| 12 12 11 1 1 23 1 13 11 21 3 24 17 24 24 1 17 5 25 5 24 24 25 2 2 7 3 2 21 10 2 5 2 2 25 25 14 11 21 20 1 1 14 2 4 18 4 18 18 7 11 6 17 1 6 5 7 11 12 12 13 11 1 11 11 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * USB Serial Converter driver * * Copyright (C) 2009 - 2013 Johan Hovold (jhovold@gmail.com) * Copyright (C) 1999 - 2012 Greg Kroah-Hartman (greg@kroah.com) * Copyright (C) 2000 Peter Berger (pberger@brimson.com) * Copyright (C) 2000 Al Borchers (borchers@steinerpoint.com) * * This driver was originally based on the ACM driver by Armin Fuerst (which was * based on a driver by Brad Keryan) * * See Documentation/usb/usb-serial.rst for more information on using this * driver */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/kernel.h> #include <linux/errno.h> #include <linux/init.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/tty_driver.h> #include <linux/module.h> #include <linux/seq_file.h> #include <linux/spinlock.h> #include <linux/mutex.h> #include <linux/list.h> #include <linux/serial.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include <linux/kfifo.h> #include <linux/idr.h> #define DRIVER_AUTHOR "Greg Kroah-Hartman <gregkh@linuxfoundation.org>" #define DRIVER_DESC "USB Serial Driver core" #define USB_SERIAL_TTY_MAJOR 188 #define USB_SERIAL_TTY_MINORS 512 /* should be enough for a while */ /* There is no MODULE_DEVICE_TABLE for usbserial.c. Instead the MODULE_DEVICE_TABLE declarations in each serial driver cause the "hotplug" program to pull in whatever module is necessary via modprobe, and modprobe will load usbserial because the serial drivers depend on it. */ static DEFINE_IDR(serial_minors); static DEFINE_MUTEX(table_lock); static LIST_HEAD(usb_serial_driver_list); /* * Look up the serial port structure. If it is found and it hasn't been * disconnected, return with the parent usb_serial structure's disc_mutex held * and its refcount incremented. Otherwise return NULL. */ struct usb_serial_port *usb_serial_port_get_by_minor(unsigned minor) { struct usb_serial *serial; struct usb_serial_port *port; mutex_lock(&table_lock); port = idr_find(&serial_minors, minor); if (!port) goto exit; serial = port->serial; mutex_lock(&serial->disc_mutex); if (serial->disconnected) { mutex_unlock(&serial->disc_mutex); port = NULL; } else { kref_get(&serial->kref); } exit: mutex_unlock(&table_lock); return port; } static int allocate_minors(struct usb_serial *serial, int num_ports) { struct usb_serial_port *port; unsigned int i, j; int minor; dev_dbg(&serial->interface->dev, "%s %d\n", __func__, num_ports); mutex_lock(&table_lock); for (i = 0; i < num_ports; ++i) { port = serial->port[i]; minor = idr_alloc(&serial_minors, port, 0, USB_SERIAL_TTY_MINORS, GFP_KERNEL); if (minor < 0) goto error; port->minor = minor; port->port_number = i; } serial->minors_reserved = 1; mutex_unlock(&table_lock); return 0; error: /* unwind the already allocated minors */ for (j = 0; j < i; ++j) idr_remove(&serial_minors, serial->port[j]->minor); mutex_unlock(&table_lock); return minor; } static void release_minors(struct usb_serial *serial) { int i; mutex_lock(&table_lock); for (i = 0; i < serial->num_ports; ++i) idr_remove(&serial_minors, serial->port[i]->minor); mutex_unlock(&table_lock); serial->minors_reserved = 0; } int usb_serial_claim_interface(struct usb_serial *serial, struct usb_interface *intf) { struct usb_driver *driver = serial->type->usb_driver; int ret; if (serial->sibling) return -EBUSY; ret = usb_driver_claim_interface(driver, intf, serial); if (ret) { dev_err(&serial->interface->dev, "failed to claim sibling interface: %d\n", ret); return ret; } serial->sibling = intf; return 0; } EXPORT_SYMBOL_GPL(usb_serial_claim_interface); static void release_sibling(struct usb_serial *serial, struct usb_interface *intf) { struct usb_driver *driver = serial->type->usb_driver; struct usb_interface *sibling; if (!serial->sibling) return; if (intf == serial->sibling) sibling = serial->interface; else sibling = serial->sibling; usb_set_intfdata(sibling, NULL); usb_driver_release_interface(driver, sibling); } static void destroy_serial(struct kref *kref) { struct usb_serial *serial; struct usb_serial_port *port; int i; serial = to_usb_serial(kref); /* return the minor range that this device had */ if (serial->minors_reserved) release_minors(serial); if (serial->attached && serial->type->release) serial->type->release(serial); /* Now that nothing is using the ports, they can be freed */ for (i = 0; i < serial->num_port_pointers; ++i) { port = serial->port[i]; if (port) { port->serial = NULL; put_device(&port->dev); } } usb_put_intf(serial->interface); usb_put_dev(serial->dev); kfree(serial); } void usb_serial_put(struct usb_serial *serial) { kref_put(&serial->kref, destroy_serial); } /***************************************************************************** * Driver tty interface functions *****************************************************************************/ /** * serial_install - install tty * @driver: the driver (USB in our case) * @tty: the tty being created * * Initialise the termios structure for this tty. We use the default * USB serial settings but permit them to be overridden by * serial->type->init_termios on first open. * * This is the first place a new tty gets used. Hence this is where we * acquire references to the usb_serial structure and the driver module, * where we store a pointer to the port. All these actions are reversed * in serial_cleanup(). */ static int serial_install(struct tty_driver *driver, struct tty_struct *tty) { int idx = tty->index; struct usb_serial *serial; struct usb_serial_port *port; bool init_termios; int retval = -ENODEV; port = usb_serial_port_get_by_minor(idx); if (!port) return retval; serial = port->serial; if (!try_module_get(serial->type->driver.owner)) goto err_put_serial; init_termios = (driver->termios[idx] == NULL); retval = tty_standard_install(driver, tty); if (retval) goto err_put_module; mutex_unlock(&serial->disc_mutex); /* allow the driver to update the initial settings */ if (init_termios && serial->type->init_termios) serial->type->init_termios(tty); tty->driver_data = port; return retval; err_put_module: module_put(serial->type->driver.owner); err_put_serial: usb_serial_put(serial); mutex_unlock(&serial->disc_mutex); return retval; } static int serial_port_activate(struct tty_port *tport, struct tty_struct *tty) { struct usb_serial_port *port = container_of(tport, struct usb_serial_port, port); struct usb_serial *serial = port->serial; int retval; mutex_lock(&serial->disc_mutex); if (serial->disconnected) { retval = -ENODEV; goto out_unlock; } retval = usb_autopm_get_interface(serial->interface); if (retval) goto out_unlock; retval = port->serial->type->open(tty, port); if (retval) usb_autopm_put_interface(serial->interface); out_unlock: mutex_unlock(&serial->disc_mutex); if (retval < 0) retval = usb_translate_errors(retval); return retval; } static int serial_open(struct tty_struct *tty, struct file *filp) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); return tty_port_open(&port->port, tty, filp); } /** * serial_port_shutdown - shut down hardware * @tport: tty port to shut down * * Shut down a USB serial port. Serialized against activate by the * tport mutex and kept to matching open/close pairs * of calls by the tty-port initialized flag. * * Not called if tty is console. */ static void serial_port_shutdown(struct tty_port *tport) { struct usb_serial_port *port = container_of(tport, struct usb_serial_port, port); struct usb_serial_driver *drv = port->serial->type; if (drv->close) drv->close(port); usb_autopm_put_interface(port->serial->interface); } static void serial_hangup(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); tty_port_hangup(&port->port); } static void serial_close(struct tty_struct *tty, struct file *filp) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); tty_port_close(&port->port, tty, filp); } /** * serial_cleanup - free resources post close/hangup * @tty: tty to clean up * * Do the resource freeing and refcount dropping for the port. * Avoid freeing the console. * * Called asynchronously after the last tty kref is dropped. */ static void serial_cleanup(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct usb_serial *serial; struct module *owner; dev_dbg(&port->dev, "%s\n", __func__); /* The console is magical. Do not hang up the console hardware * or there will be tears. */ if (port->port.console) return; tty->driver_data = NULL; serial = port->serial; owner = serial->type->driver.owner; usb_serial_put(serial); module_put(owner); } static ssize_t serial_write(struct tty_struct *tty, const u8 *buf, size_t count) { struct usb_serial_port *port = tty->driver_data; int retval = -ENODEV; if (port->serial->dev->state == USB_STATE_NOTATTACHED) goto exit; dev_dbg(&port->dev, "%s - %zu byte(s)\n", __func__, count); retval = port->serial->type->write(tty, port, buf, count); if (retval < 0) retval = usb_translate_errors(retval); exit: return retval; } static unsigned int serial_write_room(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); return port->serial->type->write_room(tty); } static unsigned int serial_chars_in_buffer(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct usb_serial *serial = port->serial; dev_dbg(&port->dev, "%s\n", __func__); if (serial->disconnected) return 0; return serial->type->chars_in_buffer(tty); } static void serial_wait_until_sent(struct tty_struct *tty, int timeout) { struct usb_serial_port *port = tty->driver_data; struct usb_serial *serial = port->serial; dev_dbg(&port->dev, "%s\n", __func__); if (!port->serial->type->wait_until_sent) return; mutex_lock(&serial->disc_mutex); if (!serial->disconnected) port->serial->type->wait_until_sent(tty, timeout); mutex_unlock(&serial->disc_mutex); } static void serial_throttle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->throttle) port->serial->type->throttle(tty); } static void serial_unthrottle(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->unthrottle) port->serial->type->unthrottle(tty); } static int serial_get_serial(struct tty_struct *tty, struct serial_struct *ss) { struct usb_serial_port *port = tty->driver_data; struct tty_port *tport = &port->port; unsigned int close_delay, closing_wait; mutex_lock(&tport->mutex); close_delay = jiffies_to_msecs(tport->close_delay) / 10; closing_wait = tport->closing_wait; if (closing_wait != ASYNC_CLOSING_WAIT_NONE) closing_wait = jiffies_to_msecs(closing_wait) / 10; ss->line = port->minor; ss->close_delay = close_delay; ss->closing_wait = closing_wait; if (port->serial->type->get_serial) port->serial->type->get_serial(tty, ss); mutex_unlock(&tport->mutex); return 0; } static int serial_set_serial(struct tty_struct *tty, struct serial_struct *ss) { struct usb_serial_port *port = tty->driver_data; struct tty_port *tport = &port->port; unsigned int close_delay, closing_wait; int ret = 0; close_delay = msecs_to_jiffies(ss->close_delay * 10); closing_wait = ss->closing_wait; if (closing_wait != ASYNC_CLOSING_WAIT_NONE) closing_wait = msecs_to_jiffies(closing_wait * 10); mutex_lock(&tport->mutex); if (!capable(CAP_SYS_ADMIN)) { if (close_delay != tport->close_delay || closing_wait != tport->closing_wait) { ret = -EPERM; goto out_unlock; } } if (port->serial->type->set_serial) { ret = port->serial->type->set_serial(tty, ss); if (ret) goto out_unlock; } tport->close_delay = close_delay; tport->closing_wait = closing_wait; out_unlock: mutex_unlock(&tport->mutex); return ret; } static int serial_ioctl(struct tty_struct *tty, unsigned int cmd, unsigned long arg) { struct usb_serial_port *port = tty->driver_data; int retval = -ENOIOCTLCMD; dev_dbg(&port->dev, "%s - cmd 0x%04x\n", __func__, cmd); switch (cmd) { case TIOCMIWAIT: if (port->serial->type->tiocmiwait) retval = port->serial->type->tiocmiwait(tty, arg); break; default: if (port->serial->type->ioctl) retval = port->serial->type->ioctl(tty, cmd, arg); } return retval; } static void serial_set_termios(struct tty_struct *tty, const struct ktermios *old) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->set_termios) port->serial->type->set_termios(tty, port, old); else tty_termios_copy_hw(&tty->termios, old); } static int serial_break(struct tty_struct *tty, int break_state) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->break_ctl) return port->serial->type->break_ctl(tty, break_state); return -ENOTTY; } static int serial_proc_show(struct seq_file *m, void *v) { struct usb_serial *serial; struct usb_serial_port *port; int i; char tmp[40]; seq_puts(m, "usbserinfo:1.0 driver:2.0\n"); for (i = 0; i < USB_SERIAL_TTY_MINORS; ++i) { port = usb_serial_port_get_by_minor(i); if (port == NULL) continue; serial = port->serial; seq_printf(m, "%d:", i); if (serial->type->driver.owner) seq_printf(m, " module:%s", module_name(serial->type->driver.owner)); seq_printf(m, " name:\"%s\"", serial->type->description); seq_printf(m, " vendor:%04x product:%04x", le16_to_cpu(serial->dev->descriptor.idVendor), le16_to_cpu(serial->dev->descriptor.idProduct)); seq_printf(m, " num_ports:%d", serial->num_ports); seq_printf(m, " port:%d", port->port_number); usb_make_path(serial->dev, tmp, sizeof(tmp)); seq_printf(m, " path:%s", tmp); seq_putc(m, '\n'); usb_serial_put(serial); mutex_unlock(&serial->disc_mutex); } return 0; } static int serial_tiocmget(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->tiocmget) return port->serial->type->tiocmget(tty); return -ENOTTY; } static int serial_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->tiocmset) return port->serial->type->tiocmset(tty, set, clear); return -ENOTTY; } static int serial_get_icount(struct tty_struct *tty, struct serial_icounter_struct *icount) { struct usb_serial_port *port = tty->driver_data; dev_dbg(&port->dev, "%s\n", __func__); if (port->serial->type->get_icount) return port->serial->type->get_icount(tty, icount); return -ENOTTY; } /* * We would be calling tty_wakeup here, but unfortunately some line * disciplines have an annoying habit of calling tty->write from * the write wakeup callback (e.g. n_hdlc.c). */ void usb_serial_port_softint(struct usb_serial_port *port) { schedule_work(&port->work); } EXPORT_SYMBOL_GPL(usb_serial_port_softint); static void usb_serial_port_work(struct work_struct *work) { struct usb_serial_port *port = container_of(work, struct usb_serial_port, work); tty_port_tty_wakeup(&port->port); } static void usb_serial_port_poison_urbs(struct usb_serial_port *port) { int i; for (i = 0; i < ARRAY_SIZE(port->read_urbs); ++i) usb_poison_urb(port->read_urbs[i]); for (i = 0; i < ARRAY_SIZE(port->write_urbs); ++i) usb_poison_urb(port->write_urbs[i]); usb_poison_urb(port->interrupt_in_urb); usb_poison_urb(port->interrupt_out_urb); } static void usb_serial_port_unpoison_urbs(struct usb_serial_port *port) { int i; for (i = 0; i < ARRAY_SIZE(port->read_urbs); ++i) usb_unpoison_urb(port->read_urbs[i]); for (i = 0; i < ARRAY_SIZE(port->write_urbs); ++i) usb_unpoison_urb(port->write_urbs[i]); usb_unpoison_urb(port->interrupt_in_urb); usb_unpoison_urb(port->interrupt_out_urb); } static void usb_serial_port_release(struct device *dev) { struct usb_serial_port *port = to_usb_serial_port(dev); int i; dev_dbg(dev, "%s\n", __func__); usb_free_urb(port->interrupt_in_urb); usb_free_urb(port->interrupt_out_urb); for (i = 0; i < ARRAY_SIZE(port->read_urbs); ++i) { usb_free_urb(port->read_urbs[i]); kfree(port->bulk_in_buffers[i]); } for (i = 0; i < ARRAY_SIZE(port->write_urbs); ++i) { usb_free_urb(port->write_urbs[i]); kfree(port->bulk_out_buffers[i]); } kfifo_free(&port->write_fifo); kfree(port->interrupt_in_buffer); kfree(port->interrupt_out_buffer); tty_port_destroy(&port->port); kfree(port); } static struct usb_serial *create_serial(struct usb_device *dev, struct usb_interface *interface, struct usb_serial_driver *driver) { struct usb_serial *serial; serial = kzalloc_obj(*serial); if (!serial) return NULL; serial->dev = usb_get_dev(dev); serial->type = driver; serial->interface = usb_get_intf(interface); kref_init(&serial->kref); mutex_init(&serial->disc_mutex); serial->minors_reserved = 0; return serial; } static const struct usb_device_id *match_dynamic_id(struct usb_interface *intf, struct usb_serial_driver *drv) { struct usb_dynid *dynid; guard(mutex)(&usb_dynids_lock); list_for_each_entry(dynid, &drv->dynids.list, node) { if (usb_match_one_id(intf, &dynid->id)) { return &dynid->id; } } return NULL; } static const struct usb_device_id *get_iface_id(struct usb_serial_driver *drv, struct usb_interface *intf) { const struct usb_device_id *id; id = usb_match_id(intf, drv->id_table); if (id) { dev_dbg(&intf->dev, "static descriptor matches\n"); goto exit; } id = match_dynamic_id(intf, drv); if (id) dev_dbg(&intf->dev, "dynamic descriptor matches\n"); exit: return id; } /* Caller must hold table_lock */ static struct usb_serial_driver *search_serial_device( struct usb_interface *iface) { const struct usb_device_id *id = NULL; struct usb_serial_driver *drv; struct usb_driver *driver = to_usb_driver(iface->dev.driver); /* Check if the usb id matches a known device */ list_for_each_entry(drv, &usb_serial_driver_list, driver_list) { if (drv->usb_driver == driver) id = get_iface_id(drv, iface); if (id) return drv; } return NULL; } static bool serial_port_carrier_raised(struct tty_port *port) { struct usb_serial_port *p = container_of(port, struct usb_serial_port, port); struct usb_serial_driver *drv = p->serial->type; if (drv->carrier_raised) return drv->carrier_raised(p); /* No carrier control - don't block */ return true; } static void serial_port_dtr_rts(struct tty_port *port, bool on) { struct usb_serial_port *p = container_of(port, struct usb_serial_port, port); struct usb_serial_driver *drv = p->serial->type; if (drv->dtr_rts) drv->dtr_rts(p, on); } static ssize_t port_number_show(struct device *dev, struct device_attribute *attr, char *buf) { struct usb_serial_port *port = to_usb_serial_port(dev); return sprintf(buf, "%u\n", port->port_number); } static DEVICE_ATTR_RO(port_number); static struct attribute *usb_serial_port_attrs[] = { &dev_attr_port_number.attr, NULL }; ATTRIBUTE_GROUPS(usb_serial_port); static const struct tty_port_operations serial_port_ops = { .carrier_raised = serial_port_carrier_raised, .dtr_rts = serial_port_dtr_rts, .activate = serial_port_activate, .shutdown = serial_port_shutdown, }; static void store_endpoint(struct usb_serial *serial, struct usb_serial_endpoints *epds, struct usb_endpoint_descriptor *epd) { struct device *dev = &serial->interface->dev; u8 addr = epd->bEndpointAddress; if (usb_endpoint_is_bulk_in(epd)) { if (epds->num_bulk_in == ARRAY_SIZE(epds->bulk_in)) return; dev_dbg(dev, "found bulk in endpoint %02x\n", addr); epds->bulk_in[epds->num_bulk_in++] = epd; } else if (usb_endpoint_is_bulk_out(epd)) { if (epds->num_bulk_out == ARRAY_SIZE(epds->bulk_out)) return; dev_dbg(dev, "found bulk out endpoint %02x\n", addr); epds->bulk_out[epds->num_bulk_out++] = epd; } else if (usb_endpoint_is_int_in(epd)) { if (epds->num_interrupt_in == ARRAY_SIZE(epds->interrupt_in)) return; dev_dbg(dev, "found interrupt in endpoint %02x\n", addr); epds->interrupt_in[epds->num_interrupt_in++] = epd; } else if (usb_endpoint_is_int_out(epd)) { if (epds->num_interrupt_out == ARRAY_SIZE(epds->interrupt_out)) return; dev_dbg(dev, "found interrupt out endpoint %02x\n", addr); epds->interrupt_out[epds->num_interrupt_out++] = epd; } } static void find_endpoints(struct usb_serial *serial, struct usb_serial_endpoints *epds, struct usb_interface *intf) { struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *epd; unsigned int i; iface_desc = intf->cur_altsetting; for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { epd = &iface_desc->endpoint[i].desc; store_endpoint(serial, epds, epd); } } static int setup_port_bulk_in(struct usb_serial_port *port, struct usb_endpoint_descriptor *epd) { struct usb_serial_driver *type = port->serial->type; struct usb_device *udev = port->serial->dev; int buffer_size; int i; buffer_size = max_t(int, type->bulk_in_size, usb_endpoint_maxp(epd)); port->bulk_in_size = buffer_size; port->bulk_in_endpointAddress = epd->bEndpointAddress; for (i = 0; i < ARRAY_SIZE(port->read_urbs); ++i) { set_bit(i, &port->read_urbs_free); port->read_urbs[i] = usb_alloc_urb(0, GFP_KERNEL); if (!port->read_urbs[i]) return -ENOMEM; port->bulk_in_buffers[i] = kmalloc(buffer_size, GFP_KERNEL); if (!port->bulk_in_buffers[i]) return -ENOMEM; usb_fill_bulk_urb(port->read_urbs[i], udev, usb_rcvbulkpipe(udev, epd->bEndpointAddress), port->bulk_in_buffers[i], buffer_size, type->read_bulk_callback, port); } port->read_urb = port->read_urbs[0]; port->bulk_in_buffer = port->bulk_in_buffers[0]; return 0; } static int setup_port_bulk_out(struct usb_serial_port *port, struct usb_endpoint_descriptor *epd) { struct usb_serial_driver *type = port->serial->type; struct usb_device *udev = port->serial->dev; int buffer_size; int i; if (kfifo_alloc(&port->write_fifo, PAGE_SIZE, GFP_KERNEL)) return -ENOMEM; if (type->bulk_out_size) buffer_size = type->bulk_out_size; else buffer_size = usb_endpoint_maxp(epd); port->bulk_out_size = buffer_size; port->bulk_out_endpointAddress = epd->bEndpointAddress; for (i = 0; i < ARRAY_SIZE(port->write_urbs); ++i) { set_bit(i, &port->write_urbs_free); port->write_urbs[i] = usb_alloc_urb(0, GFP_KERNEL); if (!port->write_urbs[i]) return -ENOMEM; port->bulk_out_buffers[i] = kmalloc(buffer_size, GFP_KERNEL); if (!port->bulk_out_buffers[i]) return -ENOMEM; usb_fill_bulk_urb(port->write_urbs[i], udev, usb_sndbulkpipe(udev, epd->bEndpointAddress), port->bulk_out_buffers[i], buffer_size, type->write_bulk_callback, port); } port->write_urb = port->write_urbs[0]; port->bulk_out_buffer = port->bulk_out_buffers[0]; return 0; } static int setup_port_interrupt_in(struct usb_serial_port *port, struct usb_endpoint_descriptor *epd) { struct usb_serial_driver *type = port->serial->type; struct usb_device *udev = port->serial->dev; int buffer_size; port->interrupt_in_urb = usb_alloc_urb(0, GFP_KERNEL); if (!port->interrupt_in_urb) return -ENOMEM; buffer_size = usb_endpoint_maxp(epd); port->interrupt_in_endpointAddress = epd->bEndpointAddress; port->interrupt_in_buffer = kmalloc(buffer_size, GFP_KERNEL); if (!port->interrupt_in_buffer) return -ENOMEM; usb_fill_int_urb(port->interrupt_in_urb, udev, usb_rcvintpipe(udev, epd->bEndpointAddress), port->interrupt_in_buffer, buffer_size, type->read_int_callback, port, epd->bInterval); return 0; } static int setup_port_interrupt_out(struct usb_serial_port *port, struct usb_endpoint_descriptor *epd) { struct usb_serial_driver *type = port->serial->type; struct usb_device *udev = port->serial->dev; int buffer_size; port->interrupt_out_urb = usb_alloc_urb(0, GFP_KERNEL); if (!port->interrupt_out_urb) return -ENOMEM; buffer_size = usb_endpoint_maxp(epd); port->interrupt_out_size = buffer_size; port->interrupt_out_endpointAddress = epd->bEndpointAddress; port->interrupt_out_buffer = kmalloc(buffer_size, GFP_KERNEL); if (!port->interrupt_out_buffer) return -ENOMEM; usb_fill_int_urb(port->interrupt_out_urb, udev, usb_sndintpipe(udev, epd->bEndpointAddress), port->interrupt_out_buffer, buffer_size, type->write_int_callback, port, epd->bInterval); return 0; } static int usb_serial_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct device *ddev = &interface->dev; struct usb_device *dev = interface_to_usbdev(interface); struct usb_serial *serial = NULL; struct usb_serial_port *port; struct usb_serial_endpoints *epds; struct usb_serial_driver *type = NULL; int retval; int i; int num_ports = 0; unsigned char max_endpoints; mutex_lock(&table_lock); type = search_serial_device(interface); if (!type) { mutex_unlock(&table_lock); dev_dbg(ddev, "none matched\n"); return -ENODEV; } if (!try_module_get(type->driver.owner)) { mutex_unlock(&table_lock); dev_err(ddev, "module get failed, exiting\n"); return -EIO; } mutex_unlock(&table_lock); serial = create_serial(dev, interface, type); if (!serial) { retval = -ENOMEM; goto err_put_module; } /* if this device type has a probe function, call it */ if (type->probe) { const struct usb_device_id *id; id = get_iface_id(type, interface); retval = type->probe(serial, id); if (retval) { dev_dbg(ddev, "sub driver rejected device\n"); goto err_release_sibling; } } /* descriptor matches, let's find the endpoints needed */ epds = kzalloc_obj(*epds); if (!epds) { retval = -ENOMEM; goto err_release_sibling; } find_endpoints(serial, epds, interface); if (serial->sibling) find_endpoints(serial, epds, serial->sibling); if (epds->num_bulk_in < type->num_bulk_in || epds->num_bulk_out < type->num_bulk_out || epds->num_interrupt_in < type->num_interrupt_in || epds->num_interrupt_out < type->num_interrupt_out) { dev_err(ddev, "required endpoints missing\n"); retval = -ENODEV; goto err_free_epds; } if (type->calc_num_ports) { retval = type->calc_num_ports(serial, epds); if (retval < 0) goto err_free_epds; num_ports = retval; } if (!num_ports) num_ports = type->num_ports; if (num_ports > MAX_NUM_PORTS) { dev_warn(ddev, "too many ports requested: %d\n", num_ports); num_ports = MAX_NUM_PORTS; } serial->num_ports = (unsigned char)num_ports; serial->num_bulk_in = epds->num_bulk_in; serial->num_bulk_out = epds->num_bulk_out; serial->num_interrupt_in = epds->num_interrupt_in; serial->num_interrupt_out = epds->num_interrupt_out; /* found all that we need */ dev_info(ddev, "%s converter detected\n", type->description); /* create our ports, we need as many as the max endpoints */ /* we don't use num_ports here because some devices have more endpoint pairs than ports */ max_endpoints = max(epds->num_bulk_in, epds->num_bulk_out); max_endpoints = max(max_endpoints, epds->num_interrupt_in); max_endpoints = max(max_endpoints, epds->num_interrupt_out); max_endpoints = max(max_endpoints, serial->num_ports); serial->num_port_pointers = max_endpoints; dev_dbg(ddev, "setting up %d port structure(s)\n", max_endpoints); for (i = 0; i < max_endpoints; ++i) { port = kzalloc_obj(struct usb_serial_port); if (!port) { retval = -ENOMEM; goto err_free_epds; } tty_port_init(&port->port); port->port.ops = &serial_port_ops; port->serial = serial; spin_lock_init(&port->lock); /* Keep this for private driver use for the moment but should probably go away */ INIT_WORK(&port->work, usb_serial_port_work); serial->port[i] = port; port->dev.parent = &interface->dev; port->dev.driver = NULL; port->dev.bus = &usb_serial_bus_type; port->dev.release = &usb_serial_port_release; port->dev.groups = usb_serial_port_groups; device_initialize(&port->dev); } /* set up the endpoint information */ for (i = 0; i < epds->num_bulk_in; ++i) { retval = setup_port_bulk_in(serial->port[i], epds->bulk_in[i]); if (retval) goto err_free_epds; } for (i = 0; i < epds->num_bulk_out; ++i) { retval = setup_port_bulk_out(serial->port[i], epds->bulk_out[i]); if (retval) goto err_free_epds; } if (serial->type->read_int_callback) { for (i = 0; i < epds->num_interrupt_in; ++i) { retval = setup_port_interrupt_in(serial->port[i], epds->interrupt_in[i]); if (retval) goto err_free_epds; } } else if (epds->num_interrupt_in) { dev_dbg(ddev, "The device claims to support interrupt in transfers, but read_int_callback is not defined\n"); } if (serial->type->write_int_callback) { for (i = 0; i < epds->num_interrupt_out; ++i) { retval = setup_port_interrupt_out(serial->port[i], epds->interrupt_out[i]); if (retval) goto err_free_epds; } } else if (epds->num_interrupt_out) { dev_dbg(ddev, "The device claims to support interrupt out transfers, but write_int_callback is not defined\n"); } usb_set_intfdata(interface, serial); /* if this device type has an attach function, call it */ if (type->attach) { retval = type->attach(serial); if (retval < 0) goto err_free_epds; serial->attached = 1; if (retval > 0) { /* quietly accept this device, but don't bind to a serial port as it's about to disappear */ serial->num_ports = 0; goto exit; } } else { serial->attached = 1; } retval = allocate_minors(serial, num_ports); if (retval) { dev_err(ddev, "No more free serial minor numbers\n"); goto err_free_epds; } /* register all of the individual ports with the driver core */ for (i = 0; i < num_ports; ++i) { port = serial->port[i]; dev_set_name(&port->dev, "ttyUSB%d", port->minor); dev_dbg(ddev, "registering %s\n", dev_name(&port->dev)); device_enable_async_suspend(&port->dev); retval = device_add(&port->dev); if (retval) dev_err(ddev, "Error registering port device, continuing\n"); } if (num_ports > 0) usb_serial_console_init(serial->port[0]->minor); exit: kfree(epds); module_put(type->driver.owner); return 0; err_free_epds: kfree(epds); err_release_sibling: release_sibling(serial, interface); usb_serial_put(serial); err_put_module: module_put(type->driver.owner); return retval; } static void usb_serial_disconnect(struct usb_interface *interface) { int i; struct usb_serial *serial = usb_get_intfdata(interface); struct device *dev = &interface->dev; struct usb_serial_port *port; /* sibling interface is cleaning up */ if (!serial) return; usb_serial_console_disconnect(serial); mutex_lock(&serial->disc_mutex); /* must set a flag, to signal subdrivers */ serial->disconnected = 1; mutex_unlock(&serial->disc_mutex); for (i = 0; i < serial->num_ports; ++i) { port = serial->port[i]; tty_port_tty_vhangup(&port->port); usb_serial_port_poison_urbs(port); wake_up_interruptible(&port->port.delta_msr_wait); cancel_work_sync(&port->work); if (device_is_registered(&port->dev)) device_del(&port->dev); } if (serial->type->disconnect) serial->type->disconnect(serial); release_sibling(serial, interface); /* let the last holder of this object cause it to be cleaned up */ usb_serial_put(serial); dev_info(dev, "device disconnected\n"); } int usb_serial_suspend(struct usb_interface *intf, pm_message_t message) { struct usb_serial *serial = usb_get_intfdata(intf); int i, r; /* suspend when called for first sibling interface */ if (serial->suspend_count++) return 0; /* * serial->type->suspend() MUST return 0 in system sleep context, * otherwise, the resume callback has to recover device from * previous suspend failure. */ if (serial->type->suspend) { r = serial->type->suspend(serial, message); if (r < 0) { serial->suspend_count--; return r; } } for (i = 0; i < serial->num_ports; ++i) usb_serial_port_poison_urbs(serial->port[i]); return 0; } EXPORT_SYMBOL(usb_serial_suspend); static void usb_serial_unpoison_port_urbs(struct usb_serial *serial) { int i; for (i = 0; i < serial->num_ports; ++i) usb_serial_port_unpoison_urbs(serial->port[i]); } int usb_serial_resume(struct usb_interface *intf) { struct usb_serial *serial = usb_get_intfdata(intf); int rv; /* resume when called for last sibling interface */ if (--serial->suspend_count) return 0; usb_serial_unpoison_port_urbs(serial); if (serial->type->resume) rv = serial->type->resume(serial); else rv = usb_serial_generic_resume(serial); return rv; } EXPORT_SYMBOL(usb_serial_resume); static int usb_serial_reset_resume(struct usb_interface *intf) { struct usb_serial *serial = usb_get_intfdata(intf); int rv; /* resume when called for last sibling interface */ if (--serial->suspend_count) return 0; usb_serial_unpoison_port_urbs(serial); if (serial->type->reset_resume) { rv = serial->type->reset_resume(serial); } else { rv = -EOPNOTSUPP; intf->needs_binding = 1; } return rv; } static const struct tty_operations serial_ops = { .open = serial_open, .close = serial_close, .write = serial_write, .hangup = serial_hangup, .write_room = serial_write_room, .ioctl = serial_ioctl, .set_termios = serial_set_termios, .throttle = serial_throttle, .unthrottle = serial_unthrottle, .break_ctl = serial_break, .chars_in_buffer = serial_chars_in_buffer, .wait_until_sent = serial_wait_until_sent, .tiocmget = serial_tiocmget, .tiocmset = serial_tiocmset, .get_icount = serial_get_icount, .set_serial = serial_set_serial, .get_serial = serial_get_serial, .cleanup = serial_cleanup, .install = serial_install, .proc_show = serial_proc_show, }; struct tty_driver *usb_serial_tty_driver; static int __init usb_serial_init(void) { int result; usb_serial_tty_driver = tty_alloc_driver(USB_SERIAL_TTY_MINORS, TTY_DRIVER_REAL_RAW | TTY_DRIVER_DYNAMIC_DEV); if (IS_ERR(usb_serial_tty_driver)) return PTR_ERR(usb_serial_tty_driver); /* Initialize our global data */ result = bus_register(&usb_serial_bus_type); if (result) { pr_err("%s - registering bus driver failed\n", __func__); goto err_put_driver; } usb_serial_tty_driver->driver_name = "usbserial"; usb_serial_tty_driver->name = "ttyUSB"; usb_serial_tty_driver->major = USB_SERIAL_TTY_MAJOR; usb_serial_tty_driver->minor_start = 0; usb_serial_tty_driver->type = TTY_DRIVER_TYPE_SERIAL; usb_serial_tty_driver->subtype = SERIAL_TYPE_NORMAL; usb_serial_tty_driver->init_termios = tty_std_termios; usb_serial_tty_driver->init_termios.c_cflag = B9600 | CS8 | CREAD | HUPCL | CLOCAL; usb_serial_tty_driver->init_termios.c_ispeed = 9600; usb_serial_tty_driver->init_termios.c_ospeed = 9600; tty_set_operations(usb_serial_tty_driver, &serial_ops); result = tty_register_driver(usb_serial_tty_driver); if (result) { pr_err("%s - tty_register_driver failed\n", __func__); goto err_unregister_bus; } /* register the generic driver, if we should */ result = usb_serial_generic_register(); if (result < 0) { pr_err("%s - registering generic driver failed\n", __func__); goto err_unregister_driver; } return result; err_unregister_driver: tty_unregister_driver(usb_serial_tty_driver); err_unregister_bus: bus_unregister(&usb_serial_bus_type); err_put_driver: pr_err("%s - returning with error %d\n", __func__, result); tty_driver_kref_put(usb_serial_tty_driver); return result; } static void __exit usb_serial_exit(void) { usb_serial_console_exit(); usb_serial_generic_deregister(); tty_unregister_driver(usb_serial_tty_driver); tty_driver_kref_put(usb_serial_tty_driver); bus_unregister(&usb_serial_bus_type); idr_destroy(&serial_minors); } module_init(usb_serial_init); module_exit(usb_serial_exit); #define set_to_generic_if_null(type, function) \ do { \ if (!type->function) { \ type->function = usb_serial_generic_##function; \ pr_debug("%s: using generic " #function "\n", \ type->driver.name); \ } \ } while (0) static void usb_serial_operations_init(struct usb_serial_driver *device) { set_to_generic_if_null(device, open); set_to_generic_if_null(device, write); set_to_generic_if_null(device, close); set_to_generic_if_null(device, write_room); set_to_generic_if_null(device, chars_in_buffer); if (device->tx_empty) set_to_generic_if_null(device, wait_until_sent); set_to_generic_if_null(device, read_bulk_callback); set_to_generic_if_null(device, write_bulk_callback); set_to_generic_if_null(device, process_read_urb); set_to_generic_if_null(device, prepare_write_buffer); } static int usb_serial_register(struct usb_serial_driver *driver) { int retval; if (usb_disabled()) return -ENODEV; if (!driver->description) driver->description = driver->driver.name; if (!driver->usb_driver) { WARN(1, "Serial driver %s has no usb_driver\n", driver->description); return -EINVAL; } /* Prevent individual ports from being unbound. */ driver->driver.suppress_bind_attrs = true; usb_serial_operations_init(driver); /* Add this device to our list of devices */ mutex_lock(&table_lock); list_add(&driver->driver_list, &usb_serial_driver_list); retval = usb_serial_bus_register(driver); if (retval) { pr_err("problem %d when registering driver %s\n", retval, driver->description); list_del(&driver->driver_list); } else { pr_info("USB Serial support registered for %s\n", driver->description); } mutex_unlock(&table_lock); return retval; } static void usb_serial_deregister(struct usb_serial_driver *device) { pr_info("USB Serial deregistering driver %s\n", device->description); mutex_lock(&table_lock); list_del(&device->driver_list); mutex_unlock(&table_lock); usb_serial_bus_deregister(device); } /** * __usb_serial_register_drivers - register drivers for a usb-serial module * @serial_drivers: NULL-terminated array of pointers to drivers to be registered * @owner: owning module * @name: name of the usb_driver for this set of @serial_drivers * @id_table: list of all devices this @serial_drivers set binds to * * Registers all the drivers in the @serial_drivers array, and dynamically * creates a struct usb_driver with the name @name and id_table of @id_table. */ int __usb_serial_register_drivers(struct usb_serial_driver *const serial_drivers[], struct module *owner, const char *name, const struct usb_device_id *id_table) { int rc; struct usb_driver *udriver; struct usb_serial_driver * const *sd; /* * udriver must be registered before any of the serial drivers, * because the store_new_id() routine for the serial drivers (in * bus.c) probes udriver. * * Performance hack: We don't want udriver to be probed until * the serial drivers are registered, because the probe would * simply fail for lack of a matching serial driver. * So we leave udriver's id_table set to NULL until we are all set. * * Suspend/resume support is implemented in the usb-serial core, * so fill in the PM-related fields in udriver. */ udriver = kzalloc_obj(*udriver); if (!udriver) return -ENOMEM; udriver->name = name; udriver->no_dynamic_id = 1; udriver->supports_autosuspend = 1; udriver->suspend = usb_serial_suspend; udriver->resume = usb_serial_resume; udriver->probe = usb_serial_probe; udriver->disconnect = usb_serial_disconnect; /* we only set the reset_resume field if the serial_driver has one */ for (sd = serial_drivers; *sd; ++sd) { if ((*sd)->reset_resume) { udriver->reset_resume = usb_serial_reset_resume; break; } } rc = usb_register(udriver); if (rc) goto err_free_driver; for (sd = serial_drivers; *sd; ++sd) { (*sd)->usb_driver = udriver; (*sd)->driver.owner = owner; rc = usb_serial_register(*sd); if (rc) goto err_deregister_drivers; } /* Now set udriver's id_table and look for matches */ udriver->id_table = id_table; rc = driver_attach(&udriver->driver); return 0; err_deregister_drivers: while (sd-- > serial_drivers) usb_serial_deregister(*sd); usb_deregister(udriver); err_free_driver: kfree(udriver); return rc; } EXPORT_SYMBOL_GPL(__usb_serial_register_drivers); /** * usb_serial_deregister_drivers - deregister drivers for a usb-serial module * @serial_drivers: NULL-terminated array of pointers to drivers to be deregistered * * Deregisters all the drivers in the @serial_drivers array and deregisters and * frees the struct usb_driver that was created by the call to * usb_serial_register_drivers(). */ void usb_serial_deregister_drivers(struct usb_serial_driver *const serial_drivers[]) { struct usb_driver *udriver = (*serial_drivers)->usb_driver; for (; *serial_drivers; ++serial_drivers) usb_serial_deregister(*serial_drivers); usb_deregister(udriver); kfree(udriver); } EXPORT_SYMBOL_GPL(usb_serial_deregister_drivers); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL v2"); |
| 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 | /* SPDX-License-Identifier: GPL-2.0 */ /* * linux/fs/hpfs/hpfs_fn.h * * Mikulas Patocka (mikulas@artax.karlin.mff.cuni.cz), 1998-1999 * * function headers */ //#define DBG //#define DEBUG_LOCKS #ifdef pr_fmt #undef pr_fmt #endif #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mutex.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/slab.h> #include <linux/sched/signal.h> #include <linux/blkdev.h> #include <linux/unaligned.h> #include "hpfs.h" #define EIOERROR EIO #define EFSERROR EUCLEAN #define ANODE_ALLOC_FWD 512 #define FNODE_ALLOC_FWD 0 #define ALLOC_FWD_MIN 16 #define ALLOC_FWD_MAX 128 #define ALLOC_M 1 #define FNODE_RD_AHEAD 16 #define ANODE_RD_AHEAD 0 #define DNODE_RD_AHEAD 72 #define COUNT_RD_AHEAD 62 #define FREE_DNODES_ADD 58 #define FREE_DNODES_DEL 29 #define CHKCOND(x,y) if (!(x)) printk y struct hpfs_inode_info { loff_t mmu_private; ino_t i_parent_dir; /* (directories) gives fnode of parent dir */ unsigned i_dno; /* (directories) root dnode */ unsigned i_dpos; /* (directories) temp for readdir */ unsigned i_dsubdno; /* (directories) temp for readdir */ unsigned i_file_sec; /* (files) minimalist cache of alloc info */ unsigned i_disk_sec; /* (files) minimalist cache of alloc info */ unsigned i_n_secs; /* (files) minimalist cache of alloc info */ unsigned i_ea_size; /* size of extended attributes */ unsigned i_ea_mode : 1; /* file's permission is stored in ea */ unsigned i_ea_uid : 1; /* file's uid is stored in ea */ unsigned i_ea_gid : 1; /* file's gid is stored in ea */ unsigned i_dirty : 1; loff_t **i_rddir_off; struct inode vfs_inode; }; struct hpfs_sb_info { struct mutex hpfs_mutex; /* global hpfs lock */ ino_t sb_root; /* inode number of root dir */ unsigned sb_fs_size; /* file system size, sectors */ unsigned sb_bitmaps; /* sector number of bitmap list */ unsigned sb_dirband_start; /* directory band start sector */ unsigned sb_dirband_size; /* directory band size, dnodes */ unsigned sb_dmap; /* sector number of dnode bit map */ unsigned sb_n_free; /* free blocks for statfs, or -1 */ unsigned sb_n_free_dnodes; /* free dnodes for statfs, or -1 */ kuid_t sb_uid; /* uid from mount options */ kgid_t sb_gid; /* gid from mount options */ umode_t sb_mode; /* mode from mount options */ unsigned sb_eas : 2; /* eas: 0-ignore, 1-ro, 2-rw */ unsigned sb_err : 2; /* on errs: 0-cont, 1-ro, 2-panic */ unsigned sb_chk : 2; /* checks: 0-no, 1-normal, 2-strict */ unsigned sb_lowercase : 1; /* downcase filenames hackery */ unsigned sb_was_error : 1; /* there was an error, set dirty flag */ unsigned sb_chkdsk : 2; /* chkdsk: 0-no, 1-on errs, 2-allways */ unsigned char *sb_cp_table; /* code page tables: */ /* 128 bytes uppercasing table & */ /* 128 bytes lowercasing table */ __le32 *sb_bmp_dir; /* main bitmap directory */ unsigned sb_c_bitmap; /* current bitmap */ unsigned sb_max_fwd_alloc; /* max forwad allocation */ int sb_timeshift; struct rcu_head rcu; unsigned n_hotfixes; secno hotfix_from[256]; secno hotfix_to[256]; }; /* Four 512-byte buffers and the 2k block obtained by concatenating them */ struct quad_buffer_head { struct buffer_head *bh[4]; void *data; }; /* The b-tree down pointer from a dir entry */ static inline dnode_secno de_down_pointer (struct hpfs_dirent *de) { CHKCOND(de->down,("HPFS: de_down_pointer: !de->down\n")); return le32_to_cpu(*(__le32 *) ((void *) de + le16_to_cpu(de->length) - 4)); } /* The first dir entry in a dnode */ static inline struct hpfs_dirent *dnode_first_de (struct dnode *dnode) { return (void *) dnode->dirent; } /* The end+1 of the dir entries */ static inline struct hpfs_dirent *dnode_end_de (struct dnode *dnode) { CHKCOND(le32_to_cpu(dnode->first_free)>=0x14 && le32_to_cpu(dnode->first_free)<=0xa00,("HPFS: dnode_end_de: dnode->first_free = %x\n",(unsigned)le32_to_cpu(dnode->first_free))); return (void *) dnode + le32_to_cpu(dnode->first_free); } /* The dir entry after dir entry de */ static inline struct hpfs_dirent *de_next_de (struct hpfs_dirent *de) { CHKCOND(le16_to_cpu(de->length)>=0x20 && le16_to_cpu(de->length)<0x800,("HPFS: de_next_de: de->length = %x\n",(unsigned)le16_to_cpu(de->length))); return (void *) de + le16_to_cpu(de->length); } static inline struct extended_attribute *fnode_ea(struct fnode *fnode) { return (struct extended_attribute *)((char *)fnode + le16_to_cpu(fnode->ea_offs) + le16_to_cpu(fnode->acl_size_s)); } static inline struct extended_attribute *fnode_end_ea(struct fnode *fnode) { return (struct extended_attribute *)((char *)fnode + le16_to_cpu(fnode->ea_offs) + le16_to_cpu(fnode->acl_size_s) + le16_to_cpu(fnode->ea_size_s)); } static unsigned ea_valuelen(struct extended_attribute *ea) { return ea->valuelen_lo + 256 * ea->valuelen_hi; } static inline struct extended_attribute *next_ea(struct extended_attribute *ea) { return (struct extended_attribute *)((char *)ea + 5 + ea->namelen + ea_valuelen(ea)); } static inline secno ea_sec(struct extended_attribute *ea) { return le32_to_cpu(get_unaligned((__le32 *)((char *)ea + 9 + ea->namelen))); } static inline secno ea_len(struct extended_attribute *ea) { return le32_to_cpu(get_unaligned((__le32 *)((char *)ea + 5 + ea->namelen))); } static inline char *ea_data(struct extended_attribute *ea) { return (char *)((char *)ea + 5 + ea->namelen); } static inline unsigned de_size(int namelen, secno down_ptr) { return ((0x1f + namelen + 3) & ~3) + (down_ptr ? 4 : 0); } static inline void copy_de(struct hpfs_dirent *dst, struct hpfs_dirent *src) { int a; int n; if (!dst || !src) return; a = dst->down; n = dst->not_8x3; memcpy((char *)dst + 2, (char *)src + 2, 28); dst->down = a; dst->not_8x3 = n; } static inline unsigned tstbits(__le32 *bmp, unsigned b, unsigned n) { int i; if ((b >= 0x4000) || (b + n - 1 >= 0x4000)) return n; if (!((le32_to_cpu(bmp[(b & 0x3fff) >> 5]) >> (b & 0x1f)) & 1)) return 1; for (i = 1; i < n; i++) if (!((le32_to_cpu(bmp[((b+i) & 0x3fff) >> 5]) >> ((b+i) & 0x1f)) & 1)) return i + 1; return 0; } /* alloc.c */ int hpfs_chk_sectors(struct super_block *, secno, int, char *); secno hpfs_alloc_sector(struct super_block *, secno, unsigned, int); int hpfs_alloc_if_possible(struct super_block *, secno); void hpfs_free_sectors(struct super_block *, secno, unsigned); int hpfs_check_free_dnodes(struct super_block *, int); void hpfs_free_dnode(struct super_block *, secno); struct dnode *hpfs_alloc_dnode(struct super_block *, secno, dnode_secno *, struct quad_buffer_head *); struct fnode *hpfs_alloc_fnode(struct super_block *, secno, fnode_secno *, struct buffer_head **); struct anode *hpfs_alloc_anode(struct super_block *, secno, anode_secno *, struct buffer_head **); int hpfs_trim_fs(struct super_block *, u64, u64, u64, unsigned *); /* anode.c */ secno hpfs_bplus_lookup(struct super_block *, struct inode *, struct bplus_header *, unsigned, struct buffer_head *); secno hpfs_add_sector_to_btree(struct super_block *, secno, int, unsigned); void hpfs_remove_btree(struct super_block *, struct bplus_header *); int hpfs_ea_read(struct super_block *, secno, int, unsigned, unsigned, char *); int hpfs_ea_write(struct super_block *, secno, int, unsigned, unsigned, const char *); void hpfs_ea_remove(struct super_block *, secno, int, unsigned); void hpfs_truncate_btree(struct super_block *, secno, int, unsigned); void hpfs_remove_fnode(struct super_block *, fnode_secno fno); /* buffer.c */ secno hpfs_search_hotfix_map(struct super_block *s, secno sec); unsigned hpfs_search_hotfix_map_for_range(struct super_block *s, secno sec, unsigned n); void hpfs_prefetch_sectors(struct super_block *, unsigned, int); void *hpfs_map_sector(struct super_block *, unsigned, struct buffer_head **, int); void *hpfs_get_sector(struct super_block *, unsigned, struct buffer_head **); void *hpfs_map_4sectors(struct super_block *, unsigned, struct quad_buffer_head *, int); void *hpfs_get_4sectors(struct super_block *, unsigned, struct quad_buffer_head *); void hpfs_brelse4(struct quad_buffer_head *); void hpfs_mark_4buffers_dirty(struct quad_buffer_head *); /* dentry.c */ extern const struct dentry_operations hpfs_dentry_operations; /* dir.c */ struct dentry *hpfs_lookup(struct inode *, struct dentry *, unsigned int); extern const struct file_operations hpfs_dir_ops; /* dnode.c */ int hpfs_add_pos(struct inode *, loff_t *); void hpfs_del_pos(struct inode *, loff_t *); struct hpfs_dirent *hpfs_add_de(struct super_block *, struct dnode *, const unsigned char *, unsigned, secno); int hpfs_add_dirent(struct inode *, const unsigned char *, unsigned, struct hpfs_dirent *); int hpfs_remove_dirent(struct inode *, dnode_secno, struct hpfs_dirent *, struct quad_buffer_head *, int); void hpfs_count_dnodes(struct super_block *, dnode_secno, int *, int *, int *); dnode_secno hpfs_de_as_down_as_possible(struct super_block *, dnode_secno dno); struct hpfs_dirent *map_pos_dirent(struct inode *, loff_t *, struct quad_buffer_head *); struct hpfs_dirent *map_dirent(struct inode *, dnode_secno, const unsigned char *, unsigned, dnode_secno *, struct quad_buffer_head *); void hpfs_remove_dtree(struct super_block *, dnode_secno); struct hpfs_dirent *map_fnode_dirent(struct super_block *, fnode_secno, struct fnode *, struct quad_buffer_head *); /* ea.c */ void hpfs_ea_ext_remove(struct super_block *, secno, int, unsigned); int hpfs_read_ea(struct super_block *, struct fnode *, char *, char *, int); char *hpfs_get_ea(struct super_block *, struct fnode *, char *, int *); void hpfs_set_ea(struct inode *, struct fnode *, const char *, const char *, int); /* file.c */ int hpfs_file_fsync(struct file *, loff_t, loff_t, int); void hpfs_truncate(struct inode *); extern const struct file_operations hpfs_file_ops; extern const struct inode_operations hpfs_file_iops; extern const struct address_space_operations hpfs_aops; /* inode.c */ void hpfs_init_inode(struct inode *); void hpfs_read_inode(struct inode *); void hpfs_write_inode(struct inode *); void hpfs_write_inode_nolock(struct inode *); int hpfs_setattr(struct mnt_idmap *, struct dentry *, struct iattr *); void hpfs_write_if_changed(struct inode *); void hpfs_evict_inode(struct inode *); /* map.c */ __le32 *hpfs_map_dnode_bitmap(struct super_block *, struct quad_buffer_head *); __le32 *hpfs_map_bitmap(struct super_block *, unsigned, struct quad_buffer_head *, char *); void hpfs_prefetch_bitmap(struct super_block *, unsigned); unsigned char *hpfs_load_code_page(struct super_block *, secno); __le32 *hpfs_load_bitmap_directory(struct super_block *, secno bmp); void hpfs_load_hotfix_map(struct super_block *s, struct hpfs_spare_block *spareblock); struct fnode *hpfs_map_fnode(struct super_block *s, ino_t, struct buffer_head **); struct anode *hpfs_map_anode(struct super_block *s, anode_secno, struct buffer_head **); struct dnode *hpfs_map_dnode(struct super_block *s, dnode_secno, struct quad_buffer_head *); dnode_secno hpfs_fnode_dno(struct super_block *s, ino_t ino); /* name.c */ unsigned char hpfs_upcase(unsigned char *, unsigned char); int hpfs_chk_name(const unsigned char *, unsigned *); unsigned char *hpfs_translate_name(struct super_block *, unsigned char *, unsigned, int, int); int hpfs_compare_names(struct super_block *, const unsigned char *, unsigned, const unsigned char *, unsigned, int); int hpfs_is_name_long(const unsigned char *, unsigned); void hpfs_adjust_length(const unsigned char *, unsigned *); /* namei.c */ extern const struct inode_operations hpfs_dir_iops; extern const struct address_space_operations hpfs_symlink_aops; static inline struct hpfs_inode_info *hpfs_i(struct inode *inode) { return container_of(inode, struct hpfs_inode_info, vfs_inode); } static inline struct hpfs_sb_info *hpfs_sb(struct super_block *sb) { return sb->s_fs_info; } /* super.c */ __printf(2, 3) void hpfs_error(struct super_block *, const char *, ...); int hpfs_stop_cycles(struct super_block *, int, int *, int *, char *); unsigned hpfs_get_free_dnodes(struct super_block *); long hpfs_ioctl(struct file *file, unsigned cmd, unsigned long arg); /* * local time (HPFS) to GMT (Unix) */ static inline time64_t local_to_gmt(struct super_block *s, time64_t t) { extern struct timezone sys_tz; return t + sys_tz.tz_minuteswest * 60 + hpfs_sb(s)->sb_timeshift; } static inline time32_t gmt_to_local(struct super_block *s, time64_t t) { extern struct timezone sys_tz; return t - sys_tz.tz_minuteswest * 60 - hpfs_sb(s)->sb_timeshift; } static inline time32_t local_get_seconds(struct super_block *s) { return gmt_to_local(s, ktime_get_real_seconds()); } /* * Locking: * * hpfs_lock() locks the whole filesystem. It must be taken * on any method called by the VFS. * * We don't do any per-file locking anymore, it is hard to * review and HPFS is not performance-sensitive anyway. */ static inline void hpfs_lock(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); mutex_lock(&sbi->hpfs_mutex); } static inline void hpfs_unlock(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); mutex_unlock(&sbi->hpfs_mutex); } static inline void hpfs_lock_assert(struct super_block *s) { struct hpfs_sb_info *sbi = hpfs_sb(s); WARN_ON(!mutex_is_locked(&sbi->hpfs_mutex)); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_state.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * YOSHIFUJI Hideaki @USAGI * Split up af-specific functions * Derek Atkins <derek@ihtfp.com> * Add UDP Encapsulation * */ #include <linux/compat.h> #include <linux/workqueue.h> #include <net/xfrm.h> #include <linux/pfkeyv2.h> #include <linux/ipsec.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/audit.h> #include <linux/uaccess.h> #include <linux/ktime.h> #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/kernel.h> #include <crypto/aead.h> #include "xfrm_hash.h" #define xfrm_state_deref_prot(table, net) \ rcu_dereference_protected((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) #define xfrm_state_deref_check(table, net) \ rcu_dereference_check((table), lockdep_is_held(&(net)->xfrm.xfrm_state_lock)) static void xfrm_state_gc_task(struct work_struct *work); /* Each xfrm_state may be linked to two tables: 1. Hash table by (spi,daddr,ah/esp) to find SA by SPI. (input,ctl) 2. Hash table by (daddr,family,reqid) to find what SAs exist for given destination/tunnel endpoint. (output) */ static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); static HLIST_HEAD(xfrm_state_dev_gc_list); static inline bool xfrm_state_hold_rcu(struct xfrm_state *x) { return refcount_inc_not_zero(&x->refcnt); } static inline unsigned int xfrm_dst_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u32 reqid, unsigned short family) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_dst_hash(daddr, saddr, reqid, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_src_hash(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } static inline unsigned int xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } static unsigned int xfrm_seq_hash(struct net *net, u32 seq) { lockdep_assert_held(&net->xfrm.xfrm_state_lock); return __xfrm_seq_hash(seq, net->xfrm.state_hmask); } #define XFRM_STATE_INSERT(by, _n, _h, _type) \ { \ struct xfrm_state *_x = NULL; \ \ if (_type != XFRM_DEV_OFFLOAD_PACKET) { \ hlist_for_each_entry_rcu(_x, _h, by) { \ if (_x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ continue; \ break; \ } \ } \ \ if (!