HFGWTR_EL2), VNCR(HFGITR_EL2), VNCR(HDFGRTR_EL2), VNCR(HDFGWTR_EL2), VNCR(HAFGRTR_EL2), VNCR(CNTVOFF_EL2), VNCR(CNTV_CVAL_EL0), VNCR(CNTV_CTL_EL0), VNCR(CNTP_CVAL_EL0), VNCR(CNTP_CTL_EL0), NR_SYS_REGS /* Nothing after this line! */ }; struct kvm_sysreg_masks { struct { u64 res0; u64 res1; } mask[NR_SYS_REGS - __VNCR_START__]; }; struct kvm_cpu_context { struct user_pt_regs regs; /* sp = sp_el0 */ u64 spsr_abt; u64 spsr_und; u64 spsr_irq; u64 spsr_fiq; struct user_fpsimd_state fp_regs; u64 sys_regs[NR_SYS_REGS]; struct kvm_vcpu *__hyp_running_vcpu; /* This pointer has to be 4kB aligned. */ u64 *vncr_array; }; struct cpu_sve_state { __u64 zcr_el1; /* * Ordering is important since __sve_save_state/__sve_restore_state * relies on it. */ __u32 fpsr; __u32 fpcr; /* Must be SVE_VQ_BYTES (128 bit) aligned. */ __u8 sve_regs[]; }; /* * This structure is instantiated on a per-CPU basis, and contains * data that is: * * - tied to a single physical CPU, and * - either have a lifetime that does not extend past vcpu_put() * - or is an invariant for the lifetime of the system * * Use host_data_ptr(field) as a way to access a pointer to such a * field. */ struct kvm_host_data { struct kvm_cpu_context host_ctxt; /* * All pointers in this union are hyp VA. * sve_state is only used in pKVM and if system_supports_sve(). */ union { struct user_fpsimd_state *fpsimd_state; struct cpu_sve_state *sve_state; }; /* Ownership of the FP regs */ enum { FP_STATE_FREE, FP_STATE_HOST_OWNED, FP_STATE_GUEST_OWNED, } fp_owner; /* * host_debug_state contains the host registers which are * saved and restored during world switches. */ struct { /* {Break,watch}point registers */ struct kvm_guest_debug_arch regs; /* Statistical profiling extension */ u64 pmscr_el1; /* Self-hosted trace */ u64 trfcr_el1; /* Values of trap registers for the host before guest entry. */ u64 mdcr_el2; } host_debug_state; }; struct kvm_host_psci_config { /* PSCI version used by host. */ u32 version; u32 smccc_version; /* Function IDs used by host if version is v0.1. */ struct psci_0_1_function_ids function_ids_0_1; bool psci_0_1_cpu_suspend_implemented; bool psci_0_1_cpu_on_implemented; bool psci_0_1_cpu_off_implemented; bool psci_0_1_migrate_implemented; }; extern struct kvm_host_psci_config kvm_nvhe_sym(kvm_host_psci_config); #define kvm_host_psci_config CHOOSE_NVHE_SYM(kvm_host_psci_config) extern s64 kvm_nvhe_sym(hyp_physvirt_offset); #define hyp_physvirt_offset CHOOSE_NVHE_SYM(hyp_physvirt_offset) extern u64 kvm_nvhe_sym(hyp_cpu_logical_map)[NR_CPUS]; #define hyp_cpu_logical_map CHOOSE_NVHE_SYM(hyp_cpu_logical_map) struct vcpu_reset_state { unsigned long pc; unsigned long r0; bool be; bool reset; }; struct kvm_vcpu_arch { struct kvm_cpu_context ctxt; /* * Guest floating point state * * The architecture has two main floating point extensions, * the original FPSIMD and SVE. These have overlapping * register views, with the FPSIMD V registers occupying the * low 128 bits of the SVE Z registers. When the core * floating point code saves the register state of a task it * records which view it saved in fp_type. */ void *sve_state; enum fp_type fp_type; unsigned int sve_max_vl; u64 svcr; u64 fpmr; /* Stage 2 paging state used by the hardware on next switch */ struct kvm_s2_mmu *hw_mmu; /* Values of trap registers for the guest. */ u64 hcr_el2; u64 hcrx_el2; u64 mdcr_el2; u64 cptr_el2; /* Exception Information */ struct kvm_vcpu_fault_info fault; /* Configuration flags, set once and for all before the vcpu can run */ u8 cflags; /* Input flags to the hypervisor code, potentially cleared after use */ u8 iflags; /* State flags for kernel bookkeeping, unused by the hypervisor code */ u8 sflags; /* * Don't run the guest (internal implementation need). * * Contrary to the flags above, this is set/cleared outside of * a vcpu context, and thus cannot be mixed with the flags * themselves (or the flag accesses need to be made atomic). */ bool pause; /* * We maintain more than a single set of debug registers to support * debugging the guest from the host and to maintain separate host and * guest state during world switches. vcpu_debug_state are the debug * registers of the vcpu as the guest sees them. * * external_debug_state contains the debug values we want to debug the * guest. This is set via the KVM_SET_GUEST_DEBUG ioctl. * * debug_ptr points to the set of debug registers that should be loaded * onto the hardware when running the guest. */ struct kvm_guest_debug_arch *debug_ptr; struct kvm_guest_debug_arch vcpu_debug_state; struct kvm_guest_debug_arch external_debug_state; /* VGIC state */ struct vgic_cpu vgic_cpu; struct arch_timer_cpu timer_cpu; struct kvm_pmu pmu; /* * Guest registers we preserve during guest debugging. * * These shadow registers are updated by the kvm_handle_sys_reg * trap handler if the guest accesses or updates them while we * are using guest debug. */ struct { u32 mdscr_el1; bool pstate_ss; } guest_debug_preserved; /* vcpu power state */ struct kvm_mp_state mp_state; spinlock_t mp_state_lock; /* Cache some mmu pages needed inside spinlock regions */ struct kvm_mmu_memory_cache mmu_page_cache; /* Virtual SError ESR to restore when HCR_EL2.VSE is set */ u64 vsesr_el2; /* Additional reset state */ struct vcpu_reset_state reset_state; /* Guest PV state */ struct { u64 last_steal; gpa_t base; } steal; /* Per-vcpu CCSIDR override or NULL */ u32 *ccsidr; }; /* * Each 'flag' is composed of a comma-separated triplet: * * - the flag-set it belongs to in the vcpu->arch structure * - the value for that flag * - the mask for that flag * * __vcpu_single_flag() builds such a triplet for a single-bit flag. * unpack_vcpu_flag() extract the flag value from the triplet for * direct use outside of the flag accessors. */ #define __vcpu_single_flag(_set, _f) _set, (_f), (_f) #define __unpack_flag(_set, _f, _m) _f #define unpack_vcpu_flag(...) __unpack_flag(__VA_ARGS__) #define __build_check_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *_fset; \ \ /* Check that the flags fit in the mask */ \ BUILD_BUG_ON(HWEIGHT(m) != HWEIGHT((f) | (m))); \ /* Check that the flags fit in the type */ \ BUILD_BUG_ON((sizeof(*_fset) * 8) <= __fls(m)); \ } while (0) #define __vcpu_get_flag(v, flagset, f, m) \ ({ \ __build_check_flag(v, flagset, f, m); \ \ READ_ONCE(v->arch.flagset) & (m); \ }) /* * Note that the set/clear accessors must be preempt-safe in order to * avoid nesting them with load/put which also manipulate flags... */ #ifdef __KVM_NVHE_HYPERVISOR__ /* the nVHE hypervisor is always non-preemptible */ #define __vcpu_flags_preempt_disable() #define __vcpu_flags_preempt_enable() #else #define __vcpu_flags_preempt_disable() preempt_disable() #define __vcpu_flags_preempt_enable() preempt_enable() #endif #define __vcpu_set_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *fset; \ \ __build_check_flag(v, flagset, f, m); \ \ fset = &v->arch.flagset; \ __vcpu_flags_preempt_disable(); \ if (HWEIGHT(m) > 1) \ *fset &= ~(m); \ *fset |= (f); \ __vcpu_flags_preempt_enable(); \ } while (0) #define __vcpu_clear_flag(v, flagset, f, m) \ do { \ typeof(v->arch.flagset) *fset; \ \ __build_check_flag(v, flagset, f, m); \ \ fset = &v->arch.flagset; \ __vcpu_flags_preempt_disable(); \ *fset &= ~(m); \ __vcpu_flags_preempt_enable(); \ } while (0) #define vcpu_get_flag(v, ...) __vcpu_get_flag((v), __VA_ARGS__) #define vcpu_set_flag(v, ...) __vcpu_set_flag((v), __VA_ARGS__) #define vcpu_clear_flag(v, ...) __vcpu_clear_flag((v), __VA_ARGS__) /* SVE exposed to guest */ #define GUEST_HAS_SVE __vcpu_single_flag(cflags, BIT(0)) /* SVE config completed */ #define VCPU_SVE_FINALIZED __vcpu_single_flag(cflags, BIT(1)) /* PTRAUTH exposed to guest */ #define GUEST_HAS_PTRAUTH __vcpu_single_flag(cflags, BIT(2)) /* KVM_ARM_VCPU_INIT completed */ #define VCPU_INITIALIZED __vcpu_single_flag(cflags, BIT(3)) /* Exception pending */ #define PENDING_EXCEPTION __vcpu_single_flag(iflags, BIT(0)) /* * PC increment. Overlaps with EXCEPT_MASK on purpose so that it can't * be set together with an exception... */ #define INCREMENT_PC __vcpu_single_flag(iflags, BIT(1)) /* Target EL/MODE (not a single flag, but let's abuse the macro) */ #define EXCEPT_MASK __vcpu_single_flag(iflags, GENMASK(3, 1)) /* Helpers to encode exceptions with minimum fuss */ #define __EXCEPT_MASK_VAL unpack_vcpu_flag(EXCEPT_MASK) #define __EXCEPT_SHIFT __builtin_ctzl(__EXCEPT_MASK_VAL) #define __vcpu_except_flags(_f) iflags, (_f << __EXCEPT_SHIFT), __EXCEPT_MASK_VAL /* * When PENDING_EXCEPTION is set, EXCEPT_MASK can take the following * values: * * For AArch32 EL1: */ #define EXCEPT_AA32_UND __vcpu_except_flags(0) #define EXCEPT_AA32_IABT __vcpu_except_flags(1) #define EXCEPT_AA32_DABT __vcpu_except_flags(2) /* For AArch64: */ #define EXCEPT_AA64_EL1_SYNC __vcpu_except_flags(0) #define EXCEPT_AA64_EL1_IRQ __vcpu_except_flags(1) #define EXCEPT_AA64_EL1_FIQ __vcpu_except_flags(2) #define EXCEPT_AA64_EL1_SERR __vcpu_except_flags(3) /* For AArch64 with NV: */ #define EXCEPT_AA64_EL2_SYNC __vcpu_except_flags(4) #define EXCEPT_AA64_EL2_IRQ __vcpu_except_flags(5) #define EXCEPT_AA64_EL2_FIQ __vcpu_except_flags(6) #define EXCEPT_AA64_EL2_SERR __vcpu_except_flags(7) /* Guest debug is live */ #define DEBUG_DIRTY __vcpu_single_flag(iflags, BIT(4)) /* Save SPE context if active */ #define DEBUG_STATE_SAVE_SPE __vcpu_single_flag(iflags, BIT(5)) /* Save TRBE context if active */ #define DEBUG_STATE_SAVE_TRBE __vcpu_single_flag(iflags, BIT(6)) /* SVE enabled for host EL0 */ #define HOST_SVE_ENABLED __vcpu_single_flag(sflags, BIT(0)) /* SME enabled for EL0 */ #define HOST_SME_ENABLED __vcpu_single_flag(sflags, BIT(1)) /* Physical CPU not in supported_cpus */ #define ON_UNSUPPORTED_CPU __vcpu_single_flag(sflags, BIT(2)) /* WFIT instruction trapped */ #define IN_WFIT __vcpu_single_flag(sflags, BIT(3)) /* vcpu system registers loaded on physical CPU */ #define SYSREGS_ON_CPU __vcpu_single_flag(sflags, BIT(4)) /* Software step state is Active-pending */ #define DBG_SS_ACTIVE_PENDING __vcpu_single_flag(sflags, BIT(5)) /* PMUSERENR for the guest EL0 is on physical CPU */ #define PMUSERENR_ON_CPU __vcpu_single_flag(sflags, BIT(6)) /* WFI instruction trapped */ #define IN_WFI __vcpu_single_flag(sflags, BIT(7)) /* Pointer to the vcpu's SVE FFR for sve_{save,load}_state() */ #define vcpu_sve_pffr(vcpu) (kern_hyp_va((vcpu)->arch.sve_state) + \ sve_ffr_offset((vcpu)->arch.sve_max_vl)) #define vcpu_sve_max_vq(vcpu) sve_vq_from_vl((vcpu)->arch.sve_max_vl) #define vcpu_sve_zcr_elx(vcpu) \ (unlikely(is_hyp_ctxt(vcpu)) ? ZCR_EL2 : ZCR_EL1) #define vcpu_sve_state_size(vcpu) ({ \ size_t __size_ret; \ unsigned int __vcpu_vq; \ \ if (WARN_ON(!sve_vl_valid((vcpu)->arch.sve_max_vl))) { \ __size_ret = 0; \ } else { \ __vcpu_vq = vcpu_sve_max_vq(vcpu); \ __size_ret = SVE_SIG_REGS_SIZE(__vcpu_vq); \ } \ \ __size_ret; \ }) #define KVM_GUESTDBG_VALID_MASK (KVM_GUESTDBG_ENABLE | \ KVM_GUESTDBG_USE_SW_BP | \ KVM_GUESTDBG_USE_HW | \ KVM_GUESTDBG_SINGLESTEP) #define vcpu_has_sve(vcpu) (system_supports_sve() && \ vcpu_get_flag(vcpu, GUEST_HAS_SVE)) #ifdef CONFIG_ARM64_PTR_AUTH #define vcpu_has_ptrauth(vcpu) \ ((cpus_have_final_cap(ARM64_HAS_ADDRESS_AUTH) || \ cpus_have_final_cap(ARM64_HAS_GENERIC_AUTH)) && \ vcpu_get_flag(vcpu, GUEST_HAS_PTRAUTH)) #else #define vcpu_has_ptrauth(vcpu) false #endif #define vcpu_on_unsupported_cpu(vcpu) \ vcpu_get_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_set_on_unsupported_cpu(vcpu) \ vcpu_set_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_clear_on_unsupported_cpu(vcpu) \ vcpu_clear_flag(vcpu, ON_UNSUPPORTED_CPU) #define vcpu_gp_regs(v) (&(v)->arch.ctxt.regs) /* * Only use __vcpu_sys_reg/ctxt_sys_reg if you know you want the * memory backed version of a register, and not the one most recently * accessed by a running VCPU. For example, for userspace access or * for system registers that are never context switched, but only * emulated. * * Don't bother with VNCR-based accesses in the nVHE code, it has no * business dealing with NV. */ static inline u64 *___ctxt_sys_reg(const struct kvm_cpu_context *ctxt, int r) { #if !defined (__KVM_NVHE_HYPERVISOR__) if (unlikely(cpus_have_final_cap(ARM64_HAS_NESTED_VIRT) && r >= __VNCR_START__ && ctxt->vncr_array)) return &ctxt->vncr_array[r - __VNCR_START__]; #endif return (u64 *)&ctxt->sys_regs[r]; } #define __ctxt_sys_reg(c,r) \ ({ \ BUILD_BUG_ON(__builtin_constant_p(r) && \ (r) >= NR_SYS_REGS); \ ___ctxt_sys_reg(c, r); \ }) #define ctxt_sys_reg(c,r) (*__ctxt_sys_reg(c,r)) u64 kvm_vcpu_sanitise_vncr_reg(const struct kvm_vcpu *, enum vcpu_sysreg); #define __vcpu_sys_reg(v,r) \ (*({ \ const struct kvm_cpu_context *ctxt = &(v)->arch.ctxt; \ u64 *__r = __ctxt_sys_reg(ctxt, (r)); \ if (vcpu_has_nv((v)) && (r) >= __VNCR_START__) \ *__r = kvm_vcpu_sanitise_vncr_reg((v), (r)); \ __r; \ })) u64 vcpu_read_sys_reg(const struct kvm_vcpu *vcpu, int reg); void vcpu_write_sys_reg(struct kvm_vcpu *vcpu, u64 val, int reg); static inline bool __vcpu_read_sys_reg_from_cpu(int reg, u64 *val) { /* * *** VHE ONLY *** * * System registers listed in the switch are not saved on every * exit from the guest but are only saved on vcpu_put. * * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but * should never be listed below, because the guest cannot modify its * own MPIDR_EL1 and MPIDR_EL1 is accessed for VCPU A from VCPU B's * thread when emulating cross-VCPU communication. */ if (!has_vhe()) return false; switch (reg) { case SCTLR_EL1: *val = read_sysreg_s(SYS_SCTLR_EL12); break; case CPACR_EL1: *val = read_sysreg_s(SYS_CPACR_EL12); break; case TTBR0_EL1: *val = read_sysreg_s(SYS_TTBR0_EL12); break; case TTBR1_EL1: *val = read_sysreg_s(SYS_TTBR1_EL12); break; case TCR_EL1: *val = read_sysreg_s(SYS_TCR_EL12); break; case ESR_EL1: *val = read_sysreg_s(SYS_ESR_EL12); break; case AFSR0_EL1: *val = read_sysreg_s(SYS_AFSR0_EL12); break; case AFSR1_EL1: *val = read_sysreg_s(SYS_AFSR1_EL12); break; case FAR_EL1: *val = read_sysreg_s(SYS_FAR_EL12); break; case MAIR_EL1: *val = read_sysreg_s(SYS_MAIR_EL12); break; case VBAR_EL1: *val = read_sysreg_s(SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: *val = read_sysreg_s(SYS_CONTEXTIDR_EL12);break; case TPIDR_EL0: *val = read_sysreg_s(SYS_TPIDR_EL0); break; case TPIDRRO_EL0: *val = read_sysreg_s(SYS_TPIDRRO_EL0); break; case TPIDR_EL1: *val = read_sysreg_s(SYS_TPIDR_EL1); break; case AMAIR_EL1: *val = read_sysreg_s(SYS_AMAIR_EL12); break; case CNTKCTL_EL1: *val = read_sysreg_s(SYS_CNTKCTL_EL12); break; case ELR_EL1: *val = read_sysreg_s(SYS_ELR_EL12); break; case SPSR_EL1: *val = read_sysreg_s(SYS_SPSR_EL12); break; case PAR_EL1: *val = read_sysreg_par(); break; case DACR32_EL2: *val = read_sysreg_s(SYS_DACR32_EL2); break; case IFSR32_EL2: *val = read_sysreg_s(SYS_IFSR32_EL2); break; case DBGVCR32_EL2: *val = read_sysreg_s(SYS_DBGVCR32_EL2); break; case ZCR_EL1: *val = read_sysreg_s(SYS_ZCR_EL12); break; default: return false; } return true; } static inline bool __vcpu_write_sys_reg_to_cpu(u64 val, int reg) { /* * *** VHE ONLY *** * * System registers listed in the switch are not restored on every * entry to the guest but are only restored on vcpu_load. * * Note that MPIDR_EL1 for the guest is set by KVM via VMPIDR_EL2 but * should never be listed below, because the MPIDR should only be set * once, before running the VCPU, and never changed later. */ if (!has_vhe()) return false; switch (reg) { case SCTLR_EL1: write_sysreg_s(val, SYS_SCTLR_EL12); break; case CPACR_EL1: write_sysreg_s(val, SYS_CPACR_EL12); break; case TTBR0_EL1: write_sysreg_s(val, SYS_TTBR0_EL12); break; case TTBR1_EL1: write_sysreg_s(val, SYS_TTBR1_EL12); break; case TCR_EL1: write_sysreg_s(val, SYS_TCR_EL12); break; case ESR_EL1: write_sysreg_s(val, SYS_ESR_EL12); break; case AFSR0_EL1: write_sysreg_s(val, SYS_AFSR0_EL12); break; case AFSR1_EL1: write_sysreg_s(val, SYS_AFSR1_EL12); break; case FAR_EL1: write_sysreg_s(val, SYS_FAR_EL12); break; case MAIR_EL1: write_sysreg_s(val, SYS_MAIR_EL12); break; case VBAR_EL1: write_sysreg_s(val, SYS_VBAR_EL12); break; case CONTEXTIDR_EL1: write_sysreg_s(val, SYS_CONTEXTIDR_EL12);break; case TPIDR_EL0: write_sysreg_s(val, SYS_TPIDR_EL0); break; case TPIDRRO_EL0: write_sysreg_s(val, SYS_TPIDRRO_EL0); break; case TPIDR_EL1: write_sysreg_s(val, SYS_TPIDR_EL1); break; case AMAIR_EL1: write_sysreg_s(val, SYS_AMAIR_EL12); break; case CNTKCTL_EL1: write_sysreg_s(val, SYS_CNTKCTL_EL12); break; case ELR_EL1: write_sysreg_s(val, SYS_ELR_EL12); break; case SPSR_EL1: write_sysreg_s(val, SYS_SPSR_EL12); break; case PAR_EL1: write_sysreg_s(val, SYS_PAR_EL1); break; case DACR32_EL2: write_sysreg_s(val, SYS_DACR32_EL2); break; case IFSR32_EL2: write_sysreg_s(val, SYS_IFSR32_EL2); break; case DBGVCR32_EL2: write_sysreg_s(val, SYS_DBGVCR32_EL2); break; case ZCR_EL1: write_sysreg_s(val, SYS_ZCR_EL12); break; default: return false; } return true; } struct kvm_vm_stat { struct kvm_vm_stat_generic generic; }; struct kvm_vcpu_stat { struct kvm_vcpu_stat_generic generic; u64 hvc_exit_stat; u64 wfe_exit_stat; u64 wfi_exit_stat; u64 mmio_exit_user; u64 mmio_exit_kernel; u64 signal_exits; u64 exits; }; unsigned long kvm_arm_num_regs(struct kvm_vcpu *vcpu); int kvm_arm_copy_reg_indices(struct kvm_vcpu *vcpu, u64 __user *indices); int kvm_arm_get_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); int kvm_arm_set_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg); unsigned long kvm_arm_num_sys_reg_descs(struct kvm_vcpu *vcpu); int kvm_arm_copy_sys_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices); int __kvm_arm_vcpu_get_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); int __kvm_arm_vcpu_set_events(struct kvm_vcpu *vcpu, struct kvm_vcpu_events *events); void kvm_arm_halt_guest(struct kvm *kvm); void kvm_arm_resume_guest(struct kvm *kvm); #define vcpu_has_run_once(vcpu) !!rcu_access_pointer((vcpu)->pid) #ifndef __KVM_NVHE_HYPERVISOR__ #define kvm_call_hyp_nvhe(f, ...) \ ({ \ struct arm_smccc_res res; \ \ arm_smccc_1_1_hvc(KVM_HOST_SMCCC_FUNC(f), \ ##__VA_ARGS__, &res); \ WARN_ON(res.a0 != SMCCC_RET_SUCCESS); \ \ res.a1; \ }) /* * The couple of isb() below are there to guarantee the same behaviour * on VHE as on !VHE, where the eret to EL1 acts as a context * synchronization event. */ #define kvm_call_hyp(f, ...) \ do { \ if (has_vhe()) { \ f(__VA_ARGS__); \ isb(); \ } else { \ kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ } while(0) #define kvm_call_hyp_ret(f, ...) \ ({ \ typeof(f(__VA_ARGS__)) ret; \ \ if (has_vhe()) { \ ret = f(__VA_ARGS__); \ isb(); \ } else { \ ret = kvm_call_hyp_nvhe(f, ##__VA_ARGS__); \ } \ \ ret; \ }) #else /* __KVM_NVHE_HYPERVISOR__ */ #define kvm_call_hyp(f, ...) f(__VA_ARGS__) #define kvm_call_hyp_ret(f, ...) f(__VA_ARGS__) #define kvm_call_hyp_nvhe(f, ...) f(__VA_ARGS__) #endif /* __KVM_NVHE_HYPERVISOR__ */ int handle_exit(struct kvm_vcpu *vcpu, int exception_index); void handle_exit_early(struct kvm_vcpu *vcpu, int exception_index); int kvm_handle_cp14_load_store(struct kvm_vcpu *vcpu); int kvm_handle_cp14_32(struct kvm_vcpu *vcpu); int kvm_handle_cp14_64(struct kvm_vcpu *vcpu); int kvm_handle_cp15_32(struct kvm_vcpu *vcpu); int kvm_handle_cp15_64(struct kvm_vcpu *vcpu); int kvm_handle_sys_reg(struct kvm_vcpu *vcpu); int kvm_handle_cp10_id(struct kvm_vcpu *vcpu); void kvm_sys_regs_create_debugfs(struct kvm *kvm); void kvm_reset_sys_regs(struct kvm_vcpu *vcpu); int __init kvm_sys_reg_table_init(void); struct sys_reg_desc; int __init populate_sysreg_config(const struct sys_reg_desc *sr, unsigned int idx); int __init populate_nv_trap_config(void); bool lock_all_vcpus(struct kvm *kvm); void unlock_all_vcpus(struct kvm *kvm); void kvm_calculate_traps(struct kvm_vcpu *vcpu); /* MMIO helpers */ void kvm_mmio_write_buf(void *buf, unsigned int len, unsigned long data); unsigned long kvm_mmio_read_buf(const void *buf, unsigned int len); int kvm_handle_mmio_return(struct kvm_vcpu *vcpu); int io_mem_abort(struct kvm_vcpu *vcpu, phys_addr_t fault_ipa); /* * Returns true if a Performance Monitoring Interrupt (PMI), a.k.a. perf event, * arrived in guest context. For arm64, any event that arrives while a vCPU is * loaded is considered to be "in guest". */ static inline bool kvm_arch_pmi_in_guest(struct kvm_vcpu *vcpu) { return IS_ENABLED(CONFIG_GUEST_PERF_EVENTS) && !!vcpu; } long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu); gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu); void kvm_update_stolen_time(struct kvm_vcpu *vcpu); bool kvm_arm_pvtime_supported(void); int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); extern unsigned int __ro_after_init kvm_arm_vmid_bits; int __init kvm_arm_vmid_alloc_init(void); void __init kvm_arm_vmid_alloc_free(void); bool kvm_arm_vmid_update(struct kvm_vmid *kvm_vmid); void kvm_arm_vmid_clear_active(void); static inline void kvm_arm_pvtime_vcpu_init(struct kvm_vcpu_arch *vcpu_arch) { vcpu_arch->steal.base = INVALID_GPA; } static inline bool kvm_arm_is_pvtime_enabled(struct kvm_vcpu_arch *vcpu_arch) { return (vcpu_arch->steal.base != INVALID_GPA); } void kvm_set_sei_esr(struct kvm_vcpu *vcpu, u64 syndrome); struct kvm_vcpu *kvm_mpidr_to_vcpu(struct kvm *kvm, unsigned long mpidr); DECLARE_KVM_HYP_PER_CPU(struct kvm_host_data, kvm_host_data); /* * How we access per-CPU host data depends on the where we access it from, * and the mode we're in: * * - VHE and nVHE hypervisor bits use their locally defined instance * * - the rest of the kernel use either the VHE or nVHE one, depending on * the mode we're running in. * * Unless we're in protected mode, fully deprivileged, and the nVHE * per-CPU stuff is exclusively accessible to the protected EL2 code. * In this case, the EL1 code uses the *VHE* data as its private state * (which makes sense in a way as there shouldn't be any shared state * between the host and the hypervisor). * * Yes, this is all totally trivial. Shoot me now. */ #if defined(__KVM_NVHE_HYPERVISOR__) || defined(__KVM_VHE_HYPERVISOR__) #define host_data_ptr(f) (&this_cpu_ptr(&kvm_host_data)->f) #else #define host_data_ptr(f) \ (static_branch_unlikely(&kvm_protected_mode_initialized) ? \ &this_cpu_ptr(&kvm_host_data)->f : \ &this_cpu_ptr_hyp_sym(kvm_host_data)->f) #endif /* Check whether the FP regs are owned by the guest */ static inline bool guest_owns_fp_regs(void) { return *host_data_ptr(fp_owner) == FP_STATE_GUEST_OWNED; } /* Check whether the FP regs are owned by the host */ static inline bool host_owns_fp_regs(void) { return *host_data_ptr(fp_owner) == FP_STATE_HOST_OWNED; } static inline void kvm_init_host_cpu_context(struct kvm_cpu_context *cpu_ctxt) { /* The host's MPIDR is immutable, so let's set it up at boot time */ ctxt_sys_reg(cpu_ctxt, MPIDR_EL1) = read_cpuid_mpidr(); } static inline bool kvm_system_needs_idmapped_vectors(void) { return cpus_have_final_cap(ARM64_SPECTRE_V3A); } static inline void kvm_arch_sync_events(struct kvm *kvm) {} static inline void kvm_arch_sched_in(struct kvm_vcpu *vcpu, int cpu) {} void kvm_arm_init_debug(void); void kvm_arm_vcpu_init_debug(struct kvm_vcpu *vcpu); void kvm_arm_setup_debug(struct kvm_vcpu *vcpu); void kvm_arm_clear_debug(struct kvm_vcpu *vcpu); void kvm_arm_reset_debug_ptr(struct kvm_vcpu *vcpu); #define kvm_vcpu_os_lock_enabled(vcpu) \ (!!(__vcpu_sys_reg(vcpu, OSLSR_EL1) & OSLSR_EL1_OSLK)) int kvm_arm_vcpu_arch_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_arm_vcpu_arch_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr); int kvm_vm_ioctl_mte_copy_tags(struct kvm *kvm, struct kvm_arm_copy_mte_tags *copy_tags); int kvm_vm_ioctl_set_counter_offset(struct kvm *kvm, struct kvm_arm_counter_offset *offset); int kvm_vm_ioctl_get_reg_writable_masks(struct kvm *kvm, struct reg_mask_range *range); /* Guest/host FPSIMD coordination helpers */ int kvm_arch_vcpu_run_map_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_load_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxflush_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_ctxsync_fp(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_fp(struct kvm_vcpu *vcpu); static inline bool kvm_pmu_counter_deferred(struct perf_event_attr *attr) { return (!has_vhe() && attr->exclude_host); } /* Flags for host debug state */ void kvm_arch_vcpu_load_debug_state_flags(struct kvm_vcpu *vcpu); void kvm_arch_vcpu_put_debug_state_flags(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr); void kvm_clr_pmu_events(u32 clr); bool kvm_set_pmuserenr(u64 val); #else static inline void kvm_set_pmu_events(u32 set, struct perf_event_attr *attr) {} static inline void kvm_clr_pmu_events(u32 clr) {} static inline bool kvm_set_pmuserenr(u64 val) { return false; } #endif void kvm_vcpu_load_vhe(struct kvm_vcpu *vcpu); void kvm_vcpu_put_vhe(struct kvm_vcpu *vcpu); int __init kvm_set_ipa_limit(void); u32 kvm_get_pa_bits(struct kvm *kvm); #define __KVM_HAVE_ARCH_VM_ALLOC struct kvm *kvm_arch_alloc_vm(void); #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS #define __KVM_HAVE_ARCH_FLUSH_REMOTE_TLBS_RANGE #define kvm_vm_is_protected(kvm) (is_protected_kvm_enabled() && (kvm)->arch.pkvm.enabled) #define vcpu_is_protected(vcpu) kvm_vm_is_protected((vcpu)->kvm) int kvm_arm_vcpu_finalize(struct kvm_vcpu *vcpu, int feature); bool kvm_arm_vcpu_is_finalized(struct kvm_vcpu *vcpu); #define kvm_arm_vcpu_sve_finalized(vcpu) vcpu_get_flag(vcpu, VCPU_SVE_FINALIZED) #define kvm_has_mte(kvm) \ (system_supports_mte() && \ test_bit(KVM_ARCH_FLAG_MTE_ENABLED, &(kvm)->arch.flags)) #define kvm_supports_32bit_el0() \ (system_supports_32bit_el0() && \ !static_branch_unlikely(&arm64_mismatched_32bit_el0)) #define kvm_vm_has_ran_once(kvm) \ (test_bit(KVM_ARCH_FLAG_HAS_RAN_ONCE, &(kvm)->arch.flags)) static inline bool __vcpu_has_feature(const struct kvm_arch *ka, int feature) { return test_bit(feature, ka->vcpu_features); } #define vcpu_has_feature(v, f) __vcpu_has_feature(&(v)->kvm->arch, (f)) #define kvm_vcpu_initialized(v) vcpu_get_flag(vcpu, VCPU_INITIALIZED) int kvm_trng_call(struct kvm_vcpu *vcpu); #ifdef CONFIG_KVM extern phys_addr_t hyp_mem_base; extern phys_addr_t hyp_mem_size; void __init kvm_hyp_reserve(void); #else static inline void kvm_hyp_reserve(void) { } #endif void kvm_arm_vcpu_power_off(struct kvm_vcpu *vcpu); bool kvm_arm_vcpu_stopped(struct kvm_vcpu *vcpu); static inline u64 *__vm_id_reg(struct kvm_arch *ka, u32 reg) { switch (reg) { case sys_reg(3, 0, 0, 1, 0) ... sys_reg(3, 0, 0, 7, 7): return &ka->id_regs[IDREG_IDX(reg)]; case SYS_CTR_EL0: return &ka->ctr_el0; default: WARN_ON_ONCE(1); return NULL; } } #define kvm_read_vm_id_reg(kvm, reg) \ ({ u64 __val = *__vm_id_reg(&(kvm)->arch, reg); __val; }) void kvm_set_vm_id_reg(struct kvm *kvm, u32 reg, u64 val); #define __expand_field_sign_unsigned(id, fld, val) \ ((u64)SYS_FIELD_VALUE(id, fld, val)) #define __expand_field_sign_signed(id, fld, val) \ ({ \ u64 __val = SYS_FIELD_VALUE(id, fld, val); \ sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) #define expand_field_sign(id, fld, val) \ (id##_##fld##_SIGNED ? \ __expand_field_sign_signed(id, fld, val) : \ __expand_field_sign_unsigned(id, fld, val)) #define get_idreg_field_unsigned(kvm, id, fld) \ ({ \ u64 __val = kvm_read_vm_id_reg((kvm), SYS_##id); \ FIELD_GET(id##_##fld##_MASK, __val); \ }) #define get_idreg_field_signed(kvm, id, fld) \ ({ \ u64 __val = get_idreg_field_unsigned(kvm, id, fld); \ sign_extend64(__val, id##_##fld##_WIDTH - 1); \ }) #define get_idreg_field_enum(kvm, id, fld) \ get_idreg_field_unsigned(kvm, id, fld) #define get_idreg_field(kvm, id, fld) \ (id##_##fld##_SIGNED ? \ get_idreg_field_signed(kvm, id, fld) : \ get_idreg_field_unsigned(kvm, id, fld)) #define kvm_has_feat(kvm, id, fld, limit) \ (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, limit)) #define kvm_has_feat_enum(kvm, id, fld, val) \ (get_idreg_field_unsigned((kvm), id, fld) == __expand_field_sign_unsigned(id, fld, val)) #define kvm_has_feat_range(kvm, id, fld, min, max) \ (get_idreg_field((kvm), id, fld) >= expand_field_sign(id, fld, min) && \ get_idreg_field((kvm), id, fld) <= expand_field_sign(id, fld, max)) /* Check for a given level of PAuth support */ #define kvm_has_pauth(k, l) \ ({ \ bool pa, pi, pa3; \ \ pa = kvm_has_feat((k), ID_AA64ISAR1_EL1, APA, l); \ pa &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPA, IMP); \ pi = kvm_has_feat((k), ID_AA64ISAR1_EL1, API, l); \ pi &= kvm_has_feat((k), ID_AA64ISAR1_EL1, GPI, IMP); \ pa3 = kvm_has_feat((k), ID_AA64ISAR2_EL1, APA3, l); \ pa3 &= kvm_has_feat((k), ID_AA64ISAR2_EL1, GPA3, IMP); \ \ (pa + pi + pa3) == 1; \ }) #endif /* __ARM64_KVM_HOST_H__ */ |
| 408 177 177 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Based on arch/arm/include/asm/memory.h * * Copyright (C) 2000-2002 Russell King * Copyright (C) 2012 ARM Ltd. * * Note: this file should not be included by non-asm/.h files */ #ifndef __ASM_MEMORY_H #define __ASM_MEMORY_H #include <linux/const.h> #include <linux/sizes.h> #include <asm/page-def.h> /* * Size of the PCI I/O space. This must remain a power of two so that * IO_SPACE_LIMIT acts as a mask for the low bits of I/O addresses. */ #define PCI_IO_SIZE SZ_16M /* * VMEMMAP_SIZE - allows the whole linear region to be covered by * a struct page array * * If we are configured with a 52-bit kernel VA then our VMEMMAP_SIZE * needs to cover the memory region from the beginning of the 52-bit * PAGE_OFFSET all the way to PAGE_END for 48-bit. This allows us to * keep a constant PAGE_OFFSET and "fallback" to using the higher end * of the VMEMMAP where 52-bit support is not available in hardware. */ #define VMEMMAP_RANGE (_PAGE_END(VA_BITS_MIN) - PAGE_OFFSET) #define VMEMMAP_SIZE ((VMEMMAP_RANGE >> PAGE_SHIFT) * sizeof(struct page)) /* * PAGE_OFFSET - the virtual address of the start of the linear map, at the * start of the TTBR1 address space. * PAGE_END - the end of the linear map, where all other kernel mappings begin. * KIMAGE_VADDR - the virtual address of the start of the kernel image. * VA_BITS - the maximum number of bits for virtual addresses. */ #define VA_BITS (CONFIG_ARM64_VA_BITS) #define _PAGE_OFFSET(va) (-(UL(1) << (va))) #define PAGE_OFFSET (_PAGE_OFFSET(VA_BITS)) #define KIMAGE_VADDR (MODULES_END) #define MODULES_END (MODULES_VADDR + MODULES_VSIZE) #define MODULES_VADDR (_PAGE_END(VA_BITS_MIN)) #define MODULES_VSIZE (SZ_2G) #define VMEMMAP_START (VMEMMAP_END - VMEMMAP_SIZE) #define VMEMMAP_END (-UL(SZ_1G)) #define PCI_IO_START (VMEMMAP_END + SZ_8M) #define PCI_IO_END (PCI_IO_START + PCI_IO_SIZE) #define FIXADDR_TOP (-UL(SZ_8M)) #if VA_BITS > 48 #ifdef CONFIG_ARM64_16K_PAGES #define VA_BITS_MIN (47) #else #define VA_BITS_MIN (48) #endif #else #define VA_BITS_MIN (VA_BITS) #endif #define _PAGE_END(va) (-(UL(1) << ((va) - 1))) #define KERNEL_START _text #define KERNEL_END _end /* * Generic and Software Tag-Based KASAN modes require 1/8th and 1/16th of the * kernel virtual address space for storing the shadow memory respectively. * * The mapping between a virtual memory address and its corresponding shadow * memory address is defined based on the formula: * * shadow_addr = (addr >> KASAN_SHADOW_SCALE_SHIFT) + KASAN_SHADOW_OFFSET * * where KASAN_SHADOW_SCALE_SHIFT is the order of the number of bits that map * to a single shadow byte and KASAN_SHADOW_OFFSET is a constant that offsets * the mapping. Note that KASAN_SHADOW_OFFSET does not point to the start of * the shadow memory region. * * Based on this mapping, we define two constants: * * KASAN_SHADOW_START: the start of the shadow memory region; * KASAN_SHADOW_END: the end of the shadow memory region. * * KASAN_SHADOW_END is defined first as the shadow address that corresponds to * the upper bound of possible virtual kernel memory addresses UL(1) << 64 * according to the mapping formula. * * KASAN_SHADOW_START is defined second based on KASAN_SHADOW_END. The shadow * memory start must map to the lowest possible kernel virtual memory address * and thus it depends on the actual bitness of the address space. * * As KASAN inserts redzones between stack variables, this increases the stack * memory usage significantly. Thus, we double the (minimum) stack size. */ #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS) #define KASAN_SHADOW_OFFSET _AC(CONFIG_KASAN_SHADOW_OFFSET, UL) #define KASAN_SHADOW_END ((UL(1) << (64 - KASAN_SHADOW_SCALE_SHIFT)) + KASAN_SHADOW_OFFSET) #define _KASAN_SHADOW_START(va) (KASAN_SHADOW_END - (UL(1) << ((va) - KASAN_SHADOW_SCALE_SHIFT))) #define KASAN_SHADOW_START _KASAN_SHADOW_START(vabits_actual) #define PAGE_END KASAN_SHADOW_START #define KASAN_THREAD_SHIFT 1 #else #define KASAN_THREAD_SHIFT 0 #define PAGE_END (_PAGE_END(VA_BITS_MIN)) #endif /* CONFIG_KASAN */ #define MIN_THREAD_SHIFT (14 + KASAN_THREAD_SHIFT) /* * VMAP'd stacks are allocated at page granularity, so we must ensure that such * stacks are a multiple of page size. */ #if defined(CONFIG_VMAP_STACK) && (MIN_THREAD_SHIFT < PAGE_SHIFT) #define THREAD_SHIFT PAGE_SHIFT #else #define THREAD_SHIFT MIN_THREAD_SHIFT #endif #if THREAD_SHIFT >= PAGE_SHIFT #define THREAD_SIZE_ORDER (THREAD_SHIFT - PAGE_SHIFT) #endif #define THREAD_SIZE (UL(1) << THREAD_SHIFT) /* * By aligning VMAP'd stacks to 2 * THREAD_SIZE, we can detect overflow by * checking sp & (1 << THREAD_SHIFT), which we can do cheaply in the entry * assembly. */ #ifdef CONFIG_VMAP_STACK #define THREAD_ALIGN (2 * THREAD_SIZE) #else #define THREAD_ALIGN THREAD_SIZE #endif #define IRQ_STACK_SIZE THREAD_SIZE #define OVERFLOW_STACK_SIZE SZ_4K /* * With the minimum frame size of [x29, x30], exactly half the combined * sizes of the hyp and overflow stacks is the maximum size needed to * save the unwinded stacktrace; plus an additional entry to delimit the * end. */ #define NVHE_STACKTRACE_SIZE ((OVERFLOW_STACK_SIZE + PAGE_SIZE) / 2 + sizeof(long)) /* * Alignment of kernel segments (e.g. .text, .data). * * 4 KB granule: 16 level 3 entries, with contiguous bit * 16 KB granule: 4 level 3 entries, without contiguous bit * 64 KB granule: 1 level 3 entry */ #define SEGMENT_ALIGN SZ_64K /* * Memory types available. * * IMPORTANT: MT_NORMAL must be index 0 since vm_get_page_prot() may 'or' in * the MT_NORMAL_TAGGED memory type for PROT_MTE mappings. Note * that protection_map[] only contains MT_NORMAL attributes. */ #define MT_NORMAL 0 #define MT_NORMAL_TAGGED 1 #define MT_NORMAL_NC 2 #define MT_DEVICE_nGnRnE 3 #define MT_DEVICE_nGnRE 4 /* * Memory types for Stage-2 translation */ #define MT_S2_NORMAL 0xf #define MT_S2_NORMAL_NC 0x5 #define MT_S2_DEVICE_nGnRE 0x1 /* * Memory types for Stage-2 translation when ID_AA64MMFR2_EL1.FWB is 0001 * Stage-2 enforces Normal-WB and Device-nGnRE */ #define MT_S2_FWB_NORMAL 6 #define MT_S2_FWB_NORMAL_NC 5 #define MT_S2_FWB_DEVICE_nGnRE 1 #ifdef CONFIG_ARM64_4K_PAGES #define IOREMAP_MAX_ORDER (PUD_SHIFT) #else #define IOREMAP_MAX_ORDER (PMD_SHIFT) #endif /* * Open-coded (swapper_pg_dir - reserved_pg_dir) as this cannot be calculated * until link time. */ #define RESERVED_SWAPPER_OFFSET (PAGE_SIZE) /* * Open-coded (swapper_pg_dir - tramp_pg_dir) as this cannot be calculated * until link time. */ #define TRAMP_SWAPPER_OFFSET (2 * PAGE_SIZE) #ifndef __ASSEMBLY__ #include <linux/bitops.h> #include <linux/compiler.h> #include <linux/mmdebug.h> #include <linux/types.h> #include <asm/boot.h> #include <asm/bug.h> #include <asm/sections.h> #include <asm/sysreg.h> static inline u64 __pure read_tcr(void) { u64 tcr; // read_sysreg() uses asm volatile, so avoid it here asm("mrs %0, tcr_el1" : "=r"(tcr)); return tcr; } #if VA_BITS > 48 // For reasons of #include hell, we can't use TCR_T1SZ_OFFSET/TCR_T1SZ_MASK here #define vabits_actual (64 - ((read_tcr() >> 16) & 63)) #else #define vabits_actual ((u64)VA_BITS) #endif extern s64 memstart_addr; /* PHYS_OFFSET - the physical address of the start of memory. */ #define PHYS_OFFSET ({ VM_BUG_ON(memstart_addr & 1); memstart_addr; }) /* the offset between the kernel virtual and physical mappings */ extern u64 kimage_voffset; static inline unsigned long kaslr_offset(void) { return (u64)&_text - KIMAGE_VADDR; } #ifdef CONFIG_RANDOMIZE_BASE void kaslr_init(void); static inline bool kaslr_enabled(void) { extern bool __kaslr_is_enabled; return __kaslr_is_enabled; } #else static inline void kaslr_init(void) { } static inline bool kaslr_enabled(void) { return false; } #endif /* * Allow all memory at the discovery stage. We will clip it later. */ #define MIN_MEMBLOCK_ADDR 0 #define MAX_MEMBLOCK_ADDR U64_MAX /* * PFNs are used to describe any physical page; this means * PFN 0 == physical address 0. * * This is the PFN of the first RAM page in the kernel * direct-mapped view. We assume this is the first page * of RAM in the mem_map as well. */ #define PHYS_PFN_OFFSET (PHYS_OFFSET >> PAGE_SHIFT) /* * When dealing with data aborts, watchpoints, or instruction traps we may end * up with a tagged userland pointer. Clear the tag to get a sane pointer to * pass on to access_ok(), for instance. */ #define __untagged_addr(addr) \ ((__force __typeof__(addr))sign_extend64((__force u64)(addr), 55)) #define untagged_addr(addr) ({ \ u64 __addr = (__force u64)(addr); \ __addr &= __untagged_addr(__addr); \ (__force __typeof__(addr))__addr; \ }) #if defined(CONFIG_KASAN_SW_TAGS) || defined(CONFIG_KASAN_HW_TAGS) #define __tag_shifted(tag) ((u64)(tag) << 56) #define __tag_reset(addr) __untagged_addr(addr) #define __tag_get(addr) (__u8)((u64)(addr) >> 56) #else #define __tag_shifted(tag) 0UL #define __tag_reset(addr) (addr) #define __tag_get(addr) 0 #endif /* CONFIG_KASAN_SW_TAGS || CONFIG_KASAN_HW_TAGS */ static inline const void *__tag_set(const void *addr, u8 tag) { u64 __addr = (u64)addr & ~__tag_shifted(0xff); return (const void *)(__addr | __tag_shifted(tag)); } #ifdef CONFIG_KASAN_HW_TAGS #define arch_enable_tag_checks_sync() mte_enable_kernel_sync() #define arch_enable_tag_checks_async() mte_enable_kernel_async() #define arch_enable_tag_checks_asymm() mte_enable_kernel_asymm() #define arch_suppress_tag_checks_start() mte_enable_tco() #define arch_suppress_tag_checks_stop() mte_disable_tco() #define arch_force_async_tag_fault() mte_check_tfsr_exit() #define arch_get_random_tag() mte_get_random_tag() #define arch_get_mem_tag(addr) mte_get_mem_tag(addr) #define arch_set_mem_tag_range(addr, size, tag, init) \ mte_set_mem_tag_range((addr), (size), (tag), (init)) #endif /* CONFIG_KASAN_HW_TAGS */ /* * Physical vs virtual RAM address space conversion. These are * private definitions which should NOT be used outside memory.h * files. Use virt_to_phys/phys_to_virt/__pa/__va instead. */ /* * Check whether an arbitrary address is within the linear map, which * lives in the [PAGE_OFFSET, PAGE_END) interval at the bottom of the * kernel's TTBR1 address range. */ #define __is_lm_address(addr) (((u64)(addr) - PAGE_OFFSET) < (PAGE_END - PAGE_OFFSET)) #define __lm_to_phys(addr) (((addr) - PAGE_OFFSET) + PHYS_OFFSET) #define __kimg_to_phys(addr) ((addr) - kimage_voffset) #define __virt_to_phys_nodebug(x) ({ \ phys_addr_t __x = (phys_addr_t)(__tag_reset(x)); \ __is_lm_address(__x) ? __lm_to_phys(__x) : __kimg_to_phys(__x); \ }) #define __pa_symbol_nodebug(x) __kimg_to_phys((phys_addr_t)(x)) #ifdef CONFIG_DEBUG_VIRTUAL extern phys_addr_t __virt_to_phys(unsigned long x); extern phys_addr_t __phys_addr_symbol(unsigned long x); #else #define __virt_to_phys(x) __virt_to_phys_nodebug(x) #define __phys_addr_symbol(x) __pa_symbol_nodebug(x) #endif /* CONFIG_DEBUG_VIRTUAL */ #define __phys_to_virt(x) ((unsigned long)((x) - PHYS_OFFSET) | PAGE_OFFSET) #define __phys_to_kimg(x) ((unsigned long)((x) + kimage_voffset)) /* * Convert a page to/from a physical address */ #define page_to_phys(page) (__pfn_to_phys(page_to_pfn(page))) #define phys_to_page(phys) (pfn_to_page(__phys_to_pfn(phys))) /* * Note: Drivers should NOT use these. They are the wrong * translation for translating DMA addresses. Use the driver * DMA support - see dma-mapping.h. */ #define virt_to_phys virt_to_phys static inline phys_addr_t virt_to_phys(const volatile void *x) { return __virt_to_phys((unsigned long)(x)); } #define phys_to_virt phys_to_virt static inline void *phys_to_virt(phys_addr_t x) { return (void *)(__phys_to_virt(x)); } /* Needed already here for resolving __phys_to_pfn() in virt_to_pfn() */ #include <asm-generic/memory_model.h> static inline unsigned long virt_to_pfn(const void *kaddr) { return __phys_to_pfn(virt_to_phys(kaddr)); } /* * Drivers should NOT use these either. */ #define __pa(x) __virt_to_phys((unsigned long)(x)) #define __pa_symbol(x) __phys_addr_symbol(RELOC_HIDE((unsigned long)(x), 0)) #define __pa_nodebug(x) __virt_to_phys_nodebug((unsigned long)(x)) #define __va(x) ((void *)__phys_to_virt((phys_addr_t)(x))) #define pfn_to_kaddr(pfn) __va((pfn) << PAGE_SHIFT) #define sym_to_pfn(x) __phys_to_pfn(__pa_symbol(x)) /* * virt_to_page(x) convert a _valid_ virtual address to struct page * * virt_addr_valid(x) indicates whether a virtual address is valid */ #define ARCH_PFN_OFFSET ((unsigned long)PHYS_PFN_OFFSET) #if defined(CONFIG_DEBUG_VIRTUAL) #define page_to_virt(x) ({ \ __typeof__(x) __page = x; \ void *__addr = __va(page_to_phys(__page)); \ (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\ }) #define virt_to_page(x) pfn_to_page(virt_to_pfn(x)) #else #define page_to_virt(x) ({ \ __typeof__(x) __page = x; \ u64 __idx = ((u64)__page - VMEMMAP_START) / sizeof(struct page);\ u64 __addr = PAGE_OFFSET + (__idx * PAGE_SIZE); \ (void *)__tag_set((const void *)__addr, page_kasan_tag(__page));\ }) #define virt_to_page(x) ({ \ u64 __idx = (__tag_reset((u64)x) - PAGE_OFFSET) / PAGE_SIZE; \ u64 __addr = VMEMMAP_START + (__idx * sizeof(struct page)); \ (struct page *)__addr; \ }) #endif /* CONFIG_DEBUG_VIRTUAL */ #define virt_addr_valid(addr) ({ \ __typeof__(addr) __addr = __tag_reset(addr); \ __is_lm_address(__addr) && pfn_is_map_memory(virt_to_pfn(__addr)); \ }) void dump_mem_limit(void); #endif /* !ASSEMBLY */ /* * Given that the GIC architecture permits ITS implementations that can only be * configured with a LPI table address once, GICv3 systems with many CPUs may * end up reserving a lot of different regions after a kexec for their LPI * tables (one per CPU), as we are forced to reuse the same memory after kexec * (and thus reserve it persistently with EFI beforehand) */ #if defined(CONFIG_EFI) && defined(CONFIG_ARM_GIC_V3_ITS) # define INIT_MEMBLOCK_RESERVED_REGIONS (INIT_MEMBLOCK_REGIONS + NR_CPUS + 1) #endif /* * memory regions which marked with flag MEMBLOCK_NOMAP(for example, the memory * of the EFI_UNUSABLE_MEMORY type) may divide a continuous memory block into * multiple parts. As a result, the number of memory regions is large. */ #ifdef CONFIG_EFI #define INIT_MEMBLOCK_MEMORY_REGIONS (INIT_MEMBLOCK_REGIONS * 8) #endif #endif /* __ASM_MEMORY_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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2012 ARM Ltd. */ #ifndef __ASM_FP_H #define __ASM_FP_H #include <asm/errno.h> #include <asm/ptrace.h> #include <asm/processor.h> #include <asm/sigcontext.h> #include <asm/sysreg.h> #ifndef __ASSEMBLY__ #include <linux/bitmap.h> #include <linux/build_bug.h> #include <linux/bug.h> #include <linux/cache.h> #include <linux/init.h> #include <linux/stddef.h> #include <linux/types.h> /* Masks for extracting the FPSR and FPCR from the FPSCR */ #define VFP_FPSCR_STAT_MASK 0xf800009f #define VFP_FPSCR_CTRL_MASK 0x07f79f00 /* * The VFP state has 32x64-bit registers and a single 32-bit * control/status register. */ #define VFP_STATE_SIZE ((32 * 8) + 4) static inline unsigned long cpacr_save_enable_kernel_sve(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_ZEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline unsigned long cpacr_save_enable_kernel_sme(void) { unsigned long old = read_sysreg(cpacr_el1); unsigned long set = CPACR_EL1_FPEN_EL1EN | CPACR_EL1_SMEN_EL1EN; write_sysreg(old | set, cpacr_el1); isb(); return old; } static inline void cpacr_restore(unsigned long cpacr) { write_sysreg(cpacr, cpacr_el1); isb(); } /* * When we defined the maximum SVE vector length we defined the ABI so * that the maximum vector length included all the reserved for future * expansion bits in ZCR rather than those just currently defined by * the architecture. Using this length to allocate worst size buffers * results in excessively large allocations, and this effect is even * more pronounced for SME due to ZA. Define more suitable VLs for * these situations. */ #define ARCH_SVE_VQ_MAX ((ZCR_ELx_LEN_MASK >> ZCR_ELx_LEN_SHIFT) + 1) #define SME_VQ_MAX ((SMCR_ELx_LEN_MASK >> SMCR_ELx_LEN_SHIFT) + 1) struct task_struct; extern void fpsimd_save_state(struct user_fpsimd_state *state); extern void fpsimd_load_state(struct user_fpsimd_state *state); extern void fpsimd_thread_switch(struct task_struct *next); extern void fpsimd_flush_thread(void); extern void fpsimd_signal_preserve_current_state(void); extern void fpsimd_preserve_current_state(void); extern void fpsimd_restore_current_state(void); extern void fpsimd_update_current_state(struct user_fpsimd_state const *state); extern void fpsimd_kvm_prepare(void); struct cpu_fp_state { struct user_fpsimd_state *st; void *sve_state; void *sme_state; u64 *svcr; u64 *fpmr; unsigned int sve_vl; unsigned int sme_vl; enum fp_type *fp_type; enum fp_type to_save; }; extern void fpsimd_bind_state_to_cpu(struct cpu_fp_state *fp_state); extern void fpsimd_flush_task_state(struct task_struct *target); extern void fpsimd_save_and_flush_cpu_state(void); static inline bool thread_sm_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_SM_MASK); } static inline bool thread_za_enabled(struct thread_struct *thread) { return system_supports_sme() && (thread->svcr & SVCR_ZA_MASK); } /* Maximum VL that SVE/SME VL-agnostic software can transparently support */ #define VL_ARCH_MAX 0x100 /* Offset of FFR in the SVE register dump */ static inline size_t sve_ffr_offset(int vl) { return SVE_SIG_FFR_OFFSET(sve_vq_from_vl(vl)) - SVE_SIG_REGS_OFFSET; } static inline void *sve_pffr(struct thread_struct *thread) { unsigned int vl; if (system_supports_sme() && thread_sm_enabled(thread)) vl = thread_get_sme_vl(thread); else vl = thread_get_sve_vl(thread); return (char *)thread->sve_state + sve_ffr_offset(vl); } static inline void *thread_zt_state(struct thread_struct *thread) { /* The ZT register state is stored immediately after the ZA state */ unsigned int sme_vq = sve_vq_from_vl(thread_get_sme_vl(thread)); return thread->sme_state + ZA_SIG_REGS_SIZE(sme_vq); } extern void sve_save_state(void *state, u32 *pfpsr, int save_ffr); extern void sve_load_state(void const *state, u32 const *pfpsr, int restore_ffr); extern void sve_flush_live(bool flush_ffr, unsigned long vq_minus_1); extern unsigned int sve_get_vl(void); extern void sve_set_vq(unsigned long vq_minus_1); extern void sme_set_vq(unsigned long vq_minus_1); extern void sme_save_state(void *state, int zt); extern void sme_load_state(void const *state, int zt); struct arm64_cpu_capabilities; extern void cpu_enable_fpsimd(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sve(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_sme2(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fa64(const struct arm64_cpu_capabilities *__unused); extern void cpu_enable_fpmr(const struct arm64_cpu_capabilities *__unused); extern u64 read_smcr_features(void); /* * Helpers to translate bit indices in sve_vq_map to VQ values (and * vice versa). This allows find_next_bit() to be used to find the * _maximum_ VQ not exceeding a certain value. */ static inline unsigned int __vq_to_bit(unsigned int vq) { return SVE_VQ_MAX - vq; } static inline unsigned int __bit_to_vq(unsigned int bit) { return SVE_VQ_MAX - bit; } struct vl_info { enum vec_type type; const char *name; /* For display purposes */ /* Minimum supported vector length across all CPUs */ int min_vl; /* Maximum supported vector length across all CPUs */ int max_vl; int max_virtualisable_vl; /* * Set of available vector lengths, * where length vq encoded as bit __vq_to_bit(vq): */ DECLARE_BITMAP(vq_map, SVE_VQ_MAX); /* Set of vector lengths present on at least one cpu: */ DECLARE_BITMAP(vq_partial_map, SVE_VQ_MAX); }; #ifdef CONFIG_ARM64_SVE extern void sve_alloc(struct task_struct *task, bool flush); extern void fpsimd_release_task(struct task_struct *task); extern void fpsimd_sync_to_sve(struct task_struct *task); extern void fpsimd_force_sync_to_sve(struct task_struct *task); extern void sve_sync_to_fpsimd(struct task_struct *task); extern void sve_sync_from_fpsimd_zeropad(struct task_struct *task); extern int vec_set_vector_length(struct task_struct *task, enum vec_type type, unsigned long vl, unsigned long flags); extern int sve_set_current_vl(unsigned long arg); extern int sve_get_current_vl(void); static inline void sve_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_ZEN_EL0EN, 0); } static inline void sve_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_ZEN_EL0EN); } #define sve_cond_update_zcr_vq(val, reg) \ do { \ u64 __zcr = read_sysreg_s((reg)); \ u64 __new = __zcr & ~ZCR_ELx_LEN_MASK; \ __new |= (val) & ZCR_ELx_LEN_MASK; \ if (__zcr != __new) \ write_sysreg_s(__new, (reg)); \ } while (0) /* * Probing and setup functions. * Calls to these functions must be serialised with one another. */ enum vec_type; extern void __init vec_init_vq_map(enum vec_type type); extern void vec_update_vq_map(enum vec_type type); extern int vec_verify_vq_map(enum vec_type type); extern void __init sve_setup(void); extern __ro_after_init struct vl_info vl_info[ARM64_VEC_MAX]; static inline void write_vl(enum vec_type type, u64 val) { u64 tmp; switch (type) { #ifdef CONFIG_ARM64_SVE case ARM64_VEC_SVE: tmp = read_sysreg_s(SYS_ZCR_EL1) & ~ZCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_ZCR_EL1); break; #endif #ifdef CONFIG_ARM64_SME case ARM64_VEC_SME: tmp = read_sysreg_s(SYS_SMCR_EL1) & ~SMCR_ELx_LEN_MASK; write_sysreg_s(tmp | val, SYS_SMCR_EL1); break; #endif default: WARN_ON_ONCE(1); break; } } static inline int vec_max_vl(enum vec_type type) { return vl_info[type].max_vl; } static inline int vec_max_virtualisable_vl(enum vec_type type) { return vl_info[type].max_virtualisable_vl; } static inline int sve_max_vl(void) { return vec_max_vl(ARM64_VEC_SVE); } static inline int sve_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SVE); } /* Ensure vq >= SVE_VQ_MIN && vq <= SVE_VQ_MAX before calling this function */ static inline bool vq_available(enum vec_type type, unsigned int vq) { return test_bit(__vq_to_bit(vq), vl_info[type].vq_map); } static inline bool sve_vq_available(unsigned int vq) { return vq_available(ARM64_VEC_SVE, vq); } size_t sve_state_size(struct task_struct const *task); #else /* ! CONFIG_ARM64_SVE */ static inline void sve_alloc(struct task_struct *task, bool flush) { } static inline void fpsimd_release_task(struct task_struct *task) { } static inline void sve_sync_to_fpsimd(struct task_struct *task) { } static inline void sve_sync_from_fpsimd_zeropad(struct task_struct *task) { } static inline int sve_max_virtualisable_vl(void) { return 0; } static inline int sve_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sve_get_current_vl(void) { return -EINVAL; } static inline int sve_max_vl(void) { return -EINVAL; } static inline bool sve_vq_available(unsigned int vq) { return false; } static inline void sve_user_disable(void) { BUILD_BUG(); } static inline void sve_user_enable(void) { BUILD_BUG(); } #define sve_cond_update_zcr_vq(val, reg) do { } while (0) static inline void vec_init_vq_map(enum vec_type t) { } static inline void vec_update_vq_map(enum vec_type t) { } static inline int vec_verify_vq_map(enum vec_type t) { return 0; } static inline void sve_setup(void) { } static inline size_t sve_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static inline void sme_user_disable(void) { sysreg_clear_set(cpacr_el1, CPACR_EL1_SMEN_EL0EN, 0); } static inline void sme_user_enable(void) { sysreg_clear_set(cpacr_el1, 0, CPACR_EL1_SMEN_EL0EN); } static inline void sme_smstart_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTART_SM_EL0, "xzr")); } static inline void sme_smstop_sm(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SM_EL0, "xzr")); } static inline void sme_smstop(void) { asm volatile(__msr_s(SYS_SVCR_SMSTOP_SMZA_EL0, "xzr")); } extern void __init sme_setup(void); static inline int sme_max_vl(void) { return vec_max_vl(ARM64_VEC_SME); } static inline int sme_max_virtualisable_vl(void) { return vec_max_virtualisable_vl(ARM64_VEC_SME); } extern void sme_alloc(struct task_struct *task, bool flush); extern unsigned int sme_get_vl(void); extern int sme_set_current_vl(unsigned long arg); extern int sme_get_current_vl(void); extern void sme_suspend_exit(void); /* * Return how many bytes of memory are required to store the full SME * specific state for task, given task's currently configured vector * length. */ static inline size_t sme_state_size(struct task_struct const *task) { unsigned int vl = task_get_sme_vl(task); size_t size; size = ZA_SIG_REGS_SIZE(sve_vq_from_vl(vl)); if (system_supports_sme2()) size += ZT_SIG_REG_SIZE; return size; } #else static inline void sme_user_disable(void) { BUILD_BUG(); } static inline void sme_user_enable(void) { BUILD_BUG(); } static inline void sme_smstart_sm(void) { } static inline void sme_smstop_sm(void) { } static inline void sme_smstop(void) { } static inline void sme_alloc(struct task_struct *task, bool flush) { } static inline void sme_setup(void) { } static inline unsigned int sme_get_vl(void) { return 0; } static inline int sme_max_vl(void) { return 0; } static inline int sme_max_virtualisable_vl(void) { return 0; } static inline int sme_set_current_vl(unsigned long arg) { return -EINVAL; } static inline int sme_get_current_vl(void) { return -EINVAL; } static inline void sme_suspend_exit(void) { } static inline size_t sme_state_size(struct task_struct const *task) { return 0; } #endif /* ! CONFIG_ARM64_SME */ /* For use by EFI runtime services calls only */ extern void __efi_fpsimd_begin(void); extern void __efi_fpsimd_end(void); #endif #endif |
| 33 33 33 33 33 33 33 33 33 18 18 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/mm/flush.c * * Copyright (C) 1995-2002 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/libnvdimm.h> #include <linux/pagemap.h> #include <asm/cacheflush.h> #include <asm/cache.h> #include <asm/tlbflush.h> void sync_icache_aliases(unsigned long start, unsigned long end) { if (icache_is_aliasing()) { dcache_clean_pou(start, end); icache_inval_all_pou(); } else { /* * Don't issue kick_all_cpus_sync() after I-cache invalidation * for user mappings. */ caches_clean_inval_pou(start, end); } } static void flush_ptrace_access(struct vm_area_struct *vma, unsigned long start, unsigned long end) { if (vma->vm_flags & VM_EXEC) sync_icache_aliases(start, end); } /* * Copy user data from/to a page which is mapped into a different processes * address space. Really, we want to allow our "user space" model to handle * this. */ void copy_to_user_page(struct vm_area_struct *vma, struct page *page, unsigned long uaddr, void *dst, const void *src, unsigned long len) { memcpy(dst, src, len); flush_ptrace_access(vma, (unsigned long)dst, (unsigned long)dst + len); } void __sync_icache_dcache(pte_t pte) { struct folio *folio = page_folio(pte_page(pte)); if (!test_bit(PG_dcache_clean, &folio->flags)) { sync_icache_aliases((unsigned long)folio_address(folio), (unsigned long)folio_address(folio) + folio_size(folio)); set_bit(PG_dcache_clean, &folio->flags); } } EXPORT_SYMBOL_GPL(__sync_icache_dcache); /* * This function is called when a page has been modified by the kernel. Mark * it as dirty for later flushing when mapped in user space (if executable, * see __sync_icache_dcache). */ void flush_dcache_folio(struct folio *folio) { if (test_bit(PG_dcache_clean, &folio->flags)) clear_bit(PG_dcache_clean, &folio->flags); } EXPORT_SYMBOL(flush_dcache_folio); void flush_dcache_page(struct page *page) { flush_dcache_folio(page_folio(page)); } EXPORT_SYMBOL(flush_dcache_page); /* * Additional functions defined in assembly. */ EXPORT_SYMBOL(caches_clean_inval_pou); #ifdef CONFIG_ARCH_HAS_PMEM_API void arch_wb_cache_pmem(void *addr, size_t size) { /* Ensure order against any prior non-cacheable writes */ dmb(osh); dcache_clean_pop((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_wb_cache_pmem); void arch_invalidate_pmem(void *addr, size_t size) { dcache_inval_poc((unsigned long)addr, (unsigned long)addr + size); } EXPORT_SYMBOL_GPL(arch_invalidate_pmem); #endif |
| 250 250 250 250 149 250 250 250 250 250 132 132 132 132 132 132 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 | // SPDX-License-Identifier: GPL-2.0-only /* * Access kernel or user memory without faulting. */ #include <linux/export.h> #include <linux/mm.h> #include <linux/uaccess.h> #include <asm/tlb.h> bool __weak copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size) { return true; } #define copy_from_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __get_kernel_nofault(dst, src, type, err_label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } long copy_from_kernel_nofault(void *dst, const void *src, size_t size) { unsigned long align = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) align = (unsigned long)dst | (unsigned long)src; if (!copy_from_kernel_nofault_allowed(src, size)) return -ERANGE; pagefault_disable(); if (!(align & 7)) copy_from_kernel_nofault_loop(dst, src, size, u64, Efault); if (!(align & 3)) copy_from_kernel_nofault_loop(dst, src, size, u32, Efault); if (!(align & 1)) copy_from_kernel_nofault_loop(dst, src, size, u16, Efault); copy_from_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } EXPORT_SYMBOL_GPL(copy_from_kernel_nofault); #define copy_to_kernel_nofault_loop(dst, src, len, type, err_label) \ while (len >= sizeof(type)) { \ __put_kernel_nofault(dst, src, type, err_label); \ dst += sizeof(type); \ src += sizeof(type); \ len -= sizeof(type); \ } long copy_to_kernel_nofault(void *dst, const void *src, size_t size) { unsigned long align = 0; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) align = (unsigned long)dst | (unsigned long)src; pagefault_disable(); if (!(align & 7)) copy_to_kernel_nofault_loop(dst, src, size, u64, Efault); if (!(align & 3)) copy_to_kernel_nofault_loop(dst, src, size, u32, Efault); if (!(align & 1)) copy_to_kernel_nofault_loop(dst, src, size, u16, Efault); copy_to_kernel_nofault_loop(dst, src, size, u8, Efault); pagefault_enable(); return 0; Efault: pagefault_enable(); return -EFAULT; } long strncpy_from_kernel_nofault(char *dst, const void *unsafe_addr, long count) { const void *src = unsafe_addr; if (unlikely(count <= 0)) return 0; if (!copy_from_kernel_nofault_allowed(unsafe_addr, count)) return -ERANGE; pagefault_disable(); do { __get_kernel_nofault(dst, src, u8, Efault); dst++; src++; } while (dst[-1] && src - unsafe_addr < count); pagefault_enable(); dst[-1] = '\0'; return src - unsafe_addr; Efault: pagefault_enable(); dst[0] = '\0'; return -EFAULT; } /** * copy_from_user_nofault(): safely attempt to read from a user-space location * @dst: pointer to the buffer that shall take the data * @src: address to read from. This must be a user address. * @size: size of the data chunk * * Safely read from user address @src to the buffer at @dst. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_from_user_nofault(void *dst, const void __user *src, size_t size) { long ret = -EFAULT; if (!__access_ok(src, size)) return ret; if (!nmi_uaccess_okay()) return ret; pagefault_disable(); ret = __copy_from_user_inatomic(dst, src, size); pagefault_enable(); if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_from_user_nofault); /** * copy_to_user_nofault(): safely attempt to write to a user-space location * @dst: address to write to * @src: pointer to the data that shall be written * @size: size of the data chunk * * Safely write to address @dst from the buffer at @src. If a kernel fault * happens, handle that and return -EFAULT. */ long copy_to_user_nofault(void __user *dst, const void *src, size_t size) { long ret = -EFAULT; if (access_ok(dst, size)) { pagefault_disable(); ret = __copy_to_user_inatomic(dst, src, size); pagefault_enable(); } if (ret) return -EFAULT; return 0; } EXPORT_SYMBOL_GPL(copy_to_user_nofault); /** * strncpy_from_user_nofault: - Copy a NUL terminated string from unsafe user * address. * @dst: Destination address, in kernel space. This buffer must be at * least @count bytes long. * @unsafe_addr: Unsafe user address. * @count: Maximum number of bytes to copy, including the trailing NUL. * * Copies a NUL-terminated string from unsafe user address to kernel buffer. * * On success, returns the length of the string INCLUDING the trailing NUL. * * If access fails, returns -EFAULT (some data may have been copied * and the trailing NUL added). * * If @count is smaller than the length of the string, copies @count-1 bytes, * sets the last byte of @dst buffer to NUL and returns @count. */ long strncpy_from_user_nofault(char *dst, const void __user *unsafe_addr, long count) { long ret; if (unlikely(count <= 0)) return 0; pagefault_disable(); ret = strncpy_from_user(dst, unsafe_addr, count); pagefault_enable(); if (ret >= count) { ret = count; dst[ret - 1] = '\0'; } else if (ret > 0) { ret++; } return ret; } /** * strnlen_user_nofault: - Get the size of a user string INCLUDING final NUL. * @unsafe_addr: The string to measure. * @count: Maximum count (including NUL) * * Get the size of a NUL-terminated string in user space without pagefault. * * Returns the size of the string INCLUDING the terminating NUL. * * If the string is too long, returns a number larger than @count. User * has to check the return value against "> count". * On exception (or invalid count), returns 0. * * Unlike strnlen_user, this can be used from IRQ handler etc. because * it disables pagefaults. */ long strnlen_user_nofault(const void __user *unsafe_addr, long count) { int ret; pagefault_disable(); ret = strnlen_user(unsafe_addr, count); pagefault_enable(); return ret; } void __copy_overflow(int size, unsigned long count) { WARN(1, "Buffer overflow detected (%d < %lu)!\n", size, count); } EXPORT_SYMBOL(__copy_overflow); |
| 7 11 11 10 10 5 6 5 2 2 2 9 10 10 9 9 10 10 9 6 10 8 7 7 7 7 5 7 7 7 9 9 7 9 9 3 10 8 6 2 2 1 2 2 1 1 1 9 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 | // 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/watch_queue.h> #include <linux/sysctl.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 */ static unsigned int pipe_max_size = 1048576; /* Maximum allocatable pages per user. Hard limit is unset by default, soft * matches default values. */ static unsigned long pipe_user_pages_hard; static unsigned long pipe_user_pages_soft = PIPE_DEF_BUFFERS * INR_OPEN_CUR; /* * We use head and tail indices that aren't masked off, except at the point of * dereference, but rather they're allowed to wrap naturally. This means there * isn't a dead spot in the buffer, but the ring has to be a power of two and * <= 2^31. * -- David Howells 2019-09-23. * * 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 */ #define cmp_int(l, r) ((l > r) - (l < r)) #ifdef CONFIG_PROVE_LOCKING static int pipe_lock_cmp_fn(const struct lockdep_map *a, const struct lockdep_map *b) { return cmp_int((unsigned long) a, (unsigned long) b); } #endif void pipe_lock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_lock(&pipe->mutex); } EXPORT_SYMBOL(pipe_lock); void pipe_unlock(struct pipe_inode_info *pipe) { if (pipe->files) mutex_unlock(&pipe->mutex); } EXPORT_SYMBOL(pipe_unlock); void pipe_double_lock(struct pipe_inode_info *pipe1, struct pipe_inode_info *pipe2) { BUG_ON(pipe1 == pipe2); if (pipe1 > pipe2) swap(pipe1, pipe2); pipe_lock(pipe1); pipe_lock(pipe2); } 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 bool anon_pipe_buf_try_steal(struct pipe_inode_info *pipe, struct pipe_buffer *buf) { struct page *page = buf->page; if (page_count(page) != 1) return false; memcg_kmem_uncharge_page(page, 0); __SetPageLocked(page); return true; } /** * generic_pipe_buf_try_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. */ bool generic_pipe_buf_try_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 true; } return false; } EXPORT_SYMBOL(generic_pipe_buf_try_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 * 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_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); static const struct pipe_buf_operations anon_pipe_buf_ops = { .release = anon_pipe_buf_release, .try_steal = anon_pipe_buf_try_steal, .get = generic_pipe_buf_get, }; /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_readable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int writers = READ_ONCE(pipe->writers); return !pipe_empty(head, tail) || !writers; } static inline unsigned int pipe_update_tail(struct pipe_inode_info *pipe, struct pipe_buffer *buf, unsigned int tail) { pipe_buf_release(pipe, buf); /* * If the pipe has a watch_queue, we need additional protection * by the spinlock because notifications get posted with only * this spinlock, no mutex */ if (pipe_has_watch_queue(pipe)) { spin_lock_irq(&pipe->rd_wait.lock); #ifdef CONFIG_WATCH_QUEUE if (buf->flags & PIPE_BUF_FLAG_LOSS) pipe->note_loss = true; #endif pipe->tail = ++tail; spin_unlock_irq(&pipe->rd_wait.lock); return tail; } /* * Without a watch_queue, we can simply increment the tail * without the spinlock - the mutex is enough. */ pipe->tail = ++tail; return tail; } 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; bool was_full, wake_next_reader = false; ssize_t ret; /* Null read succeeds. */ if (unlikely(total_len == 0)) return 0; ret = 0; mutex_lock(&pipe->mutex); /* * We only wake up writers if the pipe was full when we started * reading in order to avoid unnecessary wakeups. * * But when we do wake up writers, we do so using a sync wakeup * (WF_SYNC), because we want them to get going and generate more * data for us. */ was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); for (;;) { /* Read ->head with a barrier vs post_one_notification() */ unsigned int head = smp_load_acquire(&pipe->head); unsigned int tail = pipe->tail; unsigned int mask = pipe->ring_size - 1; #ifdef CONFIG_WATCH_QUEUE if (pipe->note_loss) { struct watch_notification n; if (total_len < 8) { if (ret == 0) ret = -ENOBUFS; break; } n.type = WATCH_TYPE_META; n.subtype = WATCH_META_LOSS_NOTIFICATION; n.info = watch_sizeof(n); if (copy_to_iter(&n, sizeof(n), to) != sizeof(n)) { if (ret == 0) ret = -EFAULT; break; } ret += sizeof(n); total_len -= sizeof(n); pipe->note_loss = false; } #endif if (!pipe_empty(head, tail)) { struct pipe_buffer *buf = &pipe->bufs[tail & mask]; size_t chars = buf->len; size_t written; int error; if (chars > total_len) { if (buf->flags & PIPE_BUF_FLAG_WHOLE) { if (ret == 0) ret = -ENOBUFS; break; } 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) tail = pipe_update_tail(pipe, buf, tail); total_len -= chars; if (!total_len) break; /* common path: read succeeded */ if (!pipe_empty(head, tail)) /* More to do? */ continue; } if (!pipe->writers) break; if (ret) break; if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { ret = -EAGAIN; break; } mutex_unlock(&pipe->mutex); /* * We only get here if we didn't actually read anything. * * However, we could have seen (and removed) a zero-sized * pipe buffer, and might have made space in the buffers * that way. * * You can't make zero-sized pipe buffers by doing an empty * write (not even in packet mode), but they can happen if * the writer gets an EFAULT when trying to fill a buffer * that already got allocated and inserted in the buffer * array. * * So we still need to wake up any pending writers in the * _very_ unlikely case that the pipe was full, but we got * no data. */ if (unlikely(was_full)) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); /* * But because we didn't read anything, at this point we can * just return directly with -ERESTARTSYS if we're interrupted, * since we've done any required wakeups and there's no need * to mark anything accessed. And we've dropped the lock. */ if (wait_event_interruptible_exclusive(pipe->rd_wait, pipe_readable(pipe)) < 0) return -ERESTARTSYS; mutex_lock(&pipe->mutex); was_full = pipe_full(pipe->head, pipe->tail, pipe->max_usage); wake_next_reader = true; } if (pipe_empty(pipe->head, pipe->tail)) wake_next_reader = false; mutex_unlock(&pipe->mutex); if (was_full) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); if (wake_next_reader) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); 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; } /* Done while waiting without holding the pipe lock - thus the READ_ONCE() */ static inline bool pipe_writable(const struct pipe_inode_info *pipe) { unsigned int head = READ_ONCE(pipe->head); unsigned int tail = READ_ONCE(pipe->tail); unsigned int max_usage = READ_ONCE(pipe->max_usage); return !pipe_full(head, tail, max_usage) || !READ_ONCE(pipe->readers); } 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; unsigned int head; ssize_t ret = 0; size_t total_len = iov_iter_count(from); ssize_t chars; bool was_empty = false; bool wake_next_writer = false; /* * Reject writing to watch queue pipes before the point where we lock * the pipe. * Otherwise, lockdep would be unhappy if the caller already has another * pipe locked. * If we had to support locking a normal pipe and a notification pipe at * the same time, we could set up lockdep annotations for that, but * since we don't actually need that, it's simpler to just bail here. */ if (pipe_has_watch_queue(pipe)) return -EXDEV; /* Null write succeeds. */ if (unlikely(total_len == 0)) return 0; mutex_lock(&pipe->mutex); if (!pipe->readers) { send_sig(SIGPIPE, current, 0); ret = -EPIPE; goto out; } /* * If it wasn't empty we try to merge new data into * the last buffer. * * That naturally merges small writes, but it also * page-aligns the rest of the writes for large writes * spanning multiple pages. */ head = pipe->head; was_empty = pipe_empty(head, pipe->tail); chars = total_len & (PAGE_SIZE-1); if (chars && !was_empty) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask]; int offset = buf->offset + buf->len; if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) && 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; } buf->len += ret; if (!iov_iter_count(from)) goto out; } } for (;;) { if (!pipe->readers) { send_sig(SIGPIPE, current, 0); if (!ret) ret = -EPIPE; break; } head = pipe->head; if (!pipe_full(head, pipe->tail, pipe->max_usage)) { unsigned int mask = pipe->ring_size - 1; struct pipe_buffer *buf; 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; } /* Allocate a slot in the ring in advance and attach an * empty buffer. If we fault or otherwise fail to use * it, either the reader will consume it or it'll still * be there for the next write. */ pipe->head = head + 1; /* Insert it into the buffer array */ buf = &pipe->bufs[head & mask]; buf->page = page; buf->ops = &anon_pipe_buf_ops; buf->offset = 0; buf->len = 0; if (is_packetized(filp)) buf->flags = PIPE_BUF_FLAG_PACKET; else buf->flags = PIPE_BUF_FLAG_CAN_MERGE; pipe->tmp_page = NULL; 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; buf->len = copied; if (!iov_iter_count(from)) break; } if (!pipe_full(head, pipe->tail, pipe->max_usage)) continue; /* Wait for buffer space to become available. */ if ((filp->f_flags & O_NONBLOCK) || (iocb->ki_flags & IOCB_NOWAIT)) { if (!ret) ret = -EAGAIN; break; } if (signal_pending(current)) { if (!ret) ret = -ERESTARTSYS; break; } /* * We're going to release the pipe lock and wait for more * space. We wake up any readers if necessary, and then * after waiting we need to re-check whether the pipe * become empty while we dropped the lock. */ mutex_unlock(&pipe->mutex); if (was_empty) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); wait_event_interruptible_exclusive(pipe->wr_wait, pipe_writable(pipe)); mutex_lock(&pipe->mutex); was_empty = pipe_empty(pipe->head, pipe->tail); wake_next_writer = true; } out: if (pipe_full(pipe->head, pipe->tail, pipe->max_usage)) wake_next_writer = false; mutex_unlock(&pipe->mutex); /* * If we do do a wakeup event, we do a 'sync' wakeup, because we * want the reader to start processing things asap, rather than * leave the data pending. * * This is particularly important for small writes, because of * how (for example) the GNU make jobserver uses small writes to * wake up pending jobs * * Epoll nonsensically wants a wakeup whether the pipe * was already empty or not. */ if (was_empty || pipe->poll_usage) wake_up_interruptible_sync_poll(&pipe->rd_wait, EPOLLIN | EPOLLRDNORM); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); if (wake_next_writer) wake_up_interruptible_sync_poll(&pipe->wr_wait, EPOLLOUT | EPOLLWRNORM); 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; unsigned int count, head, tail, mask; switch (cmd) { case FIONREAD: mutex_lock(&pipe->mutex); count = 0; head = pipe->head; tail = pipe->tail; mask = pipe->ring_size - 1; while (tail != head) { count += pipe->bufs[tail & mask].len; tail++; } mutex_unlock(&pipe->mutex); return put_user(count, (int __user *)arg); #ifdef CONFIG_WATCH_QUEUE case IOC_WATCH_QUEUE_SET_SIZE: { int ret; mutex_lock(&pipe->mutex); ret = watch_queue_set_size(pipe, arg); mutex_unlock(&pipe->mutex); return ret; } case IOC_WATCH_QUEUE_SET_FILTER: return watch_queue_set_filter( pipe, (struct watch_notification_filter __user *)arg); #endif 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; unsigned int head, tail; /* Epoll has some historical nasty semantics, this enables them */ WRITE_ONCE(pipe->poll_usage, true); /* * Reading pipe state only -- no need for acquiring the semaphore. * * But because this is racy, the code has to add the * entry to the poll table _first_ .. */ if (filp->f_mode & FMODE_READ) poll_wait(filp, &pipe->rd_wait, wait); if (filp->f_mode & FMODE_WRITE) poll_wait(filp, &pipe->wr_wait, wait); /* * .. and only then can you do the racy tests. That way, * if something changes and you got it wrong, the poll * table entry will wake you up and fix it. */ head = READ_ONCE(pipe->head); tail = READ_ONCE(pipe->tail); mask = 0; if (filp->f_mode & FMODE_READ) { if (!pipe_empty(head, tail)) mask |= EPOLLIN | EPOLLRDNORM; if (!pipe->writers && filp->f_version != pipe->w_counter) mask |= EPOLLHUP; } if (filp->f_mode & FMODE_WRITE) { if (!pipe_full(head, tail, pipe->max_usage)) mask |= EPOLLOUT | EPOLLWRNORM; /* * 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; mutex_lock(&pipe->mutex); if (file->f_mode & FMODE_READ) pipe->readers--; if (file->f_mode & FMODE_WRITE) pipe->writers--; /* Was that the last reader or writer, but not the other side? */ if (!pipe->readers != !pipe->writers) { wake_up_interruptible_all(&pipe->rd_wait); wake_up_interruptible_all(&pipe->wr_wait); kill_fasync(&pipe->fasync_readers, SIGIO, POLL_IN); kill_fasync(&pipe->fasync_writers, SIGIO, POLL_OUT); } mutex_unlock(&pipe->mutex); 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; mutex_lock(&pipe->mutex); 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); } mutex_unlock(&pipe->mutex); return retval; } 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); } 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; } 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; } bool pipe_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) && pipe_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) && pipe_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->rd_wait); init_waitqueue_head(&pipe->wr_wait); pipe->r_counter = pipe->w_counter = 1; pipe->max_usage = pipe_bufs; pipe->ring_size = pipe_bufs; pipe->nr_accounted = pipe_bufs; pipe->user = user; mutex_init(&pipe->mutex); lock_set_cmp_fn(&pipe->mutex, pipe_lock_cmp_fn, NULL); 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) { unsigned int i; #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) watch_queue_clear(pipe->watch_queue); #endif (void) account_pipe_buffers(pipe->user, pipe->nr_accounted, 0); free_uid(pipe->user); for (i = 0; i < pipe->ring_size; i++) { struct pipe_buffer *buf = pipe->bufs + i; if (buf->ops) pipe_buf_release(pipe, buf); } #ifdef CONFIG_WATCH_QUEUE if (pipe->watch_queue) put_watch_queue(pipe->watch_queue); #endif if (pipe->tmp_page) __free_page(pipe->tmp_page); kfree(pipe->bufs); kfree(pipe); } static struct vfsmount *pipe_mnt __ro_after_init; /* * pipefs_dname() is called from d_path(). */ static char *pipefs_dname(struct dentry *dentry, char *buffer, int buflen) { return dynamic_dname(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(); simple_inode_init_ts(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; int error; if (!inode) return -ENFILE; if (flags & O_NOTIFICATION_PIPE) { error = watch_queue_init(inode->i_pipe); if (error) { free_pipe_info(inode->i_pipe); iput(inode); return error; } } 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; stream_open(inode, res[0]); stream_open(inode, res[1]); 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 | O_NOTIFICATION_PIPE)) 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; /* pipe groks IOCB_NOWAIT */ files[0]->f_mode |= FMODE_NOWAIT; files[1]->f_mode |= FMODE_NOWAIT; 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); } /* * This is the stupid "wait for pipe to be readable or writable" * model. * * See pipe_read/write() for the proper kind of exclusive wait, * but that requires that we wake up any other readers/writers * if we then do not end up reading everything (ie the whole * "wake_next_reader/writer" logic in pipe_read/write()). */ void pipe_wait_readable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->rd_wait, pipe_readable(pipe)); pipe_lock(pipe); } void pipe_wait_writable(struct pipe_inode_info *pipe) { pipe_unlock(pipe); wait_event_interruptible(pipe->wr_wait, pipe_writable(pipe)); pipe_lock(pipe); } /* * This depends on both the wait (here) and the wakeup (wake_up_partner) * holding the pipe lock, so "*cnt" is stable and we know a wakeup cannot * race with the count check and waitqueue prep. * * Normally in order to avoid races, you'd do the prepare_to_wait() first, * then check the condition you're waiting for, and only then sleep. But * because of the pipe lock, we can check the condition before being on * the wait queue. * * We use the 'rd_wait' waitqueue for pipe partner waiting. */ static int wait_for_partner(struct pipe_inode_info *pipe, unsigned int *cnt) { DEFINE_WAIT(rdwait); int cur = *cnt; while (cur == *cnt) { prepare_to_wait(&pipe->rd_wait, &rdwait, TASK_INTERRUPTIBLE); pipe_unlock(pipe); schedule(); finish_wait(&pipe->rd_wait, &rdwait); pipe_lock(pipe); if (signal_pending(current)) break; } return cur == *cnt ? -ERESTARTSYS : 0; } static void wake_up_partner(struct pipe_inode_info *pipe) { wake_up_interruptible_all(&pipe->rd_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 */ mutex_lock(&pipe->mutex); /* We can only do regular read/write on fifos */ stream_open(inode, filp); switch (filp->f_mode & (FMODE_READ | FMODE_WRITE)) { 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! */ mutex_unlock(&pipe->mutex); return 0; err_rd: if (!--pipe->readers) wake_up_interruptible(&pipe->wr_wait); ret = -ERESTARTSYS; goto err; err_wr: if (!--pipe->writers) wake_up_interruptible_all(&pipe->rd_wait); ret = -ERESTARTSYS; goto err; err: mutex_unlock(&pipe->mutex); 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, .splice_write = iter_file_splice_write, }; /* * 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 int 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); } /* * Resize the pipe ring to a number of slots. * * Note the pipe can be reduced in capacity, but only if the current * occupancy doesn't exceed nr_slots; if it does, EBUSY will be * returned instead. */ int pipe_resize_ring(struct pipe_inode_info *pipe, unsigned int nr_slots) { struct pipe_buffer *bufs; unsigned int head, tail, mask, n; bufs = kcalloc(nr_slots, sizeof(*bufs), GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (unlikely(!bufs)) return -ENOMEM; spin_lock_irq(&pipe->rd_wait.lock); mask = pipe->ring_size - 1; head = pipe->head; tail = pipe->tail; n = pipe_occupancy(head, tail); if (nr_slots < n) { spin_unlock_irq(&pipe->rd_wait.lock); kfree(bufs); return -EBUSY; } /* * The pipe array wraps around, so just start the new one at zero * and adjust the indices. */ if (n > 0) { unsigned int h = head & mask; unsigned int t = tail & mask; if (h > t) { memcpy(bufs, pipe->bufs + t, n * sizeof(struct pipe_buffer)); } else { unsigned int tsize = pipe->ring_size - t; if (h > 0) memcpy(bufs + tsize, pipe->bufs, h * sizeof(struct pipe_buffer)); memcpy(bufs, pipe->bufs + t, tsize * sizeof(struct pipe_buffer)); } } head = n; tail = 0; kfree(pipe->bufs); pipe->bufs = bufs; pipe->ring_size = nr_slots; if (pipe->max_usage > nr_slots) pipe->max_usage = nr_slots; pipe->tail = tail; pipe->head = head; if (!pipe_has_watch_queue(pipe)) { pipe->max_usage = nr_slots; pipe->nr_accounted = nr_slots; } spin_unlock_irq(&pipe->rd_wait.lock); /* This might have made more room for writers */ wake_up_interruptible(&pipe->wr_wait); return 0; } /* * 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 int arg) { unsigned long user_bufs; unsigned int nr_slots, size; long ret = 0; if (pipe_has_watch_queue(pipe)) return -EBUSY; size = round_pipe_size(arg); nr_slots = size >> PAGE_SHIFT; if (!nr_slots) 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_slots > pipe->max_usage && size > pipe_max_size && !capable(CAP_SYS_RESOURCE)) return -EPERM; user_bufs = account_pipe_buffers(pipe->user, pipe->nr_accounted, nr_slots); if (nr_slots > pipe->max_usage && (too_many_pipe_buffers_hard(user_bufs) || too_many_pipe_buffers_soft(user_bufs)) && pipe_is_unprivileged_user()) { ret = -EPERM; goto out_revert_acct; } ret = pipe_resize_ring(pipe, nr_slots); if (ret < 0) goto out_revert_acct; return pipe->max_usage * PAGE_SIZE; out_revert_acct: (void) account_pipe_buffers(pipe->user, nr_slots, pipe->nr_accounted); return ret; } /* * Note that i_pipe and 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, bool for_splice) { struct pipe_inode_info *pipe = file->private_data; if (file->f_op != &pipefifo_fops || !pipe) return NULL; if (for_splice && pipe_has_watch_queue(pipe)) return NULL; return pipe; } long pipe_fcntl(struct file *file, unsigned int cmd, unsigned int arg) { struct pipe_inode_info *pipe; long ret; pipe = get_pipe_info(file, false); if (!pipe) return -EBADF; mutex_lock(&pipe->mutex); switch (cmd) { case F_SETPIPE_SZ: ret = pipe_set_size(pipe, arg); break; case F_GETPIPE_SZ: ret = pipe->max_usage * PAGE_SIZE; break; default: ret = -EINVAL; break; } mutex_unlock(&pipe->mutex); 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, }; #ifdef CONFIG_SYSCTL static int do_proc_dopipe_max_size_conv(unsigned long *lvalp, unsigned int *valp, int write, void *data) { if (write) { unsigned int val; val = round_pipe_size(*lvalp); if (val == 0) return -EINVAL; *valp = val; } else { unsigned int val = *valp; *lvalp = (unsigned long) val; } return 0; } static int proc_dopipe_max_size(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { return do_proc_douintvec(table, write, buffer, lenp, ppos, do_proc_dopipe_max_size_conv, NULL); } static struct ctl_table fs_pipe_sysctls[] = { { .procname = "pipe-max-size", .data = &pipe_max_size, .maxlen = sizeof(pipe_max_size), .mode = 0644, .proc_handler = proc_dopipe_max_size, }, { .procname = "pipe-user-pages-hard", .data = &pipe_user_pages_hard, .maxlen = sizeof(pipe_user_pages_hard), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, { .procname = "pipe-user-pages-soft", .data = &pipe_user_pages_soft, .maxlen = sizeof(pipe_user_pages_soft), .mode = 0644, .proc_handler = proc_doulongvec_minmax, }, }; #endif 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); } } #ifdef CONFIG_SYSCTL register_sysctl_init("fs", fs_pipe_sysctls); #endif return err; } fs_initcall(init_pipe_fs); |
| 248 149 149 149 149 149 155 44 155 155 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_LIST_BL_H #define _LINUX_LIST_BL_H #include <linux/list.h> #include <linux/bit_spinlock.h> /* * Special version of lists, where head of the list has a lock in the lowest * bit. This is useful for scalable hash tables without increasing memory * footprint overhead. * * For modification operations, the 0 bit of hlist_bl_head->first * pointer must be set. * * With some small modifications, this can easily be adapted to store several * arbitrary bits (not just a single lock bit), if the need arises to store * some fast and compact auxiliary data. */ #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) #define LIST_BL_LOCKMASK 1UL #else #define LIST_BL_LOCKMASK 0UL #endif #ifdef CONFIG_DEBUG_LIST #define LIST_BL_BUG_ON(x) BUG_ON(x) #else #define LIST_BL_BUG_ON(x) #endif struct hlist_bl_head { struct hlist_bl_node *first; }; struct hlist_bl_node { struct hlist_bl_node *next, **pprev; }; #define INIT_HLIST_BL_HEAD(ptr) \ ((ptr)->first = NULL) static inline void INIT_HLIST_BL_NODE(struct hlist_bl_node *h) { h->next = NULL; h->pprev = NULL; } #define hlist_bl_entry(ptr, type, member) container_of(ptr,type,member) static inline bool hlist_bl_unhashed(const struct hlist_bl_node *h) { return !h->pprev; } static inline struct hlist_bl_node *hlist_bl_first(struct hlist_bl_head *h) { return (struct hlist_bl_node *) ((unsigned long)h->first & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_set_first(struct hlist_bl_head *h, struct hlist_bl_node *n) { LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); LIST_BL_BUG_ON(((unsigned long)h->first & LIST_BL_LOCKMASK) != LIST_BL_LOCKMASK); h->first = (struct hlist_bl_node *)((unsigned long)n | LIST_BL_LOCKMASK); } static inline bool hlist_bl_empty(const struct hlist_bl_head *h) { return !((unsigned long)READ_ONCE(h->first) & ~LIST_BL_LOCKMASK); } static inline void hlist_bl_add_head(struct hlist_bl_node *n, struct hlist_bl_head *h) { struct hlist_bl_node *first = hlist_bl_first(h); n->next = first; if (first) first->pprev = &n->next; n->pprev = &h->first; hlist_bl_set_first(h, n); } static inline void hlist_bl_add_before(struct hlist_bl_node *n, struct hlist_bl_node *next) { struct hlist_bl_node **pprev = next->pprev; n->pprev = pprev; n->next = next; next->pprev = &n->next; /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((uintptr_t)n | ((uintptr_t)*pprev & LIST_BL_LOCKMASK))); } static inline void hlist_bl_add_behind(struct hlist_bl_node *n, struct hlist_bl_node *prev) { n->next = prev->next; n->pprev = &prev->next; prev->next = n; if (n->next) n->next->pprev = &n->next; } static inline void __hlist_bl_del(struct hlist_bl_node *n) { struct hlist_bl_node *next = n->next; struct hlist_bl_node **pprev = n->pprev; LIST_BL_BUG_ON((unsigned long)n & LIST_BL_LOCKMASK); /* pprev may be `first`, so be careful not to lose the lock bit */ WRITE_ONCE(*pprev, (struct hlist_bl_node *) ((unsigned long)next | ((unsigned long)*pprev & LIST_BL_LOCKMASK))); if (next) next->pprev = pprev; } static inline void hlist_bl_del(struct hlist_bl_node *n) { __hlist_bl_del(n); n->next = LIST_POISON1; n->pprev = LIST_POISON2; } static inline void hlist_bl_del_init(struct hlist_bl_node *n) { if (!hlist_bl_unhashed(n)) { __hlist_bl_del(n); INIT_HLIST_BL_NODE(n); } } static inline void hlist_bl_lock(struct hlist_bl_head *b) { bit_spin_lock(0, (unsigned long *)b); } static inline void hlist_bl_unlock(struct hlist_bl_head *b) { __bit_spin_unlock(0, (unsigned long *)b); } static inline bool hlist_bl_is_locked(struct hlist_bl_head *b) { return bit_spin_is_locked(0, (unsigned long *)b); } /** * hlist_bl_for_each_entry - iterate over list of given type * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @head: the head for your list. * @member: the name of the hlist_node within the struct. * */ #define hlist_bl_for_each_entry(tpos, pos, head, member) \ for (pos = hlist_bl_first(head); \ pos && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = pos->next) /** * hlist_bl_for_each_entry_safe - iterate over list of given type safe against removal of list entry * @tpos: the type * to use as a loop cursor. * @pos: the &struct hlist_node to use as a loop cursor. * @n: another &struct hlist_node to use as temporary storage * @head: the head for your list. * @member: the name of the hlist_node within the struct. */ #define hlist_bl_for_each_entry_safe(tpos, pos, n, head, member) \ for (pos = hlist_bl_first(head); \ pos && ({ n = pos->next; 1; }) && \ ({ tpos = hlist_bl_entry(pos, typeof(*tpos), member); 1;}); \ pos = n) #endif |
| 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FS_STRUCT_H #define _LINUX_FS_STRUCT_H #include <linux/path.h> #include <linux/spinlock.h> #include <linux/seqlock.h> struct fs_struct { int users; spinlock_t lock; seqcount_spinlock_t seq; int umask; int in_exec; struct path root, pwd; } __randomize_layout; extern struct kmem_cache *fs_cachep; extern void exit_fs(struct task_struct *); extern void set_fs_root(struct fs_struct *, const struct path *); extern void set_fs_pwd(struct fs_struct *, const struct path *); extern struct fs_struct *copy_fs_struct(struct fs_struct *); extern void free_fs_struct(struct fs_struct *); extern int unshare_fs_struct(void); static inline void get_fs_root(struct fs_struct *fs, struct path *root) { spin_lock(&fs->lock); *root = fs->root; path_get(root); spin_unlock(&fs->lock); } static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd) { spin_lock(&fs->lock); *pwd = fs->pwd; path_get(pwd); spin_unlock(&fs->lock); } extern bool current_chrooted(void); #endif /* _LINUX_FS_STRUCT_H */ |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 | /* 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 Interfaces handler. * * Version: @(#)dev.h 1.0.10 08/12/93 * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Corey Minyard <wf-rch!minyard@relay.EU.net> * Donald J. Becker, <becker@cesdis.gsfc.nasa.gov> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Bjorn Ekwall. <bj0rn@blox.se> * Pekka Riikonen <priikone@poseidon.pspt.fi> * * Moved to /usr/include/linux for NET3 */ #ifndef _LINUX_NETDEVICE_H #define _LINUX_NETDEVICE_H #include <linux/timer.h> #include <linux/bug.h> #include <linux/delay.h> #include <linux/atomic.h> #include <linux/prefetch.h> #include <asm/cache.h> #include <asm/byteorder.h> #include <asm/local.h> #include <linux/percpu.h> #include <linux/rculist.h> #include <linux/workqueue.h> #include <linux/dynamic_queue_limits.h> #include <net/net_namespace.h> #ifdef CONFIG_DCB #include <net/dcbnl.h> #endif #include <net/netprio_cgroup.h> #include <linux/netdev_features.h> #include <linux/neighbour.h> #include <uapi/linux/netdevice.h> #include <uapi/linux/if_bonding.h> #include <uapi/linux/pkt_cls.h> #include <uapi/linux/netdev.h> #include <linux/hashtable.h> #include <linux/rbtree.h> #include <net/net_trackers.h> #include <net/net_debug.h> #include <net/dropreason-core.h> struct netpoll_info; struct device; struct ethtool_ops; struct kernel_hwtstamp_config; struct phy_device; struct dsa_port; struct ip_tunnel_parm_kern; struct macsec_context; struct macsec_ops; struct netdev_name_node; struct sd_flow_limit; struct sfp_bus; /* 802.11 specific */ struct wireless_dev; /* 802.15.4 specific */ struct wpan_dev; struct mpls_dev; /* UDP Tunnel offloads */ struct udp_tunnel_info; struct udp_tunnel_nic_info; struct udp_tunnel_nic; struct bpf_prog; struct xdp_buff; struct xdp_frame; struct xdp_metadata_ops; struct xdp_md; typedef u32 xdp_features_t; void synchronize_net(void); void netdev_set_default_ethtool_ops(struct net_device *dev, const struct ethtool_ops *ops); void netdev_sw_irq_coalesce_default_on(struct net_device *dev); /* Backlog congestion levels */ #define NET_RX_SUCCESS 0 /* keep 'em coming, baby */ #define NET_RX_DROP 1 /* packet dropped */ #define MAX_NEST_DEV 8 /* * Transmit return codes: transmit return codes originate from three different * namespaces: * * - qdisc return codes * - driver transmit return codes * - errno values * * Drivers are allowed to return any one of those in their hard_start_xmit() * function. Real network devices commonly used with qdiscs should only return * the driver transmit return codes though - when qdiscs are used, the actual * transmission happens asynchronously, so the value is not propagated to * higher layers. Virtual network devices transmit synchronously; in this case * the driver transmit return codes are consumed by dev_queue_xmit(), and all * others are propagated to higher layers. */ /* qdisc ->enqueue() return codes. */ #define NET_XMIT_SUCCESS 0x00 #define NET_XMIT_DROP 0x01 /* skb dropped */ #define NET_XMIT_CN 0x02 /* congestion notification */ #define NET_XMIT_MASK 0x0f /* qdisc flags in net/sch_generic.h */ /* NET_XMIT_CN is special. It does not guarantee that this packet is lost. It * indicates that the device will soon be dropping packets, or already drops * some packets of the same priority; prompting us to send less aggressively. */ #define net_xmit_eval(e) ((e) == NET_XMIT_CN ? 0 : (e)) #define net_xmit_errno(e) ((e) != NET_XMIT_CN ? -ENOBUFS : 0) /* Driver transmit return codes */ #define NETDEV_TX_MASK 0xf0 enum netdev_tx { __NETDEV_TX_MIN = INT_MIN, /* make sure enum is signed */ NETDEV_TX_OK = 0x00, /* driver took care of packet */ NETDEV_TX_BUSY = 0x10, /* driver tx path was busy*/ }; typedef enum netdev_tx netdev_tx_t; /* * Current order: NETDEV_TX_MASK > NET_XMIT_MASK >= 0 is significant; * hard_start_xmit() return < NET_XMIT_MASK means skb was consumed. */ static inline bool dev_xmit_complete(int rc) { /* * Positive cases with an skb consumed by a driver: * - successful transmission (rc == NETDEV_TX_OK) * - error while transmitting (rc < 0) * - error while queueing to a different device (rc & NET_XMIT_MASK) */ if (likely(rc < NET_XMIT_MASK)) return true; return false; } /* * Compute the worst-case header length according to the protocols * used. */ #if defined(CONFIG_HYPERV_NET) # define LL_MAX_HEADER 128 #elif defined(CONFIG_WLAN) || IS_ENABLED(CONFIG_AX25) # if defined(CONFIG_MAC80211_MESH) # define LL_MAX_HEADER 128 # else # define LL_MAX_HEADER 96 # endif #else # define LL_MAX_HEADER 32 #endif #if !IS_ENABLED(CONFIG_NET_IPIP) && !IS_ENABLED(CONFIG_NET_IPGRE) && \ !IS_ENABLED(CONFIG_IPV6_SIT) && !IS_ENABLED(CONFIG_IPV6_TUNNEL) #define MAX_HEADER LL_MAX_HEADER #else #define MAX_HEADER (LL_MAX_HEADER + 48) #endif /* * Old network device statistics. Fields are native words * (unsigned long) so they can be read and written atomically. */ #define NET_DEV_STAT(FIELD) \ union { \ unsigned long FIELD; \ atomic_long_t __##FIELD; \ } struct net_device_stats { NET_DEV_STAT(rx_packets); NET_DEV_STAT(tx_packets); NET_DEV_STAT(rx_bytes); NET_DEV_STAT(tx_bytes); NET_DEV_STAT(rx_errors); NET_DEV_STAT(tx_errors); NET_DEV_STAT(rx_dropped); NET_DEV_STAT(tx_dropped); NET_DEV_STAT(multicast); NET_DEV_STAT(collisions); NET_DEV_STAT(rx_length_errors); NET_DEV_STAT(rx_over_errors); NET_DEV_STAT(rx_crc_errors); NET_DEV_STAT(rx_frame_errors); NET_DEV_STAT(rx_fifo_errors); NET_DEV_STAT(rx_missed_errors); NET_DEV_STAT(tx_aborted_errors); NET_DEV_STAT(tx_carrier_errors); NET_DEV_STAT(tx_fifo_errors); NET_DEV_STAT(tx_heartbeat_errors); NET_DEV_STAT(tx_window_errors); NET_DEV_STAT(rx_compressed); NET_DEV_STAT(tx_compressed); }; #undef NET_DEV_STAT /* per-cpu stats, allocated on demand. * Try to fit them in a single cache line, for dev_get_stats() sake. */ struct net_device_core_stats { unsigned long rx_dropped; unsigned long tx_dropped; unsigned long rx_nohandler; unsigned long rx_otherhost_dropped; } __aligned(4 * sizeof(unsigned long)); #include <linux/cache.h> #include <linux/skbuff.h> struct neighbour; struct neigh_parms; struct sk_buff; struct netdev_hw_addr { struct list_head list; struct rb_node node; unsigned char addr[MAX_ADDR_LEN]; unsigned char type; #define NETDEV_HW_ADDR_T_LAN 1 #define NETDEV_HW_ADDR_T_SAN 2 #define NETDEV_HW_ADDR_T_UNICAST 3 #define NETDEV_HW_ADDR_T_MULTICAST 4 bool global_use; int sync_cnt; int refcount; int synced; struct rcu_head rcu_head; }; struct netdev_hw_addr_list { struct list_head list; int count; /* Auxiliary tree for faster lookup on addition and deletion */ struct rb_root tree; }; #define netdev_hw_addr_list_count(l) ((l)->count) #define netdev_hw_addr_list_empty(l) (netdev_hw_addr_list_count(l) == 0) #define netdev_hw_addr_list_for_each(ha, l) \ list_for_each_entry(ha, &(l)->list, list) #define netdev_uc_count(dev) netdev_hw_addr_list_count(&(dev)->uc) #define netdev_uc_empty(dev) netdev_hw_addr_list_empty(&(dev)->uc) #define netdev_for_each_uc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->uc) #define netdev_for_each_synced_uc_addr(_ha, _dev) \ netdev_for_each_uc_addr((_ha), (_dev)) \ if ((_ha)->sync_cnt) #define netdev_mc_count(dev) netdev_hw_addr_list_count(&(dev)->mc) #define netdev_mc_empty(dev) netdev_hw_addr_list_empty(&(dev)->mc) #define netdev_for_each_mc_addr(ha, dev) \ netdev_hw_addr_list_for_each(ha, &(dev)->mc) #define netdev_for_each_synced_mc_addr(_ha, _dev) \ netdev_for_each_mc_addr((_ha), (_dev)) \ if ((_ha)->sync_cnt) struct hh_cache { unsigned int hh_len; seqlock_t hh_lock; /* cached hardware header; allow for machine alignment needs. */ #define HH_DATA_MOD 16 #define HH_DATA_OFF(__len) \ (HH_DATA_MOD - (((__len - 1) & (HH_DATA_MOD - 1)) + 1)) #define HH_DATA_ALIGN(__len) \ (((__len)+(HH_DATA_MOD-1))&~(HH_DATA_MOD - 1)) unsigned long hh_data[HH_DATA_ALIGN(LL_MAX_HEADER) / sizeof(long)]; }; /* Reserve HH_DATA_MOD byte-aligned hard_header_len, but at least that much. * Alternative is: * dev->hard_header_len ? (dev->hard_header_len + * (HH_DATA_MOD - 1)) & ~(HH_DATA_MOD - 1) : 0 * * We could use other alignment values, but we must maintain the * relationship HH alignment <= LL alignment. */ #define LL_RESERVED_SPACE(dev) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) #define LL_RESERVED_SPACE_EXTRA(dev,extra) \ ((((dev)->hard_header_len + READ_ONCE((dev)->needed_headroom) + (extra)) \ & ~(HH_DATA_MOD - 1)) + HH_DATA_MOD) struct header_ops { int (*create) (struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len); int (*parse)(const struct sk_buff *skb, unsigned char *haddr); int (*cache)(const struct neighbour *neigh, struct hh_cache *hh, __be16 type); void (*cache_update)(struct hh_cache *hh, const struct net_device *dev, const unsigned char *haddr); bool (*validate)(const char *ll_header, unsigned int len); __be16 (*parse_protocol)(const struct sk_buff *skb); }; /* These flag bits are private to the generic network queueing * layer; they may not be explicitly referenced by any other * code. */ enum netdev_state_t { __LINK_STATE_START, __LINK_STATE_PRESENT, __LINK_STATE_NOCARRIER, __LINK_STATE_LINKWATCH_PENDING, __LINK_STATE_DORMANT, __LINK_STATE_TESTING, }; struct gro_list { struct list_head list; int count; }; /* * size of gro hash buckets, must less than bit number of * napi_struct::gro_bitmask */ #define GRO_HASH_BUCKETS 8 /* * Structure for NAPI scheduling similar to tasklet but with weighting */ struct napi_struct { /* The poll_list must only be managed by the entity which * changes the state of the NAPI_STATE_SCHED bit. This means * whoever atomically sets that bit can add this napi_struct * to the per-CPU poll_list, and whoever clears that bit * can remove from the list right before clearing the bit. */ struct list_head poll_list; unsigned long state; int weight; int defer_hard_irqs_count; unsigned long gro_bitmask; int (*poll)(struct napi_struct *, int); #ifdef CONFIG_NETPOLL /* CPU actively polling if netpoll is configured */ int poll_owner; #endif /* CPU on which NAPI has been scheduled for processing */ int list_owner; struct net_device *dev; struct gro_list gro_hash[GRO_HASH_BUCKETS]; struct sk_buff *skb; struct list_head rx_list; /* Pending GRO_NORMAL skbs */ int rx_count; /* length of rx_list */ unsigned int napi_id; struct hrtimer timer; struct task_struct *thread; /* control-path-only fields follow */ struct list_head dev_list; struct hlist_node napi_hash_node; int irq; }; enum { NAPI_STATE_SCHED, /* Poll is scheduled */ NAPI_STATE_MISSED, /* reschedule a napi */ NAPI_STATE_DISABLE, /* Disable pending */ NAPI_STATE_NPSVC, /* Netpoll - don't dequeue from poll_list */ NAPI_STATE_LISTED, /* NAPI added to system lists */ NAPI_STATE_NO_BUSY_POLL, /* Do not add in napi_hash, no busy polling */ NAPI_STATE_IN_BUSY_POLL, /* sk_busy_loop() owns this NAPI */ NAPI_STATE_PREFER_BUSY_POLL, /* prefer busy-polling over softirq processing*/ NAPI_STATE_THREADED, /* The poll is performed inside its own thread*/ NAPI_STATE_SCHED_THREADED, /* Napi is currently scheduled in threaded mode */ }; enum { NAPIF_STATE_SCHED = BIT(NAPI_STATE_SCHED), NAPIF_STATE_MISSED = BIT(NAPI_STATE_MISSED), NAPIF_STATE_DISABLE = BIT(NAPI_STATE_DISABLE), NAPIF_STATE_NPSVC = BIT(NAPI_STATE_NPSVC), NAPIF_STATE_LISTED = BIT(NAPI_STATE_LISTED), NAPIF_STATE_NO_BUSY_POLL = BIT(NAPI_STATE_NO_BUSY_POLL), NAPIF_STATE_IN_BUSY_POLL = BIT(NAPI_STATE_IN_BUSY_POLL), NAPIF_STATE_PREFER_BUSY_POLL = BIT(NAPI_STATE_PREFER_BUSY_POLL), NAPIF_STATE_THREADED = BIT(NAPI_STATE_THREADED), NAPIF_STATE_SCHED_THREADED = BIT(NAPI_STATE_SCHED_THREADED), }; enum gro_result { GRO_MERGED, GRO_MERGED_FREE, GRO_HELD, GRO_NORMAL, GRO_CONSUMED, }; typedef enum gro_result gro_result_t; /* * enum rx_handler_result - Possible return values for rx_handlers. * @RX_HANDLER_CONSUMED: skb was consumed by rx_handler, do not process it * further. * @RX_HANDLER_ANOTHER: Do another round in receive path. This is indicated in * case skb->dev was changed by rx_handler. * @RX_HANDLER_EXACT: Force exact delivery, no wildcard. * @RX_HANDLER_PASS: Do nothing, pass the skb as if no rx_handler was called. * * rx_handlers are functions called from inside __netif_receive_skb(), to do * special processing of the skb, prior to delivery to protocol handlers. * * Currently, a net_device can only have a single rx_handler registered. Trying * to register a second rx_handler will return -EBUSY. * * To register a rx_handler on a net_device, use netdev_rx_handler_register(). * To unregister a rx_handler on a net_device, use * netdev_rx_handler_unregister(). * * Upon return, rx_handler is expected to tell __netif_receive_skb() what to * do with the skb. * * If the rx_handler consumed the skb in some way, it should return * RX_HANDLER_CONSUMED. This is appropriate when the rx_handler arranged for * the skb to be delivered in some other way. * * If the rx_handler changed skb->dev, to divert the skb to another * net_device, it should return RX_HANDLER_ANOTHER. The rx_handler for the * new device will be called if it exists. * * If the rx_handler decides the skb should be ignored, it should return * RX_HANDLER_EXACT. The skb will only be delivered to protocol handlers that * are registered on exact device (ptype->dev == skb->dev). * * If the rx_handler didn't change skb->dev, but wants the skb to be normally * delivered, it should return RX_HANDLER_PASS. * * A device without a registered rx_handler will behave as if rx_handler * returned RX_HANDLER_PASS. */ enum rx_handler_result { RX_HANDLER_CONSUMED, RX_HANDLER_ANOTHER, RX_HANDLER_EXACT, RX_HANDLER_PASS, }; typedef enum rx_handler_result rx_handler_result_t; typedef rx_handler_result_t rx_handler_func_t(struct sk_buff **pskb); void __napi_schedule(struct napi_struct *n); void __napi_schedule_irqoff(struct napi_struct *n); static inline bool napi_disable_pending(struct napi_struct *n) { return test_bit(NAPI_STATE_DISABLE, &n->state); } static inline bool napi_prefer_busy_poll(struct napi_struct *n) { return test_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); } /** * napi_is_scheduled - test if NAPI is scheduled * @n: NAPI context * * This check is "best-effort". With no locking implemented, * a NAPI can be scheduled or terminate right after this check * and produce not precise results. * * NAPI_STATE_SCHED is an internal state, napi_is_scheduled * should not be used normally and napi_schedule should be * used instead. * * Use only if the driver really needs to check if a NAPI * is scheduled for example in the context of delayed timer * that can be skipped if a NAPI is already scheduled. * * Return True if NAPI is scheduled, False otherwise. */ static inline bool napi_is_scheduled(struct napi_struct *n) { return test_bit(NAPI_STATE_SCHED, &n->state); } bool napi_schedule_prep(struct napi_struct *n); /** * napi_schedule - schedule NAPI poll * @n: NAPI context * * Schedule NAPI poll routine to be called if it is not already * running. * Return true if we schedule a NAPI or false if not. * Refer to napi_schedule_prep() for additional reason on why * a NAPI might not be scheduled. */ static inline bool napi_schedule(struct napi_struct *n) { if (napi_schedule_prep(n)) { __napi_schedule(n); return true; } return false; } /** * napi_schedule_irqoff - schedule NAPI poll * @n: NAPI context * * Variant of napi_schedule(), assuming hard irqs are masked. */ static inline void napi_schedule_irqoff(struct napi_struct *n) { if (napi_schedule_prep(n)) __napi_schedule_irqoff(n); } /** * napi_complete_done - NAPI processing complete * @n: NAPI context * @work_done: number of packets processed * * Mark NAPI processing as complete. Should only be called if poll budget * has not been completely consumed. * Prefer over napi_complete(). * Return false if device should avoid rearming interrupts. */ bool napi_complete_done(struct napi_struct *n, int work_done); static inline bool napi_complete(struct napi_struct *n) { return napi_complete_done(n, 0); } int dev_set_threaded(struct net_device *dev, bool threaded); /** * napi_disable - prevent NAPI from scheduling * @n: NAPI context * * Stop NAPI from being scheduled on this context. * Waits till any outstanding processing completes. */ void napi_disable(struct napi_struct *n); void napi_enable(struct napi_struct *n); /** * napi_synchronize - wait until NAPI is not running * @n: NAPI context * * Wait until NAPI is done being scheduled on this context. * Waits till any outstanding processing completes but * does not disable future activations. */ static inline void napi_synchronize(const struct napi_struct *n) { if (IS_ENABLED(CONFIG_SMP)) while (test_bit(NAPI_STATE_SCHED, &n->state)) msleep(1); else barrier(); } /** * napi_if_scheduled_mark_missed - if napi is running, set the * NAPIF_STATE_MISSED * @n: NAPI context * * If napi is running, set the NAPIF_STATE_MISSED, and return true if * NAPI is scheduled. **/ static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n) { unsigned long val, new; val = READ_ONCE(n->state); do { if (val & NAPIF_STATE_DISABLE) return true; if (!(val & NAPIF_STATE_SCHED)) return false; new = val | NAPIF_STATE_MISSED; } while (!try_cmpxchg(&n->state, &val, new)); return true; } enum netdev_queue_state_t { __QUEUE_STATE_DRV_XOFF, __QUEUE_STATE_STACK_XOFF, __QUEUE_STATE_FROZEN, }; #define QUEUE_STATE_DRV_XOFF (1 << __QUEUE_STATE_DRV_XOFF) #define QUEUE_STATE_STACK_XOFF (1 << __QUEUE_STATE_STACK_XOFF) #define QUEUE_STATE_FROZEN (1 << __QUEUE_STATE_FROZEN) #define QUEUE_STATE_ANY_XOFF (QUEUE_STATE_DRV_XOFF | QUEUE_STATE_STACK_XOFF) #define QUEUE_STATE_ANY_XOFF_OR_FROZEN (QUEUE_STATE_ANY_XOFF | \ QUEUE_STATE_FROZEN) #define QUEUE_STATE_DRV_XOFF_OR_FROZEN (QUEUE_STATE_DRV_XOFF | \ QUEUE_STATE_FROZEN) /* * __QUEUE_STATE_DRV_XOFF is used by drivers to stop the transmit queue. The * netif_tx_* functions below are used to manipulate this flag. The * __QUEUE_STATE_STACK_XOFF flag is used by the stack to stop the transmit * queue independently. The netif_xmit_*stopped functions below are called * to check if the queue has been stopped by the driver or stack (either * of the XOFF bits are set in the state). Drivers should not need to call * netif_xmit*stopped functions, they should only be using netif_tx_*. */ struct netdev_queue { /* * read-mostly part */ struct net_device *dev; netdevice_tracker dev_tracker; struct Qdisc __rcu *qdisc; struct Qdisc __rcu *qdisc_sleeping; #ifdef CONFIG_SYSFS struct kobject kobj; #endif #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) int numa_node; #endif unsigned long tx_maxrate; /* * Number of TX timeouts for this queue * (/sys/class/net/DEV/Q/trans_timeout) */ atomic_long_t trans_timeout; /* Subordinate device that the queue has been assigned to */ struct net_device *sb_dev; #ifdef CONFIG_XDP_SOCKETS struct xsk_buff_pool *pool; #endif /* NAPI instance for the queue * Readers and writers must hold RTNL */ struct napi_struct *napi; /* * write-mostly part */ spinlock_t _xmit_lock ____cacheline_aligned_in_smp; int xmit_lock_owner; /* * Time (in jiffies) of last Tx */ unsigned long trans_start; unsigned long state; #ifdef CONFIG_BQL struct dql dql; #endif } ____cacheline_aligned_in_smp; extern int sysctl_fb_tunnels_only_for_init_net; extern int sysctl_devconf_inherit_init_net; /* * sysctl_fb_tunnels_only_for_init_net == 0 : For all netns * == 1 : For initns only * == 2 : For none. */ static inline bool net_has_fallback_tunnels(const struct net *net) { #if IS_ENABLED(CONFIG_SYSCTL) int fb_tunnels_only_for_init_net = READ_ONCE(sysctl_fb_tunnels_only_for_init_net); return !fb_tunnels_only_for_init_net || (net_eq(net, &init_net) && fb_tunnels_only_for_init_net == 1); #else return true; #endif } static inline int net_inherit_devconf(void) { #if IS_ENABLED(CONFIG_SYSCTL) return READ_ONCE(sysctl_devconf_inherit_init_net); #else return 0; #endif } static inline int netdev_queue_numa_node_read(const struct netdev_queue *q) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) return q->numa_node; #else return NUMA_NO_NODE; #endif } static inline void netdev_queue_numa_node_write(struct netdev_queue *q, int node) { #if defined(CONFIG_XPS) && defined(CONFIG_NUMA) q->numa_node = node; #endif } #ifdef CONFIG_RFS_ACCEL bool rps_may_expire_flow(struct net_device *dev, u16 rxq_index, u32 flow_id, u16 filter_id); #endif /* XPS map type and offset of the xps map within net_device->xps_maps[]. */ enum xps_map_type { XPS_CPUS = 0, XPS_RXQS, XPS_MAPS_MAX, }; #ifdef CONFIG_XPS /* * This structure holds an XPS map which can be of variable length. The * map is an array of queues. */ struct xps_map { unsigned int len; unsigned int alloc_len; struct rcu_head rcu; u16 queues[]; }; #define XPS_MAP_SIZE(_num) (sizeof(struct xps_map) + ((_num) * sizeof(u16))) #define XPS_MIN_MAP_ALLOC ((L1_CACHE_ALIGN(offsetof(struct xps_map, queues[1])) \ - sizeof(struct xps_map)) / sizeof(u16)) /* * This structure holds all XPS maps for device. Maps are indexed by CPU. * * We keep track of the number of cpus/rxqs used when the struct is allocated, * in nr_ids. This will help not accessing out-of-bound memory. * * We keep track of the number of traffic classes used when the struct is * allocated, in num_tc. This will be used to navigate the maps, to ensure we're * not crossing its upper bound, as the original dev->num_tc can be updated in * the meantime. */ struct xps_dev_maps { struct rcu_head rcu; unsigned int nr_ids; s16 num_tc; struct xps_map __rcu *attr_map[]; /* Either CPUs map or RXQs map */ }; #define XPS_CPU_DEV_MAPS_SIZE(_tcs) (sizeof(struct xps_dev_maps) + \ (nr_cpu_ids * (_tcs) * sizeof(struct xps_map *))) #define XPS_RXQ_DEV_MAPS_SIZE(_tcs, _rxqs) (sizeof(struct xps_dev_maps) +\ (_rxqs * (_tcs) * sizeof(struct xps_map *))) #endif /* CONFIG_XPS */ #define TC_MAX_QUEUE 16 #define TC_BITMASK 15 /* HW offloaded queuing disciplines txq count and offset maps */ struct netdev_tc_txq { u16 count; u16 offset; }; #if defined(CONFIG_FCOE) || defined(CONFIG_FCOE_MODULE) /* * This structure is to hold information about the device * configured to run FCoE protocol stack. */ struct netdev_fcoe_hbainfo { char manufacturer[64]; char serial_number[64]; char hardware_version[64]; char driver_version[64]; char optionrom_version[64]; char firmware_version[64]; char model[256]; char model_description[256]; }; #endif #define MAX_PHYS_ITEM_ID_LEN 32 /* This structure holds a unique identifier to identify some * physical item (port for example) used by a netdevice. */ struct netdev_phys_item_id { unsigned char id[MAX_PHYS_ITEM_ID_LEN]; unsigned char id_len; }; static inline bool netdev_phys_item_id_same(struct netdev_phys_item_id *a, struct netdev_phys_item_id *b) { return a->id_len == b->id_len && memcmp(a->id, b->id, a->id_len) == 0; } typedef u16 (*select_queue_fallback_t)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); enum net_device_path_type { DEV_PATH_ETHERNET = 0, DEV_PATH_VLAN, DEV_PATH_BRIDGE, DEV_PATH_PPPOE, DEV_PATH_DSA, DEV_PATH_MTK_WDMA, }; struct net_device_path { enum net_device_path_type type; const struct net_device *dev; union { struct { u16 id; __be16 proto; u8 h_dest[ETH_ALEN]; } encap; struct { enum { DEV_PATH_BR_VLAN_KEEP, DEV_PATH_BR_VLAN_TAG, DEV_PATH_BR_VLAN_UNTAG, DEV_PATH_BR_VLAN_UNTAG_HW, } vlan_mode; u16 vlan_id; __be16 vlan_proto; } bridge; struct { int port; u16 proto; } dsa; struct { u8 wdma_idx; u8 queue; u16 wcid; u8 bss; u8 amsdu; } mtk_wdma; }; }; #define NET_DEVICE_PATH_STACK_MAX 5 #define NET_DEVICE_PATH_VLAN_MAX 2 struct net_device_path_stack { int num_paths; struct net_device_path path[NET_DEVICE_PATH_STACK_MAX]; }; struct net_device_path_ctx { const struct net_device *dev; u8 daddr[ETH_ALEN]; int num_vlans; struct { u16 id; __be16 proto; } vlan[NET_DEVICE_PATH_VLAN_MAX]; }; enum tc_setup_type { TC_QUERY_CAPS, TC_SETUP_QDISC_MQPRIO, TC_SETUP_CLSU32, TC_SETUP_CLSFLOWER, TC_SETUP_CLSMATCHALL, TC_SETUP_CLSBPF, TC_SETUP_BLOCK, TC_SETUP_QDISC_CBS, TC_SETUP_QDISC_RED, TC_SETUP_QDISC_PRIO, TC_SETUP_QDISC_MQ, TC_SETUP_QDISC_ETF, TC_SETUP_ROOT_QDISC, TC_SETUP_QDISC_GRED, TC_SETUP_QDISC_TAPRIO, TC_SETUP_FT, TC_SETUP_QDISC_ETS, TC_SETUP_QDISC_TBF, TC_SETUP_QDISC_FIFO, TC_SETUP_QDISC_HTB, TC_SETUP_ACT, }; /* These structures hold the attributes of bpf state that are being passed * to the netdevice through the bpf op. */ enum bpf_netdev_command { /* Set or clear a bpf program used in the earliest stages of packet * rx. The prog will have been loaded as BPF_PROG_TYPE_XDP. The callee * is responsible for calling bpf_prog_put on any old progs that are * stored. In case of error, the callee need not release the new prog * reference, but on success it takes ownership and must bpf_prog_put * when it is no longer used. */ XDP_SETUP_PROG, XDP_SETUP_PROG_HW, /* BPF program for offload callbacks, invoked at program load time. */ BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE, XDP_SETUP_XSK_POOL, }; struct bpf_prog_offload_ops; struct netlink_ext_ack; struct xdp_umem; struct xdp_dev_bulk_queue; struct bpf_xdp_link; enum bpf_xdp_mode { XDP_MODE_SKB = 0, XDP_MODE_DRV = 1, XDP_MODE_HW = 2, __MAX_XDP_MODE }; struct bpf_xdp_entity { struct bpf_prog *prog; struct bpf_xdp_link *link; }; struct netdev_bpf { enum bpf_netdev_command command; union { /* XDP_SETUP_PROG */ struct { u32 flags; struct bpf_prog *prog; struct netlink_ext_ack *extack; }; /* BPF_OFFLOAD_MAP_ALLOC, BPF_OFFLOAD_MAP_FREE */ struct { struct bpf_offloaded_map *offmap; }; /* XDP_SETUP_XSK_POOL */ struct { struct xsk_buff_pool *pool; u16 queue_id; } xsk; }; }; /* Flags for ndo_xsk_wakeup. */ #define XDP_WAKEUP_RX (1 << 0) #define XDP_WAKEUP_TX (1 << 1) #ifdef CONFIG_XFRM_OFFLOAD struct xfrmdev_ops { int (*xdo_dev_state_add) (struct xfrm_state *x, struct netlink_ext_ack *extack); void (*xdo_dev_state_delete) (struct xfrm_state *x); void (*xdo_dev_state_free) (struct xfrm_state *x); bool (*xdo_dev_offload_ok) (struct sk_buff *skb, struct xfrm_state *x); void (*xdo_dev_state_advance_esn) (struct xfrm_state *x); void (*xdo_dev_state_update_stats) (struct xfrm_state *x); int (*xdo_dev_policy_add) (struct xfrm_policy *x, struct netlink_ext_ack *extack); void (*xdo_dev_policy_delete) (struct xfrm_policy *x); void (*xdo_dev_policy_free) (struct xfrm_policy *x); }; #endif struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; }; struct devlink; struct tlsdev_ops; struct netdev_net_notifier { struct list_head list; struct notifier_block *nb; }; /* * This structure defines the management hooks for network devices. * The following hooks can be defined; unless noted otherwise, they are * optional and can be filled with a null pointer. * * int (*ndo_init)(struct net_device *dev); * This function is called once when a network device is registered. * The network device can use this for any late stage initialization * or semantic validation. It can fail with an error code which will * be propagated back to register_netdev. * * void (*ndo_uninit)(struct net_device *dev); * This function is called when device is unregistered or when registration * fails. It is not called if init fails. * * int (*ndo_open)(struct net_device *dev); * This function is called when a network device transitions to the up * state. * * int (*ndo_stop)(struct net_device *dev); * This function is called when a network device transitions to the down * state. * * netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, * struct net_device *dev); * Called when a packet needs to be transmitted. * Returns NETDEV_TX_OK. Can return NETDEV_TX_BUSY, but you should stop * the queue before that can happen; it's for obsolete devices and weird * corner cases, but the stack really does a non-trivial amount * of useless work if you return NETDEV_TX_BUSY. * Required; cannot be NULL. * * netdev_features_t (*ndo_features_check)(struct sk_buff *skb, * struct net_device *dev * netdev_features_t features); * Called by core transmit path to determine if device is capable of * performing offload operations on a given packet. This is to give * the device an opportunity to implement any restrictions that cannot * be otherwise expressed by feature flags. The check is called with * the set of features that the stack has calculated and it returns * those the driver believes to be appropriate. * * u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, * struct net_device *sb_dev); * Called to decide which queue to use when device supports multiple * transmit queues. * * void (*ndo_change_rx_flags)(struct net_device *dev, int flags); * This function is called to allow device receiver to make * changes to configuration when multicast or promiscuous is enabled. * * void (*ndo_set_rx_mode)(struct net_device *dev); * This function is called device changes address list filtering. * If driver handles unicast address filtering, it should set * IFF_UNICAST_FLT in its priv_flags. * * int (*ndo_set_mac_address)(struct net_device *dev, void *addr); * This function is called when the Media Access Control address * needs to be changed. If this interface is not defined, the * MAC address can not be changed. * * int (*ndo_validate_addr)(struct net_device *dev); * Test if Media Access Control address is valid for the device. * * int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Old-style ioctl entry point. This is used internally by the * appletalk and ieee802154 subsystems but is no longer called by * the device ioctl handler. * * int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); * Used by the bonding driver for its device specific ioctls: * SIOCBONDENSLAVE, SIOCBONDRELEASE, SIOCBONDSETHWADDR, SIOCBONDCHANGEACTIVE, * SIOCBONDSLAVEINFOQUERY, and SIOCBONDINFOQUERY * * * int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); * Called for ethernet specific ioctls: SIOCGMIIPHY, SIOCGMIIREG, * SIOCSMIIREG, SIOCSHWTSTAMP and SIOCGHWTSTAMP. * * int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); * Used to set network devices bus interface parameters. This interface * is retained for legacy reasons; new devices should use the bus * interface (PCI) for low level management. * * int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); * Called when a user wants to change the Maximum Transfer Unit * of a device. * * void (*ndo_tx_timeout)(struct net_device *dev, unsigned int txqueue); * Callback used when the transmitter has not made any progress * for dev->watchdog ticks. * * void (*ndo_get_stats64)(struct net_device *dev, * struct rtnl_link_stats64 *storage); * struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); * Called when a user wants to get the network device usage * statistics. Drivers must do one of the following: * 1. Define @ndo_get_stats64 to fill in a zero-initialised * rtnl_link_stats64 structure passed by the caller. * 2. Define @ndo_get_stats to update a net_device_stats structure * (which should normally be dev->stats) and return a pointer to * it. The structure may be changed asynchronously only if each * field is written atomically. * 3. Update dev->stats asynchronously and atomically, and define * neither operation. * * bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id) * Return true if this device supports offload stats of this attr_id. * * int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, * void *attr_data) * Get statistics for offload operations by attr_id. Write it into the * attr_data pointer. * * int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is registered. * * int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); * If device supports VLAN filtering this function is called when a * VLAN id is unregistered. * * void (*ndo_poll_controller)(struct net_device *dev); * * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, * u8 qos, __be16 proto); * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); * int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); * int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); * int (*ndo_set_vf_port)(struct net_device *dev, int vf, * struct nlattr *port[]); * * Enable or disable the VF ability to query its RSS Redirection Table and * Hash Key. This is needed since on some devices VF share this information * with PF and querying it may introduce a theoretical security risk. * int (*ndo_set_vf_rss_query_en)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); * int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, * void *type_data); * Called to setup any 'tc' scheduler, classifier or action on @dev. * This is always called from the stack with the rtnl lock held and netif * tx queues stopped. This allows the netdevice to perform queue * management safely. * * Fiber Channel over Ethernet (FCoE) offload functions. * int (*ndo_fcoe_enable)(struct net_device *dev); * Called when the FCoE protocol stack wants to start using LLD for FCoE * so the underlying device can perform whatever needed configuration or * initialization to support acceleration of FCoE traffic. * * int (*ndo_fcoe_disable)(struct net_device *dev); * Called when the FCoE protocol stack wants to stop using LLD for FCoE * so the underlying device can perform whatever needed clean-ups to * stop supporting acceleration of FCoE traffic. * * int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Initiator wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); * Called when the FCoE Initiator/Target is done with the DDPed I/O as * indicated by the FC exchange id 'xid', so the underlying device can * clean up and reuse resources for later DDP requests. * * int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, * struct scatterlist *sgl, unsigned int sgc); * Called when the FCoE Target wants to initialize an I/O that * is a possible candidate for Direct Data Placement (DDP). The LLD can * perform necessary setup and returns 1 to indicate the device is set up * successfully to perform DDP on this I/O, otherwise this returns 0. * * int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, * struct netdev_fcoe_hbainfo *hbainfo); * Called when the FCoE Protocol stack wants information on the underlying * device. This information is utilized by the FCoE protocol stack to * register attributes with Fiber Channel management service as per the * FC-GS Fabric Device Management Information(FDMI) specification. * * int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); * Called when the underlying device wants to override default World Wide * Name (WWN) generation mechanism in FCoE protocol stack to pass its own * World Wide Port Name (WWPN) or World Wide Node Name (WWNN) to the FCoE * protocol stack to use. * * RFS acceleration. * int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, * u16 rxq_index, u32 flow_id); * Set hardware filter for RFS. rxq_index is the target queue index; * flow_id is a flow ID to be passed to rps_may_expire_flow() later. * Return the filter ID on success, or a negative error code. * * Slave management functions (for bridge, bonding, etc). * int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to make another netdev an underling. * * int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); * Called to release previously enslaved netdev. * * struct net_device *(*ndo_get_xmit_slave)(struct net_device *dev, * struct sk_buff *skb, * bool all_slaves); * Get the xmit slave of master device. If all_slaves is true, function * assume all the slaves can transmit. * * Feature/offload setting functions. * netdev_features_t (*ndo_fix_features)(struct net_device *dev, * netdev_features_t features); * Adjusts the requested feature flags according to device-specific * constraints, and returns the resulting flags. Must not modify * the device state. * * int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); * Called to update device configuration to new features. Passed * feature set might be less than what was returned by ndo_fix_features()). * Must return >0 or -errno if it changed dev->features itself. * * int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid, u16 flags, * struct netlink_ext_ack *extack); * Adds an FDB entry to dev for addr. * int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], * struct net_device *dev, * const unsigned char *addr, u16 vid) * Deletes the FDB entry from dev coresponding to addr. * int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, * struct netlink_ext_ack *extack); * int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, * struct net_device *dev, struct net_device *filter_dev, * int *idx) * Used to add FDB entries to dump requests. Implementers should add * entries to skb and update idx with the number of entries. * * int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], * u16 nlmsg_flags, struct netlink_ext_ack *extack); * Adds an MDB entry to dev. * int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], * struct netlink_ext_ack *extack); * Deletes the MDB entry from dev. * int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], * struct netlink_ext_ack *extack); * Bulk deletes MDB entries from dev. * int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, * struct netlink_callback *cb); * Dumps MDB entries from dev. The first argument (marker) in the netlink * callback is used by core rtnetlink code. * * int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags, struct netlink_ext_ack *extack) * int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, * struct net_device *dev, u32 filter_mask, * int nlflags) * int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, * u16 flags); * * int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); * Called to change device carrier. Soft-devices (like dummy, team, etc) * which do not represent real hardware may define this to allow their * userspace components to manage their virtual carrier state. Devices * that determine carrier state from physical hardware properties (eg * network cables) or protocol-dependent mechanisms (eg * USB_CDC_NOTIFY_NETWORK_CONNECTION) should NOT implement this function. * * int (*ndo_get_phys_port_id)(struct net_device *dev, * struct netdev_phys_item_id *ppid); * Called to get ID of physical port of this device. If driver does * not implement this, it is assumed that the hw is not able to have * multiple net devices on single physical port. * * int (*ndo_get_port_parent_id)(struct net_device *dev, * struct netdev_phys_item_id *ppid) * Called to get the parent ID of the physical port of this device. * * void* (*ndo_dfwd_add_station)(struct net_device *pdev, * struct net_device *dev) * Called by upper layer devices to accelerate switching or other * station functionality into hardware. 'pdev is the lowerdev * to use for the offload and 'dev' is the net device that will * back the offload. Returns a pointer to the private structure * the upper layer will maintain. * void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv) * Called by upper layer device to delete the station created * by 'ndo_dfwd_add_station'. 