_x || _x->xso.type == XFRM_DEV_OFFLOAD_PACKET) \ /* SAD is empty or consist from HW SAs only */ \ hlist_add_head_rcu(_n, _h); \ else \ hlist_add_before_rcu(_n, &_x->by); \ } static void xfrm_hash_transfer(struct hlist_head *list, struct hlist_head *ndsttable, struct hlist_head *nsrctable, struct hlist_head *nspitable, struct hlist_head *nseqtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_state *x; hlist_for_each_entry_safe(x, tmp, list, bydst) { unsigned int h; h = __xfrm_dst_hash(&x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family, nhashmask); XFRM_STATE_INSERT(bydst, &x->bydst, ndsttable + h, x->xso.type); h = __xfrm_src_hash(&x->id.daddr, &x->props.saddr, x->props.family, nhashmask); XFRM_STATE_INSERT(bysrc, &x->bysrc, nsrctable + h, x->xso.type); if (x->id.spi) { h = __xfrm_spi_hash(&x->id.daddr, x->id.spi, x->id.proto, x->props.family, nhashmask); XFRM_STATE_INSERT(byspi, &x->byspi, nspitable + h, x->xso.type); } if (x->km.seq) { h = __xfrm_seq_hash(x->km.seq, nhashmask); XFRM_STATE_INSERT(byseq, &x->byseq, nseqtable + h, x->xso.type); } } } static unsigned long xfrm_hash_new_size(unsigned int state_hmask) { return ((state_hmask + 1) << 1) * sizeof(struct hlist_head); } static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.state_hash_work); struct hlist_head *ndst, *nsrc, *nspi, *nseq, *odst, *osrc, *ospi, *oseq; unsigned long nsize, osize; unsigned int nhashmask, ohashmask; int i; nsize = xfrm_hash_new_size(net->xfrm.state_hmask); ndst = xfrm_hash_alloc(nsize); if (!ndst) return; nsrc = xfrm_hash_alloc(nsize); if (!nsrc) { xfrm_hash_free(ndst, nsize); return; } nspi = xfrm_hash_alloc(nsize); if (!nspi) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); return; } nseq = xfrm_hash_alloc(nsize); if (!nseq) { xfrm_hash_free(ndst, nsize); xfrm_hash_free(nsrc, nsize); xfrm_hash_free(nspi, nsize); return; } spin_lock_bh(&net->xfrm.xfrm_state_lock); write_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); nhashmask = (nsize / sizeof(struct hlist_head)) - 1U; odst = xfrm_state_deref_prot(net->xfrm.state_bydst, net); for (i = net->xfrm.state_hmask; i >= 0; i--) xfrm_hash_transfer(odst + i, ndst, nsrc, nspi, nseq, nhashmask); osrc = xfrm_state_deref_prot(net->xfrm.state_bysrc, net); ospi = xfrm_state_deref_prot(net->xfrm.state_byspi, net); oseq = xfrm_state_deref_prot(net->xfrm.state_byseq, net); ohashmask = net->xfrm.state_hmask; rcu_assign_pointer(net->xfrm.state_bydst, ndst); rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); rcu_assign_pointer(net->xfrm.state_byspi, nspi); rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_state_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_state_lock); osize = (ohashmask + 1) * sizeof(struct hlist_head); synchronize_rcu(); xfrm_hash_free(odst, osize); xfrm_hash_free(osrc, osize); xfrm_hash_free(ospi, osize); xfrm_hash_free(oseq, osize); } static DEFINE_SPINLOCK(xfrm_state_afinfo_lock); static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO]; static DEFINE_SPINLOCK(xfrm_state_gc_lock); static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock); int __xfrm_state_delete(struct xfrm_state *x); int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); static bool km_is_alive(const struct km_event *c); void km_state_expired(struct xfrm_state *x, int hard, u32 portid); int xfrm_register_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (!afinfo) return -EAFNOSUPPORT; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name); \ (afi)->type_ ## name = (T); \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } #undef X rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type); void xfrm_unregister_type(const struct xfrm_type *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; #define X(afi, T, name) do { \ WARN_ON((afi)->type_ ## name != (T)); \ (afi)->type_ ## name = NULL; \ } while (0) switch (type->proto) { case IPPROTO_COMP: X(afinfo, type, comp); break; case IPPROTO_AH: X(afinfo, type, ah); break; case IPPROTO_ESP: X(afinfo, type, esp); break; case IPPROTO_IPIP: X(afinfo, type, ipip); break; case IPPROTO_DSTOPTS: X(afinfo, type, dstopts); break; case IPPROTO_ROUTING: X(afinfo, type, routing); break; case IPPROTO_IPV6: X(afinfo, type, ipip6); break; default: WARN_ON(1); break; } #undef X rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type); static const struct xfrm_type *xfrm_get_type(u8 proto, unsigned short family) { const struct xfrm_type *type = NULL; struct xfrm_state_afinfo *afinfo; int modload_attempted = 0; retry: afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return NULL; switch (proto) { case IPPROTO_COMP: type = afinfo->type_comp; break; case IPPROTO_AH: type = afinfo->type_ah; break; case IPPROTO_ESP: type = afinfo->type_esp; break; case IPPROTO_IPIP: type = afinfo->type_ipip; break; case IPPROTO_DSTOPTS: type = afinfo->type_dstopts; break; case IPPROTO_ROUTING: type = afinfo->type_routing; break; case IPPROTO_IPV6: type = afinfo->type_ipip6; break; default: break; } if (unlikely(type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && !modload_attempted) { request_module("xfrm-type-%d-%d", family, proto); modload_attempted = 1; goto retry; } return type; } static void xfrm_put_type(const struct xfrm_type *type) { module_put(type->owner); } int xfrm_register_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); int err = 0; if (unlikely(afinfo == NULL)) return -EAFNOSUPPORT; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp); afinfo->type_offload_esp = type; break; default: WARN_ON(1); err = -EPROTONOSUPPORT; break; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(xfrm_register_type_offload); void xfrm_unregister_type_offload(const struct xfrm_type_offload *type, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); if (unlikely(afinfo == NULL)) return; switch (type->proto) { case IPPROTO_ESP: WARN_ON(afinfo->type_offload_esp != type); afinfo->type_offload_esp = NULL; break; default: WARN_ON(1); break; } rcu_read_unlock(); } EXPORT_SYMBOL(xfrm_unregister_type_offload); void xfrm_set_type_offload(struct xfrm_state *x, bool try_load) { const struct xfrm_type_offload *type = NULL; struct xfrm_state_afinfo *afinfo; retry: afinfo = xfrm_state_get_afinfo(x->props.family); if (unlikely(afinfo == NULL)) goto out; switch (x->id.proto) { case IPPROTO_ESP: type = afinfo->type_offload_esp; break; default: break; } if ((type && !try_module_get(type->owner))) type = NULL; rcu_read_unlock(); if (!type && try_load) { request_module("xfrm-offload-%d-%d", x->props.family, x->id.proto); try_load = false; goto retry; } out: x->type_offload = type; } EXPORT_SYMBOL(xfrm_set_type_offload); static const struct xfrm_mode xfrm4_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, [XFRM_MODE_IPTFS] = { .encap = XFRM_MODE_IPTFS, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET, }, }; static const struct xfrm_mode xfrm6_mode_map[XFRM_MODE_MAX] = { [XFRM_MODE_BEET] = { .encap = XFRM_MODE_BEET, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, [XFRM_MODE_ROUTEOPTIMIZATION] = { .encap = XFRM_MODE_ROUTEOPTIMIZATION, .family = AF_INET6, }, [XFRM_MODE_TRANSPORT] = { .encap = XFRM_MODE_TRANSPORT, .family = AF_INET6, }, [XFRM_MODE_TUNNEL] = { .encap = XFRM_MODE_TUNNEL, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, [XFRM_MODE_IPTFS] = { .encap = XFRM_MODE_IPTFS, .flags = XFRM_MODE_FLAG_TUNNEL, .family = AF_INET6, }, }; static const struct xfrm_mode *xfrm_get_mode(unsigned int encap, int family) { const struct xfrm_mode *mode; if (unlikely(encap >= XFRM_MODE_MAX)) return NULL; switch (family) { case AF_INET: mode = &xfrm4_mode_map[encap]; if (mode->family == family) return mode; break; case AF_INET6: mode = &xfrm6_mode_map[encap]; if (mode->family == family) return mode; break; default: break; } return NULL; } static const struct xfrm_mode_cbs __rcu *xfrm_mode_cbs_map[XFRM_MODE_MAX]; static DEFINE_SPINLOCK(xfrm_mode_cbs_map_lock); int xfrm_register_mode_cbs(u8 mode, const struct xfrm_mode_cbs *mode_cbs) { if (mode >= XFRM_MODE_MAX) return -EINVAL; spin_lock_bh(&xfrm_mode_cbs_map_lock); rcu_assign_pointer(xfrm_mode_cbs_map[mode], mode_cbs); spin_unlock_bh(&xfrm_mode_cbs_map_lock); return 0; } EXPORT_SYMBOL(xfrm_register_mode_cbs); void xfrm_unregister_mode_cbs(u8 mode) { if (mode >= XFRM_MODE_MAX) return; spin_lock_bh(&xfrm_mode_cbs_map_lock); RCU_INIT_POINTER(xfrm_mode_cbs_map[mode], NULL); spin_unlock_bh(&xfrm_mode_cbs_map_lock); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_unregister_mode_cbs); static const struct xfrm_mode_cbs *xfrm_get_mode_cbs(u8 mode) { const struct xfrm_mode_cbs *cbs; bool try_load = true; if (mode >= XFRM_MODE_MAX) return NULL; retry: rcu_read_lock(); cbs = rcu_dereference(xfrm_mode_cbs_map[mode]); if (cbs && !try_module_get(cbs->owner)) cbs = NULL; rcu_read_unlock(); if (mode == XFRM_MODE_IPTFS && !cbs && try_load) { request_module("xfrm-iptfs"); try_load = false; goto retry; } return cbs; } void xfrm_state_free(struct xfrm_state *x) { kmem_cache_free(xfrm_state_cache, x); } EXPORT_SYMBOL(xfrm_state_free); static void xfrm_state_delete_tunnel(struct xfrm_state *x); static void xfrm_state_gc_destroy(struct xfrm_state *x) { if (x->mode_cbs && x->mode_cbs->destroy_state) x->mode_cbs->destroy_state(x); hrtimer_cancel(&x->mtimer); timer_delete_sync(&x->rtimer); kfree_sensitive(x->aead); kfree_sensitive(x->aalg); kfree_sensitive(x->ealg); kfree(x->calg); kfree(x->encap); kfree(x->coaddr); kfree(x->replay_esn); kfree(x->preplay_esn); xfrm_unset_type_offload(x); xfrm_state_delete_tunnel(x); if (x->type) { x->type->destructor(x); xfrm_put_type(x->type); } if (x->xfrag.page) put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) { struct xfrm_state *x; struct hlist_node *tmp; struct hlist_head gc_list; spin_lock_bh(&xfrm_state_gc_lock); hlist_move_list(&xfrm_state_gc_list, &gc_list); spin_unlock_bh(&xfrm_state_gc_lock); synchronize_rcu(); hlist_for_each_entry_safe(x, tmp, &gc_list, gclist) xfrm_state_gc_destroy(x); } static enum hrtimer_restart xfrm_timer_handler(struct hrtimer *me) { struct xfrm_state *x = container_of(me, struct xfrm_state, mtimer); enum hrtimer_restart ret = HRTIMER_NORESTART; time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int err = 0; spin_lock(&x->lock); xfrm_dev_state_update_stats(x); if (x->km.state == XFRM_STATE_DEAD) goto out; if (x->km.state == XFRM_STATE_EXPIRED) goto expired; if (x->lft.hard_add_expires_seconds) { time64_t tmo = x->lft.hard_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { if (x->xflags & XFRM_SOFT_EXPIRE) { /* enter hard expire without soft expire first?! * setting a new date could trigger this. * workaround: fix x->curflt.add_time by below: */ x->curlft.add_time = now - x->saved_tmo - 1; tmo = x->lft.hard_add_expires_seconds - x->saved_tmo; } else goto expired; } if (tmo < next) next = tmo; } if (x->lft.hard_use_expires_seconds) { time64_t tmo = x->lft.hard_use_expires_seconds + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (x->km.dying) goto resched; if (x->lft.soft_add_expires_seconds) { time64_t tmo = x->lft.soft_add_expires_seconds + x->curlft.add_time - now; if (tmo <= 0) { warn = 1; x->xflags &= ~XFRM_SOFT_EXPIRE; } else if (tmo < next) { next = tmo; x->xflags |= XFRM_SOFT_EXPIRE; x->saved_tmo = tmo; } } if (x->lft.soft_use_expires_seconds) { time64_t tmo = x->lft.soft_use_expires_seconds + (READ_ONCE(x->curlft.use_time) ? : now) - now; if (tmo <= 0) warn = 1; else if (tmo < next) next = tmo; } x->km.dying = warn; if (warn) km_state_expired(x, 0, 0); resched: if (next != TIME64_MAX) { hrtimer_forward_now(&x->mtimer, ktime_set(next, 0)); ret = HRTIMER_RESTART; } goto out; expired: if (x->km.state == XFRM_STATE_ACQ && x->id.spi == 0) x->km.state = XFRM_STATE_EXPIRED; err = __xfrm_state_delete(x); if (!err) km_state_expired(x, 1, 0); xfrm_audit_state_delete(x, err ? 0 : 1, true); out: spin_unlock(&x->lock); return ret; } static void xfrm_replay_timer_handler(struct timer_list *t); struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; x = kmem_cache_zalloc(xfrm_state_cache, GFP_ATOMIC); if (x) { write_pnet(&x->xs_net, net); refcount_set(&x->refcnt, 1); atomic_set(&x->tunnel_users, 0); INIT_LIST_HEAD(&x->km.all); INIT_HLIST_NODE(&x->state_cache); INIT_HLIST_NODE(&x->bydst); INIT_HLIST_NODE(&x->bysrc); INIT_HLIST_NODE(&x->byspi); INIT_HLIST_NODE(&x->byseq); hrtimer_setup(&x->mtimer, xfrm_timer_handler, CLOCK_BOOTTIME, HRTIMER_MODE_ABS_SOFT); timer_setup(&x->rtimer, xfrm_replay_timer_handler, 0); x->curlft.add_time = ktime_get_real_seconds(); x->lft.soft_byte_limit = XFRM_INF; x->lft.soft_packet_limit = XFRM_INF; x->lft.hard_byte_limit = XFRM_INF; x->lft.hard_packet_limit = XFRM_INF; x->replay_maxage = 0; x->replay_maxdiff = 0; x->pcpu_num = UINT_MAX; spin_lock_init(&x->lock); x->mode_data = NULL; } return x; } EXPORT_SYMBOL(xfrm_state_alloc); #ifdef CONFIG_XFRM_OFFLOAD void xfrm_dev_state_delete(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev) { dev->xfrmdev_ops->xdo_dev_state_delete(dev, x); spin_lock_bh(&xfrm_state_dev_gc_lock); hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list); spin_unlock_bh(&xfrm_state_dev_gc_lock); } } EXPORT_SYMBOL_GPL(xfrm_dev_state_delete); void xfrm_dev_state_free(struct xfrm_state *x) { struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = READ_ONCE(xso->dev); if (dev && dev->xfrmdev_ops) { spin_lock_bh(&xfrm_state_dev_gc_lock); if (!hlist_unhashed(&x->dev_gclist)) hlist_del(&x->dev_gclist); spin_unlock_bh(&xfrm_state_dev_gc_lock); if (dev->xfrmdev_ops->xdo_dev_state_free) dev->xfrmdev_ops->xdo_dev_state_free(dev, x); WRITE_ONCE(xso->dev, NULL); xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; netdev_put(dev, &xso->dev_tracker); } } #endif void __xfrm_state_destroy(struct xfrm_state *x) { WARN_ON(x->km.state != XFRM_STATE_DEAD); spin_lock_bh(&xfrm_state_gc_lock); hlist_add_head(&x->gclist, &xfrm_state_gc_list); spin_unlock_bh(&xfrm_state_gc_lock); schedule_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(__xfrm_state_destroy); int __xfrm_state_delete(struct xfrm_state *x) { struct net *net = xs_net(x); int err = -ESRCH; if (x->km.state != XFRM_STATE_DEAD) { x->km.state = XFRM_STATE_DEAD; spin_lock(&net->xfrm.xfrm_state_lock); list_del(&x->km.all); hlist_del_init_rcu(&x->bydst); hlist_del_init_rcu(&x->bysrc); if (!hlist_unhashed(&x->byseq)) hlist_del_init_rcu(&x->byseq); if (!hlist_unhashed(&x->state_cache)) hlist_del_rcu(&x->state_cache); if (!hlist_unhashed(&x->state_cache_input)) hlist_del_rcu(&x->state_cache_input); if (!hlist_unhashed(&x->byspi)) hlist_del_init_rcu(&x->byspi); net->xfrm.state_num--; xfrm_nat_keepalive_state_updated(x); spin_unlock(&net->xfrm.xfrm_state_lock); xfrm_dev_state_delete(x); xfrm_state_delete_tunnel(x); /* All xfrm_state objects are created by xfrm_state_alloc. * The xfrm_state_alloc call gives a reference, and that * is what we are dropping here. */ xfrm_state_put(x); err = 0; } return err; } EXPORT_SYMBOL(__xfrm_state_delete); int xfrm_state_delete(struct xfrm_state *x) { int err; spin_lock_bh(&x->lock); err = __xfrm_state_delete(x); spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_state_delete); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { if (xfrm_id_proto_match(x->id.proto, proto) && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { int i, err = 0; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; struct xfrm_dev_offload *xso; hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { xso = &x->xso; if (xso->dev == dev && (err = security_xfrm_state_delete(x)) != 0) { xfrm_audit_state_delete(x, 0, task_valid); return err; } } } return err; } #else static inline int xfrm_state_flush_secctx_check(struct net *net, u8 proto, bool task_valid) { return 0; } static inline int xfrm_dev_state_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { return 0; } #endif int xfrm_state_flush(struct net *net, u8 proto, bool task_valid) { int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_flush_secctx_check(net, proto, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { struct xfrm_state *x; restart: hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { if (!xfrm_state_kern(x) && xfrm_id_proto_match(x->id.proto, proto)) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (cnt) err = 0; return err; } EXPORT_SYMBOL(xfrm_state_flush); int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid) { struct xfrm_state *x; struct hlist_node *tmp; struct xfrm_dev_offload *xso; int i, err = 0, cnt = 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_dev_state_flush_secctx_check(net, dev, task_valid); if (err) goto out; err = -ESRCH; for (i = 0; i <= net->xfrm.state_hmask; i++) { restart: hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) { xso = &x->xso; if (!xfrm_state_kern(x) && xso->dev == dev) { xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = xfrm_state_delete(x); xfrm_dev_state_free(x); xfrm_audit_state_delete(x, err ? 0 : 1, task_valid); xfrm_state_put(x); if (!err) cnt++; spin_lock_bh(&net->xfrm.xfrm_state_lock); goto restart; } } } if (cnt) err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); spin_lock_bh(&xfrm_state_dev_gc_lock); restart_gc: hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) { xso = &x->xso; if (xso->dev == dev) { spin_unlock_bh(&xfrm_state_dev_gc_lock); xfrm_dev_state_free(x); spin_lock_bh(&xfrm_state_dev_gc_lock); goto restart_gc; } } spin_unlock_bh(&xfrm_state_dev_gc_lock); xfrm_flush_gc(); return err; } EXPORT_SYMBOL(xfrm_dev_state_flush); void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_sad_getinfo); static void __xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; sel->daddr.a4 = fl4->daddr; sel->saddr.a4 = fl4->saddr; sel->dport = xfrm_flowi_dport(fl, &fl4->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl4->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET; sel->prefixlen_d = 32; sel->prefixlen_s = 32; sel->proto = fl4->flowi4_proto; sel->ifindex = fl4->flowi4_oif; } static void __xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; /* Initialize temporary selector matching only to current session. */ *(struct in6_addr *)&sel->daddr = fl6->daddr; *(struct in6_addr *)&sel->saddr = fl6->saddr; sel->dport = xfrm_flowi_dport(fl, &fl6->uli); sel->dport_mask = htons(0xffff); sel->sport = xfrm_flowi_sport(fl, &fl6->uli); sel->sport_mask = htons(0xffff); sel->family = AF_INET6; sel->prefixlen_d = 128; sel->prefixlen_s = 128; sel->proto = fl6->flowi6_proto; sel->ifindex = fl6->flowi6_oif; } static void xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, const struct xfrm_tmpl *tmpl, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { case AF_INET: __xfrm4_init_tempsel(&x->sel, fl); break; case AF_INET6: __xfrm6_init_tempsel(&x->sel, fl); break; } x->id = tmpl->id; switch (tmpl->encap_family) { case AF_INET: if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; x->props.saddr = tmpl->saddr; if (x->props.saddr.a4 == 0) x->props.saddr.a4 = saddr->a4; break; case AF_INET6: if (ipv6_addr_any((struct in6_addr *)&x->id.daddr)) memcpy(&x->id.daddr, daddr, sizeof(x->sel.daddr)); memcpy(&x->props.saddr, &tmpl->saddr, sizeof(x->props.saddr)); if (ipv6_addr_any((struct in6_addr *)&x->props.saddr)) memcpy(&x->props.saddr, saddr, sizeof(x->props.saddr)); break; } x->props.mode = tmpl->mode; x->props.reqid = tmpl->reqid; x->props.family = tmpl->encap_family; } struct xfrm_hash_state_ptrs { const struct hlist_head *bydst; const struct hlist_head *bysrc; const struct hlist_head *byspi; unsigned int hmask; }; static void xfrm_hash_ptrs_get(const struct net *net, struct xfrm_hash_state_ptrs *ptrs) { unsigned int sequence; do { sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); ptrs->bydst = xfrm_state_deref_check(net->xfrm.state_bydst, net); ptrs->bysrc = xfrm_state_deref_check(net->xfrm.state_bysrc, net); ptrs->byspi = xfrm_state_deref_check(net->xfrm.state_byspi, net); ptrs->hmask = net->xfrm.state_hmask; } while (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)); } static struct xfrm_state *__xfrm_state_lookup_all(const struct xfrm_hash_state_ptrs *state_ptrs, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, struct xfrm_dev_offload *xdo) { unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { #ifdef CONFIG_XFRM_OFFLOAD if (xdo->type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (xdo->dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static struct xfrm_state *__xfrm_state_lookup(const struct xfrm_hash_state_ptrs *state_ptrs, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { unsigned int h = __xfrm_spi_hash(daddr, spi, proto, family, state_ptrs->hmask); struct xfrm_state *x; hlist_for_each_entry_rcu(x, state_ptrs->byspi + h, byspi) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } struct xfrm_state *xfrm_input_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_hash_state_ptrs state_ptrs; struct hlist_head *state_cache_input; struct xfrm_state *x = NULL; /* BH is always disabled on the input path. */ lockdep_assert_in_softirq(); state_cache_input = raw_cpu_ptr(net->xfrm.state_cache_input); hlist_for_each_entry_rcu(x, state_cache_input, state_cache_input) { if (x->props.family != family || x->id.spi != spi || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; goto out; } xfrm_hash_ptrs_get(net, &state_ptrs); x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); if (x) { spin_lock(&net->xfrm.xfrm_state_lock); if (x->km.state != XFRM_STATE_VALID) { /* * The state is about to be destroyed. * * Don't add it to the cache but still * return it to the caller. */ } else if (hlist_unhashed(&x->state_cache_input)) { hlist_add_head_rcu(&x->state_cache_input, state_cache_input); } else { hlist_del_rcu(&x->state_cache_input); hlist_add_head_rcu(&x->state_cache_input, state_cache_input); } spin_unlock(&net->xfrm.xfrm_state_lock); } out: return x; } EXPORT_SYMBOL(xfrm_input_state_lookup); static struct xfrm_state *__xfrm_state_lookup_byaddr(const struct xfrm_hash_state_ptrs *state_ptrs, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { unsigned int h = __xfrm_src_hash(daddr, saddr, family, state_ptrs->hmask); struct xfrm_state *x; hlist_for_each_entry_rcu(x, state_ptrs->bysrc + h, bysrc) { if (x->props.family != family || x->id.proto != proto || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; if ((mark & x->mark.m) != x->mark.v) continue; if (!xfrm_state_hold_rcu(x)) continue; return x; } return NULL; } static inline struct xfrm_state * __xfrm_state_locate(struct xfrm_state *x, int use_spi, int family) { struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xs_net(x); u32 mark = x->mark.v & x->mark.m; xfrm_hash_ptrs_get(net, &state_ptrs); if (use_spi) return __xfrm_state_lookup(&state_ptrs, mark, &x->id.daddr, x->id.spi, x->id.proto, family); else return __xfrm_state_lookup_byaddr(&state_ptrs, mark, &x->id.daddr, &x->props.saddr, x->id.proto, family); } static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) { if (have_hash_collision && (net->xfrm.state_hmask + 1) < xfrm_state_hashmax && net->xfrm.state_num > net->xfrm.state_hmask) schedule_work(&net->xfrm.state_hash_work); } static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, int *error, unsigned int pcpu_id) { /* Resolution logic: * 1. There is a valid state with matching selector. Done. * 2. Valid state with inappropriate selector. Skip. * * Entering area of "sysdeps". * * 3. If state is not valid, selector is temporary, it selects * only session which triggered previous resolution. Key * manager will do something to install a state with proper * selector. */ if (x->km.state == XFRM_STATE_VALID) { if ((x->sel.family && (x->sel.family != family || !xfrm_selector_match(&x->sel, fl, family))) || !security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) return; if (x->pcpu_num != UINT_MAX && x->pcpu_num != pcpu_id) return; if (!*best || ((*best)->pcpu_num == UINT_MAX && x->pcpu_num == pcpu_id) || (*best)->km.dying > x->km.dying || ((*best)->km.dying == x->km.dying && (*best)->curlft.add_time < x->curlft.add_time)) *best = x; } else if (x->km.state == XFRM_STATE_ACQ) { if (!*best || x->pcpu_num == pcpu_id) *acq_in_progress = 1; } else if (x->km.state == XFRM_STATE_ERROR || x->km.state == XFRM_STATE_EXPIRED) { if ((!x->sel.family || (x->sel.family == family && xfrm_selector_match(&x->sel, fl, family))) && security_xfrm_state_pol_flow_match(x, pol, &fl->u.__fl_common)) *error = -ESRCH; } } struct xfrm_state * xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family, u32 if_id) { static xfrm_address_t saddr_wildcard = { }; struct xfrm_hash_state_ptrs state_ptrs; struct net *net = xp_net(pol); unsigned int h, h_wildcard; struct xfrm_state *x, *x0, *to_put; int acquire_in_progress = 0; int error = 0; struct xfrm_state *best = NULL; u32 mark = pol->mark.v & pol->mark.m; unsigned short encap_family = tmpl->encap_family; unsigned int sequence; struct km_event c; unsigned int pcpu_id; bool cached = false; /* We need the cpu id just as a lookup key, * we don't require it to be stable. */ pcpu_id = raw_smp_processor_id(); to_put = NULL; sequence = read_seqcount_begin(&net->xfrm.xfrm_state_hash_generation); rcu_read_lock(); xfrm_hash_ptrs_get(net, &state_ptrs); hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, encap_family, &best, &acquire_in_progress, &error, pcpu_id); } if (best) goto cached; hlist_for_each_entry_rcu(x, &pol->state_cache_list, state_cache) { if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error, pcpu_id); } cached: cached = true; if (best) goto found; else if (error) best = NULL; else if (acquire_in_progress) /* XXX: acquire_in_progress should not happen */ WARN_ON(1); h = __xfrm_dst_hash(daddr, saddr, tmpl->reqid, encap_family, state_ptrs.hmask); hlist_for_each_entry_rcu(x, state_ptrs.bydst + h, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (pol->xdo.dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error, pcpu_id); } if (best || acquire_in_progress) goto found; h_wildcard = __xfrm_dst_hash(daddr, &saddr_wildcard, tmpl->reqid, encap_family, state_ptrs.hmask); hlist_for_each_entry_rcu(x, state_ptrs.bydst + h_wildcard, bydst) { #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { if (x->xso.type != XFRM_DEV_OFFLOAD_PACKET) /* HW states are in the head of list, there is * no need to iterate further. */ break; /* Packet offload: both policy and SA should * have same device. */ if (pol->xdo.dev != x->xso.dev) continue; } else if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) /* Skip HW policy for SW lookups */ continue; #endif if (x->props.family == encap_family && x->props.reqid == tmpl->reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_addr_equal(&x->id.daddr, daddr, encap_family) && tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) xfrm_state_look_at(pol, x, fl, family, &best, &acquire_in_progress, &error, pcpu_id); } found: if (!(pol->flags & XFRM_POLICY_CPU_ACQUIRE) || (best && (best->pcpu_num == pcpu_id))) x = best; if (!x && !error && !acquire_in_progress) { if (tmpl->id.spi && (x0 = __xfrm_state_lookup_all(&state_ptrs, mark, daddr, tmpl->id.spi, tmpl->id.proto, encap_family, &pol->xdo)) != NULL) { to_put = x0; error = -EEXIST; goto out; } c.net = net; /* If the KMs have no listeners (yet...), avoid allocating an SA * for each and every packet - garbage collection might not * handle the flood. */ if (!km_is_alive(&c)) { error = -ESRCH; goto out; } x = xfrm_state_alloc(net); if (x == NULL) { error = -ENOMEM; goto out; } /* Initialize temporary state matching only * to current session. */ xfrm_init_tempstate(x, fl, tmpl, daddr, saddr, family); memcpy(&x->mark, &pol->mark, sizeof(x->mark)); x->if_id = if_id; if ((pol->flags & XFRM_POLICY_CPU_ACQUIRE) && best) x->pcpu_num = pcpu_id; error = security_xfrm_state_alloc_acquire(x, pol->security, fl->flowi_secid); if (error) { x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } #ifdef CONFIG_XFRM_OFFLOAD if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { struct xfrm_dev_offload *xdo = &pol->xdo; struct xfrm_dev_offload *xso = &x->xso; struct net_device *dev = xdo->dev; xso->type = XFRM_DEV_OFFLOAD_PACKET; xso->dir = xdo->dir; xso->dev = dev; xso->ifindex = dev->ifindex; xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ; netdev_hold(dev, &xso->dev_tracker, GFP_ATOMIC); error = dev->xfrmdev_ops->xdo_dev_state_add(dev, x, NULL); if (error) { xso->dir = 0; netdev_put(dev, &xso->dev_tracker); xso->dev = NULL; xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED; x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; goto out; } } #endif if (km_query(x, tmpl, pol) == 0) { spin_lock_bh(&net->xfrm.xfrm_state_lock); x->km.state = XFRM_STATE_ACQ; x->dir = XFRM_SA_DIR_OUT; list_add(&x->km.all, &net->xfrm.state_all); h = xfrm_dst_hash(net, daddr, saddr, tmpl->reqid, encap_family); XFRM_STATE_INSERT(bydst, &x->bydst, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, encap_family); XFRM_STATE_INSERT(bysrc, &x->bysrc, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); INIT_HLIST_NODE(&x->state_cache); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, encap_family); XFRM_STATE_INSERT(byspi, &x->byspi, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, x->xso.type); } x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } else { #ifdef CONFIG_XFRM_OFFLOAD struct xfrm_dev_offload *xso = &x->xso; if (xso->type == XFRM_DEV_OFFLOAD_PACKET) { xfrm_dev_state_delete(x); xfrm_dev_state_free(x); } #endif x->km.state = XFRM_STATE_DEAD; to_put = x; x = NULL; error = -ESRCH; } /* Use the already installed 'fallback' while the CPU-specific * SA acquire is handled*/ if (best) x = best; } out: if (x) { if (!xfrm_state_hold_rcu(x)) { *err = -EAGAIN; x = NULL; } } else { *err = acquire_in_progress ? -EAGAIN : error; } if (x && x->km.state == XFRM_STATE_VALID && !cached && (!(pol->flags & XFRM_POLICY_CPU_ACQUIRE) || x->pcpu_num == pcpu_id)) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (hlist_unhashed(&x->state_cache)) hlist_add_head_rcu(&x->state_cache, &pol->state_cache_list); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } rcu_read_unlock(); if (to_put) xfrm_state_put(to_put); if (read_seqcount_retry(&net->xfrm.xfrm_state_hash_generation, sequence)) { *err = -EAGAIN; if (x) { xfrm_state_put(x); x = NULL; } } return x; } struct xfrm_state * xfrm_stateonly_find(struct net *net, u32 mark, u32 if_id, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, u8 mode, u8 proto, u32 reqid) { unsigned int h; struct xfrm_state *rx = NULL, *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); h = xfrm_dst_hash(net, daddr, saddr, reqid, family); hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.family == family && x->props.reqid == reqid && (mark & x->mark.m) == x->mark.v && x->if_id == if_id && !(x->props.flags & XFRM_STATE_WILDRECV) && xfrm_state_addr_check(x, daddr, saddr, family) && mode == x->props.mode && proto == x->id.proto && x->km.state == XFRM_STATE_VALID) { rx = x; break; } } if (rx) xfrm_state_hold(rx); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return rx; } EXPORT_SYMBOL(xfrm_stateonly_find); struct xfrm_state *xfrm_state_lookup_byspi(struct net *net, __be32 spi, unsigned short family) { struct xfrm_state *x; struct xfrm_state_walk *w; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_for_each_entry(w, &net->xfrm.state_all, all) { x = container_of(w, struct xfrm_state, km); if (x->props.family != family || x->id.spi != spi) continue; xfrm_state_hold(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return NULL; } EXPORT_SYMBOL(xfrm_state_lookup_byspi); static struct xfrm_state *xfrm_state_lookup_spi_proto(struct net *net, __be32 spi, u8 proto) { struct xfrm_state *x; unsigned int i; for (i = 0; i <= net->xfrm.state_hmask; i++) { hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + i, byspi) { if (x->id.spi == spi && x->id.proto == proto) return x; } } return NULL; } static void __xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); unsigned int h; list_add(&x->km.all, &net->xfrm.state_all); /* Sanitize mark before store */ x->mark.v &= x->mark.m; h = xfrm_dst_hash(net, &x->id.daddr, &x->props.saddr, x->props.reqid, x->props.family); XFRM_STATE_INSERT(bydst, &x->bydst, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, &x->id.daddr, &x->props.saddr, x->props.family); XFRM_STATE_INSERT(bysrc, &x->bysrc, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); if (x->id.spi) { h = xfrm_spi_hash(net, &x->id.daddr, x->id.spi, x->id.proto, x->props.family); XFRM_STATE_INSERT(byspi, &x->byspi, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); } if (x->km.seq) { h = xfrm_seq_hash(net, x->km.seq); XFRM_STATE_INSERT(byseq, &x->byseq, xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, x->xso.type); } hrtimer_start(&x->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (x->replay_maxage) mod_timer(&x->rtimer, jiffies + x->replay_maxage); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); xfrm_nat_keepalive_state_updated(x); } /* net->xfrm.xfrm_state_lock is held */ static void __xfrm_state_bump_genids(struct xfrm_state *xnew) { struct net *net = xs_net(xnew); unsigned short family = xnew->props.family; u32 reqid = xnew->props.reqid; struct xfrm_state *x; unsigned int h; u32 mark = xnew->mark.v & xnew->mark.m; u32 if_id = xnew->if_id; u32 cpu_id = xnew->pcpu_num; h = xfrm_dst_hash(net, &xnew->id.daddr, &xnew->props.saddr, reqid, family); hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.family == family && x->props.reqid == reqid && x->if_id == if_id && x->pcpu_num == cpu_id && (mark & x->mark.m) == x->mark.v && xfrm_addr_equal(&x->id.daddr, &xnew->id.daddr, family) && xfrm_addr_equal(&x->props.saddr, &xnew->props.saddr, family)) x->genid++; } } void xfrm_state_insert(struct xfrm_state *x) { struct net *net = xs_net(x); spin_lock_bh(&net->xfrm.xfrm_state_lock); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_insert); /* net->xfrm.xfrm_state_lock is held */ static struct xfrm_state *__find_acq_core(struct net *net, const struct xfrm_mark *m, unsigned short family, u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create) { unsigned int h = xfrm_dst_hash(net, daddr, saddr, reqid, family); struct xfrm_state *x; u32 mark = m->v & m->m; hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.reqid != reqid || x->props.mode != mode || x->props.family != family || x->km.state != XFRM_STATE_ACQ || x->id.spi != 0 || x->id.proto != proto || (mark & x->mark.m) != x->mark.v || x->pcpu_num != pcpu_num || !xfrm_addr_equal(&x->id.daddr, daddr, family) || !xfrm_addr_equal(&x->props.saddr, saddr, family)) continue; xfrm_state_hold(x); return x; } if (!create) return NULL; x = xfrm_state_alloc(net); if (likely(x)) { switch (family) { case AF_INET: x->sel.daddr.a4 = daddr->a4; x->sel.saddr.a4 = saddr->a4; x->sel.prefixlen_d = 32; x->sel.prefixlen_s = 32; x->props.saddr.a4 = saddr->a4; x->id.daddr.a4 = daddr->a4; break; case AF_INET6: x->sel.daddr.in6 = daddr->in6; x->sel.saddr.in6 = saddr->in6; x->sel.prefixlen_d = 128; x->sel.prefixlen_s = 128; x->props.saddr.in6 = saddr->in6; x->id.daddr.in6 = daddr->in6; break; } x->pcpu_num = pcpu_num; x->km.state = XFRM_STATE_ACQ; x->id.proto = proto; x->props.family = family; x->props.mode = mode; x->props.reqid = reqid; x->if_id = if_id; x->mark.v = m->v; x->mark.m = m->m; x->lft.hard_add_expires_seconds = net->xfrm.sysctl_acq_expires; xfrm_state_hold(x); hrtimer_start(&x->mtimer, ktime_set(net->xfrm.sysctl_acq_expires, 0), HRTIMER_MODE_REL_SOFT); list_add(&x->km.all, &net->xfrm.state_all); XFRM_STATE_INSERT(bydst, &x->bydst, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, x->xso.type); h = xfrm_src_hash(net, daddr, saddr, family); XFRM_STATE_INSERT(bysrc, &x->bysrc, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, x->xso.type); net->xfrm.state_num++; xfrm_hash_grow_check(net, x->bydst.next != NULL); } return x; } static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num); int xfrm_state_add(struct xfrm_state *x) { struct net *net = xs_net(x); struct xfrm_state *x1, *to_put; int family; int err; u32 mark = x->mark.v & x->mark.m; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); family = x->props.family; to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, family); if (x1) { to_put = x1; x1 = NULL; err = -EEXIST; goto out; } if (use_spi && x->km.seq) { x1 = __xfrm_find_acq_byseq(net, mark, x->km.seq, x->pcpu_num); if (x1 && ((x1->id.proto != x->id.proto) || !xfrm_addr_equal(&x1->id.daddr, &x->id.daddr, family))) { to_put = x1; x1 = NULL; } } if (use_spi && !x1) x1 = __find_acq_core(net, &x->mark, family, x->props.mode, x->props.reqid, x->if_id, x->pcpu_num, x->id.proto, &x->id.daddr, &x->props.saddr, 0); __xfrm_state_bump_genids(x); __xfrm_state_insert(x); err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (x1) { xfrm_state_delete(x1); xfrm_state_put(x1); } if (to_put) xfrm_state_put(to_put); return err; } EXPORT_SYMBOL(xfrm_state_add); #ifdef CONFIG_XFRM_MIGRATE static inline int clone_security(struct xfrm_state *x, struct xfrm_sec_ctx *security) { struct xfrm_user_sec_ctx *uctx; int size = sizeof(*uctx) + security->ctx_len; int err; uctx = kmalloc(size, GFP_KERNEL); if (!uctx) return -ENOMEM; uctx->exttype = XFRMA_SEC_CTX; uctx->len = size; uctx->ctx_doi = security->ctx_doi; uctx->ctx_alg = security->ctx_alg; uctx->ctx_len = security->ctx_len; memcpy(uctx + 1, security->ctx_str, security->ctx_len); err = security_xfrm_state_alloc(x, uctx); kfree(uctx); if (err) return err; return 0; } static struct xfrm_state *xfrm_state_clone_and_setup(struct xfrm_state *orig, const struct xfrm_migrate *m) { struct net *net = xs_net(orig); struct xfrm_state *x = xfrm_state_alloc(net); if (!x) goto out; memcpy(&x->id, &orig->id, sizeof(x->id)); if (m->msg_type == XFRM_MSG_MIGRATE_STATE) { if (m->flags & XFRM_MIGRATE_STATE_UPDATE_H2H_SEL) { u8 prefixlen = (m->new_family == AF_INET6) ? 128 : 32; x->sel = orig->sel; x->sel.family = m->new_family; x->sel.prefixlen_d = prefixlen; x->sel.prefixlen_s = prefixlen; x->sel.daddr = m->new_daddr; x->sel.saddr = m->new_saddr; } else { x->sel = *m->new_sel; } } else { x->sel = orig->sel; } memcpy(&x->lft, &orig->lft, sizeof(x->lft)); x->props.mode = orig->props.mode; x->props.replay_window = orig->props.replay_window; if (orig->aalg) { x->aalg = xfrm_algo_auth_clone(orig->aalg); if (!x->aalg) goto error; } x->props.aalgo = orig->props.aalgo; if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); x->geniv = orig->geniv; if (!x->aead) goto error; } if (orig->ealg) { x->ealg = xfrm_algo_clone(orig->ealg); if (!x->ealg) goto error; } x->props.ealgo = orig->props.ealgo; if (orig->calg) { x->calg = xfrm_algo_clone(orig->calg); if (!x->calg) goto error; } x->props.calgo = orig->props.calgo; if (m->encap) { x->encap = kmemdup(m->encap, sizeof(*x->encap), GFP_KERNEL); if (!x->encap) goto error; x->mapping_maxage = m->mapping_maxage; x->nat_keepalive_interval = m->nat_keepalive_interval; } if (orig->security) if (clone_security(x, orig->security)) goto error; if (orig->coaddr) { x->coaddr = kmemdup(orig->coaddr, sizeof(*x->coaddr), GFP_KERNEL); if (!x->coaddr) goto error; } if (xfrm_replay_clone(x, orig)) goto error; x->mark = m->new_mark ? *m->new_mark : m->old_mark; x->props.smark = m->smark; x->props.flags = orig->props.flags; x->props.extra_flags = orig->props.extra_flags; x->pcpu_num = orig->pcpu_num; x->if_id = orig->if_id; x->tfcpad = orig->tfcpad; x->replay_maxdiff = orig->replay_maxdiff; x->replay_maxage = orig->replay_maxage; x->km.state = orig->km.state; x->km.seq = orig->km.seq; x->lastused = orig->lastused; x->new_mapping = 0; x->new_mapping_sport = 0; x->dir = orig->dir; x->mode_cbs = orig->mode_cbs; if (x->mode_cbs && x->mode_cbs->clone_state) { if (x->mode_cbs->clone_state(x, orig)) { if (!x->mode_data) x->mode_cbs = NULL; goto error; } } x->props.reqid = m->new_reqid; x->props.family = m->new_family; memcpy(&x->id.daddr, &m->new_daddr, sizeof(x->id.daddr)); memcpy(&x->props.saddr, &m->new_saddr, sizeof(x->props.saddr)); return x; error: x->km.state = XFRM_STATE_DEAD; xfrm_state_put(x); out: return NULL; } struct xfrm_state *xfrm_migrate_state_find(struct xfrm_migrate *m, struct net *net, u32 if_id) { unsigned int h; struct xfrm_state *x = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (m->old_reqid) { h = xfrm_dst_hash(net, &m->old_daddr, &m->old_saddr, m->old_reqid, m->old_family); hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + h, bydst) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (m->old_reqid && x->props.reqid != m->old_reqid) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } else { h = xfrm_src_hash(net, &m->old_daddr, &m->old_saddr, m->old_family); hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bysrc, net) + h, bysrc) { if (x->props.mode != m->mode || x->id.proto != m->proto) continue; if (if_id != 0 && x->if_id != if_id) continue; if (!xfrm_addr_equal(&x->id.daddr, &m->old_daddr, m->old_family) || !xfrm_addr_equal(&x->props.saddr, &m->old_saddr, m->old_family)) continue; xfrm_state_hold(x); break; } } spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_migrate_state_find); struct xfrm_state *xfrm_state_migrate_create(struct xfrm_state *x, const struct xfrm_migrate *m, struct net *net, struct netlink_ext_ack *extack) { struct xfrm_state *xc; xc = xfrm_state_clone_and_setup(x, m); if (!xc) { NL_SET_ERR_MSG(extack, "Failed to clone and setup state"); return NULL; } if (xfrm_init_state(xc, extack) < 0) { NL_SET_ERR_MSG_WEAK(extack, "Failed to initialize migrated state"); goto error; } /* configure the hardware if offload is requested */ if (m->xuo && xfrm_dev_state_add(net, xc, m->xuo, extack)) goto error; return xc; error: xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); return NULL; } EXPORT_SYMBOL(xfrm_state_migrate_create); int xfrm_state_migrate_install(const struct xfrm_state *x, struct xfrm_state *xc, const struct xfrm_migrate *m, struct netlink_ext_ack *extack) { if (m->new_family == m->old_family && xfrm_addr_equal(&x->id.daddr, &m->new_daddr, m->new_family)) { /* * Care is needed when the destination address of the state is * to be updated as it is a part of triplet. */ xfrm_state_insert(xc); } else { if (xfrm_state_add(xc) < 0) { NL_SET_ERR_MSG(extack, "Failed to add migrated state"); if (m->xuo) xfrm_dev_state_delete(xc); xc->km.state = XFRM_STATE_DEAD; xfrm_state_put(xc); return -EEXIST; } } return 0; } EXPORT_SYMBOL(xfrm_state_migrate_install); struct xfrm_state *xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m, struct net *net, struct netlink_ext_ack *extack) { struct xfrm_state *xc; xc = xfrm_state_migrate_create(x, m, net, extack); if (!xc) return NULL; xfrm_migrate_sync(xc, x); if (xfrm_state_migrate_install(x, xc, m, extack) < 0) return NULL; return xc; } EXPORT_SYMBOL(xfrm_state_migrate); #endif int xfrm_state_update(struct xfrm_state *x) { struct xfrm_state *x1, *to_put; int err; int use_spi = xfrm_id_proto_match(x->id.proto, IPSEC_PROTO_ANY); struct net *net = xs_net(x); to_put = NULL; spin_lock_bh(&net->xfrm.xfrm_state_lock); x1 = __xfrm_state_locate(x, use_spi, x->props.family); err = -ESRCH; if (!x1) goto out; if (xfrm_state_kern(x1)) { to_put = x1; err = -EEXIST; goto out; } if (x1->km.state == XFRM_STATE_ACQ) { if (x->dir && x1->dir != x->dir) { to_put = x1; goto out; } __xfrm_state_insert(x); x = NULL; } else { if (x1->dir != x->dir) { to_put = x1; goto out; } } err = 0; out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); if (to_put) xfrm_state_put(to_put); if (err) return err; if (!x) { xfrm_state_delete(x1); xfrm_state_put(x1); return 0; } err = -EINVAL; spin_lock_bh(&x1->lock); if (likely(x1->km.state == XFRM_STATE_VALID)) { if (x->encap && x1->encap && x->encap->encap_type == x1->encap->encap_type) memcpy(x1->encap, x->encap, sizeof(*x1->encap)); else if (x->encap || x1->encap) goto fail; if (x->coaddr && x1->coaddr) { memcpy(x1->coaddr, x->coaddr, sizeof(*x1->coaddr)); } if (!use_spi && memcmp(&x1->sel, &x->sel, sizeof(x1->sel))) memcpy(&x1->sel, &x->sel, sizeof(x1->sel)); memcpy(&x1->lft, &x->lft, sizeof(x1->lft)); x1->km.dying = 0; hrtimer_start(&x1->mtimer, ktime_set(1, 0), HRTIMER_MODE_REL_SOFT); if (READ_ONCE(x1->curlft.use_time)) xfrm_state_check_expire(x1); if (x->props.smark.m || x->props.smark.v || x->if_id) { spin_lock_bh(&net->xfrm.xfrm_state_lock); if (x->props.smark.m || x->props.smark.v) x1->props.smark = x->props.smark; if (x->if_id) x1->if_id = x->if_id; __xfrm_state_bump_genids(x1); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } err = 0; x->km.state = XFRM_STATE_DEAD; xfrm_dev_state_delete(x); __xfrm_state_put(x); } fail: spin_unlock_bh(&x1->lock); xfrm_state_put(x1); return err; } EXPORT_SYMBOL(xfrm_state_update); int xfrm_state_check_expire(struct xfrm_state *x) { /* All counters which are needed to decide if state is expired * are handled by SW for non-packet offload modes. Simply skip * the following update and save extra boilerplate in drivers. */ if (x->xso.type == XFRM_DEV_OFFLOAD_PACKET) xfrm_dev_state_update_stats(x); if (!READ_ONCE(x->curlft.use_time)) WRITE_ONCE(x->curlft.use_time, ktime_get_real_seconds()); if (x->curlft.bytes >= x->lft.hard_byte_limit || x->curlft.packets >= x->lft.hard_packet_limit) { x->km.state = XFRM_STATE_EXPIRED; hrtimer_start(&x->mtimer, 0, HRTIMER_MODE_REL_SOFT); return -EINVAL; } if (!x->km.dying && (x->curlft.bytes >= x->lft.soft_byte_limit || x->curlft.packets >= x->lft.soft_packet_limit)) { x->km.dying = 1; km_state_expired(x, 0, 0); } return 0; } EXPORT_SYMBOL(xfrm_state_check_expire); void xfrm_state_update_stats(struct net *net) { struct xfrm_state *x; int i; spin_lock_bh(&net->xfrm.xfrm_state_lock); for (i = 0; i <= net->xfrm.state_hmask; i++) { hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_bydst, net) + i, bydst) xfrm_dev_state_update_stats(x); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); } struct xfrm_state * xfrm_state_lookup(struct net *net, u32 mark, const xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) { struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; rcu_read_lock(); xfrm_hash_ptrs_get(net, &state_ptrs); x = __xfrm_state_lookup(&state_ptrs, mark, daddr, spi, proto, family); rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup); struct xfrm_state * xfrm_state_lookup_byaddr(struct net *net, u32 mark, const xfrm_address_t *daddr, const xfrm_address_t *saddr, u8 proto, unsigned short family) { struct xfrm_hash_state_ptrs state_ptrs; struct xfrm_state *x; rcu_read_lock(); xfrm_hash_ptrs_get(net, &state_ptrs); x = __xfrm_state_lookup_byaddr(&state_ptrs, mark, daddr, saddr, proto, family); rcu_read_unlock(); return x; } EXPORT_SYMBOL(xfrm_state_lookup_byaddr); struct xfrm_state * xfrm_find_acq(struct net *net, const struct xfrm_mark *mark, u8 mode, u32 reqid, u32 if_id, u32 pcpu_num, u8 proto, const xfrm_address_t *daddr, const xfrm_address_t *saddr, int create, unsigned short family) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __find_acq_core(net, mark, family, mode, reqid, if_id, pcpu_num, proto, daddr, saddr, create); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq); #ifdef CONFIG_XFRM_SUB_POLICY #if IS_ENABLED(CONFIG_IPV6) /* distribution counting sort function for xfrm_state and xfrm_tmpl */ static void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int count[XFRM_MAX_DEPTH] = { }; int class[XFRM_MAX_DEPTH]; int i; for (i = 0; i < n; i++) { int c = cmp(src[i]); class[i] = c; count[c]++; } for (i = 2; i < maxclass; i++) count[i] += count[i - 1]; for (i = 0; i < n; i++) { dst[count[class[i] - 1]++] = src[i]; src[i] = NULL; } } /* Rule for xfrm_state: * * rule 1: select IPsec transport except AH * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec transport AH * rule 4: select IPsec tunnel * rule 5: others */ static int __xfrm6_state_sort_cmp(const void *p) { const struct xfrm_state *v = p; switch (v->props.mode) { case XFRM_MODE_TRANSPORT: if (v->id.proto != IPPROTO_AH) return 1; else return 3; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: case XFRM_MODE_IPTFS: return 4; } return 5; } /* Rule for xfrm_tmpl: * * rule 1: select IPsec transport * rule 2: select MIPv6 RO or inbound trigger * rule 3: select IPsec tunnel * rule 4: others */ static int __xfrm6_tmpl_sort_cmp(const void *p) { const struct xfrm_tmpl *v = p; switch (v->mode) { case XFRM_MODE_TRANSPORT: return 1; #if IS_ENABLED(CONFIG_IPV6_MIP6) case XFRM_MODE_ROUTEOPTIMIZATION: case XFRM_MODE_IN_TRIGGER: return 2; #endif case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: case XFRM_MODE_IPTFS: return 3; } return 4; } #else static inline int __xfrm6_state_sort_cmp(const void *p) { return 5; } static inline int __xfrm6_tmpl_sort_cmp(const void *p) { return 4; } static inline void __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(const void *p), int maxclass) { int i; for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* CONFIG_IPV6 */ void xfrm_tmpl_sort(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_tmpl_sort_cmp, 5); else for (i = 0; i < n; i++) dst[i] = src[i]; } void xfrm_state_sort(struct xfrm_state **dst, struct xfrm_state **src, int n, unsigned short family) { int i; if (family == AF_INET6) __xfrm6_sort((void **)dst, (void **)src, n, __xfrm6_state_sort_cmp, 6); else for (i = 0; i < n; i++) dst[i] = src[i]; } #endif /* Silly enough, but I'm lazy to build resolution list */ static struct xfrm_state *__xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num) { unsigned int h = xfrm_seq_hash(net, seq); struct xfrm_state *x; hlist_for_each_entry(x, xfrm_state_deref_prot(net->xfrm.state_byseq, net) + h, byseq) { if (x->km.seq == seq && (mark & x->mark.m) == x->mark.v && x->pcpu_num == pcpu_num && x->km.state == XFRM_STATE_ACQ) { xfrm_state_hold(x); return x; } } return NULL; } struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 mark, u32 seq, u32 pcpu_num) { struct xfrm_state *x; spin_lock_bh(&net->xfrm.xfrm_state_lock); x = __xfrm_find_acq_byseq(net, mark, seq, pcpu_num); spin_unlock_bh(&net->xfrm.xfrm_state_lock); return x; } EXPORT_SYMBOL(xfrm_find_acq_byseq); u32 xfrm_get_acqseq(void) { u32 res; static atomic_t acqseq; do { res = atomic_inc_return(&acqseq); } while (!res); return res; } EXPORT_SYMBOL(xfrm_get_acqseq); int verify_spi_info(u8 proto, u32 min, u32 max, struct netlink_ext_ack *extack) { switch (proto) { case IPPROTO_AH: case IPPROTO_ESP: break; case IPPROTO_COMP: /* IPCOMP spi is 16-bits. */ if (max >= 0x10000) { NL_SET_ERR_MSG(extack, "IPCOMP SPI must be <= 65535"); return -EINVAL; } break; default: NL_SET_ERR_MSG(extack, "Invalid protocol, must be one of AH, ESP, IPCOMP"); return -EINVAL; } if (min > max) { NL_SET_ERR_MSG(extack, "Invalid SPI range: min > max"); return -EINVAL; } return 0; } EXPORT_SYMBOL(verify_spi_info); int xfrm_alloc_spi(struct xfrm_state *x, u32 low, u32 high, struct netlink_ext_ack *extack) { struct net *net = xs_net(x); unsigned int h; struct xfrm_state *x0; int err = -ENOENT; u32 range = high - low + 1; __be32 newspi = 0; spin_lock_bh(&x->lock); if (x->km.state == XFRM_STATE_DEAD) { NL_SET_ERR_MSG(extack, "Target ACQUIRE is in DEAD state"); goto unlock; } err = 0; if (x->id.spi) goto unlock; err = -ENOENT; for (h = 0; h < range; h++) { u32 spi = (low == high) ? low : get_random_u32_inclusive(low, high); if (spi == 0) goto next; newspi = htonl(spi); spin_lock_bh(&net->xfrm.xfrm_state_lock); x0 = xfrm_state_lookup_spi_proto(net, newspi, x->id.proto); if (!x0) { x->id.spi = newspi; h = xfrm_spi_hash(net, &x->id.daddr, newspi, x->id.proto, x->props.family); XFRM_STATE_INSERT(byspi, &x->byspi, xfrm_state_deref_prot(net->xfrm.state_byspi, net) + h, x->xso.type); spin_unlock_bh(&net->xfrm.xfrm_state_lock); err = 0; goto unlock; } spin_unlock_bh(&net->xfrm.xfrm_state_lock); next: if (signal_pending(current)) { err = -ERESTARTSYS; goto unlock; } if (low == high) break; } if (err) NL_SET_ERR_MSG(extack, "No SPI available in the requested range"); unlock: spin_unlock_bh(&x->lock); return err; } EXPORT_SYMBOL(xfrm_alloc_spi); static bool __xfrm_state_filter_match(struct xfrm_state *x, struct xfrm_address_filter *filter) { if (filter) { if ((filter->family == AF_INET || filter->family == AF_INET6) && x->props.family != filter->family) return false; return addr_match(&x->props.saddr, &filter->saddr, filter->splen) && addr_match(&x->id.daddr, &filter->daddr, filter->dplen); } return true; } int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *data) { struct xfrm_state *state; struct xfrm_state_walk *x; int err = 0; if (walk->seq != 0 && list_empty(&walk->all)) return 0; spin_lock_bh(&net->xfrm.xfrm_state_lock); if (list_empty(&walk->all)) x = list_first_entry(&net->xfrm.state_all, struct xfrm_state_walk, all); else x = list_first_entry(&walk->all, struct xfrm_state_walk, all); list_for_each_entry_from(x, &net->xfrm.state_all, all) { if (x->state == XFRM_STATE_DEAD) continue; state = container_of(x, struct xfrm_state, km); if (!xfrm_id_proto_match(state->id.proto, walk->proto)) continue; if (!__xfrm_state_filter_match(state, walk->filter)) continue; err = func(state, walk->seq, data); if (err) { list_move_tail(&walk->all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { err = -ENOENT; goto out; } list_del_init(&walk->all); out: spin_unlock_bh(&net->xfrm.xfrm_state_lock); return err; } EXPORT_SYMBOL(xfrm_state_walk); void xfrm_state_walk_init(struct xfrm_state_walk *walk, u8 proto, struct xfrm_address_filter *filter) { INIT_LIST_HEAD(&walk->all); walk->proto = proto; walk->state = XFRM_STATE_DEAD; walk->seq = 0; walk->filter = filter; } EXPORT_SYMBOL(xfrm_state_walk_init); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net) { kfree(walk->filter); if (list_empty(&walk->all)) return; spin_lock_bh(&net->xfrm.xfrm_state_lock); list_del(&walk->all); spin_unlock_bh(&net->xfrm.xfrm_state_lock); } EXPORT_SYMBOL(xfrm_state_walk_done); static void xfrm_replay_timer_handler(struct timer_list *t) { struct xfrm_state *x = timer_container_of(x, t, rtimer); spin_lock(&x->lock); if (x->km.state == XFRM_STATE_VALID) { if (xfrm_aevent_is_on(xs_net(x))) xfrm_replay_notify(x, XFRM_REPLAY_TIMEOUT); else x->xflags |= XFRM_TIME_DEFER; } spin_unlock(&x->lock); } static LIST_HEAD(xfrm_km_list); void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify_policy) km->notify_policy(xp, dir, c); rcu_read_unlock(); } void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) if (km->notify) km->notify(x, c); rcu_read_unlock(); } EXPORT_SYMBOL(km_policy_notify); EXPORT_SYMBOL(km_state_notify); void km_state_expired(struct xfrm_state *x, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_EXPIRE; km_state_notify(x, &c); } EXPORT_SYMBOL(km_state_expired); /* * We send to all registered managers regardless of failure * We are happy with one success */ int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol) { int err = -EINVAL, acqret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { acqret = km->acquire(x, t, pol); if (!acqret) err = acqret; } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_query); static int __km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int err = -EINVAL; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->new_mapping) err = km->new_mapping(x, ipaddr, sport); if (!err) break; } rcu_read_unlock(); return err; } int km_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport) { int ret = 0; if (x->mapping_maxage) { if ((jiffies / HZ - x->new_mapping) > x->mapping_maxage || x->new_mapping_sport != sport) { x->new_mapping_sport = sport; x->new_mapping = jiffies / HZ; ret = __km_new_mapping(x, ipaddr, sport); } } else { ret = __km_new_mapping(x, ipaddr, sport); } return ret; } EXPORT_SYMBOL(km_new_mapping); void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 portid) { struct km_event c; c.data.hard = hard; c.portid = portid; c.event = XFRM_MSG_POLEXPIRE; km_policy_notify(pol, dir, &c); } EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, const struct xfrm_migrate *m, int num_migrate, const struct xfrm_kmaddress *k, struct net *net, const struct xfrm_encap_tmpl *encap) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->migrate) { ret = km->migrate(sel, dir, type, m, num_migrate, k, net, encap); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_migrate); #endif int km_report(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr) { int err = -EINVAL; int ret; struct xfrm_mgr *km; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->report) { ret = km->report(net, proto, sel, addr); if (!ret) err = ret; } } rcu_read_unlock(); return err; } EXPORT_SYMBOL(km_report); static bool km_is_alive(const struct km_event *c) { struct xfrm_mgr *km; bool is_alive = false; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { if (km->is_alive && km->is_alive(c)) { is_alive = true; break; } } rcu_read_unlock(); return is_alive; } #if IS_ENABLED(CONFIG_XFRM_USER_COMPAT) static DEFINE_SPINLOCK(xfrm_translator_lock); static struct xfrm_translator __rcu *xfrm_translator; struct xfrm_translator *xfrm_get_translator(void) { struct xfrm_translator *xtr; rcu_read_lock(); xtr = rcu_dereference(xfrm_translator); if (unlikely(!xtr)) goto out; if (!try_module_get(xtr->owner)) xtr = NULL; out: rcu_read_unlock(); return xtr; } EXPORT_SYMBOL_GPL(xfrm_get_translator); void xfrm_put_translator(struct xfrm_translator *xtr) { module_put(xtr->owner); } EXPORT_SYMBOL_GPL(xfrm_put_translator); int xfrm_register_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (unlikely(xfrm_translator != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_translator, xtr); spin_unlock_bh(&xfrm_translator_lock); return err; } EXPORT_SYMBOL_GPL(xfrm_register_translator); int xfrm_unregister_translator(struct xfrm_translator *xtr) { int err = 0; spin_lock_bh(&xfrm_translator_lock); if (likely(xfrm_translator != NULL)) { if (rcu_access_pointer(xfrm_translator) != xtr) err = -EINVAL; else RCU_INIT_POINTER(xfrm_translator, NULL); } spin_unlock_bh(&xfrm_translator_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL_GPL(xfrm_unregister_translator); #endif int xfrm_user_policy(struct sock *sk, int optname, sockptr_t optval, int optlen) { int err; u8 *data; struct xfrm_mgr *km; struct xfrm_policy *pol = NULL; if (sockptr_is_null(optval) && !optlen) { xfrm_sk_policy_insert(sk, XFRM_POLICY_IN, NULL); xfrm_sk_policy_insert(sk, XFRM_POLICY_OUT, NULL); sk_dst_reset(sk); return 0; } if (optlen <= 0 || optlen > PAGE_SIZE) return -EMSGSIZE; data = memdup_sockptr(optval, optlen); if (IS_ERR(data)) return PTR_ERR(data); if (IS_ENABLED(CONFIG_COMPAT_FOR_U64_ALIGNMENT) && in_compat_syscall()) { struct xfrm_translator *xtr = xfrm_get_translator(); if (!xtr) { kfree(data); return -EOPNOTSUPP; } err = xtr->xlate_user_policy_sockptr(&data, optlen); xfrm_put_translator(xtr); if (err) { kfree(data); return err; } } err = -EINVAL; rcu_read_lock(); list_for_each_entry_rcu(km, &xfrm_km_list, list) { pol = km->compile_policy(sk, optname, data, optlen, &err); if (err >= 0) break; } rcu_read_unlock(); if (err >= 0) { xfrm_sk_policy_insert(sk, err, pol); xfrm_pol_put(pol); sk_dst_reset(sk); err = 0; } kfree(data); return err; } EXPORT_SYMBOL(xfrm_user_policy); static DEFINE_SPINLOCK(xfrm_km_lock); void xfrm_register_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_add_tail_rcu(&km->list, &xfrm_km_list); spin_unlock_bh(&xfrm_km_lock); } EXPORT_SYMBOL(xfrm_register_km); void xfrm_unregister_km(struct xfrm_mgr *km) { spin_lock_bh(&xfrm_km_lock); list_del_rcu(&km->list); spin_unlock_bh(&xfrm_km_lock); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_unregister_km); int xfrm_state_register_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0; if (WARN_ON(afinfo->family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (unlikely(xfrm_state_afinfo[afinfo->family] != NULL)) err = -EEXIST; else rcu_assign_pointer(xfrm_state_afinfo[afinfo->family], afinfo); spin_unlock_bh(&xfrm_state_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_state_register_afinfo); int xfrm_state_unregister_afinfo(struct xfrm_state_afinfo *afinfo) { int err = 0, family = afinfo->family; if (WARN_ON(family >= NPROTO)) return -EAFNOSUPPORT; spin_lock_bh(&xfrm_state_afinfo_lock); if (likely(xfrm_state_afinfo[afinfo->family] != NULL)) { if (rcu_access_pointer(xfrm_state_afinfo[family]) != afinfo) err = -EINVAL; else RCU_INIT_POINTER(xfrm_state_afinfo[afinfo->family], NULL); } spin_unlock_bh(&xfrm_state_afinfo_lock); synchronize_rcu(); return err; } EXPORT_SYMBOL(xfrm_state_unregister_afinfo); struct xfrm_state_afinfo *xfrm_state_afinfo_get_rcu(unsigned int family) { if (unlikely(family >= NPROTO)) return NULL; return rcu_dereference(xfrm_state_afinfo[family]); } EXPORT_SYMBOL_GPL(xfrm_state_afinfo_get_rcu); struct xfrm_state_afinfo *xfrm_state_get_afinfo(unsigned int family) { struct xfrm_state_afinfo *afinfo; if (unlikely(family >= NPROTO)) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_state_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } void xfrm_flush_gc(void) { flush_work(&xfrm_state_gc_work); } EXPORT_SYMBOL(xfrm_flush_gc); static void xfrm_state_delete_tunnel(struct xfrm_state *x) { if (x->tunnel) { struct xfrm_state *t = x->tunnel; if (atomic_dec_return(&t->tunnel_users) == 1) xfrm_state_delete(t); xfrm_state_put(t); x->tunnel = NULL; } } u32 xfrm_state_mtu(struct xfrm_state *x, int mtu) { const struct xfrm_type *type = READ_ONCE(x->type); struct crypto_aead *aead; u32 blksize, net_adj = 0; u32 overhead, payload_mtu; if (x->km.state != XFRM_STATE_VALID || !type || type->proto != IPPROTO_ESP) { if (mtu <= x->props.header_len) return 1; return mtu - x->props.header_len; } aead = x->data; blksize = ALIGN(crypto_aead_blocksize(aead), 4); switch (x->props.mode) { case XFRM_MODE_TRANSPORT: case XFRM_MODE_BEET: if (x->props.family == AF_INET) net_adj = sizeof(struct iphdr); else if (x->props.family == AF_INET6) net_adj = sizeof(struct ipv6hdr); break; case XFRM_MODE_TUNNEL: break; default: if (x->mode_cbs && x->mode_cbs->get_inner_mtu) return x->mode_cbs->get_inner_mtu(x, mtu); WARN_ON_ONCE(1); break; } overhead = x->props.header_len + crypto_aead_authsize(aead) + net_adj; if (mtu <= overhead) return 1; payload_mtu = mtu - overhead; payload_mtu &= ~(blksize - 1); if (payload_mtu <= 2) return 1; return payload_mtu + net_adj - 2; } EXPORT_SYMBOL_GPL(xfrm_state_mtu); int __xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { const struct xfrm_mode *inner_mode; const struct xfrm_mode *outer_mode; int family = x->props.family; int err; if (family == AF_INET && (!x->dir || x->dir == XFRM_SA_DIR_OUT) && READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; if (x->sel.family != AF_UNSPEC) { inner_mode = xfrm_get_mode(x->props.mode, x->sel.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } if (!(inner_mode->flags & XFRM_MODE_FLAG_TUNNEL) && family != x->sel.family) { NL_SET_ERR_MSG(extack, "Only tunnel modes can accommodate a change of family"); goto error; } x->inner_mode = *inner_mode; } else { const struct xfrm_mode *inner_mode_iaf; int iafamily = AF_INET; inner_mode = xfrm_get_mode(x->props.mode, x->props.family); if (inner_mode == NULL) { NL_SET_ERR_MSG(extack, "Requested mode not found"); goto error; } x->inner_mode = *inner_mode; if (x->props.family == AF_INET) iafamily = AF_INET6; inner_mode_iaf = xfrm_get_mode(x->props.mode, iafamily); if (inner_mode_iaf) { if (inner_mode_iaf->flags & XFRM_MODE_FLAG_TUNNEL) x->inner_mode_iaf = *inner_mode_iaf; } } x->type = xfrm_get_type(x->id.proto, family); if (x->type == NULL) { NL_SET_ERR_MSG(extack, "Requested type not found"); goto error; } err = x->type->init_state(x, extack); if (err) goto error; outer_mode = xfrm_get_mode(x->props.mode, family); if (!outer_mode) { NL_SET_ERR_MSG(extack, "Requested mode not found"); err = -EPROTONOSUPPORT; goto error; } x->outer_mode = *outer_mode; if (x->nat_keepalive_interval) { if (x->dir != XFRM_SA_DIR_OUT) { NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for outbound SAs"); err = -EINVAL; goto error; } if (!x->encap || x->encap->encap_type != UDP_ENCAP_ESPINUDP) { NL_SET_ERR_MSG(extack, "NAT keepalive is only supported for UDP encapsulation"); err = -EINVAL; goto error; } } x->mode_cbs = xfrm_get_mode_cbs(x->props.mode); if (x->mode_cbs) { if (x->mode_cbs->init_state) err = x->mode_cbs->init_state(x); module_put(x->mode_cbs->owner); if (err && !x->mode_data) x->mode_cbs = NULL; } error: return err; } EXPORT_SYMBOL(__xfrm_init_state); int xfrm_init_state(struct xfrm_state *x, struct netlink_ext_ack *extack) { int err; err = __xfrm_init_state(x, extack); if (err) return err; err = xfrm_init_replay(x, NULL); if (err) return err; x->km.state = XFRM_STATE_VALID; return 0; } EXPORT_SYMBOL(xfrm_init_state); int __net_init xfrm_state_init(struct net *net) { struct hlist_head *ndst, *nsrc, *nspi, *nseq; unsigned int sz; if (net_eq(net, &init_net)) xfrm_state_cache = KMEM_CACHE(xfrm_state, SLAB_HWCACHE_ALIGN | SLAB_PANIC); INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; ndst = xfrm_hash_alloc(sz); if (!ndst) goto out_bydst; rcu_assign_pointer(net->xfrm.state_bydst, ndst); nsrc = xfrm_hash_alloc(sz); if (!nsrc) goto out_bysrc; rcu_assign_pointer(net->xfrm.state_bysrc, nsrc); nspi = xfrm_hash_alloc(sz); if (!nspi) goto out_byspi; rcu_assign_pointer(net->xfrm.state_byspi, nspi); nseq = xfrm_hash_alloc(sz); if (!nseq) goto out_byseq; rcu_assign_pointer(net->xfrm.state_byseq, nseq); net->xfrm.state_cache_input = alloc_percpu(struct hlist_head); if (!net->xfrm.state_cache_input) goto out_state_cache_input; net->xfrm.state_hmask = ((sz / sizeof(struct hlist_head)) - 1); net->xfrm.state_num = 0; INIT_WORK(&net->xfrm.state_hash_work, xfrm_hash_resize); spin_lock_init(&net->xfrm.xfrm_state_lock); seqcount_spinlock_init(&net->xfrm.xfrm_state_hash_generation, &net->xfrm.xfrm_state_lock); return 0; out_state_cache_input: xfrm_hash_free(nseq, sz); out_byseq: xfrm_hash_free(nspi, sz); out_byspi: xfrm_hash_free(nsrc, sz); out_bysrc: xfrm_hash_free(ndst, sz); out_bydst: return -ENOMEM; } #define xfrm_state_deref_netexit(table) \ rcu_dereference_protected((table), true /* netns is going away */) void xfrm_state_fini(struct net *net) { unsigned int sz; int i; flush_work(&net->xfrm.state_hash_work); xfrm_state_flush(net, 0, false); flush_work(&xfrm_state_gc_work); WARN_ON(!list_empty(&net->xfrm.state_all)); for (i = 0; i <= net->xfrm.state_hmask; i++) { WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byseq) + i)); WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_byspi) + i)); WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bysrc) + i)); WARN_ON(!hlist_empty(xfrm_state_deref_netexit(net->xfrm.state_bydst) + i)); } sz = (net->xfrm.state_hmask + 1) * sizeof(struct hlist_head); xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byseq), sz); xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_byspi), sz); xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bysrc), sz); xfrm_hash_free(xfrm_state_deref_netexit(net->xfrm.state_bydst), sz); free_percpu(net->xfrm.state_cache_input); } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_helper_sainfo(struct xfrm_state *x, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = x->security; u32 spi = ntohl(x->id.spi); if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (x->props.family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &x->props.saddr.a4, &x->id.daddr.a4); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6 dst=%pI6", x->props.saddr.a6, x->id.daddr.a6); break; } audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); } static void xfrm_audit_helper_pktinfo(struct sk_buff *skb, u16 family, struct audit_buffer *audit_buf) { const struct iphdr *iph4; const struct ipv6hdr *iph6; switch (family) { case AF_INET: iph4 = ip_hdr(skb); audit_log_format(audit_buf, " src=%pI4 dst=%pI4", &iph4->saddr, &iph4->daddr); break; case AF_INET6: iph6 = ipv6_hdr(skb); audit_log_format(audit_buf, " src=%pI6 dst=%pI6 flowlbl=0x%x%02x%02x", &iph6->saddr, &iph6->daddr, iph6->flow_lbl[0] & 0x0f, iph6->flow_lbl[1], iph6->flow_lbl[2]); break; } } void xfrm_audit_state_add(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_add); void xfrm_audit_state_delete(struct xfrm_state *x, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SAD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); xfrm_audit_helper_sainfo(x, audit_buf); audit_log_format(audit_buf, " res=%u", result); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_delete); void xfrm_audit_state_replay_overflow(struct xfrm_state *x, struct sk_buff *skb) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replay-overflow"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); /* don't record the sequence number because it's inherent in this kind * of audit message */ spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x)", spi, spi); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay_overflow); void xfrm_audit_state_replay(struct xfrm_state *x, struct sk_buff *skb, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-replayed-pkt"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); spi = ntohl(x->id.spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_replay); void xfrm_audit_state_notfound_simple(struct sk_buff *skb, u16 family) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound_simple); void xfrm_audit_state_notfound(struct sk_buff *skb, u16 family, __be32 net_spi, __be32 net_seq) { struct audit_buffer *audit_buf; u32 spi; audit_buf = xfrm_audit_start("SA-notfound"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, family, audit_buf); spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_notfound); void xfrm_audit_state_icvfail(struct xfrm_state *x, struct sk_buff *skb, u8 proto) { struct audit_buffer *audit_buf; __be32 net_spi; __be32 net_seq; audit_buf = xfrm_audit_start("SA-icv-failure"); if (audit_buf == NULL) return; xfrm_audit_helper_pktinfo(skb, x->props.family, audit_buf); if (xfrm_parse_spi(skb, proto, &net_spi, &net_seq) == 0) { u32 spi = ntohl(net_spi); audit_log_format(audit_buf, " spi=%u(0x%x) seqno=%u", spi, spi, ntohl(net_seq)); } audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_state_icvfail); #endif /* CONFIG_AUDITSYSCALL */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Multipath TCP * * Copyright (c) 2025, Matthieu Baerts. */ #define pr_fmt(fmt) "MPTCP: " fmt #include <net/netns/generic.h> #include "protocol.h" #include "mib.h" #include "mptcp_pm_gen.h" static int pm_nl_pernet_id; struct pm_nl_pernet { /* protects pernet updates */ spinlock_t lock; struct list_head endp_list; u8 endpoints; u8 endp_signal_max; u8 endp_subflow_max; u8 endp_laminar_max; u8 endp_fullmesh_max; u8 limit_add_addr_accepted; u8 limit_extra_subflows; u8 next_id; DECLARE_BITMAP(id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); }; #define MPTCP_PM_ADDR_MAX 8 #define MPTCP_PM_SUBFLOWS_MAX 64 static struct pm_nl_pernet *pm_nl_get_pernet(const struct net *net) { return net_generic(net, pm_nl_pernet_id); } static struct pm_nl_pernet * pm_nl_get_pernet_from_msk(const struct mptcp_sock *msk) { return pm_nl_get_pernet(sock_net((struct sock *)msk)); } static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info) { return pm_nl_get_pernet(genl_info_net(info)); } u8 mptcp_pm_get_endp_signal_max(const struct mptcp_sock *msk) { const struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->endp_signal_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_signal_max); u8 mptcp_pm_get_endp_subflow_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->endp_subflow_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_subflow_max); u8 mptcp_pm_get_endp_laminar_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->endp_laminar_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_laminar_max); u8 mptcp_pm_get_endp_fullmesh_max(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->endp_fullmesh_max); } EXPORT_SYMBOL_GPL(mptcp_pm_get_endp_fullmesh_max); u8 mptcp_pm_get_limit_add_addr_accepted(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->limit_add_addr_accepted); } EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_add_addr_accepted); u8 mptcp_pm_get_limit_extra_subflows(const struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); return READ_ONCE(pernet->limit_extra_subflows); } EXPORT_SYMBOL_GPL(mptcp_pm_get_limit_extra_subflows); static bool has_subflow_daddr(const struct mptcp_sock *msk, const struct mptcp_addr_info *daddr) { struct mptcp_subflow_context *subflow; struct mptcp_addr_info cur; mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if (!((1 << inet_sk_state_load(ssk)) & (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV))) continue; mptcp_remote_address((struct sock_common *)ssk, &cur); if (mptcp_addresses_equal(&cur, daddr, daddr->port)) return true; } return false; } static bool select_local_address(const struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, struct mptcp_pm_local *new_local) { struct mptcp_pm_addr_entry *entry; bool found = false; msk_owned_by_me(msk); rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->endp_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) continue; if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; new_local->addr = entry->addr; new_local->flags = entry->flags; new_local->ifindex = entry->ifindex; found = true; break; } rcu_read_unlock(); return found; } static bool select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk, struct mptcp_pm_local *new_local) { struct mptcp_pm_addr_entry *entry; bool found = false; rcu_read_lock(); /* do not keep any additional per socket state, just signal * the address list in order. * Note: removal from the local address list during the msk life-cycle * can lead to additional addresses not being announced. */ list_for_each_entry_rcu(entry, &pernet->endp_list, list) { if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap)) continue; if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) continue; new_local->addr = entry->addr; new_local->flags = entry->flags; new_local->ifindex = entry->ifindex; found = true; break; } rcu_read_unlock(); return found; } static unsigned int fill_remote_addr(struct mptcp_sock *msk, struct mptcp_addr_info *local, struct mptcp_addr_info *addrs) { bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); struct mptcp_addr_info remote = { 0 }; struct sock *sk = (struct sock *)msk; if (deny_id0) return 0; mptcp_remote_address((struct sock_common *)sk, &remote); if (!mptcp_pm_addr_families_match(sk, local, &remote)) return 0; msk->pm.extra_subflows++; *addrs = remote; return 1; } static unsigned int fill_remote_addresses_fullmesh(struct mptcp_sock *msk, struct mptcp_addr_info *local, struct mptcp_addr_info *addrs, int addrs_size) { u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk); bool deny_id0 = READ_ONCE(msk->pm.remote_deny_join_id0); DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); struct sock *sk = (struct sock *)msk, *ssk; struct mptcp_subflow_context *subflow; int i = 0; /* Forbid creation of new subflows matching existing ones, possibly * already created by incoming ADD_ADDR */ bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); mptcp_for_each_subflow(msk, subflow) if (READ_ONCE(subflow->local_id) == local->id) __set_bit(subflow->remote_id, unavail_id); mptcp_for_each_subflow(msk, subflow) { ssk = mptcp_subflow_tcp_sock(subflow); mptcp_remote_address((struct sock_common *)ssk, &addrs[i]); addrs[i].id = READ_ONCE(subflow->remote_id); if (deny_id0 && !addrs[i].id) continue; if (test_bit(addrs[i].id, unavail_id)) continue; if (!mptcp_pm_addr_families_match(sk, local, &addrs[i])) continue; /* forbid creating multiple address towards this id */ __set_bit(addrs[i].id, unavail_id); msk->pm.extra_subflows++; i++; if (msk->pm.extra_subflows >= limit_extra_subflows || i == addrs_size) break; } return i; } /* Fill all the remote addresses into the array addrs[], * and return the array size. */ static unsigned int fill_remote_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *local, bool fullmesh, struct mptcp_addr_info *addrs, int addrs_size) { /* Non-fullmesh: fill in the single entry corresponding to the primary * MPC subflow remote address, and return 1, corresponding to 1 entry. */ if (!fullmesh) return fill_remote_addr(msk, local, addrs); /* Fullmesh endpoint: fill all possible remote addresses */ return fill_remote_addresses_fullmesh(msk, local, addrs, addrs_size); } static struct mptcp_pm_addr_entry * __lookup_addr_by_id(struct pm_nl_pernet *pernet, unsigned int id) { struct mptcp_pm_addr_entry *entry; list_for_each_entry_rcu(entry, &pernet->endp_list, list, lockdep_is_held(&pernet->lock)) { if (entry->addr.id == id) return entry; } return NULL; } static struct mptcp_pm_addr_entry * __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info) { struct mptcp_pm_addr_entry *entry; list_for_each_entry_rcu(entry, &pernet->endp_list, list, lockdep_is_held(&pernet->lock)) { if (mptcp_addresses_equal(&entry->addr, info, entry->addr.port)) return entry; } return NULL; } static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk, const struct mptcp_addr_info *addr) { return msk->mpc_endpoint_id == addr->id ? 0 : addr->id; } /* Set mpc_endpoint_id, and send MP_PRIO for ID0 if needed */ static void mptcp_mpc_endpoint_setup(struct mptcp_sock *msk) { struct mptcp_subflow_context *subflow; struct mptcp_pm_addr_entry *entry; struct mptcp_addr_info mpc_addr; struct pm_nl_pernet *pernet; bool backup = false; /* do lazy endpoint usage accounting for the MPC subflows */ if (likely(msk->pm.status & BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED)) || !msk->first) return; subflow = mptcp_subflow_ctx(msk->first); pernet = pm_nl_get_pernet_from_msk(msk); mptcp_local_address((struct sock_common *)msk->first, &mpc_addr); rcu_read_lock(); entry = __lookup_addr(pernet, &mpc_addr); if (entry) { __clear_bit(entry->addr.id, msk->pm.id_avail_bitmap); msk->mpc_endpoint_id = entry->addr.id; backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); } rcu_read_unlock(); /* Send MP_PRIO */ if (backup) mptcp_pm_send_ack(msk, subflow, true, backup); msk->pm.status |= BIT(MPTCP_PM_MPC_ENDPOINT_ACCOUNTED); } static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk) { u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk); struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); u8 endp_subflow_max = mptcp_pm_get_endp_subflow_max(msk); u8 endp_signal_max = mptcp_pm_get_endp_signal_max(msk); struct sock *sk = (struct sock *)msk; bool signal_and_subflow = false; struct mptcp_pm_local local; mptcp_mpc_endpoint_setup(msk); if (!mptcp_is_fully_established(sk)) return; pr_debug("local %d:%d signal %d:%d subflows %d:%d\n", msk->pm.local_addr_used, endp_subflow_max, msk->pm.add_addr_signaled, endp_signal_max, msk->pm.extra_subflows, limit_extra_subflows); /* check first for announce */ if (msk->pm.add_addr_signaled < endp_signal_max) { u8 endp_id; /* due to racing events on both ends we can reach here while * previous add address is still running: if we invoke now * mptcp_pm_announce_addr(), that will fail and the * corresponding id will be marked as used. * Instead let the PM machinery reschedule us when the * current address announce will be completed. */ if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL)) return; if (!select_signal_address(pernet, msk, &local)) goto subflow; /* Special case for ID0: set the correct ID */ endp_id = local.addr.id; if (endp_id == msk->mpc_endpoint_id) local.addr.id = 0; /* If the alloc fails, we are on memory pressure, not worth * continuing, and trying to create subflows. */ if (!mptcp_pm_announced_alloc(msk, &local.addr)) return; __clear_bit(endp_id, msk->pm.id_avail_bitmap); msk->pm.add_addr_signaled++; mptcp_pm_announce_addr(msk, &local.addr, false); mptcp_pm_addr_send_ack(msk); if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) signal_and_subflow = true; } subflow: /* No need to try establishing subflows to remote id0 if not allowed */ if (mptcp_pm_add_addr_c_flag_case(msk)) goto exit; /* check if should create a new subflow */ while (msk->pm.local_addr_used < endp_subflow_max && msk->pm.extra_subflows < limit_extra_subflows) { struct mptcp_addr_info addrs[MPTCP_PM_ADDR_MAX]; bool fullmesh; int i, nr; if (signal_and_subflow) signal_and_subflow = false; else if (!select_local_address(pernet, msk, &local)) break; fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH); __clear_bit(local.addr.id, msk->pm.id_avail_bitmap); /* Special case for ID0: set the correct ID */ if (local.addr.id == msk->mpc_endpoint_id) local.addr.id = 0; else /* local_addr_used is not decr for ID 0 */ msk->pm.local_addr_used++; nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs, ARRAY_SIZE(addrs)); if (nr == 0) continue; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) __mptcp_subflow_connect(sk, &local, &addrs[i]); spin_lock_bh(&msk->pm.lock); } exit: /* If an endpoint has both the signal and subflow flags, but it is not * possible to create subflows -- the 'while' loop body above never * executed -- then still mark the endp as used, which is somehow the * case. This avoids issues later when removing the endpoint and calling * __mark_subflow_endp_available(), which expects the increment here. */ if (signal_and_subflow && local.addr.id != msk->mpc_endpoint_id) msk->pm.local_addr_used++; mptcp_pm_nl_check_work_pending(msk); } static void mptcp_pm_nl_fully_established(struct mptcp_sock *msk) { mptcp_pm_create_subflow_or_signal_addr(msk); } static void mptcp_pm_nl_subflow_established(struct mptcp_sock *msk) { mptcp_pm_create_subflow_or_signal_addr(msk); } static unsigned int fill_local_addresses_vec_fullmesh(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *locals, int locals_size, bool c_flag_case) { u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk); struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; struct mptcp_pm_local *local; int i = 0; rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->endp_list, list) { bool is_id0; if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH)) continue; if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote)) continue; local = &locals[i]; local->addr = entry->addr; local->flags = entry->flags; local->ifindex = entry->ifindex; is_id0 = local->addr.id == msk->mpc_endpoint_id; if (c_flag_case && (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)) { __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); if (!is_id0) msk->pm.local_addr_used++; } /* Special case for ID0: set the correct ID */ if (is_id0) local->addr.id = 0; msk->pm.extra_subflows++; i++; if (msk->pm.extra_subflows >= limit_extra_subflows || i == locals_size) break; } rcu_read_unlock(); return i; } static unsigned int fill_local_laminar_endp(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *locals) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); DECLARE_BITMAP(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); struct mptcp_subflow_context *subflow; struct sock *sk = (struct sock *)msk; struct mptcp_pm_addr_entry *entry; struct mptcp_pm_local *local; int found = 0; /* Forbid creation of new subflows matching existing ones, possibly * already created by 'subflow' endpoints */ bitmap_zero(unavail_id, MPTCP_PM_MAX_ADDR_ID + 1); mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); if ((1 << inet_sk_state_load(ssk)) & (TCPF_FIN_WAIT1 | TCPF_FIN_WAIT2 | TCPF_CLOSING | TCPF_CLOSE)) continue; __set_bit(subflow_get_local_id(subflow), unavail_id); } rcu_read_lock(); list_for_each_entry_rcu(entry, &pernet->endp_list, list) { if (!(entry->flags & MPTCP_PM_ADDR_FLAG_LAMINAR)) continue; if (!mptcp_pm_addr_families_match(sk, &entry->addr, remote)) continue; if (test_bit(mptcp_endp_get_local_id(msk, &entry->addr), unavail_id)) continue; local = &locals[0]; local->addr = entry->addr; local->flags = entry->flags; local->ifindex = entry->ifindex; if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); if (local->addr.id != msk->mpc_endpoint_id) msk->pm.local_addr_used++; } msk->pm.extra_subflows++; found = 1; break; } rcu_read_unlock(); return found; } static unsigned int fill_local_addresses_vec_c_flag(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *locals, int locals_size) { u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk); struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); u8 endp_subflow_max = mptcp_pm_get_endp_subflow_max(msk); struct sock *sk = (struct sock *)msk; struct mptcp_pm_local *local; int i = 0; while (msk->pm.local_addr_used < endp_subflow_max) { local = &locals[i]; if (!select_local_address(pernet, msk, local)) break; __clear_bit(local->addr.id, msk->pm.id_avail_bitmap); if (!mptcp_pm_addr_families_match(sk, &local->addr, remote)) continue; if (local->addr.id == msk->mpc_endpoint_id) continue; msk->pm.local_addr_used++; msk->pm.extra_subflows++; i++; if (msk->pm.extra_subflows >= limit_extra_subflows || i == locals_size) break; } return i; } static unsigned int fill_local_address_any(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *local) { struct sock *sk = (struct sock *)msk; memset(local, 0, sizeof(*local)); local->addr.family = #if IS_ENABLED(CONFIG_MPTCP_IPV6) remote->family == AF_INET6 && ipv6_addr_v4mapped(&remote->addr6) ? AF_INET : #endif remote->family; if (!mptcp_pm_addr_families_match(sk, &local->addr, remote)) return 0; msk->pm.extra_subflows++; return 1; } /* Fill all the local addresses into the array addrs[], * and return the array size. */ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk, struct mptcp_addr_info *remote, struct mptcp_pm_local *locals, int locals_size) { bool c_flag_case = remote->id && mptcp_pm_add_addr_c_flag_case(msk); /* If there is at least one MPTCP endpoint with a fullmesh flag */ if (mptcp_pm_get_endp_fullmesh_max(msk)) return fill_local_addresses_vec_fullmesh(msk, remote, locals, locals_size, c_flag_case); /* If there is at least one MPTCP endpoint with a laminar flag */ if (mptcp_pm_get_endp_laminar_max(msk)) return fill_local_laminar_endp(msk, remote, locals); /* Special case: peer sets the C flag, accept one ADD_ADDR if default * limits are used -- accepting no ADD_ADDR -- and use subflow endpoints */ if (c_flag_case) return fill_local_addresses_vec_c_flag(msk, remote, locals, locals_size); /* No special case: fill in the single 'IPADDRANY' local address */ return fill_local_address_any(msk, remote, &locals[0]); } static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk) { u8 limit_add_addr_accepted = mptcp_pm_get_limit_add_addr_accepted(msk); u8 limit_extra_subflows = mptcp_pm_get_limit_extra_subflows(msk); struct mptcp_pm_local locals[MPTCP_PM_ADDR_MAX]; struct sock *sk = (struct sock *)msk; struct mptcp_addr_info remote; bool sf_created = false; int i, nr; pr_debug("accepted %d:%d remote family %d\n", msk->pm.add_addr_accepted, limit_add_addr_accepted, msk->pm.remote.family); remote = msk->pm.remote; mptcp_pm_announce_addr(msk, &remote, true); mptcp_pm_addr_send_ack(msk); mptcp_mpc_endpoint_setup(msk); if (has_subflow_daddr(msk, &remote)) return; /* pick id 0 port, if none is provided the remote address */ if (!remote.port) remote.port = sk->sk_dport; /* connect to the specified remote address, using whatever * local address the routing configuration will pick. */ nr = fill_local_addresses_vec(msk, &remote, locals, ARRAY_SIZE(locals)); if (nr == 0) return; spin_unlock_bh(&msk->pm.lock); for (i = 0; i < nr; i++) if (__mptcp_subflow_connect(sk, &locals[i], &remote) == 0) sf_created = true; spin_lock_bh(&msk->pm.lock); if (sf_created) { /* add_addr_accepted is not decr for ID 0 */ if (remote.id) msk->pm.add_addr_accepted++; if (msk->pm.add_addr_accepted >= limit_add_addr_accepted || msk->pm.extra_subflows >= limit_extra_subflows) WRITE_ONCE(msk->pm.accept_addr, false); } } void mptcp_pm_nl_rm_addr(struct mptcp_sock *msk, u8 rm_id) { if (rm_id && !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) { u8 limit_add_addr_accepted = mptcp_pm_get_limit_add_addr_accepted(msk); /* Note: if the subflow has been closed before, this * add_addr_accepted counter will not be decremented. */ if (--msk->pm.add_addr_accepted < limit_add_addr_accepted) WRITE_ONCE(msk->pm.accept_addr, true); } } static bool address_use_port(struct mptcp_pm_addr_entry *entry) { return (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_SUBFLOW)) == MPTCP_PM_ADDR_FLAG_SIGNAL; } /* caller must ensure the RCU grace period is already elapsed */ static void __mptcp_pm_release_addr_entry(struct mptcp_pm_addr_entry *entry) { if (entry->lsk) sock_release(entry->lsk); kfree(entry); } static int mptcp_pm_nl_append_new_local_addr(struct pm_nl_pernet *pernet, struct mptcp_pm_addr_entry *entry, bool replace) { struct mptcp_pm_addr_entry *cur, *del_entry = NULL; int ret = -EINVAL; u8 addr_max; spin_lock_bh(&pernet->lock); /* to keep the code simple, don't do IDR-like allocation for address ID, * just bail when we exceed limits */ if (pernet->next_id == MPTCP_PM_MAX_ADDR_ID) pernet->next_id = 1; if (pernet->endpoints == MPTCP_PM_MAX_ADDR_ID) { ret = -ERANGE; goto out; } if (test_bit(entry->addr.id, pernet->id_bitmap)) { ret = -EBUSY; goto out; } /* do not insert duplicate address, differentiate on port only * singled addresses */ if (!address_use_port(entry)) entry->addr.port = 0; list_for_each_entry(cur, &pernet->endp_list, list) { if (mptcp_addresses_equal(&cur->addr, &entry->addr, cur->addr.port || entry->addr.port)) { /* allow replacing the exiting endpoint only if such * endpoint is an implicit one and the user-space * did not provide an endpoint id */ if (!(cur->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)) { ret = -EEXIST; goto out; } if (entry->addr.id) goto out; /* allow callers that only need to look up the local * addr's id to skip replacement. This allows them to * avoid calling synchronize_rcu in the packet recv * path. */ if (!replace) { kfree(entry); ret = cur->addr.id; goto out; } pernet->endpoints--; entry->addr.id = cur->addr.id; list_del_rcu(&cur->list); del_entry = cur; break; } } if (!entry->addr.id) { find_next: entry->addr.id = find_next_zero_bit(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, pernet->next_id); if (!entry->addr.id && pernet->next_id != 1) { pernet->next_id = 1; goto find_next; } } if (!entry->addr.id) goto out; __set_bit(entry->addr.id, pernet->id_bitmap); if (entry->addr.id > pernet->next_id) pernet->next_id = entry->addr.id; if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { addr_max = pernet->endp_signal_max; WRITE_ONCE(pernet->endp_signal_max, addr_max + 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { addr_max = pernet->endp_subflow_max; WRITE_ONCE(pernet->endp_subflow_max, addr_max + 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_LAMINAR) { addr_max = pernet->endp_laminar_max; WRITE_ONCE(pernet->endp_laminar_max, addr_max + 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { addr_max = pernet->endp_fullmesh_max; WRITE_ONCE(pernet->endp_fullmesh_max, addr_max + 1); } pernet->endpoints++; if (!entry->addr.port) list_add_tail_rcu(&entry->list, &pernet->endp_list); else list_add_rcu(&entry->list, &pernet->endp_list); ret = entry->addr.id; out: spin_unlock_bh(&pernet->lock); /* just replaced an existing entry, free it */ if (del_entry) { synchronize_rcu(); __mptcp_pm_release_addr_entry(del_entry); } return ret; } static struct lock_class_key mptcp_slock_keys[2]; static struct lock_class_key mptcp_keys[2]; static int mptcp_pm_nl_create_listen_socket(struct sock *sk, struct mptcp_pm_addr_entry *entry) { bool is_ipv6 = entry->addr.family == AF_INET6; int addrlen = sizeof(struct sockaddr_in); struct sockaddr_storage addr; struct sock *newsk, *ssk; int backlog = 1024; int err; err = sock_create_kern(sock_net(sk), entry->addr.family, SOCK_STREAM, IPPROTO_MPTCP, &entry->lsk); if (err) return err; newsk = entry->lsk->sk; if (!newsk) return -EINVAL; /* The subflow socket lock is acquired in a nested to the msk one * in several places, even by the TCP stack, and this msk is a kernel * socket: lockdep complains. Instead of propagating the _nested * modifiers in several places, re-init the lock class for the msk * socket to an mptcp specific one. */ sock_lock_init_class_and_name(newsk, is_ipv6 ? "mlock-AF_INET6" : "mlock-AF_INET", &mptcp_slock_keys[is_ipv6], is_ipv6 ? "msk_lock-AF_INET6" : "msk_lock-AF_INET", &mptcp_keys[is_ipv6]); lock_sock(newsk); ssk = __mptcp_nmpc_sk(mptcp_sk(newsk)); release_sock(newsk); if (IS_ERR(ssk)) return PTR_ERR(ssk); mptcp_info2sockaddr(&entry->addr, &addr, entry->addr.family); #if IS_ENABLED(CONFIG_MPTCP_IPV6) if (entry->addr.family == AF_INET6) addrlen = sizeof(struct sockaddr_in6); #endif if (ssk->sk_family == AF_INET) err = inet_bind_sk(ssk, (struct sockaddr_unsized *)&addr, addrlen); #if IS_ENABLED(CONFIG_MPTCP_IPV6) else if (ssk->sk_family == AF_INET6) err = inet6_bind_sk(ssk, (struct sockaddr_unsized *)&addr, addrlen); #endif if (err) return err; /* We don't use mptcp_set_state() here because it needs to be called * under the msk socket lock. For the moment, that will not bring * anything more than only calling inet_sk_state_store(), because the * old status is known (TCP_CLOSE). */ inet_sk_state_store(newsk, TCP_LISTEN); lock_sock(ssk); WRITE_ONCE(mptcp_subflow_ctx(ssk)->pm_listener, true); err = __inet_listen_sk(ssk, backlog); if (!err) mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CREATED); release_sock(ssk); return err; } int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_pm_addr_entry *skc) { struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; int ret; pernet = pm_nl_get_pernet_from_msk(msk); rcu_read_lock(); entry = __lookup_addr(pernet, &skc->addr); ret = entry ? entry->addr.id : -1; rcu_read_unlock(); if (ret >= 0) return ret; /* address not found, add to local list */ entry = kmemdup(skc, sizeof(*skc), GFP_ATOMIC); if (!entry) return -ENOMEM; entry->addr.port = 0; ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, false); if (ret < 0) kfree(entry); return ret; } bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); struct mptcp_pm_addr_entry *entry; bool backup; rcu_read_lock(); entry = __lookup_addr(pernet, skc); backup = entry && !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP); rcu_read_unlock(); return backup; } static int mptcp_nl_add_subflow_or_signal_addr(struct net *net, struct mptcp_addr_info *addr) { struct mptcp_sock *msk; long s_slot = 0, s_num = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; struct mptcp_addr_info mpc_addr; if (!READ_ONCE(msk->fully_established) || mptcp_pm_is_userspace(msk)) goto next; /* if the endp linked to the init sf is re-added with a != ID */ mptcp_local_address((struct sock_common *)msk, &mpc_addr); lock_sock(sk); spin_lock_bh(&msk->pm.lock); if (mptcp_addresses_equal(addr, &mpc_addr, addr->port)) msk->mpc_endpoint_id = addr->id; mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); release_sock(sk); next: sock_put(sk); cond_resched(); } return 0; } /* Add an MPTCP endpoint */ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct nlattr *attr; int ret; if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR)) return -EINVAL; attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; ret = mptcp_pm_parse_entry(attr, info, true, &addr); if (ret < 0) return ret; if (addr.addr.port && !address_use_port(&addr)) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "flags must have signal and not subflow when using port"); return -EINVAL; } if (addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL && addr.flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "flags mustn't have both signal and fullmesh"); return -EINVAL; } if (addr.flags & MPTCP_PM_ADDR_FLAG_IMPLICIT) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "can't create IMPLICIT endpoint"); return -EINVAL; } entry = kmemdup(&addr, sizeof(addr), GFP_KERNEL_ACCOUNT); if (!entry) { GENL_SET_ERR_MSG(info, "can't allocate addr"); return -ENOMEM; } if (entry->addr.port) { ret = mptcp_pm_nl_create_listen_socket(skb->sk, entry); if (ret) { GENL_SET_ERR_MSG_FMT(info, "create listen socket error: %d", ret); goto out_free; } } ret = mptcp_pm_nl_append_new_local_addr(pernet, entry, true); if (ret < 0) { GENL_SET_ERR_MSG_FMT(info, "too many addresses or duplicate one: %d", ret); goto out_free; } mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr); return 0; out_free: __mptcp_pm_release_addr_entry(entry); return ret; } static void mptcp_pm_remove_announced(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool force) { struct mptcp_rm_list list = { .nr = 0 }; bool announced; list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); announced = mptcp_pm_announced_remove(msk, addr); if (announced || force) { spin_lock_bh(&msk->pm.lock); if (announced) msk->pm.add_addr_signaled--; mptcp_pm_remove_addr(msk, &list); spin_unlock_bh(&msk->pm.lock); } } static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id) { /* If it was marked as used, and not ID 0, decrement local_addr_used */ if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) && id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0)) msk->pm.local_addr_used--; } static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net, const struct mptcp_pm_addr_entry *entry) { const struct mptcp_addr_info *addr = &entry->addr; struct mptcp_rm_list list = { .nr = 1 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; pr_debug("remove_id=%d\n", addr->id); while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; bool remove_subflow; if (mptcp_pm_is_userspace(msk)) goto next; lock_sock(sk); remove_subflow = mptcp_pm_has_subflow_saddr(msk, addr); mptcp_pm_remove_announced(msk, addr, remove_subflow && !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT)); list.ids[0] = mptcp_endp_get_local_id(msk, addr); spin_lock_bh(&msk->pm.lock); if (remove_subflow) mptcp_pm_rm_subflow(msk, &list); if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) __mark_subflow_endp_available(msk, list.ids[0]); else /* mark endp ID as available, e.g. Signal or MPC endp */ __set_bit(addr->id, msk->pm.id_avail_bitmap); spin_unlock_bh(&msk->pm.lock); if (msk->mpc_endpoint_id == entry->addr.id) msk->mpc_endpoint_id = 0; release_sock(sk); next: sock_put(sk); cond_resched(); } return 0; } static int mptcp_nl_remove_id_zero_address(struct net *net, struct mptcp_addr_info *addr) { struct mptcp_rm_list list = { .nr = 0 }; long s_slot = 0, s_num = 0; struct mptcp_sock *msk; list.ids[list.nr++] = 0; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; struct mptcp_addr_info msk_local; if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; mptcp_local_address((struct sock_common *)msk, &msk_local); if (!mptcp_addresses_equal(&msk_local, addr, addr->port)) goto next; lock_sock(sk); spin_lock_bh(&msk->pm.lock); mptcp_pm_remove_addr(msk, &list); mptcp_pm_rm_subflow(msk, &list); __mark_subflow_endp_available(msk, 0); spin_unlock_bh(&msk->pm.lock); release_sock(sk); next: sock_put(sk); cond_resched(); } return 0; } /* Remove an MPTCP endpoint */ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry addr, *entry; struct nlattr *attr; u8 addr_max; int ret; if (GENL_REQ_ATTR_CHECK(info, MPTCP_PM_ENDPOINT_ADDR)) return -EINVAL; attr = info->attrs[MPTCP_PM_ENDPOINT_ADDR]; ret = mptcp_pm_parse_entry(attr, info, false, &addr); if (ret < 0) return ret; /* the zero id address is special: the first address used by the msk * always gets such an id, so different subflows can have different zero * id addresses. Additionally zero id is not accounted for in id_bitmap. * Let's use an 'mptcp_rm_list' instead of the common remove code. */ if (addr.addr.id == 0) return mptcp_nl_remove_id_zero_address(sock_net(skb->sk), &addr.addr); spin_lock_bh(&pernet->lock); entry = __lookup_addr_by_id(pernet, addr.addr.id); if (!entry) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found"); spin_unlock_bh(&pernet->lock); return -EINVAL; } if (entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL) { addr_max = pernet->endp_signal_max; WRITE_ONCE(pernet->endp_signal_max, addr_max - 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) { addr_max = pernet->endp_subflow_max; WRITE_ONCE(pernet->endp_subflow_max, addr_max - 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_LAMINAR) { addr_max = pernet->endp_laminar_max; WRITE_ONCE(pernet->endp_laminar_max, addr_max - 1); } if (entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) { addr_max = pernet->endp_fullmesh_max; WRITE_ONCE(pernet->endp_fullmesh_max, addr_max - 1); } pernet->endpoints--; list_del_rcu(&entry->list); __clear_bit(entry->addr.id, pernet->id_bitmap); spin_unlock_bh(&pernet->lock); mptcp_nl_remove_subflow_and_signal_addr(sock_net(skb->sk), entry); synchronize_rcu(); __mptcp_pm_release_addr_entry(entry); return ret; } static void mptcp_pm_flush_addrs_and_subflows(struct mptcp_sock *msk, struct list_head *rm_list, struct mptcp_pm_addr_entry *entry) { struct mptcp_rm_list alist, slist; bool more; again: alist.nr = 0; slist.nr = 0; more = false; entry = list_prepare_entry(entry, rm_list, list); list_for_each_entry_continue(entry, rm_list, list) { if (mptcp_pm_has_subflow_saddr(msk, &entry->addr)) slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); if (mptcp_pm_announced_remove(msk, &entry->addr)) alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr); if (slist.nr == MPTCP_RM_IDS_MAX || alist.nr == MPTCP_RM_IDS_MAX) { more = !list_is_last(&entry->list, rm_list); break; } } spin_lock_bh(&msk->pm.lock); if (alist.nr) { msk->pm.add_addr_signaled -= alist.nr; mptcp_pm_remove_addr(msk, &alist); } if (slist.nr) mptcp_pm_rm_subflow(msk, &slist); /* Reset counters: maybe some subflows have been removed before */ if (!more) { bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); msk->pm.local_addr_used = 0; } spin_unlock_bh(&msk->pm.lock); if (more) goto again; } static void mptcp_nl_flush_addrs_list(struct net *net, struct list_head *rm_list) { long s_slot = 0, s_num = 0; struct mptcp_sock *msk; if (list_empty(rm_list)) return; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; if (!mptcp_pm_is_userspace(msk)) { lock_sock(sk); mptcp_pm_flush_addrs_and_subflows(msk, rm_list, NULL); release_sock(sk); } sock_put(sk); cond_resched(); } } /* caller must ensure the RCU grace period is already elapsed */ static void __flush_addrs(struct list_head *list) { while (!list_empty(list)) { struct mptcp_pm_addr_entry *cur; cur = list_entry(list->next, struct mptcp_pm_addr_entry, list); list_del_rcu(&cur->list); __mptcp_pm_release_addr_entry(cur); } } static void __reset_counters(struct pm_nl_pernet *pernet) { WRITE_ONCE(pernet->endp_signal_max, 0); WRITE_ONCE(pernet->endp_subflow_max, 0); WRITE_ONCE(pernet->endp_laminar_max, 0); WRITE_ONCE(pernet->endp_fullmesh_max, 0); pernet->endpoints = 0; } int mptcp_pm_nl_flush_addrs_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct list_head free_list; spin_lock_bh(&pernet->lock); free_list = pernet->endp_list; INIT_LIST_HEAD_RCU(&pernet->endp_list); __reset_counters(pernet); pernet->next_id = 1; bitmap_zero(pernet->id_bitmap, MPTCP_PM_MAX_ADDR_ID + 1); spin_unlock_bh(&pernet->lock); if (free_list.next == &pernet->endp_list) return 0; synchronize_rcu(); /* Adjust the pointers to free_list instead of pernet->endp_list */ free_list.prev->next = &free_list; free_list.next->prev = &free_list; mptcp_nl_flush_addrs_list(sock_net(skb->sk), &free_list); __flush_addrs(&free_list); return 0; } int mptcp_pm_nl_get_addr(u8 id, struct mptcp_pm_addr_entry *addr, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct mptcp_pm_addr_entry *entry; int ret = -EINVAL; rcu_read_lock(); entry = __lookup_addr_by_id(pernet, id); if (entry) { *addr = *entry; ret = 0; } rcu_read_unlock(); return ret; } int mptcp_pm_nl_dump_addr(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(msg->sk); struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; int id = cb->args[0]; int i; pernet = pm_nl_get_pernet(net); rcu_read_lock(); for (i = id; i < MPTCP_PM_MAX_ADDR_ID + 1; i++) { if (test_bit(i, pernet->id_bitmap)) { entry = __lookup_addr_by_id(pernet, i); if (!entry) break; if (entry->addr.id <= id) continue; if (mptcp_pm_genl_fill_addr(msg, cb, entry) < 0) break; id = entry->addr.id; } } rcu_read_unlock(); cb->args[0] = id; return msg->len; } static int parse_limit(struct genl_info *info, int id, unsigned int *limit) { struct nlattr *attr = info->attrs[id]; if (!attr) return 0; *limit = nla_get_u32(attr); if (*limit > MPTCP_PM_SUBFLOWS_MAX) { NL_SET_ERR_MSG_ATTR_FMT(info->extack, attr, "limit greater than maximum (%u)", MPTCP_PM_SUBFLOWS_MAX); return -EINVAL; } return 0; } int mptcp_pm_nl_set_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); unsigned int rcv_addrs, subflows; int ret; spin_lock_bh(&pernet->lock); rcv_addrs = pernet->limit_add_addr_accepted; ret = parse_limit(info, MPTCP_PM_ATTR_RCV_ADD_ADDRS, &rcv_addrs); if (ret) goto unlock; subflows = pernet->limit_extra_subflows; ret = parse_limit(info, MPTCP_PM_ATTR_SUBFLOWS, &subflows); if (ret) goto unlock; WRITE_ONCE(pernet->limit_add_addr_accepted, rcv_addrs); WRITE_ONCE(pernet->limit_extra_subflows, subflows); unlock: spin_unlock_bh(&pernet->lock); return ret; } int mptcp_pm_nl_get_limits_doit(struct sk_buff *skb, struct genl_info *info) { struct pm_nl_pernet *pernet = genl_info_pm_nl(info); struct sk_buff *msg; void *reply; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return -ENOMEM; reply = genlmsg_put_reply(msg, info, &mptcp_genl_family, 0, MPTCP_PM_CMD_GET_LIMITS); if (!reply) goto fail; if (nla_put_u32(msg, MPTCP_PM_ATTR_RCV_ADD_ADDRS, READ_ONCE(pernet->limit_add_addr_accepted))) goto fail; if (nla_put_u32(msg, MPTCP_PM_ATTR_SUBFLOWS, READ_ONCE(pernet->limit_extra_subflows))) goto fail; genlmsg_end(msg, reply); return genlmsg_reply(msg, info); fail: GENL_SET_ERR_MSG(info, "not enough space in Netlink message"); nlmsg_free(msg); return -EMSGSIZE; } static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, struct mptcp_addr_info *addr) { struct mptcp_rm_list list = { .nr = 0 }; list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr); spin_lock_bh(&msk->pm.lock); mptcp_pm_rm_subflow(msk, &list); __mark_subflow_endp_available(msk, list.ids[0]); mptcp_pm_create_subflow_or_signal_addr(msk); spin_unlock_bh(&msk->pm.lock); } static void mptcp_pm_nl_set_flags_all(struct net *net, struct mptcp_pm_addr_entry *local, u8 changed) { u8 is_subflow = !!(local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW); u8 bkup = !!(local->flags & MPTCP_PM_ADDR_FLAG_BACKUP); long s_slot = 0, s_num = 0; struct mptcp_sock *msk; if (changed == MPTCP_PM_ADDR_FLAG_FULLMESH && !is_subflow) return; while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) { struct sock *sk = (struct sock *)msk; if (list_empty(&msk->conn_list) || mptcp_pm_is_userspace(msk)) goto next; lock_sock(sk); if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) mptcp_pm_mp_prio_send_ack(msk, &local->addr, NULL, bkup); /* Subflows will only be recreated if the SUBFLOW flag is set */ if (is_subflow && (changed & MPTCP_PM_ADDR_FLAG_FULLMESH)) mptcp_pm_nl_fullmesh(msk, &local->addr); release_sock(sk); next: sock_put(sk); cond_resched(); } } int mptcp_pm_nl_set_flags(struct mptcp_pm_addr_entry *local, struct genl_info *info) { struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | MPTCP_PM_ADDR_FLAG_FULLMESH; struct net *net = genl_info_net(info); struct mptcp_pm_addr_entry *entry; struct pm_nl_pernet *pernet; u8 lookup_by_id = 0; pernet = pm_nl_get_pernet(net); if (local->addr.family == AF_UNSPEC) { lookup_by_id = 1; if (!local->addr.id) { NL_SET_ERR_MSG_ATTR(info->extack, attr, "missing address ID"); return -EOPNOTSUPP; } } spin_lock_bh(&pernet->lock); entry = lookup_by_id ? __lookup_addr_by_id(pernet, local->addr.id) : __lookup_addr(pernet, &local->addr); if (!entry) { spin_unlock_bh(&pernet->lock); NL_SET_ERR_MSG_ATTR(info->extack, attr, "address not found"); return -EINVAL; } if ((local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) && (entry->flags & (MPTCP_PM_ADDR_FLAG_SIGNAL | MPTCP_PM_ADDR_FLAG_IMPLICIT))) { spin_unlock_bh(&pernet->lock); NL_SET_ERR_MSG_ATTR(info->extack, attr, "invalid addr flags"); return -EINVAL; } changed = (local->flags ^ entry->flags) & mask; entry->flags = (entry->flags & ~mask) | (local->flags & mask); *local = *entry; if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) { u8 addr_max = pernet->endp_fullmesh_max; if (entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH) addr_max++; else addr_max--; WRITE_ONCE(pernet->endp_fullmesh_max, addr_max); } spin_unlock_bh(&pernet->lock); mptcp_pm_nl_set_flags_all(net, local, changed); return 0; } bool mptcp_pm_nl_check_work_pending(struct mptcp_sock *msk) { struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk); if (msk->pm.extra_subflows == mptcp_pm_get_limit_extra_subflows(msk) || (find_next_and_bit(pernet->id_bitmap, msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1, 0) == MPTCP_PM_MAX_ADDR_ID + 1)) { WRITE_ONCE(msk->pm.work_pending, false); return false; } return true; } /* Called under PM lock */ void __mptcp_pm_kernel_worker(struct mptcp_sock *msk) { struct mptcp_pm_data *pm = &msk->pm; if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) { pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED); mptcp_pm_nl_add_addr_received(msk); } if (pm->status & BIT(MPTCP_PM_ESTABLISHED)) { pm->status &= ~BIT(MPTCP_PM_ESTABLISHED); mptcp_pm_nl_fully_established(msk); } if (pm->status & BIT(MPTCP_PM_SUBFLOW_ESTABLISHED)) { pm->status &= ~BIT(MPTCP_PM_SUBFLOW_ESTABLISHED); mptcp_pm_nl_subflow_established(msk); } } static int __net_init pm_nl_init_net(struct net *net) { struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); INIT_LIST_HEAD_RCU(&pernet->endp_list); /* Cit. 2 subflows ought to be enough for anybody. */ pernet->limit_extra_subflows = 2; pernet->next_id = 1; spin_lock_init(&pernet->lock); /* No need to initialize other pernet fields, the struct is zeroed at * allocation time. */ return 0; } static void __net_exit pm_nl_exit_net(struct list_head *net_list) { struct net *net; list_for_each_entry(net, net_list, exit_list) { struct pm_nl_pernet *pernet = pm_nl_get_pernet(net); /* net is removed from namespace list, can't race with * other modifiers, also netns core already waited for a * RCU grace period. */ __flush_addrs(&pernet->endp_list); } } static struct pernet_operations mptcp_pm_pernet_ops = { .init = pm_nl_init_net, .exit_batch = pm_nl_exit_net, .id = &pm_nl_pernet_id, .size = sizeof(struct pm_nl_pernet), }; struct mptcp_pm_ops mptcp_pm_kernel = { .name = "kernel", .owner = THIS_MODULE, }; void __init mptcp_pm_kernel_register(void) { if (register_pernet_subsys(&mptcp_pm_pernet_ops) < 0) panic("Failed to register MPTCP PM pernet subsystem.\n"); mptcp_pm_register(&mptcp_pm_kernel); } |
| 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * ip_vs_proto.c: transport protocol load balancing support for IPVS * * Authors: Wensong Zhang <wensong@linuxvirtualserver.org> * Julian Anastasov <ja@ssi.bg> * * Changes: */ #define pr_fmt(fmt) "IPVS: " fmt #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/gfp.h> #include <linux/in.h> #include <linux/ip.h> #include <net/protocol.h> #include <net/tcp.h> #include <net/udp.h> #include <linux/stat.h> #include <linux/proc_fs.h> #include <net/ip_vs.h> /* * IPVS protocols can only be registered/unregistered when the ipvs * module is loaded/unloaded, so no lock is needed in accessing the * ipvs protocol table. */ #define IP_VS_PROTO_TAB_SIZE 32 /* must be power of 2 */ #define IP_VS_PROTO_HASH(proto) ((proto) & (IP_VS_PROTO_TAB_SIZE-1)) static struct ip_vs_protocol *ip_vs_proto_table[IP_VS_PROTO_TAB_SIZE]; /* States for conn templates: NONE or words separated with ",", max 15 chars */ static const char *ip_vs_ctpl_state_name_table[IP_VS_CTPL_S_LAST] = { [IP_VS_CTPL_S_NONE] = "NONE", [IP_VS_CTPL_S_ASSURED] = "ASSURED", }; /* * register an ipvs protocol */ static int __used __init register_ip_vs_protocol(struct ip_vs_protocol *pp) { unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp->next = ip_vs_proto_table[hash]; ip_vs_proto_table[hash] = pp; if (pp->init != NULL) pp->init(pp); return 0; } /* * register an ipvs protocols netns related data */ static int register_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_protocol *pp) { unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); struct ip_vs_proto_data *pd = kzalloc_obj(struct ip_vs_proto_data); if (!pd) return -ENOMEM; pd->pp = pp; /* For speed issues */ pd->next = ipvs->proto_data_table[hash]; ipvs->proto_data_table[hash] = pd; atomic_set(&pd->appcnt, 0); /* Init app counter */ if (pp->init_netns != NULL) { int ret = pp->init_netns(ipvs, pd); if (ret) { /* unlink an free proto data */ ipvs->proto_data_table[hash] = pd->next; kfree(pd); return ret; } } return 0; } /* * unregister an ipvs protocol */ static int unregister_ip_vs_protocol(struct ip_vs_protocol *pp) { struct ip_vs_protocol **pp_p; unsigned int hash = IP_VS_PROTO_HASH(pp->protocol); pp_p = &ip_vs_proto_table[hash]; for (; *pp_p; pp_p = &(*pp_p)->next) { if (*pp_p == pp) { *pp_p = pp->next; if (pp->exit != NULL) pp->exit(pp); return 0; } } return -ESRCH; } /* * unregister an ipvs protocols netns data */ static int unregister_ip_vs_proto_netns(struct netns_ipvs *ipvs, struct ip_vs_proto_data *pd) { struct ip_vs_proto_data **pd_p; unsigned int hash = IP_VS_PROTO_HASH(pd->pp->protocol); pd_p = &ipvs->proto_data_table[hash]; for (; *pd_p; pd_p = &(*pd_p)->next) { if (*pd_p == pd) { *pd_p = pd->next; if (pd->pp->exit_netns != NULL) pd->pp->exit_netns(ipvs, pd); kfree(pd); return 0; } } return -ESRCH; } /* * get ip_vs_protocol object by its proto. */ struct ip_vs_protocol * ip_vs_proto_get(unsigned short proto) { struct ip_vs_protocol *pp; unsigned int hash = IP_VS_PROTO_HASH(proto); for (pp = ip_vs_proto_table[hash]; pp; pp = pp->next) { if (pp->protocol == proto) return pp; } return NULL; } EXPORT_SYMBOL(ip_vs_proto_get); /* * get ip_vs_protocol object data by netns and proto */ struct ip_vs_proto_data * ip_vs_proto_data_get(struct netns_ipvs *ipvs, unsigned short proto) { struct ip_vs_proto_data *pd; unsigned int hash = IP_VS_PROTO_HASH(proto); for (pd = ipvs->proto_data_table[hash]; pd; pd = pd->next) { if (pd->pp->protocol == proto) return pd; } return NULL; } EXPORT_SYMBOL(ip_vs_proto_data_get); /* * Propagate event for state change to all protocols */ void ip_vs_protocol_timeout_change(struct netns_ipvs *ipvs, int flags) { struct ip_vs_proto_data *pd; int i; for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { for (pd = ipvs->proto_data_table[i]; pd; pd = pd->next) { if (pd->pp->timeout_change) pd->pp->timeout_change(pd, flags); } } } int * ip_vs_create_timeout_table(int *table, int size) { return kmemdup(table, size, GFP_KERNEL); } const char *ip_vs_state_name(const struct ip_vs_conn *cp) { unsigned int state = cp->state; struct ip_vs_protocol *pp; if (cp->flags & IP_VS_CONN_F_TEMPLATE) { if (state >= IP_VS_CTPL_S_LAST) return "ERR!"; return ip_vs_ctpl_state_name_table[state] ? : "?"; } pp = ip_vs_proto_get(cp->protocol); if (pp == NULL || pp->state_name == NULL) return (cp->protocol == IPPROTO_IP) ? "NONE" : "ERR!"; return pp->state_name(state); } static void ip_vs_tcpudp_debug_packet_v4(struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { char buf[128]; struct iphdr _iph, *ih; ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->frag_off & htons(IP_OFFSET)) sprintf(buf, "%pI4->%pI4 frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + ih->ihl*4, sizeof(_ports), _ports); if (pptr == NULL) sprintf(buf, "TRUNCATED %pI4->%pI4", &ih->saddr, &ih->daddr); else sprintf(buf, "%pI4:%u->%pI4:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } pr_debug("%s: %s %s\n", msg, pp->name, buf); } #ifdef CONFIG_IP_VS_IPV6 static void ip_vs_tcpudp_debug_packet_v6(struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { char buf[192]; struct ipv6hdr _iph, *ih; ih = skb_header_pointer(skb, offset, sizeof(_iph), &_iph); if (ih == NULL) sprintf(buf, "TRUNCATED"); else if (ih->nexthdr == IPPROTO_FRAGMENT) sprintf(buf, "%pI6c->%pI6c frag", &ih->saddr, &ih->daddr); else { __be16 _ports[2], *pptr; pptr = skb_header_pointer(skb, offset + sizeof(struct ipv6hdr), sizeof(_ports), _ports); if (pptr == NULL) sprintf(buf, "TRUNCATED %pI6c->%pI6c", &ih->saddr, &ih->daddr); else sprintf(buf, "%pI6c:%u->%pI6c:%u", &ih->saddr, ntohs(pptr[0]), &ih->daddr, ntohs(pptr[1])); } pr_debug("%s: %s %s\n", msg, pp->name, buf); } #endif void ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, const struct sk_buff *skb, int offset, const char *msg) { #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) ip_vs_tcpudp_debug_packet_v6(pp, skb, offset, msg); else #endif ip_vs_tcpudp_debug_packet_v4(pp, skb, offset, msg); } /* * per network name-space init */ int __net_init ip_vs_protocol_net_init(struct netns_ipvs *ipvs) { int i, ret; static struct ip_vs_protocol *protos[] = { #ifdef CONFIG_IP_VS_PROTO_TCP &ip_vs_protocol_tcp, #endif #ifdef CONFIG_IP_VS_PROTO_UDP &ip_vs_protocol_udp, #endif #ifdef CONFIG_IP_VS_PROTO_SCTP &ip_vs_protocol_sctp, #endif #ifdef CONFIG_IP_VS_PROTO_AH &ip_vs_protocol_ah, #endif #ifdef CONFIG_IP_VS_PROTO_ESP &ip_vs_protocol_esp, #endif }; for (i = 0; i < ARRAY_SIZE(protos); i++) { ret = register_ip_vs_proto_netns(ipvs, protos[i]); if (ret < 0) goto cleanup; } return 0; cleanup: ip_vs_protocol_net_cleanup(ipvs); return ret; } void __net_exit ip_vs_protocol_net_cleanup(struct netns_ipvs *ipvs) { struct ip_vs_proto_data *pd; int i; /* unregister all the ipvs proto data for this netns */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pd = ipvs->proto_data_table[i]) != NULL) unregister_ip_vs_proto_netns(ipvs, pd); } } int __init ip_vs_protocol_init(void) { char protocols[64] = { 0 }; #define REGISTER_PROTOCOL(p) \ do { \ register_ip_vs_protocol(p); \ strcat(protocols, ", "); \ strcat(protocols, (p)->name); \ } while (0) #ifdef CONFIG_IP_VS_PROTO_TCP REGISTER_PROTOCOL(&ip_vs_protocol_tcp); #endif #ifdef CONFIG_IP_VS_PROTO_UDP REGISTER_PROTOCOL(&ip_vs_protocol_udp); #endif #ifdef CONFIG_IP_VS_PROTO_SCTP REGISTER_PROTOCOL(&ip_vs_protocol_sctp); #endif #ifdef CONFIG_IP_VS_PROTO_AH REGISTER_PROTOCOL(&ip_vs_protocol_ah); #endif #ifdef CONFIG_IP_VS_PROTO_ESP REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); return 0; } void ip_vs_protocol_cleanup(void) { struct ip_vs_protocol *pp; int i; /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) unregister_ip_vs_protocol(pp); } } |