'pdev' is the net device backing * the station and priv is the structure returned by the add * operation. * int (*ndo_set_tx_maxrate)(struct net_device *dev, * int queue_index, u32 maxrate); * Called when a user wants to set a max-rate limitation of specific * TX queue. * int (*ndo_get_iflink)(const struct net_device *dev); * Called to get the iflink value of this device. * int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); * This function is used to get egress tunnel information for given skb. * This is useful for retrieving outer tunnel header parameters while * sampling packet. * void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); * This function is used to specify the headroom that the skb must * consider when allocation skb during packet reception. Setting * appropriate rx headroom value allows avoiding skb head copy on * forward. Setting a negative value resets the rx headroom to the * default value. * int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. * int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, * u32 flags); * This function is used to submit @n XDP packets for transmit on a * netdevice. Returns number of frames successfully transmitted, frames * that got dropped are freed/returned via xdp_return_frame(). * Returns negative number, means general error invoking ndo, meaning * no frames were xmit'ed and core-caller will free all frames. * struct net_device *(*ndo_xdp_get_xmit_slave)(struct net_device *dev, * struct xdp_buff *xdp); * Get the xmit slave of master device based on the xdp_buff. * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); * This function is used to wake up the softirq, ksoftirqd or kthread * responsible for sending and/or receiving packets on a specific * queue id bound to an AF_XDP socket. The flags field specifies if * only RX, only Tx, or both should be woken up using the flags * XDP_WAKEUP_RX and XDP_WAKEUP_TX. * int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, * int cmd); * Add, change, delete or get information on an IPv4 tunnel. * struct net_device *(*ndo_get_peer_dev)(struct net_device *dev); * If a device is paired with a peer device, return the peer instance. * The caller must be under RCU read context. * int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); * Get the forwarding path to reach the real device from the HW destination address * ktime_t (*ndo_get_tstamp)(struct net_device *dev, * const struct skb_shared_hwtstamps *hwtstamps, * bool cycles); * Get hardware timestamp based on normal/adjustable time or free running * cycle counter. This function is required if physical clock supports a * free running cycle counter. * * int (*ndo_hwtstamp_get)(struct net_device *dev, * struct kernel_hwtstamp_config *kernel_config); * Get the currently configured hardware timestamping parameters for the * NIC device. * * int (*ndo_hwtstamp_set)(struct net_device *dev, * struct kernel_hwtstamp_config *kernel_config, * struct netlink_ext_ack *extack); * Change the hardware timestamping parameters for NIC device. */ struct net_device_ops { int (*ndo_init)(struct net_device *dev); void (*ndo_uninit)(struct net_device *dev); int (*ndo_open)(struct net_device *dev); int (*ndo_stop)(struct net_device *dev); netdev_tx_t (*ndo_start_xmit)(struct sk_buff *skb, struct net_device *dev); netdev_features_t (*ndo_features_check)(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); u16 (*ndo_select_queue)(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); void (*ndo_change_rx_flags)(struct net_device *dev, int flags); void (*ndo_set_rx_mode)(struct net_device *dev); int (*ndo_set_mac_address)(struct net_device *dev, void *addr); int (*ndo_validate_addr)(struct net_device *dev); int (*ndo_do_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_eth_ioctl)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_siocbond)(struct net_device *dev, struct ifreq *ifr, int cmd); int (*ndo_siocwandev)(struct net_device *dev, struct if_settings *ifs); int (*ndo_siocdevprivate)(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd); int (*ndo_set_config)(struct net_device *dev, struct ifmap *map); int (*ndo_change_mtu)(struct net_device *dev, int new_mtu); int (*ndo_neigh_setup)(struct net_device *dev, struct neigh_parms *); void (*ndo_tx_timeout) (struct net_device *dev, unsigned int txqueue); void (*ndo_get_stats64)(struct net_device *dev, struct rtnl_link_stats64 *storage); bool (*ndo_has_offload_stats)(const struct net_device *dev, int attr_id); int (*ndo_get_offload_stats)(int attr_id, const struct net_device *dev, void *attr_data); struct net_device_stats* (*ndo_get_stats)(struct net_device *dev); int (*ndo_vlan_rx_add_vid)(struct net_device *dev, __be16 proto, u16 vid); int (*ndo_vlan_rx_kill_vid)(struct net_device *dev, __be16 proto, u16 vid); #ifdef CONFIG_NET_POLL_CONTROLLER void (*ndo_poll_controller)(struct net_device *dev); int (*ndo_netpoll_setup)(struct net_device *dev, struct netpoll_info *info); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, int queue, u16 vlan, u8 qos, __be16 proto); int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); int (*ndo_set_vf_trust)(struct net_device *dev, int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, int vf, struct ifla_vf_info *ivf); int (*ndo_set_vf_link_state)(struct net_device *dev, int vf, int link_state); int (*ndo_get_vf_stats)(struct net_device *dev, int vf, struct ifla_vf_stats *vf_stats); int (*ndo_set_vf_port)(struct net_device *dev, int vf, struct nlattr *port[]); int (*ndo_get_vf_port)(struct net_device *dev, int vf, struct sk_buff *skb); int (*ndo_get_vf_guid)(struct net_device *dev, int vf, struct ifla_vf_guid *node_guid, struct ifla_vf_guid *port_guid); int (*ndo_set_vf_guid)(struct net_device *dev, int vf, u64 guid, int guid_type); int (*ndo_set_vf_rss_query_en)( struct net_device *dev, int vf, bool setting); int (*ndo_setup_tc)(struct net_device *dev, enum tc_setup_type type, void *type_data); #if IS_ENABLED(CONFIG_FCOE) int (*ndo_fcoe_enable)(struct net_device *dev); int (*ndo_fcoe_disable)(struct net_device *dev); int (*ndo_fcoe_ddp_setup)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_ddp_done)(struct net_device *dev, u16 xid); int (*ndo_fcoe_ddp_target)(struct net_device *dev, u16 xid, struct scatterlist *sgl, unsigned int sgc); int (*ndo_fcoe_get_hbainfo)(struct net_device *dev, struct netdev_fcoe_hbainfo *hbainfo); #endif #if IS_ENABLED(CONFIG_LIBFCOE) #define NETDEV_FCOE_WWNN 0 #define NETDEV_FCOE_WWPN 1 int (*ndo_fcoe_get_wwn)(struct net_device *dev, u64 *wwn, int type); #endif #ifdef CONFIG_RFS_ACCEL int (*ndo_rx_flow_steer)(struct net_device *dev, const struct sk_buff *skb, u16 rxq_index, u32 flow_id); #endif int (*ndo_add_slave)(struct net_device *dev, struct net_device *slave_dev, struct netlink_ext_ack *extack); int (*ndo_del_slave)(struct net_device *dev, struct net_device *slave_dev); struct net_device* (*ndo_get_xmit_slave)(struct net_device *dev, struct sk_buff *skb, bool all_slaves); struct net_device* (*ndo_sk_get_lower_dev)(struct net_device *dev, struct sock *sk); netdev_features_t (*ndo_fix_features)(struct net_device *dev, netdev_features_t features); int (*ndo_set_features)(struct net_device *dev, netdev_features_t features); int (*ndo_neigh_construct)(struct net_device *dev, struct neighbour *n); void (*ndo_neigh_destroy)(struct net_device *dev, struct neighbour *n); int (*ndo_fdb_add)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u16 flags, struct netlink_ext_ack *extack); int (*ndo_fdb_del)(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, struct netlink_ext_ack *extack); int (*ndo_fdb_del_bulk)(struct nlmsghdr *nlh, struct net_device *dev, struct netlink_ext_ack *extack); int (*ndo_fdb_dump)(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *filter_dev, int *idx); int (*ndo_fdb_get)(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, u32 portid, u32 seq, struct netlink_ext_ack *extack); int (*ndo_mdb_add)(struct net_device *dev, struct nlattr *tb[], u16 nlmsg_flags, struct netlink_ext_ack *extack); int (*ndo_mdb_del)(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack); int (*ndo_mdb_del_bulk)(struct net_device *dev, struct nlattr *tb[], struct netlink_ext_ack *extack); int (*ndo_mdb_dump)(struct net_device *dev, struct sk_buff *skb, struct netlink_callback *cb); int (*ndo_mdb_get)(struct net_device *dev, struct nlattr *tb[], u32 portid, u32 seq, struct netlink_ext_ack *extack); int (*ndo_bridge_setlink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags, struct netlink_ext_ack *extack); int (*ndo_bridge_getlink)(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags); int (*ndo_bridge_dellink)(struct net_device *dev, struct nlmsghdr *nlh, u16 flags); int (*ndo_change_carrier)(struct net_device *dev, bool new_carrier); int (*ndo_get_phys_port_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); int (*ndo_get_port_parent_id)(struct net_device *dev, struct netdev_phys_item_id *ppid); int (*ndo_get_phys_port_name)(struct net_device *dev, char *name, size_t len); void* (*ndo_dfwd_add_station)(struct net_device *pdev, struct net_device *dev); void (*ndo_dfwd_del_station)(struct net_device *pdev, void *priv); int (*ndo_set_tx_maxrate)(struct net_device *dev, int queue_index, u32 maxrate); int (*ndo_get_iflink)(const struct net_device *dev); int (*ndo_fill_metadata_dst)(struct net_device *dev, struct sk_buff *skb); void (*ndo_set_rx_headroom)(struct net_device *dev, int needed_headroom); int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, int n, struct xdp_frame **xdp, u32 flags); struct net_device * (*ndo_xdp_get_xmit_slave)(struct net_device *dev, struct xdp_buff *xdp); int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags); int (*ndo_tunnel_ctl)(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd); struct net_device * (*ndo_get_peer_dev)(struct net_device *dev); int (*ndo_fill_forward_path)(struct net_device_path_ctx *ctx, struct net_device_path *path); ktime_t (*ndo_get_tstamp)(struct net_device *dev, const struct skb_shared_hwtstamps *hwtstamps, bool cycles); int (*ndo_hwtstamp_get)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config); int (*ndo_hwtstamp_set)(struct net_device *dev, struct kernel_hwtstamp_config *kernel_config, struct netlink_ext_ack *extack); }; /** * enum netdev_priv_flags - &struct net_device priv_flags * * These are the &struct net_device, they are only set internally * by drivers and used in the kernel. These flags are invisible to * userspace; this means that the order of these flags can change * during any kernel release. * * You should have a pretty good reason to be extending these flags. * * @IFF_802_1Q_VLAN: 802.1Q VLAN device * @IFF_EBRIDGE: Ethernet bridging device * @IFF_BONDING: bonding master or slave * @IFF_ISATAP: ISATAP interface (RFC4214) * @IFF_WAN_HDLC: WAN HDLC device * @IFF_XMIT_DST_RELEASE: dev_hard_start_xmit() is allowed to * release skb->dst * @IFF_DONT_BRIDGE: disallow bridging this ether dev * @IFF_DISABLE_NETPOLL: disable netpoll at run-time * @IFF_MACVLAN_PORT: device used as macvlan port * @IFF_BRIDGE_PORT: device used as bridge port * @IFF_OVS_DATAPATH: device used as Open vSwitch datapath port * @IFF_TX_SKB_SHARING: The interface supports sharing skbs on transmit * @IFF_UNICAST_FLT: Supports unicast filtering * @IFF_TEAM_PORT: device used as team port * @IFF_SUPP_NOFCS: device supports sending custom FCS * @IFF_LIVE_ADDR_CHANGE: device supports hardware address * change when it's running * @IFF_MACVLAN: Macvlan device * @IFF_XMIT_DST_RELEASE_PERM: IFF_XMIT_DST_RELEASE not taking into account * underlying stacked devices * @IFF_L3MDEV_MASTER: device is an L3 master device * @IFF_NO_QUEUE: device can run without qdisc attached * @IFF_OPENVSWITCH: device is a Open vSwitch master * @IFF_L3MDEV_SLAVE: device is enslaved to an L3 master device * @IFF_TEAM: device is a team device * @IFF_RXFH_CONFIGURED: device has had Rx Flow indirection table configured * @IFF_PHONY_HEADROOM: the headroom value is controlled by an external * entity (i.e. the master device for bridged veth) * @IFF_MACSEC: device is a MACsec device * @IFF_NO_RX_HANDLER: device doesn't support the rx_handler hook * @IFF_FAILOVER: device is a failover master device * @IFF_FAILOVER_SLAVE: device is lower dev of a failover master device * @IFF_L3MDEV_RX_HANDLER: only invoke the rx handler of L3 master device * @IFF_NO_ADDRCONF: prevent ipv6 addrconf * @IFF_TX_SKB_NO_LINEAR: device/driver is capable of xmitting frames with * skb_headlen(skb) == 0 (data starts from frag0) * @IFF_CHANGE_PROTO_DOWN: device supports setting carrier via IFLA_PROTO_DOWN * @IFF_SEE_ALL_HWTSTAMP_REQUESTS: device wants to see calls to * ndo_hwtstamp_set() for all timestamp requests regardless of source, * even if those aren't HWTSTAMP_SOURCE_NETDEV. */ enum netdev_priv_flags { IFF_802_1Q_VLAN = 1<<0, IFF_EBRIDGE = 1<<1, IFF_BONDING = 1<<2, IFF_ISATAP = 1<<3, IFF_WAN_HDLC = 1<<4, IFF_XMIT_DST_RELEASE = 1<<5, IFF_DONT_BRIDGE = 1<<6, IFF_DISABLE_NETPOLL = 1<<7, IFF_MACVLAN_PORT = 1<<8, IFF_BRIDGE_PORT = 1<<9, IFF_OVS_DATAPATH = 1<<10, IFF_TX_SKB_SHARING = 1<<11, IFF_UNICAST_FLT = 1<<12, IFF_TEAM_PORT = 1<<13, IFF_SUPP_NOFCS = 1<<14, IFF_LIVE_ADDR_CHANGE = 1<<15, IFF_MACVLAN = 1<<16, IFF_XMIT_DST_RELEASE_PERM = 1<<17, IFF_L3MDEV_MASTER = 1<<18, IFF_NO_QUEUE = 1<<19, IFF_OPENVSWITCH = 1<<20, IFF_L3MDEV_SLAVE = 1<<21, IFF_TEAM = 1<<22, IFF_RXFH_CONFIGURED = 1<<23, IFF_PHONY_HEADROOM = 1<<24, IFF_MACSEC = 1<<25, IFF_NO_RX_HANDLER = 1<<26, IFF_FAILOVER = 1<<27, IFF_FAILOVER_SLAVE = 1<<28, IFF_L3MDEV_RX_HANDLER = 1<<29, IFF_NO_ADDRCONF = BIT_ULL(30), IFF_TX_SKB_NO_LINEAR = BIT_ULL(31), IFF_CHANGE_PROTO_DOWN = BIT_ULL(32), IFF_SEE_ALL_HWTSTAMP_REQUESTS = BIT_ULL(33), }; #define IFF_802_1Q_VLAN IFF_802_1Q_VLAN #define IFF_EBRIDGE IFF_EBRIDGE #define IFF_BONDING IFF_BONDING #define IFF_ISATAP IFF_ISATAP #define IFF_WAN_HDLC IFF_WAN_HDLC #define IFF_XMIT_DST_RELEASE IFF_XMIT_DST_RELEASE #define IFF_DONT_BRIDGE IFF_DONT_BRIDGE #define IFF_DISABLE_NETPOLL IFF_DISABLE_NETPOLL #define IFF_MACVLAN_PORT IFF_MACVLAN_PORT #define IFF_BRIDGE_PORT IFF_BRIDGE_PORT #define IFF_OVS_DATAPATH IFF_OVS_DATAPATH #define IFF_TX_SKB_SHARING IFF_TX_SKB_SHARING #define IFF_UNICAST_FLT IFF_UNICAST_FLT #define IFF_TEAM_PORT IFF_TEAM_PORT #define IFF_SUPP_NOFCS IFF_SUPP_NOFCS #define IFF_LIVE_ADDR_CHANGE IFF_LIVE_ADDR_CHANGE #define IFF_MACVLAN IFF_MACVLAN #define IFF_XMIT_DST_RELEASE_PERM IFF_XMIT_DST_RELEASE_PERM #define IFF_L3MDEV_MASTER IFF_L3MDEV_MASTER #define IFF_NO_QUEUE IFF_NO_QUEUE #define IFF_OPENVSWITCH IFF_OPENVSWITCH #define IFF_L3MDEV_SLAVE IFF_L3MDEV_SLAVE #define IFF_TEAM IFF_TEAM #define IFF_RXFH_CONFIGURED IFF_RXFH_CONFIGURED #define IFF_PHONY_HEADROOM IFF_PHONY_HEADROOM #define IFF_MACSEC IFF_MACSEC #define IFF_NO_RX_HANDLER IFF_NO_RX_HANDLER #define IFF_FAILOVER IFF_FAILOVER #define IFF_FAILOVER_SLAVE IFF_FAILOVER_SLAVE #define IFF_L3MDEV_RX_HANDLER IFF_L3MDEV_RX_HANDLER #define IFF_TX_SKB_NO_LINEAR IFF_TX_SKB_NO_LINEAR /* Specifies the type of the struct net_device::ml_priv pointer */ enum netdev_ml_priv_type { ML_PRIV_NONE, ML_PRIV_CAN, }; enum netdev_stat_type { NETDEV_PCPU_STAT_NONE, NETDEV_PCPU_STAT_LSTATS, /* struct pcpu_lstats */ NETDEV_PCPU_STAT_TSTATS, /* struct pcpu_sw_netstats */ NETDEV_PCPU_STAT_DSTATS, /* struct pcpu_dstats */ }; enum netdev_reg_state { NETREG_UNINITIALIZED = 0, NETREG_REGISTERED, /* completed register_netdevice */ NETREG_UNREGISTERING, /* called unregister_netdevice */ NETREG_UNREGISTERED, /* completed unregister todo */ NETREG_RELEASED, /* called free_netdev */ NETREG_DUMMY, /* dummy device for NAPI poll */ }; /** * struct net_device - The DEVICE structure. * * Actually, this whole structure is a big mistake. It mixes I/O * data with strictly "high-level" data, and it has to know about * almost every data structure used in the INET module. * * @name: This is the first field of the "visible" part of this structure * (i.e. as seen by users in the "Space.c" file). It is the name * of the interface. * * @name_node: Name hashlist node * @ifalias: SNMP alias * @mem_end: Shared memory end * @mem_start: Shared memory start * @base_addr: Device I/O address * @irq: Device IRQ number * * @state: Generic network queuing layer state, see netdev_state_t * @dev_list: The global list of network devices * @napi_list: List entry used for polling NAPI devices * @unreg_list: List entry when we are unregistering the * device; see the function unregister_netdev * @close_list: List entry used when we are closing the device * @ptype_all: Device-specific packet handlers for all protocols * @ptype_specific: Device-specific, protocol-specific packet handlers * * @adj_list: Directly linked devices, like slaves for bonding * @features: Currently active device features * @hw_features: User-changeable features * * @wanted_features: User-requested features * @vlan_features: Mask of features inheritable by VLAN devices * * @hw_enc_features: Mask of features inherited by encapsulating devices * This field indicates what encapsulation * offloads the hardware is capable of doing, * and drivers will need to set them appropriately. * * @mpls_features: Mask of features inheritable by MPLS * @gso_partial_features: value(s) from NETIF_F_GSO\* * * @ifindex: interface index * @group: The group the device belongs to * * @stats: Statistics struct, which was left as a legacy, use * rtnl_link_stats64 instead * * @core_stats: core networking counters, * do not use this in drivers * @carrier_up_count: Number of times the carrier has been up * @carrier_down_count: Number of times the carrier has been down * * @wireless_handlers: List of functions to handle Wireless Extensions, * instead of ioctl, * see <net/iw_handler.h> for details. * @wireless_data: Instance data managed by the core of wireless extensions * * @netdev_ops: Includes several pointers to callbacks, * if one wants to override the ndo_*() functions * @xdp_metadata_ops: Includes pointers to XDP metadata callbacks. * @xsk_tx_metadata_ops: Includes pointers to AF_XDP TX metadata callbacks. * @ethtool_ops: Management operations * @l3mdev_ops: Layer 3 master device operations * @ndisc_ops: Includes callbacks for different IPv6 neighbour * discovery handling. Necessary for e.g. 6LoWPAN. * @xfrmdev_ops: Transformation offload operations * @tlsdev_ops: Transport Layer Security offload operations * @header_ops: Includes callbacks for creating,parsing,caching,etc * of Layer 2 headers. * * @flags: Interface flags (a la BSD) * @xdp_features: XDP capability supported by the device * @priv_flags: Like 'flags' but invisible to userspace, * see if.h for the definitions * @gflags: Global flags ( kept as legacy ) * @padded: How much padding added by alloc_netdev() * @operstate: RFC2863 operstate * @link_mode: Mapping policy to operstate * @if_port: Selectable AUI, TP, ... * @dma: DMA channel * @mtu: Interface MTU value * @min_mtu: Interface Minimum MTU value * @max_mtu: Interface Maximum MTU value * @type: Interface hardware type * @hard_header_len: Maximum hardware header length. * @min_header_len: Minimum hardware header length * * @needed_headroom: Extra headroom the hardware may need, but not in all * cases can this be guaranteed * @needed_tailroom: Extra tailroom the hardware may need, but not in all * cases can this be guaranteed. Some cases also use * LL_MAX_HEADER instead to allocate the skb * * interface address info: * * @perm_addr: Permanent hw address * @addr_assign_type: Hw address assignment type * @addr_len: Hardware address length * @upper_level: Maximum depth level of upper devices. * @lower_level: Maximum depth level of lower devices. * @neigh_priv_len: Used in neigh_alloc() * @dev_id: Used to differentiate devices that share * the same link layer address * @dev_port: Used to differentiate devices that share * the same function * @addr_list_lock: XXX: need comments on this one * @name_assign_type: network interface name assignment type * @uc_promisc: Counter that indicates promiscuous mode * has been enabled due to the need to listen to * additional unicast addresses in a device that * does not implement ndo_set_rx_mode() * @uc: unicast mac addresses * @mc: multicast mac addresses * @dev_addrs: list of device hw addresses * @queues_kset: Group of all Kobjects in the Tx and RX queues * @promiscuity: Number of times the NIC is told to work in * promiscuous mode; if it becomes 0 the NIC will * exit promiscuous mode * @allmulti: Counter, enables or disables allmulticast mode * * @vlan_info: VLAN info * @dsa_ptr: dsa specific data * @tipc_ptr: TIPC specific data * @atalk_ptr: AppleTalk link * @ip_ptr: IPv4 specific data * @ip6_ptr: IPv6 specific data * @ax25_ptr: AX.25 specific data * @ieee80211_ptr: IEEE 802.11 specific data, assign before registering * @ieee802154_ptr: IEEE 802.15.4 low-rate Wireless Personal Area Network * device struct * @mpls_ptr: mpls_dev struct pointer * @mctp_ptr: MCTP specific data * * @dev_addr: Hw address (before bcast, * because most packets are unicast) * * @_rx: Array of RX queues * @num_rx_queues: Number of RX queues * allocated at register_netdev() time * @real_num_rx_queues: Number of RX queues currently active in device * @xdp_prog: XDP sockets filter program pointer * @gro_flush_timeout: timeout for GRO layer in NAPI * @napi_defer_hard_irqs: If not zero, provides a counter that would * allow to avoid NIC hard IRQ, on busy queues. * * @rx_handler: handler for received packets * @rx_handler_data: XXX: need comments on this one * @tcx_ingress: BPF & clsact qdisc specific data for ingress processing * @ingress_queue: XXX: need comments on this one * @nf_hooks_ingress: netfilter hooks executed for ingress packets * @broadcast: hw bcast address * * @rx_cpu_rmap: CPU reverse-mapping for RX completion interrupts, * indexed by RX queue number. Assigned by driver. * This must only be set if the ndo_rx_flow_steer * operation is defined * @index_hlist: Device index hash chain * * @_tx: Array of TX queues * @num_tx_queues: Number of TX queues allocated at alloc_netdev_mq() time * @real_num_tx_queues: Number of TX queues currently active in device * @qdisc: Root qdisc from userspace point of view * @tx_queue_len: Max frames per queue allowed * @tx_global_lock: XXX: need comments on this one * @xdp_bulkq: XDP device bulk queue * @xps_maps: all CPUs/RXQs maps for XPS device * * @xps_maps: XXX: need comments on this one * @tcx_egress: BPF & clsact qdisc specific data for egress processing * @nf_hooks_egress: netfilter hooks executed for egress packets * @qdisc_hash: qdisc hash table * @watchdog_timeo: Represents the timeout that is used by * the watchdog (see dev_watchdog()) * @watchdog_timer: List of timers * * @proto_down_reason: reason a netdev interface is held down * @pcpu_refcnt: Number of references to this device * @dev_refcnt: Number of references to this device * @refcnt_tracker: Tracker directory for tracked references to this device * @todo_list: Delayed register/unregister * @link_watch_list: XXX: need comments on this one * * @reg_state: Register/unregister state machine * @dismantle: Device is going to be freed * @rtnl_link_state: This enum represents the phases of creating * a new link * * @needs_free_netdev: Should unregister perform free_netdev? * @priv_destructor: Called from unregister * @npinfo: XXX: need comments on this one * @nd_net: Network namespace this network device is inside * * @ml_priv: Mid-layer private * @ml_priv_type: Mid-layer private type * * @pcpu_stat_type: Type of device statistics which the core should * allocate/free: none, lstats, tstats, dstats. none * means the driver is handling statistics allocation/ * freeing internally. * @lstats: Loopback statistics: packets, bytes * @tstats: Tunnel statistics: RX/TX packets, RX/TX bytes * @dstats: Dummy statistics: RX/TX/drop packets, RX/TX bytes * * @garp_port: GARP * @mrp_port: MRP * * @dm_private: Drop monitor private * * @dev: Class/net/name entry * @sysfs_groups: Space for optional device, statistics and wireless * sysfs groups * * @sysfs_rx_queue_group: Space for optional per-rx queue attributes * @rtnl_link_ops: Rtnl_link_ops * @stat_ops: Optional ops for queue-aware statistics * @queue_mgmt_ops: Optional ops for queue management * * @gso_max_size: Maximum size of generic segmentation offload * @tso_max_size: Device (as in HW) limit on the max TSO request size * @gso_max_segs: Maximum number of segments that can be passed to the * NIC for GSO * @tso_max_segs: Device (as in HW) limit on the max TSO segment count * @gso_ipv4_max_size: Maximum size of generic segmentation offload, * for IPv4. * * @dcbnl_ops: Data Center Bridging netlink ops * @num_tc: Number of traffic classes in the net device * @tc_to_txq: XXX: need comments on this one * @prio_tc_map: XXX: need comments on this one * * @fcoe_ddp_xid: Max exchange id for FCoE LRO by ddp * * @priomap: XXX: need comments on this one * @phydev: Physical device may attach itself * for hardware timestamping * @sfp_bus: attached &struct sfp_bus structure. * * @qdisc_tx_busylock: lockdep class annotating Qdisc->busylock spinlock * * @proto_down: protocol port state information can be sent to the * switch driver and used to set the phys state of the * switch port. * * @wol_enabled: Wake-on-LAN is enabled * * @threaded: napi threaded mode is enabled * * @net_notifier_list: List of per-net netdev notifier block * that follow this device when it is moved * to another network namespace. * * @macsec_ops: MACsec offloading ops * * @udp_tunnel_nic_info: static structure describing the UDP tunnel * offload capabilities of the device * @udp_tunnel_nic: UDP tunnel offload state * @xdp_state: stores info on attached XDP BPF programs * * @nested_level: Used as a parameter of spin_lock_nested() of * dev->addr_list_lock. * @unlink_list: As netif_addr_lock() can be called recursively, * keep a list of interfaces to be deleted. * @gro_max_size: Maximum size of aggregated packet in generic * receive offload (GRO) * @gro_ipv4_max_size: Maximum size of aggregated packet in generic * receive offload (GRO), for IPv4. * @xdp_zc_max_segs: Maximum number of segments supported by AF_XDP * zero copy driver * * @dev_addr_shadow: Copy of @dev_addr to catch direct writes. * @linkwatch_dev_tracker: refcount tracker used by linkwatch. * @watchdog_dev_tracker: refcount tracker used by watchdog. * @dev_registered_tracker: tracker for reference held while * registered * @offload_xstats_l3: L3 HW stats for this netdevice. * * @devlink_port: Pointer to related devlink port structure. * Assigned by a driver before netdev registration using * SET_NETDEV_DEVLINK_PORT macro. This pointer is static * during the time netdevice is registered. * * @dpll_pin: Pointer to the SyncE source pin of a DPLL subsystem, * where the clock is recovered. * * FIXME: cleanup struct net_device such that network protocol info * moves out. */ struct net_device { /* Cacheline organization can be found documented in * Documentation/networking/net_cachelines/net_device.rst. * Please update the document when adding new fields. */ /* TX read-mostly hotpath */ __cacheline_group_begin(net_device_read_tx); unsigned long long priv_flags; const struct net_device_ops *netdev_ops; const struct header_ops *header_ops; struct netdev_queue *_tx; netdev_features_t gso_partial_features; unsigned int real_num_tx_queues; unsigned int gso_max_size; unsigned int gso_ipv4_max_size; u16 gso_max_segs; s16 num_tc; /* Note : dev->mtu is often read without holding a lock. * Writers usually hold RTNL. * It is recommended to use READ_ONCE() to annotate the reads, * and to use WRITE_ONCE() to annotate the writes. */ unsigned int mtu; unsigned short needed_headroom; struct netdev_tc_txq tc_to_txq[TC_MAX_QUEUE]; #ifdef CONFIG_XPS struct xps_dev_maps __rcu *xps_maps[XPS_MAPS_MAX]; #endif #ifdef CONFIG_NETFILTER_EGRESS struct nf_hook_entries __rcu *nf_hooks_egress; #endif #ifdef CONFIG_NET_XGRESS struct bpf_mprog_entry __rcu *tcx_egress; #endif __cacheline_group_end(net_device_read_tx); /* TXRX read-mostly hotpath */ __cacheline_group_begin(net_device_read_txrx); union { struct pcpu_lstats __percpu *lstats; struct pcpu_sw_netstats __percpu *tstats; struct pcpu_dstats __percpu *dstats; }; unsigned long state; unsigned int flags; unsigned short hard_header_len; netdev_features_t features; struct inet6_dev __rcu *ip6_ptr; __cacheline_group_end(net_device_read_txrx); /* RX read-mostly hotpath */ __cacheline_group_begin(net_device_read_rx); struct bpf_prog __rcu *xdp_prog; struct list_head ptype_specific; int ifindex; unsigned int real_num_rx_queues; struct netdev_rx_queue *_rx; unsigned long gro_flush_timeout; int napi_defer_hard_irqs; unsigned int gro_max_size; unsigned int gro_ipv4_max_size; rx_handler_func_t __rcu *rx_handler; void __rcu *rx_handler_data; possible_net_t nd_net; #ifdef CONFIG_NETPOLL struct netpoll_info __rcu *npinfo; #endif #ifdef CONFIG_NET_XGRESS struct bpf_mprog_entry __rcu *tcx_ingress; #endif __cacheline_group_end(net_device_read_rx); char name[IFNAMSIZ]; struct netdev_name_node *name_node; struct dev_ifalias __rcu *ifalias; /* * I/O specific fields * FIXME: Merge these and struct ifmap into one */ unsigned long mem_end; unsigned long mem_start; unsigned long base_addr; /* * Some hardware also needs these fields (state,dev_list, * napi_list,unreg_list,close_list) but they are not * part of the usual set specified in Space.c. */ struct list_head dev_list; struct list_head napi_list; struct list_head unreg_list; struct list_head close_list; struct list_head ptype_all; struct { struct list_head upper; struct list_head lower; } adj_list; /* Read-mostly cache-line for fast-path access */ xdp_features_t xdp_features; const struct xdp_metadata_ops *xdp_metadata_ops; const struct xsk_tx_metadata_ops *xsk_tx_metadata_ops; unsigned short gflags; unsigned short needed_tailroom; netdev_features_t hw_features; netdev_features_t wanted_features; netdev_features_t vlan_features; netdev_features_t hw_enc_features; netdev_features_t mpls_features; unsigned int min_mtu; unsigned int max_mtu; unsigned short type; unsigned char min_header_len; unsigned char name_assign_type; int group; struct net_device_stats stats; /* not used by modern drivers */ struct net_device_core_stats __percpu *core_stats; /* Stats to monitor link on/off, flapping */ atomic_t carrier_up_count; atomic_t carrier_down_count; #ifdef CONFIG_WIRELESS_EXT const struct iw_handler_def *wireless_handlers; struct iw_public_data *wireless_data; #endif const struct ethtool_ops *ethtool_ops; #ifdef CONFIG_NET_L3_MASTER_DEV const struct l3mdev_ops *l3mdev_ops; #endif #if IS_ENABLED(CONFIG_IPV6) const struct ndisc_ops *ndisc_ops; #endif #ifdef CONFIG_XFRM_OFFLOAD const struct xfrmdev_ops *xfrmdev_ops; #endif #if IS_ENABLED(CONFIG_TLS_DEVICE) const struct tlsdev_ops *tlsdev_ops; #endif unsigned int operstate; unsigned char link_mode; unsigned char if_port; unsigned char dma; /* Interface address info. */ unsigned char perm_addr[MAX_ADDR_LEN]; unsigned char addr_assign_type; unsigned char addr_len; unsigned char upper_level; unsigned char lower_level; unsigned short neigh_priv_len; unsigned short dev_id; unsigned short dev_port; unsigned short padded; spinlock_t addr_list_lock; int irq; struct netdev_hw_addr_list uc; struct netdev_hw_addr_list mc; struct netdev_hw_addr_list dev_addrs; #ifdef CONFIG_SYSFS struct kset *queues_kset; #endif #ifdef CONFIG_LOCKDEP struct list_head unlink_list; #endif unsigned int promiscuity; unsigned int allmulti; bool uc_promisc; #ifdef CONFIG_LOCKDEP unsigned char nested_level; #endif /* Protocol-specific pointers */ struct in_device __rcu *ip_ptr; #if IS_ENABLED(CONFIG_VLAN_8021Q) struct vlan_info __rcu *vlan_info; #endif #if IS_ENABLED(CONFIG_NET_DSA) struct dsa_port *dsa_ptr; #endif #if IS_ENABLED(CONFIG_TIPC) struct tipc_bearer __rcu *tipc_ptr; #endif #if IS_ENABLED(CONFIG_ATALK) void *atalk_ptr; #endif #if IS_ENABLED(CONFIG_AX25) void *ax25_ptr; #endif #if IS_ENABLED(CONFIG_CFG80211) struct wireless_dev *ieee80211_ptr; #endif #if IS_ENABLED(CONFIG_IEEE802154) || IS_ENABLED(CONFIG_6LOWPAN) struct wpan_dev *ieee802154_ptr; #endif #if IS_ENABLED(CONFIG_MPLS_ROUTING) struct mpls_dev __rcu *mpls_ptr; #endif #if IS_ENABLED(CONFIG_MCTP) struct mctp_dev __rcu *mctp_ptr; #endif /* * Cache lines mostly used on receive path (including eth_type_trans()) */ /* Interface address info used in eth_type_trans() */ const unsigned char *dev_addr; unsigned int num_rx_queues; #define GRO_LEGACY_MAX_SIZE 65536u /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), * and shinfo->gso_segs is a 16bit field. */ #define GRO_MAX_SIZE (8 * 65535u) unsigned int xdp_zc_max_segs; struct netdev_queue __rcu *ingress_queue; #ifdef CONFIG_NETFILTER_INGRESS struct nf_hook_entries __rcu *nf_hooks_ingress; #endif unsigned char broadcast[MAX_ADDR_LEN]; #ifdef CONFIG_RFS_ACCEL struct cpu_rmap *rx_cpu_rmap; #endif struct hlist_node index_hlist; /* * Cache lines mostly used on transmit path */ unsigned int num_tx_queues; struct Qdisc __rcu *qdisc; unsigned int tx_queue_len; spinlock_t tx_global_lock; struct xdp_dev_bulk_queue __percpu *xdp_bulkq; #ifdef CONFIG_NET_SCHED DECLARE_HASHTABLE (qdisc_hash, 4); #endif /* These may be needed for future network-power-down code. */ struct timer_list watchdog_timer; int watchdog_timeo; u32 proto_down_reason; struct list_head todo_list; #ifdef CONFIG_PCPU_DEV_REFCNT int __percpu *pcpu_refcnt; #else refcount_t dev_refcnt; #endif struct ref_tracker_dir refcnt_tracker; struct list_head link_watch_list; u8 reg_state; bool dismantle; enum { RTNL_LINK_INITIALIZED, RTNL_LINK_INITIALIZING, } rtnl_link_state:16; bool needs_free_netdev; void (*priv_destructor)(struct net_device *dev); /* mid-layer private */ void *ml_priv; enum netdev_ml_priv_type ml_priv_type; enum netdev_stat_type pcpu_stat_type:8; #if IS_ENABLED(CONFIG_GARP) struct garp_port __rcu *garp_port; #endif #if IS_ENABLED(CONFIG_MRP) struct mrp_port __rcu *mrp_port; #endif #if IS_ENABLED(CONFIG_NET_DROP_MONITOR) struct dm_hw_stat_delta __rcu *dm_private; #endif struct device dev; const struct attribute_group *sysfs_groups[4]; const struct attribute_group *sysfs_rx_queue_group; const struct rtnl_link_ops *rtnl_link_ops; const struct netdev_stat_ops *stat_ops; const struct netdev_queue_mgmt_ops *queue_mgmt_ops; /* for setting kernel sock attribute on TCP connection setup */ #define GSO_MAX_SEGS 65535u #define GSO_LEGACY_MAX_SIZE 65536u /* TCP minimal MSS is 8 (TCP_MIN_GSO_SIZE), * and shinfo->gso_segs is a 16bit field. */ #define GSO_MAX_SIZE (8 * GSO_MAX_SEGS) #define TSO_LEGACY_MAX_SIZE 65536 #define TSO_MAX_SIZE UINT_MAX unsigned int tso_max_size; #define TSO_MAX_SEGS U16_MAX u16 tso_max_segs; #ifdef CONFIG_DCB const struct dcbnl_rtnl_ops *dcbnl_ops; #endif u8 prio_tc_map[TC_BITMASK + 1]; #if IS_ENABLED(CONFIG_FCOE) unsigned int fcoe_ddp_xid; #endif #if IS_ENABLED(CONFIG_CGROUP_NET_PRIO) struct netprio_map __rcu *priomap; #endif struct phy_device *phydev; struct sfp_bus *sfp_bus; struct lock_class_key *qdisc_tx_busylock; bool proto_down; bool threaded; unsigned wol_enabled:1; struct list_head net_notifier_list; #if IS_ENABLED(CONFIG_MACSEC) /* MACsec management functions */ const struct macsec_ops *macsec_ops; #endif const struct udp_tunnel_nic_info *udp_tunnel_nic_info; struct udp_tunnel_nic *udp_tunnel_nic; /* protected by rtnl_lock */ struct bpf_xdp_entity xdp_state[__MAX_XDP_MODE]; u8 dev_addr_shadow[MAX_ADDR_LEN]; netdevice_tracker linkwatch_dev_tracker; netdevice_tracker watchdog_dev_tracker; netdevice_tracker dev_registered_tracker; struct rtnl_hw_stats64 *offload_xstats_l3; struct devlink_port *devlink_port; #if IS_ENABLED(CONFIG_DPLL) struct dpll_pin __rcu *dpll_pin; #endif #if IS_ENABLED(CONFIG_PAGE_POOL) /** @page_pools: page pools created for this netdevice */ struct hlist_head page_pools; #endif }; #define to_net_dev(d) container_of(d, struct net_device, dev) /* * Driver should use this to assign devlink port instance to a netdevice * before it registers the netdevice. Therefore devlink_port is static * during the netdev lifetime after it is registered. */ #define SET_NETDEV_DEVLINK_PORT(dev, port) \ ({ \ WARN_ON((dev)->reg_state != NETREG_UNINITIALIZED); \ ((dev)->devlink_port = (port)); \ }) static inline bool netif_elide_gro(const struct net_device *dev) { if (!(dev->features & NETIF_F_GRO) || dev->xdp_prog) return true; return false; } #define NETDEV_ALIGN 32 static inline int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio) { return dev->prio_tc_map[prio & TC_BITMASK]; } static inline int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc) { if (tc >= dev->num_tc) return -EINVAL; dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK; return 0; } int netdev_txq_to_tc(struct net_device *dev, unsigned int txq); void netdev_reset_tc(struct net_device *dev); int netdev_set_tc_queue(struct net_device *dev, u8 tc, u16 count, u16 offset); int netdev_set_num_tc(struct net_device *dev, u8 num_tc); static inline int netdev_get_num_tc(struct net_device *dev) { return dev->num_tc; } static inline void net_prefetch(void *p) { prefetch(p); #if L1_CACHE_BYTES < 128 prefetch((u8 *)p + L1_CACHE_BYTES); #endif } static inline void net_prefetchw(void *p) { prefetchw(p); #if L1_CACHE_BYTES < 128 prefetchw((u8 *)p + L1_CACHE_BYTES); #endif } void netdev_unbind_sb_channel(struct net_device *dev, struct net_device *sb_dev); int netdev_bind_sb_channel_queue(struct net_device *dev, struct net_device *sb_dev, u8 tc, u16 count, u16 offset); int netdev_set_sb_channel(struct net_device *dev, u16 channel); static inline int netdev_get_sb_channel(struct net_device *dev) { return max_t(int, -dev->num_tc, 0); } static inline struct netdev_queue *netdev_get_tx_queue(const struct net_device *dev, unsigned int index) { DEBUG_NET_WARN_ON_ONCE(index >= dev->num_tx_queues); return &dev->_tx[index]; } static inline struct netdev_queue *skb_get_tx_queue(const struct net_device *dev, const struct sk_buff *skb) { return netdev_get_tx_queue(dev, skb_get_queue_mapping(skb)); } static inline void netdev_for_each_tx_queue(struct net_device *dev, void (*f)(struct net_device *, struct netdev_queue *, void *), void *arg) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) f(dev, &dev->_tx[i], arg); } #define netdev_lockdep_set_classes(dev) \ { \ static struct lock_class_key qdisc_tx_busylock_key; \ static struct lock_class_key qdisc_xmit_lock_key; \ static struct lock_class_key dev_addr_list_lock_key; \ unsigned int i; \ \ (dev)->qdisc_tx_busylock = &qdisc_tx_busylock_key; \ lockdep_set_class(&(dev)->addr_list_lock, \ &dev_addr_list_lock_key); \ for (i = 0; i < (dev)->num_tx_queues; i++) \ lockdep_set_class(&(dev)->_tx[i]._xmit_lock, \ &qdisc_xmit_lock_key); \ } u16 netdev_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); struct netdev_queue *netdev_core_pick_tx(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); /* returns the headroom that the master device needs to take in account * when forwarding to this dev */ static inline unsigned netdev_get_fwd_headroom(struct net_device *dev) { return dev->priv_flags & IFF_PHONY_HEADROOM ? 0 : dev->needed_headroom; } static inline void netdev_set_rx_headroom(struct net_device *dev, int new_hr) { if (dev->netdev_ops->ndo_set_rx_headroom) dev->netdev_ops->ndo_set_rx_headroom(dev, new_hr); } /* set the device rx headroom to the dev's default */ static inline void netdev_reset_rx_headroom(struct net_device *dev) { netdev_set_rx_headroom(dev, -1); } static inline void *netdev_get_ml_priv(struct net_device *dev, enum netdev_ml_priv_type type) { if (dev->ml_priv_type != type) return NULL; return dev->ml_priv; } static inline void netdev_set_ml_priv(struct net_device *dev, void *ml_priv, enum netdev_ml_priv_type type) { WARN(dev->ml_priv_type && dev->ml_priv_type != type, "Overwriting already set ml_priv_type (%u) with different ml_priv_type (%u)!\n", dev->ml_priv_type, type); WARN(!dev->ml_priv_type && dev->ml_priv, "Overwriting already set ml_priv and ml_priv_type is ML_PRIV_NONE!\n"); dev->ml_priv = ml_priv; dev->ml_priv_type = type; } /* * Net namespace inlines */ static inline struct net *dev_net(const struct net_device *dev) { return read_pnet(&dev->nd_net); } static inline void dev_net_set(struct net_device *dev, struct net *net) { write_pnet(&dev->nd_net, net); } /** * netdev_priv - access network device private data * @dev: network device * * Get network device private data */ static inline void *netdev_priv(const struct net_device *dev) { return (char *)dev + ALIGN(sizeof(struct net_device), NETDEV_ALIGN); } /* Set the sysfs physical device reference for the network logical device * if set prior to registration will cause a symlink during initialization. */ #define SET_NETDEV_DEV(net, pdev) ((net)->dev.parent = (pdev)) /* Set the sysfs device type for the network logical device to allow * fine-grained identification of different network device types. For * example Ethernet, Wireless LAN, Bluetooth, WiMAX etc. */ #define SET_NETDEV_DEVTYPE(net, devtype) ((net)->dev.type = (devtype)) void netif_queue_set_napi(struct net_device *dev, unsigned int queue_index, enum netdev_queue_type type, struct napi_struct *napi); static inline void netif_napi_set_irq(struct napi_struct *napi, int irq) { napi->irq = irq; } /* Default NAPI poll() weight * Device drivers are strongly advised to not use bigger value */ #define NAPI_POLL_WEIGHT 64 void netif_napi_add_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight); /** * netif_napi_add() - initialize a NAPI context * @dev: network device * @napi: NAPI context * @poll: polling function * * netif_napi_add() must be used to initialize a NAPI context prior to calling * *any* of the other NAPI-related functions. */ static inline void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int)) { netif_napi_add_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } static inline void netif_napi_add_tx_weight(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { set_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state); netif_napi_add_weight(dev, napi, poll, weight); } /** * netif_napi_add_tx() - initialize a NAPI context to be used for Tx only * @dev: network device * @napi: NAPI context * @poll: polling function * * This variant of netif_napi_add() should be used from drivers using NAPI * to exclusively poll a TX queue. * This will avoid we add it into napi_hash[], thus polluting this hash table. */ static inline void netif_napi_add_tx(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int)) { netif_napi_add_tx_weight(dev, napi, poll, NAPI_POLL_WEIGHT); } /** * __netif_napi_del - remove a NAPI context * @napi: NAPI context * * Warning: caller must observe RCU grace period before freeing memory * containing @napi. Drivers might want to call this helper to combine * all the needed RCU grace periods into a single one. */ void __netif_napi_del(struct napi_struct *napi); /** * netif_napi_del - remove a NAPI context * @napi: NAPI context * * netif_napi_del() removes a NAPI context from the network device NAPI list */ static inline void netif_napi_del(struct napi_struct *napi) { __netif_napi_del(napi); synchronize_net(); } struct packet_type { __be16 type; /* This is really htons(ether_type). */ bool ignore_outgoing; struct net_device *dev; /* NULL is wildcarded here */ netdevice_tracker dev_tracker; int (*func) (struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *); void (*list_func) (struct list_head *, struct packet_type *, struct net_device *); bool (*id_match)(struct packet_type *ptype, struct sock *sk); struct net *af_packet_net; void *af_packet_priv; struct list_head list; }; struct offload_callbacks { struct sk_buff *(*gso_segment)(struct sk_buff *skb, netdev_features_t features); struct sk_buff *(*gro_receive)(struct list_head *head, struct sk_buff *skb); int (*gro_complete)(struct sk_buff *skb, int nhoff); }; struct packet_offload { __be16 type; /* This is really htons(ether_type). */ u16 priority; struct offload_callbacks callbacks; struct list_head list; }; /* often modified stats are per-CPU, other are shared (netdev->stats) */ struct pcpu_sw_netstats { u64_stats_t rx_packets; u64_stats_t rx_bytes; u64_stats_t tx_packets; u64_stats_t tx_bytes; struct u64_stats_sync syncp; } __aligned(4 * sizeof(u64)); struct pcpu_dstats { u64 rx_packets; u64 rx_bytes; u64 rx_drops; u64 tx_packets; u64 tx_bytes; u64 tx_drops; struct u64_stats_sync syncp; } __aligned(8 * sizeof(u64)); struct pcpu_lstats { u64_stats_t packets; u64_stats_t bytes; struct u64_stats_sync syncp; } __aligned(2 * sizeof(u64)); void dev_lstats_read(struct net_device *dev, u64 *packets, u64 *bytes); static inline void dev_sw_netstats_rx_add(struct net_device *dev, unsigned int len) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); u64_stats_add(&tstats->rx_bytes, len); u64_stats_inc(&tstats->rx_packets); u64_stats_update_end(&tstats->syncp); } static inline void dev_sw_netstats_tx_add(struct net_device *dev, unsigned int packets, unsigned int len) { struct pcpu_sw_netstats *tstats = this_cpu_ptr(dev->tstats); u64_stats_update_begin(&tstats->syncp); u64_stats_add(&tstats->tx_bytes, len); u64_stats_add(&tstats->tx_packets, packets); u64_stats_update_end(&tstats->syncp); } static inline void dev_lstats_add(struct net_device *dev, unsigned int len) { struct pcpu_lstats *lstats = this_cpu_ptr(dev->lstats); u64_stats_update_begin(&lstats->syncp); u64_stats_add(&lstats->bytes, len); u64_stats_inc(&lstats->packets); u64_stats_update_end(&lstats->syncp); } #define __netdev_alloc_pcpu_stats(type, gfp) \ ({ \ typeof(type) __percpu *pcpu_stats = alloc_percpu_gfp(type, gfp);\ if (pcpu_stats) { \ int __cpu; \ for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ pcpu_stats; \ }) #define netdev_alloc_pcpu_stats(type) \ __netdev_alloc_pcpu_stats(type, GFP_KERNEL) #define devm_netdev_alloc_pcpu_stats(dev, type) \ ({ \ typeof(type) __percpu *pcpu_stats = devm_alloc_percpu(dev, type);\ if (pcpu_stats) { \ int __cpu; \ for_each_possible_cpu(__cpu) { \ typeof(type) *stat; \ stat = per_cpu_ptr(pcpu_stats, __cpu); \ u64_stats_init(&stat->syncp); \ } \ } \ pcpu_stats; \ }) enum netdev_lag_tx_type { NETDEV_LAG_TX_TYPE_UNKNOWN, NETDEV_LAG_TX_TYPE_RANDOM, NETDEV_LAG_TX_TYPE_BROADCAST, NETDEV_LAG_TX_TYPE_ROUNDROBIN, NETDEV_LAG_TX_TYPE_ACTIVEBACKUP, NETDEV_LAG_TX_TYPE_HASH, }; enum netdev_lag_hash { NETDEV_LAG_HASH_NONE, NETDEV_LAG_HASH_L2, NETDEV_LAG_HASH_L34, NETDEV_LAG_HASH_L23, NETDEV_LAG_HASH_E23, NETDEV_LAG_HASH_E34, NETDEV_LAG_HASH_VLAN_SRCMAC, NETDEV_LAG_HASH_UNKNOWN, }; struct netdev_lag_upper_info { enum netdev_lag_tx_type tx_type; enum netdev_lag_hash hash_type; }; struct netdev_lag_lower_state_info { u8 link_up : 1, tx_enabled : 1; }; #include <linux/notifier.h> /* netdevice notifier chain. Please remember to update netdev_cmd_to_name() * and the rtnetlink notification exclusion list in rtnetlink_event() when * adding new types. */ enum netdev_cmd { NETDEV_UP = 1, /* For now you can't veto a device up/down */ NETDEV_DOWN, NETDEV_REBOOT, /* Tell a protocol stack a network interface detected a hardware crash and restarted - we can use this eg to kick tcp sessions once done */ NETDEV_CHANGE, /* Notify device state change */ NETDEV_REGISTER, NETDEV_UNREGISTER, NETDEV_CHANGEMTU, /* notify after mtu change happened */ NETDEV_CHANGEADDR, /* notify after the address change */ NETDEV_PRE_CHANGEADDR, /* notify before the address change */ NETDEV_GOING_DOWN, NETDEV_CHANGENAME, NETDEV_FEAT_CHANGE, NETDEV_BONDING_FAILOVER, NETDEV_PRE_UP, NETDEV_PRE_TYPE_CHANGE, NETDEV_POST_TYPE_CHANGE, NETDEV_POST_INIT, NETDEV_PRE_UNINIT, NETDEV_RELEASE, NETDEV_NOTIFY_PEERS, NETDEV_JOIN, NETDEV_CHANGEUPPER, NETDEV_RESEND_IGMP, NETDEV_PRECHANGEMTU, /* notify before mtu change happened */ NETDEV_CHANGEINFODATA, NETDEV_BONDING_INFO, NETDEV_PRECHANGEUPPER, NETDEV_CHANGELOWERSTATE, NETDEV_UDP_TUNNEL_PUSH_INFO, NETDEV_UDP_TUNNEL_DROP_INFO, NETDEV_CHANGE_TX_QUEUE_LEN, NETDEV_CVLAN_FILTER_PUSH_INFO, NETDEV_CVLAN_FILTER_DROP_INFO, NETDEV_SVLAN_FILTER_PUSH_INFO, NETDEV_SVLAN_FILTER_DROP_INFO, NETDEV_OFFLOAD_XSTATS_ENABLE, NETDEV_OFFLOAD_XSTATS_DISABLE, NETDEV_OFFLOAD_XSTATS_REPORT_USED, NETDEV_OFFLOAD_XSTATS_REPORT_DELTA, NETDEV_XDP_FEAT_CHANGE, }; const char *netdev_cmd_to_name(enum netdev_cmd cmd); int register_netdevice_notifier(struct notifier_block *nb); int unregister_netdevice_notifier(struct notifier_block *nb); int register_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int unregister_netdevice_notifier_net(struct net *net, struct notifier_block *nb); int register_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); int unregister_netdevice_notifier_dev_net(struct net_device *dev, struct notifier_block *nb, struct netdev_net_notifier *nn); struct netdev_notifier_info { struct net_device *dev; struct netlink_ext_ack *extack; }; struct netdev_notifier_info_ext { struct netdev_notifier_info info; /* must be first */ union { u32 mtu; } ext; }; struct netdev_notifier_change_info { struct netdev_notifier_info info; /* must be first */ unsigned int flags_changed; }; struct netdev_notifier_changeupper_info { struct netdev_notifier_info info; /* must be first */ struct net_device *upper_dev; /* new upper dev */ bool master; /* is upper dev master */ bool linking; /* is the notification for link or unlink */ void *upper_info; /* upper dev info */ }; struct netdev_notifier_changelowerstate_info { struct netdev_notifier_info info; /* must be first */ void *lower_state_info; /* is lower dev state */ }; struct netdev_notifier_pre_changeaddr_info { struct netdev_notifier_info info; /* must be first */ const unsigned char *dev_addr; }; enum netdev_offload_xstats_type { NETDEV_OFFLOAD_XSTATS_TYPE_L3 = 1, }; struct netdev_notifier_offload_xstats_info { struct netdev_notifier_info info; /* must be first */ enum netdev_offload_xstats_type type; union { /* NETDEV_OFFLOAD_XSTATS_REPORT_DELTA */ struct netdev_notifier_offload_xstats_rd *report_delta; /* NETDEV_OFFLOAD_XSTATS_REPORT_USED */ struct netdev_notifier_offload_xstats_ru *report_used; }; }; int netdev_offload_xstats_enable(struct net_device *dev, enum netdev_offload_xstats_type type, struct netlink_ext_ack *extack); int netdev_offload_xstats_disable(struct net_device *dev, enum netdev_offload_xstats_type type); bool netdev_offload_xstats_enabled(const struct net_device *dev, enum netdev_offload_xstats_type type); int netdev_offload_xstats_get(struct net_device *dev, enum netdev_offload_xstats_type type, struct rtnl_hw_stats64 *stats, bool *used, struct netlink_ext_ack *extack); void netdev_offload_xstats_report_delta(struct netdev_notifier_offload_xstats_rd *rd, const struct rtnl_hw_stats64 *stats); void netdev_offload_xstats_report_used(struct netdev_notifier_offload_xstats_ru *ru); void netdev_offload_xstats_push_delta(struct net_device *dev, enum netdev_offload_xstats_type type, const struct rtnl_hw_stats64 *stats); static inline void netdev_notifier_info_init(struct netdev_notifier_info *info, struct net_device *dev) { info->dev = dev; info->extack = NULL; } static inline struct net_device * netdev_notifier_info_to_dev(const struct netdev_notifier_info *info) { return info->dev; } static inline struct netlink_ext_ack * netdev_notifier_info_to_extack(const struct netdev_notifier_info *info) { return info->extack; } int call_netdevice_notifiers(unsigned long val, struct net_device *dev); int call_netdevice_notifiers_info(unsigned long val, struct netdev_notifier_info *info); #define for_each_netdev(net, d) \ list_for_each_entry(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_reverse(net, d) \ list_for_each_entry_reverse(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_rcu(net, d) \ list_for_each_entry_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_safe(net, d, n) \ list_for_each_entry_safe(d, n, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue(net, d) \ list_for_each_entry_continue(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_continue_reverse(net, d) \ list_for_each_entry_continue_reverse(d, &(net)->dev_base_head, \ dev_list) #define for_each_netdev_continue_rcu(net, d) \ list_for_each_entry_continue_rcu(d, &(net)->dev_base_head, dev_list) #define for_each_netdev_in_bond_rcu(bond, slave) \ for_each_netdev_rcu(&init_net, slave) \ if (netdev_master_upper_dev_get_rcu(slave) == (bond)) #define net_device_entry(lh) list_entry(lh, struct net_device, dev_list) #define for_each_netdev_dump(net, d, ifindex) \ xa_for_each_start(&(net)->dev_by_index, (ifindex), (d), (ifindex)) static inline struct net_device *next_net_device(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = dev->dev_list.next; return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *next_net_device_rcu(struct net_device *dev) { struct list_head *lh; struct net *net; net = dev_net(dev); lh = rcu_dereference(list_next_rcu(&dev->dev_list)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } static inline struct net_device *first_net_device(struct net *net) { return list_empty(&net->dev_base_head) ? NULL : net_device_entry(net->dev_base_head.next); } static inline struct net_device *first_net_device_rcu(struct net *net) { struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head)); return lh == &net->dev_base_head ? NULL : net_device_entry(lh); } int netdev_boot_setup_check(struct net_device *dev); struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, const char *hwaddr); struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type); void dev_add_pack(struct packet_type *pt); void dev_remove_pack(struct packet_type *pt); void __dev_remove_pack(struct packet_type *pt); void dev_add_offload(struct packet_offload *po); void dev_remove_offload(struct packet_offload *po); int dev_get_iflink(const struct net_device *dev); int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb); int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr, struct net_device_path_stack *stack); struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags, unsigned short mask); struct net_device *dev_get_by_name(struct net *net, const char *name); struct net_device *dev_get_by_name_rcu(struct net *net, const char *name); struct net_device *__dev_get_by_name(struct net *net, const char *name); bool netdev_name_in_use(struct net *net, const char *name); int dev_alloc_name(struct net_device *dev, const char *name); int dev_open(struct net_device *dev, struct netlink_ext_ack *extack); void dev_close(struct net_device *dev); void dev_close_many(struct list_head *head, bool unlink); void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); u16 dev_pick_tx_zero(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); u16 dev_pick_tx_cpu_id(struct net_device *dev, struct sk_buff *skb, struct net_device *sb_dev); int __dev_queue_xmit(struct sk_buff *skb, struct net_device *sb_dev); int __dev_direct_xmit(struct sk_buff *skb, u16 queue_id); static inline int dev_queue_xmit(struct sk_buff *skb) { return __dev_queue_xmit(skb, NULL); } static inline int dev_queue_xmit_accel(struct sk_buff *skb, struct net_device *sb_dev) { return __dev_queue_xmit(skb, sb_dev); } static inline int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) { int ret; ret = __dev_direct_xmit(skb, queue_id); if (!dev_xmit_complete(ret)) kfree_skb(skb); return ret; } int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); static inline void unregister_netdevice(struct net_device *dev) { unregister_netdevice_queue(dev, NULL); } int netdev_refcnt_read(const struct net_device *dev); void free_netdev(struct net_device *dev); void netdev_freemem(struct net_device *dev); void init_dummy_netdev(struct net_device *dev); struct net_device *netdev_get_xmit_slave(struct net_device *dev, struct sk_buff *skb, bool all_slaves); struct net_device *netdev_sk_get_lowest_dev(struct net_device *dev, struct sock *sk); struct net_device *dev_get_by_index(struct net *net, int ifindex); struct net_device *__dev_get_by_index(struct net *net, int ifindex); struct net_device *netdev_get_by_index(struct net *net, int ifindex, netdevice_tracker *tracker, gfp_t gfp); struct net_device *netdev_get_by_name(struct net *net, const char *name, netdevice_tracker *tracker, gfp_t gfp); struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex); struct net_device *dev_get_by_napi_id(unsigned int napi_id); void netdev_copy_name(struct net_device *dev, char *name); static inline int dev_hard_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, const void *daddr, const void *saddr, unsigned int len) { if (!dev->header_ops || !dev->header_ops->create) return 0; return dev->header_ops->create(skb, dev, type, daddr, saddr, len); } static inline int dev_parse_header(const struct sk_buff *skb, unsigned char *haddr) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse) return 0; return dev->header_ops->parse(skb, haddr); } static inline __be16 dev_parse_header_protocol(const struct sk_buff *skb) { const struct net_device *dev = skb->dev; if (!dev->header_ops || !dev->header_ops->parse_protocol) return 0; return dev->header_ops->parse_protocol(skb); } /* ll_header must have at least hard_header_len allocated */ static inline bool dev_validate_header(const struct net_device *dev, char *ll_header, int len) { if (likely(len >= dev->hard_header_len)) return true; if (len < dev->min_header_len) return false; if (capable(CAP_SYS_RAWIO)) { memset(ll_header + len, 0, dev->hard_header_len - len); return true; } if (dev->header_ops && dev->header_ops->validate) return dev->header_ops->validate(ll_header, len); return false; } static inline bool dev_has_header(const struct net_device *dev) { return dev->header_ops && dev->header_ops->create; } /* * Incoming packets are placed on per-CPU queues */ struct softnet_data { struct list_head poll_list; struct sk_buff_head process_queue; /* stats */ unsigned int processed; unsigned int time_squeeze; #ifdef CONFIG_RPS struct softnet_data *rps_ipi_list; #endif unsigned int received_rps; bool in_net_rx_action; bool in_napi_threaded_poll; #ifdef CONFIG_NET_FLOW_LIMIT struct sd_flow_limit __rcu *flow_limit; #endif struct Qdisc *output_queue; struct Qdisc **output_queue_tailp; struct sk_buff *completion_queue; #ifdef CONFIG_XFRM_OFFLOAD struct sk_buff_head xfrm_backlog; #endif /* written and read only by owning cpu: */ struct { u16 recursion; u8 more; #ifdef CONFIG_NET_EGRESS u8 skip_txqueue; #endif } xmit; #ifdef CONFIG_RPS /* input_queue_head should be written by cpu owning this struct, * and only read by other cpus. Worth using a cache line. */ unsigned int input_queue_head ____cacheline_aligned_in_smp; /* Elements below can be accessed between CPUs for RPS/RFS */ call_single_data_t csd ____cacheline_aligned_in_smp; struct softnet_data *rps_ipi_next; unsigned int cpu; unsigned int input_queue_tail; #endif struct sk_buff_head input_pkt_queue; struct napi_struct backlog; atomic_t dropped ____cacheline_aligned_in_smp; /* Another possibly contended cache line */ spinlock_t defer_lock ____cacheline_aligned_in_smp; int defer_count; int defer_ipi_scheduled; struct sk_buff *defer_list; call_single_data_t defer_csd; }; DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data); static inline int dev_recursion_level(void) { return this_cpu_read(softnet_data.xmit.recursion); } void __netif_schedule(struct Qdisc *q); void netif_schedule_queue(struct netdev_queue *txq); static inline void netif_tx_schedule_all(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) netif_schedule_queue(netdev_get_tx_queue(dev, i)); } static __always_inline void netif_tx_start_queue(struct netdev_queue *dev_queue) { clear_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_start_queue - allow transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. */ static inline void netif_start_queue(struct net_device *dev) { netif_tx_start_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif_tx_start_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_start_queue(txq); } } void netif_tx_wake_queue(struct netdev_queue *dev_queue); /** * netif_wake_queue - restart transmit * @dev: network device * * Allow upper layers to call the device hard_start_xmit routine. * Used for flow control when transmit resources are available. */ static inline void netif_wake_queue(struct net_device *dev) { netif_tx_wake_queue(netdev_get_tx_queue(dev, 0)); } static inline void netif_tx_wake_all_queues(struct net_device *dev) { unsigned int i; for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); netif_tx_wake_queue(txq); } } static __always_inline void netif_tx_stop_queue(struct netdev_queue *dev_queue) { /* Must be an atomic op see netif_txq_try_stop() */ set_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_stop_queue - stop transmitted packets * @dev: network device * * Stop upper layers calling the device hard_start_xmit routine. * Used for flow control when transmit resources are unavailable. */ static inline void netif_stop_queue(struct net_device *dev) { netif_tx_stop_queue(netdev_get_tx_queue(dev, 0)); } void netif_tx_stop_all_queues(struct net_device *dev); static inline bool netif_tx_queue_stopped(const struct netdev_queue *dev_queue) { return test_bit(__QUEUE_STATE_DRV_XOFF, &dev_queue->state); } /** * netif_queue_stopped - test if transmit queue is flowblocked * @dev: network device * * Test if transmit queue on device is currently unable to send. */ static inline bool netif_queue_stopped(const struct net_device *dev) { return netif_tx_queue_stopped(netdev_get_tx_queue(dev, 0)); } static inline bool netif_xmit_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF; } static inline bool netif_xmit_frozen_or_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_ANY_XOFF_OR_FROZEN; } static inline bool netif_xmit_frozen_or_drv_stopped(const struct netdev_queue *dev_queue) { return dev_queue->state & QUEUE_STATE_DRV_XOFF_OR_FROZEN; } /** * netdev_queue_set_dql_min_limit - set dql minimum limit * @dev_queue: pointer to transmit queue * @min_limit: dql minimum limit * * Forces xmit_more() to return true until the minimum threshold * defined by @min_limit is reached (or until the tx queue is * empty). Warning: to be use with care, misuse will impact the * latency. */ static inline void netdev_queue_set_dql_min_limit(struct netdev_queue *dev_queue, unsigned int min_limit) { #ifdef CONFIG_BQL dev_queue->dql.min_limit = min_limit; #endif } static inline int netdev_queue_dql_avail(const struct netdev_queue *txq) { #ifdef CONFIG_BQL /* Non-BQL migrated drivers will return 0, too. */ return dql_avail(&txq->dql); #else return 0; #endif } /** * netdev_txq_bql_enqueue_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their ndo_start_xmit(), * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_enqueue_prefetchw(struct netdev_queue *dev_queue) { #ifdef CONFIG_BQL prefetchw(&dev_queue->dql.num_queued); #endif } /** * netdev_txq_bql_complete_prefetchw - prefetch bql data for write * @dev_queue: pointer to transmit queue * * BQL enabled drivers might use this helper in their TX completion path, * to give appropriate hint to the CPU. */ static inline void netdev_txq_bql_complete_prefetchw(struct netdev_queue *dev_queue) { #ifdef CONFIG_BQL prefetchw(&dev_queue->dql.limit); #endif } /** * netdev_tx_sent_queue - report the number of bytes queued to a given tx queue * @dev_queue: network device queue * @bytes: number of bytes queued to the device queue * * Report the number of bytes queued for sending/completion to the network * device hardware queue. @bytes should be a good approximation and should * exactly match netdev_completed_queue() @bytes. * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes) { #ifdef CONFIG_BQL dql_queued(&dev_queue->dql, bytes); if (likely(dql_avail(&dev_queue->dql) >= 0)) return; set_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); /* * The XOFF flag must be set before checking the dql_avail below, * because in netdev_tx_completed_queue we update the dql_completed * before checking the XOFF flag. */ smp_mb(); /* check again in case another CPU has just made room avail */ if (unlikely(dql_avail(&dev_queue->dql) >= 0)) clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state); #endif } /* Variant of netdev_tx_sent_queue() for drivers that are aware * that they should not test BQL status themselves. * We do want to change __QUEUE_STATE_STACK_XOFF only for the last * skb of a batch. * Returns true if the doorbell must be used to kick the NIC. */ static inline bool __netdev_tx_sent_queue(struct netdev_queue *dev_queue, unsigned int bytes, bool xmit_more) { if (xmit_more) { #ifdef CONFIG_BQL dql_queued(&dev_queue->dql, bytes); #endif return netif_tx_queue_stopped(dev_queue); } netdev_tx_sent_queue(dev_queue, bytes); return true; } /** * netdev_sent_queue - report the number of bytes queued to hardware * @dev: network device * @bytes: number of bytes queued to the hardware device queue * * Report the number of bytes queued for sending/completion to the network * device hardware queue#0. @bytes should be a good approximation and should * exactly match netdev_completed_queue() @bytes. * This is typically called once per packet, from ndo_start_xmit(). */ static inline void netdev_sent_queue(struct net_device *dev, unsigned int bytes) { netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes); } static inline bool __netdev_sent_queue(struct net_device *dev, unsigned int bytes, bool xmit_more) { return __netdev_tx_sent_queue(netdev_get_tx_queue(dev, 0), bytes, xmit_more); } /** * netdev_tx_completed_queue - report number of packets/bytes at TX completion. * @dev_queue: network device queue * @pkts: number of packets (currently ignored) * @bytes: number of bytes dequeued from the device queue * * Must be called at most once per TX completion round (and not per * individual packet), so that BQL can adjust its limits appropriately. */ static inline void netdev_tx_completed_queue(struct netdev_queue *dev_queue, unsigned int pkts, unsigned int bytes) { #ifdef CONFIG_BQL if (unlikely(!bytes)) return; dql_completed(&dev_queue->dql, bytes); /* * Without the memory barrier there is a small possiblity that * netdev_tx_sent_queue will miss the update and cause the queue to * be stopped forever */ smp_mb(); /* NOTE: netdev_txq_completed_mb() assumes this exists */ if (unlikely(dql_avail(&dev_queue->dql) < 0)) return; if (test_and_clear_bit(__QUEUE_STATE_STACK_XOFF, &dev_queue->state)) netif_schedule_queue(dev_queue); #endif } /** * netdev_completed_queue - report bytes and packets completed by device * @dev: network device * @pkts: actual number of packets sent over the medium * @bytes: actual number of bytes sent over the medium * * Report the number of bytes and packets transmitted by the network device * hardware queue over the physical medium, @bytes must exactly match the * @bytes amount passed to netdev_sent_queue() */ static inline void netdev_completed_queue(struct net_device *dev, unsigned int pkts, unsigned int bytes) { netdev_tx_completed_queue(netdev_get_tx_queue(dev, 0), pkts, bytes); } static inline void netdev_tx_reset_queue(struct netdev_queue *q) { #ifdef CONFIG_BQL clear_bit(__QUEUE_STATE_STACK_XOFF, &q->state); dql_reset(&q->dql); #endif } /** * netdev_reset_queue - reset the packets and bytes count of a network device * @dev_queue: network device * * Reset the bytes and packet count of a network device and clear the * software flow control OFF bit for this network device */ static inline void netdev_reset_queue(struct net_device *dev_queue) { netdev_tx_reset_queue(netdev_get_tx_queue(dev_queue, 0)); } /** * netdev_cap_txqueue - check if selected tx queue exceeds device queues * @dev: network device * @queue_index: given tx queue index * * Returns 0 if given tx queue index >= number of device tx queues, * otherwise returns the originally passed tx queue index. */ static inline u16 netdev_cap_txqueue(struct net_device *dev, u16 queue_index) { if (unlikely(queue_index >= dev->real_num_tx_queues)) { net_warn_ratelimited("%s selects TX queue %d, but real number of TX queues is %d\n", dev->name, queue_index, dev->real_num_tx_queues); return 0; } return queue_index; } /** * netif_running - test if up * @dev: network device * * Test if the device has been brought up. */ static inline bool netif_running(const struct net_device *dev) { return test_bit(__LINK_STATE_START, &dev->state); } /* * Routines to manage the subqueues on a device. We only need start, * stop, and a check if it's stopped. All other device management is * done at the overall netdevice level. * Also test the device if we're multiqueue. */ /** * netif_start_subqueue - allow sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Start individual transmit queue of a device with multiple transmit queues. */ static inline void netif_start_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_start_queue(txq); } /** * netif_stop_subqueue - stop sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Stop individual transmit queue of a device with multiple transmit queues. */ static inline void netif_stop_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_stop_queue(txq); } /** * __netif_subqueue_stopped - test status of subqueue * @dev: network device * @queue_index: sub queue index * * Check individual transmit queue of a device with multiple transmit queues. */ static inline bool __netif_subqueue_stopped(const struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); return netif_tx_queue_stopped(txq); } /** * netif_subqueue_stopped - test status of subqueue * @dev: network device * @skb: sub queue buffer pointer * * Check individual transmit queue of a device with multiple transmit queues. */ static inline bool netif_subqueue_stopped(const struct net_device *dev, struct sk_buff *skb) { return __netif_subqueue_stopped(dev, skb_get_queue_mapping(skb)); } /** * netif_wake_subqueue - allow sending packets on subqueue * @dev: network device * @queue_index: sub queue index * * Resume individual transmit queue of a device with multiple transmit queues. */ static inline void netif_wake_subqueue(struct net_device *dev, u16 queue_index) { struct netdev_queue *txq = netdev_get_tx_queue(dev, queue_index); netif_tx_wake_queue(txq); } #ifdef CONFIG_XPS int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index); int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type); /** * netif_attr_test_mask - Test a CPU or Rx queue set in a mask * @j: CPU/Rx queue index * @mask: bitmask of all cpus/rx queues * @nr_bits: number of bits in the bitmask * * Test if a CPU or Rx queue index is set in a mask of all CPU/Rx queues. */ static inline bool netif_attr_test_mask(unsigned long j, const unsigned long *mask, unsigned int nr_bits) { cpu_max_bits_warn(j, nr_bits); return test_bit(j, mask); } /** * netif_attr_test_online - Test for online CPU/Rx queue * @j: CPU/Rx queue index * @online_mask: bitmask for CPUs/Rx queues that are online * @nr_bits: number of bits in the bitmask * * Returns true if a CPU/Rx queue is online. */ static inline bool netif_attr_test_online(unsigned long j, const unsigned long *online_mask, unsigned int nr_bits) { cpu_max_bits_warn(j, nr_bits); if (online_mask) return test_bit(j, online_mask); return (j < nr_bits); } /** * netif_attrmask_next - get the next CPU/Rx queue in a cpu/Rx queues mask * @n: CPU/Rx queue index * @srcp: the cpumask/Rx queue mask pointer * @nr_bits: number of bits in the bitmask * * Returns >= nr_bits if no further CPUs/Rx queues set. */ static inline unsigned int netif_attrmask_next(int n, const unsigned long *srcp, unsigned int nr_bits) { /* -1 is a legal arg here. */ if (n != -1) cpu_max_bits_warn(n, nr_bits); if (srcp) return find_next_bit(srcp, nr_bits, n + 1); return n + 1; } /** * netif_attrmask_next_and - get the next CPU/Rx queue in \*src1p & \*src2p * @n: CPU/Rx queue index * @src1p: the first CPUs/Rx queues mask pointer * @src2p: the second CPUs/Rx queues mask pointer * @nr_bits: number of bits in the bitmask * * Returns >= nr_bits if no further CPUs/Rx queues set in both. */ static inline int netif_attrmask_next_and(int n, const unsigned long *src1p, const unsigned long *src2p, unsigned int nr_bits) { /* -1 is a legal arg here. */ if (n != -1) cpu_max_bits_warn(n, nr_bits); if (src1p && src2p) return find_next_and_bit(src1p, src2p, nr_bits, n + 1); else if (src1p) return find_next_bit(src1p, nr_bits, n + 1); else if (src2p) return find_next_bit(src2p, nr_bits, n + 1); return n + 1; } #else static inline int netif_set_xps_queue(struct net_device *dev, const struct cpumask *mask, u16 index) { return 0; } static inline int __netif_set_xps_queue(struct net_device *dev, const unsigned long *mask, u16 index, enum xps_map_type type) { return 0; } #endif /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device * * Check if device has multiple transmit queues */ static inline bool netif_is_multiqueue(const struct net_device *dev) { return dev->num_tx_queues > 1; } int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq); #ifdef CONFIG_SYSFS int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq); #else static inline int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxqs) { dev->real_num_rx_queues = rxqs; return 0; } #endif int netif_set_real_num_queues(struct net_device *dev, unsigned int txq, unsigned int rxq); int netif_get_num_default_rss_queues(void); void dev_kfree_skb_irq_reason(struct sk_buff *skb, enum skb_drop_reason reason); void dev_kfree_skb_any_reason(struct sk_buff *skb, enum skb_drop_reason reason); /* * It is not allowed to call kfree_skb() or consume_skb() from hardware * interrupt context or with hardware interrupts being disabled. * (in_hardirq() || irqs_disabled()) * * We provide four helpers that can be used in following contexts : * * dev_kfree_skb_irq(skb) when caller drops a packet from irq context, * replacing kfree_skb(skb) * * dev_consume_skb_irq(skb) when caller consumes a packet from irq context. * Typically used in place of consume_skb(skb) in TX completion path * * dev_kfree_skb_any(skb) when caller doesn't know its current irq context, * replacing kfree_skb(skb) * * dev_consume_skb_any(skb) when caller doesn't know its current irq context, * and consumed a packet. Used in place of consume_skb(skb) */ static inline void dev_kfree_skb_irq(struct sk_buff *skb) { dev_kfree_skb_irq_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_irq(struct sk_buff *skb) { dev_kfree_skb_irq_reason(skb, SKB_CONSUMED); } static inline void dev_kfree_skb_any(struct sk_buff *skb) { dev_kfree_skb_any_reason(skb, SKB_DROP_REASON_NOT_SPECIFIED); } static inline void dev_consume_skb_any(struct sk_buff *skb) { dev_kfree_skb_any_reason(skb, SKB_CONSUMED); } u32 bpf_prog_run_generic_xdp(struct sk_buff *skb, struct xdp_buff *xdp, struct bpf_prog *xdp_prog); void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff **pskb); int netif_rx(struct sk_buff *skb); int __netif_rx(struct sk_buff *skb); int netif_receive_skb(struct sk_buff *skb); int netif_receive_skb_core(struct sk_buff *skb); void netif_receive_skb_list_internal(struct list_head *head); void netif_receive_skb_list(struct list_head *head); gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb); void napi_gro_flush(struct napi_struct *napi, bool flush_old); struct sk_buff *napi_get_frags(struct napi_struct *napi); void napi_get_frags_check(struct napi_struct *napi); gro_result_t napi_gro_frags(struct napi_struct *napi); static inline void napi_free_frags(struct napi_struct *napi) { kfree_skb(napi->skb); napi->skb = NULL; } bool netdev_is_rx_handler_busy(struct net_device *dev); int netdev_rx_handler_register(struct net_device *dev, rx_handler_func_t *rx_handler, void *rx_handler_data); void netdev_rx_handler_unregister(struct net_device *dev); bool dev_valid_name(const char *name); static inline bool is_socket_ioctl_cmd(unsigned int cmd) { return _IOC_TYPE(cmd) == SOCK_IOC_TYPE; } int get_user_ifreq(struct ifreq *ifr, void __user **ifrdata, void __user *arg); int put_user_ifreq(struct ifreq *ifr, void __user *arg); int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr, void __user *data, bool *need_copyout); int dev_ifconf(struct net *net, struct ifconf __user *ifc); int generic_hwtstamp_get_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg); int generic_hwtstamp_set_lower(struct net_device *dev, struct kernel_hwtstamp_config *kernel_cfg, struct netlink_ext_ack *extack); int dev_set_hwtstamp_phylib(struct net_device *dev, struct kernel_hwtstamp_config *cfg, struct netlink_ext_ack *extack); int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata); unsigned int dev_get_flags(const struct net_device *); int __dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int dev_change_flags(struct net_device *dev, unsigned int flags, struct netlink_ext_ack *extack); int dev_set_alias(struct net_device *, const char *, size_t); int dev_get_alias(const struct net_device *, char *, size_t); int __dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat, int new_ifindex); static inline int dev_change_net_namespace(struct net_device *dev, struct net *net, const char *pat) { return __dev_change_net_namespace(dev, net, pat, 0); } int __dev_set_mtu(struct net_device *, int); int dev_set_mtu(struct net_device *, int); int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr, struct netlink_ext_ack *extack); int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_set_mac_address_user(struct net_device *dev, struct sockaddr *sa, struct netlink_ext_ack *extack); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name); int dev_get_port_parent_id(struct net_device *dev, struct netdev_phys_item_id *ppid, bool recurse); bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b); struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again); struct sk_buff *dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, int *ret); int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog); u8 dev_xdp_prog_count(struct net_device *dev); u32 dev_xdp_prog_id(struct net_device *dev, enum bpf_xdp_mode mode); int __dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb(struct net_device *dev, struct sk_buff *skb); int dev_forward_skb_nomtu(struct net_device *dev, struct sk_buff *skb); bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb); static __always_inline bool __is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb, const bool check_mtu) { const u32 vlan_hdr_len = 4; /* VLAN_HLEN */ unsigned int len; if (!(dev->flags & IFF_UP)) return false; if (!check_mtu) return true; len = dev->mtu + dev->hard_header_len + vlan_hdr_len; if (skb->len <= len) return true; /* if TSO is enabled, we don't care about the length as the packet * could be forwarded without being segmented before */ if (skb_is_gso(skb)) return true; return false; } void netdev_core_stats_inc(struct net_device *dev, u32 offset); #define DEV_CORE_STATS_INC(FIELD) \ static inline void dev_core_stats_##FIELD##_inc(struct net_device *dev) \ { \ netdev_core_stats_inc(dev, \ offsetof(struct net_device_core_stats, FIELD)); \ } DEV_CORE_STATS_INC(rx_dropped) DEV_CORE_STATS_INC(tx_dropped) DEV_CORE_STATS_INC(rx_nohandler) DEV_CORE_STATS_INC(rx_otherhost_dropped) #undef DEV_CORE_STATS_INC static __always_inline int ____dev_forward_skb(struct net_device *dev, struct sk_buff *skb, const bool check_mtu) { if (skb_orphan_frags(skb, GFP_ATOMIC) || unlikely(!__is_skb_forwardable(dev, skb, check_mtu))) { dev_core_stats_rx_dropped_inc(dev); kfree_skb(skb); return NET_RX_DROP; } skb_scrub_packet(skb, !net_eq(dev_net(dev), dev_net(skb->dev))); skb->priority = 0; return 0; } bool dev_nit_active(struct net_device *dev); void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev); static inline void __dev_put(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT this_cpu_dec(*dev->pcpu_refcnt); #else refcount_dec(&dev->dev_refcnt); #endif } } static inline void __dev_hold(struct net_device *dev) { if (dev) { #ifdef CONFIG_PCPU_DEV_REFCNT this_cpu_inc(*dev->pcpu_refcnt); #else refcount_inc(&dev->dev_refcnt); #endif } } static inline void __netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER ref_tracker_alloc(&dev->refcnt_tracker, tracker, gfp); #endif } /* netdev_tracker_alloc() can upgrade a prior untracked reference * taken by dev_get_by_name()/dev_get_by_index() to a tracked one. */ static inline void netdev_tracker_alloc(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER refcount_dec(&dev->refcnt_tracker.no_tracker); __netdev_tracker_alloc(dev, tracker, gfp); #endif } static inline void netdev_tracker_free(struct net_device *dev, netdevice_tracker *tracker) { #ifdef CONFIG_NET_DEV_REFCNT_TRACKER ref_tracker_free(&dev->refcnt_tracker, tracker); #endif } static inline void netdev_hold(struct net_device *dev, netdevice_tracker *tracker, gfp_t gfp) { if (dev) { __dev_hold(dev); __netdev_tracker_alloc(dev, tracker, gfp); } } static inline void netdev_put(struct net_device *dev, netdevice_tracker *tracker) { if (dev) { netdev_tracker_free(dev, tracker); __dev_put(dev); } } /** * dev_hold - get reference to device * @dev: network device * * Hold reference to device to keep it from being freed. * Try using netdev_hold() instead. */ static inline void dev_hold(struct net_device *dev) { netdev_hold(dev, NULL, GFP_ATOMIC); } /** * dev_put - release reference to device * @dev: network device * * Release reference to device to allow it to be freed. * Try using netdev_put() instead. */ static inline void dev_put(struct net_device *dev) { netdev_put(dev, NULL); } DEFINE_FREE(dev_put, struct net_device *, if (_T) dev_put(_T)) static inline void netdev_ref_replace(struct net_device *odev, struct net_device *ndev, netdevice_tracker *tracker, gfp_t gfp) { if (odev) netdev_tracker_free(odev, tracker); __dev_hold(ndev); __dev_put(odev); if (ndev) __netdev_tracker_alloc(ndev, tracker, gfp); } /* Carrier loss detection, dial on demand. The functions netif_carrier_on * and _off may be called from IRQ context, but it is caller * who is responsible for serialization of these calls. * * The name carrier is inappropriate, these functions should really be * called netif_lowerlayer_*() because they represent the state of any * kind of lower layer not just hardware media. */ void linkwatch_fire_event(struct net_device *dev); /** * linkwatch_sync_dev - sync linkwatch for the given device * @dev: network device to sync linkwatch for * * Sync linkwatch for the given device, removing it from the * pending work list (if queued). */ void linkwatch_sync_dev(struct net_device *dev); /** * netif_carrier_ok - test if carrier present * @dev: network device * * Check if carrier is present on device */ static inline bool netif_carrier_ok(const struct net_device *dev) { return !test_bit(__LINK_STATE_NOCARRIER, &dev->state); } unsigned long dev_trans_start(struct net_device *dev); void __netdev_watchdog_up(struct net_device *dev); void netif_carrier_on(struct net_device *dev); void netif_carrier_off(struct net_device *dev); void netif_carrier_event(struct net_device *dev); /** * netif_dormant_on - mark device as dormant. * @dev: network device * * Mark device as dormant (as per RFC2863). * * The dormant state indicates that the relevant interface is not * actually in a condition to pass packets (i.e., it is not 'up') but is * in a "pending" state, waiting for some external event. For "on- * demand" interfaces, this new state identifies the situation where the * interface is waiting for events to place it in the up state. */ static inline void netif_dormant_on(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_DORMANT, &dev->state)) linkwatch_fire_event(dev); } /** * netif_dormant_off - set device as not dormant. * @dev: network device * * Device is not in dormant state. */ static inline void netif_dormant_off(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_DORMANT, &dev->state)) linkwatch_fire_event(dev); } /** * netif_dormant - test if device is dormant * @dev: network device * * Check if device is dormant. */ static inline bool netif_dormant(const struct net_device *dev) { return test_bit(__LINK_STATE_DORMANT, &dev->state); } /** * netif_testing_on - mark device as under test. * @dev: network device * * Mark device as under test (as per RFC2863). * * The testing state indicates that some test(s) must be performed on * the interface. After completion, of the test, the interface state * will change to up, dormant, or down, as appropriate. */ static inline void netif_testing_on(struct net_device *dev) { if (!test_and_set_bit(__LINK_STATE_TESTING, &dev->state)) linkwatch_fire_event(dev); } /** * netif_testing_off - set device as not under test. * @dev: network device * * Device is not in testing state. */ static inline void netif_testing_off(struct net_device *dev) { if (test_and_clear_bit(__LINK_STATE_TESTING, &dev->state)) linkwatch_fire_event(dev); } /** * netif_testing - test if device is under test * @dev: network device * * Check if device is under test */ static inline bool netif_testing(const struct net_device *dev) { return test_bit(__LINK_STATE_TESTING, &dev->state); } /** * netif_oper_up - test if device is operational * @dev: network device * * Check if carrier is operational */ static inline bool netif_oper_up(const struct net_device *dev) { unsigned int operstate = READ_ONCE(dev->operstate); return operstate == IF_OPER_UP || operstate == IF_OPER_UNKNOWN /* backward compat */; } /** * netif_device_present - is device available or removed * @dev: network device * * Check if device has not been removed from system. */ static inline bool netif_device_present(const struct net_device *dev) { return test_bit(__LINK_STATE_PRESENT, &dev->state); } void netif_device_detach(struct net_device *dev); void netif_device_attach(struct net_device *dev); /* * Network interface message level settings */ enum { NETIF_MSG_DRV_BIT, NETIF_MSG_PROBE_BIT, NETIF_MSG_LINK_BIT, NETIF_MSG_TIMER_BIT, NETIF_MSG_IFDOWN_BIT, NETIF_MSG_IFUP_BIT, NETIF_MSG_RX_ERR_BIT, NETIF_MSG_TX_ERR_BIT, NETIF_MSG_TX_QUEUED_BIT, NETIF_MSG_INTR_BIT, NETIF_MSG_TX_DONE_BIT, NETIF_MSG_RX_STATUS_BIT, NETIF_MSG_PKTDATA_BIT, NETIF_MSG_HW_BIT, NETIF_MSG_WOL_BIT, /* When you add a new bit above, update netif_msg_class_names array * in net/ethtool/common.c */ NETIF_MSG_CLASS_COUNT, }; /* Both ethtool_ops interface and internal driver implementation use u32 */ static_assert(NETIF_MSG_CLASS_COUNT <= 32); #define __NETIF_MSG_BIT(bit) ((u32)1 << (bit)) #define __NETIF_MSG(name) __NETIF_MSG_BIT(NETIF_MSG_ ## name ## _BIT) #define NETIF_MSG_DRV __NETIF_MSG(DRV) #define NETIF_MSG_PROBE __NETIF_MSG(PROBE) #define NETIF_MSG_LINK __NETIF_MSG(LINK) #define NETIF_MSG_TIMER __NETIF_MSG(TIMER) #define NETIF_MSG_IFDOWN __NETIF_MSG(IFDOWN) #define NETIF_MSG_IFUP __NETIF_MSG(IFUP) #define NETIF_MSG_RX_ERR __NETIF_MSG(RX_ERR) #define NETIF_MSG_TX_ERR __NETIF_MSG(TX_ERR) #define NETIF_MSG_TX_QUEUED __NETIF_MSG(TX_QUEUED) #define NETIF_MSG_INTR __NETIF_MSG(INTR) #define NETIF_MSG_TX_DONE __NETIF_MSG(TX_DONE) #define NETIF_MSG_RX_STATUS __NETIF_MSG(RX_STATUS) #define NETIF_MSG_PKTDATA __NETIF_MSG(PKTDATA) #define NETIF_MSG_HW __NETIF_MSG(HW) #define NETIF_MSG_WOL __NETIF_MSG(WOL) #define netif_msg_drv(p) ((p)->msg_enable & NETIF_MSG_DRV) #define netif_msg_probe(p) ((p)->msg_enable & NETIF_MSG_PROBE) #define netif_msg_link(p) ((p)->msg_enable & NETIF_MSG_LINK) #define netif_msg_timer(p) ((p)->msg_enable & NETIF_MSG_TIMER) #define netif_msg_ifdown(p) ((p)->msg_enable & NETIF_MSG_IFDOWN) #define netif_msg_ifup(p) ((p)->msg_enable & NETIF_MSG_IFUP) #define netif_msg_rx_err(p) ((p)->msg_enable & NETIF_MSG_RX_ERR) #define netif_msg_tx_err(p) ((p)->msg_enable & NETIF_MSG_TX_ERR) #define netif_msg_tx_queued(p) ((p)->msg_enable & NETIF_MSG_TX_QUEUED) #define netif_msg_intr(p) ((p)->msg_enable & NETIF_MSG_INTR) #define netif_msg_tx_done(p) ((p)->msg_enable & NETIF_MSG_TX_DONE) #define netif_msg_rx_status(p) ((p)->msg_enable & NETIF_MSG_RX_STATUS) #define netif_msg_pktdata(p) ((p)->msg_enable & NETIF_MSG_PKTDATA) #define netif_msg_hw(p) ((p)->msg_enable & NETIF_MSG_HW) #define netif_msg_wol(p) ((p)->msg_enable & NETIF_MSG_WOL) static inline u32 netif_msg_init(int debug_value, int default_msg_enable_bits) { /* use default */ if (debug_value < 0 || debug_value >= (sizeof(u32) * 8)) return default_msg_enable_bits; if (debug_value == 0) /* no output */ return 0; /* set low N bits */ return (1U << debug_value) - 1; } static inline void __netif_tx_lock(struct netdev_queue *txq, int cpu) { spin_lock(&txq->_xmit_lock); /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, cpu); } static inline bool __netif_tx_acquire(struct netdev_queue *txq) { __acquire(&txq->_xmit_lock); return true; } static inline void __netif_tx_release(struct netdev_queue *txq) { __release(&txq->_xmit_lock); } static inline void __netif_tx_lock_bh(struct netdev_queue *txq) { spin_lock_bh(&txq->_xmit_lock); /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } static inline bool __netif_tx_trylock(struct netdev_queue *txq) { bool ok = spin_trylock(&txq->_xmit_lock); if (likely(ok)) { /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, smp_processor_id()); } return ok; } static inline void __netif_tx_unlock(struct netdev_queue *txq) { /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock(&txq->_xmit_lock); } static inline void __netif_tx_unlock_bh(struct netdev_queue *txq) { /* Pairs with READ_ONCE() in __dev_queue_xmit() */ WRITE_ONCE(txq->xmit_lock_owner, -1); spin_unlock_bh(&txq->_xmit_lock); } /* * txq->trans_start can be read locklessly from dev_watchdog() */ static inline void txq_trans_update(struct netdev_queue *txq) { if (txq->xmit_lock_owner != -1) WRITE_ONCE(txq->trans_start, jiffies); } static inline void txq_trans_cond_update(struct netdev_queue *txq) { unsigned long now = jiffies; if (READ_ONCE(txq->trans_start) != now) WRITE_ONCE(txq->trans_start, now); } /* legacy drivers only, netdev_start_xmit() sets txq->trans_start */ static inline void netif_trans_update(struct net_device *dev) { struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); txq_trans_cond_update(txq); } /** * netif_tx_lock - grab network device transmit lock * @dev: network device * * Get network device transmit lock */ void netif_tx_lock(struct net_device *dev); static inline void netif_tx_lock_bh(struct net_device *dev) { local_bh_disable(); netif_tx_lock(dev); } void netif_tx_unlock(struct net_device *dev); static inline void netif_tx_unlock_bh(struct net_device *dev) { netif_tx_unlock(dev); local_bh_enable(); } #define HARD_TX_LOCK(dev, txq, cpu) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_lock(txq, cpu); \ } else { \ __netif_tx_acquire(txq); \ } \ } #define HARD_TX_TRYLOCK(dev, txq) \ (((dev->features & NETIF_F_LLTX) == 0) ? \ __netif_tx_trylock(txq) : \ __netif_tx_acquire(txq)) #define HARD_TX_UNLOCK(dev, txq) { \ if ((dev->features & NETIF_F_LLTX) == 0) { \ __netif_tx_unlock(txq); \ } else { \ __netif_tx_release(txq); \ } \ } static inline void netif_tx_disable(struct net_device *dev) { unsigned int i; int cpu; local_bh_disable(); cpu = smp_processor_id(); spin_lock(&dev->tx_global_lock); for (i = 0; i < dev->num_tx_queues; i++) { struct netdev_queue *txq = netdev_get_tx_queue(dev, i); __netif_tx_lock(txq, cpu); netif_tx_stop_queue(txq); __netif_tx_unlock(txq); } spin_unlock(&dev->tx_global_lock); local_bh_enable(); } static inline void netif_addr_lock(struct net_device *dev) { unsigned char nest_level = 0; #ifdef CONFIG_LOCKDEP nest_level = dev->nested_level; #endif spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_lock_bh(struct net_device *dev) { unsigned char nest_level = 0; #ifdef CONFIG_LOCKDEP nest_level = dev->nested_level; #endif local_bh_disable(); spin_lock_nested(&dev->addr_list_lock, nest_level); } static inline void netif_addr_unlock(struct net_device *dev) { spin_unlock(&dev->addr_list_lock); } static inline void netif_addr_unlock_bh(struct net_device *dev) { spin_unlock_bh(&dev->addr_list_lock); } /* * dev_addrs walker. Should be used only for read access. Call with * rcu_read_lock held. */ #define for_each_dev_addr(dev, ha) \ list_for_each_entry_rcu(ha, &dev->dev_addrs.list, list) /* These functions live elsewhere (drivers/net/net_init.c, but related) */ void ether_setup(struct net_device *dev); /* Allocate dummy net_device */ struct net_device *alloc_netdev_dummy(int sizeof_priv); /* Support for loadable net-drivers */ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, unsigned char name_assign_type, void (*setup)(struct net_device *), unsigned int txqs, unsigned int rxqs); #define alloc_netdev(sizeof_priv, name, name_assign_type, setup) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, 1, 1) #define alloc_netdev_mq(sizeof_priv, name, name_assign_type, setup, count) \ alloc_netdev_mqs(sizeof_priv, name, name_assign_type, setup, count, \ count) int register_netdev(struct net_device *dev); void unregister_netdev(struct net_device *dev); int devm_register_netdev(struct device *dev, struct net_device *ndev); /* General hardware address lists handling functions */ int __hw_addr_sync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); void __hw_addr_unsync(struct netdev_hw_addr_list *to_list, struct netdev_hw_addr_list *from_list, int addr_len); int __hw_addr_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)); int __hw_addr_ref_sync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *, int), int (*unsync)(struct net_device *, const unsigned char *, int)); void __hw_addr_ref_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *, int)); void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list, struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)); void __hw_addr_init(struct netdev_hw_addr_list *list); /* Functions used for device addresses handling */ void dev_addr_mod(struct net_device *dev, unsigned int offset, const void *addr, size_t len); static inline void __dev_addr_set(struct net_device *dev, const void *addr, size_t len) { dev_addr_mod(dev, 0, addr, len); } static inline void dev_addr_set(struct net_device *dev, const u8 *addr) { __dev_addr_set(dev, addr, dev->addr_len); } int dev_addr_add(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); int dev_addr_del(struct net_device *dev, const unsigned char *addr, unsigned char addr_type); /* Functions used for unicast addresses handling */ int dev_uc_add(struct net_device *dev, const unsigned char *addr); int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr); int dev_uc_del(struct net_device *dev, const unsigned char *addr); int dev_uc_sync(struct net_device *to, struct net_device *from); int dev_uc_sync_multiple(struct net_device *to, struct net_device *from); void dev_uc_unsync(struct net_device *to, struct net_device *from); void dev_uc_flush(struct net_device *dev); void dev_uc_init(struct net_device *dev); /** * __dev_uc_sync - Synchonize device's unicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * Add newly added addresses to the interface, and release * addresses that have been deleted. */ static inline int __dev_uc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { return __hw_addr_sync_dev(&dev->uc, dev, sync, unsync); } /** * __dev_uc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_uc_sync(). */ static inline void __dev_uc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { __hw_addr_unsync_dev(&dev->uc, dev, unsync); } /* Functions used for multicast addresses handling */ int dev_mc_add(struct net_device *dev, const unsigned char *addr); int dev_mc_add_global(struct net_device *dev, const unsigned char *addr); int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr); int dev_mc_del(struct net_device *dev, const unsigned char *addr); int dev_mc_del_global(struct net_device *dev, const unsigned char *addr); int dev_mc_sync(struct net_device *to, struct net_device *from); int dev_mc_sync_multiple(struct net_device *to, struct net_device *from); void dev_mc_unsync(struct net_device *to, struct net_device *from); void dev_mc_flush(struct net_device *dev); void dev_mc_init(struct net_device *dev); /** * __dev_mc_sync - Synchonize device's multicast list * @dev: device to sync * @sync: function to call if address should be added * @unsync: function to call if address should be removed * * Add newly added addresses to the interface, and release * addresses that have been deleted. */ static inline int __dev_mc_sync(struct net_device *dev, int (*sync)(struct net_device *, const unsigned char *), int (*unsync)(struct net_device *, const unsigned char *)) { return __hw_addr_sync_dev(&dev->mc, dev, sync, unsync); } /** * __dev_mc_unsync - Remove synchronized addresses from device * @dev: device to sync * @unsync: function to call if address should be removed * * Remove all addresses that were added to the device by dev_mc_sync(). */ static inline void __dev_mc_unsync(struct net_device *dev, int (*unsync)(struct net_device *, const unsigned char *)) { __hw_addr_unsync_dev(&dev->mc, dev, unsync); } /* Functions used for secondary unicast and multicast support */ void dev_set_rx_mode(struct net_device *dev); int dev_set_promiscuity(struct net_device *dev, int inc); int dev_set_allmulti(struct net_device *dev, int inc); void netdev_state_change(struct net_device *dev); void __netdev_notify_peers(struct net_device *dev); void netdev_notify_peers(struct net_device *dev); void netdev_features_change(struct net_device *dev); /* Load a device via the kmod */ void dev_load(struct net *net, const char *name); struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, struct rtnl_link_stats64 *storage); void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, const struct net_device_stats *netdev_stats); void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, const struct pcpu_sw_netstats __percpu *netstats); void dev_get_tstats64(struct net_device *dev, struct rtnl_link_stats64 *s); enum { NESTED_SYNC_IMM_BIT, NESTED_SYNC_TODO_BIT, }; #define __NESTED_SYNC_BIT(bit) ((u32)1 << (bit)) #define __NESTED_SYNC(name) __NESTED_SYNC_BIT(NESTED_SYNC_ ## name ## _BIT) #define NESTED_SYNC_IMM __NESTED_SYNC(IMM) #define NESTED_SYNC_TODO __NESTED_SYNC(TODO) struct netdev_nested_priv { unsigned char flags; void *data; }; bool netdev_has_upper_dev(struct net_device *dev, struct net_device *upper_dev); struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, struct list_head **iter); /* iterate through upper list, must be called under RCU read lock */ #define netdev_for_each_upper_dev_rcu(dev, updev, iter) \ for (iter = &(dev)->adj_list.upper, \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter)); \ updev; \ updev = netdev_upper_get_next_dev_rcu(dev, &(iter))) int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *upper_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); bool netdev_has_upper_dev_all_rcu(struct net_device *dev, struct net_device *upper_dev); bool netdev_has_any_upper_dev(struct net_device *dev); void *netdev_lower_get_next_private(struct net_device *dev, struct list_head **iter); void *netdev_lower_get_next_private_rcu(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_private(dev, priv, iter) \ for (iter = (dev)->adj_list.lower.next, \ priv = netdev_lower_get_next_private(dev, &(iter)); \ priv; \ priv = netdev_lower_get_next_private(dev, &(iter))) #define netdev_for_each_lower_private_rcu(dev, priv, iter) \ for (iter = &(dev)->adj_list.lower, \ priv = netdev_lower_get_next_private_rcu(dev, &(iter)); \ priv; \ priv = netdev_lower_get_next_private_rcu(dev, &(iter))) void *netdev_lower_get_next(struct net_device *dev, struct list_head **iter); #define netdev_for_each_lower_dev(dev, ldev, iter) \ for (iter = (dev)->adj_list.lower.next, \ ldev = netdev_lower_get_next(dev, &(iter)); \ ldev; \ ldev = netdev_lower_get_next(dev, &(iter))) struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, struct list_head **iter); int netdev_walk_all_lower_dev(struct net_device *dev, int (*fn)(struct net_device *lower_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); int netdev_walk_all_lower_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *lower_dev, struct netdev_nested_priv *priv), struct netdev_nested_priv *priv); void *netdev_adjacent_get_private(struct list_head *adj_list); void *netdev_lower_get_first_private_rcu(struct net_device *dev); struct net_device *netdev_master_upper_dev_get(struct net_device *dev); struct net_device *netdev_master_upper_dev_get_rcu(struct net_device *dev); int netdev_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, struct netlink_ext_ack *extack); int netdev_master_upper_dev_link(struct net_device *dev, struct net_device *upper_dev, void *upper_priv, void *upper_info, struct netlink_ext_ack *extack); void netdev_upper_dev_unlink(struct net_device *dev, struct net_device *upper_dev); int netdev_adjacent_change_prepare(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev, struct netlink_ext_ack *extack); void netdev_adjacent_change_commit(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev); void netdev_adjacent_change_abort(struct net_device *old_dev, struct net_device *new_dev, struct net_device *dev); void netdev_adjacent_rename_links(struct net_device *dev, char *oldname); void *netdev_lower_dev_get_private(struct net_device *dev, struct net_device *lower_dev); void netdev_lower_state_changed(struct net_device *lower_dev, void *lower_state_info); /* RSS keys are 40 or 52 bytes long */ #define NETDEV_RSS_KEY_LEN 52 extern u8 netdev_rss_key[NETDEV_RSS_KEY_LEN] __read_mostly; void netdev_rss_key_fill(void *buffer, size_t len); int skb_checksum_help(struct sk_buff *skb); int skb_crc32c_csum_help(struct sk_buff *skb); int skb_csum_hwoffload_help(struct sk_buff *skb, const netdev_features_t features); struct netdev_bonding_info { ifslave slave; ifbond master; }; struct netdev_notifier_bonding_info { struct netdev_notifier_info info; /* must be first */ struct netdev_bonding_info bonding_info; }; void netdev_bonding_info_change(struct net_device *dev, struct netdev_bonding_info *bonding_info); #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK) void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data); #else static inline void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data) { } #endif __be16 skb_network_protocol(struct sk_buff *skb, int *depth); static inline bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { if (protocol == htons(ETH_P_FCOE)) return !!(features & NETIF_F_FCOE_CRC); /* Assume this is an IP checksum (not SCTP CRC) */ if (features & NETIF_F_HW_CSUM) { /* Can checksum everything */ return true; } switch (protocol) { case htons(ETH_P_IP): return !!(features & NETIF_F_IP_CSUM); case htons(ETH_P_IPV6): return !!(features & NETIF_F_IPV6_CSUM); default: return false; } } #ifdef CONFIG_BUG void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb); #else static inline void netdev_rx_csum_fault(struct net_device *dev, struct sk_buff *skb) { } #endif /* rx skb timestamps */ void net_enable_timestamp(void); void net_disable_timestamp(void); static inline ktime_t netdev_get_tstamp(struct net_device *dev, const struct skb_shared_hwtstamps *hwtstamps, bool cycles) { const struct net_device_ops *ops = dev->netdev_ops; if (ops->ndo_get_tstamp) return ops->ndo_get_tstamp(dev, hwtstamps, cycles); return hwtstamps->hwtstamp; } static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops, struct sk_buff *skb, struct net_device *dev, bool more) { __this_cpu_write(softnet_data.xmit.more, more); return ops->ndo_start_xmit(skb, dev); } static inline bool netdev_xmit_more(void) { return __this_cpu_read(softnet_data.xmit.more); } static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq, bool more) { const struct net_device_ops *ops = dev->netdev_ops; netdev_tx_t rc; rc = __netdev_start_xmit(ops, skb, dev, more); if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; } int netdev_class_create_file_ns(const struct class_attribute *class_attr, const void *ns); void netdev_class_remove_file_ns(const struct class_attribute *class_attr, const void *ns); extern const struct kobj_ns_type_operations net_ns_type_operations; const char *netdev_drivername(const struct net_device *dev); static inline netdev_features_t netdev_intersect_features(netdev_features_t f1, netdev_features_t f2) { if ((f1 ^ f2) & NETIF_F_HW_CSUM) { if (f1 & NETIF_F_HW_CSUM) f1 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); else f2 |= (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM); } return f1 & f2; } static inline netdev_features_t netdev_get_wanted_features( struct net_device *dev) { return (dev->features & ~dev->hw_features) | dev->wanted_features; } netdev_features_t netdev_increment_features(netdev_features_t all, netdev_features_t one, netdev_features_t mask); /* Allow TSO being used on stacked device : * Performing the GSO segmentation before last device * is a performance improvement. */ static inline netdev_features_t netdev_add_tso_features(netdev_features_t features, netdev_features_t mask) { return netdev_increment_features(features, NETIF_F_ALL_TSO, mask); } int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); void netif_stacked_transfer_operstate(const struct net_device *rootdev, struct net_device *dev); netdev_features_t passthru_features_check(struct sk_buff *skb, struct net_device *dev, netdev_features_t features); netdev_features_t netif_skb_features(struct sk_buff *skb); void skb_warn_bad_offload(const struct sk_buff *skb); static inline bool net_gso_ok(netdev_features_t features, int gso_type) { netdev_features_t feature = (netdev_features_t)gso_type << NETIF_F_GSO_SHIFT; /* check flags correspondence */ BUILD_BUG_ON(SKB_GSO_TCPV4 != (NETIF_F_TSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_DODGY != (NETIF_F_GSO_ROBUST >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_ECN != (NETIF_F_TSO_ECN >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCP_FIXEDID != (NETIF_F_TSO_MANGLEID >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TCPV6 != (NETIF_F_TSO6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FCOE != (NETIF_F_FSO >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE != (NETIF_F_GSO_GRE >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_GRE_CSUM != (NETIF_F_GSO_GRE_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_IPXIP4 != (NETIF_F_GSO_IPXIP4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_IPXIP6 != (NETIF_F_GSO_IPXIP6 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL != (NETIF_F_GSO_UDP_TUNNEL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_TUNNEL_CSUM != (NETIF_F_GSO_UDP_TUNNEL_CSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_PARTIAL != (NETIF_F_GSO_PARTIAL >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_TUNNEL_REMCSUM != (NETIF_F_GSO_TUNNEL_REMCSUM >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_FRAGLIST != (NETIF_F_GSO_FRAGLIST >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } static inline bool skb_gso_ok(struct sk_buff *skb, netdev_features_t features) { return net_gso_ok(features, skb_shinfo(skb)->gso_type) && (!skb_has_frag_list(skb) || (features & NETIF_F_FRAGLIST)); } static inline bool netif_needs_gso(struct sk_buff *skb, netdev_features_t features) { return skb_is_gso(skb) && (!skb_gso_ok(skb, features) || unlikely((skb->ip_summed != CHECKSUM_PARTIAL) && (skb->ip_summed != CHECKSUM_UNNECESSARY))); } void netif_set_tso_max_size(struct net_device *dev, unsigned int size); void netif_set_tso_max_segs(struct net_device *dev, unsigned int segs); void netif_inherit_tso_max(struct net_device *to, const struct net_device *from); static inline bool netif_is_macsec(const struct net_device *dev) { return dev->priv_flags & IFF_MACSEC; } static inline bool netif_is_macvlan(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN; } static inline bool netif_is_macvlan_port(const struct net_device *dev) { return dev->priv_flags & IFF_MACVLAN_PORT; } static inline bool netif_is_bond_master(const struct net_device *dev) { return dev->flags & IFF_MASTER && dev->priv_flags & IFF_BONDING; } static inline bool netif_is_bond_slave(const struct net_device *dev) { return dev->flags & IFF_SLAVE && dev->priv_flags & IFF_BONDING; } static inline bool netif_supports_nofcs(struct net_device *dev) { return dev->priv_flags & IFF_SUPP_NOFCS; } static inline bool netif_has_l3_rx_handler(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_RX_HANDLER; } static inline bool netif_is_l3_master(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_MASTER; } static inline bool netif_is_l3_slave(const struct net_device *dev) { return dev->priv_flags & IFF_L3MDEV_SLAVE; } static inline int dev_sdif(const struct net_device *dev) { #ifdef CONFIG_NET_L3_MASTER_DEV if (netif_is_l3_slave(dev)) return dev->ifindex; #endif return 0; } static inline bool netif_is_bridge_master(const struct net_device *dev) { return dev->priv_flags & IFF_EBRIDGE; } static inline bool netif_is_bridge_port(const struct net_device *dev) { return dev->priv_flags & IFF_BRIDGE_PORT; } static inline bool netif_is_ovs_master(const struct net_device *dev) { return dev->priv_flags & IFF_OPENVSWITCH; } static inline bool netif_is_ovs_port(const struct net_device *dev) { return dev->priv_flags & IFF_OVS_DATAPATH; } static inline bool netif_is_any_bridge_master(const struct net_device *dev) { return netif_is_bridge_master(dev) || netif_is_ovs_master(dev); } static inline bool netif_is_any_bridge_port(const struct net_device *dev) { return netif_is_bridge_port(dev) || netif_is_ovs_port(dev); } static inline bool netif_is_team_master(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM; } static inline bool netif_is_team_port(const struct net_device *dev) { return dev->priv_flags & IFF_TEAM_PORT; } static inline bool netif_is_lag_master(const struct net_device *dev) { return netif_is_bond_master(dev) || netif_is_team_master(dev); } static inline bool netif_is_lag_port(const struct net_device *dev) { return netif_is_bond_slave(dev) || netif_is_team_port(dev); } static inline bool netif_is_rxfh_configured(const struct net_device *dev) { return dev->priv_flags & IFF_RXFH_CONFIGURED; } static inline bool netif_is_failover(const struct net_device *dev) { return dev->priv_flags & IFF_FAILOVER; } static inline bool netif_is_failover_slave(const struct net_device *dev) { return dev->priv_flags & IFF_FAILOVER_SLAVE; } /* This device needs to keep skb dst for qdisc enqueue or ndo_start_xmit() */ static inline void netif_keep_dst(struct net_device *dev) { dev->priv_flags &= ~(IFF_XMIT_DST_RELEASE | IFF_XMIT_DST_RELEASE_PERM); } /* return true if dev can't cope with mtu frames that need vlan tag insertion */ static inline bool netif_reduces_vlan_mtu(struct net_device *dev) { /* TODO: reserve and use an additional IFF bit, if we get more users */ return netif_is_macsec(dev); } extern struct pernet_operations __net_initdata loopback_net_ops; /* Logging, debugging and troubleshooting/diagnostic helpers. */ /* netdev_printk helpers, similar to dev_printk */ static inline const char *netdev_name(const struct net_device *dev) { if (!dev->name[0] || strchr(dev->name, '%')) return "(unnamed net_device)"; return dev->name; } static inline const char *netdev_reg_state(const struct net_device *dev) { u8 reg_state = READ_ONCE(dev->reg_state); switch (reg_state) { case NETREG_UNINITIALIZED: return " (uninitialized)"; case NETREG_REGISTERED: return ""; case NETREG_UNREGISTERING: return " (unregistering)"; case NETREG_UNREGISTERED: return " (unregistered)"; case NETREG_RELEASED: return " (released)"; case NETREG_DUMMY: return " (dummy)"; } WARN_ONCE(1, "%s: unknown reg_state %d\n", dev->name, reg_state); return " (unknown)"; } #define MODULE_ALIAS_NETDEV(device) \ MODULE_ALIAS("netdev-" device) /* * netdev_WARN() acts like dev_printk(), but with the key difference * of using a WARN/WARN_ON to get the message out, including the * file/line information and a backtrace. */ #define netdev_WARN(dev, format, args...) \ WARN(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) #define netdev_WARN_ONCE(dev, format, args...) \ WARN_ONCE(1, "netdevice: %s%s: " format, netdev_name(dev), \ netdev_reg_state(dev), ##args) /* * The list of packet types we will receive (as opposed to discard) * and the routines to invoke. * * Why 16. Because with 16 the only overlap we get on a hash of the * low nibble of the protocol value is RARP/SNAP/X.25. * * 0800 IP * 0001 802.3 * 0002 AX.25 * 0004 802.2 * 8035 RARP * 0005 SNAP * 0805 X.25 * 0806 ARP * 8137 IPX * 0009 Localtalk * 86DD IPv6 */ #define PTYPE_HASH_SIZE (16) #define PTYPE_HASH_MASK (PTYPE_HASH_SIZE - 1) extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly; extern struct net_device *blackhole_netdev; /* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */ #define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD) #define DEV_STATS_ADD(DEV, FIELD, VAL) \ atomic_long_add((VAL), &(DEV)->stats.__##FIELD) #define DEV_STATS_READ(DEV, FIELD) atomic_long_read(&(DEV)->stats.__##FIELD) #endif /* _LINUX_NETDEVICE_H */ |
| 59 2 131 131 109 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_MMAN_H #define _LINUX_MMAN_H #include <linux/mm.h> #include <linux/percpu_counter.h> #include <linux/atomic.h> #include <uapi/linux/mman.h> /* * Arrange for legacy / undefined architecture specific flags to be * ignored by mmap handling code. */ #ifndef MAP_32BIT #define MAP_32BIT 0 #endif #ifndef MAP_ABOVE4G #define MAP_ABOVE4G 0 #endif #ifndef MAP_HUGE_2MB #define MAP_HUGE_2MB 0 #endif #ifndef MAP_HUGE_1GB #define MAP_HUGE_1GB 0 #endif #ifndef MAP_UNINITIALIZED #define MAP_UNINITIALIZED 0 #endif #ifndef MAP_SYNC #define MAP_SYNC 0 #endif /* * The historical set of flags that all mmap implementations implicitly * support when a ->mmap_validate() op is not provided in file_operations. * * MAP_EXECUTABLE and MAP_DENYWRITE are completely ignored throughout the * kernel. */ #define LEGACY_MAP_MASK (MAP_SHARED \ | MAP_PRIVATE \ | MAP_FIXED \ | MAP_ANONYMOUS \ | MAP_DENYWRITE \ | MAP_EXECUTABLE \ | MAP_UNINITIALIZED \ | MAP_GROWSDOWN \ | MAP_LOCKED \ | MAP_NORESERVE \ | MAP_POPULATE \ | MAP_NONBLOCK \ | MAP_STACK \ | MAP_HUGETLB \ | MAP_32BIT \ | MAP_ABOVE4G \ | MAP_HUGE_2MB \ | MAP_HUGE_1GB) extern int sysctl_overcommit_memory; extern int sysctl_overcommit_ratio; extern unsigned long sysctl_overcommit_kbytes; extern struct percpu_counter vm_committed_as; #ifdef CONFIG_SMP extern s32 vm_committed_as_batch; extern void mm_compute_batch(int overcommit_policy); #else #define vm_committed_as_batch 0 static inline void mm_compute_batch(int overcommit_policy) { } #endif unsigned long vm_memory_committed(void); static inline void vm_acct_memory(long pages) { percpu_counter_add_batch(&vm_committed_as, pages, vm_committed_as_batch); } static inline void vm_unacct_memory(long pages) { vm_acct_memory(-pages); } /* * Allow architectures to handle additional protection and flag bits. The * overriding macros must be defined in the arch-specific asm/mman.h file. */ #ifndef arch_calc_vm_prot_bits #define arch_calc_vm_prot_bits(prot, pkey) 0 #endif #ifndef arch_calc_vm_flag_bits #define arch_calc_vm_flag_bits(flags) 0 #endif #ifndef arch_validate_prot /* * This is called from mprotect(). PROT_GROWSDOWN and PROT_GROWSUP have * already been masked out. * * Returns true if the prot flags are valid */ static inline bool arch_validate_prot(unsigned long prot, unsigned long addr) { return (prot & ~(PROT_READ | PROT_WRITE | PROT_EXEC | PROT_SEM)) == 0; } #define arch_validate_prot arch_validate_prot #endif #ifndef arch_validate_flags /* * This is called from mmap() and mprotect() with the updated vma->vm_flags. * * Returns true if the VM_* flags are valid. */ static inline bool arch_validate_flags(unsigned long flags) { return true; } #define arch_validate_flags arch_validate_flags #endif /* * Optimisation macro. It is equivalent to: * (x & bit1) ? bit2 : 0 * but this version is faster. * ("bit1" and "bit2" must be single bits) */ #define _calc_vm_trans(x, bit1, bit2) \ ((!(bit1) || !(bit2)) ? 0 : \ ((bit1) <= (bit2) ? ((x) & (bit1)) * ((bit2) / (bit1)) \ : ((x) & (bit1)) / ((bit1) / (bit2)))) /* * Combine the mmap "prot" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_prot_bits(unsigned long prot, unsigned long pkey) { return _calc_vm_trans(prot, PROT_READ, VM_READ ) | _calc_vm_trans(prot, PROT_WRITE, VM_WRITE) | _calc_vm_trans(prot, PROT_EXEC, VM_EXEC) | arch_calc_vm_prot_bits(prot, pkey); } /* * Combine the mmap "flags" argument into "vm_flags" used internally. */ static inline unsigned long calc_vm_flag_bits(unsigned long flags) { return _calc_vm_trans(flags, MAP_GROWSDOWN, VM_GROWSDOWN ) | _calc_vm_trans(flags, MAP_LOCKED, VM_LOCKED ) | _calc_vm_trans(flags, MAP_SYNC, VM_SYNC ) | _calc_vm_trans(flags, MAP_STACK, VM_NOHUGEPAGE) | arch_calc_vm_flag_bits(flags); } unsigned long vm_commit_limit(void); #ifndef arch_memory_deny_write_exec_supported static inline bool arch_memory_deny_write_exec_supported(void) { return true; } #define arch_memory_deny_write_exec_supported arch_memory_deny_write_exec_supported #endif /* * Denies creating a writable executable mapping or gaining executable permissions. * * This denies the following: * * a) mmap(PROT_WRITE | PROT_EXEC) * * b) mmap(PROT_WRITE) * mprotect(PROT_EXEC) * * c) mmap(PROT_WRITE) * mprotect(PROT_READ) * mprotect(PROT_EXEC) * * But allows the following: * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) */ static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) { if (!test_bit(MMF_HAS_MDWE, ¤t->mm->flags)) return false; if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) return true; if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) return true; return false; } #endif /* _LINUX_MMAN_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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * include/linux/signalfd.h * * Copyright (C) 2007 Davide Libenzi <davidel@xmailserver.org> * */ #ifndef _LINUX_SIGNALFD_H #define _LINUX_SIGNALFD_H #include <uapi/linux/signalfd.h> #include <linux/sched/signal.h> #ifdef CONFIG_SIGNALFD /* * Deliver the signal to listening signalfd. */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { if (unlikely(waitqueue_active(&tsk->sighand->signalfd_wqh))) wake_up(&tsk->sighand->signalfd_wqh); } extern void signalfd_cleanup(struct sighand_struct *sighand); #else /* CONFIG_SIGNALFD */ static inline void signalfd_notify(struct task_struct *tsk, int sig) { } static inline void signalfd_cleanup(struct sighand_struct *sighand) { } #endif /* CONFIG_SIGNALFD */ #endif /* _LINUX_SIGNALFD_H */ |
| 188 188 188 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/blkdev.h> #include <linux/wait.h> #include <linux/rbtree.h> #include <linux/kthread.h> #include <linux/backing-dev.h> #include <linux/blk-cgroup.h> #include <linux/freezer.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/mm.h> #include <linux/sched/mm.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/writeback.h> #include <linux/device.h> #include <trace/events/writeback.h> #include "internal.h" struct backing_dev_info noop_backing_dev_info; EXPORT_SYMBOL_GPL(noop_backing_dev_info); static const char *bdi_unknown_name = "(unknown)"; /* * bdi_lock protects bdi_tree and updates to bdi_list. bdi_list has RCU * reader side locking. */ DEFINE_SPINLOCK(bdi_lock); static u64 bdi_id_cursor; static struct rb_root bdi_tree = RB_ROOT; LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> struct wb_stats { unsigned long nr_dirty; unsigned long nr_io; unsigned long nr_more_io; unsigned long nr_dirty_time; unsigned long nr_writeback; unsigned long nr_reclaimable; unsigned long nr_dirtied; unsigned long nr_written; unsigned long dirty_thresh; unsigned long wb_thresh; }; static struct dentry *bdi_debug_root; static void bdi_debug_init(void) { bdi_debug_root = debugfs_create_dir("bdi", NULL); } static void collect_wb_stats(struct wb_stats *stats, struct bdi_writeback *wb) { struct inode *inode; spin_lock(&wb->list_lock); list_for_each_entry(inode, &wb->b_dirty, i_io_list) stats->nr_dirty++; list_for_each_entry(inode, &wb->b_io, i_io_list) stats->nr_io++; list_for_each_entry(inode, &wb->b_more_io, i_io_list) stats->nr_more_io++; list_for_each_entry(inode, &wb->b_dirty_time, i_io_list) if (inode->i_state & I_DIRTY_TIME) stats->nr_dirty_time++; spin_unlock(&wb->list_lock); stats->nr_writeback += wb_stat(wb, WB_WRITEBACK); stats->nr_reclaimable += wb_stat(wb, WB_RECLAIMABLE); stats->nr_dirtied += wb_stat(wb, WB_DIRTIED); stats->nr_written += wb_stat(wb, WB_WRITTEN); stats->wb_thresh += wb_calc_thresh(wb, stats->dirty_thresh); } #ifdef CONFIG_CGROUP_WRITEBACK static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { struct bdi_writeback *wb; rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { if (!wb_tryget(wb)) continue; collect_wb_stats(stats, wb); wb_put(wb); } rcu_read_unlock(); } #else static void bdi_collect_stats(struct backing_dev_info *bdi, struct wb_stats *stats) { collect_wb_stats(stats, &bdi->wb); } #endif static int bdi_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct wb_stats stats; unsigned long tot_bw; global_dirty_limits(&background_thresh, &dirty_thresh); memset(&stats, 0, sizeof(stats)); stats.dirty_thresh = dirty_thresh; bdi_collect_stats(bdi, &stats); tot_bw = atomic_long_read(&bdi->tot_write_bandwidth); seq_printf(m, "BdiWriteback: %10lu kB\n" "BdiReclaimable: %10lu kB\n" "BdiDirtyThresh: %10lu kB\n" "DirtyThresh: %10lu kB\n" "BackgroundThresh: %10lu kB\n" "BdiDirtied: %10lu kB\n" "BdiWritten: %10lu kB\n" "BdiWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "bdi_list: %10u\n" "state: %10lx\n", K(stats.nr_writeback), K(stats.nr_reclaimable), K(stats.wb_thresh), K(dirty_thresh), K(background_thresh), K(stats.nr_dirtied), K(stats.nr_written), K(tot_bw), stats.nr_dirty, stats.nr_io, stats.nr_more_io, stats.nr_dirty_time, !list_empty(&bdi->bdi_list), bdi->wb.state); return 0; } DEFINE_SHOW_ATTRIBUTE(bdi_debug_stats); static void wb_stats_show(struct seq_file *m, struct bdi_writeback *wb, struct wb_stats *stats) { seq_printf(m, "WbCgIno: %10lu\n" "WbWriteback: %10lu kB\n" "WbReclaimable: %10lu kB\n" "WbDirtyThresh: %10lu kB\n" "WbDirtied: %10lu kB\n" "WbWritten: %10lu kB\n" "WbWriteBandwidth: %10lu kBps\n" "b_dirty: %10lu\n" "b_io: %10lu\n" "b_more_io: %10lu\n" "b_dirty_time: %10lu\n" "state: %10lx\n\n", #ifdef CONFIG_CGROUP_WRITEBACK cgroup_ino(wb->memcg_css->cgroup), #else 1ul, #endif K(stats->nr_writeback), K(stats->nr_reclaimable), K(stats->wb_thresh), K(stats->nr_dirtied), K(stats->nr_written), K(wb->avg_write_bandwidth), stats->nr_dirty, stats->nr_io, stats->nr_more_io, stats->nr_dirty_time, wb->state); } static int cgwb_debug_stats_show(struct seq_file *m, void *v) { struct backing_dev_info *bdi = m->private; unsigned long background_thresh; unsigned long dirty_thresh; struct bdi_writeback *wb; global_dirty_limits(&background_thresh, &dirty_thresh); rcu_read_lock(); list_for_each_entry_rcu(wb, &bdi->wb_list, bdi_node) { struct wb_stats stats = { .dirty_thresh = dirty_thresh }; if (!wb_tryget(wb)) continue; collect_wb_stats(&stats, wb); /* * Calculate thresh of wb in writeback cgroup which is min of * thresh in global domain and thresh in cgroup domain. Drop * rcu lock because cgwb_calc_thresh may sleep in * cgroup_rstat_flush. We can do so here because we have a ref. */ if (mem_cgroup_wb_domain(wb)) { rcu_read_unlock(); stats.wb_thresh = min(stats.wb_thresh, cgwb_calc_thresh(wb)); rcu_read_lock(); } wb_stats_show(m, wb, &stats); wb_put(wb); } rcu_read_unlock(); return 0; } DEFINE_SHOW_ATTRIBUTE(cgwb_debug_stats); static void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { bdi->debug_dir = debugfs_create_dir(name, bdi_debug_root); debugfs_create_file("stats", 0444, bdi->debug_dir, bdi, &bdi_debug_stats_fops); debugfs_create_file("wb_stats", 0444, bdi->debug_dir, bdi, &cgwb_debug_stats_fops); } static void bdi_debug_unregister(struct backing_dev_info *bdi) { debugfs_remove_recursive(bdi->debug_dir); } #else /* CONFIG_DEBUG_FS */ static inline void bdi_debug_init(void) { } static inline void bdi_debug_register(struct backing_dev_info *bdi, const char *name) { } static inline void bdi_debug_unregister(struct backing_dev_info *bdi) { } #endif /* CONFIG_DEBUG_FS */ static ssize_t read_ahead_kb_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned long read_ahead_kb; ssize_t ret; ret = kstrtoul(buf, 10, &read_ahead_kb); if (ret < 0) return ret; bdi->ra_pages = read_ahead_kb >> (PAGE_SHIFT - 10); return count; } #define BDI_SHOW(name, expr) \ static ssize_t name##_show(struct device *dev, \ struct device_attribute *attr, char *buf) \ { \ struct backing_dev_info *bdi = dev_get_drvdata(dev); \ \ return sysfs_emit(buf, "%lld\n", (long long)expr); \ } \ static DEVICE_ATTR_RW(name); BDI_SHOW(read_ahead_kb, K(bdi->ra_pages)) static ssize_t min_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio, bdi->min_ratio / BDI_RATIO_SCALE) static ssize_t min_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_min_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(min_ratio_fine, bdi->min_ratio) static ssize_t max_ratio_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio, bdi->max_ratio / BDI_RATIO_SCALE) static ssize_t max_ratio_fine_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int ratio; ssize_t ret; ret = kstrtouint(buf, 10, &ratio); if (ret < 0) return ret; ret = bdi_set_max_ratio_no_scale(bdi, ratio); if (!ret) ret = count; return ret; } BDI_SHOW(max_ratio_fine, bdi->max_ratio) static ssize_t min_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_min_bytes(bdi)); } static ssize_t min_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_min_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(min_bytes); static ssize_t max_bytes_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%llu\n", bdi_get_max_bytes(bdi)); } static ssize_t max_bytes_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); u64 bytes; ssize_t ret; ret = kstrtoull(buf, 10, &bytes); if (ret < 0) return ret; ret = bdi_set_max_bytes(bdi, bytes); if (!ret) ret = count; return ret; } static DEVICE_ATTR_RW(max_bytes); static ssize_t stable_pages_required_show(struct device *dev, struct device_attribute *attr, char *buf) { dev_warn_once(dev, "the stable_pages_required attribute has been removed. Use the stable_writes queue attribute instead.\n"); return sysfs_emit(buf, "%d\n", 0); } static DEVICE_ATTR_RO(stable_pages_required); static ssize_t strict_limit_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct backing_dev_info *bdi = dev_get_drvdata(dev); unsigned int strict_limit; ssize_t ret; ret = kstrtouint(buf, 10, &strict_limit); if (ret < 0) return ret; ret = bdi_set_strict_limit(bdi, strict_limit); if (!ret) ret = count; return ret; } static ssize_t strict_limit_show(struct device *dev, struct device_attribute *attr, char *buf) { struct backing_dev_info *bdi = dev_get_drvdata(dev); return sysfs_emit(buf, "%d\n", !!(bdi->capabilities & BDI_CAP_STRICTLIMIT)); } static DEVICE_ATTR_RW(strict_limit); static struct attribute *bdi_dev_attrs[] = { &dev_attr_read_ahead_kb.attr, &dev_attr_min_ratio.attr, &dev_attr_min_ratio_fine.attr, &dev_attr_max_ratio.attr, &dev_attr_max_ratio_fine.attr, &dev_attr_min_bytes.attr, &dev_attr_max_bytes.attr, &dev_attr_stable_pages_required.attr, &dev_attr_strict_limit.attr, NULL, }; ATTRIBUTE_GROUPS(bdi_dev); static const struct class bdi_class = { .name = "bdi", .dev_groups = bdi_dev_groups, }; static __init int bdi_class_init(void) { int ret; ret = class_register(&bdi_class); if (ret) return ret; bdi_debug_init(); return 0; } postcore_initcall(bdi_class_init); static int __init default_bdi_init(void) { bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; return 0; } subsys_initcall(default_bdi_init); static void wb_update_bandwidth_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(to_delayed_work(work), struct bdi_writeback, bw_dwork); wb_update_bandwidth(wb); } /* * Initial write bandwidth: 100 MB/s */ #define INIT_BW (100 << (20 - PAGE_SHIFT)) static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, gfp_t gfp) { int err; memset(wb, 0, sizeof(*wb)); wb->bdi = bdi; wb->last_old_flush = jiffies; INIT_LIST_HEAD(&wb->b_dirty); INIT_LIST_HEAD(&wb->b_io); INIT_LIST_HEAD(&wb->b_more_io); INIT_LIST_HEAD(&wb->b_dirty_time); spin_lock_init(&wb->list_lock); atomic_set(&wb->writeback_inodes, 0); wb->bw_time_stamp = jiffies; wb->balanced_dirty_ratelimit = INIT_BW; wb->dirty_ratelimit = INIT_BW; wb->write_bandwidth = INIT_BW; wb->avg_write_bandwidth = INIT_BW; spin_lock_init(&wb->work_lock); INIT_LIST_HEAD(&wb->work_list); INIT_DELAYED_WORK(&wb->dwork, wb_workfn); INIT_DELAYED_WORK(&wb->bw_dwork, wb_update_bandwidth_workfn); err = fprop_local_init_percpu(&wb->completions, gfp); if (err) return err; err = percpu_counter_init_many(wb->stat, 0, gfp, NR_WB_STAT_ITEMS); if (err) fprop_local_destroy_percpu(&wb->completions); return err; } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb); /* * Remove bdi from the global list and shutdown any threads we have running */ static void wb_shutdown(struct bdi_writeback *wb) { /* Make sure nobody queues further work */ spin_lock_irq(&wb->work_lock); if (!test_and_clear_bit(WB_registered, &wb->state)) { spin_unlock_irq(&wb->work_lock); return; } spin_unlock_irq(&wb->work_lock); cgwb_remove_from_bdi_list(wb); /* * Drain work list and shutdown the delayed_work. !WB_registered * tells wb_workfn() that @wb is dying and its work_list needs to * be drained no matter what. */ mod_delayed_work(bdi_wq, &wb->dwork, 0); flush_delayed_work(&wb->dwork); WARN_ON(!list_empty(&wb->work_list)); flush_delayed_work(&wb->bw_dwork); } static void wb_exit(struct bdi_writeback *wb) { WARN_ON(delayed_work_pending(&wb->dwork)); percpu_counter_destroy_many(wb->stat, NR_WB_STAT_ITEMS); fprop_local_destroy_percpu(&wb->completions); } #ifdef CONFIG_CGROUP_WRITEBACK #include <linux/memcontrol.h> /* * cgwb_lock protects bdi->cgwb_tree, blkcg->cgwb_list, offline_cgwbs and * memcg->cgwb_list. bdi->cgwb_tree is also RCU protected. */ static DEFINE_SPINLOCK(cgwb_lock); static struct workqueue_struct *cgwb_release_wq; static LIST_HEAD(offline_cgwbs); static void cleanup_offline_cgwbs_workfn(struct work_struct *work); static DECLARE_WORK(cleanup_offline_cgwbs_work, cleanup_offline_cgwbs_workfn); static void cgwb_free_rcu(struct rcu_head *rcu_head) { struct bdi_writeback *wb = container_of(rcu_head, struct bdi_writeback, rcu); percpu_ref_exit(&wb->refcnt); kfree(wb); } static void cgwb_release_workfn(struct work_struct *work) { struct bdi_writeback *wb = container_of(work, struct bdi_writeback, release_work); struct backing_dev_info *bdi = wb->bdi; mutex_lock(&wb->bdi->cgwb_release_mutex); wb_shutdown(wb); css_put(wb->memcg_css); css_put(wb->blkcg_css); mutex_unlock(&wb->bdi->cgwb_release_mutex); /* triggers blkg destruction if no online users left */ blkcg_unpin_online(wb->blkcg_css); fprop_local_destroy_percpu(&wb->memcg_completions); spin_lock_irq(&cgwb_lock); list_del(&wb->offline_node); spin_unlock_irq(&cgwb_lock); wb_exit(wb); bdi_put(bdi); WARN_ON_ONCE(!list_empty(&wb->b_attached)); call_rcu(&wb->rcu, cgwb_free_rcu); } static void cgwb_release(struct percpu_ref *refcnt) { struct bdi_writeback *wb = container_of(refcnt, struct bdi_writeback, refcnt); queue_work(cgwb_release_wq, &wb->release_work); } static void cgwb_kill(struct bdi_writeback *wb) { lockdep_assert_held(&cgwb_lock); WARN_ON(!radix_tree_delete(&wb->bdi->cgwb_tree, wb->memcg_css->id)); list_del(&wb->memcg_node); list_del(&wb->blkcg_node); list_add(&wb->offline_node, &offline_cgwbs); percpu_ref_kill(&wb->refcnt); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { spin_lock_irq(&cgwb_lock); list_del_rcu(&wb->bdi_node); spin_unlock_irq(&cgwb_lock); } static int cgwb_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct mem_cgroup *memcg; struct cgroup_subsys_state *blkcg_css; struct list_head *memcg_cgwb_list, *blkcg_cgwb_list; struct bdi_writeback *wb; unsigned long flags; int ret = 0; memcg = mem_cgroup_from_css(memcg_css); blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); memcg_cgwb_list = &memcg->cgwb_list; blkcg_cgwb_list = blkcg_get_cgwb_list(blkcg_css); /* look up again under lock and discard on blkcg mismatch */ spin_lock_irqsave(&cgwb_lock, flags); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb && wb->blkcg_css != blkcg_css) { cgwb_kill(wb); wb = NULL; } spin_unlock_irqrestore(&cgwb_lock, flags); if (wb) goto out_put; /* need to create a new one */ wb = kmalloc(sizeof(*wb), gfp); if (!wb) { ret = -ENOMEM; goto out_put; } ret = wb_init(wb, bdi, gfp); if (ret) goto err_free; ret = percpu_ref_init(&wb->refcnt, cgwb_release, 0, gfp); if (ret) goto err_wb_exit; ret = fprop_local_init_percpu(&wb->memcg_completions, gfp); if (ret) goto err_ref_exit; wb->memcg_css = memcg_css; wb->blkcg_css = blkcg_css; INIT_LIST_HEAD(&wb->b_attached); INIT_WORK(&wb->release_work, cgwb_release_workfn); set_bit(WB_registered, &wb->state); bdi_get(bdi); /* * The root wb determines the registered state of the whole bdi and * memcg_cgwb_list and blkcg_cgwb_list's next pointers indicate * whether they're still online. Don't link @wb if any is dead. * See wb_memcg_offline() and wb_blkcg_offline(). */ ret = -ENODEV; spin_lock_irqsave(&cgwb_lock, flags); if (test_bit(WB_registered, &bdi->wb.state) && blkcg_cgwb_list->next && memcg_cgwb_list->next) { /* we might have raced another instance of this function */ ret = radix_tree_insert(&bdi->cgwb_tree, memcg_css->id, wb); if (!ret) { list_add_tail_rcu(&wb->bdi_node, &bdi->wb_list); list_add(&wb->memcg_node, memcg_cgwb_list); list_add(&wb->blkcg_node, blkcg_cgwb_list); blkcg_pin_online(blkcg_css); css_get(memcg_css); css_get(blkcg_css); } } spin_unlock_irqrestore(&cgwb_lock, flags); if (ret) { if (ret == -EEXIST) ret = 0; goto err_fprop_exit; } goto out_put; err_fprop_exit: bdi_put(bdi); fprop_local_destroy_percpu(&wb->memcg_completions); err_ref_exit: percpu_ref_exit(&wb->refcnt); err_wb_exit: wb_exit(wb); err_free: kfree(wb); out_put: css_put(blkcg_css); return ret; } /** * wb_get_lookup - get wb for a given memcg * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * * Try to get the wb for @memcg_css on @bdi. The returned wb has its * refcount incremented. * * This function uses css_get() on @memcg_css and thus expects its refcnt * to be positive on invocation. IOW, rcu_read_lock() protection on * @memcg_css isn't enough. try_get it before calling this function. * * A wb is keyed by its associated memcg. As blkcg implicitly enables * memcg on the default hierarchy, memcg association is guaranteed to be * more specific (equal or descendant to the associated blkcg) and thus can * identify both the memcg and blkcg associations. * * Because the blkcg associated with a memcg may change as blkcg is enabled * and disabled closer to root in the hierarchy, each wb keeps track of * both the memcg and blkcg associated with it and verifies the blkcg on * each lookup. On mismatch, the existing wb is discarded and a new one is * created. */ struct bdi_writeback *wb_get_lookup(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css) { struct bdi_writeback *wb; if (!memcg_css->parent) return &bdi->wb; rcu_read_lock(); wb = radix_tree_lookup(&bdi->cgwb_tree, memcg_css->id); if (wb) { struct cgroup_subsys_state *blkcg_css; /* see whether the blkcg association has changed */ blkcg_css = cgroup_get_e_css(memcg_css->cgroup, &io_cgrp_subsys); if (unlikely(wb->blkcg_css != blkcg_css || !wb_tryget(wb))) wb = NULL; css_put(blkcg_css); } rcu_read_unlock(); return wb; } /** * wb_get_create - get wb for a given memcg, create if necessary * @bdi: target bdi * @memcg_css: cgroup_subsys_state of the target memcg (must have positive ref) * @gfp: allocation mask to use * * Try to get the wb for @memcg_css on @bdi. If it doesn't exist, try to * create one. See wb_get_lookup() for more details. */ struct bdi_writeback *wb_get_create(struct backing_dev_info *bdi, struct cgroup_subsys_state *memcg_css, gfp_t gfp) { struct bdi_writeback *wb; might_alloc(gfp); do { wb = wb_get_lookup(bdi, memcg_css); } while (!wb && !cgwb_create(bdi, memcg_css, gfp)); return wb; } static int cgwb_bdi_init(struct backing_dev_info *bdi) { int ret; INIT_RADIX_TREE(&bdi->cgwb_tree, GFP_ATOMIC); mutex_init(&bdi->cgwb_release_mutex); init_rwsem(&bdi->wb_switch_rwsem); ret = wb_init(&bdi->wb, bdi, GFP_KERNEL); if (!ret) { bdi->wb.memcg_css = &root_mem_cgroup->css; bdi->wb.blkcg_css = blkcg_root_css; } return ret; } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { struct radix_tree_iter iter; void **slot; struct bdi_writeback *wb; WARN_ON(test_bit(WB_registered, &bdi->wb.state)); spin_lock_irq(&cgwb_lock); radix_tree_for_each_slot(slot, &bdi->cgwb_tree, &iter, 0) cgwb_kill(*slot); spin_unlock_irq(&cgwb_lock); mutex_lock(&bdi->cgwb_release_mutex); spin_lock_irq(&cgwb_lock); while (!list_empty(&bdi->wb_list)) { wb = list_first_entry(&bdi->wb_list, struct bdi_writeback, bdi_node); spin_unlock_irq(&cgwb_lock); wb_shutdown(wb); spin_lock_irq(&cgwb_lock); } spin_unlock_irq(&cgwb_lock); mutex_unlock(&bdi->cgwb_release_mutex); } /* * cleanup_offline_cgwbs_workfn - try to release dying cgwbs * * Try to release dying cgwbs by switching attached inodes to the nearest * living ancestor's writeback. Processed wbs are placed at the end * of the list to guarantee the forward progress. */ static void cleanup_offline_cgwbs_workfn(struct work_struct *work) { struct bdi_writeback *wb; LIST_HEAD(processed); spin_lock_irq(&cgwb_lock); while (!list_empty(&offline_cgwbs)) { wb = list_first_entry(&offline_cgwbs, struct bdi_writeback, offline_node); list_move(&wb->offline_node, &processed); /* * If wb is dirty, cleaning up the writeback by switching * attached inodes will result in an effective removal of any * bandwidth restrictions, which isn't the goal. Instead, * it can be postponed until the next time, when all io * will be likely completed. If in the meantime some inodes * will get re-dirtied, they should be eventually switched to * a new cgwb. */ if (wb_has_dirty_io(wb)) continue; if (!wb_tryget(wb)) continue; spin_unlock_irq(&cgwb_lock); while (cleanup_offline_cgwb(wb)) cond_resched(); spin_lock_irq(&cgwb_lock); wb_put(wb); } if (!list_empty(&processed)) list_splice_tail(&processed, &offline_cgwbs); spin_unlock_irq(&cgwb_lock); } /** * wb_memcg_offline - kill all wb's associated with a memcg being offlined * @memcg: memcg being offlined * * Also prevents creation of any new wb's associated with @memcg. */ void wb_memcg_offline(struct mem_cgroup *memcg) { struct list_head *memcg_cgwb_list = &memcg->cgwb_list; struct bdi_writeback *wb, *next; spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, memcg_cgwb_list, memcg_node) cgwb_kill(wb); memcg_cgwb_list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); queue_work(system_unbound_wq, &cleanup_offline_cgwbs_work); } /** * wb_blkcg_offline - kill all wb's associated with a blkcg being offlined * @css: blkcg being offlined * * Also prevents creation of any new wb's associated with @blkcg. */ void wb_blkcg_offline(struct cgroup_subsys_state *css) { struct bdi_writeback *wb, *next; struct list_head *list = blkcg_get_cgwb_list(css); spin_lock_irq(&cgwb_lock); list_for_each_entry_safe(wb, next, list, blkcg_node) cgwb_kill(wb); list->next = NULL; /* prevent new wb's */ spin_unlock_irq(&cgwb_lock); } static void cgwb_bdi_register(struct backing_dev_info *bdi) { spin_lock_irq(&cgwb_lock); list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); spin_unlock_irq(&cgwb_lock); } static int __init cgwb_init(void) { /* * There can be many concurrent release work items overwhelming * system_wq. Put them in a separate wq and limit concurrency. * There's no point in executing many of these in parallel. */ cgwb_release_wq = alloc_workqueue("cgwb_release", 0, 1); if (!cgwb_release_wq) return -ENOMEM; return 0; } subsys_initcall(cgwb_init); #else /* CONFIG_CGROUP_WRITEBACK */ static int cgwb_bdi_init(struct backing_dev_info *bdi) { return wb_init(&bdi->wb, bdi, GFP_KERNEL); } static void cgwb_bdi_unregister(struct backing_dev_info *bdi) { } static void cgwb_bdi_register(struct backing_dev_info *bdi) { list_add_tail_rcu(&bdi->wb.bdi_node, &bdi->wb_list); } static void cgwb_remove_from_bdi_list(struct bdi_writeback *wb) { list_del_rcu(&wb->bdi_node); } #endif /* CONFIG_CGROUP_WRITEBACK */ int bdi_init(struct backing_dev_info *bdi) { bdi->dev = NULL; kref_init(&bdi->refcnt); bdi->min_ratio = 0; bdi->max_ratio = 100 * BDI_RATIO_SCALE; bdi->max_prop_frac = FPROP_FRAC_BASE; INIT_LIST_HEAD(&bdi->bdi_list); INIT_LIST_HEAD(&bdi->wb_list); init_waitqueue_head(&bdi->wb_waitq); bdi->last_bdp_sleep = jiffies; return cgwb_bdi_init(bdi); } struct backing_dev_info *bdi_alloc(int node_id) { struct backing_dev_info *bdi; bdi = kzalloc_node(sizeof(*bdi), GFP_KERNEL, node_id); if (!bdi) return NULL; if (bdi_init(bdi)) { kfree(bdi); return NULL; } bdi->capabilities = BDI_CAP_WRITEBACK | BDI_CAP_WRITEBACK_ACCT; bdi->ra_pages = VM_READAHEAD_PAGES; bdi->io_pages = VM_READAHEAD_PAGES; timer_setup(&bdi->laptop_mode_wb_timer, laptop_mode_timer_fn, 0); return bdi; } EXPORT_SYMBOL(bdi_alloc); static struct rb_node **bdi_lookup_rb_node(u64 id, struct rb_node **parentp) { struct rb_node **p = &bdi_tree.rb_node; struct rb_node *parent = NULL; struct backing_dev_info *bdi; lockdep_assert_held(&bdi_lock); while (*p) { parent = *p; bdi = rb_entry(parent, struct backing_dev_info, rb_node); if (bdi->id > id) p = &(*p)->rb_left; else if (bdi->id < id) p = &(*p)->rb_right; else break; } if (parentp) *parentp = parent; return p; } /** * bdi_get_by_id - lookup and get bdi from its id * @id: bdi id to lookup * * Find bdi matching @id and get it. Returns NULL if the matching bdi * doesn't exist or is already unregistered. */ struct backing_dev_info *bdi_get_by_id(u64 id) { struct backing_dev_info *bdi = NULL; struct rb_node **p; spin_lock_bh(&bdi_lock); p = bdi_lookup_rb_node(id, NULL); if (*p) { bdi = rb_entry(*p, struct backing_dev_info, rb_node); bdi_get(bdi); } spin_unlock_bh(&bdi_lock); return bdi; } int bdi_register_va(struct backing_dev_info *bdi, const char *fmt, va_list args) { struct device *dev; struct rb_node *parent, **p; if (bdi->dev) /* The driver needs to use separate queues per device */ return 0; vsnprintf(bdi->dev_name, sizeof(bdi->dev_name), fmt, args); dev = device_create(&bdi_class, NULL, MKDEV(0, 0), bdi, bdi->dev_name); if (IS_ERR(dev)) return PTR_ERR(dev); cgwb_bdi_register(bdi); bdi->dev = dev; bdi_debug_register(bdi, dev_name(dev)); set_bit(WB_registered, &bdi->wb.state); spin_lock_bh(&bdi_lock); bdi->id = ++bdi_id_cursor; p = bdi_lookup_rb_node(bdi->id, &parent); rb_link_node(&bdi->rb_node, parent, p); rb_insert_color(&bdi->rb_node, &bdi_tree); list_add_tail_rcu(&bdi->bdi_list, &bdi_list); spin_unlock_bh(&bdi_lock); trace_writeback_bdi_register(bdi); return 0; } int bdi_register(struct backing_dev_info *bdi, const char *fmt, ...) { va_list args; int ret; va_start(args, fmt); ret = bdi_register_va(bdi, fmt, args); va_end(args); return ret; } EXPORT_SYMBOL(bdi_register); void bdi_set_owner(struct backing_dev_info *bdi, struct device *owner) { WARN_ON_ONCE(bdi->owner); bdi->owner = owner; get_device(owner); } /* * Remove bdi from bdi_list, and ensure that it is no longer visible */ static void bdi_remove_from_list(struct backing_dev_info *bdi) { spin_lock_bh(&bdi_lock); rb_erase(&bdi->rb_node, &bdi_tree); list_del_rcu(&bdi->bdi_list); spin_unlock_bh(&bdi_lock); synchronize_rcu_expedited(); } void bdi_unregister(struct backing_dev_info *bdi) { del_timer_sync(&bdi->laptop_mode_wb_timer); /* make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); wb_shutdown(&bdi->wb); cgwb_bdi_unregister(bdi); /* * If this BDI's min ratio has been set, use bdi_set_min_ratio() to * update the global bdi_min_ratio. */ if (bdi->min_ratio) bdi_set_min_ratio(bdi, 0); if (bdi->dev) { bdi_debug_unregister(bdi); device_unregister(bdi->dev); bdi->dev = NULL; } if (bdi->owner) { put_device(bdi->owner); bdi->owner = NULL; } } EXPORT_SYMBOL(bdi_unregister); static void release_bdi(struct kref *ref) { struct backing_dev_info *bdi = container_of(ref, struct backing_dev_info, refcnt); WARN_ON_ONCE(test_bit(WB_registered, &bdi->wb.state)); WARN_ON_ONCE(bdi->dev); wb_exit(&bdi->wb); kfree(bdi); } void bdi_put(struct backing_dev_info *bdi) { kref_put(&bdi->refcnt, release_bdi); } EXPORT_SYMBOL(bdi_put); 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_disk->bdi; #endif return sb->s_bdi; } EXPORT_SYMBOL(inode_to_bdi); const char *bdi_dev_name(struct backing_dev_info *bdi) { if (!bdi || !bdi->dev) return bdi_unknown_name; return bdi->dev_name; } EXPORT_SYMBOL_GPL(bdi_dev_name); |
| 152 152 152 152 152 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _MM_PERCPU_INTERNAL_H #define _MM_PERCPU_INTERNAL_H #include <linux/types.h> #include <linux/percpu.h> #include <linux/memcontrol.h> /* * pcpu_block_md is the metadata block struct. * Each chunk's bitmap is split into a number of full blocks. * All units are in terms of bits. * * The scan hint is the largest known contiguous area before the contig hint. * It is not necessarily the actual largest contig hint though. There is an * invariant that the scan_hint_start > contig_hint_start iff * scan_hint == contig_hint. This is necessary because when scanning forward, * we don't know if a new contig hint would be better than the current one. */ struct pcpu_block_md { int scan_hint; /* scan hint for block */ int scan_hint_start; /* block relative starting position of the scan hint */ int contig_hint; /* contig hint for block */ int contig_hint_start; /* block relative starting position of the contig hint */ int left_free; /* size of free space along the left side of the block */ int right_free; /* size of free space along the right side of the block */ int first_free; /* block position of first free */ int nr_bits; /* total bits responsible for */ }; struct pcpuobj_ext { #ifdef CONFIG_MEMCG_KMEM struct obj_cgroup *cgroup; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref tag; #endif }; #if defined(CONFIG_MEMCG_KMEM) || defined(CONFIG_MEM_ALLOC_PROFILING) #define NEED_PCPUOBJ_EXT #endif struct pcpu_chunk { #ifdef CONFIG_PERCPU_STATS int nr_alloc; /* # of allocations */ size_t max_alloc_size; /* largest allocation size */ #endif struct list_head list; /* linked to pcpu_slot lists */ int free_bytes; /* free bytes in the chunk */ struct pcpu_block_md chunk_md; unsigned long *bound_map; /* boundary map */ /* * base_addr is the base address of this chunk. * To reduce false sharing, current layout is optimized to make sure * base_addr locate in the different cacheline with free_bytes and * chunk_md. */ void *base_addr ____cacheline_aligned_in_smp; unsigned long *alloc_map; /* allocation map */ struct pcpu_block_md *md_blocks; /* metadata blocks */ void *data; /* chunk data */ bool immutable; /* no [de]population allowed */ bool isolated; /* isolated from active chunk slots */ int start_offset; /* the overlap with the previous region to have a page aligned base_addr */ int end_offset; /* additional area required to have the region end page aligned */ #ifdef NEED_PCPUOBJ_EXT struct pcpuobj_ext *obj_exts; /* vector of object cgroups */ #endif int nr_pages; /* # of pages served by this chunk */ int nr_populated; /* # of populated pages */ int nr_empty_pop_pages; /* # of empty populated pages */ unsigned long populated[]; /* populated bitmap */ }; static inline bool need_pcpuobj_ext(void) { if (IS_ENABLED(CONFIG_MEM_ALLOC_PROFILING)) return true; if (!mem_cgroup_kmem_disabled()) return true; return false; } extern spinlock_t pcpu_lock; extern struct list_head *pcpu_chunk_lists; extern int pcpu_nr_slots; extern int pcpu_sidelined_slot; extern int pcpu_to_depopulate_slot; extern int pcpu_nr_empty_pop_pages; extern struct pcpu_chunk *pcpu_first_chunk; extern struct pcpu_chunk *pcpu_reserved_chunk; /** * pcpu_chunk_nr_blocks - converts nr_pages to # of md_blocks * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bitmap blocks used. */ static inline int pcpu_chunk_nr_blocks(struct pcpu_chunk *chunk) { return chunk->nr_pages * PAGE_SIZE / PCPU_BITMAP_BLOCK_SIZE; } /** * pcpu_nr_pages_to_map_bits - converts the pages to size of bitmap * @pages: number of physical pages * * This conversion is from physical pages to the number of bits * required in the bitmap. */ static inline int pcpu_nr_pages_to_map_bits(int pages) { return pages * PAGE_SIZE / PCPU_MIN_ALLOC_SIZE; } /** * pcpu_chunk_map_bits - helper to convert nr_pages to size of bitmap * @chunk: chunk of interest * * This conversion is from the number of physical pages that the chunk * serves to the number of bits in the bitmap. */ static inline int pcpu_chunk_map_bits(struct pcpu_chunk *chunk) { return pcpu_nr_pages_to_map_bits(chunk->nr_pages); } /** * pcpu_obj_full_size - helper to calculate size of each accounted object * @size: size of area to allocate in bytes * * For each accounted object there is an extra space which is used to store * obj_cgroup membership if kmemcg is not disabled. Charge it too. */ static inline size_t pcpu_obj_full_size(size_t size) { size_t extra_size = 0; #ifdef CONFIG_MEMCG_KMEM if (!mem_cgroup_kmem_disabled()) extra_size += size / PCPU_MIN_ALLOC_SIZE * sizeof(struct obj_cgroup *); #endif return size * num_possible_cpus() + extra_size; } #ifdef CONFIG_PERCPU_STATS #include <linux/spinlock.h> struct percpu_stats { u64 nr_alloc; /* lifetime # of allocations */ u64 nr_dealloc; /* lifetime # of deallocations */ u64 nr_cur_alloc; /* current # of allocations */ u64 nr_max_alloc; /* max # of live allocations */ u32 nr_chunks; /* current # of live chunks */ u32 nr_max_chunks; /* max # of live chunks */ size_t min_alloc_size; /* min allocation size */ size_t max_alloc_size; /* max allocation size */ }; extern struct percpu_stats pcpu_stats; extern struct pcpu_alloc_info pcpu_stats_ai; /* * For debug purposes. We don't care about the flexible array. */ static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { memcpy(&pcpu_stats_ai, ai, sizeof(struct pcpu_alloc_info)); /* initialize min_alloc_size to unit_size */ pcpu_stats.min_alloc_size = pcpu_stats_ai.unit_size; } /* * pcpu_stats_area_alloc - increment area allocation stats * @chunk: the location of the area being allocated * @size: size of area to allocate in bytes * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_alloc++; pcpu_stats.nr_cur_alloc++; pcpu_stats.nr_max_alloc = max(pcpu_stats.nr_max_alloc, pcpu_stats.nr_cur_alloc); pcpu_stats.min_alloc_size = min(pcpu_stats.min_alloc_size, size); pcpu_stats.max_alloc_size = max(pcpu_stats.max_alloc_size, size); chunk->nr_alloc++; chunk->max_alloc_size = max(chunk->max_alloc_size, size); } /* * pcpu_stats_area_dealloc - decrement allocation stats * @chunk: the location of the area being deallocated * * CONTEXT: * pcpu_lock. */ static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { lockdep_assert_held(&pcpu_lock); pcpu_stats.nr_dealloc++; pcpu_stats.nr_cur_alloc--; chunk->nr_alloc--; } /* * pcpu_stats_chunk_alloc - increment chunk stats */ static inline void pcpu_stats_chunk_alloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks++; pcpu_stats.nr_max_chunks = max(pcpu_stats.nr_max_chunks, pcpu_stats.nr_chunks); spin_unlock_irqrestore(&pcpu_lock, flags); } /* * pcpu_stats_chunk_dealloc - decrement chunk stats */ static inline void pcpu_stats_chunk_dealloc(void) { unsigned long flags; spin_lock_irqsave(&pcpu_lock, flags); pcpu_stats.nr_chunks--; spin_unlock_irqrestore(&pcpu_lock, flags); } #else static inline void pcpu_stats_save_ai(const struct pcpu_alloc_info *ai) { } static inline void pcpu_stats_area_alloc(struct pcpu_chunk *chunk, size_t size) { } static inline void pcpu_stats_area_dealloc(struct pcpu_chunk *chunk) { } static inline void pcpu_stats_chunk_alloc(void) { } static inline void pcpu_stats_chunk_dealloc(void) { } #endif /* !CONFIG_PERCPU_STATS */ #endif |