| 290 290 290 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/audit.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include "common.h" #include <linux/slab.h> /** * tomoyo_print_bprm - Print "struct linux_binprm" for auditing. * * @bprm: Pointer to "struct linux_binprm". * @dump: Pointer to "struct tomoyo_page_dump". * * Returns the contents of @bprm on success, NULL otherwise. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_bprm(struct linux_binprm *bprm, struct tomoyo_page_dump *dump) { static const int tomoyo_buffer_len = 4096 * 2; char *buffer = kzalloc(tomoyo_buffer_len, GFP_NOFS); char *cp; char *last_start; int len; unsigned long pos = bprm->p; int offset = pos % PAGE_SIZE; int argv_count = bprm->argc; int envp_count = bprm->envc; bool truncated = false; if (!buffer) return NULL; len = snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ "); cp = buffer + len; if (!argv_count) { memmove(cp, "} envp[]={ ", 11); cp += 11; } last_start = cp; while (argv_count || envp_count) { if (!tomoyo_dump_page(bprm, pos, dump)) goto out; pos += PAGE_SIZE - offset; /* Read. */ while (offset < PAGE_SIZE) { const char *kaddr = dump->data; const unsigned char c = kaddr[offset++]; if (cp == last_start) *cp++ = '"'; if (cp >= buffer + tomoyo_buffer_len - 32) { /* Reserve some room for "..." string. */ truncated = true; } else if (c == '\\') { *cp++ = '\\'; *cp++ = '\\'; } else if (c > ' ' && c < 127) { *cp++ = c; } else if (!c) { *cp++ = '"'; *cp++ = ' '; last_start = cp; } else { *cp++ = '\\'; *cp++ = (c >> 6) + '0'; *cp++ = ((c >> 3) & 7) + '0'; *cp++ = (c & 7) + '0'; } if (c) continue; if (argv_count) { if (--argv_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } memmove(cp, "} envp[]={ ", 11); cp += 11; last_start = cp; truncated = false; } } else if (envp_count) { if (--envp_count == 0) { if (truncated) { cp = last_start; memmove(cp, "... ", 4); cp += 4; } } } if (!argv_count && !envp_count) break; } offset = 0; } *cp++ = '}'; *cp = '\0'; return buffer; out: snprintf(buffer, tomoyo_buffer_len - 1, "argv[]={ ... } envp[]= { ... }"); return buffer; } /** * tomoyo_filetype - Get string representation of file type. * * @mode: Mode value for stat(). * * Returns file type string. */ static inline const char *tomoyo_filetype(const umode_t mode) { switch (mode & S_IFMT) { case S_IFREG: case 0: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FILE]; case S_IFDIR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_DIRECTORY]; case S_IFLNK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SYMLINK]; case S_IFIFO: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_FIFO]; case S_IFSOCK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_SOCKET]; case S_IFBLK: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_BLOCK_DEV]; case S_IFCHR: return tomoyo_condition_keyword[TOMOYO_TYPE_IS_CHAR_DEV]; } return "unknown"; /* This should not happen. */ } /** * tomoyo_print_header - Get header line of audit log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns string representation. * * This function uses kmalloc(), so caller must kfree() if this function * didn't return NULL. */ static char *tomoyo_print_header(struct tomoyo_request_info *r) { struct tomoyo_time stamp; const pid_t gpid = task_pid_nr(current); struct tomoyo_obj_info *obj = r->obj; static const int tomoyo_buffer_len = 4096; char *buffer = kmalloc(tomoyo_buffer_len, GFP_NOFS); int pos; u8 i; if (!buffer) return NULL; tomoyo_convert_time(ktime_get_real_seconds(), &stamp); pos = snprintf(buffer, tomoyo_buffer_len - 1, "#%04u/%02u/%02u %02u:%02u:%02u# profile=%u mode=%s granted=%s (global-pid=%u) task={ pid=%u ppid=%u uid=%u gid=%u euid=%u egid=%u suid=%u sgid=%u fsuid=%u fsgid=%u }", stamp.year, stamp.month, stamp.day, stamp.hour, stamp.min, stamp.sec, r->profile, tomoyo_mode[r->mode], str_yes_no(r->granted), gpid, tomoyo_sys_getpid(), tomoyo_sys_getppid(), from_kuid(&init_user_ns, current_uid()), from_kgid(&init_user_ns, current_gid()), from_kuid(&init_user_ns, current_euid()), from_kgid(&init_user_ns, current_egid()), from_kuid(&init_user_ns, current_suid()), from_kgid(&init_user_ns, current_sgid()), from_kuid(&init_user_ns, current_fsuid()), from_kgid(&init_user_ns, current_fsgid())); if (!obj) goto no_obj_info; if (!obj->validate_done) { tomoyo_get_attributes(obj); obj->validate_done = true; } for (i = 0; i < TOMOYO_MAX_PATH_STAT; i++) { struct tomoyo_mini_stat *stat; unsigned int dev; umode_t mode; if (!obj->stat_valid[i]) continue; stat = &obj->stat[i]; dev = stat->dev; mode = stat->mode; if (i & 1) { pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u.parent={ uid=%u gid=%u ino=%llu perm=0%o }", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), stat->ino, stat->mode & S_IALLUGO); continue; } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " path%u={ uid=%u gid=%u ino=%llu major=%u minor=%u perm=0%o type=%s", (i >> 1) + 1, from_kuid(&init_user_ns, stat->uid), from_kgid(&init_user_ns, stat->gid), stat->ino, MAJOR(dev), MINOR(dev), mode & S_IALLUGO, tomoyo_filetype(mode)); if (S_ISCHR(mode) || S_ISBLK(mode)) { dev = stat->rdev; pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " dev_major=%u dev_minor=%u", MAJOR(dev), MINOR(dev)); } pos += snprintf(buffer + pos, tomoyo_buffer_len - 1 - pos, " }"); } no_obj_info: if (pos < tomoyo_buffer_len - 1) return buffer; kfree(buffer); return NULL; } /** * tomoyo_init_log - Allocate buffer for audit logs. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns pointer to allocated memory. * * This function uses kzalloc(), so caller must kfree() if this function * didn't return NULL. */ char *tomoyo_init_log(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf = NULL; char *bprm_info = NULL; const char *header = NULL; char *realpath = NULL; const char *symlink = NULL; int pos; const char *domainname = r->domain->domainname->name; header = tomoyo_print_header(r); if (!header) return NULL; /* +10 is for '\n' etc. and '\0'. */ len += strlen(domainname) + strlen(header) + 10; if (r->ee) { struct file *file = r->ee->bprm->file; realpath = tomoyo_realpath_from_path(&file->f_path); bprm_info = tomoyo_print_bprm(r->ee->bprm, &r->ee->dump); if (!realpath || !bprm_info) goto out; /* +80 is for " exec={ realpath=\"%s\" argc=%d envc=%d %s }" */ len += strlen(realpath) + 80 + strlen(bprm_info); } else if (r->obj && r->obj->symlink_target) { symlink = r->obj->symlink_target->name; /* +18 is for " symlink.target=\"%s\"" */ len += 18 + strlen(symlink); } len = kmalloc_size_roundup(len); buf = kzalloc(len, GFP_NOFS); if (!buf) goto out; len--; pos = snprintf(buf, len, "%s", header); if (realpath) { struct linux_binprm *bprm = r->ee->bprm; pos += snprintf(buf + pos, len - pos, " exec={ realpath=\"%s\" argc=%d envc=%d %s }", realpath, bprm->argc, bprm->envc, bprm_info); } else if (symlink) pos += snprintf(buf + pos, len - pos, " symlink.target=\"%s\"", symlink); pos += snprintf(buf + pos, len - pos, "\n%s\n", domainname); vsnprintf(buf + pos, len - pos, fmt, args); out: kfree(realpath); kfree(bprm_info); kfree(header); return buf; } /* Wait queue for /sys/kernel/security/tomoyo/audit. */ static DECLARE_WAIT_QUEUE_HEAD(tomoyo_log_wait); /* Structure for audit log. */ struct tomoyo_log { struct list_head list; char *log; int size; }; /* The list for "struct tomoyo_log". */ static LIST_HEAD(tomoyo_log); /* Lock for "struct list_head tomoyo_log". */ static DEFINE_SPINLOCK(tomoyo_log_lock); /* Length of "struct list_head tomoyo_log". */ static unsigned int tomoyo_log_count; /** * tomoyo_get_audit - Get audit mode. * * @ns: Pointer to "struct tomoyo_policy_namespace". * @profile: Profile number. * @index: Index number of functionality. * @matched_acl: Pointer to "struct tomoyo_acl_info". * @is_granted: True if granted log, false otherwise. * * Returns true if this request should be audited, false otherwise. */ static bool tomoyo_get_audit(const struct tomoyo_policy_namespace *ns, const u8 profile, const u8 index, const struct tomoyo_acl_info *matched_acl, const bool is_granted) { u8 mode; const u8 category = tomoyo_index2category[index] + TOMOYO_MAX_MAC_INDEX; struct tomoyo_profile *p; if (!tomoyo_policy_loaded) return false; p = tomoyo_profile(ns, profile); if (tomoyo_log_count >= p->pref[TOMOYO_PREF_MAX_AUDIT_LOG]) return false; if (is_granted && matched_acl && matched_acl->cond && matched_acl->cond->grant_log != TOMOYO_GRANTLOG_AUTO) return matched_acl->cond->grant_log == TOMOYO_GRANTLOG_YES; mode = p->config[index]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->config[category]; if (mode == TOMOYO_CONFIG_USE_DEFAULT) mode = p->default_config; if (is_granted) return mode & TOMOYO_CONFIG_WANT_GRANT_LOG; return mode & TOMOYO_CONFIG_WANT_REJECT_LOG; } /** * tomoyo_write_log2 - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @len: Buffer size needed for @fmt and @args. * @fmt: The printf()'s format string. * @args: va_list structure for @fmt. * * Returns nothing. */ void tomoyo_write_log2(struct tomoyo_request_info *r, int len, const char *fmt, va_list args) { char *buf; struct tomoyo_log *entry; bool quota_exceeded = false; if (!tomoyo_get_audit(r->domain->ns, r->profile, r->type, r->matched_acl, r->granted)) goto out; buf = tomoyo_init_log(r, len, fmt, args); if (!buf) goto out; entry = kzalloc_obj(*entry, GFP_NOFS); if (!entry) { kfree(buf); goto out; } entry->log = buf; len = kmalloc_size_roundup(strlen(buf) + 1); /* * The entry->size is used for memory quota checks. * Don't go beyond strlen(entry->log). */ entry->size = len + kmalloc_size_roundup(sizeof(*entry)); spin_lock(&tomoyo_log_lock); if (tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT] && tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] + entry->size >= tomoyo_memory_quota[TOMOYO_MEMORY_AUDIT]) { quota_exceeded = true; } else { tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] += entry->size; list_add_tail(&entry->list, &tomoyo_log); tomoyo_log_count++; } spin_unlock(&tomoyo_log_lock); if (quota_exceeded) { kfree(buf); kfree(entry); goto out; } wake_up(&tomoyo_log_wait); out: return; } /** * tomoyo_write_log - Write an audit log. * * @r: Pointer to "struct tomoyo_request_info". * @fmt: The printf()'s format string, followed by parameters. * * Returns nothing. */ void tomoyo_write_log(struct tomoyo_request_info *r, const char *fmt, ...) { va_list args; int len; va_start(args, fmt); len = vsnprintf(NULL, 0, fmt, args) + 1; va_end(args); va_start(args, fmt); tomoyo_write_log2(r, len, fmt, args); va_end(args); } /** * tomoyo_read_log - Read an audit log. * * @head: Pointer to "struct tomoyo_io_buffer". * * Returns nothing. */ void tomoyo_read_log(struct tomoyo_io_buffer *head) { struct tomoyo_log *ptr = NULL; if (head->r.w_pos) return; kfree(head->read_buf); head->read_buf = NULL; spin_lock(&tomoyo_log_lock); if (!list_empty(&tomoyo_log)) { ptr = list_entry(tomoyo_log.next, typeof(*ptr), list); list_del(&ptr->list); tomoyo_log_count--; tomoyo_memory_used[TOMOYO_MEMORY_AUDIT] -= ptr->size; } spin_unlock(&tomoyo_log_lock); if (ptr) { head->read_buf = ptr->log; head->r.w[head->r.w_pos++] = head->read_buf; kfree(ptr); } } /** * tomoyo_poll_log - Wait for an audit log. * * @file: Pointer to "struct file". * @wait: Pointer to "poll_table". Maybe NULL. * * Returns EPOLLIN | EPOLLRDNORM when ready to read an audit log. */ __poll_t tomoyo_poll_log(struct file *file, poll_table *wait) { if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; poll_wait(file, &tomoyo_log_wait, wait); if (tomoyo_log_count) return EPOLLIN | EPOLLRDNORM; return 0; } |
| 2 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_KDEV_T_H #define _LINUX_KDEV_T_H #include <uapi/linux/kdev_t.h> #define MINORBITS 20 #define MINORMASK ((1U << MINORBITS) - 1) #define MAJOR(dev) ((unsigned int) ((dev) >> MINORBITS)) #define MINOR(dev) ((unsigned int) ((dev) & MINORMASK)) #define MKDEV(ma,mi) (((ma) << MINORBITS) | (mi)) #define print_dev_t(buffer, dev) \ sprintf((buffer), "%u:%u\n", MAJOR(dev), MINOR(dev)) #define format_dev_t(buffer, dev) \ ({ \ sprintf(buffer, "%u:%u", MAJOR(dev), MINOR(dev)); \ buffer; \ }) /* acceptable for old filesystems */ static __always_inline bool old_valid_dev(dev_t dev) { return MAJOR(dev) < 256 && MINOR(dev) < 256; } static __always_inline u16 old_encode_dev(dev_t dev) { return (MAJOR(dev) << 8) | MINOR(dev); } static __always_inline dev_t old_decode_dev(u16 val) { return MKDEV((val >> 8) & 255, val & 255); } static __always_inline u32 new_encode_dev(dev_t dev) { unsigned major = MAJOR(dev); unsigned minor = MINOR(dev); return (minor & 0xff) | (major << 8) | ((minor & ~0xff) << 12); } static __always_inline dev_t new_decode_dev(u32 dev) { unsigned major = (dev & 0xfff00) >> 8; unsigned minor = (dev & 0xff) | ((dev >> 12) & 0xfff00); return MKDEV(major, minor); } static __always_inline u64 huge_encode_dev(dev_t dev) { return new_encode_dev(dev); } static __always_inline dev_t huge_decode_dev(u64 dev) { return new_decode_dev(dev); } static __always_inline int sysv_valid_dev(dev_t dev) { return MAJOR(dev) < (1<<14) && MINOR(dev) < (1<<18); } static __always_inline u32 sysv_encode_dev(dev_t dev) { return MINOR(dev) | (MAJOR(dev) << 18); } static __always_inline unsigned sysv_major(u32 dev) { return (dev >> 18) & 0x3fff; } static __always_inline unsigned sysv_minor(u32 dev) { return dev & 0x3ffff; } #endif |
| 849 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef __X86_KERNEL_FPU_INTERNAL_H #define __X86_KERNEL_FPU_INTERNAL_H extern struct fpstate init_fpstate; /* CPU feature check wrappers */ static __always_inline __pure bool use_xsave(void) { return cpu_feature_enabled(X86_FEATURE_XSAVE); } static __always_inline __pure bool use_fxsr(void) { return cpu_feature_enabled(X86_FEATURE_FXSR); } #ifdef CONFIG_X86_DEBUG_FPU # define WARN_ON_FPU(x) WARN_ON_ONCE(x) #else # define WARN_ON_FPU(x) ({ BUILD_BUG_ON_INVALID(x); 0; }) #endif /* Used in init.c */ extern void fpstate_init_user(struct fpstate *fpstate); extern void fpstate_reset(struct fpu *fpu); #endif |
| 6 6 5 6 6 6 6 6 1 1 1 1 1 1 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 | // SPDX-License-Identifier: GPL-2.0-only /* * vfsv0 quota IO operations on file */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/mount.h> #include <linux/dqblk_v2.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> #include <linux/slab.h> #include <linux/quotaops.h> #include <asm/byteorder.h> #include "quota_tree.h" #include "quotaio_v2.h" MODULE_AUTHOR("Jan Kara"); MODULE_DESCRIPTION("Quota format v2 support"); MODULE_LICENSE("GPL"); static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r0_disk2memdqb(struct dquot *dquot, void *dp); static int v2r0_is_id(void *dp, struct dquot *dquot); static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot); static void v2r1_disk2memdqb(struct dquot *dquot, void *dp); static int v2r1_is_id(void *dp, struct dquot *dquot); static const struct qtree_fmt_operations v2r0_qtree_ops = { .mem2disk_dqblk = v2r0_mem2diskdqb, .disk2mem_dqblk = v2r0_disk2memdqb, .is_id = v2r0_is_id, }; static const struct qtree_fmt_operations v2r1_qtree_ops = { .mem2disk_dqblk = v2r1_mem2diskdqb, .disk2mem_dqblk = v2r1_disk2memdqb, .is_id = v2r1_is_id, }; #define QUOTABLOCK_BITS 10 #define QUOTABLOCK_SIZE (1 << QUOTABLOCK_BITS) static inline qsize_t v2_stoqb(qsize_t space) { return (space + QUOTABLOCK_SIZE - 1) >> QUOTABLOCK_BITS; } static inline qsize_t v2_qbtos(qsize_t blocks) { return blocks << QUOTABLOCK_BITS; } static int v2_read_header(struct super_block *sb, int type, struct v2_disk_dqheader *dqhead) { ssize_t size; size = sb->s_op->quota_read(sb, type, (char *)dqhead, sizeof(struct v2_disk_dqheader), 0); if (size != sizeof(struct v2_disk_dqheader)) { quota_error(sb, "Failed header read: expected=%zd got=%zd", sizeof(struct v2_disk_dqheader), size); if (size < 0) return size; return -EIO; } return 0; } /* Check whether given file is really vfsv0 quotafile */ static int v2_check_quota_file(struct super_block *sb, int type) { struct v2_disk_dqheader dqhead; static const uint quota_magics[] = V2_INITQMAGICS; static const uint quota_versions[] = V2_INITQVERSIONS; if (v2_read_header(sb, type, &dqhead)) return 0; if (le32_to_cpu(dqhead.dqh_magic) != quota_magics[type] || le32_to_cpu(dqhead.dqh_version) > quota_versions[type]) return 0; return 1; } /* Read information header from quota file */ static int v2_read_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct v2_disk_dqheader dqhead; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo; ssize_t size; unsigned int version; unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = v2_read_header(sb, type, &dqhead); if (ret < 0) goto out; version = le32_to_cpu(dqhead.dqh_version); if ((info->dqi_fmt_id == QFMT_VFS_V0 && version != 0) || (info->dqi_fmt_id == QFMT_VFS_V1 && version != 1)) { ret = -EINVAL; goto out; } size = sb->s_op->quota_read(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't read info structure"); if (size < 0) ret = size; else ret = -EIO; goto out; } info->dqi_priv = kmalloc_obj(struct qtree_mem_dqinfo); if (!info->dqi_priv) { ret = -ENOMEM; goto out; } qinfo = info->dqi_priv; if (version == 0) { /* limits are stored as unsigned 32-bit data */ info->dqi_max_spc_limit = 0xffffffffLL << QUOTABLOCK_BITS; info->dqi_max_ino_limit = 0xffffffff; } else { /* * Used space is stored as unsigned 64-bit value in bytes but * quota core supports only signed 64-bit values so use that * as a limit */ info->dqi_max_spc_limit = 0x7fffffffffffffffLL; /* 2^63-1 */ info->dqi_max_ino_limit = 0x7fffffffffffffffLL; } info->dqi_bgrace = le32_to_cpu(dinfo.dqi_bgrace); info->dqi_igrace = le32_to_cpu(dinfo.dqi_igrace); /* No flags currently supported */ info->dqi_flags = 0; qinfo->dqi_sb = sb; qinfo->dqi_type = type; qinfo->dqi_blocks = le32_to_cpu(dinfo.dqi_blocks); qinfo->dqi_free_blk = le32_to_cpu(dinfo.dqi_free_blk); qinfo->dqi_free_entry = le32_to_cpu(dinfo.dqi_free_entry); qinfo->dqi_blocksize_bits = V2_DQBLKSIZE_BITS; qinfo->dqi_usable_bs = 1 << V2_DQBLKSIZE_BITS; qinfo->dqi_qtree_depth = qtree_depth(qinfo); if (version == 0) { qinfo->dqi_entry_size = sizeof(struct v2r0_disk_dqblk); qinfo->dqi_ops = &v2r0_qtree_ops; } else { qinfo->dqi_entry_size = sizeof(struct v2r1_disk_dqblk); qinfo->dqi_ops = &v2r1_qtree_ops; } ret = -EUCLEAN; /* Some sanity checks of the read headers... */ if ((loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits > i_size_read(sb_dqopt(sb)->files[type])) { quota_error(sb, "Number of blocks too big for quota file size (%llu > %llu).", (loff_t)qinfo->dqi_blocks << qinfo->dqi_blocksize_bits, i_size_read(sb_dqopt(sb)->files[type])); goto out_free; } if (qinfo->dqi_free_blk && (qinfo->dqi_free_blk <= QT_TREEOFF || qinfo->dqi_free_blk >= qinfo->dqi_blocks)) { quota_error(sb, "Free block number %u out of range (%u, %u).", qinfo->dqi_free_blk, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } if (qinfo->dqi_free_entry && (qinfo->dqi_free_entry <= QT_TREEOFF || qinfo->dqi_free_entry >= qinfo->dqi_blocks)) { quota_error(sb, "Block with free entry %u out of range (%u, %u).", qinfo->dqi_free_entry, QT_TREEOFF, qinfo->dqi_blocks); goto out_free; } ret = 0; out_free: if (ret) { kfree(info->dqi_priv); info->dqi_priv = NULL; } out: memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } /* Write information header to quota file */ static int v2_write_file_info(struct super_block *sb, int type) { struct v2_disk_dqinfo dinfo; struct quota_info *dqopt = sb_dqopt(sb); struct mem_dqinfo *info = &dqopt->info[type]; struct qtree_mem_dqinfo *qinfo = info->dqi_priv; ssize_t size; unsigned int memalloc; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); spin_lock(&dq_data_lock); info->dqi_flags &= ~DQF_INFO_DIRTY; dinfo.dqi_bgrace = cpu_to_le32(info->dqi_bgrace); dinfo.dqi_igrace = cpu_to_le32(info->dqi_igrace); /* No flags currently supported */ dinfo.dqi_flags = cpu_to_le32(0); spin_unlock(&dq_data_lock); dinfo.dqi_blocks = cpu_to_le32(qinfo->dqi_blocks); dinfo.dqi_free_blk = cpu_to_le32(qinfo->dqi_free_blk); dinfo.dqi_free_entry = cpu_to_le32(qinfo->dqi_free_entry); size = sb->s_op->quota_write(sb, type, (char *)&dinfo, sizeof(struct v2_disk_dqinfo), V2_DQINFOOFF); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); if (size != sizeof(struct v2_disk_dqinfo)) { quota_error(sb, "Can't write info structure"); return size < 0 ? size : -EIO; } return 0; } static void v2r0_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r0_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le32_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le32_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le32_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le32_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le32_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r0_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r0_disk_dqblk))) m->dqb_itime = 0; } static void v2r0_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le32(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le32(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le32(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le32(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le32(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r0_is_id(void *dp, struct dquot *dquot) { struct v2r0_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static void v2r1_disk2memdqb(struct dquot *dquot, void *dp) { struct v2r1_disk_dqblk *d = dp, empty; struct mem_dqblk *m = &dquot->dq_dqb; m->dqb_ihardlimit = le64_to_cpu(d->dqb_ihardlimit); m->dqb_isoftlimit = le64_to_cpu(d->dqb_isoftlimit); m->dqb_curinodes = le64_to_cpu(d->dqb_curinodes); m->dqb_itime = le64_to_cpu(d->dqb_itime); m->dqb_bhardlimit = v2_qbtos(le64_to_cpu(d->dqb_bhardlimit)); m->dqb_bsoftlimit = v2_qbtos(le64_to_cpu(d->dqb_bsoftlimit)); m->dqb_curspace = le64_to_cpu(d->dqb_curspace); m->dqb_btime = le64_to_cpu(d->dqb_btime); /* We need to escape back all-zero structure */ memset(&empty, 0, sizeof(struct v2r1_disk_dqblk)); empty.dqb_itime = cpu_to_le64(1); if (!memcmp(&empty, dp, sizeof(struct v2r1_disk_dqblk))) m->dqb_itime = 0; } static void v2r1_mem2diskdqb(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct mem_dqblk *m = &dquot->dq_dqb; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; d->dqb_ihardlimit = cpu_to_le64(m->dqb_ihardlimit); d->dqb_isoftlimit = cpu_to_le64(m->dqb_isoftlimit); d->dqb_curinodes = cpu_to_le64(m->dqb_curinodes); d->dqb_itime = cpu_to_le64(m->dqb_itime); d->dqb_bhardlimit = cpu_to_le64(v2_stoqb(m->dqb_bhardlimit)); d->dqb_bsoftlimit = cpu_to_le64(v2_stoqb(m->dqb_bsoftlimit)); d->dqb_curspace = cpu_to_le64(m->dqb_curspace); d->dqb_btime = cpu_to_le64(m->dqb_btime); d->dqb_id = cpu_to_le32(from_kqid(&init_user_ns, dquot->dq_id)); d->dqb_pad = 0; if (qtree_entry_unused(info, dp)) d->dqb_itime = cpu_to_le64(1); } static int v2r1_is_id(void *dp, struct dquot *dquot) { struct v2r1_disk_dqblk *d = dp; struct qtree_mem_dqinfo *info = sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv; if (qtree_entry_unused(info, dp)) return 0; return qid_eq(make_kqid(&init_user_ns, dquot->dq_id.type, le32_to_cpu(d->dqb_id)), dquot->dq_id); } static int v2_read_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; unsigned int memalloc; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_read_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static int v2_write_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); int ret; bool alloc = false; unsigned int memalloc; /* * If space for dquot is already allocated, we don't need any * protection as we'll only overwrite the place of dquot. We are * still protected by concurrent writes of the same dquot by * dquot->dq_lock. */ if (!dquot->dq_off) { alloc = true; down_write(&dqopt->dqio_sem); } else { down_read(&dqopt->dqio_sem); } memalloc = memalloc_nofs_save(); ret = qtree_write_dquot( sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); if (alloc) up_write(&dqopt->dqio_sem); else up_read(&dqopt->dqio_sem); return ret; } static int v2_release_dquot(struct dquot *dquot) { struct quota_info *dqopt = sb_dqopt(dquot->dq_sb); unsigned int memalloc; int ret; down_write(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_release_dquot(sb_dqinfo(dquot->dq_sb, dquot->dq_id.type)->dqi_priv, dquot); memalloc_nofs_restore(memalloc); up_write(&dqopt->dqio_sem); return ret; } static int v2_free_file_info(struct super_block *sb, int type) { kfree(sb_dqinfo(sb, type)->dqi_priv); return 0; } static int v2_get_next_id(struct super_block *sb, struct kqid *qid) { struct quota_info *dqopt = sb_dqopt(sb); unsigned int memalloc; int ret; down_read(&dqopt->dqio_sem); memalloc = memalloc_nofs_save(); ret = qtree_get_next_id(sb_dqinfo(sb, qid->type)->dqi_priv, qid); memalloc_nofs_restore(memalloc); up_read(&dqopt->dqio_sem); return ret; } static const struct quota_format_ops v2_format_ops = { .check_quota_file = v2_check_quota_file, .read_file_info = v2_read_file_info, .write_file_info = v2_write_file_info, .free_file_info = v2_free_file_info, .read_dqblk = v2_read_dquot, .commit_dqblk = v2_write_dquot, .release_dqblk = v2_release_dquot, .get_next_id = v2_get_next_id, }; static struct quota_format_type v2r0_quota_format = { .qf_fmt_id = QFMT_VFS_V0, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static struct quota_format_type v2r1_quota_format = { .qf_fmt_id = QFMT_VFS_V1, .qf_ops = &v2_format_ops, .qf_owner = THIS_MODULE }; static int __init init_v2_quota_format(void) { register_quota_format(&v2r0_quota_format); register_quota_format(&v2r1_quota_format); return 0; } static void __exit exit_v2_quota_format(void) { unregister_quota_format(&v2r0_quota_format); unregister_quota_format(&v2r1_quota_format); } module_init(init_v2_quota_format); module_exit(exit_v2_quota_format); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_CONTEXT_TRACKING_H #define _LINUX_CONTEXT_TRACKING_H #include <linux/sched.h> #include <linux/vtime.h> #include <linux/context_tracking_state.h> #include <linux/instrumentation.h> #include <asm/ptrace.h> #ifdef CONFIG_CONTEXT_TRACKING_USER extern void ct_cpu_track_user(int cpu); /* Called with interrupts disabled. */ extern void __ct_user_enter(enum ctx_state state); extern void __ct_user_exit(enum ctx_state state); extern void ct_user_enter(enum ctx_state state); extern void ct_user_exit(enum ctx_state state); extern void user_enter_callable(void); extern void user_exit_callable(void); static inline void user_enter(void) { if (context_tracking_enabled()) ct_user_enter(CT_STATE_USER); } static inline void user_exit(void) { if (context_tracking_enabled()) ct_user_exit(CT_STATE_USER); } /* Called with interrupts disabled. */ static __always_inline void user_enter_irqoff(void) { if (context_tracking_enabled()) __ct_user_enter(CT_STATE_USER); } static __always_inline void user_exit_irqoff(void) { if (context_tracking_enabled()) __ct_user_exit(CT_STATE_USER); } static inline enum ctx_state exception_enter(void) { enum ctx_state prev_ctx; if (IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) || !context_tracking_enabled()) return 0; prev_ctx = __ct_state(); if (prev_ctx != CT_STATE_KERNEL) ct_user_exit(prev_ctx); return prev_ctx; } static inline void exception_exit(enum ctx_state prev_ctx) { if (!IS_ENABLED(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK) && context_tracking_enabled()) { if (prev_ctx != CT_STATE_KERNEL) ct_user_enter(prev_ctx); } } static __always_inline bool context_tracking_guest_enter(void) { if (context_tracking_enabled()) __ct_user_enter(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } static __always_inline bool context_tracking_guest_exit(void) { if (context_tracking_enabled()) __ct_user_exit(CT_STATE_GUEST); return context_tracking_enabled_this_cpu(); } #define CT_WARN_ON(cond) WARN_ON(context_tracking_enabled() && (cond)) #else static inline void user_enter(void) { } static inline void user_exit(void) { } static inline void user_enter_irqoff(void) { } static inline void user_exit_irqoff(void) { } static inline int exception_enter(void) { return 0; } static inline void exception_exit(enum ctx_state prev_ctx) { } static inline int ct_state(void) { return -1; } static inline int __ct_state(void) { return -1; } static __always_inline bool context_tracking_guest_enter(void) { return false; } static __always_inline bool context_tracking_guest_exit(void) { return false; } #define CT_WARN_ON(cond) do { } while (0) #endif /* !CONFIG_CONTEXT_TRACKING_USER */ #ifdef CONFIG_CONTEXT_TRACKING_USER_FORCE extern void context_tracking_init(void); #else static inline void context_tracking_init(void) { } #endif /* CONFIG_CONTEXT_TRACKING_USER_FORCE */ #ifdef CONFIG_CONTEXT_TRACKING_IDLE extern void ct_idle_enter(void); extern void ct_idle_exit(void); /* * Is RCU watching the current CPU (IOW, it is not in an extended quiescent state)? * * Note that this returns the actual boolean data (watching / not watching), * whereas ct_rcu_watching() returns the RCU_WATCHING subvariable of * context_tracking.state. * * No ordering, as we are sampling CPU-local information. */ static __always_inline bool rcu_is_watching_curr_cpu(void) { return raw_atomic_read(this_cpu_ptr(&context_tracking.state)) & CT_RCU_WATCHING; } /* * Increment the current CPU's context_tracking structure's ->state field * with ordering. Return the new value. */ static __always_inline unsigned long ct_state_inc(int incby) { return raw_atomic_add_return(incby, this_cpu_ptr(&context_tracking.state)); } static __always_inline bool warn_rcu_enter(void) { bool ret = false; /* * Horrible hack to shut up recursive RCU isn't watching fail since * lots of the actual reporting also relies on RCU. */ preempt_disable_notrace(); if (!rcu_is_watching_curr_cpu()) { ret = true; ct_state_inc(CT_RCU_WATCHING); } return ret; } static __always_inline void warn_rcu_exit(bool rcu) { if (rcu) ct_state_inc(CT_RCU_WATCHING); preempt_enable_notrace(); } #else static inline void ct_idle_enter(void) { } static inline void ct_idle_exit(void) { } static __always_inline bool warn_rcu_enter(void) { return false; } static __always_inline void warn_rcu_exit(bool rcu) { } #endif /* !CONFIG_CONTEXT_TRACKING_IDLE */ #endif |
| 1 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 | // SPDX-License-Identifier: GPL-2.0-or-later /* * SNAP data link layer. Derived from 802.2 * * Alan Cox <alan@lxorguk.ukuu.org.uk>, * from the 802.2 layer by Greg Page. * Merged in additions from Greg Page's psnap.c. */ #include <linux/module.h> #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/slab.h> #include <net/datalink.h> #include <net/llc.h> #include <net/psnap.h> #include <linux/mm.h> #include <linux/in.h> #include <linux/init.h> #include <linux/rculist.h> static LIST_HEAD(snap_list); static DEFINE_SPINLOCK(snap_lock); static struct llc_sap *snap_sap; /* * Find a snap client by matching the 5 bytes. */ static struct datalink_proto *find_snap_client(const unsigned char *desc) { struct datalink_proto *proto = NULL, *p; list_for_each_entry_rcu(p, &snap_list, node, lockdep_is_held(&snap_lock)) { if (!memcmp(p->type, desc, 5)) { proto = p; break; } } return proto; } /* * A SNAP packet has arrived */ static int snap_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, struct net_device *orig_dev) { int rc = 1; struct datalink_proto *proto; static struct packet_type snap_packet_type = { .type = cpu_to_be16(ETH_P_SNAP), }; if (unlikely(!pskb_may_pull(skb, 5))) goto drop; rcu_read_lock(); proto = find_snap_client(skb->data); if (proto) { /* Pass the frame on. */ skb_pull_rcsum(skb, 5); skb_reset_transport_header(skb); rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev); } rcu_read_unlock(); if (unlikely(!proto)) goto drop; out: return rc; drop: kfree_skb(skb); goto out; } /* * Put a SNAP header on a frame and pass to 802.2 */ static int snap_request(struct datalink_proto *dl, struct sk_buff *skb, const u8 *dest) { memcpy(skb_push(skb, 5), dl->type, 5); llc_build_and_send_ui_pkt(snap_sap, skb, dest, snap_sap->laddr.lsap); return 0; } /* * Set up the SNAP layer */ EXPORT_SYMBOL(register_snap_client); EXPORT_SYMBOL(unregister_snap_client); static const char snap_err_msg[] __initconst = KERN_CRIT "SNAP - unable to register with 802.2\n"; static int __init snap_init(void) { snap_sap = llc_sap_open(0xAA, snap_rcv); if (!snap_sap) { printk(snap_err_msg); return -EBUSY; } return 0; } module_init(snap_init); static void __exit snap_exit(void) { llc_sap_put(snap_sap); } module_exit(snap_exit); /* * Register SNAP clients. We don't yet use this for IP. */ struct datalink_proto *register_snap_client(const unsigned char *desc, int (*rcvfunc)(struct sk_buff *, struct net_device *, struct packet_type *, struct net_device *)) { struct datalink_proto *proto = NULL; spin_lock_bh(&snap_lock); if (find_snap_client(desc)) goto out; proto = kmalloc_obj(*proto, GFP_ATOMIC); if (proto) { memcpy(proto->type, desc, 5); proto->rcvfunc = rcvfunc; proto->header_length = 5 + 3; /* snap + 802.2 */ proto->request = snap_request; list_add_rcu(&proto->node, &snap_list); } out: spin_unlock_bh(&snap_lock); return proto; } /* * Unregister SNAP clients. Protocols no longer want to play with us ... */ void unregister_snap_client(struct datalink_proto *proto) { spin_lock_bh(&snap_lock); list_del_rcu(&proto->node); spin_unlock_bh(&snap_lock); synchronize_net(); kfree(proto); } MODULE_DESCRIPTION("SNAP data link layer. Derived from 802.2"); MODULE_LICENSE("GPL"); |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* Copyright 2011-2014 Autronica Fire and Security AS * * Author(s): * 2011-2014 Arvid Brodin, arvid.brodin@alten.se * This file contains device methods for creating, using and destroying * virtual HSR or PRP devices. */ #include <linux/netdevice.h> #include <linux/skbuff.h> #include <linux/etherdevice.h> #include <linux/rtnetlink.h> #include <linux/pkt_sched.h> #include "hsr_device.h" #include "hsr_slave.h" #include "hsr_framereg.h" #include "hsr_main.h" #include "hsr_forward.h" static bool is_admin_up(struct net_device *dev) { return dev && (dev->flags & IFF_UP); } static bool is_slave_up(struct net_device *dev) { return dev && is_admin_up(dev) && netif_oper_up(dev); } static void hsr_set_operstate(struct hsr_port *master, bool has_carrier) { struct net_device *dev = master->dev; if (!is_admin_up(dev)) { netif_set_operstate(dev, IF_OPER_DOWN); return; } if (has_carrier) netif_set_operstate(dev, IF_OPER_UP); else netif_set_operstate(dev, IF_OPER_LOWERLAYERDOWN); } static bool hsr_check_carrier(struct hsr_port *master) { struct hsr_port *port; ASSERT_RTNL(); hsr_for_each_port_rtnl(master->hsr, port) { if (port->type != HSR_PT_MASTER && is_slave_up(port->dev)) { netif_carrier_on(master->dev); return true; } } netif_carrier_off(master->dev); return false; } static void hsr_check_announce(struct net_device *hsr_dev) { struct hsr_priv *hsr; hsr = netdev_priv(hsr_dev); if (netif_running(hsr_dev) && netif_oper_up(hsr_dev)) { /* Enable announce timer and start sending supervisory frames */ if (!timer_pending(&hsr->announce_timer)) { hsr->announce_count = 0; mod_timer(&hsr->announce_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL)); } if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer)) mod_timer(&hsr->announce_proxy_timer, jiffies + msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2); } else { /* Deactivate the announce timer */ timer_delete(&hsr->announce_timer); if (hsr->redbox) timer_delete(&hsr->announce_proxy_timer); } } void hsr_check_carrier_and_operstate(struct hsr_priv *hsr) { struct hsr_port *master; bool has_carrier; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); /* netif_stacked_transfer_operstate() cannot be used here since * it doesn't set IF_OPER_LOWERLAYERDOWN (?) */ has_carrier = hsr_check_carrier(master); hsr_set_operstate(master, has_carrier); hsr_check_announce(master->dev); } int hsr_get_max_mtu(struct hsr_priv *hsr) { unsigned int mtu_max; struct hsr_port *port; mtu_max = ETH_DATA_LEN; hsr_for_each_port_rtnl(hsr, port) if (port->type != HSR_PT_MASTER) mtu_max = min(port->dev->mtu, mtu_max); if (mtu_max < HSR_HLEN) return 0; return mtu_max - HSR_HLEN; } static int hsr_dev_change_mtu(struct net_device *dev, int new_mtu) { struct hsr_priv *hsr; hsr = netdev_priv(dev); if (new_mtu > hsr_get_max_mtu(hsr)) { netdev_info(dev, "A HSR master's MTU cannot be greater than the smallest MTU of its slaves minus the HSR Tag length (%d octets).\n", HSR_HLEN); return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } static int hsr_dev_open(struct net_device *dev) { struct hsr_priv *hsr; struct hsr_port *port; const char *designation = NULL; hsr = netdev_priv(dev); hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: designation = "Slave A"; break; case HSR_PT_SLAVE_B: designation = "Slave B"; break; case HSR_PT_INTERLINK: designation = "Interlink"; break; default: designation = "Unknown"; } if (!is_slave_up(port->dev)) netdev_warn(dev, "%s (%s) is not up; please bring it up to get a fully working HSR network\n", designation, port->dev->name); } if (!designation) netdev_warn(dev, "No slave devices configured\n"); return 0; } static int hsr_dev_close(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_uc_unsync(port->dev, dev); dev_mc_unsync(port->dev, dev); break; default: break; } } return 0; } static netdev_features_t hsr_features_recompute(struct hsr_priv *hsr, netdev_features_t features) { netdev_features_t mask; struct hsr_port *port; mask = features; /* Mask out all features that, if supported by one device, should be * enabled for all devices (see NETIF_F_ONE_FOR_ALL). * * Anything that's off in mask will not be enabled - so only things * that were in features originally, and also is in NETIF_F_ONE_FOR_ALL, * may become enabled. */ features &= ~NETIF_F_ONE_FOR_ALL; hsr_for_each_port_rtnl(hsr, port) features = netdev_increment_features(features, port->dev->features, mask); return features; } static netdev_features_t hsr_fix_features(struct net_device *dev, netdev_features_t features) { struct hsr_priv *hsr = netdev_priv(dev); return hsr_features_recompute(hsr, features); } static netdev_tx_t hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) { struct hsr_priv *hsr = netdev_priv(dev); struct hsr_port *master; rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (master) { skb->dev = master->dev; skb_reset_mac_header(skb); skb_reset_mac_len(skb); spin_lock_bh(&hsr->seqnr_lock); hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } else { dev_core_stats_tx_dropped_inc(dev); dev_kfree_skb_any(skb); } rcu_read_unlock(); return NETDEV_TX_OK; } static const struct header_ops hsr_header_ops = { .create = eth_header, .parse = eth_header_parse, }; static struct sk_buff *hsr_init_skb(struct hsr_port *master, int extra) { struct hsr_priv *hsr = master->hsr; struct sk_buff *skb; int hlen, tlen; int len; hlen = LL_RESERVED_SPACE(master->dev); tlen = master->dev->needed_tailroom; len = sizeof(struct hsr_sup_tag) + sizeof(struct hsr_sup_payload); /* skb size is same for PRP/HSR frames, only difference * being, for PRP it is a trailer and for HSR it is a * header. * RedBox might use @extra more bytes. */ skb = dev_alloc_skb(len + extra + hlen + tlen); if (!skb) return skb; skb_reserve(skb, hlen); skb->dev = master->dev; skb->priority = TC_PRIO_CONTROL; skb_reset_network_header(skb); skb_reset_transport_header(skb); if (dev_hard_header(skb, skb->dev, ETH_P_PRP, hsr->sup_multicast_addr, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); skb_reset_mac_len(skb); return skb; out: kfree_skb(skb); return NULL; } static void send_hsr_supervision_frame(struct hsr_port *port, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = port->hsr; __u8 type = HSR_TLV_LIFE_CHECK; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tlv *hsr_stlv; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; int extra = 0; *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); if (hsr->announce_count < 3 && hsr->prot_version == 0) { type = HSR_TLV_ANNOUNCE; *interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); hsr->announce_count++; } if (hsr->redbox) extra = sizeof(struct hsr_sup_tlv) + sizeof(struct hsr_sup_payload); skb = hsr_init_skb(port, extra); if (!skb) { netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n"); return; } hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); skb_set_network_header(skb, ETH_HLEN + HSR_HLEN); skb_reset_mac_len(skb); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, hsr->prot_version); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); if (hsr->prot_version > 0) { hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; } else { hsr_stag->sequence_nr = htons(hsr->sequence_nr); hsr->sequence_nr++; } hsr_stag->tlv.HSR_TLV_type = type; /* HSRv0 has 6 unused bytes after the MAC */ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ? sizeof(struct hsr_sup_payload) : 12; /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, addr); if (hsr->redbox && hsr_is_node_in_db(&hsr->proxy_node_db, addr)) { hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv)); hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC; hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressRedBox */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, hsr->macaddress_redbox); } if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, port); spin_unlock_bh(&hsr->seqnr_lock); return; } static void send_prp_supervision_frame(struct hsr_port *master, unsigned long *interval, const unsigned char *addr) { struct hsr_priv *hsr = master->hsr; struct hsr_sup_payload *hsr_sp; struct hsr_sup_tag *hsr_stag; struct sk_buff *skb; skb = hsr_init_skb(master, 0); if (!skb) { netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } *interval = msecs_to_jiffies(HSR_LIFE_CHECK_INTERVAL); hsr_stag = skb_put(skb, sizeof(struct hsr_sup_tag)); set_hsr_stag_path(hsr_stag, (hsr->prot_version ? 0x0 : 0xf)); set_hsr_stag_HSR_ver(hsr_stag, (hsr->prot_version ? 1 : 0)); /* From HSRv1 on we have separate supervision sequence numbers. */ spin_lock_bh(&hsr->seqnr_lock); hsr_stag->sequence_nr = htons(hsr->sup_sequence_nr); hsr->sup_sequence_nr++; hsr_stag->tlv.HSR_TLV_type = PRP_TLV_LIFE_CHECK_DD; hsr_stag->tlv.HSR_TLV_length = sizeof(struct hsr_sup_payload); /* Payload: MacAddressA */ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload)); ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr); if (skb_put_padto(skb, ETH_ZLEN)) { spin_unlock_bh(&hsr->seqnr_lock); return; } hsr_forward_skb(skb, master); spin_unlock_bh(&hsr->seqnr_lock); } /* Announce (supervision frame) timer function */ static void hsr_announce(struct timer_list *t) { struct hsr_priv *hsr; struct hsr_port *master; unsigned long interval; hsr = timer_container_of(hsr, t, announce_timer); rcu_read_lock(); master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr); if (is_admin_up(master->dev)) mod_timer(&hsr->announce_timer, jiffies + interval); rcu_read_unlock(); } /* Announce (supervision frame) timer function for RedBox */ static void hsr_proxy_announce(struct timer_list *t) { struct hsr_priv *hsr = timer_container_of(hsr, t, announce_proxy_timer); struct hsr_port *interlink; unsigned long interval = 0; struct hsr_node *node; rcu_read_lock(); /* RedBOX sends supervisory frames to HSR network with MAC addresses * of SAN nodes stored in ProxyNodeTable. */ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (!interlink) goto done; list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) { if (hsr_addr_is_redbox(hsr, node->macaddress_A)) continue; hsr->proto_ops->send_sv_frame(interlink, &interval, node->macaddress_A); } if (is_admin_up(interlink->dev)) { if (!interval) interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL); mod_timer(&hsr->announce_proxy_timer, jiffies + interval); } done: rcu_read_unlock(); } void hsr_del_ports(struct hsr_priv *hsr) { struct hsr_port *port; port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK); if (port) hsr_del_port(port); port = hsr_port_get_hsr(hsr, HSR_PT_MASTER); if (port) hsr_del_port(port); } static void hsr_set_rx_mode(struct net_device *dev) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: dev_mc_sync_multiple(port->dev, dev); dev_uc_sync_multiple(port->dev, dev); break; default: break; } } } static void hsr_change_rx_flags(struct net_device *dev, int change) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER) continue; switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: if (change & IFF_ALLMULTI) dev_set_allmulti(port->dev, dev->flags & IFF_ALLMULTI ? 1 : -1); break; default: break; } } } static int hsr_ndo_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { struct net_device *slave_a_dev = NULL; struct net_device *slave_b_dev = NULL; struct hsr_port *port; struct hsr_priv *hsr; int ret = 0; hsr = netdev_priv(dev); hsr_for_each_port_rtnl(hsr, port) { if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) continue; ret = vlan_vid_add(port->dev, proto, vid); switch (port->type) { case HSR_PT_SLAVE_A: if (ret) { netdev_err(dev, "add vid failed for Slave-A\n"); goto unwind; } slave_a_dev = port->dev; break; case HSR_PT_SLAVE_B: if (ret) { netdev_err(dev, "add vid failed for Slave-B\n"); goto unwind; } slave_b_dev = port->dev; break; default: if (ret) goto unwind; break; } } return 0; unwind: if (slave_a_dev) vlan_vid_del(slave_a_dev, proto, vid); if (slave_b_dev) vlan_vid_del(slave_b_dev, proto, vid); return ret; } static int hsr_ndo_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid) { struct hsr_port *port; struct hsr_priv *hsr; hsr = netdev_priv(dev); hsr_for_each_port_rtnl(hsr, port) { switch (port->type) { case HSR_PT_SLAVE_A: case HSR_PT_SLAVE_B: vlan_vid_del(port->dev, proto, vid); break; default: break; } } return 0; } static const struct net_device_ops hsr_device_ops = { .ndo_change_mtu = hsr_dev_change_mtu, .ndo_open = hsr_dev_open, .ndo_stop = hsr_dev_close, .ndo_start_xmit = hsr_dev_xmit, .ndo_change_rx_flags = hsr_change_rx_flags, .ndo_fix_features = hsr_fix_features, .ndo_set_rx_mode = hsr_set_rx_mode, .ndo_vlan_rx_add_vid = hsr_ndo_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hsr_ndo_vlan_rx_kill_vid, }; static const struct device_type hsr_type = { .name = "hsr", }; static const struct hsr_proto_ops hsr_ops = { .send_sv_frame = send_hsr_supervision_frame, .create_tagged_frame = hsr_create_tagged_frame, .get_untagged_frame = hsr_get_untagged_frame, .drop_frame = hsr_drop_frame, .fill_frame_info = hsr_fill_frame_info, .invalid_dan_ingress_frame = hsr_invalid_dan_ingress_frame, .register_frame_out = hsr_register_frame_out, }; static const struct hsr_proto_ops prp_ops = { .send_sv_frame = send_prp_supervision_frame, .create_tagged_frame = prp_create_tagged_frame, .get_untagged_frame = prp_get_untagged_frame, .drop_frame = prp_drop_frame, .fill_frame_info = prp_fill_frame_info, .handle_san_frame = prp_handle_san_frame, .update_san_info = prp_update_san_info, .register_frame_out = prp_register_frame_out, }; void hsr_dev_setup(struct net_device *dev) { eth_hw_addr_random(dev); ether_setup(dev); dev->min_mtu = 0; dev->header_ops = &hsr_header_ops; dev->netdev_ops = &hsr_device_ops; SET_NETDEV_DEVTYPE(dev, &hsr_type); dev->priv_flags |= IFF_NO_QUEUE | IFF_DISABLE_NETPOLL; /* Prevent recursive tx locking */ dev->lltx = true; /* Not sure about this. Taken from bridge code. netdevice.h says * it means "Does not change network namespaces". */ dev->netns_immutable = true; dev->needs_free_netdev = true; dev->hw_features = NETIF_F_SG | NETIF_F_FRAGLIST | NETIF_F_HIGHDMA | NETIF_F_GSO_MASK | NETIF_F_HW_CSUM | NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_FILTER; dev->features = dev->hw_features; } /* Return true if dev is a HSR master; return false otherwise. */ bool is_hsr_master(struct net_device *dev) { return (dev->netdev_ops->ndo_start_xmit == hsr_dev_xmit); } EXPORT_SYMBOL(is_hsr_master); struct net_device *hsr_get_port_ndev(struct net_device *ndev, enum hsr_port_type pt) { struct hsr_priv *hsr = netdev_priv(ndev); struct hsr_port *port; rcu_read_lock(); hsr_for_each_port(hsr, port) if (port->type == pt) { dev_hold(port->dev); rcu_read_unlock(); return port->dev; } rcu_read_unlock(); return NULL; } EXPORT_SYMBOL(hsr_get_port_ndev); int hsr_get_port_type(struct net_device *hsr_dev, struct net_device *dev, enum hsr_port_type *type) { struct hsr_priv *hsr = netdev_priv(hsr_dev); struct hsr_port *port; rcu_read_lock(); hsr_for_each_port(hsr, port) { if (port->dev == dev) { *type = port->type; rcu_read_unlock(); return 0; } } rcu_read_unlock(); return -EINVAL; } EXPORT_SYMBOL(hsr_get_port_type); /* Default multicast address for HSR Supervision frames */ static const unsigned char def_multicast_addr[ETH_ALEN] __aligned(2) = { 0x01, 0x15, 0x4e, 0x00, 0x01, 0x00 }; int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], struct net_device *interlink, unsigned char multicast_spec, u8 protocol_version, struct netlink_ext_ack *extack) { bool unregister = false; struct hsr_priv *hsr; int res; hsr = netdev_priv(hsr_dev); INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->proxy_node_db); spin_lock_init(&hsr->list_lock); eth_hw_addr_set(hsr_dev, slave[0]->dev_addr); /* initialize protocol specific functions */ if (protocol_version == PRP_V1) { /* For PRP, lan_id has most significant 3 bits holding * the net_id of PRP_LAN_ID */ hsr->net_id = PRP_LAN_ID << 1; hsr->proto_ops = &prp_ops; } else { hsr->proto_ops = &hsr_ops; } /* Make sure we recognize frames from ourselves in hsr_handle_frame() */ res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; spin_lock_init(&hsr->seqnr_lock); /* Overflow soon to find bugs easier: */ hsr->sequence_nr = HSR_SEQNR_START; hsr->sup_sequence_nr = HSR_SUP_SEQNR_START; timer_setup(&hsr->announce_timer, hsr_announce, 0); timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0); timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0); timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0); ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr); hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec; hsr->prot_version = protocol_version; /* Make sure the 1st call to netif_carrier_on() gets through */ netif_carrier_off(hsr_dev); res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER, extack); if (res) goto err_add_master; /* HSR forwarding offload supported in lower device? */ if ((slave[0]->features & NETIF_F_HW_HSR_FWD) && (slave[1]->features & NETIF_F_HW_HSR_FWD)) hsr->fwd_offloaded = true; if ((slave[0]->features & NETIF_F_HW_VLAN_CTAG_FILTER) && (slave[1]->features & NETIF_F_HW_VLAN_CTAG_FILTER)) hsr_dev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; res = register_netdevice(hsr_dev); if (res) goto err_unregister; unregister = true; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A, extack); if (res) goto err_unregister; res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B, extack); if (res) goto err_unregister; if (protocol_version == PRP_V1) { eth_hw_addr_set(slave[1], slave[0]->dev_addr); call_netdevice_notifiers(NETDEV_CHANGEADDR, slave[1]); } if (interlink) { res = hsr_add_port(hsr, interlink, HSR_PT_INTERLINK, extack); if (res) goto err_unregister; hsr->redbox = true; ether_addr_copy(hsr->macaddress_redbox, interlink->dev_addr); mod_timer(&hsr->prune_proxy_timer, jiffies + msecs_to_jiffies(PRUNE_PROXY_PERIOD)); } hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); return 0; err_unregister: hsr_del_ports(hsr); err_add_master: hsr_del_self_node(hsr); if (unregister) unregister_netdevice(hsr_dev); return res; } |
| 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 | /* * Copyright (C) 2017 Netronome Systems, Inc. * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this * source tree. * * THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE PROGRAM "AS IS" * WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED, INCLUDING, * BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS * FOR A PARTICULAR PURPOSE. THE ENTIRE RISK AS TO THE QUALITY AND PERFORMANCE * OF THE PROGRAM IS WITH YOU. SHOULD THE PROGRAM PROVE DEFECTIVE, YOU ASSUME * THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION. */ #include <linux/bpf.h> #include <linux/bpf_verifier.h> #include <linux/debugfs.h> #include <linux/kernel.h> #include <linux/mutex.h> #include <linux/rtnetlink.h> #include <net/pkt_cls.h> #include "netdevsim.h" #define pr_vlog(env, fmt, ...) \ bpf_verifier_log_write(env, "[netdevsim] " fmt, ##__VA_ARGS__) struct nsim_bpf_bound_prog { struct nsim_dev *nsim_dev; struct bpf_prog *prog; struct dentry *ddir; const char *state; bool is_loaded; struct list_head l; }; #define NSIM_BPF_MAX_KEYS 2 struct nsim_bpf_bound_map { struct netdevsim *ns; struct bpf_offloaded_map *map; struct mutex mutex; struct nsim_map_entry { void *key; void *value; } entry[NSIM_BPF_MAX_KEYS]; struct list_head l; }; static int nsim_bpf_string_show(struct seq_file *file, void *data) { const char **str = file->private; if (*str) seq_printf(file, "%s\n", *str); return 0; } DEFINE_SHOW_ATTRIBUTE(nsim_bpf_string); static int nsim_bpf_verify_insn(struct bpf_verifier_env *env, int insn_idx, int prev_insn) { struct nsim_bpf_bound_prog *state; int ret = 0; state = env->prog->aux->offload->dev_priv; if (state->nsim_dev->bpf_bind_verifier_delay && !insn_idx) msleep(state->nsim_dev->bpf_bind_verifier_delay); if (insn_idx == env->prog->len - 1) { pr_vlog(env, "Hello from netdevsim!\n"); if (!state->nsim_dev->bpf_bind_verifier_accept) ret = -EOPNOTSUPP; } return ret; } static int nsim_bpf_finalize(struct bpf_verifier_env *env) { return 0; } static bool nsim_xdp_offload_active(struct netdevsim *ns) { return ns->xdp_hw.prog; } static void nsim_prog_set_loaded(struct bpf_prog *prog, bool loaded) { struct nsim_bpf_bound_prog *state; if (!prog || !bpf_prog_is_offloaded(prog->aux)) return; state = prog->aux->offload->dev_priv; state->is_loaded = loaded; } static int nsim_bpf_offload(struct netdevsim *ns, struct bpf_prog *prog, bool oldprog) { nsim_prog_set_loaded(ns->bpf_offloaded, false); WARN(!!ns->bpf_offloaded != oldprog, "bad offload state, expected offload %sto be active", oldprog ? "" : "not "); ns->bpf_offloaded = prog; ns->bpf_offloaded_id = prog ? prog->aux->id : 0; nsim_prog_set_loaded(prog, true); return 0; } int nsim_bpf_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_priv) { struct tc_cls_bpf_offload *cls_bpf = type_data; struct bpf_prog *prog = cls_bpf->prog; struct netdevsim *ns = cb_priv; struct bpf_prog *oldprog; if (!tc_cls_can_offload_and_chain0(ns->netdev, &cls_bpf->common)) return -EOPNOTSUPP; if (cls_bpf->common.protocol != htons(ETH_P_ALL)) { NSIM_EA(cls_bpf->common.extack, "only ETH_P_ALL supported as filter protocol"); return -EOPNOTSUPP; } if (!ns->bpf_tc_accept) { NSIM_EA(cls_bpf->common.extack, "netdevsim configured to reject BPF TC offload"); return -EOPNOTSUPP; } /* Note: progs without skip_sw will probably not be dev bound */ if (prog && !prog->aux->offload && !ns->bpf_tc_non_bound_accept) { NSIM_EA(cls_bpf->common.extack, "netdevsim configured to reject unbound programs"); return -EOPNOTSUPP; } if (cls_bpf->command != TC_CLSBPF_OFFLOAD) return -EOPNOTSUPP; oldprog = cls_bpf->oldprog; /* Don't remove if oldprog doesn't match driver's state */ if (ns->bpf_offloaded != oldprog) { oldprog = NULL; if (!cls_bpf->prog) return 0; if (ns->bpf_offloaded) { NSIM_EA(cls_bpf->common.extack, "driver and netdev offload states mismatch"); return -EBUSY; } } return nsim_bpf_offload(ns, cls_bpf->prog, oldprog); } int nsim_bpf_disable_tc(struct netdevsim *ns) { if (ns->bpf_offloaded && !nsim_xdp_offload_active(ns)) return -EBUSY; return 0; } static int nsim_xdp_offload_prog(struct netdevsim *ns, struct netdev_bpf *bpf) { if (!nsim_xdp_offload_active(ns) && !bpf->prog) return 0; if (!nsim_xdp_offload_active(ns) && bpf->prog && ns->bpf_offloaded) { NSIM_EA(bpf->extack, "TC program is already loaded"); return -EBUSY; } return nsim_bpf_offload(ns, bpf->prog, nsim_xdp_offload_active(ns)); } static int nsim_xdp_set_prog(struct netdevsim *ns, struct netdev_bpf *bpf, struct xdp_attachment_info *xdp) { int err; if (bpf->command == XDP_SETUP_PROG && !ns->bpf_xdpdrv_accept) { NSIM_EA(bpf->extack, "driver XDP disabled in DebugFS"); return -EOPNOTSUPP; } if (bpf->command == XDP_SETUP_PROG_HW && !ns->bpf_xdpoffload_accept) { NSIM_EA(bpf->extack, "XDP offload disabled in DebugFS"); return -EOPNOTSUPP; } if (bpf->command == XDP_SETUP_PROG_HW) { err = nsim_xdp_offload_prog(ns, bpf); if (err) return err; } xdp_attachment_setup(xdp, bpf); return 0; } static int nsim_bpf_create_prog(struct nsim_dev *nsim_dev, struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state; char name[16]; int ret; state = kzalloc_obj(*state); if (!state) return -ENOMEM; state->nsim_dev = nsim_dev; state->prog = prog; state->state = "verify"; /* Program id is not populated yet when we create the state. */ sprintf(name, "%u", nsim_dev->prog_id_gen++); state->ddir = debugfs_create_dir(name, nsim_dev->ddir_bpf_bound_progs); if (IS_ERR(state->ddir)) { ret = PTR_ERR(state->ddir); kfree(state); return ret; } debugfs_create_u32("id", 0400, state->ddir, &prog->aux->id); debugfs_create_file("state", 0400, state->ddir, &state->state, &nsim_bpf_string_fops); debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded); mutex_lock(&nsim_dev->progs_list_lock); list_add_tail(&state->l, &nsim_dev->bpf_bound_progs); mutex_unlock(&nsim_dev->progs_list_lock); prog->aux->offload->dev_priv = state; return 0; } static int nsim_bpf_verifier_prep(struct bpf_prog *prog) { struct nsim_dev *nsim_dev = bpf_offload_dev_priv(prog->aux->offload->offdev); if (!nsim_dev->bpf_bind_accept) return -EOPNOTSUPP; return nsim_bpf_create_prog(nsim_dev, prog); } static int nsim_bpf_translate(struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state = prog->aux->offload->dev_priv; state->state = "xlated"; return 0; } static void nsim_bpf_destroy_prog(struct bpf_prog *prog) { struct nsim_bpf_bound_prog *state; struct nsim_dev *nsim_dev; state = prog->aux->offload->dev_priv; nsim_dev = state->nsim_dev; WARN(state->is_loaded, "offload state destroyed while program still bound"); debugfs_remove_recursive(state->ddir); mutex_lock(&nsim_dev->progs_list_lock); list_del(&state->l); mutex_unlock(&nsim_dev->progs_list_lock); kfree(state); } static const struct bpf_prog_offload_ops nsim_bpf_dev_ops = { .insn_hook = nsim_bpf_verify_insn, .finalize = nsim_bpf_finalize, .prepare = nsim_bpf_verifier_prep, .translate = nsim_bpf_translate, .destroy = nsim_bpf_destroy_prog, }; static int nsim_setup_prog_checks(struct netdevsim *ns, struct netdev_bpf *bpf) { if (bpf->prog && bpf->prog->aux->offload) { NSIM_EA(bpf->extack, "attempt to load offloaded prog to drv"); return -EINVAL; } if (bpf->prog && !bpf->prog->aux->xdp_has_frags && ns->netdev->mtu > NSIM_XDP_MAX_MTU) { NSIM_EA(bpf->extack, "MTU too large w/ XDP enabled"); return -EINVAL; } return 0; } static int nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf) { struct nsim_bpf_bound_prog *state; if (!bpf->prog) return 0; if (!bpf_prog_is_offloaded(bpf->prog->aux)) { NSIM_EA(bpf->extack, "xdpoffload of non-bound program"); return -EINVAL; } state = bpf->prog->aux->offload->dev_priv; if (WARN_ON(strcmp(state->state, "xlated"))) { NSIM_EA(bpf->extack, "offloading program in bad state"); return -EINVAL; } return 0; } static bool nsim_map_key_match(struct bpf_map *map, struct nsim_map_entry *e, void *key) { return e->key && !memcmp(key, e->key, map->key_size); } static int nsim_map_key_find(struct bpf_offloaded_map *offmap, void *key) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; unsigned int i; for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) if (nsim_map_key_match(&offmap->map, &nmap->entry[i], key)) return i; return -ENOENT; } static int nsim_map_alloc_elem(struct bpf_offloaded_map *offmap, unsigned int idx) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; nmap->entry[idx].key = kmalloc(offmap->map.key_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!nmap->entry[idx].key) return -ENOMEM; nmap->entry[idx].value = kmalloc(offmap->map.value_size, GFP_KERNEL_ACCOUNT | __GFP_NOWARN); if (!nmap->entry[idx].value) { kfree(nmap->entry[idx].key); nmap->entry[idx].key = NULL; return -ENOMEM; } return 0; } static int nsim_map_get_next_key(struct bpf_offloaded_map *offmap, void *key, void *next_key) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; int idx = -ENOENT; mutex_lock(&nmap->mutex); if (key) idx = nsim_map_key_find(offmap, key); if (idx == -ENOENT) idx = 0; else idx++; for (; idx < ARRAY_SIZE(nmap->entry); idx++) { if (nmap->entry[idx].key) { memcpy(next_key, nmap->entry[idx].key, offmap->map.key_size); break; } } mutex_unlock(&nmap->mutex); if (idx == ARRAY_SIZE(nmap->entry)) return -ENOENT; return 0; } static int nsim_map_lookup_elem(struct bpf_offloaded_map *offmap, void *key, void *value) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; int idx; mutex_lock(&nmap->mutex); idx = nsim_map_key_find(offmap, key); if (idx >= 0) memcpy(value, nmap->entry[idx].value, offmap->map.value_size); mutex_unlock(&nmap->mutex); return idx < 0 ? idx : 0; } static int nsim_map_update_elem(struct bpf_offloaded_map *offmap, void *key, void *value, u64 flags) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; int idx, err = 0; mutex_lock(&nmap->mutex); idx = nsim_map_key_find(offmap, key); if (idx < 0 && flags == BPF_EXIST) { err = idx; goto exit_unlock; } if (idx >= 0 && flags == BPF_NOEXIST) { err = -EEXIST; goto exit_unlock; } if (idx < 0) { for (idx = 0; idx < ARRAY_SIZE(nmap->entry); idx++) if (!nmap->entry[idx].key) break; if (idx == ARRAY_SIZE(nmap->entry)) { err = -E2BIG; goto exit_unlock; } err = nsim_map_alloc_elem(offmap, idx); if (err) goto exit_unlock; } memcpy(nmap->entry[idx].key, key, offmap->map.key_size); memcpy(nmap->entry[idx].value, value, offmap->map.value_size); exit_unlock: mutex_unlock(&nmap->mutex); return err; } static int nsim_map_delete_elem(struct bpf_offloaded_map *offmap, void *key) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; int idx; if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY) return -EINVAL; mutex_lock(&nmap->mutex); idx = nsim_map_key_find(offmap, key); if (idx >= 0) { kfree(nmap->entry[idx].key); kfree(nmap->entry[idx].value); memset(&nmap->entry[idx], 0, sizeof(nmap->entry[idx])); } mutex_unlock(&nmap->mutex); return idx < 0 ? idx : 0; } static const struct bpf_map_dev_ops nsim_bpf_map_ops = { .map_get_next_key = nsim_map_get_next_key, .map_lookup_elem = nsim_map_lookup_elem, .map_update_elem = nsim_map_update_elem, .map_delete_elem = nsim_map_delete_elem, }; static int nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) { struct nsim_bpf_bound_map *nmap; int i, err; if (WARN_ON(offmap->map.map_type != BPF_MAP_TYPE_ARRAY && offmap->map.map_type != BPF_MAP_TYPE_HASH)) return -EINVAL; if (offmap->map.max_entries > NSIM_BPF_MAX_KEYS) return -ENOMEM; if (offmap->map.map_flags) return -EINVAL; nmap = kzalloc_obj(*nmap, GFP_KERNEL_ACCOUNT); if (!nmap) return -ENOMEM; offmap->dev_priv = nmap; nmap->ns = ns; nmap->map = offmap; mutex_init(&nmap->mutex); if (offmap->map.map_type == BPF_MAP_TYPE_ARRAY) { for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) { u32 *key; err = nsim_map_alloc_elem(offmap, i); if (err) goto err_free; key = nmap->entry[i].key; *key = i; memset(nmap->entry[i].value, 0, offmap->map.value_size); } } offmap->dev_ops = &nsim_bpf_map_ops; list_add_tail(&nmap->l, &ns->nsim_dev->bpf_bound_maps); return 0; err_free: while (--i >= 0) { kfree(nmap->entry[i].key); kfree(nmap->entry[i].value); } kfree(nmap); return err; } static void nsim_bpf_map_free(struct bpf_offloaded_map *offmap) { struct nsim_bpf_bound_map *nmap = offmap->dev_priv; unsigned int i; for (i = 0; i < ARRAY_SIZE(nmap->entry); i++) { kfree(nmap->entry[i].key); kfree(nmap->entry[i].value); } list_del_init(&nmap->l); mutex_destroy(&nmap->mutex); kfree(nmap); } int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) { struct netdevsim *ns = netdev_priv(dev); int err; ASSERT_RTNL(); switch (bpf->command) { case XDP_SETUP_PROG: err = nsim_setup_prog_checks(ns, bpf); if (err) return err; return nsim_xdp_set_prog(ns, bpf, &ns->xdp); case XDP_SETUP_PROG_HW: err = nsim_setup_prog_hw_checks(ns, bpf); if (err) return err; return nsim_xdp_set_prog(ns, bpf, &ns->xdp_hw); case BPF_OFFLOAD_MAP_ALLOC: if (!ns->bpf_map_accept) return -EOPNOTSUPP; return nsim_bpf_map_alloc(ns, bpf->offmap); case BPF_OFFLOAD_MAP_FREE: nsim_bpf_map_free(bpf->offmap); return 0; default: return -EINVAL; } } int nsim_bpf_dev_init(struct nsim_dev *nsim_dev) { int err; INIT_LIST_HEAD(&nsim_dev->bpf_bound_progs); INIT_LIST_HEAD(&nsim_dev->bpf_bound_maps); nsim_dev->ddir_bpf_bound_progs = debugfs_create_dir("bpf_bound_progs", nsim_dev->ddir); if (IS_ERR(nsim_dev->ddir_bpf_bound_progs)) return PTR_ERR(nsim_dev->ddir_bpf_bound_progs); nsim_dev->bpf_dev = bpf_offload_dev_create(&nsim_bpf_dev_ops, nsim_dev); err = PTR_ERR_OR_ZERO(nsim_dev->bpf_dev); if (err) return err; nsim_dev->bpf_bind_accept = true; debugfs_create_bool("bpf_bind_accept", 0600, nsim_dev->ddir, &nsim_dev->bpf_bind_accept); debugfs_create_u32("bpf_bind_verifier_delay", 0600, nsim_dev->ddir, &nsim_dev->bpf_bind_verifier_delay); nsim_dev->bpf_bind_verifier_accept = true; debugfs_create_bool("bpf_bind_verifier_accept", 0600, nsim_dev->ddir, &nsim_dev->bpf_bind_verifier_accept); return 0; } void nsim_bpf_dev_exit(struct nsim_dev *nsim_dev) { WARN_ON(!list_empty(&nsim_dev->bpf_bound_progs)); WARN_ON(!list_empty(&nsim_dev->bpf_bound_maps)); bpf_offload_dev_destroy(nsim_dev->bpf_dev); } int nsim_bpf_init(struct netdevsim *ns) { struct dentry *ddir = ns->nsim_dev_port->ddir; int err; err = bpf_offload_dev_netdev_register(ns->nsim_dev->bpf_dev, ns->netdev); if (err) return err; debugfs_create_u32("bpf_offloaded_id", 0400, ddir, &ns->bpf_offloaded_id); ns->bpf_tc_accept = true; debugfs_create_bool("bpf_tc_accept", 0600, ddir, &ns->bpf_tc_accept); debugfs_create_bool("bpf_tc_non_bound_accept", 0600, ddir, &ns->bpf_tc_non_bound_accept); ns->bpf_xdpdrv_accept = true; debugfs_create_bool("bpf_xdpdrv_accept", 0600, ddir, &ns->bpf_xdpdrv_accept); ns->bpf_xdpoffload_accept = true; debugfs_create_bool("bpf_xdpoffload_accept", 0600, ddir, &ns->bpf_xdpoffload_accept); ns->bpf_map_accept = true; debugfs_create_bool("bpf_map_accept", 0600, ddir, &ns->bpf_map_accept); return 0; } void nsim_bpf_uninit(struct netdevsim *ns) { WARN_ON(ns->xdp.prog); WARN_ON(ns->xdp_hw.prog); WARN_ON(ns->bpf_offloaded); bpf_offload_dev_netdev_unregister(ns->nsim_dev->bpf_dev, ns->netdev); } |