| 49 49 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/ptrace.c * * By Ross Biro 1/23/92 * edited by Linus Torvalds * ARM modifications Copyright (C) 2000 Russell King * Copyright (C) 2012 ARM Ltd. */ #include <linux/audit.h> #include <linux/compat.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/sched/task_stack.h> #include <linux/mm.h> #include <linux/nospec.h> #include <linux/smp.h> #include <linux/ptrace.h> #include <linux/user.h> #include <linux/seccomp.h> #include <linux/security.h> #include <linux/init.h> #include <linux/signal.h> #include <linux/string.h> #include <linux/uaccess.h> #include <linux/perf_event.h> #include <linux/hw_breakpoint.h> #include <linux/regset.h> #include <linux/elf.h> #include <linux/rseq.h> #include <asm/compat.h> #include <asm/cpufeature.h> #include <asm/debug-monitors.h> #include <asm/fpsimd.h> #include <asm/mte.h> #include <asm/pointer_auth.h> #include <asm/stacktrace.h> #include <asm/syscall.h> #include <asm/traps.h> #include <asm/system_misc.h> #define CREATE_TRACE_POINTS #include <trace/events/syscalls.h> struct pt_regs_offset { const char *name; int offset; }; #define REG_OFFSET_NAME(r) {.name = #r, .offset = offsetof(struct pt_regs, r)} #define REG_OFFSET_END {.name = NULL, .offset = 0} #define GPR_OFFSET_NAME(r) \ {.name = "x" #r, .offset = offsetof(struct pt_regs, regs[r])} static const struct pt_regs_offset regoffset_table[] = { GPR_OFFSET_NAME(0), GPR_OFFSET_NAME(1), GPR_OFFSET_NAME(2), GPR_OFFSET_NAME(3), GPR_OFFSET_NAME(4), GPR_OFFSET_NAME(5), GPR_OFFSET_NAME(6), GPR_OFFSET_NAME(7), GPR_OFFSET_NAME(8), GPR_OFFSET_NAME(9), GPR_OFFSET_NAME(10), GPR_OFFSET_NAME(11), GPR_OFFSET_NAME(12), GPR_OFFSET_NAME(13), GPR_OFFSET_NAME(14), GPR_OFFSET_NAME(15), GPR_OFFSET_NAME(16), GPR_OFFSET_NAME(17), GPR_OFFSET_NAME(18), GPR_OFFSET_NAME(19), GPR_OFFSET_NAME(20), GPR_OFFSET_NAME(21), GPR_OFFSET_NAME(22), GPR_OFFSET_NAME(23), GPR_OFFSET_NAME(24), GPR_OFFSET_NAME(25), GPR_OFFSET_NAME(26), GPR_OFFSET_NAME(27), GPR_OFFSET_NAME(28), GPR_OFFSET_NAME(29), GPR_OFFSET_NAME(30), {.name = "lr", .offset = offsetof(struct pt_regs, regs[30])}, REG_OFFSET_NAME(sp), REG_OFFSET_NAME(pc), REG_OFFSET_NAME(pstate), REG_OFFSET_END, }; /** * regs_query_register_offset() - query register offset from its name * @name: the name of a register * * regs_query_register_offset() returns the offset of a register in struct * pt_regs from its name. If the name is invalid, this returns -EINVAL; */ int regs_query_register_offset(const char *name) { const struct pt_regs_offset *roff; for (roff = regoffset_table; roff->name != NULL; roff++) if (!strcmp(roff->name, name)) return roff->offset; return -EINVAL; } /** * regs_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 bool regs_within_kernel_stack(struct pt_regs *regs, unsigned long addr) { return ((addr & ~(THREAD_SIZE - 1)) == (kernel_stack_pointer(regs) & ~(THREAD_SIZE - 1))) || on_irq_stack(addr, sizeof(unsigned long)); } /** * 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. */ unsigned long regs_get_kernel_stack_nth(struct pt_regs *regs, unsigned int n) { unsigned long *addr = (unsigned long *)kernel_stack_pointer(regs); addr += n; if (regs_within_kernel_stack(regs, (unsigned long)addr)) return *addr; else return 0; } /* * TODO: does not yet catch signals sent when the child dies. * in exit.c or in signal.c. */ /* * Called by kernel/ptrace.c when detaching.. */ void ptrace_disable(struct task_struct *child) { /* * This would be better off in core code, but PTRACE_DETACH has * grown its fair share of arch-specific worts and changing it * is likely to cause regressions on obscure architectures. */ user_disable_single_step(child); } #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * Handle hitting a HW-breakpoint. */ static void ptrace_hbptriggered(struct perf_event *bp, struct perf_sample_data *data, struct pt_regs *regs) { struct arch_hw_breakpoint *bkpt = counter_arch_bp(bp); const char *desc = "Hardware breakpoint trap (ptrace)"; if (is_compat_task()) { int si_errno = 0; int i; for (i = 0; i < ARM_MAX_BRP; ++i) { if (current->thread.debug.hbp_break[i] == bp) { si_errno = (i << 1) + 1; break; } } for (i = 0; i < ARM_MAX_WRP; ++i) { if (current->thread.debug.hbp_watch[i] == bp) { si_errno = -((i << 1) + 1); break; } } arm64_force_sig_ptrace_errno_trap(si_errno, bkpt->trigger, desc); return; } arm64_force_sig_fault(SIGTRAP, TRAP_HWBKPT, bkpt->trigger, desc); } /* * Unregister breakpoints from this task and reset the pointers in * the thread_struct. */ void flush_ptrace_hw_breakpoint(struct task_struct *tsk) { int i; struct thread_struct *t = &tsk->thread; for (i = 0; i < ARM_MAX_BRP; i++) { if (t->debug.hbp_break[i]) { unregister_hw_breakpoint(t->debug.hbp_break[i]); t->debug.hbp_break[i] = NULL; } } for (i = 0; i < ARM_MAX_WRP; i++) { if (t->debug.hbp_watch[i]) { unregister_hw_breakpoint(t->debug.hbp_watch[i]); t->debug.hbp_watch[i] = NULL; } } } void ptrace_hw_copy_thread(struct task_struct *tsk) { memset(&tsk->thread.debug, 0, sizeof(struct debug_info)); } static struct perf_event *ptrace_hbp_get_event(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp = ERR_PTR(-EINVAL); switch (note_type) { case NT_ARM_HW_BREAK: if (idx >= ARM_MAX_BRP) goto out; idx = array_index_nospec(idx, ARM_MAX_BRP); bp = tsk->thread.debug.hbp_break[idx]; break; case NT_ARM_HW_WATCH: if (idx >= ARM_MAX_WRP) goto out; idx = array_index_nospec(idx, ARM_MAX_WRP); bp = tsk->thread.debug.hbp_watch[idx]; break; } out: return bp; } static int ptrace_hbp_set_event(unsigned int note_type, struct task_struct *tsk, unsigned long idx, struct perf_event *bp) { int err = -EINVAL; switch (note_type) { case NT_ARM_HW_BREAK: if (idx >= ARM_MAX_BRP) goto out; idx = array_index_nospec(idx, ARM_MAX_BRP); tsk->thread.debug.hbp_break[idx] = bp; err = 0; break; case NT_ARM_HW_WATCH: if (idx >= ARM_MAX_WRP) goto out; idx = array_index_nospec(idx, ARM_MAX_WRP); tsk->thread.debug.hbp_watch[idx] = bp; err = 0; break; } out: return err; } static struct perf_event *ptrace_hbp_create(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp; struct perf_event_attr attr; int err, type; switch (note_type) { case NT_ARM_HW_BREAK: type = HW_BREAKPOINT_X; break; case NT_ARM_HW_WATCH: type = HW_BREAKPOINT_RW; break; default: return ERR_PTR(-EINVAL); } ptrace_breakpoint_init(&attr); /* * Initialise fields to sane defaults * (i.e. values that will pass validation). */ attr.bp_addr = 0; attr.bp_len = HW_BREAKPOINT_LEN_4; attr.bp_type = type; attr.disabled = 1; bp = register_user_hw_breakpoint(&attr, ptrace_hbptriggered, NULL, tsk); if (IS_ERR(bp)) return bp; err = ptrace_hbp_set_event(note_type, tsk, idx, bp); if (err) return ERR_PTR(err); return bp; } static int ptrace_hbp_fill_attr_ctrl(unsigned int note_type, struct arch_hw_breakpoint_ctrl ctrl, struct perf_event_attr *attr) { int err, len, type, offset, disabled = !ctrl.enabled; attr->disabled = disabled; if (disabled) return 0; err = arch_bp_generic_fields(ctrl, &len, &type, &offset); if (err) return err; switch (note_type) { case NT_ARM_HW_BREAK: if ((type & HW_BREAKPOINT_X) != type) return -EINVAL; break; case NT_ARM_HW_WATCH: if ((type & HW_BREAKPOINT_RW) != type) return -EINVAL; break; default: return -EINVAL; } attr->bp_len = len; attr->bp_type = type; attr->bp_addr += offset; return 0; } static int ptrace_hbp_get_resource_info(unsigned int note_type, u32 *info) { u8 num; u32 reg = 0; switch (note_type) { case NT_ARM_HW_BREAK: num = hw_breakpoint_slots(TYPE_INST); break; case NT_ARM_HW_WATCH: num = hw_breakpoint_slots(TYPE_DATA); break; default: return -EINVAL; } reg |= debug_monitors_arch(); reg <<= 8; reg |= num; *info = reg; return 0; } static int ptrace_hbp_get_ctrl(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u32 *ctrl) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); *ctrl = bp ? encode_ctrl_reg(counter_arch_bp(bp)->ctrl) : 0; return 0; } static int ptrace_hbp_get_addr(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u64 *addr) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (IS_ERR(bp)) return PTR_ERR(bp); *addr = bp ? counter_arch_bp(bp)->address : 0; return 0; } static struct perf_event *ptrace_hbp_get_initialised_bp(unsigned int note_type, struct task_struct *tsk, unsigned long idx) { struct perf_event *bp = ptrace_hbp_get_event(note_type, tsk, idx); if (!bp) bp = ptrace_hbp_create(note_type, tsk, idx); return bp; } static int ptrace_hbp_set_ctrl(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u32 uctrl) { int err; struct perf_event *bp; struct perf_event_attr attr; struct arch_hw_breakpoint_ctrl ctrl; bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) { err = PTR_ERR(bp); return err; } attr = bp->attr; decode_ctrl_reg(uctrl, &ctrl); err = ptrace_hbp_fill_attr_ctrl(note_type, ctrl, &attr); if (err) return err; return modify_user_hw_breakpoint(bp, &attr); } static int ptrace_hbp_set_addr(unsigned int note_type, struct task_struct *tsk, unsigned long idx, u64 addr) { int err; struct perf_event *bp; struct perf_event_attr attr; bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx); if (IS_ERR(bp)) { err = PTR_ERR(bp); return err; } attr = bp->attr; attr.bp_addr = addr; err = modify_user_hw_breakpoint(bp, &attr); return err; } #define PTRACE_HBP_ADDR_SZ sizeof(u64) #define PTRACE_HBP_CTRL_SZ sizeof(u32) #define PTRACE_HBP_PAD_SZ sizeof(u32) static int hw_break_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { unsigned int note_type = regset->core_note_type; int ret, idx = 0; u32 info, ctrl; u64 addr; /* Resource info */ ret = ptrace_hbp_get_resource_info(note_type, &info); if (ret) return ret; membuf_write(&to, &info, sizeof(info)); membuf_zero(&to, sizeof(u32)); /* (address, ctrl) registers */ while (to.left) { ret = ptrace_hbp_get_addr(note_type, target, idx, &addr); if (ret) return ret; ret = ptrace_hbp_get_ctrl(note_type, target, idx, &ctrl); if (ret) return ret; membuf_store(&to, addr); membuf_store(&to, ctrl); membuf_zero(&to, sizeof(u32)); idx++; } return 0; } static int hw_break_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { unsigned int note_type = regset->core_note_type; int ret, idx = 0, offset, limit; u32 ctrl; u64 addr; /* Resource info and pad */ offset = offsetof(struct user_hwdebug_state, dbg_regs); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, 0, offset); /* (address, ctrl) registers */ limit = regset->n * regset->size; while (count && offset < limit) { if (count < PTRACE_HBP_ADDR_SZ) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &addr, offset, offset + PTRACE_HBP_ADDR_SZ); if (ret) return ret; ret = ptrace_hbp_set_addr(note_type, target, idx, addr); if (ret) return ret; offset += PTRACE_HBP_ADDR_SZ; if (!count) break; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, offset, offset + PTRACE_HBP_CTRL_SZ); if (ret) return ret; ret = ptrace_hbp_set_ctrl(note_type, target, idx, ctrl); if (ret) return ret; offset += PTRACE_HBP_CTRL_SZ; user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, offset, offset + PTRACE_HBP_PAD_SZ); offset += PTRACE_HBP_PAD_SZ; idx++; } return 0; } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ static int gpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_pt_regs *uregs = &task_pt_regs(target)->user_regs; return membuf_write(&to, uregs, sizeof(*uregs)); } static int gpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_pt_regs newregs = task_pt_regs(target)->user_regs; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newregs, 0, -1); if (ret) return ret; if (!valid_user_regs(&newregs, target)) return -EINVAL; task_pt_regs(target)->user_regs = newregs; return 0; } static int fpr_active(struct task_struct *target, const struct user_regset *regset) { if (!system_supports_fpsimd()) return -ENODEV; return regset->n; } /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ static int __fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_fpsimd_state *uregs; sve_sync_to_fpsimd(target); uregs = &target->thread.uw.fpsimd_state; return membuf_write(&to, uregs, sizeof(*uregs)); } static int fpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_fpsimd()) return -EINVAL; if (target == current) fpsimd_preserve_current_state(); return __fpr_get(target, regset, to); } static int __fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf, unsigned int start_pos) { int ret; struct user_fpsimd_state newstate; /* * Ensure target->thread.uw.fpsimd_state is up to date, so that a * short copyin can't resurrect stale data. */ sve_sync_to_fpsimd(target); newstate = target->thread.uw.fpsimd_state; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &newstate, start_pos, start_pos + sizeof(newstate)); if (ret) return ret; target->thread.uw.fpsimd_state = newstate; return ret; } static int fpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; if (!system_supports_fpsimd()) return -EINVAL; ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; sve_sync_from_fpsimd_zeropad(target); fpsimd_flush_task_state(target); return ret; } static int tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int ret; if (target == current) tls_preserve_current_state(); ret = membuf_store(&to, target->thread.uw.tp_value); if (system_supports_tpidr2()) ret = membuf_store(&to, target->thread.tpidr2_el0); else ret = membuf_zero(&to, sizeof(u64)); return ret; } static int tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; unsigned long tls[2]; tls[0] = target->thread.uw.tp_value; if (system_supports_tpidr2()) tls[1] = target->thread.tpidr2_el0; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, tls, 0, count); if (ret) return ret; target->thread.uw.tp_value = tls[0]; if (system_supports_tpidr2()) target->thread.tpidr2_el0 = tls[1]; return ret; } static int fpmr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_fpmr()) return -EINVAL; if (target == current) fpsimd_preserve_current_state(); return membuf_store(&to, target->thread.uw.fpmr); } static int fpmr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; unsigned long fpmr; if (!system_supports_fpmr()) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpmr, 0, count); if (ret) return ret; target->thread.uw.fpmr = fpmr; fpsimd_flush_task_state(target); return 0; } static int system_call_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { return membuf_store(&to, task_pt_regs(target)->syscallno); } static int system_call_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int syscallno = task_pt_regs(target)->syscallno; int ret; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &syscallno, 0, -1); if (ret) return ret; task_pt_regs(target)->syscallno = syscallno; return ret; } #ifdef CONFIG_ARM64_SVE static void sve_init_header_from_task(struct user_sve_header *header, struct task_struct *target, enum vec_type type) { unsigned int vq; bool active; enum vec_type task_type; memset(header, 0, sizeof(*header)); /* Check if the requested registers are active for the task */ if (thread_sm_enabled(&target->thread)) task_type = ARM64_VEC_SME; else task_type = ARM64_VEC_SVE; active = (task_type == type); switch (type) { case ARM64_VEC_SVE: if (test_tsk_thread_flag(target, TIF_SVE_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; break; case ARM64_VEC_SME: if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header->flags |= SVE_PT_VL_INHERIT; break; default: WARN_ON_ONCE(1); return; } if (active) { if (target->thread.fp_type == FP_STATE_FPSIMD) { header->flags |= SVE_PT_REGS_FPSIMD; } else { header->flags |= SVE_PT_REGS_SVE; } } header->vl = task_get_vl(target, type); vq = sve_vq_from_vl(header->vl); header->max_vl = vec_max_vl(type); header->size = SVE_PT_SIZE(vq, header->flags); header->max_size = SVE_PT_SIZE(sve_vq_from_vl(header->max_vl), SVE_PT_REGS_SVE); } static unsigned int sve_size_from_header(struct user_sve_header const *header) { return ALIGN(header->size, SVE_VQ_BYTES); } static int sve_get_common(struct task_struct *target, const struct user_regset *regset, struct membuf to, enum vec_type type) { struct user_sve_header header; unsigned int vq; unsigned long start, end; /* Header */ sve_init_header_from_task(&header, target, type); vq = sve_vq_from_vl(header.vl); membuf_write(&to, &header, sizeof(header)); if (target == current) fpsimd_preserve_current_state(); BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); switch ((header.flags & SVE_PT_REGS_MASK)) { case SVE_PT_REGS_FPSIMD: return __fpr_get(target, regset, to); case SVE_PT_REGS_SVE: start = SVE_PT_SVE_OFFSET; end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); membuf_write(&to, target->thread.sve_state, end - start); start = end; end = SVE_PT_SVE_FPSR_OFFSET(vq); membuf_zero(&to, end - start); /* * Copy fpsr, and fpcr which must follow contiguously in * struct fpsimd_state: */ start = end; end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; membuf_write(&to, &target->thread.uw.fpsimd_state.fpsr, end - start); start = end; end = sve_size_from_header(&header); return membuf_zero(&to, end - start); default: return 0; } } static int sve_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sve()) return -EINVAL; return sve_get_common(target, regset, to, ARM64_VEC_SVE); } static int sve_set_common(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf, enum vec_type type) { int ret; struct user_sve_header header; unsigned int vq; unsigned long start, end; /* Header */ if (count < sizeof(header)) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, 0, sizeof(header)); if (ret) goto out; /* * Apart from SVE_PT_REGS_MASK, all SVE_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for us: */ ret = vec_set_vector_length(target, type, header.vl, ((unsigned long)header.flags & ~SVE_PT_REGS_MASK) << 16); if (ret) goto out; /* Actual VL set may be less than the user asked for: */ vq = sve_vq_from_vl(task_get_vl(target, type)); /* Enter/exit streaming mode */ if (system_supports_sme()) { u64 old_svcr = target->thread.svcr; switch (type) { case ARM64_VEC_SVE: target->thread.svcr &= ~SVCR_SM_MASK; break; case ARM64_VEC_SME: target->thread.svcr |= SVCR_SM_MASK; /* * Disable traps and ensure there is SME storage but * preserve any currently set values in ZA/ZT. */ sme_alloc(target, false); set_tsk_thread_flag(target, TIF_SME); break; default: WARN_ON_ONCE(1); ret = -EINVAL; goto out; } /* * If we switched then invalidate any existing SVE * state and ensure there's storage. */ if (target->thread.svcr != old_svcr) sve_alloc(target, true); } /* Registers: FPSIMD-only case */ BUILD_BUG_ON(SVE_PT_FPSIMD_OFFSET != sizeof(header)); if ((header.flags & SVE_PT_REGS_MASK) == SVE_PT_REGS_FPSIMD) { ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, SVE_PT_FPSIMD_OFFSET); clear_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_FPSIMD; goto out; } /* * Otherwise: no registers or full SVE case. For backwards * compatibility reasons we treat empty flags as SVE registers. */ /* * If setting a different VL from the requested VL and there is * register data, the data layout will be wrong: don't even * try to set the registers in this case. */ if (count && vq != sve_vq_from_vl(header.vl)) { ret = -EIO; goto out; } sve_alloc(target, true); if (!target->thread.sve_state) { ret = -ENOMEM; clear_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_FPSIMD; goto out; } /* * Ensure target->thread.sve_state is up to date with target's * FPSIMD regs, so that a short copyin leaves trailing * registers unmodified. Only enable SVE if we are * configuring normal SVE, a system with streaming SVE may not * have normal SVE. */ fpsimd_sync_to_sve(target); if (type == ARM64_VEC_SVE) set_tsk_thread_flag(target, TIF_SVE); target->thread.fp_type = FP_STATE_SVE; BUILD_BUG_ON(SVE_PT_SVE_OFFSET != sizeof(header)); start = SVE_PT_SVE_OFFSET; end = SVE_PT_SVE_FFR_OFFSET(vq) + SVE_PT_SVE_FFR_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, target->thread.sve_state, start, end); if (ret) goto out; start = end; end = SVE_PT_SVE_FPSR_OFFSET(vq); user_regset_copyin_ignore(&pos, &count, &kbuf, &ubuf, start, end); /* * Copy fpsr, and fpcr which must follow contiguously in * struct fpsimd_state: */ start = end; end = SVE_PT_SVE_FPCR_OFFSET(vq) + SVE_PT_SVE_FPCR_SIZE; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &target->thread.uw.fpsimd_state.fpsr, start, end); out: fpsimd_flush_task_state(target); return ret; } static int sve_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { if (!system_supports_sve()) return -EINVAL; return sve_set_common(target, regset, pos, count, kbuf, ubuf, ARM64_VEC_SVE); } #endif /* CONFIG_ARM64_SVE */ #ifdef CONFIG_ARM64_SME static int ssve_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sme()) return -EINVAL; return sve_get_common(target, regset, to, ARM64_VEC_SME); } static int ssve_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { if (!system_supports_sme()) return -EINVAL; return sve_set_common(target, regset, pos, count, kbuf, ubuf, ARM64_VEC_SME); } static int za_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_za_header header; unsigned int vq; unsigned long start, end; if (!system_supports_sme()) return -EINVAL; /* Header */ memset(&header, 0, sizeof(header)); if (test_tsk_thread_flag(target, TIF_SME_VL_INHERIT)) header.flags |= ZA_PT_VL_INHERIT; header.vl = task_get_sme_vl(target); vq = sve_vq_from_vl(header.vl); header.max_vl = sme_max_vl(); header.max_size = ZA_PT_SIZE(vq); /* If ZA is not active there is only the header */ if (thread_za_enabled(&target->thread)) header.size = ZA_PT_SIZE(vq); else header.size = ZA_PT_ZA_OFFSET; membuf_write(&to, &header, sizeof(header)); BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); end = ZA_PT_ZA_OFFSET; if (target == current) fpsimd_preserve_current_state(); /* Any register data to include? */ if (thread_za_enabled(&target->thread)) { start = end; end = ZA_PT_SIZE(vq); membuf_write(&to, target->thread.sme_state, end - start); } /* Zero any trailing padding */ start = end; end = ALIGN(header.size, SVE_VQ_BYTES); return membuf_zero(&to, end - start); } static int za_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; struct user_za_header header; unsigned int vq; unsigned long start, end; if (!system_supports_sme()) return -EINVAL; /* Header */ if (count < sizeof(header)) return -EINVAL; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &header, 0, sizeof(header)); if (ret) goto out; /* * All current ZA_PT_* flags are consumed by * vec_set_vector_length(), which will also validate them for * us: */ ret = vec_set_vector_length(target, ARM64_VEC_SME, header.vl, ((unsigned long)header.flags) << 16); if (ret) goto out; /* Actual VL set may be less than the user asked for: */ vq = sve_vq_from_vl(task_get_sme_vl(target)); /* Ensure there is some SVE storage for streaming mode */ if (!target->thread.sve_state) { sve_alloc(target, false); if (!target->thread.sve_state) { ret = -ENOMEM; goto out; } } /* * Only flush the storage if PSTATE.ZA was not already set, * otherwise preserve any existing data. */ sme_alloc(target, !thread_za_enabled(&target->thread)); if (!target->thread.sme_state) return -ENOMEM; /* If there is no data then disable ZA */ if (!count) { target->thread.svcr &= ~SVCR_ZA_MASK; goto out; } /* * If setting a different VL from the requested VL and there is * register data, the data layout will be wrong: don't even * try to set the registers in this case. */ if (vq != sve_vq_from_vl(header.vl)) { ret = -EIO; goto out; } BUILD_BUG_ON(ZA_PT_ZA_OFFSET != sizeof(header)); start = ZA_PT_ZA_OFFSET; end = ZA_PT_SIZE(vq); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, target->thread.sme_state, start, end); if (ret) goto out; /* Mark ZA as active and let userspace use it */ set_tsk_thread_flag(target, TIF_SME); target->thread.svcr |= SVCR_ZA_MASK; out: fpsimd_flush_task_state(target); return ret; } static int zt_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { if (!system_supports_sme2()) return -EINVAL; /* * If PSTATE.ZA is not set then ZT will be zeroed when it is * enabled so report the current register value as zero. */ if (thread_za_enabled(&target->thread)) membuf_write(&to, thread_zt_state(&target->thread), ZT_SIG_REG_BYTES); else membuf_zero(&to, ZT_SIG_REG_BYTES); return 0; } static int zt_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; if (!system_supports_sme2()) return -EINVAL; /* Ensure SVE storage in case this is first use of SME */ sve_alloc(target, false); if (!target->thread.sve_state) return -ENOMEM; if (!thread_za_enabled(&target->thread)) { sme_alloc(target, true); if (!target->thread.sme_state) return -ENOMEM; } ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, thread_zt_state(&target->thread), 0, ZT_SIG_REG_BYTES); if (ret == 0) { target->thread.svcr |= SVCR_ZA_MASK; set_tsk_thread_flag(target, TIF_SME); } fpsimd_flush_task_state(target); return ret; } #endif /* CONFIG_ARM64_SME */ #ifdef CONFIG_ARM64_PTR_AUTH static int pac_mask_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { /* * The PAC bits can differ across data and instruction pointers * depending on TCR_EL1.TBID*, which we may make use of in future, so * we expose separate masks. */ unsigned long mask = ptrauth_user_pac_mask(); struct user_pac_mask uregs = { .data_mask = mask, .insn_mask = mask, }; if (!system_supports_address_auth()) return -EINVAL; return membuf_write(&to, &uregs, sizeof(uregs)); } static int pac_enabled_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { long enabled_keys = ptrauth_get_enabled_keys(target); if (IS_ERR_VALUE(enabled_keys)) return enabled_keys; return membuf_write(&to, &enabled_keys, sizeof(enabled_keys)); } static int pac_enabled_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long enabled_keys = ptrauth_get_enabled_keys(target); if (IS_ERR_VALUE(enabled_keys)) return enabled_keys; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &enabled_keys, 0, sizeof(long)); if (ret) return ret; return ptrauth_set_enabled_keys(target, PR_PAC_ENABLED_KEYS_MASK, enabled_keys); } #ifdef CONFIG_CHECKPOINT_RESTORE static __uint128_t pac_key_to_user(const struct ptrauth_key *key) { return (__uint128_t)key->hi << 64 | key->lo; } static struct ptrauth_key pac_key_from_user(__uint128_t ukey) { struct ptrauth_key key = { .lo = (unsigned long)ukey, .hi = (unsigned long)(ukey >> 64), }; return key; } static void pac_address_keys_to_user(struct user_pac_address_keys *ukeys, const struct ptrauth_keys_user *keys) { ukeys->apiakey = pac_key_to_user(&keys->apia); ukeys->apibkey = pac_key_to_user(&keys->apib); ukeys->apdakey = pac_key_to_user(&keys->apda); ukeys->apdbkey = pac_key_to_user(&keys->apdb); } static void pac_address_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_address_keys *ukeys) { keys->apia = pac_key_from_user(ukeys->apiakey); keys->apib = pac_key_from_user(ukeys->apibkey); keys->apda = pac_key_from_user(ukeys->apdakey); keys->apdb = pac_key_from_user(ukeys->apdbkey); } static int pac_address_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; if (!system_supports_address_auth()) return -EINVAL; pac_address_keys_to_user(&user_keys, keys); return membuf_write(&to, &user_keys, sizeof(user_keys)); } static int pac_address_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_address_keys user_keys; int ret; if (!system_supports_address_auth()) return -EINVAL; pac_address_keys_to_user(&user_keys, keys); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_keys, 0, -1); if (ret) return ret; pac_address_keys_from_user(keys, &user_keys); return 0; } static void pac_generic_keys_to_user(struct user_pac_generic_keys *ukeys, const struct ptrauth_keys_user *keys) { ukeys->apgakey = pac_key_to_user(&keys->apga); } static void pac_generic_keys_from_user(struct ptrauth_keys_user *keys, const struct user_pac_generic_keys *ukeys) { keys->apga = pac_key_from_user(ukeys->apgakey); } static int pac_generic_keys_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; if (!system_supports_generic_auth()) return -EINVAL; pac_generic_keys_to_user(&user_keys, keys); return membuf_write(&to, &user_keys, sizeof(user_keys)); } static int pac_generic_keys_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct ptrauth_keys_user *keys = &target->thread.keys_user; struct user_pac_generic_keys user_keys; int ret; if (!system_supports_generic_auth()) return -EINVAL; pac_generic_keys_to_user(&user_keys, keys); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &user_keys, 0, -1); if (ret) return ret; pac_generic_keys_from_user(keys, &user_keys); return 0; } #endif /* CONFIG_CHECKPOINT_RESTORE */ #endif /* CONFIG_ARM64_PTR_AUTH */ #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI static int tagged_addr_ctrl_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { long ctrl = get_tagged_addr_ctrl(target); if (IS_ERR_VALUE(ctrl)) return ctrl; return membuf_write(&to, &ctrl, sizeof(ctrl)); } static int tagged_addr_ctrl_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; long ctrl; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &ctrl, 0, -1); if (ret) return ret; return set_tagged_addr_ctrl(target, ctrl); } #endif enum aarch64_regset { REGSET_GPR, REGSET_FPR, REGSET_TLS, #ifdef CONFIG_HAVE_HW_BREAKPOINT REGSET_HW_BREAK, REGSET_HW_WATCH, #endif REGSET_FPMR, REGSET_SYSTEM_CALL, #ifdef CONFIG_ARM64_SVE REGSET_SVE, #endif #ifdef CONFIG_ARM64_SME REGSET_SSVE, REGSET_ZA, REGSET_ZT, #endif #ifdef CONFIG_ARM64_PTR_AUTH REGSET_PAC_MASK, REGSET_PAC_ENABLED_KEYS, #ifdef CONFIG_CHECKPOINT_RESTORE REGSET_PACA_KEYS, REGSET_PACG_KEYS, #endif #endif #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI REGSET_TAGGED_ADDR_CTRL, #endif }; static const struct user_regset aarch64_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = sizeof(struct user_pt_regs) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = gpr_get, .set = gpr_set }, [REGSET_FPR] = { .core_note_type = NT_PRFPREG, .n = sizeof(struct user_fpsimd_state) / sizeof(u32), /* * We pretend we have 32-bit registers because the fpsr and * fpcr are 32-bits wide. */ .size = sizeof(u32), .align = sizeof(u32), .active = fpr_active, .regset_get = fpr_get, .set = fpr_set }, [REGSET_TLS] = { .core_note_type = NT_ARM_TLS, .n = 2, .size = sizeof(void *), .align = sizeof(void *), .regset_get = tls_get, .set = tls_set, }, #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { .core_note_type = NT_ARM_HW_BREAK, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { .core_note_type = NT_ARM_HW_WATCH, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, #endif [REGSET_SYSTEM_CALL] = { .core_note_type = NT_ARM_SYSTEM_CALL, .n = 1, .size = sizeof(int), .align = sizeof(int), .regset_get = system_call_get, .set = system_call_set, }, [REGSET_FPMR] = { .core_note_type = NT_ARM_FPMR, .n = 1, .size = sizeof(u64), .align = sizeof(u64), .regset_get = fpmr_get, .set = fpmr_set, }, #ifdef CONFIG_ARM64_SVE [REGSET_SVE] = { /* Scalable Vector Extension */ .core_note_type = NT_ARM_SVE, .n = DIV_ROUND_UP(SVE_PT_SIZE(ARCH_SVE_VQ_MAX, SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = sve_get, .set = sve_set, }, #endif #ifdef CONFIG_ARM64_SME [REGSET_SSVE] = { /* Streaming mode SVE */ .core_note_type = NT_ARM_SSVE, .n = DIV_ROUND_UP(SVE_PT_SIZE(SME_VQ_MAX, SVE_PT_REGS_SVE), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = ssve_get, .set = ssve_set, }, [REGSET_ZA] = { /* SME ZA */ .core_note_type = NT_ARM_ZA, /* * ZA is a single register but it's variably sized and * the ptrace core requires that the size of any data * be an exact multiple of the configured register * size so report as though we had SVE_VQ_BYTES * registers. These values aren't exposed to * userspace. */ .n = DIV_ROUND_UP(ZA_PT_SIZE(SME_VQ_MAX), SVE_VQ_BYTES), .size = SVE_VQ_BYTES, .align = SVE_VQ_BYTES, .regset_get = za_get, .set = za_set, }, [REGSET_ZT] = { /* SME ZT */ .core_note_type = NT_ARM_ZT, .n = 1, .size = ZT_SIG_REG_BYTES, .align = sizeof(u64), .regset_get = zt_get, .set = zt_set, }, #endif #ifdef CONFIG_ARM64_PTR_AUTH [REGSET_PAC_MASK] = { .core_note_type = NT_ARM_PAC_MASK, .n = sizeof(struct user_pac_mask) / sizeof(u64), .size = sizeof(u64), .align = sizeof(u64), .regset_get = pac_mask_get, /* this cannot be set dynamically */ }, [REGSET_PAC_ENABLED_KEYS] = { .core_note_type = NT_ARM_PAC_ENABLED_KEYS, .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = pac_enabled_keys_get, .set = pac_enabled_keys_set, }, #ifdef CONFIG_CHECKPOINT_RESTORE [REGSET_PACA_KEYS] = { .core_note_type = NT_ARM_PACA_KEYS, .n = sizeof(struct user_pac_address_keys) / sizeof(__uint128_t), .size = sizeof(__uint128_t), .align = sizeof(__uint128_t), .regset_get = pac_address_keys_get, .set = pac_address_keys_set, }, [REGSET_PACG_KEYS] = { .core_note_type = NT_ARM_PACG_KEYS, .n = sizeof(struct user_pac_generic_keys) / sizeof(__uint128_t), .size = sizeof(__uint128_t), .align = sizeof(__uint128_t), .regset_get = pac_generic_keys_get, .set = pac_generic_keys_set, }, #endif #endif #ifdef CONFIG_ARM64_TAGGED_ADDR_ABI [REGSET_TAGGED_ADDR_CTRL] = { .core_note_type = NT_ARM_TAGGED_ADDR_CTRL, .n = 1, .size = sizeof(long), .align = sizeof(long), .regset_get = tagged_addr_ctrl_get, .set = tagged_addr_ctrl_set, }, #endif }; static const struct user_regset_view user_aarch64_view = { .name = "aarch64", .e_machine = EM_AARCH64, .regsets = aarch64_regsets, .n = ARRAY_SIZE(aarch64_regsets) }; enum compat_regset { REGSET_COMPAT_GPR, REGSET_COMPAT_VFP, }; static inline compat_ulong_t compat_get_user_reg(struct task_struct *task, int idx) { struct pt_regs *regs = task_pt_regs(task); switch (idx) { case 15: return regs->pc; case 16: return pstate_to_compat_psr(regs->pstate); case 17: return regs->orig_x0; default: return regs->regs[idx]; } } static int compat_gpr_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { int i = 0; while (to.left) membuf_store(&to, compat_get_user_reg(target, i++)); return 0; } static int compat_gpr_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct pt_regs newregs; int ret = 0; unsigned int i, start, num_regs; /* Calculate the number of AArch32 registers contained in count */ num_regs = count / regset->size; /* Convert pos into an register number */ start = pos / regset->size; if (start + num_regs > regset->n) return -EIO; newregs = *task_pt_regs(target); for (i = 0; i < num_regs; ++i) { unsigned int idx = start + i; compat_ulong_t reg; if (kbuf) { memcpy(®, kbuf, sizeof(reg)); kbuf += sizeof(reg); } else { ret = copy_from_user(®, ubuf, sizeof(reg)); if (ret) { ret = -EFAULT; break; } ubuf += sizeof(reg); } switch (idx) { case 15: newregs.pc = reg; break; case 16: reg = compat_psr_to_pstate(reg); newregs.pstate = reg; break; case 17: newregs.orig_x0 = reg; break; default: newregs.regs[idx] = reg; } } if (valid_user_regs(&newregs.user_regs, target)) *task_pt_regs(target) = newregs; else ret = -EINVAL; return ret; } static int compat_vfp_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { struct user_fpsimd_state *uregs; compat_ulong_t fpscr; if (!system_supports_fpsimd()) return -EINVAL; uregs = &target->thread.uw.fpsimd_state; if (target == current) fpsimd_preserve_current_state(); /* * The VFP registers are packed into the fpsimd_state, so they all sit * nicely together for us. We just need to create the fpscr separately. */ membuf_write(&to, uregs, VFP_STATE_SIZE - sizeof(compat_ulong_t)); fpscr = (uregs->fpsr & VFP_FPSCR_STAT_MASK) | (uregs->fpcr & VFP_FPSCR_CTRL_MASK); return membuf_store(&to, fpscr); } static int compat_vfp_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { struct user_fpsimd_state *uregs; compat_ulong_t fpscr; int ret, vregs_end_pos; if (!system_supports_fpsimd()) return -EINVAL; uregs = &target->thread.uw.fpsimd_state; vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t); ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, uregs, 0, vregs_end_pos); if (count && !ret) { ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &fpscr, vregs_end_pos, VFP_STATE_SIZE); if (!ret) { uregs->fpsr = fpscr & VFP_FPSCR_STAT_MASK; uregs->fpcr = fpscr & VFP_FPSCR_CTRL_MASK; } } fpsimd_flush_task_state(target); return ret; } static int compat_tls_get(struct task_struct *target, const struct user_regset *regset, struct membuf to) { return membuf_store(&to, (compat_ulong_t)target->thread.uw.tp_value); } static int compat_tls_set(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, const void *kbuf, const void __user *ubuf) { int ret; compat_ulong_t tls = target->thread.uw.tp_value; ret = user_regset_copyin(&pos, &count, &kbuf, &ubuf, &tls, 0, -1); if (ret) return ret; target->thread.uw.tp_value = tls; return ret; } static const struct user_regset aarch32_regsets[] = { [REGSET_COMPAT_GPR] = { .core_note_type = NT_PRSTATUS, .n = COMPAT_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .regset_get = compat_gpr_get, .set = compat_gpr_set }, [REGSET_COMPAT_VFP] = { .core_note_type = NT_ARM_VFP, .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .active = fpr_active, .regset_get = compat_vfp_get, .set = compat_vfp_set }, }; static const struct user_regset_view user_aarch32_view = { .name = "aarch32", .e_machine = EM_ARM, .regsets = aarch32_regsets, .n = ARRAY_SIZE(aarch32_regsets) }; static const struct user_regset aarch32_ptrace_regsets[] = { [REGSET_GPR] = { .core_note_type = NT_PRSTATUS, .n = COMPAT_ELF_NGREG, .size = sizeof(compat_elf_greg_t), .align = sizeof(compat_elf_greg_t), .regset_get = compat_gpr_get, .set = compat_gpr_set }, [REGSET_FPR] = { .core_note_type = NT_ARM_VFP, .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .regset_get = compat_vfp_get, .set = compat_vfp_set }, [REGSET_TLS] = { .core_note_type = NT_ARM_TLS, .n = 1, .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), .regset_get = compat_tls_get, .set = compat_tls_set, }, #ifdef CONFIG_HAVE_HW_BREAKPOINT [REGSET_HW_BREAK] = { .core_note_type = NT_ARM_HW_BREAK, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, [REGSET_HW_WATCH] = { .core_note_type = NT_ARM_HW_WATCH, .n = sizeof(struct user_hwdebug_state) / sizeof(u32), .size = sizeof(u32), .align = sizeof(u32), .regset_get = hw_break_get, .set = hw_break_set, }, #endif [REGSET_SYSTEM_CALL] = { .core_note_type = NT_ARM_SYSTEM_CALL, .n = 1, .size = sizeof(int), .align = sizeof(int), .regset_get = system_call_get, .set = system_call_set, }, }; static const struct user_regset_view user_aarch32_ptrace_view = { .name = "aarch32", .e_machine = EM_ARM, .regsets = aarch32_ptrace_regsets, .n = ARRAY_SIZE(aarch32_ptrace_regsets) }; #ifdef CONFIG_COMPAT static int compat_ptrace_read_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t __user *ret) { compat_ulong_t tmp; if (off & 3) return -EIO; if (off == COMPAT_PT_TEXT_ADDR) tmp = tsk->mm->start_code; else if (off == COMPAT_PT_DATA_ADDR) tmp = tsk->mm->start_data; else if (off == COMPAT_PT_TEXT_END_ADDR) tmp = tsk->mm->end_code; else if (off < sizeof(compat_elf_gregset_t)) tmp = compat_get_user_reg(tsk, off >> 2); else if (off >= COMPAT_USER_SZ) return -EIO; else tmp = 0; return put_user(tmp, ret); } static int compat_ptrace_write_user(struct task_struct *tsk, compat_ulong_t off, compat_ulong_t val) { struct pt_regs newregs = *task_pt_regs(tsk); unsigned int idx = off / 4; if (off & 3 || off >= COMPAT_USER_SZ) return -EIO; if (off >= sizeof(compat_elf_gregset_t)) return 0; switch (idx) { case 15: newregs.pc = val; break; case 16: newregs.pstate = compat_psr_to_pstate(val); break; case 17: newregs.orig_x0 = val; break; default: newregs.regs[idx] = val; } if (!valid_user_regs(&newregs.user_regs, tsk)) return -EINVAL; *task_pt_regs(tsk) = newregs; return 0; } #ifdef CONFIG_HAVE_HW_BREAKPOINT /* * Convert a virtual register number into an index for a thread_info * breakpoint array. Breakpoints are identified using positive numbers * whilst watchpoints are negative. The registers are laid out as pairs * of (address, control), each pair mapping to a unique hw_breakpoint struct. * Register 0 is reserved for describing resource information. */ static int compat_ptrace_hbp_num_to_idx(compat_long_t num) { return (abs(num) - 1) >> 1; } static int compat_ptrace_hbp_get_resource_info(u32 *kdata) { u8 num_brps, num_wrps, debug_arch, wp_len; u32 reg = 0; num_brps = hw_breakpoint_slots(TYPE_INST); num_wrps = hw_breakpoint_slots(TYPE_DATA); debug_arch = debug_monitors_arch(); wp_len = 8; reg |= debug_arch; reg <<= 8; reg |= wp_len; reg <<= 8; reg |= num_wrps; reg <<= 8; reg |= num_brps; *kdata = reg; return 0; } static int compat_ptrace_hbp_get(unsigned int note_type, struct task_struct *tsk, compat_long_t num, u32 *kdata) { u64 addr = 0; u32 ctrl = 0; int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { err = ptrace_hbp_get_addr(note_type, tsk, idx, &addr); *kdata = (u32)addr; } else { err = ptrace_hbp_get_ctrl(note_type, tsk, idx, &ctrl); *kdata = ctrl; } return err; } static int compat_ptrace_hbp_set(unsigned int note_type, struct task_struct *tsk, compat_long_t num, u32 *kdata) { u64 addr; u32 ctrl; int err, idx = compat_ptrace_hbp_num_to_idx(num); if (num & 1) { addr = *kdata; err = ptrace_hbp_set_addr(note_type, tsk, idx, addr); } else { ctrl = *kdata; err = ptrace_hbp_set_ctrl(note_type, tsk, idx, ctrl); } return err; } static int compat_ptrace_gethbpregs(struct task_struct *tsk, compat_long_t num, compat_ulong_t __user *data) { int ret; u32 kdata; /* Watchpoint */ if (num < 0) { ret = compat_ptrace_hbp_get(NT_ARM_HW_WATCH, tsk, num, &kdata); /* Resource info */ } else if (num == 0) { ret = compat_ptrace_hbp_get_resource_info(&kdata); /* Breakpoint */ } else { ret = compat_ptrace_hbp_get(NT_ARM_HW_BREAK, tsk, num, &kdata); } if (!ret) ret = put_user(kdata, data); return ret; } static int compat_ptrace_sethbpregs(struct task_struct *tsk, compat_long_t num, compat_ulong_t __user *data) { int ret; u32 kdata = 0; if (num == 0) return 0; ret = get_user(kdata, data); if (ret) return ret; if (num < 0) ret = compat_ptrace_hbp_set(NT_ARM_HW_WATCH, tsk, num, &kdata); else ret = compat_ptrace_hbp_set(NT_ARM_HW_BREAK, tsk, num, &kdata); return ret; } #endif /* CONFIG_HAVE_HW_BREAKPOINT */ long compat_arch_ptrace(struct task_struct *child, compat_long_t request, compat_ulong_t caddr, compat_ulong_t cdata) { unsigned long addr = caddr; unsigned long data = cdata; void __user *datap = compat_ptr(data); int ret; switch (request) { case PTRACE_PEEKUSR: ret = compat_ptrace_read_user(child, addr, datap); break; case PTRACE_POKEUSR: ret = compat_ptrace_write_user(child, addr, data); break; case COMPAT_PTRACE_GETREGS: ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, 0, sizeof(compat_elf_gregset_t), datap); break; case COMPAT_PTRACE_SETREGS: ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_GPR, 0, sizeof(compat_elf_gregset_t), datap); break; case COMPAT_PTRACE_GET_THREAD_AREA: ret = put_user((compat_ulong_t)child->thread.uw.tp_value, (compat_ulong_t __user *)datap); break; case COMPAT_PTRACE_SET_SYSCALL: task_pt_regs(child)->syscallno = data; ret = 0; break; case COMPAT_PTRACE_GETVFPREGS: ret = copy_regset_to_user(child, &user_aarch32_view, REGSET_COMPAT_VFP, 0, VFP_STATE_SIZE, datap); break; case COMPAT_PTRACE_SETVFPREGS: ret = copy_regset_from_user(child, &user_aarch32_view, REGSET_COMPAT_VFP, 0, VFP_STATE_SIZE, datap); break; #ifdef CONFIG_HAVE_HW_BREAKPOINT case COMPAT_PTRACE_GETHBPREGS: ret = compat_ptrace_gethbpregs(child, addr, datap); break; case COMPAT_PTRACE_SETHBPREGS: ret = compat_ptrace_sethbpregs(child, addr, datap); break; #endif default: ret = compat_ptrace_request(child, request, addr, data); break; } return ret; } #endif /* CONFIG_COMPAT */ const struct user_regset_view *task_user_regset_view(struct task_struct *task) { /* * Core dumping of 32-bit tasks or compat ptrace requests must use the * user_aarch32_view compatible with arm32. Native ptrace requests on * 32-bit children use an extended user_aarch32_ptrace_view to allow * access to the TLS register. */ if (is_compat_task()) return &user_aarch32_view; else if (is_compat_thread(task_thread_info(task))) return &user_aarch32_ptrace_view; return &user_aarch64_view; } long arch_ptrace(struct task_struct *child, long request, unsigned long addr, unsigned long data) { switch (request) { case PTRACE_PEEKMTETAGS: case PTRACE_POKEMTETAGS: return mte_ptrace_copy_tags(child, request, addr, data); } return ptrace_request(child, request, addr, data); } enum ptrace_syscall_dir { PTRACE_SYSCALL_ENTER = 0, PTRACE_SYSCALL_EXIT, }; static void report_syscall(struct pt_regs *regs, enum ptrace_syscall_dir dir) { int regno; unsigned long saved_reg; /* * We have some ABI weirdness here in the way that we handle syscall * exit stops because we indicate whether or not the stop has been * signalled from syscall entry or syscall exit by clobbering a general * purpose register (ip/r12 for AArch32, x7 for AArch64) in the tracee * and restoring its old value after the stop. This means that: * * - Any writes by the tracer to this register during the stop are * ignored/discarded. * * - The actual value of the register is not available during the stop, * so the tracer cannot save it and restore it later. * * - Syscall stops behave differently to seccomp and pseudo-step traps * (the latter do not nobble any registers). */ regno = (is_compat_task() ? 12 : 7); saved_reg = regs->regs[regno]; regs->regs[regno] = dir; if (dir == PTRACE_SYSCALL_ENTER) { if (ptrace_report_syscall_entry(regs)) forget_syscall(regs); regs->regs[regno] = saved_reg; } else if (!test_thread_flag(TIF_SINGLESTEP)) { ptrace_report_syscall_exit(regs, 0); regs->regs[regno] = saved_reg; } else { regs->regs[regno] = saved_reg; /* * Signal a pseudo-step exception since we are stepping but * tracer modifications to the registers may have rewound the * state machine. */ ptrace_report_syscall_exit(regs, 1); } } int syscall_trace_enter(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); if (flags & (_TIF_SYSCALL_EMU | _TIF_SYSCALL_TRACE)) { report_syscall(regs, PTRACE_SYSCALL_ENTER); if (flags & _TIF_SYSCALL_EMU) return NO_SYSCALL; } /* Do the secure computing after ptrace; failures should be fast. */ if (secure_computing() == -1) return NO_SYSCALL; if (test_thread_flag(TIF_SYSCALL_TRACEPOINT)) trace_sys_enter(regs, regs->syscallno); audit_syscall_entry(regs->syscallno, regs->orig_x0, regs->regs[1], regs->regs[2], regs->regs[3]); return regs->syscallno; } void syscall_trace_exit(struct pt_regs *regs) { unsigned long flags = read_thread_flags(); audit_syscall_exit(regs); if (flags & _TIF_SYSCALL_TRACEPOINT) trace_sys_exit(regs, syscall_get_return_value(current, regs)); if (flags & (_TIF_SYSCALL_TRACE | _TIF_SINGLESTEP)) report_syscall(regs, PTRACE_SYSCALL_EXIT); rseq_syscall(regs); } /* * SPSR_ELx bits which are always architecturally RES0 per ARM DDI 0487D.a. * We permit userspace to set SSBS (AArch64 bit 12, AArch32 bit 23) which is * not described in ARM DDI 0487D.a. * We treat PAN and UAO as RES0 bits, as they are meaningless at EL0, and may * be allocated an EL0 meaning in future. * Userspace cannot use these until they have an architectural meaning. * Note that this follows the SPSR_ELx format, not the AArch32 PSR format. * We also reserve IL for the kernel; SS is handled dynamically. */ #define SPSR_EL1_AARCH64_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(27, 26) | GENMASK_ULL(23, 22) | \ GENMASK_ULL(20, 13) | GENMASK_ULL(5, 5)) #define SPSR_EL1_AARCH32_RES0_BITS \ (GENMASK_ULL(63, 32) | GENMASK_ULL(22, 22) | GENMASK_ULL(20, 20)) static int valid_compat_regs(struct user_pt_regs *regs) { regs->pstate &= ~SPSR_EL1_AARCH32_RES0_BITS; if (!system_supports_mixed_endian_el0()) { if (IS_ENABLED(CONFIG_CPU_BIG_ENDIAN)) regs->pstate |= PSR_AA32_E_BIT; else regs->pstate &= ~PSR_AA32_E_BIT; } if (user_mode(regs) && (regs->pstate & PSR_MODE32_BIT) && (regs->pstate & PSR_AA32_A_BIT) == 0 && (regs->pstate & PSR_AA32_I_BIT) == 0 && (regs->pstate & PSR_AA32_F_BIT) == 0) { return 1; } /* * Force PSR to a valid 32-bit EL0t, preserving the same bits as * arch/arm. */ regs->pstate &= PSR_AA32_N_BIT | PSR_AA32_Z_BIT | PSR_AA32_C_BIT | PSR_AA32_V_BIT | PSR_AA32_Q_BIT | PSR_AA32_IT_MASK | PSR_AA32_GE_MASK | PSR_AA32_E_BIT | PSR_AA32_T_BIT; regs->pstate |= PSR_MODE32_BIT; return 0; } static int valid_native_regs(struct user_pt_regs *regs) { regs->pstate &= ~SPSR_EL1_AARCH64_RES0_BITS; if (user_mode(regs) && !(regs->pstate & PSR_MODE32_BIT) && (regs->pstate & PSR_D_BIT) == 0 && (regs->pstate & PSR_A_BIT) == 0 && (regs->pstate & PSR_I_BIT) == 0 && (regs->pstate & PSR_F_BIT) == 0) { return 1; } /* Force PSR to a valid 64-bit EL0t */ regs->pstate &= PSR_N_BIT | PSR_Z_BIT | PSR_C_BIT | PSR_V_BIT; return 0; } /* * Are the current registers suitable for user mode? (used to maintain * security in signal handlers) */ int valid_user_regs(struct user_pt_regs *regs, struct task_struct *task) { /* https://lore.kernel.org/lkml/20191118131525.GA4180@willie-the-truck */ user_regs_reset_single_step(regs, task); if (is_compat_thread(task_thread_info(task))) return valid_compat_regs(regs); else return valid_native_regs(regs); } |
| 61 60 2 2 61 61 61 61 61 61 61 61 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 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Implementation of the access vector table type. * * Author : Stephen Smalley, <stephen.smalley.work@gmail.com> */ /* Updated: Frank Mayer <mayerf@tresys.com> and * Karl MacMillan <kmacmillan@tresys.com> * Added conditional policy language extensions * Copyright (C) 2003 Tresys Technology, LLC * * Updated: Yuichi Nakamura <ynakam@hitachisoft.jp> * Tuned number of hash slots for avtab to reduce memory usage */ #include <linux/bitops.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/errno.h> #include "avtab.h" #include "policydb.h" static struct kmem_cache *avtab_node_cachep __ro_after_init; static struct kmem_cache *avtab_xperms_cachep __ro_after_init; /* Based on MurmurHash3, written by Austin Appleby and placed in the * public domain. */ static inline u32 avtab_hash(const struct avtab_key *keyp, u32 mask) { static const u32 c1 = 0xcc9e2d51; static const u32 c2 = 0x1b873593; static const u32 r1 = 15; static const u32 r2 = 13; static const u32 m = 5; static const u32 n = 0xe6546b64; u32 hash = 0; #define mix(input) \ do { \ u32 v = input; \ v *= c1; \ v = (v << r1) | (v >> (32 - r1)); \ v *= c2; \ hash ^= v; \ hash = (hash << r2) | (hash >> (32 - r2)); \ hash = hash * m + n; \ } while (0) mix(keyp->target_class); mix(keyp->target_type); mix(keyp->source_type); #undef mix hash ^= hash >> 16; hash *= 0x85ebca6b; hash ^= hash >> 13; hash *= 0xc2b2ae35; hash ^= hash >> 16; return hash & mask; } static struct avtab_node *avtab_insert_node(struct avtab *h, struct avtab_node **dst, const struct avtab_key *key, const struct avtab_datum *datum) { struct avtab_node *newnode; struct avtab_extended_perms *xperms; newnode = kmem_cache_zalloc(avtab_node_cachep, GFP_KERNEL); if (newnode == NULL) return NULL; newnode->key = *key; if (key->specified & AVTAB_XPERMS) { xperms = kmem_cache_zalloc(avtab_xperms_cachep, GFP_KERNEL); if (xperms == NULL) { kmem_cache_free(avtab_node_cachep, newnode); return NULL; } *xperms = *(datum->u.xperms); newnode->datum.u.xperms = xperms; } else { newnode->datum.u.data = datum->u.data; } newnode->next = *dst; *dst = newnode; h->nel++; return newnode; } static int avtab_node_cmp(const struct avtab_key *key1, const struct avtab_key *key2) { u16 specified = key1->specified & ~(AVTAB_ENABLED | AVTAB_ENABLED_OLD); if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class == key2->target_class && (specified & key2->specified)) return 0; if (key1->source_type < key2->source_type) return -1; if (key1->source_type == key2->source_type && key1->target_type < key2->target_type) return -1; if (key1->source_type == key2->source_type && key1->target_type == key2->target_type && key1->target_class < key2->target_class) return -1; return 1; } static int avtab_insert(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur, *newnode; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return -EINVAL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); /* extended perms may not be unique */ if (cmp == 0 && !(key->specified & AVTAB_XPERMS)) return -EEXIST; if (cmp <= 0) break; } newnode = avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); if (!newnode) return -ENOMEM; return 0; } /* Unlike avtab_insert(), this function allow multiple insertions of the same * key/specified mask into the table, as needed by the conditional avtab. * It also returns a pointer to the node inserted. */ struct avtab_node *avtab_insert_nonunique(struct avtab *h, const struct avtab_key *key, const struct avtab_datum *datum) { u32 hvalue; struct avtab_node *prev, *cur; int cmp; if (!h || !h->nslot || h->nel == U32_MAX) return NULL; hvalue = avtab_hash(key, h->mask); for (prev = NULL, cur = h->htable[hvalue]; cur; prev = cur, cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp <= 0) break; } return avtab_insert_node(h, prev ? &prev->next : &h->htable[hvalue], key, datum); } /* This search function returns a node pointer, and can be used in * conjunction with avtab_search_next_node() */ struct avtab_node *avtab_search_node(struct avtab *h, const struct avtab_key *key) { u32 hvalue; struct avtab_node *cur; int cmp; if (!h || !h->nslot) return NULL; hvalue = avtab_hash(key, h->mask); for (cur = h->htable[hvalue]; cur; cur = cur->next) { cmp = avtab_node_cmp(key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } struct avtab_node *avtab_search_node_next(struct avtab_node *node, u16 specified) { struct avtab_key tmp_key; struct avtab_node *cur; int cmp; if (!node) return NULL; tmp_key = node->key; tmp_key.specified = specified; for (cur = node->next; cur; cur = cur->next) { cmp = avtab_node_cmp(&tmp_key, &cur->key); if (cmp == 0) return cur; if (cmp < 0) break; } return NULL; } void avtab_destroy(struct avtab *h) { u32 i; struct avtab_node *cur, *temp; if (!h) return; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; while (cur) { temp = cur; cur = cur->next; if (temp->key.specified & AVTAB_XPERMS) kmem_cache_free(avtab_xperms_cachep, temp->datum.u.xperms); kmem_cache_free(avtab_node_cachep, temp); } } kvfree(h->htable); h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } void avtab_init(struct avtab *h) { h->htable = NULL; h->nel = 0; h->nslot = 0; h->mask = 0; } static int avtab_alloc_common(struct avtab *h, u32 nslot) { if (!nslot) return 0; h->htable = kvcalloc(nslot, sizeof(void *), GFP_KERNEL); if (!h->htable) return -ENOMEM; h->nslot = nslot; h->mask = nslot - 1; return 0; } int avtab_alloc(struct avtab *h, u32 nrules) { int rc; u32 nslot = 0; if (nrules != 0) { nslot = nrules > 3 ? rounddown_pow_of_two(nrules / 2) : 2; if (nslot > MAX_AVTAB_HASH_BUCKETS) nslot = MAX_AVTAB_HASH_BUCKETS; rc = avtab_alloc_common(h, nslot); if (rc) return rc; } pr_debug("SELinux: %d avtab hash slots, %d rules.\n", nslot, nrules); return 0; } int avtab_alloc_dup(struct avtab *new, const struct avtab *orig) { return avtab_alloc_common(new, orig->nslot); } #ifdef CONFIG_SECURITY_SELINUX_DEBUG void avtab_hash_eval(struct avtab *h, const char *tag) { u32 i, chain_len, slots_used, max_chain_len; unsigned long long chain2_len_sum; struct avtab_node *cur; slots_used = 0; max_chain_len = 0; chain2_len_sum = 0; for (i = 0; i < h->nslot; i++) { cur = h->htable[i]; if (cur) { slots_used++; chain_len = 0; while (cur) { chain_len++; cur = cur->next; } if (chain_len > max_chain_len) max_chain_len = chain_len; chain2_len_sum += (unsigned long long)chain_len * chain_len; } } pr_debug("SELinux: %s: %d entries and %d/%d buckets used, " "longest chain length %d, sum of chain length^2 %llu\n", tag, h->nel, slots_used, h->nslot, max_chain_len, chain2_len_sum); } #endif /* CONFIG_SECURITY_SELINUX_DEBUG */ /* clang-format off */ static const uint16_t spec_order[] = { AVTAB_ALLOWED, AVTAB_AUDITDENY, AVTAB_AUDITALLOW, AVTAB_TRANSITION, AVTAB_CHANGE, AVTAB_MEMBER, AVTAB_XPERMS_ALLOWED, AVTAB_XPERMS_AUDITALLOW, AVTAB_XPERMS_DONTAUDIT }; /* clang-format on */ int avtab_read_item(struct avtab *a, void *fp, struct policydb *pol, int (*insertf)(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p), void *p) { __le16 buf16[4]; u16 enabled; u32 items, items2, val, i; struct avtab_key key; struct avtab_datum datum; struct avtab_extended_perms xperms; __le32 buf32[ARRAY_SIZE(xperms.perms.p)]; int rc; unsigned int set, vers = pol->policyvers; memset(&key, 0, sizeof(struct avtab_key)); memset(&datum, 0, sizeof(struct avtab_datum)); if (vers < POLICYDB_VERSION_AVTAB) { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items2 = le32_to_cpu(buf32[0]); if (items2 > ARRAY_SIZE(buf32)) { pr_err("SELinux: avtab: entry overflow\n"); return -EINVAL; } rc = next_entry(buf32, fp, sizeof(u32) * items2); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; val = le32_to_cpu(buf32[items++]); key.source_type = (u16)val; if (key.source_type != val) { pr_err("SELinux: avtab: truncated source type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_type = (u16)val; if (key.target_type != val) { pr_err("SELinux: avtab: truncated target type\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); key.target_class = (u16)val; if (key.target_class != val) { pr_err("SELinux: avtab: truncated target class\n"); return -EINVAL; } val = le32_to_cpu(buf32[items++]); enabled = (val & AVTAB_ENABLED_OLD) ? AVTAB_ENABLED : 0; if (!(val & (AVTAB_AV | AVTAB_TYPE))) { pr_err("SELinux: avtab: null entry\n"); return -EINVAL; } if ((val & AVTAB_AV) && (val & AVTAB_TYPE)) { pr_err("SELinux: avtab: entry has both access vectors and types\n"); return -EINVAL; } if (val & AVTAB_XPERMS) { pr_err("SELinux: avtab: entry has extended permissions\n"); return -EINVAL; } for (i = 0; i < ARRAY_SIZE(spec_order); i++) { if (val & spec_order[i]) { key.specified = spec_order[i] | enabled; datum.u.data = le32_to_cpu(buf32[items++]); rc = insertf(a, &key, &datum, p); if (rc) return rc; } } if (items != items2) { pr_err("SELinux: avtab: entry only had %d items, expected %d\n", items2, items); return -EINVAL; } return 0; } rc = next_entry(buf16, fp, sizeof(u16) * 4); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } items = 0; key.source_type = le16_to_cpu(buf16[items++]); key.target_type = le16_to_cpu(buf16[items++]); key.target_class = le16_to_cpu(buf16[items++]); key.specified = le16_to_cpu(buf16[items++]); if (!policydb_type_isvalid(pol, key.source_type) || !policydb_type_isvalid(pol, key.target_type) || !policydb_class_isvalid(pol, key.target_class)) { pr_err("SELinux: avtab: invalid type or class\n"); return -EINVAL; } set = hweight16(key.specified & (AVTAB_XPERMS | AVTAB_TYPE | AVTAB_AV)); if (!set || set > 1) { pr_err("SELinux: avtab: more than one specifier\n"); return -EINVAL; } if ((vers < POLICYDB_VERSION_XPERMS_IOCTL) && (key.specified & AVTAB_XPERMS)) { pr_err("SELinux: avtab: policy version %u does not " "support extended permissions rules and one " "was specified\n", vers); return -EINVAL; } else if (key.specified & AVTAB_XPERMS) { memset(&xperms, 0, sizeof(struct avtab_extended_perms)); rc = next_entry(&xperms.specified, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(&xperms.driver, fp, sizeof(u8)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } rc = next_entry(buf32, fp, sizeof(u32) * ARRAY_SIZE(xperms.perms.p)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } for (i = 0; i < ARRAY_SIZE(xperms.perms.p); i++) xperms.perms.p[i] = le32_to_cpu(buf32[i]); datum.u.xperms = &xperms; } else { rc = next_entry(buf32, fp, sizeof(u32)); if (rc) { pr_err("SELinux: avtab: truncated entry\n"); return rc; } datum.u.data = le32_to_cpu(*buf32); } if ((key.specified & AVTAB_TYPE) && !policydb_type_isvalid(pol, datum.u.data)) { pr_err("SELinux: avtab: invalid type\n"); return -EINVAL; } return insertf(a, &key, &datum, p); } static int avtab_insertf(struct avtab *a, const struct avtab_key *k, const struct avtab_datum *d, void *p) { return avtab_insert(a, k, d); } int avtab_read(struct avtab *a, void *fp, struct policydb *pol) { int rc; __le32 buf[1]; u32 nel, i; rc = next_entry(buf, fp, sizeof(u32)); if (rc < 0) { pr_err("SELinux: avtab: truncated table\n"); goto bad; } nel = le32_to_cpu(buf[0]); if (!nel) { pr_err("SELinux: avtab: table is empty\n"); rc = -EINVAL; goto bad; } rc = avtab_alloc(a, nel); if (rc) goto bad; for (i = 0; i < nel; i++) { rc = avtab_read_item(a, fp, pol, avtab_insertf, NULL); if (rc) { if (rc == -ENOMEM) pr_err("SELinux: avtab: out of memory\n"); else if (rc == -EEXIST) pr_err("SELinux: avtab: duplicate entry\n"); goto bad; } } rc = 0; out: return rc; bad: avtab_destroy(a); goto out; } int avtab_write_item(struct policydb *p, const struct avtab_node *cur, void *fp) { __le16 buf16[4]; __le32 buf32[ARRAY_SIZE(cur->datum.u.xperms->perms.p)]; int rc; unsigned int i; buf16[0] = cpu_to_le16(cur->key.source_type); buf16[1] = cpu_to_le16(cur->key.target_type); buf16[2] = cpu_to_le16(cur->key.target_class); buf16[3] = cpu_to_le16(cur->key.specified); rc = put_entry(buf16, sizeof(u16), 4, fp); if (rc) return rc; if (cur->key.specified & AVTAB_XPERMS) { rc = put_entry(&cur->datum.u.xperms->specified, sizeof(u8), 1, fp); if (rc) return rc; rc = put_entry(&cur->datum.u.xperms->driver, sizeof(u8), 1, fp); if (rc) return rc; for (i = 0; i < ARRAY_SIZE(cur->datum.u.xperms->perms.p); i++) buf32[i] = cpu_to_le32(cur->datum.u.xperms->perms.p[i]); rc = put_entry(buf32, sizeof(u32), ARRAY_SIZE(cur->datum.u.xperms->perms.p), fp); } else { buf32[0] = cpu_to_le32(cur->datum.u.data); rc = put_entry(buf32, sizeof(u32), 1, fp); } if (rc) return rc; return 0; } int avtab_write(struct policydb *p, struct avtab *a, void *fp) { u32 i; int rc = 0; struct avtab_node *cur; __le32 buf[1]; buf[0] = cpu_to_le32(a->nel); rc = put_entry(buf, sizeof(u32), 1, fp); if (rc) return rc; for (i = 0; i < a->nslot; i++) { for (cur = a->htable[i]; cur; cur = cur->next) { rc = avtab_write_item(p, cur, fp); if (rc) return rc; } } return rc; } void __init avtab_cache_init(void) { avtab_node_cachep = kmem_cache_create( "avtab_node", sizeof(struct avtab_node), 0, SLAB_PANIC, NULL); avtab_xperms_cachep = kmem_cache_create( "avtab_extended_perms", sizeof(struct avtab_extended_perms), 0, SLAB_PANIC, NULL); } |
| 3 3 3 1 2 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * VGIC MMIO handling functions */ #include <linux/bitops.h> #include <linux/bsearch.h> #include <linux/interrupt.h> #include <linux/irq.h> #include <linux/kvm.h> #include <linux/kvm_host.h> #include <kvm/iodev.h> #include <kvm/arm_arch_timer.h> #include <kvm/arm_vgic.h> #include "vgic.h" #include "vgic-mmio.h" unsigned long vgic_mmio_read_raz(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return 0; } unsigned long vgic_mmio_read_rao(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return -1UL; } void vgic_mmio_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ } int vgic_mmio_uaccess_write_wi(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { /* Ignore */ return 0; } unsigned long vgic_mmio_read_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); if (irq->group) value |= BIT(i); vgic_put_irq(vcpu->kvm, irq); } return value; } static void vgic_update_vsgi(struct vgic_irq *irq) { WARN_ON(its_prop_update_vsgi(irq->host_irq, irq->priority, irq->group)); } void vgic_mmio_write_group(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->group = !!(val & BIT(i)); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } else { vgic_queue_irq_unlock(vcpu->kvm, irq, flags); } vgic_put_irq(vcpu->kvm, irq); } } /* * Read accesses to both GICD_ICENABLER and GICD_ISENABLER return the value * of the enabled bit, so there is only one function for both here. */ unsigned long vgic_mmio_read_enable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); if (irq->enabled) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return value; } void vgic_mmio_write_senable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { if (!irq->enabled) { struct irq_data *data; irq->enabled = true; data = &irq_to_desc(irq->host_irq)->irq_data; while (irqd_irq_disabled(data)) enable_irq(irq->host_irq); } raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } else if (vgic_irq_is_mapped_level(irq)) { bool was_high = irq->line_level; /* * We need to update the state of the interrupt because * the guest might have changed the state of the device * while the interrupt was disabled at the VGIC level. */ irq->line_level = vgic_get_phys_line_level(irq); /* * Deactivate the physical interrupt so the GIC will let * us know when it is asserted again. */ if (!irq->active && was_high && !irq->line_level) vgic_irq_set_phys_active(irq, false); } irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid) && irq->enabled) disable_irq_nosync(irq->host_irq); irq->enabled = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } int vgic_uaccess_write_senable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = true; vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } return 0; } int vgic_uaccess_write_cenable(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->enabled = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } return 0; } static unsigned long __read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); unsigned long flags; bool val; /* * When used from userspace with a GICv3 model: * * Pending state of interrupt is latched in pending_latch * variable. Userspace will save and restore pending state * and line_level separately. * Refer to Documentation/virt/kvm/devices/arm-vgic-v3.rst * for handling of ISPENDR and ICPENDR. */ raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { int err; val = false; err = irq_get_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, &val); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); } else if (!is_user && vgic_irq_is_mapped_level(irq)) { val = vgic_get_phys_line_level(irq); } else { switch (vcpu->kvm->arch.vgic.vgic_model) { case KVM_DEV_TYPE_ARM_VGIC_V3: if (is_user) { val = irq->pending_latch; break; } fallthrough; default: val = irq_is_pending(irq); break; } } value |= ((u32)val << i); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } return value; } unsigned long vgic_mmio_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __read_pending(vcpu, addr, len, false); } unsigned long vgic_uaccess_read_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __read_pending(vcpu, addr, len, true); } static bool is_vgic_v2_sgi(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { return (vgic_irq_is_sgi(irq->intid) && vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V2); } static void __set_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); /* GICD_ISPENDR0 SGI bits are WI when written from the guest. */ if (is_vgic_v2_sgi(vcpu, irq) && !is_user) { vgic_put_irq(vcpu->kvm, irq); continue; } raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * GICv2 SGIs are terribly broken. We can't restore * the source of the interrupt, so just pick the vcpu * itself as the source... */ if (is_vgic_v2_sgi(vcpu, irq)) irq->source |= BIT(vcpu->vcpu_id); if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* HW SGI? Ask the GIC to inject it */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, true); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } irq->pending_latch = true; if (irq->hw && !is_user) vgic_irq_set_phys_active(irq, true); vgic_queue_irq_unlock(vcpu->kvm, irq, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __set_pending(vcpu, addr, len, val, false); } int vgic_uaccess_write_spending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __set_pending(vcpu, addr, len, val, true); return 0; } /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_cpending(struct kvm_vcpu *vcpu, struct vgic_irq *irq) { irq->pending_latch = false; /* * We don't want the guest to effectively mask the physical * interrupt by doing a write to SPENDR followed by a write to * CPENDR for HW interrupts, so we clear the active state on * the physical side if the virtual interrupt is not active. * This may lead to taking an additional interrupt on the * host, but that should not be a problem as the worst that * can happen is an additional vgic injection. We also clear * the pending state to maintain proper semantics for edge HW * interrupts. */ vgic_irq_set_phys_pending(irq, false); if (!irq->active) vgic_irq_set_phys_active(irq, false); } static void __clear_pending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val, bool is_user) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; unsigned long flags; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); /* GICD_ICPENDR0 SGI bits are WI when written from the guest. */ if (is_vgic_v2_sgi(vcpu, irq) && !is_user) { vgic_put_irq(vcpu->kvm, irq); continue; } raw_spin_lock_irqsave(&irq->irq_lock, flags); /* * More fun with GICv2 SGIs! If we're clearing one of them * from userspace, which source vcpu to clear? Let's not * even think of it, and blow the whole set. */ if (is_vgic_v2_sgi(vcpu, irq)) irq->source = 0; if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* HW SGI? Ask the GIC to clear its pending bit */ int err; err = irq_set_irqchip_state(irq->host_irq, IRQCHIP_STATE_PENDING, false); WARN_RATELIMIT(err, "IRQ %d", irq->host_irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); continue; } if (irq->hw && !is_user) vgic_hw_irq_cpending(vcpu, irq); else irq->pending_latch = false; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __clear_pending(vcpu, addr, len, val, false); } int vgic_uaccess_write_cpending(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __clear_pending(vcpu, addr, len, val, true); return 0; } /* * If we are fiddling with an IRQ's active state, we have to make sure the IRQ * is not queued on some running VCPU's LRs, because then the change to the * active state can be overwritten when the VCPU's state is synced coming back * from the guest. * * For shared interrupts as well as GICv3 private interrupts accessed from the * non-owning CPU, we have to stop all the VCPUs because interrupts can be * migrated while we don't hold the IRQ locks and we don't want to be chasing * moving targets. * * For GICv2 private interrupts we don't have to do anything because * userspace accesses to the VGIC state already require all VCPUs to be * stopped, and only the VCPU itself can modify its private interrupts * active state, which guarantees that the VCPU is not running. */ static void vgic_access_active_prepare(struct kvm_vcpu *vcpu, u32 intid) { if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_halt_guest(vcpu->kvm); } /* See vgic_access_active_prepare */ static void vgic_access_active_finish(struct kvm_vcpu *vcpu, u32 intid) { if ((vcpu->kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3 && vcpu != kvm_get_running_vcpu()) || intid >= VGIC_NR_PRIVATE_IRQS) kvm_arm_resume_guest(vcpu->kvm); } static unsigned long __vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 value = 0; int i; /* Loop over all IRQs affected by this read */ for (i = 0; i < len * 8; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); /* * Even for HW interrupts, don't evaluate the HW state as * all the guest is interested in is the virtual state. */ if (irq->active) value |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return value; } unsigned long vgic_mmio_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); u32 val; mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); val = __vgic_mmio_read_active(vcpu, addr, len); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); return val; } unsigned long vgic_uaccess_read_active(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { return __vgic_mmio_read_active(vcpu, addr, len); } /* Must be called with irq->irq_lock held */ static void vgic_hw_irq_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active, bool is_uaccess) { if (is_uaccess) return; irq->active = active; vgic_irq_set_phys_active(irq, active); } static void vgic_mmio_change_active(struct kvm_vcpu *vcpu, struct vgic_irq *irq, bool active) { unsigned long flags; struct kvm_vcpu *requester_vcpu = kvm_get_running_vcpu(); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (irq->hw && !vgic_irq_is_sgi(irq->intid)) { vgic_hw_irq_change_active(vcpu, irq, active, !requester_vcpu); } else if (irq->hw && vgic_irq_is_sgi(irq->intid)) { /* * GICv4.1 VSGI feature doesn't track an active state, * so let's not kid ourselves, there is nothing we can * do here. */ irq->active = false; } else { u32 model = vcpu->kvm->arch.vgic.vgic_model; u8 active_source; irq->active = active; /* * The GICv2 architecture indicates that the source CPUID for * an SGI should be provided during an EOI which implies that * the active state is stored somewhere, but at the same time * this state is not architecturally exposed anywhere and we * have no way of knowing the right source. * * This may lead to a VCPU not being able to receive * additional instances of a particular SGI after migration * for a GICv2 VM on some GIC implementations. Oh well. */ active_source = (requester_vcpu) ? requester_vcpu->vcpu_id : 0; if (model == KVM_DEV_TYPE_ARM_VGIC_V2 && active && vgic_irq_is_sgi(irq->intid)) irq->active_source = active_source; } if (irq->active) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else raw_spin_unlock_irqrestore(&irq->irq_lock, flags); } static void __vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); vgic_mmio_change_active(vcpu, irq, false); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_cactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_cactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __vgic_mmio_write_cactive(vcpu, addr, len, val); return 0; } static void __vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); int i; for_each_set_bit(i, &val, len * 8) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); vgic_mmio_change_active(vcpu, irq, true); vgic_put_irq(vcpu->kvm, irq); } } void vgic_mmio_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 1); mutex_lock(&vcpu->kvm->arch.config_lock); vgic_access_active_prepare(vcpu, intid); __vgic_mmio_write_sactive(vcpu, addr, len, val); vgic_access_active_finish(vcpu, intid); mutex_unlock(&vcpu->kvm->arch.config_lock); } int vgic_mmio_uaccess_write_sactive(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { __vgic_mmio_write_sactive(vcpu, addr, len, val); return 0; } unsigned long vgic_mmio_read_priority(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 8); int i; u64 val = 0; for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); val |= (u64)irq->priority << (i * 8); vgic_put_irq(vcpu->kvm, irq); } return val; } /* * We currently don't handle changing the priority of an interrupt that * is already pending on a VCPU. If there is a need for this, we would * need to make this VCPU exit and re-evaluate the priorities, potentially * leading to this interrupt getting presented now to the guest (if it has * been masked by the priority mask before). */ void vgic_mmio_write_priority(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 8); int i; unsigned long flags; for (i = 0; i < len; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); /* Narrow the priority range to what we actually support */ irq->priority = (val >> (i * 8)) & GENMASK(7, 8 - VGIC_PRI_BITS); if (irq->hw && vgic_irq_is_sgi(irq->intid)) vgic_update_vsgi(irq); raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } unsigned long vgic_mmio_read_config(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len) { u32 intid = VGIC_ADDR_TO_INTID(addr, 2); u32 value = 0; int i; for (i = 0; i < len * 4; i++) { struct vgic_irq *irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); if (irq->config == VGIC_CONFIG_EDGE) value |= (2U << (i * 2)); vgic_put_irq(vcpu->kvm, irq); } return value; } void vgic_mmio_write_config(struct kvm_vcpu *vcpu, gpa_t addr, unsigned int len, unsigned long val) { u32 intid = VGIC_ADDR_TO_INTID(addr, 2); int i; unsigned long flags; for (i = 0; i < len * 4; i++) { struct vgic_irq *irq; /* * The configuration cannot be changed for SGIs in general, * for PPIs this is IMPLEMENTATION DEFINED. The arch timer * code relies on PPIs being level triggered, so we also * make them read-only here. */ if (intid + i < VGIC_NR_PRIVATE_IRQS) continue; irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); raw_spin_lock_irqsave(&irq->irq_lock, flags); if (test_bit(i * 2 + 1, &val)) irq->config = VGIC_CONFIG_EDGE; else irq->config = VGIC_CONFIG_LEVEL; raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } u32 vgic_read_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid) { int i; u32 val = 0; int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; for (i = 0; i < 32; i++) { struct vgic_irq *irq; if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) continue; irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); if (irq->config == VGIC_CONFIG_LEVEL && irq->line_level) val |= (1U << i); vgic_put_irq(vcpu->kvm, irq); } return val; } void vgic_write_irq_line_level_info(struct kvm_vcpu *vcpu, u32 intid, const u32 val) { int i; int nr_irqs = vcpu->kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; unsigned long flags; for (i = 0; i < 32; i++) { struct vgic_irq *irq; bool new_level; if ((intid + i) < VGIC_NR_SGIS || (intid + i) >= nr_irqs) continue; irq = vgic_get_irq(vcpu->kvm, vcpu, intid + i); /* * Line level is set irrespective of irq type * (level or edge) to avoid dependency that VM should * restore irq config before line level. */ new_level = !!(val & (1U << i)); raw_spin_lock_irqsave(&irq->irq_lock, flags); irq->line_level = new_level; if (new_level) vgic_queue_irq_unlock(vcpu->kvm, irq, flags); else raw_spin_unlock_irqrestore(&irq->irq_lock, flags); vgic_put_irq(vcpu->kvm, irq); } } static int match_region(const void *key, const void *elt) { const unsigned int offset = (unsigned long)key; const struct vgic_register_region *region = elt; if (offset < region->reg_offset) return -1; if (offset >= region->reg_offset + region->len) return 1; return 0; } const struct vgic_register_region * vgic_find_mmio_region(const struct vgic_register_region *regions, int nr_regions, unsigned int offset) { return bsearch((void *)(uintptr_t)offset, regions, nr_regions, sizeof(regions[0]), match_region); } void vgic_set_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_set_vmcr(vcpu, vmcr); else vgic_v3_set_vmcr(vcpu, vmcr); } void vgic_get_vmcr(struct kvm_vcpu *vcpu, struct vgic_vmcr *vmcr) { if (kvm_vgic_global_state.type == VGIC_V2) vgic_v2_get_vmcr(vcpu, vmcr); else vgic_v3_get_vmcr(vcpu, vmcr); } /* * kvm_mmio_read_buf() returns a value in a format where it can be converted * to a byte array and be directly observed as the guest wanted it to appear * in memory if it had done the store itself, which is LE for the GIC, as the * guest knows the GIC is always LE. * * We convert this value to the CPUs native format to deal with it as a data * value. */ unsigned long vgic_data_mmio_bus_to_host(const void *val, unsigned int len) { unsigned long data = kvm_mmio_read_buf(val, len); switch (len) { case 1: return data; case 2: return le16_to_cpu(data); case 4: return le32_to_cpu(data); default: return le64_to_cpu(data); } } /* * kvm_mmio_write_buf() expects a value in a format such that if converted to * a byte array it is observed as the guest would see it if it could perform * the load directly. Since the GIC is LE, and the guest knows this, the * guest expects a value in little endian format. * * We convert the data value from the CPUs native format to LE so that the * value is returned in the proper format. */ void vgic_data_host_to_mmio_bus(void *buf, unsigned int len, unsigned long data) { switch (len) { case 1: break; case 2: data = cpu_to_le16(data); break; case 4: data = cpu_to_le32(data); break; default: data = cpu_to_le64(data); } kvm_mmio_write_buf(buf, len, data); } static struct vgic_io_device *kvm_to_vgic_iodev(const struct kvm_io_device *dev) { return container_of(dev, struct vgic_io_device, dev); } static bool check_region(const struct kvm *kvm, const struct vgic_register_region *region, gpa_t addr, int len) { int flags, nr_irqs = kvm->arch.vgic.nr_spis + VGIC_NR_PRIVATE_IRQS; switch (len) { case sizeof(u8): flags = VGIC_ACCESS_8bit; break; case sizeof(u32): flags = VGIC_ACCESS_32bit; break; case sizeof(u64): flags = VGIC_ACCESS_64bit; break; default: return false; } if ((region->access_flags & flags) && IS_ALIGNED(addr, len)) { if (!region->bits_per_irq) return true; /* Do we access a non-allocated IRQ? */ return VGIC_ADDR_TO_INTID(addr, region->bits_per_irq) < nr_irqs; } return false; } const struct vgic_register_region * vgic_get_mmio_region(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, int len) { const struct vgic_register_region *region; region = vgic_find_mmio_region(iodev->regions, iodev->nr_regions, addr - iodev->base_addr); if (!region || !check_region(vcpu->kvm, region, addr, len)) return NULL; return region; } static int vgic_uaccess_read(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, u32 *val) { const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); if (!region) { *val = 0; return 0; } r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; if (region->uaccess_read) *val = region->uaccess_read(r_vcpu, addr, sizeof(u32)); else *val = region->read(r_vcpu, addr, sizeof(u32)); return 0; } static int vgic_uaccess_write(struct kvm_vcpu *vcpu, struct vgic_io_device *iodev, gpa_t addr, const u32 *val) { const struct vgic_register_region *region; struct kvm_vcpu *r_vcpu; region = vgic_get_mmio_region(vcpu, iodev, addr, sizeof(u32)); if (!region) return 0; r_vcpu = iodev->redist_vcpu ? iodev->redist_vcpu : vcpu; if (region->uaccess_write) return region->uaccess_write(r_vcpu, addr, sizeof(u32), *val); region->write(r_vcpu, addr, sizeof(u32), *val); return 0; } /* * Userland access to VGIC registers. */ int vgic_uaccess(struct kvm_vcpu *vcpu, struct vgic_io_device *dev, bool is_write, int offset, u32 *val) { if (is_write) return vgic_uaccess_write(vcpu, dev, offset, val); else return vgic_uaccess_read(vcpu, dev, offset, val); } static int dispatch_mmio_read(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, void *val) { struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; unsigned long data = 0; region = vgic_get_mmio_region(vcpu, iodev, addr, len); if (!region) { memset(val, 0, len); return 0; } switch (iodev->iodev_type) { case IODEV_CPUIF: data = region->read(vcpu, addr, len); break; case IODEV_DIST: data = region->read(vcpu, addr, len); break; case IODEV_REDIST: data = region->read(iodev->redist_vcpu, addr, len); break; case IODEV_ITS: data = region->its_read(vcpu->kvm, iodev->its, addr, len); break; } vgic_data_host_to_mmio_bus(val, len, data); return 0; } static int dispatch_mmio_write(struct kvm_vcpu *vcpu, struct kvm_io_device *dev, gpa_t addr, int len, const void *val) { struct vgic_io_device *iodev = kvm_to_vgic_iodev(dev); const struct vgic_register_region *region; unsigned long data = vgic_data_mmio_bus_to_host(val, len); region = vgic_get_mmio_region(vcpu, iodev, addr, len); if (!region) return 0; switch (iodev->iodev_type) { case IODEV_CPUIF: region->write(vcpu, addr, len, data); break; case IODEV_DIST: region->write(vcpu, addr, len, data); break; case IODEV_REDIST: region->write(iodev->redist_vcpu, addr, len, data); break; case IODEV_ITS: region->its_write(vcpu->kvm, iodev->its, addr, len, data); break; } return 0; } const struct kvm_io_device_ops kvm_io_gic_ops = { .read = dispatch_mmio_read, .write = dispatch_mmio_write, }; int vgic_register_dist_iodev(struct kvm *kvm, gpa_t dist_base_address, enum vgic_type type) { struct vgic_io_device *io_device = &kvm->arch.vgic.dist_iodev; unsigned int len; switch (type) { case VGIC_V2: len = vgic_v2_init_dist_iodev(io_device); break; case VGIC_V3: len = vgic_v3_init_dist_iodev(io_device); break; default: BUG_ON(1); } io_device->base_addr = dist_base_address; io_device->iodev_type = IODEV_DIST; io_device->redist_vcpu = NULL; return kvm_io_bus_register_dev(kvm, KVM_MMIO_BUS, dist_base_address, len, &io_device->dev); } |
| 252 166 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 | /* * include/linux/topology.h * * Written by: Matthew Dobson, IBM Corporation * * Copyright (C) 2002, IBM Corp. * * All rights reserved. * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License as published by * the Free Software Foundation; either version 2 of the License, or * (at your option) any later version. * * This program is distributed in the hope that it will be useful, but * WITHOUT ANY WARRANTY; without even the implied warranty of * MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or * NON INFRINGEMENT. See the GNU General Public License for more * details. * * You should have received a copy of the GNU General Public License * along with this program; if not, write to the Free Software * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. * * Send feedback to <colpatch@us.ibm.com> */ #ifndef _LINUX_TOPOLOGY_H #define _LINUX_TOPOLOGY_H #include <linux/arch_topology.h> #include <linux/cpumask.h> #include <linux/bitops.h> #include <linux/mmzone.h> #include <linux/smp.h> #include <linux/percpu.h> #include <asm/topology.h> #ifndef nr_cpus_node #define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node)) #endif #define for_each_node_with_cpus(node) \ for_each_online_node(node) \ if (nr_cpus_node(node)) int arch_update_cpu_topology(void); /* Conform to ACPI 2.0 SLIT distance definitions */ #define LOCAL_DISTANCE 10 #define REMOTE_DISTANCE 20 #define DISTANCE_BITS 8 #ifndef node_distance #define node_distance(from,to) ((from) == (to) ? LOCAL_DISTANCE : REMOTE_DISTANCE) #endif #ifndef RECLAIM_DISTANCE /* * If the distance between nodes in a system is larger than RECLAIM_DISTANCE * (in whatever arch specific measurement units returned by node_distance()) * and node_reclaim_mode is enabled then the VM will only call node_reclaim() * on nodes within this distance. */ #define RECLAIM_DISTANCE 30 #endif /* * The following tunable allows platforms to override the default node * reclaim distance (RECLAIM_DISTANCE) if remote memory accesses are * sufficiently fast that the default value actually hurts * performance. * * AMD EPYC machines use this because even though the 2-hop distance * is 32 (3.2x slower than a local memory access) performance actually * *improves* if allowed to reclaim memory and load balance tasks * between NUMA nodes 2-hops apart. */ extern int __read_mostly node_reclaim_distance; #ifndef PENALTY_FOR_NODE_WITH_CPUS #define PENALTY_FOR_NODE_WITH_CPUS (1) #endif #ifdef CONFIG_USE_PERCPU_NUMA_NODE_ID DECLARE_PER_CPU(int, numa_node); #ifndef numa_node_id /* Returns the number of the current Node. */ static inline int numa_node_id(void) { return raw_cpu_read(numa_node); } #endif #ifndef cpu_to_node static inline int cpu_to_node(int cpu) { return per_cpu(numa_node, cpu); } #endif #ifndef set_numa_node static inline void set_numa_node(int node) { this_cpu_write(numa_node, node); } #endif #ifndef set_cpu_numa_node static inline void set_cpu_numa_node(int cpu, int node) { per_cpu(numa_node, cpu) = node; } #endif #else /* !CONFIG_USE_PERCPU_NUMA_NODE_ID */ /* Returns the number of the current Node. */ #ifndef numa_node_id static inline int numa_node_id(void) { return cpu_to_node(raw_smp_processor_id()); } #endif #endif /* [!]CONFIG_USE_PERCPU_NUMA_NODE_ID */ #ifdef CONFIG_HAVE_MEMORYLESS_NODES /* * N.B., Do NOT reference the '_numa_mem_' per cpu variable directly. * It will not be defined when CONFIG_HAVE_MEMORYLESS_NODES is not defined. * Use the accessor functions set_numa_mem(), numa_mem_id() and cpu_to_mem(). */ DECLARE_PER_CPU(int, _numa_mem_); #ifndef set_numa_mem static inline void set_numa_mem(int node) { this_cpu_write(_numa_mem_, node); } #endif #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return raw_cpu_read(_numa_mem_); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return per_cpu(_numa_mem_, cpu); } #endif #ifndef set_cpu_numa_mem static inline void set_cpu_numa_mem(int cpu, int node) { per_cpu(_numa_mem_, cpu) = node; } #endif #else /* !CONFIG_HAVE_MEMORYLESS_NODES */ #ifndef numa_mem_id /* Returns the number of the nearest Node with memory */ static inline int numa_mem_id(void) { return numa_node_id(); } #endif #ifndef cpu_to_mem static inline int cpu_to_mem(int cpu) { return cpu_to_node(cpu); } #endif #endif /* [!]CONFIG_HAVE_MEMORYLESS_NODES */ #if defined(topology_die_id) && defined(topology_die_cpumask) #define TOPOLOGY_DIE_SYSFS #endif #if defined(topology_cluster_id) && defined(topology_cluster_cpumask) #define TOPOLOGY_CLUSTER_SYSFS #endif #if defined(topology_book_id) && defined(topology_book_cpumask) #define TOPOLOGY_BOOK_SYSFS #endif #if defined(topology_drawer_id) && defined(topology_drawer_cpumask) #define TOPOLOGY_DRAWER_SYSFS #endif #ifndef topology_physical_package_id #define topology_physical_package_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_die_id #define topology_die_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_cluster_id #define topology_cluster_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_core_id #define topology_core_id(cpu) ((void)(cpu), 0) #endif #ifndef topology_book_id #define topology_book_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_drawer_id #define topology_drawer_id(cpu) ((void)(cpu), -1) #endif #ifndef topology_ppin #define topology_ppin(cpu) ((void)(cpu), 0ull) #endif #ifndef topology_sibling_cpumask #define topology_sibling_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_core_cpumask #define topology_core_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_cluster_cpumask #define topology_cluster_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_die_cpumask #define topology_die_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_book_cpumask #define topology_book_cpumask(cpu) cpumask_of(cpu) #endif #ifndef topology_drawer_cpumask #define topology_drawer_cpumask(cpu) cpumask_of(cpu) #endif #if defined(CONFIG_SCHED_SMT) && !defined(cpu_smt_mask) static inline const struct cpumask *cpu_smt_mask(int cpu) { return topology_sibling_cpumask(cpu); } #endif static inline const struct cpumask *cpu_cpu_mask(int cpu) { return cpumask_of_node(cpu_to_node(cpu)); } #ifdef CONFIG_NUMA int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node); extern const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops); #else static __always_inline int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node) { return cpumask_nth_and(cpu, cpus, cpu_online_mask); } static inline const struct cpumask * sched_numa_hop_mask(unsigned int node, unsigned int hops) { return ERR_PTR(-EOPNOTSUPP); } #endif /* CONFIG_NUMA */ /** * for_each_numa_hop_mask - iterate over cpumasks of increasing NUMA distance * from a given node. * @mask: the iteration variable. * @node: the NUMA node to start the search from. * * Requires rcu_lock to be held. * * Yields cpu_online_mask for @node == NUMA_NO_NODE. */ #define for_each_numa_hop_mask(mask, node) \ for (unsigned int __hops = 0; \ mask = (node != NUMA_NO_NODE || __hops) ? \ sched_numa_hop_mask(node, __hops) : \ cpu_online_mask, \ !IS_ERR_OR_NULL(mask); \ __hops++) #endif /* _LINUX_TOPOLOGY_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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/fcntl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/init.h> #include <linux/mm.h> #include <linux/sched/task.h> #include <linux/fs.h> #include <linux/filelock.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/capability.h> #include <linux/dnotify.h> #include <linux/slab.h> #include <linux/module.h> #include <linux/pipe_fs_i.h> #include <linux/security.h> #include <linux/ptrace.h> #include <linux/signal.h> #include <linux/rcupdate.h> #include <linux/pid_namespace.h> #include <linux/user_namespace.h> #include <linux/memfd.h> #include <linux/compat.h> #include <linux/mount.h> #include <linux/rw_hint.h> #include <linux/poll.h> #include <asm/siginfo.h> #include <linux/uaccess.h> #define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned int arg) { struct inode * inode = file_inode(filp); int error = 0; /* * O_APPEND cannot be cleared if the file is marked as append-only * and the file is open for write. */ if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; /* O_NOATIME can only be set by the owner or superuser */ if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) if (!inode_owner_or_capable(file_mnt_idmap(filp), inode)) return -EPERM; /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) arg |= O_NONBLOCK; /* Pipe packetized mode is controlled by O_DIRECT flag */ if (!S_ISFIFO(inode->i_mode) && (arg & O_DIRECT) && !(filp->f_mode & FMODE_CAN_ODIRECT)) return -EINVAL; if (filp->f_op->check_flags) error = filp->f_op->check_flags(arg); if (error) return error; /* * ->fasync() is responsible for setting the FASYNC bit. */ if (((arg ^ filp->f_flags) & FASYNC) && filp->f_op->fasync) { error = filp->f_op->fasync(fd, filp, (arg & FASYNC) != 0); if (error < 0) goto out; if (error > 0) error = 0; } spin_lock(&filp->f_lock); filp->f_flags = (arg & SETFL_MASK) | (filp->f_flags & ~SETFL_MASK); filp->f_iocb_flags = iocb_flags(filp); spin_unlock(&filp->f_lock); out: return error; } static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { put_pid(filp->f_owner.pid); filp->f_owner.pid = get_pid(pid); filp->f_owner.pid_type = type; if (pid) { const struct cred *cred = current_cred(); filp->f_owner.uid = cred->uid; filp->f_owner.euid = cred->euid; } } write_unlock_irq(&filp->f_owner.lock); } void __f_setown(struct file *filp, struct pid *pid, enum pid_type type, int force) { security_file_set_fowner(filp); f_modown(filp, pid, type, force); } EXPORT_SYMBOL(__f_setown); int f_setown(struct file *filp, int who, int force) { enum pid_type type; struct pid *pid = NULL; int ret = 0; type = PIDTYPE_TGID; if (who < 0) { /* avoid overflow below */ if (who == INT_MIN) return -EINVAL; type = PIDTYPE_PGID; who = -who; } rcu_read_lock(); if (who) { pid = find_vpid(who); if (!pid) ret = -ESRCH; } if (!ret) __f_setown(filp, pid, type, force); rcu_read_unlock(); return ret; } EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { f_modown(filp, NULL, PIDTYPE_TGID, 1); } pid_t f_getown(struct file *filp) { pid_t pid = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) { pid = pid_vnr(filp->f_owner.pid); if (filp->f_owner.pid_type == PIDTYPE_PGID) pid = -pid; } rcu_read_unlock(); read_unlock_irq(&filp->f_owner.lock); return pid; } static int f_setown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner; struct pid *pid; int type; int ret; ret = copy_from_user(&owner, owner_p, sizeof(owner)); if (ret) return -EFAULT; switch (owner.type) { case F_OWNER_TID: type = PIDTYPE_PID; break; case F_OWNER_PID: type = PIDTYPE_TGID; break; case F_OWNER_PGRP: type = PIDTYPE_PGID; break; default: return -EINVAL; } rcu_read_lock(); pid = find_vpid(owner.pid); if (owner.pid && !pid) ret = -ESRCH; else __f_setown(filp, pid, type, 1); rcu_read_unlock(); return ret; } static int f_getown_ex(struct file *filp, unsigned long arg) { struct f_owner_ex __user *owner_p = (void __user *)arg; struct f_owner_ex owner = {}; int ret = 0; read_lock_irq(&filp->f_owner.lock); rcu_read_lock(); if (pid_task(filp->f_owner.pid, filp->f_owner.pid_type)) owner.pid = pid_vnr(filp->f_owner.pid); rcu_read_unlock(); switch (filp->f_owner.pid_type) { case PIDTYPE_PID: owner.type = F_OWNER_TID; break; case PIDTYPE_TGID: owner.type = F_OWNER_PID; break; case PIDTYPE_PGID: owner.type = F_OWNER_PGRP; break; default: WARN_ON(1); ret = -EINVAL; break; } read_unlock_irq(&filp->f_owner.lock); if (!ret) { ret = copy_to_user(owner_p, &owner, sizeof(owner)); if (ret) ret = -EFAULT; } return ret; } #ifdef CONFIG_CHECKPOINT_RESTORE static int f_getowner_uids(struct file *filp, unsigned long arg) { struct user_namespace *user_ns = current_user_ns(); uid_t __user *dst = (void __user *)arg; uid_t src[2]; int err; read_lock_irq(&filp->f_owner.lock); src[0] = from_kuid(user_ns, filp->f_owner.uid); src[1] = from_kuid(user_ns, filp->f_owner.euid); read_unlock_irq(&filp->f_owner.lock); err = put_user(src[0], &dst[0]); err |= put_user(src[1], &dst[1]); return err; } #else static int f_getowner_uids(struct file *filp, unsigned long arg) { return -EINVAL; } #endif static bool rw_hint_valid(u64 hint) { BUILD_BUG_ON(WRITE_LIFE_NOT_SET != RWH_WRITE_LIFE_NOT_SET); BUILD_BUG_ON(WRITE_LIFE_NONE != RWH_WRITE_LIFE_NONE); BUILD_BUG_ON(WRITE_LIFE_SHORT != RWH_WRITE_LIFE_SHORT); BUILD_BUG_ON(WRITE_LIFE_MEDIUM != RWH_WRITE_LIFE_MEDIUM); BUILD_BUG_ON(WRITE_LIFE_LONG != RWH_WRITE_LIFE_LONG); BUILD_BUG_ON(WRITE_LIFE_EXTREME != RWH_WRITE_LIFE_EXTREME); switch (hint) { case RWH_WRITE_LIFE_NOT_SET: case RWH_WRITE_LIFE_NONE: case RWH_WRITE_LIFE_SHORT: case RWH_WRITE_LIFE_MEDIUM: case RWH_WRITE_LIFE_LONG: case RWH_WRITE_LIFE_EXTREME: return true; default: return false; } } static long fcntl_get_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint = READ_ONCE(inode->i_write_hint); if (copy_to_user(argp, &hint, sizeof(*argp))) return -EFAULT; return 0; } static long fcntl_set_rw_hint(struct file *file, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(file); u64 __user *argp = (u64 __user *)arg; u64 hint; if (copy_from_user(&hint, argp, sizeof(hint))) return -EFAULT; if (!rw_hint_valid(hint)) return -EINVAL; WRITE_ONCE(inode->i_write_hint, hint); /* * file->f_mapping->host may differ from inode. As an example, * blkdev_open() modifies file->f_mapping. */ if (file->f_mapping->host != inode) WRITE_ONCE(file->f_mapping->host->i_write_hint, hint); return 0; } /* Is the file descriptor a dup of the file? */ static long f_dupfd_query(int fd, struct file *filp) { CLASS(fd_raw, f)(fd); /* * We can do the 'fdput()' immediately, as the only thing that * matters is the pointer value which isn't changed by the fdput. * * Technically we didn't need a ref at all, and 'fdget()' was * overkill, but given our lockless file pointer lookup, the * alternatives are complicated. */ return f.file == filp; } static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, struct file *filp) { void __user *argp = (void __user *)arg; int argi = (int)arg; struct flock flock; long err = -EINVAL; switch (cmd) { case F_DUPFD: err = f_dupfd(argi, filp, 0); break; case F_DUPFD_CLOEXEC: err = f_dupfd(argi, filp, O_CLOEXEC); break; case F_DUPFD_QUERY: err = f_dupfd_query(argi, filp); break; case F_GETFD: err = get_close_on_exec(fd) ? FD_CLOEXEC : 0; break; case F_SETFD: err = 0; set_close_on_exec(fd, argi & FD_CLOEXEC); break; case F_GETFL: err = filp->f_flags; break; case F_SETFL: err = setfl(fd, filp, argi); break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_GETLK: #endif case F_GETLK: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_getlk(filp, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) return -EFAULT; break; #if BITS_PER_LONG != 32 /* 32-bit arches must use fcntl64() */ case F_OFD_SETLK: case F_OFD_SETLKW: fallthrough; #endif case F_SETLK: case F_SETLKW: if (copy_from_user(&flock, argp, sizeof(flock))) return -EFAULT; err = fcntl_setlk(fd, filp, cmd, &flock); break; case F_GETOWN: /* * XXX If f_owner is a process group, the * negative return value will get converted * into an error. Oops. If we keep the * current syscall conventions, the only way * to fix this will be in libc. */ err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: err = f_setown(filp, argi, 1); break; case F_GETOWN_EX: err = f_getown_ex(filp, arg); break; case F_SETOWN_EX: err = f_setown_ex(filp, arg); break; case F_GETOWNER_UIDS: err = f_getowner_uids(filp, arg); break; case F_GETSIG: err = filp->f_owner.signum; break; case F_SETSIG: /* arg == 0 restores default behaviour. */ if (!valid_signal(argi)) { break; } err = 0; filp->f_owner.signum = argi; break; case F_GETLEASE: err = fcntl_getlease(filp); break; case F_SETLEASE: err = fcntl_setlease(fd, filp, argi); break; case F_NOTIFY: err = fcntl_dirnotify(fd, filp, argi); break; case F_SETPIPE_SZ: case F_GETPIPE_SZ: err = pipe_fcntl(filp, cmd, argi); break; case F_ADD_SEALS: case F_GET_SEALS: err = memfd_fcntl(filp, cmd, argi); break; case F_GET_RW_HINT: err = fcntl_get_rw_hint(filp, cmd, arg); break; case F_SET_RW_HINT: err = fcntl_set_rw_hint(filp, cmd, arg); break; default: break; } return err; } static int check_fcntl_cmd(unsigned cmd) { switch (cmd) { case F_DUPFD: case F_DUPFD_CLOEXEC: case F_DUPFD_QUERY: case F_GETFD: case F_SETFD: case F_GETFL: return 1; } return 0; } SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget_raw(fd); long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (!err) err = do_fcntl(fd, cmd, arg, f.file); out1: fdput(f); out: return err; } #if BITS_PER_LONG == 32 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { void __user *argp = (void __user *)arg; struct fd f = fdget_raw(fd); struct flock64 flock; long err = -EBADF; if (!f.file) goto out; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out1; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out1; switch (cmd) { case F_GETLK64: case F_OFD_GETLK: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_getlk64(f.file, cmd, &flock); if (!err && copy_to_user(argp, &flock, sizeof(flock))) err = -EFAULT; break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = -EFAULT; if (copy_from_user(&flock, argp, sizeof(flock))) break; err = fcntl_setlk64(fd, f.file, cmd, &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out1: fdput(f); out: return err; } #endif #ifdef CONFIG_COMPAT /* careful - don't use anywhere else */ #define copy_flock_fields(dst, src) \ (dst)->l_type = (src)->l_type; \ (dst)->l_whence = (src)->l_whence; \ (dst)->l_start = (src)->l_start; \ (dst)->l_len = (src)->l_len; \ (dst)->l_pid = (src)->l_pid; static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl) { struct compat_flock fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl) { struct compat_flock64 fl; if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64))) return -EFAULT; copy_flock_fields(kfl, &fl); return 0; } static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl) { struct compat_flock fl; memset(&fl, 0, sizeof(struct compat_flock)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock))) return -EFAULT; return 0; } static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl) { struct compat_flock64 fl; BUILD_BUG_ON(sizeof(kfl->l_start) > sizeof(ufl->l_start)); BUILD_BUG_ON(sizeof(kfl->l_len) > sizeof(ufl->l_len)); memset(&fl, 0, sizeof(struct compat_flock64)); copy_flock_fields(&fl, kfl); if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64))) return -EFAULT; return 0; } #undef copy_flock_fields static unsigned int convert_fcntl_cmd(unsigned int cmd) { switch (cmd) { case F_GETLK64: return F_GETLK; case F_SETLK64: return F_SETLK; case F_SETLKW64: return F_SETLKW; } return cmd; } /* * GETLK was successful and we need to return the data, but it needs to fit in * the compat structure. * l_start shouldn't be too big, unless the original start + end is greater than * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return * -EOVERFLOW in that case. l_len could be too big, in which case we just * truncate it, and only allow the app to see that part of the conflicting lock * that might make sense to it anyway */ static int fixup_compat_flock(struct flock *flock) { if (flock->l_start > COMPAT_OFF_T_MAX) return -EOVERFLOW; if (flock->l_len > COMPAT_OFF_T_MAX) flock->l_len = COMPAT_OFF_T_MAX; return 0; } static long do_compat_fcntl64(unsigned int fd, unsigned int cmd, compat_ulong_t arg) { struct fd f = fdget_raw(fd); struct flock flock; long err = -EBADF; if (!f.file) return err; if (unlikely(f.file->f_mode & FMODE_PATH)) { if (!check_fcntl_cmd(cmd)) goto out_put; } err = security_file_fcntl(f.file, cmd, arg); if (err) goto out_put; switch (cmd) { case F_GETLK: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (err) break; err = fixup_compat_flock(&flock); if (!err) err = put_compat_flock(&flock, compat_ptr(arg)); break; case F_GETLK64: case F_OFD_GETLK: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock); if (!err) err = put_compat_flock64(&flock, compat_ptr(arg)); break; case F_SETLK: case F_SETLKW: err = get_compat_flock(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; case F_SETLK64: case F_SETLKW64: case F_OFD_SETLK: case F_OFD_SETLKW: err = get_compat_flock64(&flock, compat_ptr(arg)); if (err) break; err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock); break; default: err = do_fcntl(fd, cmd, arg, f.file); break; } out_put: fdput(f); return err; } COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { return do_compat_fcntl64(fd, cmd, arg); } COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { switch (cmd) { case F_GETLK64: case F_SETLK64: case F_SETLKW64: case F_OFD_GETLK: case F_OFD_SETLK: case F_OFD_SETLKW: return -EINVAL; } return do_compat_fcntl64(fd, cmd, arg); } #endif /* Table to convert sigio signal codes into poll band bitmaps */ static const __poll_t band_table[NSIGPOLL] = { EPOLLIN | EPOLLRDNORM, /* POLL_IN */ EPOLLOUT | EPOLLWRNORM | EPOLLWRBAND, /* POLL_OUT */ EPOLLIN | EPOLLRDNORM | EPOLLMSG, /* POLL_MSG */ EPOLLERR, /* POLL_ERR */ EPOLLPRI | EPOLLRDBAND, /* POLL_PRI */ EPOLLHUP | EPOLLERR /* POLL_HUP */ }; static inline int sigio_perm(struct task_struct *p, struct fown_struct *fown, int sig) { const struct cred *cred; int ret; rcu_read_lock(); cred = __task_cred(p); ret = ((uid_eq(fown->euid, GLOBAL_ROOT_UID) || uid_eq(fown->euid, cred->suid) || uid_eq(fown->euid, cred->uid) || uid_eq(fown->uid, cred->suid) || uid_eq(fown->uid, cred->uid)) && !security_file_send_sigiotask(p, fown, sig)); rcu_read_unlock(); return ret; } static void send_sigio_to_task(struct task_struct *p, struct fown_struct *fown, int fd, int reason, enum pid_type type) { /* * F_SETSIG can change ->signum lockless in parallel, make * sure we read it once and use the same value throughout. */ int signum = READ_ONCE(fown->signum); if (!sigio_perm(p, fown, signum)) return; switch (signum) { default: { kernel_siginfo_t si; /* Queue a rt signal with the appropriate fd as its value. We use SI_SIGIO as the source, not SI_KERNEL, since kernel signals always get delivered even if we can't queue. Failure to queue in this case _should_ be reported; we fall back to SIGIO in that case. --sct */ clear_siginfo(&si); si.si_signo = signum; si.si_errno = 0; si.si_code = reason; /* * Posix definies POLL_IN and friends to be signal * specific si_codes for SIG_POLL. Linux extended * these si_codes to other signals in a way that is * ambiguous if other signals also have signal * specific si_codes. In that case use SI_SIGIO instead * to remove the ambiguity. */ if ((signum != SIGPOLL) && sig_specific_sicodes(signum)) si.si_code = SI_SIGIO; /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ BUG_ON((reason < POLL_IN) || ((reason - POLL_IN) >= NSIGPOLL)); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = mangle_poll(band_table[reason - POLL_IN]); si.si_fd = fd; if (!do_send_sig_info(signum, &si, p, type)) break; } fallthrough; /* fall back on the old plain SIGIO signal */ case 0: do_send_sig_info(SIGIO, SEND_SIG_PRIV, p, type); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; enum pid_type type; unsigned long flags; struct pid *pid; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigio_to_task(p, fown, fd, band, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigio_to_task(p, fown, fd, band, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); } static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown, enum pid_type type) { if (sigio_perm(p, fown, SIGURG)) do_send_sig_info(SIGURG, SEND_SIG_PRIV, p, type); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; enum pid_type type; struct pid *pid; unsigned long flags; int ret = 0; read_lock_irqsave(&fown->lock, flags); type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; ret = 1; if (type <= PIDTYPE_TGID) { rcu_read_lock(); p = pid_task(pid, PIDTYPE_PID); if (p) send_sigurg_to_task(p, fown, type); rcu_read_unlock(); } else { read_lock(&tasklist_lock); do_each_pid_task(pid, type, p) { send_sigurg_to_task(p, fown, type); } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); } out_unlock_fown: read_unlock_irqrestore(&fown->lock, flags); return ret; } static DEFINE_SPINLOCK(fasync_lock); static struct kmem_cache *fasync_cache __ro_after_init; /* * Remove a fasync entry. If successfully removed, return * positive and clear the FASYNC flag. If no entry exists, * do nothing and return 0. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". * */ int fasync_remove_entry(struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *fa, **fp; int result = 0; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_file = NULL; write_unlock_irq(&fa->fa_lock); *fp = fa->fa_next; kfree_rcu(fa, fa_rcu); filp->f_flags &= ~FASYNC; result = 1; break; } spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return result; } struct fasync_struct *fasync_alloc(void) { return kmem_cache_alloc(fasync_cache, GFP_KERNEL); } /* * NOTE! This can be used only for unused fasync entries: * entries that actually got inserted on the fasync list * need to be released by rcu - see fasync_remove_entry. */ void fasync_free(struct fasync_struct *new) { kmem_cache_free(fasync_cache, new); } /* * Insert a new entry into the fasync list. Return the pointer to the * old one if we didn't use the new one. * * NOTE! It is very important that the FASYNC flag always * match the state "is the filp on a fasync list". */ struct fasync_struct *fasync_insert_entry(int fd, struct file *filp, struct fasync_struct **fapp, struct fasync_struct *new) { struct fasync_struct *fa, **fp; spin_lock(&filp->f_lock); spin_lock(&fasync_lock); for (fp = fapp; (fa = *fp) != NULL; fp = &fa->fa_next) { if (fa->fa_file != filp) continue; write_lock_irq(&fa->fa_lock); fa->fa_fd = fd; write_unlock_irq(&fa->fa_lock); goto out; } rwlock_init(&new->fa_lock); new->magic = FASYNC_MAGIC; new->fa_file = filp; new->fa_fd = fd; new->fa_next = *fapp; rcu_assign_pointer(*fapp, new); filp->f_flags |= FASYNC; out: spin_unlock(&fasync_lock); spin_unlock(&filp->f_lock); return fa; } /* * Add a fasync entry. Return negative on error, positive if * added, and zero if did nothing but change an existing one. */ static int fasync_add_entry(int fd, struct file *filp, struct fasync_struct **fapp) { struct fasync_struct *new; new = fasync_alloc(); if (!new) return -ENOMEM; /* * fasync_insert_entry() returns the old (update) entry if * it existed. * * So free the (unused) new entry and return 0 to let the * caller know that we didn't add any new fasync entries. */ if (fasync_insert_entry(fd, filp, fapp, new)) { fasync_free(new); return 0; } return 1; } /* * fasync_helper() is used by almost all character device drivers * to set up the fasync queue, and for regular files by the file * lease code. It returns negative on error, 0 if it did no changes * and positive if it added/deleted the entry. */ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fapp) { if (!on) return fasync_remove_entry(filp, fapp); return fasync_add_entry(fd, filp, fapp); } EXPORT_SYMBOL(fasync_helper); /* * rcu_read_lock() is held */ static void kill_fasync_rcu(struct fasync_struct *fa, int sig, int band) { while (fa) { struct fown_struct *fown; unsigned long flags; if (fa->magic != FASYNC_MAGIC) { printk(KERN_ERR "kill_fasync: bad magic number in " "fasync_struct!\n"); return; } read_lock_irqsave(&fa->fa_lock, flags); if (fa->fa_file) { fown = &fa->fa_file->f_owner; /* Don't send SIGURG to processes which have not set a queued signum: SIGURG has its own default signalling mechanism. */ if (!(sig == SIGURG && fown->signum == 0)) send_sigio(fown, fa->fa_fd, band); } read_unlock_irqrestore(&fa->fa_lock, flags); fa = rcu_dereference(fa->fa_next); } } void kill_fasync(struct fasync_struct **fp, int sig, int band) { /* First a quick test without locking: usually * the list is empty. */ if (*fp) { rcu_read_lock(); kill_fasync_rcu(rcu_dereference(*fp), sig, band); rcu_read_unlock(); } } EXPORT_SYMBOL(kill_fasync); static int __init fcntl_init(void) { /* * Please add new bits here to ensure allocation uniqueness. * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY * is defined as O_NONBLOCK on some platforms and not on others. */ BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32( (VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) | __FMODE_EXEC | __FMODE_NONOTIFY)); fasync_cache = kmem_cache_create("fasync_cache", sizeof(struct fasync_struct), 0, SLAB_PANIC | SLAB_ACCOUNT, NULL); return 0; } module_init(fcntl_init) |
| 49 49 49 49 49 49 49 49 49 49 49 49 49 49 48 49 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/stat.h> #include <linux/sysctl.h> #include <linux/slab.h> #include <linux/cred.h> #include <linux/hash.h> #include <linux/kmemleak.h> #include <linux/user_namespace.h> struct ucounts init_ucounts = { .ns = &init_user_ns, .uid = GLOBAL_ROOT_UID, .count = ATOMIC_INIT(1), }; #define UCOUNTS_HASHTABLE_BITS 10 static struct hlist_head ucounts_hashtable[(1 << UCOUNTS_HASHTABLE_BITS)]; static DEFINE_SPINLOCK(ucounts_lock); #define ucounts_hashfn(ns, uid) \ hash_long((unsigned long)__kuid_val(uid) + (unsigned long)(ns), \ UCOUNTS_HASHTABLE_BITS) #define ucounts_hashentry(ns, uid) \ (ucounts_hashtable + ucounts_hashfn(ns, uid)) #ifdef CONFIG_SYSCTL static struct ctl_table_set * set_lookup(struct ctl_table_root *root) { return ¤t_user_ns()->set; } static int set_is_seen(struct ctl_table_set *set) { return ¤t_user_ns()->set == set; } static int set_permissions(struct ctl_table_header *head, const struct ctl_table *table) { struct user_namespace *user_ns = container_of(head->set, struct user_namespace, set); int mode; /* Allow users with CAP_SYS_RESOURCE unrestrained access */ if (ns_capable(user_ns, CAP_SYS_RESOURCE)) mode = (table->mode & S_IRWXU) >> 6; else /* Allow all others at most read-only access */ mode = table->mode & S_IROTH; return (mode << 6) | (mode << 3) | mode; } static struct ctl_table_root set_root = { .lookup = set_lookup, .permissions = set_permissions, }; static long ue_zero = 0; static long ue_int_max = INT_MAX; #define UCOUNT_ENTRY(name) \ { \ .procname = name, \ .maxlen = sizeof(long), \ .mode = 0644, \ .proc_handler = proc_doulongvec_minmax, \ .extra1 = &ue_zero, \ .extra2 = &ue_int_max, \ } static struct ctl_table user_table[] = { UCOUNT_ENTRY("max_user_namespaces"), UCOUNT_ENTRY("max_pid_namespaces"), UCOUNT_ENTRY("max_uts_namespaces"), UCOUNT_ENTRY("max_ipc_namespaces"), UCOUNT_ENTRY("max_net_namespaces"), UCOUNT_ENTRY("max_mnt_namespaces"), UCOUNT_ENTRY("max_cgroup_namespaces"), UCOUNT_ENTRY("max_time_namespaces"), #ifdef CONFIG_INOTIFY_USER UCOUNT_ENTRY("max_inotify_instances"), UCOUNT_ENTRY("max_inotify_watches"), #endif #ifdef CONFIG_FANOTIFY UCOUNT_ENTRY("max_fanotify_groups"), UCOUNT_ENTRY("max_fanotify_marks"), #endif }; #endif /* CONFIG_SYSCTL */ bool setup_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL struct ctl_table *tbl; BUILD_BUG_ON(ARRAY_SIZE(user_table) != UCOUNT_COUNTS); setup_sysctl_set(&ns->set, &set_root, set_is_seen); tbl = kmemdup(user_table, sizeof(user_table), GFP_KERNEL); if (tbl) { int i; for (i = 0; i < UCOUNT_COUNTS; i++) { tbl[i].data = &ns->ucount_max[i]; } ns->sysctls = __register_sysctl_table(&ns->set, "user", tbl, ARRAY_SIZE(user_table)); } if (!ns->sysctls) { kfree(tbl); retire_sysctl_set(&ns->set); return false; } #endif return true; } void retire_userns_sysctls(struct user_namespace *ns) { #ifdef CONFIG_SYSCTL const struct ctl_table *tbl; tbl = ns->sysctls->ctl_table_arg; unregister_sysctl_table(ns->sysctls); retire_sysctl_set(&ns->set); kfree(tbl); #endif } static struct ucounts *find_ucounts(struct user_namespace *ns, kuid_t uid, struct hlist_head *hashent) { struct ucounts *ucounts; hlist_for_each_entry(ucounts, hashent, node) { if (uid_eq(ucounts->uid, uid) && (ucounts->ns == ns)) return ucounts; } return NULL; } static void hlist_add_ucounts(struct ucounts *ucounts) { struct hlist_head *hashent = ucounts_hashentry(ucounts->ns, ucounts->uid); spin_lock_irq(&ucounts_lock); hlist_add_head(&ucounts->node, hashent); spin_unlock_irq(&ucounts_lock); } static inline bool get_ucounts_or_wrap(struct ucounts *ucounts) { /* Returns true on a successful get, false if the count wraps. */ return !atomic_add_negative(1, &ucounts->count); } struct ucounts *get_ucounts(struct ucounts *ucounts) { if (!get_ucounts_or_wrap(ucounts)) { put_ucounts(ucounts); ucounts = NULL; } return ucounts; } struct ucounts *alloc_ucounts(struct user_namespace *ns, kuid_t uid) { struct hlist_head *hashent = ucounts_hashentry(ns, uid); struct ucounts *ucounts, *new; bool wrapped; spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (!ucounts) { spin_unlock_irq(&ucounts_lock); new = kzalloc(sizeof(*new), GFP_KERNEL); if (!new) return NULL; new->ns = ns; new->uid = uid; atomic_set(&new->count, 1); spin_lock_irq(&ucounts_lock); ucounts = find_ucounts(ns, uid, hashent); if (ucounts) { kfree(new); } else { hlist_add_head(&new->node, hashent); get_user_ns(new->ns); spin_unlock_irq(&ucounts_lock); return new; } } wrapped = !get_ucounts_or_wrap(ucounts); spin_unlock_irq(&ucounts_lock); if (wrapped) { put_ucounts(ucounts); return NULL; } return ucounts; } void put_ucounts(struct ucounts *ucounts) { unsigned long flags; if (atomic_dec_and_lock_irqsave(&ucounts->count, &ucounts_lock, flags)) { hlist_del_init(&ucounts->node); spin_unlock_irqrestore(&ucounts_lock, flags); put_user_ns(ucounts->ns); kfree(ucounts); } } static inline bool atomic_long_inc_below(atomic_long_t *v, int u) { long c, old; c = atomic_long_read(v); for (;;) { if (unlikely(c >= u)) return false; old = atomic_long_cmpxchg(v, c, c+1); if (likely(old == c)) return true; c = old; } } struct ucounts *inc_ucount(struct user_namespace *ns, kuid_t uid, enum ucount_type type) { struct ucounts *ucounts, *iter, *bad; struct user_namespace *tns; ucounts = alloc_ucounts(ns, uid); for (iter = ucounts; iter; iter = tns->ucounts) { long max; tns = iter->ns; max = READ_ONCE(tns->ucount_max[type]); if (!atomic_long_inc_below(&iter->ucount[type], max)) goto fail; } return ucounts; fail: bad = iter; for (iter = ucounts; iter != bad; iter = iter->ns->ucounts) atomic_long_dec(&iter->ucount[type]); put_ucounts(ucounts); return NULL; } void dec_ucount(struct ucounts *ucounts, enum ucount_type type) { struct ucounts *iter; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long dec = atomic_long_dec_if_positive(&iter->ucount[type]); WARN_ON_ONCE(dec < 0); } put_ucounts(ucounts); } long inc_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long max = LONG_MAX; long ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(v, &iter->rlimit[type]); if (new < 0 || new > max) ret = LONG_MAX; else if (iter == ucounts) ret = new; max = get_userns_rlimit_max(iter->ns, type); } return ret; } bool dec_rlimit_ucounts(struct ucounts *ucounts, enum rlimit_type type, long v) { struct ucounts *iter; long new = -1; /* Silence compiler warning */ for (iter = ucounts; iter; iter = iter->ns->ucounts) { long dec = atomic_long_sub_return(v, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); if (iter == ucounts) new = dec; } return (new == 0); } static void do_dec_rlimit_put_ucounts(struct ucounts *ucounts, struct ucounts *last, enum rlimit_type type) { struct ucounts *iter, *next; for (iter = ucounts; iter != last; iter = next) { long dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); next = iter->ns->ucounts; if (dec == 0) put_ucounts(iter); } } void dec_rlimit_put_ucounts(struct ucounts *ucounts, enum rlimit_type type) { do_dec_rlimit_put_ucounts(ucounts, NULL, type); } long inc_rlimit_get_ucounts(struct ucounts *ucounts, enum rlimit_type type) { /* Caller must hold a reference to ucounts */ struct ucounts *iter; long max = LONG_MAX; long dec, ret = 0; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long new = atomic_long_add_return(1, &iter->rlimit[type]); if (new < 0 || new > max) goto unwind; if (iter == ucounts) ret = new; max = get_userns_rlimit_max(iter->ns, type); /* * Grab an extra ucount reference for the caller when * the rlimit count was previously 0. */ if (new != 1) continue; if (!get_ucounts(iter)) goto dec_unwind; } return ret; dec_unwind: dec = atomic_long_sub_return(1, &iter->rlimit[type]); WARN_ON_ONCE(dec < 0); unwind: do_dec_rlimit_put_ucounts(ucounts, iter, type); return 0; } bool is_rlimit_overlimit(struct ucounts *ucounts, enum rlimit_type type, unsigned long rlimit) { struct ucounts *iter; long max = rlimit; if (rlimit > LONG_MAX) max = LONG_MAX; for (iter = ucounts; iter; iter = iter->ns->ucounts) { long val = get_rlimit_value(iter, type); if (val < 0 || val > max) return true; max = get_userns_rlimit_max(iter->ns, type); } return false; } static __init int user_namespace_sysctl_init(void) { #ifdef CONFIG_SYSCTL static struct ctl_table_header *user_header; static struct ctl_table empty[1]; /* * It is necessary to register the user directory in the * default set so that registrations in the child sets work * properly. */ user_header = register_sysctl_sz("user", empty, 0); kmemleak_ignore(user_header); BUG_ON(!user_header); BUG_ON(!setup_userns_sysctls(&init_user_ns)); #endif hlist_add_ucounts(&init_ucounts); inc_rlimit_ucounts(&init_ucounts, UCOUNT_RLIMIT_NPROC, 1); return 0; } subsys_initcall(user_namespace_sysctl_init); |
| 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 14 2 2 2 2 2 2 2 14 14 14 14 14 14 14 14 2 14 14 14 9 9 9 9 9 9 14 14 14 14 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* audit.c -- Auditing support * Gateway between the kernel (e.g., selinux) and the user-space audit daemon. * System-call specific features have moved to auditsc.c * * Copyright 2003-2007 Red Hat Inc., Durham, North Carolina. * All Rights Reserved. * * Written by Rickard E. (Rik) Faith <faith@redhat.com> * * Goals: 1) Integrate fully with Security Modules. * 2) Minimal run-time overhead: * a) Minimal when syscall auditing is disabled (audit_enable=0). * b) Small when syscall auditing is enabled and no audit record * is generated (defer as much work as possible to record * generation time): * i) context is allocated, * ii) names from getname are stored without a copy, and * iii) inode information stored from path_lookup. * 3) Ability to disable syscall auditing at boot time (audit=0). * 4) Usable by other parts of the kernel (if audit_log* is called, * then a syscall record will be generated automatically for the * current syscall). * 5) Netlink interface to user-space. * 6) Support low-overhead kernel-based filtering to minimize the * information that must be passed to user-space. * * Audit userspace, documentation, tests, and bug/issue trackers: * https://github.com/linux-audit */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/file.h> #include <linux/init.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/mm.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/err.h> #include <linux/kthread.h> #include <linux/kernel.h> #include <linux/syscalls.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/mutex.h> #include <linux/gfp.h> #include <linux/pid.h> #include <linux/audit.h> #include <net/sock.h> #include <net/netlink.h> #include <linux/skbuff.h> #include <linux/security.h> #include <linux/freezer.h> #include <linux/pid_namespace.h> #include <net/netns/generic.h> #include "audit.h" /* No auditing will take place until audit_initialized == AUDIT_INITIALIZED. * (Initialization happens after skb_init is called.) */ #define AUDIT_DISABLED -1 #define AUDIT_UNINITIALIZED 0 #define AUDIT_INITIALIZED 1 static int audit_initialized = AUDIT_UNINITIALIZED; u32 audit_enabled = AUDIT_OFF; bool audit_ever_enabled = !!AUDIT_OFF; EXPORT_SYMBOL_GPL(audit_enabled); /* Default state when kernel boots without any parameters. */ static u32 audit_default = AUDIT_OFF; /* If auditing cannot proceed, audit_failure selects what happens. */ static u32 audit_failure = AUDIT_FAIL_PRINTK; /* private audit network namespace index */ static unsigned int audit_net_id; /** * struct audit_net - audit private network namespace data * @sk: communication socket */ struct audit_net { struct sock *sk; }; /** * struct auditd_connection - kernel/auditd connection state * @pid: auditd PID * @portid: netlink portid * @net: the associated network namespace * @rcu: RCU head * * Description: * This struct is RCU protected; you must either hold the RCU lock for reading * or the associated spinlock for writing. */ struct auditd_connection { struct pid *pid; u32 portid; struct net *net; struct rcu_head rcu; }; static struct auditd_connection __rcu *auditd_conn; static DEFINE_SPINLOCK(auditd_conn_lock); /* If audit_rate_limit is non-zero, limit the rate of sending audit records * to that number per second. This prevents DoS attacks, but results in * audit records being dropped. */ static u32 audit_rate_limit; /* Number of outstanding audit_buffers allowed. * When set to zero, this means unlimited. */ static u32 audit_backlog_limit = 64; #define AUDIT_BACKLOG_WAIT_TIME (60 * HZ) static u32 audit_backlog_wait_time = AUDIT_BACKLOG_WAIT_TIME; /* The identity of the user shutting down the audit system. */ static kuid_t audit_sig_uid = INVALID_UID; static pid_t audit_sig_pid = -1; static u32 audit_sig_sid; /* Records can be lost in several ways: 0) [suppressed in audit_alloc] 1) out of memory in audit_log_start [kmalloc of struct audit_buffer] 2) out of memory in audit_log_move [alloc_skb] 3) suppressed due to audit_rate_limit 4) suppressed due to audit_backlog_limit */ static atomic_t audit_lost = ATOMIC_INIT(0); /* Monotonically increasing sum of time the kernel has spent * waiting while the backlog limit is exceeded. */ static atomic_t audit_backlog_wait_time_actual = ATOMIC_INIT(0); /* Hash for inode-based rules */ struct list_head audit_inode_hash[AUDIT_INODE_BUCKETS]; static struct kmem_cache *audit_buffer_cache; /* queue msgs to send via kauditd_task */ static struct sk_buff_head audit_queue; /* queue msgs due to temporary unicast send problems */ static struct sk_buff_head audit_retry_queue; /* queue msgs waiting for new auditd connection */ static struct sk_buff_head audit_hold_queue; /* queue servicing thread */ static struct task_struct *kauditd_task; static DECLARE_WAIT_QUEUE_HEAD(kauditd_wait); /* waitqueue for callers who are blocked on the audit backlog */ static DECLARE_WAIT_QUEUE_HEAD(audit_backlog_wait); static struct audit_features af = {.vers = AUDIT_FEATURE_VERSION, .mask = -1, .features = 0, .lock = 0,}; static char *audit_feature_names[2] = { "only_unset_loginuid", "loginuid_immutable", }; /** * struct audit_ctl_mutex - serialize requests from userspace * @lock: the mutex used for locking * @owner: the task which owns the lock * * Description: * This is the lock struct used to ensure we only process userspace requests * in an orderly fashion. We can't simply use a mutex/lock here because we * need to track lock ownership so we don't end up blocking the lock owner in * audit_log_start() or similar. */ static struct audit_ctl_mutex { struct mutex lock; void *owner; } audit_cmd_mutex; /* AUDIT_BUFSIZ is the size of the temporary buffer used for formatting * audit records. Since printk uses a 1024 byte buffer, this buffer * should be at least that large. */ #define AUDIT_BUFSIZ 1024 /* The audit_buffer is used when formatting an audit record. The caller * locks briefly to get the record off the freelist or to allocate the * buffer, and locks briefly to send the buffer to the netlink layer or * to place it on a transmit queue. Multiple audit_buffers can be in * use simultaneously. */ struct audit_buffer { struct sk_buff *skb; /* formatted skb ready to send */ struct audit_context *ctx; /* NULL or associated context */ gfp_t gfp_mask; }; struct audit_reply { __u32 portid; struct net *net; struct sk_buff *skb; }; /** * auditd_test_task - Check to see if a given task is an audit daemon * @task: the task to check * * Description: * Return 1 if the task is a registered audit daemon, 0 otherwise. */ int auditd_test_task(struct task_struct *task) { int rc; struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); rc = (ac && ac->pid == task_tgid(task) ? 1 : 0); rcu_read_unlock(); return rc; } /** * audit_ctl_lock - Take the audit control lock */ void audit_ctl_lock(void) { mutex_lock(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = current; } /** * audit_ctl_unlock - Drop the audit control lock */ void audit_ctl_unlock(void) { audit_cmd_mutex.owner = NULL; mutex_unlock(&audit_cmd_mutex.lock); } /** * audit_ctl_owner_current - Test to see if the current task owns the lock * * Description: * Return true if the current task owns the audit control lock, false if it * doesn't own the lock. */ static bool audit_ctl_owner_current(void) { return (current == audit_cmd_mutex.owner); } /** * auditd_pid_vnr - Return the auditd PID relative to the namespace * * Description: * Returns the PID in relation to the namespace, 0 on failure. */ static pid_t auditd_pid_vnr(void) { pid_t pid; const struct auditd_connection *ac; rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac || !ac->pid) pid = 0; else pid = pid_vnr(ac->pid); rcu_read_unlock(); return pid; } /** * audit_get_sk - Return the audit socket for the given network namespace * @net: the destination network namespace * * Description: * Returns the sock pointer if valid, NULL otherwise. The caller must ensure * that a reference is held for the network namespace while the sock is in use. */ static struct sock *audit_get_sk(const struct net *net) { struct audit_net *aunet; if (!net) return NULL; aunet = net_generic(net, audit_net_id); return aunet->sk; } void audit_panic(const char *message) { switch (audit_failure) { case AUDIT_FAIL_SILENT: break; case AUDIT_FAIL_PRINTK: if (printk_ratelimit()) pr_err("%s\n", message); break; case AUDIT_FAIL_PANIC: panic("audit: %s\n", message); break; } } static inline int audit_rate_check(void) { static unsigned long last_check = 0; static int messages = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int retval = 0; if (!audit_rate_limit) return 1; spin_lock_irqsave(&lock, flags); if (++messages < audit_rate_limit) { retval = 1; } else { now = jiffies; if (time_after(now, last_check + HZ)) { last_check = now; messages = 0; retval = 1; } } spin_unlock_irqrestore(&lock, flags); return retval; } /** * audit_log_lost - conditionally log lost audit message event * @message: the message stating reason for lost audit message * * Emit at least 1 message per second, even if audit_rate_check is * throttling. * Always increment the lost messages counter. */ void audit_log_lost(const char *message) { static unsigned long last_msg = 0; static DEFINE_SPINLOCK(lock); unsigned long flags; unsigned long now; int print; atomic_inc(&audit_lost); print = (audit_failure == AUDIT_FAIL_PANIC || !audit_rate_limit); if (!print) { spin_lock_irqsave(&lock, flags); now = jiffies; if (time_after(now, last_msg + HZ)) { print = 1; last_msg = now; } spin_unlock_irqrestore(&lock, flags); } if (print) { if (printk_ratelimit()) pr_warn("audit_lost=%u audit_rate_limit=%u audit_backlog_limit=%u\n", atomic_read(&audit_lost), audit_rate_limit, audit_backlog_limit); audit_panic(message); } } static int audit_log_config_change(char *function_name, u32 new, u32 old, int allow_changes) { struct audit_buffer *ab; int rc = 0; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_CONFIG_CHANGE); if (unlikely(!ab)) return rc; audit_log_format(ab, "op=set %s=%u old=%u ", function_name, new, old); audit_log_session_info(ab); rc = audit_log_task_context(ab); if (rc) allow_changes = 0; /* Something weird, deny request */ audit_log_format(ab, " res=%d", allow_changes); audit_log_end(ab); return rc; } static int audit_do_config_change(char *function_name, u32 *to_change, u32 new) { int allow_changes, rc = 0; u32 old = *to_change; /* check if we are locked */ if (audit_enabled == AUDIT_LOCKED) allow_changes = 0; else allow_changes = 1; if (audit_enabled != AUDIT_OFF) { rc = audit_log_config_change(function_name, new, old, allow_changes); if (rc) allow_changes = 0; } /* If we are allowed, make the change */ if (allow_changes == 1) *to_change = new; /* Not allowed, update reason */ else if (rc == 0) rc = -EPERM; return rc; } static int audit_set_rate_limit(u32 limit) { return audit_do_config_change("audit_rate_limit", &audit_rate_limit, limit); } static int audit_set_backlog_limit(u32 limit) { return audit_do_config_change("audit_backlog_limit", &audit_backlog_limit, limit); } static int audit_set_backlog_wait_time(u32 timeout) { return audit_do_config_change("audit_backlog_wait_time", &audit_backlog_wait_time, timeout); } static int audit_set_enabled(u32 state) { int rc; if (state > AUDIT_LOCKED) return -EINVAL; rc = audit_do_config_change("audit_enabled", &audit_enabled, state); if (!rc) audit_ever_enabled |= !!state; return rc; } static int audit_set_failure(u32 state) { if (state != AUDIT_FAIL_SILENT && state != AUDIT_FAIL_PRINTK && state != AUDIT_FAIL_PANIC) return -EINVAL; return audit_do_config_change("audit_failure", &audit_failure, state); } /** * auditd_conn_free - RCU helper to release an auditd connection struct * @rcu: RCU head * * Description: * Drop any references inside the auditd connection tracking struct and free * the memory. */ static void auditd_conn_free(struct rcu_head *rcu) { struct auditd_connection *ac; ac = container_of(rcu, struct auditd_connection, rcu); put_pid(ac->pid); put_net(ac->net); kfree(ac); } /** * auditd_set - Set/Reset the auditd connection state * @pid: auditd PID * @portid: auditd netlink portid * @net: auditd network namespace pointer * @skb: the netlink command from the audit daemon * @ack: netlink ack flag, cleared if ack'd here * * Description: * This function will obtain and drop network namespace references as * necessary. Returns zero on success, negative values on failure. */ static int auditd_set(struct pid *pid, u32 portid, struct net *net, struct sk_buff *skb, bool *ack) { unsigned long flags; struct auditd_connection *ac_old, *ac_new; struct nlmsghdr *nlh; if (!pid || !net) return -EINVAL; ac_new = kzalloc(sizeof(*ac_new), GFP_KERNEL); if (!ac_new) return -ENOMEM; ac_new->pid = get_pid(pid); ac_new->portid = portid; ac_new->net = get_net(net); /* send the ack now to avoid a race with the queue backlog */ if (*ack) { nlh = nlmsg_hdr(skb); netlink_ack(skb, nlh, 0, NULL); *ack = false; } spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); rcu_assign_pointer(auditd_conn, ac_new); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); return 0; } /** * kauditd_printk_skb - Print the audit record to the ring buffer * @skb: audit record * * Whatever the reason, this packet may not make it to the auditd connection * so write it via printk so the information isn't completely lost. */ static void kauditd_printk_skb(struct sk_buff *skb) { struct nlmsghdr *nlh = nlmsg_hdr(skb); char *data = nlmsg_data(nlh); if (nlh->nlmsg_type != AUDIT_EOE && printk_ratelimit()) pr_notice("type=%d %s\n", nlh->nlmsg_type, data); } /** * kauditd_rehold_skb - Handle a audit record send failure in the hold queue * @skb: audit record * @error: error code (unused) * * Description: * This should only be used by the kauditd_thread when it fails to flush the * hold queue. */ static void kauditd_rehold_skb(struct sk_buff *skb, __always_unused int error) { /* put the record back in the queue */ skb_queue_tail(&audit_hold_queue, skb); } /** * kauditd_hold_skb - Queue an audit record, waiting for auditd * @skb: audit record * @error: error code * * Description: * Queue the audit record, waiting for an instance of auditd. When this * function is called we haven't given up yet on sending the record, but things * are not looking good. The first thing we want to do is try to write the * record via printk and then see if we want to try and hold on to the record * and queue it, if we have room. If we want to hold on to the record, but we * don't have room, record a record lost message. */ static void kauditd_hold_skb(struct sk_buff *skb, int error) { /* at this point it is uncertain if we will ever send this to auditd so * try to send the message via printk before we go any further */ kauditd_printk_skb(skb); /* can we just silently drop the message? */ if (!audit_default) goto drop; /* the hold queue is only for when the daemon goes away completely, * not -EAGAIN failures; if we are in a -EAGAIN state requeue the * record on the retry queue unless it's full, in which case drop it */ if (error == -EAGAIN) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } audit_log_lost("kauditd retry queue overflow"); goto drop; } /* if we have room in the hold queue, queue the message */ if (!audit_backlog_limit || skb_queue_len(&audit_hold_queue) < audit_backlog_limit) { skb_queue_tail(&audit_hold_queue, skb); return; } /* we have no other options - drop the message */ audit_log_lost("kauditd hold queue overflow"); drop: kfree_skb(skb); } /** * kauditd_retry_skb - Queue an audit record, attempt to send again to auditd * @skb: audit record * @error: error code (unused) * * Description: * Not as serious as kauditd_hold_skb() as we still have a connected auditd, * but for some reason we are having problems sending it audit records so * queue the given record and attempt to resend. */ static void kauditd_retry_skb(struct sk_buff *skb, __always_unused int error) { if (!audit_backlog_limit || skb_queue_len(&audit_retry_queue) < audit_backlog_limit) { skb_queue_tail(&audit_retry_queue, skb); return; } /* we have to drop the record, send it via printk as a last effort */ kauditd_printk_skb(skb); audit_log_lost("kauditd retry queue overflow"); kfree_skb(skb); } /** * auditd_reset - Disconnect the auditd connection * @ac: auditd connection state * * Description: * Break the auditd/kauditd connection and move all the queued records into the * hold queue in case auditd reconnects. It is important to note that the @ac * pointer should never be dereferenced inside this function as it may be NULL * or invalid, you can only compare the memory address! If @ac is NULL then * the connection will always be reset. */ static void auditd_reset(const struct auditd_connection *ac) { unsigned long flags; struct sk_buff *skb; struct auditd_connection *ac_old; /* if it isn't already broken, break the connection */ spin_lock_irqsave(&auditd_conn_lock, flags); ac_old = rcu_dereference_protected(auditd_conn, lockdep_is_held(&auditd_conn_lock)); if (ac && ac != ac_old) { /* someone already registered a new auditd connection */ spin_unlock_irqrestore(&auditd_conn_lock, flags); return; } rcu_assign_pointer(auditd_conn, NULL); spin_unlock_irqrestore(&auditd_conn_lock, flags); if (ac_old) call_rcu(&ac_old->rcu, auditd_conn_free); /* flush the retry queue to the hold queue, but don't touch the main * queue since we need to process that normally for multicast */ while ((skb = skb_dequeue(&audit_retry_queue))) kauditd_hold_skb(skb, -ECONNREFUSED); } /** * auditd_send_unicast_skb - Send a record via unicast to auditd * @skb: audit record * * Description: * Send a skb to the audit daemon, returns positive/zero values on success and * negative values on failure; in all cases the skb will be consumed by this * function. If the send results in -ECONNREFUSED the connection with auditd * will be reset. This function may sleep so callers should not hold any locks * where this would cause a problem. */ static int auditd_send_unicast_skb(struct sk_buff *skb) { int rc; u32 portid; struct net *net; struct sock *sk; struct auditd_connection *ac; /* NOTE: we can't call netlink_unicast while in the RCU section so * take a reference to the network namespace and grab local * copies of the namespace, the sock, and the portid; the * namespace and sock aren't going to go away while we hold a * reference and if the portid does become invalid after the RCU * section netlink_unicast() should safely return an error */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); kfree_skb(skb); rc = -ECONNREFUSED; goto err; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); rc = netlink_unicast(sk, skb, portid, 0); put_net(net); if (rc < 0) goto err; return rc; err: if (ac && rc == -ECONNREFUSED) auditd_reset(ac); return rc; } /** * kauditd_send_queue - Helper for kauditd_thread to flush skb queues * @sk: the sending sock * @portid: the netlink destination * @queue: the skb queue to process * @retry_limit: limit on number of netlink unicast failures * @skb_hook: per-skb hook for additional processing * @err_hook: hook called if the skb fails the netlink unicast send * * Description: * Run through the given queue and attempt to send the audit records to auditd, * returns zero on success, negative values on failure. It is up to the caller * to ensure that the @sk is valid for the duration of this function. * */ static int kauditd_send_queue(struct sock *sk, u32 portid, struct sk_buff_head *queue, unsigned int retry_limit, void (*skb_hook)(struct sk_buff *skb), void (*err_hook)(struct sk_buff *skb, int error)) { int rc = 0; struct sk_buff *skb = NULL; struct sk_buff *skb_tail; unsigned int failed = 0; /* NOTE: kauditd_thread takes care of all our locking, we just use * the netlink info passed to us (e.g. sk and portid) */ skb_tail = skb_peek_tail(queue); while ((skb != skb_tail) && (skb = skb_dequeue(queue))) { /* call the skb_hook for each skb we touch */ if (skb_hook) (*skb_hook)(skb); /* can we send to anyone via unicast? */ if (!sk) { if (err_hook) (*err_hook)(skb, -ECONNREFUSED); continue; } retry: /* grab an extra skb reference in case of error */ skb_get(skb); rc = netlink_unicast(sk, skb, portid, 0); if (rc < 0) { /* send failed - try a few times unless fatal error */ if (++failed >= retry_limit || rc == -ECONNREFUSED || rc == -EPERM) { sk = NULL; if (err_hook) (*err_hook)(skb, rc); if (rc == -EAGAIN) rc = 0; /* continue to drain the queue */ continue; } else goto retry; } else { /* skb sent - drop the extra reference and continue */ consume_skb(skb); failed = 0; } } return (rc >= 0 ? 0 : rc); } /* * kauditd_send_multicast_skb - Send a record to any multicast listeners * @skb: audit record * * Description: * Write a multicast message to anyone listening in the initial network * namespace. This function doesn't consume an skb as might be expected since * it has to copy it anyways. */ static void kauditd_send_multicast_skb(struct sk_buff *skb) { struct sk_buff *copy; struct sock *sock = audit_get_sk(&init_net); struct nlmsghdr *nlh; /* NOTE: we are not taking an additional reference for init_net since * we don't have to worry about it going away */ if (!netlink_has_listeners(sock, AUDIT_NLGRP_READLOG)) return; /* * The seemingly wasteful skb_copy() rather than bumping the refcount * using skb_get() is necessary because non-standard mods are made to * the skb by the original kaudit unicast socket send routine. The * existing auditd daemon assumes this breakage. Fixing this would * require co-ordinating a change in the established protocol between * the kaudit kernel subsystem and the auditd userspace code. There is * no reason for new multicast clients to continue with this * non-compliance. */ copy = skb_copy(skb, GFP_KERNEL); if (!copy) return; nlh = nlmsg_hdr(copy); nlh->nlmsg_len = skb->len; nlmsg_multicast(sock, copy, 0, AUDIT_NLGRP_READLOG, GFP_KERNEL); } /** * kauditd_thread - Worker thread to send audit records to userspace * @dummy: unused */ static int kauditd_thread(void *dummy) { int rc; u32 portid = 0; struct net *net = NULL; struct sock *sk = NULL; struct auditd_connection *ac; #define UNICAST_RETRIES 5 set_freezable(); while (!kthread_should_stop()) { /* NOTE: see the lock comments in auditd_send_unicast_skb() */ rcu_read_lock(); ac = rcu_dereference(auditd_conn); if (!ac) { rcu_read_unlock(); goto main_queue; } net = get_net(ac->net); sk = audit_get_sk(net); portid = ac->portid; rcu_read_unlock(); /* attempt to flush the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_hold_queue, UNICAST_RETRIES, NULL, kauditd_rehold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } /* attempt to flush the retry queue */ rc = kauditd_send_queue(sk, portid, &audit_retry_queue, UNICAST_RETRIES, NULL, kauditd_hold_skb); if (rc < 0) { sk = NULL; auditd_reset(ac); goto main_queue; } main_queue: /* process the main queue - do the multicast send and attempt * unicast, dump failed record sends to the retry queue; if * sk == NULL due to previous failures we will just do the * multicast send and move the record to the hold queue */ rc = kauditd_send_queue(sk, portid, &audit_queue, 1, kauditd_send_multicast_skb, (sk ? kauditd_retry_skb : kauditd_hold_skb)); if (ac && rc < 0) auditd_reset(ac); sk = NULL; /* drop our netns reference, no auditd sends past this line */ if (net) { put_net(net); net = NULL; } /* we have processed all the queues so wake everyone */ wake_up(&audit_backlog_wait); /* NOTE: we want to wake up if there is anything on the queue, * regardless of if an auditd is connected, as we need to * do the multicast send and rotate records from the * main queue to the retry/hold queues */ wait_event_freezable(kauditd_wait, (skb_queue_len(&audit_queue) ? 1 : 0)); } return 0; } int audit_send_list_thread(void *_dest) { struct audit_netlink_list *dest = _dest; struct sk_buff *skb; struct sock *sk = audit_get_sk(dest->net); /* wait for parent to finish and send an ACK */ audit_ctl_lock(); audit_ctl_unlock(); while ((skb = __skb_dequeue(&dest->q)) != NULL) netlink_unicast(sk, skb, dest->portid, 0); put_net(dest->net); kfree(dest); return 0; } struct sk_buff *audit_make_reply(int seq, int type, int done, int multi, const void *payload, int size) { struct sk_buff *skb; struct nlmsghdr *nlh; void *data; int flags = multi ? NLM_F_MULTI : 0; int t = done ? NLMSG_DONE : type; skb = nlmsg_new(size, GFP_KERNEL); if (!skb) return NULL; nlh = nlmsg_put(skb, 0, seq, t, size, flags); if (!nlh) goto out_kfree_skb; data = nlmsg_data(nlh); memcpy(data, payload, size); return skb; out_kfree_skb: kfree_skb(skb); return NULL; } static void audit_free_reply(struct audit_reply *reply) { if (!reply) return; kfree_skb(reply->skb); if (reply->net) put_net(reply->net); kfree(reply); } static int audit_send_reply_thread(void *arg) { struct audit_reply *reply = (struct audit_reply *)arg; audit_ctl_lock(); audit_ctl_unlock(); /* Ignore failure. It'll only happen if the sender goes away, because our timeout is set to infinite. */ netlink_unicast(audit_get_sk(reply->net), reply->skb, reply->portid, 0); reply->skb = NULL; audit_free_reply(reply); return 0; } /** * audit_send_reply - send an audit reply message via netlink * @request_skb: skb of request we are replying to (used to target the reply) * @seq: sequence number * @type: audit message type * @done: done (last) flag * @multi: multi-part message flag * @payload: payload data * @size: payload size * * Allocates a skb, builds the netlink message, and sends it to the port id. */ static void audit_send_reply(struct sk_buff *request_skb, int seq, int type, int done, int multi, const void *payload, int size) { struct task_struct *tsk; struct audit_reply *reply; reply = kzalloc(sizeof(*reply), GFP_KERNEL); if (!reply) return; reply->skb = audit_make_reply(seq, type, done, multi, payload, size); if (!reply->skb) goto err; reply->net = get_net(sock_net(NETLINK_CB(request_skb).sk)); reply->portid = NETLINK_CB(request_skb).portid; tsk = kthread_run(audit_send_reply_thread, reply, "audit_send_reply"); if (IS_ERR(tsk)) goto err; return; err: audit_free_reply(reply); } /* * Check for appropriate CAP_AUDIT_ capabilities on incoming audit * control messages. */ static int audit_netlink_ok(struct sk_buff *skb, u16 msg_type) { int err = 0; /* Only support initial user namespace for now. */ /* * We return ECONNREFUSED because it tricks userspace into thinking * that audit was not configured into the kernel. Lots of users * configure their PAM stack (because that's what the distro does) * to reject login if unable to send messages to audit. If we return * ECONNREFUSED the PAM stack thinks the kernel does not have audit * configured in and will let login proceed. If we return EPERM * userspace will reject all logins. This should be removed when we * support non init namespaces!! */ if (current_user_ns() != &init_user_ns) return -ECONNREFUSED; switch (msg_type) { case AUDIT_LIST: case AUDIT_ADD: case AUDIT_DEL: return -EOPNOTSUPP; case AUDIT_GET: case AUDIT_SET: case AUDIT_GET_FEATURE: case AUDIT_SET_FEATURE: case AUDIT_LIST_RULES: case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: case AUDIT_SIGNAL_INFO: case AUDIT_TTY_GET: case AUDIT_TTY_SET: case AUDIT_TRIM: case AUDIT_MAKE_EQUIV: /* Only support auditd and auditctl in initial pid namespace * for now. */ if (task_active_pid_ns(current) != &init_pid_ns) return -EPERM; if (!netlink_capable(skb, CAP_AUDIT_CONTROL)) err = -EPERM; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!netlink_capable(skb, CAP_AUDIT_WRITE)) err = -EPERM; break; default: /* bad msg */ err = -EINVAL; } return err; } static void audit_log_common_recv_msg(struct audit_context *context, struct audit_buffer **ab, u16 msg_type) { uid_t uid = from_kuid(&init_user_ns, current_uid()); pid_t pid = task_tgid_nr(current); if (!audit_enabled && msg_type != AUDIT_USER_AVC) { *ab = NULL; return; } *ab = audit_log_start(context, GFP_KERNEL, msg_type); if (unlikely(!*ab)) return; audit_log_format(*ab, "pid=%d uid=%u ", pid, uid); audit_log_session_info(*ab); audit_log_task_context(*ab); } static inline void audit_log_user_recv_msg(struct audit_buffer **ab, u16 msg_type) { audit_log_common_recv_msg(NULL, ab, msg_type); } static int is_audit_feature_set(int i) { return af.features & AUDIT_FEATURE_TO_MASK(i); } static int audit_get_feature(struct sk_buff *skb) { u32 seq; seq = nlmsg_hdr(skb)->nlmsg_seq; audit_send_reply(skb, seq, AUDIT_GET_FEATURE, 0, 0, &af, sizeof(af)); return 0; } static void audit_log_feature_change(int which, u32 old_feature, u32 new_feature, u32 old_lock, u32 new_lock, int res) { struct audit_buffer *ab; if (audit_enabled == AUDIT_OFF) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_FEATURE_CHANGE); if (!ab) return; audit_log_task_info(ab); audit_log_format(ab, " feature=%s old=%u new=%u old_lock=%u new_lock=%u res=%d", audit_feature_names[which], !!old_feature, !!new_feature, !!old_lock, !!new_lock, res); audit_log_end(ab); } static int audit_set_feature(struct audit_features *uaf) { int i; BUILD_BUG_ON(AUDIT_LAST_FEATURE + 1 > ARRAY_SIZE(audit_feature_names)); /* if there is ever a version 2 we should handle that here */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; new_lock = (uaf->lock | af.lock) & feature; old_lock = af.lock & feature; /* are we changing a locked feature? */ if (old_lock && (new_feature != old_feature)) { audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 0); return -EPERM; } } /* nothing invalid, do the changes */ for (i = 0; i <= AUDIT_LAST_FEATURE; i++) { u32 feature = AUDIT_FEATURE_TO_MASK(i); u32 old_feature, new_feature, old_lock, new_lock; /* if we are not changing this feature, move along */ if (!(feature & uaf->mask)) continue; old_feature = af.features & feature; new_feature = uaf->features & feature; old_lock = af.lock & feature; new_lock = (uaf->lock | af.lock) & feature; if (new_feature != old_feature) audit_log_feature_change(i, old_feature, new_feature, old_lock, new_lock, 1); if (new_feature) af.features |= feature; else af.features &= ~feature; af.lock |= new_lock; } return 0; } static int audit_replace(struct pid *pid) { pid_t pvnr; struct sk_buff *skb; pvnr = pid_vnr(pid); skb = audit_make_reply(0, AUDIT_REPLACE, 0, 0, &pvnr, sizeof(pvnr)); if (!skb) return -ENOMEM; return auditd_send_unicast_skb(skb); } static int audit_receive_msg(struct sk_buff *skb, struct nlmsghdr *nlh, bool *ack) { u32 seq; void *data; int data_len; int err; struct audit_buffer *ab; u16 msg_type = nlh->nlmsg_type; struct audit_sig_info *sig_data; char *ctx = NULL; u32 len; err = audit_netlink_ok(skb, msg_type); if (err) return err; seq = nlh->nlmsg_seq; data = nlmsg_data(nlh); data_len = nlmsg_len(nlh); switch (msg_type) { case AUDIT_GET: { struct audit_status s; memset(&s, 0, sizeof(s)); s.enabled = audit_enabled; s.failure = audit_failure; /* NOTE: use pid_vnr() so the PID is relative to the current * namespace */ s.pid = auditd_pid_vnr(); s.rate_limit = audit_rate_limit; s.backlog_limit = audit_backlog_limit; s.lost = atomic_read(&audit_lost); s.backlog = skb_queue_len(&audit_queue); s.feature_bitmap = AUDIT_FEATURE_BITMAP_ALL; s.backlog_wait_time = audit_backlog_wait_time; s.backlog_wait_time_actual = atomic_read(&audit_backlog_wait_time_actual); audit_send_reply(skb, seq, AUDIT_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_SET: { struct audit_status s; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); if (s.mask & AUDIT_STATUS_ENABLED) { err = audit_set_enabled(s.enabled); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_FAILURE) { err = audit_set_failure(s.failure); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_PID) { /* NOTE: we are using the vnr PID functions below * because the s.pid value is relative to the * namespace of the caller; at present this * doesn't matter much since you can really only * run auditd from the initial pid namespace, but * something to keep in mind if this changes */ pid_t new_pid = s.pid; pid_t auditd_pid; struct pid *req_pid = task_tgid(current); /* Sanity check - PID values must match. Setting * pid to 0 is how auditd ends auditing. */ if (new_pid && (new_pid != pid_vnr(req_pid))) return -EINVAL; /* test the auditd connection */ audit_replace(req_pid); auditd_pid = auditd_pid_vnr(); if (auditd_pid) { /* replacing a healthy auditd is not allowed */ if (new_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EEXIST; } /* only current auditd can unregister itself */ if (pid_vnr(req_pid) != auditd_pid) { audit_log_config_change("audit_pid", new_pid, auditd_pid, 0); return -EACCES; } } if (new_pid) { /* register a new auditd connection */ err = auditd_set(req_pid, NETLINK_CB(skb).portid, sock_net(NETLINK_CB(skb).sk), skb, ack); if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, err ? 0 : 1); if (err) return err; /* try to process any backlog */ wake_up_interruptible(&kauditd_wait); } else { if (audit_enabled != AUDIT_OFF) audit_log_config_change("audit_pid", new_pid, auditd_pid, 1); /* unregister the auditd connection */ auditd_reset(NULL); } } if (s.mask & AUDIT_STATUS_RATE_LIMIT) { err = audit_set_rate_limit(s.rate_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_LIMIT) { err = audit_set_backlog_limit(s.backlog_limit); if (err < 0) return err; } if (s.mask & AUDIT_STATUS_BACKLOG_WAIT_TIME) { if (sizeof(s) > (size_t)nlh->nlmsg_len) return -EINVAL; if (s.backlog_wait_time > 10*AUDIT_BACKLOG_WAIT_TIME) return -EINVAL; err = audit_set_backlog_wait_time(s.backlog_wait_time); if (err < 0) return err; } if (s.mask == AUDIT_STATUS_LOST) { u32 lost = atomic_xchg(&audit_lost, 0); audit_log_config_change("lost", 0, lost, 1); return lost; } if (s.mask == AUDIT_STATUS_BACKLOG_WAIT_TIME_ACTUAL) { u32 actual = atomic_xchg(&audit_backlog_wait_time_actual, 0); audit_log_config_change("backlog_wait_time_actual", 0, actual, 1); return actual; } break; } case AUDIT_GET_FEATURE: err = audit_get_feature(skb); if (err) return err; break; case AUDIT_SET_FEATURE: if (data_len < sizeof(struct audit_features)) return -EINVAL; err = audit_set_feature(data); if (err) return err; break; case AUDIT_USER: case AUDIT_FIRST_USER_MSG ... AUDIT_LAST_USER_MSG: case AUDIT_FIRST_USER_MSG2 ... AUDIT_LAST_USER_MSG2: if (!audit_enabled && msg_type != AUDIT_USER_AVC) return 0; /* exit early if there isn't at least one character to print */ if (data_len < 2) return -EINVAL; err = audit_filter(msg_type, AUDIT_FILTER_USER); if (err == 1) { /* match or error */ char *str = data; err = 0; if (msg_type == AUDIT_USER_TTY) { err = tty_audit_push(); if (err) break; } audit_log_user_recv_msg(&ab, msg_type); if (msg_type != AUDIT_USER_TTY) { /* ensure NULL termination */ str[data_len - 1] = '\0'; audit_log_format(ab, " msg='%.*s'", AUDIT_MESSAGE_TEXT_MAX, str); } else { audit_log_format(ab, " data="); if (str[data_len - 1] == '\0') data_len--; audit_log_n_untrustedstring(ab, str, data_len); } audit_log_end(ab); } break; case AUDIT_ADD_RULE: case AUDIT_DEL_RULE: if (data_len < sizeof(struct audit_rule_data)) return -EINVAL; if (audit_enabled == AUDIT_LOCKED) { audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=%s audit_enabled=%d res=0", msg_type == AUDIT_ADD_RULE ? "add_rule" : "remove_rule", audit_enabled); audit_log_end(ab); return -EPERM; } err = audit_rule_change(msg_type, seq, data, data_len); break; case AUDIT_LIST_RULES: err = audit_list_rules_send(skb, seq); break; case AUDIT_TRIM: audit_trim_trees(); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=trim res=1"); audit_log_end(ab); break; case AUDIT_MAKE_EQUIV: { void *bufp = data; u32 sizes[2]; size_t msglen = data_len; char *old, *new; err = -EINVAL; if (msglen < 2 * sizeof(u32)) break; memcpy(sizes, bufp, 2 * sizeof(u32)); bufp += 2 * sizeof(u32); msglen -= 2 * sizeof(u32); old = audit_unpack_string(&bufp, &msglen, sizes[0]); if (IS_ERR(old)) { err = PTR_ERR(old); break; } new = audit_unpack_string(&bufp, &msglen, sizes[1]); if (IS_ERR(new)) { err = PTR_ERR(new); kfree(old); break; } /* OK, here comes... */ err = audit_tag_tree(old, new); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=make_equiv old="); audit_log_untrustedstring(ab, old); audit_log_format(ab, " new="); audit_log_untrustedstring(ab, new); audit_log_format(ab, " res=%d", !err); audit_log_end(ab); kfree(old); kfree(new); break; } case AUDIT_SIGNAL_INFO: len = 0; if (audit_sig_sid) { err = security_secid_to_secctx(audit_sig_sid, &ctx, &len); if (err) return err; } sig_data = kmalloc(struct_size(sig_data, ctx, len), GFP_KERNEL); if (!sig_data) { if (audit_sig_sid) security_release_secctx(ctx, len); return -ENOMEM; } sig_data->uid = from_kuid(&init_user_ns, audit_sig_uid); sig_data->pid = audit_sig_pid; if (audit_sig_sid) { memcpy(sig_data->ctx, ctx, len); security_release_secctx(ctx, len); } audit_send_reply(skb, seq, AUDIT_SIGNAL_INFO, 0, 0, sig_data, struct_size(sig_data, ctx, len)); kfree(sig_data); break; case AUDIT_TTY_GET: { struct audit_tty_status s; unsigned int t; t = READ_ONCE(current->signal->audit_tty); s.enabled = t & AUDIT_TTY_ENABLE; s.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_send_reply(skb, seq, AUDIT_TTY_GET, 0, 0, &s, sizeof(s)); break; } case AUDIT_TTY_SET: { struct audit_tty_status s, old; struct audit_buffer *ab; unsigned int t; memset(&s, 0, sizeof(s)); /* guard against past and future API changes */ memcpy(&s, data, min_t(size_t, sizeof(s), data_len)); /* check if new data is valid */ if ((s.enabled != 0 && s.enabled != 1) || (s.log_passwd != 0 && s.log_passwd != 1)) err = -EINVAL; if (err) t = READ_ONCE(current->signal->audit_tty); else { t = s.enabled | (-s.log_passwd & AUDIT_TTY_LOG_PASSWD); t = xchg(¤t->signal->audit_tty, t); } old.enabled = t & AUDIT_TTY_ENABLE; old.log_passwd = !!(t & AUDIT_TTY_LOG_PASSWD); audit_log_common_recv_msg(audit_context(), &ab, AUDIT_CONFIG_CHANGE); audit_log_format(ab, " op=tty_set old-enabled=%d new-enabled=%d" " old-log_passwd=%d new-log_passwd=%d res=%d", old.enabled, s.enabled, old.log_passwd, s.log_passwd, !err); audit_log_end(ab); break; } default: err = -EINVAL; break; } return err < 0 ? err : 0; } /** * audit_receive - receive messages from a netlink control socket * @skb: the message buffer * * Parse the provided skb and deal with any messages that may be present, * malformed skbs are discarded. */ static void audit_receive(struct sk_buff *skb) { struct nlmsghdr *nlh; bool ack; /* * len MUST be signed for nlmsg_next to be able to dec it below 0 * if the nlmsg_len was not aligned */ int len; int err; nlh = nlmsg_hdr(skb); len = skb->len; audit_ctl_lock(); while (nlmsg_ok(nlh, len)) { ack = nlh->nlmsg_flags & NLM_F_ACK; err = audit_receive_msg(skb, nlh, &ack); /* send an ack if the user asked for one and audit_receive_msg * didn't already do it, or if there was an error. */ if (ack || err) netlink_ack(skb, nlh, err, NULL); nlh = nlmsg_next(nlh, &len); } audit_ctl_unlock(); /* can't block with the ctrl lock, so penalize the sender now */ if (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { DECLARE_WAITQUEUE(wait, current); /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); schedule_timeout(audit_backlog_wait_time); remove_wait_queue(&audit_backlog_wait, &wait); } } /* Log information about who is connecting to the audit multicast socket */ static void audit_log_multicast(int group, const char *op, int err) { const struct cred *cred; struct tty_struct *tty; char comm[sizeof(current->comm)]; struct audit_buffer *ab; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_EVENT_LISTENER); if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, "pid=%u uid=%u auid=%u tty=%s ses=%u", task_pid_nr(current), from_kuid(&init_user_ns, cred->uid), from_kuid(&init_user_ns, audit_get_loginuid(current)), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_task_context(ab); /* subj= */ audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); /* exe= */ audit_log_format(ab, " nl-mcgrp=%d op=%s res=%d", group, op, !err); audit_log_end(ab); } /* Run custom bind function on netlink socket group connect or bind requests. */ static int audit_multicast_bind(struct net *net, int group) { int err = 0; if (!capable(CAP_AUDIT_READ)) err = -EPERM; audit_log_multicast(group, "connect", err); return err; } static void audit_multicast_unbind(struct net *net, int group) { audit_log_multicast(group, "disconnect", 0); } static int __net_init audit_net_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = audit_receive, .bind = audit_multicast_bind, .unbind = audit_multicast_unbind, .flags = NL_CFG_F_NONROOT_RECV, .groups = AUDIT_NLGRP_MAX, }; struct audit_net *aunet = net_generic(net, audit_net_id); aunet->sk = netlink_kernel_create(net, NETLINK_AUDIT, &cfg); if (aunet->sk == NULL) { audit_panic("cannot initialize netlink socket in namespace"); return -ENOMEM; } /* limit the timeout in case auditd is blocked/stopped */ aunet->sk->sk_sndtimeo = HZ / 10; return 0; } static void __net_exit audit_net_exit(struct net *net) { struct audit_net *aunet = net_generic(net, audit_net_id); /* NOTE: you would think that we would want to check the auditd * connection and potentially reset it here if it lives in this * namespace, but since the auditd connection tracking struct holds a * reference to this namespace (see auditd_set()) we are only ever * going to get here after that connection has been released */ netlink_kernel_release(aunet->sk); } static struct pernet_operations audit_net_ops __net_initdata = { .init = audit_net_init, .exit = audit_net_exit, .id = &audit_net_id, .size = sizeof(struct audit_net), }; /* Initialize audit support at boot time. */ static int __init audit_init(void) { int i; if (audit_initialized == AUDIT_DISABLED) return 0; audit_buffer_cache = KMEM_CACHE(audit_buffer, SLAB_PANIC); skb_queue_head_init(&audit_queue); skb_queue_head_init(&audit_retry_queue); skb_queue_head_init(&audit_hold_queue); for (i = 0; i < AUDIT_INODE_BUCKETS; i++) INIT_LIST_HEAD(&audit_inode_hash[i]); mutex_init(&audit_cmd_mutex.lock); audit_cmd_mutex.owner = NULL; pr_info("initializing netlink subsys (%s)\n", audit_default ? "enabled" : "disabled"); register_pernet_subsys(&audit_net_ops); audit_initialized = AUDIT_INITIALIZED; kauditd_task = kthread_run(kauditd_thread, NULL, "kauditd"); if (IS_ERR(kauditd_task)) { int err = PTR_ERR(kauditd_task); panic("audit: failed to start the kauditd thread (%d)\n", err); } audit_log(NULL, GFP_KERNEL, AUDIT_KERNEL, "state=initialized audit_enabled=%u res=1", audit_enabled); return 0; } postcore_initcall(audit_init); /* * Process kernel command-line parameter at boot time. * audit={0|off} or audit={1|on}. */ static int __init audit_enable(char *str) { if (!strcasecmp(str, "off") || !strcmp(str, "0")) audit_default = AUDIT_OFF; else if (!strcasecmp(str, "on") || !strcmp(str, "1")) audit_default = AUDIT_ON; else { pr_err("audit: invalid 'audit' parameter value (%s)\n", str); audit_default = AUDIT_ON; } if (audit_default == AUDIT_OFF) audit_initialized = AUDIT_DISABLED; if (audit_set_enabled(audit_default)) pr_err("audit: error setting audit state (%d)\n", audit_default); pr_info("%s\n", audit_default ? "enabled (after initialization)" : "disabled (until reboot)"); return 1; } __setup("audit=", audit_enable); /* Process kernel command-line parameter at boot time. * audit_backlog_limit=<n> */ static int __init audit_backlog_limit_set(char *str) { u32 audit_backlog_limit_arg; pr_info("audit_backlog_limit: "); if (kstrtouint(str, 0, &audit_backlog_limit_arg)) { pr_cont("using default of %u, unable to parse %s\n", audit_backlog_limit, str); return 1; } audit_backlog_limit = audit_backlog_limit_arg; pr_cont("%d\n", audit_backlog_limit); return 1; } __setup("audit_backlog_limit=", audit_backlog_limit_set); static void audit_buffer_free(struct audit_buffer *ab) { if (!ab) return; kfree_skb(ab->skb); kmem_cache_free(audit_buffer_cache, ab); } static struct audit_buffer *audit_buffer_alloc(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; ab = kmem_cache_alloc(audit_buffer_cache, gfp_mask); if (!ab) return NULL; ab->skb = nlmsg_new(AUDIT_BUFSIZ, gfp_mask); if (!ab->skb) goto err; if (!nlmsg_put(ab->skb, 0, 0, type, 0, 0)) goto err; ab->ctx = ctx; ab->gfp_mask = gfp_mask; return ab; err: audit_buffer_free(ab); return NULL; } /** * audit_serial - compute a serial number for the audit record * * Compute a serial number for the audit record. Audit records are * written to user-space as soon as they are generated, so a complete * audit record may be written in several pieces. The timestamp of the * record and this serial number are used by the user-space tools to * determine which pieces belong to the same audit record. The * (timestamp,serial) tuple is unique for each syscall and is live from * syscall entry to syscall exit. * * NOTE: Another possibility is to store the formatted records off the * audit context (for those records that have a context), and emit them * all at syscall exit. However, this could delay the reporting of * significant errors until syscall exit (or never, if the system * halts). */ unsigned int audit_serial(void) { static atomic_t serial = ATOMIC_INIT(0); return atomic_inc_return(&serial); } static inline void audit_get_stamp(struct audit_context *ctx, struct timespec64 *t, unsigned int *serial) { if (!ctx || !auditsc_get_stamp(ctx, t, serial)) { ktime_get_coarse_real_ts64(t); *serial = audit_serial(); } } /** * audit_log_start - obtain an audit buffer * @ctx: audit_context (may be NULL) * @gfp_mask: type of allocation * @type: audit message type * * Returns audit_buffer pointer on success or NULL on error. * * Obtain an audit buffer. This routine does locking to obtain the * audit buffer, but then no locking is required for calls to * audit_log_*format. If the task (ctx) is a task that is currently in a * syscall, then the syscall is marked as auditable and an audit record * will be written at syscall exit. If there is no associated task, then * task context (ctx) should be NULL. */ struct audit_buffer *audit_log_start(struct audit_context *ctx, gfp_t gfp_mask, int type) { struct audit_buffer *ab; struct timespec64 t; unsigned int serial; if (audit_initialized != AUDIT_INITIALIZED) return NULL; if (unlikely(!audit_filter(type, AUDIT_FILTER_EXCLUDE))) return NULL; /* NOTE: don't ever fail/sleep on these two conditions: * 1. auditd generated record - since we need auditd to drain the * queue; also, when we are checking for auditd, compare PIDs using * task_tgid_vnr() since auditd_pid is set in audit_receive_msg() * using a PID anchored in the caller's namespace * 2. generator holding the audit_cmd_mutex - we don't want to block * while holding the mutex, although we do penalize the sender * later in audit_receive() when it is safe to block */ if (!(auditd_test_task(current) || audit_ctl_owner_current())) { long stime = audit_backlog_wait_time; while (audit_backlog_limit && (skb_queue_len(&audit_queue) > audit_backlog_limit)) { /* wake kauditd to try and flush the queue */ wake_up_interruptible(&kauditd_wait); /* sleep if we are allowed and we haven't exhausted our * backlog wait limit */ if (gfpflags_allow_blocking(gfp_mask) && (stime > 0)) { long rtime = stime; DECLARE_WAITQUEUE(wait, current); add_wait_queue_exclusive(&audit_backlog_wait, &wait); set_current_state(TASK_UNINTERRUPTIBLE); stime = schedule_timeout(rtime); atomic_add(rtime - stime, &audit_backlog_wait_time_actual); remove_wait_queue(&audit_backlog_wait, &wait); } else { if (audit_rate_check() && printk_ratelimit()) pr_warn("audit_backlog=%d > audit_backlog_limit=%d\n", skb_queue_len(&audit_queue), audit_backlog_limit); audit_log_lost("backlog limit exceeded"); return NULL; } } } ab = audit_buffer_alloc(ctx, gfp_mask, type); if (!ab) { audit_log_lost("out of memory in audit_log_start"); return NULL; } audit_get_stamp(ab->ctx, &t, &serial); /* cancel dummy context to enable supporting records */ if (ctx) ctx->dummy = 0; audit_log_format(ab, "audit(%llu.%03lu:%u): ", (unsigned long long)t.tv_sec, t.tv_nsec/1000000, serial); return ab; } /** * audit_expand - expand skb in the audit buffer * @ab: audit_buffer * @extra: space to add at tail of the skb * * Returns 0 (no space) on failed expansion, or available space if * successful. */ static inline int audit_expand(struct audit_buffer *ab, int extra) { struct sk_buff *skb = ab->skb; int oldtail = skb_tailroom(skb); int ret = pskb_expand_head(skb, 0, extra, ab->gfp_mask); int newtail = skb_tailroom(skb); if (ret < 0) { audit_log_lost("out of memory in audit_expand"); return 0; } skb->truesize += newtail - oldtail; return newtail; } /* * Format an audit message into the audit buffer. If there isn't enough * room in the audit buffer, more room will be allocated and vsnprint * will be called a second time. Currently, we assume that a printk * can't format message larger than 1024 bytes, so we don't either. */ static void audit_log_vformat(struct audit_buffer *ab, const char *fmt, va_list args) { int len, avail; struct sk_buff *skb; va_list args2; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); if (avail == 0) { avail = audit_expand(ab, AUDIT_BUFSIZ); if (!avail) goto out; } va_copy(args2, args); len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args); if (len >= avail) { /* The printk buffer is 1024 bytes long, so if we get * here and AUDIT_BUFSIZ is at least 1024, then we can * log everything that printk could have logged. */ avail = audit_expand(ab, max_t(unsigned, AUDIT_BUFSIZ, 1+len-avail)); if (!avail) goto out_va_end; len = vsnprintf(skb_tail_pointer(skb), avail, fmt, args2); } if (len > 0) skb_put(skb, len); out_va_end: va_end(args2); out: return; } /** * audit_log_format - format a message into the audit buffer. * @ab: audit_buffer * @fmt: format string * @...: optional parameters matching @fmt string * * All the work is done in audit_log_vformat. */ void audit_log_format(struct audit_buffer *ab, const char *fmt, ...) { va_list args; if (!ab) return; va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); } /** * audit_log_n_hex - convert a buffer to hex and append it to the audit skb * @ab: the audit_buffer * @buf: buffer to convert to hex * @len: length of @buf to be converted * * No return value; failure to expand is silently ignored. * * This function will take the passed buf and convert it into a string of * ascii hex digits. The new string is placed onto the skb. */ void audit_log_n_hex(struct audit_buffer *ab, const unsigned char *buf, size_t len) { int i, avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = len<<1; if (new_len >= avail) { /* Round the buffer request up to the next multiple */ new_len = AUDIT_BUFSIZ*(((new_len-avail)/AUDIT_BUFSIZ) + 1); avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); for (i = 0; i < len; i++) ptr = hex_byte_pack_upper(ptr, buf[i]); *ptr = 0; skb_put(skb, len << 1); /* new string is twice the old string */ } /* * Format a string of no more than slen characters into the audit buffer, * enclosed in quote marks. */ void audit_log_n_string(struct audit_buffer *ab, const char *string, size_t slen) { int avail, new_len; unsigned char *ptr; struct sk_buff *skb; if (!ab) return; BUG_ON(!ab->skb); skb = ab->skb; avail = skb_tailroom(skb); new_len = slen + 3; /* enclosing quotes + null terminator */ if (new_len > avail) { avail = audit_expand(ab, new_len); if (!avail) return; } ptr = skb_tail_pointer(skb); *ptr++ = '"'; memcpy(ptr, string, slen); ptr += slen; *ptr++ = '"'; *ptr = 0; skb_put(skb, slen + 2); /* don't include null terminator */ } /** * audit_string_contains_control - does a string need to be logged in hex * @string: string to be checked * @len: max length of the string to check */ bool audit_string_contains_control(const char *string, size_t len) { const unsigned char *p; for (p = string; p < (const unsigned char *)string + len; p++) { if (*p == '"' || *p < 0x21 || *p > 0x7e) return true; } return false; } /** * audit_log_n_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @len: length of string (not including trailing null) * @string: string to be logged * * This code will escape a string that is passed to it if the string * contains a control character, unprintable character, double quote mark, * or a space. Unescaped strings will start and end with a double quote mark. * Strings that are escaped are printed in hex (2 digits per char). * * The caller specifies the number of characters in the string to log, which may * or may not be the entire string. */ void audit_log_n_untrustedstring(struct audit_buffer *ab, const char *string, size_t len) { if (audit_string_contains_control(string, len)) audit_log_n_hex(ab, string, len); else audit_log_n_string(ab, string, len); } /** * audit_log_untrustedstring - log a string that may contain random characters * @ab: audit_buffer * @string: string to be logged * * Same as audit_log_n_untrustedstring(), except that strlen is used to * determine string length. */ void audit_log_untrustedstring(struct audit_buffer *ab, const char *string) { audit_log_n_untrustedstring(ab, string, strlen(string)); } /* This is a helper-function to print the escaped d_path */ void audit_log_d_path(struct audit_buffer *ab, const char *prefix, const struct path *path) { char *p, *pathname; if (prefix) audit_log_format(ab, "%s", prefix); /* We will allow 11 spaces for ' (deleted)' to be appended */ pathname = kmalloc(PATH_MAX+11, ab->gfp_mask); if (!pathname) { audit_log_format(ab, "\"<no_memory>\""); return; } p = d_path(path, pathname, PATH_MAX+11); if (IS_ERR(p)) { /* Should never happen since we send PATH_MAX */ /* FIXME: can we save some information here? */ audit_log_format(ab, "\"<too_long>\""); } else audit_log_untrustedstring(ab, p); kfree(pathname); } void audit_log_session_info(struct audit_buffer *ab) { unsigned int sessionid = audit_get_sessionid(current); uid_t auid = from_kuid(&init_user_ns, audit_get_loginuid(current)); audit_log_format(ab, "auid=%u ses=%u", auid, sessionid); } void audit_log_key(struct audit_buffer *ab, char *key) { audit_log_format(ab, " key="); if (key) audit_log_untrustedstring(ab, key); else audit_log_format(ab, "(null)"); } int audit_log_task_context(struct audit_buffer *ab) { char *ctx = NULL; unsigned len; int error; u32 sid; security_current_getsecid_subj(&sid); if (!sid) return 0; error = security_secid_to_secctx(sid, &ctx, &len); if (error) { if (error != -EINVAL) goto error_path; return 0; } audit_log_format(ab, " subj=%s", ctx); security_release_secctx(ctx, len); return 0; error_path: audit_panic("error in audit_log_task_context"); return error; } EXPORT_SYMBOL(audit_log_task_context); void audit_log_d_path_exe(struct audit_buffer *ab, struct mm_struct *mm) { struct file *exe_file; if (!mm) goto out_null; exe_file = get_mm_exe_file(mm); if (!exe_file) goto out_null; audit_log_d_path(ab, " exe=", &exe_file->f_path); fput(exe_file); return; out_null: audit_log_format(ab, " exe=(null)"); } struct tty_struct *audit_get_tty(void) { struct tty_struct *tty = NULL; unsigned long flags; spin_lock_irqsave(¤t->sighand->siglock, flags); if (current->signal) tty = tty_kref_get(current->signal->tty); spin_unlock_irqrestore(¤t->sighand->siglock, flags); return tty; } void audit_put_tty(struct tty_struct *tty) { tty_kref_put(tty); } void audit_log_task_info(struct audit_buffer *ab) { const struct cred *cred; char comm[sizeof(current->comm)]; struct tty_struct *tty; if (!ab) return; cred = current_cred(); tty = audit_get_tty(); audit_log_format(ab, " ppid=%d pid=%d auid=%u uid=%u gid=%u" " euid=%u suid=%u fsuid=%u" " egid=%u sgid=%u fsgid=%u tty=%s ses=%u", task_ppid_nr(current), task_tgid_nr(current), from_kuid(&init_user_ns, audit_get_loginuid(current)), from_kuid(&init_user_ns, cred->uid), from_kgid(&init_user_ns, cred->gid), from_kuid(&init_user_ns, cred->euid), from_kuid(&init_user_ns, cred->suid), from_kuid(&init_user_ns, cred->fsuid), from_kgid(&init_user_ns, cred->egid), from_kgid(&init_user_ns, cred->sgid), from_kgid(&init_user_ns, cred->fsgid), tty ? tty_name(tty) : "(none)", audit_get_sessionid(current)); audit_put_tty(tty); audit_log_format(ab, " comm="); audit_log_untrustedstring(ab, get_task_comm(comm, current)); audit_log_d_path_exe(ab, current->mm); audit_log_task_context(ab); } EXPORT_SYMBOL(audit_log_task_info); /** * audit_log_path_denied - report a path restriction denial * @type: audit message type (AUDIT_ANOM_LINK, AUDIT_ANOM_CREAT, etc) * @operation: specific operation name */ void audit_log_path_denied(int type, const char *operation) { struct audit_buffer *ab; if (!audit_enabled || audit_dummy_context()) return; /* Generate log with subject, operation, outcome. */ ab = audit_log_start(audit_context(), GFP_KERNEL, type); if (!ab) return; audit_log_format(ab, "op=%s", operation); audit_log_task_info(ab); audit_log_format(ab, " res=0"); audit_log_end(ab); } /* global counter which is incremented every time something logs in */ static atomic_t session_id = ATOMIC_INIT(0); static int audit_set_loginuid_perm(kuid_t loginuid) { /* if we are unset, we don't need privs */ if (!audit_loginuid_set(current)) return 0; /* if AUDIT_FEATURE_LOGINUID_IMMUTABLE means never ever allow a change*/ if (is_audit_feature_set(AUDIT_FEATURE_LOGINUID_IMMUTABLE)) return -EPERM; /* it is set, you need permission */ if (!capable(CAP_AUDIT_CONTROL)) return -EPERM; /* reject if this is not an unset and we don't allow that */ if (is_audit_feature_set(AUDIT_FEATURE_ONLY_UNSET_LOGINUID) && uid_valid(loginuid)) return -EPERM; return 0; } static void audit_log_set_loginuid(kuid_t koldloginuid, kuid_t kloginuid, unsigned int oldsessionid, unsigned int sessionid, int rc) { struct audit_buffer *ab; uid_t uid, oldloginuid, loginuid; struct tty_struct *tty; if (!audit_enabled) return; ab = audit_log_start(audit_context(), GFP_KERNEL, AUDIT_LOGIN); if (!ab) return; uid = from_kuid(&init_user_ns, task_uid(current)); oldloginuid = from_kuid(&init_user_ns, koldloginuid); loginuid = from_kuid(&init_user_ns, kloginuid); tty = audit_get_tty(); audit_log_format(ab, "pid=%d uid=%u", task_tgid_nr(current), uid); audit_log_task_context(ab); audit_log_format(ab, " old-auid=%u auid=%u tty=%s old-ses=%u ses=%u res=%d", oldloginuid, loginuid, tty ? tty_name(tty) : "(none)", oldsessionid, sessionid, !rc); audit_put_tty(tty); audit_log_end(ab); } /** * audit_set_loginuid - set current task's loginuid * @loginuid: loginuid value * * Returns 0. * * Called (set) from fs/proc/base.c::proc_loginuid_write(). */ int audit_set_loginuid(kuid_t loginuid) { unsigned int oldsessionid, sessionid = AUDIT_SID_UNSET; kuid_t oldloginuid; int rc; oldloginuid = audit_get_loginuid(current); oldsessionid = audit_get_sessionid(current); rc = audit_set_loginuid_perm(loginuid); if (rc) goto out; /* are we setting or clearing? */ if (uid_valid(loginuid)) { sessionid = (unsigned int)atomic_inc_return(&session_id); if (unlikely(sessionid == AUDIT_SID_UNSET)) sessionid = (unsigned int)atomic_inc_return(&session_id); } current->sessionid = sessionid; current->loginuid = loginuid; out: audit_log_set_loginuid(oldloginuid, loginuid, oldsessionid, sessionid, rc); return rc; } /** * audit_signal_info - record signal info for shutting down audit subsystem * @sig: signal value * @t: task being signaled * * If the audit subsystem is being terminated, record the task (pid) * and uid that is doing that. */ int audit_signal_info(int sig, struct task_struct *t) { kuid_t uid = current_uid(), auid; if (auditd_test_task(t) && (sig == SIGTERM || sig == SIGHUP || sig == SIGUSR1 || sig == SIGUSR2)) { audit_sig_pid = task_tgid_nr(current); auid = audit_get_loginuid(current); if (uid_valid(auid)) audit_sig_uid = auid; else audit_sig_uid = uid; security_current_getsecid_subj(&audit_sig_sid); } return audit_signal_info_syscall(t); } /** * audit_log_end - end one audit record * @ab: the audit_buffer * * We can not do a netlink send inside an irq context because it blocks (last * arg, flags, is not set to MSG_DONTWAIT), so the audit buffer is placed on a * queue and a kthread is scheduled to remove them from the queue outside the * irq context. May be called in any context. */ void audit_log_end(struct audit_buffer *ab) { struct sk_buff *skb; struct nlmsghdr *nlh; if (!ab) return; if (audit_rate_check()) { skb = ab->skb; ab->skb = NULL; /* setup the netlink header, see the comments in * kauditd_send_multicast_skb() for length quirks */ nlh = nlmsg_hdr(skb); nlh->nlmsg_len = skb->len - NLMSG_HDRLEN; /* queue the netlink packet and poke the kauditd thread */ skb_queue_tail(&audit_queue, skb); wake_up_interruptible(&kauditd_wait); } else audit_log_lost("rate limit exceeded"); audit_buffer_free(ab); } /** * audit_log - Log an audit record * @ctx: audit context * @gfp_mask: type of allocation * @type: audit message type * @fmt: format string to use * @...: variable parameters matching the format string * * This is a convenience function that calls audit_log_start, * audit_log_vformat, and audit_log_end. It may be called * in any context. */ void audit_log(struct audit_context *ctx, gfp_t gfp_mask, int type, const char *fmt, ...) { struct audit_buffer *ab; va_list args; ab = audit_log_start(ctx, gfp_mask, type); if (ab) { va_start(args, fmt); audit_log_vformat(ab, fmt, args); va_end(args); audit_log_end(ab); } } EXPORT_SYMBOL(audit_log_start); EXPORT_SYMBOL(audit_log_end); EXPORT_SYMBOL(audit_log_format); EXPORT_SYMBOL(audit_log); |
| 155 165 181 347 81 218 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 | /* SPDX-License-Identifier: GPL-2.0 */ /* * This header provides generic wrappers for memory access instrumentation that * the compiler cannot emit for: KASAN, KCSAN, KMSAN. */ #ifndef _LINUX_INSTRUMENTED_H #define _LINUX_INSTRUMENTED_H #include <linux/compiler.h> #include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> #include <linux/kmsan-checks.h> #include <linux/types.h> /** * instrument_read - instrument regular read access * @v: address of access * @size: size of access * * Instrument a regular read access. The instrumentation should be inserted * before the actual read happens. */ static __always_inline void instrument_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_read(v, size); } /** * instrument_write - instrument regular write access * @v: address of access * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_write(v, size); } /** * instrument_read_write - instrument regular read-write access * @v: address of access * @size: size of access * * Instrument a regular write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_read_write(v, size); } /** * instrument_atomic_read - instrument atomic read access * @v: address of access * @size: size of access * * Instrument an atomic read access. The instrumentation should be inserted * before the actual read happens. */ static __always_inline void instrument_atomic_read(const volatile void *v, size_t size) { kasan_check_read(v, size); kcsan_check_atomic_read(v, size); } /** * instrument_atomic_write - instrument atomic write access * @v: address of access * @size: size of access * * Instrument an atomic write access. The instrumentation should be inserted * before the actual write happens. */ static __always_inline void instrument_atomic_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_write(v, size); } /** * instrument_atomic_read_write - instrument atomic read-write access * @v: address of access * @size: size of access * * Instrument an atomic read-write access. The instrumentation should be * inserted before the actual write happens. */ static __always_inline void instrument_atomic_read_write(const volatile void *v, size_t size) { kasan_check_write(v, size); kcsan_check_atomic_read_write(v, size); } /** * instrument_copy_to_user - instrument reads of copy_to_user * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument reads from kernel memory, that are due to copy_to_user (and * variants). The instrumentation must be inserted before the accesses. */ static __always_inline void instrument_copy_to_user(void __user *to, const void *from, unsigned long n) { kasan_check_read(from, n); kcsan_check_read(from, n); kmsan_copy_to_user(to, from, n, 0); } /** * instrument_copy_from_user_before - add instrumentation before copy_from_user * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted before the accesses. */ static __always_inline void instrument_copy_from_user_before(const void *to, const void __user *from, unsigned long n) { kasan_check_write(to, n); kcsan_check_write(to, n); } /** * instrument_copy_from_user_after - add instrumentation after copy_from_user * @to: destination address * @from: source address * @n: number of bytes to copy * @left: number of bytes not copied (as returned by copy_from_user) * * Instrument writes to kernel memory, that are due to copy_from_user (and * variants). The instrumentation should be inserted after the accesses. */ static __always_inline void instrument_copy_from_user_after(const void *to, const void __user *from, unsigned long n, unsigned long left) { kmsan_unpoison_memory(to, n - left); } /** * instrument_memcpy_before - add instrumentation before non-instrumented memcpy * @to: destination address * @from: source address * @n: number of bytes to copy * * Instrument memory accesses that happen in custom memcpy implementations. The * instrumentation should be inserted before the memcpy call. */ static __always_inline void instrument_memcpy_before(void *to, const void *from, unsigned long n) { kasan_check_write(to, n); kasan_check_read(from, n); kcsan_check_write(to, n); kcsan_check_read(from, n); } /** * instrument_memcpy_after - add instrumentation after non-instrumented memcpy * @to: destination address * @from: source address * @n: number of bytes to copy * @left: number of bytes not copied (if known) * * Instrument memory accesses that happen in custom memcpy implementations. The * instrumentation should be inserted after the memcpy call. */ static __always_inline void instrument_memcpy_after(void *to, const void *from, unsigned long n, unsigned long left) { kmsan_memmove(to, from, n - left); } /** * instrument_get_user() - add instrumentation to get_user()-like macros * @to: destination variable, may not be address-taken * * get_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. */ #define instrument_get_user(to) \ ({ \ u64 __tmp = (u64)(to); \ kmsan_unpoison_memory(&__tmp, sizeof(__tmp)); \ to = __tmp; \ }) /** * instrument_put_user() - add instrumentation to put_user()-like macros * @from: source address * @ptr: userspace pointer to copy to * @size: number of bytes to copy * * put_user() and friends are fragile, so it may depend on the implementation * whether the instrumentation happens before or after the data is copied from * the userspace. */ #define instrument_put_user(from, ptr, size) \ ({ \ kmsan_copy_to_user(ptr, &from, sizeof(from), 0); \ }) #endif /* _LINUX_INSTRUMENTED_H */ |
| 43 152 152 152 20 43 43 48 45 48 33 43 43 43 5 1 43 43 43 43 43 43 43 43 43 43 42 43 43 43 43 43 43 43 43 42 42 43 43 43 43 43 43 33 43 43 43 43 43 42 43 43 43 43 43 59 59 59 2 2 2 2 2 18 56 57 56 57 57 41 41 18 18 56 57 57 57 57 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 19 20 20 20 5 5 5 5 5 20 20 20 20 20 20 20 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 2484 2485 2486 2487 2488 2489 2490 2491 2492 2493 2494 2495 2496 2497 2498 2499 2500 2501 2502 2503 2504 2505 2506 2507 2508 2509 2510 2511 2512 2513 2514 2515 2516 2517 2518 2519 2520 2521 2522 2523 2524 2525 2526 2527 2528 2529 2530 2531 2532 2533 2534 2535 2536 2537 2538 2539 2540 2541 2542 2543 2544 2545 2546 2547 2548 2549 2550 2551 2552 2553 2554 2555 2556 2557 2558 2559 2560 2561 2562 2563 2564 2565 2566 2567 2568 2569 2570 2571 2572 2573 2574 2575 2576 2577 2578 2579 2580 2581 2582 2583 2584 2585 2586 2587 2588 2589 2590 2591 2592 2593 2594 2595 2596 2597 2598 2599 2600 2601 2602 2603 2604 2605 2606 2607 2608 2609 2610 2611 2612 2613 2614 2615 2616 2617 2618 2619 2620 2621 2622 2623 2624 2625 2626 2627 2628 2629 2630 2631 2632 2633 2634 2635 2636 2637 2638 2639 2640 2641 2642 2643 2644 2645 2646 2647 2648 2649 2650 2651 2652 2653 2654 2655 2656 2657 2658 2659 2660 2661 2662 2663 2664 2665 2666 2667 2668 2669 2670 2671 2672 2673 2674 2675 2676 2677 2678 2679 2680 2681 2682 2683 2684 2685 2686 2687 2688 2689 2690 2691 2692 2693 2694 2695 2696 2697 2698 2699 2700 2701 2702 2703 2704 2705 2706 2707 2708 2709 2710 2711 2712 2713 2714 2715 2716 2717 2718 2719 2720 2721 2722 2723 2724 2725 2726 2727 2728 2729 2730 2731 2732 2733 2734 2735 2736 2737 2738 2739 2740 2741 2742 2743 2744 2745 2746 2747 2748 2749 2750 2751 2752 2753 2754 2755 2756 2757 2758 2759 2760 2761 2762 2763 2764 2765 2766 2767 2768 2769 2770 2771 2772 2773 2774 2775 2776 2777 2778 2779 2780 2781 2782 2783 2784 2785 2786 2787 2788 2789 2790 2791 2792 2793 2794 2795 2796 2797 2798 2799 2800 2801 2802 2803 2804 2805 2806 2807 2808 2809 2810 2811 2812 2813 2814 2815 2816 2817 2818 2819 2820 2821 2822 2823 2824 2825 2826 2827 2828 2829 2830 2831 2832 2833 2834 2835 2836 2837 2838 2839 2840 2841 2842 2843 2844 2845 2846 2847 2848 2849 2850 2851 2852 2853 2854 2855 2856 2857 2858 2859 2860 2861 2862 2863 2864 2865 2866 2867 2868 2869 2870 2871 2872 2873 2874 2875 2876 2877 2878 2879 2880 2881 2882 2883 2884 2885 2886 2887 2888 2889 2890 2891 2892 2893 2894 2895 2896 2897 2898 2899 2900 2901 2902 2903 2904 2905 2906 2907 2908 2909 2910 2911 2912 2913 2914 2915 2916 2917 2918 2919 2920 2921 2922 2923 2924 2925 2926 2927 2928 2929 2930 2931 2932 2933 2934 2935 2936 2937 2938 2939 2940 2941 2942 2943 2944 2945 2946 2947 2948 2949 2950 2951 2952 2953 2954 2955 2956 2957 2958 2959 2960 2961 2962 2963 2964 2965 2966 2967 2968 2969 2970 2971 2972 2973 2974 2975 2976 2977 2978 2979 2980 2981 2982 2983 2984 2985 2986 2987 2988 2989 2990 2991 2992 2993 2994 2995 2996 2997 2998 2999 3000 3001 3002 3003 3004 3005 3006 3007 3008 3009 3010 3011 3012 3013 3014 3015 3016 3017 3018 3019 3020 3021 3022 3023 3024 3025 3026 3027 3028 3029 3030 3031 3032 3033 3034 3035 3036 3037 3038 3039 3040 3041 3042 3043 3044 3045 3046 3047 3048 3049 3050 3051 3052 3053 3054 3055 3056 3057 3058 3059 3060 3061 3062 3063 3064 3065 3066 3067 3068 3069 3070 3071 3072 3073 3074 3075 3076 3077 3078 3079 3080 3081 3082 3083 3084 3085 3086 3087 3088 3089 3090 3091 3092 3093 3094 3095 3096 3097 3098 3099 3100 3101 3102 3103 3104 3105 3106 3107 3108 3109 3110 3111 3112 3113 3114 3115 3116 3117 3118 3119 3120 3121 3122 3123 3124 3125 3126 3127 3128 3129 3130 3131 3132 3133 3134 3135 3136 3137 3138 3139 3140 3141 3142 3143 3144 3145 3146 3147 3148 3149 3150 3151 3152 3153 3154 3155 3156 3157 3158 3159 3160 3161 3162 3163 3164 3165 3166 3167 3168 3169 3170 3171 3172 3173 3174 3175 3176 3177 3178 3179 3180 3181 3182 3183 3184 3185 3186 3187 3188 3189 3190 3191 3192 3193 3194 3195 3196 3197 3198 3199 3200 3201 3202 3203 3204 3205 3206 3207 3208 3209 3210 3211 3212 3213 3214 3215 3216 3217 3218 3219 3220 3221 3222 3223 3224 3225 3226 3227 3228 3229 3230 3231 3232 3233 3234 3235 3236 3237 3238 3239 3240 3241 3242 3243 3244 3245 3246 3247 3248 3249 3250 3251 3252 3253 3254 3255 3256 3257 3258 3259 3260 3261 3262 3263 3264 3265 3266 3267 3268 3269 3270 3271 3272 3273 3274 3275 3276 3277 3278 3279 3280 3281 3282 3283 3284 3285 3286 3287 3288 3289 3290 3291 3292 3293 3294 3295 3296 3297 3298 3299 3300 3301 3302 3303 3304 3305 3306 3307 3308 3309 3310 3311 3312 3313 3314 3315 3316 3317 3318 3319 3320 3321 3322 3323 3324 3325 3326 3327 3328 3329 3330 3331 3332 3333 3334 3335 3336 3337 3338 3339 3340 3341 3342 3343 3344 3345 3346 3347 3348 3349 3350 3351 3352 3353 3354 3355 3356 3357 3358 3359 3360 3361 3362 3363 3364 3365 3366 3367 3368 3369 3370 3371 3372 3373 3374 3375 3376 3377 3378 3379 3380 3381 3382 3383 3384 3385 3386 3387 3388 3389 3390 3391 3392 3393 3394 3395 3396 3397 3398 3399 3400 3401 3402 3403 3404 3405 3406 3407 3408 3409 3410 3411 3412 3413 3414 3415 3416 3417 3418 3419 3420 3421 3422 3423 3424 3425 3426 3427 3428 3429 3430 3431 3432 3433 3434 3435 3436 3437 3438 3439 3440 3441 3442 3443 3444 3445 3446 3447 3448 3449 3450 3451 3452 3453 3454 3455 3456 3457 3458 3459 3460 3461 3462 3463 3464 3465 3466 3467 3468 3469 3470 3471 3472 3473 3474 3475 3476 3477 3478 3479 3480 3481 3482 3483 3484 3485 3486 3487 3488 3489 3490 3491 3492 3493 3494 3495 3496 3497 3498 3499 3500 3501 3502 3503 3504 3505 3506 3507 3508 3509 3510 3511 3512 3513 3514 3515 3516 3517 3518 3519 3520 3521 3522 3523 3524 3525 3526 3527 3528 3529 3530 3531 3532 3533 3534 3535 3536 3537 3538 3539 3540 3541 3542 3543 3544 3545 3546 3547 3548 3549 3550 3551 3552 3553 3554 3555 3556 3557 3558 3559 3560 3561 3562 3563 3564 3565 3566 3567 3568 3569 3570 3571 3572 3573 3574 3575 3576 3577 3578 3579 3580 3581 3582 3583 3584 3585 3586 3587 3588 3589 3590 3591 3592 3593 3594 3595 3596 3597 3598 3599 3600 3601 3602 3603 3604 3605 3606 3607 3608 3609 3610 3611 3612 3613 3614 3615 3616 3617 3618 3619 3620 3621 3622 3623 3624 3625 3626 3627 3628 3629 3630 3631 3632 3633 3634 3635 3636 3637 3638 3639 3640 3641 3642 3643 3644 3645 3646 3647 3648 3649 3650 3651 3652 3653 3654 3655 3656 3657 3658 3659 3660 3661 3662 3663 3664 3665 3666 3667 3668 3669 3670 3671 3672 3673 3674 3675 3676 3677 3678 3679 3680 3681 3682 3683 3684 3685 3686 3687 3688 3689 3690 3691 3692 3693 3694 3695 3696 3697 3698 3699 3700 3701 3702 3703 3704 3705 3706 3707 3708 3709 3710 3711 3712 3713 3714 3715 3716 3717 3718 3719 3720 3721 3722 3723 3724 3725 3726 3727 3728 3729 3730 3731 3732 3733 3734 3735 3736 3737 3738 3739 3740 3741 3742 3743 3744 3745 3746 3747 3748 3749 3750 3751 3752 3753 3754 3755 3756 3757 3758 3759 3760 3761 3762 3763 3764 3765 3766 3767 3768 3769 3770 3771 3772 3773 3774 3775 3776 3777 3778 3779 3780 3781 3782 3783 3784 3785 3786 3787 3788 3789 3790 3791 3792 3793 3794 3795 3796 3797 3798 3799 3800 3801 3802 3803 3804 3805 3806 3807 3808 3809 3810 3811 3812 3813 3814 3815 3816 3817 3818 3819 3820 3821 3822 3823 3824 3825 3826 3827 3828 3829 3830 3831 3832 3833 3834 3835 3836 3837 3838 3839 3840 3841 3842 3843 3844 3845 3846 3847 3848 3849 3850 3851 3852 3853 3854 3855 3856 3857 3858 3859 3860 3861 3862 3863 3864 3865 3866 3867 3868 3869 3870 3871 3872 3873 3874 3875 3876 3877 3878 3879 3880 3881 3882 3883 3884 3885 3886 3887 3888 3889 3890 3891 3892 3893 3894 3895 3896 3897 3898 3899 3900 3901 3902 3903 3904 3905 3906 3907 3908 3909 3910 3911 3912 3913 3914 3915 3916 3917 3918 3919 3920 3921 3922 3923 3924 3925 3926 3927 3928 3929 3930 3931 3932 3933 3934 3935 3936 3937 3938 3939 3940 3941 3942 3943 3944 3945 3946 3947 3948 3949 3950 3951 3952 3953 3954 3955 3956 3957 3958 3959 3960 3961 3962 3963 3964 3965 3966 3967 3968 3969 3970 3971 3972 3973 3974 3975 3976 3977 3978 3979 3980 3981 3982 3983 3984 3985 3986 3987 3988 3989 3990 3991 3992 3993 3994 3995 3996 3997 3998 3999 4000 4001 4002 4003 4004 4005 4006 4007 4008 4009 4010 4011 4012 4013 4014 4015 4016 4017 4018 4019 4020 4021 4022 4023 4024 4025 4026 4027 4028 4029 4030 4031 4032 4033 4034 4035 4036 4037 4038 4039 4040 4041 4042 4043 4044 4045 4046 4047 4048 4049 4050 4051 4052 4053 4054 4055 4056 4057 4058 4059 4060 4061 4062 4063 4064 4065 4066 4067 4068 4069 4070 4071 4072 4073 4074 4075 4076 4077 4078 4079 4080 4081 4082 4083 4084 4085 4086 4087 4088 4089 4090 4091 4092 4093 4094 4095 4096 4097 4098 4099 4100 4101 4102 4103 4104 4105 4106 4107 4108 4109 4110 4111 4112 4113 4114 4115 4116 4117 4118 4119 4120 4121 4122 4123 4124 4125 4126 4127 4128 4129 4130 4131 4132 4133 4134 4135 4136 4137 4138 4139 4140 4141 4142 4143 4144 4145 4146 4147 4148 4149 4150 4151 4152 4153 4154 4155 4156 4157 4158 4159 4160 4161 4162 4163 4164 4165 4166 4167 4168 4169 4170 4171 4172 4173 4174 4175 4176 4177 4178 4179 4180 4181 4182 4183 4184 4185 4186 4187 4188 4189 4190 4191 4192 4193 4194 4195 4196 4197 4198 4199 4200 4201 4202 4203 4204 4205 4206 4207 4208 4209 4210 4211 4212 4213 4214 4215 4216 4217 4218 4219 4220 4221 4222 4223 4224 4225 4226 4227 4228 4229 4230 4231 4232 4233 4234 4235 4236 4237 4238 4239 4240 4241 4242 4243 4244 4245 4246 4247 4248 4249 4250 4251 4252 4253 4254 4255 4256 4257 4258 4259 4260 4261 4262 4263 4264 4265 4266 4267 4268 4269 4270 4271 4272 4273 4274 4275 4276 4277 4278 4279 4280 4281 4282 4283 4284 4285 4286 4287 4288 4289 4290 4291 4292 4293 4294 4295 4296 4297 4298 4299 4300 4301 4302 4303 4304 4305 4306 4307 4308 4309 4310 4311 4312 4313 4314 4315 4316 4317 4318 4319 4320 4321 4322 4323 4324 4325 4326 4327 4328 4329 4330 4331 4332 4333 4334 4335 4336 4337 4338 4339 4340 4341 4342 4343 4344 4345 4346 4347 4348 4349 4350 4351 4352 4353 4354 4355 4356 4357 4358 4359 4360 4361 4362 4363 4364 4365 4366 4367 4368 4369 4370 4371 4372 4373 4374 4375 4376 4377 4378 4379 4380 4381 4382 4383 4384 4385 4386 4387 4388 4389 4390 4391 4392 4393 4394 4395 4396 4397 4398 4399 4400 4401 4402 4403 4404 4405 4406 4407 4408 4409 4410 4411 4412 4413 4414 4415 4416 4417 4418 4419 4420 4421 4422 4423 4424 4425 4426 4427 4428 4429 4430 4431 4432 4433 4434 4435 4436 4437 4438 4439 4440 4441 4442 4443 4444 4445 4446 4447 4448 4449 4450 4451 4452 4453 4454 4455 4456 4457 4458 4459 4460 4461 4462 4463 4464 4465 4466 4467 4468 4469 4470 4471 4472 4473 4474 4475 4476 4477 4478 4479 4480 4481 4482 4483 4484 4485 4486 4487 4488 4489 4490 4491 4492 4493 4494 4495 4496 4497 4498 4499 4500 4501 4502 4503 4504 4505 4506 4507 4508 4509 4510 4511 4512 4513 4514 4515 4516 4517 4518 4519 4520 4521 4522 4523 4524 4525 4526 4527 4528 4529 4530 4531 4532 4533 4534 4535 4536 4537 4538 4539 4540 4541 4542 4543 4544 4545 4546 4547 4548 4549 4550 4551 4552 4553 4554 4555 4556 4557 4558 4559 4560 4561 4562 4563 4564 4565 4566 4567 4568 4569 4570 4571 4572 4573 4574 4575 4576 4577 4578 4579 4580 4581 4582 4583 4584 4585 4586 4587 4588 4589 4590 4591 4592 4593 4594 4595 4596 4597 4598 4599 4600 4601 4602 4603 4604 4605 4606 4607 4608 4609 4610 4611 4612 4613 4614 4615 4616 4617 4618 4619 4620 4621 4622 4623 4624 4625 4626 4627 4628 4629 4630 4631 4632 4633 4634 4635 4636 4637 4638 4639 4640 4641 4642 4643 4644 4645 4646 4647 4648 4649 4650 4651 4652 4653 4654 4655 4656 4657 4658 4659 4660 4661 4662 4663 4664 4665 4666 4667 4668 4669 4670 4671 4672 4673 4674 4675 4676 4677 4678 4679 4680 4681 4682 4683 4684 4685 4686 4687 4688 4689 4690 4691 4692 4693 4694 4695 4696 4697 4698 4699 4700 4701 4702 4703 4704 4705 4706 4707 4708 4709 4710 4711 4712 4713 4714 4715 4716 4717 4718 4719 4720 4721 4722 4723 4724 4725 4726 4727 4728 4729 4730 4731 4732 4733 4734 4735 4736 4737 4738 4739 4740 4741 4742 4743 4744 4745 4746 4747 4748 4749 4750 4751 4752 4753 4754 4755 4756 4757 4758 4759 4760 4761 4762 4763 4764 4765 4766 4767 4768 4769 4770 4771 4772 4773 4774 4775 4776 4777 4778 4779 4780 4781 4782 4783 4784 4785 4786 4787 4788 4789 4790 4791 4792 4793 4794 4795 4796 4797 4798 4799 4800 4801 4802 4803 4804 4805 4806 4807 4808 4809 4810 4811 4812 4813 4814 4815 4816 4817 4818 4819 4820 4821 4822 4823 4824 4825 4826 4827 4828 4829 4830 4831 4832 4833 4834 4835 4836 4837 4838 4839 4840 4841 4842 4843 4844 4845 4846 4847 4848 4849 4850 4851 4852 4853 4854 4855 4856 4857 4858 4859 4860 4861 4862 4863 4864 4865 4866 4867 4868 4869 4870 4871 4872 4873 4874 4875 4876 4877 4878 4879 4880 4881 4882 4883 4884 4885 4886 4887 4888 4889 4890 4891 4892 4893 4894 4895 4896 4897 4898 4899 4900 4901 4902 4903 4904 4905 4906 4907 4908 4909 4910 4911 4912 4913 4914 4915 4916 4917 4918 4919 4920 4921 4922 4923 4924 4925 4926 4927 4928 4929 4930 4931 4932 4933 4934 4935 4936 4937 4938 4939 4940 4941 4942 4943 4944 4945 4946 4947 4948 4949 4950 4951 4952 4953 4954 4955 4956 4957 4958 4959 4960 4961 4962 4963 4964 4965 4966 4967 4968 4969 4970 4971 4972 4973 4974 4975 4976 4977 4978 4979 4980 4981 4982 4983 4984 4985 4986 4987 4988 4989 4990 4991 4992 4993 4994 4995 4996 4997 4998 4999 5000 5001 5002 5003 5004 5005 5006 5007 5008 5009 5010 5011 5012 5013 5014 5015 5016 5017 5018 5019 5020 5021 5022 5023 5024 5025 5026 5027 5028 5029 5030 5031 5032 5033 5034 5035 5036 5037 5038 5039 5040 5041 5042 5043 5044 5045 5046 5047 5048 5049 5050 5051 5052 5053 5054 5055 5056 5057 5058 5059 5060 5061 5062 5063 5064 5065 5066 5067 5068 5069 5070 5071 5072 5073 5074 5075 5076 5077 5078 5079 5080 5081 5082 5083 5084 5085 5086 5087 5088 5089 5090 5091 5092 5093 5094 5095 5096 5097 5098 5099 5100 5101 5102 5103 5104 5105 5106 5107 5108 5109 5110 5111 5112 5113 5114 5115 5116 5117 5118 5119 5120 5121 5122 5123 5124 5125 5126 5127 5128 5129 5130 5131 5132 5133 5134 5135 5136 5137 5138 5139 5140 5141 5142 5143 5144 5145 5146 5147 5148 5149 5150 5151 5152 5153 5154 5155 5156 5157 5158 5159 5160 5161 5162 5163 5164 5165 5166 5167 5168 5169 5170 5171 5172 5173 5174 5175 5176 5177 5178 5179 5180 5181 5182 5183 5184 5185 5186 5187 5188 5189 5190 5191 5192 5193 5194 5195 5196 5197 5198 5199 5200 5201 5202 5203 5204 5205 5206 5207 5208 5209 5210 5211 5212 5213 5214 5215 5216 5217 5218 5219 5220 5221 5222 5223 5224 5225 5226 5227 5228 5229 5230 5231 5232 5233 5234 5235 5236 5237 5238 5239 5240 5241 5242 5243 5244 5245 5246 5247 5248 5249 5250 5251 5252 5253 5254 5255 5256 5257 5258 5259 5260 5261 5262 5263 5264 5265 5266 5267 5268 5269 5270 5271 5272 5273 5274 5275 5276 5277 5278 5279 5280 5281 5282 5283 5284 5285 5286 5287 5288 5289 5290 5291 5292 5293 5294 5295 5296 5297 5298 5299 5300 5301 5302 5303 5304 5305 5306 5307 5308 5309 5310 5311 5312 5313 5314 5315 5316 5317 5318 5319 5320 5321 5322 5323 5324 5325 5326 5327 5328 5329 5330 5331 5332 5333 5334 5335 5336 5337 5338 5339 5340 5341 5342 5343 5344 5345 5346 5347 5348 5349 5350 5351 5352 5353 5354 5355 5356 5357 5358 5359 5360 5361 5362 5363 5364 5365 5366 5367 5368 5369 5370 5371 5372 5373 5374 5375 5376 5377 5378 5379 5380 5381 5382 5383 5384 5385 5386 5387 5388 5389 5390 5391 5392 5393 5394 5395 5396 5397 5398 5399 5400 5401 5402 5403 5404 5405 5406 5407 5408 5409 5410 5411 5412 5413 5414 5415 5416 5417 5418 5419 5420 5421 5422 5423 5424 5425 5426 5427 5428 5429 5430 5431 5432 5433 5434 5435 5436 5437 5438 5439 5440 5441 5442 5443 5444 5445 5446 5447 5448 5449 5450 5451 5452 5453 5454 5455 5456 5457 5458 5459 5460 5461 5462 5463 5464 5465 5466 5467 5468 5469 5470 5471 5472 5473 5474 5475 5476 5477 5478 5479 5480 5481 5482 5483 5484 5485 5486 5487 5488 5489 5490 5491 5492 5493 5494 5495 5496 5497 5498 5499 5500 5501 5502 5503 5504 5505 5506 5507 5508 5509 5510 5511 5512 5513 5514 5515 5516 5517 5518 5519 5520 5521 5522 5523 5524 5525 5526 5527 5528 5529 5530 5531 5532 5533 5534 5535 5536 5537 5538 5539 5540 5541 5542 5543 5544 5545 5546 5547 5548 5549 5550 5551 5552 5553 5554 5555 5556 5557 5558 5559 5560 5561 5562 5563 5564 5565 5566 5567 5568 5569 5570 5571 5572 5573 5574 5575 5576 5577 5578 5579 5580 5581 5582 5583 5584 5585 5586 5587 5588 5589 5590 5591 5592 5593 5594 5595 5596 5597 5598 5599 5600 5601 5602 5603 5604 5605 5606 5607 5608 5609 5610 5611 5612 5613 5614 5615 5616 5617 5618 5619 5620 5621 5622 5623 5624 5625 5626 5627 5628 5629 5630 5631 5632 5633 5634 5635 5636 5637 5638 5639 5640 5641 5642 5643 5644 5645 5646 5647 5648 5649 5650 5651 5652 5653 5654 5655 5656 5657 5658 5659 5660 5661 5662 5663 5664 5665 5666 5667 5668 5669 5670 5671 5672 5673 5674 5675 5676 5677 5678 5679 5680 5681 5682 5683 5684 5685 5686 5687 5688 5689 5690 5691 5692 5693 5694 5695 5696 5697 5698 5699 5700 5701 5702 5703 5704 5705 5706 5707 5708 5709 5710 5711 5712 5713 5714 5715 5716 5717 5718 5719 5720 5721 5722 5723 5724 5725 5726 5727 5728 5729 5730 5731 5732 5733 5734 5735 5736 5737 5738 5739 5740 5741 5742 5743 5744 5745 5746 5747 5748 5749 5750 5751 5752 5753 5754 5755 5756 5757 5758 5759 5760 5761 5762 5763 5764 5765 5766 5767 5768 5769 5770 5771 5772 5773 5774 5775 5776 5777 5778 5779 5780 5781 5782 5783 5784 5785 5786 5787 5788 5789 5790 5791 5792 5793 5794 5795 5796 5797 5798 5799 5800 5801 5802 5803 5804 5805 5806 5807 5808 5809 5810 5811 5812 5813 5814 5815 5816 5817 5818 5819 5820 5821 5822 5823 5824 5825 5826 5827 5828 5829 5830 5831 5832 5833 5834 5835 5836 5837 5838 5839 5840 5841 5842 5843 5844 5845 5846 5847 5848 5849 5850 5851 5852 5853 5854 5855 5856 5857 5858 5859 5860 5861 5862 5863 5864 5865 5866 5867 5868 5869 5870 5871 5872 5873 5874 5875 5876 5877 5878 5879 5880 5881 5882 5883 5884 5885 5886 5887 5888 5889 5890 5891 5892 5893 5894 5895 5896 5897 5898 5899 5900 5901 5902 5903 5904 5905 5906 5907 5908 5909 5910 5911 5912 5913 5914 5915 5916 5917 5918 5919 5920 5921 5922 5923 5924 5925 5926 5927 5928 5929 5930 5931 5932 5933 5934 5935 5936 5937 5938 5939 5940 5941 5942 5943 5944 5945 5946 5947 5948 5949 5950 5951 5952 5953 5954 5955 5956 5957 5958 5959 5960 5961 5962 5963 5964 5965 5966 5967 5968 5969 5970 5971 5972 5973 5974 5975 5976 5977 5978 5979 5980 5981 5982 5983 5984 5985 5986 5987 5988 5989 5990 5991 5992 5993 5994 5995 5996 5997 5998 5999 6000 6001 6002 6003 6004 6005 6006 6007 6008 6009 6010 6011 6012 6013 6014 6015 6016 6017 6018 6019 6020 6021 6022 6023 6024 6025 6026 6027 6028 6029 6030 6031 6032 6033 6034 6035 6036 6037 6038 6039 6040 6041 6042 6043 6044 6045 6046 6047 6048 6049 6050 6051 6052 6053 6054 6055 6056 6057 6058 6059 6060 6061 6062 6063 6064 6065 6066 6067 6068 6069 6070 6071 6072 6073 6074 6075 6076 6077 6078 6079 6080 6081 6082 6083 6084 6085 6086 6087 6088 6089 6090 6091 6092 6093 6094 6095 6096 6097 6098 6099 6100 6101 6102 6103 6104 6105 6106 6107 6108 6109 6110 6111 6112 6113 6114 6115 6116 6117 6118 6119 6120 6121 6122 6123 6124 6125 6126 6127 6128 6129 6130 6131 6132 6133 6134 6135 6136 6137 6138 6139 6140 6141 6142 6143 6144 6145 6146 6147 6148 6149 6150 6151 6152 6153 6154 6155 6156 6157 6158 6159 6160 6161 6162 6163 6164 6165 6166 6167 6168 6169 6170 6171 6172 6173 6174 6175 6176 6177 6178 6179 6180 6181 6182 6183 6184 6185 6186 6187 6188 6189 6190 6191 6192 6193 6194 6195 6196 6197 6198 6199 6200 6201 6202 6203 6204 6205 6206 6207 6208 6209 6210 6211 6212 6213 6214 6215 6216 6217 6218 6219 6220 6221 6222 6223 6224 6225 6226 6227 6228 6229 6230 6231 6232 6233 6234 6235 6236 6237 6238 6239 6240 6241 6242 6243 6244 6245 6246 6247 6248 6249 6250 6251 6252 6253 6254 6255 6256 6257 6258 6259 6260 6261 6262 6263 6264 6265 6266 6267 6268 6269 6270 6271 6272 6273 6274 6275 6276 6277 6278 6279 6280 6281 6282 6283 6284 6285 6286 6287 6288 6289 6290 6291 6292 6293 6294 6295 6296 6297 6298 6299 6300 6301 6302 6303 6304 6305 6306 6307 6308 6309 6310 6311 6312 6313 6314 6315 6316 6317 6318 6319 6320 6321 6322 6323 6324 6325 6326 6327 6328 6329 6330 6331 6332 6333 6334 6335 6336 6337 6338 6339 6340 6341 6342 6343 6344 6345 6346 6347 6348 6349 6350 6351 6352 6353 6354 6355 6356 6357 6358 6359 6360 6361 6362 6363 6364 6365 6366 6367 6368 6369 6370 6371 6372 6373 6374 6375 6376 6377 6378 6379 6380 6381 6382 6383 6384 6385 6386 6387 6388 6389 6390 6391 6392 6393 6394 6395 6396 6397 6398 6399 6400 6401 6402 6403 6404 6405 6406 6407 6408 6409 6410 6411 6412 6413 6414 6415 6416 6417 6418 6419 6420 6421 6422 6423 6424 6425 6426 6427 6428 6429 6430 6431 6432 6433 6434 6435 6436 6437 6438 6439 6440 6441 6442 6443 6444 6445 6446 6447 6448 6449 6450 6451 6452 6453 6454 6455 6456 6457 6458 6459 6460 6461 6462 6463 6464 6465 6466 6467 6468 6469 6470 6471 6472 6473 6474 6475 6476 6477 6478 6479 6480 6481 6482 6483 6484 6485 6486 6487 6488 6489 6490 6491 6492 6493 6494 6495 6496 6497 6498 6499 6500 6501 6502 6503 6504 6505 6506 6507 6508 6509 6510 6511 6512 6513 6514 6515 6516 6517 6518 6519 6520 6521 6522 6523 6524 6525 6526 6527 6528 6529 6530 6531 6532 6533 6534 6535 6536 6537 6538 6539 6540 6541 6542 6543 6544 6545 6546 6547 6548 6549 6550 6551 6552 6553 6554 6555 6556 6557 6558 6559 6560 6561 6562 6563 6564 6565 6566 6567 6568 6569 6570 6571 6572 6573 6574 6575 6576 6577 6578 6579 6580 6581 6582 6583 6584 6585 6586 6587 6588 6589 6590 6591 6592 6593 6594 6595 6596 6597 6598 6599 6600 6601 6602 6603 6604 6605 6606 6607 6608 6609 6610 6611 6612 6613 6614 6615 6616 6617 6618 6619 6620 6621 6622 6623 6624 6625 6626 6627 6628 6629 6630 6631 6632 6633 6634 6635 6636 6637 6638 6639 6640 6641 6642 6643 6644 6645 6646 6647 6648 6649 6650 6651 6652 6653 6654 6655 6656 6657 6658 6659 6660 6661 6662 6663 6664 6665 6666 6667 6668 6669 6670 6671 6672 6673 6674 6675 6676 6677 6678 6679 6680 6681 6682 6683 6684 6685 6686 6687 6688 6689 6690 6691 6692 6693 6694 6695 6696 6697 6698 6699 6700 6701 6702 6703 6704 6705 6706 6707 6708 6709 6710 6711 6712 6713 6714 6715 6716 6717 6718 6719 6720 6721 6722 6723 6724 6725 6726 6727 6728 6729 6730 6731 6732 6733 6734 6735 6736 6737 6738 6739 6740 6741 6742 6743 6744 6745 6746 6747 6748 6749 6750 6751 6752 6753 6754 6755 6756 6757 6758 6759 6760 6761 6762 6763 6764 6765 6766 6767 6768 6769 6770 6771 6772 6773 6774 6775 6776 6777 6778 6779 6780 6781 6782 6783 6784 6785 6786 6787 6788 6789 6790 6791 6792 6793 6794 6795 6796 6797 6798 6799 6800 6801 6802 6803 6804 6805 6806 6807 6808 6809 6810 6811 6812 6813 6814 6815 6816 6817 6818 6819 6820 6821 6822 6823 6824 6825 6826 6827 6828 6829 6830 6831 6832 6833 6834 6835 6836 6837 6838 6839 6840 6841 6842 6843 6844 6845 6846 6847 6848 6849 6850 6851 6852 6853 6854 6855 6856 6857 6858 6859 6860 6861 6862 6863 6864 6865 6866 6867 6868 6869 6870 6871 6872 6873 6874 6875 6876 6877 6878 6879 6880 6881 6882 6883 6884 6885 6886 6887 6888 6889 6890 6891 6892 6893 6894 6895 6896 6897 6898 6899 6900 6901 6902 6903 6904 6905 6906 6907 6908 6909 6910 6911 6912 6913 6914 6915 6916 6917 6918 6919 6920 6921 6922 6923 6924 6925 6926 6927 6928 6929 6930 6931 6932 6933 6934 6935 6936 6937 6938 6939 6940 6941 6942 6943 6944 6945 6946 6947 6948 6949 6950 6951 6952 6953 6954 6955 6956 6957 6958 6959 6960 6961 6962 6963 6964 6965 6966 6967 6968 6969 6970 6971 6972 6973 6974 6975 6976 6977 6978 6979 6980 6981 6982 6983 6984 6985 6986 6987 6988 6989 6990 6991 6992 6993 6994 6995 6996 6997 6998 6999 7000 7001 7002 7003 7004 7005 7006 7007 7008 7009 7010 7011 7012 7013 7014 7015 7016 7017 7018 7019 7020 7021 7022 7023 7024 7025 7026 7027 7028 7029 7030 7031 7032 7033 7034 7035 7036 7037 7038 7039 7040 7041 7042 7043 7044 7045 7046 7047 7048 7049 7050 7051 7052 7053 7054 7055 7056 7057 7058 7059 7060 7061 7062 7063 7064 7065 7066 7067 7068 7069 7070 7071 7072 7073 7074 7075 7076 7077 7078 7079 7080 7081 7082 7083 7084 7085 7086 7087 7088 7089 7090 7091 7092 7093 7094 7095 7096 7097 7098 7099 7100 7101 7102 7103 7104 7105 7106 7107 7108 7109 7110 7111 7112 7113 7114 7115 7116 7117 7118 7119 7120 7121 7122 7123 7124 7125 7126 7127 7128 7129 7130 7131 7132 7133 7134 7135 7136 7137 7138 7139 7140 7141 7142 7143 7144 7145 7146 7147 7148 7149 7150 7151 7152 7153 7154 7155 7156 7157 7158 7159 7160 7161 7162 7163 7164 7165 7166 7167 7168 7169 7170 7171 7172 7173 7174 7175 7176 7177 7178 7179 7180 7181 7182 7183 7184 7185 7186 7187 7188 7189 7190 7191 7192 7193 7194 7195 7196 7197 7198 7199 7200 7201 7202 7203 7204 7205 7206 7207 7208 7209 7210 7211 7212 7213 7214 7215 7216 7217 7218 7219 7220 7221 7222 7223 7224 7225 7226 7227 7228 7229 7230 7231 7232 7233 7234 7235 7236 7237 7238 7239 7240 7241 7242 7243 7244 7245 7246 7247 7248 7249 7250 7251 7252 7253 7254 7255 7256 7257 7258 7259 7260 7261 7262 7263 7264 7265 7266 7267 7268 7269 7270 7271 7272 7273 7274 7275 7276 7277 7278 7279 7280 7281 7282 7283 7284 7285 7286 7287 7288 7289 7290 7291 7292 7293 7294 7295 7296 7297 7298 7299 7300 7301 7302 7303 7304 7305 7306 7307 7308 7309 7310 7311 7312 7313 7314 7315 7316 7317 7318 7319 7320 7321 7322 7323 7324 7325 7326 7327 7328 7329 7330 7331 7332 7333 7334 7335 7336 7337 7338 7339 7340 7341 7342 7343 7344 7345 7346 7347 7348 7349 7350 7351 7352 7353 7354 7355 7356 7357 7358 7359 7360 7361 7362 7363 7364 7365 7366 7367 7368 7369 7370 7371 7372 7373 7374 7375 7376 7377 7378 7379 7380 7381 7382 7383 7384 7385 7386 7387 7388 7389 7390 7391 7392 7393 7394 7395 7396 7397 7398 7399 7400 7401 7402 7403 7404 7405 7406 7407 7408 7409 7410 7411 7412 7413 7414 7415 7416 7417 7418 7419 7420 7421 7422 7423 7424 7425 7426 7427 7428 7429 7430 7431 7432 7433 7434 7435 7436 7437 7438 7439 7440 7441 7442 7443 7444 7445 7446 7447 7448 7449 7450 7451 7452 7453 7454 7455 7456 7457 7458 7459 7460 7461 7462 7463 7464 7465 7466 7467 7468 7469 7470 7471 7472 7473 7474 7475 7476 7477 7478 7479 7480 7481 7482 7483 7484 7485 7486 7487 7488 7489 7490 7491 7492 7493 7494 7495 7496 7497 7498 7499 7500 7501 7502 7503 7504 7505 7506 7507 7508 7509 7510 7511 7512 7513 7514 7515 7516 7517 7518 7519 7520 7521 7522 7523 7524 7525 7526 7527 7528 7529 7530 7531 7532 7533 7534 7535 7536 7537 7538 7539 7540 7541 7542 7543 7544 7545 7546 7547 7548 7549 7550 7551 7552 7553 7554 7555 7556 7557 7558 7559 7560 7561 7562 7563 7564 7565 7566 7567 7568 7569 7570 7571 7572 7573 7574 7575 7576 7577 7578 7579 7580 7581 7582 7583 7584 7585 7586 7587 7588 7589 7590 7591 7592 7593 7594 7595 7596 7597 7598 7599 7600 7601 7602 7603 7604 7605 7606 7607 7608 7609 7610 7611 7612 7613 7614 7615 7616 7617 7618 7619 7620 7621 7622 7623 7624 7625 7626 7627 7628 7629 7630 7631 7632 7633 7634 7635 7636 7637 7638 7639 7640 7641 7642 7643 7644 7645 7646 7647 7648 7649 7650 7651 7652 7653 7654 7655 7656 7657 7658 7659 7660 7661 7662 7663 7664 7665 7666 7667 7668 7669 7670 7671 7672 7673 7674 7675 7676 7677 7678 7679 7680 7681 7682 7683 7684 7685 7686 7687 7688 7689 7690 7691 7692 7693 7694 7695 7696 7697 7698 7699 7700 7701 7702 7703 7704 7705 7706 7707 7708 7709 7710 7711 7712 7713 7714 7715 7716 7717 7718 7719 7720 7721 7722 7723 7724 7725 7726 7727 7728 7729 7730 7731 7732 7733 7734 7735 7736 7737 7738 7739 7740 7741 7742 7743 7744 7745 7746 7747 7748 7749 7750 7751 7752 7753 7754 7755 7756 7757 7758 7759 7760 7761 7762 7763 7764 7765 7766 7767 7768 7769 7770 7771 7772 7773 7774 7775 7776 7777 7778 7779 7780 7781 7782 7783 7784 7785 7786 7787 7788 7789 7790 7791 7792 7793 7794 7795 7796 7797 7798 7799 7800 7801 7802 7803 7804 7805 7806 7807 7808 7809 7810 7811 7812 7813 7814 7815 7816 7817 7818 7819 7820 7821 7822 7823 7824 7825 7826 7827 7828 7829 7830 7831 7832 7833 7834 7835 7836 7837 7838 7839 7840 7841 7842 7843 7844 7845 7846 7847 7848 7849 7850 7851 7852 7853 7854 7855 7856 7857 7858 7859 7860 7861 7862 7863 7864 7865 7866 7867 7868 7869 7870 7871 7872 7873 7874 7875 7876 7877 7878 7879 7880 7881 7882 7883 7884 7885 7886 7887 7888 7889 7890 7891 7892 7893 7894 7895 7896 7897 7898 7899 7900 7901 7902 7903 7904 7905 7906 7907 7908 7909 7910 7911 7912 7913 7914 7915 7916 7917 7918 7919 7920 7921 7922 7923 7924 7925 7926 7927 7928 7929 7930 7931 7932 7933 7934 7935 7936 7937 7938 7939 7940 7941 7942 7943 7944 7945 7946 7947 7948 7949 7950 7951 7952 7953 7954 7955 7956 7957 7958 7959 7960 7961 7962 7963 7964 7965 7966 7967 7968 7969 7970 7971 7972 7973 7974 7975 7976 7977 7978 7979 7980 7981 7982 7983 7984 7985 7986 7987 7988 7989 7990 7991 7992 7993 7994 7995 7996 7997 7998 7999 8000 8001 8002 8003 8004 8005 | // SPDX-License-Identifier: GPL-2.0-only /* * kernel/workqueue.c - generic async execution with shared worker pool * * Copyright (C) 2002 Ingo Molnar * * Derived from the taskqueue/keventd code by: * David Woodhouse <dwmw2@infradead.org> * Andrew Morton * Kai Petzke <wpp@marie.physik.tu-berlin.de> * Theodore Ts'o <tytso@mit.edu> * * Made to use alloc_percpu by Christoph Lameter. * * Copyright (C) 2010 SUSE Linux Products GmbH * Copyright (C) 2010 Tejun Heo <tj@kernel.org> * * This is the generic async execution mechanism. Work items as are * executed in process context. The worker pool is shared and * automatically managed. There are two worker pools for each CPU (one for * normal work items and the other for high priority ones) and some extra * pools for workqueues which are not bound to any specific CPU - the * number of these backing pools is dynamic. * * Please read Documentation/core-api/workqueue.rst for details. */ #include <linux/export.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/init.h> #include <linux/interrupt.h> #include <linux/signal.h> #include <linux/completion.h> #include <linux/workqueue.h> #include <linux/slab.h> #include <linux/cpu.h> #include <linux/notifier.h> #include <linux/kthread.h> #include <linux/hardirq.h> #include <linux/mempolicy.h> #include <linux/freezer.h> #include <linux/debug_locks.h> #include <linux/lockdep.h> #include <linux/idr.h> #include <linux/jhash.h> #include <linux/hashtable.h> #include <linux/rculist.h> #include <linux/nodemask.h> #include <linux/moduleparam.h> #include <linux/uaccess.h> #include <linux/sched/isolation.h> #include <linux/sched/debug.h> #include <linux/nmi.h> #include <linux/kvm_para.h> #include <linux/delay.h> #include <linux/irq_work.h> #include "workqueue_internal.h" enum worker_pool_flags { /* * worker_pool flags * * A bound pool is either associated or disassociated with its CPU. * While associated (!DISASSOCIATED), all workers are bound to the * CPU and none has %WORKER_UNBOUND set and concurrency management * is in effect. * * While DISASSOCIATED, the cpu may be offline and all workers have * %WORKER_UNBOUND set and concurrency management disabled, and may * be executing on any CPU. The pool behaves as an unbound one. * * Note that DISASSOCIATED should be flipped only while holding * wq_pool_attach_mutex to avoid changing binding state while * worker_attach_to_pool() is in progress. * * As there can only be one concurrent BH execution context per CPU, a * BH pool is per-CPU and always DISASSOCIATED. */ POOL_BH = 1 << 0, /* is a BH pool */ POOL_MANAGER_ACTIVE = 1 << 1, /* being managed */ POOL_DISASSOCIATED = 1 << 2, /* cpu can't serve workers */ POOL_BH_DRAINING = 1 << 3, /* draining after CPU offline */ }; enum worker_flags { /* worker flags */ WORKER_DIE = 1 << 1, /* die die die */ WORKER_IDLE = 1 << 2, /* is idle */ WORKER_PREP = 1 << 3, /* preparing to run works */ WORKER_CPU_INTENSIVE = 1 << 6, /* cpu intensive */ WORKER_UNBOUND = 1 << 7, /* worker is unbound */ WORKER_REBOUND = 1 << 8, /* worker was rebound */ WORKER_NOT_RUNNING = WORKER_PREP | WORKER_CPU_INTENSIVE | WORKER_UNBOUND | WORKER_REBOUND, }; enum work_cancel_flags { WORK_CANCEL_DELAYED = 1 << 0, /* canceling a delayed_work */ WORK_CANCEL_DISABLE = 1 << 1, /* canceling to disable */ }; enum wq_internal_consts { NR_STD_WORKER_POOLS = 2, /* # standard pools per cpu */ UNBOUND_POOL_HASH_ORDER = 6, /* hashed by pool->attrs */ BUSY_WORKER_HASH_ORDER = 6, /* 64 pointers */ MAX_IDLE_WORKERS_RATIO = 4, /* 1/4 of busy can be idle */ IDLE_WORKER_TIMEOUT = 300 * HZ, /* keep idle ones for 5 mins */ MAYDAY_INITIAL_TIMEOUT = HZ / 100 >= 2 ? HZ / 100 : 2, /* call for help after 10ms (min two ticks) */ MAYDAY_INTERVAL = HZ / 10, /* and then every 100ms */ CREATE_COOLDOWN = HZ, /* time to breath after fail */ /* * Rescue workers are used only on emergencies and shared by * all cpus. Give MIN_NICE. */ RESCUER_NICE_LEVEL = MIN_NICE, HIGHPRI_NICE_LEVEL = MIN_NICE, WQ_NAME_LEN = 32, WORKER_ID_LEN = 10 + WQ_NAME_LEN, /* "kworker/R-" + WQ_NAME_LEN */ }; /* * We don't want to trap softirq for too long. See MAX_SOFTIRQ_TIME and * MAX_SOFTIRQ_RESTART in kernel/softirq.c. These are macros because * msecs_to_jiffies() can't be an initializer. */ #define BH_WORKER_JIFFIES msecs_to_jiffies(2) #define BH_WORKER_RESTARTS 10 /* * Structure fields follow one of the following exclusion rules. * * I: Modifiable by initialization/destruction paths and read-only for * everyone else. * * P: Preemption protected. Disabling preemption is enough and should * only be modified and accessed from the local cpu. * * L: pool->lock protected. Access with pool->lock held. * * LN: pool->lock and wq_node_nr_active->lock protected for writes. Either for * reads. * * K: Only modified by worker while holding pool->lock. Can be safely read by * self, while holding pool->lock or from IRQ context if %current is the * kworker. * * S: Only modified by worker self. * * A: wq_pool_attach_mutex protected. * * PL: wq_pool_mutex protected. * * PR: wq_pool_mutex protected for writes. RCU protected for reads. * * PW: wq_pool_mutex and wq->mutex protected for writes. Either for reads. * * PWR: wq_pool_mutex and wq->mutex protected for writes. Either or * RCU for reads. * * WQ: wq->mutex protected. * * WR: wq->mutex protected for writes. RCU protected for reads. * * WO: wq->mutex protected for writes. Updated with WRITE_ONCE() and can be read * with READ_ONCE() without locking. * * MD: wq_mayday_lock protected. * * WD: Used internally by the watchdog. */ /* struct worker is defined in workqueue_internal.h */ struct worker_pool { raw_spinlock_t lock; /* the pool lock */ int cpu; /* I: the associated cpu */ int node; /* I: the associated node ID */ int id; /* I: pool ID */ unsigned int flags; /* L: flags */ unsigned long watchdog_ts; /* L: watchdog timestamp */ bool cpu_stall; /* WD: stalled cpu bound pool */ /* * The counter is incremented in a process context on the associated CPU * w/ preemption disabled, and decremented or reset in the same context * but w/ pool->lock held. The readers grab pool->lock and are * guaranteed to see if the counter reached zero. */ int nr_running; struct list_head worklist; /* L: list of pending works */ int nr_workers; /* L: total number of workers */ int nr_idle; /* L: currently idle workers */ struct list_head idle_list; /* L: list of idle workers */ struct timer_list idle_timer; /* L: worker idle timeout */ struct work_struct idle_cull_work; /* L: worker idle cleanup */ struct timer_list mayday_timer; /* L: SOS timer for workers */ /* a workers is either on busy_hash or idle_list, or the manager */ DECLARE_HASHTABLE(busy_hash, BUSY_WORKER_HASH_ORDER); /* L: hash of busy workers */ struct worker *manager; /* L: purely informational */ struct list_head workers; /* A: attached workers */ struct list_head dying_workers; /* A: workers about to die */ struct completion *detach_completion; /* all workers detached */ struct ida worker_ida; /* worker IDs for task name */ struct workqueue_attrs *attrs; /* I: worker attributes */ struct hlist_node hash_node; /* PL: unbound_pool_hash node */ int refcnt; /* PL: refcnt for unbound pools */ /* * Destruction of pool is RCU protected to allow dereferences * from get_work_pool(). */ struct rcu_head rcu; }; /* * Per-pool_workqueue statistics. These can be monitored using * tools/workqueue/wq_monitor.py. */ enum pool_workqueue_stats { PWQ_STAT_STARTED, /* work items started execution */ PWQ_STAT_COMPLETED, /* work items completed execution */ PWQ_STAT_CPU_TIME, /* total CPU time consumed */ PWQ_STAT_CPU_INTENSIVE, /* wq_cpu_intensive_thresh_us violations */ PWQ_STAT_CM_WAKEUP, /* concurrency-management worker wakeups */ PWQ_STAT_REPATRIATED, /* unbound workers brought back into scope */ PWQ_STAT_MAYDAY, /* maydays to rescuer */ PWQ_STAT_RESCUED, /* linked work items executed by rescuer */ PWQ_NR_STATS, }; /* * The per-pool workqueue. While queued, bits below WORK_PWQ_SHIFT * of work_struct->data are used for flags and the remaining high bits * point to the pwq; thus, pwqs need to be aligned at two's power of the * number of flag bits. */ struct pool_workqueue { struct worker_pool *pool; /* I: the associated pool */ struct workqueue_struct *wq; /* I: the owning workqueue */ int work_color; /* L: current color */ int flush_color; /* L: flushing color */ int refcnt; /* L: reference count */ int nr_in_flight[WORK_NR_COLORS]; /* L: nr of in_flight works */ bool plugged; /* L: execution suspended */ /* * nr_active management and WORK_STRUCT_INACTIVE: * * When pwq->nr_active >= max_active, new work item is queued to * pwq->inactive_works instead of pool->worklist and marked with * WORK_STRUCT_INACTIVE. * * All work items marked with WORK_STRUCT_INACTIVE do not participate in * nr_active and all work items in pwq->inactive_works are marked with * WORK_STRUCT_INACTIVE. But not all WORK_STRUCT_INACTIVE work items are * in pwq->inactive_works. Some of them are ready to run in * pool->worklist or worker->scheduled. Those work itmes are only struct * wq_barrier which is used for flush_work() and should not participate * in nr_active. For non-barrier work item, it is marked with * WORK_STRUCT_INACTIVE iff it is in pwq->inactive_works. */ int nr_active; /* L: nr of active works */ struct list_head inactive_works; /* L: inactive works */ struct list_head pending_node; /* LN: node on wq_node_nr_active->pending_pwqs */ struct list_head pwqs_node; /* WR: node on wq->pwqs */ struct list_head mayday_node; /* MD: node on wq->maydays */ u64 stats[PWQ_NR_STATS]; /* * Release of unbound pwq is punted to a kthread_worker. See put_pwq() * and pwq_release_workfn() for details. pool_workqueue itself is also * RCU protected so that the first pwq can be determined without * grabbing wq->mutex. */ struct kthread_work release_work; struct rcu_head rcu; } __aligned(1 << WORK_STRUCT_PWQ_SHIFT); /* * Structure used to wait for workqueue flush. */ struct wq_flusher { struct list_head list; /* WQ: list of flushers */ int flush_color; /* WQ: flush color waiting for */ struct completion done; /* flush completion */ }; struct wq_device; /* * Unlike in a per-cpu workqueue where max_active limits its concurrency level * on each CPU, in an unbound workqueue, max_active applies to the whole system. * As sharing a single nr_active across multiple sockets can be very expensive, * the counting and enforcement is per NUMA node. * * The following struct is used to enforce per-node max_active. When a pwq wants * to start executing a work item, it should increment ->nr using * tryinc_node_nr_active(). If acquisition fails due to ->nr already being over * ->max, the pwq is queued on ->pending_pwqs. As in-flight work items finish * and decrement ->nr, node_activate_pending_pwq() activates the pending pwqs in * round-robin order. */ struct wq_node_nr_active { int max; /* per-node max_active */ atomic_t nr; /* per-node nr_active */ raw_spinlock_t lock; /* nests inside pool locks */ struct list_head pending_pwqs; /* LN: pwqs with inactive works */ }; /* * The externally visible workqueue. It relays the issued work items to * the appropriate worker_pool through its pool_workqueues. */ struct workqueue_struct { struct list_head pwqs; /* WR: all pwqs of this wq */ struct list_head list; /* PR: list of all workqueues */ struct mutex mutex; /* protects this wq */ int work_color; /* WQ: current work color */ int flush_color; /* WQ: current flush color */ atomic_t nr_pwqs_to_flush; /* flush in progress */ struct wq_flusher *first_flusher; /* WQ: first flusher */ struct list_head flusher_queue; /* WQ: flush waiters */ struct list_head flusher_overflow; /* WQ: flush overflow list */ struct list_head maydays; /* MD: pwqs requesting rescue */ struct worker *rescuer; /* MD: rescue worker */ int nr_drainers; /* WQ: drain in progress */ /* See alloc_workqueue() function comment for info on min/max_active */ int max_active; /* WO: max active works */ int min_active; /* WO: min active works */ int saved_max_active; /* WQ: saved max_active */ int saved_min_active; /* WQ: saved min_active */ struct workqueue_attrs *unbound_attrs; /* PW: only for unbound wqs */ struct pool_workqueue __rcu *dfl_pwq; /* PW: only for unbound wqs */ #ifdef CONFIG_SYSFS struct wq_device *wq_dev; /* I: for sysfs interface */ #endif #ifdef CONFIG_LOCKDEP char *lock_name; struct lock_class_key key; struct lockdep_map lockdep_map; #endif char name[WQ_NAME_LEN]; /* I: workqueue name */ /* * Destruction of workqueue_struct is RCU protected to allow walking * the workqueues list without grabbing wq_pool_mutex. * This is used to dump all workqueues from sysrq. */ struct rcu_head rcu; /* hot fields used during command issue, aligned to cacheline */ unsigned int flags ____cacheline_aligned; /* WQ: WQ_* flags */ struct pool_workqueue __percpu __rcu **cpu_pwq; /* I: per-cpu pwqs */ struct wq_node_nr_active *node_nr_active[]; /* I: per-node nr_active */ }; /* * Each pod type describes how CPUs should be grouped for unbound workqueues. * See the comment above workqueue_attrs->affn_scope. */ struct wq_pod_type { int nr_pods; /* number of pods */ cpumask_var_t *pod_cpus; /* pod -> cpus */ int *pod_node; /* pod -> node */ int *cpu_pod; /* cpu -> pod */ }; struct work_offq_data { u32 pool_id; u32 disable; u32 flags; }; static const char *wq_affn_names[WQ_AFFN_NR_TYPES] = { [WQ_AFFN_DFL] = "default", [WQ_AFFN_CPU] = "cpu", [WQ_AFFN_SMT] = "smt", [WQ_AFFN_CACHE] = "cache", [WQ_AFFN_NUMA] = "numa", [WQ_AFFN_SYSTEM] = "system", }; /* * Per-cpu work items which run for longer than the following threshold are * automatically considered CPU intensive and excluded from concurrency * management to prevent them from noticeably delaying other per-cpu work items. * ULONG_MAX indicates that the user hasn't overridden it with a boot parameter. * The actual value is initialized in wq_cpu_intensive_thresh_init(). */ static unsigned long wq_cpu_intensive_thresh_us = ULONG_MAX; module_param_named(cpu_intensive_thresh_us, wq_cpu_intensive_thresh_us, ulong, 0644); #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT static unsigned int wq_cpu_intensive_warning_thresh = 4; module_param_named(cpu_intensive_warning_thresh, wq_cpu_intensive_warning_thresh, uint, 0644); #endif /* see the comment above the definition of WQ_POWER_EFFICIENT */ static bool wq_power_efficient = IS_ENABLED(CONFIG_WQ_POWER_EFFICIENT_DEFAULT); module_param_named(power_efficient, wq_power_efficient, bool, 0444); static bool wq_online; /* can kworkers be created yet? */ static bool wq_topo_initialized __read_mostly = false; static struct kmem_cache *pwq_cache; static struct wq_pod_type wq_pod_types[WQ_AFFN_NR_TYPES]; static enum wq_affn_scope wq_affn_dfl = WQ_AFFN_CACHE; /* buf for wq_update_unbound_pod_attrs(), protected by CPU hotplug exclusion */ static struct workqueue_attrs *wq_update_pod_attrs_buf; static DEFINE_MUTEX(wq_pool_mutex); /* protects pools and workqueues list */ static DEFINE_MUTEX(wq_pool_attach_mutex); /* protects worker attach/detach */ static DEFINE_RAW_SPINLOCK(wq_mayday_lock); /* protects wq->maydays list */ /* wait for manager to go away */ static struct rcuwait manager_wait = __RCUWAIT_INITIALIZER(manager_wait); static LIST_HEAD(workqueues); /* PR: list of all workqueues */ static bool workqueue_freezing; /* PL: have wqs started freezing? */ /* PL&A: allowable cpus for unbound wqs and work items */ static cpumask_var_t wq_unbound_cpumask; /* PL: user requested unbound cpumask via sysfs */ static cpumask_var_t wq_requested_unbound_cpumask; /* PL: isolated cpumask to be excluded from unbound cpumask */ static cpumask_var_t wq_isolated_cpumask; /* for further constrain wq_unbound_cpumask by cmdline parameter*/ static struct cpumask wq_cmdline_cpumask __initdata; /* CPU where unbound work was last round robin scheduled from this CPU */ static DEFINE_PER_CPU(int, wq_rr_cpu_last); /* * Local execution of unbound work items is no longer guaranteed. The * following always forces round-robin CPU selection on unbound work items * to uncover usages which depend on it. */ #ifdef CONFIG_DEBUG_WQ_FORCE_RR_CPU static bool wq_debug_force_rr_cpu = true; #else static bool wq_debug_force_rr_cpu = false; #endif module_param_named(debug_force_rr_cpu, wq_debug_force_rr_cpu, bool, 0644); /* to raise softirq for the BH worker pools on other CPUs */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct irq_work [NR_STD_WORKER_POOLS], bh_pool_irq_works); /* the BH worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], bh_worker_pools); /* the per-cpu worker pools */ static DEFINE_PER_CPU_SHARED_ALIGNED(struct worker_pool [NR_STD_WORKER_POOLS], cpu_worker_pools); static DEFINE_IDR(worker_pool_idr); /* PR: idr of all pools */ /* PL: hash of all unbound pools keyed by pool->attrs */ static DEFINE_HASHTABLE(unbound_pool_hash, UNBOUND_POOL_HASH_ORDER); /* I: attributes used when instantiating standard unbound pools on demand */ static struct workqueue_attrs *unbound_std_wq_attrs[NR_STD_WORKER_POOLS]; /* I: attributes used when instantiating ordered pools on demand */ static struct workqueue_attrs *ordered_wq_attrs[NR_STD_WORKER_POOLS]; /* * I: kthread_worker to release pwq's. pwq release needs to be bounced to a * process context while holding a pool lock. Bounce to a dedicated kthread * worker to avoid A-A deadlocks. */ static struct kthread_worker *pwq_release_worker __ro_after_init; struct workqueue_struct *system_wq __ro_after_init; EXPORT_SYMBOL(system_wq); struct workqueue_struct *system_highpri_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_highpri_wq); struct workqueue_struct *system_long_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_long_wq); struct workqueue_struct *system_unbound_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_unbound_wq); struct workqueue_struct *system_freezable_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_wq); struct workqueue_struct *system_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_power_efficient_wq); struct workqueue_struct *system_freezable_power_efficient_wq __ro_after_init; EXPORT_SYMBOL_GPL(system_freezable_power_efficient_wq); struct workqueue_struct *system_bh_wq; EXPORT_SYMBOL_GPL(system_bh_wq); struct workqueue_struct *system_bh_highpri_wq; EXPORT_SYMBOL_GPL(system_bh_highpri_wq); static int worker_thread(void *__worker); static void workqueue_sysfs_unregister(struct workqueue_struct *wq); static void show_pwq(struct pool_workqueue *pwq); static void show_one_worker_pool(struct worker_pool *pool); #define CREATE_TRACE_POINTS #include <trace/events/workqueue.h> #define assert_rcu_or_pool_mutex() \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU or wq_pool_mutex should be held") #define assert_rcu_or_wq_mutex_or_pool_mutex(wq) \ RCU_LOCKDEP_WARN(!rcu_read_lock_any_held() && \ !lockdep_is_held(&wq->mutex) && \ !lockdep_is_held(&wq_pool_mutex), \ "RCU, wq->mutex or wq_pool_mutex should be held") #define for_each_bh_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(bh_worker_pools, cpu)[0]; \ (pool) < &per_cpu(bh_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) #define for_each_cpu_worker_pool(pool, cpu) \ for ((pool) = &per_cpu(cpu_worker_pools, cpu)[0]; \ (pool) < &per_cpu(cpu_worker_pools, cpu)[NR_STD_WORKER_POOLS]; \ (pool)++) /** * for_each_pool - iterate through all worker_pools in the system * @pool: iteration cursor * @pi: integer used for iteration * * This must be called either with wq_pool_mutex held or RCU read * locked. If the pool needs to be used beyond the locking in effect, the * caller is responsible for guaranteeing that the pool stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool(pool, pi) \ idr_for_each_entry(&worker_pool_idr, pool, pi) \ if (({ assert_rcu_or_pool_mutex(); false; })) { } \ else /** * for_each_pool_worker - iterate through all workers of a worker_pool * @worker: iteration cursor * @pool: worker_pool to iterate workers of * * This must be called with wq_pool_attach_mutex. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pool_worker(worker, pool) \ list_for_each_entry((worker), &(pool)->workers, node) \ if (({ lockdep_assert_held(&wq_pool_attach_mutex); false; })) { } \ else /** * for_each_pwq - iterate through all pool_workqueues of the specified workqueue * @pwq: iteration cursor * @wq: the target workqueue * * This must be called either with wq->mutex held or RCU read locked. * If the pwq needs to be used beyond the locking in effect, the caller is * responsible for guaranteeing that the pwq stays online. * * The if/else clause exists only for the lockdep assertion and can be * ignored. */ #define for_each_pwq(pwq, wq) \ list_for_each_entry_rcu((pwq), &(wq)->pwqs, pwqs_node, \ lockdep_is_held(&(wq->mutex))) #ifdef CONFIG_DEBUG_OBJECTS_WORK static const struct debug_obj_descr work_debug_descr; static void *work_debug_hint(void *addr) { return ((struct work_struct *) addr)->func; } static bool work_is_static_object(void *addr) { struct work_struct *work = addr; return test_bit(WORK_STRUCT_STATIC_BIT, work_data_bits(work)); } /* * fixup_init is called when: * - an active object is initialized */ static bool work_fixup_init(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_init(work, &work_debug_descr); return true; default: return false; } } /* * fixup_free is called when: * - an active object is freed */ static bool work_fixup_free(void *addr, enum debug_obj_state state) { struct work_struct *work = addr; switch (state) { case ODEBUG_STATE_ACTIVE: cancel_work_sync(work); debug_object_free(work, &work_debug_descr); return true; default: return false; } } static const struct debug_obj_descr work_debug_descr = { .name = "work_struct", .debug_hint = work_debug_hint, .is_static_object = work_is_static_object, .fixup_init = work_fixup_init, .fixup_free = work_fixup_free, }; static inline void debug_work_activate(struct work_struct *work) { debug_object_activate(work, &work_debug_descr); } static inline void debug_work_deactivate(struct work_struct *work) { debug_object_deactivate(work, &work_debug_descr); } void __init_work(struct work_struct *work, int onstack) { if (onstack) debug_object_init_on_stack(work, &work_debug_descr); else debug_object_init(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(__init_work); void destroy_work_on_stack(struct work_struct *work) { debug_object_free(work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_work_on_stack); void destroy_delayed_work_on_stack(struct delayed_work *work) { destroy_timer_on_stack(&work->timer); debug_object_free(&work->work, &work_debug_descr); } EXPORT_SYMBOL_GPL(destroy_delayed_work_on_stack); #else static inline void debug_work_activate(struct work_struct *work) { } static inline void debug_work_deactivate(struct work_struct *work) { } #endif /** * worker_pool_assign_id - allocate ID and assign it to @pool * @pool: the pool pointer of interest * * Returns 0 if ID in [0, WORK_OFFQ_POOL_NONE) is allocated and assigned * successfully, -errno on failure. */ static int worker_pool_assign_id(struct worker_pool *pool) { int ret; lockdep_assert_held(&wq_pool_mutex); ret = idr_alloc(&worker_pool_idr, pool, 0, WORK_OFFQ_POOL_NONE, GFP_KERNEL); if (ret >= 0) { pool->id = ret; return 0; } return ret; } static struct pool_workqueue __rcu ** unbound_pwq_slot(struct workqueue_struct *wq, int cpu) { if (cpu >= 0) return per_cpu_ptr(wq->cpu_pwq, cpu); else return &wq->dfl_pwq; } /* @cpu < 0 for dfl_pwq */ static struct pool_workqueue *unbound_pwq(struct workqueue_struct *wq, int cpu) { return rcu_dereference_check(*unbound_pwq_slot(wq, cpu), lockdep_is_held(&wq_pool_mutex) || lockdep_is_held(&wq->mutex)); } /** * unbound_effective_cpumask - effective cpumask of an unbound workqueue * @wq: workqueue of interest * * @wq->unbound_attrs->cpumask contains the cpumask requested by the user which * is masked with wq_unbound_cpumask to determine the effective cpumask. The * default pwq is always mapped to the pool with the current effective cpumask. */ static struct cpumask *unbound_effective_cpumask(struct workqueue_struct *wq) { return unbound_pwq(wq, -1)->pool->attrs->__pod_cpumask; } static unsigned int work_color_to_flags(int color) { return color << WORK_STRUCT_COLOR_SHIFT; } static int get_work_color(unsigned long work_data) { return (work_data >> WORK_STRUCT_COLOR_SHIFT) & ((1 << WORK_STRUCT_COLOR_BITS) - 1); } static int work_next_color(int color) { return (color + 1) % WORK_NR_COLORS; } static unsigned long pool_offq_flags(struct worker_pool *pool) { return (pool->flags & POOL_BH) ? WORK_OFFQ_BH : 0; } /* * While queued, %WORK_STRUCT_PWQ is set and non flag bits of a work's data * contain the pointer to the queued pwq. Once execution starts, the flag * is cleared and the high bits contain OFFQ flags and pool ID. * * set_work_pwq(), set_work_pool_and_clear_pending() and mark_work_canceling() * can be used to set the pwq, pool or clear work->data. These functions should * only be called while the work is owned - ie. while the PENDING bit is set. * * get_work_pool() and get_work_pwq() can be used to obtain the pool or pwq * corresponding to a work. Pool is available once the work has been * queued anywhere after initialization until it is sync canceled. pwq is * available only while the work item is queued. */ static inline void set_work_data(struct work_struct *work, unsigned long data) { WARN_ON_ONCE(!work_pending(work)); atomic_long_set(&work->data, data | work_static(work)); } static void set_work_pwq(struct work_struct *work, struct pool_workqueue *pwq, unsigned long flags) { set_work_data(work, (unsigned long)pwq | WORK_STRUCT_PENDING | WORK_STRUCT_PWQ | flags); } static void set_work_pool_and_keep_pending(struct work_struct *work, int pool_id, unsigned long flags) { set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | WORK_STRUCT_PENDING | flags); } static void set_work_pool_and_clear_pending(struct work_struct *work, int pool_id, unsigned long flags) { /* * The following wmb is paired with the implied mb in * test_and_set_bit(PENDING) and ensures all updates to @work made * here are visible to and precede any updates by the next PENDING * owner. */ smp_wmb(); set_work_data(work, ((unsigned long)pool_id << WORK_OFFQ_POOL_SHIFT) | flags); /* * The following mb guarantees that previous clear of a PENDING bit * will not be reordered with any speculative LOADS or STORES from * work->current_func, which is executed afterwards. This possible * reordering can lead to a missed execution on attempt to queue * the same @work. E.g. consider this case: * * CPU#0 CPU#1 * ---------------------------- -------------------------------- * * 1 STORE event_indicated * 2 queue_work_on() { * 3 test_and_set_bit(PENDING) * 4 } set_..._and_clear_pending() { * 5 set_work_data() # clear bit * 6 smp_mb() * 7 work->current_func() { * 8 LOAD event_indicated * } * * Without an explicit full barrier speculative LOAD on line 8 can * be executed before CPU#0 does STORE on line 1. If that happens, * CPU#0 observes the PENDING bit is still set and new execution of * a @work is not queued in a hope, that CPU#1 will eventually * finish the queued @work. Meanwhile CPU#1 does not see * event_indicated is set, because speculative LOAD was executed * before actual STORE. */ smp_mb(); } static inline struct pool_workqueue *work_struct_pwq(unsigned long data) { return (struct pool_workqueue *)(data & WORK_STRUCT_PWQ_MASK); } static struct pool_workqueue *get_work_pwq(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data); else return NULL; } /** * get_work_pool - return the worker_pool a given work was associated with * @work: the work item of interest * * Pools are created and destroyed under wq_pool_mutex, and allows read * access under RCU read lock. As such, this function should be * called under wq_pool_mutex or inside of a rcu_read_lock() region. * * All fields of the returned pool are accessible as long as the above * mentioned locking is in effect. If the returned pool needs to be used * beyond the critical section, the caller is responsible for ensuring the * returned pool is and stays online. * * Return: The worker_pool @work was last associated with. %NULL if none. */ static struct worker_pool *get_work_pool(struct work_struct *work) { unsigned long data = atomic_long_read(&work->data); int pool_id; assert_rcu_or_pool_mutex(); if (data & WORK_STRUCT_PWQ) return work_struct_pwq(data)->pool; pool_id = data >> WORK_OFFQ_POOL_SHIFT; if (pool_id == WORK_OFFQ_POOL_NONE) return NULL; return idr_find(&worker_pool_idr, pool_id); } static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits) { return (v >> shift) & ((1 << bits) - 1); } static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data) { WARN_ON_ONCE(data & WORK_STRUCT_PWQ); offqd->pool_id = shift_and_mask(data, WORK_OFFQ_POOL_SHIFT, WORK_OFFQ_POOL_BITS); offqd->disable = shift_and_mask(data, WORK_OFFQ_DISABLE_SHIFT, WORK_OFFQ_DISABLE_BITS); offqd->flags = data & WORK_OFFQ_FLAG_MASK; } static unsigned long work_offqd_pack_flags(struct work_offq_data *offqd) { return ((unsigned long)offqd->disable << WORK_OFFQ_DISABLE_SHIFT) | ((unsigned long)offqd->flags); } /* * Policy functions. These define the policies on how the global worker * pools are managed. Unless noted otherwise, these functions assume that * they're being called with pool->lock held. */ /* * Need to wake up a worker? Called from anything but currently * running workers. * * Note that, because unbound workers never contribute to nr_running, this * function will always return %true for unbound pools as long as the * worklist isn't empty. */ static bool need_more_worker(struct worker_pool *pool) { return !list_empty(&pool->worklist) && !pool->nr_running; } /* Can I start working? Called from busy but !running workers. */ static bool may_start_working(struct worker_pool *pool) { return pool->nr_idle; } /* Do I need to keep working? Called from currently running workers. */ static bool keep_working(struct worker_pool *pool) { return !list_empty(&pool->worklist) && (pool->nr_running <= 1); } /* Do we need a new worker? Called from manager. */ static bool need_to_create_worker(struct worker_pool *pool) { return need_more_worker(pool) && !may_start_working(pool); } /* Do we have too many workers and should some go away? */ static bool too_many_workers(struct worker_pool *pool) { bool managing = pool->flags & POOL_MANAGER_ACTIVE; int nr_idle = pool->nr_idle + managing; /* manager is considered idle */ int nr_busy = pool->nr_workers - nr_idle; return nr_idle > 2 && (nr_idle - 2) * MAX_IDLE_WORKERS_RATIO >= nr_busy; } /** * worker_set_flags - set worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to set * * Set @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_set_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); /* If transitioning into NOT_RUNNING, adjust nr_running. */ if ((flags & WORKER_NOT_RUNNING) && !(worker->flags & WORKER_NOT_RUNNING)) { pool->nr_running--; } worker->flags |= flags; } /** * worker_clr_flags - clear worker flags and adjust nr_running accordingly * @worker: self * @flags: flags to clear * * Clear @flags in @worker->flags and adjust nr_running accordingly. */ static inline void worker_clr_flags(struct worker *worker, unsigned int flags) { struct worker_pool *pool = worker->pool; unsigned int oflags = worker->flags; lockdep_assert_held(&pool->lock); worker->flags &= ~flags; /* * If transitioning out of NOT_RUNNING, increment nr_running. Note * that the nested NOT_RUNNING is not a noop. NOT_RUNNING is mask * of multiple flags, not a single flag. */ if ((flags & WORKER_NOT_RUNNING) && (oflags & WORKER_NOT_RUNNING)) if (!(worker->flags & WORKER_NOT_RUNNING)) pool->nr_running++; } /* Return the first idle worker. Called with pool->lock held. */ static struct worker *first_idle_worker(struct worker_pool *pool) { if (unlikely(list_empty(&pool->idle_list))) return NULL; return list_first_entry(&pool->idle_list, struct worker, entry); } /** * worker_enter_idle - enter idle state * @worker: worker which is entering idle state * * @worker is entering idle state. Update stats and idle timer if * necessary. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_enter_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(worker->flags & WORKER_IDLE) || WARN_ON_ONCE(!list_empty(&worker->entry) && (worker->hentry.next || worker->hentry.pprev))) return; /* can't use worker_set_flags(), also called from create_worker() */ worker->flags |= WORKER_IDLE; pool->nr_idle++; worker->last_active = jiffies; /* idle_list is LIFO */ list_add(&worker->entry, &pool->idle_list); if (too_many_workers(pool) && !timer_pending(&pool->idle_timer)) mod_timer(&pool->idle_timer, jiffies + IDLE_WORKER_TIMEOUT); /* Sanity check nr_running. */ WARN_ON_ONCE(pool->nr_workers == pool->nr_idle && pool->nr_running); } /** * worker_leave_idle - leave idle state * @worker: worker which is leaving idle state * * @worker is leaving idle state. Update stats. * * LOCKING: * raw_spin_lock_irq(pool->lock). */ static void worker_leave_idle(struct worker *worker) { struct worker_pool *pool = worker->pool; if (WARN_ON_ONCE(!(worker->flags & WORKER_IDLE))) return; worker_clr_flags(worker, WORKER_IDLE); pool->nr_idle--; list_del_init(&worker->entry); } /** * find_worker_executing_work - find worker which is executing a work * @pool: pool of interest * @work: work to find worker for * * Find a worker which is executing @work on @pool by searching * @pool->busy_hash which is keyed by the address of @work. For a worker * to match, its current execution should match the address of @work and * its work function. This is to avoid unwanted dependency between * unrelated work executions through a work item being recycled while still * being executed. * * This is a bit tricky. A work item may be freed once its execution * starts and nothing prevents the freed area from being recycled for * another work item. If the same work item address ends up being reused * before the original execution finishes, workqueue will identify the * recycled work item as currently executing and make it wait until the * current execution finishes, introducing an unwanted dependency. * * This function checks the work item address and work function to avoid * false positives. Note that this isn't complete as one may construct a * work function which can introduce dependency onto itself through a * recycled work item. Well, if somebody wants to shoot oneself in the * foot that badly, there's only so much we can do, and if such deadlock * actually occurs, it should be easy to locate the culprit work function. * * CONTEXT: * raw_spin_lock_irq(pool->lock). * * Return: * Pointer to worker which is executing @work if found, %NULL * otherwise. */ static struct worker *find_worker_executing_work(struct worker_pool *pool, struct work_struct *work) { struct worker *worker; hash_for_each_possible(pool->busy_hash, worker, hentry, (unsigned long)work) if (worker->current_work == work && worker->current_func == work->func) return worker; return NULL; } /** * move_linked_works - move linked works to a list * @work: start of series of works to be scheduled * @head: target list to append @work to * @nextp: out parameter for nested worklist walking * * Schedule linked works starting from @work to @head. Work series to be * scheduled starts at @work and includes any consecutive work with * WORK_STRUCT_LINKED set in its predecessor. See assign_work() for details on * @nextp. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void move_linked_works(struct work_struct *work, struct list_head *head, struct work_struct **nextp) { struct work_struct *n; /* * Linked worklist will always end before the end of the list, * use NULL for list head. */ list_for_each_entry_safe_from(work, n, NULL, entry) { list_move_tail(&work->entry, head); if (!(*work_data_bits(work) & WORK_STRUCT_LINKED)) break; } /* * If we're already inside safe list traversal and have moved * multiple works to the scheduled queue, the next position * needs to be updated. */ if (nextp) *nextp = n; } /** * assign_work - assign a work item and its linked work items to a worker * @work: work to assign * @worker: worker to assign to * @nextp: out parameter for nested worklist walking * * Assign @work and its linked work items to @worker. If @work is already being * executed by another worker in the same pool, it'll be punted there. * * If @nextp is not NULL, it's updated to point to the next work of the last * scheduled work. This allows assign_work() to be nested inside * list_for_each_entry_safe(). * * Returns %true if @work was successfully assigned to @worker. %false if @work * was punted to another worker already executing it. */ static bool assign_work(struct work_struct *work, struct worker *worker, struct work_struct **nextp) { struct worker_pool *pool = worker->pool; struct worker *collision; lockdep_assert_held(&pool->lock); /* * A single work shouldn't be executed concurrently by multiple workers. * __queue_work() ensures that @work doesn't jump to a different pool * while still running in the previous pool. Here, we should ensure that * @work is not executed concurrently by multiple workers from the same * pool. Check whether anyone is already processing the work. If so, * defer the work to the currently executing one. */ collision = find_worker_executing_work(pool, work); if (unlikely(collision)) { move_linked_works(work, &collision->scheduled, nextp); return false; } move_linked_works(work, &worker->scheduled, nextp); return true; } static struct irq_work *bh_pool_irq_work(struct worker_pool *pool) { int high = pool->attrs->nice == HIGHPRI_NICE_LEVEL ? 1 : 0; return &per_cpu(bh_pool_irq_works, pool->cpu)[high]; } static void kick_bh_pool(struct worker_pool *pool) { #ifdef CONFIG_SMP /* see drain_dead_softirq_workfn() for BH_DRAINING */ if (unlikely(pool->cpu != smp_processor_id() && !(pool->flags & POOL_BH_DRAINING))) { irq_work_queue_on(bh_pool_irq_work(pool), pool->cpu); return; } #endif if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) raise_softirq_irqoff(HI_SOFTIRQ); else raise_softirq_irqoff(TASKLET_SOFTIRQ); } /** * kick_pool - wake up an idle worker if necessary * @pool: pool to kick * * @pool may have pending work items. Wake up worker if necessary. Returns * whether a worker was woken up. */ static bool kick_pool(struct worker_pool *pool) { struct worker *worker = first_idle_worker(pool); struct task_struct *p; lockdep_assert_held(&pool->lock); if (!need_more_worker(pool) || !worker) return false; if (pool->flags & POOL_BH) { kick_bh_pool(pool); return true; } p = worker->task; #ifdef CONFIG_SMP /* * Idle @worker is about to execute @work and waking up provides an * opportunity to migrate @worker at a lower cost by setting the task's * wake_cpu field. Let's see if we want to move @worker to improve * execution locality. * * We're waking the worker that went idle the latest and there's some * chance that @worker is marked idle but hasn't gone off CPU yet. If * so, setting the wake_cpu won't do anything. As this is a best-effort * optimization and the race window is narrow, let's leave as-is for * now. If this becomes pronounced, we can skip over workers which are * still on cpu when picking an idle worker. * * If @pool has non-strict affinity, @worker might have ended up outside * its affinity scope. Repatriate. */ if (!pool->attrs->affn_strict && !cpumask_test_cpu(p->wake_cpu, pool->attrs->__pod_cpumask)) { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); int wake_cpu = cpumask_any_and_distribute(pool->attrs->__pod_cpumask, cpu_online_mask); if (wake_cpu < nr_cpu_ids) { p->wake_cpu = wake_cpu; get_work_pwq(work)->stats[PWQ_STAT_REPATRIATED]++; } } #endif wake_up_process(p); return true; } #ifdef CONFIG_WQ_CPU_INTENSIVE_REPORT /* * Concurrency-managed per-cpu work items that hog CPU for longer than * wq_cpu_intensive_thresh_us trigger the automatic CPU_INTENSIVE mechanism, * which prevents them from stalling other concurrency-managed work items. If a * work function keeps triggering this mechanism, it's likely that the work item * should be using an unbound workqueue instead. * * wq_cpu_intensive_report() tracks work functions which trigger such conditions * and report them so that they can be examined and converted to use unbound * workqueues as appropriate. To avoid flooding the console, each violating work * function is tracked and reported with exponential backoff. */ #define WCI_MAX_ENTS 128 struct wci_ent { work_func_t func; atomic64_t cnt; struct hlist_node hash_node; }; static struct wci_ent wci_ents[WCI_MAX_ENTS]; static int wci_nr_ents; static DEFINE_RAW_SPINLOCK(wci_lock); static DEFINE_HASHTABLE(wci_hash, ilog2(WCI_MAX_ENTS)); static struct wci_ent *wci_find_ent(work_func_t func) { struct wci_ent *ent; hash_for_each_possible_rcu(wci_hash, ent, hash_node, (unsigned long)func) { if (ent->func == func) return ent; } return NULL; } static void wq_cpu_intensive_report(work_func_t func) { struct wci_ent *ent; restart: ent = wci_find_ent(func); if (ent) { u64 cnt; /* * Start reporting from the warning_thresh and back off * exponentially. */ cnt = atomic64_inc_return_relaxed(&ent->cnt); if (wq_cpu_intensive_warning_thresh && cnt >= wq_cpu_intensive_warning_thresh && is_power_of_2(cnt + 1 - wq_cpu_intensive_warning_thresh)) printk_deferred(KERN_WARNING "workqueue: %ps hogged CPU for >%luus %llu times, consider switching to WQ_UNBOUND\n", ent->func, wq_cpu_intensive_thresh_us, atomic64_read(&ent->cnt)); return; } /* * @func is a new violation. Allocate a new entry for it. If wcn_ents[] * is exhausted, something went really wrong and we probably made enough * noise already. */ if (wci_nr_ents >= WCI_MAX_ENTS) return; raw_spin_lock(&wci_lock); if (wci_nr_ents >= WCI_MAX_ENTS) { raw_spin_unlock(&wci_lock); return; } if (wci_find_ent(func)) { raw_spin_unlock(&wci_lock); goto restart; } ent = &wci_ents[wci_nr_ents++]; ent->func = func; atomic64_set(&ent->cnt, 0); hash_add_rcu(wci_hash, &ent->hash_node, (unsigned long)func); raw_spin_unlock(&wci_lock); goto restart; } #else /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ static void wq_cpu_intensive_report(work_func_t func) {} #endif /* CONFIG_WQ_CPU_INTENSIVE_REPORT */ /** * wq_worker_running - a worker is running again * @task: task waking up * * This function is called when a worker returns from schedule() */ void wq_worker_running(struct task_struct *task) { struct worker *worker = kthread_data(task); if (!READ_ONCE(worker->sleeping)) return; /* * If preempted by unbind_workers() between the WORKER_NOT_RUNNING check * and the nr_running increment below, we may ruin the nr_running reset * and leave with an unexpected pool->nr_running == 1 on the newly unbound * pool. Protect against such race. */ preempt_disable(); if (!(worker->flags & WORKER_NOT_RUNNING)) worker->pool->nr_running++; preempt_enable(); /* * CPU intensive auto-detection cares about how long a work item hogged * CPU without sleeping. Reset the starting timestamp on wakeup. */ worker->current_at = worker->task->se.sum_exec_runtime; WRITE_ONCE(worker->sleeping, 0); } /** * wq_worker_sleeping - a worker is going to sleep * @task: task going to sleep * * This function is called from schedule() when a busy worker is * going to sleep. */ void wq_worker_sleeping(struct task_struct *task) { struct worker *worker = kthread_data(task); struct worker_pool *pool; /* * Rescuers, which may not have all the fields set up like normal * workers, also reach here, let's not access anything before * checking NOT_RUNNING. */ if (worker->flags & WORKER_NOT_RUNNING) return; pool = worker->pool; /* Return if preempted before wq_worker_running() was reached */ if (READ_ONCE(worker->sleeping)) return; WRITE_ONCE(worker->sleeping, 1); raw_spin_lock_irq(&pool->lock); /* * Recheck in case unbind_workers() preempted us. We don't * want to decrement nr_running after the worker is unbound * and nr_running has been reset. */ if (worker->flags & WORKER_NOT_RUNNING) { raw_spin_unlock_irq(&pool->lock); return; } pool->nr_running--; if (kick_pool(pool)) worker->current_pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock_irq(&pool->lock); } /** * wq_worker_tick - a scheduler tick occurred while a kworker is running * @task: task currently running * * Called from sched_tick(). We're in the IRQ context and the current * worker's fields which follow the 'K' locking rule can be accessed safely. */ void wq_worker_tick(struct task_struct *task) { struct worker *worker = kthread_data(task); struct pool_workqueue *pwq = worker->current_pwq; struct worker_pool *pool = worker->pool; if (!pwq) return; pwq->stats[PWQ_STAT_CPU_TIME] += TICK_USEC; if (!wq_cpu_intensive_thresh_us) return; /* * If the current worker is concurrency managed and hogged the CPU for * longer than wq_cpu_intensive_thresh_us, it's automatically marked * CPU_INTENSIVE to avoid stalling other concurrency-managed work items. * * Set @worker->sleeping means that @worker is in the process of * switching out voluntarily and won't be contributing to * @pool->nr_running until it wakes up. As wq_worker_sleeping() also * decrements ->nr_running, setting CPU_INTENSIVE here can lead to * double decrements. The task is releasing the CPU anyway. Let's skip. * We probably want to make this prettier in the future. */ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) || worker->task->se.sum_exec_runtime - worker->current_at < wq_cpu_intensive_thresh_us * NSEC_PER_USEC) return; raw_spin_lock(&pool->lock); worker_set_flags(worker, WORKER_CPU_INTENSIVE); wq_cpu_intensive_report(worker->current_func); pwq->stats[PWQ_STAT_CPU_INTENSIVE]++; if (kick_pool(pool)) pwq->stats[PWQ_STAT_CM_WAKEUP]++; raw_spin_unlock(&pool->lock); } /** * wq_worker_last_func - retrieve worker's last work function * @task: Task to retrieve last work function of. * * Determine the last function a worker executed. This is called from * the scheduler to get a worker's last known identity. * * CONTEXT: * raw_spin_lock_irq(rq->lock) * * This function is called during schedule() when a kworker is going * to sleep. It's used by psi to identify aggregation workers during * dequeuing, to allow periodic aggregation to shut-off when that * worker is the last task in the system or cgroup to go to sleep. * * As this function doesn't involve any workqueue-related locking, it * only returns stable values when called from inside the scheduler's * queuing and dequeuing paths, when @task, which must be a kworker, * is guaranteed to not be processing any works. * * Return: * The last work function %current executed as a worker, NULL if it * hasn't executed any work yet. */ work_func_t wq_worker_last_func(struct task_struct *task) { struct worker *worker = kthread_data(task); return worker->last_func; } /** * wq_node_nr_active - Determine wq_node_nr_active to use * @wq: workqueue of interest * @node: NUMA node, can be %NUMA_NO_NODE * * Determine wq_node_nr_active to use for @wq on @node. Returns: * * - %NULL for per-cpu workqueues as they don't need to use shared nr_active. * * - node_nr_active[nr_node_ids] if @node is %NUMA_NO_NODE. * * - Otherwise, node_nr_active[@node]. */ static struct wq_node_nr_active *wq_node_nr_active(struct workqueue_struct *wq, int node) { if (!(wq->flags & WQ_UNBOUND)) return NULL; if (node == NUMA_NO_NODE) node = nr_node_ids; return wq->node_nr_active[node]; } /** * wq_update_node_max_active - Update per-node max_actives to use * @wq: workqueue to update * @off_cpu: CPU that's going down, -1 if a CPU is not going down * * Update @wq->node_nr_active[]->max. @wq must be unbound. max_active is * distributed among nodes according to the proportions of numbers of online * cpus. The result is always between @wq->min_active and max_active. */ static void wq_update_node_max_active(struct workqueue_struct *wq, int off_cpu) { struct cpumask *effective = unbound_effective_cpumask(wq); int min_active = READ_ONCE(wq->min_active); int max_active = READ_ONCE(wq->max_active); int total_cpus, node; lockdep_assert_held(&wq->mutex); if (!wq_topo_initialized) return; if (off_cpu >= 0 && !cpumask_test_cpu(off_cpu, effective)) off_cpu = -1; total_cpus = cpumask_weight_and(effective, cpu_online_mask); if (off_cpu >= 0) total_cpus--; /* If all CPUs of the wq get offline, use the default values */ if (unlikely(!total_cpus)) { for_each_node(node) wq_node_nr_active(wq, node)->max = min_active; wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; return; } for_each_node(node) { int node_cpus; node_cpus = cpumask_weight_and(effective, cpumask_of_node(node)); if (off_cpu >= 0 && cpu_to_node(off_cpu) == node) node_cpus--; wq_node_nr_active(wq, node)->max = clamp(DIV_ROUND_UP(max_active * node_cpus, total_cpus), min_active, max_active); } wq_node_nr_active(wq, NUMA_NO_NODE)->max = max_active; } /** * get_pwq - get an extra reference on the specified pool_workqueue * @pwq: pool_workqueue to get * * Obtain an extra reference on @pwq. The caller should guarantee that * @pwq has positive refcnt and be holding the matching pool->lock. */ static void get_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); WARN_ON_ONCE(pwq->refcnt <= 0); pwq->refcnt++; } /** * put_pwq - put a pool_workqueue reference * @pwq: pool_workqueue to put * * Drop a reference of @pwq. If its refcnt reaches zero, schedule its * destruction. The caller should be holding the matching pool->lock. */ static void put_pwq(struct pool_workqueue *pwq) { lockdep_assert_held(&pwq->pool->lock); if (likely(--pwq->refcnt)) return; /* * @pwq can't be released under pool->lock, bounce to a dedicated * kthread_worker to avoid A-A deadlocks. */ kthread_queue_work(pwq_release_worker, &pwq->release_work); } /** * put_pwq_unlocked - put_pwq() with surrounding pool lock/unlock * @pwq: pool_workqueue to put (can be %NULL) * * put_pwq() with locking. This function also allows %NULL @pwq. */ static void put_pwq_unlocked(struct pool_workqueue *pwq) { if (pwq) { /* * As both pwqs and pools are RCU protected, the * following lock operations are safe. */ raw_spin_lock_irq(&pwq->pool->lock); put_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); } } static bool pwq_is_empty(struct pool_workqueue *pwq) { return !pwq->nr_active && list_empty(&pwq->inactive_works); } static void __pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { unsigned long *wdb = work_data_bits(work); WARN_ON_ONCE(!(*wdb & WORK_STRUCT_INACTIVE)); trace_workqueue_activate_work(work); if (list_empty(&pwq->pool->worklist)) pwq->pool->watchdog_ts = jiffies; move_linked_works(work, &pwq->pool->worklist, NULL); __clear_bit(WORK_STRUCT_INACTIVE_BIT, wdb); } /** * pwq_activate_work - Activate a work item if inactive * @pwq: pool_workqueue @work belongs to * @work: work item to activate * * Returns %true if activated. %false if already active. */ static bool pwq_activate_work(struct pool_workqueue *pwq, struct work_struct *work) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna; lockdep_assert_held(&pool->lock); if (!(*work_data_bits(work) & WORK_STRUCT_INACTIVE)) return false; nna = wq_node_nr_active(pwq->wq, pool->node); if (nna) atomic_inc(&nna->nr); pwq->nr_active++; __pwq_activate_work(pwq, work); return true; } static bool tryinc_node_nr_active(struct wq_node_nr_active *nna) { int max = READ_ONCE(nna->max); while (true) { int old, tmp; old = atomic_read(&nna->nr); if (old >= max) return false; tmp = atomic_cmpxchg_relaxed(&nna->nr, old, old + 1); if (tmp == old) return true; } } /** * pwq_tryinc_nr_active - Try to increment nr_active for a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Try to increment nr_active for @pwq. Returns %true if an nr_active count is * successfully obtained. %false otherwise. */ static bool pwq_tryinc_nr_active(struct pool_workqueue *pwq, bool fill) { struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(wq, pool->node); bool obtained = false; lockdep_assert_held(&pool->lock); if (!nna) { /* BH or per-cpu workqueue, pwq->nr_active is sufficient */ obtained = pwq->nr_active < READ_ONCE(wq->max_active); goto out; } if (unlikely(pwq->plugged)) return false; /* * Unbound workqueue uses per-node shared nr_active $nna. If @pwq is * already waiting on $nna, pwq_dec_nr_active() will maintain the * concurrency level. Don't jump the line. * * We need to ignore the pending test after max_active has increased as * pwq_dec_nr_active() can only maintain the concurrency level but not * increase it. This is indicated by @fill. */ if (!list_empty(&pwq->pending_node) && likely(!fill)) goto out; obtained = tryinc_node_nr_active(nna); if (obtained) goto out; /* * Lockless acquisition failed. Lock, add ourself to $nna->pending_pwqs * and try again. The smp_mb() is paired with the implied memory barrier * of atomic_dec_return() in pwq_dec_nr_active() to ensure that either * we see the decremented $nna->nr or they see non-empty * $nna->pending_pwqs. */ raw_spin_lock(&nna->lock); if (list_empty(&pwq->pending_node)) list_add_tail(&pwq->pending_node, &nna->pending_pwqs); else if (likely(!fill)) goto out_unlock; smp_mb(); obtained = tryinc_node_nr_active(nna); /* * If @fill, @pwq might have already been pending. Being spuriously * pending in cold paths doesn't affect anything. Let's leave it be. */ if (obtained && likely(!fill)) list_del_init(&pwq->pending_node); out_unlock: raw_spin_unlock(&nna->lock); out: if (obtained) pwq->nr_active++; return obtained; } /** * pwq_activate_first_inactive - Activate the first inactive work item on a pwq * @pwq: pool_workqueue of interest * @fill: max_active may have increased, try to increase concurrency level * * Activate the first inactive work item of @pwq if available and allowed by * max_active limit. * * Returns %true if an inactive work item has been activated. %false if no * inactive work item is found or max_active limit is reached. */ static bool pwq_activate_first_inactive(struct pool_workqueue *pwq, bool fill) { struct work_struct *work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (work && pwq_tryinc_nr_active(pwq, fill)) { __pwq_activate_work(pwq, work); return true; } else { return false; } } /** * unplug_oldest_pwq - unplug the oldest pool_workqueue * @wq: workqueue_struct where its oldest pwq is to be unplugged * * This function should only be called for ordered workqueues where only the * oldest pwq is unplugged, the others are plugged to suspend execution to * ensure proper work item ordering:: * * dfl_pwq --------------+ [P] - plugged * | * v * pwqs -> A -> B [P] -> C [P] (newest) * | | | * 1 3 5 * | | | * 2 4 6 * * When the oldest pwq is drained and removed, this function should be called * to unplug the next oldest one to start its work item execution. Note that * pwq's are linked into wq->pwqs with the oldest first, so the first one in * the list is the oldest. */ static void unplug_oldest_pwq(struct workqueue_struct *wq) { struct pool_workqueue *pwq; lockdep_assert_held(&wq->mutex); /* Caller should make sure that pwqs isn't empty before calling */ pwq = list_first_entry_or_null(&wq->pwqs, struct pool_workqueue, pwqs_node); raw_spin_lock_irq(&pwq->pool->lock); if (pwq->plugged) { pwq->plugged = false; if (pwq_activate_first_inactive(pwq, true)) kick_pool(pwq->pool); } raw_spin_unlock_irq(&pwq->pool->lock); } /** * node_activate_pending_pwq - Activate a pending pwq on a wq_node_nr_active * @nna: wq_node_nr_active to activate a pending pwq for * @caller_pool: worker_pool the caller is locking * * Activate a pwq in @nna->pending_pwqs. Called with @caller_pool locked. * @caller_pool may be unlocked and relocked to lock other worker_pools. */ static void node_activate_pending_pwq(struct wq_node_nr_active *nna, struct worker_pool *caller_pool) { struct worker_pool *locked_pool = caller_pool; struct pool_workqueue *pwq; struct work_struct *work; lockdep_assert_held(&caller_pool->lock); raw_spin_lock(&nna->lock); retry: pwq = list_first_entry_or_null(&nna->pending_pwqs, struct pool_workqueue, pending_node); if (!pwq) goto out_unlock; /* * If @pwq is for a different pool than @locked_pool, we need to lock * @pwq->pool->lock. Let's trylock first. If unsuccessful, do the unlock * / lock dance. For that, we also need to release @nna->lock as it's * nested inside pool locks. */ if (pwq->pool != locked_pool) { raw_spin_unlock(&locked_pool->lock); locked_pool = pwq->pool; if (!raw_spin_trylock(&locked_pool->lock)) { raw_spin_unlock(&nna->lock); raw_spin_lock(&locked_pool->lock); raw_spin_lock(&nna->lock); goto retry; } } /* * $pwq may not have any inactive work items due to e.g. cancellations. * Drop it from pending_pwqs and see if there's another one. */ work = list_first_entry_or_null(&pwq->inactive_works, struct work_struct, entry); if (!work) { list_del_init(&pwq->pending_node); goto retry; } /* * Acquire an nr_active count and activate the inactive work item. If * $pwq still has inactive work items, rotate it to the end of the * pending_pwqs so that we round-robin through them. This means that * inactive work items are not activated in queueing order which is fine * given that there has never been any ordering across different pwqs. */ if (likely(tryinc_node_nr_active(nna))) { pwq->nr_active++; __pwq_activate_work(pwq, work); if (list_empty(&pwq->inactive_works)) list_del_init(&pwq->pending_node); else list_move_tail(&pwq->pending_node, &nna->pending_pwqs); /* if activating a foreign pool, make sure it's running */ if (pwq->pool != caller_pool) kick_pool(pwq->pool); } out_unlock: raw_spin_unlock(&nna->lock); if (locked_pool != caller_pool) { raw_spin_unlock(&locked_pool->lock); raw_spin_lock(&caller_pool->lock); } } /** * pwq_dec_nr_active - Retire an active count * @pwq: pool_workqueue of interest * * Decrement @pwq's nr_active and try to activate the first inactive work item. * For unbound workqueues, this function may temporarily drop @pwq->pool->lock. */ static void pwq_dec_nr_active(struct pool_workqueue *pwq) { struct worker_pool *pool = pwq->pool; struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pool->node); lockdep_assert_held(&pool->lock); /* * @pwq->nr_active should be decremented for both percpu and unbound * workqueues. */ pwq->nr_active--; /* * For a percpu workqueue, it's simple. Just need to kick the first * inactive work item on @pwq itself. */ if (!nna) { pwq_activate_first_inactive(pwq, false); return; } /* * If @pwq is for an unbound workqueue, it's more complicated because * multiple pwqs and pools may be sharing the nr_active count. When a * pwq needs to wait for an nr_active count, it puts itself on * $nna->pending_pwqs. The following atomic_dec_return()'s implied * memory barrier is paired with smp_mb() in pwq_tryinc_nr_active() to * guarantee that either we see non-empty pending_pwqs or they see * decremented $nna->nr. * * $nna->max may change as CPUs come online/offline and @pwq->wq's * max_active gets updated. However, it is guaranteed to be equal to or * larger than @pwq->wq->min_active which is above zero unless freezing. * This maintains the forward progress guarantee. */ if (atomic_dec_return(&nna->nr) >= READ_ONCE(nna->max)) return; if (!list_empty(&nna->pending_pwqs)) node_activate_pending_pwq(nna, pool); } /** * pwq_dec_nr_in_flight - decrement pwq's nr_in_flight * @pwq: pwq of interest * @work_data: work_data of work which left the queue * * A work either has completed or is removed from pending queue, * decrement nr_in_flight of its pwq and handle workqueue flushing. * * NOTE: * For unbound workqueues, this function may temporarily drop @pwq->pool->lock * and thus should be called after all other state updates for the in-flight * work item is complete. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void pwq_dec_nr_in_flight(struct pool_workqueue *pwq, unsigned long work_data) { int color = get_work_color(work_data); if (!(work_data & WORK_STRUCT_INACTIVE)) pwq_dec_nr_active(pwq); pwq->nr_in_flight[color]--; /* is flush in progress and are we at the flushing tip? */ if (likely(pwq->flush_color != color)) goto out_put; /* are there still in-flight works? */ if (pwq->nr_in_flight[color]) goto out_put; /* this pwq is done, clear flush_color */ pwq->flush_color = -1; /* * If this was the last pwq, wake up the first flusher. It * will handle the rest. */ if (atomic_dec_and_test(&pwq->wq->nr_pwqs_to_flush)) complete(&pwq->wq->first_flusher->done); out_put: put_pwq(pwq); } /** * try_to_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store irq state * * Try to grab PENDING bit of @work. This function can handle @work in any * stable state - idle, on timer or on worklist. * * Return: * * ======== ================================================================ * 1 if @work was pending and we successfully stole PENDING * 0 if @work was idle and we claimed PENDING * -EAGAIN if PENDING couldn't be grabbed at the moment, safe to busy-retry * ======== ================================================================ * * Note: * On >= 0 return, the caller owns @work's PENDING bit. To avoid getting * interrupted while holding PENDING and @work off queue, irq must be * disabled on entry. This, combined with delayed_work->timer being * irqsafe, ensures that we return -EAGAIN for finite short period of time. * * On successful return, >= 0, irq is disabled and the caller is * responsible for releasing it using local_irq_restore(*@irq_flags). * * This function is safe to call from any context including IRQ handler. */ static int try_to_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { struct worker_pool *pool; struct pool_workqueue *pwq; local_irq_save(*irq_flags); /* try to steal the timer if it exists */ if (cflags & WORK_CANCEL_DELAYED) { struct delayed_work *dwork = to_delayed_work(work); /* * dwork->timer is irqsafe. If del_timer() fails, it's * guaranteed that the timer is not queued anywhere and not * running on the local CPU. */ if (likely(del_timer(&dwork->timer))) return 1; } /* try to claim PENDING the normal way */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work))) return 0; rcu_read_lock(); /* * The queueing is in progress, or it is already queued. Try to * steal it from ->worklist without clearing WORK_STRUCT_PENDING. */ pool = get_work_pool(work); if (!pool) goto fail; raw_spin_lock(&pool->lock); /* * work->data is guaranteed to point to pwq only while the work * item is queued on pwq->wq, and both updating work->data to point * to pwq on queueing and to pool on dequeueing are done under * pwq->pool->lock. This in turn guarantees that, if work->data * points to pwq which is associated with a locked pool, the work * item is currently queued on that pool. */ pwq = get_work_pwq(work); if (pwq && pwq->pool == pool) { unsigned long work_data; debug_work_deactivate(work); /* * A cancelable inactive work item must be in the * pwq->inactive_works since a queued barrier can't be * canceled (see the comments in insert_wq_barrier()). * * An inactive work item cannot be grabbed directly because * it might have linked barrier work items which, if left * on the inactive_works list, will confuse pwq->nr_active * management later on and cause stall. Make sure the work * item is activated before grabbing. */ pwq_activate_work(pwq, work); list_del_init(&work->entry); /* * work->data points to pwq iff queued. Let's point to pool. As * this destroys work->data needed by the next step, stash it. */ work_data = *work_data_bits(work); set_work_pool_and_keep_pending(work, pool->id, pool_offq_flags(pool)); /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); raw_spin_unlock(&pool->lock); rcu_read_unlock(); return 1; } raw_spin_unlock(&pool->lock); fail: rcu_read_unlock(); local_irq_restore(*irq_flags); return -EAGAIN; } /** * work_grab_pending - steal work item from worklist and disable irq * @work: work item to steal * @cflags: %WORK_CANCEL_ flags * @irq_flags: place to store IRQ state * * Grab PENDING bit of @work. @work can be in any stable state - idle, on timer * or on worklist. * * Can be called from any context. IRQ is disabled on return with IRQ state * stored in *@irq_flags. The caller is responsible for re-enabling it using * local_irq_restore(). * * Returns %true if @work was pending. %false if idle. */ static bool work_grab_pending(struct work_struct *work, u32 cflags, unsigned long *irq_flags) { int ret; while (true) { ret = try_to_grab_pending(work, cflags, irq_flags); if (ret >= 0) return ret; cpu_relax(); } } /** * insert_work - insert a work into a pool * @pwq: pwq @work belongs to * @work: work to insert * @head: insertion point * @extra_flags: extra WORK_STRUCT_* flags to set * * Insert @work which belongs to @pwq after @head. @extra_flags is or'd to * work_struct flags. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_work(struct pool_workqueue *pwq, struct work_struct *work, struct list_head *head, unsigned int extra_flags) { debug_work_activate(work); /* record the work call stack in order to print it in KASAN reports */ kasan_record_aux_stack_noalloc(work); /* we own @work, set data and link */ set_work_pwq(work, pwq, extra_flags); list_add_tail(&work->entry, head); get_pwq(pwq); } /* * Test whether @work is being queued from another work executing on the * same workqueue. */ static bool is_chained_work(struct workqueue_struct *wq) { struct worker *worker; worker = current_wq_worker(); /* * Return %true iff I'm a worker executing a work item on @wq. If * I'm @worker, it's safe to dereference it without locking. */ return worker && worker->current_pwq->wq == wq; } /* * When queueing an unbound work item to a wq, prefer local CPU if allowed * by wq_unbound_cpumask. Otherwise, round robin among the allowed ones to * avoid perturbing sensitive tasks. */ static int wq_select_unbound_cpu(int cpu) { int new_cpu; if (likely(!wq_debug_force_rr_cpu)) { if (cpumask_test_cpu(cpu, wq_unbound_cpumask)) return cpu; } else { pr_warn_once("workqueue: round-robin CPU selection forced, expect performance impact\n"); } new_cpu = __this_cpu_read(wq_rr_cpu_last); new_cpu = cpumask_next_and(new_cpu, wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) { new_cpu = cpumask_first_and(wq_unbound_cpumask, cpu_online_mask); if (unlikely(new_cpu >= nr_cpu_ids)) return cpu; } __this_cpu_write(wq_rr_cpu_last, new_cpu); return new_cpu; } static void __queue_work(int cpu, struct workqueue_struct *wq, struct work_struct *work) { struct pool_workqueue *pwq; struct worker_pool *last_pool, *pool; unsigned int work_flags; unsigned int req_cpu = cpu; /* * While a work item is PENDING && off queue, a task trying to * steal the PENDING will busy-loop waiting for it to either get * queued or lose PENDING. Grabbing PENDING and queueing should * happen with IRQ disabled. */ lockdep_assert_irqs_disabled(); /* * For a draining wq, only works from the same workqueue are * allowed. The __WQ_DESTROYING helps to spot the issue that * queues a new work item to a wq after destroy_workqueue(wq). */ if (unlikely(wq->flags & (__WQ_DESTROYING | __WQ_DRAINING) && WARN_ON_ONCE(!is_chained_work(wq)))) return; rcu_read_lock(); retry: /* pwq which will be used unless @work is executing elsewhere */ if (req_cpu == WORK_CPU_UNBOUND) { if (wq->flags & WQ_UNBOUND) cpu = wq_select_unbound_cpu(raw_smp_processor_id()); else cpu = raw_smp_processor_id(); } pwq = rcu_dereference(*per_cpu_ptr(wq->cpu_pwq, cpu)); pool = pwq->pool; /* * If @work was previously on a different pool, it might still be * running there, in which case the work needs to be queued on that * pool to guarantee non-reentrancy. */ last_pool = get_work_pool(work); if (last_pool && last_pool != pool) { struct worker *worker; raw_spin_lock(&last_pool->lock); worker = find_worker_executing_work(last_pool, work); if (worker && worker->current_pwq->wq == wq) { pwq = worker->current_pwq; pool = pwq->pool; WARN_ON_ONCE(pool != last_pool); } else { /* meh... not running there, queue here */ raw_spin_unlock(&last_pool->lock); raw_spin_lock(&pool->lock); } } else { raw_spin_lock(&pool->lock); } /* * pwq is determined and locked. For unbound pools, we could have raced * with pwq release and it could already be dead. If its refcnt is zero, * repeat pwq selection. Note that unbound pwqs never die without * another pwq replacing it in cpu_pwq or while work items are executing * on it, so the retrying is guaranteed to make forward-progress. */ if (unlikely(!pwq->refcnt)) { if (wq->flags & WQ_UNBOUND) { raw_spin_unlock(&pool->lock); cpu_relax(); goto retry; } /* oops */ WARN_ONCE(true, "workqueue: per-cpu pwq for %s on cpu%d has 0 refcnt", wq->name, cpu); } /* pwq determined, queue */ trace_workqueue_queue_work(req_cpu, pwq, work); if (WARN_ON(!list_empty(&work->entry))) goto out; pwq->nr_in_flight[pwq->work_color]++; work_flags = work_color_to_flags(pwq->work_color); /* * Limit the number of concurrently active work items to max_active. * @work must also queue behind existing inactive work items to maintain * ordering when max_active changes. See wq_adjust_max_active(). */ if (list_empty(&pwq->inactive_works) && pwq_tryinc_nr_active(pwq, false)) { if (list_empty(&pool->worklist)) pool->watchdog_ts = jiffies; trace_workqueue_activate_work(work); insert_work(pwq, work, &pool->worklist, work_flags); kick_pool(pool); } else { work_flags |= WORK_STRUCT_INACTIVE; insert_work(pwq, work, &pwq->inactive_works, work_flags); } out: raw_spin_unlock(&pool->lock); rcu_read_unlock(); } static bool clear_pending_if_disabled(struct work_struct *work) { unsigned long data = *work_data_bits(work); struct work_offq_data offqd; if (likely((data & WORK_STRUCT_PWQ) || !(data & WORK_OFFQ_DISABLE_MASK))) return false; work_offqd_unpack(&offqd, data); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); return true; } /** * queue_work_on - queue work on specific cpu * @cpu: CPU number to execute work on * @wq: workqueue to use * @work: work to queue * * We queue the work to a specific CPU, the caller must ensure it * can't go away. Callers that fail to ensure that the specified * CPU cannot go away will execute on a randomly chosen CPU. * But note well that callers specifying a CPU that never has been * online will get a splat. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_on(int cpu, struct workqueue_struct *wq, struct work_struct *work) { bool ret = false; unsigned long irq_flags; local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_work_on); /** * select_numa_node_cpu - Select a CPU based on NUMA node * @node: NUMA node ID that we want to select a CPU from * * This function will attempt to find a "random" cpu available on a given * node. If there are no CPUs available on the given node it will return * WORK_CPU_UNBOUND indicating that we should just schedule to any * available CPU if we need to schedule this work. */ static int select_numa_node_cpu(int node) { int cpu; /* Delay binding to CPU if node is not valid or online */ if (node < 0 || node >= MAX_NUMNODES || !node_online(node)) return WORK_CPU_UNBOUND; /* Use local node/cpu if we are already there */ cpu = raw_smp_processor_id(); if (node == cpu_to_node(cpu)) return cpu; /* Use "random" otherwise know as "first" online CPU of node */ cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask); /* If CPU is valid return that, otherwise just defer */ return cpu < nr_cpu_ids ? cpu : WORK_CPU_UNBOUND; } /** * queue_work_node - queue work on a "random" cpu for a given NUMA node * @node: NUMA node that we are targeting the work for * @wq: workqueue to use * @work: work to queue * * We queue the work to a "random" CPU within a given NUMA node. The basic * idea here is to provide a way to somehow associate work with a given * NUMA node. * * This function will only make a best effort attempt at getting this onto * the right NUMA node. If no node is requested or the requested node is * offline then we just fall back to standard queue_work behavior. * * Currently the "random" CPU ends up being the first available CPU in the * intersection of cpu_online_mask and the cpumask of the node, unless we * are running on the node. In that case we just use the current CPU. * * Return: %false if @work was already on a queue, %true otherwise. */ bool queue_work_node(int node, struct workqueue_struct *wq, struct work_struct *work) { unsigned long irq_flags; bool ret = false; /* * This current implementation is specific to unbound workqueues. * Specifically we only return the first available CPU for a given * node instead of cycling through individual CPUs within the node. * * If this is used with a per-cpu workqueue then the logic in * workqueue_select_cpu_near would need to be updated to allow for * some round robin type logic. */ WARN_ON_ONCE(!(wq->flags & WQ_UNBOUND)); local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { int cpu = select_numa_node_cpu(node); __queue_work(cpu, wq, work); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(queue_work_node); void delayed_work_timer_fn(struct timer_list *t) { struct delayed_work *dwork = from_timer(dwork, t, timer); /* should have been called from irqsafe timer with irq already off */ __queue_work(dwork->cpu, dwork->wq, &dwork->work); } EXPORT_SYMBOL(delayed_work_timer_fn); static void __queue_delayed_work(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct timer_list *timer = &dwork->timer; struct work_struct *work = &dwork->work; WARN_ON_ONCE(!wq); WARN_ON_ONCE(timer->function != delayed_work_timer_fn); WARN_ON_ONCE(timer_pending(timer)); WARN_ON_ONCE(!list_empty(&work->entry)); /* * If @delay is 0, queue @dwork->work immediately. This is for * both optimization and correctness. The earliest @timer can * expire is on the closest next tick and delayed_work users depend * on that there's no such delay when @delay is 0. */ if (!delay) { __queue_work(cpu, wq, &dwork->work); return; } dwork->wq = wq; dwork->cpu = cpu; timer->expires = jiffies + delay; if (housekeeping_enabled(HK_TYPE_TIMER)) { /* If the current cpu is a housekeeping cpu, use it. */ cpu = smp_processor_id(); if (!housekeeping_test_cpu(cpu, HK_TYPE_TIMER)) cpu = housekeeping_any_cpu(HK_TYPE_TIMER); add_timer_on(timer, cpu); } else { if (likely(cpu == WORK_CPU_UNBOUND)) add_timer_global(timer); else add_timer_on(timer, cpu); } } /** * queue_delayed_work_on - queue work on specific CPU after delay * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * Return: %false if @work was already on a queue, %true otherwise. If * @delay is zero and @dwork is idle, it will be scheduled for immediate * execution. */ bool queue_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { struct work_struct *work = &dwork->work; bool ret = false; unsigned long irq_flags; /* read the comment in __queue_work() */ local_irq_save(irq_flags); if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !clear_pending_if_disabled(work)) { __queue_delayed_work(cpu, wq, dwork, delay); ret = true; } local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL(queue_delayed_work_on); /** * mod_delayed_work_on - modify delay of or queue a delayed work on specific CPU * @cpu: CPU number to execute work on * @wq: workqueue to use * @dwork: work to queue * @delay: number of jiffies to wait before queueing * * If @dwork is idle, equivalent to queue_delayed_work_on(); otherwise, * modify @dwork's timer so that it expires after @delay. If @delay is * zero, @work is guaranteed to be scheduled immediately regardless of its * current state. * * Return: %false if @dwork was idle and queued, %true if @dwork was * pending and its timer was modified. * * This function is safe to call from any context including IRQ handler. * See try_to_grab_pending() for details. */ bool mod_delayed_work_on(int cpu, struct workqueue_struct *wq, struct delayed_work *dwork, unsigned long delay) { unsigned long irq_flags; bool ret; ret = work_grab_pending(&dwork->work, WORK_CANCEL_DELAYED, &irq_flags); if (!clear_pending_if_disabled(&dwork->work)) __queue_delayed_work(cpu, wq, dwork, delay); local_irq_restore(irq_flags); return ret; } EXPORT_SYMBOL_GPL(mod_delayed_work_on); static void rcu_work_rcufn(struct rcu_head *rcu) { struct rcu_work *rwork = container_of(rcu, struct rcu_work, rcu); /* read the comment in __queue_work() */ local_irq_disable(); __queue_work(WORK_CPU_UNBOUND, rwork->wq, &rwork->work); local_irq_enable(); } /** * queue_rcu_work - queue work after a RCU grace period * @wq: workqueue to use * @rwork: work to queue * * Return: %false if @rwork was already pending, %true otherwise. Note * that a full RCU grace period is guaranteed only after a %true return. * While @rwork is guaranteed to be executed after a %false return, the * execution may happen before a full RCU grace period has passed. */ bool queue_rcu_work(struct workqueue_struct *wq, struct rcu_work *rwork) { struct work_struct *work = &rwork->work; /* * rcu_work can't be canceled or disabled. Warn if the user reached * inside @rwork and disabled the inner work. */ if (!test_and_set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(work)) && !WARN_ON_ONCE(clear_pending_if_disabled(work))) { rwork->wq = wq; call_rcu_hurry(&rwork->rcu, rcu_work_rcufn); return true; } return false; } EXPORT_SYMBOL(queue_rcu_work); static struct worker *alloc_worker(int node) { struct worker *worker; worker = kzalloc_node(sizeof(*worker), GFP_KERNEL, node); if (worker) { INIT_LIST_HEAD(&worker->entry); INIT_LIST_HEAD(&worker->scheduled); INIT_LIST_HEAD(&worker->node); /* on creation a worker is in !idle && prep state */ worker->flags = WORKER_PREP; } return worker; } static cpumask_t *pool_allowed_cpus(struct worker_pool *pool) { if (pool->cpu < 0 && pool->attrs->affn_strict) return pool->attrs->__pod_cpumask; else return pool->attrs->cpumask; } /** * worker_attach_to_pool() - attach a worker to a pool * @worker: worker to be attached * @pool: the target pool * * Attach @worker to @pool. Once attached, the %WORKER_UNBOUND flag and * cpu-binding of @worker are kept coordinated with the pool across * cpu-[un]hotplugs. */ static void worker_attach_to_pool(struct worker *worker, struct worker_pool *pool) { mutex_lock(&wq_pool_attach_mutex); /* * The wq_pool_attach_mutex ensures %POOL_DISASSOCIATED remains stable * across this function. See the comments above the flag definition for * details. BH workers are, while per-CPU, always DISASSOCIATED. */ if (pool->flags & POOL_DISASSOCIATED) { worker->flags |= WORKER_UNBOUND; } else { WARN_ON_ONCE(pool->flags & POOL_BH); kthread_set_per_cpu(worker->task, pool->cpu); } if (worker->rescue_wq) set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)); list_add_tail(&worker->node, &pool->workers); worker->pool = pool; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_detach_from_pool() - detach a worker from its pool * @worker: worker which is attached to its pool * * Undo the attaching which had been done in worker_attach_to_pool(). The * caller worker shouldn't access to the pool after detached except it has * other reference to the pool. */ static void worker_detach_from_pool(struct worker *worker) { struct worker_pool *pool = worker->pool; struct completion *detach_completion = NULL; /* there is one permanent BH worker per CPU which should never detach */ WARN_ON_ONCE(pool->flags & POOL_BH); mutex_lock(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); list_del(&worker->node); worker->pool = NULL; if (list_empty(&pool->workers) && list_empty(&pool->dying_workers)) detach_completion = pool->detach_completion; mutex_unlock(&wq_pool_attach_mutex); /* clear leftover flags without pool->lock after it is detached */ worker->flags &= ~(WORKER_UNBOUND | WORKER_REBOUND); if (detach_completion) complete(detach_completion); } static int format_worker_id(char *buf, size_t size, struct worker *worker, struct worker_pool *pool) { if (worker->rescue_wq) return scnprintf(buf, size, "kworker/R-%s", worker->rescue_wq->name); if (pool) { if (pool->cpu >= 0) return scnprintf(buf, size, "kworker/%d:%d%s", pool->cpu, worker->id, pool->attrs->nice < 0 ? "H" : ""); else return scnprintf(buf, size, "kworker/u%d:%d", pool->id, worker->id); } else { return scnprintf(buf, size, "kworker/dying"); } } /** * create_worker - create a new workqueue worker * @pool: pool the new worker will belong to * * Create and start a new worker which is attached to @pool. * * CONTEXT: * Might sleep. Does GFP_KERNEL allocations. * * Return: * Pointer to the newly created worker. */ static struct worker *create_worker(struct worker_pool *pool) { struct worker *worker; int id; /* ID is needed to determine kthread name */ id = ida_alloc(&pool->worker_ida, GFP_KERNEL); if (id < 0) { pr_err_once("workqueue: Failed to allocate a worker ID: %pe\n", ERR_PTR(id)); return NULL; } worker = alloc_worker(pool->node); if (!worker) { pr_err_once("workqueue: Failed to allocate a worker\n"); goto fail; } worker->id = id; if (!(pool->flags & POOL_BH)) { char id_buf[WORKER_ID_LEN]; format_worker_id(id_buf, sizeof(id_buf), worker, pool); worker->task = kthread_create_on_node(worker_thread, worker, pool->node, "%s", id_buf); if (IS_ERR(worker->task)) { if (PTR_ERR(worker->task) == -EINTR) { pr_err("workqueue: Interrupted when creating a worker thread \"%s\"\n", id_buf); } else { pr_err_once("workqueue: Failed to create a worker thread: %pe", worker->task); } goto fail; } set_user_nice(worker->task, pool->attrs->nice); kthread_bind_mask(worker->task, pool_allowed_cpus(pool)); } /* successful, attach the worker to the pool */ worker_attach_to_pool(worker, pool); /* start the newly created worker */ raw_spin_lock_irq(&pool->lock); worker->pool->nr_workers++; worker_enter_idle(worker); /* * @worker is waiting on a completion in kthread() and will trigger hung * check if not woken up soon. As kick_pool() is noop if @pool is empty, * wake it up explicitly. */ if (worker->task) wake_up_process(worker->task); raw_spin_unlock_irq(&pool->lock); return worker; fail: ida_free(&pool->worker_ida, id); kfree(worker); return NULL; } static void unbind_worker(struct worker *worker) { lockdep_assert_held(&wq_pool_attach_mutex); kthread_set_per_cpu(worker->task, -1); if (cpumask_intersects(wq_unbound_cpumask, cpu_active_mask)) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, wq_unbound_cpumask) < 0); else WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, cpu_possible_mask) < 0); } static void wake_dying_workers(struct list_head *cull_list) { struct worker *worker, *tmp; list_for_each_entry_safe(worker, tmp, cull_list, entry) { list_del_init(&worker->entry); unbind_worker(worker); /* * If the worker was somehow already running, then it had to be * in pool->idle_list when set_worker_dying() happened or we * wouldn't have gotten here. * * Thus, the worker must either have observed the WORKER_DIE * flag, or have set its state to TASK_IDLE. Either way, the * below will be observed by the worker and is safe to do * outside of pool->lock. */ wake_up_process(worker->task); } } /** * set_worker_dying - Tag a worker for destruction * @worker: worker to be destroyed * @list: transfer worker away from its pool->idle_list and into list * * Tag @worker for destruction and adjust @pool stats accordingly. The worker * should be idle. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void set_worker_dying(struct worker *worker, struct list_head *list) { struct worker_pool *pool = worker->pool; lockdep_assert_held(&pool->lock); lockdep_assert_held(&wq_pool_attach_mutex); /* sanity check frenzy */ if (WARN_ON(worker->current_work) || WARN_ON(!list_empty(&worker->scheduled)) || WARN_ON(!(worker->flags & WORKER_IDLE))) return; pool->nr_workers--; pool->nr_idle--; worker->flags |= WORKER_DIE; list_move(&worker->entry, list); list_move(&worker->node, &pool->dying_workers); } /** * idle_worker_timeout - check if some idle workers can now be deleted. * @t: The pool's idle_timer that just expired * * The timer is armed in worker_enter_idle(). Note that it isn't disarmed in * worker_leave_idle(), as a worker flicking between idle and active while its * pool is at the too_many_workers() tipping point would cause too much timer * housekeeping overhead. Since IDLE_WORKER_TIMEOUT is long enough, we just let * it expire and re-evaluate things from there. */ static void idle_worker_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, idle_timer); bool do_cull = false; if (work_pending(&pool->idle_cull_work)) return; raw_spin_lock_irq(&pool->lock); if (too_many_workers(pool)) { struct worker *worker; unsigned long expires; /* idle_list is kept in LIFO order, check the last one */ worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; do_cull = !time_before(jiffies, expires); if (!do_cull) mod_timer(&pool->idle_timer, expires); } raw_spin_unlock_irq(&pool->lock); if (do_cull) queue_work(system_unbound_wq, &pool->idle_cull_work); } /** * idle_cull_fn - cull workers that have been idle for too long. * @work: the pool's work for handling these idle workers * * This goes through a pool's idle workers and gets rid of those that have been * idle for at least IDLE_WORKER_TIMEOUT seconds. * * We don't want to disturb isolated CPUs because of a pcpu kworker being * culled, so this also resets worker affinity. This requires a sleepable * context, hence the split between timer callback and work item. */ static void idle_cull_fn(struct work_struct *work) { struct worker_pool *pool = container_of(work, struct worker_pool, idle_cull_work); LIST_HEAD(cull_list); /* * Grabbing wq_pool_attach_mutex here ensures an already-running worker * cannot proceed beyong worker_detach_from_pool() in its self-destruct * path. This is required as a previously-preempted worker could run after * set_worker_dying() has happened but before wake_dying_workers() did. */ mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); while (too_many_workers(pool)) { struct worker *worker; unsigned long expires; worker = list_last_entry(&pool->idle_list, struct worker, entry); expires = worker->last_active + IDLE_WORKER_TIMEOUT; if (time_before(jiffies, expires)) { mod_timer(&pool->idle_timer, expires); break; } set_worker_dying(worker, &cull_list); } raw_spin_unlock_irq(&pool->lock); wake_dying_workers(&cull_list); mutex_unlock(&wq_pool_attach_mutex); } static void send_mayday(struct work_struct *work) { struct pool_workqueue *pwq = get_work_pwq(work); struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq_mayday_lock); if (!wq->rescuer) return; /* mayday mayday mayday */ if (list_empty(&pwq->mayday_node)) { /* * If @pwq is for an unbound wq, its base ref may be put at * any time due to an attribute change. Pin @pwq until the * rescuer is done with it. */ get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); wake_up_process(wq->rescuer->task); pwq->stats[PWQ_STAT_MAYDAY]++; } } static void pool_mayday_timeout(struct timer_list *t) { struct worker_pool *pool = from_timer(pool, t, mayday_timer); struct work_struct *work; raw_spin_lock_irq(&pool->lock); raw_spin_lock(&wq_mayday_lock); /* for wq->maydays */ if (need_to_create_worker(pool)) { /* * We've been trying to create a new worker but * haven't been successful. We might be hitting an * allocation deadlock. Send distress signals to * rescuers. */ list_for_each_entry(work, &pool->worklist, entry) send_mayday(work); } raw_spin_unlock(&wq_mayday_lock); raw_spin_unlock_irq(&pool->lock); mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INTERVAL); } /** * maybe_create_worker - create a new worker if necessary * @pool: pool to create a new worker for * * Create a new worker for @pool if necessary. @pool is guaranteed to * have at least one idle worker on return from this function. If * creating a new worker takes longer than MAYDAY_INTERVAL, mayday is * sent to all rescuers with works scheduled on @pool to resolve * possible allocation deadlock. * * On return, need_to_create_worker() is guaranteed to be %false and * may_start_working() %true. * * LOCKING: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. Called only from * manager. */ static void maybe_create_worker(struct worker_pool *pool) __releases(&pool->lock) __acquires(&pool->lock) { restart: raw_spin_unlock_irq(&pool->lock); /* if we don't make progress in MAYDAY_INITIAL_TIMEOUT, call for help */ mod_timer(&pool->mayday_timer, jiffies + MAYDAY_INITIAL_TIMEOUT); while (true) { if (create_worker(pool) || !need_to_create_worker(pool)) break; schedule_timeout_interruptible(CREATE_COOLDOWN); if (!need_to_create_worker(pool)) break; } del_timer_sync(&pool->mayday_timer); raw_spin_lock_irq(&pool->lock); /* * This is necessary even after a new worker was just successfully * created as @pool->lock was dropped and the new worker might have * already become busy. */ if (need_to_create_worker(pool)) goto restart; } /** * manage_workers - manage worker pool * @worker: self * * Assume the manager role and manage the worker pool @worker belongs * to. At any given time, there can be only zero or one manager per * pool. The exclusion is handled automatically by this function. * * The caller can safely start processing works on false return. On * true return, it's guaranteed that need_to_create_worker() is false * and may_start_working() is true. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. Does GFP_KERNEL allocations. * * Return: * %false if the pool doesn't need management and the caller can safely * start processing works, %true if management function was performed and * the conditions that the caller verified before calling the function may * no longer be true. */ static bool manage_workers(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & POOL_MANAGER_ACTIVE) return false; pool->flags |= POOL_MANAGER_ACTIVE; pool->manager = worker; maybe_create_worker(pool); pool->manager = NULL; pool->flags &= ~POOL_MANAGER_ACTIVE; rcuwait_wake_up(&manager_wait); return true; } /** * process_one_work - process single work * @worker: self * @work: work to process * * Process @work. This function contains all the logics necessary to * process a single work including synchronization against and * interaction with other workers on the same cpu, queueing and * flushing. As long as context requirement is met, any worker can * call this function to process a work. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which is released and regrabbed. */ static void process_one_work(struct worker *worker, struct work_struct *work) __releases(&pool->lock) __acquires(&pool->lock) { struct pool_workqueue *pwq = get_work_pwq(work); struct worker_pool *pool = worker->pool; unsigned long work_data; int lockdep_start_depth, rcu_start_depth; bool bh_draining = pool->flags & POOL_BH_DRAINING; #ifdef CONFIG_LOCKDEP /* * It is permissible to free the struct work_struct from * inside the function that is called from it, this we need to * take into account for lockdep too. To avoid bogus "held * lock freed" warnings as well as problems when looking into * work->lockdep_map, make a copy and use that here. */ struct lockdep_map lockdep_map; lockdep_copy_map(&lockdep_map, &work->lockdep_map); #endif /* ensure we're on the correct CPU */ WARN_ON_ONCE(!(pool->flags & POOL_DISASSOCIATED) && raw_smp_processor_id() != pool->cpu); /* claim and dequeue */ debug_work_deactivate(work); hash_add(pool->busy_hash, &worker->hentry, (unsigned long)work); worker->current_work = work; worker->current_func = work->func; worker->current_pwq = pwq; if (worker->task) worker->current_at = worker->task->se.sum_exec_runtime; work_data = *work_data_bits(work); worker->current_color = get_work_color(work_data); /* * Record wq name for cmdline and debug reporting, may get * overridden through set_worker_desc(). */ strscpy(worker->desc, pwq->wq->name, WORKER_DESC_LEN); list_del_init(&work->entry); /* * CPU intensive works don't participate in concurrency management. * They're the scheduler's responsibility. This takes @worker out * of concurrency management and the next code block will chain * execution of the pending work items. */ if (unlikely(pwq->wq->flags & WQ_CPU_INTENSIVE)) worker_set_flags(worker, WORKER_CPU_INTENSIVE); /* * Kick @pool if necessary. It's always noop for per-cpu worker pools * since nr_running would always be >= 1 at this point. This is used to * chain execution of the pending work items for WORKER_NOT_RUNNING * workers such as the UNBOUND and CPU_INTENSIVE ones. */ kick_pool(pool); /* * Record the last pool and clear PENDING which should be the last * update to @work. Also, do this inside @pool->lock so that * PENDING and queued state changes happen together while IRQ is * disabled. */ set_work_pool_and_clear_pending(work, pool->id, pool_offq_flags(pool)); pwq->stats[PWQ_STAT_STARTED]++; raw_spin_unlock_irq(&pool->lock); rcu_start_depth = rcu_preempt_depth(); lockdep_start_depth = lockdep_depth(current); /* see drain_dead_softirq_workfn() */ if (!bh_draining) lock_map_acquire(&pwq->wq->lockdep_map); lock_map_acquire(&lockdep_map); /* * Strictly speaking we should mark the invariant state without holding * any locks, that is, before these two lock_map_acquire()'s. * * However, that would result in: * * A(W1) * WFC(C) * A(W1) * C(C) * * Which would create W1->C->W1 dependencies, even though there is no * actual deadlock possible. There are two solutions, using a * read-recursive acquire on the work(queue) 'locks', but this will then * hit the lockdep limitation on recursive locks, or simply discard * these locks. * * AFAICT there is no possible deadlock scenario between the * flush_work() and complete() primitives (except for single-threaded * workqueues), so hiding them isn't a problem. */ lockdep_invariant_state(true); trace_workqueue_execute_start(work); worker->current_func(work); /* * While we must be careful to not use "work" after this, the trace * point will only record its address. */ trace_workqueue_execute_end(work, worker->current_func); pwq->stats[PWQ_STAT_COMPLETED]++; lock_map_release(&lockdep_map); if (!bh_draining) lock_map_release(&pwq->wq->lockdep_map); if (unlikely((worker->task && in_atomic()) || lockdep_depth(current) != lockdep_start_depth || rcu_preempt_depth() != rcu_start_depth)) { pr_err("BUG: workqueue leaked atomic, lock or RCU: %s[%d]\n" " preempt=0x%08x lock=%d->%d RCU=%d->%d workfn=%ps\n", current->comm, task_pid_nr(current), preempt_count(), lockdep_start_depth, lockdep_depth(current), rcu_start_depth, rcu_preempt_depth(), worker->current_func); debug_show_held_locks(current); dump_stack(); } /* * The following prevents a kworker from hogging CPU on !PREEMPTION * kernels, where a requeueing work item waiting for something to * happen could deadlock with stop_machine as such work item could * indefinitely requeue itself while all other CPUs are trapped in * stop_machine. At the same time, report a quiescent RCU state so * the same condition doesn't freeze RCU. */ if (worker->task) cond_resched(); raw_spin_lock_irq(&pool->lock); /* * In addition to %WQ_CPU_INTENSIVE, @worker may also have been marked * CPU intensive by wq_worker_tick() if @work hogged CPU longer than * wq_cpu_intensive_thresh_us. Clear it. */ worker_clr_flags(worker, WORKER_CPU_INTENSIVE); /* tag the worker for identification in schedule() */ worker->last_func = worker->current_func; /* we're done with it, release */ hash_del(&worker->hentry); worker->current_work = NULL; worker->current_func = NULL; worker->current_pwq = NULL; worker->current_color = INT_MAX; /* must be the last step, see the function comment */ pwq_dec_nr_in_flight(pwq, work_data); } /** * process_scheduled_works - process scheduled works * @worker: self * * Process all scheduled works. Please note that the scheduled list * may change while processing a work, so this function repeatedly * fetches a work from the top and executes it. * * CONTEXT: * raw_spin_lock_irq(pool->lock) which may be released and regrabbed * multiple times. */ static void process_scheduled_works(struct worker *worker) { struct work_struct *work; bool first = true; while ((work = list_first_entry_or_null(&worker->scheduled, struct work_struct, entry))) { if (first) { worker->pool->watchdog_ts = jiffies; first = false; } process_one_work(worker, work); } } static void set_pf_worker(bool val) { mutex_lock(&wq_pool_attach_mutex); if (val) current->flags |= PF_WQ_WORKER; else current->flags &= ~PF_WQ_WORKER; mutex_unlock(&wq_pool_attach_mutex); } /** * worker_thread - the worker thread function * @__worker: self * * The worker thread function. All workers belong to a worker_pool - * either a per-cpu one or dynamic unbound one. These workers process all * work items regardless of their specific target workqueue. The only * exception is work items which belong to workqueues with a rescuer which * will be explained in rescuer_thread(). * * Return: 0 */ static int worker_thread(void *__worker) { struct worker *worker = __worker; struct worker_pool *pool = worker->pool; /* tell the scheduler that this is a workqueue worker */ set_pf_worker(true); woke_up: raw_spin_lock_irq(&pool->lock); /* am I supposed to die? */ if (unlikely(worker->flags & WORKER_DIE)) { raw_spin_unlock_irq(&pool->lock); set_pf_worker(false); ida_free(&pool->worker_ida, worker->id); worker_detach_from_pool(worker); WARN_ON_ONCE(!list_empty(&worker->entry)); kfree(worker); return 0; } worker_leave_idle(worker); recheck: /* no more worker necessary? */ if (!need_more_worker(pool)) goto sleep; /* do we need to manage? */ if (unlikely(!may_start_working(pool)) && manage_workers(worker)) goto recheck; /* * ->scheduled list can only be filled while a worker is * preparing to process a work or actually processing it. * Make sure nobody diddled with it while I was sleeping. */ WARN_ON_ONCE(!list_empty(&worker->scheduled)); /* * Finish PREP stage. We're guaranteed to have at least one idle * worker or that someone else has already assumed the manager * role. This is where @worker starts participating in concurrency * management if applicable and concurrency management is restored * after being rebound. See rebind_workers() for details. */ worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool)); worker_set_flags(worker, WORKER_PREP); sleep: /* * pool->lock is held and there's no work to process and no need to * manage, sleep. Workers are woken up only while holding * pool->lock or from local cpu, so setting the current state * before releasing pool->lock is enough to prevent losing any * event. */ worker_enter_idle(worker); __set_current_state(TASK_IDLE); raw_spin_unlock_irq(&pool->lock); schedule(); goto woke_up; } /** * rescuer_thread - the rescuer thread function * @__rescuer: self * * Workqueue rescuer thread function. There's one rescuer for each * workqueue which has WQ_MEM_RECLAIM set. * * Regular work processing on a pool may block trying to create a new * worker which uses GFP_KERNEL allocation which has slight chance of * developing into deadlock if some works currently on the same queue * need to be processed to satisfy the GFP_KERNEL allocation. This is * the problem rescuer solves. * * When such condition is possible, the pool summons rescuers of all * workqueues which have works queued on the pool and let them process * those works so that forward progress can be guaranteed. * * This should happen rarely. * * Return: 0 */ static int rescuer_thread(void *__rescuer) { struct worker *rescuer = __rescuer; struct workqueue_struct *wq = rescuer->rescue_wq; bool should_stop; set_user_nice(current, RESCUER_NICE_LEVEL); /* * Mark rescuer as worker too. As WORKER_PREP is never cleared, it * doesn't participate in concurrency management. */ set_pf_worker(true); repeat: set_current_state(TASK_IDLE); /* * By the time the rescuer is requested to stop, the workqueue * shouldn't have any work pending, but @wq->maydays may still have * pwq(s) queued. This can happen by non-rescuer workers consuming * all the work items before the rescuer got to them. Go through * @wq->maydays processing before acting on should_stop so that the * list is always empty on exit. */ should_stop = kthread_should_stop(); /* see whether any pwq is asking for help */ raw_spin_lock_irq(&wq_mayday_lock); while (!list_empty(&wq->maydays)) { struct pool_workqueue *pwq = list_first_entry(&wq->maydays, struct pool_workqueue, mayday_node); struct worker_pool *pool = pwq->pool; struct work_struct *work, *n; __set_current_state(TASK_RUNNING); list_del_init(&pwq->mayday_node); raw_spin_unlock_irq(&wq_mayday_lock); worker_attach_to_pool(rescuer, pool); raw_spin_lock_irq(&pool->lock); /* * Slurp in all works issued via this workqueue and * process'em. */ WARN_ON_ONCE(!list_empty(&rescuer->scheduled)); list_for_each_entry_safe(work, n, &pool->worklist, entry) { if (get_work_pwq(work) == pwq && assign_work(work, rescuer, &n)) pwq->stats[PWQ_STAT_RESCUED]++; } if (!list_empty(&rescuer->scheduled)) { process_scheduled_works(rescuer); /* * The above execution of rescued work items could * have created more to rescue through * pwq_activate_first_inactive() or chained * queueing. Let's put @pwq back on mayday list so * that such back-to-back work items, which may be * being used to relieve memory pressure, don't * incur MAYDAY_INTERVAL delay inbetween. */ if (pwq->nr_active && need_to_create_worker(pool)) { raw_spin_lock(&wq_mayday_lock); /* * Queue iff we aren't racing destruction * and somebody else hasn't queued it already. */ if (wq->rescuer && list_empty(&pwq->mayday_node)) { get_pwq(pwq); list_add_tail(&pwq->mayday_node, &wq->maydays); } raw_spin_unlock(&wq_mayday_lock); } } /* * Put the reference grabbed by send_mayday(). @pool won't * go away while we're still attached to it. */ put_pwq(pwq); /* * Leave this pool. Notify regular workers; otherwise, we end up * with 0 concurrency and stalling the execution. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); worker_detach_from_pool(rescuer); raw_spin_lock_irq(&wq_mayday_lock); } raw_spin_unlock_irq(&wq_mayday_lock); if (should_stop) { __set_current_state(TASK_RUNNING); set_pf_worker(false); return 0; } /* rescuers should never participate in concurrency management */ WARN_ON_ONCE(!(rescuer->flags & WORKER_NOT_RUNNING)); schedule(); goto repeat; } static void bh_worker(struct worker *worker) { struct worker_pool *pool = worker->pool; int nr_restarts = BH_WORKER_RESTARTS; unsigned long end = jiffies + BH_WORKER_JIFFIES; raw_spin_lock_irq(&pool->lock); worker_leave_idle(worker); /* * This function follows the structure of worker_thread(). See there for * explanations on each step. */ if (!need_more_worker(pool)) goto done; WARN_ON_ONCE(!list_empty(&worker->scheduled)); worker_clr_flags(worker, WORKER_PREP | WORKER_REBOUND); do { struct work_struct *work = list_first_entry(&pool->worklist, struct work_struct, entry); if (assign_work(work, worker, NULL)) process_scheduled_works(worker); } while (keep_working(pool) && --nr_restarts && time_before(jiffies, end)); worker_set_flags(worker, WORKER_PREP); done: worker_enter_idle(worker); kick_pool(pool); raw_spin_unlock_irq(&pool->lock); } /* * TODO: Convert all tasklet users to workqueue and use softirq directly. * * This is currently called from tasklet[_hi]action() and thus is also called * whenever there are tasklets to run. Let's do an early exit if there's nothing * queued. Once conversion from tasklet is complete, the need_more_worker() test * can be dropped. * * After full conversion, we'll add worker->softirq_action, directly use the * softirq action and obtain the worker pointer from the softirq_action pointer. */ void workqueue_softirq_action(bool highpri) { struct worker_pool *pool = &per_cpu(bh_worker_pools, smp_processor_id())[highpri]; if (need_more_worker(pool)) bh_worker(list_first_entry(&pool->workers, struct worker, node)); } struct wq_drain_dead_softirq_work { struct work_struct work; struct worker_pool *pool; struct completion done; }; static void drain_dead_softirq_workfn(struct work_struct *work) { struct wq_drain_dead_softirq_work *dead_work = container_of(work, struct wq_drain_dead_softirq_work, work); struct worker_pool *pool = dead_work->pool; bool repeat; /* * @pool's CPU is dead and we want to execute its still pending work * items from this BH work item which is running on a different CPU. As * its CPU is dead, @pool can't be kicked and, as work execution path * will be nested, a lockdep annotation needs to be suppressed. Mark * @pool with %POOL_BH_DRAINING for the special treatments. */ raw_spin_lock_irq(&pool->lock); pool->flags |= POOL_BH_DRAINING; raw_spin_unlock_irq(&pool->lock); bh_worker(list_first_entry(&pool->workers, struct worker, node)); raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_BH_DRAINING; repeat = need_more_worker(pool); raw_spin_unlock_irq(&pool->lock); /* * bh_worker() might hit consecutive execution limit and bail. If there * still are pending work items, reschedule self and return so that we * don't hog this CPU's BH. */ if (repeat) { if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, work); else queue_work(system_bh_wq, work); } else { complete(&dead_work->done); } } /* * @cpu is dead. Drain the remaining BH work items on the current CPU. It's * possible to allocate dead_work per CPU and avoid flushing. However, then we * have to worry about draining overlapping with CPU coming back online or * nesting (one CPU's dead_work queued on another CPU which is also dead and so * on). Let's keep it simple and drain them synchronously. These are BH work * items which shouldn't be requeued on the same pool. Shouldn't take long. */ void workqueue_softirq_dead(unsigned int cpu) { int i; for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct worker_pool *pool = &per_cpu(bh_worker_pools, cpu)[i]; struct wq_drain_dead_softirq_work dead_work; if (!need_more_worker(pool)) continue; INIT_WORK_ONSTACK(&dead_work.work, drain_dead_softirq_workfn); dead_work.pool = pool; init_completion(&dead_work.done); if (pool->attrs->nice == HIGHPRI_NICE_LEVEL) queue_work(system_bh_highpri_wq, &dead_work.work); else queue_work(system_bh_wq, &dead_work.work); wait_for_completion(&dead_work.done); destroy_work_on_stack(&dead_work.work); } } /** * check_flush_dependency - check for flush dependency sanity * @target_wq: workqueue being flushed * @target_work: work item being flushed (NULL for workqueue flushes) * * %current is trying to flush the whole @target_wq or @target_work on it. * If @target_wq doesn't have %WQ_MEM_RECLAIM, verify that %current is not * reclaiming memory or running on a workqueue which doesn't have * %WQ_MEM_RECLAIM as that can break forward-progress guarantee leading to * a deadlock. */ static void check_flush_dependency(struct workqueue_struct *target_wq, struct work_struct *target_work) { work_func_t target_func = target_work ? target_work->func : NULL; struct worker *worker; if (target_wq->flags & WQ_MEM_RECLAIM) return; worker = current_wq_worker(); WARN_ONCE(current->flags & PF_MEMALLOC, "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%ps", current->pid, current->comm, target_wq->name, target_func); WARN_ONCE(worker && ((worker->current_pwq->wq->flags & (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM), "workqueue: WQ_MEM_RECLAIM %s:%ps is flushing !WQ_MEM_RECLAIM %s:%ps", worker->current_pwq->wq->name, worker->current_func, target_wq->name, target_func); } struct wq_barrier { struct work_struct work; struct completion done; struct task_struct *task; /* purely informational */ }; static void wq_barrier_func(struct work_struct *work) { struct wq_barrier *barr = container_of(work, struct wq_barrier, work); complete(&barr->done); } /** * insert_wq_barrier - insert a barrier work * @pwq: pwq to insert barrier into * @barr: wq_barrier to insert * @target: target work to attach @barr to * @worker: worker currently executing @target, NULL if @target is not executing * * @barr is linked to @target such that @barr is completed only after * @target finishes execution. Please note that the ordering * guarantee is observed only with respect to @target and on the local * cpu. * * Currently, a queued barrier can't be canceled. This is because * try_to_grab_pending() can't determine whether the work to be * grabbed is at the head of the queue and thus can't clear LINKED * flag of the previous work while there must be a valid next work * after a work with LINKED flag set. * * Note that when @worker is non-NULL, @target may be modified * underneath us, so we can't reliably determine pwq from @target. * * CONTEXT: * raw_spin_lock_irq(pool->lock). */ static void insert_wq_barrier(struct pool_workqueue *pwq, struct wq_barrier *barr, struct work_struct *target, struct worker *worker) { static __maybe_unused struct lock_class_key bh_key, thr_key; unsigned int work_flags = 0; unsigned int work_color; struct list_head *head; /* * debugobject calls are safe here even with pool->lock locked * as we know for sure that this will not trigger any of the * checks and call back into the fixup functions where we * might deadlock. * * BH and threaded workqueues need separate lockdep keys to avoid * spuriously triggering "inconsistent {SOFTIRQ-ON-W} -> {IN-SOFTIRQ-W} * usage". */ INIT_WORK_ONSTACK_KEY(&barr->work, wq_barrier_func, (pwq->wq->flags & WQ_BH) ? &bh_key : &thr_key); __set_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&barr->work)); init_completion_map(&barr->done, &target->lockdep_map); barr->task = current; /* The barrier work item does not participate in nr_active. */ work_flags |= WORK_STRUCT_INACTIVE; /* * If @target is currently being executed, schedule the * barrier to the worker; otherwise, put it after @target. */ if (worker) { head = worker->scheduled.next; work_color = worker->current_color; } else { unsigned long *bits = work_data_bits(target); head = target->entry.next; /* there can already be other linked works, inherit and set */ work_flags |= *bits & WORK_STRUCT_LINKED; work_color = get_work_color(*bits); __set_bit(WORK_STRUCT_LINKED_BIT, bits); } pwq->nr_in_flight[work_color]++; work_flags |= work_color_to_flags(work_color); insert_work(pwq, &barr->work, head, work_flags); } /** * flush_workqueue_prep_pwqs - prepare pwqs for workqueue flushing * @wq: workqueue being flushed * @flush_color: new flush color, < 0 for no-op * @work_color: new work color, < 0 for no-op * * Prepare pwqs for workqueue flushing. * * If @flush_color is non-negative, flush_color on all pwqs should be * -1. If no pwq has in-flight commands at the specified color, all * pwq->flush_color's stay at -1 and %false is returned. If any pwq * has in flight commands, its pwq->flush_color is set to * @flush_color, @wq->nr_pwqs_to_flush is updated accordingly, pwq * wakeup logic is armed and %true is returned. * * The caller should have initialized @wq->first_flusher prior to * calling this function with non-negative @flush_color. If * @flush_color is negative, no flush color update is done and %false * is returned. * * If @work_color is non-negative, all pwqs should have the same * work_color which is previous to @work_color and all will be * advanced to @work_color. * * CONTEXT: * mutex_lock(wq->mutex). * * Return: * %true if @flush_color >= 0 and there's something to flush. %false * otherwise. */ static bool flush_workqueue_prep_pwqs(struct workqueue_struct *wq, int flush_color, int work_color) { bool wait = false; struct pool_workqueue *pwq; if (flush_color >= 0) { WARN_ON_ONCE(atomic_read(&wq->nr_pwqs_to_flush)); atomic_set(&wq->nr_pwqs_to_flush, 1); } for_each_pwq(pwq, wq) { struct worker_pool *pool = pwq->pool; raw_spin_lock_irq(&pool->lock); if (flush_color >= 0) { WARN_ON_ONCE(pwq->flush_color != -1); if (pwq->nr_in_flight[flush_color]) { pwq->flush_color = flush_color; atomic_inc(&wq->nr_pwqs_to_flush); wait = true; } } if (work_color >= 0) { WARN_ON_ONCE(work_color != work_next_color(pwq->work_color)); pwq->work_color = work_color; } raw_spin_unlock_irq(&pool->lock); } if (flush_color >= 0 && atomic_dec_and_test(&wq->nr_pwqs_to_flush)) complete(&wq->first_flusher->done); return wait; } static void touch_wq_lockdep_map(struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&wq->lockdep_map); lock_map_release(&wq->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } static void touch_work_lockdep_map(struct work_struct *work, struct workqueue_struct *wq) { #ifdef CONFIG_LOCKDEP if (wq->flags & WQ_BH) local_bh_disable(); lock_map_acquire(&work->lockdep_map); lock_map_release(&work->lockdep_map); if (wq->flags & WQ_BH) local_bh_enable(); #endif } /** * __flush_workqueue - ensure that any scheduled work has run to completion. * @wq: workqueue to flush * * This function sleeps until all work items which were queued on entry * have finished execution, but it is not livelocked by new incoming ones. */ void __flush_workqueue(struct workqueue_struct *wq) { struct wq_flusher this_flusher = { .list = LIST_HEAD_INIT(this_flusher.list), .flush_color = -1, .done = COMPLETION_INITIALIZER_ONSTACK_MAP(this_flusher.done, wq->lockdep_map), }; int next_color; if (WARN_ON(!wq_online)) return; touch_wq_lockdep_map(wq); mutex_lock(&wq->mutex); /* * Start-to-wait phase */ next_color = work_next_color(wq->work_color); if (next_color != wq->flush_color) { /* * Color space is not full. The current work_color * becomes our flush_color and work_color is advanced * by one. */ WARN_ON_ONCE(!list_empty(&wq->flusher_overflow)); this_flusher.flush_color = wq->work_color; wq->work_color = next_color; if (!wq->first_flusher) { /* no flush in progress, become the first flusher */ WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); wq->first_flusher = &this_flusher; if (!flush_workqueue_prep_pwqs(wq, wq->flush_color, wq->work_color)) { /* nothing to flush, done */ wq->flush_color = next_color; wq->first_flusher = NULL; goto out_unlock; } } else { /* wait in queue */ WARN_ON_ONCE(wq->flush_color == this_flusher.flush_color); list_add_tail(&this_flusher.list, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } } else { /* * Oops, color space is full, wait on overflow queue. * The next flush completion will assign us * flush_color and transfer to flusher_queue. */ list_add_tail(&this_flusher.list, &wq->flusher_overflow); } check_flush_dependency(wq, NULL); mutex_unlock(&wq->mutex); wait_for_completion(&this_flusher.done); /* * Wake-up-and-cascade phase * * First flushers are responsible for cascading flushes and * handling overflow. Non-first flushers can simply return. */ if (READ_ONCE(wq->first_flusher) != &this_flusher) return; mutex_lock(&wq->mutex); /* we might have raced, check again with mutex held */ if (wq->first_flusher != &this_flusher) goto out_unlock; WRITE_ONCE(wq->first_flusher, NULL); WARN_ON_ONCE(!list_empty(&this_flusher.list)); WARN_ON_ONCE(wq->flush_color != this_flusher.flush_color); while (true) { struct wq_flusher *next, *tmp; /* complete all the flushers sharing the current flush color */ list_for_each_entry_safe(next, tmp, &wq->flusher_queue, list) { if (next->flush_color != wq->flush_color) break; list_del_init(&next->list); complete(&next->done); } WARN_ON_ONCE(!list_empty(&wq->flusher_overflow) && wq->flush_color != work_next_color(wq->work_color)); /* this flush_color is finished, advance by one */ wq->flush_color = work_next_color(wq->flush_color); /* one color has been freed, handle overflow queue */ if (!list_empty(&wq->flusher_overflow)) { /* * Assign the same color to all overflowed * flushers, advance work_color and append to * flusher_queue. This is the start-to-wait * phase for these overflowed flushers. */ list_for_each_entry(tmp, &wq->flusher_overflow, list) tmp->flush_color = wq->work_color; wq->work_color = work_next_color(wq->work_color); list_splice_tail_init(&wq->flusher_overflow, &wq->flusher_queue); flush_workqueue_prep_pwqs(wq, -1, wq->work_color); } if (list_empty(&wq->flusher_queue)) { WARN_ON_ONCE(wq->flush_color != wq->work_color); break; } /* * Need to flush more colors. Make the next flusher * the new first flusher and arm pwqs. */ WARN_ON_ONCE(wq->flush_color == wq->work_color); WARN_ON_ONCE(wq->flush_color != next->flush_color); list_del_init(&next->list); wq->first_flusher = next; if (flush_workqueue_prep_pwqs(wq, wq->flush_color, -1)) break; /* * Meh... this color is already done, clear first * flusher and repeat cascading. */ wq->first_flusher = NULL; } out_unlock: mutex_unlock(&wq->mutex); } EXPORT_SYMBOL(__flush_workqueue); /** * drain_workqueue - drain a workqueue * @wq: workqueue to drain * * Wait until the workqueue becomes empty. While draining is in progress, * only chain queueing is allowed. IOW, only currently pending or running * work items on @wq can queue further work items on it. @wq is flushed * repeatedly until it becomes empty. The number of flushing is determined * by the depth of chaining and should be relatively short. Whine if it * takes too long. */ void drain_workqueue(struct workqueue_struct *wq) { unsigned int flush_cnt = 0; struct pool_workqueue *pwq; /* * __queue_work() needs to test whether there are drainers, is much * hotter than drain_workqueue() and already looks at @wq->flags. * Use __WQ_DRAINING so that queue doesn't have to check nr_drainers. */ mutex_lock(&wq->mutex); if (!wq->nr_drainers++) wq->flags |= __WQ_DRAINING; mutex_unlock(&wq->mutex); reflush: __flush_workqueue(wq); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { bool drained; raw_spin_lock_irq(&pwq->pool->lock); drained = pwq_is_empty(pwq); raw_spin_unlock_irq(&pwq->pool->lock); if (drained) continue; if (++flush_cnt == 10 || (flush_cnt % 100 == 0 && flush_cnt <= 1000)) pr_warn("workqueue %s: %s() isn't complete after %u tries\n", wq->name, __func__, flush_cnt); mutex_unlock(&wq->mutex); goto reflush; } if (!--wq->nr_drainers) wq->flags &= ~__WQ_DRAINING; mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(drain_workqueue); static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr, bool from_cancel) { struct worker *worker = NULL; struct worker_pool *pool; struct pool_workqueue *pwq; struct workqueue_struct *wq; rcu_read_lock(); pool = get_work_pool(work); if (!pool) { rcu_read_unlock(); return false; } raw_spin_lock_irq(&pool->lock); /* see the comment in try_to_grab_pending() with the same code */ pwq = get_work_pwq(work); if (pwq) { if (unlikely(pwq->pool != pool)) goto already_gone; } else { worker = find_worker_executing_work(pool, work); if (!worker) goto already_gone; pwq = worker->current_pwq; } wq = pwq->wq; check_flush_dependency(wq, work); insert_wq_barrier(pwq, barr, work, worker); raw_spin_unlock_irq(&pool->lock); touch_work_lockdep_map(work, wq); /* * Force a lock recursion deadlock when using flush_work() inside a * single-threaded or rescuer equipped workqueue. * * For single threaded workqueues the deadlock happens when the work * is after the work issuing the flush_work(). For rescuer equipped * workqueues the deadlock happens when the rescuer stalls, blocking * forward progress. */ if (!from_cancel && (wq->saved_max_active == 1 || wq->rescuer)) touch_wq_lockdep_map(wq); rcu_read_unlock(); return true; already_gone: raw_spin_unlock_irq(&pool->lock); rcu_read_unlock(); return false; } static bool __flush_work(struct work_struct *work, bool from_cancel) { struct wq_barrier barr; unsigned long data; if (WARN_ON(!wq_online)) return false; if (WARN_ON(!work->func)) return false; if (!start_flush_work(work, &barr, from_cancel)) return false; /* * start_flush_work() returned %true. If @from_cancel is set, we know * that @work must have been executing during start_flush_work() and * can't currently be queued. Its data must contain OFFQ bits. If @work * was queued on a BH workqueue, we also know that it was running in the * BH context and thus can be busy-waited. */ data = *work_data_bits(work); if (from_cancel && !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) { /* * On RT, prevent a live lock when %current preempted soft * interrupt processing or prevents ksoftirqd from running by * keeping flipping BH. If the BH work item runs on a different * CPU then this has no effect other than doing the BH * disable/enable dance for nothing. This is copied from * kernel/softirq.c::tasklet_unlock_spin_wait(). */ while (!try_wait_for_completion(&barr.done)) { if (IS_ENABLED(CONFIG_PREEMPT_RT)) { local_bh_disable(); local_bh_enable(); } else { cpu_relax(); } } } else { wait_for_completion(&barr.done); } destroy_work_on_stack(&barr.work); return true; } /** * flush_work - wait for a work to finish executing the last queueing instance * @work: the work to flush * * Wait until @work has finished execution. @work is guaranteed to be idle * on return if it hasn't been requeued since flush started. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_work(struct work_struct *work) { might_sleep(); return __flush_work(work, false); } EXPORT_SYMBOL_GPL(flush_work); /** * flush_delayed_work - wait for a dwork to finish executing the last queueing * @dwork: the delayed work to flush * * Delayed timer is cancelled and the pending work is queued for * immediate execution. Like flush_work(), this function only * considers the last queueing instance of @dwork. * * Return: * %true if flush_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_delayed_work(struct delayed_work *dwork) { local_irq_disable(); if (del_timer_sync(&dwork->timer)) __queue_work(dwork->cpu, dwork->wq, &dwork->work); local_irq_enable(); return flush_work(&dwork->work); } EXPORT_SYMBOL(flush_delayed_work); /** * flush_rcu_work - wait for a rwork to finish executing the last queueing * @rwork: the rcu work to flush * * Return: * %true if flush_rcu_work() waited for the work to finish execution, * %false if it was already idle. */ bool flush_rcu_work(struct rcu_work *rwork) { if (test_bit(WORK_STRUCT_PENDING_BIT, work_data_bits(&rwork->work))) { rcu_barrier(); flush_work(&rwork->work); return true; } else { return flush_work(&rwork->work); } } EXPORT_SYMBOL(flush_rcu_work); static void work_offqd_disable(struct work_offq_data *offqd) { const unsigned long max = (1lu << WORK_OFFQ_DISABLE_BITS) - 1; if (likely(offqd->disable < max)) offqd->disable++; else WARN_ONCE(true, "workqueue: work disable count overflowed\n"); } static void work_offqd_enable(struct work_offq_data *offqd) { if (likely(offqd->disable > 0)) offqd->disable--; else WARN_ONCE(true, "workqueue: work disable count underflowed\n"); } static bool __cancel_work(struct work_struct *work, u32 cflags) { struct work_offq_data offqd; unsigned long irq_flags; int ret; ret = work_grab_pending(work, cflags, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); if (cflags & WORK_CANCEL_DISABLE) work_offqd_disable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return ret; } static bool __cancel_work_sync(struct work_struct *work, u32 cflags) { bool ret; ret = __cancel_work(work, cflags | WORK_CANCEL_DISABLE); if (*work_data_bits(work) & WORK_OFFQ_BH) WARN_ON_ONCE(in_hardirq()); else might_sleep(); /* * Skip __flush_work() during early boot when we know that @work isn't * executing. This allows canceling during early boot. */ if (wq_online) __flush_work(work, true); if (!(cflags & WORK_CANCEL_DISABLE)) enable_work(work); return ret; } /* * See cancel_delayed_work() */ bool cancel_work(struct work_struct *work) { return __cancel_work(work, 0); } EXPORT_SYMBOL(cancel_work); /** * cancel_work_sync - cancel a work and wait for it to finish * @work: the work to cancel * * Cancel @work and wait for its execution to finish. This function can be used * even if the work re-queues itself or migrates to another workqueue. On return * from this function, @work is guaranteed to be not pending or executing on any * CPU as long as there aren't racing enqueues. * * cancel_work_sync(&delayed_work->work) must not be used for delayed_work's. * Use cancel_delayed_work_sync() instead. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool cancel_work_sync(struct work_struct *work) { return __cancel_work_sync(work, 0); } EXPORT_SYMBOL_GPL(cancel_work_sync); /** * cancel_delayed_work - cancel a delayed work * @dwork: delayed_work to cancel * * Kill off a pending delayed_work. * * Return: %true if @dwork was pending and canceled; %false if it wasn't * pending. * * Note: * The work callback function may still be running on return, unless * it returns %true and the work doesn't re-arm itself. Explicitly flush or * use cancel_delayed_work_sync() to wait on it. * * This function is safe to call from any context including IRQ handler. */ bool cancel_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work); /** * cancel_delayed_work_sync - cancel a delayed work and wait for it to finish * @dwork: the delayed work cancel * * This is cancel_work_sync() for delayed works. * * Return: * %true if @dwork was pending, %false otherwise. */ bool cancel_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED); } EXPORT_SYMBOL(cancel_delayed_work_sync); /** * disable_work - Disable and cancel a work item * @work: work item to disable * * Disable @work by incrementing its disable count and cancel it if currently * pending. As long as the disable count is non-zero, any attempt to queue @work * will fail and return %false. The maximum supported disable depth is 2 to the * power of %WORK_OFFQ_DISABLE_BITS, currently 65536. * * Can be called from any context. Returns %true if @work was pending, %false * otherwise. */ bool disable_work(struct work_struct *work) { return __cancel_work(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work); /** * disable_work_sync - Disable, cancel and drain a work item * @work: work item to disable * * Similar to disable_work() but also wait for @work to finish if currently * executing. * * Must be called from a sleepable context if @work was last queued on a non-BH * workqueue. Can also be called from non-hardirq atomic contexts including BH * if @work was last queued on a BH workqueue. * * Returns %true if @work was pending, %false otherwise. */ bool disable_work_sync(struct work_struct *work) { return __cancel_work_sync(work, WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_work_sync); /** * enable_work - Enable a work item * @work: work item to enable * * Undo disable_work[_sync]() by decrementing @work's disable count. @work can * only be queued if its disable count is 0. * * Can be called from any context. Returns %true if the disable count reached 0. * Otherwise, %false. */ bool enable_work(struct work_struct *work) { struct work_offq_data offqd; unsigned long irq_flags; work_grab_pending(work, 0, &irq_flags); work_offqd_unpack(&offqd, *work_data_bits(work)); work_offqd_enable(&offqd); set_work_pool_and_clear_pending(work, offqd.pool_id, work_offqd_pack_flags(&offqd)); local_irq_restore(irq_flags); return !offqd.disable; } EXPORT_SYMBOL_GPL(enable_work); /** * disable_delayed_work - Disable and cancel a delayed work item * @dwork: delayed work item to disable * * disable_work() for delayed work items. */ bool disable_delayed_work(struct delayed_work *dwork) { return __cancel_work(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work); /** * disable_delayed_work_sync - Disable, cancel and drain a delayed work item * @dwork: delayed work item to disable * * disable_work_sync() for delayed work items. */ bool disable_delayed_work_sync(struct delayed_work *dwork) { return __cancel_work_sync(&dwork->work, WORK_CANCEL_DELAYED | WORK_CANCEL_DISABLE); } EXPORT_SYMBOL_GPL(disable_delayed_work_sync); /** * enable_delayed_work - Enable a delayed work item * @dwork: delayed work item to enable * * enable_work() for delayed work items. */ bool enable_delayed_work(struct delayed_work *dwork) { return enable_work(&dwork->work); } EXPORT_SYMBOL_GPL(enable_delayed_work); /** * schedule_on_each_cpu - execute a function synchronously on each online CPU * @func: the function to call * * schedule_on_each_cpu() executes @func on each online CPU using the * system workqueue and blocks until all CPUs have completed. * schedule_on_each_cpu() is very slow. * * Return: * 0 on success, -errno on failure. */ int schedule_on_each_cpu(work_func_t func) { int cpu; struct work_struct __percpu *works; works = alloc_percpu(struct work_struct); if (!works) return -ENOMEM; cpus_read_lock(); for_each_online_cpu(cpu) { struct work_struct *work = per_cpu_ptr(works, cpu); INIT_WORK(work, func); schedule_work_on(cpu, work); } for_each_online_cpu(cpu) flush_work(per_cpu_ptr(works, cpu)); cpus_read_unlock(); free_percpu(works); return 0; } /** * execute_in_process_context - reliably execute the routine with user context * @fn: the function to execute * @ew: guaranteed storage for the execute work structure (must * be available when the work executes) * * Executes the function immediately if process context is available, * otherwise schedules the function for delayed execution. * * Return: 0 - function was executed * 1 - function was scheduled for execution */ int execute_in_process_context(work_func_t fn, struct execute_work *ew) { if (!in_interrupt()) { fn(&ew->work); return 0; } INIT_WORK(&ew->work, fn); schedule_work(&ew->work); return 1; } EXPORT_SYMBOL_GPL(execute_in_process_context); /** * free_workqueue_attrs - free a workqueue_attrs * @attrs: workqueue_attrs to free * * Undo alloc_workqueue_attrs(). */ void free_workqueue_attrs(struct workqueue_attrs *attrs) { if (attrs) { free_cpumask_var(attrs->cpumask); free_cpumask_var(attrs->__pod_cpumask); kfree(attrs); } } /** * alloc_workqueue_attrs - allocate a workqueue_attrs * * Allocate a new workqueue_attrs, initialize with default settings and * return it. * * Return: The allocated new workqueue_attr on success. %NULL on failure. */ struct workqueue_attrs *alloc_workqueue_attrs(void) { struct workqueue_attrs *attrs; attrs = kzalloc(sizeof(*attrs), GFP_KERNEL); if (!attrs) goto fail; if (!alloc_cpumask_var(&attrs->cpumask, GFP_KERNEL)) goto fail; if (!alloc_cpumask_var(&attrs->__pod_cpumask, GFP_KERNEL)) goto fail; cpumask_copy(attrs->cpumask, cpu_possible_mask); attrs->affn_scope = WQ_AFFN_DFL; return attrs; fail: free_workqueue_attrs(attrs); return NULL; } static void copy_workqueue_attrs(struct workqueue_attrs *to, const struct workqueue_attrs *from) { to->nice = from->nice; cpumask_copy(to->cpumask, from->cpumask); cpumask_copy(to->__pod_cpumask, from->__pod_cpumask); to->affn_strict = from->affn_strict; /* * Unlike hash and equality test, copying shouldn't ignore wq-only * fields as copying is used for both pool and wq attrs. Instead, * get_unbound_pool() explicitly clears the fields. */ to->affn_scope = from->affn_scope; to->ordered = from->ordered; } /* * Some attrs fields are workqueue-only. Clear them for worker_pool's. See the * comments in 'struct workqueue_attrs' definition. */ static void wqattrs_clear_for_pool(struct workqueue_attrs *attrs) { attrs->affn_scope = WQ_AFFN_NR_TYPES; attrs->ordered = false; if (attrs->affn_strict) cpumask_copy(attrs->cpumask, cpu_possible_mask); } /* hash value of the content of @attr */ static u32 wqattrs_hash(const struct workqueue_attrs *attrs) { u32 hash = 0; hash = jhash_1word(attrs->nice, hash); hash = jhash_1word(attrs->affn_strict, hash); hash = jhash(cpumask_bits(attrs->__pod_cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); if (!attrs->affn_strict) hash = jhash(cpumask_bits(attrs->cpumask), BITS_TO_LONGS(nr_cpumask_bits) * sizeof(long), hash); return hash; } /* content equality test */ static bool wqattrs_equal(const struct workqueue_attrs *a, const struct workqueue_attrs *b) { if (a->nice != b->nice) return false; if (a->affn_strict != b->affn_strict) return false; if (!cpumask_equal(a->__pod_cpumask, b->__pod_cpumask)) return false; if (!a->affn_strict && !cpumask_equal(a->cpumask, b->cpumask)) return false; return true; } /* Update @attrs with actually available CPUs */ static void wqattrs_actualize_cpumask(struct workqueue_attrs *attrs, const cpumask_t *unbound_cpumask) { /* * Calculate the effective CPU mask of @attrs given @unbound_cpumask. If * @attrs->cpumask doesn't overlap with @unbound_cpumask, we fallback to * @unbound_cpumask. */ cpumask_and(attrs->cpumask, attrs->cpumask, unbound_cpumask); if (unlikely(cpumask_empty(attrs->cpumask))) cpumask_copy(attrs->cpumask, unbound_cpumask); } /* find wq_pod_type to use for @attrs */ static const struct wq_pod_type * wqattrs_pod_type(const struct workqueue_attrs *attrs) { enum wq_affn_scope scope; struct wq_pod_type *pt; /* to synchronize access to wq_affn_dfl */ lockdep_assert_held(&wq_pool_mutex); if (attrs->affn_scope == WQ_AFFN_DFL) scope = wq_affn_dfl; else scope = attrs->affn_scope; pt = &wq_pod_types[scope]; if (!WARN_ON_ONCE(attrs->affn_scope == WQ_AFFN_NR_TYPES) && likely(pt->nr_pods)) return pt; /* * Before workqueue_init_topology(), only SYSTEM is available which is * initialized in workqueue_init_early(). */ pt = &wq_pod_types[WQ_AFFN_SYSTEM]; BUG_ON(!pt->nr_pods); return pt; } /** * init_worker_pool - initialize a newly zalloc'd worker_pool * @pool: worker_pool to initialize * * Initialize a newly zalloc'd @pool. It also allocates @pool->attrs. * * Return: 0 on success, -errno on failure. Even on failure, all fields * inside @pool proper are initialized and put_unbound_pool() can be called * on @pool safely to release it. */ static int init_worker_pool(struct worker_pool *pool) { raw_spin_lock_init(&pool->lock); pool->id = -1; pool->cpu = -1; pool->node = NUMA_NO_NODE; pool->flags |= POOL_DISASSOCIATED; pool->watchdog_ts = jiffies; INIT_LIST_HEAD(&pool->worklist); INIT_LIST_HEAD(&pool->idle_list); hash_init(pool->busy_hash); timer_setup(&pool->idle_timer, idle_worker_timeout, TIMER_DEFERRABLE); INIT_WORK(&pool->idle_cull_work, idle_cull_fn); timer_setup(&pool->mayday_timer, pool_mayday_timeout, 0); INIT_LIST_HEAD(&pool->workers); INIT_LIST_HEAD(&pool->dying_workers); ida_init(&pool->worker_ida); INIT_HLIST_NODE(&pool->hash_node); pool->refcnt = 1; /* shouldn't fail above this point */ pool->attrs = alloc_workqueue_attrs(); if (!pool->attrs) return -ENOMEM; wqattrs_clear_for_pool(pool->attrs); return 0; } #ifdef CONFIG_LOCKDEP static void wq_init_lockdep(struct workqueue_struct *wq) { char *lock_name; lockdep_register_key(&wq->key); lock_name = kasprintf(GFP_KERNEL, "%s%s", "(wq_completion)", wq->name); if (!lock_name) lock_name = wq->name; wq->lock_name = lock_name; lockdep_init_map(&wq->lockdep_map, lock_name, &wq->key, 0); } static void wq_unregister_lockdep(struct workqueue_struct *wq) { lockdep_unregister_key(&wq->key); } static void wq_free_lockdep(struct workqueue_struct *wq) { if (wq->lock_name != wq->name) kfree(wq->lock_name); } #else static void wq_init_lockdep(struct workqueue_struct *wq) { } static void wq_unregister_lockdep(struct workqueue_struct *wq) { } static void wq_free_lockdep(struct workqueue_struct *wq) { } #endif static void free_node_nr_active(struct wq_node_nr_active **nna_ar) { int node; for_each_node(node) { kfree(nna_ar[node]); nna_ar[node] = NULL; } kfree(nna_ar[nr_node_ids]); nna_ar[nr_node_ids] = NULL; } static void init_node_nr_active(struct wq_node_nr_active *nna) { nna->max = WQ_DFL_MIN_ACTIVE; atomic_set(&nna->nr, 0); raw_spin_lock_init(&nna->lock); INIT_LIST_HEAD(&nna->pending_pwqs); } /* * Each node's nr_active counter will be accessed mostly from its own node and * should be allocated in the node. */ static int alloc_node_nr_active(struct wq_node_nr_active **nna_ar) { struct wq_node_nr_active *nna; int node; for_each_node(node) { nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, node); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[node] = nna; } /* [nr_node_ids] is used as the fallback */ nna = kzalloc_node(sizeof(*nna), GFP_KERNEL, NUMA_NO_NODE); if (!nna) goto err_free; init_node_nr_active(nna); nna_ar[nr_node_ids] = nna; return 0; err_free: free_node_nr_active(nna_ar); return -ENOMEM; } static void rcu_free_wq(struct rcu_head *rcu) { struct workqueue_struct *wq = container_of(rcu, struct workqueue_struct, rcu); if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); wq_free_lockdep(wq); free_percpu(wq->cpu_pwq); free_workqueue_attrs(wq->unbound_attrs); kfree(wq); } static void rcu_free_pool(struct rcu_head *rcu) { struct worker_pool *pool = container_of(rcu, struct worker_pool, rcu); ida_destroy(&pool->worker_ida); free_workqueue_attrs(pool->attrs); kfree(pool); } /** * put_unbound_pool - put a worker_pool * @pool: worker_pool to put * * Put @pool. If its refcnt reaches zero, it gets destroyed in RCU * safe manner. get_unbound_pool() calls this function on its failure path * and this function should be able to release pools which went through, * successfully or not, init_worker_pool(). * * Should be called with wq_pool_mutex held. */ static void put_unbound_pool(struct worker_pool *pool) { DECLARE_COMPLETION_ONSTACK(detach_completion); struct worker *worker; LIST_HEAD(cull_list); lockdep_assert_held(&wq_pool_mutex); if (--pool->refcnt) return; /* sanity checks */ if (WARN_ON(!(pool->cpu < 0)) || WARN_ON(!list_empty(&pool->worklist))) return; /* release id and unhash */ if (pool->id >= 0) idr_remove(&worker_pool_idr, pool->id); hash_del(&pool->hash_node); /* * Become the manager and destroy all workers. This prevents * @pool's workers from blocking on attach_mutex. We're the last * manager and @pool gets freed with the flag set. * * Having a concurrent manager is quite unlikely to happen as we can * only get here with * pwq->refcnt == pool->refcnt == 0 * which implies no work queued to the pool, which implies no worker can * become the manager. However a worker could have taken the role of * manager before the refcnts dropped to 0, since maybe_create_worker() * drops pool->lock */ while (true) { rcuwait_wait_event(&manager_wait, !(pool->flags & POOL_MANAGER_ACTIVE), TASK_UNINTERRUPTIBLE); mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); if (!(pool->flags & POOL_MANAGER_ACTIVE)) { pool->flags |= POOL_MANAGER_ACTIVE; break; } raw_spin_unlock_irq(&pool->lock); mutex_unlock(&wq_pool_attach_mutex); } while ((worker = first_idle_worker(pool))) set_worker_dying(worker, &cull_list); WARN_ON(pool->nr_workers || pool->nr_idle); raw_spin_unlock_irq(&pool->lock); wake_dying_workers(&cull_list); if (!list_empty(&pool->workers) || !list_empty(&pool->dying_workers)) pool->detach_completion = &detach_completion; mutex_unlock(&wq_pool_attach_mutex); if (pool->detach_completion) wait_for_completion(pool->detach_completion); /* shut down the timers */ del_timer_sync(&pool->idle_timer); cancel_work_sync(&pool->idle_cull_work); del_timer_sync(&pool->mayday_timer); /* RCU protected to allow dereferences from get_work_pool() */ call_rcu(&pool->rcu, rcu_free_pool); } /** * get_unbound_pool - get a worker_pool with the specified attributes * @attrs: the attributes of the worker_pool to get * * Obtain a worker_pool which has the same attributes as @attrs, bump the * reference count and return it. If there already is a matching * worker_pool, it will be used; otherwise, this function attempts to * create a new one. * * Should be called with wq_pool_mutex held. * * Return: On success, a worker_pool with the same attributes as @attrs. * On failure, %NULL. */ static struct worker_pool *get_unbound_pool(const struct workqueue_attrs *attrs) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_NUMA]; u32 hash = wqattrs_hash(attrs); struct worker_pool *pool; int pod, node = NUMA_NO_NODE; lockdep_assert_held(&wq_pool_mutex); /* do we already have a matching pool? */ hash_for_each_possible(unbound_pool_hash, pool, hash_node, hash) { if (wqattrs_equal(pool->attrs, attrs)) { pool->refcnt++; return pool; } } /* If __pod_cpumask is contained inside a NUMA pod, that's our node */ for (pod = 0; pod < pt->nr_pods; pod++) { if (cpumask_subset(attrs->__pod_cpumask, pt->pod_cpus[pod])) { node = pt->pod_node[pod]; break; } } /* nope, create a new one */ pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, node); if (!pool || init_worker_pool(pool) < 0) goto fail; pool->node = node; copy_workqueue_attrs(pool->attrs, attrs); wqattrs_clear_for_pool(pool->attrs); if (worker_pool_assign_id(pool) < 0) goto fail; /* create and start the initial worker */ if (wq_online && !create_worker(pool)) goto fail; /* install */ hash_add(unbound_pool_hash, &pool->hash_node, hash); return pool; fail: if (pool) put_unbound_pool(pool); return NULL; } static void rcu_free_pwq(struct rcu_head *rcu) { kmem_cache_free(pwq_cache, container_of(rcu, struct pool_workqueue, rcu)); } /* * Scheduled on pwq_release_worker by put_pwq() when an unbound pwq hits zero * refcnt and needs to be destroyed. */ static void pwq_release_workfn(struct kthread_work *work) { struct pool_workqueue *pwq = container_of(work, struct pool_workqueue, release_work); struct workqueue_struct *wq = pwq->wq; struct worker_pool *pool = pwq->pool; bool is_last = false; /* * When @pwq is not linked, it doesn't hold any reference to the * @wq, and @wq is invalid to access. */ if (!list_empty(&pwq->pwqs_node)) { mutex_lock(&wq->mutex); list_del_rcu(&pwq->pwqs_node); is_last = list_empty(&wq->pwqs); /* * For ordered workqueue with a plugged dfl_pwq, restart it now. */ if (!is_last && (wq->flags & __WQ_ORDERED)) unplug_oldest_pwq(wq); mutex_unlock(&wq->mutex); } if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq_pool_mutex); put_unbound_pool(pool); mutex_unlock(&wq_pool_mutex); } if (!list_empty(&pwq->pending_node)) { struct wq_node_nr_active *nna = wq_node_nr_active(pwq->wq, pwq->pool->node); raw_spin_lock_irq(&nna->lock); list_del_init(&pwq->pending_node); raw_spin_unlock_irq(&nna->lock); } call_rcu(&pwq->rcu, rcu_free_pwq); /* * If we're the last pwq going away, @wq is already dead and no one * is gonna access it anymore. Schedule RCU free. */ if (is_last) { wq_unregister_lockdep(wq); call_rcu(&wq->rcu, rcu_free_wq); } } /* initialize newly allocated @pwq which is associated with @wq and @pool */ static void init_pwq(struct pool_workqueue *pwq, struct workqueue_struct *wq, struct worker_pool *pool) { BUG_ON((unsigned long)pwq & ~WORK_STRUCT_PWQ_MASK); memset(pwq, 0, sizeof(*pwq)); pwq->pool = pool; pwq->wq = wq; pwq->flush_color = -1; pwq->refcnt = 1; INIT_LIST_HEAD(&pwq->inactive_works); INIT_LIST_HEAD(&pwq->pending_node); INIT_LIST_HEAD(&pwq->pwqs_node); INIT_LIST_HEAD(&pwq->mayday_node); kthread_init_work(&pwq->release_work, pwq_release_workfn); } /* sync @pwq with the current state of its associated wq and link it */ static void link_pwq(struct pool_workqueue *pwq) { struct workqueue_struct *wq = pwq->wq; lockdep_assert_held(&wq->mutex); /* may be called multiple times, ignore if already linked */ if (!list_empty(&pwq->pwqs_node)) return; /* set the matching work_color */ pwq->work_color = wq->work_color; /* link in @pwq */ list_add_tail_rcu(&pwq->pwqs_node, &wq->pwqs); } /* obtain a pool matching @attr and create a pwq associating the pool and @wq */ static struct pool_workqueue *alloc_unbound_pwq(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct worker_pool *pool; struct pool_workqueue *pwq; lockdep_assert_held(&wq_pool_mutex); pool = get_unbound_pool(attrs); if (!pool) return NULL; pwq = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!pwq) { put_unbound_pool(pool); return NULL; } init_pwq(pwq, wq, pool); return pwq; } /** * wq_calc_pod_cpumask - calculate a wq_attrs' cpumask for a pod * @attrs: the wq_attrs of the default pwq of the target workqueue * @cpu: the target CPU * @cpu_going_down: if >= 0, the CPU to consider as offline * * Calculate the cpumask a workqueue with @attrs should use on @pod. If * @cpu_going_down is >= 0, that cpu is considered offline during calculation. * The result is stored in @attrs->__pod_cpumask. * * If pod affinity is not enabled, @attrs->cpumask is always used. If enabled * and @pod has online CPUs requested by @attrs, the returned cpumask is the * intersection of the possible CPUs of @pod and @attrs->cpumask. * * The caller is responsible for ensuring that the cpumask of @pod stays stable. */ static void wq_calc_pod_cpumask(struct workqueue_attrs *attrs, int cpu, int cpu_going_down) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int pod = pt->cpu_pod[cpu]; /* does @pod have any online CPUs @attrs wants? */ cpumask_and(attrs->__pod_cpumask, pt->pod_cpus[pod], attrs->cpumask); cpumask_and(attrs->__pod_cpumask, attrs->__pod_cpumask, cpu_online_mask); if (cpu_going_down >= 0) cpumask_clear_cpu(cpu_going_down, attrs->__pod_cpumask); if (cpumask_empty(attrs->__pod_cpumask)) { cpumask_copy(attrs->__pod_cpumask, attrs->cpumask); return; } /* yeap, return possible CPUs in @pod that @attrs wants */ cpumask_and(attrs->__pod_cpumask, attrs->cpumask, pt->pod_cpus[pod]); if (cpumask_empty(attrs->__pod_cpumask)) pr_warn_once("WARNING: workqueue cpumask: online intersect > " "possible intersect\n"); } /* install @pwq into @wq and return the old pwq, @cpu < 0 for dfl_pwq */ static struct pool_workqueue *install_unbound_pwq(struct workqueue_struct *wq, int cpu, struct pool_workqueue *pwq) { struct pool_workqueue __rcu **slot = unbound_pwq_slot(wq, cpu); struct pool_workqueue *old_pwq; lockdep_assert_held(&wq_pool_mutex); lockdep_assert_held(&wq->mutex); /* link_pwq() can handle duplicate calls */ link_pwq(pwq); old_pwq = rcu_access_pointer(*slot); rcu_assign_pointer(*slot, pwq); return old_pwq; } /* context to store the prepared attrs & pwqs before applying */ struct apply_wqattrs_ctx { struct workqueue_struct *wq; /* target workqueue */ struct workqueue_attrs *attrs; /* attrs to apply */ struct list_head list; /* queued for batching commit */ struct pool_workqueue *dfl_pwq; struct pool_workqueue *pwq_tbl[]; }; /* free the resources after success or abort */ static void apply_wqattrs_cleanup(struct apply_wqattrs_ctx *ctx) { if (ctx) { int cpu; for_each_possible_cpu(cpu) put_pwq_unlocked(ctx->pwq_tbl[cpu]); put_pwq_unlocked(ctx->dfl_pwq); free_workqueue_attrs(ctx->attrs); kfree(ctx); } } /* allocate the attrs and pwqs for later installation */ static struct apply_wqattrs_ctx * apply_wqattrs_prepare(struct workqueue_struct *wq, const struct workqueue_attrs *attrs, const cpumask_var_t unbound_cpumask) { struct apply_wqattrs_ctx *ctx; struct workqueue_attrs *new_attrs; int cpu; lockdep_assert_held(&wq_pool_mutex); if (WARN_ON(attrs->affn_scope < 0 || attrs->affn_scope >= WQ_AFFN_NR_TYPES)) return ERR_PTR(-EINVAL); ctx = kzalloc(struct_size(ctx, pwq_tbl, nr_cpu_ids), GFP_KERNEL); new_attrs = alloc_workqueue_attrs(); if (!ctx || !new_attrs) goto out_free; /* * If something goes wrong during CPU up/down, we'll fall back to * the default pwq covering whole @attrs->cpumask. Always create * it even if we don't use it immediately. */ copy_workqueue_attrs(new_attrs, attrs); wqattrs_actualize_cpumask(new_attrs, unbound_cpumask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->dfl_pwq = alloc_unbound_pwq(wq, new_attrs); if (!ctx->dfl_pwq) goto out_free; for_each_possible_cpu(cpu) { if (new_attrs->ordered) { ctx->dfl_pwq->refcnt++; ctx->pwq_tbl[cpu] = ctx->dfl_pwq; } else { wq_calc_pod_cpumask(new_attrs, cpu, -1); ctx->pwq_tbl[cpu] = alloc_unbound_pwq(wq, new_attrs); if (!ctx->pwq_tbl[cpu]) goto out_free; } } /* save the user configured attrs and sanitize it. */ copy_workqueue_attrs(new_attrs, attrs); cpumask_and(new_attrs->cpumask, new_attrs->cpumask, cpu_possible_mask); cpumask_copy(new_attrs->__pod_cpumask, new_attrs->cpumask); ctx->attrs = new_attrs; /* * For initialized ordered workqueues, there should only be one pwq * (dfl_pwq). Set the plugged flag of ctx->dfl_pwq to suspend execution * of newly queued work items until execution of older work items in * the old pwq's have completed. */ if ((wq->flags & __WQ_ORDERED) && !list_empty(&wq->pwqs)) ctx->dfl_pwq->plugged = true; ctx->wq = wq; return ctx; out_free: free_workqueue_attrs(new_attrs); apply_wqattrs_cleanup(ctx); return ERR_PTR(-ENOMEM); } /* set attrs and install prepared pwqs, @ctx points to old pwqs on return */ static void apply_wqattrs_commit(struct apply_wqattrs_ctx *ctx) { int cpu; /* all pwqs have been created successfully, let's install'em */ mutex_lock(&ctx->wq->mutex); copy_workqueue_attrs(ctx->wq->unbound_attrs, ctx->attrs); /* save the previous pwqs and install the new ones */ for_each_possible_cpu(cpu) ctx->pwq_tbl[cpu] = install_unbound_pwq(ctx->wq, cpu, ctx->pwq_tbl[cpu]); ctx->dfl_pwq = install_unbound_pwq(ctx->wq, -1, ctx->dfl_pwq); /* update node_nr_active->max */ wq_update_node_max_active(ctx->wq, -1); /* rescuer needs to respect wq cpumask changes */ if (ctx->wq->rescuer) set_cpus_allowed_ptr(ctx->wq->rescuer->task, unbound_effective_cpumask(ctx->wq)); mutex_unlock(&ctx->wq->mutex); } static int apply_workqueue_attrs_locked(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { struct apply_wqattrs_ctx *ctx; /* only unbound workqueues can change attributes */ if (WARN_ON(!(wq->flags & WQ_UNBOUND))) return -EINVAL; ctx = apply_wqattrs_prepare(wq, attrs, wq_unbound_cpumask); if (IS_ERR(ctx)) return PTR_ERR(ctx); /* the ctx has been prepared successfully, let's commit it */ apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); return 0; } /** * apply_workqueue_attrs - apply new workqueue_attrs to an unbound workqueue * @wq: the target workqueue * @attrs: the workqueue_attrs to apply, allocated with alloc_workqueue_attrs() * * Apply @attrs to an unbound workqueue @wq. Unless disabled, this function maps * a separate pwq to each CPU pod with possibles CPUs in @attrs->cpumask so that * work items are affine to the pod it was issued on. Older pwqs are released as * in-flight work items finish. Note that a work item which repeatedly requeues * itself back-to-back will stay on its current pwq. * * Performs GFP_KERNEL allocations. * * Assumes caller has CPU hotplug read exclusion, i.e. cpus_read_lock(). * * Return: 0 on success and -errno on failure. */ int apply_workqueue_attrs(struct workqueue_struct *wq, const struct workqueue_attrs *attrs) { int ret; lockdep_assert_cpus_held(); mutex_lock(&wq_pool_mutex); ret = apply_workqueue_attrs_locked(wq, attrs); mutex_unlock(&wq_pool_mutex); return ret; } /** * wq_update_pod - update pod affinity of a wq for CPU hot[un]plug * @wq: the target workqueue * @cpu: the CPU to update pool association for * @hotplug_cpu: the CPU coming up or going down * @online: whether @cpu is coming up or going down * * This function is to be called from %CPU_DOWN_PREPARE, %CPU_ONLINE and * %CPU_DOWN_FAILED. @cpu is being hot[un]plugged, update pod affinity of * @wq accordingly. * * * If pod affinity can't be adjusted due to memory allocation failure, it falls * back to @wq->dfl_pwq which may not be optimal but is always correct. * * Note that when the last allowed CPU of a pod goes offline for a workqueue * with a cpumask spanning multiple pods, the workers which were already * executing the work items for the workqueue will lose their CPU affinity and * may execute on any CPU. This is similar to how per-cpu workqueues behave on * CPU_DOWN. If a workqueue user wants strict affinity, it's the user's * responsibility to flush the work item from CPU_DOWN_PREPARE. */ static void wq_update_pod(struct workqueue_struct *wq, int cpu, int hotplug_cpu, bool online) { int off_cpu = online ? -1 : hotplug_cpu; struct pool_workqueue *old_pwq = NULL, *pwq; struct workqueue_attrs *target_attrs; lockdep_assert_held(&wq_pool_mutex); if (!(wq->flags & WQ_UNBOUND) || wq->unbound_attrs->ordered) return; /* * We don't wanna alloc/free wq_attrs for each wq for each CPU. * Let's use a preallocated one. The following buf is protected by * CPU hotplug exclusion. */ target_attrs = wq_update_pod_attrs_buf; copy_workqueue_attrs(target_attrs, wq->unbound_attrs); wqattrs_actualize_cpumask(target_attrs, wq_unbound_cpumask); /* nothing to do if the target cpumask matches the current pwq */ wq_calc_pod_cpumask(target_attrs, cpu, off_cpu); if (wqattrs_equal(target_attrs, unbound_pwq(wq, cpu)->pool->attrs)) return; /* create a new pwq */ pwq = alloc_unbound_pwq(wq, target_attrs); if (!pwq) { pr_warn("workqueue: allocation failed while updating CPU pod affinity of \"%s\"\n", wq->name); goto use_dfl_pwq; } /* Install the new pwq. */ mutex_lock(&wq->mutex); old_pwq = install_unbound_pwq(wq, cpu, pwq); goto out_unlock; use_dfl_pwq: mutex_lock(&wq->mutex); pwq = unbound_pwq(wq, -1); raw_spin_lock_irq(&pwq->pool->lock); get_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); old_pwq = install_unbound_pwq(wq, cpu, pwq); out_unlock: mutex_unlock(&wq->mutex); put_pwq_unlocked(old_pwq); } static int alloc_and_link_pwqs(struct workqueue_struct *wq) { bool highpri = wq->flags & WQ_HIGHPRI; int cpu, ret; wq->cpu_pwq = alloc_percpu(struct pool_workqueue *); if (!wq->cpu_pwq) goto enomem; if (!(wq->flags & WQ_UNBOUND)) { for_each_possible_cpu(cpu) { struct pool_workqueue **pwq_p; struct worker_pool __percpu *pools; struct worker_pool *pool; if (wq->flags & WQ_BH) pools = bh_worker_pools; else pools = cpu_worker_pools; pool = &(per_cpu_ptr(pools, cpu)[highpri]); pwq_p = per_cpu_ptr(wq->cpu_pwq, cpu); *pwq_p = kmem_cache_alloc_node(pwq_cache, GFP_KERNEL, pool->node); if (!*pwq_p) goto enomem; init_pwq(*pwq_p, wq, pool); mutex_lock(&wq->mutex); link_pwq(*pwq_p); mutex_unlock(&wq->mutex); } return 0; } cpus_read_lock(); if (wq->flags & __WQ_ORDERED) { struct pool_workqueue *dfl_pwq; ret = apply_workqueue_attrs(wq, ordered_wq_attrs[highpri]); /* there should only be single pwq for ordering guarantee */ dfl_pwq = rcu_access_pointer(wq->dfl_pwq); WARN(!ret && (wq->pwqs.next != &dfl_pwq->pwqs_node || wq->pwqs.prev != &dfl_pwq->pwqs_node), "ordering guarantee broken for workqueue %s\n", wq->name); } else { ret = apply_workqueue_attrs(wq, unbound_std_wq_attrs[highpri]); } cpus_read_unlock(); /* for unbound pwq, flush the pwq_release_worker ensures that the * pwq_release_workfn() completes before calling kfree(wq). */ if (ret) kthread_flush_worker(pwq_release_worker); return ret; enomem: if (wq->cpu_pwq) { for_each_possible_cpu(cpu) { struct pool_workqueue *pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); if (pwq) kmem_cache_free(pwq_cache, pwq); } free_percpu(wq->cpu_pwq); wq->cpu_pwq = NULL; } return -ENOMEM; } static int wq_clamp_max_active(int max_active, unsigned int flags, const char *name) { if (max_active < 1 || max_active > WQ_MAX_ACTIVE) pr_warn("workqueue: max_active %d requested for %s is out of range, clamping between %d and %d\n", max_active, name, 1, WQ_MAX_ACTIVE); return clamp_val(max_active, 1, WQ_MAX_ACTIVE); } /* * Workqueues which may be used during memory reclaim should have a rescuer * to guarantee forward progress. */ static int init_rescuer(struct workqueue_struct *wq) { struct worker *rescuer; char id_buf[WORKER_ID_LEN]; int ret; if (!(wq->flags & WQ_MEM_RECLAIM)) return 0; rescuer = alloc_worker(NUMA_NO_NODE); if (!rescuer) { pr_err("workqueue: Failed to allocate a rescuer for wq \"%s\"\n", wq->name); return -ENOMEM; } rescuer->rescue_wq = wq; format_worker_id(id_buf, sizeof(id_buf), rescuer, NULL); rescuer->task = kthread_create(rescuer_thread, rescuer, "%s", id_buf); if (IS_ERR(rescuer->task)) { ret = PTR_ERR(rescuer->task); pr_err("workqueue: Failed to create a rescuer kthread for wq \"%s\": %pe", wq->name, ERR_PTR(ret)); kfree(rescuer); return ret; } wq->rescuer = rescuer; if (wq->flags & WQ_UNBOUND) kthread_bind_mask(rescuer->task, wq_unbound_cpumask); else kthread_bind_mask(rescuer->task, cpu_possible_mask); wake_up_process(rescuer->task); return 0; } /** * wq_adjust_max_active - update a wq's max_active to the current setting * @wq: target workqueue * * If @wq isn't freezing, set @wq->max_active to the saved_max_active and * activate inactive work items accordingly. If @wq is freezing, clear * @wq->max_active to zero. */ static void wq_adjust_max_active(struct workqueue_struct *wq) { bool activated; int new_max, new_min; lockdep_assert_held(&wq->mutex); if ((wq->flags & WQ_FREEZABLE) && workqueue_freezing) { new_max = 0; new_min = 0; } else { new_max = wq->saved_max_active; new_min = wq->saved_min_active; } if (wq->max_active == new_max && wq->min_active == new_min) return; /* * Update @wq->max/min_active and then kick inactive work items if more * active work items are allowed. This doesn't break work item ordering * because new work items are always queued behind existing inactive * work items if there are any. */ WRITE_ONCE(wq->max_active, new_max); WRITE_ONCE(wq->min_active, new_min); if (wq->flags & WQ_UNBOUND) wq_update_node_max_active(wq, -1); if (new_max == 0) return; /* * Round-robin through pwq's activating the first inactive work item * until max_active is filled. */ do { struct pool_workqueue *pwq; activated = false; for_each_pwq(pwq, wq) { unsigned long irq_flags; /* can be called during early boot w/ irq disabled */ raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (pwq_activate_first_inactive(pwq, true)) { activated = true; kick_pool(pwq->pool); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); } } while (activated); } __printf(1, 4) struct workqueue_struct *alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...) { va_list args; struct workqueue_struct *wq; size_t wq_size; int name_len; if (flags & WQ_BH) { if (WARN_ON_ONCE(flags & ~__WQ_BH_ALLOWS)) return NULL; if (WARN_ON_ONCE(max_active)) return NULL; } /* see the comment above the definition of WQ_POWER_EFFICIENT */ if ((flags & WQ_POWER_EFFICIENT) && wq_power_efficient) flags |= WQ_UNBOUND; /* allocate wq and format name */ if (flags & WQ_UNBOUND) wq_size = struct_size(wq, node_nr_active, nr_node_ids + 1); else wq_size = sizeof(*wq); wq = kzalloc(wq_size, GFP_KERNEL); if (!wq) return NULL; if (flags & WQ_UNBOUND) { wq->unbound_attrs = alloc_workqueue_attrs(); if (!wq->unbound_attrs) goto err_free_wq; } va_start(args, max_active); name_len = vsnprintf(wq->name, sizeof(wq->name), fmt, args); va_end(args); if (name_len >= WQ_NAME_LEN) pr_warn_once("workqueue: name exceeds WQ_NAME_LEN. Truncating to: %s\n", wq->name); if (flags & WQ_BH) { /* * BH workqueues always share a single execution context per CPU * and don't impose any max_active limit. */ max_active = INT_MAX; } else { max_active = max_active ?: WQ_DFL_ACTIVE; max_active = wq_clamp_max_active(max_active, flags, wq->name); } /* init wq */ wq->flags = flags; wq->max_active = max_active; wq->min_active = min(max_active, WQ_DFL_MIN_ACTIVE); wq->saved_max_active = wq->max_active; wq->saved_min_active = wq->min_active; mutex_init(&wq->mutex); atomic_set(&wq->nr_pwqs_to_flush, 0); INIT_LIST_HEAD(&wq->pwqs); INIT_LIST_HEAD(&wq->flusher_queue); INIT_LIST_HEAD(&wq->flusher_overflow); INIT_LIST_HEAD(&wq->maydays); wq_init_lockdep(wq); INIT_LIST_HEAD(&wq->list); if (flags & WQ_UNBOUND) { if (alloc_node_nr_active(wq->node_nr_active) < 0) goto err_unreg_lockdep; } if (alloc_and_link_pwqs(wq) < 0) goto err_free_node_nr_active; if (wq_online && init_rescuer(wq) < 0) goto err_destroy; if ((wq->flags & WQ_SYSFS) && workqueue_sysfs_register(wq)) goto err_destroy; /* * wq_pool_mutex protects global freeze state and workqueues list. * Grab it, adjust max_active and add the new @wq to workqueues * list. */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); list_add_tail_rcu(&wq->list, &workqueues); mutex_unlock(&wq_pool_mutex); return wq; err_free_node_nr_active: if (wq->flags & WQ_UNBOUND) free_node_nr_active(wq->node_nr_active); err_unreg_lockdep: wq_unregister_lockdep(wq); wq_free_lockdep(wq); err_free_wq: free_workqueue_attrs(wq->unbound_attrs); kfree(wq); return NULL; err_destroy: destroy_workqueue(wq); return NULL; } EXPORT_SYMBOL_GPL(alloc_workqueue); static bool pwq_busy(struct pool_workqueue *pwq) { int i; for (i = 0; i < WORK_NR_COLORS; i++) if (pwq->nr_in_flight[i]) return true; if ((pwq != rcu_access_pointer(pwq->wq->dfl_pwq)) && (pwq->refcnt > 1)) return true; if (!pwq_is_empty(pwq)) return true; return false; } /** * destroy_workqueue - safely terminate a workqueue * @wq: target workqueue * * Safely destroy a workqueue. All work currently pending will be done first. */ void destroy_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; int cpu; /* * Remove it from sysfs first so that sanity check failure doesn't * lead to sysfs name conflicts. */ workqueue_sysfs_unregister(wq); /* mark the workqueue destruction is in progress */ mutex_lock(&wq->mutex); wq->flags |= __WQ_DESTROYING; mutex_unlock(&wq->mutex); /* drain it before proceeding with destruction */ drain_workqueue(wq); /* kill rescuer, if sanity checks fail, leave it w/o rescuer */ if (wq->rescuer) { struct worker *rescuer = wq->rescuer; /* this prevents new queueing */ raw_spin_lock_irq(&wq_mayday_lock); wq->rescuer = NULL; raw_spin_unlock_irq(&wq_mayday_lock); /* rescuer will empty maydays list before exiting */ kthread_stop(rescuer->task); kfree(rescuer); } /* * Sanity checks - grab all the locks so that we wait for all * in-flight operations which may do put_pwq(). */ mutex_lock(&wq_pool_mutex); mutex_lock(&wq->mutex); for_each_pwq(pwq, wq) { raw_spin_lock_irq(&pwq->pool->lock); if (WARN_ON(pwq_busy(pwq))) { pr_warn("%s: %s has the following busy pwq\n", __func__, wq->name); show_pwq(pwq); raw_spin_unlock_irq(&pwq->pool->lock); mutex_unlock(&wq->mutex); mutex_unlock(&wq_pool_mutex); show_one_workqueue(wq); return; } raw_spin_unlock_irq(&pwq->pool->lock); } mutex_unlock(&wq->mutex); /* * wq list is used to freeze wq, remove from list after * flushing is complete in case freeze races us. */ list_del_rcu(&wq->list); mutex_unlock(&wq_pool_mutex); /* * We're the sole accessor of @wq. Directly access cpu_pwq and dfl_pwq * to put the base refs. @wq will be auto-destroyed from the last * pwq_put. RCU read lock prevents @wq from going away from under us. */ rcu_read_lock(); for_each_possible_cpu(cpu) { put_pwq_unlocked(unbound_pwq(wq, cpu)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, cpu), NULL); } put_pwq_unlocked(unbound_pwq(wq, -1)); RCU_INIT_POINTER(*unbound_pwq_slot(wq, -1), NULL); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(destroy_workqueue); /** * workqueue_set_max_active - adjust max_active of a workqueue * @wq: target workqueue * @max_active: new max_active value. * * Set max_active of @wq to @max_active. See the alloc_workqueue() function * comment. * * CONTEXT: * Don't call from IRQ context. */ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active) { /* max_active doesn't mean anything for BH workqueues */ if (WARN_ON(wq->flags & WQ_BH)) return; /* disallow meddling with max_active for ordered workqueues */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return; max_active = wq_clamp_max_active(max_active, wq->flags, wq->name); mutex_lock(&wq->mutex); wq->saved_max_active = max_active; if (wq->flags & WQ_UNBOUND) wq->saved_min_active = min(wq->saved_min_active, max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } EXPORT_SYMBOL_GPL(workqueue_set_max_active); /** * workqueue_set_min_active - adjust min_active of an unbound workqueue * @wq: target unbound workqueue * @min_active: new min_active value * * Set min_active of an unbound workqueue. Unlike other types of workqueues, an * unbound workqueue is not guaranteed to be able to process max_active * interdependent work items. Instead, an unbound workqueue is guaranteed to be * able to process min_active number of interdependent work items which is * %WQ_DFL_MIN_ACTIVE by default. * * Use this function to adjust the min_active value between 0 and the current * max_active. */ void workqueue_set_min_active(struct workqueue_struct *wq, int min_active) { /* min_active is only meaningful for non-ordered unbound workqueues */ if (WARN_ON((wq->flags & (WQ_BH | WQ_UNBOUND | __WQ_ORDERED)) != WQ_UNBOUND)) return; mutex_lock(&wq->mutex); wq->saved_min_active = clamp(min_active, 0, wq->saved_max_active); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } /** * current_work - retrieve %current task's work struct * * Determine if %current task is a workqueue worker and what it's working on. * Useful to find out the context that the %current task is running in. * * Return: work struct if %current task is a workqueue worker, %NULL otherwise. */ struct work_struct *current_work(void) { struct worker *worker = current_wq_worker(); return worker ? worker->current_work : NULL; } EXPORT_SYMBOL(current_work); /** * current_is_workqueue_rescuer - is %current workqueue rescuer? * * Determine whether %current is a workqueue rescuer. Can be used from * work functions to determine whether it's being run off the rescuer task. * * Return: %true if %current is a workqueue rescuer. %false otherwise. */ bool current_is_workqueue_rescuer(void) { struct worker *worker = current_wq_worker(); return worker && worker->rescue_wq; } /** * workqueue_congested - test whether a workqueue is congested * @cpu: CPU in question * @wq: target workqueue * * Test whether @wq's cpu workqueue for @cpu is congested. There is * no synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * If @cpu is WORK_CPU_UNBOUND, the test is performed on the local CPU. * * With the exception of ordered workqueues, all workqueues have per-cpu * pool_workqueues, each with its own congested state. A workqueue being * congested on one CPU doesn't mean that the workqueue is contested on any * other CPUs. * * Return: * %true if congested, %false otherwise. */ bool workqueue_congested(int cpu, struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool ret; rcu_read_lock(); preempt_disable(); if (cpu == WORK_CPU_UNBOUND) cpu = smp_processor_id(); pwq = *per_cpu_ptr(wq->cpu_pwq, cpu); ret = !list_empty(&pwq->inactive_works); preempt_enable(); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(workqueue_congested); /** * work_busy - test whether a work is currently pending or running * @work: the work to be tested * * Test whether @work is currently pending or running. There is no * synchronization around this function and the test result is * unreliable and only useful as advisory hints or for debugging. * * Return: * OR'd bitmask of WORK_BUSY_* bits. */ unsigned int work_busy(struct work_struct *work) { struct worker_pool *pool; unsigned long irq_flags; unsigned int ret = 0; if (work_pending(work)) ret |= WORK_BUSY_PENDING; rcu_read_lock(); pool = get_work_pool(work); if (pool) { raw_spin_lock_irqsave(&pool->lock, irq_flags); if (find_worker_executing_work(pool, work)) ret |= WORK_BUSY_RUNNING; raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_busy); /** * set_worker_desc - set description for the current work item * @fmt: printf-style format string * @...: arguments for the format string * * This function can be called by a running work function to describe what * the work item is about. If the worker task gets dumped, this * information will be printed out together to help debugging. The * description can be at most WORKER_DESC_LEN including the trailing '\0'. */ void set_worker_desc(const char *fmt, ...) { struct worker *worker = current_wq_worker(); va_list args; if (worker) { va_start(args, fmt); vsnprintf(worker->desc, sizeof(worker->desc), fmt, args); va_end(args); } } EXPORT_SYMBOL_GPL(set_worker_desc); /** * print_worker_info - print out worker information and description * @log_lvl: the log level to use when printing * @task: target task * * If @task is a worker and currently executing a work item, print out the * name of the workqueue being serviced and worker description set with * set_worker_desc() by the currently executing work item. * * This function can be safely called on any task as long as the * task_struct itself is accessible. While safe, this function isn't * synchronized and may print out mixups or garbages of limited length. */ void print_worker_info(const char *log_lvl, struct task_struct *task) { work_func_t *fn = NULL; char name[WQ_NAME_LEN] = { }; char desc[WORKER_DESC_LEN] = { }; struct pool_workqueue *pwq = NULL; struct workqueue_struct *wq = NULL; struct worker *worker; if (!(task->flags & PF_WQ_WORKER)) return; /* * This function is called without any synchronization and @task * could be in any state. Be careful with dereferences. */ worker = kthread_probe_data(task); /* * Carefully copy the associated workqueue's workfn, name and desc. * Keep the original last '\0' in case the original is garbage. */ copy_from_kernel_nofault(&fn, &worker->current_func, sizeof(fn)); copy_from_kernel_nofault(&pwq, &worker->current_pwq, sizeof(pwq)); copy_from_kernel_nofault(&wq, &pwq->wq, sizeof(wq)); copy_from_kernel_nofault(name, wq->name, sizeof(name) - 1); copy_from_kernel_nofault(desc, worker->desc, sizeof(desc) - 1); if (fn || name[0] || desc[0]) { printk("%sWorkqueue: %s %ps", log_lvl, name, fn); if (strcmp(name, desc)) pr_cont(" (%s)", desc); pr_cont("\n"); } } static void pr_cont_pool_info(struct worker_pool *pool) { pr_cont(" cpus=%*pbl", nr_cpumask_bits, pool->attrs->cpumask); if (pool->node != NUMA_NO_NODE) pr_cont(" node=%d", pool->node); pr_cont(" flags=0x%x", pool->flags); if (pool->flags & POOL_BH) pr_cont(" bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont(" nice=%d", pool->attrs->nice); } static void pr_cont_worker_id(struct worker *worker) { struct worker_pool *pool = worker->pool; if (pool->flags & WQ_BH) pr_cont("bh%s", pool->attrs->nice == HIGHPRI_NICE_LEVEL ? "-hi" : ""); else pr_cont("%d%s", task_pid_nr(worker->task), worker->rescue_wq ? "(RESCUER)" : ""); } struct pr_cont_work_struct { bool comma; work_func_t func; long ctr; }; static void pr_cont_work_flush(bool comma, work_func_t func, struct pr_cont_work_struct *pcwsp) { if (!pcwsp->ctr) goto out_record; if (func == pcwsp->func) { pcwsp->ctr++; return; } if (pcwsp->ctr == 1) pr_cont("%s %ps", pcwsp->comma ? "," : "", pcwsp->func); else pr_cont("%s %ld*%ps", pcwsp->comma ? "," : "", pcwsp->ctr, pcwsp->func); pcwsp->ctr = 0; out_record: if ((long)func == -1L) return; pcwsp->comma = comma; pcwsp->func = func; pcwsp->ctr = 1; } static void pr_cont_work(bool comma, struct work_struct *work, struct pr_cont_work_struct *pcwsp) { if (work->func == wq_barrier_func) { struct wq_barrier *barr; barr = container_of(work, struct wq_barrier, work); pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont("%s BAR(%d)", comma ? "," : "", task_pid_nr(barr->task)); } else { if (!comma) pr_cont_work_flush(comma, (work_func_t)-1, pcwsp); pr_cont_work_flush(comma, work->func, pcwsp); } } static void show_pwq(struct pool_workqueue *pwq) { struct pr_cont_work_struct pcws = { .ctr = 0, }; struct worker_pool *pool = pwq->pool; struct work_struct *work; struct worker *worker; bool has_in_flight = false, has_pending = false; int bkt; pr_info(" pwq %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" active=%d refcnt=%d%s\n", pwq->nr_active, pwq->refcnt, !list_empty(&pwq->mayday_node) ? " MAYDAY" : ""); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq == pwq) { has_in_flight = true; break; } } if (has_in_flight) { bool comma = false; pr_info(" in-flight:"); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (worker->current_pwq != pwq) continue; pr_cont(" %s", comma ? "," : ""); pr_cont_worker_id(worker); pr_cont(":%ps", worker->current_func); list_for_each_entry(work, &worker->scheduled, entry) pr_cont_work(false, work, &pcws); pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); comma = true; } pr_cont("\n"); } list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) == pwq) { has_pending = true; break; } } if (has_pending) { bool comma = false; pr_info(" pending:"); list_for_each_entry(work, &pool->worklist, entry) { if (get_work_pwq(work) != pwq) continue; pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } if (!list_empty(&pwq->inactive_works)) { bool comma = false; pr_info(" inactive:"); list_for_each_entry(work, &pwq->inactive_works, entry) { pr_cont_work(comma, work, &pcws); comma = !(*work_data_bits(work) & WORK_STRUCT_LINKED); } pr_cont_work_flush(comma, (work_func_t)-1L, &pcws); pr_cont("\n"); } } /** * show_one_workqueue - dump state of specified workqueue * @wq: workqueue whose state will be printed */ void show_one_workqueue(struct workqueue_struct *wq) { struct pool_workqueue *pwq; bool idle = true; unsigned long irq_flags; for_each_pwq(pwq, wq) { if (!pwq_is_empty(pwq)) { idle = false; break; } } if (idle) /* Nothing to print for idle workqueue */ return; pr_info("workqueue %s: flags=0x%x\n", wq->name, wq->flags); for_each_pwq(pwq, wq) { raw_spin_lock_irqsave(&pwq->pool->lock, irq_flags); if (!pwq_is_empty(pwq)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); show_pwq(pwq); printk_deferred_exit(); } raw_spin_unlock_irqrestore(&pwq->pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } } /** * show_one_worker_pool - dump state of specified worker pool * @pool: worker pool whose state will be printed */ static void show_one_worker_pool(struct worker_pool *pool) { struct worker *worker; bool first = true; unsigned long irq_flags; unsigned long hung = 0; raw_spin_lock_irqsave(&pool->lock, irq_flags); if (pool->nr_workers == pool->nr_idle) goto next_pool; /* How long the first pending work is waiting for a worker. */ if (!list_empty(&pool->worklist)) hung = jiffies_to_msecs(jiffies - pool->watchdog_ts) / 1000; /* * Defer printing to avoid deadlocks in console drivers that * queue work while holding locks also taken in their write * paths. */ printk_deferred_enter(); pr_info("pool %d:", pool->id); pr_cont_pool_info(pool); pr_cont(" hung=%lus workers=%d", hung, pool->nr_workers); if (pool->manager) pr_cont(" manager: %d", task_pid_nr(pool->manager->task)); list_for_each_entry(worker, &pool->idle_list, entry) { pr_cont(" %s", first ? "idle: " : ""); pr_cont_worker_id(worker); first = false; } pr_cont("\n"); printk_deferred_exit(); next_pool: raw_spin_unlock_irqrestore(&pool->lock, irq_flags); /* * We could be printing a lot from atomic context, e.g. * sysrq-t -> show_all_workqueues(). Avoid triggering * hard lockup. */ touch_nmi_watchdog(); } /** * show_all_workqueues - dump workqueue state * * Called from a sysrq handler and prints out all busy workqueues and pools. */ void show_all_workqueues(void) { struct workqueue_struct *wq; struct worker_pool *pool; int pi; rcu_read_lock(); pr_info("Showing busy workqueues and worker pools:\n"); list_for_each_entry_rcu(wq, &workqueues, list) show_one_workqueue(wq); for_each_pool(pool, pi) show_one_worker_pool(pool); rcu_read_unlock(); } /** * show_freezable_workqueues - dump freezable workqueue state * * Called from try_to_freeze_tasks() and prints out all freezable workqueues * still busy. */ void show_freezable_workqueues(void) { struct workqueue_struct *wq; rcu_read_lock(); pr_info("Showing freezable workqueues that are still busy:\n"); list_for_each_entry_rcu(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; show_one_workqueue(wq); } rcu_read_unlock(); } /* used to show worker information through /proc/PID/{comm,stat,status} */ void wq_worker_comm(char *buf, size_t size, struct task_struct *task) { /* stabilize PF_WQ_WORKER and worker pool association */ mutex_lock(&wq_pool_attach_mutex); if (task->flags & PF_WQ_WORKER) { struct worker *worker = kthread_data(task); struct worker_pool *pool = worker->pool; int off; off = format_worker_id(buf, size, worker, pool); if (pool) { raw_spin_lock_irq(&pool->lock); /* * ->desc tracks information (wq name or * set_worker_desc()) for the latest execution. If * current, prepend '+', otherwise '-'. */ if (worker->desc[0] != '\0') { if (worker->current_work) scnprintf(buf + off, size - off, "+%s", worker->desc); else scnprintf(buf + off, size - off, "-%s", worker->desc); } raw_spin_unlock_irq(&pool->lock); } } else { strscpy(buf, task->comm, size); } mutex_unlock(&wq_pool_attach_mutex); } #ifdef CONFIG_SMP /* * CPU hotplug. * * There are two challenges in supporting CPU hotplug. Firstly, there * are a lot of assumptions on strong associations among work, pwq and * pool which make migrating pending and scheduled works very * difficult to implement without impacting hot paths. Secondly, * worker pools serve mix of short, long and very long running works making * blocked draining impractical. * * This is solved by allowing the pools to be disassociated from the CPU * running as an unbound one and allowing it to be reattached later if the * cpu comes back online. */ static void unbind_workers(int cpu) { struct worker_pool *pool; struct worker *worker; for_each_cpu_worker_pool(pool, cpu) { mutex_lock(&wq_pool_attach_mutex); raw_spin_lock_irq(&pool->lock); /* * We've blocked all attach/detach operations. Make all workers * unbound and set DISASSOCIATED. Before this, all workers * must be on the cpu. After this, they may become diasporas. * And the preemption disabled section in their sched callbacks * are guaranteed to see WORKER_UNBOUND since the code here * is on the same cpu. */ for_each_pool_worker(worker, pool) worker->flags |= WORKER_UNBOUND; pool->flags |= POOL_DISASSOCIATED; /* * The handling of nr_running in sched callbacks are disabled * now. Zap nr_running. After this, nr_running stays zero and * need_more_worker() and keep_working() are always true as * long as the worklist is not empty. This pool now behaves as * an unbound (in terms of concurrency management) pool which * are served by workers tied to the pool. */ pool->nr_running = 0; /* * With concurrency management just turned off, a busy * worker blocking could lead to lengthy stalls. Kick off * unbound chain execution of currently pending work items. */ kick_pool(pool); raw_spin_unlock_irq(&pool->lock); for_each_pool_worker(worker, pool) unbind_worker(worker); mutex_unlock(&wq_pool_attach_mutex); } } /** * rebind_workers - rebind all workers of a pool to the associated CPU * @pool: pool of interest * * @pool->cpu is coming online. Rebind all workers to the CPU. */ static void rebind_workers(struct worker_pool *pool) { struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* * Restore CPU affinity of all workers. As all idle workers should * be on the run-queue of the associated CPU before any local * wake-ups for concurrency management happen, restore CPU affinity * of all workers first and then clear UNBOUND. As we're called * from CPU_ONLINE, the following shouldn't fail. */ for_each_pool_worker(worker, pool) { kthread_set_per_cpu(worker->task, pool->cpu); WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, pool_allowed_cpus(pool)) < 0); } raw_spin_lock_irq(&pool->lock); pool->flags &= ~POOL_DISASSOCIATED; for_each_pool_worker(worker, pool) { unsigned int worker_flags = worker->flags; /* * We want to clear UNBOUND but can't directly call * worker_clr_flags() or adjust nr_running. Atomically * replace UNBOUND with another NOT_RUNNING flag REBOUND. * @worker will clear REBOUND using worker_clr_flags() when * it initiates the next execution cycle thus restoring * concurrency management. Note that when or whether * @worker clears REBOUND doesn't affect correctness. * * WRITE_ONCE() is necessary because @worker->flags may be * tested without holding any lock in * wq_worker_running(). Without it, NOT_RUNNING test may * fail incorrectly leading to premature concurrency * management operations. */ WARN_ON_ONCE(!(worker_flags & WORKER_UNBOUND)); worker_flags |= WORKER_REBOUND; worker_flags &= ~WORKER_UNBOUND; WRITE_ONCE(worker->flags, worker_flags); } raw_spin_unlock_irq(&pool->lock); } /** * restore_unbound_workers_cpumask - restore cpumask of unbound workers * @pool: unbound pool of interest * @cpu: the CPU which is coming up * * An unbound pool may end up with a cpumask which doesn't have any online * CPUs. When a worker of such pool get scheduled, the scheduler resets * its cpus_allowed. If @cpu is in @pool's cpumask which didn't have any * online CPU before, cpus_allowed of all its workers should be restored. */ static void restore_unbound_workers_cpumask(struct worker_pool *pool, int cpu) { static cpumask_t cpumask; struct worker *worker; lockdep_assert_held(&wq_pool_attach_mutex); /* is @cpu allowed for @pool? */ if (!cpumask_test_cpu(cpu, pool->attrs->cpumask)) return; cpumask_and(&cpumask, pool->attrs->cpumask, cpu_online_mask); /* as we're called from CPU_ONLINE, the following shouldn't fail */ for_each_pool_worker(worker, pool) WARN_ON_ONCE(set_cpus_allowed_ptr(worker->task, &cpumask) < 0); } int workqueue_prepare_cpu(unsigned int cpu) { struct worker_pool *pool; for_each_cpu_worker_pool(pool, cpu) { if (pool->nr_workers) continue; if (!create_worker(pool)) return -ENOMEM; } return 0; } int workqueue_online_cpu(unsigned int cpu) { struct worker_pool *pool; struct workqueue_struct *wq; int pi; mutex_lock(&wq_pool_mutex); for_each_pool(pool, pi) { /* BH pools aren't affected by hotplug */ if (pool->flags & POOL_BH) continue; mutex_lock(&wq_pool_attach_mutex); if (pool->cpu == cpu) rebind_workers(pool); else if (pool->cpu < 0) restore_unbound_workers_cpumask(pool, cpu); mutex_unlock(&wq_pool_attach_mutex); } /* update pod affinity of unbound workqueues */ list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, true); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } int workqueue_offline_cpu(unsigned int cpu) { struct workqueue_struct *wq; /* unbinding per-cpu workers should happen on the local CPU */ if (WARN_ON(cpu != smp_processor_id())) return -1; unbind_workers(cpu); /* update pod affinity of unbound workqueues */ mutex_lock(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { struct workqueue_attrs *attrs = wq->unbound_attrs; if (attrs) { const struct wq_pod_type *pt = wqattrs_pod_type(attrs); int tcpu; for_each_cpu(tcpu, pt->pod_cpus[pt->cpu_pod[cpu]]) wq_update_pod(wq, tcpu, cpu, false); mutex_lock(&wq->mutex); wq_update_node_max_active(wq, cpu); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); return 0; } struct work_for_cpu { struct work_struct work; long (*fn)(void *); void *arg; long ret; }; static void work_for_cpu_fn(struct work_struct *work) { struct work_for_cpu *wfc = container_of(work, struct work_for_cpu, work); wfc->ret = wfc->fn(wfc->arg); } /** * work_on_cpu_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function arg * @key: The lock class key for lock debugging purposes * * It is up to the caller to ensure that the cpu doesn't go offline. * The caller must not hold any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { struct work_for_cpu wfc = { .fn = fn, .arg = arg }; INIT_WORK_ONSTACK_KEY(&wfc.work, work_for_cpu_fn, key); schedule_work_on(cpu, &wfc.work); flush_work(&wfc.work); destroy_work_on_stack(&wfc.work); return wfc.ret; } EXPORT_SYMBOL_GPL(work_on_cpu_key); /** * work_on_cpu_safe_key - run a function in thread context on a particular cpu * @cpu: the cpu to run on * @fn: the function to run * @arg: the function argument * @key: The lock class key for lock debugging purposes * * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold * any locks which would prevent @fn from completing. * * Return: The value @fn returns. */ long work_on_cpu_safe_key(int cpu, long (*fn)(void *), void *arg, struct lock_class_key *key) { long ret = -ENODEV; cpus_read_lock(); if (cpu_online(cpu)) ret = work_on_cpu_key(cpu, fn, arg, key); cpus_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(work_on_cpu_safe_key); #endif /* CONFIG_SMP */ #ifdef CONFIG_FREEZER /** * freeze_workqueues_begin - begin freezing workqueues * * Start freezing workqueues. After this function returns, all freezable * workqueues will queue new works to their inactive_works list instead of * pool->worklist. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void freeze_workqueues_begin(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(workqueue_freezing); workqueue_freezing = true; list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } mutex_unlock(&wq_pool_mutex); } /** * freeze_workqueues_busy - are freezable workqueues still busy? * * Check whether freezing is complete. This function must be called * between freeze_workqueues_begin() and thaw_workqueues(). * * CONTEXT: * Grabs and releases wq_pool_mutex. * * Return: * %true if some freezable workqueues are still busy. %false if freezing * is complete. */ bool freeze_workqueues_busy(void) { bool busy = false; struct workqueue_struct *wq; struct pool_workqueue *pwq; mutex_lock(&wq_pool_mutex); WARN_ON_ONCE(!workqueue_freezing); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_FREEZABLE)) continue; /* * nr_active is monotonically decreasing. It's safe * to peek without lock. */ rcu_read_lock(); for_each_pwq(pwq, wq) { WARN_ON_ONCE(pwq->nr_active < 0); if (pwq->nr_active) { busy = true; rcu_read_unlock(); goto out_unlock; } } rcu_read_unlock(); } out_unlock: mutex_unlock(&wq_pool_mutex); return busy; } /** * thaw_workqueues - thaw workqueues * * Thaw workqueues. Normal queueing is restored and all collected * frozen works are transferred to their respective pool worklists. * * CONTEXT: * Grabs and releases wq_pool_mutex, wq->mutex and pool->lock's. */ void thaw_workqueues(void) { struct workqueue_struct *wq; mutex_lock(&wq_pool_mutex); if (!workqueue_freezing) goto out_unlock; workqueue_freezing = false; /* restore max_active and repopulate worklist */ list_for_each_entry(wq, &workqueues, list) { mutex_lock(&wq->mutex); wq_adjust_max_active(wq); mutex_unlock(&wq->mutex); } out_unlock: mutex_unlock(&wq_pool_mutex); } #endif /* CONFIG_FREEZER */ static int workqueue_apply_unbound_cpumask(const cpumask_var_t unbound_cpumask) { LIST_HEAD(ctxs); int ret = 0; struct workqueue_struct *wq; struct apply_wqattrs_ctx *ctx, *n; lockdep_assert_held(&wq_pool_mutex); list_for_each_entry(wq, &workqueues, list) { if (!(wq->flags & WQ_UNBOUND) || (wq->flags & __WQ_DESTROYING)) continue; ctx = apply_wqattrs_prepare(wq, wq->unbound_attrs, unbound_cpumask); if (IS_ERR(ctx)) { ret = PTR_ERR(ctx); break; } list_add_tail(&ctx->list, &ctxs); } list_for_each_entry_safe(ctx, n, &ctxs, list) { if (!ret) apply_wqattrs_commit(ctx); apply_wqattrs_cleanup(ctx); } if (!ret) { mutex_lock(&wq_pool_attach_mutex); cpumask_copy(wq_unbound_cpumask, unbound_cpumask); mutex_unlock(&wq_pool_attach_mutex); } return ret; } /** * workqueue_unbound_exclude_cpumask - Exclude given CPUs from unbound cpumask * @exclude_cpumask: the cpumask to be excluded from wq_unbound_cpumask * * This function can be called from cpuset code to provide a set of isolated * CPUs that should be excluded from wq_unbound_cpumask. The caller must hold * either cpus_read_lock or cpus_write_lock. */ int workqueue_unbound_exclude_cpumask(cpumask_var_t exclude_cpumask) { cpumask_var_t cpumask; int ret = 0; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; lockdep_assert_cpus_held(); mutex_lock(&wq_pool_mutex); /* Save the current isolated cpumask & export it via sysfs */ cpumask_copy(wq_isolated_cpumask, exclude_cpumask); /* * If the operation fails, it will fall back to * wq_requested_unbound_cpumask which is initially set to * (HK_TYPE_WQ ∩ HK_TYPE_DOMAIN) house keeping mask and rewritten * by any subsequent write to workqueue/cpumask sysfs file. */ if (!cpumask_andnot(cpumask, wq_requested_unbound_cpumask, exclude_cpumask)) cpumask_copy(cpumask, wq_requested_unbound_cpumask); if (!cpumask_equal(cpumask, wq_unbound_cpumask)) ret = workqueue_apply_unbound_cpumask(cpumask); mutex_unlock(&wq_pool_mutex); free_cpumask_var(cpumask); return ret; } static int parse_affn_scope(const char *val) { int i; for (i = 0; i < ARRAY_SIZE(wq_affn_names); i++) { if (!strncasecmp(val, wq_affn_names[i], strlen(wq_affn_names[i]))) return i; } return -EINVAL; } static int wq_affn_dfl_set(const char *val, const struct kernel_param *kp) { struct workqueue_struct *wq; int affn, cpu; affn = parse_affn_scope(val); if (affn < 0) return affn; if (affn == WQ_AFFN_DFL) return -EINVAL; cpus_read_lock(); mutex_lock(&wq_pool_mutex); wq_affn_dfl = affn; list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) { wq_update_pod(wq, cpu, cpu, true); } } mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); return 0; } static int wq_affn_dfl_get(char *buffer, const struct kernel_param *kp) { return scnprintf(buffer, PAGE_SIZE, "%s\n", wq_affn_names[wq_affn_dfl]); } static const struct kernel_param_ops wq_affn_dfl_ops = { .set = wq_affn_dfl_set, .get = wq_affn_dfl_get, }; module_param_cb(default_affinity_scope, &wq_affn_dfl_ops, NULL, 0644); #ifdef CONFIG_SYSFS /* * Workqueues with WQ_SYSFS flag set is visible to userland via * /sys/bus/workqueue/devices/WQ_NAME. All visible workqueues have the * following attributes. * * per_cpu RO bool : whether the workqueue is per-cpu or unbound * max_active RW int : maximum number of in-flight work items * * Unbound workqueues have the following extra attributes. * * nice RW int : nice value of the workers * cpumask RW mask : bitmask of allowed CPUs for the workers * affinity_scope RW str : worker CPU affinity scope (cache, numa, none) * affinity_strict RW bool : worker CPU affinity is strict */ struct wq_device { struct workqueue_struct *wq; struct device dev; }; static struct workqueue_struct *dev_to_wq(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); return wq_dev->wq; } static ssize_t per_cpu_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", (bool)!(wq->flags & WQ_UNBOUND)); } static DEVICE_ATTR_RO(per_cpu); static ssize_t max_active_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->saved_max_active); } static ssize_t max_active_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); int val; if (sscanf(buf, "%d", &val) != 1 || val <= 0) return -EINVAL; workqueue_set_max_active(wq, val); return count; } static DEVICE_ATTR_RW(max_active); static struct attribute *wq_sysfs_attrs[] = { &dev_attr_per_cpu.attr, &dev_attr_max_active.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs); static void apply_wqattrs_lock(void) { /* CPUs should stay stable across pwq creations and installations */ cpus_read_lock(); mutex_lock(&wq_pool_mutex); } static void apply_wqattrs_unlock(void) { mutex_unlock(&wq_pool_mutex); cpus_read_unlock(); } static ssize_t wq_nice_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->nice); mutex_unlock(&wq->mutex); return written; } /* prepare workqueue_attrs for sysfs store operations */ static struct workqueue_attrs *wq_sysfs_prep_attrs(struct workqueue_struct *wq) { struct workqueue_attrs *attrs; lockdep_assert_held(&wq_pool_mutex); attrs = alloc_workqueue_attrs(); if (!attrs) return NULL; copy_workqueue_attrs(attrs, wq->unbound_attrs); return attrs; } static ssize_t wq_nice_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; if (sscanf(buf, "%d", &attrs->nice) == 1 && attrs->nice >= MIN_NICE && attrs->nice <= MAX_NICE) ret = apply_workqueue_attrs_locked(wq, attrs); else ret = -EINVAL; out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(wq->unbound_attrs->cpumask)); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int ret = -ENOMEM; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (!attrs) goto out_unlock; ret = cpumask_parse(buf, attrs->cpumask); if (!ret) ret = apply_workqueue_attrs_locked(wq, attrs); out_unlock: apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affn_scope_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); int written; mutex_lock(&wq->mutex); if (wq->unbound_attrs->affn_scope == WQ_AFFN_DFL) written = scnprintf(buf, PAGE_SIZE, "%s (%s)\n", wq_affn_names[WQ_AFFN_DFL], wq_affn_names[wq_affn_dfl]); else written = scnprintf(buf, PAGE_SIZE, "%s\n", wq_affn_names[wq->unbound_attrs->affn_scope]); mutex_unlock(&wq->mutex); return written; } static ssize_t wq_affn_scope_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int affn, ret = -ENOMEM; affn = parse_affn_scope(buf); if (affn < 0) return affn; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_scope = affn; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static ssize_t wq_affinity_strict_show(struct device *dev, struct device_attribute *attr, char *buf) { struct workqueue_struct *wq = dev_to_wq(dev); return scnprintf(buf, PAGE_SIZE, "%d\n", wq->unbound_attrs->affn_strict); } static ssize_t wq_affinity_strict_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { struct workqueue_struct *wq = dev_to_wq(dev); struct workqueue_attrs *attrs; int v, ret = -ENOMEM; if (sscanf(buf, "%d", &v) != 1) return -EINVAL; apply_wqattrs_lock(); attrs = wq_sysfs_prep_attrs(wq); if (attrs) { attrs->affn_strict = (bool)v; ret = apply_workqueue_attrs_locked(wq, attrs); } apply_wqattrs_unlock(); free_workqueue_attrs(attrs); return ret ?: count; } static struct device_attribute wq_sysfs_unbound_attrs[] = { __ATTR(nice, 0644, wq_nice_show, wq_nice_store), __ATTR(cpumask, 0644, wq_cpumask_show, wq_cpumask_store), __ATTR(affinity_scope, 0644, wq_affn_scope_show, wq_affn_scope_store), __ATTR(affinity_strict, 0644, wq_affinity_strict_show, wq_affinity_strict_store), __ATTR_NULL, }; static const struct bus_type wq_subsys = { .name = "workqueue", .dev_groups = wq_sysfs_groups, }; /** * workqueue_set_unbound_cpumask - Set the low-level unbound cpumask * @cpumask: the cpumask to set * * The low-level workqueues cpumask is a global cpumask that limits * the affinity of all unbound workqueues. This function check the @cpumask * and apply it to all unbound workqueues and updates all pwqs of them. * * Return: 0 - Success * -EINVAL - Invalid @cpumask * -ENOMEM - Failed to allocate memory for attrs or pwqs. */ static int workqueue_set_unbound_cpumask(cpumask_var_t cpumask) { int ret = -EINVAL; /* * Not excluding isolated cpus on purpose. * If the user wishes to include them, we allow that. */ cpumask_and(cpumask, cpumask, cpu_possible_mask); if (!cpumask_empty(cpumask)) { apply_wqattrs_lock(); cpumask_copy(wq_requested_unbound_cpumask, cpumask); if (cpumask_equal(cpumask, wq_unbound_cpumask)) { ret = 0; goto out_unlock; } ret = workqueue_apply_unbound_cpumask(cpumask); out_unlock: apply_wqattrs_unlock(); } return ret; } static ssize_t __wq_cpumask_show(struct device *dev, struct device_attribute *attr, char *buf, cpumask_var_t mask) { int written; mutex_lock(&wq_pool_mutex); written = scnprintf(buf, PAGE_SIZE, "%*pb\n", cpumask_pr_args(mask)); mutex_unlock(&wq_pool_mutex); return written; } static ssize_t cpumask_requested_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_requested_unbound_cpumask); } static DEVICE_ATTR_RO(cpumask_requested); static ssize_t cpumask_isolated_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_isolated_cpumask); } static DEVICE_ATTR_RO(cpumask_isolated); static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr, char *buf) { return __wq_cpumask_show(dev, attr, buf, wq_unbound_cpumask); } static ssize_t cpumask_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { cpumask_var_t cpumask; int ret; if (!zalloc_cpumask_var(&cpumask, GFP_KERNEL)) return -ENOMEM; ret = cpumask_parse(buf, cpumask); if (!ret) ret = workqueue_set_unbound_cpumask(cpumask); free_cpumask_var(cpumask); return ret ? ret : count; } static DEVICE_ATTR_RW(cpumask); static struct attribute *wq_sysfs_cpumask_attrs[] = { &dev_attr_cpumask.attr, &dev_attr_cpumask_requested.attr, &dev_attr_cpumask_isolated.attr, NULL, }; ATTRIBUTE_GROUPS(wq_sysfs_cpumask); static int __init wq_sysfs_init(void) { return subsys_virtual_register(&wq_subsys, wq_sysfs_cpumask_groups); } core_initcall(wq_sysfs_init); static void wq_device_release(struct device *dev) { struct wq_device *wq_dev = container_of(dev, struct wq_device, dev); kfree(wq_dev); } /** * workqueue_sysfs_register - make a workqueue visible in sysfs * @wq: the workqueue to register * * Expose @wq in sysfs under /sys/bus/workqueue/devices. * alloc_workqueue*() automatically calls this function if WQ_SYSFS is set * which is the preferred method. * * Workqueue user should use this function directly iff it wants to apply * workqueue_attrs before making the workqueue visible in sysfs; otherwise, * apply_workqueue_attrs() may race against userland updating the * attributes. * * Return: 0 on success, -errno on failure. */ int workqueue_sysfs_register(struct workqueue_struct *wq) { struct wq_device *wq_dev; int ret; /* * Adjusting max_active breaks ordering guarantee. Disallow exposing * ordered workqueues. */ if (WARN_ON(wq->flags & __WQ_ORDERED)) return -EINVAL; wq->wq_dev = wq_dev = kzalloc(sizeof(*wq_dev), GFP_KERNEL); if (!wq_dev) return -ENOMEM; wq_dev->wq = wq; wq_dev->dev.bus = &wq_subsys; wq_dev->dev.release = wq_device_release; dev_set_name(&wq_dev->dev, "%s", wq->name); /* * unbound_attrs are created separately. Suppress uevent until * everything is ready. */ dev_set_uevent_suppress(&wq_dev->dev, true); ret = device_register(&wq_dev->dev); if (ret) { put_device(&wq_dev->dev); wq->wq_dev = NULL; return ret; } if (wq->flags & WQ_UNBOUND) { struct device_attribute *attr; for (attr = wq_sysfs_unbound_attrs; attr->attr.name; attr++) { ret = device_create_file(&wq_dev->dev, attr); if (ret) { device_unregister(&wq_dev->dev); wq->wq_dev = NULL; return ret; } } } dev_set_uevent_suppress(&wq_dev->dev, false); kobject_uevent(&wq_dev->dev.kobj, KOBJ_ADD); return 0; } /** * workqueue_sysfs_unregister - undo workqueue_sysfs_register() * @wq: the workqueue to unregister * * If @wq is registered to sysfs by workqueue_sysfs_register(), unregister. */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { struct wq_device *wq_dev = wq->wq_dev; if (!wq->wq_dev) return; wq->wq_dev = NULL; device_unregister(&wq_dev->dev); } #else /* CONFIG_SYSFS */ static void workqueue_sysfs_unregister(struct workqueue_struct *wq) { } #endif /* CONFIG_SYSFS */ /* * Workqueue watchdog. * * Stall may be caused by various bugs - missing WQ_MEM_RECLAIM, illegal * flush dependency, a concurrency managed work item which stays RUNNING * indefinitely. Workqueue stalls can be very difficult to debug as the * usual warning mechanisms don't trigger and internal workqueue state is * largely opaque. * * Workqueue watchdog monitors all worker pools periodically and dumps * state if some pools failed to make forward progress for a while where * forward progress is defined as the first item on ->worklist changing. * * This mechanism is controlled through the kernel parameter * "workqueue.watchdog_thresh" which can be updated at runtime through the * corresponding sysfs parameter file. */ #ifdef CONFIG_WQ_WATCHDOG static unsigned long wq_watchdog_thresh = 30; static struct timer_list wq_watchdog_timer; static unsigned long wq_watchdog_touched = INITIAL_JIFFIES; static DEFINE_PER_CPU(unsigned long, wq_watchdog_touched_cpu) = INITIAL_JIFFIES; /* * Show workers that might prevent the processing of pending work items. * The only candidates are CPU-bound workers in the running state. * Pending work items should be handled by another idle worker * in all other situations. */ static void show_cpu_pool_hog(struct worker_pool *pool) { struct worker *worker; unsigned long irq_flags; int bkt; raw_spin_lock_irqsave(&pool->lock, irq_flags); hash_for_each(pool->busy_hash, bkt, worker, hentry) { if (task_is_running(worker->task)) { /* * Defer printing to avoid deadlocks in console * drivers that queue work while holding locks * also taken in their write paths. */ printk_deferred_enter(); pr_info("pool %d:\n", pool->id); sched_show_task(worker->task); printk_deferred_exit(); } } raw_spin_unlock_irqrestore(&pool->lock, irq_flags); } static void show_cpu_pools_hogs(void) { struct worker_pool *pool; int pi; pr_info("Showing backtraces of running workers in stalled CPU-bound worker pools:\n"); rcu_read_lock(); for_each_pool(pool, pi) { if (pool->cpu_stall) show_cpu_pool_hog(pool); } rcu_read_unlock(); } static void wq_watchdog_reset_touched(void) { int cpu; wq_watchdog_touched = jiffies; for_each_possible_cpu(cpu) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; } static void wq_watchdog_timer_fn(struct timer_list *unused) { unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ; bool lockup_detected = false; bool cpu_pool_stall = false; unsigned long now = jiffies; struct worker_pool *pool; int pi; if (!thresh) return; rcu_read_lock(); for_each_pool(pool, pi) { unsigned long pool_ts, touched, ts; pool->cpu_stall = false; if (list_empty(&pool->worklist)) continue; /* * If a virtual machine is stopped by the host it can look to * the watchdog like a stall. */ kvm_check_and_clear_guest_paused(); /* get the latest of pool and touched timestamps */ if (pool->cpu >= 0) touched = READ_ONCE(per_cpu(wq_watchdog_touched_cpu, pool->cpu)); else touched = READ_ONCE(wq_watchdog_touched); pool_ts = READ_ONCE(pool->watchdog_ts); if (time_after(pool_ts, touched)) ts = pool_ts; else ts = touched; /* did we stall? */ if (time_after(now, ts + thresh)) { lockup_detected = true; if (pool->cpu >= 0 && !(pool->flags & POOL_BH)) { pool->cpu_stall = true; cpu_pool_stall = true; } pr_emerg("BUG: workqueue lockup - pool"); pr_cont_pool_info(pool); pr_cont(" stuck for %us!\n", jiffies_to_msecs(now - pool_ts) / 1000); } } rcu_read_unlock(); if (lockup_detected) show_all_workqueues(); if (cpu_pool_stall) show_cpu_pools_hogs(); wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh); } notrace void wq_watchdog_touch(int cpu) { if (cpu >= 0) per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies; wq_watchdog_touched = jiffies; } static void wq_watchdog_set_thresh(unsigned long thresh) { wq_watchdog_thresh = 0; del_timer_sync(&wq_watchdog_timer); if (thresh) { wq_watchdog_thresh = thresh; wq_watchdog_reset_touched(); mod_timer(&wq_watchdog_timer, jiffies + thresh * HZ); } } static int wq_watchdog_param_set_thresh(const char *val, const struct kernel_param *kp) { unsigned long thresh; int ret; ret = kstrtoul(val, 0, &thresh); if (ret) return ret; if (system_wq) wq_watchdog_set_thresh(thresh); else wq_watchdog_thresh = thresh; return 0; } static const struct kernel_param_ops wq_watchdog_thresh_ops = { .set = wq_watchdog_param_set_thresh, .get = param_get_ulong, }; module_param_cb(watchdog_thresh, &wq_watchdog_thresh_ops, &wq_watchdog_thresh, 0644); static void wq_watchdog_init(void) { timer_setup(&wq_watchdog_timer, wq_watchdog_timer_fn, TIMER_DEFERRABLE); wq_watchdog_set_thresh(wq_watchdog_thresh); } #else /* CONFIG_WQ_WATCHDOG */ static inline void wq_watchdog_init(void) { } #endif /* CONFIG_WQ_WATCHDOG */ static void bh_pool_kick_normal(struct irq_work *irq_work) { raise_softirq_irqoff(TASKLET_SOFTIRQ); } static void bh_pool_kick_highpri(struct irq_work *irq_work) { raise_softirq_irqoff(HI_SOFTIRQ); } static void __init restrict_unbound_cpumask(const char *name, const struct cpumask *mask) { if (!cpumask_intersects(wq_unbound_cpumask, mask)) { pr_warn("workqueue: Restricting unbound_cpumask (%*pb) with %s (%*pb) leaves no CPU, ignoring\n", cpumask_pr_args(wq_unbound_cpumask), name, cpumask_pr_args(mask)); return; } cpumask_and(wq_unbound_cpumask, wq_unbound_cpumask, mask); } static void __init init_cpu_worker_pool(struct worker_pool *pool, int cpu, int nice) { BUG_ON(init_worker_pool(pool)); pool->cpu = cpu; cpumask_copy(pool->attrs->cpumask, cpumask_of(cpu)); cpumask_copy(pool->attrs->__pod_cpumask, cpumask_of(cpu)); pool->attrs->nice = nice; pool->attrs->affn_strict = true; pool->node = cpu_to_node(cpu); /* alloc pool ID */ mutex_lock(&wq_pool_mutex); BUG_ON(worker_pool_assign_id(pool)); mutex_unlock(&wq_pool_mutex); } /** * workqueue_init_early - early init for workqueue subsystem * * This is the first step of three-staged workqueue subsystem initialization and * invoked as soon as the bare basics - memory allocation, cpumasks and idr are * up. It sets up all the data structures and system workqueues and allows early * boot code to create workqueues and queue/cancel work items. Actual work item * execution starts only after kthreads can be created and scheduled right * before early initcalls. */ void __init workqueue_init_early(void) { struct wq_pod_type *pt = &wq_pod_types[WQ_AFFN_SYSTEM]; int std_nice[NR_STD_WORKER_POOLS] = { 0, HIGHPRI_NICE_LEVEL }; void (*irq_work_fns[2])(struct irq_work *) = { bh_pool_kick_normal, bh_pool_kick_highpri }; int i, cpu; BUILD_BUG_ON(__alignof__(struct pool_workqueue) < __alignof__(long long)); BUG_ON(!alloc_cpumask_var(&wq_unbound_cpumask, GFP_KERNEL)); BUG_ON(!alloc_cpumask_var(&wq_requested_unbound_cpumask, GFP_KERNEL)); BUG_ON(!zalloc_cpumask_var(&wq_isolated_cpumask, GFP_KERNEL)); cpumask_copy(wq_unbound_cpumask, cpu_possible_mask); restrict_unbound_cpumask("HK_TYPE_WQ", housekeeping_cpumask(HK_TYPE_WQ)); restrict_unbound_cpumask("HK_TYPE_DOMAIN", housekeeping_cpumask(HK_TYPE_DOMAIN)); if (!cpumask_empty(&wq_cmdline_cpumask)) restrict_unbound_cpumask("workqueue.unbound_cpus", &wq_cmdline_cpumask); cpumask_copy(wq_requested_unbound_cpumask, wq_unbound_cpumask); pwq_cache = KMEM_CACHE(pool_workqueue, SLAB_PANIC); wq_update_pod_attrs_buf = alloc_workqueue_attrs(); BUG_ON(!wq_update_pod_attrs_buf); /* * If nohz_full is enabled, set power efficient workqueue as unbound. * This allows workqueue items to be moved to HK CPUs. */ if (housekeeping_enabled(HK_TYPE_TICK)) wq_power_efficient = true; /* initialize WQ_AFFN_SYSTEM pods */ pt->pod_cpus = kcalloc(1, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(1, sizeof(pt->pod_node[0]), GFP_KERNEL); pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node || !pt->cpu_pod); BUG_ON(!zalloc_cpumask_var_node(&pt->pod_cpus[0], GFP_KERNEL, NUMA_NO_NODE)); pt->nr_pods = 1; cpumask_copy(pt->pod_cpus[0], cpu_possible_mask); pt->pod_node[0] = NUMA_NO_NODE; pt->cpu_pod[0] = 0; /* initialize BH and CPU pools */ for_each_possible_cpu(cpu) { struct worker_pool *pool; i = 0; for_each_bh_worker_pool(pool, cpu) { init_cpu_worker_pool(pool, cpu, std_nice[i]); pool->flags |= POOL_BH; init_irq_work(bh_pool_irq_work(pool), irq_work_fns[i]); i++; } i = 0; for_each_cpu_worker_pool(pool, cpu) init_cpu_worker_pool(pool, cpu, std_nice[i++]); } /* create default unbound and ordered wq attrs */ for (i = 0; i < NR_STD_WORKER_POOLS; i++) { struct workqueue_attrs *attrs; BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; unbound_std_wq_attrs[i] = attrs; /* * An ordered wq should have only one pwq as ordering is * guaranteed by max_active which is enforced by pwqs. */ BUG_ON(!(attrs = alloc_workqueue_attrs())); attrs->nice = std_nice[i]; attrs->ordered = true; ordered_wq_attrs[i] = attrs; } system_wq = alloc_workqueue("events", 0, 0); system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0); system_long_wq = alloc_workqueue("events_long", 0, 0); system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE); system_freezable_wq = alloc_workqueue("events_freezable", WQ_FREEZABLE, 0); system_power_efficient_wq = alloc_workqueue("events_power_efficient", WQ_POWER_EFFICIENT, 0); system_freezable_power_efficient_wq = alloc_workqueue("events_freezable_pwr_efficient", WQ_FREEZABLE | WQ_POWER_EFFICIENT, 0); system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0); system_bh_highpri_wq = alloc_workqueue("events_bh_highpri", WQ_BH | WQ_HIGHPRI, 0); BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq || !system_unbound_wq || !system_freezable_wq || !system_power_efficient_wq || !system_freezable_power_efficient_wq || !system_bh_wq || !system_bh_highpri_wq); } static void __init wq_cpu_intensive_thresh_init(void) { unsigned long thresh; unsigned long bogo; pwq_release_worker = kthread_create_worker(0, "pool_workqueue_release"); BUG_ON(IS_ERR(pwq_release_worker)); /* if the user set it to a specific value, keep it */ if (wq_cpu_intensive_thresh_us != ULONG_MAX) return; /* * The default of 10ms is derived from the fact that most modern (as of * 2023) processors can do a lot in 10ms and that it's just below what * most consider human-perceivable. However, the kernel also runs on a * lot slower CPUs including microcontrollers where the threshold is way * too low. * * Let's scale up the threshold upto 1 second if BogoMips is below 4000. * This is by no means accurate but it doesn't have to be. The mechanism * is still useful even when the threshold is fully scaled up. Also, as * the reports would usually be applicable to everyone, some machines * operating on longer thresholds won't significantly diminish their * usefulness. */ thresh = 10 * USEC_PER_MSEC; /* see init/calibrate.c for lpj -> BogoMIPS calculation */ bogo = max_t(unsigned long, loops_per_jiffy / 500000 * HZ, 1); if (bogo < 4000) thresh = min_t(unsigned long, thresh * 4000 / bogo, USEC_PER_SEC); pr_debug("wq_cpu_intensive_thresh: lpj=%lu BogoMIPS=%lu thresh_us=%lu\n", loops_per_jiffy, bogo, thresh); wq_cpu_intensive_thresh_us = thresh; } /** * workqueue_init - bring workqueue subsystem fully online * * This is the second step of three-staged workqueue subsystem initialization * and invoked as soon as kthreads can be created and scheduled. Workqueues have * been created and work items queued on them, but there are no kworkers * executing the work items yet. Populate the worker pools with the initial * workers and enable future kworker creations. */ void __init workqueue_init(void) { struct workqueue_struct *wq; struct worker_pool *pool; int cpu, bkt; wq_cpu_intensive_thresh_init(); mutex_lock(&wq_pool_mutex); /* * Per-cpu pools created earlier could be missing node hint. Fix them * up. Also, create a rescuer for workqueues that requested it. */ for_each_possible_cpu(cpu) { for_each_bh_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); for_each_cpu_worker_pool(pool, cpu) pool->node = cpu_to_node(cpu); } list_for_each_entry(wq, &workqueues, list) { WARN(init_rescuer(wq), "workqueue: failed to create early rescuer for %s", wq->name); } mutex_unlock(&wq_pool_mutex); /* * Create the initial workers. A BH pool has one pseudo worker that * represents the shared BH execution context and thus doesn't get * affected by hotplug events. Create the BH pseudo workers for all * possible CPUs here. */ for_each_possible_cpu(cpu) for_each_bh_worker_pool(pool, cpu) BUG_ON(!create_worker(pool)); for_each_online_cpu(cpu) { for_each_cpu_worker_pool(pool, cpu) { pool->flags &= ~POOL_DISASSOCIATED; BUG_ON(!create_worker(pool)); } } hash_for_each(unbound_pool_hash, bkt, pool, hash_node) BUG_ON(!create_worker(pool)); wq_online = true; wq_watchdog_init(); } /* * Initialize @pt by first initializing @pt->cpu_pod[] with pod IDs according to * @cpu_shares_pod(). Each subset of CPUs that share a pod is assigned a unique * and consecutive pod ID. The rest of @pt is initialized accordingly. */ static void __init init_pod_type(struct wq_pod_type *pt, bool (*cpus_share_pod)(int, int)) { int cur, pre, cpu, pod; pt->nr_pods = 0; /* init @pt->cpu_pod[] according to @cpus_share_pod() */ pt->cpu_pod = kcalloc(nr_cpu_ids, sizeof(pt->cpu_pod[0]), GFP_KERNEL); BUG_ON(!pt->cpu_pod); for_each_possible_cpu(cur) { for_each_possible_cpu(pre) { if (pre >= cur) { pt->cpu_pod[cur] = pt->nr_pods++; break; } if (cpus_share_pod(cur, pre)) { pt->cpu_pod[cur] = pt->cpu_pod[pre]; break; } } } /* init the rest to match @pt->cpu_pod[] */ pt->pod_cpus = kcalloc(pt->nr_pods, sizeof(pt->pod_cpus[0]), GFP_KERNEL); pt->pod_node = kcalloc(pt->nr_pods, sizeof(pt->pod_node[0]), GFP_KERNEL); BUG_ON(!pt->pod_cpus || !pt->pod_node); for (pod = 0; pod < pt->nr_pods; pod++) BUG_ON(!zalloc_cpumask_var(&pt->pod_cpus[pod], GFP_KERNEL)); for_each_possible_cpu(cpu) { cpumask_set_cpu(cpu, pt->pod_cpus[pt->cpu_pod[cpu]]); pt->pod_node[pt->cpu_pod[cpu]] = cpu_to_node(cpu); } } static bool __init cpus_dont_share(int cpu0, int cpu1) { return false; } static bool __init cpus_share_smt(int cpu0, int cpu1) { #ifdef CONFIG_SCHED_SMT return cpumask_test_cpu(cpu0, cpu_smt_mask(cpu1)); #else return false; #endif } static bool __init cpus_share_numa(int cpu0, int cpu1) { return cpu_to_node(cpu0) == cpu_to_node(cpu1); } /** * workqueue_init_topology - initialize CPU pods for unbound workqueues * * This is the third step of three-staged workqueue subsystem initialization and * invoked after SMP and topology information are fully initialized. It * initializes the unbound CPU pods accordingly. */ void __init workqueue_init_topology(void) { struct workqueue_struct *wq; int cpu; init_pod_type(&wq_pod_types[WQ_AFFN_CPU], cpus_dont_share); init_pod_type(&wq_pod_types[WQ_AFFN_SMT], cpus_share_smt); init_pod_type(&wq_pod_types[WQ_AFFN_CACHE], cpus_share_cache); init_pod_type(&wq_pod_types[WQ_AFFN_NUMA], cpus_share_numa); wq_topo_initialized = true; mutex_lock(&wq_pool_mutex); /* * Workqueues allocated earlier would have all CPUs sharing the default * worker pool. Explicitly call wq_update_pod() on all workqueue and CPU * combinations to apply per-pod sharing. */ list_for_each_entry(wq, &workqueues, list) { for_each_online_cpu(cpu) wq_update_pod(wq, cpu, cpu, true); if (wq->flags & WQ_UNBOUND) { mutex_lock(&wq->mutex); wq_update_node_max_active(wq, -1); mutex_unlock(&wq->mutex); } } mutex_unlock(&wq_pool_mutex); } void __warn_flushing_systemwide_wq(void) { pr_warn("WARNING: Flushing system-wide workqueues will be prohibited in near future.\n"); dump_stack(); } EXPORT_SYMBOL(__warn_flushing_systemwide_wq); static int __init workqueue_unbound_cpus_setup(char *str) { if (cpulist_parse(str, &wq_cmdline_cpumask) < 0) { cpumask_clear(&wq_cmdline_cpumask); pr_warn("workqueue.unbound_cpus: incorrect CPU range, using default\n"); } return 1; } __setup("workqueue.unbound_cpus=", workqueue_unbound_cpus_setup); |