| 1 1 1 1 15 16 11 15 16 16 16 5 5 11 8 8 1 1 4 4 5 1 4 5 1 1 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 1582 1583 1584 1585 1586 1587 1588 1589 1590 1591 1592 1593 1594 1595 1596 1597 1598 1599 1600 1601 1602 1603 1604 1605 1606 1607 1608 1609 1610 1611 1612 1613 1614 1615 1616 1617 1618 1619 1620 1621 1622 1623 1624 1625 1626 1627 1628 1629 1630 1631 1632 1633 1634 1635 1636 1637 1638 1639 1640 1641 1642 1643 1644 1645 1646 1647 1648 1649 1650 1651 1652 1653 1654 1655 1656 1657 1658 1659 1660 1661 1662 1663 1664 1665 1666 1667 1668 1669 1670 1671 1672 1673 1674 1675 1676 1677 1678 1679 1680 1681 1682 1683 1684 1685 1686 1687 1688 1689 1690 1691 1692 1693 1694 1695 1696 1697 1698 1699 1700 1701 1702 1703 1704 1705 1706 1707 1708 1709 1710 1711 1712 1713 1714 1715 1716 1717 1718 1719 1720 1721 1722 1723 1724 1725 1726 1727 1728 1729 1730 1731 1732 1733 1734 1735 1736 1737 1738 1739 1740 1741 1742 1743 1744 1745 1746 1747 1748 1749 1750 1751 1752 1753 1754 1755 1756 1757 1758 1759 1760 1761 1762 1763 1764 1765 1766 1767 1768 1769 1770 1771 1772 1773 1774 1775 1776 1777 1778 1779 1780 1781 1782 1783 1784 1785 1786 1787 1788 1789 1790 1791 1792 1793 1794 1795 1796 1797 1798 1799 1800 1801 1802 1803 1804 1805 1806 1807 1808 1809 1810 1811 1812 1813 1814 1815 1816 1817 1818 1819 1820 1821 1822 1823 1824 1825 1826 1827 1828 1829 1830 1831 1832 1833 1834 1835 1836 1837 1838 1839 1840 1841 1842 1843 1844 1845 1846 1847 1848 1849 1850 1851 1852 1853 1854 1855 1856 1857 1858 1859 1860 1861 1862 1863 1864 1865 1866 1867 1868 1869 1870 1871 1872 1873 1874 1875 1876 1877 1878 1879 1880 1881 1882 1883 1884 1885 1886 1887 1888 1889 1890 1891 1892 1893 1894 1895 1896 1897 1898 1899 1900 1901 1902 1903 1904 1905 1906 1907 1908 1909 1910 1911 1912 1913 1914 1915 1916 1917 1918 1919 1920 1921 1922 1923 1924 1925 1926 1927 1928 1929 1930 1931 1932 1933 1934 1935 1936 1937 1938 1939 1940 1941 1942 1943 1944 1945 1946 1947 1948 1949 1950 1951 1952 1953 1954 1955 1956 1957 1958 1959 1960 1961 1962 1963 1964 1965 1966 1967 1968 1969 1970 1971 1972 1973 1974 1975 1976 1977 1978 1979 1980 1981 1982 1983 1984 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 2015 2016 2017 2018 2019 2020 2021 2022 2023 2024 2025 2026 2027 2028 2029 2030 2031 2032 2033 2034 2035 2036 2037 2038 2039 2040 2041 2042 2043 2044 2045 2046 2047 2048 2049 2050 2051 2052 2053 2054 2055 2056 2057 2058 2059 2060 2061 2062 2063 2064 2065 2066 2067 2068 2069 2070 2071 2072 2073 2074 2075 2076 2077 2078 2079 2080 2081 2082 2083 2084 2085 2086 2087 2088 2089 2090 2091 2092 2093 2094 2095 2096 2097 2098 2099 2100 2101 2102 2103 2104 2105 2106 2107 2108 2109 2110 2111 2112 2113 2114 2115 2116 2117 2118 2119 2120 2121 2122 2123 2124 2125 2126 2127 2128 2129 2130 2131 2132 2133 2134 2135 2136 2137 2138 2139 2140 2141 2142 2143 2144 2145 2146 2147 2148 2149 2150 2151 2152 2153 2154 2155 2156 2157 2158 2159 2160 2161 2162 2163 2164 2165 2166 2167 2168 2169 2170 2171 2172 2173 2174 2175 2176 2177 2178 2179 2180 2181 2182 2183 2184 2185 2186 2187 2188 2189 2190 2191 2192 2193 2194 2195 2196 2197 2198 2199 2200 2201 2202 2203 2204 2205 2206 2207 2208 2209 2210 2211 2212 2213 2214 2215 2216 2217 2218 2219 2220 2221 2222 2223 2224 2225 2226 2227 2228 2229 2230 2231 2232 2233 2234 2235 2236 2237 2238 2239 2240 2241 2242 2243 2244 2245 2246 2247 2248 2249 2250 2251 2252 2253 2254 2255 2256 2257 2258 2259 2260 2261 2262 2263 2264 2265 2266 2267 2268 2269 2270 2271 2272 2273 2274 2275 2276 2277 2278 2279 2280 2281 2282 2283 2284 2285 2286 2287 2288 2289 2290 2291 2292 2293 2294 2295 2296 2297 2298 2299 2300 2301 2302 2303 2304 2305 2306 2307 2308 2309 2310 2311 2312 2313 2314 2315 2316 2317 2318 2319 2320 2321 2322 2323 2324 2325 2326 2327 2328 2329 2330 2331 2332 2333 2334 2335 2336 2337 2338 2339 2340 2341 2342 2343 2344 2345 2346 2347 2348 2349 2350 2351 2352 2353 2354 2355 2356 2357 2358 2359 2360 2361 2362 2363 2364 2365 2366 2367 2368 2369 2370 2371 2372 2373 2374 2375 2376 2377 2378 2379 2380 2381 2382 2383 2384 2385 2386 2387 2388 2389 2390 2391 2392 2393 2394 2395 2396 2397 2398 2399 2400 2401 2402 2403 2404 2405 2406 2407 2408 2409 2410 2411 2412 2413 2414 2415 2416 2417 2418 2419 2420 2421 2422 2423 2424 2425 2426 2427 2428 2429 2430 2431 2432 2433 2434 2435 2436 2437 2438 2439 2440 2441 2442 2443 2444 2445 2446 2447 2448 2449 2450 2451 2452 2453 2454 2455 2456 2457 2458 2459 2460 2461 2462 2463 2464 2465 2466 2467 2468 2469 2470 2471 2472 2473 2474 2475 2476 2477 2478 2479 2480 2481 2482 2483 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 | // SPDX-License-Identifier: GPL-2.0-only /* * xfrm_policy.c * * Changes: * Mitsuru KANDA @USAGI * Kazunori MIYAZAWA @USAGI * Kunihiro Ishiguro <kunihiro@ipinfusion.com> * IPv6 support * Kazunori MIYAZAWA @USAGI * YOSHIFUJI Hideaki * Split up af-specific portion * Derek Atkins <derek@ihtfp.com> Add the post_input processor * */ #include <linux/err.h> #include <linux/slab.h> #include <linux/kmod.h> #include <linux/list.h> #include <linux/spinlock.h> #include <linux/workqueue.h> #include <linux/notifier.h> #include <linux/netdevice.h> #include <linux/netfilter.h> #include <linux/module.h> #include <linux/cache.h> #include <linux/cpu.h> #include <linux/audit.h> #include <linux/rhashtable.h> #include <linux/if_tunnel.h> #include <linux/icmp.h> #include <net/dst.h> #include <net/flow.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/ip.h> #include <net/gre.h> #if IS_ENABLED(CONFIG_IPV6_MIP6) #include <net/mip6.h> #endif #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif #ifdef CONFIG_XFRM_ESPINTCP #include <net/espintcp.h> #endif #include <net/inet_dscp.h> #include "xfrm_hash.h" #define XFRM_QUEUE_TMO_MIN ((unsigned)(HZ/10)) #define XFRM_QUEUE_TMO_MAX ((unsigned)(60*HZ)) #define XFRM_MAX_QUEUE_LEN 100 struct xfrm_flo { struct dst_entry *dst_orig; u8 flags; }; /* prefixes smaller than this are stored in lists, not trees. */ #define INEXACT_PREFIXLEN_IPV4 16 #define INEXACT_PREFIXLEN_IPV6 48 struct xfrm_pol_inexact_node { struct rb_node node; union { xfrm_address_t addr; struct rcu_head rcu; }; u8 prefixlen; struct rb_root root; /* the policies matching this node, can be empty list */ struct hlist_head hhead; }; /* xfrm inexact policy search tree: * xfrm_pol_inexact_bin = hash(dir,type,family,if_id); * | * +---- root_d: sorted by daddr:prefix * | | * | xfrm_pol_inexact_node * | | * | +- root: sorted by saddr/prefix * | | | * | | xfrm_pol_inexact_node * | | | * | | + root: unused * | | | * | | + hhead: saddr:daddr policies * | | * | +- coarse policies and all any:daddr policies * | * +---- root_s: sorted by saddr:prefix * | | * | xfrm_pol_inexact_node * | | * | + root: unused * | | * | + hhead: saddr:any policies * | * +---- coarse policies and all any:any policies * * Lookups return four candidate lists: * 1. any:any list from top-level xfrm_pol_inexact_bin * 2. any:daddr list from daddr tree * 3. saddr:daddr list from 2nd level daddr tree * 4. saddr:any list from saddr tree * * This result set then needs to be searched for the policy with * the lowest priority. If two candidates have the same priority, the * struct xfrm_policy pos member with the lower number is used. * * This replicates previous single-list-search algorithm which would * return first matching policy in the (ordered-by-priority) list. */ struct xfrm_pol_inexact_key { possible_net_t net; u32 if_id; u16 family; u8 dir, type; }; struct xfrm_pol_inexact_bin { struct xfrm_pol_inexact_key k; struct rhash_head head; /* list containing '*:*' policies */ struct hlist_head hhead; seqcount_spinlock_t count; /* tree sorted by daddr/prefix */ struct rb_root root_d; /* tree sorted by saddr/prefix */ struct rb_root root_s; /* slow path below */ struct list_head inexact_bins; struct rcu_head rcu; }; enum xfrm_pol_inexact_candidate_type { XFRM_POL_CAND_BOTH, XFRM_POL_CAND_SADDR, XFRM_POL_CAND_DADDR, XFRM_POL_CAND_ANY, XFRM_POL_CAND_MAX, }; struct xfrm_pol_inexact_candidates { struct hlist_head *res[XFRM_POL_CAND_MAX]; }; struct xfrm_flow_keys { struct flow_dissector_key_basic basic; struct flow_dissector_key_control control; union { struct flow_dissector_key_ipv4_addrs ipv4; struct flow_dissector_key_ipv6_addrs ipv6; } addrs; struct flow_dissector_key_ip ip; struct flow_dissector_key_icmp icmp; struct flow_dissector_key_ports ports; struct flow_dissector_key_keyid gre; }; static struct flow_dissector xfrm_session_dissector __ro_after_init; static DEFINE_SPINLOCK(xfrm_if_cb_lock); static struct xfrm_if_cb const __rcu *xfrm_if_cb __read_mostly; static DEFINE_SPINLOCK(xfrm_policy_afinfo_lock); static struct xfrm_policy_afinfo const __rcu *xfrm_policy_afinfo[AF_INET6 + 1] __read_mostly; static struct kmem_cache *xfrm_dst_cache __ro_after_init; static struct rhashtable xfrm_policy_inexact_table; static const struct rhashtable_params xfrm_pol_inexact_params; static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_dst *xdst); static void xfrm_policy_queue_process(struct timer_list *t); static void __xfrm_policy_link(struct xfrm_policy *pol, int dir); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id); static struct xfrm_policy * xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl); static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr); static inline bool xfrm_pol_hold_rcu(struct xfrm_policy *policy) { return refcount_inc_not_zero(&policy->refcnt); } static inline bool __xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi4 *fl4 = &fl->u.ip4; return addr4_match(fl4->daddr, sel->daddr.a4, sel->prefixlen_d) && addr4_match(fl4->saddr, sel->saddr.a4, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl4->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl4->uli) ^ sel->sport) & sel->sport_mask) && (fl4->flowi4_proto == sel->proto || !sel->proto) && (fl4->flowi4_oif == sel->ifindex || !sel->ifindex); } static inline bool __xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { const struct flowi6 *fl6 = &fl->u.ip6; return addr_match(&fl6->daddr, &sel->daddr, sel->prefixlen_d) && addr_match(&fl6->saddr, &sel->saddr, sel->prefixlen_s) && !((xfrm_flowi_dport(fl, &fl6->uli) ^ sel->dport) & sel->dport_mask) && !((xfrm_flowi_sport(fl, &fl6->uli) ^ sel->sport) & sel->sport_mask) && (fl6->flowi6_proto == sel->proto || !sel->proto) && (fl6->flowi6_oif == sel->ifindex || !sel->ifindex); } bool xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, unsigned short family) { if (family != sel->family && sel->family != AF_UNSPEC) return false; switch (family) { case AF_INET: return __xfrm4_selector_match(sel, fl); case AF_INET6: return __xfrm6_selector_match(sel, fl); } return false; } static const struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) { const struct xfrm_policy_afinfo *afinfo; if (unlikely(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return NULL; rcu_read_lock(); afinfo = rcu_dereference(xfrm_policy_afinfo[family]); if (unlikely(!afinfo)) rcu_read_unlock(); return afinfo; } /* Called with rcu_read_lock(). */ static const struct xfrm_if_cb *xfrm_if_get_cb(void) { return rcu_dereference(xfrm_if_cb); } struct dst_entry *__xfrm_dst_lookup(int family, const struct xfrm_dst_lookup_params *params) { const struct xfrm_policy_afinfo *afinfo; struct dst_entry *dst; afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return ERR_PTR(-EAFNOSUPPORT); dst = afinfo->dst_lookup(params); rcu_read_unlock(); return dst; } EXPORT_SYMBOL(__xfrm_dst_lookup); static inline struct dst_entry *xfrm_dst_lookup(struct xfrm_state *x, dscp_t dscp, int oif, xfrm_address_t *prev_saddr, xfrm_address_t *prev_daddr, int family, u32 mark) { struct xfrm_dst_lookup_params params; struct net *net = xs_net(x); xfrm_address_t *saddr = &x->props.saddr; xfrm_address_t *daddr = &x->id.daddr; struct dst_entry *dst; if (x->type->flags & XFRM_TYPE_LOCAL_COADDR) { saddr = x->coaddr; daddr = prev_daddr; } if (x->type->flags & XFRM_TYPE_REMOTE_COADDR) { saddr = prev_saddr; daddr = x->coaddr; } params.net = net; params.saddr = saddr; params.daddr = daddr; params.dscp = dscp; params.oif = oif; params.mark = mark; params.ipproto = x->id.proto; if (x->encap) { switch (x->encap->encap_type) { case UDP_ENCAP_ESPINUDP: params.ipproto = IPPROTO_UDP; params.uli.ports.sport = x->encap->encap_sport; params.uli.ports.dport = x->encap->encap_dport; break; case TCP_ENCAP_ESPINTCP: params.ipproto = IPPROTO_TCP; params.uli.ports.sport = x->encap->encap_sport; params.uli.ports.dport = x->encap->encap_dport; break; } } dst = __xfrm_dst_lookup(family, ¶ms); if (!IS_ERR(dst)) { if (prev_saddr != saddr) memcpy(prev_saddr, saddr, sizeof(*prev_saddr)); if (prev_daddr != daddr) memcpy(prev_daddr, daddr, sizeof(*prev_daddr)); } return dst; } static inline unsigned long make_jiffies(long secs) { if (secs >= (MAX_SCHEDULE_TIMEOUT-1)/HZ) return MAX_SCHEDULE_TIMEOUT-1; else return secs*HZ; } static void xfrm_policy_timer(struct timer_list *t) { struct xfrm_policy *xp = timer_container_of(xp, t, timer); time64_t now = ktime_get_real_seconds(); time64_t next = TIME64_MAX; int warn = 0; int dir; read_lock(&xp->lock); if (unlikely(xp->walk.dead)) goto out; dir = xfrm_policy_id2dir(xp->index); if (xp->lft.hard_add_expires_seconds) { time64_t tmo = xp->lft.hard_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.hard_use_expires_seconds) { time64_t tmo = xp->lft.hard_use_expires_seconds + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) goto expired; if (tmo < next) next = tmo; } if (xp->lft.soft_add_expires_seconds) { time64_t tmo = xp->lft.soft_add_expires_seconds + xp->curlft.add_time - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (xp->lft.soft_use_expires_seconds) { time64_t tmo = xp->lft.soft_use_expires_seconds + (READ_ONCE(xp->curlft.use_time) ? : xp->curlft.add_time) - now; if (tmo <= 0) { warn = 1; tmo = XFRM_KM_TIMEOUT; } if (tmo < next) next = tmo; } if (warn) km_policy_expired(xp, dir, 0, 0); if (next != TIME64_MAX && !mod_timer(&xp->timer, jiffies + make_jiffies(next))) xfrm_pol_hold(xp); out: read_unlock(&xp->lock); xfrm_pol_put(xp); return; expired: read_unlock(&xp->lock); if (!xfrm_policy_delete(xp, dir)) km_policy_expired(xp, dir, 1, 0); xfrm_pol_put(xp); } /* Allocate xfrm_policy. Not used here, it is supposed to be used by pfkeyv2 * SPD calls. */ struct xfrm_policy *xfrm_policy_alloc(struct net *net, gfp_t gfp) { struct xfrm_policy *policy; policy = kzalloc_obj(struct xfrm_policy, gfp); if (policy) { write_pnet(&policy->xp_net, net); INIT_LIST_HEAD(&policy->walk.all); INIT_HLIST_HEAD(&policy->state_cache_list); INIT_HLIST_NODE(&policy->bydst); INIT_HLIST_NODE(&policy->byidx); rwlock_init(&policy->lock); refcount_set(&policy->refcnt, 1); skb_queue_head_init(&policy->polq.hold_queue); timer_setup(&policy->timer, xfrm_policy_timer, 0); timer_setup(&policy->polq.hold_timer, xfrm_policy_queue_process, 0); } return policy; } EXPORT_SYMBOL(xfrm_policy_alloc); static void xfrm_policy_destroy_rcu(struct rcu_head *head) { struct xfrm_policy *policy = container_of(head, struct xfrm_policy, rcu); security_xfrm_policy_free(policy->security); kfree(policy); } /* Destroy xfrm_policy: descendant resources must be released to this moment. */ void xfrm_policy_destroy(struct xfrm_policy *policy) { BUG_ON(!policy->walk.dead); if (timer_delete(&policy->timer) || timer_delete(&policy->polq.hold_timer)) BUG(); xfrm_dev_policy_free(policy); call_rcu(&policy->rcu, xfrm_policy_destroy_rcu); } EXPORT_SYMBOL(xfrm_policy_destroy); /* Rule must be locked. Release descendant resources, announce * entry dead. The rule must be unlinked from lists to the moment. */ static void xfrm_policy_kill(struct xfrm_policy *policy) { struct net *net = xp_net(policy); struct xfrm_state *x; xfrm_dev_policy_delete(policy); write_lock_bh(&policy->lock); policy->walk.dead = 1; write_unlock_bh(&policy->lock); atomic_inc(&policy->genid); if (timer_delete(&policy->polq.hold_timer)) xfrm_pol_put(policy); skb_queue_purge(&policy->polq.hold_queue); if (timer_delete(&policy->timer)) xfrm_pol_put(policy); /* XXX: Flush state cache */ spin_lock_bh(&net->xfrm.xfrm_state_lock); hlist_for_each_entry_rcu(x, &policy->state_cache_list, state_cache) { hlist_del_init_rcu(&x->state_cache); } spin_unlock_bh(&net->xfrm.xfrm_state_lock); xfrm_pol_put(policy); } static unsigned int xfrm_policy_hashmax __read_mostly = 1 * 1024 * 1024; static inline unsigned int idx_hash(struct net *net, u32 index) { return __idx_hash(index, net->xfrm.policy_idx_hmask); } /* calculate policy hash thresholds */ static void __get_hash_thresh(struct net *net, unsigned short family, int dir, u8 *dbits, u8 *sbits) { switch (family) { case AF_INET: *dbits = net->xfrm.policy_bydst[dir].dbits4; *sbits = net->xfrm.policy_bydst[dir].sbits4; break; case AF_INET6: *dbits = net->xfrm.policy_bydst[dir].dbits6; *sbits = net->xfrm.policy_bydst[dir].sbits6; break; default: *dbits = 0; *sbits = 0; } } static struct hlist_head *policy_hash_bysel(struct net *net, const struct xfrm_selector *sel, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __sel_hash(sel, family, hmask, dbits, sbits); if (hash == hmask + 1) return NULL; return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static struct hlist_head *policy_hash_direct(struct net *net, const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash; u8 dbits; u8 sbits; __get_hash_thresh(net, family, dir, &dbits, &sbits); hash = __addr_hash(daddr, saddr, family, hmask, dbits, sbits); return rcu_dereference_check(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)) + hash; } static void xfrm_dst_hash_transfer(struct net *net, struct hlist_head *list, struct hlist_head *ndsttable, unsigned int nhashmask, int dir) { struct hlist_node *tmp, *entry0 = NULL; struct xfrm_policy *pol; unsigned int h0 = 0; u8 dbits; u8 sbits; redo: hlist_for_each_entry_safe(pol, tmp, list, bydst) { unsigned int h; __get_hash_thresh(net, pol->family, dir, &dbits, &sbits); h = __addr_hash(&pol->selector.daddr, &pol->selector.saddr, pol->family, nhashmask, dbits, sbits); if (!entry0 || pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET) { hlist_del_rcu(&pol->bydst); hlist_add_head_rcu(&pol->bydst, ndsttable + h); h0 = h; } else { if (h != h0) continue; hlist_del_rcu(&pol->bydst); hlist_add_behind_rcu(&pol->bydst, entry0); } entry0 = &pol->bydst; } if (!hlist_empty(list)) { entry0 = NULL; goto redo; } } static void xfrm_idx_hash_transfer(struct hlist_head *list, struct hlist_head *nidxtable, unsigned int nhashmask) { struct hlist_node *tmp; struct xfrm_policy *pol; hlist_for_each_entry_safe(pol, tmp, list, byidx) { unsigned int h; h = __idx_hash(pol->index, nhashmask); hlist_add_head(&pol->byidx, nidxtable+h); } } static unsigned long xfrm_new_hash_mask(unsigned int old_hmask) { return ((old_hmask + 1) << 1) - 1; } static void xfrm_bydst_resize(struct net *net, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *ndst = xfrm_hash_alloc(nsize); struct hlist_head *odst; int i; if (!ndst) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); odst = rcu_dereference_protected(net->xfrm.policy_bydst[dir].table, lockdep_is_held(&net->xfrm.xfrm_policy_lock)); for (i = hmask; i >= 0; i--) xfrm_dst_hash_transfer(net, odst + i, ndst, nhashmask, dir); rcu_assign_pointer(net->xfrm.policy_bydst[dir].table, ndst); net->xfrm.policy_bydst[dir].hmask = nhashmask; write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); synchronize_rcu(); xfrm_hash_free(odst, (hmask + 1) * sizeof(struct hlist_head)); } static void xfrm_byidx_resize(struct net *net) { unsigned int hmask = net->xfrm.policy_idx_hmask; unsigned int nhashmask = xfrm_new_hash_mask(hmask); unsigned int nsize = (nhashmask + 1) * sizeof(struct hlist_head); struct hlist_head *oidx = net->xfrm.policy_byidx; struct hlist_head *nidx = xfrm_hash_alloc(nsize); int i; if (!nidx) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); for (i = hmask; i >= 0; i--) xfrm_idx_hash_transfer(oidx + i, nidx, nhashmask); net->xfrm.policy_byidx = nidx; net->xfrm.policy_idx_hmask = nhashmask; spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_hash_free(oidx, (hmask + 1) * sizeof(struct hlist_head)); } static inline int xfrm_bydst_should_resize(struct net *net, int dir, int *total) { unsigned int cnt = READ_ONCE(net->xfrm.policy_count[dir]); unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; if (total) *total += cnt; if ((hmask + 1) < xfrm_policy_hashmax && cnt > hmask) return 1; return 0; } static inline int xfrm_byidx_should_resize(struct net *net, int total) { unsigned int hmask = net->xfrm.policy_idx_hmask; if ((hmask + 1) < xfrm_policy_hashmax && total > hmask) return 1; return 0; } void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { si->incnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN]); si->outcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]); si->fwdcnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD]); si->inscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]); si->outscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]); si->fwdscnt = READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]); si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; } EXPORT_SYMBOL(xfrm_spd_getinfo); static DEFINE_MUTEX(hash_resize_mutex); static void xfrm_hash_resize(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hash_work); int dir, total; mutex_lock(&hash_resize_mutex); total = 0; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { if (xfrm_bydst_should_resize(net, dir, &total)) xfrm_bydst_resize(net, dir); } if (xfrm_byidx_should_resize(net, total)) xfrm_byidx_resize(net); mutex_unlock(&hash_resize_mutex); } /* Make sure *pol can be inserted into fastbin. * Useful to check that later insert requests will be successful * (provided xfrm_policy_lock is held throughout). */ static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_alloc_bin(const struct xfrm_policy *pol, u8 dir) { struct xfrm_pol_inexact_bin *bin, *prev; struct xfrm_pol_inexact_key k = { .family = pol->family, .type = pol->type, .dir = dir, .if_id = pol->if_id, }; struct net *net = xp_net(pol); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); write_pnet(&k.net, net); bin = rhashtable_lookup_fast(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); if (bin) return bin; bin = kzalloc_obj(*bin, GFP_ATOMIC); if (!bin) return NULL; bin->k = k; INIT_HLIST_HEAD(&bin->hhead); bin->root_d = RB_ROOT; bin->root_s = RB_ROOT; seqcount_spinlock_init(&bin->count, &net->xfrm.xfrm_policy_lock); prev = rhashtable_lookup_get_insert_key(&xfrm_policy_inexact_table, &bin->k, &bin->head, xfrm_pol_inexact_params); if (!prev) { list_add(&bin->inexact_bins, &net->xfrm.inexact_bins); return bin; } kfree(bin); return IS_ERR(prev) ? NULL : prev; } static bool xfrm_pol_inexact_addr_use_any_list(const xfrm_address_t *addr, int family, u8 prefixlen) { if (xfrm_addr_any(addr, family)) return true; if (family == AF_INET6 && prefixlen < INEXACT_PREFIXLEN_IPV6) return true; if (family == AF_INET && prefixlen < INEXACT_PREFIXLEN_IPV4) return true; return false; } static bool xfrm_policy_inexact_insert_use_any_list(const struct xfrm_policy *policy) { const xfrm_address_t *addr; bool saddr_any, daddr_any; u8 prefixlen; addr = &policy->selector.saddr; prefixlen = policy->selector.prefixlen_s; saddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); addr = &policy->selector.daddr; prefixlen = policy->selector.prefixlen_d; daddr_any = xfrm_pol_inexact_addr_use_any_list(addr, policy->family, prefixlen); return saddr_any && daddr_any; } static void xfrm_pol_inexact_node_init(struct xfrm_pol_inexact_node *node, const xfrm_address_t *addr, u8 prefixlen) { node->addr = *addr; node->prefixlen = prefixlen; } static struct xfrm_pol_inexact_node * xfrm_pol_inexact_node_alloc(const xfrm_address_t *addr, u8 prefixlen) { struct xfrm_pol_inexact_node *node; node = kzalloc_obj(*node, GFP_ATOMIC); if (node) xfrm_pol_inexact_node_init(node, addr, prefixlen); return node; } static int xfrm_policy_addr_delta(const xfrm_address_t *a, const xfrm_address_t *b, u8 prefixlen, u16 family) { u32 ma, mb, mask; unsigned int pdw, pbi; int delta = 0; switch (family) { case AF_INET: if (prefixlen == 0) return 0; mask = ~0U << (32 - prefixlen); ma = ntohl(a->a4) & mask; mb = ntohl(b->a4) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; break; case AF_INET6: pdw = prefixlen >> 5; pbi = prefixlen & 0x1f; if (pdw) { delta = memcmp(a->a6, b->a6, pdw << 2); if (delta) return delta; } if (pbi) { mask = ~0U << (32 - pbi); ma = ntohl(a->a6[pdw]) & mask; mb = ntohl(b->a6[pdw]) & mask; if (ma < mb) delta = -1; else if (ma > mb) delta = 1; } break; default: break; } return delta; } static void xfrm_policy_inexact_list_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, u16 family) { unsigned int matched_s, matched_d; struct xfrm_policy *policy, *p; matched_s = 0; matched_d = 0; list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { struct hlist_node *newpos = NULL; bool matches_s, matches_d; if (policy->walk.dead || !policy->bydst_reinsert) continue; WARN_ON_ONCE(policy->family != family); policy->bydst_reinsert = false; hlist_for_each_entry(p, &n->hhead, bydst) { if (policy->priority > p->priority) newpos = &p->bydst; else if (policy->priority == p->priority && policy->pos > p->pos) newpos = &p->bydst; else break; } if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, &n->hhead); /* paranoia checks follow. * Check that the reinserted policy matches at least * saddr or daddr for current node prefix. * * Matching both is fine, matching saddr in one policy * (but not daddr) and then matching only daddr in another * is a bug. */ matches_s = xfrm_policy_addr_delta(&policy->selector.saddr, &n->addr, n->prefixlen, family) == 0; matches_d = xfrm_policy_addr_delta(&policy->selector.daddr, &n->addr, n->prefixlen, family) == 0; if (matches_s && matches_d) continue; WARN_ON_ONCE(!matches_s && !matches_d); if (matches_s) matched_s++; if (matches_d) matched_d++; WARN_ON_ONCE(matched_s && matched_d); } } static void xfrm_policy_inexact_node_reinsert(struct net *net, struct xfrm_pol_inexact_node *n, struct rb_root *new, u16 family) { struct xfrm_pol_inexact_node *node; struct rb_node **p, *parent; /* we should not have another subtree here */ WARN_ON_ONCE(!RB_EMPTY_ROOT(&n->root)); restart: parent = NULL; p = &new->rb_node; while (*p) { u8 prefixlen; int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); prefixlen = min(node->prefixlen, n->prefixlen); delta = xfrm_policy_addr_delta(&n->addr, &node->addr, prefixlen, family); if (delta < 0) { p = &parent->rb_left; } else if (delta > 0) { p = &parent->rb_right; } else { bool same_prefixlen = node->prefixlen == n->prefixlen; struct xfrm_policy *tmp; hlist_for_each_entry(tmp, &n->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } node->prefixlen = prefixlen; xfrm_policy_inexact_list_reinsert(net, node, family); if (same_prefixlen) { kfree_rcu(n, rcu); return; } rb_erase(*p, new); kfree_rcu(n, rcu); n = node; goto restart; } } rb_link_node_rcu(&n->node, parent, p); rb_insert_color(&n->node, new); } /* merge nodes v and n */ static void xfrm_policy_inexact_node_merge(struct net *net, struct xfrm_pol_inexact_node *v, struct xfrm_pol_inexact_node *n, u16 family) { struct xfrm_pol_inexact_node *node; struct xfrm_policy *tmp; struct rb_node *rnode; /* To-be-merged node v has a subtree. * * Dismantle it and insert its nodes to n->root. */ while ((rnode = rb_first(&v->root)) != NULL) { node = rb_entry(rnode, struct xfrm_pol_inexact_node, node); rb_erase(&node->node, &v->root); xfrm_policy_inexact_node_reinsert(net, node, &n->root, family); } hlist_for_each_entry(tmp, &v->hhead, bydst) { tmp->bydst_reinsert = true; hlist_del_rcu(&tmp->bydst); } xfrm_policy_inexact_list_reinsert(net, n, family); } static struct xfrm_pol_inexact_node * xfrm_policy_inexact_insert_node(struct net *net, struct rb_root *root, xfrm_address_t *addr, u16 family, u8 prefixlen, u8 dir) { struct xfrm_pol_inexact_node *cached = NULL; struct rb_node **p, *parent = NULL; struct xfrm_pol_inexact_node *node; p = &root->rb_node; while (*p) { int delta; parent = *p; node = rb_entry(*p, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta == 0 && prefixlen >= node->prefixlen) { WARN_ON_ONCE(cached); /* ipsec policies got lost */ return node; } if (delta < 0) p = &parent->rb_left; else p = &parent->rb_right; if (prefixlen < node->prefixlen) { delta = xfrm_policy_addr_delta(addr, &node->addr, prefixlen, family); if (delta) continue; /* This node is a subnet of the new prefix. It needs * to be removed and re-inserted with the smaller * prefix and all nodes that are now also covered * by the reduced prefixlen. */ rb_erase(&node->node, root); if (!cached) { xfrm_pol_inexact_node_init(node, addr, prefixlen); cached = node; } else { /* This node also falls within the new * prefixlen. Merge the to-be-reinserted * node and this one. */ xfrm_policy_inexact_node_merge(net, node, cached, family); kfree_rcu(node, rcu); } /* restart */ p = &root->rb_node; parent = NULL; } } node = cached; if (!node) { node = xfrm_pol_inexact_node_alloc(addr, prefixlen); if (!node) return NULL; } rb_link_node_rcu(&node->node, parent, p); rb_insert_color(&node->node, root); return node; } static void xfrm_policy_inexact_gc_tree(struct rb_root *r, bool rm) { struct xfrm_pol_inexact_node *node; struct rb_node *rn = rb_first(r); while (rn) { node = rb_entry(rn, struct xfrm_pol_inexact_node, node); xfrm_policy_inexact_gc_tree(&node->root, rm); rn = rb_next(rn); if (!hlist_empty(&node->hhead) || !RB_EMPTY_ROOT(&node->root)) { WARN_ON_ONCE(rm); continue; } rb_erase(&node->node, r); kfree_rcu(node, rcu); } } static void __xfrm_policy_inexact_prune_bin(struct xfrm_pol_inexact_bin *b, bool net_exit) { write_seqcount_begin(&b->count); xfrm_policy_inexact_gc_tree(&b->root_d, net_exit); xfrm_policy_inexact_gc_tree(&b->root_s, net_exit); write_seqcount_end(&b->count); if (!RB_EMPTY_ROOT(&b->root_d) || !RB_EMPTY_ROOT(&b->root_s) || !hlist_empty(&b->hhead)) { WARN_ON_ONCE(net_exit); return; } if (rhashtable_remove_fast(&xfrm_policy_inexact_table, &b->head, xfrm_pol_inexact_params) == 0) { list_del(&b->inexact_bins); kfree_rcu(b, rcu); } } static void __xfrm_policy_inexact_flush(struct net *net) { struct xfrm_pol_inexact_bin *bin, *t; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(bin, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(bin, false); } static struct hlist_head * xfrm_policy_inexact_alloc_chain(struct xfrm_pol_inexact_bin *bin, struct xfrm_policy *policy, u8 dir) { struct xfrm_pol_inexact_node *n; struct net *net; net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); if (xfrm_policy_inexact_insert_use_any_list(policy)) return &bin->hhead; if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.daddr, policy->family, policy->selector.prefixlen_d)) { write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_s, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } /* daddr is fixed */ write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &bin->root_d, &policy->selector.daddr, policy->family, policy->selector.prefixlen_d, dir); write_seqcount_end(&bin->count); if (!n) return NULL; /* saddr is wildcard */ if (xfrm_pol_inexact_addr_use_any_list(&policy->selector.saddr, policy->family, policy->selector.prefixlen_s)) return &n->hhead; write_seqcount_begin(&bin->count); n = xfrm_policy_inexact_insert_node(net, &n->root, &policy->selector.saddr, policy->family, policy->selector.prefixlen_s, dir); write_seqcount_end(&bin->count); if (!n) return NULL; return &n->hhead; } static struct xfrm_policy * xfrm_policy_inexact_insert(struct xfrm_policy *policy, u8 dir, int excl) { struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *delpol; struct hlist_head *chain; struct net *net; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) return ERR_PTR(-ENOMEM); net = xp_net(policy); lockdep_assert_held(&net->xfrm.xfrm_policy_lock); chain = xfrm_policy_inexact_alloc_chain(bin, policy, dir); if (!chain) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-ENOMEM); } delpol = xfrm_policy_insert_list(chain, policy, excl); if (delpol && excl) { __xfrm_policy_inexact_prune_bin(bin, false); return ERR_PTR(-EEXIST); } if (delpol) __xfrm_policy_inexact_prune_bin(bin, false); return delpol; } static bool xfrm_policy_is_dead_or_sk(const struct xfrm_policy *policy) { int dir; if (policy->walk.dead) return true; dir = xfrm_policy_id2dir(policy->index); return dir >= XFRM_POLICY_MAX; } static void xfrm_hash_rebuild(struct work_struct *work) { struct net *net = container_of(work, struct net, xfrm.policy_hthresh.work); struct xfrm_policy *pol; struct xfrm_policy *policy; struct hlist_head *chain; struct hlist_node *newpos; int dir; unsigned seq; u8 lbits4, rbits4, lbits6, rbits6; mutex_lock(&hash_resize_mutex); /* read selector prefixlen thresholds */ do { seq = read_seqbegin(&net->xfrm.policy_hthresh.lock); lbits4 = net->xfrm.policy_hthresh.lbits4; rbits4 = net->xfrm.policy_hthresh.rbits4; lbits6 = net->xfrm.policy_hthresh.lbits6; rbits6 = net->xfrm.policy_hthresh.rbits6; } while (read_seqretry(&net->xfrm.policy_hthresh.lock, seq)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); write_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); /* make sure that we can insert the indirect policies again before * we start with destructive action. */ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { struct xfrm_pol_inexact_bin *bin; u8 dbits, sbits; if (xfrm_policy_is_dead_or_sk(policy)) continue; dir = xfrm_policy_id2dir(policy->index); if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { if (policy->family == AF_INET) { dbits = rbits4; sbits = lbits4; } else { dbits = rbits6; sbits = lbits6; } } else { if (policy->family == AF_INET) { dbits = lbits4; sbits = rbits4; } else { dbits = lbits6; sbits = rbits6; } } if (policy->selector.prefixlen_d >= dbits && policy->selector.prefixlen_s >= sbits) continue; bin = xfrm_policy_inexact_alloc_bin(policy, dir); if (!bin) goto out_unlock; if (!xfrm_policy_inexact_alloc_chain(bin, policy, dir)) goto out_unlock; } for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { if ((dir & XFRM_POLICY_MASK) == XFRM_POLICY_OUT) { /* dir out => dst = remote, src = local */ net->xfrm.policy_bydst[dir].dbits4 = rbits4; net->xfrm.policy_bydst[dir].sbits4 = lbits4; net->xfrm.policy_bydst[dir].dbits6 = rbits6; net->xfrm.policy_bydst[dir].sbits6 = lbits6; } else { /* dir in/fwd => dst = local, src = remote */ net->xfrm.policy_bydst[dir].dbits4 = lbits4; net->xfrm.policy_bydst[dir].sbits4 = rbits4; net->xfrm.policy_bydst[dir].dbits6 = lbits6; net->xfrm.policy_bydst[dir].sbits6 = rbits6; } } /* re-insert all policies by order of creation */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { if (xfrm_policy_is_dead_or_sk(policy)) continue; hlist_del_rcu(&policy->bydst); newpos = NULL; dir = xfrm_policy_id2dir(policy->index); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (!chain) { void *p = xfrm_policy_inexact_insert(policy, dir, 0); WARN_ONCE(IS_ERR(p), "reinsert: %ld\n", PTR_ERR(p)); continue; } hlist_for_each_entry(pol, chain, bydst) { if (policy->priority >= pol->priority) newpos = &pol->bydst; else break; } if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) hlist_add_behind_rcu(&policy->bydst, newpos); else hlist_add_head_rcu(&policy->bydst, chain); } out_unlock: __xfrm_policy_inexact_flush(net); write_seqcount_end(&net->xfrm.xfrm_policy_hash_generation); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); mutex_unlock(&hash_resize_mutex); } void xfrm_policy_hash_rebuild(struct net *net) { schedule_work(&net->xfrm.policy_hthresh.work); } EXPORT_SYMBOL(xfrm_policy_hash_rebuild); /* Generate new index... KAME seems to generate them ordered by cost * of an absolute inpredictability of ordering of rules. This will not pass. */ static u32 xfrm_gen_index(struct net *net, int dir, u32 index) { for (;;) { struct hlist_head *list; struct xfrm_policy *p; u32 idx; int found; if (!index) { idx = (net->xfrm.idx_generator | dir); net->xfrm.idx_generator += 8; } else { idx = index; index = 0; } if (idx == 0) idx = 8; list = net->xfrm.policy_byidx + idx_hash(net, idx); found = 0; hlist_for_each_entry(p, list, byidx) { if (p->index == idx) { found = 1; break; } } if (!found) return idx; } } static inline int selector_cmp(struct xfrm_selector *s1, struct xfrm_selector *s2) { u32 *p1 = (u32 *) s1; u32 *p2 = (u32 *) s2; int len = sizeof(struct xfrm_selector) / sizeof(u32); int i; for (i = 0; i < len; i++) { if (p1[i] != p2[i]) return 1; } return 0; } static void xfrm_policy_requeue(struct xfrm_policy *old, struct xfrm_policy *new) { struct xfrm_policy_queue *pq = &old->polq; struct sk_buff_head list; if (skb_queue_empty(&pq->hold_queue)) return; __skb_queue_head_init(&list); spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice_init(&pq->hold_queue, &list); if (timer_delete(&pq->hold_timer)) xfrm_pol_put(old); spin_unlock_bh(&pq->hold_queue.lock); pq = &new->polq; spin_lock_bh(&pq->hold_queue.lock); skb_queue_splice(&list, &pq->hold_queue); pq->timeout = XFRM_QUEUE_TMO_MIN; if (!mod_timer(&pq->hold_timer, jiffies)) xfrm_pol_hold(new); spin_unlock_bh(&pq->hold_queue.lock); } static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, struct xfrm_policy *pol) { return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_key *k = data; u32 a = k->type << 24 | k->dir << 16 | k->family; return jhash_3words(a, k->if_id, net_hash_mix(read_pnet(&k->net)), seed); } static u32 xfrm_pol_bin_obj(const void *data, u32 len, u32 seed) { const struct xfrm_pol_inexact_bin *b = data; return xfrm_pol_bin_key(&b->k, 0, seed); } static int xfrm_pol_bin_cmp(struct rhashtable_compare_arg *arg, const void *ptr) { const struct xfrm_pol_inexact_key *key = arg->key; const struct xfrm_pol_inexact_bin *b = ptr; int ret; if (!net_eq(read_pnet(&b->k.net), read_pnet(&key->net))) return -1; ret = b->k.dir ^ key->dir; if (ret) return ret; ret = b->k.type ^ key->type; if (ret) return ret; ret = b->k.family ^ key->family; if (ret) return ret; return b->k.if_id ^ key->if_id; } static const struct rhashtable_params xfrm_pol_inexact_params = { .head_offset = offsetof(struct xfrm_pol_inexact_bin, head), .hashfn = xfrm_pol_bin_key, .obj_hashfn = xfrm_pol_bin_obj, .obj_cmpfn = xfrm_pol_bin_cmp, .automatic_shrinking = true, }; static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, struct xfrm_policy *policy, bool excl) { struct xfrm_policy *pol, *newpos = NULL, *delpol = NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) return ERR_PTR(-EEXIST); delpol = pol; if (policy->priority > pol->priority) continue; } else if (policy->priority >= pol->priority) { newpos = pol; continue; } if (delpol) break; } if (newpos && policy->xdo.type != XFRM_DEV_OFFLOAD_PACKET) hlist_add_behind_rcu(&policy->bydst, &newpos->bydst); else /* Packet offload policies enter to the head * to speed-up lookups. */ hlist_add_head_rcu(&policy->bydst, chain); return delpol; } int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) { struct net *net = xp_net(policy); struct xfrm_policy *delpol; struct hlist_head *chain; /* Sanitize mark before store */ policy->mark.v &= policy->mark.m; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, &policy->selector, policy->family, dir); if (chain) delpol = xfrm_policy_insert_list(chain, policy, excl); else delpol = xfrm_policy_inexact_insert(policy, dir, excl); if (IS_ERR(delpol)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return PTR_ERR(delpol); } __xfrm_policy_link(policy, dir); /* After previous checking, family can either be AF_INET or AF_INET6 */ if (policy->family == AF_INET) rt_genid_bump_ipv4(net); else rt_genid_bump_ipv6(net); if (delpol) { xfrm_policy_requeue(delpol, policy); __xfrm_policy_unlink(delpol, dir); } policy->index = delpol ? delpol->index : xfrm_gen_index(net, dir, policy->index); hlist_add_head(&policy->byidx, net->xfrm.policy_byidx+idx_hash(net, policy->index)); policy->curlft.add_time = ktime_get_real_seconds(); policy->curlft.use_time = 0; if (!mod_timer(&policy->timer, jiffies + HZ)) xfrm_pol_hold(policy); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (delpol) xfrm_policy_kill(delpol); else if (xfrm_bydst_should_resize(net, dir, NULL)) schedule_work(&net->xfrm.policy_hash_work); return 0; } EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * __xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; } return NULL; } struct xfrm_policy * xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; struct hlist_head *chain; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = policy_hash_bysel(net, sel, sel->family, dir); if (!chain) { struct xfrm_pol_inexact_candidates cand; int i; bin = xfrm_policy_inexact_lookup(net, type, sel->family, dir, if_id); if (!bin) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } if (!xfrm_policy_find_inexact_candidates(&cand, bin, &sel->saddr, &sel->daddr)) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return NULL; } pol = NULL; for (i = 0; i < ARRAY_SIZE(cand.res); i++) { struct xfrm_policy *tmp; tmp = __xfrm_policy_bysel_ctx(cand.res[i], mark, if_id, type, dir, sel, ctx); if (!tmp) continue; if (!pol || tmp->pos < pol->pos) pol = tmp; } } else { pol = __xfrm_policy_bysel_ctx(chain, mark, if_id, type, dir, sel, ctx); } if (pol) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete(pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; } if (bin && delete) __xfrm_policy_inexact_prune_bin(bin, false); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); return ret; } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); struct xfrm_policy * xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; *err = -ENOENT; if (xfrm_policy_id2dir(id) != dir) return NULL; *err = 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); chain = net->xfrm.policy_byidx + idx_hash(net, id); ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( pol->security); if (*err) { spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return pol; } __xfrm_policy_unlink(pol, dir); } ret = pol; break; } } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (ret && delete) xfrm_policy_kill(ret); return ret; } EXPORT_SYMBOL(xfrm_policy_byid); #ifdef CONFIG_SECURITY_NETWORK_XFRM static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { struct xfrm_policy *pol; int err = 0; list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead || xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || pol->type != type) continue; err = security_xfrm_policy_delete(pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } return err; } static inline int xfrm_dev_policy_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { struct xfrm_policy *pol; int err = 0; list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead || xfrm_policy_id2dir(pol->index) >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; err = security_xfrm_policy_delete(pol->security); if (err) { xfrm_audit_policy_delete(pol, 0, task_valid); return err; } } return err; } #else static inline int xfrm_policy_flush_secctx_check(struct net *net, u8 type, bool task_valid) { return 0; } static inline int xfrm_dev_policy_flush_secctx_check(struct net *net, struct net_device *dev, bool task_valid) { return 0; } #endif int xfrm_policy_flush(struct net *net, u8 type, bool task_valid) { int dir, err = 0, cnt = 0; struct xfrm_policy *pol; spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_policy_flush_secctx_check(net, type, task_valid); if (err) goto out; again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead) continue; dir = xfrm_policy_id2dir(pol->index); if (dir >= XFRM_POLICY_MAX || pol->type != type) continue; __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again; } if (cnt) __xfrm_policy_inexact_flush(net); else err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_policy_flush); int xfrm_dev_policy_flush(struct net *net, struct net_device *dev, bool task_valid) { int dir, err = 0, cnt = 0; struct xfrm_policy *pol; spin_lock_bh(&net->xfrm.xfrm_policy_lock); err = xfrm_dev_policy_flush_secctx_check(net, dev, task_valid); if (err) goto out; again: list_for_each_entry(pol, &net->xfrm.policy_all, walk.all) { if (pol->walk.dead) continue; dir = xfrm_policy_id2dir(pol->index); if (dir >= XFRM_POLICY_MAX || pol->xdo.dev != dev) continue; __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); cnt++; xfrm_audit_policy_delete(pol, 1, task_valid); xfrm_policy_kill(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); goto again; } if (cnt) __xfrm_policy_inexact_flush(net); else err = -ESRCH; out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return err; } EXPORT_SYMBOL(xfrm_dev_policy_flush); int xfrm_policy_walk(struct net *net, struct xfrm_policy_walk *walk, int (*func)(struct xfrm_policy *, int, int, void*), void *data) { struct xfrm_policy *pol; struct xfrm_policy_walk_entry *x; int error = 0; if (walk->type >= XFRM_POLICY_TYPE_MAX && walk->type != XFRM_POLICY_TYPE_ANY) return -EINVAL; if (list_empty(&walk->walk.all) && walk->seq != 0) return 0; spin_lock_bh(&net->xfrm.xfrm_policy_lock); if (list_empty(&walk->walk.all)) x = list_first_entry(&net->xfrm.policy_all, struct xfrm_policy_walk_entry, all); else x = list_first_entry(&walk->walk.all, struct xfrm_policy_walk_entry, all); list_for_each_entry_from(x, &net->xfrm.policy_all, all) { if (x->dead) continue; pol = container_of(x, struct xfrm_policy, walk); if (walk->type != XFRM_POLICY_TYPE_ANY && walk->type != pol->type) continue; error = func(pol, xfrm_policy_id2dir(pol->index), walk->seq, data); if (error) { list_move_tail(&walk->walk.all, &x->all); goto out; } walk->seq++; } if (walk->seq == 0) { error = -ENOENT; goto out; } list_del_init(&walk->walk.all); out: spin_unlock_bh(&net->xfrm.xfrm_policy_lock); return error; } EXPORT_SYMBOL(xfrm_policy_walk); void xfrm_policy_walk_init(struct xfrm_policy_walk *walk, u8 type) { INIT_LIST_HEAD(&walk->walk.all); walk->walk.dead = 1; walk->type = type; walk->seq = 0; } EXPORT_SYMBOL(xfrm_policy_walk_init); void xfrm_policy_walk_done(struct xfrm_policy_walk *walk, struct net *net) { if (list_empty(&walk->walk.all)) return; spin_lock_bh(&net->xfrm.xfrm_policy_lock); /*FIXME where is net? */ list_del(&walk->walk.all); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } EXPORT_SYMBOL(xfrm_policy_walk_done); /* * Find policy to apply to this flow. * * Returns 0 if policy found, else an -errno. */ static int xfrm_policy_match(const struct xfrm_policy *pol, const struct flowi *fl, u8 type, u16 family, u32 if_id) { const struct xfrm_selector *sel = &pol->selector; int ret = -ESRCH; bool match; if (pol->family != family || pol->if_id != if_id || (fl->flowi_mark & pol->mark.m) != pol->mark.v || pol->type != type) return ret; match = xfrm_selector_match(sel, fl, family); if (match) ret = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); return ret; } static struct xfrm_pol_inexact_node * xfrm_policy_lookup_inexact_addr(const struct rb_root *r, seqcount_spinlock_t *count, const xfrm_address_t *addr, u16 family) { const struct rb_node *parent; int seq; again: seq = read_seqcount_begin(count); parent = rcu_dereference_raw(r->rb_node); while (parent) { struct xfrm_pol_inexact_node *node; int delta; node = rb_entry(parent, struct xfrm_pol_inexact_node, node); delta = xfrm_policy_addr_delta(addr, &node->addr, node->prefixlen, family); if (delta < 0) { parent = rcu_dereference_raw(parent->rb_left); continue; } else if (delta > 0) { parent = rcu_dereference_raw(parent->rb_right); continue; } return node; } if (read_seqcount_retry(count, seq)) goto again; return NULL; } static bool xfrm_policy_find_inexact_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_pol_inexact_bin *b, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { struct xfrm_pol_inexact_node *n; u16 family; if (!b) return false; family = b->k.family; memset(cand, 0, sizeof(*cand)); cand->res[XFRM_POL_CAND_ANY] = &b->hhead; n = xfrm_policy_lookup_inexact_addr(&b->root_d, &b->count, daddr, family); if (n) { cand->res[XFRM_POL_CAND_DADDR] = &n->hhead; n = xfrm_policy_lookup_inexact_addr(&n->root, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_BOTH] = &n->hhead; } n = xfrm_policy_lookup_inexact_addr(&b->root_s, &b->count, saddr, family); if (n) cand->res[XFRM_POL_CAND_SADDR] = &n->hhead; return true; } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup_rcu(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_key k = { .family = family, .type = type, .dir = dir, .if_id = if_id, }; write_pnet(&k.net, net); return rhashtable_lookup(&xfrm_policy_inexact_table, &k, xfrm_pol_inexact_params); } static struct xfrm_pol_inexact_bin * xfrm_policy_inexact_lookup(struct net *net, u8 type, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_bin *bin; lockdep_assert_held(&net->xfrm.xfrm_policy_lock); rcu_read_lock(); bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); rcu_read_unlock(); return bin; } static struct xfrm_policy * __xfrm_policy_eval_candidates(struct hlist_head *chain, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, u32 if_id) { u32 priority = prefer ? prefer->priority : ~0u; struct xfrm_policy *pol; if (!chain) return NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { int err; if (pol->priority > priority) break; err = xfrm_policy_match(pol, fl, type, family, if_id); if (err) { if (err != -ESRCH) return ERR_PTR(err); continue; } if (prefer) { /* matches. Is it older than *prefer? */ if (pol->priority == priority && prefer->pos < pol->pos) return prefer; } return pol; } return NULL; } static struct xfrm_policy * xfrm_policy_eval_candidates(struct xfrm_pol_inexact_candidates *cand, struct xfrm_policy *prefer, const struct flowi *fl, u8 type, u16 family, u32 if_id) { struct xfrm_policy *tmp; int i; for (i = 0; i < ARRAY_SIZE(cand->res); i++) { tmp = __xfrm_policy_eval_candidates(cand->res[i], prefer, fl, type, family, if_id); if (!tmp) continue; if (IS_ERR(tmp)) return tmp; prefer = tmp; } return prefer; } static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { struct xfrm_pol_inexact_candidates cand; const xfrm_address_t *daddr, *saddr; struct xfrm_pol_inexact_bin *bin; struct xfrm_policy *pol, *ret; struct hlist_head *chain; unsigned int sequence; int err; daddr = xfrm_flowi_daddr(fl, family); saddr = xfrm_flowi_saddr(fl, family); if (unlikely(!daddr || !saddr)) return NULL; rcu_read_lock(); retry: do { sequence = read_seqcount_begin(&net->xfrm.xfrm_policy_hash_generation); chain = policy_hash_direct(net, daddr, saddr, family, dir); } while (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)); ret = NULL; hlist_for_each_entry_rcu(pol, chain, bydst) { err = xfrm_policy_match(pol, fl, type, family, if_id); if (err) { if (err == -ESRCH) continue; else { ret = ERR_PTR(err); goto fail; } } else { ret = pol; break; } } if (ret && ret->xdo.type == XFRM_DEV_OFFLOAD_PACKET) goto skip_inexact; bin = xfrm_policy_inexact_lookup_rcu(net, type, family, dir, if_id); if (!bin || !xfrm_policy_find_inexact_candidates(&cand, bin, saddr, daddr)) goto skip_inexact; pol = xfrm_policy_eval_candidates(&cand, ret, fl, type, family, if_id); if (pol) { ret = pol; if (IS_ERR(pol)) goto fail; } skip_inexact: if (read_seqcount_retry(&net->xfrm.xfrm_policy_hash_generation, sequence)) goto retry; if (ret && !xfrm_pol_hold_rcu(ret)) goto retry; fail: rcu_read_unlock(); return ret; } static struct xfrm_policy *xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, u32 if_id) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; pol = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_SUB, fl, family, dir, if_id); if (pol != NULL) return pol; #endif return xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, fl, family, dir, if_id); } static struct xfrm_policy *xfrm_sk_policy_lookup(const struct sock *sk, int dir, const struct flowi *fl, u16 family, u32 if_id) { struct xfrm_policy *pol; rcu_read_lock(); again: pol = rcu_dereference(sk->sk_policy[dir]); if (pol != NULL) { bool match; int err = 0; if (pol->family != family) { pol = NULL; goto out; } match = xfrm_selector_match(&pol->selector, fl, family); if (match) { if ((READ_ONCE(sk->sk_mark) & pol->mark.m) != pol->mark.v || pol->if_id != if_id) { pol = NULL; goto out; } err = security_xfrm_policy_lookup(pol->security, fl->flowi_secid); if (!err) { if (!xfrm_pol_hold_rcu(pol)) goto again; } else if (err == -ESRCH) { pol = NULL; } else { pol = ERR_PTR(err); } } else pol = NULL; } out: rcu_read_unlock(); return pol; } static u32 xfrm_gen_pos_slow(struct net *net) { struct xfrm_policy *policy; u32 i = 0; /* oldest entry is last in list */ list_for_each_entry_reverse(policy, &net->xfrm.policy_all, walk.all) { if (!xfrm_policy_is_dead_or_sk(policy)) policy->pos = ++i; } return i; } static u32 xfrm_gen_pos(struct net *net) { const struct xfrm_policy *policy; u32 i = 0; /* most recently added policy is at the head of the list */ list_for_each_entry(policy, &net->xfrm.policy_all, walk.all) { if (xfrm_policy_is_dead_or_sk(policy)) continue; if (policy->pos == UINT_MAX) return xfrm_gen_pos_slow(net); i = policy->pos + 1; break; } return i; } static void __xfrm_policy_link(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); switch (dir) { case XFRM_POLICY_IN: case XFRM_POLICY_FWD: case XFRM_POLICY_OUT: pol->pos = xfrm_gen_pos(net); break; } list_add(&pol->walk.all, &net->xfrm.policy_all); WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] + 1); xfrm_pol_hold(pol); } static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); if (list_empty(&pol->walk.all)) return NULL; /* Socket policies are not hashed. */ if (!hlist_unhashed(&pol->bydst)) { hlist_del_rcu(&pol->bydst); hlist_del(&pol->byidx); } list_del_init(&pol->walk.all); WRITE_ONCE(net->xfrm.policy_count[dir], net->xfrm.policy_count[dir] - 1); return pol; } static void xfrm_sk_policy_link(struct xfrm_policy *pol, int dir) { __xfrm_policy_link(pol, XFRM_POLICY_MAX + dir); } static void xfrm_sk_policy_unlink(struct xfrm_policy *pol, int dir) { __xfrm_policy_unlink(pol, XFRM_POLICY_MAX + dir); } int xfrm_policy_delete(struct xfrm_policy *pol, int dir) { struct net *net = xp_net(pol); spin_lock_bh(&net->xfrm.xfrm_policy_lock); pol = __xfrm_policy_unlink(pol, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (pol) { xfrm_policy_kill(pol); return 0; } return -ENOENT; } EXPORT_SYMBOL(xfrm_policy_delete); int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) { struct net *net = sock_net(sk); struct xfrm_policy *old_pol; #ifdef CONFIG_XFRM_SUB_POLICY if (pol && pol->type != XFRM_POLICY_TYPE_MAIN) return -EINVAL; #endif spin_lock_bh(&net->xfrm.xfrm_policy_lock); old_pol = rcu_dereference_protected(sk->sk_policy[dir], lockdep_is_held(&net->xfrm.xfrm_policy_lock)); if (pol) { pol->curlft.add_time = ktime_get_real_seconds(); pol->index = xfrm_gen_index(net, XFRM_POLICY_MAX+dir, 0); xfrm_sk_policy_link(pol, dir); } rcu_assign_pointer(sk->sk_policy[dir], pol); if (old_pol) { if (pol) xfrm_policy_requeue(old_pol, pol); /* Unlinking succeeds always. This is the only function * allowed to delete or replace socket policy. */ xfrm_sk_policy_unlink(old_pol, dir); } spin_unlock_bh(&net->xfrm.xfrm_policy_lock); if (old_pol) { xfrm_policy_kill(old_pol); } return 0; } static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); struct net *net = xp_net(old); if (newp) { newp->selector = old->selector; if (security_xfrm_policy_clone(old->security, &newp->security)) { kfree(newp); return NULL; /* ENOMEM */ } newp->lft = old->lft; newp->curlft = old->curlft; newp->mark = old->mark; newp->if_id = old->if_id; newp->action = old->action; newp->flags = old->flags; newp->xfrm_nr = old->xfrm_nr; newp->index = old->index; newp->type = old->type; newp->family = old->family; memcpy(newp->xfrm_vec, old->xfrm_vec, newp->xfrm_nr*sizeof(struct xfrm_tmpl)); spin_lock_bh(&net->xfrm.xfrm_policy_lock); xfrm_sk_policy_link(newp, dir); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); xfrm_pol_put(newp); } return newp; } int __xfrm_sk_clone_policy(struct sock *sk, const struct sock *osk) { const struct xfrm_policy *p; struct xfrm_policy *np; int i, ret = 0; rcu_read_lock(); for (i = 0; i < 2; i++) { p = rcu_dereference(osk->sk_policy[i]); if (p) { np = clone_policy(p, i); if (unlikely(!np)) { ret = -ENOMEM; break; } rcu_assign_pointer(sk->sk_policy[i], np); } } rcu_read_unlock(); return ret; } static int xfrm_get_saddr(unsigned short family, xfrm_address_t *saddr, const struct xfrm_dst_lookup_params *params) { int err; const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); if (unlikely(afinfo == NULL)) return -EINVAL; err = afinfo->get_saddr(saddr, params); rcu_read_unlock(); return err; } /* Resolve list of templates for the flow, given policy. */ static int xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct net *net = xp_net(policy); int nx; int i, error; xfrm_address_t *daddr = xfrm_flowi_daddr(fl, family); xfrm_address_t *saddr = xfrm_flowi_saddr(fl, family); xfrm_address_t tmp; for (nx = 0, i = 0; i < policy->xfrm_nr; i++) { struct xfrm_state *x; xfrm_address_t *remote = daddr; xfrm_address_t *local = saddr; struct xfrm_tmpl *tmpl = &policy->xfrm_vec[i]; if (tmpl->mode == XFRM_MODE_TUNNEL || tmpl->mode == XFRM_MODE_IPTFS || tmpl->mode == XFRM_MODE_BEET) { remote = &tmpl->id.daddr; local = &tmpl->saddr; if (xfrm_addr_any(local, tmpl->encap_family)) { struct xfrm_dst_lookup_params params; memset(¶ms, 0, sizeof(params)); params.net = net; params.oif = fl->flowi_oif; params.daddr = remote; error = xfrm_get_saddr(tmpl->encap_family, &tmp, ¶ms); if (error) goto fail; local = &tmp; } } x = xfrm_state_find(remote, local, fl, tmpl, policy, &error, family, policy->if_id); if (x && x->dir && x->dir != XFRM_SA_DIR_OUT) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTSTATEDIRERROR); xfrm_state_put(x); error = -EINVAL; goto fail; } if (x && x->km.state == XFRM_STATE_VALID) { xfrm[nx++] = x; daddr = remote; saddr = local; continue; } if (x) { error = (x->km.state == XFRM_STATE_ERROR ? -EINVAL : -EAGAIN); xfrm_state_put(x); } else if (error == -ESRCH) { error = -EAGAIN; } if (!tmpl->optional) goto fail; } return nx; fail: for (nx--; nx >= 0; nx--) xfrm_state_put(xfrm[nx]); return error; } static int xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, struct xfrm_state **xfrm, unsigned short family) { struct xfrm_state *tp[XFRM_MAX_DEPTH]; struct xfrm_state **tpp = (npols > 1) ? tp : xfrm; int cnx = 0; int error; int ret; int i; for (i = 0; i < npols; i++) { if (cnx + pols[i]->xfrm_nr >= XFRM_MAX_DEPTH) { error = -ENOBUFS; goto fail; } ret = xfrm_tmpl_resolve_one(pols[i], fl, &tpp[cnx], family); if (ret < 0) { error = ret; goto fail; } else cnx += ret; } /* found states are sorted for outbound processing */ if (npols > 1) xfrm_state_sort(xfrm, tpp, cnx, family); return cnx; fail: for (cnx--; cnx >= 0; cnx--) xfrm_state_put(tpp[cnx]); return error; } static dscp_t xfrm_get_dscp(const struct flowi *fl, int family) { if (family == AF_INET) return fl->u.ip4.flowi4_dscp; return 0; } static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_ops *dst_ops; struct xfrm_dst *xdst; if (!afinfo) return ERR_PTR(-EINVAL); switch (family) { case AF_INET: dst_ops = &net->xfrm.xfrm4_dst_ops; break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: dst_ops = &net->xfrm.xfrm6_dst_ops; break; #endif default: BUG(); } xdst = dst_alloc(dst_ops, NULL, DST_OBSOLETE_NONE, 0); if (likely(xdst)) { memset_after(xdst, 0, u.dst); } else xdst = ERR_PTR(-ENOBUFS); rcu_read_unlock(); return xdst; } static void xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len) { if (dst->ops->family == AF_INET6) { path->path_cookie = rt6_get_cookie(dst_rt6_info(dst)); path->u.rt6.rt6i_nfheader_len = nfheader_len; } } static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, const struct flowi *fl) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(xdst->u.dst.ops->family); int err; if (!afinfo) return -EINVAL; err = afinfo->fill_dst(xdst, dev, fl); rcu_read_unlock(); return err; } /* Allocate chain of dst_entry's, attach known xfrm's, calculate * all the metrics... Shortly, bundle a bundle. */ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, struct xfrm_dst **bundle, int nx, const struct flowi *fl, struct dst_entry *dst) { const struct xfrm_state_afinfo *afinfo; const struct xfrm_mode *inner_mode; struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; struct xfrm_dst *xdst_prev = NULL; struct xfrm_dst *xdst0 = NULL; int i = 0; int err; int header_len = 0; int nfheader_len = 0; int trailer_len = 0; int family = policy->selector.family; xfrm_address_t saddr, daddr; dscp_t dscp; xfrm_flowi_addr_get(fl, &saddr, &daddr, family); dscp = xfrm_get_dscp(fl, family); dst_hold(dst); for (; i < nx; i++) { struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); if (IS_ERR(xdst)) { dst_release(dst); goto put_states; } bundle[i] = xdst; if (!xdst_prev) xdst0 = xdst; else /* Ref count is taken during xfrm_alloc_dst() * No need to do dst_clone() on dst1 */ xfrm_dst_set_child(xdst_prev, &xdst->u.dst); if (xfrm[i]->sel.family == AF_UNSPEC) { inner_mode = xfrm_ip2inner_mode(xfrm[i], xfrm_af2proto(family)); if (!inner_mode) { err = -EAFNOSUPPORT; dst_release(dst); goto put_states; } } else inner_mode = &xfrm[i]->inner_mode; xdst->route = dst; dst_copy_metrics(dst1, dst); if (xfrm[i]->props.mode != XFRM_MODE_TRANSPORT) { __u32 mark = 0; int oif; if (xfrm[i]->props.smark.v || xfrm[i]->props.smark.m) mark = xfrm_smark_get(fl->flowi_mark, xfrm[i]); if (xfrm[i]->xso.type != XFRM_DEV_OFFLOAD_PACKET) family = xfrm[i]->props.family; oif = fl->flowi_oif ? : fl->flowi_l3mdev; dst = xfrm_dst_lookup(xfrm[i], dscp, oif, &saddr, &daddr, family, mark); err = PTR_ERR(dst); if (IS_ERR(dst)) goto put_states; } else dst_hold(dst); dst1->xfrm = xfrm[i]; xdst->xfrm_genid = xfrm[i]->genid; dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->lastuse = now; dst1->input = dst_discard; if (xfrm[i]->mode_cbs && xfrm[i]->mode_cbs->output) { dst1->output = xfrm[i]->mode_cbs->output; } else { rcu_read_lock(); afinfo = xfrm_state_afinfo_get_rcu(inner_mode->family); if (likely(afinfo)) dst1->output = afinfo->output; else dst1->output = dst_discard_out; rcu_read_unlock(); } xdst_prev = xdst; header_len += xfrm[i]->props.header_len; if (xfrm[i]->type->flags & XFRM_TYPE_NON_FRAGMENT) nfheader_len += xfrm[i]->props.header_len; trailer_len += xfrm[i]->props.trailer_len; } xfrm_dst_set_child(xdst_prev, dst); xdst0->path = dst; err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; xfrm_init_path(xdst0, dst, nfheader_len); xfrm_init_pmtu(bundle, nx); for (xdst_prev = xdst0; xdst_prev != (struct xfrm_dst *)dst; xdst_prev = (struct xfrm_dst *) xfrm_dst_child(&xdst_prev->u.dst)) { err = xfrm_fill_dst(xdst_prev, dev, fl); if (err) goto free_dst; xdst_prev->u.dst.header_len = header_len; xdst_prev->u.dst.trailer_len = trailer_len; header_len -= xdst_prev->u.dst.xfrm->props.header_len; trailer_len -= xdst_prev->u.dst.xfrm->props.trailer_len; } return &xdst0->u.dst; put_states: for (; i < nx; i++) xfrm_state_put(xfrm[i]); free_dst: if (xdst0) dst_release_immediate(&xdst0->u.dst); return ERR_PTR(err); } static int xfrm_expand_policies(const struct flowi *fl, u16 family, struct xfrm_policy **pols, int *num_pols, int *num_xfrms) { int i; if (*num_pols == 0 || !pols[0]) { *num_pols = 0; *num_xfrms = 0; return 0; } if (IS_ERR(pols[0])) { *num_pols = 0; return PTR_ERR(pols[0]); } *num_xfrms = pols[0]->xfrm_nr; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->action == XFRM_POLICY_ALLOW && pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(xp_net(pols[0]), XFRM_POLICY_TYPE_MAIN, fl, family, XFRM_POLICY_OUT, pols[0]->if_id); if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; (*num_xfrms) += pols[1]->xfrm_nr; } } #endif for (i = 0; i < *num_pols; i++) { if (pols[i]->action != XFRM_POLICY_ALLOW) { *num_xfrms = -1; break; } } return 0; } static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, const struct flowi *fl, u16 family, struct dst_entry *dst_orig) { struct net *net = xp_net(pols[0]); struct xfrm_state *xfrm[XFRM_MAX_DEPTH]; struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct xfrm_dst *xdst; struct dst_entry *dst; int err; /* Try to instantiate a bundle */ err = xfrm_tmpl_resolve(pols, num_pols, fl, xfrm, family); if (err <= 0) { if (err == 0) return NULL; if (err != -EAGAIN) XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); return ERR_PTR(err); } dst = xfrm_bundle_create(pols[0], xfrm, bundle, err, fl, dst_orig); if (IS_ERR(dst)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTBUNDLEGENERROR); return ERR_CAST(dst); } xdst = (struct xfrm_dst *)dst; xdst->num_xfrms = err; xdst->num_pols = num_pols; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); xdst->policy_genid = atomic_read(&pols[0]->genid); return xdst; } static void xfrm_policy_queue_process(struct timer_list *t) { struct sk_buff *skb; struct sock *sk; struct dst_entry *dst; struct xfrm_policy *pol = timer_container_of(pol, t, polq.hold_timer); struct net *net = xp_net(pol); struct xfrm_policy_queue *pq = &pol->polq; struct flowi fl; struct sk_buff_head list; __u32 skb_mark; spin_lock(&pq->hold_queue.lock); skb = skb_peek(&pq->hold_queue); if (!skb) { spin_unlock(&pq->hold_queue.lock); goto out; } dst = skb_dst(skb); sk = skb->sk; /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(net, skb, &fl, dst->ops->family); skb->mark = skb_mark; spin_unlock(&pq->hold_queue.lock); dst_hold(xfrm_dst_path(dst)); dst = xfrm_lookup(net, xfrm_dst_path(dst), &fl, sk, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) goto purge_queue; if (dst->flags & DST_XFRM_QUEUE) { dst_release(dst); if (pq->timeout >= XFRM_QUEUE_TMO_MAX) goto purge_queue; pq->timeout = pq->timeout << 1; if (!mod_timer(&pq->hold_timer, jiffies + pq->timeout)) xfrm_pol_hold(pol); goto out; } dst_release(dst); __skb_queue_head_init(&list); spin_lock(&pq->hold_queue.lock); pq->timeout = 0; skb_queue_splice_init(&pq->hold_queue, &list); spin_unlock(&pq->hold_queue.lock); while (!skb_queue_empty(&list)) { skb = __skb_dequeue(&list); /* Fixup the mark to support VTI. */ skb_mark = skb->mark; skb->mark = pol->mark.v; xfrm_decode_session(net, skb, &fl, skb_dst(skb)->ops->family); skb->mark = skb_mark; dst_hold(xfrm_dst_path(skb_dst(skb))); dst = xfrm_lookup(net, xfrm_dst_path(skb_dst(skb)), &fl, skb->sk, 0); if (IS_ERR(dst)) { kfree_skb(skb); continue; } nf_reset_ct(skb); skb_dst_drop(skb); skb_dst_set(skb, dst); dst_output(net, skb_to_full_sk(skb), skb); } out: xfrm_pol_put(pol); return; purge_queue: pq->timeout = 0; skb_queue_purge(&pq->hold_queue); xfrm_pol_put(pol); } static int xdst_queue_output(struct net *net, struct sock *sk, struct sk_buff *skb) { unsigned long sched_next; struct dst_entry *dst = skb_dst(skb); struct xfrm_dst *xdst = (struct xfrm_dst *) dst; struct xfrm_policy *pol = xdst->pols[0]; struct xfrm_policy_queue *pq = &pol->polq; if (unlikely(skb_fclone_busy(sk, skb))) { kfree_skb(skb); return 0; } if (pq->hold_queue.qlen > XFRM_MAX_QUEUE_LEN) { kfree_skb(skb); return -EAGAIN; } skb_dst_force(skb); spin_lock_bh(&pq->hold_queue.lock); if (!pq->timeout) pq->timeout = XFRM_QUEUE_TMO_MIN; sched_next = jiffies + pq->timeout; if (timer_delete(&pq->hold_timer)) { if (time_before(pq->hold_timer.expires, sched_next)) sched_next = pq->hold_timer.expires; xfrm_pol_put(pol); } __skb_queue_tail(&pq->hold_queue, skb); if (!mod_timer(&pq->hold_timer, sched_next)) xfrm_pol_hold(pol); spin_unlock_bh(&pq->hold_queue.lock); return 0; } static struct xfrm_dst *xfrm_create_dummy_bundle(struct net *net, struct xfrm_flo *xflo, const struct flowi *fl, int num_xfrms, u16 family) { int err; struct net_device *dev; struct dst_entry *dst; struct dst_entry *dst1; struct xfrm_dst *xdst; xdst = xfrm_alloc_dst(net, family); if (IS_ERR(xdst)) return xdst; if (!(xflo->flags & XFRM_LOOKUP_QUEUE) || net->xfrm.sysctl_larval_drop || num_xfrms <= 0) return xdst; dst = xflo->dst_orig; dst1 = &xdst->u.dst; dst_hold(dst); xdst->route = dst; dst_copy_metrics(dst1, dst); dst1->obsolete = DST_OBSOLETE_FORCE_CHK; dst1->flags |= DST_XFRM_QUEUE; dst1->lastuse = jiffies; dst1->input = dst_discard; dst1->output = xdst_queue_output; dst_hold(dst); xfrm_dst_set_child(xdst, dst); xdst->path = dst; xfrm_init_path((struct xfrm_dst *)dst1, dst, 0); err = -ENODEV; dev = dst->dev; if (!dev) goto free_dst; err = xfrm_fill_dst(xdst, dev, fl); if (err) goto free_dst; out: return xdst; free_dst: dst_release(dst1); xdst = ERR_PTR(err); goto out; } static struct xfrm_dst *xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct xfrm_flo *xflo, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int num_pols = 0, num_xfrms = 0, err; struct xfrm_dst *xdst; /* Resolve policies to use if we couldn't get them from * previous cache entry */ num_pols = 1; pols[0] = xfrm_policy_lookup(net, fl, family, dir, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto inc_error; if (num_pols == 0) return NULL; if (num_xfrms <= 0) goto make_dummy_bundle; xdst = xfrm_resolve_and_create_bundle(pols, num_pols, fl, family, xflo->dst_orig); if (IS_ERR(xdst)) { err = PTR_ERR(xdst); if (err == -EREMOTE) { xfrm_pols_put(pols, num_pols); return NULL; } if (err != -EAGAIN) goto error; goto make_dummy_bundle; } else if (xdst == NULL) { num_xfrms = 0; goto make_dummy_bundle; } return xdst; make_dummy_bundle: /* We found policies, but there's no bundles to instantiate: * either because the policy blocks, has no transformations or * we could not build template (no xfrm_states).*/ xdst = xfrm_create_dummy_bundle(net, xflo, fl, num_xfrms, family); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); return ERR_CAST(xdst); } xdst->num_pols = num_pols; xdst->num_xfrms = num_xfrms; memcpy(xdst->pols, pols, sizeof(struct xfrm_policy *) * num_pols); return xdst; inc_error: XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLERROR); error: xfrm_pols_put(pols, num_pols); return ERR_PTR(err); } static struct dst_entry *make_blackhole(struct net *net, u16 family, struct dst_entry *dst_orig) { const struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); struct dst_entry *ret; if (!afinfo) { dst_release(dst_orig); return ERR_PTR(-EINVAL); } else { ret = afinfo->blackhole_route(net, dst_orig); } rcu_read_unlock(); return ret; } /* Finds/creates a bundle for given flow and if_id * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. * * xfrm_lookup uses an if_id of 0 by default, and is provided for * compatibility */ struct dst_entry *xfrm_lookup_with_ifid(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags, u32 if_id) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; struct xfrm_dst *xdst; struct dst_entry *dst, *route; u16 family = dst_orig->ops->family; u8 dir = XFRM_POLICY_OUT; int i, err, num_pols, num_xfrms = 0, drop_pols = 0; dst = NULL; xdst = NULL; route = NULL; sk = sk_const_to_full_sk(sk); if (sk && sk->sk_policy[XFRM_POLICY_OUT]) { num_pols = 1; pols[0] = xfrm_sk_policy_lookup(sk, XFRM_POLICY_OUT, fl, family, if_id); err = xfrm_expand_policies(fl, family, pols, &num_pols, &num_xfrms); if (err < 0) goto dropdst; if (num_pols) { if (num_xfrms <= 0) { drop_pols = num_pols; goto no_transform; } xdst = xfrm_resolve_and_create_bundle( pols, num_pols, fl, family, dst_orig); if (IS_ERR(xdst)) { xfrm_pols_put(pols, num_pols); err = PTR_ERR(xdst); if (err == -EREMOTE) goto nopol; goto dropdst; } else if (xdst == NULL) { num_xfrms = 0; drop_pols = num_pols; goto no_transform; } route = xdst->route; } } if (xdst == NULL) { struct xfrm_flo xflo; xflo.dst_orig = dst_orig; xflo.flags = flags; /* To accelerate a bit... */ if (!if_id && ((dst_orig->flags & DST_NOXFRM) || !READ_ONCE(net->xfrm.policy_count[XFRM_POLICY_OUT]))) goto nopol; xdst = xfrm_bundle_lookup(net, fl, family, dir, &xflo, if_id); if (xdst == NULL) goto nopol; if (IS_ERR(xdst)) { err = PTR_ERR(xdst); goto dropdst; } num_pols = xdst->num_pols; num_xfrms = xdst->num_xfrms; memcpy(pols, xdst->pols, sizeof(struct xfrm_policy *) * num_pols); route = xdst->route; } dst = &xdst->u.dst; if (route == NULL && num_xfrms > 0) { /* The only case when xfrm_bundle_lookup() returns a * bundle with null route, is when the template could * not be resolved. It means policies are there, but * bundle could not be created, since we don't yet * have the xfrm_state's. We need to wait for KM to * negotiate new SA's or bail out with error.*/ if (net->xfrm.sysctl_larval_drop) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); err = -EREMOTE; goto error; } err = -EAGAIN; XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTNOSTATES); goto error; } no_transform: if (num_pols == 0) goto nopol; if ((flags & XFRM_LOOKUP_ICMP) && !(pols[0]->flags & XFRM_POLICY_ICMP)) { err = -ENOENT; goto error; } for (i = 0; i < num_pols; i++) WRITE_ONCE(pols[i]->curlft.use_time, ktime_get_real_seconds()); if (num_xfrms < 0) { /* Prohibit the flow */ XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTPOLBLOCK); err = -EPERM; goto error; } else if (num_xfrms > 0) { /* Flow transformed */ dst_release(dst_orig); } else { /* Flow passes untransformed */ dst_release(dst); dst = dst_orig; } ok: xfrm_pols_put(pols, drop_pols); if (dst->xfrm && (dst->xfrm->props.mode == XFRM_MODE_TUNNEL || dst->xfrm->props.mode == XFRM_MODE_IPTFS)) dst->flags |= DST_XFRM_TUNNEL; return dst; nopol: if ((!dst_orig->dev || !(dst_orig->dev->flags & IFF_LOOPBACK)) && READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) { err = -EPERM; goto error; } if (!(flags & XFRM_LOOKUP_ICMP)) { dst = dst_orig; goto ok; } err = -ENOENT; error: dst_release(dst); dropdst: if (!(flags & XFRM_LOOKUP_KEEP_DST_REF)) dst_release(dst_orig); xfrm_pols_put(pols, drop_pols); return ERR_PTR(err); } EXPORT_SYMBOL(xfrm_lookup_with_ifid); /* Main function: finds/creates a bundle for given flow. * * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. */ struct dst_entry *xfrm_lookup(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { return xfrm_lookup_with_ifid(net, dst_orig, fl, sk, flags, 0); } EXPORT_SYMBOL(xfrm_lookup); /* Callers of xfrm_lookup_route() must ensure a call to dst_output(). * Otherwise we may send out blackholed packets. */ struct dst_entry *xfrm_lookup_route(struct net *net, struct dst_entry *dst_orig, const struct flowi *fl, const struct sock *sk, int flags) { struct dst_entry *dst = xfrm_lookup(net, dst_orig, fl, sk, flags | XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_KEEP_DST_REF); if (PTR_ERR(dst) == -EREMOTE) return make_blackhole(net, dst_orig->ops->family, dst_orig); if (IS_ERR(dst)) dst_release(dst_orig); return dst; } EXPORT_SYMBOL(xfrm_lookup_route); static inline int xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { struct sec_path *sp = skb_sec_path(skb); struct xfrm_state *x; if (!sp || idx < 0 || idx >= sp->len) return 0; x = sp->xvec[idx]; if (!x->type->reject) return 0; return x->type->reject(x, skb, fl); } /* When skb is transformed back to its "native" form, we have to * check policy restrictions. At the moment we make this in maximally * stupid way. Shame on me. :-) Of course, connected sockets must * have policy cached at them. */ static inline int xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family, u32 if_id) { if (xfrm_state_kern(x)) return tmpl->optional && !xfrm_state_addr_cmp(tmpl, x, tmpl->encap_family); return x->id.proto == tmpl->id.proto && (x->id.spi == tmpl->id.spi || !tmpl->id.spi) && (x->props.reqid == tmpl->reqid || !tmpl->reqid) && x->props.mode == tmpl->mode && (tmpl->allalgs || (tmpl->aalgos & (1<<x->props.aalgo)) || !(xfrm_id_proto_match(tmpl->id.proto, IPSEC_PROTO_ANY))) && !(x->props.mode != XFRM_MODE_TRANSPORT && xfrm_state_addr_cmp(tmpl, x, family)) && (if_id == 0 || if_id == x->if_id); } /* * 0 or more than 0 is returned when validation is succeeded (either bypass * because of optional transport mode, or next index of the matched secpath * state with the template. * -1 is returned when no matching template is found. * Otherwise "-2 - errored_index" is returned. */ static inline int xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, unsigned short family, u32 if_id) { int idx = start; if (tmpl->optional) { if (tmpl->mode == XFRM_MODE_TRANSPORT) return start; } else start = -1; for (; idx < sp->len; idx++) { if (xfrm_state_ok(tmpl, sp->xvec[idx], family, if_id)) return ++idx; if (sp->xvec[idx]->props.mode != XFRM_MODE_TRANSPORT) { if (idx < sp->verified_cnt) { /* Secpath entry previously verified, consider optional and * continue searching */ continue; } if (start == -1) start = -2-idx; break; } } return start; } static void decode_session4(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse) { struct flowi4 *fl4 = &fl->u.ip4; memset(fl4, 0, sizeof(struct flowi4)); if (reverse) { fl4->saddr = flkeys->addrs.ipv4.dst; fl4->daddr = flkeys->addrs.ipv4.src; fl4->fl4_sport = flkeys->ports.dst; fl4->fl4_dport = flkeys->ports.src; } else { fl4->saddr = flkeys->addrs.ipv4.src; fl4->daddr = flkeys->addrs.ipv4.dst; fl4->fl4_sport = flkeys->ports.src; fl4->fl4_dport = flkeys->ports.dst; } switch (flkeys->basic.ip_proto) { case IPPROTO_GRE: fl4->fl4_gre_key = flkeys->gre.keyid; break; case IPPROTO_ICMP: fl4->fl4_icmp_type = flkeys->icmp.type; fl4->fl4_icmp_code = flkeys->icmp.code; break; } fl4->flowi4_proto = flkeys->basic.ip_proto; fl4->flowi4_dscp = inet_dsfield_to_dscp(flkeys->ip.tos); } #if IS_ENABLED(CONFIG_IPV6) static void decode_session6(const struct xfrm_flow_keys *flkeys, struct flowi *fl, bool reverse) { struct flowi6 *fl6 = &fl->u.ip6; memset(fl6, 0, sizeof(struct flowi6)); if (reverse) { fl6->saddr = flkeys->addrs.ipv6.dst; fl6->daddr = flkeys->addrs.ipv6.src; fl6->fl6_sport = flkeys->ports.dst; fl6->fl6_dport = flkeys->ports.src; } else { fl6->saddr = flkeys->addrs.ipv6.src; fl6->daddr = flkeys->addrs.ipv6.dst; fl6->fl6_sport = flkeys->ports.src; fl6->fl6_dport = flkeys->ports.dst; } switch (flkeys->basic.ip_proto) { case IPPROTO_GRE: fl6->fl6_gre_key = flkeys->gre.keyid; break; case IPPROTO_ICMPV6: fl6->fl6_icmp_type = flkeys->icmp.type; fl6->fl6_icmp_code = flkeys->icmp.code; break; } fl6->flowi6_proto = flkeys->basic.ip_proto; } #endif int __xfrm_decode_session(struct net *net, struct sk_buff *skb, struct flowi *fl, unsigned int family, int reverse) { struct xfrm_flow_keys flkeys; memset(&flkeys, 0, sizeof(flkeys)); __skb_flow_dissect(net, skb, &xfrm_session_dissector, &flkeys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_ENCAP); switch (family) { case AF_INET: decode_session4(&flkeys, fl, reverse); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: decode_session6(&flkeys, fl, reverse); break; #endif default: return -EAFNOSUPPORT; } fl->flowi_mark = skb->mark; if (reverse) { fl->flowi_oif = skb->skb_iif; } else { int oif = 0; if (skb_dst(skb) && skb_dst(skb)->dev) oif = skb_dst(skb)->dev->ifindex; fl->flowi_oif = oif; } return security_xfrm_decode_session(skb, &fl->flowi_secid); } EXPORT_SYMBOL(__xfrm_decode_session); static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { *idxp = k; return 1; } } return 0; } static bool icmp_err_packet(const struct flowi *fl, unsigned short family) { const struct flowi4 *fl4 = &fl->u.ip4; if (family == AF_INET && fl4->flowi4_proto == IPPROTO_ICMP && (fl4->fl4_icmp_type == ICMP_DEST_UNREACH || fl4->fl4_icmp_type == ICMP_TIME_EXCEEDED)) return true; #if IS_ENABLED(CONFIG_IPV6) if (family == AF_INET6) { const struct flowi6 *fl6 = &fl->u.ip6; if (fl6->flowi6_proto == IPPROTO_ICMPV6 && (fl6->fl6_icmp_type == ICMPV6_DEST_UNREACH || fl6->fl6_icmp_type == ICMPV6_PKT_TOOBIG || fl6->fl6_icmp_type == ICMPV6_TIME_EXCEED)) return true; } #endif return false; } static bool xfrm_icmp_flow_decode(struct sk_buff *skb, unsigned short family, const struct flowi *fl, struct flowi *fl1) { bool ret = true; struct sk_buff *newskb = skb_clone(skb, GFP_ATOMIC); int hl = family == AF_INET ? (sizeof(struct iphdr) + sizeof(struct icmphdr)) : (sizeof(struct ipv6hdr) + sizeof(struct icmp6hdr)); if (!newskb) return true; if (!pskb_pull(newskb, hl)) goto out; skb_reset_network_header(newskb); if (xfrm_decode_session_reverse(dev_net(skb->dev), newskb, fl1, family) < 0) goto out; fl1->flowi_oif = fl->flowi_oif; fl1->flowi_mark = fl->flowi_mark; fl1->flowi_dscp = fl->flowi_dscp; nf_nat_decode_session(newskb, fl1, family); ret = false; out: consume_skb(newskb); return ret; } static bool xfrm_selector_inner_icmp_match(struct sk_buff *skb, unsigned short family, const struct xfrm_selector *sel, const struct flowi *fl) { bool ret = false; if (icmp_err_packet(fl, family)) { struct flowi fl1; if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) return ret; ret = xfrm_selector_match(sel, &fl1, family); } return ret; } static inline struct xfrm_policy *xfrm_in_fwd_icmp(struct sk_buff *skb, const struct flowi *fl, unsigned short family, u32 if_id) { struct xfrm_policy *pol = NULL; if (icmp_err_packet(fl, family)) { struct flowi fl1; struct net *net = dev_net(skb->dev); if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) return pol; pol = xfrm_policy_lookup(net, &fl1, family, XFRM_POLICY_FWD, if_id); if (IS_ERR(pol)) pol = NULL; } return pol; } static inline struct dst_entry *xfrm_out_fwd_icmp(struct sk_buff *skb, struct flowi *fl, unsigned short family, struct dst_entry *dst) { if (icmp_err_packet(fl, family)) { struct net *net = dev_net(skb->dev); struct dst_entry *dst2; struct flowi fl1; if (xfrm_icmp_flow_decode(skb, family, fl, &fl1)) return dst; dst_hold(dst); dst2 = xfrm_lookup(net, dst, &fl1, NULL, (XFRM_LOOKUP_QUEUE | XFRM_LOOKUP_ICMP)); if (IS_ERR(dst2)) return dst; if (dst2->xfrm) { dst_release(dst); dst = dst2; } else { dst_release(dst2); } } return dst; } int __xfrm_policy_check(struct sock *sk, int dir, struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct xfrm_policy *pol; struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; int npols = 0; int xfrm_nr; int pi; int reverse; struct flowi fl; int xerr_idx = -1; const struct xfrm_if_cb *ifcb; struct sec_path *sp; u32 if_id = 0; rcu_read_lock(); ifcb = xfrm_if_get_cb(); if (ifcb) { struct xfrm_if_decode_session_result r; if (ifcb->decode_session(skb, family, &r)) { if_id = r.if_id; net = r.net; } } rcu_read_unlock(); reverse = dir & ~XFRM_POLICY_MASK; dir &= XFRM_POLICY_MASK; if (__xfrm_decode_session(net, skb, &fl, family, reverse) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINHDRERROR); return 0; } nf_nat_decode_session(skb, &fl, family); /* First, check used SA against their selectors. */ sp = skb_sec_path(skb); if (sp) { int i; for (i = sp->len - 1; i >= 0; i--) { struct xfrm_state *x = sp->xvec[i]; int ret = 0; if (!xfrm_selector_match(&x->sel, &fl, family)) { ret = 1; if (x->props.flags & XFRM_STATE_ICMP && xfrm_selector_inner_icmp_match(skb, family, &x->sel, &fl)) ret = 0; if (ret) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEMISMATCH); return 0; } } } } pol = NULL; sk = sk_to_full_sk(sk); if (sk && sk->sk_policy[dir]) { pol = xfrm_sk_policy_lookup(sk, dir, &fl, family, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } } if (!pol) pol = xfrm_policy_lookup(net, &fl, family, dir, if_id); if (IS_ERR(pol)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); return 0; } if (!pol && dir == XFRM_POLICY_FWD) pol = xfrm_in_fwd_icmp(skb, &fl, family, if_id); if (!pol) { const bool is_crypto_offload = sp && (xfrm_input_state(skb)->xso.type == XFRM_DEV_OFFLOAD_CRYPTO); if (READ_ONCE(net->xfrm.policy_default[dir]) == XFRM_USERPOLICY_BLOCK) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } if (sp && secpath_has_nontransport(sp, 0, &xerr_idx) && !is_crypto_offload) { xfrm_secpath_reject(xerr_idx, skb, &fl); XFRM_INC_STATS(net, LINUX_MIB_XFRMINNOPOLS); return 0; } return 1; } /* This lockless write can happen from different cpus. */ WRITE_ONCE(pol->curlft.use_time, ktime_get_real_seconds()); pols[0] = pol; npols++; #ifdef CONFIG_XFRM_SUB_POLICY if (pols[0]->type != XFRM_POLICY_TYPE_MAIN) { pols[1] = xfrm_policy_lookup_bytype(net, XFRM_POLICY_TYPE_MAIN, &fl, family, XFRM_POLICY_IN, if_id); if (pols[1]) { if (IS_ERR(pols[1])) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLERROR); xfrm_pol_put(pols[0]); return 0; } /* This write can happen from different cpus. */ WRITE_ONCE(pols[1]->curlft.use_time, ktime_get_real_seconds()); npols++; } } #endif if (pol->action == XFRM_POLICY_ALLOW) { static struct sec_path dummy; struct xfrm_tmpl *tp[XFRM_MAX_DEPTH]; struct xfrm_tmpl *stp[XFRM_MAX_DEPTH]; struct xfrm_tmpl **tpp = tp; int i, k = 0; int ti = 0; sp = skb_sec_path(skb); if (!sp) sp = &dummy; for (pi = 0; pi < npols; pi++) { if (pols[pi] != pol && pols[pi]->action != XFRM_POLICY_ALLOW) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); goto reject; } if (ti + pols[pi]->xfrm_nr >= XFRM_MAX_DEPTH) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINBUFFERERROR); goto reject_error; } for (i = 0; i < pols[pi]->xfrm_nr; i++) tpp[ti++] = &pols[pi]->xfrm_vec[i]; } xfrm_nr = ti; if (npols > 1) { xfrm_tmpl_sort(stp, tpp, xfrm_nr, family); tpp = stp; } if (pol->xdo.type == XFRM_DEV_OFFLOAD_PACKET && sp == &dummy) /* This policy template was already checked by HW * and secpath was removed in __xfrm_policy_check2. */ goto out; /* For each tunnel xfrm, find the first matching tmpl. * For each tmpl before that, find corresponding xfrm. * Order is _important_. Later we will implement * some barriers, but at the moment barriers * are implied between each two transformations. * Upon success, marks secpath entries as having been * verified to allow them to be skipped in future policy * checks (e.g. nested tunnels). */ for (i = xfrm_nr - 1; i >= 0; i--) { k = xfrm_policy_ok(tpp[i], sp, k, family, if_id); if (k < 0) { if (k < -1) /* "-2 - errored_index" returned */ xerr_idx = -(2+k); XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } } if (secpath_has_nontransport(sp, k, &xerr_idx)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMINTMPLMISMATCH); goto reject; } out: xfrm_pols_put(pols, npols); sp->verified_cnt = k; return 1; } XFRM_INC_STATS(net, LINUX_MIB_XFRMINPOLBLOCK); reject: xfrm_secpath_reject(xerr_idx, skb, &fl); reject_error: xfrm_pols_put(pols, npols); return 0; } EXPORT_SYMBOL(__xfrm_policy_check); int __xfrm_route_forward(struct sk_buff *skb, unsigned short family) { struct net *net = dev_net(skb->dev); struct flowi fl; struct dst_entry *dst; int res = 1; if (xfrm_decode_session(net, skb, &fl, family) < 0) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } skb_dst_force(skb); dst = skb_dst(skb); if (!dst) { XFRM_INC_STATS(net, LINUX_MIB_XFRMFWDHDRERROR); return 0; } /* ignore return value from skb_dstref_steal, xfrm_lookup takes * care of dropping the refcnt if needed. */ skb_dstref_steal(skb); dst = xfrm_lookup(net, dst, &fl, NULL, XFRM_LOOKUP_QUEUE); if (IS_ERR(dst)) { res = 0; dst = NULL; } if (dst && !dst->xfrm) dst = xfrm_out_fwd_icmp(skb, &fl, family, dst); skb_dst_set(skb, dst); return res; } EXPORT_SYMBOL(__xfrm_route_forward); /* Optimize later using cookies and generation ids. */ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) { /* Code (such as xfrm_bundle_create()) sets dst->obsolete * to DST_OBSOLETE_FORCE_CHK to force all XFRM destinations to * get validated by dst_ops->check on every use. We do this * because when a normal route referenced by an XFRM dst is * obsoleted we do not go looking around for all parent * referencing XFRM dsts so that we can invalidate them. It * is just too much work. Instead we make the checks here on * every use. For example: * * XFRM dst A --> IPv4 dst X * * X is the "xdst->route" of A (X is also the "dst->path" of A * in this example). If X is marked obsolete, "A" will not * notice. That's what we are validating here via the * stale_bundle() check. * * When a dst is removed from the fib tree, DST_OBSOLETE_DEAD will * be marked on it. * This will force stale_bundle() to fail on any xdst bundle with * this dst linked in it. */ if (READ_ONCE(dst->obsolete) < 0 && !stale_bundle(dst)) return dst; return NULL; } static int stale_bundle(struct dst_entry *dst) { return !xfrm_bundle_ok((struct xfrm_dst *)dst); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) { while ((dst = xfrm_dst_child(dst)) && dst->xfrm && dst->dev == dev) { dst->dev = blackhole_netdev; dev_hold(dst->dev); dev_put(dev); } } EXPORT_SYMBOL(xfrm_dst_ifdown); static void xfrm_link_failure(struct sk_buff *skb) { /* Impossible. Such dst must be popped before reaches point of failure. */ } static void xfrm_negative_advice(struct sock *sk, struct dst_entry *dst) { if (READ_ONCE(dst->obsolete)) sk_dst_reset(sk); } static void xfrm_init_pmtu(struct xfrm_dst **bundle, int nr) { while (nr--) { struct xfrm_dst *xdst = bundle[nr]; u32 pmtu, route_mtu_cached; struct dst_entry *dst; dst = &xdst->u.dst; pmtu = dst_mtu(xfrm_dst_child(dst)); xdst->child_mtu_cached = pmtu; pmtu = xfrm_state_mtu(dst->xfrm, pmtu); route_mtu_cached = dst_mtu(xdst->route); xdst->route_mtu_cached = route_mtu_cached; if (pmtu > route_mtu_cached) pmtu = route_mtu_cached; dst_metric_set(dst, RTAX_MTU, pmtu); } } /* Check that the bundle accepts the flow and its components are * still valid. */ static int xfrm_bundle_ok(struct xfrm_dst *first) { struct xfrm_dst *bundle[XFRM_MAX_DEPTH]; struct dst_entry *dst = &first->u.dst; struct xfrm_dst *xdst; int start_from, nr; u32 mtu; if (!dst_check(xfrm_dst_path(dst), ((struct xfrm_dst *)dst)->path_cookie) || (dst->dev && !netif_running(dst->dev))) return 0; if (dst->flags & DST_XFRM_QUEUE) return 1; start_from = nr = 0; do { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; if (dst->xfrm->km.state != XFRM_STATE_VALID) return 0; if (xdst->xfrm_genid != dst->xfrm->genid) return 0; if (xdst->num_pols > 0 && xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; bundle[nr++] = xdst; mtu = dst_mtu(xfrm_dst_child(dst)); if (xdst->child_mtu_cached != mtu) { start_from = nr; xdst->child_mtu_cached = mtu; } if (!dst_check(xdst->route, xdst->route_cookie)) return 0; mtu = dst_mtu(xdst->route); if (xdst->route_mtu_cached != mtu) { start_from = nr; xdst->route_mtu_cached = mtu; } dst = xfrm_dst_child(dst); } while (dst->xfrm); if (likely(!start_from)) return 1; xdst = bundle[start_from - 1]; mtu = xdst->child_mtu_cached; while (start_from--) { dst = &xdst->u.dst; mtu = xfrm_state_mtu(dst->xfrm, mtu); if (mtu > xdst->route_mtu_cached) mtu = xdst->route_mtu_cached; dst_metric_set(dst, RTAX_MTU, mtu); if (!start_from) break; xdst = bundle[start_from - 1]; xdst->child_mtu_cached = mtu; } return 1; } static unsigned int xfrm_default_advmss(const struct dst_entry *dst) { return dst_metric_advmss(xfrm_dst_path(dst)); } static unsigned int xfrm_mtu(const struct dst_entry *dst) { unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); return mtu ? : dst_mtu(xfrm_dst_path(dst)); } static const void *xfrm_get_dst_nexthop(const struct dst_entry *dst, const void *daddr) { while (dst->xfrm) { const struct xfrm_state *xfrm = dst->xfrm; dst = xfrm_dst_child(dst); if (xfrm->props.mode == XFRM_MODE_TRANSPORT) continue; if (xfrm->type->flags & XFRM_TYPE_REMOTE_COADDR) daddr = xfrm->coaddr; else if (!(xfrm->type->flags & XFRM_TYPE_LOCAL_COADDR)) daddr = &xfrm->id.daddr; } return daddr; } static struct neighbour *xfrm_neigh_lookup(const struct dst_entry *dst, struct sk_buff *skb, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); if (!skb) daddr = xfrm_get_dst_nexthop(dst, daddr); return path->ops->neigh_lookup(path, skb, daddr); } static void xfrm_confirm_neigh(const struct dst_entry *dst, const void *daddr) { const struct dst_entry *path = xfrm_dst_path(dst); daddr = xfrm_get_dst_nexthop(dst, daddr); path->ops->confirm_neigh(path, daddr); } int xfrm_policy_register_afinfo(const struct xfrm_policy_afinfo *afinfo, int family) { int err = 0; if (WARN_ON(family >= ARRAY_SIZE(xfrm_policy_afinfo))) return -EAFNOSUPPORT; spin_lock(&xfrm_policy_afinfo_lock); if (unlikely(xfrm_policy_afinfo[family] != NULL)) err = -EEXIST; else { struct dst_ops *dst_ops = afinfo->dst_ops; if (likely(dst_ops->kmem_cachep == NULL)) dst_ops->kmem_cachep = xfrm_dst_cache; if (likely(dst_ops->check == NULL)) dst_ops->check = xfrm_dst_check; if (likely(dst_ops->default_advmss == NULL)) dst_ops->default_advmss = xfrm_default_advmss; if (likely(dst_ops->mtu == NULL)) dst_ops->mtu = xfrm_mtu; if (likely(dst_ops->negative_advice == NULL)) dst_ops->negative_advice = xfrm_negative_advice; if (likely(dst_ops->link_failure == NULL)) dst_ops->link_failure = xfrm_link_failure; if (likely(dst_ops->neigh_lookup == NULL)) dst_ops->neigh_lookup = xfrm_neigh_lookup; if (likely(!dst_ops->confirm_neigh)) dst_ops->confirm_neigh = xfrm_confirm_neigh; rcu_assign_pointer(xfrm_policy_afinfo[family], afinfo); } spin_unlock(&xfrm_policy_afinfo_lock); return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); void xfrm_policy_unregister_afinfo(const struct xfrm_policy_afinfo *afinfo) { struct dst_ops *dst_ops = afinfo->dst_ops; int i; for (i = 0; i < ARRAY_SIZE(xfrm_policy_afinfo); i++) { if (rcu_access_pointer(xfrm_policy_afinfo[i]) != afinfo) continue; RCU_INIT_POINTER(xfrm_policy_afinfo[i], NULL); break; } synchronize_rcu(); dst_ops->kmem_cachep = NULL; dst_ops->check = NULL; dst_ops->negative_advice = NULL; dst_ops->link_failure = NULL; } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); void xfrm_if_register_cb(const struct xfrm_if_cb *ifcb) { spin_lock(&xfrm_if_cb_lock); rcu_assign_pointer(xfrm_if_cb, ifcb); spin_unlock(&xfrm_if_cb_lock); } EXPORT_SYMBOL(xfrm_if_register_cb); void xfrm_if_unregister_cb(void) { RCU_INIT_POINTER(xfrm_if_cb, NULL); synchronize_rcu(); } EXPORT_SYMBOL(xfrm_if_unregister_cb); #ifdef CONFIG_XFRM_STATISTICS static int __net_init xfrm_statistics_init(struct net *net) { int rv; net->mib.xfrm_statistics = alloc_percpu(struct linux_xfrm_mib); if (!net->mib.xfrm_statistics) return -ENOMEM; rv = xfrm_proc_init(net); if (rv < 0) free_percpu(net->mib.xfrm_statistics); return rv; } static void xfrm_statistics_fini(struct net *net) { xfrm_proc_fini(net); free_percpu(net->mib.xfrm_statistics); } #else static int __net_init xfrm_statistics_init(struct net *net) { return 0; } static void xfrm_statistics_fini(struct net *net) { } #endif static int __net_init xfrm_policy_init(struct net *net) { unsigned int hmask, sz; int dir, err; if (net_eq(net, &init_net)) { xfrm_dst_cache = KMEM_CACHE(xfrm_dst, SLAB_HWCACHE_ALIGN | SLAB_PANIC); err = rhashtable_init(&xfrm_policy_inexact_table, &xfrm_pol_inexact_params); BUG_ON(err); } hmask = 8 - 1; sz = (hmask+1) * sizeof(struct hlist_head); net->xfrm.policy_byidx = xfrm_hash_alloc(sz); if (!net->xfrm.policy_byidx) goto out_byidx; net->xfrm.policy_idx_hmask = hmask; for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; net->xfrm.policy_count[dir] = 0; net->xfrm.policy_count[XFRM_POLICY_MAX + dir] = 0; htab = &net->xfrm.policy_bydst[dir]; rcu_assign_pointer(htab->table, xfrm_hash_alloc(sz)); if (!htab->table) goto out_bydst; htab->hmask = hmask; htab->dbits4 = 32; htab->sbits4 = 32; htab->dbits6 = 128; htab->sbits6 = 128; } net->xfrm.policy_hthresh.lbits4 = 32; net->xfrm.policy_hthresh.rbits4 = 32; net->xfrm.policy_hthresh.lbits6 = 128; net->xfrm.policy_hthresh.rbits6 = 128; seqlock_init(&net->xfrm.policy_hthresh.lock); INIT_LIST_HEAD(&net->xfrm.policy_all); INIT_LIST_HEAD(&net->xfrm.inexact_bins); INIT_WORK(&net->xfrm.policy_hash_work, xfrm_hash_resize); INIT_WORK(&net->xfrm.policy_hthresh.work, xfrm_hash_rebuild); return 0; out_bydst: for (dir--; dir >= 0; dir--) { struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } xfrm_hash_free(net->xfrm.policy_byidx, sz); out_byidx: return -ENOMEM; } static void __net_exit xfrm_net_pre_exit(struct net *net) { disable_work_sync(&net->xfrm.policy_hthresh.work); flush_work(&net->xfrm.policy_hash_work); #ifdef CONFIG_XFRM_SUB_POLICY xfrm_policy_flush(net, XFRM_POLICY_TYPE_SUB, false); #endif xfrm_policy_flush(net, XFRM_POLICY_TYPE_MAIN, false); } static void xfrm_policy_fini(struct net *net) { struct xfrm_pol_inexact_bin *b, *t; unsigned int sz; int dir; WARN_ON(!list_empty(&net->xfrm.policy_all)); for (dir = 0; dir < XFRM_POLICY_MAX; dir++) { struct xfrm_policy_hash *htab; htab = &net->xfrm.policy_bydst[dir]; sz = (htab->hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(rcu_dereference_protected(htab->table, true))); xfrm_hash_free(rcu_dereference_protected(htab->table, true), sz); } sz = (net->xfrm.policy_idx_hmask + 1) * sizeof(struct hlist_head); WARN_ON(!hlist_empty(net->xfrm.policy_byidx)); xfrm_hash_free(net->xfrm.policy_byidx, sz); spin_lock_bh(&net->xfrm.xfrm_policy_lock); list_for_each_entry_safe(b, t, &net->xfrm.inexact_bins, inexact_bins) __xfrm_policy_inexact_prune_bin(b, true); spin_unlock_bh(&net->xfrm.xfrm_policy_lock); } static int __net_init xfrm_net_init(struct net *net) { int rv; /* Initialize the per-net locks here */ spin_lock_init(&net->xfrm.xfrm_state_lock); spin_lock_init(&net->xfrm.xfrm_policy_lock); seqcount_spinlock_init(&net->xfrm.xfrm_policy_hash_generation, &net->xfrm.xfrm_policy_lock); mutex_init(&net->xfrm.xfrm_cfg_mutex); net->xfrm.policy_default[XFRM_POLICY_IN] = XFRM_USERPOLICY_ACCEPT; net->xfrm.policy_default[XFRM_POLICY_FWD] = XFRM_USERPOLICY_ACCEPT; net->xfrm.policy_default[XFRM_POLICY_OUT] = XFRM_USERPOLICY_ACCEPT; rv = xfrm_statistics_init(net); if (rv < 0) goto out_statistics; rv = xfrm_state_init(net); if (rv < 0) goto out_state; rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; rv = xfrm_nat_keepalive_net_init(net); if (rv < 0) goto out_nat_keepalive; return 0; out_nat_keepalive: xfrm_sysctl_fini(net); out_sysctl: xfrm_policy_fini(net); out_policy: xfrm_state_fini(net); out_state: xfrm_statistics_fini(net); out_statistics: return rv; } static void __net_exit xfrm_net_exit(struct net *net) { xfrm_nat_keepalive_net_fini(net); xfrm_sysctl_fini(net); xfrm_policy_fini(net); xfrm_state_fini(net); xfrm_statistics_fini(net); } static struct pernet_operations __net_initdata xfrm_net_ops = { .init = xfrm_net_init, .pre_exit = xfrm_net_pre_exit, .exit = xfrm_net_exit, }; static const struct flow_dissector_key xfrm_flow_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct xfrm_flow_keys, control), }, { .key_id = FLOW_DISSECTOR_KEY_BASIC, .offset = offsetof(struct xfrm_flow_keys, basic), }, { .key_id = FLOW_DISSECTOR_KEY_IPV4_ADDRS, .offset = offsetof(struct xfrm_flow_keys, addrs.ipv4), }, { .key_id = FLOW_DISSECTOR_KEY_IPV6_ADDRS, .offset = offsetof(struct xfrm_flow_keys, addrs.ipv6), }, { .key_id = FLOW_DISSECTOR_KEY_PORTS, .offset = offsetof(struct xfrm_flow_keys, ports), }, { .key_id = FLOW_DISSECTOR_KEY_GRE_KEYID, .offset = offsetof(struct xfrm_flow_keys, gre), }, { .key_id = FLOW_DISSECTOR_KEY_IP, .offset = offsetof(struct xfrm_flow_keys, ip), }, { .key_id = FLOW_DISSECTOR_KEY_ICMP, .offset = offsetof(struct xfrm_flow_keys, icmp), }, }; void __init xfrm_init(void) { skb_flow_dissector_init(&xfrm_session_dissector, xfrm_flow_dissector_keys, ARRAY_SIZE(xfrm_flow_dissector_keys)); register_pernet_subsys(&xfrm_net_ops); xfrm_dev_init(); xfrm_input_init(); #ifdef CONFIG_XFRM_ESPINTCP espintcp_init(); #endif register_xfrm_state_bpf(); xfrm_nat_keepalive_init(AF_INET); } #ifdef CONFIG_AUDITSYSCALL static void xfrm_audit_common_policyinfo(struct xfrm_policy *xp, struct audit_buffer *audit_buf) { struct xfrm_sec_ctx *ctx = xp->security; struct xfrm_selector *sel = &xp->selector; if (ctx) audit_log_format(audit_buf, " sec_alg=%u sec_doi=%u sec_obj=%s", ctx->ctx_alg, ctx->ctx_doi, ctx->ctx_str); switch (sel->family) { case AF_INET: audit_log_format(audit_buf, " src=%pI4", &sel->saddr.a4); if (sel->prefixlen_s != 32) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); audit_log_format(audit_buf, " dst=%pI4", &sel->daddr.a4); if (sel->prefixlen_d != 32) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; case AF_INET6: audit_log_format(audit_buf, " src=%pI6", sel->saddr.a6); if (sel->prefixlen_s != 128) audit_log_format(audit_buf, " src_prefixlen=%d", sel->prefixlen_s); audit_log_format(audit_buf, " dst=%pI6", sel->daddr.a6); if (sel->prefixlen_d != 128) audit_log_format(audit_buf, " dst_prefixlen=%d", sel->prefixlen_d); break; } } void xfrm_audit_policy_add(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-add"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_policy_add); void xfrm_audit_policy_delete(struct xfrm_policy *xp, int result, bool task_valid) { struct audit_buffer *audit_buf; audit_buf = xfrm_audit_start("SPD-delete"); if (audit_buf == NULL) return; xfrm_audit_helper_usrinfo(task_valid, audit_buf); audit_log_format(audit_buf, " res=%u", result); xfrm_audit_common_policyinfo(xp, audit_buf); audit_log_end(audit_buf); } EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE static struct xfrm_policy *xfrm_migrate_policy_find(const struct xfrm_selector *sel, u8 dir, u8 type, struct net *net, u32 if_id) { struct xfrm_policy *pol; struct flowi fl; memset(&fl, 0, sizeof(fl)); fl.flowi_proto = sel->proto; switch (sel->family) { case AF_INET: fl.u.ip4.saddr = sel->saddr.a4; fl.u.ip4.daddr = sel->daddr.a4; if (sel->proto == IPSEC_ULPROTO_ANY) break; fl.u.flowi4_oif = sel->ifindex; fl.u.ip4.fl4_sport = sel->sport; fl.u.ip4.fl4_dport = sel->dport; break; case AF_INET6: fl.u.ip6.saddr = sel->saddr.in6; fl.u.ip6.daddr = sel->daddr.in6; if (sel->proto == IPSEC_ULPROTO_ANY) break; fl.u.flowi6_oif = sel->ifindex; fl.u.ip6.fl4_sport = sel->sport; fl.u.ip6.fl4_dport = sel->dport; break; default: return ERR_PTR(-EAFNOSUPPORT); } rcu_read_lock(); pol = xfrm_policy_lookup_bytype(net, type, &fl, sel->family, dir, if_id); if (IS_ERR_OR_NULL(pol)) goto out_unlock; out_unlock: rcu_read_unlock(); return pol; } static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t) { int match = 0; if (t->mode == m->mode && t->id.proto == m->proto && (m->old_reqid == 0 || t->reqid == m->old_reqid)) { switch (t->mode) { case XFRM_MODE_TUNNEL: case XFRM_MODE_BEET: case XFRM_MODE_IPTFS: if (xfrm_addr_equal(&t->id.daddr, &m->old_daddr, m->old_family) && xfrm_addr_equal(&t->saddr, &m->old_saddr, m->old_family)) { match = 1; } break; case XFRM_MODE_TRANSPORT: /* in case of transport mode, template does not store any IP addresses, hence we just compare mode and protocol */ match = 1; break; default: break; } } return match; } /* update endpoint address(es) of template(s) */ static int xfrm_policy_migrate(struct xfrm_policy *pol, struct xfrm_migrate *m, int num_migrate, struct netlink_ext_ack *extack) { struct xfrm_migrate *mp; int i, j, n = 0; write_lock_bh(&pol->lock); if (unlikely(pol->walk.dead)) { /* target policy has been deleted */ NL_SET_ERR_MSG(extack, "Target policy not found"); write_unlock_bh(&pol->lock); return -ENOENT; } for (i = 0; i < pol->xfrm_nr; i++) { for (j = 0, mp = m; j < num_migrate; j++, mp++) { if (!migrate_tmpl_match(mp, &pol->xfrm_vec[i])) continue; n++; if (pol->xfrm_vec[i].mode != XFRM_MODE_TUNNEL && pol->xfrm_vec[i].mode != XFRM_MODE_BEET && pol->xfrm_vec[i].mode != XFRM_MODE_IPTFS) continue; /* update endpoints */ memcpy(&pol->xfrm_vec[i].id.daddr, &mp->new_daddr, sizeof(pol->xfrm_vec[i].id.daddr)); memcpy(&pol->xfrm_vec[i].saddr, &mp->new_saddr, sizeof(pol->xfrm_vec[i].saddr)); pol->xfrm_vec[i].encap_family = mp->new_family; /* flush bundles */ atomic_inc(&pol->genid); } } write_unlock_bh(&pol->lock); if (!n) return -ENODATA; return 0; } static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate, struct netlink_ext_ack *extack) { int i, j; if (num_migrate < 1 || num_migrate > XFRM_MAX_DEPTH) { NL_SET_ERR_MSG(extack, "Invalid number of SAs to migrate, must be 0 < num <= XFRM_MAX_DEPTH (6)"); return -EINVAL; } for (i = 0; i < num_migrate; i++) { if (xfrm_addr_any(&m[i].new_daddr, m[i].new_family) || xfrm_addr_any(&m[i].new_saddr, m[i].new_family)) { NL_SET_ERR_MSG(extack, "Addresses in the MIGRATE attribute's list cannot be null"); return -EINVAL; } /* check if there is any duplicated entry */ for (j = i + 1; j < num_migrate; j++) { if (!memcmp(&m[i].old_daddr, &m[j].old_daddr, sizeof(m[i].old_daddr)) && !memcmp(&m[i].old_saddr, &m[j].old_saddr, sizeof(m[i].old_saddr)) && m[i].proto == m[j].proto && m[i].mode == m[j].mode && m[i].old_reqid == m[j].old_reqid && m[i].old_family == m[j].old_family) { NL_SET_ERR_MSG(extack, "Entries in the MIGRATE attribute's list must be unique"); return -EINVAL; } } } return 0; } /* * Fill migrate fields that are invariant in XFRM_MSG_MIGRATE: inherited * from the existing SA unchanged. XFRM_MSG_MIGRATE_STATE can update these. */ static void xfrm_migrate_copy_old(const struct xfrm_state *x, struct xfrm_migrate *mp) { mp->msg_type = XFRM_MSG_MIGRATE; mp->smark = x->props.smark; mp->new_reqid = x->props.reqid; mp->nat_keepalive_interval = x->nat_keepalive_interval; mp->mapping_maxage = x->mapping_maxage; mp->new_mark = &x->mark; } int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k, struct net *net, struct xfrm_encap_tmpl *encap, u32 if_id, struct netlink_ext_ack *extack, struct xfrm_user_offload *xuo) { int i, err, nx_cur = 0, nx_new = 0; struct xfrm_policy *pol = NULL; struct xfrm_state *x, *xc; struct xfrm_state *x_cur[XFRM_MAX_DEPTH]; struct xfrm_state *x_new[XFRM_MAX_DEPTH]; struct xfrm_migrate *mp; /* Stage 0 - sanity checks */ err = xfrm_migrate_check(m, num_migrate, extack); if (err < 0) goto out; if (dir >= XFRM_POLICY_MAX) { NL_SET_ERR_MSG(extack, "Invalid policy direction"); err = -EINVAL; goto out; } /* Stage 1 - find policy */ pol = xfrm_migrate_policy_find(sel, dir, type, net, if_id); if (IS_ERR_OR_NULL(pol)) { NL_SET_ERR_MSG(extack, "Target policy not found"); err = IS_ERR(pol) ? PTR_ERR(pol) : -ENOENT; goto out; } /* Stage 2 - find and update state(s) */ for (i = 0, mp = m; i < num_migrate; i++, mp++) { if ((x = xfrm_migrate_state_find(mp, net, if_id))) { x_cur[nx_cur] = x; nx_cur++; mp->encap = encap; mp->xuo = xuo; xfrm_migrate_copy_old(x, mp); xc = xfrm_state_migrate(x, mp, net, extack); if (xc) { x_new[nx_new] = xc; nx_new++; } else { err = -ENODATA; goto restore_state; } } } /* Stage 3 - update policy */ err = xfrm_policy_migrate(pol, m, num_migrate, extack); if (err < 0) goto restore_state; /* Stage 4 - delete old state(s) */ if (nx_cur) { xfrm_states_put(x_cur, nx_cur); xfrm_states_delete(x_cur, nx_cur); } /* Stage 5 - announce */ km_migrate(sel, dir, type, m, num_migrate, k, net, encap); xfrm_pol_put(pol); return 0; out: return err; restore_state: if (pol) xfrm_pol_put(pol); if (nx_cur) xfrm_states_put(x_cur, nx_cur); if (nx_new) xfrm_states_delete(x_new, nx_new); return err; } EXPORT_SYMBOL(xfrm_migrate); #endif |