| 10 10 10 11 11 14 1 11 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 | /* SPDX-License-Identifier: GPL-2.0 */ #if !defined(_TRACE_ARM_ARM64_KVM_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_ARM_ARM64_KVM_H #include <asm/kvm_emulate.h> #include <kvm/arm_arch_timer.h> #include <linux/tracepoint.h> #undef TRACE_SYSTEM #define TRACE_SYSTEM kvm /* * Tracepoints for entry/exit to guest */ TRACE_EVENT(kvm_entry, TP_PROTO(unsigned long vcpu_pc), TP_ARGS(vcpu_pc), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; ), TP_printk("PC: 0x%016lx", __entry->vcpu_pc) ); TRACE_EVENT(kvm_exit, TP_PROTO(int ret, unsigned int esr_ec, unsigned long vcpu_pc), TP_ARGS(ret, esr_ec, vcpu_pc), TP_STRUCT__entry( __field( int, ret ) __field( unsigned int, esr_ec ) __field( unsigned long, vcpu_pc ) ), TP_fast_assign( __entry->ret = ARM_EXCEPTION_CODE(ret); __entry->esr_ec = ARM_EXCEPTION_IS_TRAP(ret) ? esr_ec : 0; __entry->vcpu_pc = vcpu_pc; ), TP_printk("%s: HSR_EC: 0x%04x (%s), PC: 0x%016lx", __print_symbolic(__entry->ret, kvm_arm_exception_type), __entry->esr_ec, __print_symbolic(__entry->esr_ec, kvm_arm_exception_class), __entry->vcpu_pc) ); TRACE_EVENT(kvm_guest_fault, TP_PROTO(unsigned long vcpu_pc, unsigned long hsr, unsigned long hxfar, unsigned long long ipa), TP_ARGS(vcpu_pc, hsr, hxfar, ipa), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, hsr ) __field( unsigned long, hxfar ) __field( unsigned long long, ipa ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->hsr = hsr; __entry->hxfar = hxfar; __entry->ipa = ipa; ), TP_printk("ipa %#llx, hsr %#08lx, hxfar %#08lx, pc %#016lx", __entry->ipa, __entry->hsr, __entry->hxfar, __entry->vcpu_pc) ); TRACE_EVENT(kvm_access_fault, TP_PROTO(unsigned long ipa), TP_ARGS(ipa), TP_STRUCT__entry( __field( unsigned long, ipa ) ), TP_fast_assign( __entry->ipa = ipa; ), TP_printk("IPA: %lx", __entry->ipa) ); TRACE_EVENT(kvm_irq_line, TP_PROTO(unsigned int type, int vcpu_idx, int irq_num, int level), TP_ARGS(type, vcpu_idx, irq_num, level), TP_STRUCT__entry( __field( unsigned int, type ) __field( int, vcpu_idx ) __field( int, irq_num ) __field( int, level ) ), TP_fast_assign( __entry->type = type; __entry->vcpu_idx = vcpu_idx; __entry->irq_num = irq_num; __entry->level = level; ), TP_printk("Inject %s interrupt (%d), vcpu->idx: %d, num: %d, level: %d", (__entry->type == KVM_ARM_IRQ_TYPE_CPU) ? "CPU" : (__entry->type == KVM_ARM_IRQ_TYPE_PPI) ? "VGIC PPI" : (__entry->type == KVM_ARM_IRQ_TYPE_SPI) ? "VGIC SPI" : "UNKNOWN", __entry->type, __entry->vcpu_idx, __entry->irq_num, __entry->level) ); TRACE_EVENT(kvm_mmio_emulate, TP_PROTO(unsigned long vcpu_pc, unsigned long instr, unsigned long cpsr), TP_ARGS(vcpu_pc, instr, cpsr), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, instr ) __field( unsigned long, cpsr ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->instr = instr; __entry->cpsr = cpsr; ), TP_printk("Emulate MMIO at: 0x%016lx (instr: %08lx, cpsr: %08lx)", __entry->vcpu_pc, __entry->instr, __entry->cpsr) ); TRACE_EVENT(kvm_mmio_nisv, TP_PROTO(unsigned long vcpu_pc, unsigned long esr, unsigned long far, unsigned long ipa), TP_ARGS(vcpu_pc, esr, far, ipa), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( unsigned long, esr ) __field( unsigned long, far ) __field( unsigned long, ipa ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->esr = esr; __entry->far = far; __entry->ipa = ipa; ), TP_printk("ipa %#016lx, esr %#016lx, far %#016lx, pc %#016lx", __entry->ipa, __entry->esr, __entry->far, __entry->vcpu_pc) ); TRACE_EVENT(kvm_set_way_flush, TP_PROTO(unsigned long vcpu_pc, bool cache), TP_ARGS(vcpu_pc, cache), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( bool, cache ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->cache = cache; ), TP_printk("S/W flush at 0x%016lx (cache %s)", __entry->vcpu_pc, __entry->cache ? "on" : "off") ); TRACE_EVENT(kvm_toggle_cache, TP_PROTO(unsigned long vcpu_pc, bool was, bool now), TP_ARGS(vcpu_pc, was, now), TP_STRUCT__entry( __field( unsigned long, vcpu_pc ) __field( bool, was ) __field( bool, now ) ), TP_fast_assign( __entry->vcpu_pc = vcpu_pc; __entry->was = was; __entry->now = now; ), TP_printk("VM op at 0x%016lx (cache was %s, now %s)", __entry->vcpu_pc, __entry->was ? "on" : "off", __entry->now ? "on" : "off") ); /* * Tracepoints for arch_timer */ TRACE_EVENT(kvm_timer_update_irq, TP_PROTO(unsigned long vcpu_id, __u32 irq, int level), TP_ARGS(vcpu_id, irq, level), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( __u32, irq ) __field( int, level ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->irq = irq; __entry->level = level; ), TP_printk("VCPU: %ld, IRQ %d, level %d", __entry->vcpu_id, __entry->irq, __entry->level) ); TRACE_EVENT(kvm_get_timer_map, TP_PROTO(unsigned long vcpu_id, struct timer_map *map), TP_ARGS(vcpu_id, map), TP_STRUCT__entry( __field( unsigned long, vcpu_id ) __field( int, direct_vtimer ) __field( int, direct_ptimer ) __field( int, emul_vtimer ) __field( int, emul_ptimer ) ), TP_fast_assign( __entry->vcpu_id = vcpu_id; __entry->direct_vtimer = arch_timer_ctx_index(map->direct_vtimer); __entry->direct_ptimer = (map->direct_ptimer) ? arch_timer_ctx_index(map->direct_ptimer) : -1; __entry->emul_vtimer = (map->emul_vtimer) ? arch_timer_ctx_index(map->emul_vtimer) : -1; __entry->emul_ptimer = (map->emul_ptimer) ? arch_timer_ctx_index(map->emul_ptimer) : -1; ), TP_printk("VCPU: %ld, dv: %d, dp: %d, ev: %d, ep: %d", __entry->vcpu_id, __entry->direct_vtimer, __entry->direct_ptimer, __entry->emul_vtimer, __entry->emul_ptimer) ); TRACE_EVENT(kvm_timer_save_state, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( unsigned long, ctl ) __field( unsigned long long, cval ) __field( int, timer_idx ) ), TP_fast_assign( __entry->ctl = timer_get_ctl(ctx); __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk(" CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", __entry->ctl, __entry->cval, __entry->timer_idx) ); TRACE_EVENT(kvm_timer_restore_state, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( unsigned long, ctl ) __field( unsigned long long, cval ) __field( int, timer_idx ) ), TP_fast_assign( __entry->ctl = timer_get_ctl(ctx); __entry->cval = timer_get_cval(ctx); __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk("CTL: %#08lx CVAL: %#16llx arch_timer_ctx_index: %d", __entry->ctl, __entry->cval, __entry->timer_idx) ); TRACE_EVENT(kvm_timer_hrtimer_expire, TP_PROTO(struct arch_timer_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field( int, timer_idx ) ), TP_fast_assign( __entry->timer_idx = arch_timer_ctx_index(ctx); ), TP_printk("arch_timer_ctx_index: %d", __entry->timer_idx) ); TRACE_EVENT(kvm_timer_emulate, TP_PROTO(struct arch_timer_context *ctx, bool should_fire), TP_ARGS(ctx, should_fire), TP_STRUCT__entry( __field( int, timer_idx ) __field( bool, should_fire ) ), TP_fast_assign( __entry->timer_idx = arch_timer_ctx_index(ctx); __entry->should_fire = should_fire; ), TP_printk("arch_timer_ctx_index: %d (should_fire: %d)", __entry->timer_idx, __entry->should_fire) ); TRACE_EVENT(kvm_nested_eret, TP_PROTO(struct kvm_vcpu *vcpu, unsigned long elr_el2, unsigned long spsr_el2), TP_ARGS(vcpu, elr_el2, spsr_el2), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(unsigned long, elr_el2) __field(unsigned long, spsr_el2) __field(unsigned long, target_mode) __field(unsigned long, hcr_el2) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->elr_el2 = elr_el2; __entry->spsr_el2 = spsr_el2; __entry->target_mode = spsr_el2 & (PSR_MODE_MASK | PSR_MODE32_BIT); __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); ), TP_printk("elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", __entry->elr_el2, __entry->spsr_el2, __print_symbolic(__entry->target_mode, kvm_mode_names), __entry->hcr_el2) ); TRACE_EVENT(kvm_inject_nested_exception, TP_PROTO(struct kvm_vcpu *vcpu, u64 esr_el2, int type), TP_ARGS(vcpu, esr_el2, type), TP_STRUCT__entry( __field(struct kvm_vcpu *, vcpu) __field(unsigned long, esr_el2) __field(int, type) __field(unsigned long, spsr_el2) __field(unsigned long, pc) __field(unsigned long, source_mode) __field(unsigned long, hcr_el2) ), TP_fast_assign( __entry->vcpu = vcpu; __entry->esr_el2 = esr_el2; __entry->type = type; __entry->spsr_el2 = *vcpu_cpsr(vcpu); __entry->pc = *vcpu_pc(vcpu); __entry->source_mode = *vcpu_cpsr(vcpu) & (PSR_MODE_MASK | PSR_MODE32_BIT); __entry->hcr_el2 = __vcpu_sys_reg(vcpu, HCR_EL2); ), TP_printk("%s: esr_el2 0x%lx elr_el2: 0x%lx spsr_el2: 0x%08lx (M: %s) hcr_el2: %lx", __print_symbolic(__entry->type, kvm_exception_type_names), __entry->esr_el2, __entry->pc, __entry->spsr_el2, __print_symbolic(__entry->source_mode, kvm_mode_names), __entry->hcr_el2) ); TRACE_EVENT(kvm_forward_sysreg_trap, TP_PROTO(struct kvm_vcpu *vcpu, u32 sysreg, bool is_read), TP_ARGS(vcpu, sysreg, is_read), TP_STRUCT__entry( __field(u64, pc) __field(u32, sysreg) __field(bool, is_read) ), TP_fast_assign( __entry->pc = *vcpu_pc(vcpu); __entry->sysreg = sysreg; __entry->is_read = is_read; ), TP_printk("%llx %c (%d,%d,%d,%d,%d)", __entry->pc, __entry->is_read ? 'R' : 'W', sys_reg_Op0(__entry->sysreg), sys_reg_Op1(__entry->sysreg), sys_reg_CRn(__entry->sysreg), sys_reg_CRm(__entry->sysreg), sys_reg_Op2(__entry->sysreg)) ); #endif /* _TRACE_ARM_ARM64_KVM_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #undef TRACE_INCLUDE_FILE #define TRACE_INCLUDE_FILE trace_arm /* This part must be outside protection */ #include <trace/define_trace.h> |
| 5 4 3 5 14 10 10 3 10 16 16 13 13 2 1 13 8 5 8 4 16 17 16 15 16 15 16 16 16 16 15 15 6 12 13 4 10 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 | // SPDX-License-Identifier: GPL-2.0-only /* * irqchip.c: Common API for in kernel interrupt controllers * Copyright (c) 2007, Intel Corporation. * Copyright 2010 Red Hat, Inc. and/or its affiliates. * Copyright (c) 2013, Alexander Graf <agraf@suse.de> * * This file is derived from virt/kvm/irq_comm.c. * * Authors: * Yaozu (Eddie) Dong <Eddie.dong@intel.com> * Alexander Graf <agraf@suse.de> */ #include <linux/kvm_host.h> #include <linux/slab.h> #include <linux/srcu.h> #include <linux/export.h> #include <trace/events/kvm.h> int kvm_irq_map_gsi(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *entries, int gsi) { struct kvm_irq_routing_table *irq_rt; struct kvm_kernel_irq_routing_entry *e; int n = 0; irq_rt = srcu_dereference_check(kvm->irq_routing, &kvm->irq_srcu, lockdep_is_held(&kvm->irq_lock)); if (irq_rt && gsi < irq_rt->nr_rt_entries) { hlist_for_each_entry(e, &irq_rt->map[gsi], link) { entries[n] = *e; ++n; } } return n; } int kvm_irq_map_chip_pin(struct kvm *kvm, unsigned irqchip, unsigned pin) { struct kvm_irq_routing_table *irq_rt; irq_rt = srcu_dereference(kvm->irq_routing, &kvm->irq_srcu); return irq_rt->chip[irqchip][pin]; } int kvm_send_userspace_msi(struct kvm *kvm, struct kvm_msi *msi) { struct kvm_kernel_irq_routing_entry route; if (!kvm_arch_irqchip_in_kernel(kvm) || (msi->flags & ~KVM_MSI_VALID_DEVID)) return -EINVAL; route.msi.address_lo = msi->address_lo; route.msi.address_hi = msi->address_hi; route.msi.data = msi->data; route.msi.flags = msi->flags; route.msi.devid = msi->devid; return kvm_set_msi(&route, kvm, KVM_USERSPACE_IRQ_SOURCE_ID, 1, false); } /* * Return value: * < 0 Interrupt was ignored (masked or not delivered for other reasons) * = 0 Interrupt was coalesced (previous irq is still pending) * > 0 Number of CPUs interrupt was delivered to */ int kvm_set_irq(struct kvm *kvm, int irq_source_id, u32 irq, int level, bool line_status) { struct kvm_kernel_irq_routing_entry irq_set[KVM_NR_IRQCHIPS]; int ret = -1, i, idx; trace_kvm_set_irq(irq, level, irq_source_id); /* Not possible to detect if the guest uses the PIC or the * IOAPIC. So set the bit in both. The guest will ignore * writes to the unused one. */ idx = srcu_read_lock(&kvm->irq_srcu); i = kvm_irq_map_gsi(kvm, irq_set, irq); srcu_read_unlock(&kvm->irq_srcu, idx); while (i--) { int r; r = irq_set[i].set(&irq_set[i], kvm, irq_source_id, level, line_status); if (r < 0) continue; ret = r + ((ret < 0) ? 0 : ret); } return ret; } static void free_irq_routing_table(struct kvm_irq_routing_table *rt) { int i; if (!rt) return; for (i = 0; i < rt->nr_rt_entries; ++i) { struct kvm_kernel_irq_routing_entry *e; struct hlist_node *n; hlist_for_each_entry_safe(e, n, &rt->map[i], link) { hlist_del(&e->link); kfree(e); } } kfree(rt); } void kvm_free_irq_routing(struct kvm *kvm) { /* Called only during vm destruction. Nobody can use the pointer at this stage */ struct kvm_irq_routing_table *rt = rcu_access_pointer(kvm->irq_routing); free_irq_routing_table(rt); } static int setup_routing_entry(struct kvm *kvm, struct kvm_irq_routing_table *rt, struct kvm_kernel_irq_routing_entry *e, const struct kvm_irq_routing_entry *ue) { struct kvm_kernel_irq_routing_entry *ei; int r; u32 gsi = array_index_nospec(ue->gsi, KVM_MAX_IRQ_ROUTES); /* * Do not allow GSI to be mapped to the same irqchip more than once. * Allow only one to one mapping between GSI and non-irqchip routing. */ hlist_for_each_entry(ei, &rt->map[gsi], link) if (ei->type != KVM_IRQ_ROUTING_IRQCHIP || ue->type != KVM_IRQ_ROUTING_IRQCHIP || ue->u.irqchip.irqchip == ei->irqchip.irqchip) return -EINVAL; e->gsi = gsi; e->type = ue->type; r = kvm_set_routing_entry(kvm, e, ue); if (r) return r; if (e->type == KVM_IRQ_ROUTING_IRQCHIP) rt->chip[e->irqchip.irqchip][e->irqchip.pin] = e->gsi; hlist_add_head(&e->link, &rt->map[e->gsi]); return 0; } void __attribute__((weak)) kvm_arch_irq_routing_update(struct kvm *kvm) { } bool __weak kvm_arch_can_set_irq_routing(struct kvm *kvm) { return true; } int kvm_set_irq_routing(struct kvm *kvm, const struct kvm_irq_routing_entry *ue, unsigned nr, unsigned flags) { struct kvm_irq_routing_table *new, *old; struct kvm_kernel_irq_routing_entry *e; u32 i, j, nr_rt_entries = 0; int r; for (i = 0; i < nr; ++i) { if (ue[i].gsi >= KVM_MAX_IRQ_ROUTES) return -EINVAL; nr_rt_entries = max(nr_rt_entries, ue[i].gsi); } nr_rt_entries += 1; new = kzalloc(struct_size(new, map, nr_rt_entries), GFP_KERNEL_ACCOUNT); if (!new) return -ENOMEM; new->nr_rt_entries = nr_rt_entries; for (i = 0; i < KVM_NR_IRQCHIPS; i++) for (j = 0; j < KVM_IRQCHIP_NUM_PINS; j++) new->chip[i][j] = -1; for (i = 0; i < nr; ++i) { r = -ENOMEM; e = kzalloc(sizeof(*e), GFP_KERNEL_ACCOUNT); if (!e) goto out; r = -EINVAL; switch (ue->type) { case KVM_IRQ_ROUTING_MSI: if (ue->flags & ~KVM_MSI_VALID_DEVID) goto free_entry; break; default: if (ue->flags) goto free_entry; break; } r = setup_routing_entry(kvm, new, e, ue); if (r) goto free_entry; ++ue; } mutex_lock(&kvm->irq_lock); old = rcu_dereference_protected(kvm->irq_routing, 1); rcu_assign_pointer(kvm->irq_routing, new); kvm_irq_routing_update(kvm); kvm_arch_irq_routing_update(kvm); mutex_unlock(&kvm->irq_lock); kvm_arch_post_irq_routing_update(kvm); synchronize_srcu_expedited(&kvm->irq_srcu); new = old; r = 0; goto out; free_entry: kfree(e); out: free_irq_routing_table(new); return r; } |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 | // SPDX-License-Identifier: GPL-2.0-only /* * Guest PC manipulation helpers * * Copyright (C) 2012,2013 - ARM Ltd * Copyright (C) 2020 - Google LLC * Author: Marc Zyngier <maz@kernel.org> */ #ifndef __ARM64_KVM_HYP_ADJUST_PC_H__ #define __ARM64_KVM_HYP_ADJUST_PC_H__ #include <asm/kvm_emulate.h> #include <asm/kvm_host.h> static inline void kvm_skip_instr(struct kvm_vcpu *vcpu) { if (vcpu_mode_is_32bit(vcpu)) { kvm_skip_instr32(vcpu); } else { *vcpu_pc(vcpu) += 4; *vcpu_cpsr(vcpu) &= ~PSR_BTYPE_MASK; } /* advance the singlestep state machine */ *vcpu_cpsr(vcpu) &= ~DBG_SPSR_SS; } /* * Skip an instruction which has been emulated at hyp while most guest sysregs * are live. */ static inline void __kvm_skip_instr(struct kvm_vcpu *vcpu) { *vcpu_pc(vcpu) = read_sysreg_el2(SYS_ELR); vcpu_gp_regs(vcpu)->pstate = read_sysreg_el2(SYS_SPSR); kvm_skip_instr(vcpu); write_sysreg_el2(vcpu_gp_regs(vcpu)->pstate, SYS_SPSR); write_sysreg_el2(*vcpu_pc(vcpu), SYS_ELR); } /* * Skip an instruction while host sysregs are live. * Assumes host is always 64-bit. */ static inline void kvm_skip_host_instr(void) { write_sysreg_el2(read_sysreg_el2(SYS_ELR) + 4, SYS_ELR); } #endif |
| 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM sock #if !defined(_TRACE_SOCK_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SOCK_H #include <net/sock.h> #include <net/ipv6.h> #include <linux/tracepoint.h> #include <linux/ipv6.h> #include <linux/tcp.h> #include <trace/events/net_probe_common.h> #define family_names \ EM(AF_INET) \ EMe(AF_INET6) /* The protocol traced by inet_sock_set_state */ #define inet_protocol_names \ EM(IPPROTO_TCP) \ EM(IPPROTO_DCCP) \ EM(IPPROTO_SCTP) \ EMe(IPPROTO_MPTCP) #define tcp_state_names \ EM(TCP_ESTABLISHED) \ EM(TCP_SYN_SENT) \ EM(TCP_SYN_RECV) \ EM(TCP_FIN_WAIT1) \ EM(TCP_FIN_WAIT2) \ EM(TCP_TIME_WAIT) \ EM(TCP_CLOSE) \ EM(TCP_CLOSE_WAIT) \ EM(TCP_LAST_ACK) \ EM(TCP_LISTEN) \ EM(TCP_CLOSING) \ EMe(TCP_NEW_SYN_RECV) #define skmem_kind_names \ EM(SK_MEM_SEND) \ EMe(SK_MEM_RECV) /* enums need to be exported to user space */ #undef EM #undef EMe #define EM(a) TRACE_DEFINE_ENUM(a); #define EMe(a) TRACE_DEFINE_ENUM(a); family_names inet_protocol_names tcp_state_names skmem_kind_names #undef EM #undef EMe #define EM(a) { a, #a }, #define EMe(a) { a, #a } #define show_family_name(val) \ __print_symbolic(val, family_names) #define show_inet_protocol_name(val) \ __print_symbolic(val, inet_protocol_names) #define show_tcp_state_name(val) \ __print_symbolic(val, tcp_state_names) #define show_skmem_kind_names(val) \ __print_symbolic(val, skmem_kind_names) TRACE_EVENT(sock_rcvqueue_full, TP_PROTO(struct sock *sk, struct sk_buff *skb), TP_ARGS(sk, skb), TP_STRUCT__entry( __field(int, rmem_alloc) __field(unsigned int, truesize) __field(int, sk_rcvbuf) ), TP_fast_assign( __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->truesize = skb->truesize; __entry->sk_rcvbuf = READ_ONCE(sk->sk_rcvbuf); ), TP_printk("rmem_alloc=%d truesize=%u sk_rcvbuf=%d", __entry->rmem_alloc, __entry->truesize, __entry->sk_rcvbuf) ); TRACE_EVENT(sock_exceed_buf_limit, TP_PROTO(struct sock *sk, struct proto *prot, long allocated, int kind), TP_ARGS(sk, prot, allocated, kind), TP_STRUCT__entry( __array(char, name, 32) __array(long, sysctl_mem, 3) __field(long, allocated) __field(int, sysctl_rmem) __field(int, rmem_alloc) __field(int, sysctl_wmem) __field(int, wmem_alloc) __field(int, wmem_queued) __field(int, kind) ), TP_fast_assign( strscpy(__entry->name, prot->name, 32); __entry->sysctl_mem[0] = READ_ONCE(prot->sysctl_mem[0]); __entry->sysctl_mem[1] = READ_ONCE(prot->sysctl_mem[1]); __entry->sysctl_mem[2] = READ_ONCE(prot->sysctl_mem[2]); __entry->allocated = allocated; __entry->sysctl_rmem = sk_get_rmem0(sk, prot); __entry->rmem_alloc = atomic_read(&sk->sk_rmem_alloc); __entry->sysctl_wmem = sk_get_wmem0(sk, prot); __entry->wmem_alloc = refcount_read(&sk->sk_wmem_alloc); __entry->wmem_queued = READ_ONCE(sk->sk_wmem_queued); __entry->kind = kind; ), TP_printk("proto:%s sysctl_mem=%ld,%ld,%ld allocated=%ld sysctl_rmem=%d rmem_alloc=%d sysctl_wmem=%d wmem_alloc=%d wmem_queued=%d kind=%s", __entry->name, __entry->sysctl_mem[0], __entry->sysctl_mem[1], __entry->sysctl_mem[2], __entry->allocated, __entry->sysctl_rmem, __entry->rmem_alloc, __entry->sysctl_wmem, __entry->wmem_alloc, __entry->wmem_queued, show_skmem_kind_names(__entry->kind) ) ); TRACE_EVENT(inet_sock_set_state, TP_PROTO(const struct sock *sk, const int oldstate, const int newstate), TP_ARGS(sk, oldstate, newstate), TP_STRUCT__entry( __field(const void *, skaddr) __field(int, oldstate) __field(int, newstate) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->skaddr = sk; __entry->oldstate = oldstate; __entry->newstate = newstate; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, show_tcp_state_name(__entry->oldstate), show_tcp_state_name(__entry->newstate)) ); TRACE_EVENT(inet_sk_error_report, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(int, error) __field(__u16, sport) __field(__u16, dport) __field(__u16, family) __field(__u16, protocol) __array(__u8, saddr, 4) __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) ), TP_fast_assign( const struct inet_sock *inet = inet_sk(sk); __be32 *p32; __entry->error = sk->sk_err; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->sport = ntohs(inet->inet_sport); __entry->dport = ntohs(inet->inet_dport); p32 = (__be32 *) __entry->saddr; *p32 = inet->inet_saddr; p32 = (__be32 *) __entry->daddr; *p32 = inet->inet_daddr; TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); ), TP_printk("family=%s protocol=%s sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c error=%d", show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, __entry->saddr_v6, __entry->daddr_v6, __entry->error) ); TRACE_EVENT(sk_data_ready, TP_PROTO(const struct sock *sk), TP_ARGS(sk), TP_STRUCT__entry( __field(const void *, skaddr) __field(__u16, family) __field(__u16, protocol) __field(unsigned long, ip) ), TP_fast_assign( __entry->skaddr = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ip = _RET_IP_; ), TP_printk("family=%u protocol=%u func=%ps", __entry->family, __entry->protocol, (void *)__entry->ip) ); /* * sock send/recv msg length */ DECLARE_EVENT_CLASS(sock_msg_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags), TP_STRUCT__entry( __field(void *, sk) __field(__u16, family) __field(__u16, protocol) __field(int, ret) __field(int, flags) ), TP_fast_assign( __entry->sk = sk; __entry->family = sk->sk_family; __entry->protocol = sk->sk_protocol; __entry->ret = ret; __entry->flags = flags; ), TP_printk("sk address = %p, family = %s protocol = %s, length = %d, error = %d, flags = 0x%x", __entry->sk, show_family_name(__entry->family), show_inet_protocol_name(__entry->protocol), !(__entry->flags & MSG_PEEK) ? (__entry->ret > 0 ? __entry->ret : 0) : 0, __entry->ret < 0 ? __entry->ret : 0, __entry->flags) ); DEFINE_EVENT(sock_msg_length, sock_send_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); DEFINE_EVENT(sock_msg_length, sock_recv_length, TP_PROTO(struct sock *sk, int ret, int flags), TP_ARGS(sk, ret, flags) ); #endif /* _TRACE_SOCK_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 226 15 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_NODEMASK_H #define __LINUX_NODEMASK_H /* * Nodemasks provide a bitmap suitable for representing the * set of Node's in a system, one bit position per Node number. * * See detailed comments in the file linux/bitmap.h describing the * data type on which these nodemasks are based. * * For details of nodemask_parse_user(), see bitmap_parse_user() in * lib/bitmap.c. For details of nodelist_parse(), see bitmap_parselist(), * also in bitmap.c. For details of node_remap(), see bitmap_bitremap in * lib/bitmap.c. For details of nodes_remap(), see bitmap_remap in * lib/bitmap.c. For details of nodes_onto(), see bitmap_onto in * lib/bitmap.c. For details of nodes_fold(), see bitmap_fold in * lib/bitmap.c. * * The available nodemask operations are: * * void node_set(node, mask) turn on bit 'node' in mask * void node_clear(node, mask) turn off bit 'node' in mask * void nodes_setall(mask) set all bits * void nodes_clear(mask) clear all bits * int node_isset(node, mask) true iff bit 'node' set in mask * int node_test_and_set(node, mask) test and set bit 'node' in mask * * void nodes_and(dst, src1, src2) dst = src1 & src2 [intersection] * void nodes_or(dst, src1, src2) dst = src1 | src2 [union] * void nodes_xor(dst, src1, src2) dst = src1 ^ src2 * void nodes_andnot(dst, src1, src2) dst = src1 & ~src2 * void nodes_complement(dst, src) dst = ~src * * int nodes_equal(mask1, mask2) Does mask1 == mask2? * int nodes_intersects(mask1, mask2) Do mask1 and mask2 intersect? * int nodes_subset(mask1, mask2) Is mask1 a subset of mask2? * int nodes_empty(mask) Is mask empty (no bits sets)? * int nodes_full(mask) Is mask full (all bits sets)? * int nodes_weight(mask) Hamming weight - number of set bits * * void nodes_shift_right(dst, src, n) Shift right * void nodes_shift_left(dst, src, n) Shift left * * unsigned int first_node(mask) Number lowest set bit, or MAX_NUMNODES * unsigend int next_node(node, mask) Next node past 'node', or MAX_NUMNODES * unsigned int next_node_in(node, mask) Next node past 'node', or wrap to first, * or MAX_NUMNODES * unsigned int first_unset_node(mask) First node not set in mask, or * MAX_NUMNODES * * nodemask_t nodemask_of_node(node) Return nodemask with bit 'node' set * NODE_MASK_ALL Initializer - all bits set * NODE_MASK_NONE Initializer - no bits set * unsigned long *nodes_addr(mask) Array of unsigned long's in mask * * int nodemask_parse_user(ubuf, ulen, mask) Parse ascii string as nodemask * int nodelist_parse(buf, map) Parse ascii string as nodelist * int node_remap(oldbit, old, new) newbit = map(old, new)(oldbit) * void nodes_remap(dst, src, old, new) *dst = map(old, new)(src) * void nodes_onto(dst, orig, relmap) *dst = orig relative to relmap * void nodes_fold(dst, orig, sz) dst bits = orig bits mod sz * * for_each_node_mask(node, mask) for-loop node over mask * * int num_online_nodes() Number of online Nodes * int num_possible_nodes() Number of all possible Nodes * * int node_random(mask) Random node with set bit in mask * * int node_online(node) Is some node online? * int node_possible(node) Is some node possible? * * node_set_online(node) set bit 'node' in node_online_map * node_set_offline(node) clear bit 'node' in node_online_map * * for_each_node(node) for-loop node over node_possible_map * for_each_online_node(node) for-loop node over node_online_map * * Subtlety: * 1) The 'type-checked' form of node_isset() causes gcc (3.3.2, anyway) * to generate slightly worse code. So use a simple one-line #define * for node_isset(), instead of wrapping an inline inside a macro, the * way we do the other calls. * * NODEMASK_SCRATCH * When doing above logical AND, OR, XOR, Remap operations the callers tend to * need temporary nodemask_t's on the stack. But if NODES_SHIFT is large, * nodemask_t's consume too much stack space. NODEMASK_SCRATCH is a helper * for such situations. See below and CPUMASK_ALLOC also. */ #include <linux/threads.h> #include <linux/bitmap.h> #include <linux/minmax.h> #include <linux/nodemask_types.h> #include <linux/numa.h> #include <linux/random.h> extern nodemask_t _unused_nodemask_arg_; /** * nodemask_pr_args - printf args to output a nodemask * @maskp: nodemask to be printed * * Can be used to provide arguments for '%*pb[l]' when printing a nodemask. */ #define nodemask_pr_args(maskp) __nodemask_pr_numnodes(maskp), \ __nodemask_pr_bits(maskp) static inline unsigned int __nodemask_pr_numnodes(const nodemask_t *m) { return m ? MAX_NUMNODES : 0; } static inline const unsigned long *__nodemask_pr_bits(const nodemask_t *m) { return m ? m->bits : NULL; } /* * The inline keyword gives the compiler room to decide to inline, or * not inline a function as it sees best. However, as these functions * are called in both __init and non-__init functions, if they are not * inlined we will end up with a section mismatch error (of the type of * freeable items not being freed). So we must use __always_inline here * to fix the problem. If other functions in the future also end up in * this situation they will also need to be annotated as __always_inline */ #define node_set(node, dst) __node_set((node), &(dst)) static __always_inline void __node_set(int node, volatile nodemask_t *dstp) { set_bit(node, dstp->bits); } #define node_clear(node, dst) __node_clear((node), &(dst)) static inline void __node_clear(int node, volatile nodemask_t *dstp) { clear_bit(node, dstp->bits); } #define nodes_setall(dst) __nodes_setall(&(dst), MAX_NUMNODES) static inline void __nodes_setall(nodemask_t *dstp, unsigned int nbits) { bitmap_fill(dstp->bits, nbits); } #define nodes_clear(dst) __nodes_clear(&(dst), MAX_NUMNODES) static inline void __nodes_clear(nodemask_t *dstp, unsigned int nbits) { bitmap_zero(dstp->bits, nbits); } /* No static inline type checking - see Subtlety (1) above. */ #define node_isset(node, nodemask) test_bit((node), (nodemask).bits) #define node_test_and_set(node, nodemask) \ __node_test_and_set((node), &(nodemask)) static inline bool __node_test_and_set(int node, nodemask_t *addr) { return test_and_set_bit(node, addr->bits); } #define nodes_and(dst, src1, src2) \ __nodes_and(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_and(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_and(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_or(dst, src1, src2) \ __nodes_or(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_or(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_or(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_xor(dst, src1, src2) \ __nodes_xor(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_xor(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_xor(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_andnot(dst, src1, src2) \ __nodes_andnot(&(dst), &(src1), &(src2), MAX_NUMNODES) static inline void __nodes_andnot(nodemask_t *dstp, const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { bitmap_andnot(dstp->bits, src1p->bits, src2p->bits, nbits); } #define nodes_complement(dst, src) \ __nodes_complement(&(dst), &(src), MAX_NUMNODES) static inline void __nodes_complement(nodemask_t *dstp, const nodemask_t *srcp, unsigned int nbits) { bitmap_complement(dstp->bits, srcp->bits, nbits); } #define nodes_equal(src1, src2) \ __nodes_equal(&(src1), &(src2), MAX_NUMNODES) static inline bool __nodes_equal(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_equal(src1p->bits, src2p->bits, nbits); } #define nodes_intersects(src1, src2) \ __nodes_intersects(&(src1), &(src2), MAX_NUMNODES) static inline bool __nodes_intersects(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_intersects(src1p->bits, src2p->bits, nbits); } #define nodes_subset(src1, src2) \ __nodes_subset(&(src1), &(src2), MAX_NUMNODES) static inline bool __nodes_subset(const nodemask_t *src1p, const nodemask_t *src2p, unsigned int nbits) { return bitmap_subset(src1p->bits, src2p->bits, nbits); } #define nodes_empty(src) __nodes_empty(&(src), MAX_NUMNODES) static inline bool __nodes_empty(const nodemask_t *srcp, unsigned int nbits) { return bitmap_empty(srcp->bits, nbits); } #define nodes_full(nodemask) __nodes_full(&(nodemask), MAX_NUMNODES) static inline bool __nodes_full(const nodemask_t *srcp, unsigned int nbits) { return bitmap_full(srcp->bits, nbits); } #define nodes_weight(nodemask) __nodes_weight(&(nodemask), MAX_NUMNODES) static inline int __nodes_weight(const nodemask_t *srcp, unsigned int nbits) { return bitmap_weight(srcp->bits, nbits); } #define nodes_shift_right(dst, src, n) \ __nodes_shift_right(&(dst), &(src), (n), MAX_NUMNODES) static inline void __nodes_shift_right(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_right(dstp->bits, srcp->bits, n, nbits); } #define nodes_shift_left(dst, src, n) \ __nodes_shift_left(&(dst), &(src), (n), MAX_NUMNODES) static inline void __nodes_shift_left(nodemask_t *dstp, const nodemask_t *srcp, int n, int nbits) { bitmap_shift_left(dstp->bits, srcp->bits, n, nbits); } /* FIXME: better would be to fix all architectures to never return > MAX_NUMNODES, then the silly min_ts could be dropped. */ #define first_node(src) __first_node(&(src)) static inline unsigned int __first_node(const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_first_bit(srcp->bits, MAX_NUMNODES)); } #define next_node(n, src) __next_node((n), &(src)) static inline unsigned int __next_node(int n, const nodemask_t *srcp) { return min_t(unsigned int, MAX_NUMNODES, find_next_bit(srcp->bits, MAX_NUMNODES, n+1)); } /* * Find the next present node in src, starting after node n, wrapping around to * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) { unsigned int ret = __next_node(node, srcp); if (ret == MAX_NUMNODES) ret = __first_node(srcp); return ret; } static inline void init_nodemask_of_node(nodemask_t *mask, int node) { nodes_clear(*mask); node_set(node, *mask); } #define nodemask_of_node(node) \ ({ \ typeof(_unused_nodemask_arg_) m; \ if (sizeof(m) == sizeof(unsigned long)) { \ m.bits[0] = 1UL << (node); \ } else { \ init_nodemask_of_node(&m, (node)); \ } \ m; \ }) #define first_unset_node(mask) __first_unset_node(&(mask)) static inline unsigned int __first_unset_node(const nodemask_t *maskp) { return min_t(unsigned int, MAX_NUMNODES, find_first_zero_bit(maskp->bits, MAX_NUMNODES)); } #define NODE_MASK_LAST_WORD BITMAP_LAST_WORD_MASK(MAX_NUMNODES) #if MAX_NUMNODES <= BITS_PER_LONG #define NODE_MASK_ALL \ ((nodemask_t) { { \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #else #define NODE_MASK_ALL \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-2] = ~0UL, \ [BITS_TO_LONGS(MAX_NUMNODES)-1] = NODE_MASK_LAST_WORD \ } }) #endif #define NODE_MASK_NONE \ ((nodemask_t) { { \ [0 ... BITS_TO_LONGS(MAX_NUMNODES)-1] = 0UL \ } }) #define nodes_addr(src) ((src).bits) #define nodemask_parse_user(ubuf, ulen, dst) \ __nodemask_parse_user((ubuf), (ulen), &(dst), MAX_NUMNODES) static inline int __nodemask_parse_user(const char __user *buf, int len, nodemask_t *dstp, int nbits) { return bitmap_parse_user(buf, len, dstp->bits, nbits); } #define nodelist_parse(buf, dst) __nodelist_parse((buf), &(dst), MAX_NUMNODES) static inline int __nodelist_parse(const char *buf, nodemask_t *dstp, int nbits) { return bitmap_parselist(buf, dstp->bits, nbits); } #define node_remap(oldbit, old, new) \ __node_remap((oldbit), &(old), &(new), MAX_NUMNODES) static inline int __node_remap(int oldbit, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { return bitmap_bitremap(oldbit, oldp->bits, newp->bits, nbits); } #define nodes_remap(dst, src, old, new) \ __nodes_remap(&(dst), &(src), &(old), &(new), MAX_NUMNODES) static inline void __nodes_remap(nodemask_t *dstp, const nodemask_t *srcp, const nodemask_t *oldp, const nodemask_t *newp, int nbits) { bitmap_remap(dstp->bits, srcp->bits, oldp->bits, newp->bits, nbits); } #define nodes_onto(dst, orig, relmap) \ __nodes_onto(&(dst), &(orig), &(relmap), MAX_NUMNODES) static inline void __nodes_onto(nodemask_t *dstp, const nodemask_t *origp, const nodemask_t *relmapp, int nbits) { bitmap_onto(dstp->bits, origp->bits, relmapp->bits, nbits); } #define nodes_fold(dst, orig, sz) \ __nodes_fold(&(dst), &(orig), sz, MAX_NUMNODES) static inline void __nodes_fold(nodemask_t *dstp, const nodemask_t *origp, int sz, int nbits) { bitmap_fold(dstp->bits, origp->bits, sz, nbits); } #if MAX_NUMNODES > 1 #define for_each_node_mask(node, mask) \ for ((node) = first_node(mask); \ (node) < MAX_NUMNODES; \ (node) = next_node((node), (mask))) #else /* MAX_NUMNODES == 1 */ #define for_each_node_mask(node, mask) \ for ((node) = 0; (node) < 1 && !nodes_empty(mask); (node)++) #endif /* MAX_NUMNODES */ /* * Bitmasks that are kept for all the nodes. */ enum node_states { N_POSSIBLE, /* The node could become online at some point */ N_ONLINE, /* The node is online */ N_NORMAL_MEMORY, /* The node has regular memory */ #ifdef CONFIG_HIGHMEM N_HIGH_MEMORY, /* The node has regular or high memory */ #else N_HIGH_MEMORY = N_NORMAL_MEMORY, #endif N_MEMORY, /* The node has memory(regular, high, movable) */ N_CPU, /* The node has one or more cpus */ N_GENERIC_INITIATOR, /* The node has one or more Generic Initiators */ NR_NODE_STATES }; /* * The following particular system nodemasks and operations * on them manage all possible and online nodes. */ extern nodemask_t node_states[NR_NODE_STATES]; #if MAX_NUMNODES > 1 static inline int node_state(int node, enum node_states state) { return node_isset(node, node_states[state]); } static inline void node_set_state(int node, enum node_states state) { __node_set(node, &node_states[state]); } static inline void node_clear_state(int node, enum node_states state) { __node_clear(node, &node_states[state]); } static inline int num_node_state(enum node_states state) { return nodes_weight(node_states[state]); } #define for_each_node_state(__node, __state) \ for_each_node_mask((__node), node_states[__state]) #define first_online_node first_node(node_states[N_ONLINE]) #define first_memory_node first_node(node_states[N_MEMORY]) static inline unsigned int next_online_node(int nid) { return next_node(nid, node_states[N_ONLINE]); } static inline unsigned int next_memory_node(int nid) { return next_node(nid, node_states[N_MEMORY]); } extern unsigned int nr_node_ids; extern unsigned int nr_online_nodes; static inline void node_set_online(int nid) { node_set_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } static inline void node_set_offline(int nid) { node_clear_state(nid, N_ONLINE); nr_online_nodes = num_node_state(N_ONLINE); } #else static inline int node_state(int node, enum node_states state) { return node == 0; } static inline void node_set_state(int node, enum node_states state) { } static inline void node_clear_state(int node, enum node_states state) { } static inline int num_node_state(enum node_states state) { return 1; } #define for_each_node_state(node, __state) \ for ( (node) = 0; (node) == 0; (node) = 1) #define first_online_node 0 #define first_memory_node 0 #define next_online_node(nid) (MAX_NUMNODES) #define next_memory_node(nid) (MAX_NUMNODES) #define nr_node_ids 1U #define nr_online_nodes 1U #define node_set_online(node) node_set_state((node), N_ONLINE) #define node_set_offline(node) node_clear_state((node), N_ONLINE) #endif static inline int node_random(const nodemask_t *maskp) { #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) int w, bit; w = nodes_weight(*maskp); switch (w) { case 0: bit = NUMA_NO_NODE; break; case 1: bit = first_node(*maskp); break; default: bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_u32_below(w)); break; } return bit; #else return 0; #endif } #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] #define num_online_nodes() num_node_state(N_ONLINE) #define num_possible_nodes() num_node_state(N_POSSIBLE) #define node_online(node) node_state((node), N_ONLINE) #define node_possible(node) node_state((node), N_POSSIBLE) #define for_each_node(node) for_each_node_state(node, N_POSSIBLE) #define for_each_online_node(node) for_each_node_state(node, N_ONLINE) /* * For nodemask scratch area. * NODEMASK_ALLOC(type, name) allocates an object with a specified type and * name. */ #if NODES_SHIFT > 8 /* nodemask_t > 32 bytes */ #define NODEMASK_ALLOC(type, name, gfp_flags) \ type *name = kmalloc(sizeof(*name), gfp_flags) #define NODEMASK_FREE(m) kfree(m) #else #define NODEMASK_ALLOC(type, name, gfp_flags) type _##name, *name = &_##name #define NODEMASK_FREE(m) do {} while (0) #endif /* Example structure for using NODEMASK_ALLOC, used in mempolicy. */ struct nodemask_scratch { nodemask_t mask1; nodemask_t mask2; }; #define NODEMASK_SCRATCH(x) \ NODEMASK_ALLOC(struct nodemask_scratch, x, \ GFP_KERNEL | __GFP_NORETRY) #define NODEMASK_SCRATCH_FREE(x) NODEMASK_FREE(x) #endif /* __LINUX_NODEMASK_H */ |
| 148 145 230 230 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Filesystem access notification for Linux * * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ #ifndef __LINUX_FSNOTIFY_BACKEND_H #define __LINUX_FSNOTIFY_BACKEND_H #ifdef __KERNEL__ #include <linux/idr.h> /* inotify uses this */ #include <linux/fs.h> /* struct inode */ #include <linux/list.h> #include <linux/path.h> /* struct path */ #include <linux/spinlock.h> #include <linux/types.h> #include <linux/atomic.h> #include <linux/user_namespace.h> #include <linux/refcount.h> #include <linux/mempool.h> #include <linux/sched/mm.h> /* * IN_* from inotfy.h lines up EXACTLY with FS_*, this is so we can easily * convert between them. dnotify only needs conversion at watch creation * so no perf loss there. fanotify isn't defined yet, so it can use the * wholes if it needs more events. */ #define FS_ACCESS 0x00000001 /* File was accessed */ #define FS_MODIFY 0x00000002 /* File was modified */ #define FS_ATTRIB 0x00000004 /* Metadata changed */ #define FS_CLOSE_WRITE 0x00000008 /* Writable file was closed */ #define FS_CLOSE_NOWRITE 0x00000010 /* Unwritable file closed */ #define FS_OPEN 0x00000020 /* File was opened */ #define FS_MOVED_FROM 0x00000040 /* File was moved from X */ #define FS_MOVED_TO 0x00000080 /* File was moved to Y */ #define FS_CREATE 0x00000100 /* Subfile was created */ #define FS_DELETE 0x00000200 /* Subfile was deleted */ #define FS_DELETE_SELF 0x00000400 /* Self was deleted */ #define FS_MOVE_SELF 0x00000800 /* Self was moved */ #define FS_OPEN_EXEC 0x00001000 /* File was opened for exec */ #define FS_UNMOUNT 0x00002000 /* inode on umount fs */ #define FS_Q_OVERFLOW 0x00004000 /* Event queued overflowed */ #define FS_ERROR 0x00008000 /* Filesystem Error (fanotify) */ /* * FS_IN_IGNORED overloads FS_ERROR. It is only used internally by inotify * which does not support FS_ERROR. */ #define FS_IN_IGNORED 0x00008000 /* last inotify event here */ #define FS_OPEN_PERM 0x00010000 /* open event in an permission hook */ #define FS_ACCESS_PERM 0x00020000 /* access event in a permissions hook */ #define FS_OPEN_EXEC_PERM 0x00040000 /* open/exec event in a permission hook */ /* * Set on inode mark that cares about things that happen to its children. * Always set for dnotify and inotify. * Set on inode/sb/mount marks that care about parent/name info. */ #define FS_EVENT_ON_CHILD 0x08000000 #define FS_RENAME 0x10000000 /* File was renamed */ #define FS_DN_MULTISHOT 0x20000000 /* dnotify multishot */ #define FS_ISDIR 0x40000000 /* event occurred against dir */ #define FS_MOVE (FS_MOVED_FROM | FS_MOVED_TO) /* * Directory entry modification events - reported only to directory * where entry is modified and not to a watching parent. * The watching parent may get an FS_ATTRIB|FS_EVENT_ON_CHILD event * when a directory entry inside a child subdir changes. */ #define ALL_FSNOTIFY_DIRENT_EVENTS (FS_CREATE | FS_DELETE | FS_MOVE | FS_RENAME) #define ALL_FSNOTIFY_PERM_EVENTS (FS_OPEN_PERM | FS_ACCESS_PERM | \ FS_OPEN_EXEC_PERM) /* * This is a list of all events that may get sent to a parent that is watching * with flag FS_EVENT_ON_CHILD based on fs event on a child of that directory. */ #define FS_EVENTS_POSS_ON_CHILD (ALL_FSNOTIFY_PERM_EVENTS | \ FS_ACCESS | FS_MODIFY | FS_ATTRIB | \ FS_CLOSE_WRITE | FS_CLOSE_NOWRITE | \ FS_OPEN | FS_OPEN_EXEC) /* * This is a list of all events that may get sent with the parent inode as the * @to_tell argument of fsnotify(). * It may include events that can be sent to an inode/sb/mount mark, but cannot * be sent to a parent watching children. */ #define FS_EVENTS_POSS_TO_PARENT (FS_EVENTS_POSS_ON_CHILD) /* Events that can be reported to backends */ #define ALL_FSNOTIFY_EVENTS (ALL_FSNOTIFY_DIRENT_EVENTS | \ FS_EVENTS_POSS_ON_CHILD | \ FS_DELETE_SELF | FS_MOVE_SELF | \ FS_UNMOUNT | FS_Q_OVERFLOW | FS_IN_IGNORED | \ FS_ERROR) /* Extra flags that may be reported with event or control handling of events */ #define ALL_FSNOTIFY_FLAGS (FS_ISDIR | FS_EVENT_ON_CHILD | FS_DN_MULTISHOT) #define ALL_FSNOTIFY_BITS (ALL_FSNOTIFY_EVENTS | ALL_FSNOTIFY_FLAGS) struct fsnotify_group; struct fsnotify_event; struct fsnotify_mark; struct fsnotify_event_private_data; struct fsnotify_fname; struct fsnotify_iter_info; struct mem_cgroup; /* * Each group much define these ops. The fsnotify infrastructure will call * these operations for each relevant group. * * handle_event - main call for a group to handle an fs event * @group: group to notify * @mask: event type and flags * @data: object that event happened on * @data_type: type of object for fanotify_data_XXX() accessors * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to * @file_name: optional file name associated with event * @cookie: inotify rename cookie * @iter_info: array of marks from this group that are interested in the event * * handle_inode_event - simple variant of handle_event() for groups that only * have inode marks and don't have ignore mask * @mark: mark to notify * @mask: event type and flags * @inode: inode that event happened on * @dir: optional directory associated with event - * if @file_name is not NULL, this is the directory that * @file_name is relative to. * Either @inode or @dir must be non-NULL. * @file_name: optional file name associated with event * @cookie: inotify rename cookie * * free_group_priv - called when a group refcnt hits 0 to clean up the private union * freeing_mark - called when a mark is being destroyed for some reason. The group * MUST be holding a reference on each mark and that reference must be * dropped in this function. inotify uses this function to send * userspace messages that marks have been removed. */ struct fsnotify_ops { int (*handle_event)(struct fsnotify_group *group, u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *file_name, u32 cookie, struct fsnotify_iter_info *iter_info); int (*handle_inode_event)(struct fsnotify_mark *mark, u32 mask, struct inode *inode, struct inode *dir, const struct qstr *file_name, u32 cookie); void (*free_group_priv)(struct fsnotify_group *group); void (*freeing_mark)(struct fsnotify_mark *mark, struct fsnotify_group *group); void (*free_event)(struct fsnotify_group *group, struct fsnotify_event *event); /* called on final put+free to free memory */ void (*free_mark)(struct fsnotify_mark *mark); }; /* * all of the information about the original object we want to now send to * a group. If you want to carry more info from the accessing task to the * listener this structure is where you need to be adding fields. */ struct fsnotify_event { struct list_head list; }; /* * fsnotify group priorities. * Events are sent in order from highest priority to lowest priority. */ enum fsnotify_group_prio { FSNOTIFY_PRIO_NORMAL = 0, /* normal notifiers, no permissions */ FSNOTIFY_PRIO_CONTENT, /* fanotify permission events */ FSNOTIFY_PRIO_PRE_CONTENT, /* fanotify pre-content events */ __FSNOTIFY_PRIO_NUM }; /* * A group is a "thing" that wants to receive notification about filesystem * events. The mask holds the subset of event types this group cares about. * refcnt on a group is up to the implementor and at any moment if it goes 0 * everything will be cleaned up. */ struct fsnotify_group { const struct fsnotify_ops *ops; /* how this group handles things */ /* * How the refcnt is used is up to each group. When the refcnt hits 0 * fsnotify will clean up all of the resources associated with this group. * As an example, the dnotify group will always have a refcnt=1 and that * will never change. Inotify, on the other hand, has a group per * inotify_init() and the refcnt will hit 0 only when that fd has been * closed. */ refcount_t refcnt; /* things with interest in this group */ /* needed to send notification to userspace */ spinlock_t notification_lock; /* protect the notification_list */ struct list_head notification_list; /* list of event_holder this group needs to send to userspace */ wait_queue_head_t notification_waitq; /* read() on the notification file blocks on this waitq */ unsigned int q_len; /* events on the queue */ unsigned int max_events; /* maximum events allowed on the list */ enum fsnotify_group_prio priority; /* priority for sending events */ bool shutdown; /* group is being shut down, don't queue more events */ #define FSNOTIFY_GROUP_USER 0x01 /* user allocated group */ #define FSNOTIFY_GROUP_DUPS 0x02 /* allow multiple marks per object */ #define FSNOTIFY_GROUP_NOFS 0x04 /* group lock is not direct reclaim safe */ int flags; unsigned int owner_flags; /* stored flags of mark_mutex owner */ /* stores all fastpath marks assoc with this group so they can be cleaned on unregister */ struct mutex mark_mutex; /* protect marks_list */ atomic_t user_waits; /* Number of tasks waiting for user * response */ struct list_head marks_list; /* all inode marks for this group */ struct fasync_struct *fsn_fa; /* async notification */ struct fsnotify_event *overflow_event; /* Event we queue when the * notification list is too * full */ struct mem_cgroup *memcg; /* memcg to charge allocations */ /* groups can define private fields here or use the void *private */ union { void *private; #ifdef CONFIG_INOTIFY_USER struct inotify_group_private_data { spinlock_t idr_lock; struct idr idr; struct ucounts *ucounts; } inotify_data; #endif #ifdef CONFIG_FANOTIFY struct fanotify_group_private_data { /* Hash table of events for merge */ struct hlist_head *merge_hash; /* allows a group to block waiting for a userspace response */ struct list_head access_list; wait_queue_head_t access_waitq; int flags; /* flags from fanotify_init() */ int f_flags; /* event_f_flags from fanotify_init() */ struct ucounts *ucounts; mempool_t error_events_pool; } fanotify_data; #endif /* CONFIG_FANOTIFY */ }; }; /* * These helpers are used to prevent deadlock when reclaiming inodes with * evictable marks of the same group that is allocating a new mark. */ static inline void fsnotify_group_lock(struct fsnotify_group *group) { mutex_lock(&group->mark_mutex); if (group->flags & FSNOTIFY_GROUP_NOFS) group->owner_flags = memalloc_nofs_save(); } static inline void fsnotify_group_unlock(struct fsnotify_group *group) { if (group->flags & FSNOTIFY_GROUP_NOFS) memalloc_nofs_restore(group->owner_flags); mutex_unlock(&group->mark_mutex); } static inline void fsnotify_group_assert_locked(struct fsnotify_group *group) { WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex)); if (group->flags & FSNOTIFY_GROUP_NOFS) WARN_ON_ONCE(!(current->flags & PF_MEMALLOC_NOFS)); } /* When calling fsnotify tell it if the data is a path or inode */ enum fsnotify_data_type { FSNOTIFY_EVENT_NONE, FSNOTIFY_EVENT_PATH, FSNOTIFY_EVENT_INODE, FSNOTIFY_EVENT_DENTRY, FSNOTIFY_EVENT_ERROR, }; struct fs_error_report { int error; struct inode *inode; struct super_block *sb; }; static inline struct inode *fsnotify_data_inode(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return (struct inode *)data; case FSNOTIFY_EVENT_DENTRY: return d_inode(data); case FSNOTIFY_EVENT_PATH: return d_inode(((const struct path *)data)->dentry); case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *)data)->inode; default: return NULL; } } static inline struct dentry *fsnotify_data_dentry(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_DENTRY: /* Non const is needed for dget() */ return (struct dentry *)data; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry; default: return NULL; } } static inline const struct path *fsnotify_data_path(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_PATH: return data; default: return NULL; } } static inline struct super_block *fsnotify_data_sb(const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_INODE: return ((struct inode *)data)->i_sb; case FSNOTIFY_EVENT_DENTRY: return ((struct dentry *)data)->d_sb; case FSNOTIFY_EVENT_PATH: return ((const struct path *)data)->dentry->d_sb; case FSNOTIFY_EVENT_ERROR: return ((struct fs_error_report *) data)->sb; default: return NULL; } } static inline struct fs_error_report *fsnotify_data_error_report( const void *data, int data_type) { switch (data_type) { case FSNOTIFY_EVENT_ERROR: return (struct fs_error_report *) data; default: return NULL; } } /* * Index to merged marks iterator array that correlates to a type of watch. * The type of watched object can be deduced from the iterator type, but not * the other way around, because an event can match different watched objects * of the same object type. * For example, both parent and child are watching an object of type inode. */ enum fsnotify_iter_type { FSNOTIFY_ITER_TYPE_INODE, FSNOTIFY_ITER_TYPE_VFSMOUNT, FSNOTIFY_ITER_TYPE_SB, FSNOTIFY_ITER_TYPE_PARENT, FSNOTIFY_ITER_TYPE_INODE2, FSNOTIFY_ITER_TYPE_COUNT }; /* The type of object that a mark is attached to */ enum fsnotify_obj_type { FSNOTIFY_OBJ_TYPE_ANY = -1, FSNOTIFY_OBJ_TYPE_INODE, FSNOTIFY_OBJ_TYPE_VFSMOUNT, FSNOTIFY_OBJ_TYPE_SB, FSNOTIFY_OBJ_TYPE_COUNT, FSNOTIFY_OBJ_TYPE_DETACHED = FSNOTIFY_OBJ_TYPE_COUNT }; static inline bool fsnotify_valid_obj_type(unsigned int obj_type) { return (obj_type < FSNOTIFY_OBJ_TYPE_COUNT); } struct fsnotify_iter_info { struct fsnotify_mark *marks[FSNOTIFY_ITER_TYPE_COUNT]; struct fsnotify_group *current_group; unsigned int report_mask; int srcu_idx; }; static inline bool fsnotify_iter_should_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { return (iter_info->report_mask & (1U << iter_type)); } static inline void fsnotify_iter_set_report_type( struct fsnotify_iter_info *iter_info, int iter_type) { iter_info->report_mask |= (1U << iter_type); } static inline struct fsnotify_mark *fsnotify_iter_mark( struct fsnotify_iter_info *iter_info, int iter_type) { if (fsnotify_iter_should_report_type(iter_info, iter_type)) return iter_info->marks[iter_type]; return NULL; } static inline int fsnotify_iter_step(struct fsnotify_iter_info *iter, int type, struct fsnotify_mark **markp) { while (type < FSNOTIFY_ITER_TYPE_COUNT) { *markp = fsnotify_iter_mark(iter, type); if (*markp) break; type++; } return type; } #define FSNOTIFY_ITER_FUNCS(name, NAME) \ static inline struct fsnotify_mark *fsnotify_iter_##name##_mark( \ struct fsnotify_iter_info *iter_info) \ { \ return fsnotify_iter_mark(iter_info, FSNOTIFY_ITER_TYPE_##NAME); \ } FSNOTIFY_ITER_FUNCS(inode, INODE) FSNOTIFY_ITER_FUNCS(parent, PARENT) FSNOTIFY_ITER_FUNCS(vfsmount, VFSMOUNT) FSNOTIFY_ITER_FUNCS(sb, SB) #define fsnotify_foreach_iter_type(type) \ for (type = 0; type < FSNOTIFY_ITER_TYPE_COUNT; type++) #define fsnotify_foreach_iter_mark_type(iter, mark, type) \ for (type = 0; \ type = fsnotify_iter_step(iter, type, &mark), \ type < FSNOTIFY_ITER_TYPE_COUNT; \ type++) /* * Inode/vfsmount/sb point to this structure which tracks all marks attached to * the inode/vfsmount/sb. The reference to inode/vfsmount/sb is held by this * structure. We destroy this structure when there are no more marks attached * to it. The structure is protected by fsnotify_mark_srcu. */ struct fsnotify_mark_connector { spinlock_t lock; unsigned char type; /* Type of object [lock] */ unsigned char prio; /* Highest priority group */ #define FSNOTIFY_CONN_FLAG_IS_WATCHED 0x01 #define FSNOTIFY_CONN_FLAG_HAS_IREF 0x02 unsigned short flags; /* flags [lock] */ union { /* Object pointer [lock] */ void *obj; /* Used listing heads to free after srcu period expires */ struct fsnotify_mark_connector *destroy_next; }; struct hlist_head list; }; /* * Container for per-sb fsnotify state (sb marks and more). * Attached lazily on first marked object on the sb and freed when killing sb. */ struct fsnotify_sb_info { struct fsnotify_mark_connector __rcu *sb_marks; /* * Number of inode/mount/sb objects that are being watched in this sb. * Note that inodes objects are currently double-accounted. * * The value in watched_objects[prio] is the number of objects that are * watched by groups of priority >= prio, so watched_objects[0] is the * total number of watched objects in this sb. */ atomic_long_t watched_objects[__FSNOTIFY_PRIO_NUM]; }; static inline struct fsnotify_sb_info *fsnotify_sb_info(struct super_block *sb) { #ifdef CONFIG_FSNOTIFY return READ_ONCE(sb->s_fsnotify_info); #else return NULL; #endif } static inline atomic_long_t *fsnotify_sb_watched_objects(struct super_block *sb) { return &fsnotify_sb_info(sb)->watched_objects[0]; } /* * A mark is simply an object attached to an in core inode which allows an * fsnotify listener to indicate they are either no longer interested in events * of a type matching mask or only interested in those events. * * These are flushed when an inode is evicted from core and may be flushed * when the inode is modified (as seen by fsnotify_access). Some fsnotify * users (such as dnotify) will flush these when the open fd is closed and not * at inode eviction or modification. * * Text in brackets is showing the lock(s) protecting modifications of a * particular entry. obj_lock means either inode->i_lock or * mnt->mnt_root->d_lock depending on the mark type. */ struct fsnotify_mark { /* Mask this mark is for [mark->lock, group->mark_mutex] */ __u32 mask; /* We hold one for presence in g_list. Also one ref for each 'thing' * in kernel that found and may be using this mark. */ refcount_t refcnt; /* Group this mark is for. Set on mark creation, stable until last ref * is dropped */ struct fsnotify_group *group; /* List of marks by group->marks_list. Also reused for queueing * mark into destroy_list when it's waiting for the end of SRCU period * before it can be freed. [group->mark_mutex] */ struct list_head g_list; /* Protects inode / mnt pointers, flags, masks */ spinlock_t lock; /* List of marks for inode / vfsmount [connector->lock, mark ref] */ struct hlist_node obj_list; /* Head of list of marks for an object [mark ref] */ struct fsnotify_mark_connector *connector; /* Events types and flags to ignore [mark->lock, group->mark_mutex] */ __u32 ignore_mask; /* General fsnotify mark flags */ #define FSNOTIFY_MARK_FLAG_ALIVE 0x0001 #define FSNOTIFY_MARK_FLAG_ATTACHED 0x0002 /* inotify mark flags */ #define FSNOTIFY_MARK_FLAG_EXCL_UNLINK 0x0010 #define FSNOTIFY_MARK_FLAG_IN_ONESHOT 0x0020 /* fanotify mark flags */ #define FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY 0x0100 #define FSNOTIFY_MARK_FLAG_NO_IREF 0x0200 #define FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS 0x0400 #define FSNOTIFY_MARK_FLAG_HAS_FSID 0x0800 #define FSNOTIFY_MARK_FLAG_WEAK_FSID 0x1000 unsigned int flags; /* flags [mark->lock] */ }; #ifdef CONFIG_FSNOTIFY /* called from the vfs helpers */ /* main fsnotify call to send events */ extern int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie); extern int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type); extern void __fsnotify_inode_delete(struct inode *inode); extern void __fsnotify_vfsmount_delete(struct vfsmount *mnt); extern void fsnotify_sb_delete(struct super_block *sb); extern void fsnotify_sb_free(struct super_block *sb); extern u32 fsnotify_get_cookie(void); static inline __u32 fsnotify_parent_needed_mask(__u32 mask) { /* FS_EVENT_ON_CHILD is set on marks that want parent/name info */ if (!(mask & FS_EVENT_ON_CHILD)) return 0; /* * This object might be watched by a mark that cares about parent/name * info, does it care about the specific set of events that can be * reported with parent/name info? */ return mask & FS_EVENTS_POSS_TO_PARENT; } static inline int fsnotify_inode_watches_children(struct inode *inode) { /* FS_EVENT_ON_CHILD is set if the inode may care */ if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD)) return 0; /* this inode might care about child events, does it care about the * specific set of events that can happen on a child? */ return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD; } /* * Update the dentry with a flag indicating the interest of its parent to receive * filesystem events when those events happens to this dentry->d_inode. */ static inline void fsnotify_update_flags(struct dentry *dentry) { assert_spin_locked(&dentry->d_lock); /* * Serialisation of setting PARENT_WATCHED on the dentries is provided * by d_lock. If inotify_inode_watched changes after we have taken * d_lock, the following __fsnotify_update_child_dentry_flags call will * find our entry, so it will spin until we complete here, and update * us with the new state. */ if (fsnotify_inode_watches_children(dentry->d_parent->d_inode)) dentry->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED; else dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED; } /* called from fsnotify listeners, such as fanotify or dnotify */ /* create a new group */ extern struct fsnotify_group *fsnotify_alloc_group( const struct fsnotify_ops *ops, int flags); /* get reference to a group */ extern void fsnotify_get_group(struct fsnotify_group *group); /* drop reference on a group from fsnotify_alloc_group */ extern void fsnotify_put_group(struct fsnotify_group *group); /* group destruction begins, stop queuing new events */ extern void fsnotify_group_stop_queueing(struct fsnotify_group *group); /* destroy group */ extern void fsnotify_destroy_group(struct fsnotify_group *group); /* fasync handler function */ extern int fsnotify_fasync(int fd, struct file *file, int on); /* Free event from memory */ extern void fsnotify_destroy_event(struct fsnotify_group *group, struct fsnotify_event *event); /* attach the event to the group notification queue */ extern int fsnotify_insert_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *), void (*insert)(struct fsnotify_group *, struct fsnotify_event *)); static inline int fsnotify_add_event(struct fsnotify_group *group, struct fsnotify_event *event, int (*merge)(struct fsnotify_group *, struct fsnotify_event *)) { return fsnotify_insert_event(group, event, merge, NULL); } /* Queue overflow event to a notification group */ static inline void fsnotify_queue_overflow(struct fsnotify_group *group) { fsnotify_add_event(group, group->overflow_event, NULL); } static inline bool fsnotify_is_overflow_event(u32 mask) { return mask & FS_Q_OVERFLOW; } static inline bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group) { assert_spin_locked(&group->notification_lock); return list_empty(&group->notification_list); } extern bool fsnotify_notify_queue_is_empty(struct fsnotify_group *group); /* return, but do not dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_peek_first_event(struct fsnotify_group *group); /* return AND dequeue the first event on the notification queue */ extern struct fsnotify_event *fsnotify_remove_first_event(struct fsnotify_group *group); /* Remove event queued in the notification list */ extern void fsnotify_remove_queued_event(struct fsnotify_group *group, struct fsnotify_event *event); /* functions used to manipulate the marks attached to inodes */ /* * Canonical "ignore mask" including event flags. * * Note the subtle semantic difference from the legacy ->ignored_mask. * ->ignored_mask traditionally only meant which events should be ignored, * while ->ignore_mask also includes flags regarding the type of objects on * which events should be ignored. */ static inline __u32 fsnotify_ignore_mask(struct fsnotify_mark *mark) { __u32 ignore_mask = mark->ignore_mask; /* The event flags in ignore mask take effect */ if (mark->flags & FSNOTIFY_MARK_FLAG_HAS_IGNORE_FLAGS) return ignore_mask; /* * Legacy behavior: * - Always ignore events on dir * - Ignore events on child if parent is watching children */ ignore_mask |= FS_ISDIR; ignore_mask &= ~FS_EVENT_ON_CHILD; ignore_mask |= mark->mask & FS_EVENT_ON_CHILD; return ignore_mask; } /* Legacy ignored_mask - only event types to ignore */ static inline __u32 fsnotify_ignored_events(struct fsnotify_mark *mark) { return mark->ignore_mask & ALL_FSNOTIFY_EVENTS; } /* * Check if mask (or ignore mask) should be applied depending if victim is a * directory and whether it is reported to a watching parent. */ static inline bool fsnotify_mask_applicable(__u32 mask, bool is_dir, int iter_type) { /* Should mask be applied to a directory? */ if (is_dir && !(mask & FS_ISDIR)) return false; /* Should mask be applied to a child? */ if (iter_type == FSNOTIFY_ITER_TYPE_PARENT && !(mask & FS_EVENT_ON_CHILD)) return false; return true; } /* * Effective ignore mask taking into account if event victim is a * directory and whether it is reported to a watching parent. */ static inline __u32 fsnotify_effective_ignore_mask(struct fsnotify_mark *mark, bool is_dir, int iter_type) { __u32 ignore_mask = fsnotify_ignored_events(mark); if (!ignore_mask) return 0; /* For non-dir and non-child, no need to consult the event flags */ if (!is_dir && iter_type != FSNOTIFY_ITER_TYPE_PARENT) return ignore_mask; ignore_mask = fsnotify_ignore_mask(mark); if (!fsnotify_mask_applicable(ignore_mask, is_dir, iter_type)) return 0; return ignore_mask & ALL_FSNOTIFY_EVENTS; } /* Get mask for calculating object interest taking ignore mask into account */ static inline __u32 fsnotify_calc_mask(struct fsnotify_mark *mark) { __u32 mask = mark->mask; if (!fsnotify_ignored_events(mark)) return mask; /* Interest in FS_MODIFY may be needed for clearing ignore mask */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)) mask |= FS_MODIFY; /* * If mark is interested in ignoring events on children, the object must * show interest in those events for fsnotify_parent() to notice it. */ return mask | mark->ignore_mask; } /* Get mask of events for a list of marks */ extern __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn); /* Calculate mask of events for a list of marks */ extern void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn); extern void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* Find mark belonging to given group in the list of marks */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group); /* attach the mark to the object */ int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags); /* attach the mark to the inode */ static inline int fsnotify_add_inode_mark(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline int fsnotify_add_inode_mark_locked(struct fsnotify_mark *mark, struct inode *inode, int add_flags) { return fsnotify_add_mark_locked(mark, inode, FSNOTIFY_OBJ_TYPE_INODE, add_flags); } static inline struct fsnotify_mark *fsnotify_find_inode_mark( struct inode *inode, struct fsnotify_group *group) { return fsnotify_find_mark(inode, FSNOTIFY_OBJ_TYPE_INODE, group); } /* given a group and a mark, flag mark to be freed when all references are dropped */ extern void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group); /* detach mark from inode / mount list, group list, drop inode reference */ extern void fsnotify_detach_mark(struct fsnotify_mark *mark); /* free mark */ extern void fsnotify_free_mark(struct fsnotify_mark *mark); /* Wait until all marks queued for destruction are destroyed */ extern void fsnotify_wait_marks_destroyed(void); /* Clear all of the marks of a group attached to a given object type */ extern void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type); /* run all the marks in a group, and clear all of the vfsmount marks */ static inline void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_VFSMOUNT); } /* run all the marks in a group, and clear all of the inode marks */ static inline void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_INODE); } /* run all the marks in a group, and clear all of the sn marks */ static inline void fsnotify_clear_sb_marks_by_group(struct fsnotify_group *group) { fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_TYPE_SB); } extern void fsnotify_get_mark(struct fsnotify_mark *mark); extern void fsnotify_put_mark(struct fsnotify_mark *mark); extern void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info); extern bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info); static inline void fsnotify_init_event(struct fsnotify_event *event) { INIT_LIST_HEAD(&event->list); } #else static inline int fsnotify(__u32 mask, const void *data, int data_type, struct inode *dir, const struct qstr *name, struct inode *inode, u32 cookie) { return 0; } static inline int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data, int data_type) { return 0; } static inline void __fsnotify_inode_delete(struct inode *inode) {} static inline void __fsnotify_vfsmount_delete(struct vfsmount *mnt) {} static inline void fsnotify_sb_delete(struct super_block *sb) {} static inline void fsnotify_sb_free(struct super_block *sb) {} static inline void fsnotify_update_flags(struct dentry *dentry) {} static inline u32 fsnotify_get_cookie(void) { return 0; } static inline void fsnotify_unmount_inodes(struct super_block *sb) {} #endif /* CONFIG_FSNOTIFY */ #endif /* __KERNEL __ */ #endif /* __LINUX_FSNOTIFY_BACKEND_H */ |
| 20 20 16 16 16 11 11 11 11 11 11 11 11 9 9 2 9 9 9 7 7 7 7 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 | // SPDX-License-Identifier: GPL-2.0-only /* * arch/arm64/mm/hugetlbpage.c * * Copyright (C) 2013 Linaro Ltd. * * Based on arch/x86/mm/hugetlbpage.c. */ #include <linux/init.h> #include <linux/fs.h> #include <linux/mm.h> #include <linux/hugetlb.h> #include <linux/pagemap.h> #include <linux/err.h> #include <linux/sysctl.h> #include <asm/mman.h> #include <asm/tlb.h> #include <asm/tlbflush.h> /* * HugeTLB Support Matrix * * --------------------------------------------------- * | Page Size | CONT PTE | PMD | CONT PMD | PUD | * --------------------------------------------------- * | 4K | 64K | 2M | 32M | 1G | * | 16K | 2M | 32M | 1G | | * | 64K | 2M | 512M | 16G | | * --------------------------------------------------- */ /* * Reserve CMA areas for the largest supported gigantic * huge page when requested. Any other smaller gigantic * huge pages could still be served from those areas. */ #ifdef CONFIG_CMA void __init arm64_hugetlb_cma_reserve(void) { int order; if (pud_sect_supported()) order = PUD_SHIFT - PAGE_SHIFT; else order = CONT_PMD_SHIFT - PAGE_SHIFT; hugetlb_cma_reserve(order); } #endif /* CONFIG_CMA */ static bool __hugetlb_valid_size(unsigned long size) { switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return pud_sect_supported(); #endif case CONT_PMD_SIZE: case PMD_SIZE: case CONT_PTE_SIZE: return true; } return false; } #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION bool arch_hugetlb_migration_supported(struct hstate *h) { size_t pagesize = huge_page_size(h); if (!__hugetlb_valid_size(pagesize)) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); return false; } return true; } #endif static int find_num_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, size_t *pgsize) { pgd_t *pgdp = pgd_offset(mm, addr); p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; *pgsize = PAGE_SIZE; p4dp = p4d_offset(pgdp, addr); pudp = pud_offset(p4dp, addr); pmdp = pmd_offset(pudp, addr); if ((pte_t *)pmdp == ptep) { *pgsize = PMD_SIZE; return CONT_PMDS; } return CONT_PTES; } static inline int num_contig_ptes(unsigned long size, size_t *pgsize) { int contig_ptes = 0; *pgsize = size; switch (size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: if (pud_sect_supported()) contig_ptes = 1; break; #endif case PMD_SIZE: contig_ptes = 1; break; case CONT_PMD_SIZE: *pgsize = PMD_SIZE; contig_ptes = CONT_PMDS; break; case CONT_PTE_SIZE: *pgsize = PAGE_SIZE; contig_ptes = CONT_PTES; break; } return contig_ptes; } pte_t huge_ptep_get(pte_t *ptep) { int ncontig, i; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_present(orig_pte) || !pte_cont(orig_pte)) return orig_pte; ncontig = num_contig_ptes(page_size(pte_page(orig_pte)), &pgsize); for (i = 0; i < ncontig; i++, ptep++) { pte_t pte = __ptep_get(ptep); if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step. */ static pte_t get_clear_contig(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = __ptep_get(ptep); unsigned long i; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) { pte_t pte = __ptep_get_and_clear(mm, addr, ptep); /* * If HW_AFDBM is enabled, then the HW could turn on * the dirty or accessed bit for any page in the set, * so check them all. */ if (pte_dirty(pte)) orig_pte = pte_mkdirty(orig_pte); if (pte_young(pte)) orig_pte = pte_mkyoung(orig_pte); } return orig_pte; } static pte_t get_clear_contig_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { pte_t orig_pte = get_clear_contig(mm, addr, ptep, pgsize, ncontig); struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); flush_tlb_range(&vma, addr, addr + (pgsize * ncontig)); return orig_pte; } /* * Changing some bits of contiguous entries requires us to follow a * Break-Before-Make approach, breaking the whole contiguous set * before we can change any entries. See ARM DDI 0487A.k_iss10775, * "Misprogramming of the Contiguous bit", page D4-1762. * * This helper performs the break step for use cases where the * original pte is not needed. */ static void clear_flush(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long pgsize, unsigned long ncontig) { struct vm_area_struct vma = TLB_FLUSH_VMA(mm, 0); unsigned long i, saddr = addr; for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __ptep_get_and_clear(mm, addr, ptep); flush_tlb_range(&vma, saddr, addr); } void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { size_t pgsize; int i; int ncontig; unsigned long pfn, dpfn; pgprot_t hugeprot; ncontig = num_contig_ptes(sz, &pgsize); if (!pte_present(pte)) { for (i = 0; i < ncontig; i++, ptep++, addr += pgsize) __set_ptes(mm, addr, ptep, pte, 1); return; } if (!pte_cont(pte)) { __set_ptes(mm, addr, ptep, pte, 1); return; } pfn = pte_pfn(pte); dpfn = pgsize >> PAGE_SHIFT; hugeprot = pte_pgprot(pte); clear_flush(mm, addr, ptep, pgsize, ncontig); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep = NULL; pgdp = pgd_offset(mm, addr); p4dp = p4d_alloc(mm, pgdp, addr); if (!p4dp) return NULL; pudp = pud_alloc(mm, p4dp, addr); if (!pudp) return NULL; if (sz == PUD_SIZE) { ptep = (pte_t *)pudp; } else if (sz == (CONT_PTE_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); if (!pmdp) return NULL; WARN_ON(addr & (sz - 1)); ptep = pte_alloc_huge(mm, pmdp, addr); } else if (sz == PMD_SIZE) { if (want_pmd_share(vma, addr) && pud_none(READ_ONCE(*pudp))) ptep = huge_pmd_share(mm, vma, addr, pudp); else ptep = (pte_t *)pmd_alloc(mm, pudp, addr); } else if (sz == (CONT_PMD_SIZE)) { pmdp = pmd_alloc(mm, pudp, addr); WARN_ON(addr & (sz - 1)); return (pte_t *)pmdp; } return ptep; } pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { pgd_t *pgdp; p4d_t *p4dp; pud_t *pudp, pud; pmd_t *pmdp, pmd; pgdp = pgd_offset(mm, addr); if (!pgd_present(READ_ONCE(*pgdp))) return NULL; p4dp = p4d_offset(pgdp, addr); if (!p4d_present(READ_ONCE(*p4dp))) return NULL; pudp = pud_offset(p4dp, addr); pud = READ_ONCE(*pudp); if (sz != PUD_SIZE && pud_none(pud)) return NULL; /* hugepage or swap? */ if (pud_leaf(pud) || !pud_present(pud)) return (pte_t *)pudp; /* table; check the next level */ if (sz == CONT_PMD_SIZE) addr &= CONT_PMD_MASK; pmdp = pmd_offset(pudp, addr); pmd = READ_ONCE(*pmdp); if (!(sz == PMD_SIZE || sz == CONT_PMD_SIZE) && pmd_none(pmd)) return NULL; if (pmd_leaf(pmd) || !pmd_present(pmd)) return (pte_t *)pmdp; if (sz == CONT_PTE_SIZE) return pte_offset_huge(pmdp, (addr & CONT_PTE_MASK)); return NULL; } unsigned long hugetlb_mask_last_page(struct hstate *h) { unsigned long hp_size = huge_page_size(h); switch (hp_size) { #ifndef __PAGETABLE_PMD_FOLDED case PUD_SIZE: return PGDIR_SIZE - PUD_SIZE; #endif case CONT_PMD_SIZE: return PUD_SIZE - CONT_PMD_SIZE; case PMD_SIZE: return PUD_SIZE - PMD_SIZE; case CONT_PTE_SIZE: return PMD_SIZE - CONT_PTE_SIZE; default: break; } return 0UL; } pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { size_t pagesize = 1UL << shift; entry = pte_mkhuge(entry); if (pagesize == CONT_PTE_SIZE) { entry = pte_mkcont(entry); } else if (pagesize == CONT_PMD_SIZE) { entry = pmd_pte(pmd_mkcont(pte_pmd(entry))); } else if (pagesize != PUD_SIZE && pagesize != PMD_SIZE) { pr_warn("%s: unrecognized huge page size 0x%lx\n", __func__, pagesize); } return entry; } void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) { int i, ncontig; size_t pgsize; ncontig = num_contig_ptes(sz, &pgsize); for (i = 0; i < ncontig; i++, addr += pgsize, ptep++) __pte_clear(mm, addr, ptep); } pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { int ncontig; size_t pgsize; pte_t orig_pte = __ptep_get(ptep); if (!pte_cont(orig_pte)) return __ptep_get_and_clear(mm, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig(mm, addr, ptep, pgsize, ncontig); } /* * huge_ptep_set_access_flags will update access flags (dirty, accesssed) * and write permission. * * For a contiguous huge pte range we need to check whether or not write * permission has to change only on the first pte in the set. Then for * all the contiguous ptes we need to check whether or not there is a * discrepancy between dirty or young. */ static int __cont_access_flags_changed(pte_t *ptep, pte_t pte, int ncontig) { int i; if (pte_write(pte) != pte_write(__ptep_get(ptep))) return 1; for (i = 0; i < ncontig; i++) { pte_t orig_pte = __ptep_get(ptep + i); if (pte_dirty(pte) != pte_dirty(orig_pte)) return 1; if (pte_young(pte) != pte_young(orig_pte)) return 1; } return 0; } int huge_ptep_set_access_flags(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t pte, int dirty) { int ncontig, i; size_t pgsize = 0; unsigned long pfn = pte_pfn(pte), dpfn; struct mm_struct *mm = vma->vm_mm; pgprot_t hugeprot; pte_t orig_pte; if (!pte_cont(pte)) return __ptep_set_access_flags(vma, addr, ptep, pte, dirty); ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; if (!__cont_access_flags_changed(ptep, pte, ncontig)) return 0; orig_pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); /* Make sure we don't lose the dirty or young state */ if (pte_dirty(orig_pte)) pte = pte_mkdirty(pte); if (pte_young(orig_pte)) pte = pte_mkyoung(pte); hugeprot = pte_pgprot(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); return 1; } void huge_ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep) { unsigned long pfn, dpfn; pgprot_t hugeprot; int ncontig, i; size_t pgsize; pte_t pte; if (!pte_cont(__ptep_get(ptep))) { __ptep_set_wrprotect(mm, addr, ptep); return; } ncontig = find_num_contig(mm, addr, ptep, &pgsize); dpfn = pgsize >> PAGE_SHIFT; pte = get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); pte = pte_wrprotect(pte); hugeprot = pte_pgprot(pte); pfn = pte_pfn(pte); for (i = 0; i < ncontig; i++, ptep++, addr += pgsize, pfn += dpfn) __set_ptes(mm, addr, ptep, pfn_pte(pfn, hugeprot), 1); } pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { struct mm_struct *mm = vma->vm_mm; size_t pgsize; int ncontig; if (!pte_cont(__ptep_get(ptep))) return ptep_clear_flush(vma, addr, ptep); ncontig = find_num_contig(mm, addr, ptep, &pgsize); return get_clear_contig_flush(mm, addr, ptep, pgsize, ncontig); } static int __init hugetlbpage_init(void) { if (pud_sect_supported()) hugetlb_add_hstate(PUD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(PMD_SHIFT - PAGE_SHIFT); hugetlb_add_hstate(CONT_PTE_SHIFT - PAGE_SHIFT); return 0; } arch_initcall(hugetlbpage_init); bool __init arch_hugetlb_valid_size(unsigned long size) { return __hugetlb_valid_size(size); } pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) { /* * Break-before-make (BBM) is required for all user space mappings * when the permission changes from executable to non-executable * in cases where cpu is affected with errata #2645198. */ if (pte_user_exec(__ptep_get(ptep))) return huge_ptep_clear_flush(vma, addr, ptep); } return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep); } void huge_ptep_modify_prot_commit(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep, pte_t old_pte, pte_t pte) { unsigned long psize = huge_page_size(hstate_vma(vma)); set_huge_pte_at(vma->vm_mm, addr, ptep, pte, psize); } |
| 130 130 130 130 130 130 130 130 130 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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-only /* * Copyright (C) 2012-2015 - ARM Ltd * Author: Marc Zyngier <marc.zyngier@arm.com> */ #include <hyp/adjust_pc.h> #include <linux/compiler.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <asm/kvm_hyp.h> #include <asm/kvm_mmu.h> #define vtr_to_max_lr_idx(v) ((v) & 0xf) #define vtr_to_nr_pre_bits(v) ((((u32)(v) >> 26) & 7) + 1) #define vtr_to_nr_apr_regs(v) (1 << (vtr_to_nr_pre_bits(v) - 5)) static u64 __gic_v3_get_lr(unsigned int lr) { switch (lr & 0xf) { case 0: return read_gicreg(ICH_LR0_EL2); case 1: return read_gicreg(ICH_LR1_EL2); case 2: return read_gicreg(ICH_LR2_EL2); case 3: return read_gicreg(ICH_LR3_EL2); case 4: return read_gicreg(ICH_LR4_EL2); case 5: return read_gicreg(ICH_LR5_EL2); case 6: return read_gicreg(ICH_LR6_EL2); case 7: return read_gicreg(ICH_LR7_EL2); case 8: return read_gicreg(ICH_LR8_EL2); case 9: return read_gicreg(ICH_LR9_EL2); case 10: return read_gicreg(ICH_LR10_EL2); case 11: return read_gicreg(ICH_LR11_EL2); case 12: return read_gicreg(ICH_LR12_EL2); case 13: return read_gicreg(ICH_LR13_EL2); case 14: return read_gicreg(ICH_LR14_EL2); case 15: return read_gicreg(ICH_LR15_EL2); } unreachable(); } static void __gic_v3_set_lr(u64 val, int lr) { switch (lr & 0xf) { case 0: write_gicreg(val, ICH_LR0_EL2); break; case 1: write_gicreg(val, ICH_LR1_EL2); break; case 2: write_gicreg(val, ICH_LR2_EL2); break; case 3: write_gicreg(val, ICH_LR3_EL2); break; case 4: write_gicreg(val, ICH_LR4_EL2); break; case 5: write_gicreg(val, ICH_LR5_EL2); break; case 6: write_gicreg(val, ICH_LR6_EL2); break; case 7: write_gicreg(val, ICH_LR7_EL2); break; case 8: write_gicreg(val, ICH_LR8_EL2); break; case 9: write_gicreg(val, ICH_LR9_EL2); break; case 10: write_gicreg(val, ICH_LR10_EL2); break; case 11: write_gicreg(val, ICH_LR11_EL2); break; case 12: write_gicreg(val, ICH_LR12_EL2); break; case 13: write_gicreg(val, ICH_LR13_EL2); break; case 14: write_gicreg(val, ICH_LR14_EL2); break; case 15: write_gicreg(val, ICH_LR15_EL2); break; } } static void __vgic_v3_write_ap0rn(u32 val, int n) { switch (n) { case 0: write_gicreg(val, ICH_AP0R0_EL2); break; case 1: write_gicreg(val, ICH_AP0R1_EL2); break; case 2: write_gicreg(val, ICH_AP0R2_EL2); break; case 3: write_gicreg(val, ICH_AP0R3_EL2); break; } } static void __vgic_v3_write_ap1rn(u32 val, int n) { switch (n) { case 0: write_gicreg(val, ICH_AP1R0_EL2); break; case 1: write_gicreg(val, ICH_AP1R1_EL2); break; case 2: write_gicreg(val, ICH_AP1R2_EL2); break; case 3: write_gicreg(val, ICH_AP1R3_EL2); break; } } static u32 __vgic_v3_read_ap0rn(int n) { u32 val; switch (n) { case 0: val = read_gicreg(ICH_AP0R0_EL2); break; case 1: val = read_gicreg(ICH_AP0R1_EL2); break; case 2: val = read_gicreg(ICH_AP0R2_EL2); break; case 3: val = read_gicreg(ICH_AP0R3_EL2); break; default: unreachable(); } return val; } static u32 __vgic_v3_read_ap1rn(int n) { u32 val; switch (n) { case 0: val = read_gicreg(ICH_AP1R0_EL2); break; case 1: val = read_gicreg(ICH_AP1R1_EL2); break; case 2: val = read_gicreg(ICH_AP1R2_EL2); break; case 3: val = read_gicreg(ICH_AP1R3_EL2); break; default: unreachable(); } return val; } void __vgic_v3_save_state(struct vgic_v3_cpu_if *cpu_if) { u64 used_lrs = cpu_if->used_lrs; /* * Make sure stores to the GIC via the memory mapped interface * are now visible to the system register interface when reading the * LRs, and when reading back the VMCR on non-VHE systems. */ if (used_lrs || !has_vhe()) { if (!cpu_if->vgic_sre) { dsb(sy); isb(); } } if (used_lrs || cpu_if->its_vpe.its_vm) { int i; u32 elrsr; elrsr = read_gicreg(ICH_ELRSR_EL2); write_gicreg(cpu_if->vgic_hcr & ~ICH_HCR_EN, ICH_HCR_EL2); for (i = 0; i < used_lrs; i++) { if (elrsr & (1 << i)) cpu_if->vgic_lr[i] &= ~ICH_LR_STATE; else cpu_if->vgic_lr[i] = __gic_v3_get_lr(i); __gic_v3_set_lr(0, i); } } } void __vgic_v3_restore_state(struct vgic_v3_cpu_if *cpu_if) { u64 used_lrs = cpu_if->used_lrs; int i; if (used_lrs || cpu_if->its_vpe.its_vm) { write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); for (i = 0; i < used_lrs; i++) __gic_v3_set_lr(cpu_if->vgic_lr[i], i); } /* * Ensure that writes to the LRs, and on non-VHE systems ensure that * the write to the VMCR in __vgic_v3_activate_traps(), will have * reached the (re)distributors. This ensure the guest will read the * correct values from the memory-mapped interface. */ if (used_lrs || !has_vhe()) { if (!cpu_if->vgic_sre) { isb(); dsb(sy); } } } void __vgic_v3_activate_traps(struct vgic_v3_cpu_if *cpu_if) { /* * VFIQEn is RES1 if ICC_SRE_EL1.SRE is 1. This causes a * Group0 interrupt (as generated in GICv2 mode) to be * delivered as a FIQ to the guest, with potentially fatal * consequences. So we must make sure that ICC_SRE_EL1 has * been actually programmed with the value we want before * starting to mess with the rest of the GIC, and VMCR_EL2 in * particular. This logic must be called before * __vgic_v3_restore_state(). */ if (!cpu_if->vgic_sre) { write_gicreg(0, ICC_SRE_EL1); isb(); write_gicreg(cpu_if->vgic_vmcr, ICH_VMCR_EL2); if (has_vhe()) { /* * Ensure that the write to the VMCR will have reached * the (re)distributors. This ensure the guest will * read the correct values from the memory-mapped * interface. */ isb(); dsb(sy); } } /* * Prevent the guest from touching the GIC system registers if * SRE isn't enabled for GICv3 emulation. */ write_gicreg(read_gicreg(ICC_SRE_EL2) & ~ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); /* * If we need to trap system registers, we must write * ICH_HCR_EL2 anyway, even if no interrupts are being * injected, */ if (static_branch_unlikely(&vgic_v3_cpuif_trap) || cpu_if->its_vpe.its_vm) write_gicreg(cpu_if->vgic_hcr, ICH_HCR_EL2); } void __vgic_v3_deactivate_traps(struct vgic_v3_cpu_if *cpu_if) { u64 val; if (!cpu_if->vgic_sre) { cpu_if->vgic_vmcr = read_gicreg(ICH_VMCR_EL2); } val = read_gicreg(ICC_SRE_EL2); write_gicreg(val | ICC_SRE_EL2_ENABLE, ICC_SRE_EL2); if (!cpu_if->vgic_sre) { /* Make sure ENABLE is set at EL2 before setting SRE at EL1 */ isb(); write_gicreg(1, ICC_SRE_EL1); } /* * If we were trapping system registers, we enabled the VGIC even if * no interrupts were being injected, and we disable it again here. */ if (static_branch_unlikely(&vgic_v3_cpuif_trap) || cpu_if->its_vpe.its_vm) write_gicreg(0, ICH_HCR_EL2); } static void __vgic_v3_save_aprs(struct vgic_v3_cpu_if *cpu_if) { u64 val; u32 nr_pre_bits; val = read_gicreg(ICH_VTR_EL2); nr_pre_bits = vtr_to_nr_pre_bits(val); switch (nr_pre_bits) { case 7: cpu_if->vgic_ap0r[3] = __vgic_v3_read_ap0rn(3); cpu_if->vgic_ap0r[2] = __vgic_v3_read_ap0rn(2); fallthrough; case 6: cpu_if->vgic_ap0r[1] = __vgic_v3_read_ap0rn(1); fallthrough; default: cpu_if->vgic_ap0r[0] = __vgic_v3_read_ap0rn(0); } switch (nr_pre_bits) { case 7: cpu_if->vgic_ap1r[3] = __vgic_v3_read_ap1rn(3); cpu_if->vgic_ap1r[2] = __vgic_v3_read_ap1rn(2); fallthrough; case 6: cpu_if->vgic_ap1r[1] = __vgic_v3_read_ap1rn(1); fallthrough; default: cpu_if->vgic_ap1r[0] = __vgic_v3_read_ap1rn(0); } } static void __vgic_v3_restore_aprs(struct vgic_v3_cpu_if *cpu_if) { u64 val; u32 nr_pre_bits; val = read_gicreg(ICH_VTR_EL2); nr_pre_bits = vtr_to_nr_pre_bits(val); switch (nr_pre_bits) { case 7: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[3], 3); __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[2], 2); fallthrough; case 6: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[1], 1); fallthrough; default: __vgic_v3_write_ap0rn(cpu_if->vgic_ap0r[0], 0); } switch (nr_pre_bits) { case 7: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[3], 3); __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[2], 2); fallthrough; case 6: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[1], 1); fallthrough; default: __vgic_v3_write_ap1rn(cpu_if->vgic_ap1r[0], 0); } } void __vgic_v3_init_lrs(void) { int max_lr_idx = vtr_to_max_lr_idx(read_gicreg(ICH_VTR_EL2)); int i; for (i = 0; i <= max_lr_idx; i++) __gic_v3_set_lr(0, i); } /* * Return the GIC CPU configuration: * - [31:0] ICH_VTR_EL2 * - [62:32] RES0 * - [63] MMIO (GICv2) capable */ u64 __vgic_v3_get_gic_config(void) { u64 val, sre = read_gicreg(ICC_SRE_EL1); unsigned long flags = 0; /* * To check whether we have a MMIO-based (GICv2 compatible) * CPU interface, we need to disable the system register * view. To do that safely, we have to prevent any interrupt * from firing (which would be deadly). * * Note that this only makes sense on VHE, as interrupts are * already masked for nVHE as part of the exception entry to * EL2. */ if (has_vhe()) flags = local_daif_save(); /* * Table 11-2 "Permitted ICC_SRE_ELx.SRE settings" indicates * that to be able to set ICC_SRE_EL1.SRE to 0, all the * interrupt overrides must be set. You've got to love this. */ sysreg_clear_set(hcr_el2, 0, HCR_AMO | HCR_FMO | HCR_IMO); isb(); write_gicreg(0, ICC_SRE_EL1); isb(); val = read_gicreg(ICC_SRE_EL1); write_gicreg(sre, ICC_SRE_EL1); isb(); sysreg_clear_set(hcr_el2, HCR_AMO | HCR_FMO | HCR_IMO, 0); isb(); if (has_vhe()) local_daif_restore(flags); val = (val & ICC_SRE_EL1_SRE) ? 0 : (1ULL << 63); val |= read_gicreg(ICH_VTR_EL2); return val; } static u64 __vgic_v3_read_vmcr(void) { return read_gicreg(ICH_VMCR_EL2); } static void __vgic_v3_write_vmcr(u32 vmcr) { write_gicreg(vmcr, ICH_VMCR_EL2); } void __vgic_v3_save_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if) { __vgic_v3_save_aprs(cpu_if); if (cpu_if->vgic_sre) cpu_if->vgic_vmcr = __vgic_v3_read_vmcr(); } void __vgic_v3_restore_vmcr_aprs(struct vgic_v3_cpu_if *cpu_if) { /* * If dealing with a GICv2 emulation on GICv3, VMCR_EL2.VFIQen * is dependent on ICC_SRE_EL1.SRE, and we have to perform the * VMCR_EL2 save/restore in the world switch. */ if (cpu_if->vgic_sre) __vgic_v3_write_vmcr(cpu_if->vgic_vmcr); __vgic_v3_restore_aprs(cpu_if); } static int __vgic_v3_bpr_min(void) { /* See Pseudocode for VPriorityGroup */ return 8 - vtr_to_nr_pre_bits(read_gicreg(ICH_VTR_EL2)); } static int __vgic_v3_get_group(struct kvm_vcpu *vcpu) { u64 esr = kvm_vcpu_get_esr(vcpu); u8 crm = (esr & ESR_ELx_SYS64_ISS_CRM_MASK) >> ESR_ELx_SYS64_ISS_CRM_SHIFT; return crm != 8; } #define GICv3_IDLE_PRIORITY 0xff static int __vgic_v3_highest_priority_lr(struct kvm_vcpu *vcpu, u32 vmcr, u64 *lr_val) { unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; u8 priority = GICv3_IDLE_PRIORITY; int i, lr = -1; for (i = 0; i < used_lrs; i++) { u64 val = __gic_v3_get_lr(i); u8 lr_prio = (val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; /* Not pending in the state? */ if ((val & ICH_LR_STATE) != ICH_LR_PENDING_BIT) continue; /* Group-0 interrupt, but Group-0 disabled? */ if (!(val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG0_MASK)) continue; /* Group-1 interrupt, but Group-1 disabled? */ if ((val & ICH_LR_GROUP) && !(vmcr & ICH_VMCR_ENG1_MASK)) continue; /* Not the highest priority? */ if (lr_prio >= priority) continue; /* This is a candidate */ priority = lr_prio; *lr_val = val; lr = i; } if (lr == -1) *lr_val = ICC_IAR1_EL1_SPURIOUS; return lr; } static int __vgic_v3_find_active_lr(struct kvm_vcpu *vcpu, int intid, u64 *lr_val) { unsigned int used_lrs = vcpu->arch.vgic_cpu.vgic_v3.used_lrs; int i; for (i = 0; i < used_lrs; i++) { u64 val = __gic_v3_get_lr(i); if ((val & ICH_LR_VIRTUAL_ID_MASK) == intid && (val & ICH_LR_ACTIVE_BIT)) { *lr_val = val; return i; } } *lr_val = ICC_IAR1_EL1_SPURIOUS; return -1; } static int __vgic_v3_get_highest_active_priority(void) { u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); u32 hap = 0; int i; for (i = 0; i < nr_apr_regs; i++) { u32 val; /* * The ICH_AP0Rn_EL2 and ICH_AP1Rn_EL2 registers * contain the active priority levels for this VCPU * for the maximum number of supported priority * levels, and we return the full priority level only * if the BPR is programmed to its minimum, otherwise * we return a combination of the priority level and * subpriority, as determined by the setting of the * BPR, but without the full subpriority. */ val = __vgic_v3_read_ap0rn(i); val |= __vgic_v3_read_ap1rn(i); if (!val) { hap += 32; continue; } return (hap + __ffs(val)) << __vgic_v3_bpr_min(); } return GICv3_IDLE_PRIORITY; } static unsigned int __vgic_v3_get_bpr0(u32 vmcr) { return (vmcr & ICH_VMCR_BPR0_MASK) >> ICH_VMCR_BPR0_SHIFT; } static unsigned int __vgic_v3_get_bpr1(u32 vmcr) { unsigned int bpr; if (vmcr & ICH_VMCR_CBPR_MASK) { bpr = __vgic_v3_get_bpr0(vmcr); if (bpr < 7) bpr++; } else { bpr = (vmcr & ICH_VMCR_BPR1_MASK) >> ICH_VMCR_BPR1_SHIFT; } return bpr; } /* * Convert a priority to a preemption level, taking the relevant BPR * into account by zeroing the sub-priority bits. */ static u8 __vgic_v3_pri_to_pre(u8 pri, u32 vmcr, int grp) { unsigned int bpr; if (!grp) bpr = __vgic_v3_get_bpr0(vmcr) + 1; else bpr = __vgic_v3_get_bpr1(vmcr); return pri & (GENMASK(7, 0) << bpr); } /* * The priority value is independent of any of the BPR values, so we * normalize it using the minimal BPR value. This guarantees that no * matter what the guest does with its BPR, we can always set/get the * same value of a priority. */ static void __vgic_v3_set_active_priority(u8 pri, u32 vmcr, int grp) { u8 pre, ap; u32 val; int apr; pre = __vgic_v3_pri_to_pre(pri, vmcr, grp); ap = pre >> __vgic_v3_bpr_min(); apr = ap / 32; if (!grp) { val = __vgic_v3_read_ap0rn(apr); __vgic_v3_write_ap0rn(val | BIT(ap % 32), apr); } else { val = __vgic_v3_read_ap1rn(apr); __vgic_v3_write_ap1rn(val | BIT(ap % 32), apr); } } static int __vgic_v3_clear_highest_active_priority(void) { u8 nr_apr_regs = vtr_to_nr_apr_regs(read_gicreg(ICH_VTR_EL2)); u32 hap = 0; int i; for (i = 0; i < nr_apr_regs; i++) { u32 ap0, ap1; int c0, c1; ap0 = __vgic_v3_read_ap0rn(i); ap1 = __vgic_v3_read_ap1rn(i); if (!ap0 && !ap1) { hap += 32; continue; } c0 = ap0 ? __ffs(ap0) : 32; c1 = ap1 ? __ffs(ap1) : 32; /* Always clear the LSB, which is the highest priority */ if (c0 < c1) { ap0 &= ~BIT(c0); __vgic_v3_write_ap0rn(ap0, i); hap += c0; } else { ap1 &= ~BIT(c1); __vgic_v3_write_ap1rn(ap1, i); hap += c1; } /* Rescale to 8 bits of priority */ return hap << __vgic_v3_bpr_min(); } return GICv3_IDLE_PRIORITY; } static void __vgic_v3_read_iar(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 lr_val; u8 lr_prio, pmr; int lr, grp; grp = __vgic_v3_get_group(vcpu); lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); if (lr < 0) goto spurious; if (grp != !!(lr_val & ICH_LR_GROUP)) goto spurious; pmr = (vmcr & ICH_VMCR_PMR_MASK) >> ICH_VMCR_PMR_SHIFT; lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; if (pmr <= lr_prio) goto spurious; if (__vgic_v3_get_highest_active_priority() <= __vgic_v3_pri_to_pre(lr_prio, vmcr, grp)) goto spurious; lr_val &= ~ICH_LR_STATE; lr_val |= ICH_LR_ACTIVE_BIT; __gic_v3_set_lr(lr_val, lr); __vgic_v3_set_active_priority(lr_prio, vmcr, grp); vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); return; spurious: vcpu_set_reg(vcpu, rt, ICC_IAR1_EL1_SPURIOUS); } static void __vgic_v3_clear_active_lr(int lr, u64 lr_val) { lr_val &= ~ICH_LR_ACTIVE_BIT; if (lr_val & ICH_LR_HW) { u32 pid; pid = (lr_val & ICH_LR_PHYS_ID_MASK) >> ICH_LR_PHYS_ID_SHIFT; gic_write_dir(pid); } __gic_v3_set_lr(lr_val, lr); } static void __vgic_v3_bump_eoicount(void) { u32 hcr; hcr = read_gicreg(ICH_HCR_EL2); hcr += 1 << ICH_HCR_EOIcount_SHIFT; write_gicreg(hcr, ICH_HCR_EL2); } static void __vgic_v3_write_dir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vid = vcpu_get_reg(vcpu, rt); u64 lr_val; int lr; /* EOImode == 0, nothing to be done here */ if (!(vmcr & ICH_VMCR_EOIM_MASK)) return; /* No deactivate to be performed on an LPI */ if (vid >= VGIC_MIN_LPI) return; lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); if (lr == -1) { __vgic_v3_bump_eoicount(); return; } __vgic_v3_clear_active_lr(lr, lr_val); } static void __vgic_v3_write_eoir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vid = vcpu_get_reg(vcpu, rt); u64 lr_val; u8 lr_prio, act_prio; int lr, grp; grp = __vgic_v3_get_group(vcpu); /* Drop priority in any case */ act_prio = __vgic_v3_clear_highest_active_priority(); lr = __vgic_v3_find_active_lr(vcpu, vid, &lr_val); if (lr == -1) { /* Do not bump EOIcount for LPIs that aren't in the LRs */ if (!(vid >= VGIC_MIN_LPI)) __vgic_v3_bump_eoicount(); return; } /* EOImode == 1 and not an LPI, nothing to be done here */ if ((vmcr & ICH_VMCR_EOIM_MASK) && !(vid >= VGIC_MIN_LPI)) return; lr_prio = (lr_val & ICH_LR_PRIORITY_MASK) >> ICH_LR_PRIORITY_SHIFT; /* If priorities or group do not match, the guest has fscked-up. */ if (grp != !!(lr_val & ICH_LR_GROUP) || __vgic_v3_pri_to_pre(lr_prio, vmcr, grp) != act_prio) return; /* Let's now perform the deactivation */ __vgic_v3_clear_active_lr(lr, lr_val); } static void __vgic_v3_read_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG0_MASK)); } static void __vgic_v3_read_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, !!(vmcr & ICH_VMCR_ENG1_MASK)); } static void __vgic_v3_write_igrpen0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); if (val & 1) vmcr |= ICH_VMCR_ENG0_MASK; else vmcr &= ~ICH_VMCR_ENG0_MASK; __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_write_igrpen1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); if (val & 1) vmcr |= ICH_VMCR_ENG1_MASK; else vmcr &= ~ICH_VMCR_ENG1_MASK; __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_read_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr0(vmcr)); } static void __vgic_v3_read_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vcpu_set_reg(vcpu, rt, __vgic_v3_get_bpr1(vmcr)); } static void __vgic_v3_write_bpr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); u8 bpr_min = __vgic_v3_bpr_min() - 1; /* Enforce BPR limiting */ if (val < bpr_min) val = bpr_min; val <<= ICH_VMCR_BPR0_SHIFT; val &= ICH_VMCR_BPR0_MASK; vmcr &= ~ICH_VMCR_BPR0_MASK; vmcr |= val; __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_write_bpr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 val = vcpu_get_reg(vcpu, rt); u8 bpr_min = __vgic_v3_bpr_min(); if (vmcr & ICH_VMCR_CBPR_MASK) return; /* Enforce BPR limiting */ if (val < bpr_min) val = bpr_min; val <<= ICH_VMCR_BPR1_SHIFT; val &= ICH_VMCR_BPR1_MASK; vmcr &= ~ICH_VMCR_BPR1_MASK; vmcr |= val; __vgic_v3_write_vmcr(vmcr); } static void __vgic_v3_read_apxrn(struct kvm_vcpu *vcpu, int rt, int n) { u32 val; if (!__vgic_v3_get_group(vcpu)) val = __vgic_v3_read_ap0rn(n); else val = __vgic_v3_read_ap1rn(n); vcpu_set_reg(vcpu, rt, val); } static void __vgic_v3_write_apxrn(struct kvm_vcpu *vcpu, int rt, int n) { u32 val = vcpu_get_reg(vcpu, rt); if (!__vgic_v3_get_group(vcpu)) __vgic_v3_write_ap0rn(val, n); else __vgic_v3_write_ap1rn(val, n); } static void __vgic_v3_read_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 0); } static void __vgic_v3_read_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 1); } static void __vgic_v3_read_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 2); } static void __vgic_v3_read_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_read_apxrn(vcpu, rt, 3); } static void __vgic_v3_write_apxr0(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 0); } static void __vgic_v3_write_apxr1(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 1); } static void __vgic_v3_write_apxr2(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 2); } static void __vgic_v3_write_apxr3(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { __vgic_v3_write_apxrn(vcpu, rt, 3); } static void __vgic_v3_read_hppir(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u64 lr_val; int lr, lr_grp, grp; grp = __vgic_v3_get_group(vcpu); lr = __vgic_v3_highest_priority_lr(vcpu, vmcr, &lr_val); if (lr == -1) goto spurious; lr_grp = !!(lr_val & ICH_LR_GROUP); if (lr_grp != grp) lr_val = ICC_IAR1_EL1_SPURIOUS; spurious: vcpu_set_reg(vcpu, rt, lr_val & ICH_LR_VIRTUAL_ID_MASK); } static void __vgic_v3_read_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { vmcr &= ICH_VMCR_PMR_MASK; vmcr >>= ICH_VMCR_PMR_SHIFT; vcpu_set_reg(vcpu, rt, vmcr); } static void __vgic_v3_write_pmr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = vcpu_get_reg(vcpu, rt); val <<= ICH_VMCR_PMR_SHIFT; val &= ICH_VMCR_PMR_MASK; vmcr &= ~ICH_VMCR_PMR_MASK; vmcr |= val; write_gicreg(vmcr, ICH_VMCR_EL2); } static void __vgic_v3_read_rpr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = __vgic_v3_get_highest_active_priority(); vcpu_set_reg(vcpu, rt, val); } static void __vgic_v3_read_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 vtr, val; vtr = read_gicreg(ICH_VTR_EL2); /* PRIbits */ val = ((vtr >> 29) & 7) << ICC_CTLR_EL1_PRI_BITS_SHIFT; /* IDbits */ val |= ((vtr >> 23) & 7) << ICC_CTLR_EL1_ID_BITS_SHIFT; /* SEIS */ if (kvm_vgic_global_state.ich_vtr_el2 & ICH_VTR_SEIS_MASK) val |= BIT(ICC_CTLR_EL1_SEIS_SHIFT); /* A3V */ val |= ((vtr >> 21) & 1) << ICC_CTLR_EL1_A3V_SHIFT; /* EOImode */ val |= ((vmcr & ICH_VMCR_EOIM_MASK) >> ICH_VMCR_EOIM_SHIFT) << ICC_CTLR_EL1_EOImode_SHIFT; /* CBPR */ val |= (vmcr & ICH_VMCR_CBPR_MASK) >> ICH_VMCR_CBPR_SHIFT; vcpu_set_reg(vcpu, rt, val); } static void __vgic_v3_write_ctlr(struct kvm_vcpu *vcpu, u32 vmcr, int rt) { u32 val = vcpu_get_reg(vcpu, rt); if (val & ICC_CTLR_EL1_CBPR_MASK) vmcr |= ICH_VMCR_CBPR_MASK; else vmcr &= ~ICH_VMCR_CBPR_MASK; if (val & ICC_CTLR_EL1_EOImode_MASK) vmcr |= ICH_VMCR_EOIM_MASK; else vmcr &= ~ICH_VMCR_EOIM_MASK; write_gicreg(vmcr, ICH_VMCR_EL2); } int __vgic_v3_perform_cpuif_access(struct kvm_vcpu *vcpu) { int rt; u64 esr; u32 vmcr; void (*fn)(struct kvm_vcpu *, u32, int); bool is_read; u32 sysreg; esr = kvm_vcpu_get_esr(vcpu); if (vcpu_mode_is_32bit(vcpu)) { if (!kvm_condition_valid(vcpu)) { __kvm_skip_instr(vcpu); return 1; } sysreg = esr_cp15_to_sysreg(esr); } else { sysreg = esr_sys64_to_sysreg(esr); } is_read = (esr & ESR_ELx_SYS64_ISS_DIR_MASK) == ESR_ELx_SYS64_ISS_DIR_READ; switch (sysreg) { case SYS_ICC_IAR0_EL1: case SYS_ICC_IAR1_EL1: if (unlikely(!is_read)) return 0; fn = __vgic_v3_read_iar; break; case SYS_ICC_EOIR0_EL1: case SYS_ICC_EOIR1_EL1: if (unlikely(is_read)) return 0; fn = __vgic_v3_write_eoir; break; case SYS_ICC_IGRPEN1_EL1: if (is_read) fn = __vgic_v3_read_igrpen1; else fn = __vgic_v3_write_igrpen1; break; case SYS_ICC_BPR1_EL1: if (is_read) fn = __vgic_v3_read_bpr1; else fn = __vgic_v3_write_bpr1; break; case SYS_ICC_AP0Rn_EL1(0): case SYS_ICC_AP1Rn_EL1(0): if (is_read) fn = __vgic_v3_read_apxr0; else fn = __vgic_v3_write_apxr0; break; case SYS_ICC_AP0Rn_EL1(1): case SYS_ICC_AP1Rn_EL1(1): if (is_read) fn = __vgic_v3_read_apxr1; else fn = __vgic_v3_write_apxr1; break; case SYS_ICC_AP0Rn_EL1(2): case SYS_ICC_AP1Rn_EL1(2): if (is_read) fn = __vgic_v3_read_apxr2; else fn = __vgic_v3_write_apxr2; break; case SYS_ICC_AP0Rn_EL1(3): case SYS_ICC_AP1Rn_EL1(3): if (is_read) fn = __vgic_v3_read_apxr3; else fn = __vgic_v3_write_apxr3; break; case SYS_ICC_HPPIR0_EL1: case SYS_ICC_HPPIR1_EL1: if (unlikely(!is_read)) return 0; fn = __vgic_v3_read_hppir; break; case SYS_ICC_IGRPEN0_EL1: if (is_read) fn = __vgic_v3_read_igrpen0; else fn = __vgic_v3_write_igrpen0; break; case SYS_ICC_BPR0_EL1: if (is_read) fn = __vgic_v3_read_bpr0; else fn = __vgic_v3_write_bpr0; break; case SYS_ICC_DIR_EL1: if (unlikely(is_read)) return 0; fn = __vgic_v3_write_dir; break; case SYS_ICC_RPR_EL1: if (unlikely(!is_read)) return 0; fn = __vgic_v3_read_rpr; break; case SYS_ICC_CTLR_EL1: if (is_read) fn = __vgic_v3_read_ctlr; else fn = __vgic_v3_write_ctlr; break; case SYS_ICC_PMR_EL1: if (is_read) fn = __vgic_v3_read_pmr; else fn = __vgic_v3_write_pmr; break; default: return 0; } vmcr = __vgic_v3_read_vmcr(); rt = kvm_vcpu_sys_get_rt(vcpu); fn(vcpu, vmcr, rt); __kvm_skip_instr(vcpu); return 1; } |
| 49 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_FILELOCK_H #define _LINUX_FILELOCK_H #include <linux/fs.h> #define FL_POSIX 1 #define FL_FLOCK 2 #define FL_DELEG 4 /* NFSv4 delegation */ #define FL_ACCESS 8 /* not trying to lock, just looking */ #define FL_EXISTS 16 /* when unlocking, test for existence */ #define FL_LEASE 32 /* lease held on this file */ #define FL_CLOSE 64 /* unlock on close */ #define FL_SLEEP 128 /* A blocking lock */ #define FL_DOWNGRADE_PENDING 256 /* Lease is being downgraded */ #define FL_UNLOCK_PENDING 512 /* Lease is being broken */ #define FL_OFDLCK 1024 /* lock is "owned" by struct file */ #define FL_LAYOUT 2048 /* outstanding pNFS layout */ #define FL_RECLAIM 4096 /* reclaiming from a reboot server */ #define FL_CLOSE_POSIX (FL_POSIX | FL_CLOSE) /* * Special return value from posix_lock_file() and vfs_lock_file() for * asynchronous locking. */ #define FILE_LOCK_DEFERRED 1 struct file_lock; struct file_lease; struct file_lock_operations { void (*fl_copy_lock)(struct file_lock *, struct file_lock *); void (*fl_release_private)(struct file_lock *); }; struct lock_manager_operations { void *lm_mod_owner; fl_owner_t (*lm_get_owner)(fl_owner_t); void (*lm_put_owner)(fl_owner_t); void (*lm_notify)(struct file_lock *); /* unblock callback */ int (*lm_grant)(struct file_lock *, int); bool (*lm_lock_expirable)(struct file_lock *cfl); void (*lm_expire_lock)(void); }; struct lease_manager_operations { bool (*lm_break)(struct file_lease *); int (*lm_change)(struct file_lease *, int, struct list_head *); void (*lm_setup)(struct file_lease *, void **); bool (*lm_breaker_owns_lease)(struct file_lease *); }; struct lock_manager { struct list_head list; /* * NFSv4 and up also want opens blocked during the grace period; * NLM doesn't care: */ bool block_opens; }; struct net; void locks_start_grace(struct net *, struct lock_manager *); void locks_end_grace(struct lock_manager *); bool locks_in_grace(struct net *); bool opens_in_grace(struct net *); /* * struct file_lock has a union that some filesystems use to track * their own private info. The NFS side of things is defined here: */ #include <linux/nfs_fs_i.h> /* * struct file_lock represents a generic "file lock". It's used to represent * POSIX byte range locks, BSD (flock) locks, and leases. It's important to * note that the same struct is used to represent both a request for a lock and * the lock itself, but the same object is never used for both. * * FIXME: should we create a separate "struct lock_request" to help distinguish * these two uses? * * The varous i_flctx lists are ordered by: * * 1) lock owner * 2) lock range start * 3) lock range end * * Obviously, the last two criteria only matter for POSIX locks. */ struct file_lock_core { struct file_lock_core *flc_blocker; /* The lock that is blocking us */ struct list_head flc_list; /* link into file_lock_context */ struct hlist_node flc_link; /* node in global lists */ struct list_head flc_blocked_requests; /* list of requests with * ->fl_blocker pointing here */ struct list_head flc_blocked_member; /* node in * ->fl_blocker->fl_blocked_requests */ fl_owner_t flc_owner; unsigned int flc_flags; unsigned char flc_type; pid_t flc_pid; int flc_link_cpu; /* what cpu's list is this on? */ wait_queue_head_t flc_wait; struct file *flc_file; }; struct file_lock { struct file_lock_core c; loff_t fl_start; loff_t fl_end; const struct file_lock_operations *fl_ops; /* Callbacks for filesystems */ const struct lock_manager_operations *fl_lmops; /* Callbacks for lockmanagers */ union { struct nfs_lock_info nfs_fl; struct nfs4_lock_info nfs4_fl; struct { struct list_head link; /* link in AFS vnode's pending_locks list */ int state; /* state of grant or error if -ve */ unsigned int debug_id; } afs; struct { struct inode *inode; } ceph; } fl_u; } __randomize_layout; struct file_lease { struct file_lock_core c; struct fasync_struct * fl_fasync; /* for lease break notifications */ /* for lease breaks: */ unsigned long fl_break_time; unsigned long fl_downgrade_time; const struct lease_manager_operations *fl_lmops; /* Callbacks for lease managers */ } __randomize_layout; struct file_lock_context { spinlock_t flc_lock; struct list_head flc_flock; struct list_head flc_posix; struct list_head flc_lease; }; #ifdef CONFIG_FILE_LOCKING int fcntl_getlk(struct file *, unsigned int, struct flock *); int fcntl_setlk(unsigned int, struct file *, unsigned int, struct flock *); #if BITS_PER_LONG == 32 int fcntl_getlk64(struct file *, unsigned int, struct flock64 *); int fcntl_setlk64(unsigned int, struct file *, unsigned int, struct flock64 *); #endif int fcntl_setlease(unsigned int fd, struct file *filp, int arg); int fcntl_getlease(struct file *filp); static inline bool lock_is_unlock(struct file_lock *fl) { return fl->c.flc_type == F_UNLCK; } static inline bool lock_is_read(struct file_lock *fl) { return fl->c.flc_type == F_RDLCK; } static inline bool lock_is_write(struct file_lock *fl) { return fl->c.flc_type == F_WRLCK; } static inline void locks_wake_up(struct file_lock *fl) { wake_up(&fl->c.flc_wait); } /* fs/locks.c */ void locks_free_lock_context(struct inode *inode); void locks_free_lock(struct file_lock *fl); void locks_init_lock(struct file_lock *); struct file_lock *locks_alloc_lock(void); void locks_copy_lock(struct file_lock *, struct file_lock *); void locks_copy_conflock(struct file_lock *, struct file_lock *); void locks_remove_posix(struct file *, fl_owner_t); void locks_remove_file(struct file *); void locks_release_private(struct file_lock *); void posix_test_lock(struct file *, struct file_lock *); int posix_lock_file(struct file *, struct file_lock *, struct file_lock *); int locks_delete_block(struct file_lock *); int vfs_test_lock(struct file *, struct file_lock *); int vfs_lock_file(struct file *, unsigned int, struct file_lock *, struct file_lock *); int vfs_cancel_lock(struct file *filp, struct file_lock *fl); bool vfs_inode_has_locks(struct inode *inode); int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl); void locks_init_lease(struct file_lease *); void locks_free_lease(struct file_lease *fl); struct file_lease *locks_alloc_lease(void); int __break_lease(struct inode *inode, unsigned int flags, unsigned int type); void lease_get_mtime(struct inode *, struct timespec64 *time); int generic_setlease(struct file *, int, struct file_lease **, void **priv); int kernel_setlease(struct file *, int, struct file_lease **, void **); int vfs_setlease(struct file *, int, struct file_lease **, void **); int lease_modify(struct file_lease *, int, struct list_head *); struct notifier_block; int lease_register_notifier(struct notifier_block *); void lease_unregister_notifier(struct notifier_block *); struct files_struct; void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files); bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner); static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return smp_load_acquire(&inode->i_flctx); } #else /* !CONFIG_FILE_LOCKING */ static inline int fcntl_getlk(struct file *file, unsigned int cmd, struct flock __user *user) { return -EINVAL; } static inline int fcntl_setlk(unsigned int fd, struct file *file, unsigned int cmd, struct flock __user *user) { return -EACCES; } #if BITS_PER_LONG == 32 static inline int fcntl_getlk64(struct file *file, unsigned int cmd, struct flock64 *user) { return -EINVAL; } static inline int fcntl_setlk64(unsigned int fd, struct file *file, unsigned int cmd, struct flock64 *user) { return -EACCES; } #endif static inline int fcntl_setlease(unsigned int fd, struct file *filp, int arg) { return -EINVAL; } static inline int fcntl_getlease(struct file *filp) { return F_UNLCK; } static inline bool lock_is_unlock(struct file_lock *fl) { return false; } static inline bool lock_is_read(struct file_lock *fl) { return false; } static inline bool lock_is_write(struct file_lock *fl) { return false; } static inline void locks_wake_up(struct file_lock *fl) { } static inline void locks_free_lock_context(struct inode *inode) { } static inline void locks_init_lock(struct file_lock *fl) { return; } static inline void locks_init_lease(struct file_lease *fl) { return; } static inline void locks_copy_conflock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_copy_lock(struct file_lock *new, struct file_lock *fl) { return; } static inline void locks_remove_posix(struct file *filp, fl_owner_t owner) { return; } static inline void locks_remove_file(struct file *filp) { return; } static inline void posix_test_lock(struct file *filp, struct file_lock *fl) { return; } static inline int posix_lock_file(struct file *filp, struct file_lock *fl, struct file_lock *conflock) { return -ENOLCK; } static inline int locks_delete_block(struct file_lock *waiter) { return -ENOENT; } static inline int vfs_test_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline int vfs_lock_file(struct file *filp, unsigned int cmd, struct file_lock *fl, struct file_lock *conf) { return -ENOLCK; } static inline int vfs_cancel_lock(struct file *filp, struct file_lock *fl) { return 0; } static inline bool vfs_inode_has_locks(struct inode *inode) { return false; } static inline int locks_lock_inode_wait(struct inode *inode, struct file_lock *fl) { return -ENOLCK; } static inline int __break_lease(struct inode *inode, unsigned int mode, unsigned int type) { return 0; } static inline void lease_get_mtime(struct inode *inode, struct timespec64 *time) { return; } static inline int generic_setlease(struct file *filp, int arg, struct file_lease **flp, void **priv) { return -EINVAL; } static inline int kernel_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int vfs_setlease(struct file *filp, int arg, struct file_lease **lease, void **priv) { return -EINVAL; } static inline int lease_modify(struct file_lease *fl, int arg, struct list_head *dispose) { return -EINVAL; } struct files_struct; static inline void show_fd_locks(struct seq_file *f, struct file *filp, struct files_struct *files) {} static inline bool locks_owner_has_blockers(struct file_lock_context *flctx, fl_owner_t owner) { return false; } static inline struct file_lock_context * locks_inode_context(const struct inode *inode) { return NULL; } #endif /* !CONFIG_FILE_LOCKING */ /* for walking lists of file_locks linked by fl_list */ #define for_each_file_lock(_fl, _head) list_for_each_entry(_fl, _head, c.flc_list) static inline int locks_lock_file_wait(struct file *filp, struct file_lock *fl) { return locks_lock_inode_wait(file_inode(filp), fl); } #ifdef CONFIG_FILE_LOCKING static inline int break_lease(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_LEASE); return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { /* * Since this check is lockless, we must ensure that any refcounts * taken are done before checking i_flctx->flc_lease. Otherwise, we * could end up racing with tasks trying to set a new lease on this * file. */ smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, mode, FL_DELEG); return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { int ret; ret = break_deleg(inode, O_WRONLY|O_NONBLOCK); if (ret == -EWOULDBLOCK && delegated_inode) { *delegated_inode = inode; ihold(inode); } return ret; } static inline int break_deleg_wait(struct inode **delegated_inode) { int ret; ret = break_deleg(*delegated_inode, O_WRONLY); iput(*delegated_inode); *delegated_inode = NULL; return ret; } static inline int break_layout(struct inode *inode, bool wait) { smp_mb(); if (inode->i_flctx && !list_empty_careful(&inode->i_flctx->flc_lease)) return __break_lease(inode, wait ? O_WRONLY : O_WRONLY | O_NONBLOCK, FL_LAYOUT); return 0; } #else /* !CONFIG_FILE_LOCKING */ static inline int break_lease(struct inode *inode, unsigned int mode) { return 0; } static inline int break_deleg(struct inode *inode, unsigned int mode) { return 0; } static inline int try_break_deleg(struct inode *inode, struct inode **delegated_inode) { return 0; } static inline int break_deleg_wait(struct inode **delegated_inode) { BUG(); return 0; } static inline int break_layout(struct inode *inode, bool wait) { return 0; } #endif /* CONFIG_FILE_LOCKING */ #endif /* _LINUX_FILELOCK_H */ |
| 40 40 117 117 117 117 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/kernel/exit.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/mm.h> #include <linux/slab.h> #include <linux/sched/autogroup.h> #include <linux/sched/mm.h> #include <linux/sched/stat.h> #include <linux/sched/task.h> #include <linux/sched/task_stack.h> #include <linux/sched/cputime.h> #include <linux/interrupt.h> #include <linux/module.h> #include <linux/capability.h> #include <linux/completion.h> #include <linux/personality.h> #include <linux/tty.h> #include <linux/iocontext.h> #include <linux/key.h> #include <linux/cpu.h> #include <linux/acct.h> #include <linux/tsacct_kern.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/freezer.h> #include <linux/binfmts.h> #include <linux/nsproxy.h> #include <linux/pid_namespace.h> #include <linux/ptrace.h> #include <linux/profile.h> #include <linux/mount.h> #include <linux/proc_fs.h> #include <linux/kthread.h> #include <linux/mempolicy.h> #include <linux/taskstats_kern.h> #include <linux/delayacct.h> #include <linux/cgroup.h> #include <linux/syscalls.h> #include <linux/signal.h> #include <linux/posix-timers.h> #include <linux/cn_proc.h> #include <linux/mutex.h> #include <linux/futex.h> #include <linux/pipe_fs_i.h> #include <linux/audit.h> /* for audit_free() */ #include <linux/resource.h> #include <linux/task_io_accounting_ops.h> #include <linux/blkdev.h> #include <linux/task_work.h> #include <linux/fs_struct.h> #include <linux/init_task.h> #include <linux/perf_event.h> #include <trace/events/sched.h> #include <linux/hw_breakpoint.h> #include <linux/oom.h> #include <linux/writeback.h> #include <linux/shm.h> #include <linux/kcov.h> #include <linux/kmsan.h> #include <linux/random.h> #include <linux/rcuwait.h> #include <linux/compat.h> #include <linux/io_uring.h> #include <linux/kprobes.h> #include <linux/rethook.h> #include <linux/sysfs.h> #include <linux/user_events.h> #include <linux/uaccess.h> #include <uapi/linux/wait.h> #include <asm/unistd.h> #include <asm/mmu_context.h> #include "exit.h" /* * The default value should be high enough to not crash a system that randomly * crashes its kernel from time to time, but low enough to at least not permit * overflowing 32-bit refcounts or the ldsem writer count. */ static unsigned int oops_limit = 10000; #ifdef CONFIG_SYSCTL static struct ctl_table kern_exit_table[] = { { .procname = "oops_limit", .data = &oops_limit, .maxlen = sizeof(oops_limit), .mode = 0644, .proc_handler = proc_douintvec, }, }; static __init int kernel_exit_sysctls_init(void) { register_sysctl_init("kernel", kern_exit_table); return 0; } late_initcall(kernel_exit_sysctls_init); #endif static atomic_t oops_count = ATOMIC_INIT(0); #ifdef CONFIG_SYSFS static ssize_t oops_count_show(struct kobject *kobj, struct kobj_attribute *attr, char *page) { return sysfs_emit(page, "%d\n", atomic_read(&oops_count)); } static struct kobj_attribute oops_count_attr = __ATTR_RO(oops_count); static __init int kernel_exit_sysfs_init(void) { sysfs_add_file_to_group(kernel_kobj, &oops_count_attr.attr, NULL); return 0; } late_initcall(kernel_exit_sysfs_init); #endif static void __unhash_process(struct task_struct *p, bool group_dead) { nr_threads--; detach_pid(p, PIDTYPE_PID); if (group_dead) { detach_pid(p, PIDTYPE_TGID); detach_pid(p, PIDTYPE_PGID); detach_pid(p, PIDTYPE_SID); list_del_rcu(&p->tasks); list_del_init(&p->sibling); __this_cpu_dec(process_counts); } list_del_rcu(&p->thread_node); } /* * This function expects the tasklist_lock write-locked. */ static void __exit_signal(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; bool group_dead = thread_group_leader(tsk); struct sighand_struct *sighand; struct tty_struct *tty; u64 utime, stime; sighand = rcu_dereference_check(tsk->sighand, lockdep_tasklist_lock_is_held()); spin_lock(&sighand->siglock); #ifdef CONFIG_POSIX_TIMERS posix_cpu_timers_exit(tsk); if (group_dead) posix_cpu_timers_exit_group(tsk); #endif if (group_dead) { tty = sig->tty; sig->tty = NULL; } else { /* * If there is any task waiting for the group exit * then notify it: */ if (sig->notify_count > 0 && !--sig->notify_count) wake_up_process(sig->group_exec_task); if (tsk == sig->curr_target) sig->curr_target = next_thread(tsk); } add_device_randomness((const void*) &tsk->se.sum_exec_runtime, sizeof(unsigned long long)); /* * Accumulate here the counters for all threads as they die. We could * skip the group leader because it is the last user of signal_struct, * but we want to avoid the race with thread_group_cputime() which can * see the empty ->thread_head list. */ task_cputime(tsk, &utime, &stime); write_seqlock(&sig->stats_lock); sig->utime += utime; sig->stime += stime; sig->gtime += task_gtime(tsk); sig->min_flt += tsk->min_flt; sig->maj_flt += tsk->maj_flt; sig->nvcsw += tsk->nvcsw; sig->nivcsw += tsk->nivcsw; sig->inblock += task_io_get_inblock(tsk); sig->oublock += task_io_get_oublock(tsk); task_io_accounting_add(&sig->ioac, &tsk->ioac); sig->sum_sched_runtime += tsk->se.sum_exec_runtime; sig->nr_threads--; __unhash_process(tsk, group_dead); write_sequnlock(&sig->stats_lock); /* * Do this under ->siglock, we can race with another thread * doing sigqueue_free() if we have SIGQUEUE_PREALLOC signals. */ flush_sigqueue(&tsk->pending); tsk->sighand = NULL; spin_unlock(&sighand->siglock); __cleanup_sighand(sighand); clear_tsk_thread_flag(tsk, TIF_SIGPENDING); if (group_dead) { flush_sigqueue(&sig->shared_pending); tty_kref_put(tty); } } static void delayed_put_task_struct(struct rcu_head *rhp) { struct task_struct *tsk = container_of(rhp, struct task_struct, rcu); kprobe_flush_task(tsk); rethook_flush_task(tsk); perf_event_delayed_put(tsk); trace_sched_process_free(tsk); put_task_struct(tsk); } void put_task_struct_rcu_user(struct task_struct *task) { if (refcount_dec_and_test(&task->rcu_users)) call_rcu(&task->rcu, delayed_put_task_struct); } void __weak release_thread(struct task_struct *dead_task) { } void release_task(struct task_struct *p) { struct task_struct *leader; struct pid *thread_pid; int zap_leader; repeat: /* don't need to get the RCU readlock here - the process is dead and * can't be modifying its own credentials. But shut RCU-lockdep up */ rcu_read_lock(); dec_rlimit_ucounts(task_ucounts(p), UCOUNT_RLIMIT_NPROC, 1); rcu_read_unlock(); cgroup_release(p); write_lock_irq(&tasklist_lock); ptrace_release_task(p); thread_pid = get_pid(p->thread_pid); __exit_signal(p); /* * If we are the last non-leader member of the thread * group, and the leader is zombie, then notify the * group leader's parent process. (if it wants notification.) */ zap_leader = 0; leader = p->group_leader; if (leader != p && thread_group_empty(leader) && leader->exit_state == EXIT_ZOMBIE) { /* * If we were the last child thread and the leader has * exited already, and the leader's parent ignores SIGCHLD, * then we are the one who should release the leader. */ zap_leader = do_notify_parent(leader, leader->exit_signal); if (zap_leader) leader->exit_state = EXIT_DEAD; } write_unlock_irq(&tasklist_lock); seccomp_filter_release(p); proc_flush_pid(thread_pid); put_pid(thread_pid); release_thread(p); put_task_struct_rcu_user(p); p = leader; if (unlikely(zap_leader)) goto repeat; } int rcuwait_wake_up(struct rcuwait *w) { int ret = 0; struct task_struct *task; rcu_read_lock(); /* * Order condition vs @task, such that everything prior to the load * of @task is visible. This is the condition as to why the user called * rcuwait_wake() in the first place. Pairs with set_current_state() * barrier (A) in rcuwait_wait_event(). * * WAIT WAKE * [S] tsk = current [S] cond = true * MB (A) MB (B) * [L] cond [L] tsk */ smp_mb(); /* (B) */ task = rcu_dereference(w->task); if (task) ret = wake_up_process(task); rcu_read_unlock(); return ret; } EXPORT_SYMBOL_GPL(rcuwait_wake_up); /* * Determine if a process group is "orphaned", according to the POSIX * definition in 2.2.2.52. Orphaned process groups are not to be affected * by terminal-generated stop signals. Newly orphaned process groups are * to receive a SIGHUP and a SIGCONT. * * "I ask you, have you ever known what it is to be an orphan?" */ static int will_become_orphaned_pgrp(struct pid *pgrp, struct task_struct *ignored_task) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if ((p == ignored_task) || (p->exit_state && thread_group_empty(p)) || is_global_init(p->real_parent)) continue; if (task_pgrp(p->real_parent) != pgrp && task_session(p->real_parent) == task_session(p)) return 0; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return 1; } int is_current_pgrp_orphaned(void) { int retval; read_lock(&tasklist_lock); retval = will_become_orphaned_pgrp(task_pgrp(current), NULL); read_unlock(&tasklist_lock); return retval; } static bool has_stopped_jobs(struct pid *pgrp) { struct task_struct *p; do_each_pid_task(pgrp, PIDTYPE_PGID, p) { if (p->signal->flags & SIGNAL_STOP_STOPPED) return true; } while_each_pid_task(pgrp, PIDTYPE_PGID, p); return false; } /* * Check to see if any process groups have become orphaned as * a result of our exiting, and if they have any stopped jobs, * send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void kill_orphaned_pgrp(struct task_struct *tsk, struct task_struct *parent) { struct pid *pgrp = task_pgrp(tsk); struct task_struct *ignored_task = tsk; if (!parent) /* exit: our father is in a different pgrp than * we are and we were the only connection outside. */ parent = tsk->real_parent; else /* reparent: our child is in a different pgrp than * we are, and it was the only connection outside. */ ignored_task = NULL; if (task_pgrp(parent) != pgrp && task_session(parent) == task_session(tsk) && will_become_orphaned_pgrp(pgrp, ignored_task) && has_stopped_jobs(pgrp)) { __kill_pgrp_info(SIGHUP, SEND_SIG_PRIV, pgrp); __kill_pgrp_info(SIGCONT, SEND_SIG_PRIV, pgrp); } } static void coredump_task_exit(struct task_struct *tsk) { struct core_state *core_state; /* * Serialize with any possible pending coredump. * We must hold siglock around checking core_state * and setting PF_POSTCOREDUMP. The core-inducing thread * will increment ->nr_threads for each thread in the * group without PF_POSTCOREDUMP set. */ spin_lock_irq(&tsk->sighand->siglock); tsk->flags |= PF_POSTCOREDUMP; core_state = tsk->signal->core_state; spin_unlock_irq(&tsk->sighand->siglock); if (core_state) { struct core_thread self; self.task = current; if (self.task->flags & PF_SIGNALED) self.next = xchg(&core_state->dumper.next, &self); else self.task = NULL; /* * Implies mb(), the result of xchg() must be visible * to core_state->dumper. */ if (atomic_dec_and_test(&core_state->nr_threads)) complete(&core_state->startup); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE|TASK_FREEZABLE); if (!self.task) /* see coredump_finish() */ break; schedule(); } __set_current_state(TASK_RUNNING); } } #ifdef CONFIG_MEMCG /* * A task is exiting. If it owned this mm, find a new owner for the mm. */ void mm_update_next_owner(struct mm_struct *mm) { struct task_struct *c, *g, *p = current; retry: /* * If the exiting or execing task is not the owner, it's * someone else's problem. */ if (mm->owner != p) return; /* * The current owner is exiting/execing and there are no other * candidates. Do not leave the mm pointing to a possibly * freed task structure. */ if (atomic_read(&mm->mm_users) <= 1) { WRITE_ONCE(mm->owner, NULL); return; } read_lock(&tasklist_lock); /* * Search in the children */ list_for_each_entry(c, &p->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search in the siblings */ list_for_each_entry(c, &p->real_parent->children, sibling) { if (c->mm == mm) goto assign_new_owner; } /* * Search through everything else, we should not get here often. */ for_each_process(g) { if (g->flags & PF_KTHREAD) continue; for_each_thread(g, c) { if (c->mm == mm) goto assign_new_owner; if (c->mm) break; } } read_unlock(&tasklist_lock); /* * We found no owner yet mm_users > 1: this implies that we are * most likely racing with swapoff (try_to_unuse()) or /proc or * ptrace or page migration (get_task_mm()). Mark owner as NULL. */ WRITE_ONCE(mm->owner, NULL); return; assign_new_owner: BUG_ON(c == p); get_task_struct(c); /* * The task_lock protects c->mm from changing. * We always want mm->owner->mm == mm */ task_lock(c); /* * Delay read_unlock() till we have the task_lock() * to ensure that c does not slip away underneath us */ read_unlock(&tasklist_lock); if (c->mm != mm) { task_unlock(c); put_task_struct(c); goto retry; } WRITE_ONCE(mm->owner, c); lru_gen_migrate_mm(mm); task_unlock(c); put_task_struct(c); } #endif /* CONFIG_MEMCG */ /* * Turn us into a lazy TLB process if we * aren't already.. */ static void exit_mm(void) { struct mm_struct *mm = current->mm; exit_mm_release(current, mm); if (!mm) return; mmap_read_lock(mm); mmgrab_lazy_tlb(mm); BUG_ON(mm != current->active_mm); /* more a memory barrier than a real lock */ task_lock(current); /* * When a thread stops operating on an address space, the loop * in membarrier_private_expedited() may not observe that * tsk->mm, and the loop in membarrier_global_expedited() may * not observe a MEMBARRIER_STATE_GLOBAL_EXPEDITED * rq->membarrier_state, so those would not issue an IPI. * Membarrier requires a memory barrier after accessing * user-space memory, before clearing tsk->mm or the * rq->membarrier_state. */ smp_mb__after_spinlock(); local_irq_disable(); current->mm = NULL; membarrier_update_current_mm(NULL); enter_lazy_tlb(mm, current); local_irq_enable(); task_unlock(current); mmap_read_unlock(mm); mm_update_next_owner(mm); mmput(mm); if (test_thread_flag(TIF_MEMDIE)) exit_oom_victim(); } static struct task_struct *find_alive_thread(struct task_struct *p) { struct task_struct *t; for_each_thread(p, t) { if (!(t->flags & PF_EXITING)) return t; } return NULL; } static struct task_struct *find_child_reaper(struct task_struct *father, struct list_head *dead) __releases(&tasklist_lock) __acquires(&tasklist_lock) { struct pid_namespace *pid_ns = task_active_pid_ns(father); struct task_struct *reaper = pid_ns->child_reaper; struct task_struct *p, *n; if (likely(reaper != father)) return reaper; reaper = find_alive_thread(father); if (reaper) { pid_ns->child_reaper = reaper; return reaper; } write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } zap_pid_ns_processes(pid_ns); write_lock_irq(&tasklist_lock); return father; } /* * When we die, we re-parent all our children, and try to: * 1. give them to another thread in our thread group, if such a member exists * 2. give it to the first ancestor process which prctl'd itself as a * child_subreaper for its children (like a service manager) * 3. give it to the init process (PID 1) in our pid namespace */ static struct task_struct *find_new_reaper(struct task_struct *father, struct task_struct *child_reaper) { struct task_struct *thread, *reaper; thread = find_alive_thread(father); if (thread) return thread; if (father->signal->has_child_subreaper) { unsigned int ns_level = task_pid(father)->level; /* * Find the first ->is_child_subreaper ancestor in our pid_ns. * We can't check reaper != child_reaper to ensure we do not * cross the namespaces, the exiting parent could be injected * by setns() + fork(). * We check pid->level, this is slightly more efficient than * task_active_pid_ns(reaper) != task_active_pid_ns(father). */ for (reaper = father->real_parent; task_pid(reaper)->level == ns_level; reaper = reaper->real_parent) { if (reaper == &init_task) break; if (!reaper->signal->is_child_subreaper) continue; thread = find_alive_thread(reaper); if (thread) return thread; } } return child_reaper; } /* * Any that need to be release_task'd are put on the @dead list. */ static void reparent_leader(struct task_struct *father, struct task_struct *p, struct list_head *dead) { if (unlikely(p->exit_state == EXIT_DEAD)) return; /* We don't want people slaying init. */ p->exit_signal = SIGCHLD; /* If it has exited notify the new parent about this child's death. */ if (!p->ptrace && p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) { if (do_notify_parent(p, p->exit_signal)) { p->exit_state = EXIT_DEAD; list_add(&p->ptrace_entry, dead); } } kill_orphaned_pgrp(p, father); } /* * This does two things: * * A. Make init inherit all the child processes * B. Check to see if any process groups have become orphaned * as a result of our exiting, and if they have any stopped * jobs, send them a SIGHUP and then a SIGCONT. (POSIX 3.2.2.2) */ static void forget_original_parent(struct task_struct *father, struct list_head *dead) { struct task_struct *p, *t, *reaper; if (unlikely(!list_empty(&father->ptraced))) exit_ptrace(father, dead); /* Can drop and reacquire tasklist_lock */ reaper = find_child_reaper(father, dead); if (list_empty(&father->children)) return; reaper = find_new_reaper(father, reaper); list_for_each_entry(p, &father->children, sibling) { for_each_thread(p, t) { RCU_INIT_POINTER(t->real_parent, reaper); BUG_ON((!t->ptrace) != (rcu_access_pointer(t->parent) == father)); if (likely(!t->ptrace)) t->parent = t->real_parent; if (t->pdeath_signal) group_send_sig_info(t->pdeath_signal, SEND_SIG_NOINFO, t, PIDTYPE_TGID); } /* * If this is a threaded reparent there is no need to * notify anyone anything has happened. */ if (!same_thread_group(reaper, father)) reparent_leader(father, p, dead); } list_splice_tail_init(&father->children, &reaper->children); } /* * Send signals to all our closest relatives so that they know * to properly mourn us.. */ static void exit_notify(struct task_struct *tsk, int group_dead) { bool autoreap; struct task_struct *p, *n; LIST_HEAD(dead); write_lock_irq(&tasklist_lock); forget_original_parent(tsk, &dead); if (group_dead) kill_orphaned_pgrp(tsk->group_leader, NULL); tsk->exit_state = EXIT_ZOMBIE; /* * sub-thread or delay_group_leader(), wake up the * PIDFD_THREAD waiters. */ if (!thread_group_empty(tsk)) do_notify_pidfd(tsk); if (unlikely(tsk->ptrace)) { int sig = thread_group_leader(tsk) && thread_group_empty(tsk) && !ptrace_reparented(tsk) ? tsk->exit_signal : SIGCHLD; autoreap = do_notify_parent(tsk, sig); } else if (thread_group_leader(tsk)) { autoreap = thread_group_empty(tsk) && do_notify_parent(tsk, tsk->exit_signal); } else { autoreap = true; } if (autoreap) { tsk->exit_state = EXIT_DEAD; list_add(&tsk->ptrace_entry, &dead); } /* mt-exec, de_thread() is waiting for group leader */ if (unlikely(tsk->signal->notify_count < 0)) wake_up_process(tsk->signal->group_exec_task); write_unlock_irq(&tasklist_lock); list_for_each_entry_safe(p, n, &dead, ptrace_entry) { list_del_init(&p->ptrace_entry); release_task(p); } } #ifdef CONFIG_DEBUG_STACK_USAGE static void check_stack_usage(void) { static DEFINE_SPINLOCK(low_water_lock); static int lowest_to_date = THREAD_SIZE; unsigned long free; free = stack_not_used(current); if (free >= lowest_to_date) return; spin_lock(&low_water_lock); if (free < lowest_to_date) { pr_info("%s (%d) used greatest stack depth: %lu bytes left\n", current->comm, task_pid_nr(current), free); lowest_to_date = free; } spin_unlock(&low_water_lock); } #else static inline void check_stack_usage(void) {} #endif static void synchronize_group_exit(struct task_struct *tsk, long code) { struct sighand_struct *sighand = tsk->sighand; struct signal_struct *signal = tsk->signal; spin_lock_irq(&sighand->siglock); signal->quick_threads--; if ((signal->quick_threads == 0) && !(signal->flags & SIGNAL_GROUP_EXIT)) { signal->flags = SIGNAL_GROUP_EXIT; signal->group_exit_code = code; signal->group_stop_count = 0; } spin_unlock_irq(&sighand->siglock); } void __noreturn do_exit(long code) { struct task_struct *tsk = current; int group_dead; WARN_ON(irqs_disabled()); synchronize_group_exit(tsk, code); WARN_ON(tsk->plug); kcov_task_exit(tsk); kmsan_task_exit(tsk); coredump_task_exit(tsk); ptrace_event(PTRACE_EVENT_EXIT, code); user_events_exit(tsk); io_uring_files_cancel(); exit_signals(tsk); /* sets PF_EXITING */ acct_update_integrals(tsk); group_dead = atomic_dec_and_test(&tsk->signal->live); if (group_dead) { /* * If the last thread of global init has exited, panic * immediately to get a useable coredump. */ if (unlikely(is_global_init(tsk))) panic("Attempted to kill init! exitcode=0x%08x\n", tsk->signal->group_exit_code ?: (int)code); #ifdef CONFIG_POSIX_TIMERS hrtimer_cancel(&tsk->signal->real_timer); exit_itimers(tsk); #endif if (tsk->mm) setmax_mm_hiwater_rss(&tsk->signal->maxrss, tsk->mm); } acct_collect(code, group_dead); if (group_dead) tty_audit_exit(); audit_free(tsk); tsk->exit_code = code; taskstats_exit(tsk, group_dead); exit_mm(); if (group_dead) acct_process(); trace_sched_process_exit(tsk); exit_sem(tsk); exit_shm(tsk); exit_files(tsk); exit_fs(tsk); if (group_dead) disassociate_ctty(1); exit_task_namespaces(tsk); exit_task_work(tsk); exit_thread(tsk); /* * Flush inherited counters to the parent - before the parent * gets woken up by child-exit notifications. * * because of cgroup mode, must be called before cgroup_exit() */ perf_event_exit_task(tsk); sched_autogroup_exit_task(tsk); cgroup_exit(tsk); /* * FIXME: do that only when needed, using sched_exit tracepoint */ flush_ptrace_hw_breakpoint(tsk); exit_tasks_rcu_start(); exit_notify(tsk, group_dead); proc_exit_connector(tsk); mpol_put_task_policy(tsk); #ifdef CONFIG_FUTEX if (unlikely(current->pi_state_cache)) kfree(current->pi_state_cache); #endif /* * Make sure we are holding no locks: */ debug_check_no_locks_held(); if (tsk->io_context) exit_io_context(tsk); if (tsk->splice_pipe) free_pipe_info(tsk->splice_pipe); if (tsk->task_frag.page) put_page(tsk->task_frag.page); exit_task_stack_account(tsk); check_stack_usage(); preempt_disable(); if (tsk->nr_dirtied) __this_cpu_add(dirty_throttle_leaks, tsk->nr_dirtied); exit_rcu(); exit_tasks_rcu_finish(); lockdep_free_task(tsk); do_task_dead(); } void __noreturn make_task_dead(int signr) { /* * Take the task off the cpu after something catastrophic has * happened. * * We can get here from a kernel oops, sometimes with preemption off. * Start by checking for critical errors. * Then fix up important state like USER_DS and preemption. * Then do everything else. */ struct task_struct *tsk = current; unsigned int limit; if (unlikely(in_interrupt())) panic("Aiee, killing interrupt handler!"); if (unlikely(!tsk->pid)) panic("Attempted to kill the idle task!"); if (unlikely(irqs_disabled())) { pr_info("note: %s[%d] exited with irqs disabled\n", current->comm, task_pid_nr(current)); local_irq_enable(); } if (unlikely(in_atomic())) { pr_info("note: %s[%d] exited with preempt_count %d\n", current->comm, task_pid_nr(current), preempt_count()); preempt_count_set(PREEMPT_ENABLED); } /* * Every time the system oopses, if the oops happens while a reference * to an object was held, the reference leaks. * If the oops doesn't also leak memory, repeated oopsing can cause * reference counters to wrap around (if they're not using refcount_t). * This means that repeated oopsing can make unexploitable-looking bugs * exploitable through repeated oopsing. * To make sure this can't happen, place an upper bound on how often the * kernel may oops without panic(). */ limit = READ_ONCE(oops_limit); if (atomic_inc_return(&oops_count) >= limit && limit) panic("Oopsed too often (kernel.oops_limit is %d)", limit); /* * We're taking recursive faults here in make_task_dead. Safest is to just * leave this task alone and wait for reboot. */ if (unlikely(tsk->flags & PF_EXITING)) { pr_alert("Fixing recursive fault but reboot is needed!\n"); futex_exit_recursive(tsk); tsk->exit_state = EXIT_DEAD; refcount_inc(&tsk->rcu_users); do_task_dead(); } do_exit(signr); } SYSCALL_DEFINE1(exit, int, error_code) { do_exit((error_code&0xff)<<8); } /* * Take down every thread in the group. This is called by fatal signals * as well as by sys_exit_group (below). */ void __noreturn do_group_exit(int exit_code) { struct signal_struct *sig = current->signal; if (sig->flags & SIGNAL_GROUP_EXIT) exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; else { struct sighand_struct *const sighand = current->sighand; spin_lock_irq(&sighand->siglock); if (sig->flags & SIGNAL_GROUP_EXIT) /* Another thread got here before we took the lock. */ exit_code = sig->group_exit_code; else if (sig->group_exec_task) exit_code = 0; else { sig->group_exit_code = exit_code; sig->flags = SIGNAL_GROUP_EXIT; zap_other_threads(current); } spin_unlock_irq(&sighand->siglock); } do_exit(exit_code); /* NOTREACHED */ } /* * this kills every thread in the thread group. Note that any externally * wait4()-ing process will get the correct exit code - even if this * thread is not the thread group leader. */ SYSCALL_DEFINE1(exit_group, int, error_code) { do_group_exit((error_code & 0xff) << 8); /* NOTREACHED */ return 0; } static int eligible_pid(struct wait_opts *wo, struct task_struct *p) { return wo->wo_type == PIDTYPE_MAX || task_pid_type(p, wo->wo_type) == wo->wo_pid; } static int eligible_child(struct wait_opts *wo, bool ptrace, struct task_struct *p) { if (!eligible_pid(wo, p)) return 0; /* * Wait for all children (clone and not) if __WALL is set or * if it is traced by us. */ if (ptrace || (wo->wo_flags & __WALL)) return 1; /* * Otherwise, wait for clone children *only* if __WCLONE is set; * otherwise, wait for non-clone children *only*. * * Note: a "clone" child here is one that reports to its parent * using a signal other than SIGCHLD, or a non-leader thread which * we can only see if it is traced by us. */ if ((p->exit_signal != SIGCHLD) ^ !!(wo->wo_flags & __WCLONE)) return 0; return 1; } /* * Handle sys_wait4 work for one task in state EXIT_ZOMBIE. We hold * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_zombie(struct wait_opts *wo, struct task_struct *p) { int state, status; pid_t pid = task_pid_vnr(p); uid_t uid = from_kuid_munged(current_user_ns(), task_uid(p)); struct waitid_info *infop; if (!likely(wo->wo_flags & WEXITED)) return 0; if (unlikely(wo->wo_flags & WNOWAIT)) { status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); goto out_info; } /* * Move the task's state to DEAD/TRACE, only one thread can do this. */ state = (ptrace_reparented(p) && thread_group_leader(p)) ? EXIT_TRACE : EXIT_DEAD; if (cmpxchg(&p->exit_state, EXIT_ZOMBIE, state) != EXIT_ZOMBIE) return 0; /* * We own this thread, nobody else can reap it. */ read_unlock(&tasklist_lock); sched_annotate_sleep(); /* * Check thread_group_leader() to exclude the traced sub-threads. */ if (state == EXIT_DEAD && thread_group_leader(p)) { struct signal_struct *sig = p->signal; struct signal_struct *psig = current->signal; unsigned long maxrss; u64 tgutime, tgstime; /* * The resource counters for the group leader are in its * own task_struct. Those for dead threads in the group * are in its signal_struct, as are those for the child * processes it has previously reaped. All these * accumulate in the parent's signal_struct c* fields. * * We don't bother to take a lock here to protect these * p->signal fields because the whole thread group is dead * and nobody can change them. * * psig->stats_lock also protects us from our sub-threads * which can reap other children at the same time. * * We use thread_group_cputime_adjusted() to get times for * the thread group, which consolidates times for all threads * in the group including the group leader. */ thread_group_cputime_adjusted(p, &tgutime, &tgstime); write_seqlock_irq(&psig->stats_lock); psig->cutime += tgutime + sig->cutime; psig->cstime += tgstime + sig->cstime; psig->cgtime += task_gtime(p) + sig->gtime + sig->cgtime; psig->cmin_flt += p->min_flt + sig->min_flt + sig->cmin_flt; psig->cmaj_flt += p->maj_flt + sig->maj_flt + sig->cmaj_flt; psig->cnvcsw += p->nvcsw + sig->nvcsw + sig->cnvcsw; psig->cnivcsw += p->nivcsw + sig->nivcsw + sig->cnivcsw; psig->cinblock += task_io_get_inblock(p) + sig->inblock + sig->cinblock; psig->coublock += task_io_get_oublock(p) + sig->oublock + sig->coublock; maxrss = max(sig->maxrss, sig->cmaxrss); if (psig->cmaxrss < maxrss) psig->cmaxrss = maxrss; task_io_accounting_add(&psig->ioac, &p->ioac); task_io_accounting_add(&psig->ioac, &sig->ioac); write_sequnlock_irq(&psig->stats_lock); } if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); status = (p->signal->flags & SIGNAL_GROUP_EXIT) ? p->signal->group_exit_code : p->exit_code; wo->wo_stat = status; if (state == EXIT_TRACE) { write_lock_irq(&tasklist_lock); /* We dropped tasklist, ptracer could die and untrace */ ptrace_unlink(p); /* If parent wants a zombie, don't release it now */ state = EXIT_ZOMBIE; if (do_notify_parent(p, p->exit_signal)) state = EXIT_DEAD; p->exit_state = state; write_unlock_irq(&tasklist_lock); } if (state == EXIT_DEAD) release_task(p); out_info: infop = wo->wo_info; if (infop) { if ((status & 0x7f) == 0) { infop->cause = CLD_EXITED; infop->status = status >> 8; } else { infop->cause = (status & 0x80) ? CLD_DUMPED : CLD_KILLED; infop->status = status & 0x7f; } infop->pid = pid; infop->uid = uid; } return pid; } static int *task_stopped_code(struct task_struct *p, bool ptrace) { if (ptrace) { if (task_is_traced(p) && !(p->jobctl & JOBCTL_LISTENING)) return &p->exit_code; } else { if (p->signal->flags & SIGNAL_STOP_STOPPED) return &p->signal->group_exit_code; } return NULL; } /** * wait_task_stopped - Wait for %TASK_STOPPED or %TASK_TRACED * @wo: wait options * @ptrace: is the wait for ptrace * @p: task to wait for * * Handle sys_wait4() work for %p in state %TASK_STOPPED or %TASK_TRACED. * * CONTEXT: * read_lock(&tasklist_lock), which is released if return value is * non-zero. Also, grabs and releases @p->sighand->siglock. * * RETURNS: * 0 if wait condition didn't exist and search for other wait conditions * should continue. Non-zero return, -errno on failure and @p's pid on * success, implies that tasklist_lock is released and wait condition * search should terminate. */ static int wait_task_stopped(struct wait_opts *wo, int ptrace, struct task_struct *p) { struct waitid_info *infop; int exit_code, *p_code, why; uid_t uid = 0; /* unneeded, required by compiler */ pid_t pid; /* * Traditionally we see ptrace'd stopped tasks regardless of options. */ if (!ptrace && !(wo->wo_flags & WUNTRACED)) return 0; if (!task_stopped_code(p, ptrace)) return 0; exit_code = 0; spin_lock_irq(&p->sighand->siglock); p_code = task_stopped_code(p, ptrace); if (unlikely(!p_code)) goto unlock_sig; exit_code = *p_code; if (!exit_code) goto unlock_sig; if (!unlikely(wo->wo_flags & WNOWAIT)) *p_code = 0; uid = from_kuid_munged(current_user_ns(), task_uid(p)); unlock_sig: spin_unlock_irq(&p->sighand->siglock); if (!exit_code) return 0; /* * Now we are pretty sure this task is interesting. * Make sure it doesn't get reaped out from under us while we * give up the lock and then examine it below. We don't want to * keep holding onto the tasklist_lock while we call getrusage and * possibly take page faults for user memory. */ get_task_struct(p); pid = task_pid_vnr(p); why = ptrace ? CLD_TRAPPED : CLD_STOPPED; read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); if (likely(!(wo->wo_flags & WNOWAIT))) wo->wo_stat = (exit_code << 8) | 0x7f; infop = wo->wo_info; if (infop) { infop->cause = why; infop->status = exit_code; infop->pid = pid; infop->uid = uid; } return pid; } /* * Handle do_wait work for one task in a live, non-stopped state. * read_lock(&tasklist_lock) on entry. If we return zero, we still hold * the lock and this task is uninteresting. If we return nonzero, we have * released the lock and the system call should return. */ static int wait_task_continued(struct wait_opts *wo, struct task_struct *p) { struct waitid_info *infop; pid_t pid; uid_t uid; if (!unlikely(wo->wo_flags & WCONTINUED)) return 0; if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) return 0; spin_lock_irq(&p->sighand->siglock); /* Re-check with the lock held. */ if (!(p->signal->flags & SIGNAL_STOP_CONTINUED)) { spin_unlock_irq(&p->sighand->siglock); return 0; } if (!unlikely(wo->wo_flags & WNOWAIT)) p->signal->flags &= ~SIGNAL_STOP_CONTINUED; uid = from_kuid_munged(current_user_ns(), task_uid(p)); spin_unlock_irq(&p->sighand->siglock); pid = task_pid_vnr(p); get_task_struct(p); read_unlock(&tasklist_lock); sched_annotate_sleep(); if (wo->wo_rusage) getrusage(p, RUSAGE_BOTH, wo->wo_rusage); put_task_struct(p); infop = wo->wo_info; if (!infop) { wo->wo_stat = 0xffff; } else { infop->cause = CLD_CONTINUED; infop->pid = pid; infop->uid = uid; infop->status = SIGCONT; } return pid; } /* * Consider @p for a wait by @parent. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; * then ->notask_error is 0 if @p is an eligible child, * or still -ECHILD. */ static int wait_consider_task(struct wait_opts *wo, int ptrace, struct task_struct *p) { /* * We can race with wait_task_zombie() from another thread. * Ensure that EXIT_ZOMBIE -> EXIT_DEAD/EXIT_TRACE transition * can't confuse the checks below. */ int exit_state = READ_ONCE(p->exit_state); int ret; if (unlikely(exit_state == EXIT_DEAD)) return 0; ret = eligible_child(wo, ptrace, p); if (!ret) return ret; if (unlikely(exit_state == EXIT_TRACE)) { /* * ptrace == 0 means we are the natural parent. In this case * we should clear notask_error, debugger will notify us. */ if (likely(!ptrace)) wo->notask_error = 0; return 0; } if (likely(!ptrace) && unlikely(p->ptrace)) { /* * If it is traced by its real parent's group, just pretend * the caller is ptrace_do_wait() and reap this child if it * is zombie. * * This also hides group stop state from real parent; otherwise * a single stop can be reported twice as group and ptrace stop. * If a ptracer wants to distinguish these two events for its * own children it should create a separate process which takes * the role of real parent. */ if (!ptrace_reparented(p)) ptrace = 1; } /* slay zombie? */ if (exit_state == EXIT_ZOMBIE) { /* we don't reap group leaders with subthreads */ if (!delay_group_leader(p)) { /* * A zombie ptracee is only visible to its ptracer. * Notification and reaping will be cascaded to the * real parent when the ptracer detaches. */ if (unlikely(ptrace) || likely(!p->ptrace)) return wait_task_zombie(wo, p); } /* * Allow access to stopped/continued state via zombie by * falling through. Clearing of notask_error is complex. * * When !@ptrace: * * If WEXITED is set, notask_error should naturally be * cleared. If not, subset of WSTOPPED|WCONTINUED is set, * so, if there are live subthreads, there are events to * wait for. If all subthreads are dead, it's still safe * to clear - this function will be called again in finite * amount time once all the subthreads are released and * will then return without clearing. * * When @ptrace: * * Stopped state is per-task and thus can't change once the * target task dies. Only continued and exited can happen. * Clear notask_error if WCONTINUED | WEXITED. */ if (likely(!ptrace) || (wo->wo_flags & (WCONTINUED | WEXITED))) wo->notask_error = 0; } else { /* * @p is alive and it's gonna stop, continue or exit, so * there always is something to wait for. */ wo->notask_error = 0; } /* * Wait for stopped. Depending on @ptrace, different stopped state * is used and the two don't interact with each other. */ ret = wait_task_stopped(wo, ptrace, p); if (ret) return ret; /* * Wait for continued. There's only one continued state and the * ptracer can consume it which can confuse the real parent. Don't * use WCONTINUED from ptracer. You don't need or want it. */ return wait_task_continued(wo, p); } /* * Do the work of do_wait() for one thread in the group, @tsk. * * -ECHILD should be in ->notask_error before the first call. * Returns nonzero for a final return, when we have unlocked tasklist_lock. * Returns zero if the search for a child should continue; then * ->notask_error is 0 if there were any eligible children, * or still -ECHILD. */ static int do_wait_thread(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->children, sibling) { int ret = wait_consider_task(wo, 0, p); if (ret) return ret; } return 0; } static int ptrace_do_wait(struct wait_opts *wo, struct task_struct *tsk) { struct task_struct *p; list_for_each_entry(p, &tsk->ptraced, ptrace_entry) { int ret = wait_consider_task(wo, 1, p); if (ret) return ret; } return 0; } bool pid_child_should_wake(struct wait_opts *wo, struct task_struct *p) { if (!eligible_pid(wo, p)) return false; if ((wo->wo_flags & __WNOTHREAD) && wo->child_wait.private != p->parent) return false; return true; } static int child_wait_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { struct wait_opts *wo = container_of(wait, struct wait_opts, child_wait); struct task_struct *p = key; if (pid_child_should_wake(wo, p)) return default_wake_function(wait, mode, sync, key); return 0; } void __wake_up_parent(struct task_struct *p, struct task_struct *parent) { __wake_up_sync_key(&parent->signal->wait_chldexit, TASK_INTERRUPTIBLE, p); } static bool is_effectively_child(struct wait_opts *wo, bool ptrace, struct task_struct *target) { struct task_struct *parent = !ptrace ? target->real_parent : target->parent; return current == parent || (!(wo->wo_flags & __WNOTHREAD) && same_thread_group(current, parent)); } /* * Optimization for waiting on PIDTYPE_PID. No need to iterate through child * and tracee lists to find the target task. */ static int do_wait_pid(struct wait_opts *wo) { bool ptrace; struct task_struct *target; int retval; ptrace = false; target = pid_task(wo->wo_pid, PIDTYPE_TGID); if (target && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } ptrace = true; target = pid_task(wo->wo_pid, PIDTYPE_PID); if (target && target->ptrace && is_effectively_child(wo, ptrace, target)) { retval = wait_consider_task(wo, ptrace, target); if (retval) return retval; } return 0; } long __do_wait(struct wait_opts *wo) { long retval; /* * If there is nothing that can match our criteria, just get out. * We will clear ->notask_error to zero if we see any child that * might later match our criteria, even if we are not able to reap * it yet. */ wo->notask_error = -ECHILD; if ((wo->wo_type < PIDTYPE_MAX) && (!wo->wo_pid || !pid_has_task(wo->wo_pid, wo->wo_type))) goto notask; read_lock(&tasklist_lock); if (wo->wo_type == PIDTYPE_PID) { retval = do_wait_pid(wo); if (retval) return retval; } else { struct task_struct *tsk = current; do { retval = do_wait_thread(wo, tsk); if (retval) return retval; retval = ptrace_do_wait(wo, tsk); if (retval) return retval; if (wo->wo_flags & __WNOTHREAD) break; } while_each_thread(current, tsk); } read_unlock(&tasklist_lock); notask: retval = wo->notask_error; if (!retval && !(wo->wo_flags & WNOHANG)) return -ERESTARTSYS; return retval; } static long do_wait(struct wait_opts *wo) { int retval; trace_sched_process_wait(wo->wo_pid); init_waitqueue_func_entry(&wo->child_wait, child_wait_callback); wo->child_wait.private = current; add_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); do { set_current_state(TASK_INTERRUPTIBLE); retval = __do_wait(wo); if (retval != -ERESTARTSYS) break; if (signal_pending(current)) break; schedule(); } while (1); __set_current_state(TASK_RUNNING); remove_wait_queue(¤t->signal->wait_chldexit, &wo->child_wait); return retval; } int kernel_waitid_prepare(struct wait_opts *wo, int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { unsigned int f_flags = 0; struct pid *pid = NULL; enum pid_type type; if (options & ~(WNOHANG|WNOWAIT|WEXITED|WSTOPPED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; if (!(options & (WEXITED|WSTOPPED|WCONTINUED))) return -EINVAL; switch (which) { case P_ALL: type = PIDTYPE_MAX; break; case P_PID: type = PIDTYPE_PID; if (upid <= 0) return -EINVAL; pid = find_get_pid(upid); break; case P_PGID: type = PIDTYPE_PGID; if (upid < 0) return -EINVAL; if (upid) pid = find_get_pid(upid); else pid = get_task_pid(current, PIDTYPE_PGID); break; case P_PIDFD: type = PIDTYPE_PID; if (upid < 0) return -EINVAL; pid = pidfd_get_pid(upid, &f_flags); if (IS_ERR(pid)) return PTR_ERR(pid); break; default: return -EINVAL; } wo->wo_type = type; wo->wo_pid = pid; wo->wo_flags = options; wo->wo_info = infop; wo->wo_rusage = ru; if (f_flags & O_NONBLOCK) wo->wo_flags |= WNOHANG; return 0; } static long kernel_waitid(int which, pid_t upid, struct waitid_info *infop, int options, struct rusage *ru) { struct wait_opts wo; long ret; ret = kernel_waitid_prepare(&wo, which, upid, infop, options, ru); if (ret) return ret; ret = do_wait(&wo); if (!ret && !(options & WNOHANG) && (wo.wo_flags & WNOHANG)) ret = -EAGAIN; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE5(waitid, int, which, pid_t, upid, struct siginfo __user *, infop, int, options, struct rusage __user *, ru) { struct rusage r; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, upid, &info, options, ru ? &r : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } long kernel_wait4(pid_t upid, int __user *stat_addr, int options, struct rusage *ru) { struct wait_opts wo; struct pid *pid = NULL; enum pid_type type; long ret; if (options & ~(WNOHANG|WUNTRACED|WCONTINUED| __WNOTHREAD|__WCLONE|__WALL)) return -EINVAL; /* -INT_MIN is not defined */ if (upid == INT_MIN) return -ESRCH; if (upid == -1) type = PIDTYPE_MAX; else if (upid < 0) { type = PIDTYPE_PGID; pid = find_get_pid(-upid); } else if (upid == 0) { type = PIDTYPE_PGID; pid = get_task_pid(current, PIDTYPE_PGID); } else /* upid > 0 */ { type = PIDTYPE_PID; pid = find_get_pid(upid); } wo.wo_type = type; wo.wo_pid = pid; wo.wo_flags = options | WEXITED; wo.wo_info = NULL; wo.wo_stat = 0; wo.wo_rusage = ru; ret = do_wait(&wo); put_pid(pid); if (ret > 0 && stat_addr && put_user(wo.wo_stat, stat_addr)) ret = -EFAULT; return ret; } int kernel_wait(pid_t pid, int *stat) { struct wait_opts wo = { .wo_type = PIDTYPE_PID, .wo_pid = find_get_pid(pid), .wo_flags = WEXITED, }; int ret; ret = do_wait(&wo); if (ret > 0 && wo.wo_stat) *stat = wo.wo_stat; put_pid(wo.wo_pid); return ret; } SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr, int, options, struct rusage __user *, ru) { struct rusage r; long err = kernel_wait4(upid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && copy_to_user(ru, &r, sizeof(struct rusage))) return -EFAULT; } return err; } #ifdef __ARCH_WANT_SYS_WAITPID /* * sys_waitpid() remains for compatibility. waitpid() should be * implemented by calling sys_wait4() from libc.a. */ SYSCALL_DEFINE3(waitpid, pid_t, pid, int __user *, stat_addr, int, options) { return kernel_wait4(pid, stat_addr, options, NULL); } #endif #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE4(wait4, compat_pid_t, pid, compat_uint_t __user *, stat_addr, int, options, struct compat_rusage __user *, ru) { struct rusage r; long err = kernel_wait4(pid, stat_addr, options, ru ? &r : NULL); if (err > 0) { if (ru && put_compat_rusage(&r, ru)) return -EFAULT; } return err; } COMPAT_SYSCALL_DEFINE5(waitid, int, which, compat_pid_t, pid, struct compat_siginfo __user *, infop, int, options, struct compat_rusage __user *, uru) { struct rusage ru; struct waitid_info info = {.status = 0}; long err = kernel_waitid(which, pid, &info, options, uru ? &ru : NULL); int signo = 0; if (err > 0) { signo = SIGCHLD; err = 0; if (uru) { /* kernel_waitid() overwrites everything in ru */ if (COMPAT_USE_64BIT_TIME) err = copy_to_user(uru, &ru, sizeof(ru)); else err = put_compat_rusage(&ru, uru); if (err) return -EFAULT; } } if (!infop) return err; if (!user_write_access_begin(infop, sizeof(*infop))) return -EFAULT; unsafe_put_user(signo, &infop->si_signo, Efault); unsafe_put_user(0, &infop->si_errno, Efault); unsafe_put_user(info.cause, &infop->si_code, Efault); unsafe_put_user(info.pid, &infop->si_pid, Efault); unsafe_put_user(info.uid, &infop->si_uid, Efault); unsafe_put_user(info.status, &infop->si_status, Efault); user_write_access_end(); return err; Efault: user_write_access_end(); return -EFAULT; } #endif /* * This needs to be __function_aligned as GCC implicitly makes any * implementation of abort() cold and drops alignment specified by * -falign-functions=N. * * See https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88345#c11 */ __weak __function_aligned void abort(void) { BUG(); /* if that doesn't kill us, halt */ panic("Oops failed to kill thread"); } EXPORT_SYMBOL(abort); |
| 65 65 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * linux/fs/exec.c * * Copyright (C) 1991, 1992 Linus Torvalds */ /* * #!-checking implemented by tytso. */ /* * Demand-loading implemented 01.12.91 - no need to read anything but * the header into memory. The inode of the executable is put into * "current->executable", and page faults do the actual loading. Clean. * * Once more I can proudly say that linux stood up to being changed: it * was less than 2 hours work to get demand-loading completely implemented. * * Demand loading changed July 1993 by Eric Youngdale. Use mmap instead, * current->executable is only used by the procfs. This allows a dispatch * table to check for several different types of binary formats. We keep * trying until we recognize the file or we run out of supported binary * formats. */ #include <linux/kernel_read_file.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/mm.h> #include <linux/stat.h> #include <linux/fcntl.h> #include <linux/swap.h> #include <linux/string.h> #include <linux/init.h> #include <linux/sched/mm.h> #include <linux/sched/coredump.h> #include <linux/sched/signal.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/task.h> #include <linux/pagemap.h> #include <linux/perf_event.h> #include <linux/highmem.h> #include <linux/spinlock.h> #include <linux/key.h> #include <linux/personality.h> #include <linux/binfmts.h> #include <linux/utsname.h> #include <linux/pid_namespace.h> #include <linux/module.h> #include <linux/namei.h> #include <linux/mount.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/tsacct_kern.h> #include <linux/cn_proc.h> #include <linux/audit.h> #include <linux/kmod.h> #include <linux/fsnotify.h> #include <linux/fs_struct.h> #include <linux/oom.h> #include <linux/compat.h> #include <linux/vmalloc.h> #include <linux/io_uring.h> #include <linux/syscall_user_dispatch.h> #include <linux/coredump.h> #include <linux/time_namespace.h> #include <linux/user_events.h> #include <linux/rseq.h> #include <linux/ksm.h> #include <linux/uaccess.h> #include <asm/mmu_context.h> #include <asm/tlb.h> #include <trace/events/task.h> #include "internal.h" #include <trace/events/sched.h> static int bprm_creds_from_file(struct linux_binprm *bprm); int suid_dumpable = 0; static LIST_HEAD(formats); static DEFINE_RWLOCK(binfmt_lock); void __register_binfmt(struct linux_binfmt * fmt, int insert) { write_lock(&binfmt_lock); insert ? list_add(&fmt->lh, &formats) : list_add_tail(&fmt->lh, &formats); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(__register_binfmt); void unregister_binfmt(struct linux_binfmt * fmt) { write_lock(&binfmt_lock); list_del(&fmt->lh); write_unlock(&binfmt_lock); } EXPORT_SYMBOL(unregister_binfmt); static inline void put_binfmt(struct linux_binfmt * fmt) { module_put(fmt->module); } bool path_noexec(const struct path *path) { return (path->mnt->mnt_flags & MNT_NOEXEC) || (path->mnt->mnt_sb->s_iflags & SB_I_NOEXEC); } #ifdef CONFIG_USELIB /* * Note that a shared library must be both readable and executable due to * security reasons. * * Also note that we take the address to load from the file itself. */ SYSCALL_DEFINE1(uselib, const char __user *, library) { struct linux_binfmt *fmt; struct file *file; struct filename *tmp = getname(library); int error = PTR_ERR(tmp); static const struct open_flags uselib_flags = { .open_flag = O_LARGEFILE | O_RDONLY, .acc_mode = MAY_READ | MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if (IS_ERR(tmp)) goto out; file = do_filp_open(AT_FDCWD, tmp, &uselib_flags); putname(tmp); error = PTR_ERR(file); if (IS_ERR(file)) goto out; /* * may_open() has already checked for this, so it should be * impossible to trip now. But we need to be extra cautious * and check again at the very end too. */ error = -EACCES; if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || path_noexec(&file->f_path))) goto exit; error = -ENOEXEC; read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!fmt->load_shlib) continue; if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); error = fmt->load_shlib(file); read_lock(&binfmt_lock); put_binfmt(fmt); if (error != -ENOEXEC) break; } read_unlock(&binfmt_lock); exit: fput(file); out: return error; } #endif /* #ifdef CONFIG_USELIB */ #ifdef CONFIG_MMU /* * The nascent bprm->mm is not visible until exec_mmap() but it can * use a lot of memory, account these pages in current->mm temporary * for oom_badness()->get_mm_rss(). Once exec succeeds or fails, we * change the counter back via acct_arg_size(0). */ static void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { struct mm_struct *mm = current->mm; long diff = (long)(pages - bprm->vma_pages); if (!mm || !diff) return; bprm->vma_pages = pages; add_mm_counter(mm, MM_ANONPAGES, diff); } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; struct vm_area_struct *vma = bprm->vma; struct mm_struct *mm = bprm->mm; int ret; /* * Avoid relying on expanding the stack down in GUP (which * does not work for STACK_GROWSUP anyway), and just do it * by hand ahead of time. */ if (write && pos < vma->vm_start) { mmap_write_lock(mm); ret = expand_downwards(vma, pos); if (unlikely(ret < 0)) { mmap_write_unlock(mm); return NULL; } mmap_write_downgrade(mm); } else mmap_read_lock(mm); /* * We are doing an exec(). 'current' is the process * doing the exec and 'mm' is the new process's mm. */ ret = get_user_pages_remote(mm, pos, 1, write ? FOLL_WRITE : 0, &page, NULL); mmap_read_unlock(mm); if (ret <= 0) return NULL; if (write) acct_arg_size(bprm, vma_pages(vma)); return page; } static void put_arg_page(struct page *page) { put_page(page); } static void free_arg_pages(struct linux_binprm *bprm) { } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { flush_cache_page(bprm->vma, pos, page_to_pfn(page)); } static int __bprm_mm_init(struct linux_binprm *bprm) { int err; struct vm_area_struct *vma = NULL; struct mm_struct *mm = bprm->mm; bprm->vma = vma = vm_area_alloc(mm); if (!vma) return -ENOMEM; vma_set_anonymous(vma); if (mmap_write_lock_killable(mm)) { err = -EINTR; goto err_free; } /* * Need to be called with mmap write lock * held, to avoid race with ksmd. */ err = ksm_execve(mm); if (err) goto err_ksm; /* * Place the stack at the largest stack address the architecture * supports. Later, we'll move this to an appropriate place. We don't * use STACK_TOP because that can depend on attributes which aren't * configured yet. */ BUILD_BUG_ON(VM_STACK_FLAGS & VM_STACK_INCOMPLETE_SETUP); vma->vm_end = STACK_TOP_MAX; vma->vm_start = vma->vm_end - PAGE_SIZE; vm_flags_init(vma, VM_SOFTDIRTY | VM_STACK_FLAGS | VM_STACK_INCOMPLETE_SETUP); vma->vm_page_prot = vm_get_page_prot(vma->vm_flags); err = insert_vm_struct(mm, vma); if (err) goto err; mm->stack_vm = mm->total_vm = 1; mmap_write_unlock(mm); bprm->p = vma->vm_end - sizeof(void *); return 0; err: ksm_exit(mm); err_ksm: mmap_write_unlock(mm); err_free: bprm->vma = NULL; vm_area_free(vma); return err; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= MAX_ARG_STRLEN; } #else static inline void acct_arg_size(struct linux_binprm *bprm, unsigned long pages) { } static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos, int write) { struct page *page; page = bprm->page[pos / PAGE_SIZE]; if (!page && write) { page = alloc_page(GFP_HIGHUSER|__GFP_ZERO); if (!page) return NULL; bprm->page[pos / PAGE_SIZE] = page; } return page; } static void put_arg_page(struct page *page) { } static void free_arg_page(struct linux_binprm *bprm, int i) { if (bprm->page[i]) { __free_page(bprm->page[i]); bprm->page[i] = NULL; } } static void free_arg_pages(struct linux_binprm *bprm) { int i; for (i = 0; i < MAX_ARG_PAGES; i++) free_arg_page(bprm, i); } static void flush_arg_page(struct linux_binprm *bprm, unsigned long pos, struct page *page) { } static int __bprm_mm_init(struct linux_binprm *bprm) { bprm->p = PAGE_SIZE * MAX_ARG_PAGES - sizeof(void *); return 0; } static bool valid_arg_len(struct linux_binprm *bprm, long len) { return len <= bprm->p; } #endif /* CONFIG_MMU */ /* * Create a new mm_struct and populate it with a temporary stack * vm_area_struct. We don't have enough context at this point to set the stack * flags, permissions, and offset, so we use temporary values. We'll update * them later in setup_arg_pages(). */ static int bprm_mm_init(struct linux_binprm *bprm) { int err; struct mm_struct *mm = NULL; bprm->mm = mm = mm_alloc(); err = -ENOMEM; if (!mm) goto err; /* Save current stack limit for all calculations made during exec. */ task_lock(current->group_leader); bprm->rlim_stack = current->signal->rlim[RLIMIT_STACK]; task_unlock(current->group_leader); err = __bprm_mm_init(bprm); if (err) goto err; return 0; err: if (mm) { bprm->mm = NULL; mmdrop(mm); } return err; } struct user_arg_ptr { #ifdef CONFIG_COMPAT bool is_compat; #endif union { const char __user *const __user *native; #ifdef CONFIG_COMPAT const compat_uptr_t __user *compat; #endif } ptr; }; static const char __user *get_user_arg_ptr(struct user_arg_ptr argv, int nr) { const char __user *native; #ifdef CONFIG_COMPAT if (unlikely(argv.is_compat)) { compat_uptr_t compat; if (get_user(compat, argv.ptr.compat + nr)) return ERR_PTR(-EFAULT); return compat_ptr(compat); } #endif if (get_user(native, argv.ptr.native + nr)) return ERR_PTR(-EFAULT); return native; } /* * count() counts the number of strings in array ARGV. */ static int count(struct user_arg_ptr argv, int max) { int i = 0; if (argv.ptr.native != NULL) { for (;;) { const char __user *p = get_user_arg_ptr(argv, i); if (!p) break; if (IS_ERR(p)) return -EFAULT; if (i >= max) return -E2BIG; ++i; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } } return i; } static int count_strings_kernel(const char *const *argv) { int i; if (!argv) return 0; for (i = 0; argv[i]; ++i) { if (i >= MAX_ARG_STRINGS) return -E2BIG; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return i; } static int bprm_stack_limits(struct linux_binprm *bprm) { unsigned long limit, ptr_size; /* * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM * (whichever is smaller) for the argv+env strings. * This ensures that: * - the remaining binfmt code will not run out of stack space, * - the program will have a reasonable amount of stack left * to work from. */ limit = _STK_LIM / 4 * 3; limit = min(limit, bprm->rlim_stack.rlim_cur / 4); /* * We've historically supported up to 32 pages (ARG_MAX) * of argument strings even with small stacks */ limit = max_t(unsigned long, limit, ARG_MAX); /* * We must account for the size of all the argv and envp pointers to * the argv and envp strings, since they will also take up space in * the stack. They aren't stored until much later when we can't * signal to the parent that the child has run out of stack space. * Instead, calculate it here so it's possible to fail gracefully. * * In the case of argc = 0, make sure there is space for adding a * empty string (which will bump argc to 1), to ensure confused * userspace programs don't start processing from argv[1], thinking * argc can never be 0, to keep them from walking envp by accident. * See do_execveat_common(). */ ptr_size = (max(bprm->argc, 1) + bprm->envc) * sizeof(void *); if (limit <= ptr_size) return -E2BIG; limit -= ptr_size; bprm->argmin = bprm->p - limit; return 0; } /* * 'copy_strings()' copies argument/environment strings from the old * processes's memory to the new process's stack. The call to get_user_pages() * ensures the destination page is created and not swapped out. */ static int copy_strings(int argc, struct user_arg_ptr argv, struct linux_binprm *bprm) { struct page *kmapped_page = NULL; char *kaddr = NULL; unsigned long kpos = 0; int ret; while (argc-- > 0) { const char __user *str; int len; unsigned long pos; ret = -EFAULT; str = get_user_arg_ptr(argv, argc); if (IS_ERR(str)) goto out; len = strnlen_user(str, MAX_ARG_STRLEN); if (!len) goto out; ret = -E2BIG; if (!valid_arg_len(bprm, len)) goto out; /* We're going to work our way backwards. */ pos = bprm->p; str += len; bprm->p -= len; #ifdef CONFIG_MMU if (bprm->p < bprm->argmin) goto out; #endif while (len > 0) { int offset, bytes_to_copy; if (fatal_signal_pending(current)) { ret = -ERESTARTNOHAND; goto out; } cond_resched(); offset = pos % PAGE_SIZE; if (offset == 0) offset = PAGE_SIZE; bytes_to_copy = offset; if (bytes_to_copy > len) bytes_to_copy = len; offset -= bytes_to_copy; pos -= bytes_to_copy; str -= bytes_to_copy; len -= bytes_to_copy; if (!kmapped_page || kpos != (pos & PAGE_MASK)) { struct page *page; page = get_arg_page(bprm, pos, 1); if (!page) { ret = -E2BIG; goto out; } if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } kmapped_page = page; kaddr = kmap_local_page(kmapped_page); kpos = pos & PAGE_MASK; flush_arg_page(bprm, kpos, kmapped_page); } if (copy_from_user(kaddr+offset, str, bytes_to_copy)) { ret = -EFAULT; goto out; } } } ret = 0; out: if (kmapped_page) { flush_dcache_page(kmapped_page); kunmap_local(kaddr); put_arg_page(kmapped_page); } return ret; } /* * Copy and argument/environment string from the kernel to the processes stack. */ int copy_string_kernel(const char *arg, struct linux_binprm *bprm) { int len = strnlen(arg, MAX_ARG_STRLEN) + 1 /* terminating NUL */; unsigned long pos = bprm->p; if (len == 0) return -EFAULT; if (!valid_arg_len(bprm, len)) return -E2BIG; /* We're going to work our way backwards. */ arg += len; bprm->p -= len; if (IS_ENABLED(CONFIG_MMU) && bprm->p < bprm->argmin) return -E2BIG; while (len > 0) { unsigned int bytes_to_copy = min_t(unsigned int, len, min_not_zero(offset_in_page(pos), PAGE_SIZE)); struct page *page; pos -= bytes_to_copy; arg -= bytes_to_copy; len -= bytes_to_copy; page = get_arg_page(bprm, pos, 1); if (!page) return -E2BIG; flush_arg_page(bprm, pos & PAGE_MASK, page); memcpy_to_page(page, offset_in_page(pos), arg, bytes_to_copy); put_arg_page(page); } return 0; } EXPORT_SYMBOL(copy_string_kernel); static int copy_strings_kernel(int argc, const char *const *argv, struct linux_binprm *bprm) { while (argc-- > 0) { int ret = copy_string_kernel(argv[argc], bprm); if (ret < 0) return ret; if (fatal_signal_pending(current)) return -ERESTARTNOHAND; cond_resched(); } return 0; } #ifdef CONFIG_MMU /* * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX. Once * the binfmt code determines where the new stack should reside, we shift it to * its final location. The process proceeds as follows: * * 1) Use shift to calculate the new vma endpoints. * 2) Extend vma to cover both the old and new ranges. This ensures the * arguments passed to subsequent functions are consistent. * 3) Move vma's page tables to the new range. * 4) Free up any cleared pgd range. * 5) Shrink the vma to cover only the new range. */ static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift) { struct mm_struct *mm = vma->vm_mm; unsigned long old_start = vma->vm_start; unsigned long old_end = vma->vm_end; unsigned long length = old_end - old_start; unsigned long new_start = old_start - shift; unsigned long new_end = old_end - shift; VMA_ITERATOR(vmi, mm, new_start); struct vm_area_struct *next; struct mmu_gather tlb; BUG_ON(new_start > new_end); /* * ensure there are no vmas between where we want to go * and where we are */ if (vma != vma_next(&vmi)) return -EFAULT; vma_iter_prev_range(&vmi); /* * cover the whole range: [new_start, old_end) */ if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL)) return -ENOMEM; /* * move the page tables downwards, on failure we rely on * process cleanup to remove whatever mess we made. */ if (length != move_page_tables(vma, old_start, vma, new_start, length, false, true)) return -ENOMEM; lru_add_drain(); tlb_gather_mmu(&tlb, mm); next = vma_next(&vmi); if (new_end > old_start) { /* * when the old and new regions overlap clear from new_end. */ free_pgd_range(&tlb, new_end, old_end, new_end, next ? next->vm_start : USER_PGTABLES_CEILING); } else { /* * otherwise, clean from old_start; this is done to not touch * the address space in [new_end, old_start) some architectures * have constraints on va-space that make this illegal (IA64) - * for the others its just a little faster. */ free_pgd_range(&tlb, old_start, old_end, new_end, next ? next->vm_start : USER_PGTABLES_CEILING); } tlb_finish_mmu(&tlb); vma_prev(&vmi); /* Shrink the vma to just the new range */ return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff); } /* * Finalizes the stack vm_area_struct. The flags and permissions are updated, * the stack is optionally relocated, and some extra space is added. */ int setup_arg_pages(struct linux_binprm *bprm, unsigned long stack_top, int executable_stack) { unsigned long ret; unsigned long stack_shift; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = bprm->vma; struct vm_area_struct *prev = NULL; unsigned long vm_flags; unsigned long stack_base; unsigned long stack_size; unsigned long stack_expand; unsigned long rlim_stack; struct mmu_gather tlb; struct vma_iterator vmi; #ifdef CONFIG_STACK_GROWSUP /* Limit stack size */ stack_base = bprm->rlim_stack.rlim_max; stack_base = calc_max_stack_size(stack_base); /* Add space for stack randomization. */ stack_base += (STACK_RND_MASK << PAGE_SHIFT); /* Make sure we didn't let the argument array grow too large. */ if (vma->vm_end - vma->vm_start > stack_base) return -ENOMEM; stack_base = PAGE_ALIGN(stack_top - stack_base); stack_shift = vma->vm_start - stack_base; mm->arg_start = bprm->p - stack_shift; bprm->p = vma->vm_end - stack_shift; #else stack_top = arch_align_stack(stack_top); stack_top = PAGE_ALIGN(stack_top); if (unlikely(stack_top < mmap_min_addr) || unlikely(vma->vm_end - vma->vm_start >= stack_top - mmap_min_addr)) return -ENOMEM; stack_shift = vma->vm_end - stack_top; bprm->p -= stack_shift; mm->arg_start = bprm->p; #endif if (bprm->loader) bprm->loader -= stack_shift; bprm->exec -= stack_shift; if (mmap_write_lock_killable(mm)) return -EINTR; vm_flags = VM_STACK_FLAGS; /* * Adjust stack execute permissions; explicitly enable for * EXSTACK_ENABLE_X, disable for EXSTACK_DISABLE_X and leave alone * (arch default) otherwise. */ if (unlikely(executable_stack == EXSTACK_ENABLE_X)) vm_flags |= VM_EXEC; else if (executable_stack == EXSTACK_DISABLE_X) vm_flags &= ~VM_EXEC; vm_flags |= mm->def_flags; vm_flags |= VM_STACK_INCOMPLETE_SETUP; vma_iter_init(&vmi, mm, vma->vm_start); tlb_gather_mmu(&tlb, mm); ret = mprotect_fixup(&vmi, &tlb, vma, &prev, vma->vm_start, vma->vm_end, vm_flags); tlb_finish_mmu(&tlb); if (ret) goto out_unlock; BUG_ON(prev != vma); if (unlikely(vm_flags & VM_EXEC)) { pr_warn_once("process '%pD4' started with executable stack\n", bprm->file); } /* Move stack pages down in memory. */ if (stack_shift) { ret = shift_arg_pages(vma, stack_shift); if (ret) goto out_unlock; } /* mprotect_fixup is overkill to remove the temporary stack flags */ vm_flags_clear(vma, VM_STACK_INCOMPLETE_SETUP); stack_expand = 131072UL; /* randomly 32*4k (or 2*64k) pages */ stack_size = vma->vm_end - vma->vm_start; /* * Align this down to a page boundary as expand_stack * will align it up. */ rlim_stack = bprm->rlim_stack.rlim_cur & PAGE_MASK; stack_expand = min(rlim_stack, stack_size + stack_expand); #ifdef CONFIG_STACK_GROWSUP stack_base = vma->vm_start + stack_expand; #else stack_base = vma->vm_end - stack_expand; #endif current->mm->start_stack = bprm->p; ret = expand_stack_locked(vma, stack_base); if (ret) ret = -EFAULT; out_unlock: mmap_write_unlock(mm); return ret; } EXPORT_SYMBOL(setup_arg_pages); #else /* * Transfer the program arguments and environment from the holding pages * onto the stack. The provided stack pointer is adjusted accordingly. */ int transfer_args_to_stack(struct linux_binprm *bprm, unsigned long *sp_location) { unsigned long index, stop, sp; int ret = 0; stop = bprm->p >> PAGE_SHIFT; sp = *sp_location; for (index = MAX_ARG_PAGES - 1; index >= stop; index--) { unsigned int offset = index == stop ? bprm->p & ~PAGE_MASK : 0; char *src = kmap_local_page(bprm->page[index]) + offset; sp -= PAGE_SIZE - offset; if (copy_to_user((void *) sp, src, PAGE_SIZE - offset) != 0) ret = -EFAULT; kunmap_local(src); if (ret) goto out; } bprm->exec += *sp_location - MAX_ARG_PAGES * PAGE_SIZE; *sp_location = sp; out: return ret; } EXPORT_SYMBOL(transfer_args_to_stack); #endif /* CONFIG_MMU */ /* * On success, caller must call do_close_execat() on the returned * struct file to close it. */ static struct file *do_open_execat(int fd, struct filename *name, int flags) { struct file *file; int err; struct open_flags open_exec_flags = { .open_flag = O_LARGEFILE | O_RDONLY | __FMODE_EXEC, .acc_mode = MAY_EXEC, .intent = LOOKUP_OPEN, .lookup_flags = LOOKUP_FOLLOW, }; if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0) return ERR_PTR(-EINVAL); if (flags & AT_SYMLINK_NOFOLLOW) open_exec_flags.lookup_flags &= ~LOOKUP_FOLLOW; if (flags & AT_EMPTY_PATH) open_exec_flags.lookup_flags |= LOOKUP_EMPTY; file = do_filp_open(fd, name, &open_exec_flags); if (IS_ERR(file)) goto out; /* * may_open() has already checked for this, so it should be * impossible to trip now. But we need to be extra cautious * and check again at the very end too. */ err = -EACCES; if (WARN_ON_ONCE(!S_ISREG(file_inode(file)->i_mode) || path_noexec(&file->f_path))) goto exit; err = deny_write_access(file); if (err) goto exit; out: return file; exit: fput(file); return ERR_PTR(err); } /** * open_exec - Open a path name for execution * * @name: path name to open with the intent of executing it. * * Returns ERR_PTR on failure or allocated struct file on success. * * As this is a wrapper for the internal do_open_execat(), callers * must call allow_write_access() before fput() on release. Also see * do_close_execat(). */ struct file *open_exec(const char *name) { struct filename *filename = getname_kernel(name); struct file *f = ERR_CAST(filename); if (!IS_ERR(filename)) { f = do_open_execat(AT_FDCWD, filename, 0); putname(filename); } return f; } EXPORT_SYMBOL(open_exec); #if defined(CONFIG_BINFMT_FLAT) || defined(CONFIG_BINFMT_ELF_FDPIC) ssize_t read_code(struct file *file, unsigned long addr, loff_t pos, size_t len) { ssize_t res = vfs_read(file, (void __user *)addr, len, &pos); if (res > 0) flush_icache_user_range(addr, addr + len); return res; } EXPORT_SYMBOL(read_code); #endif /* * Maps the mm_struct mm into the current task struct. * On success, this function returns with exec_update_lock * held for writing. */ static int exec_mmap(struct mm_struct *mm) { struct task_struct *tsk; struct mm_struct *old_mm, *active_mm; int ret; /* Notify parent that we're no longer interested in the old VM */ tsk = current; old_mm = current->mm; exec_mm_release(tsk, old_mm); ret = down_write_killable(&tsk->signal->exec_update_lock); if (ret) return ret; if (old_mm) { /* * If there is a pending fatal signal perhaps a signal * whose default action is to create a coredump get * out and die instead of going through with the exec. */ ret = mmap_read_lock_killable(old_mm); if (ret) { up_write(&tsk->signal->exec_update_lock); return ret; } } task_lock(tsk); membarrier_exec_mmap(mm); local_irq_disable(); active_mm = tsk->active_mm; tsk->active_mm = mm; tsk->mm = mm; mm_init_cid(mm); /* * This prevents preemption while active_mm is being loaded and * it and mm are being updated, which could cause problems for * lazy tlb mm refcounting when these are updated by context * switches. Not all architectures can handle irqs off over * activate_mm yet. */ if (!IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); activate_mm(active_mm, mm); if (IS_ENABLED(CONFIG_ARCH_WANT_IRQS_OFF_ACTIVATE_MM)) local_irq_enable(); lru_gen_add_mm(mm); task_unlock(tsk); lru_gen_use_mm(mm); if (old_mm) { mmap_read_unlock(old_mm); BUG_ON(active_mm != old_mm); setmax_mm_hiwater_rss(&tsk->signal->maxrss, old_mm); mm_update_next_owner(old_mm); mmput(old_mm); return 0; } mmdrop_lazy_tlb(active_mm); return 0; } static int de_thread(struct task_struct *tsk) { struct signal_struct *sig = tsk->signal; struct sighand_struct *oldsighand = tsk->sighand; spinlock_t *lock = &oldsighand->siglock; if (thread_group_empty(tsk)) goto no_thread_group; /* * Kill all other threads in the thread group. */ spin_lock_irq(lock); if ((sig->flags & SIGNAL_GROUP_EXIT) || sig->group_exec_task) { /* * Another group action in progress, just * return so that the signal is processed. */ spin_unlock_irq(lock); return -EAGAIN; } sig->group_exec_task = tsk; sig->notify_count = zap_other_threads(tsk); if (!thread_group_leader(tsk)) sig->notify_count--; while (sig->notify_count) { __set_current_state(TASK_KILLABLE); spin_unlock_irq(lock); schedule(); if (__fatal_signal_pending(tsk)) goto killed; spin_lock_irq(lock); } spin_unlock_irq(lock); /* * At this point all other threads have exited, all we have to * do is to wait for the thread group leader to become inactive, * and to assume its PID: */ if (!thread_group_leader(tsk)) { struct task_struct *leader = tsk->group_leader; for (;;) { cgroup_threadgroup_change_begin(tsk); write_lock_irq(&tasklist_lock); /* * Do this under tasklist_lock to ensure that * exit_notify() can't miss ->group_exec_task */ sig->notify_count = -1; if (likely(leader->exit_state)) break; __set_current_state(TASK_KILLABLE); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); schedule(); if (__fatal_signal_pending(tsk)) goto killed; } /* * The only record we have of the real-time age of a * process, regardless of execs it's done, is start_time. * All the past CPU time is accumulated in signal_struct * from sister threads now dead. But in this non-leader * exec, nothing survives from the original leader thread, * whose birth marks the true age of this process now. * When we take on its identity by switching to its PID, we * also take its birthdate (always earlier than our own). */ tsk->start_time = leader->start_time; tsk->start_boottime = leader->start_boottime; BUG_ON(!same_thread_group(leader, tsk)); /* * An exec() starts a new thread group with the * TGID of the previous thread group. Rehash the * two threads with a switched PID, and release * the former thread group leader: */ /* Become a process group leader with the old leader's pid. * The old leader becomes a thread of the this thread group. */ exchange_tids(tsk, leader); transfer_pid(leader, tsk, PIDTYPE_TGID); transfer_pid(leader, tsk, PIDTYPE_PGID); transfer_pid(leader, tsk, PIDTYPE_SID); list_replace_rcu(&leader->tasks, &tsk->tasks); list_replace_init(&leader->sibling, &tsk->sibling); tsk->group_leader = tsk; leader->group_leader = tsk; tsk->exit_signal = SIGCHLD; leader->exit_signal = -1; BUG_ON(leader->exit_state != EXIT_ZOMBIE); leader->exit_state = EXIT_DEAD; /* * We are going to release_task()->ptrace_unlink() silently, * the tracer can sleep in do_wait(). EXIT_DEAD guarantees * the tracer won't block again waiting for this thread. */ if (unlikely(leader->ptrace)) __wake_up_parent(leader, leader->parent); write_unlock_irq(&tasklist_lock); cgroup_threadgroup_change_end(tsk); release_task(leader); } sig->group_exec_task = NULL; sig->notify_count = 0; no_thread_group: /* we have changed execution domain */ tsk->exit_signal = SIGCHLD; BUG_ON(!thread_group_leader(tsk)); return 0; killed: /* protects against exit_notify() and __exit_signal() */ read_lock(&tasklist_lock); sig->group_exec_task = NULL; sig->notify_count = 0; read_unlock(&tasklist_lock); return -EAGAIN; } /* * This function makes sure the current process has its own signal table, * so that flush_signal_handlers can later reset the handlers without * disturbing other processes. (Other processes might share the signal * table via the CLONE_SIGHAND option to clone().) */ static int unshare_sighand(struct task_struct *me) { struct sighand_struct *oldsighand = me->sighand; if (refcount_read(&oldsighand->count) != 1) { struct sighand_struct *newsighand; /* * This ->sighand is shared with the CLONE_SIGHAND * but not CLONE_THREAD task, switch to the new one. */ newsighand = kmem_cache_alloc(sighand_cachep, GFP_KERNEL); if (!newsighand) return -ENOMEM; refcount_set(&newsighand->count, 1); write_lock_irq(&tasklist_lock); spin_lock(&oldsighand->siglock); memcpy(newsighand->action, oldsighand->action, sizeof(newsighand->action)); rcu_assign_pointer(me->sighand, newsighand); spin_unlock(&oldsighand->siglock); write_unlock_irq(&tasklist_lock); __cleanup_sighand(oldsighand); } return 0; } char *__get_task_comm(char *buf, size_t buf_size, struct task_struct *tsk) { task_lock(tsk); /* Always NUL terminated and zero-padded */ strscpy_pad(buf, tsk->comm, buf_size); task_unlock(tsk); return buf; } EXPORT_SYMBOL_GPL(__get_task_comm); /* * These functions flushes out all traces of the currently running executable * so that a new one can be started */ void __set_task_comm(struct task_struct *tsk, const char *buf, bool exec) { task_lock(tsk); trace_task_rename(tsk, buf); strscpy_pad(tsk->comm, buf, sizeof(tsk->comm)); task_unlock(tsk); perf_event_comm(tsk, exec); } /* * Calling this is the point of no return. None of the failures will be * seen by userspace since either the process is already taking a fatal * signal (via de_thread() or coredump), or will have SEGV raised * (after exec_mmap()) by search_binary_handler (see below). */ int begin_new_exec(struct linux_binprm * bprm) { struct task_struct *me = current; int retval; /* Once we are committed compute the creds */ retval = bprm_creds_from_file(bprm); if (retval) return retval; /* * This tracepoint marks the point before flushing the old exec where * the current task is still unchanged, but errors are fatal (point of * no return). The later "sched_process_exec" tracepoint is called after * the current task has successfully switched to the new exec. */ trace_sched_prepare_exec(current, bprm); /* * Ensure all future errors are fatal. */ bprm->point_of_no_return = true; /* * Make this the only thread in the thread group. */ retval = de_thread(me); if (retval) goto out; /* * Cancel any io_uring activity across execve */ io_uring_task_cancel(); /* Ensure the files table is not shared. */ retval = unshare_files(); if (retval) goto out; /* * Must be called _before_ exec_mmap() as bprm->mm is * not visible until then. Doing it here also ensures * we don't race against replace_mm_exe_file(). */ retval = set_mm_exe_file(bprm->mm, bprm->file); if (retval) goto out; /* If the binary is not readable then enforce mm->dumpable=0 */ would_dump(bprm, bprm->file); if (bprm->have_execfd) would_dump(bprm, bprm->executable); /* * Release all of the old mmap stuff */ acct_arg_size(bprm, 0); retval = exec_mmap(bprm->mm); if (retval) goto out; bprm->mm = NULL; retval = exec_task_namespaces(); if (retval) goto out_unlock; #ifdef CONFIG_POSIX_TIMERS spin_lock_irq(&me->sighand->siglock); posix_cpu_timers_exit(me); spin_unlock_irq(&me->sighand->siglock); exit_itimers(me); flush_itimer_signals(); #endif /* * Make the signal table private. */ retval = unshare_sighand(me); if (retval) goto out_unlock; me->flags &= ~(PF_RANDOMIZE | PF_FORKNOEXEC | PF_NOFREEZE | PF_NO_SETAFFINITY); flush_thread(); me->personality &= ~bprm->per_clear; clear_syscall_work_syscall_user_dispatch(me); /* * We have to apply CLOEXEC before we change whether the process is * dumpable (in setup_new_exec) to avoid a race with a process in userspace * trying to access the should-be-closed file descriptors of a process * undergoing exec(2). */ do_close_on_exec(me->files); if (bprm->secureexec) { /* Make sure parent cannot signal privileged process. */ me->pdeath_signal = 0; /* * For secureexec, reset the stack limit to sane default to * avoid bad behavior from the prior rlimits. This has to * happen before arch_pick_mmap_layout(), which examines * RLIMIT_STACK, but after the point of no return to avoid * needing to clean up the change on failure. */ if (bprm->rlim_stack.rlim_cur > _STK_LIM) bprm->rlim_stack.rlim_cur = _STK_LIM; } me->sas_ss_sp = me->sas_ss_size = 0; /* * Figure out dumpability. Note that this checking only of current * is wrong, but userspace depends on it. This should be testing * bprm->secureexec instead. */ if (bprm->interp_flags & BINPRM_FLAGS_ENFORCE_NONDUMP || !(uid_eq(current_euid(), current_uid()) && gid_eq(current_egid(), current_gid()))) set_dumpable(current->mm, suid_dumpable); else set_dumpable(current->mm, SUID_DUMP_USER); perf_event_exec(); __set_task_comm(me, kbasename(bprm->filename), true); /* An exec changes our domain. We are no longer part of the thread group */ WRITE_ONCE(me->self_exec_id, me->self_exec_id + 1); flush_signal_handlers(me, 0); retval = set_cred_ucounts(bprm->cred); if (retval < 0) goto out_unlock; /* * install the new credentials for this executable */ security_bprm_committing_creds(bprm); commit_creds(bprm->cred); bprm->cred = NULL; /* * Disable monitoring for regular users * when executing setuid binaries. Must * wait until new credentials are committed * by commit_creds() above */ if (get_dumpable(me->mm) != SUID_DUMP_USER) perf_event_exit_task(me); /* * cred_guard_mutex must be held at least to this point to prevent * ptrace_attach() from altering our determination of the task's * credentials; any time after this it may be unlocked. */ security_bprm_committed_creds(bprm); /* Pass the opened binary to the interpreter. */ if (bprm->have_execfd) { retval = get_unused_fd_flags(0); if (retval < 0) goto out_unlock; fd_install(retval, bprm->executable); bprm->executable = NULL; bprm->execfd = retval; } return 0; out_unlock: up_write(&me->signal->exec_update_lock); if (!bprm->cred) mutex_unlock(&me->signal->cred_guard_mutex); out: return retval; } EXPORT_SYMBOL(begin_new_exec); void would_dump(struct linux_binprm *bprm, struct file *file) { struct inode *inode = file_inode(file); struct mnt_idmap *idmap = file_mnt_idmap(file); if (inode_permission(idmap, inode, MAY_READ) < 0) { struct user_namespace *old, *user_ns; bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; /* Ensure mm->user_ns contains the executable */ user_ns = old = bprm->mm->user_ns; while ((user_ns != &init_user_ns) && !privileged_wrt_inode_uidgid(user_ns, idmap, inode)) user_ns = user_ns->parent; if (old != user_ns) { bprm->mm->user_ns = get_user_ns(user_ns); put_user_ns(old); } } } EXPORT_SYMBOL(would_dump); void setup_new_exec(struct linux_binprm * bprm) { /* Setup things that can depend upon the personality */ struct task_struct *me = current; arch_pick_mmap_layout(me->mm, &bprm->rlim_stack); arch_setup_new_exec(); /* Set the new mm task size. We have to do that late because it may * depend on TIF_32BIT which is only updated in flush_thread() on * some architectures like powerpc */ me->mm->task_size = TASK_SIZE; up_write(&me->signal->exec_update_lock); mutex_unlock(&me->signal->cred_guard_mutex); } EXPORT_SYMBOL(setup_new_exec); /* Runs immediately before start_thread() takes over. */ void finalize_exec(struct linux_binprm *bprm) { /* Store any stack rlimit changes before starting thread. */ task_lock(current->group_leader); current->signal->rlim[RLIMIT_STACK] = bprm->rlim_stack; task_unlock(current->group_leader); } EXPORT_SYMBOL(finalize_exec); /* * Prepare credentials and lock ->cred_guard_mutex. * setup_new_exec() commits the new creds and drops the lock. * Or, if exec fails before, free_bprm() should release ->cred * and unlock. */ static int prepare_bprm_creds(struct linux_binprm *bprm) { if (mutex_lock_interruptible(¤t->signal->cred_guard_mutex)) return -ERESTARTNOINTR; bprm->cred = prepare_exec_creds(); if (likely(bprm->cred)) return 0; mutex_unlock(¤t->signal->cred_guard_mutex); return -ENOMEM; } /* Matches do_open_execat() */ static void do_close_execat(struct file *file) { if (!file) return; allow_write_access(file); fput(file); } static void free_bprm(struct linux_binprm *bprm) { if (bprm->mm) { acct_arg_size(bprm, 0); mmput(bprm->mm); } free_arg_pages(bprm); if (bprm->cred) { mutex_unlock(¤t->signal->cred_guard_mutex); abort_creds(bprm->cred); } do_close_execat(bprm->file); if (bprm->executable) fput(bprm->executable); /* If a binfmt changed the interp, free it. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); kfree(bprm->fdpath); kfree(bprm); } static struct linux_binprm *alloc_bprm(int fd, struct filename *filename, int flags) { struct linux_binprm *bprm; struct file *file; int retval = -ENOMEM; file = do_open_execat(fd, filename, flags); if (IS_ERR(file)) return ERR_CAST(file); bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) { do_close_execat(file); return ERR_PTR(-ENOMEM); } bprm->file = file; if (fd == AT_FDCWD || filename->name[0] == '/') { bprm->filename = filename->name; } else { if (filename->name[0] == '\0') bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d", fd); else bprm->fdpath = kasprintf(GFP_KERNEL, "/dev/fd/%d/%s", fd, filename->name); if (!bprm->fdpath) goto out_free; /* * Record that a name derived from an O_CLOEXEC fd will be * inaccessible after exec. This allows the code in exec to * choose to fail when the executable is not mmaped into the * interpreter and an open file descriptor is not passed to * the interpreter. This makes for a better user experience * than having the interpreter start and then immediately fail * when it finds the executable is inaccessible. */ if (get_close_on_exec(fd)) bprm->interp_flags |= BINPRM_FLAGS_PATH_INACCESSIBLE; bprm->filename = bprm->fdpath; } bprm->interp = bprm->filename; retval = bprm_mm_init(bprm); if (!retval) return bprm; out_free: free_bprm(bprm); return ERR_PTR(retval); } int bprm_change_interp(const char *interp, struct linux_binprm *bprm) { /* If a binfmt changed the interp, free it first. */ if (bprm->interp != bprm->filename) kfree(bprm->interp); bprm->interp = kstrdup(interp, GFP_KERNEL); if (!bprm->interp) return -ENOMEM; return 0; } EXPORT_SYMBOL(bprm_change_interp); /* * determine how safe it is to execute the proposed program * - the caller must hold ->cred_guard_mutex to protect against * PTRACE_ATTACH or seccomp thread-sync */ static void check_unsafe_exec(struct linux_binprm *bprm) { struct task_struct *p = current, *t; unsigned n_fs; if (p->ptrace) bprm->unsafe |= LSM_UNSAFE_PTRACE; /* * This isn't strictly necessary, but it makes it harder for LSMs to * mess up. */ if (task_no_new_privs(current)) bprm->unsafe |= LSM_UNSAFE_NO_NEW_PRIVS; /* * If another task is sharing our fs, we cannot safely * suid exec because the differently privileged task * will be able to manipulate the current directory, etc. * It would be nice to force an unshare instead... */ n_fs = 1; spin_lock(&p->fs->lock); rcu_read_lock(); for_other_threads(p, t) { if (t->fs == p->fs) n_fs++; } rcu_read_unlock(); /* "users" and "in_exec" locked for copy_fs() */ if (p->fs->users > n_fs) bprm->unsafe |= LSM_UNSAFE_SHARE; else p->fs->in_exec = 1; spin_unlock(&p->fs->lock); } static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file) { /* Handle suid and sgid on files */ struct mnt_idmap *idmap; struct inode *inode = file_inode(file); unsigned int mode; vfsuid_t vfsuid; vfsgid_t vfsgid; if (!mnt_may_suid(file->f_path.mnt)) return; if (task_no_new_privs(current)) return; mode = READ_ONCE(inode->i_mode); if (!(mode & (S_ISUID|S_ISGID))) return; idmap = file_mnt_idmap(file); /* Be careful if suid/sgid is set */ inode_lock(inode); /* reload atomically mode/uid/gid now that lock held */ mode = inode->i_mode; vfsuid = i_uid_into_vfsuid(idmap, inode); vfsgid = i_gid_into_vfsgid(idmap, inode); inode_unlock(inode); /* We ignore suid/sgid if there are no mappings for them in the ns */ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) || !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid)) return; if (mode & S_ISUID) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->euid = vfsuid_into_kuid(vfsuid); } if ((mode & (S_ISGID | S_IXGRP)) == (S_ISGID | S_IXGRP)) { bprm->per_clear |= PER_CLEAR_ON_SETID; bprm->cred->egid = vfsgid_into_kgid(vfsgid); } } /* * Compute brpm->cred based upon the final binary. */ static int bprm_creds_from_file(struct linux_binprm *bprm) { /* Compute creds based on which file? */ struct file *file = bprm->execfd_creds ? bprm->executable : bprm->file; bprm_fill_uid(bprm, file); return security_bprm_creds_from_file(bprm, file); } /* * Fill the binprm structure from the inode. * Read the first BINPRM_BUF_SIZE bytes * * This may be called multiple times for binary chains (scripts for example). */ static int prepare_binprm(struct linux_binprm *bprm) { loff_t pos = 0; memset(bprm->buf, 0, BINPRM_BUF_SIZE); return kernel_read(bprm->file, bprm->buf, BINPRM_BUF_SIZE, &pos); } /* * Arguments are '\0' separated strings found at the location bprm->p * points to; chop off the first by relocating brpm->p to right after * the first '\0' encountered. */ int remove_arg_zero(struct linux_binprm *bprm) { unsigned long offset; char *kaddr; struct page *page; if (!bprm->argc) return 0; do { offset = bprm->p & ~PAGE_MASK; page = get_arg_page(bprm, bprm->p, 0); if (!page) return -EFAULT; kaddr = kmap_local_page(page); for (; offset < PAGE_SIZE && kaddr[offset]; offset++, bprm->p++) ; kunmap_local(kaddr); put_arg_page(page); } while (offset == PAGE_SIZE); bprm->p++; bprm->argc--; return 0; } EXPORT_SYMBOL(remove_arg_zero); #define printable(c) (((c)=='\t') || ((c)=='\n') || (0x20<=(c) && (c)<=0x7e)) /* * cycle the list of binary formats handler, until one recognizes the image */ static int search_binary_handler(struct linux_binprm *bprm) { bool need_retry = IS_ENABLED(CONFIG_MODULES); struct linux_binfmt *fmt; int retval; retval = prepare_binprm(bprm); if (retval < 0) return retval; retval = security_bprm_check(bprm); if (retval) return retval; retval = -ENOENT; retry: read_lock(&binfmt_lock); list_for_each_entry(fmt, &formats, lh) { if (!try_module_get(fmt->module)) continue; read_unlock(&binfmt_lock); retval = fmt->load_binary(bprm); read_lock(&binfmt_lock); put_binfmt(fmt); if (bprm->point_of_no_return || (retval != -ENOEXEC)) { read_unlock(&binfmt_lock); return retval; } } read_unlock(&binfmt_lock); if (need_retry) { if (printable(bprm->buf[0]) && printable(bprm->buf[1]) && printable(bprm->buf[2]) && printable(bprm->buf[3])) return retval; if (request_module("binfmt-%04x", *(ushort *)(bprm->buf + 2)) < 0) return retval; need_retry = false; goto retry; } return retval; } /* binfmt handlers will call back into begin_new_exec() on success. */ static int exec_binprm(struct linux_binprm *bprm) { pid_t old_pid, old_vpid; int ret, depth; /* Need to fetch pid before load_binary changes it */ old_pid = current->pid; rcu_read_lock(); old_vpid = task_pid_nr_ns(current, task_active_pid_ns(current->parent)); rcu_read_unlock(); /* This allows 4 levels of binfmt rewrites before failing hard. */ for (depth = 0;; depth++) { struct file *exec; if (depth > 5) return -ELOOP; ret = search_binary_handler(bprm); if (ret < 0) return ret; if (!bprm->interpreter) break; exec = bprm->file; bprm->file = bprm->interpreter; bprm->interpreter = NULL; allow_write_access(exec); if (unlikely(bprm->have_execfd)) { if (bprm->executable) { fput(exec); return -ENOEXEC; } bprm->executable = exec; } else fput(exec); } audit_bprm(bprm); trace_sched_process_exec(current, old_pid, bprm); ptrace_event(PTRACE_EVENT_EXEC, old_vpid); proc_exec_connector(current); return 0; } static int bprm_execve(struct linux_binprm *bprm) { int retval; retval = prepare_bprm_creds(bprm); if (retval) return retval; /* * Check for unsafe execution states before exec_binprm(), which * will call back into begin_new_exec(), into bprm_creds_from_file(), * where setuid-ness is evaluated. */ check_unsafe_exec(bprm); current->in_execve = 1; sched_mm_cid_before_execve(current); sched_exec(); /* Set the unchanging part of bprm->cred */ retval = security_bprm_creds_for_exec(bprm); if (retval) goto out; retval = exec_binprm(bprm); if (retval < 0) goto out; sched_mm_cid_after_execve(current); /* execve succeeded */ current->fs->in_exec = 0; current->in_execve = 0; rseq_execve(current); user_events_execve(current); acct_update_integrals(current); task_numa_free(current, false); return retval; out: /* * If past the point of no return ensure the code never * returns to the userspace process. Use an existing fatal * signal if present otherwise terminate the process with * SIGSEGV. */ if (bprm->point_of_no_return && !fatal_signal_pending(current)) force_fatal_sig(SIGSEGV); sched_mm_cid_after_execve(current); current->fs->in_exec = 0; current->in_execve = 0; return retval; } static int do_execveat_common(int fd, struct filename *filename, struct user_arg_ptr argv, struct user_arg_ptr envp, int flags) { struct linux_binprm *bprm; int retval; if (IS_ERR(filename)) return PTR_ERR(filename); /* * We move the actual failure in case of RLIMIT_NPROC excess from * set*uid() to execve() because too many poorly written programs * don't check setuid() return code. Here we additionally recheck * whether NPROC limit is still exceeded. */ if ((current->flags & PF_NPROC_EXCEEDED) && is_rlimit_overlimit(current_ucounts(), UCOUNT_RLIMIT_NPROC, rlimit(RLIMIT_NPROC))) { retval = -EAGAIN; goto out_ret; } /* We're below the limit (still or again), so we don't want to make * further execve() calls fail. */ current->flags &= ~PF_NPROC_EXCEEDED; bprm = alloc_bprm(fd, filename, flags); if (IS_ERR(bprm)) { retval = PTR_ERR(bprm); goto out_ret; } retval = count(argv, MAX_ARG_STRINGS); if (retval == 0) pr_warn_once("process '%s' launched '%s' with NULL argv: empty string added\n", current->comm, bprm->filename); if (retval < 0) goto out_free; bprm->argc = retval; retval = count(envp, MAX_ARG_STRINGS); if (retval < 0) goto out_free; bprm->envc = retval; retval = bprm_stack_limits(bprm); if (retval < 0) goto out_free; retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out_free; bprm->exec = bprm->p; retval = copy_strings(bprm->envc, envp, bprm); if (retval < 0) goto out_free; retval = copy_strings(bprm->argc, argv, bprm); if (retval < 0) goto out_free; /* * When argv is empty, add an empty string ("") as argv[0] to * ensure confused userspace programs that start processing * from argv[1] won't end up walking envp. See also * bprm_stack_limits(). */ if (bprm->argc == 0) { retval = copy_string_kernel("", bprm); if (retval < 0) goto out_free; bprm->argc = 1; } retval = bprm_execve(bprm); out_free: free_bprm(bprm); out_ret: putname(filename); return retval; } int kernel_execve(const char *kernel_filename, const char *const *argv, const char *const *envp) { struct filename *filename; struct linux_binprm *bprm; int fd = AT_FDCWD; int retval; /* It is non-sense for kernel threads to call execve */ if (WARN_ON_ONCE(current->flags & PF_KTHREAD)) return -EINVAL; filename = getname_kernel(kernel_filename); if (IS_ERR(filename)) return PTR_ERR(filename); bprm = alloc_bprm(fd, filename, 0); if (IS_ERR(bprm)) { retval = PTR_ERR(bprm); goto out_ret; } retval = count_strings_kernel(argv); if (WARN_ON_ONCE(retval == 0)) retval = -EINVAL; if (retval < 0) goto out_free; bprm->argc = retval; retval = count_strings_kernel(envp); if (retval < 0) goto out_free; bprm->envc = retval; retval = bprm_stack_limits(bprm); if (retval < 0) goto out_free; retval = copy_string_kernel(bprm->filename, bprm); if (retval < 0) goto out_free; bprm->exec = bprm->p; retval = copy_strings_kernel(bprm->envc, envp, bprm); if (retval < 0) goto out_free; retval = copy_strings_kernel(bprm->argc, argv, bprm); if (retval < 0) goto out_free; retval = bprm_execve(bprm); out_free: free_bprm(bprm); out_ret: putname(filename); return retval; } static int do_execve(struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int do_execveat(int fd, struct filename *filename, const char __user *const __user *__argv, const char __user *const __user *__envp, int flags) { struct user_arg_ptr argv = { .ptr.native = __argv }; struct user_arg_ptr envp = { .ptr.native = __envp }; return do_execveat_common(fd, filename, argv, envp, flags); } #ifdef CONFIG_COMPAT static int compat_do_execve(struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(AT_FDCWD, filename, argv, envp, 0); } static int compat_do_execveat(int fd, struct filename *filename, const compat_uptr_t __user *__argv, const compat_uptr_t __user *__envp, int flags) { struct user_arg_ptr argv = { .is_compat = true, .ptr.compat = __argv, }; struct user_arg_ptr envp = { .is_compat = true, .ptr.compat = __envp, }; return do_execveat_common(fd, filename, argv, envp, flags); } #endif void set_binfmt(struct linux_binfmt *new) { struct mm_struct *mm = current->mm; if (mm->binfmt) module_put(mm->binfmt->module); mm->binfmt = new; if (new) __module_get(new->module); } EXPORT_SYMBOL(set_binfmt); /* * set_dumpable stores three-value SUID_DUMP_* into mm->flags. */ void set_dumpable(struct mm_struct *mm, int value) { if (WARN_ON((unsigned)value > SUID_DUMP_ROOT)) return; set_mask_bits(&mm->flags, MMF_DUMPABLE_MASK, value); } SYSCALL_DEFINE3(execve, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp) { return do_execve(getname(filename), argv, envp); } SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const char __user *const __user *, argv, const char __user *const __user *, envp, int, flags) { return do_execveat(fd, getname_uflags(filename, flags), argv, envp, flags); } #ifdef CONFIG_COMPAT COMPAT_SYSCALL_DEFINE3(execve, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp) { return compat_do_execve(getname(filename), argv, envp); } COMPAT_SYSCALL_DEFINE5(execveat, int, fd, const char __user *, filename, const compat_uptr_t __user *, argv, const compat_uptr_t __user *, envp, int, flags) { return compat_do_execveat(fd, getname_uflags(filename, flags), argv, envp, flags); } #endif #ifdef CONFIG_SYSCTL static int proc_dointvec_minmax_coredump(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) { int error = proc_dointvec_minmax(table, write, buffer, lenp, ppos); if (!error) validate_coredump_safety(); return error; } static struct ctl_table fs_exec_sysctls[] = { { .procname = "suid_dumpable", .data = &suid_dumpable, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec_minmax_coredump, .extra1 = SYSCTL_ZERO, .extra2 = SYSCTL_TWO, }, }; static int __init init_fs_exec_sysctls(void) { register_sysctl_init("fs", fs_exec_sysctls); return 0; } fs_initcall(init_fs_exec_sysctls); #endif /* CONFIG_SYSCTL */ |
| 139 9 9 9 139 139 139 139 139 139 9 9 9 9 9 9 9 130 11 11 11 11 11 130 130 130 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2013-2017 ARM Limited, All Rights Reserved. * Author: Marc Zyngier <marc.zyngier@arm.com> */ #define pr_fmt(fmt) "GICv3: " fmt #include <linux/acpi.h> #include <linux/cpu.h> #include <linux/cpu_pm.h> #include <linux/delay.h> #include <linux/interrupt.h> #include <linux/irqdomain.h> #include <linux/kstrtox.h> #include <linux/of.h> #include <linux/of_address.h> #include <linux/of_irq.h> #include <linux/percpu.h> #include <linux/refcount.h> #include <linux/slab.h> #include <linux/iopoll.h> #include <linux/irqchip.h> #include <linux/irqchip/arm-gic-common.h> #include <linux/irqchip/arm-gic-v3.h> #include <linux/irqchip/irq-partition-percpu.h> #include <linux/bitfield.h> #include <linux/bits.h> #include <linux/arm-smccc.h> #include <asm/cputype.h> #include <asm/exception.h> #include <asm/smp_plat.h> #include <asm/virt.h> #include "irq-gic-common.h" #define GICD_INT_NMI_PRI (GICD_INT_DEF_PRI & ~0x80) #define FLAGS_WORKAROUND_GICR_WAKER_MSM8996 (1ULL << 0) #define FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539 (1ULL << 1) #define FLAGS_WORKAROUND_ASR_ERRATUM_8601001 (1ULL << 2) #define GIC_IRQ_TYPE_PARTITION (GIC_IRQ_TYPE_LPI + 1) struct redist_region { void __iomem *redist_base; phys_addr_t phys_base; bool single_redist; }; struct gic_chip_data { struct fwnode_handle *fwnode; phys_addr_t dist_phys_base; void __iomem *dist_base; struct redist_region *redist_regions; struct rdists rdists; struct irq_domain *domain; u64 redist_stride; u32 nr_redist_regions; u64 flags; bool has_rss; unsigned int ppi_nr; struct partition_desc **ppi_descs; }; #define T241_CHIPS_MAX 4 static void __iomem *t241_dist_base_alias[T241_CHIPS_MAX] __read_mostly; static DEFINE_STATIC_KEY_FALSE(gic_nvidia_t241_erratum); static DEFINE_STATIC_KEY_FALSE(gic_arm64_2941627_erratum); static struct gic_chip_data gic_data __read_mostly; static DEFINE_STATIC_KEY_TRUE(supports_deactivate_key); #define GIC_ID_NR (1U << GICD_TYPER_ID_BITS(gic_data.rdists.gicd_typer)) #define GIC_LINE_NR min(GICD_TYPER_SPIS(gic_data.rdists.gicd_typer), 1020U) #define GIC_ESPI_NR GICD_TYPER_ESPIS(gic_data.rdists.gicd_typer) /* * There are 16 SGIs, though we only actually use 8 in Linux. The other 8 SGIs * are potentially stolen by the secure side. Some code, especially code dealing * with hwirq IDs, is simplified by accounting for all 16. */ #define SGI_NR 16 /* * The behaviours of RPR and PMR registers differ depending on the value of * SCR_EL3.FIQ, and the behaviour of non-secure priority registers of the * distributor and redistributors depends on whether security is enabled in the * GIC. * * When security is enabled, non-secure priority values from the (re)distributor * are presented to the GIC CPUIF as follow: * (GIC_(R)DIST_PRI[irq] >> 1) | 0x80; * * If SCR_EL3.FIQ == 1, the values written to/read from PMR and RPR at non-secure * EL1 are subject to a similar operation thus matching the priorities presented * from the (re)distributor when security is enabled. When SCR_EL3.FIQ == 0, * these values are unchanged by the GIC. * * see GICv3/GICv4 Architecture Specification (IHI0069D): * - section 4.8.1 Non-secure accesses to register fields for Secure interrupt * priorities. * - Figure 4-7 Secure read of the priority field for a Non-secure Group 1 * interrupt. */ static DEFINE_STATIC_KEY_FALSE(supports_pseudo_nmis); DEFINE_STATIC_KEY_FALSE(gic_nonsecure_priorities); EXPORT_SYMBOL(gic_nonsecure_priorities); /* * When the Non-secure world has access to group 0 interrupts (as a * consequence of SCR_EL3.FIQ == 0), reading the ICC_RPR_EL1 register will * return the Distributor's view of the interrupt priority. * * When GIC security is enabled (GICD_CTLR.DS == 0), the interrupt priority * written by software is moved to the Non-secure range by the Distributor. * * If both are true (which is when gic_nonsecure_priorities gets enabled), * we need to shift down the priority programmed by software to match it * against the value returned by ICC_RPR_EL1. */ #define GICD_INT_RPR_PRI(priority) \ ({ \ u32 __priority = (priority); \ if (static_branch_unlikely(&gic_nonsecure_priorities)) \ __priority = 0x80 | (__priority >> 1); \ \ __priority; \ }) /* rdist_nmi_refs[n] == number of cpus having the rdist interrupt n set as NMI */ static refcount_t *rdist_nmi_refs; static struct gic_kvm_info gic_v3_kvm_info __initdata; static DEFINE_PER_CPU(bool, has_rss); #define MPIDR_RS(mpidr) (((mpidr) & 0xF0UL) >> 4) #define gic_data_rdist() (this_cpu_ptr(gic_data.rdists.rdist)) #define gic_data_rdist_rd_base() (gic_data_rdist()->rd_base) #define gic_data_rdist_sgi_base() (gic_data_rdist_rd_base() + SZ_64K) /* Our default, arbitrary priority value. Linux only uses one anyway. */ #define DEFAULT_PMR_VALUE 0xf0 enum gic_intid_range { SGI_RANGE, PPI_RANGE, SPI_RANGE, EPPI_RANGE, ESPI_RANGE, LPI_RANGE, __INVALID_RANGE__ }; static enum gic_intid_range __get_intid_range(irq_hw_number_t hwirq) { switch (hwirq) { case 0 ... 15: return SGI_RANGE; case 16 ... 31: return PPI_RANGE; case 32 ... 1019: return SPI_RANGE; case EPPI_BASE_INTID ... (EPPI_BASE_INTID + 63): return EPPI_RANGE; case ESPI_BASE_INTID ... (ESPI_BASE_INTID + 1023): return ESPI_RANGE; case 8192 ... GENMASK(23, 0): return LPI_RANGE; default: return __INVALID_RANGE__; } } static enum gic_intid_range get_intid_range(struct irq_data *d) { return __get_intid_range(d->hwirq); } static inline bool gic_irq_in_rdist(struct irq_data *d) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: return true; default: return false; } } static inline void __iomem *gic_dist_base_alias(struct irq_data *d) { if (static_branch_unlikely(&gic_nvidia_t241_erratum)) { irq_hw_number_t hwirq = irqd_to_hwirq(d); u32 chip; /* * For the erratum T241-FABRIC-4, read accesses to GICD_In{E} * registers are directed to the chip that owns the SPI. The * the alias region can also be used for writes to the * GICD_In{E} except GICD_ICENABLERn. Each chip has support * for 320 {E}SPIs. Mappings for all 4 chips: * Chip0 = 32-351 * Chip1 = 352-671 * Chip2 = 672-991 * Chip3 = 4096-4415 */ switch (__get_intid_range(hwirq)) { case SPI_RANGE: chip = (hwirq - 32) / 320; break; case ESPI_RANGE: chip = 3; break; default: unreachable(); } return t241_dist_base_alias[chip]; } return gic_data.dist_base; } static inline void __iomem *gic_dist_base(struct irq_data *d) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: /* SGI+PPI -> SGI_base for this CPU */ return gic_data_rdist_sgi_base(); case SPI_RANGE: case ESPI_RANGE: /* SPI -> dist_base */ return gic_data.dist_base; default: return NULL; } } static void gic_do_wait_for_rwp(void __iomem *base, u32 bit) { u32 val; int ret; ret = readl_relaxed_poll_timeout_atomic(base + GICD_CTLR, val, !(val & bit), 1, USEC_PER_SEC); if (ret == -ETIMEDOUT) pr_err_ratelimited("RWP timeout, gone fishing\n"); } /* Wait for completion of a distributor change */ static void gic_dist_wait_for_rwp(void) { gic_do_wait_for_rwp(gic_data.dist_base, GICD_CTLR_RWP); } /* Wait for completion of a redistributor change */ static void gic_redist_wait_for_rwp(void) { gic_do_wait_for_rwp(gic_data_rdist_rd_base(), GICR_CTLR_RWP); } static void gic_enable_redist(bool enable) { void __iomem *rbase; u32 val; int ret; if (gic_data.flags & FLAGS_WORKAROUND_GICR_WAKER_MSM8996) return; rbase = gic_data_rdist_rd_base(); val = readl_relaxed(rbase + GICR_WAKER); if (enable) /* Wake up this CPU redistributor */ val &= ~GICR_WAKER_ProcessorSleep; else val |= GICR_WAKER_ProcessorSleep; writel_relaxed(val, rbase + GICR_WAKER); if (!enable) { /* Check that GICR_WAKER is writeable */ val = readl_relaxed(rbase + GICR_WAKER); if (!(val & GICR_WAKER_ProcessorSleep)) return; /* No PM support in this redistributor */ } ret = readl_relaxed_poll_timeout_atomic(rbase + GICR_WAKER, val, enable ^ (bool)(val & GICR_WAKER_ChildrenAsleep), 1, USEC_PER_SEC); if (ret == -ETIMEDOUT) { pr_err_ratelimited("redistributor failed to %s...\n", enable ? "wakeup" : "sleep"); } } /* * Routines to disable, enable, EOI and route interrupts */ static u32 convert_offset_index(struct irq_data *d, u32 offset, u32 *index) { switch (get_intid_range(d)) { case SGI_RANGE: case PPI_RANGE: case SPI_RANGE: *index = d->hwirq; return offset; case EPPI_RANGE: /* * Contrary to the ESPI range, the EPPI range is contiguous * to the PPI range in the registers, so let's adjust the * displacement accordingly. Consistency is overrated. */ *index = d->hwirq - EPPI_BASE_INTID + 32; return offset; case ESPI_RANGE: *index = d->hwirq - ESPI_BASE_INTID; switch (offset) { case GICD_ISENABLER: return GICD_ISENABLERnE; case GICD_ICENABLER: return GICD_ICENABLERnE; case GICD_ISPENDR: return GICD_ISPENDRnE; case GICD_ICPENDR: return GICD_ICPENDRnE; case GICD_ISACTIVER: return GICD_ISACTIVERnE; case GICD_ICACTIVER: return GICD_ICACTIVERnE; case GICD_IPRIORITYR: return GICD_IPRIORITYRnE; case GICD_ICFGR: return GICD_ICFGRnE; case GICD_IROUTER: return GICD_IROUTERnE; default: break; } break; default: break; } WARN_ON(1); *index = d->hwirq; return offset; } static int gic_peek_irq(struct irq_data *d, u32 offset) { void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_dist_base_alias(d); return !!(readl_relaxed(base + offset + (index / 32) * 4) & mask); } static void gic_poke_irq(struct irq_data *d, u32 offset) { void __iomem *base; u32 index, mask; offset = convert_offset_index(d, offset, &index); mask = 1 << (index % 32); if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_data.dist_base; writel_relaxed(mask, base + offset + (index / 32) * 4); } static void gic_mask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ICENABLER); if (gic_irq_in_rdist(d)) gic_redist_wait_for_rwp(); else gic_dist_wait_for_rwp(); } static void gic_eoimode1_mask_irq(struct irq_data *d) { gic_mask_irq(d); /* * When masking a forwarded interrupt, make sure it is * deactivated as well. * * This ensures that an interrupt that is getting * disabled/masked will not get "stuck", because there is * noone to deactivate it (guest is being terminated). */ if (irqd_is_forwarded_to_vcpu(d)) gic_poke_irq(d, GICD_ICACTIVER); } static void gic_unmask_irq(struct irq_data *d) { gic_poke_irq(d, GICD_ISENABLER); } static inline bool gic_supports_nmi(void) { return IS_ENABLED(CONFIG_ARM64_PSEUDO_NMI) && static_branch_likely(&supports_pseudo_nmis); } static int gic_irq_set_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool val) { u32 reg; if (d->hwirq >= 8192) /* SGI/PPI/SPI only */ return -EINVAL; switch (which) { case IRQCHIP_STATE_PENDING: reg = val ? GICD_ISPENDR : GICD_ICPENDR; break; case IRQCHIP_STATE_ACTIVE: reg = val ? GICD_ISACTIVER : GICD_ICACTIVER; break; case IRQCHIP_STATE_MASKED: if (val) { gic_mask_irq(d); return 0; } reg = GICD_ISENABLER; break; default: return -EINVAL; } gic_poke_irq(d, reg); return 0; } static int gic_irq_get_irqchip_state(struct irq_data *d, enum irqchip_irq_state which, bool *val) { if (d->hwirq >= 8192) /* PPI/SPI only */ return -EINVAL; switch (which) { case IRQCHIP_STATE_PENDING: *val = gic_peek_irq(d, GICD_ISPENDR); break; case IRQCHIP_STATE_ACTIVE: *val = gic_peek_irq(d, GICD_ISACTIVER); break; case IRQCHIP_STATE_MASKED: *val = !gic_peek_irq(d, GICD_ISENABLER); break; default: return -EINVAL; } return 0; } static void gic_irq_set_prio(struct irq_data *d, u8 prio) { void __iomem *base = gic_dist_base(d); u32 offset, index; offset = convert_offset_index(d, GICD_IPRIORITYR, &index); writeb_relaxed(prio, base + offset + index); } static u32 __gic_get_ppi_index(irq_hw_number_t hwirq) { switch (__get_intid_range(hwirq)) { case PPI_RANGE: return hwirq - 16; case EPPI_RANGE: return hwirq - EPPI_BASE_INTID + 16; default: unreachable(); } } static u32 __gic_get_rdist_index(irq_hw_number_t hwirq) { switch (__get_intid_range(hwirq)) { case SGI_RANGE: case PPI_RANGE: return hwirq; case EPPI_RANGE: return hwirq - EPPI_BASE_INTID + 32; default: unreachable(); } } static u32 gic_get_rdist_index(struct irq_data *d) { return __gic_get_rdist_index(d->hwirq); } static int gic_irq_nmi_setup(struct irq_data *d) { struct irq_desc *desc = irq_to_desc(d->irq); if (!gic_supports_nmi()) return -EINVAL; if (gic_peek_irq(d, GICD_ISENABLER)) { pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq); return -EINVAL; } /* * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return -EINVAL; /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { u32 idx = gic_get_rdist_index(d); /* * Setting up a percpu interrupt as NMI, only switch handler * for first NMI */ if (!refcount_inc_not_zero(&rdist_nmi_refs[idx])) { refcount_set(&rdist_nmi_refs[idx], 1); desc->handle_irq = handle_percpu_devid_fasteoi_nmi; } } else { desc->handle_irq = handle_fasteoi_nmi; } gic_irq_set_prio(d, GICD_INT_NMI_PRI); return 0; } static void gic_irq_nmi_teardown(struct irq_data *d) { struct irq_desc *desc = irq_to_desc(d->irq); if (WARN_ON(!gic_supports_nmi())) return; if (gic_peek_irq(d, GICD_ISENABLER)) { pr_err("Cannot set NMI property of enabled IRQ %u\n", d->irq); return; } /* * A secondary irq_chip should be in charge of LPI request, * it should not be possible to get there */ if (WARN_ON(irqd_to_hwirq(d) >= 8192)) return; /* desc lock should already be held */ if (gic_irq_in_rdist(d)) { u32 idx = gic_get_rdist_index(d); /* Tearing down NMI, only switch handler for last NMI */ if (refcount_dec_and_test(&rdist_nmi_refs[idx])) desc->handle_irq = handle_percpu_devid_irq; } else { desc->handle_irq = handle_fasteoi_irq; } gic_irq_set_prio(d, GICD_INT_DEF_PRI); } static bool gic_arm64_erratum_2941627_needed(struct irq_data *d) { enum gic_intid_range range; if (!static_branch_unlikely(&gic_arm64_2941627_erratum)) return false; range = get_intid_range(d); /* * The workaround is needed if the IRQ is an SPI and * the target cpu is different from the one we are * executing on. */ return (range == SPI_RANGE || range == ESPI_RANGE) && !cpumask_test_cpu(raw_smp_processor_id(), irq_data_get_effective_affinity_mask(d)); } static void gic_eoi_irq(struct irq_data *d) { write_gicreg(irqd_to_hwirq(d), ICC_EOIR1_EL1); isb(); if (gic_arm64_erratum_2941627_needed(d)) { /* * Make sure the GIC stream deactivate packet * issued by ICC_EOIR1_EL1 has completed before * deactivating through GICD_IACTIVER. */ dsb(sy); gic_poke_irq(d, GICD_ICACTIVER); } } static void gic_eoimode1_eoi_irq(struct irq_data *d) { /* * No need to deactivate an LPI, or an interrupt that * is is getting forwarded to a vcpu. */ if (irqd_to_hwirq(d) >= 8192 || irqd_is_forwarded_to_vcpu(d)) return; if (!gic_arm64_erratum_2941627_needed(d)) gic_write_dir(irqd_to_hwirq(d)); else gic_poke_irq(d, GICD_ICACTIVER); } static int gic_set_type(struct irq_data *d, unsigned int type) { irq_hw_number_t irq = irqd_to_hwirq(d); enum gic_intid_range range; void __iomem *base; u32 offset, index; int ret; range = get_intid_range(d); /* Interrupt configuration for SGIs can't be changed */ if (range == SGI_RANGE) return type != IRQ_TYPE_EDGE_RISING ? -EINVAL : 0; /* SPIs have restrictions on the supported types */ if ((range == SPI_RANGE || range == ESPI_RANGE) && type != IRQ_TYPE_LEVEL_HIGH && type != IRQ_TYPE_EDGE_RISING) return -EINVAL; if (gic_irq_in_rdist(d)) base = gic_data_rdist_sgi_base(); else base = gic_dist_base_alias(d); offset = convert_offset_index(d, GICD_ICFGR, &index); ret = gic_configure_irq(index, type, base + offset, NULL); if (ret && (range == PPI_RANGE || range == EPPI_RANGE)) { /* Misconfigured PPIs are usually not fatal */ pr_warn("GIC: PPI INTID%ld is secure or misconfigured\n", irq); ret = 0; } return ret; } static int gic_irq_set_vcpu_affinity(struct irq_data *d, void *vcpu) { if (get_intid_range(d) == SGI_RANGE) return -EINVAL; if (vcpu) irqd_set_forwarded_to_vcpu(d); else irqd_clr_forwarded_to_vcpu(d); return 0; } static u64 gic_cpu_to_affinity(int cpu) { u64 mpidr = cpu_logical_map(cpu); u64 aff; /* ASR8601 needs to have its affinities shifted down... */ if (unlikely(gic_data.flags & FLAGS_WORKAROUND_ASR_ERRATUM_8601001)) mpidr = (MPIDR_AFFINITY_LEVEL(mpidr, 1) | (MPIDR_AFFINITY_LEVEL(mpidr, 2) << 8)); aff = ((u64)MPIDR_AFFINITY_LEVEL(mpidr, 3) << 32 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 0)); return aff; } static void gic_deactivate_unhandled(u32 irqnr) { if (static_branch_likely(&supports_deactivate_key)) { if (irqnr < 8192) gic_write_dir(irqnr); } else { write_gicreg(irqnr, ICC_EOIR1_EL1); isb(); } } /* * Follow a read of the IAR with any HW maintenance that needs to happen prior * to invoking the relevant IRQ handler. We must do two things: * * (1) Ensure instruction ordering between a read of IAR and subsequent * instructions in the IRQ handler using an ISB. * * It is possible for the IAR to report an IRQ which was signalled *after* * the CPU took an IRQ exception as multiple interrupts can race to be * recognized by the GIC, earlier interrupts could be withdrawn, and/or * later interrupts could be prioritized by the GIC. * * For devices which are tightly coupled to the CPU, such as PMUs, a * context synchronization event is necessary to ensure that system * register state is not stale, as these may have been indirectly written * *after* exception entry. * * (2) Deactivate the interrupt when EOI mode 1 is in use. */ static inline void gic_complete_ack(u32 irqnr) { if (static_branch_likely(&supports_deactivate_key)) write_gicreg(irqnr, ICC_EOIR1_EL1); isb(); } static bool gic_rpr_is_nmi_prio(void) { if (!gic_supports_nmi()) return false; return unlikely(gic_read_rpr() == GICD_INT_RPR_PRI(GICD_INT_NMI_PRI)); } static bool gic_irqnr_is_special(u32 irqnr) { return irqnr >= 1020 && irqnr <= 1023; } static void __gic_handle_irq(u32 irqnr, struct pt_regs *regs) { if (gic_irqnr_is_special(irqnr)) return; gic_complete_ack(irqnr); if (generic_handle_domain_irq(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected interrupt (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); } } static void __gic_handle_nmi(u32 irqnr, struct pt_regs *regs) { if (gic_irqnr_is_special(irqnr)) return; gic_complete_ack(irqnr); if (generic_handle_domain_nmi(gic_data.domain, irqnr)) { WARN_ONCE(true, "Unexpected pseudo-NMI (irqnr %u)\n", irqnr); gic_deactivate_unhandled(irqnr); } } /* * An exception has been taken from a context with IRQs enabled, and this could * be an IRQ or an NMI. * * The entry code called us with DAIF.IF set to keep NMIs masked. We must clear * DAIF.IF (and update ICC_PMR_EL1 to mask regular IRQs) prior to returning, * after handling any NMI but before handling any IRQ. * * The entry code has performed IRQ entry, and if an NMI is detected we must * perform NMI entry/exit around invoking the handler. */ static void __gic_handle_irq_from_irqson(struct pt_regs *regs) { bool is_nmi; u32 irqnr; irqnr = gic_read_iar(); is_nmi = gic_rpr_is_nmi_prio(); if (is_nmi) { nmi_enter(); __gic_handle_nmi(irqnr, regs); nmi_exit(); } if (gic_prio_masking_enabled()) { gic_pmr_mask_irqs(); gic_arch_enable_irqs(); } if (!is_nmi) __gic_handle_irq(irqnr, regs); } /* * An exception has been taken from a context with IRQs disabled, which can only * be an NMI. * * The entry code called us with DAIF.IF set to keep NMIs masked. We must leave * DAIF.IF (and ICC_PMR_EL1) unchanged. * * The entry code has performed NMI entry. */ static void __gic_handle_irq_from_irqsoff(struct pt_regs *regs) { u64 pmr; u32 irqnr; /* * We were in a context with IRQs disabled. However, the * entry code has set PMR to a value that allows any * interrupt to be acknowledged, and not just NMIs. This can * lead to surprising effects if the NMI has been retired in * the meantime, and that there is an IRQ pending. The IRQ * would then be taken in NMI context, something that nobody * wants to debug twice. * * Until we sort this, drop PMR again to a level that will * actually only allow NMIs before reading IAR, and then * restore it to what it was. */ pmr = gic_read_pmr(); gic_pmr_mask_irqs(); isb(); irqnr = gic_read_iar(); gic_write_pmr(pmr); __gic_handle_nmi(irqnr, regs); } static asmlinkage void __exception_irq_entry gic_handle_irq(struct pt_regs *regs) { if (unlikely(gic_supports_nmi() && !interrupts_enabled(regs))) __gic_handle_irq_from_irqsoff(regs); else __gic_handle_irq_from_irqson(regs); } static u32 gic_get_pribits(void) { u32 pribits; pribits = gic_read_ctlr(); pribits &= ICC_CTLR_EL1_PRI_BITS_MASK; pribits >>= ICC_CTLR_EL1_PRI_BITS_SHIFT; pribits++; return pribits; } static bool gic_has_group0(void) { u32 val; u32 old_pmr; old_pmr = gic_read_pmr(); /* * Let's find out if Group0 is under control of EL3 or not by * setting the highest possible, non-zero priority in PMR. * * If SCR_EL3.FIQ is set, the priority gets shifted down in * order for the CPU interface to set bit 7, and keep the * actual priority in the non-secure range. In the process, it * looses the least significant bit and the actual priority * becomes 0x80. Reading it back returns 0, indicating that * we're don't have access to Group0. */ gic_write_pmr(BIT(8 - gic_get_pribits())); val = gic_read_pmr(); gic_write_pmr(old_pmr); return val != 0; } static void __init gic_dist_init(void) { unsigned int i; u64 affinity; void __iomem *base = gic_data.dist_base; u32 val; /* Disable the distributor */ writel_relaxed(0, base + GICD_CTLR); gic_dist_wait_for_rwp(); /* * Configure SPIs as non-secure Group-1. This will only matter * if the GIC only has a single security state. This will not * do the right thing if the kernel is running in secure mode, * but that's not the intended use case anyway. */ for (i = 32; i < GIC_LINE_NR; i += 32) writel_relaxed(~0, base + GICD_IGROUPR + i / 8); /* Extended SPI range, not handled by the GICv2/GICv3 common code */ for (i = 0; i < GIC_ESPI_NR; i += 32) { writel_relaxed(~0U, base + GICD_ICENABLERnE + i / 8); writel_relaxed(~0U, base + GICD_ICACTIVERnE + i / 8); } for (i = 0; i < GIC_ESPI_NR; i += 32) writel_relaxed(~0U, base + GICD_IGROUPRnE + i / 8); for (i = 0; i < GIC_ESPI_NR; i += 16) writel_relaxed(0, base + GICD_ICFGRnE + i / 4); for (i = 0; i < GIC_ESPI_NR; i += 4) writel_relaxed(GICD_INT_DEF_PRI_X4, base + GICD_IPRIORITYRnE + i); /* Now do the common stuff */ gic_dist_config(base, GIC_LINE_NR, NULL); val = GICD_CTLR_ARE_NS | GICD_CTLR_ENABLE_G1A | GICD_CTLR_ENABLE_G1; if (gic_data.rdists.gicd_typer2 & GICD_TYPER2_nASSGIcap) { pr_info("Enabling SGIs without active state\n"); val |= GICD_CTLR_nASSGIreq; } /* Enable distributor with ARE, Group1, and wait for it to drain */ writel_relaxed(val, base + GICD_CTLR); gic_dist_wait_for_rwp(); /* * Set all global interrupts to the boot CPU only. ARE must be * enabled. */ affinity = gic_cpu_to_affinity(smp_processor_id()); for (i = 32; i < GIC_LINE_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTER + i * 8); for (i = 0; i < GIC_ESPI_NR; i++) gic_write_irouter(affinity, base + GICD_IROUTERnE + i * 8); } static int gic_iterate_rdists(int (*fn)(struct redist_region *, void __iomem *)) { int ret = -ENODEV; int i; for (i = 0; i < gic_data.nr_redist_regions; i++) { void __iomem *ptr = gic_data.redist_regions[i].redist_base; u64 typer; u32 reg; reg = readl_relaxed(ptr + GICR_PIDR2) & GIC_PIDR2_ARCH_MASK; if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) { /* We're in trouble... */ pr_warn("No redistributor present @%p\n", ptr); break; } do { typer = gic_read_typer(ptr + GICR_TYPER); ret = fn(gic_data.redist_regions + i, ptr); if (!ret) return 0; if (gic_data.redist_regions[i].single_redist) break; if (gic_data.redist_stride) { ptr += gic_data.redist_stride; } else { ptr += SZ_64K * 2; /* Skip RD_base + SGI_base */ if (typer & GICR_TYPER_VLPIS) ptr += SZ_64K * 2; /* Skip VLPI_base + reserved page */ } } while (!(typer & GICR_TYPER_LAST)); } return ret ? -ENODEV : 0; } static int __gic_populate_rdist(struct redist_region *region, void __iomem *ptr) { unsigned long mpidr; u64 typer; u32 aff; /* * Convert affinity to a 32bit value that can be matched to * GICR_TYPER bits [63:32]. */ mpidr = gic_cpu_to_affinity(smp_processor_id()); aff = (MPIDR_AFFINITY_LEVEL(mpidr, 3) << 24 | MPIDR_AFFINITY_LEVEL(mpidr, 2) << 16 | MPIDR_AFFINITY_LEVEL(mpidr, 1) << 8 | MPIDR_AFFINITY_LEVEL(mpidr, 0)); typer = gic_read_typer(ptr + GICR_TYPER); if ((typer >> 32) == aff) { u64 offset = ptr - region->redist_base; raw_spin_lock_init(&gic_data_rdist()->rd_lock); gic_data_rdist_rd_base() = ptr; gic_data_rdist()->phys_base = region->phys_base + offset; pr_info("CPU%d: found redistributor %lx region %d:%pa\n", smp_processor_id(), mpidr, (int)(region - gic_data.redist_regions), &gic_data_rdist()->phys_base); return 0; } /* Try next one */ return 1; } static int gic_populate_rdist(void) { if (gic_iterate_rdists(__gic_populate_rdist) == 0) return 0; /* We couldn't even deal with ourselves... */ WARN(true, "CPU%d: mpidr %lx has no re-distributor!\n", smp_processor_id(), (unsigned long)cpu_logical_map(smp_processor_id())); return -ENODEV; } static int __gic_update_rdist_properties(struct redist_region *region, void __iomem *ptr) { u64 typer = gic_read_typer(ptr + GICR_TYPER); u32 ctlr = readl_relaxed(ptr + GICR_CTLR); /* Boot-time cleanup */ if ((typer & GICR_TYPER_VLPIS) && (typer & GICR_TYPER_RVPEID)) { u64 val; /* Deactivate any present vPE */ val = gicr_read_vpendbaser(ptr + SZ_128K + GICR_VPENDBASER); if (val & GICR_VPENDBASER_Valid) gicr_write_vpendbaser(GICR_VPENDBASER_PendingLast, ptr + SZ_128K + GICR_VPENDBASER); /* Mark the VPE table as invalid */ val = gicr_read_vpropbaser(ptr + SZ_128K + GICR_VPROPBASER); val &= ~GICR_VPROPBASER_4_1_VALID; gicr_write_vpropbaser(val, ptr + SZ_128K + GICR_VPROPBASER); } gic_data.rdists.has_vlpis &= !!(typer & GICR_TYPER_VLPIS); /* * TYPER.RVPEID implies some form of DirectLPI, no matter what the * doc says... :-/ And CTLR.IR implies another subset of DirectLPI * that the ITS driver can make use of for LPIs (and not VLPIs). * * These are 3 different ways to express the same thing, depending * on the revision of the architecture and its relaxations over * time. Just group them under the 'direct_lpi' banner. */ gic_data.rdists.has_rvpeid &= !!(typer & GICR_TYPER_RVPEID); gic_data.rdists.has_direct_lpi &= (!!(typer & GICR_TYPER_DirectLPIS) | !!(ctlr & GICR_CTLR_IR) | gic_data.rdists.has_rvpeid); gic_data.rdists.has_vpend_valid_dirty &= !!(typer & GICR_TYPER_DIRTY); /* Detect non-sensical configurations */ if (WARN_ON_ONCE(gic_data.rdists.has_rvpeid && !gic_data.rdists.has_vlpis)) { gic_data.rdists.has_direct_lpi = false; gic_data.rdists.has_vlpis = false; gic_data.rdists.has_rvpeid = false; } gic_data.ppi_nr = min(GICR_TYPER_NR_PPIS(typer), gic_data.ppi_nr); return 1; } static void gic_update_rdist_properties(void) { gic_data.ppi_nr = UINT_MAX; gic_iterate_rdists(__gic_update_rdist_properties); if (WARN_ON(gic_data.ppi_nr == UINT_MAX)) gic_data.ppi_nr = 0; pr_info("GICv3 features: %d PPIs%s%s\n", gic_data.ppi_nr, gic_data.has_rss ? ", RSS" : "", gic_data.rdists.has_direct_lpi ? ", DirectLPI" : ""); if (gic_data.rdists.has_vlpis) pr_info("GICv4 features: %s%s%s\n", gic_data.rdists.has_direct_lpi ? "DirectLPI " : "", gic_data.rdists.has_rvpeid ? "RVPEID " : "", gic_data.rdists.has_vpend_valid_dirty ? "Valid+Dirty " : ""); } /* Check whether it's single security state view */ static inline bool gic_dist_security_disabled(void) { return readl_relaxed(gic_data.dist_base + GICD_CTLR) & GICD_CTLR_DS; } static void gic_cpu_sys_reg_init(void) { int i, cpu = smp_processor_id(); u64 mpidr = gic_cpu_to_affinity(cpu); u64 need_rss = MPIDR_RS(mpidr); bool group0; u32 pribits; /* * Need to check that the SRE bit has actually been set. If * not, it means that SRE is disabled at EL2. We're going to * die painfully, and there is nothing we can do about it. * * Kindly inform the luser. */ if (!gic_enable_sre()) pr_err("GIC: unable to set SRE (disabled at EL2), panic ahead\n"); pribits = gic_get_pribits(); group0 = gic_has_group0(); /* Set priority mask register */ if (!gic_prio_masking_enabled()) { write_gicreg(DEFAULT_PMR_VALUE, ICC_PMR_EL1); } else if (gic_supports_nmi()) { /* * Mismatch configuration with boot CPU, the system is likely * to die as interrupt masking will not work properly on all * CPUs * * The boot CPU calls this function before enabling NMI support, * and as a result we'll never see this warning in the boot path * for that CPU. */ if (static_branch_unlikely(&gic_nonsecure_priorities)) WARN_ON(!group0 || gic_dist_security_disabled()); else WARN_ON(group0 && !gic_dist_security_disabled()); } /* * Some firmwares hand over to the kernel with the BPR changed from * its reset value (and with a value large enough to prevent * any pre-emptive interrupts from working at all). Writing a zero * to BPR restores is reset value. */ gic_write_bpr1(0); if (static_branch_likely(&supports_deactivate_key)) { /* EOI drops priority only (mode 1) */ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop); } else { /* EOI deactivates interrupt too (mode 0) */ gic_write_ctlr(ICC_CTLR_EL1_EOImode_drop_dir); } /* Always whack Group0 before Group1 */ if (group0) { switch(pribits) { case 8: case 7: write_gicreg(0, ICC_AP0R3_EL1); write_gicreg(0, ICC_AP0R2_EL1); fallthrough; case 6: write_gicreg(0, ICC_AP0R1_EL1); fallthrough; case 5: case 4: write_gicreg(0, ICC_AP0R0_EL1); } isb(); } switch(pribits) { case 8: case 7: write_gicreg(0, ICC_AP1R3_EL1); write_gicreg(0, ICC_AP1R2_EL1); fallthrough; case 6: write_gicreg(0, ICC_AP1R1_EL1); fallthrough; case 5: case 4: write_gicreg(0, ICC_AP1R0_EL1); } isb(); /* ... and let's hit the road... */ gic_write_grpen1(1); /* Keep the RSS capability status in per_cpu variable */ per_cpu(has_rss, cpu) = !!(gic_read_ctlr() & ICC_CTLR_EL1_RSS); /* Check all the CPUs have capable of sending SGIs to other CPUs */ for_each_online_cpu(i) { bool have_rss = per_cpu(has_rss, i) && per_cpu(has_rss, cpu); need_rss |= MPIDR_RS(gic_cpu_to_affinity(i)); if (need_rss && (!have_rss)) pr_crit("CPU%d (%lx) can't SGI CPU%d (%lx), no RSS\n", cpu, (unsigned long)mpidr, i, (unsigned long)gic_cpu_to_affinity(i)); } /** * GIC spec says, when ICC_CTLR_EL1.RSS==1 and GICD_TYPER.RSS==0, * writing ICC_ASGI1R_EL1 register with RS != 0 is a CONSTRAINED * UNPREDICTABLE choice of : * - The write is ignored. * - The RS field is treated as 0. */ if (need_rss && (!gic_data.has_rss)) pr_crit_once("RSS is required but GICD doesn't support it\n"); } static bool gicv3_nolpi; static int __init gicv3_nolpi_cfg(char *buf) { return kstrtobool(buf, &gicv3_nolpi); } early_param("irqchip.gicv3_nolpi", gicv3_nolpi_cfg); static int gic_dist_supports_lpis(void) { return (IS_ENABLED(CONFIG_ARM_GIC_V3_ITS) && !!(readl_relaxed(gic_data.dist_base + GICD_TYPER) & GICD_TYPER_LPIS) && !gicv3_nolpi); } static void gic_cpu_init(void) { void __iomem *rbase; int i; /* Register ourselves with the rest of the world */ if (gic_populate_rdist()) return; gic_enable_redist(true); WARN((gic_data.ppi_nr > 16 || GIC_ESPI_NR != 0) && !(gic_read_ctlr() & ICC_CTLR_EL1_ExtRange), "Distributor has extended ranges, but CPU%d doesn't\n", smp_processor_id()); rbase = gic_data_rdist_sgi_base(); /* Configure SGIs/PPIs as non-secure Group-1 */ for (i = 0; i < gic_data.ppi_nr + SGI_NR; i += 32) writel_relaxed(~0, rbase + GICR_IGROUPR0 + i / 8); gic_cpu_config(rbase, gic_data.ppi_nr + SGI_NR, gic_redist_wait_for_rwp); /* initialise system registers */ gic_cpu_sys_reg_init(); } #ifdef CONFIG_SMP #define MPIDR_TO_SGI_RS(mpidr) (MPIDR_RS(mpidr) << ICC_SGI1R_RS_SHIFT) #define MPIDR_TO_SGI_CLUSTER_ID(mpidr) ((mpidr) & ~0xFUL) static int gic_starting_cpu(unsigned int cpu) { gic_cpu_init(); if (gic_dist_supports_lpis()) its_cpu_init(); return 0; } static u16 gic_compute_target_list(int *base_cpu, const struct cpumask *mask, unsigned long cluster_id) { int next_cpu, cpu = *base_cpu; unsigned long mpidr; u16 tlist = 0; mpidr = gic_cpu_to_affinity(cpu); while (cpu < nr_cpu_ids) { tlist |= 1 << (mpidr & 0xf); next_cpu = cpumask_next(cpu, mask); if (next_cpu >= nr_cpu_ids) goto out; cpu = next_cpu; mpidr = gic_cpu_to_affinity(cpu); if (cluster_id != MPIDR_TO_SGI_CLUSTER_ID(mpidr)) { cpu--; goto out; } } out: *base_cpu = cpu; return tlist; } #define MPIDR_TO_SGI_AFFINITY(cluster_id, level) \ (MPIDR_AFFINITY_LEVEL(cluster_id, level) \ << ICC_SGI1R_AFFINITY_## level ##_SHIFT) static void gic_send_sgi(u64 cluster_id, u16 tlist, unsigned int irq) { u64 val; val = (MPIDR_TO_SGI_AFFINITY(cluster_id, 3) | MPIDR_TO_SGI_AFFINITY(cluster_id, 2) | irq << ICC_SGI1R_SGI_ID_SHIFT | MPIDR_TO_SGI_AFFINITY(cluster_id, 1) | MPIDR_TO_SGI_RS(cluster_id) | tlist << ICC_SGI1R_TARGET_LIST_SHIFT); pr_devel("CPU%d: ICC_SGI1R_EL1 %llx\n", smp_processor_id(), val); gic_write_sgi1r(val); } static void gic_ipi_send_mask(struct irq_data *d, const struct cpumask *mask) { int cpu; if (WARN_ON(d->hwirq >= 16)) return; /* * Ensure that stores to Normal memory are visible to the * other CPUs before issuing the IPI. */ dsb(ishst); for_each_cpu(cpu, mask) { u64 cluster_id = MPIDR_TO_SGI_CLUSTER_ID(gic_cpu_to_affinity(cpu)); u16 tlist; tlist = gic_compute_target_list(&cpu, mask, cluster_id); gic_send_sgi(cluster_id, tlist, d->hwirq); } /* Force the above writes to ICC_SGI1R_EL1 to be executed */ isb(); } static void __init gic_smp_init(void) { struct irq_fwspec sgi_fwspec = { .fwnode = gic_data.fwnode, .param_count = 1, }; int base_sgi; cpuhp_setup_state_nocalls(CPUHP_AP_IRQ_GIC_STARTING, "irqchip/arm/gicv3:starting", gic_starting_cpu, NULL); /* Register all 8 non-secure SGIs */ base_sgi = irq_domain_alloc_irqs(gic_data.domain, 8, NUMA_NO_NODE, &sgi_fwspec); if (WARN_ON(base_sgi <= 0)) return; set_smp_ipi_range(base_sgi, 8); } static int gic_set_affinity(struct irq_data *d, const struct cpumask *mask_val, bool force) { unsigned int cpu; u32 offset, index; void __iomem *reg; int enabled; u64 val; if (force) cpu = cpumask_first(mask_val); else cpu = cpumask_any_and(mask_val, cpu_online_mask); if (cpu >= nr_cpu_ids) return -EINVAL; if (gic_irq_in_rdist(d)) return -EINVAL; /* If interrupt was enabled, disable it first */ enabled = gic_peek_irq(d, GICD_ISENABLER); if (enabled) gic_mask_irq(d); offset = convert_offset_index(d, GICD_IROUTER, &index); reg = gic_dist_base(d) + offset + (index * 8); val = gic_cpu_to_affinity(cpu); gic_write_irouter(val, reg); /* * If the interrupt was enabled, enabled it again. Otherwise, * just wait for the distributor to have digested our changes. */ if (enabled) gic_unmask_irq(d); irq_data_update_effective_affinity(d, cpumask_of(cpu)); return IRQ_SET_MASK_OK_DONE; } #else #define gic_set_affinity NULL #define gic_ipi_send_mask NULL #define gic_smp_init() do { } while(0) #endif static int gic_retrigger(struct irq_data *data) { return !gic_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING, true); } #ifdef CONFIG_CPU_PM static int gic_cpu_pm_notifier(struct notifier_block *self, unsigned long cmd, void *v) { if (cmd == CPU_PM_EXIT) { if (gic_dist_security_disabled()) gic_enable_redist(true); gic_cpu_sys_reg_init(); } else if (cmd == CPU_PM_ENTER && gic_dist_security_disabled()) { gic_write_grpen1(0); gic_enable_redist(false); } return NOTIFY_OK; } static struct notifier_block gic_cpu_pm_notifier_block = { .notifier_call = gic_cpu_pm_notifier, }; static void gic_cpu_pm_init(void) { cpu_pm_register_notifier(&gic_cpu_pm_notifier_block); } #else static inline void gic_cpu_pm_init(void) { } #endif /* CONFIG_CPU_PM */ static struct irq_chip gic_chip = { .name = "GICv3", .irq_mask = gic_mask_irq, .irq_unmask = gic_unmask_irq, .irq_eoi = gic_eoi_irq, .irq_set_type = gic_set_type, .irq_set_affinity = gic_set_affinity, .irq_retrigger = gic_retrigger, .irq_get_irqchip_state = gic_irq_get_irqchip_state, .irq_set_irqchip_state = gic_irq_set_irqchip_state, .irq_nmi_setup = gic_irq_nmi_setup, .irq_nmi_teardown = gic_irq_nmi_teardown, .ipi_send_mask = gic_ipi_send_mask, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; static struct irq_chip gic_eoimode1_chip = { .name = "GICv3", .irq_mask = gic_eoimode1_mask_irq, .irq_unmask = gic_unmask_irq, .irq_eoi = gic_eoimode1_eoi_irq, .irq_set_type = gic_set_type, .irq_set_affinity = gic_set_affinity, .irq_retrigger = gic_retrigger, .irq_get_irqchip_state = gic_irq_get_irqchip_state, .irq_set_irqchip_state = gic_irq_set_irqchip_state, .irq_set_vcpu_affinity = gic_irq_set_vcpu_affinity, .irq_nmi_setup = gic_irq_nmi_setup, .irq_nmi_teardown = gic_irq_nmi_teardown, .ipi_send_mask = gic_ipi_send_mask, .flags = IRQCHIP_SET_TYPE_MASKED | IRQCHIP_SKIP_SET_WAKE | IRQCHIP_MASK_ON_SUSPEND, }; static int gic_irq_domain_map(struct irq_domain *d, unsigned int irq, irq_hw_number_t hw) { struct irq_chip *chip = &gic_chip; struct irq_data *irqd = irq_desc_get_irq_data(irq_to_desc(irq)); if (static_branch_likely(&supports_deactivate_key)) chip = &gic_eoimode1_chip; switch (__get_intid_range(hw)) { case SGI_RANGE: case PPI_RANGE: case EPPI_RANGE: irq_set_percpu_devid(irq); irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_percpu_devid_irq, NULL, NULL); break; case SPI_RANGE: case ESPI_RANGE: irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); irq_set_probe(irq); irqd_set_single_target(irqd); break; case LPI_RANGE: if (!gic_dist_supports_lpis()) return -EPERM; irq_domain_set_info(d, irq, hw, chip, d->host_data, handle_fasteoi_irq, NULL, NULL); break; default: return -EPERM; } /* Prevents SW retriggers which mess up the ACK/EOI ordering */ irqd_set_handle_enforce_irqctx(irqd); return 0; } static int gic_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { if (fwspec->param_count == 1 && fwspec->param[0] < 16) { *hwirq = fwspec->param[0]; *type = IRQ_TYPE_EDGE_RISING; return 0; } if (is_of_node(fwspec->fwnode)) { if (fwspec->param_count < 3) return -EINVAL; switch (fwspec->param[0]) { case 0: /* SPI */ *hwirq = fwspec->param[1] + 32; break; case 1: /* PPI */ *hwirq = fwspec->param[1] + 16; break; case 2: /* ESPI */ *hwirq = fwspec->param[1] + ESPI_BASE_INTID; break; case 3: /* EPPI */ *hwirq = fwspec->param[1] + EPPI_BASE_INTID; break; case GIC_IRQ_TYPE_LPI: /* LPI */ *hwirq = fwspec->param[1]; break; case GIC_IRQ_TYPE_PARTITION: *hwirq = fwspec->param[1]; if (fwspec->param[1] >= 16) *hwirq += EPPI_BASE_INTID - 16; else *hwirq += 16; break; default: return -EINVAL; } *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; /* * Make it clear that broken DTs are... broken. * Partitioned PPIs are an unfortunate exception. */ WARN_ON(*type == IRQ_TYPE_NONE && fwspec->param[0] != GIC_IRQ_TYPE_PARTITION); return 0; } if (is_fwnode_irqchip(fwspec->fwnode)) { if(fwspec->param_count != 2) return -EINVAL; if (fwspec->param[0] < 16) { pr_err(FW_BUG "Illegal GSI%d translation request\n", fwspec->param[0]); return -EINVAL; } *hwirq = fwspec->param[0]; *type = fwspec->param[1]; WARN_ON(*type == IRQ_TYPE_NONE); return 0; } return -EINVAL; } static int gic_irq_domain_alloc(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs, void *arg) { int i, ret; irq_hw_number_t hwirq; unsigned int type = IRQ_TYPE_NONE; struct irq_fwspec *fwspec = arg; ret = gic_irq_domain_translate(domain, fwspec, &hwirq, &type); if (ret) return ret; for (i = 0; i < nr_irqs; i++) { ret = gic_irq_domain_map(domain, virq + i, hwirq + i); if (ret) return ret; } return 0; } static void gic_irq_domain_free(struct irq_domain *domain, unsigned int virq, unsigned int nr_irqs) { int i; for (i = 0; i < nr_irqs; i++) { struct irq_data *d = irq_domain_get_irq_data(domain, virq + i); irq_set_handler(virq + i, NULL); irq_domain_reset_irq_data(d); } } static bool fwspec_is_partitioned_ppi(struct irq_fwspec *fwspec, irq_hw_number_t hwirq) { enum gic_intid_range range; if (!gic_data.ppi_descs) return false; if (!is_of_node(fwspec->fwnode)) return false; if (fwspec->param_count < 4 || !fwspec->param[3]) return false; range = __get_intid_range(hwirq); if (range != PPI_RANGE && range != EPPI_RANGE) return false; return true; } static int gic_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec, enum irq_domain_bus_token bus_token) { unsigned int type, ret, ppi_idx; irq_hw_number_t hwirq; /* Not for us */ if (fwspec->fwnode != d->fwnode) return 0; /* Handle pure domain searches */ if (!fwspec->param_count) return d->bus_token == bus_token; /* If this is not DT, then we have a single domain */ if (!is_of_node(fwspec->fwnode)) return 1; ret = gic_irq_domain_translate(d, fwspec, &hwirq, &type); if (WARN_ON_ONCE(ret)) return 0; if (!fwspec_is_partitioned_ppi(fwspec, hwirq)) return d == gic_data.domain; /* * If this is a PPI and we have a 4th (non-null) parameter, * then we need to match the partition domain. */ ppi_idx = __gic_get_ppi_index(hwirq); return d == partition_get_domain(gic_data.ppi_descs[ppi_idx]); } static const struct irq_domain_ops gic_irq_domain_ops = { .translate = gic_irq_domain_translate, .alloc = gic_irq_domain_alloc, .free = gic_irq_domain_free, .select = gic_irq_domain_select, }; static int partition_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec, unsigned long *hwirq, unsigned int *type) { unsigned long ppi_intid; struct device_node *np; unsigned int ppi_idx; int ret; if (!gic_data.ppi_descs) return -ENOMEM; np = of_find_node_by_phandle(fwspec->param[3]); if (WARN_ON(!np)) return -EINVAL; ret = gic_irq_domain_translate(d, fwspec, &ppi_intid, type); if (WARN_ON_ONCE(ret)) return 0; ppi_idx = __gic_get_ppi_index(ppi_intid); ret = partition_translate_id(gic_data.ppi_descs[ppi_idx], of_node_to_fwnode(np)); if (ret < 0) return ret; *hwirq = ret; *type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK; return 0; } static const struct irq_domain_ops partition_domain_ops = { .translate = partition_domain_translate, .select = gic_irq_domain_select, }; static bool gic_enable_quirk_msm8996(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_GICR_WAKER_MSM8996; return true; } static bool gic_enable_quirk_cavium_38539(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539; return true; } static bool gic_enable_quirk_hip06_07(void *data) { struct gic_chip_data *d = data; /* * HIP06 GICD_IIDR clashes with GIC-600 product number (despite * not being an actual ARM implementation). The saving grace is * that GIC-600 doesn't have ESPI, so nothing to do in that case. * HIP07 doesn't even have a proper IIDR, and still pretends to * have ESPI. In both cases, put them right. */ if (d->rdists.gicd_typer & GICD_TYPER_ESPI) { /* Zero both ESPI and the RES0 field next to it... */ d->rdists.gicd_typer &= ~GENMASK(9, 8); return true; } return false; } #define T241_CHIPN_MASK GENMASK_ULL(45, 44) #define T241_CHIP_GICDA_OFFSET 0x1580000 #define SMCCC_SOC_ID_T241 0x036b0241 static bool gic_enable_quirk_nvidia_t241(void *data) { s32 soc_id = arm_smccc_get_soc_id_version(); unsigned long chip_bmask = 0; phys_addr_t phys; u32 i; /* Check JEP106 code for NVIDIA T241 chip (036b:0241) */ if ((soc_id < 0) || (soc_id != SMCCC_SOC_ID_T241)) return false; /* Find the chips based on GICR regions PHYS addr */ for (i = 0; i < gic_data.nr_redist_regions; i++) { chip_bmask |= BIT(FIELD_GET(T241_CHIPN_MASK, (u64)gic_data.redist_regions[i].phys_base)); } if (hweight32(chip_bmask) < 3) return false; /* Setup GICD alias regions */ for (i = 0; i < ARRAY_SIZE(t241_dist_base_alias); i++) { if (chip_bmask & BIT(i)) { phys = gic_data.dist_phys_base + T241_CHIP_GICDA_OFFSET; phys |= FIELD_PREP(T241_CHIPN_MASK, i); t241_dist_base_alias[i] = ioremap(phys, SZ_64K); WARN_ON_ONCE(!t241_dist_base_alias[i]); } } static_branch_enable(&gic_nvidia_t241_erratum); return true; } static bool gic_enable_quirk_asr8601(void *data) { struct gic_chip_data *d = data; d->flags |= FLAGS_WORKAROUND_ASR_ERRATUM_8601001; return true; } static bool gic_enable_quirk_arm64_2941627(void *data) { static_branch_enable(&gic_arm64_2941627_erratum); return true; } static bool rd_set_non_coherent(void *data) { struct gic_chip_data *d = data; d->rdists.flags |= RDIST_FLAGS_FORCE_NON_SHAREABLE; return true; } static const struct gic_quirk gic_quirks[] = { { .desc = "GICv3: Qualcomm MSM8996 broken firmware", .compatible = "qcom,msm8996-gic-v3", .init = gic_enable_quirk_msm8996, }, { .desc = "GICv3: ASR erratum 8601001", .compatible = "asr,asr8601-gic-v3", .init = gic_enable_quirk_asr8601, }, { .desc = "GICv3: HIP06 erratum 161010803", .iidr = 0x0204043b, .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, { .desc = "GICv3: HIP07 erratum 161010803", .iidr = 0x00000000, .mask = 0xffffffff, .init = gic_enable_quirk_hip06_07, }, { /* * Reserved register accesses generate a Synchronous * External Abort. This erratum applies to: * - ThunderX: CN88xx * - OCTEON TX: CN83xx, CN81xx * - OCTEON TX2: CN93xx, CN96xx, CN98xx, CNF95xx* */ .desc = "GICv3: Cavium erratum 38539", .iidr = 0xa000034c, .mask = 0xe8f00fff, .init = gic_enable_quirk_cavium_38539, }, { .desc = "GICv3: NVIDIA erratum T241-FABRIC-4", .iidr = 0x0402043b, .mask = 0xffffffff, .init = gic_enable_quirk_nvidia_t241, }, { /* * GIC-700: 2941627 workaround - IP variant [0,1] * */ .desc = "GICv3: ARM64 erratum 2941627", .iidr = 0x0400043b, .mask = 0xff0e0fff, .init = gic_enable_quirk_arm64_2941627, }, { /* * GIC-700: 2941627 workaround - IP variant [2] */ .desc = "GICv3: ARM64 erratum 2941627", .iidr = 0x0402043b, .mask = 0xff0f0fff, .init = gic_enable_quirk_arm64_2941627, }, { .desc = "GICv3: non-coherent attribute", .property = "dma-noncoherent", .init = rd_set_non_coherent, }, { } }; static void gic_enable_nmi_support(void) { int i; if (!gic_prio_masking_enabled()) return; rdist_nmi_refs = kcalloc(gic_data.ppi_nr + SGI_NR, sizeof(*rdist_nmi_refs), GFP_KERNEL); if (!rdist_nmi_refs) return; for (i = 0; i < gic_data.ppi_nr + SGI_NR; i++) refcount_set(&rdist_nmi_refs[i], 0); pr_info("Pseudo-NMIs enabled using %s ICC_PMR_EL1 synchronisation\n", gic_has_relaxed_pmr_sync() ? "relaxed" : "forced"); /* * How priority values are used by the GIC depends on two things: * the security state of the GIC (controlled by the GICD_CTRL.DS bit) * and if Group 0 interrupts can be delivered to Linux in the non-secure * world as FIQs (controlled by the SCR_EL3.FIQ bit). These affect the * ICC_PMR_EL1 register and the priority that software assigns to * interrupts: * * GICD_CTRL.DS | SCR_EL3.FIQ | ICC_PMR_EL1 | Group 1 priority * ----------------------------------------------------------- * 1 | - | unchanged | unchanged * ----------------------------------------------------------- * 0 | 1 | non-secure | non-secure * ----------------------------------------------------------- * 0 | 0 | unchanged | non-secure * * where non-secure means that the value is right-shifted by one and the * MSB bit set, to make it fit in the non-secure priority range. * * In the first two cases, where ICC_PMR_EL1 and the interrupt priority * are both either modified or unchanged, we can use the same set of * priorities. * * In the last case, where only the interrupt priorities are modified to * be in the non-secure range, we use a different PMR value to mask IRQs * and the rest of the values that we use remain unchanged. */ if (gic_has_group0() && !gic_dist_security_disabled()) static_branch_enable(&gic_nonsecure_priorities); static_branch_enable(&supports_pseudo_nmis); if (static_branch_likely(&supports_deactivate_key)) gic_eoimode1_chip.flags |= IRQCHIP_SUPPORTS_NMI; else gic_chip.flags |= IRQCHIP_SUPPORTS_NMI; } static int __init gic_init_bases(phys_addr_t dist_phys_base, void __iomem *dist_base, struct redist_region *rdist_regs, u32 nr_redist_regions, u64 redist_stride, struct fwnode_handle *handle) { u32 typer; int err; if (!is_hyp_mode_available()) static_branch_disable(&supports_deactivate_key); if (static_branch_likely(&supports_deactivate_key)) pr_info("GIC: Using split EOI/Deactivate mode\n"); gic_data.fwnode = handle; gic_data.dist_phys_base = dist_phys_base; gic_data.dist_base = dist_base; gic_data.redist_regions = rdist_regs; gic_data.nr_redist_regions = nr_redist_regions; gic_data.redist_stride = redist_stride; /* * Find out how many interrupts are supported. */ typer = readl_relaxed(gic_data.dist_base + GICD_TYPER); gic_data.rdists.gicd_typer = typer; gic_enable_quirks(readl_relaxed(gic_data.dist_base + GICD_IIDR), gic_quirks, &gic_data); pr_info("%d SPIs implemented\n", GIC_LINE_NR - 32); pr_info("%d Extended SPIs implemented\n", GIC_ESPI_NR); /* * ThunderX1 explodes on reading GICD_TYPER2, in violation of the * architecture spec (which says that reserved registers are RES0). */ if (!(gic_data.flags & FLAGS_WORKAROUND_CAVIUM_ERRATUM_38539)) gic_data.rdists.gicd_typer2 = readl_relaxed(gic_data.dist_base + GICD_TYPER2); gic_data.domain = irq_domain_create_tree(handle, &gic_irq_domain_ops, &gic_data); gic_data.rdists.rdist = alloc_percpu(typeof(*gic_data.rdists.rdist)); if (!static_branch_unlikely(&gic_nvidia_t241_erratum)) { /* Disable GICv4.x features for the erratum T241-FABRIC-4 */ gic_data.rdists.has_rvpeid = true; gic_data.rdists.has_vlpis = true; gic_data.rdists.has_direct_lpi = true; gic_data.rdists.has_vpend_valid_dirty = true; } if (WARN_ON(!gic_data.domain) || WARN_ON(!gic_data.rdists.rdist)) { err = -ENOMEM; goto out_free; } irq_domain_update_bus_token(gic_data.domain, DOMAIN_BUS_WIRED); gic_data.has_rss = !!(typer & GICD_TYPER_RSS); if (typer & GICD_TYPER_MBIS) { err = mbi_init(handle, gic_data.domain); if (err) pr_err("Failed to initialize MBIs\n"); } set_handle_irq(gic_handle_irq); gic_update_rdist_properties(); gic_dist_init(); gic_cpu_init(); gic_enable_nmi_support(); gic_smp_init(); gic_cpu_pm_init(); if (gic_dist_supports_lpis()) { its_init(handle, &gic_data.rdists, gic_data.domain); its_cpu_init(); its_lpi_memreserve_init(); } else { if (IS_ENABLED(CONFIG_ARM_GIC_V2M)) gicv2m_init(handle, gic_data.domain); } return 0; out_free: if (gic_data.domain) irq_domain_remove(gic_data.domain); free_percpu(gic_data.rdists.rdist); return err; } static int __init gic_validate_dist_version(void __iomem *dist_base) { u32 reg = readl_relaxed(dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; if (reg != GIC_PIDR2_ARCH_GICv3 && reg != GIC_PIDR2_ARCH_GICv4) return -ENODEV; return 0; } /* Create all possible partitions at boot time */ static void __init gic_populate_ppi_partitions(struct device_node *gic_node) { struct device_node *parts_node, *child_part; int part_idx = 0, i; int nr_parts; struct partition_affinity *parts; parts_node = of_get_child_by_name(gic_node, "ppi-partitions"); if (!parts_node) return; gic_data.ppi_descs = kcalloc(gic_data.ppi_nr, sizeof(*gic_data.ppi_descs), GFP_KERNEL); if (!gic_data.ppi_descs) goto out_put_node; nr_parts = of_get_child_count(parts_node); if (!nr_parts) goto out_put_node; parts = kcalloc(nr_parts, sizeof(*parts), GFP_KERNEL); if (WARN_ON(!parts)) goto out_put_node; for_each_child_of_node(parts_node, child_part) { struct partition_affinity *part; int n; part = &parts[part_idx]; part->partition_id = of_node_to_fwnode(child_part); pr_info("GIC: PPI partition %pOFn[%d] { ", child_part, part_idx); n = of_property_count_elems_of_size(child_part, "affinity", sizeof(u32)); WARN_ON(n <= 0); for (i = 0; i < n; i++) { int err, cpu; u32 cpu_phandle; struct device_node *cpu_node; err = of_property_read_u32_index(child_part, "affinity", i, &cpu_phandle); if (WARN_ON(err)) continue; cpu_node = of_find_node_by_phandle(cpu_phandle); if (WARN_ON(!cpu_node)) continue; cpu = of_cpu_node_to_id(cpu_node); if (WARN_ON(cpu < 0)) { of_node_put(cpu_node); continue; } pr_cont("%pOF[%d] ", cpu_node, cpu); cpumask_set_cpu(cpu, &part->mask); of_node_put(cpu_node); } pr_cont("}\n"); part_idx++; } for (i = 0; i < gic_data.ppi_nr; i++) { unsigned int irq; struct partition_desc *desc; struct irq_fwspec ppi_fwspec = { .fwnode = gic_data.fwnode, .param_count = 3, .param = { [0] = GIC_IRQ_TYPE_PARTITION, [1] = i, [2] = IRQ_TYPE_NONE, }, }; irq = irq_create_fwspec_mapping(&ppi_fwspec); if (WARN_ON(!irq)) continue; desc = partition_create_desc(gic_data.fwnode, parts, nr_parts, irq, &partition_domain_ops); if (WARN_ON(!desc)) continue; gic_data.ppi_descs[i] = desc; } out_put_node: of_node_put(parts_node); } static void __init gic_of_setup_kvm_info(struct device_node *node) { int ret; struct resource r; u32 gicv_idx; gic_v3_kvm_info.type = GIC_V3; gic_v3_kvm_info.maint_irq = irq_of_parse_and_map(node, 0); if (!gic_v3_kvm_info.maint_irq) return; if (of_property_read_u32(node, "#redistributor-regions", &gicv_idx)) gicv_idx = 1; gicv_idx += 3; /* Also skip GICD, GICC, GICH */ ret = of_address_to_resource(node, gicv_idx, &r); if (!ret) gic_v3_kvm_info.vcpu = r; gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; vgic_set_kvm_info(&gic_v3_kvm_info); } static void gic_request_region(resource_size_t base, resource_size_t size, const char *name) { if (!request_mem_region(base, size, name)) pr_warn_once(FW_BUG "%s region %pa has overlapping address\n", name, &base); } static void __iomem *gic_of_iomap(struct device_node *node, int idx, const char *name, struct resource *res) { void __iomem *base; int ret; ret = of_address_to_resource(node, idx, res); if (ret) return IOMEM_ERR_PTR(ret); gic_request_region(res->start, resource_size(res), name); base = of_iomap(node, idx); return base ?: IOMEM_ERR_PTR(-ENOMEM); } static int __init gic_of_init(struct device_node *node, struct device_node *parent) { phys_addr_t dist_phys_base; void __iomem *dist_base; struct redist_region *rdist_regs; struct resource res; u64 redist_stride; u32 nr_redist_regions; int err, i; dist_base = gic_of_iomap(node, 0, "GICD", &res); if (IS_ERR(dist_base)) { pr_err("%pOF: unable to map gic dist registers\n", node); return PTR_ERR(dist_base); } dist_phys_base = res.start; err = gic_validate_dist_version(dist_base); if (err) { pr_err("%pOF: no distributor detected, giving up\n", node); goto out_unmap_dist; } if (of_property_read_u32(node, "#redistributor-regions", &nr_redist_regions)) nr_redist_regions = 1; rdist_regs = kcalloc(nr_redist_regions, sizeof(*rdist_regs), GFP_KERNEL); if (!rdist_regs) { err = -ENOMEM; goto out_unmap_dist; } for (i = 0; i < nr_redist_regions; i++) { rdist_regs[i].redist_base = gic_of_iomap(node, 1 + i, "GICR", &res); if (IS_ERR(rdist_regs[i].redist_base)) { pr_err("%pOF: couldn't map region %d\n", node, i); err = -ENODEV; goto out_unmap_rdist; } rdist_regs[i].phys_base = res.start; } if (of_property_read_u64(node, "redistributor-stride", &redist_stride)) redist_stride = 0; gic_enable_of_quirks(node, gic_quirks, &gic_data); err = gic_init_bases(dist_phys_base, dist_base, rdist_regs, nr_redist_regions, redist_stride, &node->fwnode); if (err) goto out_unmap_rdist; gic_populate_ppi_partitions(node); if (static_branch_likely(&supports_deactivate_key)) gic_of_setup_kvm_info(node); return 0; out_unmap_rdist: for (i = 0; i < nr_redist_regions; i++) if (rdist_regs[i].redist_base && !IS_ERR(rdist_regs[i].redist_base)) iounmap(rdist_regs[i].redist_base); kfree(rdist_regs); out_unmap_dist: iounmap(dist_base); return err; } IRQCHIP_DECLARE(gic_v3, "arm,gic-v3", gic_of_init); #ifdef CONFIG_ACPI static struct { void __iomem *dist_base; struct redist_region *redist_regs; u32 nr_redist_regions; bool single_redist; int enabled_rdists; u32 maint_irq; int maint_irq_mode; phys_addr_t vcpu_base; } acpi_data __initdata; static void __init gic_acpi_register_redist(phys_addr_t phys_base, void __iomem *redist_base) { static int count = 0; acpi_data.redist_regs[count].phys_base = phys_base; acpi_data.redist_regs[count].redist_base = redist_base; acpi_data.redist_regs[count].single_redist = acpi_data.single_redist; count++; } static int __init gic_acpi_parse_madt_redist(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_redistributor *redist = (struct acpi_madt_generic_redistributor *)header; void __iomem *redist_base; redist_base = ioremap(redist->base_address, redist->length); if (!redist_base) { pr_err("Couldn't map GICR region @%llx\n", redist->base_address); return -ENOMEM; } gic_request_region(redist->base_address, redist->length, "GICR"); gic_acpi_register_redist(redist->base_address, redist_base); return 0; } static int __init gic_acpi_parse_madt_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; u32 reg = readl_relaxed(acpi_data.dist_base + GICD_PIDR2) & GIC_PIDR2_ARCH_MASK; u32 size = reg == GIC_PIDR2_ARCH_GICv4 ? SZ_64K * 4 : SZ_64K * 2; void __iomem *redist_base; if (!acpi_gicc_is_usable(gicc)) return 0; redist_base = ioremap(gicc->gicr_base_address, size); if (!redist_base) return -ENOMEM; gic_request_region(gicc->gicr_base_address, size, "GICR"); gic_acpi_register_redist(gicc->gicr_base_address, redist_base); return 0; } static int __init gic_acpi_collect_gicr_base(void) { acpi_tbl_entry_handler redist_parser; enum acpi_madt_type type; if (acpi_data.single_redist) { type = ACPI_MADT_TYPE_GENERIC_INTERRUPT; redist_parser = gic_acpi_parse_madt_gicc; } else { type = ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR; redist_parser = gic_acpi_parse_madt_redist; } /* Collect redistributor base addresses in GICR entries */ if (acpi_table_parse_madt(type, redist_parser, 0) > 0) return 0; pr_info("No valid GICR entries exist\n"); return -ENODEV; } static int __init gic_acpi_match_gicr(union acpi_subtable_headers *header, const unsigned long end) { /* Subtable presence means that redist exists, that's it */ return 0; } static int __init gic_acpi_match_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; /* * If GICC is enabled and has valid gicr base address, then it means * GICR base is presented via GICC */ if (acpi_gicc_is_usable(gicc) && gicc->gicr_base_address) { acpi_data.enabled_rdists++; return 0; } /* * It's perfectly valid firmware can pass disabled GICC entry, driver * should not treat as errors, skip the entry instead of probe fail. */ if (!acpi_gicc_is_usable(gicc)) return 0; return -ENODEV; } static int __init gic_acpi_count_gicr_regions(void) { int count; /* * Count how many redistributor regions we have. It is not allowed * to mix redistributor description, GICR and GICC subtables have to be * mutually exclusive. */ count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_REDISTRIBUTOR, gic_acpi_match_gicr, 0); if (count > 0) { acpi_data.single_redist = false; return count; } count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_match_gicc, 0); if (count > 0) { acpi_data.single_redist = true; count = acpi_data.enabled_rdists; } return count; } static bool __init acpi_validate_gic_table(struct acpi_subtable_header *header, struct acpi_probe_entry *ape) { struct acpi_madt_generic_distributor *dist; int count; dist = (struct acpi_madt_generic_distributor *)header; if (dist->version != ape->driver_data) return false; /* We need to do that exercise anyway, the sooner the better */ count = gic_acpi_count_gicr_regions(); if (count <= 0) return false; acpi_data.nr_redist_regions = count; return true; } static int __init gic_acpi_parse_virt_madt_gicc(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_interrupt *gicc = (struct acpi_madt_generic_interrupt *)header; int maint_irq_mode; static int first_madt = true; if (!acpi_gicc_is_usable(gicc)) return 0; maint_irq_mode = (gicc->flags & ACPI_MADT_VGIC_IRQ_MODE) ? ACPI_EDGE_SENSITIVE : ACPI_LEVEL_SENSITIVE; if (first_madt) { first_madt = false; acpi_data.maint_irq = gicc->vgic_interrupt; acpi_data.maint_irq_mode = maint_irq_mode; acpi_data.vcpu_base = gicc->gicv_base_address; return 0; } /* * The maintenance interrupt and GICV should be the same for every CPU */ if ((acpi_data.maint_irq != gicc->vgic_interrupt) || (acpi_data.maint_irq_mode != maint_irq_mode) || (acpi_data.vcpu_base != gicc->gicv_base_address)) return -EINVAL; return 0; } static bool __init gic_acpi_collect_virt_info(void) { int count; count = acpi_table_parse_madt(ACPI_MADT_TYPE_GENERIC_INTERRUPT, gic_acpi_parse_virt_madt_gicc, 0); return (count > 0); } #define ACPI_GICV3_DIST_MEM_SIZE (SZ_64K) #define ACPI_GICV2_VCTRL_MEM_SIZE (SZ_4K) #define ACPI_GICV2_VCPU_MEM_SIZE (SZ_8K) static void __init gic_acpi_setup_kvm_info(void) { int irq; if (!gic_acpi_collect_virt_info()) { pr_warn("Unable to get hardware information used for virtualization\n"); return; } gic_v3_kvm_info.type = GIC_V3; irq = acpi_register_gsi(NULL, acpi_data.maint_irq, acpi_data.maint_irq_mode, ACPI_ACTIVE_HIGH); if (irq <= 0) return; gic_v3_kvm_info.maint_irq = irq; if (acpi_data.vcpu_base) { struct resource *vcpu = &gic_v3_kvm_info.vcpu; vcpu->flags = IORESOURCE_MEM; vcpu->start = acpi_data.vcpu_base; vcpu->end = vcpu->start + ACPI_GICV2_VCPU_MEM_SIZE - 1; } gic_v3_kvm_info.has_v4 = gic_data.rdists.has_vlpis; gic_v3_kvm_info.has_v4_1 = gic_data.rdists.has_rvpeid; vgic_set_kvm_info(&gic_v3_kvm_info); } static struct fwnode_handle *gsi_domain_handle; static struct fwnode_handle *gic_v3_get_gsi_domain_id(u32 gsi) { return gsi_domain_handle; } static int __init gic_acpi_init(union acpi_subtable_headers *header, const unsigned long end) { struct acpi_madt_generic_distributor *dist; size_t size; int i, err; /* Get distributor base address */ dist = (struct acpi_madt_generic_distributor *)header; acpi_data.dist_base = ioremap(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE); if (!acpi_data.dist_base) { pr_err("Unable to map GICD registers\n"); return -ENOMEM; } gic_request_region(dist->base_address, ACPI_GICV3_DIST_MEM_SIZE, "GICD"); err = gic_validate_dist_version(acpi_data.dist_base); if (err) { pr_err("No distributor detected at @%p, giving up\n", acpi_data.dist_base); goto out_dist_unmap; } size = sizeof(*acpi_data.redist_regs) * acpi_data.nr_redist_regions; acpi_data.redist_regs = kzalloc(size, GFP_KERNEL); if (!acpi_data.redist_regs) { err = -ENOMEM; goto out_dist_unmap; } err = gic_acpi_collect_gicr_base(); if (err) goto out_redist_unmap; gsi_domain_handle = irq_domain_alloc_fwnode(&dist->base_address); if (!gsi_domain_handle) { err = -ENOMEM; goto out_redist_unmap; } err = gic_init_bases(dist->base_address, acpi_data.dist_base, acpi_data.redist_regs, acpi_data.nr_redist_regions, 0, gsi_domain_handle); if (err) goto out_fwhandle_free; acpi_set_irq_model(ACPI_IRQ_MODEL_GIC, gic_v3_get_gsi_domain_id); if (static_branch_likely(&supports_deactivate_key)) gic_acpi_setup_kvm_info(); return 0; out_fwhandle_free: irq_domain_free_fwnode(gsi_domain_handle); out_redist_unmap: for (i = 0; i < acpi_data.nr_redist_regions; i++) if (acpi_data.redist_regs[i].redist_base) iounmap(acpi_data.redist_regs[i].redist_base); kfree(acpi_data.redist_regs); out_dist_unmap: iounmap(acpi_data.dist_base); return err; } IRQCHIP_ACPI_DECLARE(gic_v3, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V3, gic_acpi_init); IRQCHIP_ACPI_DECLARE(gic_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_V4, gic_acpi_init); IRQCHIP_ACPI_DECLARE(gic_v3_or_v4, ACPI_MADT_TYPE_GENERIC_DISTRIBUTOR, acpi_validate_gic_table, ACPI_MADT_GIC_VERSION_NONE, gic_acpi_init); #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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_NAMEI_H #define _LINUX_NAMEI_H #include <linux/fs.h> #include <linux/kernel.h> #include <linux/path.h> #include <linux/fcntl.h> #include <linux/errno.h> enum { MAX_NESTED_LINKS = 8 }; #define MAXSYMLINKS 40 /* * Type of the last component on LOOKUP_PARENT */ enum {LAST_NORM, LAST_ROOT, LAST_DOT, LAST_DOTDOT}; /* pathwalk mode */ #define LOOKUP_FOLLOW 0x0001 /* follow links at the end */ #define LOOKUP_DIRECTORY 0x0002 /* require a directory */ #define LOOKUP_AUTOMOUNT 0x0004 /* force terminal automount */ #define LOOKUP_EMPTY 0x4000 /* accept empty path [user_... only] */ #define LOOKUP_DOWN 0x8000 /* follow mounts in the starting point */ #define LOOKUP_MOUNTPOINT 0x0080 /* follow mounts in the end */ #define LOOKUP_REVAL 0x0020 /* tell ->d_revalidate() to trust no cache */ #define LOOKUP_RCU 0x0040 /* RCU pathwalk mode; semi-internal */ /* These tell filesystem methods that we are dealing with the final component... */ #define LOOKUP_OPEN 0x0100 /* ... in open */ #define LOOKUP_CREATE 0x0200 /* ... in object creation */ #define LOOKUP_EXCL 0x0400 /* ... in exclusive creation */ #define LOOKUP_RENAME_TARGET 0x0800 /* ... in destination of rename() */ /* internal use only */ #define LOOKUP_PARENT 0x0010 /* Scoping flags for lookup. */ #define LOOKUP_NO_SYMLINKS 0x010000 /* No symlink crossing. */ #define LOOKUP_NO_MAGICLINKS 0x020000 /* No nd_jump_link() crossing. */ #define LOOKUP_NO_XDEV 0x040000 /* No mountpoint crossing. */ #define LOOKUP_BENEATH 0x080000 /* No escaping from starting point. */ #define LOOKUP_IN_ROOT 0x100000 /* Treat dirfd as fs root. */ #define LOOKUP_CACHED 0x200000 /* Only do cached lookup */ #define LOOKUP_LINKAT_EMPTY 0x400000 /* Linkat request with empty path. */ /* LOOKUP_* flags which do scope-related checks based on the dirfd. */ #define LOOKUP_IS_SCOPED (LOOKUP_BENEATH | LOOKUP_IN_ROOT) extern int path_pts(struct path *path); extern int user_path_at_empty(int, const char __user *, unsigned, struct path *, int *empty); static inline int user_path_at(int dfd, const char __user *name, unsigned flags, struct path *path) { return user_path_at_empty(dfd, name, flags, path, NULL); } struct dentry *lookup_one_qstr_excl(const struct qstr *name, struct dentry *base, unsigned int flags); extern int kern_path(const char *, unsigned, struct path *); extern struct dentry *kern_path_create(int, const char *, struct path *, unsigned int); extern struct dentry *user_path_create(int, const char __user *, struct path *, unsigned int); extern void done_path_create(struct path *, struct dentry *); extern struct dentry *kern_path_locked(const char *, struct path *); extern struct dentry *user_path_locked_at(int , const char __user *, struct path *); int vfs_path_parent_lookup(struct filename *filename, unsigned int flags, struct path *parent, struct qstr *last, int *type, const struct path *root); int vfs_path_lookup(struct dentry *, struct vfsmount *, const char *, unsigned int, struct path *); extern struct dentry *try_lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len(const char *, struct dentry *, int); extern struct dentry *lookup_one_len_unlocked(const char *, struct dentry *, int); extern struct dentry *lookup_positive_unlocked(const char *, struct dentry *, int); struct dentry *lookup_one(struct mnt_idmap *, const char *, struct dentry *, int); struct dentry *lookup_one_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); struct dentry *lookup_one_positive_unlocked(struct mnt_idmap *idmap, const char *name, struct dentry *base, int len); extern int follow_down_one(struct path *); extern int follow_down(struct path *path, unsigned int flags); extern int follow_up(struct path *); extern struct dentry *lock_rename(struct dentry *, struct dentry *); extern struct dentry *lock_rename_child(struct dentry *, struct dentry *); extern void unlock_rename(struct dentry *, struct dentry *); /** * mode_strip_umask - handle vfs umask stripping * @dir: parent directory of the new inode * @mode: mode of the new inode to be created in @dir * * In most filesystems, umask stripping depends on whether or not the * filesystem supports POSIX ACLs. If the filesystem doesn't support it umask * stripping is done directly in here. If the filesystem does support POSIX * ACLs umask stripping is deferred until the filesystem calls * posix_acl_create(). * * Some filesystems (like NFSv4) also want to avoid umask stripping by the * VFS, but don't support POSIX ACLs. Those filesystems can set SB_I_NOUMASK * to get this effect without declaring that they support POSIX ACLs. * * Returns: mode */ static inline umode_t __must_check mode_strip_umask(const struct inode *dir, umode_t mode) { if (!IS_POSIXACL(dir) && !(dir->i_sb->s_iflags & SB_I_NOUMASK)) mode &= ~current_umask(); return mode; } extern int __must_check nd_jump_link(const struct path *path); static inline void nd_terminate_link(void *name, size_t len, size_t maxlen) { ((char *) name)[min(len, maxlen)] = '\0'; } /** * retry_estale - determine whether the caller should retry an operation * @error: the error that would currently be returned * @flags: flags being used for next lookup attempt * * Check to see if the error code was -ESTALE, and then determine whether * to retry the call based on whether "flags" already has LOOKUP_REVAL set. * * Returns true if the caller should try the operation again. */ static inline bool retry_estale(const long error, const unsigned int flags) { return unlikely(error == -ESTALE && !(flags & LOOKUP_REVAL)); } #endif /* _LINUX_NAMEI_H */ |