| 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 | // SPDX-License-Identifier: GPL-2.0-only /* * net/sunrpc/rpc_pipe.c * * Userland/kernel interface for rpcauth_gss. * Code shamelessly plagiarized from fs/nfsd/nfsctl.c * and fs/sysfs/inode.c * * Copyright (c) 2002, Trond Myklebust <trond.myklebust@fys.uio.no> * */ #include <linux/module.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/pagemap.h> #include <linux/mount.h> #include <linux/fs_context.h> #include <linux/namei.h> #include <linux/fsnotify.h> #include <linux/kernel.h> #include <linux/rcupdate.h> #include <linux/utsname.h> #include <asm/ioctls.h> #include <linux/poll.h> #include <linux/wait.h> #include <linux/seq_file.h> #include <linux/sunrpc/clnt.h> #include <linux/workqueue.h> #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/cache.h> #include <linux/nsproxy.h> #include <linux/notifier.h> #include "netns.h" #include "sunrpc.h" #define RPCDBG_FACILITY RPCDBG_DEBUG #define NET_NAME(net) ((net == &init_net) ? " (init_net)" : "") static struct file_system_type rpc_pipe_fs_type; static const struct rpc_pipe_ops gssd_dummy_pipe_ops; static struct kmem_cache *rpc_inode_cachep __read_mostly; #define RPC_UPCALL_TIMEOUT (30*HZ) static BLOCKING_NOTIFIER_HEAD(rpc_pipefs_notifier_list); int rpc_pipefs_notifier_register(struct notifier_block *nb) { return blocking_notifier_chain_register(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_register); void rpc_pipefs_notifier_unregister(struct notifier_block *nb) { blocking_notifier_chain_unregister(&rpc_pipefs_notifier_list, nb); } EXPORT_SYMBOL_GPL(rpc_pipefs_notifier_unregister); static void rpc_purge_list(wait_queue_head_t *waitq, struct list_head *head, void (*destroy_msg)(struct rpc_pipe_msg *), int err) { struct rpc_pipe_msg *msg; if (list_empty(head)) return; do { msg = list_entry(head->next, struct rpc_pipe_msg, list); list_del_init(&msg->list); msg->errno = err; destroy_msg(msg); } while (!list_empty(head)); if (waitq) wake_up(waitq); } static void rpc_timeout_upcall_queue(struct work_struct *work) { LIST_HEAD(free_list); struct rpc_pipe *pipe = container_of(work, struct rpc_pipe, queue_timeout.work); void (*destroy_msg)(struct rpc_pipe_msg *); struct dentry *dentry; spin_lock(&pipe->lock); destroy_msg = pipe->ops->destroy_msg; if (pipe->nreaders == 0) { list_splice_init(&pipe->pipe, &free_list); pipe->pipelen = 0; } dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); rpc_purge_list(dentry ? &RPC_I(d_inode(dentry))->waitq : NULL, &free_list, destroy_msg, -ETIMEDOUT); dput(dentry); } ssize_t rpc_pipe_generic_upcall(struct file *filp, struct rpc_pipe_msg *msg, char __user *dst, size_t buflen) { char *data = (char *)msg->data + msg->copied; size_t mlen = min(msg->len - msg->copied, buflen); unsigned long left; left = copy_to_user(dst, data, mlen); if (left == mlen) { msg->errno = -EFAULT; return -EFAULT; } mlen -= left; msg->copied += mlen; msg->errno = 0; return mlen; } EXPORT_SYMBOL_GPL(rpc_pipe_generic_upcall); /** * rpc_queue_upcall - queue an upcall message to userspace * @pipe: upcall pipe on which to queue given message * @msg: message to queue * * Call with an @inode created by rpc_mkpipe() to queue an upcall. * A userspace process may then later read the upcall by performing a * read on an open file for this inode. It is up to the caller to * initialize the fields of @msg (other than @msg->list) appropriately. */ int rpc_queue_upcall(struct rpc_pipe *pipe, struct rpc_pipe_msg *msg) { int res = -EPIPE; struct dentry *dentry; spin_lock(&pipe->lock); if (pipe->nreaders) { list_add_tail(&msg->list, &pipe->pipe); pipe->pipelen += msg->len; res = 0; } else if (pipe->flags & RPC_PIPE_WAIT_FOR_OPEN) { if (list_empty(&pipe->pipe)) queue_delayed_work(rpciod_workqueue, &pipe->queue_timeout, RPC_UPCALL_TIMEOUT); list_add_tail(&msg->list, &pipe->pipe); pipe->pipelen += msg->len; res = 0; } dentry = dget(pipe->dentry); spin_unlock(&pipe->lock); if (dentry) { wake_up(&RPC_I(d_inode(dentry))->waitq); dput(dentry); } return res; } EXPORT_SYMBOL_GPL(rpc_queue_upcall); static inline void rpc_inode_setowner(struct inode *inode, void *private) { RPC_I(inode)->private = private; } static void rpc_close_pipes(struct dentry *dentry) { struct inode *inode = dentry->d_inode; struct rpc_pipe *pipe = RPC_I(inode)->pipe; int need_release; LIST_HEAD(free_list); inode_lock(inode); spin_lock(&pipe->lock); need_release = pipe->nreaders != 0 || pipe->nwriters != 0; pipe->nreaders = 0; list_splice_init(&pipe->in_upcall, &free_list); list_splice_init(&pipe->pipe, &free_list); pipe->pipelen = 0; pipe->dentry = NULL; spin_unlock(&pipe->lock); rpc_purge_list(&RPC_I(inode)->waitq, &free_list, pipe->ops->destroy_msg, -EPIPE); pipe->nwriters = 0; if (need_release && pipe->ops->release_pipe) pipe->ops->release_pipe(inode); cancel_delayed_work_sync(&pipe->queue_timeout); rpc_inode_setowner(inode, NULL); RPC_I(inode)->pipe = NULL; inode_unlock(inode); } static struct inode * rpc_alloc_inode(struct super_block *sb) { struct rpc_inode *rpci; rpci = alloc_inode_sb(sb, rpc_inode_cachep, GFP_KERNEL); if (!rpci) return NULL; return &rpci->vfs_inode; } static void rpc_free_inode(struct inode *inode) { kmem_cache_free(rpc_inode_cachep, RPC_I(inode)); } static int rpc_pipe_open(struct inode *inode, struct file *filp) { struct rpc_pipe *pipe; int first_open; int res = -ENXIO; inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) goto out; first_open = pipe->nreaders == 0 && pipe->nwriters == 0; if (first_open && pipe->ops->open_pipe) { res = pipe->ops->open_pipe(inode); if (res) goto out; } if (filp->f_mode & FMODE_READ) pipe->nreaders++; if (filp->f_mode & FMODE_WRITE) pipe->nwriters++; res = 0; out: inode_unlock(inode); return res; } static int rpc_pipe_release(struct inode *inode, struct file *filp) { struct rpc_pipe *pipe; struct rpc_pipe_msg *msg; int last_close; inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) goto out; msg = filp->private_data; if (msg != NULL) { spin_lock(&pipe->lock); msg->errno = -EAGAIN; list_del_init(&msg->list); spin_unlock(&pipe->lock); pipe->ops->destroy_msg(msg); } if (filp->f_mode & FMODE_WRITE) pipe->nwriters --; if (filp->f_mode & FMODE_READ) { pipe->nreaders --; if (pipe->nreaders == 0) { LIST_HEAD(free_list); spin_lock(&pipe->lock); list_splice_init(&pipe->pipe, &free_list); pipe->pipelen = 0; spin_unlock(&pipe->lock); rpc_purge_list(&RPC_I(inode)->waitq, &free_list, pipe->ops->destroy_msg, -EAGAIN); } } last_close = pipe->nwriters == 0 && pipe->nreaders == 0; if (last_close && pipe->ops->release_pipe) pipe->ops->release_pipe(inode); out: inode_unlock(inode); return 0; } static ssize_t rpc_pipe_read(struct file *filp, char __user *buf, size_t len, loff_t *offset) { struct inode *inode = file_inode(filp); struct rpc_pipe *pipe; struct rpc_pipe_msg *msg; int res = 0; inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) { res = -EPIPE; goto out_unlock; } msg = filp->private_data; if (msg == NULL) { spin_lock(&pipe->lock); if (!list_empty(&pipe->pipe)) { msg = list_entry(pipe->pipe.next, struct rpc_pipe_msg, list); list_move(&msg->list, &pipe->in_upcall); pipe->pipelen -= msg->len; filp->private_data = msg; msg->copied = 0; } spin_unlock(&pipe->lock); if (msg == NULL) goto out_unlock; } /* NOTE: it is up to the callback to update msg->copied */ res = pipe->ops->upcall(filp, msg, buf, len); if (res < 0 || msg->len == msg->copied) { filp->private_data = NULL; spin_lock(&pipe->lock); list_del_init(&msg->list); spin_unlock(&pipe->lock); pipe->ops->destroy_msg(msg); } out_unlock: inode_unlock(inode); return res; } static ssize_t rpc_pipe_write(struct file *filp, const char __user *buf, size_t len, loff_t *offset) { struct inode *inode = file_inode(filp); int res; inode_lock(inode); res = -EPIPE; if (RPC_I(inode)->pipe != NULL) res = RPC_I(inode)->pipe->ops->downcall(filp, buf, len); inode_unlock(inode); return res; } static __poll_t rpc_pipe_poll(struct file *filp, struct poll_table_struct *wait) { struct inode *inode = file_inode(filp); struct rpc_inode *rpci = RPC_I(inode); __poll_t mask = EPOLLOUT | EPOLLWRNORM; poll_wait(filp, &rpci->waitq, wait); inode_lock(inode); if (rpci->pipe == NULL) mask |= EPOLLERR | EPOLLHUP; else if (filp->private_data || !list_empty(&rpci->pipe->pipe)) mask |= EPOLLIN | EPOLLRDNORM; inode_unlock(inode); return mask; } static long rpc_pipe_ioctl(struct file *filp, unsigned int cmd, unsigned long arg) { struct inode *inode = file_inode(filp); struct rpc_pipe *pipe; int len; switch (cmd) { case FIONREAD: inode_lock(inode); pipe = RPC_I(inode)->pipe; if (pipe == NULL) { inode_unlock(inode); return -EPIPE; } spin_lock(&pipe->lock); len = pipe->pipelen; if (filp->private_data) { struct rpc_pipe_msg *msg; msg = filp->private_data; len += msg->len - msg->copied; } spin_unlock(&pipe->lock); inode_unlock(inode); return put_user(len, (int __user *)arg); default: return -EINVAL; } } static const struct file_operations rpc_pipe_fops = { .owner = THIS_MODULE, .read = rpc_pipe_read, .write = rpc_pipe_write, .poll = rpc_pipe_poll, .unlocked_ioctl = rpc_pipe_ioctl, .open = rpc_pipe_open, .release = rpc_pipe_release, }; static int rpc_show_info(struct seq_file *m, void *v) { struct rpc_clnt *clnt = m->private; rcu_read_lock(); seq_printf(m, "RPC server: %s\n", rcu_dereference(clnt->cl_xprt)->servername); seq_printf(m, "service: %s (%d) version %d\n", clnt->cl_program->name, clnt->cl_prog, clnt->cl_vers); seq_printf(m, "address: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_ADDR)); seq_printf(m, "protocol: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PROTO)); seq_printf(m, "port: %s\n", rpc_peeraddr2str(clnt, RPC_DISPLAY_PORT)); rcu_read_unlock(); return 0; } static int rpc_info_open(struct inode *inode, struct file *file) { struct rpc_clnt *clnt = NULL; int ret = single_open(file, rpc_show_info, NULL); if (!ret) { struct seq_file *m = file->private_data; spin_lock(&file->f_path.dentry->d_lock); if (!d_unhashed(file->f_path.dentry)) clnt = RPC_I(inode)->private; if (clnt != NULL && refcount_inc_not_zero(&clnt->cl_count)) { spin_unlock(&file->f_path.dentry->d_lock); m->private = clnt; } else { spin_unlock(&file->f_path.dentry->d_lock); single_release(inode, file); ret = -EINVAL; } } return ret; } static int rpc_info_release(struct inode *inode, struct file *file) { struct seq_file *m = file->private_data; struct rpc_clnt *clnt = (struct rpc_clnt *)m->private; if (clnt) rpc_release_client(clnt); return single_release(inode, file); } static const struct file_operations rpc_info_operations = { .owner = THIS_MODULE, .open = rpc_info_open, .read = seq_read, .llseek = seq_lseek, .release = rpc_info_release, }; /* * Description of fs contents. */ struct rpc_filelist { const char *name; const struct file_operations *i_fop; umode_t mode; }; static struct inode * rpc_get_inode(struct super_block *sb, umode_t mode) { struct inode *inode = new_inode(sb); if (!inode) return NULL; inode->i_ino = get_next_ino(); inode->i_mode = mode; simple_inode_init_ts(inode); switch (mode & S_IFMT) { case S_IFDIR: inode->i_fop = &simple_dir_operations; inode->i_op = &simple_dir_inode_operations; inc_nlink(inode); break; default: break; } return inode; } static void init_pipe(struct rpc_pipe *pipe) { pipe->nreaders = 0; pipe->nwriters = 0; INIT_LIST_HEAD(&pipe->in_upcall); INIT_LIST_HEAD(&pipe->in_downcall); INIT_LIST_HEAD(&pipe->pipe); pipe->pipelen = 0; INIT_DELAYED_WORK(&pipe->queue_timeout, rpc_timeout_upcall_queue); pipe->ops = NULL; spin_lock_init(&pipe->lock); pipe->dentry = NULL; } void rpc_destroy_pipe_data(struct rpc_pipe *pipe) { kfree(pipe); } EXPORT_SYMBOL_GPL(rpc_destroy_pipe_data); struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags) { struct rpc_pipe *pipe; pipe = kzalloc_obj(struct rpc_pipe); if (!pipe) return ERR_PTR(-ENOMEM); init_pipe(pipe); pipe->ops = ops; pipe->flags = flags; return pipe; } EXPORT_SYMBOL_GPL(rpc_mkpipe_data); static int rpc_new_file(struct dentry *parent, const char *name, umode_t mode, const struct file_operations *i_fop, void *private) { struct dentry *dentry = simple_start_creating(parent, name); struct inode *dir = parent->d_inode; struct inode *inode; if (IS_ERR(dentry)) return PTR_ERR(dentry); inode = rpc_get_inode(dir->i_sb, S_IFREG | mode); if (unlikely(!inode)) { simple_done_creating(dentry); return -ENOMEM; } inode->i_ino = iunique(dir->i_sb, 100); if (i_fop) inode->i_fop = i_fop; rpc_inode_setowner(inode, private); d_make_persistent(dentry, inode); fsnotify_create(dir, dentry); simple_done_creating(dentry); return 0; } static struct dentry *rpc_new_dir(struct dentry *parent, const char *name, umode_t mode) { struct dentry *dentry = simple_start_creating(parent, name); struct inode *dir = parent->d_inode; struct inode *inode; if (IS_ERR(dentry)) return dentry; inode = rpc_get_inode(dir->i_sb, S_IFDIR | mode); if (unlikely(!inode)) { simple_done_creating(dentry); return ERR_PTR(-ENOMEM); } inode->i_ino = iunique(dir->i_sb, 100); inc_nlink(dir); d_make_persistent(dentry, inode); fsnotify_mkdir(dir, dentry); simple_done_creating(dentry); return dentry; // borrowed } static int rpc_populate(struct dentry *parent, const struct rpc_filelist *files, int start, int eof, void *private) { struct dentry *dentry; int i, err; for (i = start; i < eof; i++) { switch (files[i].mode & S_IFMT) { default: BUG(); case S_IFREG: err = rpc_new_file(parent, files[i].name, files[i].mode, files[i].i_fop, private); if (err) goto out_bad; break; case S_IFDIR: dentry = rpc_new_dir(parent, files[i].name, files[i].mode); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto out_bad; } } } return 0; out_bad: printk(KERN_WARNING "%s: %s failed to populate directory %pd\n", __FILE__, __func__, parent); return err; } /** * rpc_mkpipe_dentry - make an rpc_pipefs file for kernel<->userspace * communication * @parent: dentry of directory to create new "pipe" in * @name: name of pipe * @private: private data to associate with the pipe, for the caller's use * @pipe: &rpc_pipe containing input parameters * * Data is made available for userspace to read by calls to * rpc_queue_upcall(). The actual reads will result in calls to * @ops->upcall, which will be called with the file pointer, * message, and userspace buffer to copy to. * * Writes can come at any time, and do not necessarily have to be * responses to upcalls. They will result in calls to @msg->downcall. * * The @private argument passed here will be available to all these methods * from the file pointer, via RPC_I(file_inode(file))->private. */ int rpc_mkpipe_dentry(struct dentry *parent, const char *name, void *private, struct rpc_pipe *pipe) { struct inode *dir = d_inode(parent); struct dentry *dentry; struct inode *inode; struct rpc_inode *rpci; umode_t umode = S_IFIFO | 0600; int err; if (pipe->ops->upcall == NULL) umode &= ~0444; if (pipe->ops->downcall == NULL) umode &= ~0222; dentry = simple_start_creating(parent, name); if (IS_ERR(dentry)) { err = PTR_ERR(dentry); goto failed; } inode = rpc_get_inode(dir->i_sb, umode); if (unlikely(!inode)) { simple_done_creating(dentry); err = -ENOMEM; goto failed; } inode->i_ino = iunique(dir->i_sb, 100); inode->i_fop = &rpc_pipe_fops; rpci = RPC_I(inode); rpci->private = private; rpci->pipe = pipe; rpc_inode_setowner(inode, private); pipe->dentry = dentry; // borrowed d_make_persistent(dentry, inode); fsnotify_create(dir, dentry); simple_done_creating(dentry); return 0; failed: pr_warn("%s() failed to create pipe %pd/%s (errno = %d)\n", __func__, parent, name, err); return err; } EXPORT_SYMBOL_GPL(rpc_mkpipe_dentry); /** * rpc_unlink - remove a pipe * @pipe: the pipe to be removed * * After this call, lookups will no longer find the pipe, and any * attempts to read or write using preexisting opens of the pipe will * return -EPIPE. */ void rpc_unlink(struct rpc_pipe *pipe) { if (pipe->dentry) { simple_recursive_removal(pipe->dentry, rpc_close_pipes); pipe->dentry = NULL; } } EXPORT_SYMBOL_GPL(rpc_unlink); /** * rpc_init_pipe_dir_head - initialise a struct rpc_pipe_dir_head * @pdh: pointer to struct rpc_pipe_dir_head */ void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh) { INIT_LIST_HEAD(&pdh->pdh_entries); pdh->pdh_dentry = NULL; } EXPORT_SYMBOL_GPL(rpc_init_pipe_dir_head); /** * rpc_init_pipe_dir_object - initialise a struct rpc_pipe_dir_object * @pdo: pointer to struct rpc_pipe_dir_object * @pdo_ops: pointer to const struct rpc_pipe_dir_object_ops * @pdo_data: pointer to caller-defined data */ void rpc_init_pipe_dir_object(struct rpc_pipe_dir_object *pdo, const struct rpc_pipe_dir_object_ops *pdo_ops, void *pdo_data) { INIT_LIST_HEAD(&pdo->pdo_head); pdo->pdo_ops = pdo_ops; pdo->pdo_data = pdo_data; } EXPORT_SYMBOL_GPL(rpc_init_pipe_dir_object); static int rpc_add_pipe_dir_object_locked(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { int ret = 0; if (pdh->pdh_dentry) ret = pdo->pdo_ops->create(pdh->pdh_dentry, pdo); if (ret == 0) list_add_tail(&pdo->pdo_head, &pdh->pdh_entries); return ret; } static void rpc_remove_pipe_dir_object_locked(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { if (pdh->pdh_dentry) pdo->pdo_ops->destroy(pdh->pdh_dentry, pdo); list_del_init(&pdo->pdo_head); } /** * rpc_add_pipe_dir_object - associate a rpc_pipe_dir_object to a directory * @net: pointer to struct net * @pdh: pointer to struct rpc_pipe_dir_head * @pdo: pointer to struct rpc_pipe_dir_object * */ int rpc_add_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { int ret = 0; if (list_empty(&pdo->pdo_head)) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); ret = rpc_add_pipe_dir_object_locked(net, pdh, pdo); mutex_unlock(&sn->pipefs_sb_lock); } return ret; } EXPORT_SYMBOL_GPL(rpc_add_pipe_dir_object); /** * rpc_remove_pipe_dir_object - remove a rpc_pipe_dir_object from a directory * @net: pointer to struct net * @pdh: pointer to struct rpc_pipe_dir_head * @pdo: pointer to struct rpc_pipe_dir_object * */ void rpc_remove_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, struct rpc_pipe_dir_object *pdo) { if (!list_empty(&pdo->pdo_head)) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); rpc_remove_pipe_dir_object_locked(net, pdh, pdo); mutex_unlock(&sn->pipefs_sb_lock); } } EXPORT_SYMBOL_GPL(rpc_remove_pipe_dir_object); /** * rpc_find_or_alloc_pipe_dir_object * @net: pointer to struct net * @pdh: pointer to struct rpc_pipe_dir_head * @match: match struct rpc_pipe_dir_object to data * @alloc: allocate a new struct rpc_pipe_dir_object * @data: user defined data for match() and alloc() * */ struct rpc_pipe_dir_object * rpc_find_or_alloc_pipe_dir_object(struct net *net, struct rpc_pipe_dir_head *pdh, int (*match)(struct rpc_pipe_dir_object *, void *), struct rpc_pipe_dir_object *(*alloc)(void *), void *data) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe_dir_object *pdo; mutex_lock(&sn->pipefs_sb_lock); list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) { if (!match(pdo, data)) continue; goto out; } pdo = alloc(data); if (!pdo) goto out; rpc_add_pipe_dir_object_locked(net, pdh, pdo); out: mutex_unlock(&sn->pipefs_sb_lock); return pdo; } EXPORT_SYMBOL_GPL(rpc_find_or_alloc_pipe_dir_object); static void rpc_create_pipe_dir_objects(struct rpc_pipe_dir_head *pdh) { struct rpc_pipe_dir_object *pdo; struct dentry *dir = pdh->pdh_dentry; list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) pdo->pdo_ops->create(dir, pdo); } static void rpc_destroy_pipe_dir_objects(struct rpc_pipe_dir_head *pdh) { struct rpc_pipe_dir_object *pdo; struct dentry *dir = pdh->pdh_dentry; list_for_each_entry(pdo, &pdh->pdh_entries, pdo_head) pdo->pdo_ops->destroy(dir, pdo); } /** * rpc_create_client_dir - Create a new rpc_client directory in rpc_pipefs * @dentry: the parent of new directory * @name: the name of new directory * @rpc_client: rpc client to associate with this directory * * This creates a directory at the given @path associated with * @rpc_clnt, which will contain a file named "info" with some basic * information about the client, together with any "pipes" that may * later be created using rpc_mkpipe(). */ int rpc_create_client_dir(struct dentry *dentry, const char *name, struct rpc_clnt *rpc_client) { struct dentry *ret; int err; ret = rpc_new_dir(dentry, name, 0555); if (IS_ERR(ret)) return PTR_ERR(ret); err = rpc_new_file(ret, "info", S_IFREG | 0400, &rpc_info_operations, rpc_client); if (err) { pr_warn("%s failed to populate directory %pd\n", __func__, ret); simple_recursive_removal(ret, NULL); return err; } rpc_client->cl_pipedir_objects.pdh_dentry = ret; rpc_create_pipe_dir_objects(&rpc_client->cl_pipedir_objects); return 0; } /** * rpc_remove_client_dir - Remove a directory created with rpc_create_client_dir() * @rpc_client: rpc_client for the pipe */ int rpc_remove_client_dir(struct rpc_clnt *rpc_client) { struct dentry *dentry = rpc_client->cl_pipedir_objects.pdh_dentry; if (dentry == NULL) return 0; rpc_destroy_pipe_dir_objects(&rpc_client->cl_pipedir_objects); rpc_client->cl_pipedir_objects.pdh_dentry = NULL; simple_recursive_removal(dentry, NULL); return 0; } static const struct rpc_filelist cache_pipefs_files[3] = { [0] = { .name = "channel", .i_fop = &cache_file_operations_pipefs, .mode = S_IFREG | 0600, }, [1] = { .name = "content", .i_fop = &content_file_operations_pipefs, .mode = S_IFREG | 0400, }, [2] = { .name = "flush", .i_fop = &cache_flush_operations_pipefs, .mode = S_IFREG | 0600, }, }; struct dentry *rpc_create_cache_dir(struct dentry *parent, const char *name, umode_t umode, struct cache_detail *cd) { struct dentry *dentry; dentry = rpc_new_dir(parent, name, umode); if (!IS_ERR(dentry)) { int error = rpc_populate(dentry, cache_pipefs_files, 0, 3, cd); if (error) { simple_recursive_removal(dentry, NULL); return ERR_PTR(error); } } return dentry; } void rpc_remove_cache_dir(struct dentry *dentry) { simple_recursive_removal(dentry, NULL); } /* * populate the filesystem */ static const struct super_operations s_ops = { .alloc_inode = rpc_alloc_inode, .free_inode = rpc_free_inode, .statfs = simple_statfs, }; #define RPCAUTH_GSSMAGIC 0x67596969 /* * We have a single directory with 1 node in it. */ enum { RPCAUTH_lockd, RPCAUTH_mount, RPCAUTH_nfs, RPCAUTH_portmap, RPCAUTH_statd, RPCAUTH_nfsd4_cb, RPCAUTH_cache, RPCAUTH_nfsd, RPCAUTH_RootEOF }; static const struct rpc_filelist files[] = { [RPCAUTH_lockd] = { .name = "lockd", .mode = S_IFDIR | 0555, }, [RPCAUTH_mount] = { .name = "mount", .mode = S_IFDIR | 0555, }, [RPCAUTH_nfs] = { .name = "nfs", .mode = S_IFDIR | 0555, }, [RPCAUTH_portmap] = { .name = "portmap", .mode = S_IFDIR | 0555, }, [RPCAUTH_statd] = { .name = "statd", .mode = S_IFDIR | 0555, }, [RPCAUTH_nfsd4_cb] = { .name = "nfsd4_cb", .mode = S_IFDIR | 0555, }, [RPCAUTH_cache] = { .name = "cache", .mode = S_IFDIR | 0555, }, [RPCAUTH_nfsd] = { .name = "nfsd", .mode = S_IFDIR | 0555, }, }; /* * This call can be used only in RPC pipefs mount notification hooks. */ struct dentry *rpc_d_lookup_sb(const struct super_block *sb, const unsigned char *dir_name) { return try_lookup_noperm(&QSTR(dir_name), sb->s_root); } EXPORT_SYMBOL_GPL(rpc_d_lookup_sb); int rpc_pipefs_init_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); sn->gssd_dummy = rpc_mkpipe_data(&gssd_dummy_pipe_ops, 0); if (IS_ERR(sn->gssd_dummy)) return PTR_ERR(sn->gssd_dummy); mutex_init(&sn->pipefs_sb_lock); sn->pipe_version = -1; return 0; } void rpc_pipefs_exit_net(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); rpc_destroy_pipe_data(sn->gssd_dummy); } /* * This call will be used for per network namespace operations calls. * Note: Function will be returned with pipefs_sb_lock taken if superblock was * found. This lock have to be released by rpc_put_sb_net() when all operations * will be completed. */ struct super_block *rpc_get_sb_net(const struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); if (sn->pipefs_sb) return sn->pipefs_sb; mutex_unlock(&sn->pipefs_sb_lock); return NULL; } EXPORT_SYMBOL_GPL(rpc_get_sb_net); void rpc_put_sb_net(const struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); WARN_ON(sn->pipefs_sb == NULL); mutex_unlock(&sn->pipefs_sb_lock); } EXPORT_SYMBOL_GPL(rpc_put_sb_net); static ssize_t dummy_downcall(struct file *filp, const char __user *src, size_t len) { return -EINVAL; } static const struct rpc_pipe_ops gssd_dummy_pipe_ops = { .upcall = rpc_pipe_generic_upcall, .downcall = dummy_downcall, }; /* * Here we present a bogus "info" file to keep rpc.gssd happy. We don't expect * that it will ever use this info to handle an upcall, but rpc.gssd expects * that this file will be there and have a certain format. */ static int rpc_dummy_info_show(struct seq_file *m, void *v) { seq_printf(m, "RPC server: %s\n", utsname()->nodename); seq_printf(m, "service: foo (1) version 0\n"); seq_printf(m, "address: 127.0.0.1\n"); seq_printf(m, "protocol: tcp\n"); seq_printf(m, "port: 0\n"); return 0; } DEFINE_SHOW_ATTRIBUTE(rpc_dummy_info); /** * rpc_gssd_dummy_populate - create a dummy gssd pipe * @root: root of the rpc_pipefs filesystem * @pipe_data: pipe data created when netns is initialized * * Create a dummy set of directories and a pipe that gssd can hold open to * indicate that it is up and running. */ static int rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) { struct dentry *gssd_dentry, *clnt_dentry; int err; gssd_dentry = rpc_new_dir(root, "gssd", 0555); if (IS_ERR(gssd_dentry)) return -ENOENT; clnt_dentry = rpc_new_dir(gssd_dentry, "clntXX", 0555); if (IS_ERR(clnt_dentry)) return -ENOENT; err = rpc_new_file(clnt_dentry, "info", 0400, &rpc_dummy_info_fops, NULL); if (!err) err = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data); return err; } static int rpc_fill_super(struct super_block *sb, struct fs_context *fc) { struct inode *inode; struct dentry *root; struct net *net = sb->s_fs_info; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); int err; sb->s_blocksize = PAGE_SIZE; sb->s_blocksize_bits = PAGE_SHIFT; sb->s_magic = RPCAUTH_GSSMAGIC; sb->s_op = &s_ops; sb->s_d_flags = DCACHE_DONTCACHE; sb->s_time_gran = 1; inode = rpc_get_inode(sb, S_IFDIR | 0555); sb->s_root = root = d_make_root(inode); if (!root) return -ENOMEM; if (rpc_populate(root, files, RPCAUTH_lockd, RPCAUTH_RootEOF, NULL)) return -ENOMEM; err = rpc_gssd_dummy_populate(root, sn->gssd_dummy); if (err) return err; dprintk("RPC: sending pipefs MOUNT notification for net %x%s\n", net->ns.inum, NET_NAME(net)); mutex_lock(&sn->pipefs_sb_lock); sn->pipefs_sb = sb; err = blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_MOUNT, sb); mutex_unlock(&sn->pipefs_sb_lock); return err; } bool gssd_running(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct rpc_pipe *pipe = sn->gssd_dummy; return pipe->nreaders || pipe->nwriters; } EXPORT_SYMBOL_GPL(gssd_running); static int rpc_fs_get_tree(struct fs_context *fc) { return get_tree_keyed(fc, rpc_fill_super, get_net(fc->net_ns)); } static void rpc_fs_free_fc(struct fs_context *fc) { if (fc->s_fs_info) put_net(fc->s_fs_info); } static const struct fs_context_operations rpc_fs_context_ops = { .free = rpc_fs_free_fc, .get_tree = rpc_fs_get_tree, }; static int rpc_init_fs_context(struct fs_context *fc) { put_user_ns(fc->user_ns); fc->user_ns = get_user_ns(fc->net_ns->user_ns); fc->ops = &rpc_fs_context_ops; return 0; } static void rpc_kill_sb(struct super_block *sb) { struct net *net = sb->s_fs_info; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); mutex_lock(&sn->pipefs_sb_lock); if (sn->pipefs_sb != sb) { mutex_unlock(&sn->pipefs_sb_lock); goto out; } sn->pipefs_sb = NULL; dprintk("RPC: sending pipefs UMOUNT notification for net %x%s\n", net->ns.inum, NET_NAME(net)); blocking_notifier_call_chain(&rpc_pipefs_notifier_list, RPC_PIPEFS_UMOUNT, sb); mutex_unlock(&sn->pipefs_sb_lock); out: kill_anon_super(sb); put_net(net); } static struct file_system_type rpc_pipe_fs_type = { .owner = THIS_MODULE, .name = "rpc_pipefs", .init_fs_context = rpc_init_fs_context, .kill_sb = rpc_kill_sb, }; MODULE_ALIAS_FS("rpc_pipefs"); MODULE_ALIAS("rpc_pipefs"); static void init_once(void *foo) { struct rpc_inode *rpci = (struct rpc_inode *) foo; inode_init_once(&rpci->vfs_inode); rpci->private = NULL; rpci->pipe = NULL; init_waitqueue_head(&rpci->waitq); } int register_rpc_pipefs(void) { int err; rpc_inode_cachep = kmem_cache_create("rpc_inode_cache", sizeof(struct rpc_inode), 0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT| SLAB_ACCOUNT), init_once); if (!rpc_inode_cachep) return -ENOMEM; err = rpc_clients_notifier_register(); if (err) goto err_notifier; err = register_filesystem(&rpc_pipe_fs_type); if (err) goto err_register; return 0; err_register: rpc_clients_notifier_unregister(); err_notifier: kmem_cache_destroy(rpc_inode_cachep); return err; } void unregister_rpc_pipefs(void) { rpc_clients_notifier_unregister(); unregister_filesystem(&rpc_pipe_fs_type); kmem_cache_destroy(rpc_inode_cachep); } |
| 5 5 1 2 1 3 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * Linux NET3: IP/IP protocol decoder. * * Authors: * Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95 * * Fixes: * Alan Cox : Merged and made usable non modular (its so tiny its silly as * a module taking up 2 pages). * Alan Cox : Fixed bug with 1.3.18 and IPIP not working (now needs to set skb->h.iph) * to keep ip_forward happy. * Alan Cox : More fixes for 1.3.21, and firewall fix. Maybe this will work soon 8). * Kai Schulte : Fixed #defines for IP_FIREWALL->FIREWALL * David Woodhouse : Perform some basic ICMP handling. * IPIP Routing without decapsulation. * Carlos Picoto : GRE over IP support * Alexey Kuznetsov: Reworked. Really, now it is truncated version of ipv4/ip_gre.c. * I do not want to merge them together. */ /* tunnel.c: an IP tunnel driver The purpose of this driver is to provide an IP tunnel through which you can tunnel network traffic transparently across subnets. This was written by looking at Nick Holloway's dummy driver Thanks for the great code! -Sam Lantinga (slouken@cs.ucdavis.edu) 02/01/95 Minor tweaks: Cleaned up the code a little and added some pre-1.3.0 tweaks. dev->hard_header/hard_header_len changed to use no headers. Comments/bracketing tweaked. Made the tunnels use dev->name not tunnel: when error reporting. Added tx_dropped stat -Alan Cox (alan@lxorguk.ukuu.org.uk) 21 March 95 Reworked: Changed to tunnel to destination gateway in addition to the tunnel's pointopoint address Almost completely rewritten Note: There is currently no firewall or ICMP handling done. -Sam Lantinga (slouken@cs.ucdavis.edu) 02/13/96 */ /* Things I wish I had known when writing the tunnel driver: When the tunnel_xmit() function is called, the skb contains the packet to be sent (plus a great deal of extra info), and dev contains the tunnel device that _we_ are. When we are passed a packet, we are expected to fill in the source address with our source IP address. What is the proper way to allocate, copy and free a buffer? After you allocate it, it is a "0 length" chunk of memory starting at zero. If you want to add headers to the buffer later, you'll have to call "skb_reserve(skb, amount)" with the amount of memory you want reserved. Then, you call "skb_put(skb, amount)" with the amount of space you want in the buffer. skb_put() returns a pointer to the top (#0) of that buffer. skb->len is set to the amount of space you have "allocated" with skb_put(). You can then write up to skb->len bytes to that buffer. If you need more, you can call skb_put() again with the additional amount of space you need. You can find out how much more space you can allocate by calling "skb_tailroom(skb)". Now, to add header space, call "skb_push(skb, header_len)". This creates space at the beginning of the buffer and returns a pointer to this new space. If later you need to strip a header from a buffer, call "skb_pull(skb, header_len)". skb_headroom() will return how much space is left at the top of the buffer (before the main data). Remember, this headroom space must be reserved before the skb_put() function is called. */ /* This version of net/ipv4/ipip.c is cloned of net/ipv4/ip_gre.c For comments look at net/ipv4/ip_gre.c --ANK */ #include <linux/capability.h> #include <linux/module.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/skbuff.h> #include <linux/netdevice.h> #include <linux/in.h> #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/init.h> #include <linux/netfilter_ipv4.h> #include <linux/if_ether.h> #include <net/sock.h> #include <net/ip.h> #include <net/icmp.h> #include <net/ip_tunnels.h> #include <net/inet_ecn.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/dst_metadata.h> static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static unsigned int ipip_net_id __read_mostly; static int ipip_tunnel_init(struct net_device *dev); static struct rtnl_link_ops ipip_link_ops __read_mostly; static int ipip_err(struct sk_buff *skb, u32 info) { /* All the routers (except for Linux) return only * 8 bytes of packet payload. It means, that precise relaying of * ICMP in the real Internet is absolutely infeasible. */ struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); const struct iphdr *iph = (const struct iphdr *)skb->data; IP_TUNNEL_DECLARE_FLAGS(flags) = { }; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; int err = 0; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); t = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->daddr, iph->saddr, 0); if (!t) { err = -ENOENT; goto out; } switch (type) { case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: /* Impossible event. */ goto out; default: /* All others are translated to HOST_UNREACH. * rfc2003 contains "deep thoughts" about NET_UNREACH, * I believe they are just ether pollution. --ANK */ break; } break; case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) goto out; break; case ICMP_REDIRECT: break; default: goto out; } if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { ipv4_update_pmtu(skb, net, info, t->parms.link, iph->protocol); goto out; } if (type == ICMP_REDIRECT) { ipv4_redirect(skb, net, t->parms.link, iph->protocol); goto out; } if (t->parms.iph.daddr == 0) { err = -ENOENT; goto out; } if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) goto out; if (time_before(jiffies, READ_ONCE(t->err_time) + IPTUNNEL_ERR_TIMEO)) WRITE_ONCE(t->err_count, READ_ONCE(t->err_count) + 1); else WRITE_ONCE(t->err_count, 1); WRITE_ONCE(t->err_time, jiffies); out: return err; } static const struct tnl_ptk_info ipip_tpi = { /* no tunnel info required for ipip. */ .proto = htons(ETH_P_IP), }; #if IS_ENABLED(CONFIG_MPLS) static const struct tnl_ptk_info mplsip_tpi = { /* no tunnel info required for mplsip. */ .proto = htons(ETH_P_MPLS_UC), }; #endif static int ipip_tunnel_rcv(struct sk_buff *skb, u8 ipproto) { struct net *net = dev_net(skb->dev); struct ip_tunnel_net *itn = net_generic(net, ipip_net_id); IP_TUNNEL_DECLARE_FLAGS(flags) = { }; struct metadata_dst *tun_dst = NULL; struct ip_tunnel *tunnel; const struct iphdr *iph; __set_bit(IP_TUNNEL_NO_KEY_BIT, flags); iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, flags, iph->saddr, iph->daddr, 0); if (tunnel) { const struct tnl_ptk_info *tpi; if (tunnel->parms.iph.protocol != ipproto && tunnel->parms.iph.protocol != 0) goto drop; if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; #if IS_ENABLED(CONFIG_MPLS) if (ipproto == IPPROTO_MPLS) tpi = &mplsip_tpi; else #endif tpi = &ipip_tpi; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (tunnel->collect_md) { ip_tunnel_flags_zero(flags); tun_dst = ip_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) return 0; ip_tunnel_md_udp_encap(skb, &tun_dst->u.tun_info); } skb_reset_mac_header(skb); return ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); } return -1; drop: kfree_skb(skb); return 0; } static int ipip_rcv(struct sk_buff *skb) { return ipip_tunnel_rcv(skb, IPPROTO_IPIP); } #if IS_ENABLED(CONFIG_MPLS) static int mplsip_rcv(struct sk_buff *skb) { return ipip_tunnel_rcv(skb, IPPROTO_MPLS); } #endif /* * This function assumes it is being called from dev_queue_xmit() * and that skb is filled properly by that function. */ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tiph = &tunnel->parms.iph; u8 ipproto; if (!pskb_inet_may_pull(skb)) goto tx_error; switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; break; #if IS_ENABLED(CONFIG_MPLS) case htons(ETH_P_MPLS_UC): ipproto = IPPROTO_MPLS; break; #endif default: goto tx_error; } if (tiph->protocol != ipproto && tiph->protocol != 0) goto tx_error; if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP4)) goto tx_error; skb_set_inner_ipproto(skb, ipproto); if (tunnel->collect_md) ip_md_tunnel_xmit(skb, dev, ipproto, 0); else ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; tx_error: kfree_skb(skb); DEV_STATS_INC(dev, tx_errors); return NETDEV_TX_OK; } static bool ipip_tunnel_ioctl_verify_protocol(u8 ipproto) { switch (ipproto) { case 0: case IPPROTO_IPIP: #if IS_ENABLED(CONFIG_MPLS) case IPPROTO_MPLS: #endif return true; } return false; } static int ipip_tunnel_ctl(struct net_device *dev, struct ip_tunnel_parm_kern *p, int cmd) { if (cmd == SIOCADDTUNNEL || cmd == SIOCCHGTUNNEL) { if (p->iph.version != 4 || !ipip_tunnel_ioctl_verify_protocol(p->iph.protocol) || p->iph.ihl != 5 || (p->iph.frag_off & htons(~IP_DF))) return -EINVAL; } p->i_key = p->o_key = 0; ip_tunnel_flags_zero(p->i_flags); ip_tunnel_flags_zero(p->o_flags); return ip_tunnel_ctl(dev, p, cmd); } static int ipip_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ip_tunnel *tunnel = netdev_priv(ctx->dev); const struct iphdr *tiph = &tunnel->parms.iph; struct rtable *rt; rt = ip_route_output(dev_net(ctx->dev), tiph->daddr, 0, 0, 0, RT_SCOPE_UNIVERSE); if (IS_ERR(rt)) return PTR_ERR(rt); path->type = DEV_PATH_TUN; path->tun.src_v4.s_addr = tiph->saddr; path->tun.dst_v4.s_addr = tiph->daddr; path->tun.l3_proto = IPPROTO_IPIP; path->dev = ctx->dev; ctx->dev = rt->dst.dev; ip_rt_put(rt); return 0; } static const struct net_device_ops ipip_netdev_ops = { .ndo_init = ipip_tunnel_init, .ndo_uninit = ip_tunnel_uninit, .ndo_start_xmit = ipip_tunnel_xmit, .ndo_siocdevprivate = ip_tunnel_siocdevprivate, .ndo_change_mtu = ip_tunnel_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip_tunnel_get_iflink, .ndo_tunnel_ctl = ipip_tunnel_ctl, .ndo_fill_forward_path = ipip_fill_forward_path, }; #define IPIP_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->type = ARPHRD_TUNNEL; dev->flags = IFF_NOARP; dev->addr_len = 4; dev->lltx = true; netif_keep_dst(dev); dev->features |= IPIP_FEATURES; dev->hw_features |= IPIP_FEATURES; ip_tunnel_setup(dev, ipip_net_id); } static int ipip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); __dev_addr_set(dev, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); tunnel->tun_hlen = 0; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; return ip_tunnel_init(dev); } static int ipip_tunnel_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (proto != IPPROTO_IPIP && proto != IPPROTO_MPLS && proto != 0) return -EINVAL; return 0; } static void ipip_netlink_parms(struct nlattr *data[], struct ip_tunnel_parm_kern *parms, bool *collect_md, __u32 *fwmark) { memset(parms, 0, sizeof(*parms)); parms->iph.version = 4; parms->iph.protocol = IPPROTO_IPIP; parms->iph.ihl = 5; *collect_md = false; if (!data) return; ip_tunnel_netlink_parms(data, parms); if (data[IFLA_IPTUN_COLLECT_METADATA]) *collect_md = true; if (data[IFLA_IPTUN_FWMARK]) *fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } static int ipip_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ip_tunnel_encap ipencap; struct ip_tunnel_parm_kern p; __u32 fwmark = 0; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip_netlink_parms(data, &p, &t->collect_md, &fwmark); return ip_tunnel_newlink(params->link_net ? : dev_net(dev), dev, tb, &p, fwmark); } static int ipip_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); struct ip_tunnel_encap ipencap; struct ip_tunnel_parm_kern p; bool collect_md; __u32 fwmark = t->fwmark; if (!rtnl_dev_link_net_capable(dev, t->net)) return -EPERM; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } ipip_netlink_parms(data, &p, &collect_md, &fwmark); if (collect_md) return -EINVAL; if (((dev->flags & IFF_POINTOPOINT) && !p.iph.daddr) || (!(dev->flags & IFF_POINTOPOINT) && p.iph.daddr)) return -EINVAL; return ip_tunnel_changelink(dev, tb, &p, fwmark); } static size_t ipip_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(4) + /* IFLA_IPTUN_REMOTE */ nla_total_size(4) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_TOS */ nla_total_size(1) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + /* IFLA_IPTUN_PMTUDISC */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ipip_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_parm_kern *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in_addr(skb, IFLA_IPTUN_LOCAL, parm->iph.saddr) || nla_put_in_addr(skb, IFLA_IPTUN_REMOTE, parm->iph.daddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->iph.ttl) || nla_put_u8(skb, IFLA_IPTUN_TOS, parm->iph.tos) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->iph.protocol) || nla_put_u8(skb, IFLA_IPTUN_PMTUDISC, !!(parm->iph.frag_off & htons(IP_DF))) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, tunnel->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; if (tunnel->collect_md) if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } static const struct nla_policy ipip_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .type = NLA_U32 }, [IFLA_IPTUN_REMOTE] = { .type = NLA_U32 }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_TOS] = { .type = NLA_U8 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, [IFLA_IPTUN_PMTUDISC] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops ipip_link_ops __read_mostly = { .kind = "ipip", .maxtype = IFLA_IPTUN_MAX, .policy = ipip_policy, .priv_size = sizeof(struct ip_tunnel), .setup = ipip_tunnel_setup, .validate = ipip_tunnel_validate, .newlink = ipip_newlink, .changelink = ipip_changelink, .dellink = ip_tunnel_dellink, .get_size = ipip_get_size, .fill_info = ipip_fill_info, .get_link_net = ip_tunnel_get_link_net, }; static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip_err, .priority = 1, }; #if IS_ENABLED(CONFIG_MPLS) static struct xfrm_tunnel mplsip_handler __read_mostly = { .handler = mplsip_rcv, .err_handler = ipip_err, .priority = 1, }; #endif static int __net_init ipip_init_net(struct net *net) { return ip_tunnel_init_net(net, ipip_net_id, &ipip_link_ops, "tunl0"); } static void __net_exit ipip_exit_rtnl(struct net *net, struct list_head *dev_to_kill) { ip_tunnel_delete_net(net, ipip_net_id, &ipip_link_ops, dev_to_kill); } static struct pernet_operations ipip_net_ops = { .init = ipip_init_net, .exit_rtnl = ipip_exit_rtnl, .id = &ipip_net_id, .size = sizeof(struct ip_tunnel_net), }; static int __init ipip_init(void) { int err; pr_info("ipip: IPv4 and MPLS over IPv4 tunneling driver\n"); err = register_pernet_device(&ipip_net_ops); if (err < 0) return err; err = xfrm4_tunnel_register(&ipip_handler, AF_INET); if (err < 0) { pr_info("%s: can't register tunnel\n", __func__); goto xfrm_tunnel_ipip_failed; } #if IS_ENABLED(CONFIG_MPLS) err = xfrm4_tunnel_register(&mplsip_handler, AF_MPLS); if (err < 0) { pr_info("%s: can't register tunnel\n", __func__); goto xfrm_tunnel_mplsip_failed; } #endif err = rtnl_link_register(&ipip_link_ops); if (err < 0) goto rtnl_link_failed; out: return err; rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mplsip_failed: #endif xfrm4_tunnel_deregister(&ipip_handler, AF_INET); xfrm_tunnel_ipip_failed: unregister_pernet_device(&ipip_net_ops); goto out; } static void __exit ipip_fini(void) { rtnl_link_unregister(&ipip_link_ops); if (xfrm4_tunnel_deregister(&ipip_handler, AF_INET)) pr_info("%s: can't deregister tunnel\n", __func__); #if IS_ENABLED(CONFIG_MPLS) if (xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS)) pr_info("%s: can't deregister tunnel\n", __func__); #endif unregister_pernet_device(&ipip_net_ops); } module_init(ipip_init); module_exit(ipip_fini); MODULE_DESCRIPTION("IP/IP protocol decoder library"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ipip"); MODULE_ALIAS_NETDEV("tunl0"); |
| 197 197 138 19 199 15 15 14 15 302 302 3 134 197 212 212 1 198 1 1 201 199 27 10 26 5 306 2 113 112 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* memcontrol.h - Memory Controller * * Copyright IBM Corporation, 2007 * Author Balbir Singh <balbir@linux.vnet.ibm.com> * * Copyright 2007 OpenVZ SWsoft Inc * Author: Pavel Emelianov <xemul@openvz.org> */ #ifndef _LINUX_MEMCONTROL_H #define _LINUX_MEMCONTROL_H #include <linux/cgroup.h> #include <linux/vm_event_item.h> #include <linux/hardirq.h> #include <linux/jump_label.h> #include <linux/kernel.h> #include <linux/page_counter.h> #include <linux/vmpressure.h> #include <linux/eventfd.h> #include <linux/mm.h> #include <linux/vmstat.h> #include <linux/writeback.h> #include <linux/page-flags.h> #include <linux/shrinker.h> struct mem_cgroup; struct obj_cgroup; struct page; struct mm_struct; struct kmem_cache; struct swap_cluster_info; /* Cgroup-specific page state, on top of universal node page state */ enum memcg_stat_item { MEMCG_SWAP = NR_VM_NODE_STAT_ITEMS, MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_KMEM, MEMCG_ZSWAP_B, MEMCG_ZSWAPPED, MEMCG_ZSWAP_INCOMP, MEMCG_NR_STAT, }; enum memcg_memory_event { MEMCG_LOW, MEMCG_HIGH, MEMCG_MAX, MEMCG_OOM, MEMCG_OOM_KILL, MEMCG_OOM_GROUP_KILL, MEMCG_SWAP_HIGH, MEMCG_SWAP_MAX, MEMCG_SWAP_FAIL, MEMCG_SOCK_THROTTLED, MEMCG_NR_MEMORY_EVENTS, }; struct mem_cgroup_reclaim_cookie { pg_data_t *pgdat; int generation; }; #ifdef CONFIG_MEMCG #define MEM_CGROUP_ID_SHIFT 16 struct mem_cgroup_private_id { int id; refcount_t ref; }; struct memcg_vmstats_percpu; struct memcg1_events_percpu; struct memcg_vmstats; struct lruvec_stats_percpu; struct lruvec_stats; struct mem_cgroup_reclaim_iter { struct mem_cgroup *position; /* scan generation, increased every round-trip */ atomic_t generation; }; /* * per-node information in memory controller. */ struct mem_cgroup_per_node { /* Keep the read-only fields at the start */ struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ struct lruvec_stats_percpu __percpu *lruvec_stats_percpu; struct lruvec_stats *lruvec_stats; struct shrinker_info __rcu *shrinker_info; #ifdef CONFIG_MEMCG_V1 /* * Memcg-v1 only stuff in middle as buffer between read mostly fields * and update often fields to avoid false sharing. If v1 stuff is * not present, an explicit padding is needed. */ struct rb_node tree_node; /* RB tree node */ unsigned long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; #else CACHELINE_PADDING(_pad1_); #endif /* Fields which get updated often at the end. */ struct lruvec lruvec; CACHELINE_PADDING(_pad2_); unsigned long lru_zone_size[MAX_NR_ZONES][NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter iter; /* * objcg is wiped out as a part of the objcg repaprenting process. * orig_objcg preserves a pointer (and a reference) to the original * objcg until the end of live of memcg. */ struct obj_cgroup __rcu *objcg; struct obj_cgroup *orig_objcg; /* list of inherited objcgs, protected by objcg_lock */ struct list_head objcg_list; #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC /* slab stats for nmi context */ atomic_t slab_reclaimable; atomic_t slab_unreclaimable; #endif }; struct mem_cgroup_threshold { struct eventfd_ctx *eventfd; unsigned long threshold; }; /* For threshold */ struct mem_cgroup_threshold_ary { /* An array index points to threshold just below or equal to usage. */ int current_threshold; /* Size of entries[] */ unsigned int size; /* Array of thresholds */ struct mem_cgroup_threshold entries[] __counted_by(size); }; struct mem_cgroup_thresholds { /* Primary thresholds array */ struct mem_cgroup_threshold_ary *primary; /* * Spare threshold array. * This is needed to make mem_cgroup_unregister_event() "never fail". * It must be able to store at least primary->size - 1 entries. */ struct mem_cgroup_threshold_ary *spare; }; /* * Remember four most recent foreign writebacks with dirty pages in this * cgroup. Inode sharing is expected to be uncommon and, even if we miss * one in a given round, we're likely to catch it later if it keeps * foreign-dirtying, so a fairly low count should be enough. * * See mem_cgroup_track_foreign_dirty_slowpath() for details. */ #define MEMCG_CGWB_FRN_CNT 4 struct memcg_cgwb_frn { u64 bdi_id; /* bdi->id of the foreign inode */ int memcg_id; /* memcg->css.id of foreign inode */ u64 at; /* jiffies_64 at the time of dirtying */ struct wb_completion done; /* tracks in-flight foreign writebacks */ }; /* * Bucket for arbitrarily byte-sized objects charged to a memory * cgroup. The bucket can be reparented in one piece when the cgroup * is destroyed, without having to round up the individual references * of all live memory objects in the wild. */ struct obj_cgroup { struct percpu_ref refcnt; struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; bool is_root; }; /* * The memory controller data structure. The memory controller controls both * page cache and RSS per cgroup. We would eventually like to provide * statistics based on the statistics developed by Rik Van Riel for clock-pro, * to help the administrator determine what knobs to tune. */ struct mem_cgroup { struct cgroup_subsys_state css; /* Private memcg ID. Used to ID objects that outlive the cgroup */ struct mem_cgroup_private_id id; /* Accounted resources */ struct page_counter memory; /* Both v1 & v2 */ union { struct page_counter swap; /* v2 only */ struct page_counter memsw; /* v1 only */ }; /* registered local peak watchers */ struct list_head memory_peaks; struct list_head swap_peaks; spinlock_t peaks_lock; /* Range enforcement for interrupt charges */ struct work_struct high_work; #ifdef CONFIG_ZSWAP unsigned long zswap_max; /* * Prevent pages from this memcg from being written back from zswap to * swap, and from being swapped out on zswap store failures. */ bool zswap_writeback; #endif /* vmpressure notifications */ struct vmpressure vmpressure; /* * Should the OOM killer kill all belonging tasks, had it kill one? */ bool oom_group; int swappiness; /* memory.events and memory.events.local */ struct cgroup_file events_file; struct cgroup_file events_local_file; /* handle for "memory.swap.events" */ struct cgroup_file swap_events_file; /* memory.stat */ struct memcg_vmstats *vmstats; /* memory.events */ atomic_long_t memory_events[MEMCG_NR_MEMORY_EVENTS]; atomic_long_t memory_events_local[MEMCG_NR_MEMORY_EVENTS]; #ifdef CONFIG_MEMCG_NMI_SAFETY_REQUIRES_ATOMIC /* MEMCG_KMEM for nmi context */ atomic_t kmem_stat; #endif /* * Hint of reclaim pressure for socket memroy management. Note * that this indicator should NOT be used in legacy cgroup mode * where socket memory is accounted/charged separately. */ u64 socket_pressure; #if BITS_PER_LONG < 64 seqlock_t socket_pressure_seqlock; #endif int kmemcg_id; struct memcg_vmstats_percpu __percpu *vmstats_percpu; #ifdef CONFIG_CGROUP_WRITEBACK struct list_head cgwb_list; struct wb_domain cgwb_domain; struct memcg_cgwb_frn cgwb_frn[MEMCG_CGWB_FRN_CNT]; #endif #ifdef CONFIG_LRU_GEN_WALKS_MMU /* per-memcg mm_struct list */ struct lru_gen_mm_list mm_list; #endif #ifdef CONFIG_MEMCG_V1 /* Legacy consumer-oriented counters */ struct page_counter kmem; /* v1 only */ struct page_counter tcpmem; /* v1 only */ struct memcg1_events_percpu __percpu *events_percpu; unsigned long soft_limit; /* protected by memcg_oom_lock */ bool oom_lock; int under_oom; /* OOM-Killer disable */ int oom_kill_disable; /* protect arrays of thresholds */ struct mutex thresholds_lock; /* thresholds for memory usage. RCU-protected */ struct mem_cgroup_thresholds thresholds; /* thresholds for mem+swap usage. RCU-protected */ struct mem_cgroup_thresholds memsw_thresholds; /* For oom notifier event fd */ struct list_head oom_notify; /* Legacy tcp memory accounting */ bool tcpmem_active; int tcpmem_pressure; /* List of events which userspace want to receive */ struct list_head event_list; spinlock_t event_list_lock; #endif /* CONFIG_MEMCG_V1 */ struct mem_cgroup_per_node *nodeinfo[]; }; /* * size of first charge trial. * TODO: maybe necessary to use big numbers in big irons or dynamic based of the * workload. */ #define MEMCG_CHARGE_BATCH 64U extern struct mem_cgroup *root_mem_cgroup; enum page_memcg_data_flags { /* page->memcg_data is a pointer to an slabobj_ext vector */ MEMCG_DATA_OBJEXTS = (1UL << 0), /* page has been accounted as a non-slab kernel page */ MEMCG_DATA_KMEM = (1UL << 1), /* the next bit after the last actual flag */ __NR_MEMCG_DATA_FLAGS = (1UL << 2), }; #define __OBJEXTS_ALLOC_FAIL MEMCG_DATA_OBJEXTS #define __FIRST_OBJEXT_FLAG __NR_MEMCG_DATA_FLAGS #else /* CONFIG_MEMCG */ #define __OBJEXTS_ALLOC_FAIL (1UL << 0) #define __FIRST_OBJEXT_FLAG (1UL << 0) #endif /* CONFIG_MEMCG */ enum objext_flags { /* * Use bit 0 with zero other bits to signal that slabobj_ext vector * failed to allocate. The same bit 0 with valid upper bits means * MEMCG_DATA_OBJEXTS. */ OBJEXTS_ALLOC_FAIL = __OBJEXTS_ALLOC_FAIL, __OBJEXTS_FLAG_UNUSED = __FIRST_OBJEXT_FLAG, /* the next bit after the last actual flag */ __NR_OBJEXTS_FLAGS = (__FIRST_OBJEXT_FLAG << 1), }; #define OBJEXTS_FLAGS_MASK (__NR_OBJEXTS_FLAGS - 1) #ifdef CONFIG_MEMCG /* * After the initialization objcg->memcg is always pointing at * a valid memcg, but can be atomically swapped to the parent memcg. * * The caller must ensure that the returned memcg won't be released. */ static inline struct mem_cgroup *obj_cgroup_memcg(struct obj_cgroup *objcg) { lockdep_assert_once(rcu_read_lock_held() || lockdep_is_held(&cgroup_mutex)); return READ_ONCE(objcg->memcg); } /* * folio_objcg - get the object cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the object cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper object cgroup pointer. */ static inline struct obj_cgroup *folio_objcg(struct folio *folio) { unsigned long memcg_data = folio->memcg_data; VM_BUG_ON_FOLIO(folio_test_slab(folio), folio); VM_BUG_ON_FOLIO(memcg_data & MEMCG_DATA_OBJEXTS, folio); return (struct obj_cgroup *)(memcg_data & ~OBJEXTS_FLAGS_MASK); } /* * folio_memcg - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function assumes that the folio is known to have a * proper memory cgroup pointer. It's not safe to call this function * against some type of folios, e.g. slab folios or ex-slab folios. * * For a folio any of the following ensures folio and objcg binding stability: * * - the folio lock * - LRU isolation * - exclusive reference * * Based on the stable binding of folio and objcg, for a folio any of the * following ensures folio and memcg binding stability: * * - cgroup_mutex * - the lruvec lock * * If the caller only want to ensure that the page counters of memcg are * updated correctly, ensure that the binding stability of folio and objcg * is sufficient. * * Note: The caller should hold an rcu read lock or cgroup_mutex to protect * memcg associated with a folio from being released. */ static inline struct mem_cgroup *folio_memcg(struct folio *folio) { struct obj_cgroup *objcg = folio_objcg(folio); return objcg ? obj_cgroup_memcg(objcg) : NULL; } /* * folio_memcg_charged - If a folio is charged to a memory cgroup. * @folio: Pointer to the folio. * * Returns true if folio is charged to a memory cgroup, otherwise returns false. */ static inline bool folio_memcg_charged(struct folio *folio) { return folio->memcg_data != 0; } /* * folio_memcg_check - Get the memory cgroup associated with a folio. * @folio: Pointer to the folio. * * Returns a pointer to the memory cgroup associated with the folio, * or NULL. This function unlike folio_memcg() can take any folio * as an argument. It has to be used in cases when it's not known if a folio * has an associated memory cgroup pointer or an object cgroups vector or * an object cgroup. * * The page and objcg or memcg binding rules can refer to folio_memcg(). * * A caller should hold an rcu read lock to protect memcg associated with a * page from being released. */ static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { /* * Because folio->memcg_data might be changed asynchronously * for slabs, READ_ONCE() should be used here. */ unsigned long memcg_data = READ_ONCE(folio->memcg_data); struct obj_cgroup *objcg; if (memcg_data & MEMCG_DATA_OBJEXTS) return NULL; objcg = (void *)(memcg_data & ~OBJEXTS_FLAGS_MASK); return objcg ? obj_cgroup_memcg(objcg) : NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) { if (PageTail(page)) return NULL; return folio_memcg_check((struct folio *)page); } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { struct mem_cgroup *memcg; rcu_read_lock(); retry: memcg = obj_cgroup_memcg(objcg); if (unlikely(!css_tryget(&memcg->css))) goto retry; rcu_read_unlock(); return memcg; } /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. * @folio: Pointer to the folio. * * Checks if the folio has MemcgKmem flag set. The caller must ensure * that the folio has an associated memory cgroup. It's not safe to call * this function against some types of folios, e.g. slab folios. */ static inline bool folio_memcg_kmem(struct folio *folio) { VM_BUG_ON_PGFLAGS(PageTail(&folio->page), &folio->page); VM_BUG_ON_FOLIO(folio->memcg_data & MEMCG_DATA_OBJEXTS, folio); return folio->memcg_data & MEMCG_DATA_KMEM; } static inline bool PageMemcgKmem(struct page *page) { return folio_memcg_kmem(page_folio(page)); } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); } /** * mem_cgroup_shrink_is_root - is this a global or root-memcg shrink invocation? * @sc: shrink_control describing the current shrinker call * * Returns true when @sc represents a global reclaim shrink (sc->memcg == NULL) * or a root-memcg shrink, i.e. not a per-memcg iteration of * shrink_slab_memcg(). Filesystems whose ->nr_cached_objects()/ * ->free_cached_objects() implementations operate on filesystem-global state * and do not honour sc->memcg can use this to early-return 0 in per-memcg * contexts. */ static inline bool mem_cgroup_shrink_is_root(struct shrink_control *sc) { return !sc->memcg || mem_cgroup_is_root(sc->memcg); } static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) { return objcg->is_root; } static inline bool mem_cgroup_disabled(void) { return !cgroup_subsys_enabled(memory_cgrp_subsys); } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low, unsigned long *usage) { *min = *low = *usage = 0; if (mem_cgroup_disabled()) return; *usage = page_counter_read(&memcg->memory); /* * There is no reclaim protection applied to a targeted reclaim. * We are special casing this specific case here because * mem_cgroup_calculate_protection is not robust enough to keep * the protection invariant for calculated effective values for * parallel reclaimers with different reclaim target. This is * especially a problem for tail memcgs (as they have pages on LRU) * which would want to have effective values 0 for targeted reclaim * but a different value for external reclaim. * * Example * Let's have global and A's reclaim in parallel: * | * A (low=2G, usage = 3G, max = 3G, children_low_usage = 1.5G) * |\ * | C (low = 1G, usage = 2.5G) * B (low = 1G, usage = 0.5G) * * For the global reclaim * A.elow = A.low * B.elow = min(B.usage, B.low) because children_low_usage <= A.elow * C.elow = min(C.usage, C.low) * * With the effective values resetting we have A reclaim * A.elow = 0 * B.elow = B.low * C.elow = C.low * * If the global reclaim races with A's reclaim then * B.elow = C.elow = 0 because children_low_usage > A.elow) * is possible and reclaiming B would be violating the protection. * */ if (root == memcg) return; *min = READ_ONCE(memcg->memory.emin); *low = READ_ONCE(memcg->memory.elow); } void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg); static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { /* * The root memcg doesn't account charges, and doesn't support * protection. The target memcg's protection is ignored, see * mem_cgroup_calculate_protection() and mem_cgroup_protection() */ return mem_cgroup_disabled() || mem_cgroup_is_root(memcg) || memcg == target; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.elow) >= page_counter_read(&memcg->memory); } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { if (mem_cgroup_unprotected(target, memcg)) return false; return