| 61 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 | /* 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_KCMP struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff); #endif /* 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(!file->f_ep)) 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); } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock); /* Tells if the epoll_ctl(2) operation needs an event copy from userspace */ static inline int ep_op_has_event(int op) { return op != EPOLL_CTL_DEL; } #else static inline void eventpoll_release(struct file *file) {} #endif #if defined(CONFIG_ARM) && defined(CONFIG_OABI_COMPAT) /* ARM OABI has an incompatible struct layout and needs a special handler */ extern struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent); #else static inline struct epoll_event __user * epoll_put_uevent(__poll_t revents, __u64 data, struct epoll_event __user *uevent) { if (__put_user(revents, &uevent->events) || __put_user(data, &uevent->data)) return NULL; return uevent+1; } #endif #endif /* #ifndef _LINUX_EVENTPOLL_H */ |
| 150 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 | /* SPDX-License-Identifier: GPL-2.0 */ #undef TRACE_SYSTEM #define TRACE_SYSTEM skb #if !defined(_TRACE_SKB_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_SKB_H #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/tracepoint.h> #undef FN #define FN(reason) TRACE_DEFINE_ENUM(SKB_DROP_REASON_##reason); DEFINE_DROP_REASON(FN, FN) #undef FN #undef FNe #define FN(reason) { SKB_DROP_REASON_##reason, #reason }, #define FNe(reason) { SKB_DROP_REASON_##reason, #reason } /* * Tracepoint for free an sk_buff: */ TRACE_EVENT(kfree_skb, TP_PROTO(struct sk_buff *skb, void *location, enum skb_drop_reason reason), TP_ARGS(skb, location, reason), TP_STRUCT__entry( __field(void *, skbaddr) __field(void *, location) __field(unsigned short, protocol) __field(enum skb_drop_reason, reason) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; __entry->protocol = ntohs(skb->protocol); __entry->reason = reason; ), TP_printk("skbaddr=%p protocol=%u location=%pS reason: %s", __entry->skbaddr, __entry->protocol, __entry->location, __print_symbolic(__entry->reason, DEFINE_DROP_REASON(FN, FNe))) ); #undef FN #undef FNe TRACE_EVENT(consume_skb, TP_PROTO(struct sk_buff *skb, void *location), TP_ARGS(skb, location), TP_STRUCT__entry( __field( void *, skbaddr) __field( void *, location) ), TP_fast_assign( __entry->skbaddr = skb; __entry->location = location; ), TP_printk("skbaddr=%p location=%pS", __entry->skbaddr, __entry->location) ); TRACE_EVENT(skb_copy_datagram_iovec, TP_PROTO(const struct sk_buff *skb, int len), TP_ARGS(skb, len), TP_STRUCT__entry( __field( const void *, skbaddr ) __field( int, len ) ), TP_fast_assign( __entry->skbaddr = skb; __entry->len = len; ), TP_printk("skbaddr=%p len=%d", __entry->skbaddr, __entry->len) ); #endif /* _TRACE_SKB_H */ /* This part must be outside protection */ #include <trace/define_trace.h> |
| 49 49 49 49 48 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com> */ /* * fsnotify inode mark locking/lifetime/and refcnting * * REFCNT: * The group->recnt and mark->refcnt tell how many "things" in the kernel * currently are referencing the objects. Both kind of objects typically will * live inside the kernel with a refcnt of 2, one for its creation and one for * the reference a group and a mark hold to each other. * If you are holding the appropriate locks, you can take a reference and the * object itself is guaranteed to survive until the reference is dropped. * * LOCKING: * There are 3 locks involved with fsnotify inode marks and they MUST be taken * in order as follows: * * group->mark_mutex * mark->lock * mark->connector->lock * * group->mark_mutex protects the marks_list anchored inside a given group and * each mark is hooked via the g_list. It also protects the groups private * data (i.e group limits). * mark->lock protects the marks attributes like its masks and flags. * Furthermore it protects the access to a reference of the group that the mark * is assigned to as well as the access to a reference of the inode/vfsmount * that is being watched by the mark. * * mark->connector->lock protects the list of marks anchored inside an * inode / vfsmount and each mark is hooked via the i_list. * * A list of notification marks relating to inode / mnt is contained in * fsnotify_mark_connector. That structure is alive as long as there are any * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets * detached from fsnotify_mark_connector when last reference to the mark is * dropped. Thus having mark reference is enough to protect mark->connector * pointer and to make sure fsnotify_mark_connector cannot disappear. Also * because we remove mark from g_list before dropping mark reference associated * with that, any mark found through g_list is guaranteed to have * mark->connector set until we drop group->mark_mutex. * * LIFETIME: * Inode marks survive between when they are added to an inode and when their * refcnt==0. Marks are also protected by fsnotify_mark_srcu. * * The inode mark can be cleared for a number of different reasons including: * - The inode is unlinked for the last time. (fsnotify_inode_remove) * - The inode is being evicted from cache. (fsnotify_inode_delete) * - The fs the inode is on is unmounted. (fsnotify_inode_delete/fsnotify_unmount_inodes) * - Something explicitly requests that it be removed. (fsnotify_destroy_mark) * - The fsnotify_group associated with the mark is going away and all such marks * need to be cleaned up. (fsnotify_clear_marks_by_group) * * This has the very interesting property of being able to run concurrently with * any (or all) other directions. */ #include <linux/fs.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/kthread.h> #include <linux/module.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/spinlock.h> #include <linux/srcu.h> #include <linux/ratelimit.h> #include <linux/atomic.h> #include <linux/fsnotify_backend.h> #include "fsnotify.h" #define FSNOTIFY_REAPER_DELAY (1) /* 1 jiffy */ struct srcu_struct fsnotify_mark_srcu; struct kmem_cache *fsnotify_mark_connector_cachep; static DEFINE_SPINLOCK(destroy_lock); static LIST_HEAD(destroy_list); static struct fsnotify_mark_connector *connector_destroy_list; static void fsnotify_mark_destroy_workfn(struct work_struct *work); static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn); static void fsnotify_connector_destroy_workfn(struct work_struct *work); static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn); void fsnotify_get_mark(struct fsnotify_mark *mark) { WARN_ON_ONCE(!refcount_read(&mark->refcnt)); refcount_inc(&mark->refcnt); } static fsnotify_connp_t *fsnotify_object_connp(void *obj, enum fsnotify_obj_type obj_type) { switch (obj_type) { case FSNOTIFY_OBJ_TYPE_INODE: return &((struct inode *)obj)->i_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_VFSMOUNT: return &real_mount(obj)->mnt_fsnotify_marks; case FSNOTIFY_OBJ_TYPE_SB: return fsnotify_sb_marks(obj); default: return NULL; } } static __u32 *fsnotify_conn_mask_p(struct fsnotify_mark_connector *conn) { if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) return &fsnotify_conn_inode(conn)->i_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) return &fsnotify_conn_mount(conn)->mnt_fsnotify_mask; else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) return &fsnotify_conn_sb(conn)->s_fsnotify_mask; return NULL; } __u32 fsnotify_conn_mask(struct fsnotify_mark_connector *conn) { if (WARN_ON(!fsnotify_valid_obj_type(conn->type))) return 0; return *fsnotify_conn_mask_p(conn); } static void fsnotify_get_sb_watched_objects(struct super_block *sb) { atomic_long_inc(fsnotify_sb_watched_objects(sb)); } static void fsnotify_put_sb_watched_objects(struct super_block *sb) { if (atomic_long_dec_and_test(fsnotify_sb_watched_objects(sb))) wake_up_var(fsnotify_sb_watched_objects(sb)); } static void fsnotify_get_inode_ref(struct inode *inode) { ihold(inode); fsnotify_get_sb_watched_objects(inode->i_sb); } static void fsnotify_put_inode_ref(struct inode *inode) { fsnotify_put_sb_watched_objects(inode->i_sb); iput(inode); } /* * Grab or drop watched objects reference depending on whether the connector * is attached and has any marks attached. */ static void fsnotify_update_sb_watchers(struct super_block *sb, struct fsnotify_mark_connector *conn) { struct fsnotify_sb_info *sbinfo = fsnotify_sb_info(sb); bool is_watched = conn->flags & FSNOTIFY_CONN_FLAG_IS_WATCHED; struct fsnotify_mark *first_mark = NULL; unsigned int highest_prio = 0; if (conn->obj) first_mark = hlist_entry_safe(conn->list.first, struct fsnotify_mark, obj_list); if (first_mark) highest_prio = first_mark->group->priority; if (WARN_ON(highest_prio >= __FSNOTIFY_PRIO_NUM)) highest_prio = 0; /* * If the highest priority of group watching this object is prio, * then watched object has a reference on counters [0..prio]. * Update priority >= 1 watched objects counters. */ for (unsigned int p = conn->prio + 1; p <= highest_prio; p++) atomic_long_inc(&sbinfo->watched_objects[p]); for (unsigned int p = conn->prio; p > highest_prio; p--) atomic_long_dec(&sbinfo->watched_objects[p]); conn->prio = highest_prio; /* Update priority >= 0 (a.k.a total) watched objects counter */ BUILD_BUG_ON(FSNOTIFY_PRIO_NORMAL != 0); if (first_mark && !is_watched) { conn->flags |= FSNOTIFY_CONN_FLAG_IS_WATCHED; fsnotify_get_sb_watched_objects(sb); } else if (!first_mark && is_watched) { conn->flags &= ~FSNOTIFY_CONN_FLAG_IS_WATCHED; fsnotify_put_sb_watched_objects(sb); } } /* * Grab or drop inode reference for the connector if needed. * * When it's time to drop the reference, we only clear the HAS_IREF flag and * return the inode object. fsnotify_drop_object() will be resonsible for doing * iput() outside of spinlocks. This happens when last mark that wanted iref is * detached. */ static struct inode *fsnotify_update_iref(struct fsnotify_mark_connector *conn, bool want_iref) { bool has_iref = conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF; struct inode *inode = NULL; if (conn->type != FSNOTIFY_OBJ_TYPE_INODE || want_iref == has_iref) return NULL; if (want_iref) { /* Pin inode if any mark wants inode refcount held */ fsnotify_get_inode_ref(fsnotify_conn_inode(conn)); conn->flags |= FSNOTIFY_CONN_FLAG_HAS_IREF; } else { /* Unpin inode after detach of last mark that wanted iref */ inode = fsnotify_conn_inode(conn); conn->flags &= ~FSNOTIFY_CONN_FLAG_HAS_IREF; } return inode; } static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { u32 new_mask = 0; bool want_iref = false; struct fsnotify_mark *mark; assert_spin_locked(&conn->lock); /* We can get detached connector here when inode is getting unlinked. */ if (!fsnotify_valid_obj_type(conn->type)) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) continue; new_mask |= fsnotify_calc_mask(mark); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE && !(mark->flags & FSNOTIFY_MARK_FLAG_NO_IREF)) want_iref = true; } *fsnotify_conn_mask_p(conn) = new_mask; return fsnotify_update_iref(conn, want_iref); } /* * Calculate mask of events for a list of marks. The caller must make sure * connector and connector->obj cannot disappear under us. Callers achieve * this by holding a mark->lock or mark->group->mark_mutex for a mark on this * list. */ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn) { if (!conn) return; spin_lock(&conn->lock); __fsnotify_recalc_mask(conn); spin_unlock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) __fsnotify_update_child_dentry_flags( fsnotify_conn_inode(conn)); } /* Free all connectors queued for freeing once SRCU period ends */ static void fsnotify_connector_destroy_workfn(struct work_struct *work) { struct fsnotify_mark_connector *conn, *free; spin_lock(&destroy_lock); conn = connector_destroy_list; connector_destroy_list = NULL; spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); while (conn) { free = conn; conn = conn->destroy_next; kmem_cache_free(fsnotify_mark_connector_cachep, free); } } static void *fsnotify_detach_connector_from_object( struct fsnotify_mark_connector *conn, unsigned int *type) { fsnotify_connp_t *connp = fsnotify_object_connp(conn->obj, conn->type); struct super_block *sb = fsnotify_connector_sb(conn); struct inode *inode = NULL; *type = conn->type; if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) return NULL; if (conn->type == FSNOTIFY_OBJ_TYPE_INODE) { inode = fsnotify_conn_inode(conn); inode->i_fsnotify_mask = 0; /* Unpin inode when detaching from connector */ if (!(conn->flags & FSNOTIFY_CONN_FLAG_HAS_IREF)) inode = NULL; } else if (conn->type == FSNOTIFY_OBJ_TYPE_VFSMOUNT) { fsnotify_conn_mount(conn)->mnt_fsnotify_mask = 0; } else if (conn->type == FSNOTIFY_OBJ_TYPE_SB) { fsnotify_conn_sb(conn)->s_fsnotify_mask = 0; } rcu_assign_pointer(*connp, NULL); conn->obj = NULL; conn->type = FSNOTIFY_OBJ_TYPE_DETACHED; fsnotify_update_sb_watchers(sb, conn); return inode; } static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; if (WARN_ON_ONCE(!group)) return; group->ops->free_mark(mark); fsnotify_put_group(group); } /* Drop object reference originally held by a connector */ static void fsnotify_drop_object(unsigned int type, void *objp) { if (!objp) return; /* Currently only inode references are passed to be dropped */ if (WARN_ON_ONCE(type != FSNOTIFY_OBJ_TYPE_INODE)) return; fsnotify_put_inode_ref(objp); } void fsnotify_put_mark(struct fsnotify_mark *mark) { struct fsnotify_mark_connector *conn = READ_ONCE(mark->connector); void *objp = NULL; unsigned int type = FSNOTIFY_OBJ_TYPE_DETACHED; bool free_conn = false; /* Catch marks that were actually never attached to object */ if (!conn) { if (refcount_dec_and_test(&mark->refcnt)) fsnotify_final_mark_destroy(mark); return; } /* * We have to be careful so that traversals of obj_list under lock can * safely grab mark reference. */ if (!refcount_dec_and_lock(&mark->refcnt, &conn->lock)) return; hlist_del_init_rcu(&mark->obj_list); if (hlist_empty(&conn->list)) { objp = fsnotify_detach_connector_from_object(conn, &type); free_conn = true; } else { struct super_block *sb = fsnotify_connector_sb(conn); /* Update watched objects after detaching mark */ if (sb) fsnotify_update_sb_watchers(sb, conn); objp = __fsnotify_recalc_mask(conn); type = conn->type; } WRITE_ONCE(mark->connector, NULL); spin_unlock(&conn->lock); fsnotify_drop_object(type, objp); if (free_conn) { spin_lock(&destroy_lock); conn->destroy_next = connector_destroy_list; connector_destroy_list = conn; spin_unlock(&destroy_lock); queue_work(system_unbound_wq, &connector_reaper_work); } /* * Note that we didn't update flags telling whether inode cares about * what's happening with children. We update these flags from * __fsnotify_parent() lazily when next event happens on one of our * children. */ spin_lock(&destroy_lock); list_add(&mark->g_list, &destroy_list); spin_unlock(&destroy_lock); queue_delayed_work(system_unbound_wq, &reaper_work, FSNOTIFY_REAPER_DELAY); } EXPORT_SYMBOL_GPL(fsnotify_put_mark); /* * Get mark reference when we found the mark via lockless traversal of object * list. Mark can be already removed from the list by now and on its way to be * destroyed once SRCU period ends. * * Also pin the group so it doesn't disappear under us. */ static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark) { if (!mark) return true; if (refcount_inc_not_zero(&mark->refcnt)) { spin_lock(&mark->lock); if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) { /* mark is attached, group is still alive then */ atomic_inc(&mark->group->user_waits); spin_unlock(&mark->lock); return true; } spin_unlock(&mark->lock); fsnotify_put_mark(mark); } return false; } /* * Puts marks and wakes up group destruction if necessary. * * Pairs with fsnotify_get_mark_safe() */ static void fsnotify_put_mark_wake(struct fsnotify_mark *mark) { if (mark) { struct fsnotify_group *group = mark->group; fsnotify_put_mark(mark); /* * We abuse notification_waitq on group shutdown for waiting for * all marks pinned when waiting for userspace. */ if (atomic_dec_and_test(&group->user_waits) && group->shutdown) wake_up(&group->notification_waitq); } } bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info) __releases(&fsnotify_mark_srcu) { int type; fsnotify_foreach_iter_type(type) { /* This can fail if mark is being removed */ if (!fsnotify_get_mark_safe(iter_info->marks[type])) { __release(&fsnotify_mark_srcu); goto fail; } } /* * Now that both marks are pinned by refcount in the inode / vfsmount * lists, we can drop SRCU lock, and safely resume the list iteration * once userspace returns. */ srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx); return true; fail: for (type--; type >= 0; type--) fsnotify_put_mark_wake(iter_info->marks[type]); return false; } void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info) __acquires(&fsnotify_mark_srcu) { int type; iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu); fsnotify_foreach_iter_type(type) fsnotify_put_mark_wake(iter_info->marks[type]); } /* * Mark mark as detached, remove it from group list. Mark still stays in object * list until its last reference is dropped. Note that we rely on mark being * removed from group list before corresponding reference to it is dropped. In * particular we rely on mark->connector being valid while we hold * group->mark_mutex if we found the mark through g_list. * * Must be called with group->mark_mutex held. The caller must either hold * reference to the mark or be protected by fsnotify_mark_srcu. */ void fsnotify_detach_mark(struct fsnotify_mark *mark) { fsnotify_group_assert_locked(mark->group); WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) && refcount_read(&mark->refcnt) < 1 + !!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)); spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED; list_del_init(&mark->g_list); spin_unlock(&mark->lock); /* Drop mark reference acquired in fsnotify_add_mark_locked() */ fsnotify_put_mark(mark); } /* * Free fsnotify mark. The mark is actually only marked as being freed. The * freeing is actually happening only once last reference to the mark is * dropped from a workqueue which first waits for srcu period end. * * Caller must have a reference to the mark or be protected by * fsnotify_mark_srcu. */ void fsnotify_free_mark(struct fsnotify_mark *mark) { struct fsnotify_group *group = mark->group; spin_lock(&mark->lock); /* something else already called this function on this mark */ if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) { spin_unlock(&mark->lock); return; } mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE; spin_unlock(&mark->lock); /* * Some groups like to know that marks are being freed. This is a * callback to the group function to let it know that this mark * is being freed. */ if (group->ops->freeing_mark) group->ops->freeing_mark(mark, group); } void fsnotify_destroy_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { fsnotify_group_lock(group); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); } EXPORT_SYMBOL_GPL(fsnotify_destroy_mark); /* * Sorting function for lists of fsnotify marks. * * Fanotify supports different notification classes (reflected as priority of * notification group). Events shall be passed to notification groups in * decreasing priority order. To achieve this marks in notification lists for * inodes and vfsmounts are sorted so that priorities of corresponding groups * are descending. * * Furthermore correct handling of the ignore mask requires processing inode * and vfsmount marks of each group together. Using the group address as * further sort criterion provides a unique sorting order and thus we can * merge inode and vfsmount lists of marks in linear time and find groups * present in both lists. * * A return value of 1 signifies that b has priority over a. * A return value of 0 signifies that the two marks have to be handled together. * A return value of -1 signifies that a has priority over b. */ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) { if (a == b) return 0; if (!a) return 1; if (!b) return -1; if (a->priority < b->priority) return 1; if (a->priority > b->priority) return -1; if (a < b) return 1; return -1; } static int fsnotify_attach_info_to_sb(struct super_block *sb) { struct fsnotify_sb_info *sbinfo; /* sb info is freed on fsnotify_sb_delete() */ sbinfo = kzalloc(sizeof(*sbinfo), GFP_KERNEL); if (!sbinfo) return -ENOMEM; /* * cmpxchg() provides the barrier so that callers of fsnotify_sb_info() * will observe an initialized structure */ if (cmpxchg(&sb->s_fsnotify_info, NULL, sbinfo)) { /* Someone else created sbinfo for us */ kfree(sbinfo); } return 0; } static int fsnotify_attach_connector_to_object(fsnotify_connp_t *connp, void *obj, unsigned int obj_type) { struct fsnotify_mark_connector *conn; conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL); if (!conn) return -ENOMEM; spin_lock_init(&conn->lock); INIT_HLIST_HEAD(&conn->list); conn->flags = 0; conn->prio = 0; conn->type = obj_type; conn->obj = obj; /* * cmpxchg() provides the barrier so that readers of *connp can see * only initialized structure */ if (cmpxchg(connp, NULL, conn)) { /* Someone else created list structure for us */ kmem_cache_free(fsnotify_mark_connector_cachep, conn); } return 0; } /* * Get mark connector, make sure it is alive and return with its lock held. * This is for users that get connector pointer from inode or mount. Users that * hold reference to a mark on the list may directly lock connector->lock as * they are sure list cannot go away under them. */ static struct fsnotify_mark_connector *fsnotify_grab_connector( fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; int idx; idx = srcu_read_lock(&fsnotify_mark_srcu); conn = srcu_dereference(*connp, &fsnotify_mark_srcu); if (!conn) goto out; spin_lock(&conn->lock); if (conn->type == FSNOTIFY_OBJ_TYPE_DETACHED) { spin_unlock(&conn->lock); srcu_read_unlock(&fsnotify_mark_srcu, idx); return NULL; } out: srcu_read_unlock(&fsnotify_mark_srcu, idx); return conn; } /* * Add mark into proper place in given list of marks. These marks may be used * for the fsnotify backend to determine which event types should be delivered * to which group and for which inodes. These marks are ordered according to * priority, highest number first, and then by the group's location in memory. */ static int fsnotify_add_mark_list(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { struct super_block *sb = fsnotify_object_sb(obj, obj_type); struct fsnotify_mark *lmark, *last = NULL; struct fsnotify_mark_connector *conn; fsnotify_connp_t *connp; int cmp; int err = 0; if (WARN_ON(!fsnotify_valid_obj_type(obj_type))) return -EINVAL; /* * Attach the sb info before attaching a connector to any object on sb. * The sb info will remain attached as long as sb lives. */ if (!fsnotify_sb_info(sb)) { err = fsnotify_attach_info_to_sb(sb); if (err) return err; } connp = fsnotify_object_connp(obj, obj_type); restart: spin_lock(&mark->lock); conn = fsnotify_grab_connector(connp); if (!conn) { spin_unlock(&mark->lock); err = fsnotify_attach_connector_to_object(connp, obj, obj_type); if (err) return err; goto restart; } /* is mark the first mark? */ if (hlist_empty(&conn->list)) { hlist_add_head_rcu(&mark->obj_list, &conn->list); goto added; } /* should mark be in the middle of the current list? */ hlist_for_each_entry(lmark, &conn->list, obj_list) { last = lmark; if ((lmark->group == mark->group) && (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) && !(mark->group->flags & FSNOTIFY_GROUP_DUPS)) { err = -EEXIST; goto out_err; } cmp = fsnotify_compare_groups(lmark->group, mark->group); if (cmp >= 0) { hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list); goto added; } } BUG_ON(last == NULL); /* mark should be the last entry. last is the current last entry */ hlist_add_behind_rcu(&mark->obj_list, &last->obj_list); added: fsnotify_update_sb_watchers(sb, conn); /* * Since connector is attached to object using cmpxchg() we are * guaranteed that connector initialization is fully visible by anyone * seeing mark->connector set. */ WRITE_ONCE(mark->connector, conn); out_err: spin_unlock(&conn->lock); spin_unlock(&mark->lock); return err; } /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which * event types should be delivered to which group. */ int fsnotify_add_mark_locked(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { struct fsnotify_group *group = mark->group; int ret = 0; fsnotify_group_assert_locked(group); /* * LOCKING ORDER!!!! * group->mark_mutex * mark->lock * mark->connector->lock */ spin_lock(&mark->lock); mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED; list_add(&mark->g_list, &group->marks_list); fsnotify_get_mark(mark); /* for g_list */ spin_unlock(&mark->lock); ret = fsnotify_add_mark_list(mark, obj, obj_type, add_flags); if (ret) goto err; fsnotify_recalc_mask(mark->connector); return ret; err: spin_lock(&mark->lock); mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED); list_del_init(&mark->g_list); spin_unlock(&mark->lock); fsnotify_put_mark(mark); return ret; } int fsnotify_add_mark(struct fsnotify_mark *mark, void *obj, unsigned int obj_type, int add_flags) { int ret; struct fsnotify_group *group = mark->group; fsnotify_group_lock(group); ret = fsnotify_add_mark_locked(mark, obj, obj_type, add_flags); fsnotify_group_unlock(group); return ret; } EXPORT_SYMBOL_GPL(fsnotify_add_mark); /* * Given a list of marks, find the mark associated with given group. If found * take a reference to that mark and return it, else return NULL. */ struct fsnotify_mark *fsnotify_find_mark(void *obj, unsigned int obj_type, struct fsnotify_group *group) { fsnotify_connp_t *connp = fsnotify_object_connp(obj, obj_type); struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark; if (!connp) return NULL; conn = fsnotify_grab_connector(connp); if (!conn) return NULL; hlist_for_each_entry(mark, &conn->list, obj_list) { if (mark->group == group && (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); return mark; } } spin_unlock(&conn->lock); return NULL; } EXPORT_SYMBOL_GPL(fsnotify_find_mark); /* Clear any marks in a group with given type mask */ void fsnotify_clear_marks_by_group(struct fsnotify_group *group, unsigned int obj_type) { struct fsnotify_mark *lmark, *mark; LIST_HEAD(to_free); struct list_head *head = &to_free; /* Skip selection step if we want to clear all marks. */ if (obj_type == FSNOTIFY_OBJ_TYPE_ANY) { head = &group->marks_list; goto clear; } /* * We have to be really careful here. Anytime we drop mark_mutex, e.g. * fsnotify_clear_marks_by_inode() can come and free marks. Even in our * to_free list so we have to use mark_mutex even when accessing that * list. And freeing mark requires us to drop mark_mutex. So we can * reliably free only the first mark in the list. That's why we first * move marks to free to to_free list in one go and then free marks in * to_free list one by one. */ fsnotify_group_lock(group); list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) { if (mark->connector->type == obj_type) list_move(&mark->g_list, &to_free); } fsnotify_group_unlock(group); clear: while (1) { fsnotify_group_lock(group); if (list_empty(head)) { fsnotify_group_unlock(group); break; } mark = list_first_entry(head, struct fsnotify_mark, g_list); fsnotify_get_mark(mark); fsnotify_detach_mark(mark); fsnotify_group_unlock(group); fsnotify_free_mark(mark); fsnotify_put_mark(mark); } } /* Destroy all marks attached to an object via connector */ void fsnotify_destroy_marks(fsnotify_connp_t *connp) { struct fsnotify_mark_connector *conn; struct fsnotify_mark *mark, *old_mark = NULL; void *objp; unsigned int type; conn = fsnotify_grab_connector(connp); if (!conn) return; /* * We have to be careful since we can race with e.g. * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the * list can get modified. However we are holding mark reference and * thus our mark cannot be removed from obj_list so we can continue * iteration after regaining conn->lock. */ hlist_for_each_entry(mark, &conn->list, obj_list) { fsnotify_get_mark(mark); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); old_mark = mark; fsnotify_destroy_mark(mark, mark->group); spin_lock(&conn->lock); } /* * Detach list from object now so that we don't pin inode until all * mark references get dropped. It would lead to strange results such * as delaying inode deletion or blocking unmount. */ objp = fsnotify_detach_connector_from_object(conn, &type); spin_unlock(&conn->lock); if (old_mark) fsnotify_put_mark(old_mark); fsnotify_drop_object(type, objp); } /* * Nothing fancy, just initialize lists and locks and counters. */ void fsnotify_init_mark(struct fsnotify_mark *mark, struct fsnotify_group *group) { memset(mark, 0, sizeof(*mark)); spin_lock_init(&mark->lock); refcount_set(&mark->refcnt, 1); fsnotify_get_group(group); mark->group = group; WRITE_ONCE(mark->connector, NULL); } EXPORT_SYMBOL_GPL(fsnotify_init_mark); /* * Destroy all marks in destroy_list, waits for SRCU period to finish before * actually freeing marks. */ static void fsnotify_mark_destroy_workfn(struct work_struct *work) { struct fsnotify_mark *mark, *next; struct list_head private_destroy_list; spin_lock(&destroy_lock); /* exchange the list head */ list_replace_init(&destroy_list, &private_destroy_list); spin_unlock(&destroy_lock); synchronize_srcu(&fsnotify_mark_srcu); list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) { list_del_init(&mark->g_list); fsnotify_final_mark_destroy(mark); } } /* Wait for all marks queued for destruction to be actually destroyed */ void fsnotify_wait_marks_destroyed(void) { flush_delayed_work(&reaper_work); } EXPORT_SYMBOL_GPL(fsnotify_wait_marks_destroyed); |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __LINUX_KSM_H #define __LINUX_KSM_H /* * Memory merging support. * * This code enables dynamic sharing of identical pages found in different * memory areas, even if they are not shared by fork(). */ #include <linux/bitops.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/sched.h> #include <linux/sched/coredump.h> #ifdef CONFIG_KSM int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags); void ksm_add_vma(struct vm_area_struct *vma); int ksm_enable_merge_any(struct mm_struct *mm); int ksm_disable_merge_any(struct mm_struct *mm); int ksm_disable(struct mm_struct *mm); int __ksm_enter(struct mm_struct *mm); void __ksm_exit(struct mm_struct *mm); /* * To identify zeropages that were mapped by KSM, we reuse the dirty bit * in the PTE. If the PTE is dirty, the zeropage was mapped by KSM when * deduplicating memory. */ #define is_ksm_zero_pte(pte) (is_zero_pfn(pte_pfn(pte)) && pte_dirty(pte)) extern atomic_long_t ksm_zero_pages; static inline void ksm_map_zero_page(struct mm_struct *mm) { atomic_long_inc(&ksm_zero_pages); atomic_long_inc(&mm->ksm_zero_pages); } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { if (is_ksm_zero_pte(pte)) { atomic_long_dec(&ksm_zero_pages); atomic_long_dec(&mm->ksm_zero_pages); } } static inline long mm_ksm_zero_pages(struct mm_struct *mm) { return atomic_long_read(&mm->ksm_zero_pages); } static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { if (test_bit(MMF_VM_MERGEABLE, &oldmm->flags)) return __ksm_enter(mm); return 0; } static inline int ksm_execve(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGE_ANY, &mm->flags)) return __ksm_enter(mm); return 0; } static inline void ksm_exit(struct mm_struct *mm) { if (test_bit(MMF_VM_MERGEABLE, &mm->flags)) __ksm_exit(mm); } /* * When do_swap_page() first faults in from swap what used to be a KSM page, * no problem, it will be assigned to this vma's anon_vma; but thereafter, * it might be faulted into a different anon_vma (or perhaps to a different * offset in the same anon_vma). do_swap_page() cannot do all the locking * needed to reconstitute a cross-anon_vma KSM page: for now it has to make * a copy, and leave remerging the pages to a later pass of ksmd. * * We'd like to make this conditional on vma->vm_flags & VM_MERGEABLE, * but what if the vma was unmerged while the page was swapped out? */ struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr); void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc); void folio_migrate_ksm(struct folio *newfolio, struct folio *folio); void collect_procs_ksm(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early); long ksm_process_profit(struct mm_struct *); #else /* !CONFIG_KSM */ static inline void ksm_add_vma(struct vm_area_struct *vma) { } static inline int ksm_disable(struct mm_struct *mm) { return 0; } static inline int ksm_fork(struct mm_struct *mm, struct mm_struct *oldmm) { return 0; } static inline int ksm_execve(struct mm_struct *mm) { return 0; } static inline void ksm_exit(struct mm_struct *mm) { } static inline void ksm_might_unmap_zero_page(struct mm_struct *mm, pte_t pte) { } static inline void collect_procs_ksm(struct folio *folio, struct page *page, struct list_head *to_kill, int force_early) { } #ifdef CONFIG_MMU static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start, unsigned long end, int advice, unsigned long *vm_flags) { return 0; } static inline struct folio *ksm_might_need_to_copy(struct folio *folio, struct vm_area_struct *vma, unsigned long addr) { return folio; } static inline void rmap_walk_ksm(struct folio *folio, struct rmap_walk_control *rwc) { } static inline void folio_migrate_ksm(struct folio *newfolio, struct folio *old) { } #endif /* CONFIG_MMU */ #endif /* !CONFIG_KSM */ #endif /* __LINUX_KSM_H */ |
| 338 339 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 | // SPDX-License-Identifier: GPL-2.0-only /* * Based on arch/arm/kernel/irq.c * * Copyright (C) 1992 Linus Torvalds * Modifications for ARM processor Copyright (C) 1995-2000 Russell King. * Support for Dynamic Tick Timer Copyright (C) 2004-2005 Nokia Corporation. * Dynamic Tick Timer written by Tony Lindgren <tony@atomide.com> and * Tuukka Tikkanen <tuukka.tikkanen@elektrobit.com>. * Copyright (C) 2012 ARM Ltd. */ #include <linux/hardirq.h> #include <linux/init.h> #include <linux/irq.h> #include <linux/irqchip.h> #include <linux/kprobes.h> #include <linux/memory.h> #include <linux/scs.h> #include <linux/seq_file.h> #include <linux/smp.h> #include <linux/vmalloc.h> #include <asm/daifflags.h> #include <asm/exception.h> #include <asm/numa.h> #include <asm/softirq_stack.h> #include <asm/stacktrace.h> #include <asm/vmap_stack.h> /* Only access this in an NMI enter/exit */ DEFINE_PER_CPU(struct nmi_ctx, nmi_contexts); DEFINE_PER_CPU(unsigned long *, irq_stack_ptr); DECLARE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #ifdef CONFIG_SHADOW_CALL_STACK DEFINE_PER_CPU(unsigned long *, irq_shadow_call_stack_ptr); #endif static void init_irq_scs(void) { int cpu; if (!scs_is_enabled()) return; for_each_possible_cpu(cpu) per_cpu(irq_shadow_call_stack_ptr, cpu) = scs_alloc(early_cpu_to_node(cpu)); } #ifdef CONFIG_VMAP_STACK static void __init init_irq_stacks(void) { int cpu; unsigned long *p; for_each_possible_cpu(cpu) { p = arch_alloc_vmap_stack(IRQ_STACK_SIZE, early_cpu_to_node(cpu)); per_cpu(irq_stack_ptr, cpu) = p; } } #else /* irq stack only needs to be 16 byte aligned - not IRQ_STACK_SIZE aligned. */ DEFINE_PER_CPU_ALIGNED(unsigned long [IRQ_STACK_SIZE/sizeof(long)], irq_stack); static void init_irq_stacks(void) { int cpu; for_each_possible_cpu(cpu) per_cpu(irq_stack_ptr, cpu) = per_cpu(irq_stack, cpu); } #endif #ifndef CONFIG_PREEMPT_RT static void ____do_softirq(struct pt_regs *regs) { __do_softirq(); } void do_softirq_own_stack(void) { call_on_irq_stack(NULL, ____do_softirq); } #endif static void default_handle_irq(struct pt_regs *regs) { panic("IRQ taken without a root IRQ handler\n"); } static void default_handle_fiq(struct pt_regs *regs) { panic("FIQ taken without a root FIQ handler\n"); } void (*handle_arch_irq)(struct pt_regs *) __ro_after_init = default_handle_irq; void (*handle_arch_fiq)(struct pt_regs *) __ro_after_init = default_handle_fiq; int __init set_handle_irq(void (*handle_irq)(struct pt_regs *)) { if (handle_arch_irq != default_handle_irq) return -EBUSY; handle_arch_irq = handle_irq; pr_info("Root IRQ handler: %ps\n", handle_irq); return 0; } int __init set_handle_fiq(void (*handle_fiq)(struct pt_regs *)) { if (handle_arch_fiq != default_handle_fiq) return -EBUSY; handle_arch_fiq = handle_fiq; pr_info("Root FIQ handler: %ps\n", handle_fiq); return 0; } void __init init_IRQ(void) { init_irq_stacks(); init_irq_scs(); irqchip_init(); if (system_uses_irq_prio_masking()) { /* * Now that we have a stack for our IRQ handler, set * the PMR/PSR pair to a consistent state. */ WARN_ON(read_sysreg(daif) & PSR_A_BIT); local_daif_restore(DAIF_PROCCTX_NOIRQ); } } |
| 290 291 1 1 3 2 2 3 2 2 2 1 18 2 2 2 1 3 1 2 2 2 5 4 3 3 5 2 1 2 1 2 1 2 1 2 1 2 1 2 1 2 2 1 2 1 2 1 2 1 2 1 2 1 2 1 2 4 2 2 4 4 3 3 2 2 4 4 2 5 6 1 5 6 1 1 310 1 311 2 2 3 1 2 1 2 2 2 2 5 7 7 1 3 1 4 6 1 285 18 321 311 311 289 306 303 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/ioctl.c * * Copyright (C) 1991, 1992 Linus Torvalds */ #include <linux/syscalls.h> #include <linux/mm.h> #include <linux/capability.h> #include <linux/compat.h> #include <linux/file.h> #include <linux/fs.h> #include <linux/security.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/writeback.h> #include <linux/buffer_head.h> #include <linux/falloc.h> #include <linux/sched/signal.h> #include <linux/fiemap.h> #include <linux/mount.h> #include <linux/fscrypt.h> #include <linux/fileattr.h> #include "internal.h" #include <asm/ioctls.h> /* So that the fiemap access checks can't overflow on 32 bit machines. */ #define FIEMAP_MAX_EXTENTS (UINT_MAX / sizeof(struct fiemap_extent)) /** * vfs_ioctl - call filesystem specific ioctl methods * @filp: open file to invoke ioctl method on * @cmd: ioctl command to execute * @arg: command-specific argument for ioctl * * Invokes filesystem specific ->unlocked_ioctl, if one exists; otherwise * returns -ENOTTY. * * Returns 0 on success, -errno on error. */ long vfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { int error = -ENOTTY; if (!filp->f_op->unlocked_ioctl) goto out; error = filp->f_op->unlocked_ioctl(filp, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; out: return error; } EXPORT_SYMBOL(vfs_ioctl); static int ioctl_fibmap(struct file *filp, int __user *p) { struct inode *inode = file_inode(filp); struct super_block *sb = inode->i_sb; int error, ur_block; sector_t block; if (!capable(CAP_SYS_RAWIO)) return -EPERM; error = get_user(ur_block, p); if (error) return error; if (ur_block < 0) return -EINVAL; block = ur_block; error = bmap(inode, &block); if (block > INT_MAX) { error = -ERANGE; pr_warn_ratelimited("[%s/%d] FS: %s File: %pD4 would truncate fibmap result\n", current->comm, task_pid_nr(current), sb->s_id, filp); } if (error) ur_block = 0; else ur_block = block; if (put_user(ur_block, p)) error = -EFAULT; return error; } /** * fiemap_fill_next_extent - Fiemap helper function * @fieinfo: Fiemap context passed into ->fiemap * @logical: Extent logical start offset, in bytes * @phys: Extent physical start offset, in bytes * @len: Extent length, in bytes * @flags: FIEMAP_EXTENT flags that describe this extent * * Called from file system ->fiemap callback. Will populate extent * info as passed in via arguments and copy to user memory. On * success, extent count on fieinfo is incremented. * * Returns 0 on success, -errno on error, 1 if this was the last * extent that will fit in user array. */ int fiemap_fill_next_extent(struct fiemap_extent_info *fieinfo, u64 logical, u64 phys, u64 len, u32 flags) { struct fiemap_extent extent; struct fiemap_extent __user *dest = fieinfo->fi_extents_start; /* only count the extents */ if (fieinfo->fi_extents_max == 0) { fieinfo->fi_extents_mapped++; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max) return 1; #define SET_UNKNOWN_FLAGS (FIEMAP_EXTENT_DELALLOC) #define SET_NO_UNMOUNTED_IO_FLAGS (FIEMAP_EXTENT_DATA_ENCRYPTED) #define SET_NOT_ALIGNED_FLAGS (FIEMAP_EXTENT_DATA_TAIL|FIEMAP_EXTENT_DATA_INLINE) if (flags & SET_UNKNOWN_FLAGS) flags |= FIEMAP_EXTENT_UNKNOWN; if (flags & SET_NO_UNMOUNTED_IO_FLAGS) flags |= FIEMAP_EXTENT_ENCODED; if (flags & SET_NOT_ALIGNED_FLAGS) flags |= FIEMAP_EXTENT_NOT_ALIGNED; memset(&extent, 0, sizeof(extent)); extent.fe_logical = logical; extent.fe_physical = phys; extent.fe_length = len; extent.fe_flags = flags; dest += fieinfo->fi_extents_mapped; if (copy_to_user(dest, &extent, sizeof(extent))) return -EFAULT; fieinfo->fi_extents_mapped++; if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max) return 1; return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0; } EXPORT_SYMBOL(fiemap_fill_next_extent); /** * fiemap_prep - check validity of requested flags for fiemap * @inode: Inode to operate on * @fieinfo: Fiemap context passed into ->fiemap * @start: Start of the mapped range * @len: Length of the mapped range, can be truncated by this function. * @supported_flags: Set of fiemap flags that the file system understands * * This function must be called from each ->fiemap instance to validate the * fiemap request against the file system parameters. * * Returns 0 on success, or a negative error on failure. */ int fiemap_prep(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 *len, u32 supported_flags) { u64 maxbytes = inode->i_sb->s_maxbytes; u32 incompat_flags; int ret = 0; if (*len == 0) return -EINVAL; if (start >= maxbytes) return -EFBIG; /* * Shrink request scope to what the fs can actually handle. */ if (*len > maxbytes || (maxbytes - *len) < start) *len = maxbytes - start; supported_flags |= FIEMAP_FLAG_SYNC; supported_flags &= FIEMAP_FLAGS_COMPAT; incompat_flags = fieinfo->fi_flags & ~supported_flags; if (incompat_flags) { fieinfo->fi_flags = incompat_flags; return -EBADR; } if (fieinfo->fi_flags & FIEMAP_FLAG_SYNC) ret = filemap_write_and_wait(inode->i_mapping); return ret; } EXPORT_SYMBOL(fiemap_prep); static int ioctl_fiemap(struct file *filp, struct fiemap __user *ufiemap) { struct fiemap fiemap; struct fiemap_extent_info fieinfo = { 0, }; struct inode *inode = file_inode(filp); int error; if (!inode->i_op->fiemap) return -EOPNOTSUPP; if (copy_from_user(&fiemap, ufiemap, sizeof(fiemap))) return -EFAULT; if (fiemap.fm_extent_count > FIEMAP_MAX_EXTENTS) return -EINVAL; fieinfo.fi_flags = fiemap.fm_flags; fieinfo.fi_extents_max = fiemap.fm_extent_count; fieinfo.fi_extents_start = ufiemap->fm_extents; error = inode->i_op->fiemap(inode, &fieinfo, fiemap.fm_start, fiemap.fm_length); fiemap.fm_flags = fieinfo.fi_flags; fiemap.fm_mapped_extents = fieinfo.fi_extents_mapped; if (copy_to_user(ufiemap, &fiemap, sizeof(fiemap))) error = -EFAULT; return error; } static long ioctl_file_clone(struct file *dst_file, unsigned long srcfd, u64 off, u64 olen, u64 destoff) { struct fd src_file = fdget(srcfd); loff_t cloned; int ret; if (!src_file.file) return -EBADF; cloned = vfs_clone_file_range(src_file.file, off, dst_file, destoff, olen, 0); if (cloned < 0) ret = cloned; else if (olen && cloned != olen) ret = -EINVAL; else ret = 0; fdput(src_file); return ret; } static long ioctl_file_clone_range(struct file *file, struct file_clone_range __user *argp) { struct file_clone_range args; if (copy_from_user(&args, argp, sizeof(args))) return -EFAULT; return ioctl_file_clone(file, args.src_fd, args.src_offset, args.src_length, args.dest_offset); } /* * This provides compatibility with legacy XFS pre-allocation ioctls * which predate the fallocate syscall. * * Only the l_start, l_len and l_whence fields of the 'struct space_resv' * are used here, rest are ignored. */ static int ioctl_preallocate(struct file *filp, int mode, void __user *argp) { struct inode *inode = file_inode(filp); struct space_resv sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += filp->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(filp, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } /* on ia32 l_start is on a 32-bit boundary */ #if defined CONFIG_COMPAT && defined(CONFIG_X86_64) /* just account for different alignment */ static int compat_ioctl_preallocate(struct file *file, int mode, struct space_resv_32 __user *argp) { struct inode *inode = file_inode(file); struct space_resv_32 sr; if (copy_from_user(&sr, argp, sizeof(sr))) return -EFAULT; switch (sr.l_whence) { case SEEK_SET: break; case SEEK_CUR: sr.l_start += file->f_pos; break; case SEEK_END: sr.l_start += i_size_read(inode); break; default: return -EINVAL; } return vfs_fallocate(file, mode | FALLOC_FL_KEEP_SIZE, sr.l_start, sr.l_len); } #endif static int file_ioctl(struct file *filp, unsigned int cmd, int __user *p) { switch (cmd) { case FIBMAP: return ioctl_fibmap(filp, p); case FS_IOC_RESVSP: case FS_IOC_RESVSP64: return ioctl_preallocate(filp, 0, p); case FS_IOC_UNRESVSP: case FS_IOC_UNRESVSP64: return ioctl_preallocate(filp, FALLOC_FL_PUNCH_HOLE, p); case FS_IOC_ZERO_RANGE: return ioctl_preallocate(filp, FALLOC_FL_ZERO_RANGE, p); } return -ENOIOCTLCMD; } static int ioctl_fionbio(struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = O_NONBLOCK; #ifdef __sparc__ /* SunOS compatibility item. */ if (O_NONBLOCK != O_NDELAY) flag |= O_NDELAY; #endif spin_lock(&filp->f_lock); if (on) filp->f_flags |= flag; else filp->f_flags &= ~flag; spin_unlock(&filp->f_lock); return error; } static int ioctl_fioasync(unsigned int fd, struct file *filp, int __user *argp) { unsigned int flag; int on, error; error = get_user(on, argp); if (error) return error; flag = on ? FASYNC : 0; /* Did FASYNC state change ? */ if ((flag ^ filp->f_flags) & FASYNC) { if (filp->f_op->fasync) /* fasync() adjusts filp->f_flags */ error = filp->f_op->fasync(fd, filp, on); else error = -ENOTTY; } return error < 0 ? error : 0; } static int ioctl_fsfreeze(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* If filesystem doesn't support freeze feature, return. */ if (sb->s_op->freeze_fs == NULL && sb->s_op->freeze_super == NULL) return -EOPNOTSUPP; /* Freeze */ if (sb->s_op->freeze_super) return sb->s_op->freeze_super(sb, FREEZE_HOLDER_USERSPACE); return freeze_super(sb, FREEZE_HOLDER_USERSPACE); } static int ioctl_fsthaw(struct file *filp) { struct super_block *sb = file_inode(filp)->i_sb; if (!ns_capable(sb->s_user_ns, CAP_SYS_ADMIN)) return -EPERM; /* Thaw */ if (sb->s_op->thaw_super) return sb->s_op->thaw_super(sb, FREEZE_HOLDER_USERSPACE); return thaw_super(sb, FREEZE_HOLDER_USERSPACE); } static int ioctl_file_dedupe_range(struct file *file, struct file_dedupe_range __user *argp) { struct file_dedupe_range *same = NULL; int ret; unsigned long size; u16 count; if (get_user(count, &argp->dest_count)) { ret = -EFAULT; goto out; } size = offsetof(struct file_dedupe_range, info[count]); if (size > PAGE_SIZE) { ret = -ENOMEM; goto out; } same = memdup_user(argp, size); if (IS_ERR(same)) { ret = PTR_ERR(same); same = NULL; goto out; } same->dest_count = count; ret = vfs_dedupe_file_range(file, same); if (ret) goto out; ret = copy_to_user(argp, same, size); if (ret) ret = -EFAULT; out: kfree(same); return ret; } /** * fileattr_fill_xflags - initialize fileattr with xflags * @fa: fileattr pointer * @xflags: FS_XFLAG_* flags * * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags). All * other fields are zeroed. */ void fileattr_fill_xflags(struct fileattr *fa, u32 xflags) { memset(fa, 0, sizeof(*fa)); fa->fsx_valid = true; fa->fsx_xflags = xflags; if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE) fa->flags |= FS_IMMUTABLE_FL; if (fa->fsx_xflags & FS_XFLAG_APPEND) fa->flags |= FS_APPEND_FL; if (fa->fsx_xflags & FS_XFLAG_SYNC) fa->flags |= FS_SYNC_FL; if (fa->fsx_xflags & FS_XFLAG_NOATIME) fa->flags |= FS_NOATIME_FL; if (fa->fsx_xflags & FS_XFLAG_NODUMP) fa->flags |= FS_NODUMP_FL; if (fa->fsx_xflags & FS_XFLAG_DAX) fa->flags |= FS_DAX_FL; if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT) fa->flags |= FS_PROJINHERIT_FL; } EXPORT_SYMBOL(fileattr_fill_xflags); /** * fileattr_fill_flags - initialize fileattr with flags * @fa: fileattr pointer * @flags: FS_*_FL flags * * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags). * All other fields are zeroed. */ void fileattr_fill_flags(struct fileattr *fa, u32 flags) { memset(fa, 0, sizeof(*fa)); fa->flags_valid = true; fa->flags = flags; if (fa->flags & FS_SYNC_FL) fa->fsx_xflags |= FS_XFLAG_SYNC; if (fa->flags & FS_IMMUTABLE_FL) fa->fsx_xflags |= FS_XFLAG_IMMUTABLE; if (fa->flags & FS_APPEND_FL) fa->fsx_xflags |= FS_XFLAG_APPEND; if (fa->flags & FS_NODUMP_FL) fa->fsx_xflags |= FS_XFLAG_NODUMP; if (fa->flags & FS_NOATIME_FL) fa->fsx_xflags |= FS_XFLAG_NOATIME; if (fa->flags & FS_DAX_FL) fa->fsx_xflags |= FS_XFLAG_DAX; if (fa->flags & FS_PROJINHERIT_FL) fa->fsx_xflags |= FS_XFLAG_PROJINHERIT; } EXPORT_SYMBOL(fileattr_fill_flags); /** * vfs_fileattr_get - retrieve miscellaneous file attributes * @dentry: the object to retrieve from * @fa: fileattr pointer * * Call i_op->fileattr_get() callback, if exists. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); if (!inode->i_op->fileattr_get) return -ENOIOCTLCMD; return inode->i_op->fileattr_get(dentry, fa); } EXPORT_SYMBOL(vfs_fileattr_get); /** * copy_fsxattr_to_user - copy fsxattr to userspace. * @fa: fileattr pointer * @ufa: fsxattr user pointer * * Return: 0 on success, or -EFAULT on failure. */ int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; memset(&xfa, 0, sizeof(xfa)); xfa.fsx_xflags = fa->fsx_xflags; xfa.fsx_extsize = fa->fsx_extsize; xfa.fsx_nextents = fa->fsx_nextents; xfa.fsx_projid = fa->fsx_projid; xfa.fsx_cowextsize = fa->fsx_cowextsize; if (copy_to_user(ufa, &xfa, sizeof(xfa))) return -EFAULT; return 0; } EXPORT_SYMBOL(copy_fsxattr_to_user); static int copy_fsxattr_from_user(struct fileattr *fa, struct fsxattr __user *ufa) { struct fsxattr xfa; if (copy_from_user(&xfa, ufa, sizeof(xfa))) return -EFAULT; fileattr_fill_xflags(fa, xfa.fsx_xflags); fa->fsx_extsize = xfa.fsx_extsize; fa->fsx_nextents = xfa.fsx_nextents; fa->fsx_projid = xfa.fsx_projid; fa->fsx_cowextsize = xfa.fsx_cowextsize; return 0; } /* * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject * any invalid configurations. * * Note: must be called with inode lock held. */ static int fileattr_set_prepare(struct inode *inode, const struct fileattr *old_ma, struct fileattr *fa) { int err; /* * The IMMUTABLE and APPEND_ONLY flags can only be changed by * the relevant capability. */ if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) && !capable(CAP_LINUX_IMMUTABLE)) return -EPERM; err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags); if (err) return err; /* * 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_ma->fsx_projid != fa->fsx_projid) return -EINVAL; if ((old_ma->fsx_xflags ^ fa->fsx_xflags) & FS_XFLAG_PROJINHERIT) return -EINVAL; } else { /* * Caller is allowed to change the project ID. If it is being * changed, make sure that the new value is valid. */ if (old_ma->fsx_projid != fa->fsx_projid && !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid))) 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; } /** * vfs_fileattr_set - change miscellaneous file attributes * @idmap: idmap of the mount * @dentry: the object to change * @fa: fileattr pointer * * After verifying permissions, call i_op->fileattr_set() callback, if * exists. * * Verifying attributes involves retrieving current attributes with * i_op->fileattr_get(), this also allows initializing attributes that have * not been set by the caller to current values. Inode lock is held * thoughout to prevent racing with another instance. * * Return: 0 on success, or a negative error on failure. */ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry, struct fileattr *fa) { struct inode *inode = d_inode(dentry); struct fileattr old_ma = {}; int err; if (!inode->i_op->fileattr_set) return -ENOIOCTLCMD; if (!inode_owner_or_capable(idmap, inode)) return -EPERM; inode_lock(inode); err = vfs_fileattr_get(dentry, &old_ma); if (!err) { /* initialize missing bits from old_ma */ if (fa->flags_valid) { fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON; fa->fsx_extsize = old_ma.fsx_extsize; fa->fsx_nextents = old_ma.fsx_nextents; fa->fsx_projid = old_ma.fsx_projid; fa->fsx_cowextsize = old_ma.fsx_cowextsize; } else { fa->flags |= old_ma.flags & ~FS_COMMON_FL; } err = fileattr_set_prepare(inode, &old_ma, fa); if (!err) err = inode->i_op->fileattr_set(idmap, dentry, fa); } inode_unlock(inode); return err; } EXPORT_SYMBOL(vfs_fileattr_set); static int ioctl_getflags(struct file *file, unsigned int __user *argp) { struct fileattr fa = { .flags_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = put_user(fa.flags, argp); return err; } static int ioctl_setflags(struct file *file, unsigned int __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; unsigned int flags; int err; err = get_user(flags, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { fileattr_fill_flags(&fa, flags); err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } static int ioctl_fsgetxattr(struct file *file, void __user *argp) { struct fileattr fa = { .fsx_valid = true }; /* hint only */ int err; err = vfs_fileattr_get(file->f_path.dentry, &fa); if (!err) err = copy_fsxattr_to_user(&fa, argp); return err; } static int ioctl_fssetxattr(struct file *file, void __user *argp) { struct mnt_idmap *idmap = file_mnt_idmap(file); struct dentry *dentry = file->f_path.dentry; struct fileattr fa; int err; err = copy_fsxattr_from_user(&fa, argp); if (!err) { err = mnt_want_write_file(file); if (!err) { err = vfs_fileattr_set(idmap, dentry, &fa); mnt_drop_write_file(file); } } return err; } static int ioctl_getfsuuid(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; struct fsuuid2 u = { .len = sb->s_uuid_len, }; if (!sb->s_uuid_len) return -ENOTTY; memcpy(&u.uuid[0], &sb->s_uuid, sb->s_uuid_len); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } static int ioctl_get_fs_sysfs_path(struct file *file, void __user *argp) { struct super_block *sb = file_inode(file)->i_sb; if (!strlen(sb->s_sysfs_name)) return -ENOTTY; struct fs_sysfs_path u = {}; u.len = scnprintf(u.name, sizeof(u.name), "%s/%s", sb->s_type->name, sb->s_sysfs_name); return copy_to_user(argp, &u, sizeof(u)) ? -EFAULT : 0; } /* * do_vfs_ioctl() is not for drivers and not intended to be EXPORT_SYMBOL()'d. * It's just a simple helper for sys_ioctl and compat_sys_ioctl. * * When you add any new common ioctls to the switches above and below, * please ensure they have compatible arguments in compat mode. * * The LSM mailing list should also be notified of any command additions or * changes, as specific LSMs may be affected. */ static int do_vfs_ioctl(struct file *filp, unsigned int fd, unsigned int cmd, unsigned long arg) { void __user *argp = (void __user *)arg; struct inode *inode = file_inode(filp); switch (cmd) { case FIOCLEX: set_close_on_exec(fd, 1); return 0; case FIONCLEX: set_close_on_exec(fd, 0); return 0; case FIONBIO: return ioctl_fionbio(filp, argp); case FIOASYNC: return ioctl_fioasync(fd, filp, argp); case FIOQSIZE: if (S_ISDIR(inode->i_mode) || S_ISREG(inode->i_mode) || S_ISLNK(inode->i_mode)) { loff_t res = inode_get_bytes(inode); return copy_to_user(argp, &res, sizeof(res)) ? -EFAULT : 0; } return -ENOTTY; case FIFREEZE: return ioctl_fsfreeze(filp); case FITHAW: return ioctl_fsthaw(filp); case FS_IOC_FIEMAP: return ioctl_fiemap(filp, argp); case FIGETBSZ: /* anon_bdev filesystems may not have a block size */ if (!inode->i_sb->s_blocksize) return -EINVAL; return put_user(inode->i_sb->s_blocksize, (int __user *)argp); case FICLONE: return ioctl_file_clone(filp, arg, 0, 0, 0); case FICLONERANGE: return ioctl_file_clone_range(filp, argp); case FIDEDUPERANGE: return ioctl_file_dedupe_range(filp, argp); case FIONREAD: if (!S_ISREG(inode->i_mode)) return vfs_ioctl(filp, cmd, arg); return put_user(i_size_read(inode) - filp->f_pos, (int __user *)argp); case FS_IOC_GETFLAGS: return ioctl_getflags(filp, argp); case FS_IOC_SETFLAGS: return ioctl_setflags(filp, argp); case FS_IOC_FSGETXATTR: return ioctl_fsgetxattr(filp, argp); case FS_IOC_FSSETXATTR: return ioctl_fssetxattr(filp, argp); case FS_IOC_GETFSUUID: return ioctl_getfsuuid(filp, argp); case FS_IOC_GETFSSYSFSPATH: return ioctl_get_fs_sysfs_path(filp, argp); default: if (S_ISREG(inode->i_mode)) return file_ioctl(filp, cmd, argp); break; } return -ENOIOCTLCMD; } SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, unsigned long, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl(f.file, cmd, arg); if (error) goto out; error = do_vfs_ioctl(f.file, fd, cmd, arg); if (error == -ENOIOCTLCMD) error = vfs_ioctl(f.file, cmd, arg); out: fdput(f); return error; } #ifdef CONFIG_COMPAT /** * compat_ptr_ioctl - generic implementation of .compat_ioctl file operation * @file: The file to operate on. * @cmd: The ioctl command number. * @arg: The argument to the ioctl. * * This is not normally called as a function, but instead set in struct * file_operations as * * .compat_ioctl = compat_ptr_ioctl, * * On most architectures, the compat_ptr_ioctl() just passes all arguments * to the corresponding ->ioctl handler. The exception is arch/s390, where * compat_ptr() clears the top bit of a 32-bit pointer value, so user space * pointers to the second 2GB alias the first 2GB, as is the case for * native 32-bit s390 user space. * * The compat_ptr_ioctl() function must therefore be used only with ioctl * functions that either ignore the argument or pass a pointer to a * compatible data type. * * If any ioctl command handled by fops->unlocked_ioctl passes a plain * integer instead of a pointer, or any of the passed data types * is incompatible between 32-bit and 64-bit architectures, a proper * handler is required instead of compat_ptr_ioctl. */ long compat_ptr_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { if (!file->f_op->unlocked_ioctl) return -ENOIOCTLCMD; return file->f_op->unlocked_ioctl(file, cmd, (unsigned long)compat_ptr(arg)); } EXPORT_SYMBOL(compat_ptr_ioctl); COMPAT_SYSCALL_DEFINE3(ioctl, unsigned int, fd, unsigned int, cmd, compat_ulong_t, arg) { struct fd f = fdget(fd); int error; if (!f.file) return -EBADF; error = security_file_ioctl_compat(f.file, cmd, arg); if (error) goto out; switch (cmd) { /* FICLONE takes an int argument, so don't use compat_ptr() */ case FICLONE: error = ioctl_file_clone(f.file, arg, 0, 0, 0); break; #if defined(CONFIG_X86_64) /* these get messy on amd64 due to alignment differences */ case FS_IOC_RESVSP_32: case FS_IOC_RESVSP64_32: error = compat_ioctl_preallocate(f.file, 0, compat_ptr(arg)); break; case FS_IOC_UNRESVSP_32: case FS_IOC_UNRESVSP64_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_PUNCH_HOLE, compat_ptr(arg)); break; case FS_IOC_ZERO_RANGE_32: error = compat_ioctl_preallocate(f.file, FALLOC_FL_ZERO_RANGE, compat_ptr(arg)); break; #endif /* * These access 32-bit values anyway so no further handling is * necessary. */ case FS_IOC32_GETFLAGS: case FS_IOC32_SETFLAGS: cmd = (cmd == FS_IOC32_GETFLAGS) ? FS_IOC_GETFLAGS : FS_IOC_SETFLAGS; fallthrough; /* * everything else in do_vfs_ioctl() takes either a compatible * pointer argument or no argument -- call it with a modified * argument. */ default: error = do_vfs_ioctl(f.file, fd, cmd, (unsigned long)compat_ptr(arg)); if (error != -ENOIOCTLCMD) break; if (f.file->f_op->compat_ioctl) error = f.file->f_op->compat_ioctl(f.file, cmd, arg); if (error == -ENOIOCTLCMD) error = -ENOTTY; break; } out: fdput(f); return error; } #endif |
| 1 1 1 148 16 2 1 1 1 1 2 2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2019 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <asm/kvm_emulate.h> #include <kvm/arm_hypercalls.h> #include <kvm/arm_psci.h> #define KVM_ARM_SMCCC_STD_FEATURES \ GENMASK(KVM_REG_ARM_STD_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_STD_HYP_FEATURES \ GENMASK(KVM_REG_ARM_STD_HYP_BMAP_BIT_COUNT - 1, 0) #define KVM_ARM_SMCCC_VENDOR_HYP_FEATURES \ GENMASK(KVM_REG_ARM_VENDOR_HYP_BMAP_BIT_COUNT - 1, 0) static void kvm_ptp_get_time(struct kvm_vcpu *vcpu, u64 *val) { struct system_time_snapshot systime_snapshot; u64 cycles = ~0UL; u32 feature; /* * system time and counter value must captured at the same * time to keep consistency and precision. */ ktime_get_snapshot(&systime_snapshot); /* * This is only valid if the current clocksource is the * architected counter, as this is the only one the guest * can see. */ if (systime_snapshot.cs_id != CSID_ARM_ARCH_COUNTER) return; /* * The guest selects one of the two reference counters * (virtual or physical) with the first argument of the SMCCC * call. In case the identifier is not supported, error out. */ feature = smccc_get_arg1(vcpu); switch (feature) { case KVM_PTP_VIRT_COUNTER: cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.voffset; break; case KVM_PTP_PHYS_COUNTER: cycles = systime_snapshot.cycles - vcpu->kvm->arch.timer_data.poffset; break; default: return; } /* * This relies on the top bit of val[0] never being set for * valid values of system time, because that is *really* far * in the future (about 292 years from 1970, and at that stage * nobody will give a damn about it). */ val[0] = upper_32_bits(systime_snapshot.real); val[1] = lower_32_bits(systime_snapshot.real); val[2] = upper_32_bits(cycles); val[3] = lower_32_bits(cycles); } static bool kvm_smccc_default_allowed(u32 func_id) { switch (func_id) { /* * List of function-ids that are not gated with the bitmapped * feature firmware registers, and are to be allowed for * servicing the call by default. */ case ARM_SMCCC_VERSION_FUNC_ID: case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: return true; default: /* PSCI 0.2 and up is in the 0:0x1f range */ if (ARM_SMCCC_OWNER_NUM(func_id) == ARM_SMCCC_OWNER_STANDARD && ARM_SMCCC_FUNC_NUM(func_id) <= 0x1f) return true; /* * KVM's PSCI 0.1 doesn't comply with SMCCC, and has * its own function-id base and range */ if (func_id >= KVM_PSCI_FN(0) && func_id <= KVM_PSCI_FN(3)) return true; return false; } } static bool kvm_smccc_test_fw_bmap(struct kvm_vcpu *vcpu, u32 func_id) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; switch (func_id) { case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: return test_bit(KVM_REG_ARM_STD_BIT_TRNG_V1_0, &smccc_feat->std_bmap); case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: return test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, &smccc_feat->std_hyp_bmap); case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_FUNC_FEAT, &smccc_feat->vendor_hyp_bmap); case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: return test_bit(KVM_REG_ARM_VENDOR_HYP_BIT_PTP, &smccc_feat->vendor_hyp_bmap); default: return false; } } #define SMC32_ARCH_RANGE_BEGIN ARM_SMCCC_VERSION_FUNC_ID #define SMC32_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_32, \ 0, ARM_SMCCC_FUNC_MASK) #define SMC64_ARCH_RANGE_BEGIN ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ 0, 0) #define SMC64_ARCH_RANGE_END ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL, \ ARM_SMCCC_SMC_64, \ 0, ARM_SMCCC_FUNC_MASK) static int kvm_smccc_filter_insert_reserved(struct kvm *kvm) { int r; /* * Prevent userspace from handling any SMCCC calls in the architecture * range, avoiding the risk of misrepresenting Spectre mitigation status * to the guest. */ r = mtree_insert_range(&kvm->arch.smccc_filter, SMC32_ARCH_RANGE_BEGIN, SMC32_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); if (r) goto out_destroy; r = mtree_insert_range(&kvm->arch.smccc_filter, SMC64_ARCH_RANGE_BEGIN, SMC64_ARCH_RANGE_END, xa_mk_value(KVM_SMCCC_FILTER_HANDLE), GFP_KERNEL_ACCOUNT); if (r) goto out_destroy; return 0; out_destroy: mtree_destroy(&kvm->arch.smccc_filter); return r; } static bool kvm_smccc_filter_configured(struct kvm *kvm) { return !mtree_empty(&kvm->arch.smccc_filter); } static int kvm_smccc_set_filter(struct kvm *kvm, struct kvm_smccc_filter __user *uaddr) { const void *zero_page = page_to_virt(ZERO_PAGE(0)); struct kvm_smccc_filter filter; u32 start, end; int r; if (copy_from_user(&filter, uaddr, sizeof(filter))) return -EFAULT; if (memcmp(filter.pad, zero_page, sizeof(filter.pad))) return -EINVAL; start = filter.base; end = start + filter.nr_functions - 1; if (end < start || filter.action >= NR_SMCCC_FILTER_ACTIONS) return -EINVAL; mutex_lock(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm)) { r = -EBUSY; goto out_unlock; } if (!kvm_smccc_filter_configured(kvm)) { r = kvm_smccc_filter_insert_reserved(kvm); if (WARN_ON_ONCE(r)) goto out_unlock; } r = mtree_insert_range(&kvm->arch.smccc_filter, start, end, xa_mk_value(filter.action), GFP_KERNEL_ACCOUNT); out_unlock: mutex_unlock(&kvm->arch.config_lock); return r; } static u8 kvm_smccc_filter_get_action(struct kvm *kvm, u32 func_id) { unsigned long idx = func_id; void *val; if (!kvm_smccc_filter_configured(kvm)) return KVM_SMCCC_FILTER_HANDLE; /* * But where's the error handling, you say? * * mt_find() returns NULL if no entry was found, which just so happens * to match KVM_SMCCC_FILTER_HANDLE. */ val = mt_find(&kvm->arch.smccc_filter, &idx, idx); return xa_to_value(val); } static u8 kvm_smccc_get_action(struct kvm_vcpu *vcpu, u32 func_id) { /* * Intervening actions in the SMCCC filter take precedence over the * pseudo-firmware register bitmaps. */ u8 action = kvm_smccc_filter_get_action(vcpu->kvm, func_id); if (action != KVM_SMCCC_FILTER_HANDLE) return action; if (kvm_smccc_test_fw_bmap(vcpu, func_id) || kvm_smccc_default_allowed(func_id)) return KVM_SMCCC_FILTER_HANDLE; return KVM_SMCCC_FILTER_DENY; } static void kvm_prepare_hypercall_exit(struct kvm_vcpu *vcpu, u32 func_id) { u8 ec = ESR_ELx_EC(kvm_vcpu_get_esr(vcpu)); struct kvm_run *run = vcpu->run; u64 flags = 0; if (ec == ESR_ELx_EC_SMC32 || ec == ESR_ELx_EC_SMC64) flags |= KVM_HYPERCALL_EXIT_SMC; if (!kvm_vcpu_trap_il_is32bit(vcpu)) flags |= KVM_HYPERCALL_EXIT_16BIT; run->exit_reason = KVM_EXIT_HYPERCALL; run->hypercall = (typeof(run->hypercall)) { .nr = func_id, .flags = flags, }; } int kvm_smccc_call_handler(struct kvm_vcpu *vcpu) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; u32 func_id = smccc_get_function(vcpu); u64 val[4] = {SMCCC_RET_NOT_SUPPORTED}; u32 feature; u8 action; gpa_t gpa; action = kvm_smccc_get_action(vcpu, func_id); switch (action) { case KVM_SMCCC_FILTER_HANDLE: break; case KVM_SMCCC_FILTER_DENY: goto out; case KVM_SMCCC_FILTER_FWD_TO_USER: kvm_prepare_hypercall_exit(vcpu, func_id); return 0; default: WARN_RATELIMIT(1, "Unhandled SMCCC filter action: %d\n", action); goto out; } switch (func_id) { case ARM_SMCCC_VERSION_FUNC_ID: val[0] = ARM_SMCCC_VERSION_1_1; break; case ARM_SMCCC_ARCH_FEATURES_FUNC_ID: feature = smccc_get_arg1(vcpu); switch (feature) { case ARM_SMCCC_ARCH_WORKAROUND_1: switch (arm64_get_spectre_v2_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: val[0] = SMCCC_RET_SUCCESS; break; case SPECTRE_UNAFFECTED: val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; break; } break; case ARM_SMCCC_ARCH_WORKAROUND_2: switch (arm64_get_spectre_v4_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: /* * SSBS everywhere: Indicate no firmware * support, as the SSBS support will be * indicated to the guest and the default is * safe. * * Otherwise, expose a permanent mitigation * to the guest, and hide SSBS so that the * guest stays protected. */ if (cpus_have_final_cap(ARM64_SSBS)) break; fallthrough; case SPECTRE_UNAFFECTED: val[0] = SMCCC_RET_NOT_REQUIRED; break; } break; case ARM_SMCCC_ARCH_WORKAROUND_3: switch (arm64_get_spectre_bhb_state()) { case SPECTRE_VULNERABLE: break; case SPECTRE_MITIGATED: val[0] = SMCCC_RET_SUCCESS; break; case SPECTRE_UNAFFECTED: val[0] = SMCCC_ARCH_WORKAROUND_RET_UNAFFECTED; break; } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: if (test_bit(KVM_REG_ARM_STD_HYP_BIT_PV_TIME, &smccc_feat->std_hyp_bmap)) val[0] = SMCCC_RET_SUCCESS; break; } break; case ARM_SMCCC_HV_PV_TIME_FEATURES: val[0] = kvm_hypercall_pv_features(vcpu); break; case ARM_SMCCC_HV_PV_TIME_ST: gpa = kvm_init_stolen_time(vcpu); if (gpa != INVALID_GPA) val[0] = gpa; break; case ARM_SMCCC_VENDOR_HYP_CALL_UID_FUNC_ID: val[0] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_0; val[1] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_1; val[2] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_2; val[3] = ARM_SMCCC_VENDOR_HYP_UID_KVM_REG_3; break; case ARM_SMCCC_VENDOR_HYP_KVM_FEATURES_FUNC_ID: val[0] = smccc_feat->vendor_hyp_bmap; break; case ARM_SMCCC_VENDOR_HYP_KVM_PTP_FUNC_ID: kvm_ptp_get_time(vcpu, val); break; case ARM_SMCCC_TRNG_VERSION: case ARM_SMCCC_TRNG_FEATURES: case ARM_SMCCC_TRNG_GET_UUID: case ARM_SMCCC_TRNG_RND32: case ARM_SMCCC_TRNG_RND64: return kvm_trng_call(vcpu); default: return kvm_psci_call(vcpu); } out: smccc_set_retval(vcpu, val[0], val[1], val[2], val[3]); return 1; } static const u64 kvm_arm_fw_reg_ids[] = { KVM_REG_ARM_PSCI_VERSION, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2, KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3, KVM_REG_ARM_STD_BMAP, KVM_REG_ARM_STD_HYP_BMAP, KVM_REG_ARM_VENDOR_HYP_BMAP, }; void kvm_arm_init_hypercalls(struct kvm *kvm) { struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; smccc_feat->std_bmap = KVM_ARM_SMCCC_STD_FEATURES; smccc_feat->std_hyp_bmap = KVM_ARM_SMCCC_STD_HYP_FEATURES; smccc_feat->vendor_hyp_bmap = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; mt_init(&kvm->arch.smccc_filter); } void kvm_arm_teardown_hypercalls(struct kvm *kvm) { mtree_destroy(&kvm->arch.smccc_filter); } int kvm_arm_get_fw_num_regs(struct kvm_vcpu *vcpu) { return ARRAY_SIZE(kvm_arm_fw_reg_ids); } int kvm_arm_copy_fw_reg_indices(struct kvm_vcpu *vcpu, u64 __user *uindices) { int i; for (i = 0; i < ARRAY_SIZE(kvm_arm_fw_reg_ids); i++) { if (put_user(kvm_arm_fw_reg_ids[i], uindices++)) return -EFAULT; } return 0; } #define KVM_REG_FEATURE_LEVEL_MASK GENMASK(3, 0) /* * Convert the workaround level into an easy-to-compare number, where higher * values mean better protection. */ static int get_kernel_wa_level(u64 regid) { switch (regid) { case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: switch (arm64_get_spectre_v2_state()) { case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; case SPECTRE_MITIGATED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_AVAIL; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_REQUIRED; } return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1_NOT_AVAIL; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: switch (arm64_get_spectre_v4_state()) { case SPECTRE_MITIGATED: /* * As for the hypercall discovery, we pretend we * don't have any FW mitigation if SSBS is there at * all times. */ if (cpus_have_final_cap(ARM64_SSBS)) return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; fallthrough; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; } break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: switch (arm64_get_spectre_bhb_state()) { case SPECTRE_VULNERABLE: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; case SPECTRE_MITIGATED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_AVAIL; case SPECTRE_UNAFFECTED: return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_REQUIRED; } return KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3_NOT_AVAIL; } return -EINVAL; } int kvm_arm_get_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { struct kvm_smccc_features *smccc_feat = &vcpu->kvm->arch.smccc_feat; void __user *uaddr = (void __user *)(long)reg->addr; u64 val; switch (reg->id) { case KVM_REG_ARM_PSCI_VERSION: val = kvm_psci_version(vcpu); break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: val = get_kernel_wa_level(reg->id) & KVM_REG_FEATURE_LEVEL_MASK; break; case KVM_REG_ARM_STD_BMAP: val = READ_ONCE(smccc_feat->std_bmap); break; case KVM_REG_ARM_STD_HYP_BMAP: val = READ_ONCE(smccc_feat->std_hyp_bmap); break; case KVM_REG_ARM_VENDOR_HYP_BMAP: val = READ_ONCE(smccc_feat->vendor_hyp_bmap); break; default: return -ENOENT; } if (copy_to_user(uaddr, &val, KVM_REG_SIZE(reg->id))) return -EFAULT; return 0; } static int kvm_arm_set_fw_reg_bmap(struct kvm_vcpu *vcpu, u64 reg_id, u64 val) { int ret = 0; struct kvm *kvm = vcpu->kvm; struct kvm_smccc_features *smccc_feat = &kvm->arch.smccc_feat; unsigned long *fw_reg_bmap, fw_reg_features; switch (reg_id) { case KVM_REG_ARM_STD_BMAP: fw_reg_bmap = &smccc_feat->std_bmap; fw_reg_features = KVM_ARM_SMCCC_STD_FEATURES; break; case KVM_REG_ARM_STD_HYP_BMAP: fw_reg_bmap = &smccc_feat->std_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_STD_HYP_FEATURES; break; case KVM_REG_ARM_VENDOR_HYP_BMAP: fw_reg_bmap = &smccc_feat->vendor_hyp_bmap; fw_reg_features = KVM_ARM_SMCCC_VENDOR_HYP_FEATURES; break; default: return -ENOENT; } /* Check for unsupported bit */ if (val & ~fw_reg_features) return -EINVAL; mutex_lock(&kvm->arch.config_lock); if (kvm_vm_has_ran_once(kvm) && val != *fw_reg_bmap) { ret = -EBUSY; goto out; } WRITE_ONCE(*fw_reg_bmap, val); out: mutex_unlock(&kvm->arch.config_lock); return ret; } int kvm_arm_set_fw_reg(struct kvm_vcpu *vcpu, const struct kvm_one_reg *reg) { void __user *uaddr = (void __user *)(long)reg->addr; u64 val; int wa_level; if (KVM_REG_SIZE(reg->id) != sizeof(val)) return -ENOENT; if (copy_from_user(&val, uaddr, KVM_REG_SIZE(reg->id))) return -EFAULT; switch (reg->id) { case KVM_REG_ARM_PSCI_VERSION: { bool wants_02; wants_02 = vcpu_has_feature(vcpu, KVM_ARM_VCPU_PSCI_0_2); switch (val) { case KVM_ARM_PSCI_0_1: if (wants_02) return -EINVAL; vcpu->kvm->arch.psci_version = val; return 0; case KVM_ARM_PSCI_0_2: case KVM_ARM_PSCI_1_0: case KVM_ARM_PSCI_1_1: if (!wants_02) return -EINVAL; vcpu->kvm->arch.psci_version = val; return 0; } break; } case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_1: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_3: if (val & ~KVM_REG_FEATURE_LEVEL_MASK) return -EINVAL; if (get_kernel_wa_level(reg->id) < val) return -EINVAL; return 0; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2: if (val & ~(KVM_REG_FEATURE_LEVEL_MASK | KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED)) return -EINVAL; /* The enabled bit must not be set unless the level is AVAIL. */ if ((val & KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_ENABLED) && (val & KVM_REG_FEATURE_LEVEL_MASK) != KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL) return -EINVAL; /* * Map all the possible incoming states to the only two we * really want to deal with. */ switch (val & KVM_REG_FEATURE_LEVEL_MASK) { case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_UNKNOWN: wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_AVAIL; break; case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_AVAIL: case KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED: wa_level = KVM_REG_ARM_SMCCC_ARCH_WORKAROUND_2_NOT_REQUIRED; break; default: return -EINVAL; } /* * We can deal with NOT_AVAIL on NOT_REQUIRED, but not the * other way around. */ if (get_kernel_wa_level(reg->id) < wa_level) return -EINVAL; return 0; case KVM_REG_ARM_STD_BMAP: case KVM_REG_ARM_STD_HYP_BMAP: case KVM_REG_ARM_VENDOR_HYP_BMAP: return kvm_arm_set_fw_reg_bmap(vcpu, reg->id, val); default: return -ENOENT; } return -EINVAL; } int kvm_vm_smccc_has_attr(struct kvm *kvm, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VM_SMCCC_FILTER: return 0; default: return -ENXIO; } } int kvm_vm_smccc_set_attr(struct kvm *kvm, struct kvm_device_attr *attr) { void __user *uaddr = (void __user *)attr->addr; switch (attr->attr) { case KVM_ARM_VM_SMCCC_FILTER: return kvm_smccc_set_filter(kvm, uaddr); default: return -ENXIO; } } |
| 100 84 95 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_SWAP_H #define _LINUX_SWAP_H #include <linux/spinlock.h> #include <linux/linkage.h> #include <linux/mmzone.h> #include <linux/list.h> #include <linux/memcontrol.h> #include <linux/sched.h> #include <linux/node.h> #include <linux/fs.h> #include <linux/pagemap.h> #include <linux/atomic.h> #include <linux/page-flags.h> #include <uapi/linux/mempolicy.h> #include <asm/page.h> struct notifier_block; struct bio; struct pagevec; #define SWAP_FLAG_PREFER 0x8000 /* set if swap priority specified */ #define SWAP_FLAG_PRIO_MASK 0x7fff #define SWAP_FLAG_PRIO_SHIFT 0 #define SWAP_FLAG_DISCARD 0x10000 /* enable discard for swap */ #define SWAP_FLAG_DISCARD_ONCE 0x20000 /* discard swap area at swapon-time */ #define SWAP_FLAG_DISCARD_PAGES 0x40000 /* discard page-clusters after use */ #define SWAP_FLAGS_VALID (SWAP_FLAG_PRIO_MASK | SWAP_FLAG_PREFER | \ SWAP_FLAG_DISCARD | SWAP_FLAG_DISCARD_ONCE | \ SWAP_FLAG_DISCARD_PAGES) #define SWAP_BATCH 64 static inline int current_is_kswapd(void) { return current->flags & PF_KSWAPD; } /* * MAX_SWAPFILES defines the maximum number of swaptypes: things which can * be swapped to. The swap type and the offset into that swap type are * encoded into pte's and into pgoff_t's in the swapcache. Using five bits * for the type means that the maximum number of swapcache pages is 27 bits * on 32-bit-pgoff_t architectures. And that assumes that the architecture packs * the type/offset into the pte as 5/27 as well. */ #define MAX_SWAPFILES_SHIFT 5 /* * Use some of the swap files numbers for other purposes. This * is a convenient way to hook into the VM to trigger special * actions on faults. */ /* * PTE markers are used to persist information onto PTEs that otherwise * should be a none pte. As its name "PTE" hints, it should only be * applied to the leaves of pgtables. */ #define SWP_PTE_MARKER_NUM 1 #define SWP_PTE_MARKER (MAX_SWAPFILES + SWP_HWPOISON_NUM + \ SWP_MIGRATION_NUM + SWP_DEVICE_NUM) /* * Unaddressable device memory support. See include/linux/hmm.h and * Documentation/mm/hmm.rst. Short description is we need struct pages for * device memory that is unaddressable (inaccessible) by CPU, so that we can * migrate part of a process memory to device memory. * * When a page is migrated from CPU to device, we set the CPU page table entry * to a special SWP_DEVICE_{READ|WRITE} entry. * * When a page is mapped by the device for exclusive access we set the CPU page * table entries to special SWP_DEVICE_EXCLUSIVE_* entries. */ #ifdef CONFIG_DEVICE_PRIVATE #define SWP_DEVICE_NUM 4 #define SWP_DEVICE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM) #define SWP_DEVICE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+1) #define SWP_DEVICE_EXCLUSIVE_WRITE (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+2) #define SWP_DEVICE_EXCLUSIVE_READ (MAX_SWAPFILES+SWP_HWPOISON_NUM+SWP_MIGRATION_NUM+3) #else #define SWP_DEVICE_NUM 0 #endif /* * Page migration support. * * SWP_MIGRATION_READ_EXCLUSIVE is only applicable to anonymous pages and * indicates that the referenced (part of) an anonymous page is exclusive to * a single process. For SWP_MIGRATION_WRITE, that information is implicit: * (part of) an anonymous page that are mapped writable are exclusive to a * single process. */ #ifdef CONFIG_MIGRATION #define SWP_MIGRATION_NUM 3 #define SWP_MIGRATION_READ (MAX_SWAPFILES + SWP_HWPOISON_NUM) #define SWP_MIGRATION_READ_EXCLUSIVE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 1) #define SWP_MIGRATION_WRITE (MAX_SWAPFILES + SWP_HWPOISON_NUM + 2) #else #define SWP_MIGRATION_NUM 0 #endif /* * Handling of hardware poisoned pages with memory corruption. */ #ifdef CONFIG_MEMORY_FAILURE #define SWP_HWPOISON_NUM 1 #define SWP_HWPOISON MAX_SWAPFILES #else #define SWP_HWPOISON_NUM 0 #endif #define MAX_SWAPFILES \ ((1 << MAX_SWAPFILES_SHIFT) - SWP_DEVICE_NUM - \ SWP_MIGRATION_NUM - SWP_HWPOISON_NUM - \ SWP_PTE_MARKER_NUM) /* * Magic header for a swap area. The first part of the union is * what the swap magic looks like for the old (limited to 128MB) * swap area format, the second part of the union adds - in the * old reserved area - some extra information. Note that the first * kilobyte is reserved for boot loader or disk label stuff... * * Having the magic at the end of the PAGE_SIZE makes detecting swap * areas somewhat tricky on machines that support multiple page sizes. * For 2.5 we'll probably want to move the magic to just beyond the * bootbits... */ union swap_header { struct { char reserved[PAGE_SIZE - 10]; char magic[10]; /* SWAP-SPACE or SWAPSPACE2 */ } magic; struct { char bootbits[1024]; /* Space for disklabel etc. */ __u32 version; __u32 last_page; __u32 nr_badpages; unsigned char sws_uuid[16]; unsigned char sws_volume[16]; __u32 padding[117]; __u32 badpages[1]; } info; }; /* * current->reclaim_state points to one of these when a task is running * memory reclaim */ struct reclaim_state { /* pages reclaimed outside of LRU-based reclaim */ unsigned long reclaimed; #ifdef CONFIG_LRU_GEN /* per-thread mm walk data */ struct lru_gen_mm_walk *mm_walk; #endif }; /* * mm_account_reclaimed_pages(): account reclaimed pages outside of LRU-based * reclaim * @pages: number of pages reclaimed * * If the current process is undergoing a reclaim operation, increment the * number of reclaimed pages by @pages. */ static inline void mm_account_reclaimed_pages(unsigned long pages) { if (current->reclaim_state) current->reclaim_state->reclaimed += pages; } #ifdef __KERNEL__ struct address_space; struct sysinfo; struct writeback_control; struct zone; /* * A swap extent maps a range of a swapfile's PAGE_SIZE pages onto a range of * disk blocks. A rbtree of swap extents maps the entire swapfile (Where the * term `swapfile' refers to either a blockdevice or an IS_REG file). Apart * from setup, they're handled identically. * * We always assume that blocks are of size PAGE_SIZE. */ struct swap_extent { struct rb_node rb_node; pgoff_t start_page; pgoff_t nr_pages; sector_t start_block; }; /* * Max bad pages in the new format.. */ #define MAX_SWAP_BADPAGES \ ((offsetof(union swap_header, magic.magic) - \ offsetof(union swap_header, info.badpages)) / sizeof(int)) enum { SWP_USED = (1 << 0), /* is slot in swap_info[] used? */ SWP_WRITEOK = (1 << 1), /* ok to write to this swap? */ SWP_DISCARDABLE = (1 << 2), /* blkdev support discard */ SWP_DISCARDING = (1 << 3), /* now discarding a free cluster */ SWP_SOLIDSTATE = (1 << 4), /* blkdev seeks are cheap */ SWP_CONTINUED = (1 << 5), /* swap_map has count continuation */ SWP_BLKDEV = (1 << 6), /* its a block device */ SWP_ACTIVATED = (1 << 7), /* set after swap_activate success */ SWP_FS_OPS = (1 << 8), /* swapfile operations go through fs */ SWP_AREA_DISCARD = (1 << 9), /* single-time swap area discards */ SWP_PAGE_DISCARD = (1 << 10), /* freed swap page-cluster discards */ SWP_STABLE_WRITES = (1 << 11), /* no overwrite PG_writeback pages */ SWP_SYNCHRONOUS_IO = (1 << 12), /* synchronous IO is efficient */ /* add others here before... */ SWP_SCANNING = (1 << 14), /* refcount in scan_swap_map */ }; #define SWAP_CLUSTER_MAX 32UL #define COMPACT_CLUSTER_MAX SWAP_CLUSTER_MAX /* Bit flag in swap_map */ #define SWAP_HAS_CACHE 0x40 /* Flag page is cached, in first swap_map */ #define COUNT_CONTINUED 0x80 /* Flag swap_map continuation for full count */ /* Special value in first swap_map */ #define SWAP_MAP_MAX 0x3e /* Max count */ #define SWAP_MAP_BAD 0x3f /* Note page is bad */ #define SWAP_MAP_SHMEM 0xbf /* Owned by shmem/tmpfs */ /* Special value in each swap_map continuation */ #define SWAP_CONT_MAX 0x7f /* Max count */ /* * We use this to track usage of a cluster. A cluster is a block of swap disk * space with SWAPFILE_CLUSTER pages long and naturally aligns in disk. All * free clusters are organized into a list. We fetch an entry from the list to * get a free cluster. * * The data field stores next cluster if the cluster is free or cluster usage * counter otherwise. The flags field determines if a cluster is free. This is * protected by swap_info_struct.lock. */ struct swap_cluster_info { spinlock_t lock; /* * Protect swap_cluster_info fields * and swap_info_struct->swap_map * elements correspond to the swap * cluster */ unsigned int data:24; unsigned int flags:8; }; #define CLUSTER_FLAG_FREE 1 /* This cluster is free */ #define CLUSTER_FLAG_NEXT_NULL 2 /* This cluster has no next cluster */ /* * The first page in the swap file is the swap header, which is always marked * bad to prevent it from being allocated as an entry. This also prevents the * cluster to which it belongs being marked free. Therefore 0 is safe to use as * a sentinel to indicate next is not valid in percpu_cluster. */ #define SWAP_NEXT_INVALID 0 #ifdef CONFIG_THP_SWAP #define SWAP_NR_ORDERS (PMD_ORDER + 1) #else #define SWAP_NR_ORDERS 1 #endif /* * We assign a cluster to each CPU, so each CPU can allocate swap entry from * its own cluster and swapout sequentially. The purpose is to optimize swapout * throughput. */ struct percpu_cluster { unsigned int next[SWAP_NR_ORDERS]; /* Likely next allocation offset */ }; struct swap_cluster_list { struct swap_cluster_info head; struct swap_cluster_info tail; }; /* * The in-memory structure used to track swap areas. */ struct swap_info_struct { struct percpu_ref users; /* indicate and keep swap device valid. */ unsigned long flags; /* SWP_USED etc: see above */ signed short prio; /* swap priority of this type */ struct plist_node list; /* entry in swap_active_head */ signed char type; /* strange name for an index */ unsigned int max; /* extent of the swap_map */ unsigned char *swap_map; /* vmalloc'ed array of usage counts */ struct swap_cluster_info *cluster_info; /* cluster info. Only for SSD */ struct swap_cluster_list free_clusters; /* free clusters list */ unsigned int lowest_bit; /* index of first free in swap_map */ unsigned int highest_bit; /* index of last free in swap_map */ unsigned int pages; /* total of usable pages of swap */ unsigned int inuse_pages; /* number of those currently in use */ unsigned int cluster_next; /* likely index for next allocation */ unsigned int cluster_nr; /* countdown to next cluster search */ unsigned int __percpu *cluster_next_cpu; /*percpu index for next allocation */ struct percpu_cluster __percpu *percpu_cluster; /* per cpu's swap location */ struct rb_root swap_extent_root;/* root of the swap extent rbtree */ struct block_device *bdev; /* swap device or bdev of swap file */ struct file *swap_file; /* seldom referenced */ struct completion comp; /* seldom referenced */ spinlock_t lock; /* * protect map scan related fields like * swap_map, lowest_bit, highest_bit, * inuse_pages, cluster_next, * cluster_nr, lowest_alloc, * highest_alloc, free/discard cluster * list. other fields are only changed * at swapon/swapoff, so are protected * by swap_lock. changing flags need * hold this lock and swap_lock. If * both locks need hold, hold swap_lock * first. */ spinlock_t cont_lock; /* * protect swap count continuation page * list. */ struct work_struct discard_work; /* discard worker */ struct swap_cluster_list discard_clusters; /* discard clusters list */ struct plist_node avail_lists[]; /* * entries in swap_avail_heads, one * entry per node. * Must be last as the number of the * array is nr_node_ids, which is not * a fixed value so have to allocate * dynamically. * And it has to be an array so that * plist_for_each_* can work. */ }; static inline swp_entry_t page_swap_entry(struct page *page) { struct folio *folio = page_folio(page); swp_entry_t entry = folio->swap; entry.val += folio_page_idx(folio, page); return entry; } /* linux/mm/workingset.c */ bool workingset_test_recent(void *shadow, bool file, bool *workingset); void workingset_age_nonresident(struct lruvec *lruvec, unsigned long nr_pages); void *workingset_eviction(struct folio *folio, struct mem_cgroup *target_memcg); void workingset_refault(struct folio *folio, void *shadow); void workingset_activation(struct folio *folio); /* linux/mm/page_alloc.c */ extern unsigned long totalreserve_pages; /* Definition of global_zone_page_state not available yet */ #define nr_free_pages() global_zone_page_state(NR_FREE_PAGES) /* linux/mm/swap.c */ void lru_note_cost(struct lruvec *lruvec, bool file, unsigned int nr_io, unsigned int nr_rotated); void lru_note_cost_refault(struct folio *); void folio_add_lru(struct folio *); void folio_add_lru_vma(struct folio *, struct vm_area_struct *); void mark_page_accessed(struct page *); void folio_mark_accessed(struct folio *); extern atomic_t lru_disable_count; static inline bool lru_cache_disabled(void) { return atomic_read(&lru_disable_count); } static inline void lru_cache_enable(void) { atomic_dec(&lru_disable_count); } extern void lru_cache_disable(void); extern void lru_add_drain(void); extern void lru_add_drain_cpu(int cpu); extern void lru_add_drain_cpu_zone(struct zone *zone); extern void lru_add_drain_all(void); void folio_deactivate(struct folio *folio); void folio_mark_lazyfree(struct folio *folio); extern void swap_setup(void); /* linux/mm/vmscan.c */ extern unsigned long zone_reclaimable_pages(struct zone *zone); extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order, gfp_t gfp_mask, nodemask_t *mask); #define MEMCG_RECLAIM_MAY_SWAP (1 << 1) #define MEMCG_RECLAIM_PROACTIVE (1 << 2) extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, unsigned long nr_pages, gfp_t gfp_mask, unsigned int reclaim_options); extern unsigned long mem_cgroup_shrink_node(struct mem_cgroup *mem, gfp_t gfp_mask, bool noswap, pg_data_t *pgdat, unsigned long *nr_scanned); extern unsigned long shrink_all_memory(unsigned long nr_pages); extern int vm_swappiness; long remove_mapping(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_NUMA extern int node_reclaim_mode; extern int sysctl_min_unmapped_ratio; extern int sysctl_min_slab_ratio; #else #define node_reclaim_mode 0 #endif static inline bool node_reclaim_enabled(void) { /* Is any node_reclaim_mode bit set? */ return node_reclaim_mode & (RECLAIM_ZONE|RECLAIM_WRITE|RECLAIM_UNMAP); } void check_move_unevictable_folios(struct folio_batch *fbatch); extern void __meminit kswapd_run(int nid); extern void __meminit kswapd_stop(int nid); #ifdef CONFIG_SWAP int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block); int generic_swapfile_activate(struct swap_info_struct *, struct file *, sector_t *); static inline unsigned long total_swapcache_pages(void) { return global_node_page_state(NR_SWAPCACHE); } void free_swap_cache(struct folio *folio); void free_page_and_swap_cache(struct page *); void free_pages_and_swap_cache(struct encoded_page **, int); /* linux/mm/swapfile.c */ extern atomic_long_t nr_swap_pages; extern long total_swap_pages; extern atomic_t nr_rotate_swap; extern bool has_usable_swap(void); /* Swap 50% full? Release swapcache more aggressively.. */ static inline bool vm_swap_full(void) { return atomic_long_read(&nr_swap_pages) * 2 < total_swap_pages; } static inline long get_nr_swap_pages(void) { return atomic_long_read(&nr_swap_pages); } extern void si_swapinfo(struct sysinfo *); swp_entry_t folio_alloc_swap(struct folio *folio); bool folio_free_swap(struct folio *folio); void put_swap_folio(struct folio *folio, swp_entry_t entry); extern swp_entry_t get_swap_page_of_type(int); extern int get_swap_pages(int n, swp_entry_t swp_entries[], int order); extern int add_swap_count_continuation(swp_entry_t, gfp_t); extern void swap_shmem_alloc(swp_entry_t); extern int swap_duplicate(swp_entry_t); extern int swapcache_prepare(swp_entry_t); extern void swap_free(swp_entry_t); extern void swapcache_free_entries(swp_entry_t *entries, int n); extern void free_swap_and_cache_nr(swp_entry_t entry, int nr); int swap_type_of(dev_t device, sector_t offset); int find_first_swap(dev_t *device); extern unsigned int count_swap_pages(int, int); extern sector_t swapdev_block(int, pgoff_t); extern int __swap_count(swp_entry_t entry); extern int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry); extern int swp_swapcount(swp_entry_t entry); struct swap_info_struct *swp_swap_info(swp_entry_t entry); struct backing_dev_info; extern int init_swap_address_space(unsigned int type, unsigned long nr_pages); extern void exit_swap_address_space(unsigned int type); extern struct swap_info_struct *get_swap_device(swp_entry_t entry); sector_t swap_folio_sector(struct folio *folio); static inline void put_swap_device(struct swap_info_struct *si) { percpu_ref_put(&si->users); } #else /* CONFIG_SWAP */ static inline struct swap_info_struct *swp_swap_info(swp_entry_t entry) { return NULL; } static inline struct swap_info_struct *get_swap_device(swp_entry_t entry) { return NULL; } static inline void put_swap_device(struct swap_info_struct *si) { } #define get_nr_swap_pages() 0L #define total_swap_pages 0L #define total_swapcache_pages() 0UL #define vm_swap_full() 0 #define si_swapinfo(val) \ do { (val)->freeswap = (val)->totalswap = 0; } while (0) /* only sparc can not include linux/pagemap.h in this file * so leave put_page and release_pages undeclared... */ #define free_page_and_swap_cache(page) \ put_page(page) #define free_pages_and_swap_cache(pages, nr) \ release_pages((pages), (nr)); static inline void free_swap_and_cache_nr(swp_entry_t entry, int nr) { } static inline void free_swap_cache(struct folio *folio) { } static inline int add_swap_count_continuation(swp_entry_t swp, gfp_t gfp_mask) { return 0; } static inline void swap_shmem_alloc(swp_entry_t swp) { } static inline int swap_duplicate(swp_entry_t swp) { return 0; } static inline int swapcache_prepare(swp_entry_t swp) { return 0; } static inline void swap_free(swp_entry_t swp) { } static inline void put_swap_folio(struct folio *folio, swp_entry_t swp) { } static inline int __swap_count(swp_entry_t entry) { return 0; } static inline int swap_swapcount(struct swap_info_struct *si, swp_entry_t entry) { return 0; } static inline int swp_swapcount(swp_entry_t entry) { return 0; } static inline swp_entry_t folio_alloc_swap(struct folio *folio) { swp_entry_t entry; entry.val = 0; return entry; } static inline bool folio_free_swap(struct folio *folio) { return false; } static inline int add_swap_extent(struct swap_info_struct *sis, unsigned long start_page, unsigned long nr_pages, sector_t start_block) { return -EINVAL; } #endif /* CONFIG_SWAP */ static inline void free_swap_and_cache(swp_entry_t entry) { free_swap_and_cache_nr(entry, 1); } #ifdef CONFIG_MEMCG static inline int mem_cgroup_swappiness(struct mem_cgroup *memcg) { /* Cgroup2 doesn't have per-cgroup swappiness */ if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return READ_ONCE(vm_swappiness); /* root ? */ if (mem_cgroup_disabled() || mem_cgroup_is_root(memcg)) return READ_ONCE(vm_swappiness); return READ_ONCE(memcg->swappiness); } #else static inline int mem_cgroup_swappiness(struct mem_cgroup *mem) { return READ_ONCE(vm_swappiness); } #endif #if defined(CONFIG_SWAP) && defined(CONFIG_MEMCG) && defined(CONFIG_BLK_CGROUP) void __folio_throttle_swaprate(struct folio *folio, gfp_t gfp); static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { if (mem_cgroup_disabled()) return; __folio_throttle_swaprate(folio, gfp); } #else static inline void folio_throttle_swaprate(struct folio *folio, gfp_t gfp) { } #endif #if defined(CONFIG_MEMCG) && defined(CONFIG_SWAP) void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry); int __mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry); static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_try_charge_swap(folio, entry); } extern void __mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages); static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_swap(entry, nr_pages); } extern long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg); extern bool mem_cgroup_swap_full(struct folio *folio); #else static inline void mem_cgroup_swapout(struct folio *folio, swp_entry_t entry) { } static inline int mem_cgroup_try_charge_swap(struct folio *folio, swp_entry_t entry) { return 0; } static inline void mem_cgroup_uncharge_swap(swp_entry_t entry, unsigned int nr_pages) { } static inline long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) { return get_nr_swap_pages(); } static inline bool mem_cgroup_swap_full(struct folio *folio) { return vm_swap_full(); } #endif #endif /* __KERNEL__*/ #endif /* _LINUX_SWAP_H */ |
| 1 1 1 1 1 1 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 | // SPDX-License-Identifier: GPL-2.0 // Copyright (C) 2019 Arm Ltd. #include <linux/arm-smccc.h> #include <linux/kvm_host.h> #include <linux/sched/stat.h> #include <asm/kvm_mmu.h> #include <asm/pvclock-abi.h> #include <kvm/arm_hypercalls.h> void kvm_update_stolen_time(struct kvm_vcpu *vcpu) { struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; u64 last_steal = vcpu->arch.steal.last_steal; u64 offset = offsetof(struct pvclock_vcpu_stolen_time, stolen_time); u64 steal = 0; int idx; if (base == INVALID_GPA) return; idx = srcu_read_lock(&kvm->srcu); if (!kvm_get_guest(kvm, base + offset, steal)) { steal = le64_to_cpu(steal); vcpu->arch.steal.last_steal = READ_ONCE(current->sched_info.run_delay); steal += vcpu->arch.steal.last_steal - last_steal; kvm_put_guest(kvm, base + offset, cpu_to_le64(steal)); } srcu_read_unlock(&kvm->srcu, idx); } long kvm_hypercall_pv_features(struct kvm_vcpu *vcpu) { u32 feature = smccc_get_arg1(vcpu); long val = SMCCC_RET_NOT_SUPPORTED; switch (feature) { case ARM_SMCCC_HV_PV_TIME_FEATURES: case ARM_SMCCC_HV_PV_TIME_ST: if (vcpu->arch.steal.base != INVALID_GPA) val = SMCCC_RET_SUCCESS; break; } return val; } gpa_t kvm_init_stolen_time(struct kvm_vcpu *vcpu) { struct pvclock_vcpu_stolen_time init_values = {}; struct kvm *kvm = vcpu->kvm; u64 base = vcpu->arch.steal.base; if (base == INVALID_GPA) return base; /* * Start counting stolen time from the time the guest requests * the feature enabled. */ vcpu->arch.steal.last_steal = current->sched_info.run_delay; kvm_write_guest_lock(kvm, base, &init_values, sizeof(init_values)); return base; } bool kvm_arm_pvtime_supported(void) { return !!sched_info_on(); } int kvm_arm_pvtime_set_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *user = (u64 __user *)attr->addr; struct kvm *kvm = vcpu->kvm; u64 ipa; int ret = 0; int idx; if (!kvm_arm_pvtime_supported() || attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; if (get_user(ipa, user)) return -EFAULT; if (!IS_ALIGNED(ipa, 64)) return -EINVAL; if (vcpu->arch.steal.base != INVALID_GPA) return -EEXIST; /* Check the address is in a valid memslot */ idx = srcu_read_lock(&kvm->srcu); if (kvm_is_error_hva(gfn_to_hva(kvm, ipa >> PAGE_SHIFT))) ret = -EINVAL; srcu_read_unlock(&kvm->srcu, idx); if (!ret) vcpu->arch.steal.base = ipa; return ret; } int kvm_arm_pvtime_get_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { u64 __user *user = (u64 __user *)attr->addr; u64 ipa; if (!kvm_arm_pvtime_supported() || attr->attr != KVM_ARM_VCPU_PVTIME_IPA) return -ENXIO; ipa = vcpu->arch.steal.base; if (put_user(ipa, user)) return -EFAULT; return 0; } int kvm_arm_pvtime_has_attr(struct kvm_vcpu *vcpu, struct kvm_device_attr *attr) { switch (attr->attr) { case KVM_ARM_VCPU_PVTIME_IPA: if (kvm_arm_pvtime_supported()) return 0; } return -ENXIO; } |
| 152 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 | /* SPDX-License-Identifier: GPL-2.0 */ /* * Statically sized hash table implementation * (C) 2012 Sasha Levin <levinsasha928@gmail.com> */ #ifndef _LINUX_HASHTABLE_H #define _LINUX_HASHTABLE_H #include <linux/list.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/hash.h> #include <linux/rculist.h> #define DEFINE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DEFINE_READ_MOSTLY_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] __read_mostly = \ { [0 ... ((1 << (bits)) - 1)] = HLIST_HEAD_INIT } #define DECLARE_HASHTABLE(name, bits) \ struct hlist_head name[1 << (bits)] #define HASH_SIZE(name) (ARRAY_SIZE(name)) #define HASH_BITS(name) ilog2(HASH_SIZE(name)) /* Use hash_32 when possible to allow for fast 32bit hashing in 64bit kernels. */ #define hash_min(val, bits) \ (sizeof(val) <= 4 ? hash_32(val, bits) : hash_long(val, bits)) static inline void __hash_init(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) INIT_HLIST_HEAD(&ht[i]); } /** * hash_init - initialize a hash table * @hashtable: hashtable to be initialized * * Calculates the size of the hashtable from the given parameter, otherwise * same as hash_init_size. * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_init(hashtable) __hash_init(hashtable, HASH_SIZE(hashtable)) /** * hash_add - add an object to a hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add(hashtable, node, key) \ hlist_add_head(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_add_rcu - add an object to a rcu enabled hashtable * @hashtable: hashtable to add to * @node: the &struct hlist_node of the object to be added * @key: the key of the object to be added */ #define hash_add_rcu(hashtable, node, key) \ hlist_add_head_rcu(node, &hashtable[hash_min(key, HASH_BITS(hashtable))]) /** * hash_hashed - check whether an object is in any hashtable * @node: the &struct hlist_node of the object to be checked */ static inline bool hash_hashed(struct hlist_node *node) { return !hlist_unhashed(node); } static inline bool __hash_empty(struct hlist_head *ht, unsigned int sz) { unsigned int i; for (i = 0; i < sz; i++) if (!hlist_empty(&ht[i])) return false; return true; } /** * hash_empty - check whether a hashtable is empty * @hashtable: hashtable to check * * This has to be a macro since HASH_BITS() will not work on pointers since * it calculates the size during preprocessing. */ #define hash_empty(hashtable) __hash_empty(hashtable, HASH_SIZE(hashtable)) /** * hash_del - remove an object from a hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del(struct hlist_node *node) { hlist_del_init(node); } /** * hash_del_rcu - remove an object from a rcu enabled hashtable * @node: &struct hlist_node of the object to remove */ static inline void hash_del_rcu(struct hlist_node *node) { hlist_del_init_rcu(node); } /** * hash_for_each - iterate over a hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry(obj, &name[bkt], member) /** * hash_for_each_rcu - iterate over a rcu enabled hashtable * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_rcu(name, bkt, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_rcu(obj, &name[bkt], member) /** * hash_for_each_safe - iterate over a hashtable safe against removal of * hash entry * @name: hashtable to iterate * @bkt: integer to use as bucket loop cursor * @tmp: a &struct hlist_node used for temporary storage * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct */ #define hash_for_each_safe(name, bkt, tmp, obj, member) \ for ((bkt) = 0, obj = NULL; obj == NULL && (bkt) < HASH_SIZE(name);\ (bkt)++)\ hlist_for_each_entry_safe(obj, tmp, &name[bkt], member) /** * hash_for_each_possible - iterate over all possible objects hashing to the * same bucket * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible(name, obj, member, key) \ hlist_for_each_entry(obj, &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_rcu - iterate over all possible objects hashing to the * same bucket in an rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_rcu(name, obj, member, key, cond...) \ hlist_for_each_entry_rcu(obj, &name[hash_min(key, HASH_BITS(name))],\ member, ## cond) /** * hash_for_each_possible_rcu_notrace - iterate over all possible objects hashing * to the same bucket in an rcu enabled hashtable in a rcu enabled hashtable * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over * * This is the same as hash_for_each_possible_rcu() except that it does * not do any RCU debugging or tracing. */ #define hash_for_each_possible_rcu_notrace(name, obj, member, key) \ hlist_for_each_entry_rcu_notrace(obj, \ &name[hash_min(key, HASH_BITS(name))], member) /** * hash_for_each_possible_safe - iterate over all possible objects hashing to the * same bucket safe against removals * @name: hashtable to iterate * @obj: the type * to use as a loop cursor for each entry * @tmp: a &struct hlist_node used for temporary storage * @member: the name of the hlist_node within the struct * @key: the key of the objects to iterate over */ #define hash_for_each_possible_safe(name, obj, tmp, member, key) \ hlist_for_each_entry_safe(obj, tmp,\ &name[hash_min(key, HASH_BITS(name))], member) #endif |
| 207 222 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 | /* SPDX-License-Identifier: GPL-2.0-only */ /* * Copyright (C) 2005-2010 IBM Corporation * * Authors: * Mimi Zohar <zohar@us.ibm.com> * Kylene Hall <kjhall@us.ibm.com> * * File: evm.h */ #ifndef __INTEGRITY_EVM_H #define __INTEGRITY_EVM_H #include <linux/xattr.h> #include <linux/security.h> #include "../integrity.h" #define EVM_INIT_HMAC 0x0001 #define EVM_INIT_X509 0x0002 #define EVM_ALLOW_METADATA_WRITES 0x0004 #define EVM_SETUP_COMPLETE 0x80000000 /* userland has signaled key load */ #define EVM_KEY_MASK (EVM_INIT_HMAC | EVM_INIT_X509) #define EVM_INIT_MASK (EVM_INIT_HMAC | EVM_INIT_X509 | EVM_SETUP_COMPLETE | \ EVM_ALLOW_METADATA_WRITES) struct xattr_list { struct list_head list; char *name; bool enabled; }; #define EVM_NEW_FILE 0x00000001 #define EVM_IMMUTABLE_DIGSIG 0x00000002 /* EVM integrity metadata associated with an inode */ struct evm_iint_cache { unsigned long flags; enum integrity_status evm_status:4; struct integrity_inode_attributes metadata_inode; }; extern struct lsm_blob_sizes evm_blob_sizes; static inline struct evm_iint_cache *evm_iint_inode(const struct inode *inode) { if (unlikely(!inode->i_security)) return NULL; return inode->i_security + evm_blob_sizes.lbs_inode; } extern int evm_initialized; #define EVM_ATTR_FSUUID 0x0001 extern int evm_hmac_attrs; /* List of EVM protected security xattrs */ extern struct list_head evm_config_xattrnames; struct evm_digest { struct ima_digest_data_hdr hdr; char digest[IMA_MAX_DIGEST_SIZE]; } __packed; int evm_protected_xattr(const char *req_xattr_name); int evm_init_key(void); int evm_update_evmxattr(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len); int evm_calc_hmac(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len, struct evm_digest *data, struct evm_iint_cache *iint); int evm_calc_hash(struct dentry *dentry, const char *req_xattr_name, const char *req_xattr_value, size_t req_xattr_value_len, char type, struct evm_digest *data, struct evm_iint_cache *iint); int evm_init_hmac(struct inode *inode, const struct xattr *xattrs, char *hmac_val); int evm_init_secfs(void); #endif |
| 2 48 181 181 181 181 84 84 183 184 18 16 19 10 1 1 1 1 7 7 184 109 184 184 184 184 184 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* internal.h: mm/ internal definitions * * Copyright (C) 2004 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #ifndef __MM_INTERNAL_H #define __MM_INTERNAL_H #include <linux/fs.h> #include <linux/mm.h> #include <linux/pagemap.h> #include <linux/rmap.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/tracepoint-defs.h> struct folio_batch; /* * The set of flags that only affect watermark checking and reclaim * behaviour. This is used by the MM to obey the caller constraints * about IO, FS and watermark checking while ignoring placement * hints such as HIGHMEM usage. */ #define GFP_RECLAIM_MASK (__GFP_RECLAIM|__GFP_HIGH|__GFP_IO|__GFP_FS|\ __GFP_NOWARN|__GFP_RETRY_MAYFAIL|__GFP_NOFAIL|\ __GFP_NORETRY|__GFP_MEMALLOC|__GFP_NOMEMALLOC|\ __GFP_NOLOCKDEP) /* The GFP flags allowed during early boot */ #define GFP_BOOT_MASK (__GFP_BITS_MASK & ~(__GFP_RECLAIM|__GFP_IO|__GFP_FS)) /* Control allocation cpuset and node placement constraints */ #define GFP_CONSTRAINT_MASK (__GFP_HARDWALL|__GFP_THISNODE) /* Do not use these with a slab allocator */ #define GFP_SLAB_BUG_MASK (__GFP_DMA32|__GFP_HIGHMEM|~__GFP_BITS_MASK) /* * Different from WARN_ON_ONCE(), no warning will be issued * when we specify __GFP_NOWARN. */ #define WARN_ON_ONCE_GFP(cond, gfp) ({ \ static bool __section(".data.once") __warned; \ int __ret_warn_once = !!(cond); \ \ if (unlikely(!(gfp & __GFP_NOWARN) && __ret_warn_once && !__warned)) { \ __warned = true; \ WARN_ON(1); \ } \ unlikely(__ret_warn_once); \ }) void page_writeback_init(void); /* * If a 16GB hugetlb folio were mapped by PTEs of all of its 4kB pages, * its nr_pages_mapped would be 0x400000: choose the ENTIRELY_MAPPED bit * above that range, instead of 2*(PMD_SIZE/PAGE_SIZE). Hugetlb currently * leaves nr_pages_mapped at 0, but avoid surprise if it participates later. */ #define ENTIRELY_MAPPED 0x800000 #define FOLIO_PAGES_MAPPED (ENTIRELY_MAPPED - 1) /* * Flags passed to __show_mem() and show_free_areas() to suppress output in * various contexts. */ #define SHOW_MEM_FILTER_NODES (0x0001u) /* disallowed nodes */ /* * How many individual pages have an elevated _mapcount. Excludes * the folio's entire_mapcount. * * Don't use this function outside of debugging code. */ static inline int folio_nr_pages_mapped(const struct folio *folio) { return atomic_read(&folio->_nr_pages_mapped) & FOLIO_PAGES_MAPPED; } /* * Retrieve the first entry of a folio based on a provided entry within the * folio. We cannot rely on folio->swap as there is no guarantee that it has * been initialized. Used for calling arch_swap_restore() */ static inline swp_entry_t folio_swap(swp_entry_t entry, const struct folio *folio) { swp_entry_t swap = { .val = ALIGN_DOWN(entry.val, folio_nr_pages(folio)), }; return swap; } static inline void *folio_raw_mapping(const struct folio *folio) { unsigned long mapping = (unsigned long)folio->mapping; return (void *)(mapping & ~PAGE_MAPPING_FLAGS); } #ifdef CONFIG_MMU /* Flags for folio_pte_batch(). */ typedef int __bitwise fpb_t; /* Compare PTEs after pte_mkclean(), ignoring the dirty bit. */ #define FPB_IGNORE_DIRTY ((__force fpb_t)BIT(0)) /* Compare PTEs after pte_clear_soft_dirty(), ignoring the soft-dirty bit. */ #define FPB_IGNORE_SOFT_DIRTY ((__force fpb_t)BIT(1)) static inline pte_t __pte_batch_clear_ignored(pte_t pte, fpb_t flags) { if (flags & FPB_IGNORE_DIRTY) pte = pte_mkclean(pte); if (likely(flags & FPB_IGNORE_SOFT_DIRTY)) pte = pte_clear_soft_dirty(pte); return pte_wrprotect(pte_mkold(pte)); } /** * folio_pte_batch - detect a PTE batch for a large folio * @folio: The large folio to detect a PTE batch for. * @addr: The user virtual address the first page is mapped at. * @start_ptep: Page table pointer for the first entry. * @pte: Page table entry for the first page. * @max_nr: The maximum number of table entries to consider. * @flags: Flags to modify the PTE batch semantics. * @any_writable: Optional pointer to indicate whether any entry except the * first one is writable. * @any_young: Optional pointer to indicate whether any entry except the * first one is young. * @any_dirty: Optional pointer to indicate whether any entry except the * first one is dirty. * * Detect a PTE batch: consecutive (present) PTEs that map consecutive * pages of the same large folio. * * All PTEs inside a PTE batch have the same PTE bits set, excluding the PFN, * the accessed bit, writable bit, dirty bit (with FPB_IGNORE_DIRTY) and * soft-dirty bit (with FPB_IGNORE_SOFT_DIRTY). * * start_ptep must map any page of the folio. max_nr must be at least one and * must be limited by the caller so scanning cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int folio_pte_batch(struct folio *folio, unsigned long addr, pte_t *start_ptep, pte_t pte, int max_nr, fpb_t flags, bool *any_writable, bool *any_young, bool *any_dirty) { unsigned long folio_end_pfn = folio_pfn(folio) + folio_nr_pages(folio); const pte_t *end_ptep = start_ptep + max_nr; pte_t expected_pte, *ptep; bool writable, young, dirty; int nr; if (any_writable) *any_writable = false; if (any_young) *any_young = false; if (any_dirty) *any_dirty = false; VM_WARN_ON_FOLIO(!pte_present(pte), folio); VM_WARN_ON_FOLIO(!folio_test_large(folio) || max_nr < 1, folio); VM_WARN_ON_FOLIO(page_folio(pfn_to_page(pte_pfn(pte))) != folio, folio); nr = pte_batch_hint(start_ptep, pte); expected_pte = __pte_batch_clear_ignored(pte_advance_pfn(pte, nr), flags); ptep = start_ptep + nr; while (ptep < end_ptep) { pte = ptep_get(ptep); if (any_writable) writable = !!pte_write(pte); if (any_young) young = !!pte_young(pte); if (any_dirty) dirty = !!pte_dirty(pte); pte = __pte_batch_clear_ignored(pte, flags); if (!pte_same(pte, expected_pte)) break; /* * Stop immediately once we reached the end of the folio. In * corner cases the next PFN might fall into a different * folio. */ if (pte_pfn(pte) >= folio_end_pfn) break; if (any_writable) *any_writable |= writable; if (any_young) *any_young |= young; if (any_dirty) *any_dirty |= dirty; nr = pte_batch_hint(ptep, pte); expected_pte = pte_advance_pfn(expected_pte, nr); ptep += nr; } return min(ptep - start_ptep, max_nr); } /** * pte_next_swp_offset - Increment the swap entry offset field of a swap pte. * @pte: The initial pte state; is_swap_pte(pte) must be true and * non_swap_entry() must be false. * * Increments the swap offset, while maintaining all other fields, including * swap type, and any swp pte bits. The resulting pte is returned. */ static inline pte_t pte_next_swp_offset(pte_t pte) { swp_entry_t entry = pte_to_swp_entry(pte); pte_t new = __swp_entry_to_pte(__swp_entry(swp_type(entry), (swp_offset(entry) + 1))); if (pte_swp_soft_dirty(pte)) new = pte_swp_mksoft_dirty(new); if (pte_swp_exclusive(pte)) new = pte_swp_mkexclusive(new); if (pte_swp_uffd_wp(pte)) new = pte_swp_mkuffd_wp(new); return new; } /** * swap_pte_batch - detect a PTE batch for a set of contiguous swap entries * @start_ptep: Page table pointer for the first entry. * @max_nr: The maximum number of table entries to consider. * @pte: Page table entry for the first entry. * * Detect a batch of contiguous swap entries: consecutive (non-present) PTEs * containing swap entries all with consecutive offsets and targeting the same * swap type, all with matching swp pte bits. * * max_nr must be at least one and must be limited by the caller so scanning * cannot exceed a single page table. * * Return: the number of table entries in the batch. */ static inline int swap_pte_batch(pte_t *start_ptep, int max_nr, pte_t pte) { pte_t expected_pte = pte_next_swp_offset(pte); const pte_t *end_ptep = start_ptep + max_nr; pte_t *ptep = start_ptep + 1; VM_WARN_ON(max_nr < 1); VM_WARN_ON(!is_swap_pte(pte)); VM_WARN_ON(non_swap_entry(pte_to_swp_entry(pte))); while (ptep < end_ptep) { pte = ptep_get(ptep); if (!pte_same(pte, expected_pte)) break; expected_pte = pte_next_swp_offset(expected_pte); ptep++; } return ptep - start_ptep; } #endif /* CONFIG_MMU */ void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) { pg_data_t *pgdat = folio_pgdat(folio); int nr_throttled = atomic_read(&pgdat->nr_writeback_throttled); if (nr_throttled) __acct_reclaim_writeback(pgdat, folio, nr_throttled); } static inline void wake_throttle_isolated(pg_data_t *pgdat) { wait_queue_head_t *wqh; wqh = &pgdat->reclaim_wait[VMSCAN_THROTTLE_ISOLATED]; if (waitqueue_active(wqh)) wake_up(wqh); } vm_fault_t vmf_anon_prepare(struct vm_fault *vmf); vm_fault_t do_swap_page(struct vm_fault *vmf); void folio_rotate_reclaimable(struct folio *folio); bool __folio_end_writeback(struct folio *folio); void deactivate_file_folio(struct folio *folio); void folio_activate(struct folio *folio); void free_pgtables(struct mmu_gather *tlb, struct ma_state *mas, struct vm_area_struct *start_vma, unsigned long floor, unsigned long ceiling, bool mm_wr_locked); void pmd_install(struct mm_struct *mm, pmd_t *pmd, pgtable_t *pte); struct zap_details; void unmap_page_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct zap_details *details); void page_cache_ra_order(struct readahead_control *, struct file_ra_state *, unsigned int order); void force_page_cache_ra(struct readahead_control *, unsigned long nr); static inline void force_page_cache_readahead(struct address_space *mapping, struct file *file, pgoff_t index, unsigned long nr_to_read) { DEFINE_READAHEAD(ractl, file, &file->f_ra, mapping, index); force_page_cache_ra(&ractl, nr_to_read); } unsigned find_lock_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); unsigned find_get_entries(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch, pgoff_t *indices); void filemap_free_folio(struct address_space *mapping, struct folio *folio); int truncate_inode_folio(struct address_space *mapping, struct folio *folio); bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end); long mapping_evict_folio(struct address_space *mapping, struct folio *folio); unsigned long mapping_try_invalidate(struct address_space *mapping, pgoff_t start, pgoff_t end, unsigned long *nr_failed); /** * folio_evictable - Test whether a folio is evictable. * @folio: The folio to test. * * Test whether @folio is evictable -- i.e., should be placed on * active/inactive lists vs unevictable list. * * Reasons folio might not be evictable: * 1. folio's mapping marked unevictable * 2. One of the pages in the folio is part of an mlocked VMA */ static inline bool folio_evictable(struct folio *folio) { bool ret; /* Prevent address_space of inode and swap cache from being freed */ rcu_read_lock(); ret = !mapping_unevictable(folio_mapping(folio)) && !folio_test_mlocked(folio); rcu_read_unlock(); return ret; } /* * Turn a non-refcounted page (->_refcount == 0) into refcounted with * a count of one. */ static inline void set_page_refcounted(struct page *page) { VM_BUG_ON_PAGE(PageTail(page), page); VM_BUG_ON_PAGE(page_ref_count(page), page); set_page_count(page, 1); } /* * Return true if a folio needs ->release_folio() calling upon it. */ static inline bool folio_needs_release(struct folio *folio) { struct address_space *mapping = folio_mapping(folio); return folio_has_private(folio) || (mapping && mapping_release_always(mapping)); } extern unsigned long highest_memmap_pfn; /* * Maximum number of reclaim retries without progress before the OOM * killer is consider the only way forward. */ #define MAX_RECLAIM_RETRIES 16 /* * in mm/vmscan.c: */ bool isolate_lru_page(struct page *page); bool folio_isolate_lru(struct folio *folio); void putback_lru_page(struct page *page); void folio_putback_lru(struct folio *folio); extern void reclaim_throttle(pg_data_t *pgdat, enum vmscan_throttle_state reason); /* * in mm/rmap.c: */ pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ #define K(x) ((x) << (PAGE_SHIFT-10)) extern char * const zone_names[MAX_NR_ZONES]; /* perform sanity checks on struct pages being allocated or freed */ DECLARE_STATIC_KEY_MAYBE(CONFIG_DEBUG_VM, check_pages_enabled); extern int min_free_kbytes; void setup_per_zone_wmarks(void); void calculate_min_free_kbytes(void); int __meminit init_per_zone_wmark_min(void); void page_alloc_sysctl_init(void); /* * Structure for holding the mostly immutable allocation parameters passed * between functions involved in allocations, including the alloc_pages* * family of functions. * * nodemask, migratetype and highest_zoneidx are initialized only once in * __alloc_pages() and then never change. * * zonelist, preferred_zone and highest_zoneidx are set first in * __alloc_pages() for the fast path, and might be later changed * in __alloc_pages_slowpath(). All other functions pass the whole structure * by a const pointer. */ struct alloc_context { struct zonelist *zonelist; nodemask_t *nodemask; struct zoneref *preferred_zoneref; int migratetype; /* * highest_zoneidx represents highest usable zone index of * the allocation request. Due to the nature of the zone, * memory on lower zone than the highest_zoneidx will be * protected by lowmem_reserve[highest_zoneidx]. * * highest_zoneidx is also used by reclaim/compaction to limit * the target zone since higher zone than this index cannot be * usable for this allocation request. */ enum zone_type highest_zoneidx; bool spread_dirty_pages; }; /* * This function returns the order of a free page in the buddy system. In * general, page_zone(page)->lock must be held by the caller to prevent the * page from being allocated in parallel and returning garbage as the order. * If a caller does not hold page_zone(page)->lock, it must guarantee that the * page cannot be allocated or merged in parallel. Alternatively, it must * handle invalid values gracefully, and use buddy_order_unsafe() below. */ static inline unsigned int buddy_order(struct page *page) { /* PageBuddy() must be checked by the caller */ return page_private(page); } /* * Like buddy_order(), but for callers who cannot afford to hold the zone lock. * PageBuddy() should be checked first by the caller to minimize race window, * and invalid values must be handled gracefully. * * READ_ONCE is used so that if the caller assigns the result into a local * variable and e.g. tests it for valid range before using, the compiler cannot * decide to remove the variable and inline the page_private(page) multiple * times, potentially observing different values in the tests and the actual * use of the result. */ #define buddy_order_unsafe(page) READ_ONCE(page_private(page)) /* * This function checks whether a page is free && is the buddy * we can coalesce a page and its buddy if * (a) the buddy is not in a hole (check before calling!) && * (b) the buddy is in the buddy system && * (c) a page and its buddy have the same order && * (d) a page and its buddy are in the same zone. * * For recording whether a page is in the buddy system, we set PageBuddy. * Setting, clearing, and testing PageBuddy is serialized by zone->lock. * * For recording page's order, we use page_private(page). */ static inline bool page_is_buddy(struct page *page, struct page *buddy, unsigned int order) { if (!page_is_guard(buddy) && !PageBuddy(buddy)) return false; if (buddy_order(buddy) != order) return false; /* * zone check is done late to avoid uselessly calculating * zone/node ids for pages that could never merge. */ if (page_zone_id(page) != page_zone_id(buddy)) return false; VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); return true; } /* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * * 1) Any buddy B1 will have an order O twin B2 which satisfies * the following equation: * B2 = B1 ^ (1 << O) * For example, if the starting buddy (buddy2) is #8 its order * 1 buddy is #10: * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 * * 2) Any buddy B will have an order O+1 parent P which * satisfies the following equation: * P = B & ~(1 << O) * * Assumption: *_mem_map is contiguous at least up to MAX_PAGE_ORDER */ static inline unsigned long __find_buddy_pfn(unsigned long page_pfn, unsigned int order) { return page_pfn ^ (1 << order); } /* * Find the buddy of @page and validate it. * @page: The input page * @pfn: The pfn of the page, it saves a call to page_to_pfn() when the * function is used in the performance-critical __free_one_page(). * @order: The order of the page * @buddy_pfn: The output pointer to the buddy pfn, it also saves a call to * page_to_pfn(). * * The found buddy can be a non PageBuddy, out of @page's zone, or its order is * not the same as @page. The validation is necessary before use it. * * Return: the found buddy page or NULL if not found. */ static inline struct page *find_buddy_page_pfn(struct page *page, unsigned long pfn, unsigned int order, unsigned long *buddy_pfn) { unsigned long __buddy_pfn = __find_buddy_pfn(pfn, order); struct page *buddy; buddy = page + (__buddy_pfn - pfn); if (buddy_pfn) *buddy_pfn = __buddy_pfn; if (page_is_buddy(page, buddy, order)) return buddy; return NULL; } extern struct page *__pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone); static inline struct page *pageblock_pfn_to_page(unsigned long start_pfn, unsigned long end_pfn, struct zone *zone) { if (zone->contiguous) return pfn_to_page(start_pfn); return __pageblock_pfn_to_page(start_pfn, end_pfn, zone); } void set_zone_contiguous(struct zone *zone); static inline void clear_zone_contiguous(struct zone *zone) { zone->contiguous = false; } extern int __isolate_free_page(struct page *page, unsigned int order); extern void __putback_isolated_page(struct page *page, unsigned int order, int mt); extern void memblock_free_pages(struct page *page, unsigned long pfn, unsigned int order); extern void __free_pages_core(struct page *page, unsigned int order); /* * This will have no effect, other than possibly generating a warning, if the * caller passes in a non-large folio. */ static inline void folio_set_order(struct folio *folio, unsigned int order) { if (WARN_ON_ONCE(!order || !folio_test_large(folio))) return; folio->_flags_1 = (folio->_flags_1 & ~0xffUL) | order; #ifdef CONFIG_64BIT folio->_folio_nr_pages = 1U << order; #endif } void folio_undo_large_rmappable(struct folio *folio); static inline struct folio *page_rmappable_folio(struct page *page) { struct folio *folio = (struct folio *)page; if (folio && folio_test_large(folio)) folio_set_large_rmappable(folio); return folio; } static inline void prep_compound_head(struct page *page, unsigned int order) { struct folio *folio = (struct folio *)page; folio_set_order(folio, order); atomic_set(&folio->_large_mapcount, -1); atomic_set(&folio->_entire_mapcount, -1); atomic_set(&folio->_nr_pages_mapped, 0); atomic_set(&folio->_pincount, 0); if (order > 1) INIT_LIST_HEAD(&folio->_deferred_list); } static inline void prep_compound_tail(struct page *head, int tail_idx) { struct page *p = head + tail_idx; p->mapping = TAIL_MAPPING; set_compound_head(p, head); set_page_private(p, 0); } extern void prep_compound_page(struct page *page, unsigned int order); extern void post_alloc_hook(struct page *page, unsigned int order, gfp_t gfp_flags); extern bool free_pages_prepare(struct page *page, unsigned int order); extern int user_min_free_kbytes; void free_unref_page(struct page *page, unsigned int order); void free_unref_folios(struct folio_batch *fbatch); extern void zone_pcp_reset(struct zone *zone); extern void zone_pcp_disable(struct zone *zone); extern void zone_pcp_enable(struct zone *zone); extern void zone_pcp_init(struct zone *zone); extern void *memmap_alloc(phys_addr_t size, phys_addr_t align, phys_addr_t min_addr, int nid, bool exact_nid); void memmap_init_range(unsigned long, int, unsigned long, unsigned long, unsigned long, enum meminit_context, struct vmem_altmap *, int); #if defined CONFIG_COMPACTION || defined CONFIG_CMA /* * in mm/compaction.c */ /* * compact_control is used to track pages being migrated and the free pages * they are being migrated to during memory compaction. The free_pfn starts * at the end of a zone and migrate_pfn begins at the start. Movable pages * are moved to the end of a zone during a compaction run and the run * completes when free_pfn <= migrate_pfn */ struct compact_control { struct list_head freepages[NR_PAGE_ORDERS]; /* List of free pages to migrate to */ struct list_head migratepages; /* List of pages being migrated */ unsigned int nr_freepages; /* Number of isolated free pages */ unsigned int nr_migratepages; /* Number of pages to migrate */ unsigned long free_pfn; /* isolate_freepages search base */ /* * Acts as an in/out parameter to page isolation for migration. * isolate_migratepages uses it as a search base. * isolate_migratepages_block will update the value to the next pfn * after the last isolated one. */ unsigned long migrate_pfn; unsigned long fast_start_pfn; /* a pfn to start linear scan from */ struct zone *zone; unsigned long total_migrate_scanned; unsigned long total_free_scanned; unsigned short fast_search_fail;/* failures to use free list searches */ short search_order; /* order to start a fast search at */ const gfp_t gfp_mask; /* gfp mask of a direct compactor */ int order; /* order a direct compactor needs */ int migratetype; /* migratetype of direct compactor */ const unsigned int alloc_flags; /* alloc flags of a direct compactor */ const int highest_zoneidx; /* zone index of a direct compactor */ enum migrate_mode mode; /* Async or sync migration mode */ bool ignore_skip_hint; /* Scan blocks even if marked skip */ bool no_set_skip_hint; /* Don't mark blocks for skipping */ bool ignore_block_suitable; /* Scan blocks considered unsuitable */ bool direct_compaction; /* False from kcompactd or /proc/... */ bool proactive_compaction; /* kcompactd proactive compaction */ bool whole_zone; /* Whole zone should/has been scanned */ bool contended; /* Signal lock contention */ bool finish_pageblock; /* Scan the remainder of a pageblock. Used * when there are potentially transient * isolation or migration failures to * ensure forward progress. */ bool alloc_contig; /* alloc_contig_range allocation */ }; /* * Used in direct compaction when a page should be taken from the freelists * immediately when one is created during the free path. */ struct capture_control { struct compact_control *cc; struct page *page; }; unsigned long isolate_freepages_range(struct compact_control *cc, unsigned long start_pfn, unsigned long end_pfn); int isolate_migratepages_range(struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn); int __alloc_contig_migrate_range(struct compact_control *cc, unsigned long start, unsigned long end, int migratetype); /* Free whole pageblock and set its migration type to MIGRATE_CMA. */ void init_cma_reserved_pageblock(struct page *page); #endif /* CONFIG_COMPACTION || CONFIG_CMA */ int find_suitable_fallback(struct free_area *area, unsigned int order, int migratetype, bool only_stealable, bool *can_steal); static inline bool free_area_empty(struct free_area *area, int migratetype) { return list_empty(&area->free_list[migratetype]); } /* * These three helpers classifies VMAs for virtual memory accounting. */ /* * Executable code area - executable, not writable, not stack */ static inline bool is_exec_mapping(vm_flags_t flags) { return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; } /* * Stack area (including shadow stacks) * * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: * do_mmap() forbids all other combinations. */ static inline bool is_stack_mapping(vm_flags_t flags) { return ((flags & VM_STACK) == VM_STACK) || (flags & VM_SHADOW_STACK); } /* * Data area - private, writable, not stack */ static inline bool is_data_mapping(vm_flags_t flags) { return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; } /* mm/util.c */ struct anon_vma *folio_anon_vma(struct folio *folio); #ifdef CONFIG_MMU void unmap_mapping_folio(struct folio *folio); extern long populate_vma_page_range(struct vm_area_struct *vma, unsigned long start, unsigned long end, int *locked); extern long faultin_page_range(struct mm_struct *mm, unsigned long start, unsigned long end, bool write, int *locked); extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags, unsigned long bytes); /* * NOTE: This function can't tell whether the folio is "fully mapped" in the * range. * "fully mapped" means all the pages of folio is associated with the page * table of range while this function just check whether the folio range is * within the range [start, end). Function caller needs to do page table * check if it cares about the page table association. * * Typical usage (like mlock or madvise) is: * Caller knows at least 1 page of folio is associated with page table of VMA * and the range [start, end) is intersect with the VMA range. Caller wants * to know whether the folio is fully associated with the range. It calls * this function to check whether the folio is in the range first. Then checks * the page table to know whether the folio is fully mapped to the range. */ static inline bool folio_within_range(struct folio *folio, struct vm_area_struct *vma, unsigned long start, unsigned long end) { pgoff_t pgoff, addr; unsigned long vma_pglen = vma_pages(vma); VM_WARN_ON_FOLIO(folio_test_ksm(folio), folio); if (start > end) return false; if (start < vma->vm_start) start = vma->vm_start; if (end > vma->vm_end) end = vma->vm_end; pgoff = folio_pgoff(folio); /* if folio start address is not in v |