READ_ONCE(memcg->memory.emin) >= page_counter_read(&memcg->memory); } int __mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp); /** * mem_cgroup_charge - Charge a newly allocated folio to a cgroup. * @folio: Folio to charge. * @mm: mm context of the allocating task. * @gfp: Reclaim mode. * * Try to charge @folio to the memcg that @mm belongs to, reclaiming * pages according to @gfp if necessary. If @mm is NULL, try to * charge to the active memcg. * * Do not use this for folios allocated for swapin. * * Return: 0 on success. Otherwise, an error code is returned. */ static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { if (mem_cgroup_disabled()) return 0; return __mem_cgroup_charge(folio, mm, gfp); } int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp); int mem_cgroup_swapin_charge_folio(struct folio *folio, unsigned short id, struct mm_struct *mm, gfp_t gfp); void __mem_cgroup_uncharge(struct folio *folio); /** * mem_cgroup_uncharge - Uncharge a folio. * @folio: Folio to uncharge. * * Uncharge a folio previously charged with mem_cgroup_charge(). */ static inline void mem_cgroup_uncharge(struct folio *folio) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge(folio); } void __mem_cgroup_uncharge_folios(struct folio_batch *folios); static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { if (mem_cgroup_disabled()) return; __mem_cgroup_uncharge_folios(folios); } void mem_cgroup_replace_folio(struct folio *old, struct folio *new); void mem_cgroup_migrate(struct folio *old, struct folio *new); /** * mem_cgroup_lruvec - get the lru list vector for a memcg & node * @memcg: memcg of the wanted lruvec * @pgdat: pglist_data * * Returns the lru list vector holding pages for a given @memcg & * @pgdat combination. This can be the node lruvec, if the memory * controller is disabled. */ static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { struct mem_cgroup_per_node *mz; struct lruvec *lruvec; if (mem_cgroup_disabled()) { lruvec = &pgdat->__lruvec; goto out; } if (!memcg) memcg = root_mem_cgroup; mz = memcg->nodeinfo[pgdat->node_id]; lruvec = &mz->lruvec; out: /* * Since a node can be onlined after the mem_cgroup was created, * we have to be prepared to initialize lruvec->pgdat here; * and if offlined then reonlined, we need to reinitialize it. */ if (unlikely(lruvec->pgdat != pgdat)) lruvec->pgdat = pgdat; return lruvec; } /** * folio_lruvec - return lruvec for isolating/putting an LRU folio * @folio: Pointer to the folio. * * Call with rcu_read_lock() held to ensure the lifetime of the returned lruvec. * Note that this alone will NOT guarantee the stability of the folio->lruvec * association; the folio can be reparented to an ancestor if this races with * cgroup deletion. * * Use folio_lruvec_lock() to ensure both lifetime and stability of the binding. * Once a lruvec is locked, folio_lruvec() can be called on other folios, and * their binding is stable if the returned lruvec matches the one the caller has * locked. Useful for lock batching. */ static inline struct lruvec *folio_lruvec(struct folio *folio) { struct mem_cgroup *memcg = folio_memcg(folio); VM_WARN_ON_ONCE_FOLIO(!memcg && !mem_cgroup_disabled(), folio); return mem_cgroup_lruvec(memcg, folio_pgdat(folio)); } struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p); struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm); struct mem_cgroup *get_mem_cgroup_from_current(void); struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio); struct lruvec *folio_lruvec_lock(struct folio *folio); struct lruvec *folio_lruvec_lock_irq(struct folio *folio); struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flags); static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css){ return css ? container_of(css, struct mem_cgroup, css) : NULL; } static inline bool obj_cgroup_tryget(struct obj_cgroup *objcg) { if (obj_cgroup_is_root(objcg)) return true; return percpu_ref_tryget(&objcg->refcnt); } static inline void obj_cgroup_get_many(struct obj_cgroup *objcg, unsigned long nr) { if (!obj_cgroup_is_root(objcg)) percpu_ref_get_many(&objcg->refcnt, nr); } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { obj_cgroup_get_many(objcg, 1); } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { if (objcg && !obj_cgroup_is_root(objcg)) percpu_ref_put(&objcg->refcnt); } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return !memcg || css_tryget(&memcg->css); } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return !memcg || css_tryget_online(&memcg->css); } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { if (memcg) css_put(&memcg->css); } #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *, struct mem_cgroup *, struct mem_cgroup_reclaim_cookie *); void mem_cgroup_iter_break(struct mem_cgroup *, struct mem_cgroup *); void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*)(struct task_struct *, void *), void *arg); static inline unsigned short mem_cgroup_private_id(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return 0; return memcg->id.id; } struct mem_cgroup *mem_cgroup_from_private_id(unsigned short id); static inline u64 mem_cgroup_id(struct mem_cgroup *memcg) { return memcg ? cgroup_id(memcg->css.cgroup) : 0; } struct mem_cgroup *mem_cgroup_get_from_id(u64 id); static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return mem_cgroup_from_css(seq_css(m)); } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { struct mem_cgroup_per_node *mz; if (mem_cgroup_disabled()) return NULL; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return mz->memcg; } /** * parent_mem_cgroup - find the accounting parent of a memcg * @memcg: memcg whose parent to find * * Returns the parent memcg, or NULL if this is the root. */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, struct mem_cgroup *root) { if (root == memcg) return true; return cgroup_is_descendant(memcg->css.cgroup, root->css.cgroup); } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { struct mem_cgroup *task_memcg; bool match = false; rcu_read_lock(); task_memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (task_memcg) match = mem_cgroup_is_descendant(task_memcg, memcg); rcu_read_unlock(); return match; } struct cgroup_subsys_state *get_mem_cgroup_css_from_folio(struct folio *folio); ino_t page_cgroup_ino(struct page *page); static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { if (mem_cgroup_disabled()) return true; return css_is_online(&memcg->css); } void mem_cgroup_update_lru_size(struct lruvec *lruvec, enum lru_list lru, int zid, long nr_pages); static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { struct mem_cgroup_per_node *mz; mz = container_of(lruvec, struct mem_cgroup_per_node, lruvec); return READ_ONCE(mz->lru_zone_size[zone_idx][lru]); } void __mem_cgroup_handle_over_high(gfp_t gfp_mask); static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { if (unlikely(current->memcg_nr_pages_over_high)) __mem_cgroup_handle_over_high(gfp_mask); } unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg); void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p); void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg); struct mem_cgroup *mem_cgroup_get_oom_group(struct task_struct *victim, struct mem_cgroup *oom_domain); void mem_cgroup_print_oom_group(struct mem_cgroup *memcg); /* idx can be of type enum memcg_stat_item or node_stat_item */ void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int val); static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = folio_memcg(page_folio(page)); if (memcg) mod_memcg_state(memcg, idx, val); rcu_read_unlock(); } unsigned long memcg_events(struct mem_cgroup *memcg, int event); unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx); unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item); bool memcg_stat_item_valid(int idx); bool memcg_vm_event_item_valid(enum vm_event_item idx); unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx); unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx); void mem_cgroup_flush_stats(struct mem_cgroup *memcg); void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg); void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val); void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count); static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { struct mem_cgroup *memcg; if (!folio_memcg_charged(folio)) return; rcu_read_lock(); memcg = folio_memcg(folio); count_memcg_events(memcg, idx, nr); rcu_read_unlock(); } static inline void count_memcg_events_mm(struct mm_struct *mm, enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) count_memcg_events(memcg, idx, count); rcu_read_unlock(); } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { count_memcg_events_mm(mm, idx, 1); } void __memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event, bool allow_spinning); static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { __memcg_memory_event(memcg, event, true); } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (likely(memcg)) memcg_memory_event(memcg, event); rcu_read_unlock(); } void split_page_memcg(struct page *first, unsigned order); void folio_split_memcg_refs(struct folio *folio, unsigned old_order, unsigned new_order); static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { struct mem_cgroup *memcg; u64 id; if (mem_cgroup_disabled()) return 0; rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(mm->owner)); if (!memcg) memcg = root_mem_cgroup; id = cgroup_id(memcg->css.cgroup); rcu_read_unlock(); return id; } void mem_cgroup_flush_workqueue(void); extern int mem_cgroup_init(void); #else /* CONFIG_MEMCG */ #define MEM_CGROUP_ID_SHIFT 0 #define root_mem_cgroup (NULL) static inline struct mem_cgroup *folio_memcg(struct folio *folio) { return NULL; } static inline bool folio_memcg_charged(struct folio *folio) { return false; } static inline struct mem_cgroup *folio_memcg_check(struct folio *folio) { return NULL; } static inline struct mem_cgroup *page_memcg_check(struct page *page) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) { return NULL; } static inline bool folio_memcg_kmem(struct folio *folio) { return false; } static inline bool PageMemcgKmem(struct page *page) { return false; } static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_shrink_is_root(struct shrink_control *sc) { return true; } static inline bool obj_cgroup_is_root(const struct obj_cgroup *objcg) { return true; } static inline bool mem_cgroup_disabled(void) { return true; } static inline void memcg_memory_event(struct mem_cgroup *memcg, enum memcg_memory_event event) { } static inline void memcg_memory_event_mm(struct mm_struct *mm, enum memcg_memory_event event) { } static inline void mem_cgroup_protection(struct mem_cgroup *root, struct mem_cgroup *memcg, unsigned long *min, unsigned long *low, unsigned long *usage) { *min = *low = *usage = 0; } static inline void mem_cgroup_calculate_protection(struct mem_cgroup *root, struct mem_cgroup *memcg) { } static inline bool mem_cgroup_unprotected(struct mem_cgroup *target, struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_below_low(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline bool mem_cgroup_below_min(struct mem_cgroup *target, struct mem_cgroup *memcg) { return false; } static inline int mem_cgroup_charge(struct folio *folio, struct mm_struct *mm, gfp_t gfp) { return 0; } static inline int mem_cgroup_charge_hugetlb(struct folio* folio, gfp_t gfp) { return 0; } static inline int mem_cgroup_swapin_charge_folio(struct folio *folio, unsigned short id, struct mm_struct *mm, gfp_t gfp) { return 0; } static inline void mem_cgroup_uncharge(struct folio *folio) { } static inline void mem_cgroup_uncharge_folios(struct folio_batch *folios) { } static inline void mem_cgroup_replace_folio(struct folio *old, struct folio *new) { } static inline void mem_cgroup_migrate(struct folio *old, struct folio *new) { } static inline struct lruvec *mem_cgroup_lruvec(struct mem_cgroup *memcg, struct pglist_data *pgdat) { return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); return &pgdat->__lruvec; } static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { return NULL; } static inline bool mm_match_cgroup(struct mm_struct *mm, struct mem_cgroup *memcg) { return true; } static inline struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_current(void) { return NULL; } static inline struct mem_cgroup *get_mem_cgroup_from_folio(struct folio *folio) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *css) { return NULL; } static inline void obj_cgroup_get(struct obj_cgroup *objcg) { } static inline void obj_cgroup_put(struct obj_cgroup *objcg) { } static inline bool mem_cgroup_tryget(struct mem_cgroup *memcg) { return true; } static inline bool mem_cgroup_tryget_online(struct mem_cgroup *memcg) { return true; } static inline void mem_cgroup_put(struct mem_cgroup *memcg) { } static inline struct lruvec *folio_lruvec_lock(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); rcu_read_lock(); spin_lock(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irq(struct folio *folio) { struct pglist_data *pgdat = folio_pgdat(folio); rcu_read_lock(); spin_lock_irq(&pgdat->__lruvec.lru_lock); return &pgdat->__lruvec; } static inline struct lruvec *folio_lruvec_lock_irqsave(struct folio *folio, unsigned long *flagsp) { struct pglist_data *pgdat = folio_pgdat(folio); rcu_read_lock(); spin_lock_irqsave(&pgdat->__lruvec.lru_lock, *flagsp); return &pgdat->__lruvec; } static inline struct mem_cgroup * mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { return NULL; } static inline void mem_cgroup_iter_break(struct mem_cgroup *root, struct mem_cgroup *prev) { } static inline void mem_cgroup_scan_tasks(struct mem_cgroup *memcg, int (*fn)(struct task_struct *, void *), void *arg) { } static inline unsigned short mem_cgroup_private_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_from_private_id(unsigned short id) { WARN_ON_ONCE(id); /* XXX: This should always return root_mem_cgroup */ return NULL; } static inline u64 mem_cgroup_id(struct mem_cgroup *memcg) { return 0; } static inline struct mem_cgroup *mem_cgroup_get_from_id(u64 id) { return NULL; } static inline struct mem_cgroup *mem_cgroup_from_seq(struct seq_file *m) { return NULL; } static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) { return NULL; } static inline bool mem_cgroup_online(struct mem_cgroup *memcg) { return true; } static inline unsigned long mem_cgroup_get_zone_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { return 0; } static inline unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) { return 0; } static inline void mem_cgroup_print_oom_context(struct mem_cgroup *memcg, struct task_struct *p) { } static inline void mem_cgroup_print_oom_meminfo(struct mem_cgroup *memcg) { } static inline void mem_cgroup_handle_over_high(gfp_t gfp_mask) { } static inline struct mem_cgroup *mem_cgroup_get_oom_group( struct task_struct *victim, struct mem_cgroup *oom_domain) { return NULL; } static inline void mem_cgroup_print_oom_group(struct mem_cgroup *memcg) { } static inline void mod_memcg_state(struct mem_cgroup *memcg, enum memcg_stat_item idx, int nr) { } static inline void mod_memcg_page_state(struct page *page, enum memcg_stat_item idx, int val) { } static inline unsigned long memcg_page_state(struct mem_cgroup *memcg, int idx) { return 0; } static inline unsigned long memcg_page_state_output(struct mem_cgroup *memcg, int item) { return 0; } static inline bool memcg_stat_item_valid(int idx) { return false; } static inline bool memcg_vm_event_item_valid(enum vm_event_item idx) { return false; } static inline unsigned long lruvec_page_state(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline unsigned long lruvec_page_state_local(struct lruvec *lruvec, enum node_stat_item idx) { return node_page_state(lruvec_pgdat(lruvec), idx); } static inline void mem_cgroup_flush_stats(struct mem_cgroup *memcg) { } static inline void mem_cgroup_flush_stats_ratelimited(struct mem_cgroup *memcg) { } static inline void mod_lruvec_kmem_state(void *p, enum node_stat_item idx, int val) { struct page *page = virt_to_head_page(p); mod_node_page_state(page_pgdat(page), idx, val); } static inline void count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_folio_events(struct folio *folio, enum vm_event_item idx, unsigned long nr) { } static inline void count_memcg_events_mm(struct mm_struct *mm, enum vm_event_item idx, unsigned long count) { } static inline void count_memcg_event_mm(struct mm_struct *mm, enum vm_event_item idx) { } static inline void split_page_memcg(struct page *first, unsigned order) { } static inline void folio_split_memcg_refs(struct folio *folio, unsigned old_order, unsigned new_order) { } static inline u64 cgroup_id_from_mm(struct mm_struct *mm) { return 0; } static inline void mem_cgroup_flush_workqueue(void) { } static inline int mem_cgroup_init(void) { return 0; } #endif /* CONFIG_MEMCG */ /* * Extended information for slab objects stored as an array in page->memcg_data * if MEMCG_DATA_OBJEXTS is set. */ struct slabobj_ext { #ifdef CONFIG_MEMCG struct obj_cgroup *objcg; #endif #ifdef CONFIG_MEM_ALLOC_PROFILING union codetag_ref ref; #endif } __aligned(8); static inline struct lruvec *parent_lruvec(struct lruvec *lruvec) { struct mem_cgroup *memcg; memcg = lruvec_memcg(lruvec); if (!memcg) return NULL; memcg = parent_mem_cgroup(memcg); if (!memcg) return NULL; return mem_cgroup_lruvec(memcg, lruvec_pgdat(lruvec)); } static inline void lruvec_lock_irq(struct lruvec *lruvec) { rcu_read_lock(); spin_lock_irq(&lruvec->lru_lock); } static inline struct lruvec *lruvec_live_lock_irq(struct lruvec *lruvec) { #ifdef CONFIG_MEMCG struct pglist_data *pgdat = lruvec_pgdat(lruvec); struct mem_cgroup *memcg = lruvec_memcg(lruvec); rcu_read_lock(); /* * The memcg can be NULL when the memory controller is disabled. * Otherwise, the caller keeps the memcg owning @lruvec alive. */ while (unlikely(memcg && css_is_dying(&memcg->css))) { memcg = parent_mem_cgroup(memcg); lruvec = mem_cgroup_lruvec(memcg, pgdat); } spin_lock_irq(&lruvec->lru_lock); #else lruvec_lock_irq(lruvec); #endif return lruvec; } static inline void lruvec_unlock(struct lruvec *lruvec) { spin_unlock(&lruvec->lru_lock); rcu_read_unlock(); } static inline void lruvec_unlock_irq(struct lruvec *lruvec) { spin_unlock_irq(&lruvec->lru_lock); rcu_read_unlock(); } static inline void lruvec_unlock_irqrestore(struct lruvec *lruvec, unsigned long flags) { spin_unlock_irqrestore(&lruvec->lru_lock, flags); rcu_read_unlock(); } /* Test requires a stable folio->memcg binding, see folio_memcg() */ static inline bool folio_matches_lruvec(struct folio *folio, struct lruvec *lruvec) { return lruvec_pgdat(lruvec) == folio_pgdat(folio) && lruvec_memcg(lruvec) == folio_memcg(folio); } /* Don't lock again iff page's lruvec locked */ static inline struct lruvec *folio_lruvec_relock_irq(struct folio *folio, struct lruvec *locked_lruvec) { if (locked_lruvec) { if (folio_matches_lruvec(folio, locked_lruvec)) return locked_lruvec; lruvec_unlock_irq(locked_lruvec); } return folio_lruvec_lock_irq(folio); } /* Don't lock again iff folio's lruvec locked */ static inline void folio_lruvec_relock_irqsave(struct folio *folio, struct lruvec **lruvecp, unsigned long *flags) { if (*lruvecp) { if (folio_matches_lruvec(folio, *lruvecp)) return; lruvec_unlock_irqrestore(*lruvecp, *flags); } *lruvecp = folio_lruvec_lock_irqsave(folio, flags); } #ifdef CONFIG_CGROUP_WRITEBACK struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb); void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback); void mem_cgroup_track_foreign_dirty_slowpath(struct folio *folio, struct bdi_writeback *wb); static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { struct mem_cgroup *memcg; if (mem_cgroup_disabled()) return; if (!folio_memcg_charged(folio)) return; rcu_read_lock(); memcg = folio_memcg(folio); if (unlikely(&memcg->css != wb->memcg_css)) mem_cgroup_track_foreign_dirty_slowpath(folio, wb); rcu_read_unlock(); } void mem_cgroup_flush_foreign(struct bdi_writeback *wb); #else /* CONFIG_CGROUP_WRITEBACK */ static inline struct wb_domain *mem_cgroup_wb_domain(struct bdi_writeback *wb) { return NULL; } static inline void mem_cgroup_wb_stats(struct bdi_writeback *wb, unsigned long *pfilepages, unsigned long *pheadroom, unsigned long *pdirty, unsigned long *pwriteback) { } static inline void mem_cgroup_track_foreign_dirty(struct folio *folio, struct bdi_writeback *wb) { } static inline void mem_cgroup_flush_foreign(struct bdi_writeback *wb) { } #endif /* CONFIG_CGROUP_WRITEBACK */ struct sock; #ifdef CONFIG_MEMCG extern struct static_key_false memcg_sockets_enabled_key; #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key) void mem_cgroup_sk_alloc(struct sock *sk); void mem_cgroup_sk_free(struct sock *sk); void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk); bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, gfp_t gfp_mask); void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages); #if BITS_PER_LONG < 64 static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { u64 val = get_jiffies_64() + HZ; unsigned long flags; write_seqlock_irqsave(&memcg->socket_pressure_seqlock, flags); memcg->socket_pressure = val; write_sequnlock_irqrestore(&memcg->socket_pressure_seqlock, flags); } static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) { unsigned int seq; u64 val; do { seq = read_seqbegin(&memcg->socket_pressure_seqlock); val = memcg->socket_pressure; } while (read_seqretry(&memcg->socket_pressure_seqlock, seq)); return val; } #else static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg) { WRITE_ONCE(memcg->socket_pressure, jiffies + HZ); } static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg) { return READ_ONCE(memcg->socket_pressure); } #endif int alloc_shrinker_info(struct mem_cgroup *memcg); void free_shrinker_info(struct mem_cgroup *memcg); void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id); void reparent_shrinker_deferred(struct mem_cgroup *memcg); static inline int shrinker_id(struct shrinker *shrinker) { return shrinker->id; } #else #define mem_cgroup_sockets_enabled 0 static inline void mem_cgroup_sk_alloc(struct sock *sk) { } static inline void mem_cgroup_sk_free(struct sock *sk) { } static inline void mem_cgroup_sk_inherit(const struct sock *sk, struct sock *newsk) { } static inline bool mem_cgroup_sk_charge(const struct sock *sk, unsigned int nr_pages, gfp_t gfp_mask) { return false; } static inline void mem_cgroup_sk_uncharge(const struct sock *sk, unsigned int nr_pages) { } static inline void set_shrinker_bit(struct mem_cgroup *memcg, int nid, int shrinker_id) { } static inline int shrinker_id(struct shrinker *shrinker) { return -1; } #endif #ifdef CONFIG_MEMCG bool mem_cgroup_kmem_disabled(void); int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order); void __memcg_kmem_uncharge_page(struct page *page, int order); /* * The returned objcg pointer is safe to use without additional * protection within a scope. The scope is defined either by * the current task (similar to the "current" global variable) * or by set_active_memcg() pair. * Please, use obj_cgroup_get() to get a reference if the pointer * needs to be used outside of the local scope. */ struct obj_cgroup *current_obj_cgroup(void); struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio); static inline struct obj_cgroup *get_obj_cgroup_from_current(void) { struct obj_cgroup *objcg = current_obj_cgroup(); if (objcg) obj_cgroup_get(objcg); return objcg; } int obj_cgroup_charge(struct obj_cgroup *objcg, gfp_t gfp, size_t size); void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_bpf_enabled_key; static inline bool memcg_bpf_enabled(void) { return static_branch_likely(&memcg_bpf_enabled_key); } extern struct static_key_false memcg_kmem_online_key; static inline bool memcg_kmem_online(void) { return static_branch_likely(&memcg_kmem_online_key); } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { if (memcg_kmem_online()) return __memcg_kmem_charge_page(page, gfp, order); return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { if (memcg_kmem_online()) __memcg_kmem_uncharge_page(page, order); } /* * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } struct mem_cgroup *mem_cgroup_from_virt(void *p); static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, unsigned long count) { struct mem_cgroup *memcg; if (!memcg_kmem_online()) return; rcu_read_lock(); memcg = obj_cgroup_memcg(objcg); count_memcg_events(memcg, idx, count); rcu_read_unlock(); } void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask); void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg); static inline bool memcg_is_dying(struct mem_cgroup *memcg) { return memcg ? css_is_dying(&memcg->css) : false; } #else static inline bool mem_cgroup_kmem_disabled(void) { return true; } static inline int memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void memcg_kmem_uncharge_page(struct page *page, int order) { } static inline int __memcg_kmem_charge_page(struct page *page, gfp_t gfp, int order) { return 0; } static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } static inline struct obj_cgroup *get_obj_cgroup_from_folio(struct folio *folio) { return NULL; } static inline bool memcg_bpf_enabled(void) { return false; } static inline bool memcg_kmem_online(void) { return false; } static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } static inline struct mem_cgroup *mem_cgroup_from_virt(void *p) { return NULL; } static inline void count_objcg_events(struct obj_cgroup *objcg, enum vm_event_item idx, unsigned long count) { } static inline ino_t page_cgroup_ino(struct page *page) { return 0; } static inline void mem_cgroup_node_filter_allowed(struct mem_cgroup *memcg, nodemask_t *mask) { } static inline void mem_cgroup_show_protected_memory(struct mem_cgroup *memcg) { } static inline bool memcg_is_dying(struct mem_cgroup *memcg) { return false; } #endif /* CONFIG_MEMCG */ #if defined(CONFIG_MEMCG) && defined(CONFIG_ZSWAP) bool obj_cgroup_may_zswap(struct obj_cgroup *objcg); void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size); void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size); bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg); #else static inline bool obj_cgroup_may_zswap(struct obj_cgroup *objcg) { return true; } static inline void obj_cgroup_charge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size) { } static inline bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg) { /* if zswap is disabled, do not block pages going to the swapping device */ return true; } #endif /* Cgroup v1-related declarations */ #ifdef CONFIG_MEMCG_V1 unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned); bool mem_cgroup_oom_synchronize(bool wait); static inline bool task_in_memcg_oom(struct task_struct *p) { return p->memcg_in_oom; } static inline void mem_cgroup_enter_user_fault(void) { WARN_ON(current->in_user_fault); current->in_user_fault = 1; } static inline void mem_cgroup_exit_user_fault(void) { WARN_ON(!current->in_user_fault); current->in_user_fault = 0; } #else /* CONFIG_MEMCG_V1 */ static inline unsigned long memcg1_soft_limit_reclaim(pg_data_t *pgdat, int order, gfp_t gfp_mask, unsigned long *total_scanned) { return 0; } static inline bool task_in_memcg_oom(struct task_struct *p) { return false; } static inline bool mem_cgroup_oom_synchronize(bool wait) { return false; } static inline void mem_cgroup_enter_user_fault(void) { } static inline void mem_cgroup_exit_user_fault(void) { } #endif /* CONFIG_MEMCG_V1 */ #if defined(CONFIG_MEMCG_V1) && defined(CONFIG_SWAP) void __memcg1_swapout(struct folio *folio, struct swap_cluster_info *ci); void memcg1_swapin(struct folio *folio); #else static inline void __memcg1_swapout(struct folio *folio, struct swap_cluster_info *ci) { } static inline void memcg1_swapin(struct folio *folio) { } #endif #endif /* _LINUX_MEMCONTROL_H */ |
| 2 1 1 1 1 1 1 1 1 1 1 1 2 2 2 1 1 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/hfsplus/extents.c * * Copyright (C) 2001 * Brad Boyer (flar@allandria.com) * (C) 2003 Ardis Technologies <roman@ardistech.com> * * Handling of Extents both in catalog and extents overflow trees */ #include <linux/errno.h> #include <linux/fs.h> #include <linux/pagemap.h> #include "hfsplus_fs.h" #include "hfsplus_raw.h" /* Compare two extents keys, returns 0 on same, pos/neg for difference */ int hfsplus_ext_cmp_key(const hfsplus_btree_key *k1, const hfsplus_btree_key *k2) { __be32 k1id, k2id; __be32 k1s, k2s; k1id = k1->ext.cnid; k2id = k2->ext.cnid; if (k1id != k2id) return be32_to_cpu(k1id) < be32_to_cpu(k2id) ? -1 : 1; if (k1->ext.fork_type != k2->ext.fork_type) return k1->ext.fork_type < k2->ext.fork_type ? -1 : 1; k1s = k1->ext.start_block; k2s = k2->ext.start_block; if (k1s == k2s) return 0; return be32_to_cpu(k1s) < be32_to_cpu(k2s) ? -1 : 1; } static void hfsplus_ext_build_key(hfsplus_btree_key *key, u32 cnid, u32 block, u8 type) { key->key_len = cpu_to_be16(HFSPLUS_EXT_KEYLEN - 2); key->ext.cnid = cpu_to_be32(cnid); key->ext.start_block = cpu_to_be32(block); key->ext.fork_type = type; key->ext.pad = 0; } static u32 hfsplus_ext_find_block(struct hfsplus_extent *ext, u32 off) { int i; u32 count; for (i = 0; i < 8; ext++, i++) { count = be32_to_cpu(ext->block_count); if (off < count) return be32_to_cpu(ext->start_block) + off; off -= count; } /* panic? */ return 0; } static int hfsplus_ext_block_count(struct hfsplus_extent *ext) { int i; u32 count = 0; for (i = 0; i < 8; ext++, i++) count += be32_to_cpu(ext->block_count); return count; } static u32 hfsplus_ext_lastblock(struct hfsplus_extent *ext) { int i; ext += 7; for (i = 0; i < 7; ext--, i++) if (ext->block_count) break; return be32_to_cpu(ext->start_block) + be32_to_cpu(ext->block_count); } static int __hfsplus_ext_write_extent(struct inode *inode, struct hfs_find_data *fd) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res; WARN_ON(!mutex_is_locked(&hip->extents_lock)); hfsplus_ext_build_key(fd->search_key, inode->i_ino, hip->cached_start, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA); res = hfs_brec_find(fd, hfs_find_rec_by_key); if (hip->extent_state & HFSPLUS_EXT_NEW) { if (res != -ENOENT) return res; /* Fail early and avoid ENOSPC during the btree operation */ res = hfs_bmap_reserve(fd->tree, fd->tree->depth + 1); if (res) return res; hfs_brec_insert(fd, hip->cached_extents, sizeof(hfsplus_extent_rec)); hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } else { if (res) return res; hfs_bnode_write(fd->bnode, hip->cached_extents, fd->entryoffset, fd->entrylength); hip->extent_state &= ~HFSPLUS_EXT_DIRTY; } /* * We can't just use hfsplus_mark_inode_dirty here, because we * also get called from hfsplus_write_inode, which should not * redirty the inode. Instead the callers have to be careful * to explicily mark the inode dirty, too. */ set_bit(HFSPLUS_I_EXT_DIRTY, &HFSPLUS_I(HFSPLUS_EXT_TREE_I(inode->i_sb))->flags); set_bit(HFSPLUS_I_EXT_DIRTY, &hip->flags); return 0; } static int hfsplus_ext_write_extent_locked(struct inode *inode) { int res = 0; if (HFSPLUS_I(inode)->extent_state & HFSPLUS_EXT_DIRTY) { struct hfs_find_data fd; res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); if (res) return res; res = __hfsplus_ext_write_extent(inode, &fd); hfs_find_exit(&fd); } return res; } int hfsplus_ext_write_extent(struct inode *inode) { int res; mutex_lock(&HFSPLUS_I(inode)->extents_lock); res = hfsplus_ext_write_extent_locked(inode); mutex_unlock(&HFSPLUS_I(inode)->extents_lock); return res; } static inline int __hfsplus_ext_read_extent(struct hfs_find_data *fd, struct hfsplus_extent *extent, u32 cnid, u32 block, u8 type) { int res; hfsplus_ext_build_key(fd->search_key, cnid, block, type); fd->key->ext.cnid = 0; res = hfs_brec_find(fd, hfs_find_rec_by_key); if (res && res != -ENOENT) return res; if (fd->key->ext.cnid != fd->search_key->ext.cnid || fd->key->ext.fork_type != fd->search_key->ext.fork_type) return -ENOENT; if (fd->entrylength != sizeof(hfsplus_extent_rec)) return -EIO; hfs_bnode_read(fd->bnode, extent, fd->entryoffset, sizeof(hfsplus_extent_rec)); return 0; } static inline int __hfsplus_ext_cache_extent(struct hfs_find_data *fd, struct inode *inode, u32 block) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res; WARN_ON(!mutex_is_locked(&hip->extents_lock)); if (hip->extent_state & HFSPLUS_EXT_DIRTY) { res = __hfsplus_ext_write_extent(inode, fd); if (res) return res; } res = __hfsplus_ext_read_extent(fd, hip->cached_extents, inode->i_ino, block, HFSPLUS_IS_RSRC(inode) ? HFSPLUS_TYPE_RSRC : HFSPLUS_TYPE_DATA); if (!res) { hip->cached_start = be32_to_cpu(fd->key->ext.start_block); hip->cached_blocks = hfsplus_ext_block_count(hip->cached_extents); } else { hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } return res; } static int hfsplus_ext_read_extent(struct inode *inode, u32 block) { struct hfsplus_inode_info *hip = HFSPLUS_I(inode); struct hfs_find_data fd; int res; if (block >= hip->cached_start && block < hip->cached_start + hip->cached_blocks) return 0; res = hfs_find_init(HFSPLUS_SB(inode->i_sb)->ext_tree, &fd); if (!res) { res = __hfsplus_ext_cache_extent(&fd, inode, block); hfs_find_exit(&fd); } return res; } /* Get a block at iblock for inode, possibly allocating if create */ int hfsplus_get_block(struct inode *inode, sector_t iblock, struct buffer_head *bh_result, int create) { struct super_block *sb = inode->i_sb; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); int res = -EIO; u32 ablock, dblock, mask; sector_t sector; int was_dirty = 0; /* Convert inode block to disk allocation block */ ablock = iblock >> sbi->fs_shift; if (iblock >= hip->fs_blocks) { if (!create) return 0; if (iblock > hip->fs_blocks) return -EIO; if (ablock >= hip->alloc_blocks) { res = hfsplus_file_extend(inode, false); if (res) return res; } } else create = 0; if (ablock < hip->first_blocks) { dblock = hfsplus_ext_find_block(hip->first_extents, ablock); goto done; } if (inode->i_ino == HFSPLUS_EXT_CNID) return -EIO; mutex_lock(&hip->extents_lock); /* * hfsplus_ext_read_extent will write out a cached extent into * the extents btree. In that case we may have to mark the inode * dirty even for a pure read of an extent here. */ was_dirty = (hip->extent_state & HFSPLUS_EXT_DIRTY); res = hfsplus_ext_read_extent(inode, ablock); if (res) { mutex_unlock(&hip->extents_lock); return -EIO; } dblock = hfsplus_ext_find_block(hip->cached_extents, ablock - hip->cached_start); mutex_unlock(&hip->extents_lock); done: hfs_dbg("ino %llu, iblock %llu - dblock %u\n", inode->i_ino, (long long)iblock, dblock); mask = (1 << sbi->fs_shift) - 1; sector = ((sector_t)dblock << sbi->fs_shift) + sbi->blockoffset + (iblock & mask); map_bh(bh_result, sb, sector); if (create) { set_buffer_new(bh_result); hip->phys_size += sb->s_blocksize; hip->fs_blocks++; inode_add_bytes(inode, sb->s_blocksize); } if (create || was_dirty) mark_inode_dirty(inode); return 0; } static void hfsplus_dump_extent(struct hfsplus_extent *extent) { int i; hfs_dbg("extent "); for (i = 0; i < 8; i++) hfs_dbg(" start_block %u, block_count %u", be32_to_cpu(extent[i].start_block), be32_to_cpu(extent[i].block_count)); hfs_dbg("\n"); } static int hfsplus_add_extent(struct hfsplus_extent *extent, u32 offset, u32 alloc_block, u32 block_count) { u32 count, start; int i; hfsplus_dump_extent(extent); for (i = 0; i < 8; extent++, i++) { count = be32_to_cpu(extent->block_count); if (offset == count) { start = be32_to_cpu(extent->start_block); if (alloc_block != start + count) { if (++i >= 8) return -ENOSPC; extent++; extent->start_block = cpu_to_be32(alloc_block); } else block_count += count; extent->block_count = cpu_to_be32(block_count); return 0; } else if (offset < count) break; offset -= count; } /* panic? */ return -EIO; } static int hfsplus_free_extents(struct super_block *sb, struct hfsplus_extent *extent, u32 offset, u32 block_nr) { u32 count, start; int i; int err = 0; hfsplus_dump_extent(extent); for (i = 0; i < 8; extent++, i++) { count = be32_to_cpu(extent->block_count); if (offset == count) goto found; else if (offset < count) break; offset -= count; } /* panic? */ return -EIO; found: for (;;) { start = be32_to_cpu(extent->start_block); if (count <= block_nr) { err = hfsplus_block_free(sb, start, count); if (err) { pr_err("can't free extent: start %u, count %u\n", start, count); } extent->block_count = 0; extent->start_block = 0; block_nr -= count; } else { count -= block_nr; err = hfsplus_block_free(sb, start + count, block_nr); if (err) { pr_err("can't free extent: start %u, count %u\n", start, count); } extent->block_count = cpu_to_be32(count); block_nr = 0; } if (!block_nr || !i) { /* * Try to free all extents and * return only last error */ return err; } i--; extent--; count = be32_to_cpu(extent->block_count); } } int hfsplus_free_fork(struct super_block *sb, u32 cnid, struct hfsplus_fork_raw *fork, int type) { struct hfs_find_data fd; hfsplus_extent_rec ext_entry; u32 total_blocks, blocks, start; int res, i; total_blocks = be32_to_cpu(fork->total_blocks); if (!total_blocks) return 0; blocks = 0; for (i = 0; i < 8; i++) blocks += be32_to_cpu(fork->extents[i].block_count); res = hfsplus_free_extents(sb, fork->extents, blocks, blocks); if (res) return res; if (total_blocks == blocks) return 0; res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); if (res) return res; do { res = __hfsplus_ext_read_extent(&fd, ext_entry, cnid, total_blocks, type); if (res) break; start = be32_to_cpu(fd.key->ext.start_block); hfs_brec_remove(&fd); mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, ext_entry, total_blocks - start, total_blocks); total_blocks = start; mutex_lock_nested(&fd.tree->tree_lock, hfsplus_btree_lock_class(fd.tree)); } while (total_blocks > blocks); hfs_find_exit(&fd); return res; } int hfsplus_file_extend(struct inode *inode, bool zeroout) { struct super_block *sb = inode->i_sb; struct hfsplus_sb_info *sbi = HFSPLUS_SB(sb); struct hfsplus_inode_info *hip = HFSPLUS_I(inode); u32 start, len, goal; int res; if (sbi->alloc_file->i_size * 8 < sbi->total_blocks - sbi->free_blocks + 8) { /* extend alloc file */ pr_err_ratelimited("extend alloc file! (%llu,%u,%u)\n", sbi->alloc_file->i_size * 8, sbi->total_blocks, sbi->free_blocks); return -ENOSPC; } mutex_lock(&hip->extents_lock); if (hip->alloc_blocks == hip->first_blocks) goal = hfsplus_ext_lastblock(hip->first_extents); else { res = hfsplus_ext_read_extent(inode, hip->alloc_blocks); if (res) goto out; goal = hfsplus_ext_lastblock(hip->cached_extents); } len = hip->clump_blocks; start = hfsplus_block_allocate(sb, sbi->total_blocks, goal, &len); if (start >= sbi->total_blocks) { start = hfsplus_block_allocate(sb, goal, 0, &len); if (start >= goal) { res = -ENOSPC; goto out; } } if (zeroout) { res = sb_issue_zeroout(sb, start, len, GFP_NOFS); if (res) goto out; } hfs_dbg("ino %llu, start %u, len %u\n", inode->i_ino, start, len); if (hip->alloc_blocks <= hip->first_blocks) { if (!hip->first_blocks) { hfs_dbg("first_extent: start %u, len %u\n", start, len); /* no extents yet */ hip->first_extents[0].start_block = cpu_to_be32(start); hip->first_extents[0].block_count = cpu_to_be32(len); res = 0; } else { /* try to append to extents in inode */ res = hfsplus_add_extent(hip->first_extents, hip->alloc_blocks, start, len); if (res == -ENOSPC) goto insert_extent; } if (!res) { hfsplus_dump_extent(hip->first_extents); hip->first_blocks += len; } } else { res = hfsplus_add_extent(hip->cached_extents, hip->alloc_blocks - hip->cached_start, start, len); if (!res) { hfsplus_dump_extent(hip->cached_extents); hip->extent_state |= HFSPLUS_EXT_DIRTY; hip->cached_blocks += len; } else if (res == -ENOSPC) goto insert_extent; } out: if (!res) { hip->alloc_blocks += len; mutex_unlock(&hip->extents_lock); hfsplus_mark_inode_dirty(HFSPLUS_SB(sb)->alloc_file, HFSPLUS_I_ALLOC_DIRTY); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY); return 0; } mutex_unlock(&hip->extents_lock); return res; insert_extent: hfs_dbg("insert new extent\n"); res = hfsplus_ext_write_extent_locked(inode); if (res) goto out; memset(hip->cached_extents, 0, sizeof(hfsplus_extent_rec)); hip->cached_extents[0].start_block = cpu_to_be32(start); hip->cached_extents[0].block_count = cpu_to_be32(len); hfsplus_dump_extent(hip->cached_extents); hip->extent_state |= HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW; hip->cached_start = hip->alloc_blocks; hip->cached_blocks = len; res = 0; goto out; } void hfsplus_file_truncate(struct inode *inode) { struct super_block *sb = inode->i_sb; struct hfsplus_inode_info *hip = HFSPLUS_I(inode); struct hfs_find_data fd; u32 alloc_cnt, blk_cnt, start; int res; hfs_dbg("ino %llu, phys_size %llu -> i_size %llu\n", inode->i_ino, (long long)hip->phys_size, inode->i_size); if (inode->i_size > hip->phys_size) { struct address_space *mapping = inode->i_mapping; struct folio *folio; void *fsdata = NULL; loff_t size = inode->i_size; res = hfsplus_write_begin(NULL, mapping, size, 0, &folio, &fsdata); if (res) return; res = generic_write_end(NULL, mapping, size, 0, 0, folio, fsdata); if (res < 0) return; mark_inode_dirty(inode); return; } else if (inode->i_size == hip->phys_size) return; blk_cnt = (inode->i_size + HFSPLUS_SB(sb)->alloc_blksz - 1) >> HFSPLUS_SB(sb)->alloc_blksz_shift; mutex_lock(&hip->extents_lock); alloc_cnt = hip->alloc_blocks; if (blk_cnt == alloc_cnt) goto out_unlock; res = hfs_find_init(HFSPLUS_SB(sb)->ext_tree, &fd); if (res) { mutex_unlock(&hip->extents_lock); /* XXX: We lack error handling of hfsplus_file_truncate() */ return; } while (1) { if (alloc_cnt == hip->first_blocks) { mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->first_extents, alloc_cnt, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->first_extents); hip->first_blocks = blk_cnt; mutex_lock_nested(&fd.tree->tree_lock, hfsplus_btree_lock_class(fd.tree)); break; } res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt); if (res) break; start = hip->cached_start; if (blk_cnt <= start) hfs_brec_remove(&fd); mutex_unlock(&fd.tree->tree_lock); hfsplus_free_extents(sb, hip->cached_extents, alloc_cnt - start, alloc_cnt - blk_cnt); hfsplus_dump_extent(hip->cached_extents); mutex_lock_nested(&fd.tree->tree_lock, hfsplus_btree_lock_class(fd.tree)); if (blk_cnt > start) { hip->extent_state |= HFSPLUS_EXT_DIRTY; break; } alloc_cnt = start; hip->cached_start = hip->cached_blocks = 0; hip->extent_state &= ~(HFSPLUS_EXT_DIRTY | HFSPLUS_EXT_NEW); } hfs_find_exit(&fd); hip->alloc_blocks = blk_cnt; out_unlock: mutex_unlock(&hip->extents_lock); hip->phys_size = inode->i_size; hip->fs_blocks = (inode->i_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits; inode_set_bytes(inode, hip->fs_blocks << sb->s_blocksize_bits); hfsplus_mark_inode_dirty(HFSPLUS_SB(sb)->alloc_file, HFSPLUS_I_ALLOC_DIRTY); hfsplus_mark_inode_dirty(inode, HFSPLUS_I_ALLOC_DIRTY); } |
| 265 166 1 264 265 5 20 265 167 166 266 153 146 8 265 265 153 153 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * fs/eventpoll.c (Efficient event retrieval implementation) * Copyright (C) 2001,...,2009 Davide Libenzi * * Davide Libenzi <davidel@xmailserver.org> */ #include <linux/init.h> #include <linux/kernel.h> #include <linux/sched/signal.h> #include <linux/fs.h> #include <linux/file.h> #include <linux/signal.h> #include <linux/errno.h> #include <linux/mm.h> #include <linux/slab.h> #include <linux/poll.h> #include <linux/string.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/spinlock.h> #include <linux/syscalls.h> #include <linux/rbtree.h> #include <linux/wait.h> #include <linux/eventpoll.h> #include <linux/mount.h> #include <linux/bitops.h> #include <linux/mutex.h> #include <linux/anon_inodes.h> #include <linux/device.h> #include <linux/uaccess.h> #include <asm/io.h> #include <asm/mman.h> #include <linux/atomic.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/compat.h> #include <linux/rculist.h> #include <linux/capability.h> #include <linux/seqlock.h> #include <net/busy_poll.h> /* * fs/eventpoll.c - Efficient event polling ("epoll") kernel implementation. * * * Overview * -------- * * Each epoll_create(2) returns an anonymous [eventpoll] file whose * ->private_data is a struct eventpoll. Each EPOLL_CTL_ADD installs * a struct epitem linking one (watched file, fd) pair back to that * eventpoll via the watched file's f_op->poll() wait queue(s). When * the watched file signals readiness, ep_poll_callback() fires and * marks the epitem ready. epoll_wait(2) drains the ready list under * ep->mtx, re-queueing items in level-triggered mode. * * epoll instances can watch other epoll instances up to EP_MAX_NESTS * deep; cycles are forbidden and detected at EPOLL_CTL_ADD time. * * * Locking * ------- * * Three levels, acquired from outer to inner: * * epnested_mutex (global; rare; taken only for EPOLL_CTL_ADD * loop / path checks) * > ep->mtx (per-eventpoll; sleepable; serializes most ops) * > ep->lock (per-eventpoll; IRQ-safe spinlock) * * file->f_lock (per-file; NOT IRQ-safe; guards f_ep hlist ops; * nested inside ep->mtx, outside ep->lock) * * Rationale: * - ep->lock is a spinlock because ep_poll_callback() is called from * wake_up() which may run in hard-IRQ context. All ep->lock * critical sections use spin_lock_irqsave(). * - ep->mtx is a sleepable mutex because the event delivery loop * calls copy_to_user(), and ep_insert() may sleep in * kmem_cache_alloc() and f_op->poll(). * - epnested_mutex is global because cycle detection needs a global * view of the epoll topology; a per-object scheme would let two * concurrent inserts (A into B, B into A) construct a cycle * without either observer seeing it. * - Per-ep ep->mtx is preferred for scalability elsewhere. Events * that require epnested_mutex are rare. * * When EPOLL_CTL_ADD nests one eventpoll inside another we acquire * ep->mtx on both: outer first, target second. Since cycles are * forbidden the set of live ep->mtx holds is always a strict chain, * communicated to lockdep via mutex_lock_nested() subclasses derived * from the current recursion depth. * * * Field protection * ---------------- * * struct eventpoll: * mtx - self * rbr - ep->mtx * ovflist, rdllist - ep->lock (IRQ-safe) * wq - ep->lock for queue mutation * poll_wait - internal waitqueue spinlock * refs - file->f_lock for adds; ep->mtx for removes; * RCU for readers (hlist_del_rcu + kfree_rcu(ep)) * ws - ep->mtx * gen, loop_check_depth - epnested_mutex * file, user - immutable after setup * refcount - atomic (refcount_t) * napi_* - READ_ONCE / WRITE_ONCE * * struct epitem: * rbn / rcu union - rbn: ep->mtx (while epi is linked in ep->rbr). * rcu: written only by kfree_rcu(epi) on the free * path; otherwise untouched by epoll code. * rdllink, next - ep->lock * ffd, ep - immutable after ep_insert() * pwqlist - ep->mtx for writes; POLLFREE clears pwq->whead * via smp_store_release(), see below * fllink - file->f_lock for mutation; hlist_del_rcu + * kfree_rcu(epi) for safe RCU readers * ws - RCU (rcu_assign_pointer / * rcu_dereference_check(mtx)) * event - ep->mtx for writes; lockless read in * ep_poll_callback pairs with smp_mb() in * ep_modify() * * * Ready-list state machine * ------------------------ * * Readiness is tracked in two lists under ep->lock: * * rdllist - doubly-linked FIFO; the "current" ready list. * ovflist - singly-linked LIFO; used during a scan to catch * events that arrive while rdllist is being iterated * without ep->lock. * * Encoded in ep->ovflist: * EP_UNACTIVE_PTR - no scan active; callback appends to rdllist. * NULL - scan active, no spill yet. * pointer to epi - scan active with spilled items (LIFO). * * Encoded in epi->ovflist_next: * EP_UNACTIVE_PTR - epi is not on ovflist. * otherwise - next epi on ovflist (NULL at tail). * * ep_start_scan() flips "not scanning" to "scanning" and splices * rdllist into a caller-local scan_batch. ep_done_scan() drains ovflist * back to rdllist (list_add head-insert reverses LIFO to FIFO), * flips back to "not scanning", and re-splices any items the caller * left in scan_batch (e.g., level-triggered re-queues). * * * Removal paths * ------------- * * Three paths dispose of epitems and/or eventpolls: * * A. ep_remove() - EPOLL_CTL_DEL and ep_insert() * rollback. Caller holds ep->mtx. * B. ep_clear_and_put() - close of the epoll fd itself * (ep_eventpoll_release). * C. eventpoll_release_file() - close of a watched file, invoked * from __fput(). * * Coordination: * A and C exclude each other via the watched file's refcount. * A pins the file with epi_fget() before touching file->f_ep or * file->f_lock; if the pin fails, __fput() is in flight and C * will clean this epi up. See the epi_fget() block comment. * A and B both hold ep->mtx serially. B walks the rbtree with * rb_next() captured before ep_remove() erases the current node. * B and C both take ep->mtx; the loser sees fewer entries or an * empty file->f_ep. * * Within every path the internal order is strict: * ep_unregister_pollwait() - drain pwqlist; synchronizes with any * in-flight ep_poll_callback via the * watched wait-queue head's lock. * ep_remove_file() - hlist_del_rcu of epi->fllink and, * if last watcher, clear file->f_ep, * under file->f_lock. * ep_remove_epi() - rb_erase, rdllist unlink (ep->lock), * wakeup_source_unregister, * kfree_rcu(epi). * * kfree_rcu(epi) defers the free past RCU readers in * reverse_path_check_proc(); kfree_rcu(ep) defers past readers in * ep_get_upwards_depth_proc(). * * * POLLFREE handshake * ------------------ * * When a subsystem tears down a wait-queue head that an epitem is * registered on (binder, signalfd, ...), it wakes the callback with * POLLFREE and must RCU-defer the head's free. The store/load pair: * * ep_poll_callback() POLLFREE branch: * smp_store_release(&pwq->whead, NULL) * * ep_remove_wait_queue(): * smp_load_acquire(&pwq->whead) * * See those sites for the full argument. */ /* Epoll private bits inside the event mask */ #define EP_PRIVATE_BITS (EPOLLWAKEUP | EPOLLONESHOT | EPOLLET | EPOLLEXCLUSIVE) #define EPOLLINOUT_BITS (EPOLLIN | EPOLLOUT) #define EPOLLEXCLUSIVE_OK_BITS (EPOLLINOUT_BITS | EPOLLERR | EPOLLHUP | \ EPOLLWAKEUP | EPOLLET | EPOLLEXCLUSIVE) /* Maximum number of nesting allowed inside epoll sets */ #define EP_MAX_NESTS 4 #define EP_MAX_EVENTS (INT_MAX / sizeof(struct epoll_event)) #define EP_UNACTIVE_PTR ((void *) -1L) #define EP_ITEM_COST (sizeof(struct epitem) + sizeof(struct eppoll_entry)) /* Wait structure used by the poll hooks */ struct eppoll_entry { /* List header used to link this structure to the "struct epitem" */ struct eppoll_entry *next; /* The "base" pointer is set to the container "struct epitem" */ struct epitem *base; /* * Wait queue item that will be linked to the target file wait * queue head. */ wait_queue_entry_t wait; /* The wait queue head that linked the "wait" wait queue item */ wait_queue_head_t *whead; }; /* * Each file descriptor added to the eventpoll interface will * have an entry of this type linked to the "rbr" RB tree. * Avoid increasing the size of this struct, there can be many thousands * of these on a server and we do not want this to take another cache line. */ struct epitem { union { /* RB tree node links this structure to the eventpoll RB tree */ struct rb_node rbn; /* Used to free the struct epitem */ struct rcu_head rcu; }; /* Link on the owning eventpoll's ready list (ep->rdllist). */ struct list_head rdllink; /* * Link on the owning eventpoll's scan-overflow list (ep->ovflist), * EP_UNACTIVE_PTR when not linked. See epi_on_ovflist() / * epi_clear_ovflist() and the "Ready-list state machine" section * in the top-of-file banner. */ struct epitem *ovflist_next; /* The file descriptor information this item refers to */ struct epoll_key ffd; /* List containing poll wait queues */ struct eppoll_entry *pwqlist; /* The "container" of this item */ struct eventpoll *ep; /* List header used to link this item to the "struct file" items list */ struct hlist_node fllink; /* wakeup_source used when EPOLLWAKEUP is set */ struct wakeup_source __rcu *ws; /* The structure that describe the interested events and the source fd */ struct epoll_event event; }; /* * This structure is stored inside the "private_data" member of the file * structure and represents the main data structure for the eventpoll * interface. */ struct eventpoll { /* * This mutex is used to ensure that files are not removed * while epoll is using them. This is held during the event * collection loop, the file cleanup path, the epoll file exit * code and the ctl operations. */ struct mutex mtx; /* Wait queue used by sys_epoll_wait() */ wait_queue_head_t wq; /* Wait queue used by file->poll() */ wait_queue_head_t poll_wait; /* List of ready file descriptors */ struct list_head rdllist; /* Lock which protects rdllist and ovflist */ spinlock_t lock; /* Protect switching between rdllist and ovflist */ seqcount_spinlock_t seq; /* RB tree root used to store monitored fd structs */ struct rb_root_cached rbr; /* * This is a single linked list that chains all the "struct epitem" that * happened while transferring ready events to userspace w/out * holding ->lock. */ struct epitem *ovflist; /* wakeup_source used when ep_send_events or __ep_eventpoll_poll is running */ struct wakeup_source *ws; /* The user that created the eventpoll descriptor */ struct user_struct *user; struct file *file; /* used to optimize loop detection check */ u64 gen; struct hlist_head refs; u8 loop_check_depth; /* usage count, orchestrates "struct eventpoll" disposal */ refcount_t refcount; /* used to defer freeing past ep_get_upwards_depth_proc() RCU walk */ struct rcu_head rcu; #ifdef CONFIG_NET_RX_BUSY_POLL /* used to track busy poll napi_id */ unsigned int napi_id; /* busy poll timeout */ u32 busy_poll_usecs; /* busy poll packet budget */ u16 busy_poll_budget; bool prefer_busy_poll; #endif #ifdef CONFIG_DEBUG_LOCK_ALLOC /* tracks wakeup nests for lockdep validation */ u8 nests; #endif }; /* Wrapper struct used by poll queueing */ struct ep_pqueue { poll_table pt; struct epitem *epi; }; /* * Configuration options available inside /proc/sys/fs/epoll/ */ /* Maximum number of epoll watched descriptors, per user */ static long max_user_watches __read_mostly; /* * Cycle and path-length checks at EPOLL_CTL_ADD * --------------------------------------------- * * When EPOLL_CTL_ADD creates a link that either targets an eventpoll * file or extends an existing chain of eventpolls, two checks run: * * 1. no cycle is being formed -- ep_loop_check() walks downward * from the candidate target, and ep_get_upwards_depth_proc() * walks upward from the outer ep, both bounded by EP_MAX_NESTS. * 2. no file accumulates more than path_limits[depth] wakeup paths * of a given length -- reverse_path_check(). * * Both need a global view of the epoll topology and must be atomic * with the insertion, so the check is serialized by epnested_mutex * and carries its scratch state on a stack-allocated struct * ep_ctl_ctx scoped to one do_epoll_ctl() call. Non-nested inserts * skip this machinery entirely and take only ep->mtx. * * epnested_mutex Serializes the whole check. * loop_check_gen Global monotonic stamp, bumped at the start of * a check and again at the end. ep->gen caches * the value under which ep was last visited by * ep_loop_check_proc() or * ep_get_upwards_depth_proc(); the post-check * bump ensures those cached stamps can no longer * equal loop_check_gen, so the * "ep->gen == loop_check_gen" trigger in * ep_ctl_lock() only fires while another check * is in flight. * * struct ep_ctl_ctx carries the rest (inserting_into, tfile_check_list, * path_count[]) through the walk; see its declaration below. * * Commits fdcfce93073d ("eventpoll: Fix integer overflow in * ep_loop_check_proc()") and f2e467a48287 ("eventpoll: Fix * semi-unbounded recursion") hardened the walk; any refactor must * preserve both bail-outs. */ static DEFINE_MUTEX(epnested_mutex); static u64 loop_check_gen = 0; #define PATH_ARR_SIZE 5 /* * Per-do_epoll_ctl() scratch for the loop / path checks. Allocated on * the caller's stack; populated by ep_ctl_lock() and the downward * walk; consumed by reverse_path_check(); released by ep_ctl_unlock(). * Only valid while the caller holds epnested_mutex. */ struct ep_ctl_ctx { /* * Outer eventpoll for one ep_loop_check(); if the downward walk * reaches it the insert would form a cycle. */ struct eventpoll *inserting_into; /* * Singly-linked list of epitems_head objects collected during * ep_loop_check_proc(), then walked by reverse_path_check(). * Terminated by EP_UNACTIVE_PTR, not NULL: epitems_head->next * doubles as a membership flag (a NULL ->next means "not on this * list", see ep_remove_file()), so the list uses a non-NULL * sentinel to keep the tail head distinguishable from an unlisted * one. */ struct epitems_head *tfile_check_list; /* * Per-depth wakeup-path tally used by reverse_path_check_proc(); * reinitialized to zero at the start of each reverse_path_check() * iteration. */ int path_count[PATH_ARR_SIZE]; }; /* Slab cache used to allocate "struct epitem" */ static struct kmem_cache *epi_cache __ro_after_init; /* Slab cache used to allocate "struct eppoll_entry" */ static struct kmem_cache *pwq_cache __ro_after_init; /* * Wrapper anchor for file->f_ep when the watched file is not itself an * eventpoll; for the epoll-watches-epoll case, file->f_ep points at * &watched_ep->refs directly. The ->next field threads * ctx->tfile_check_list during one EPOLL_CTL_ADD path check. The ->file * field holds a reference to the associated file while the head is on * the list. */ struct epitems_head { struct hlist_head epitems; struct epitems_head *next; struct file *file; }; static struct kmem_cache *ephead_cache __ro_after_init; static inline void free_ephead(struct epitems_head *head) { if (head) kmem_cache_free(ephead_cache, head); } static void list_file(struct file *file, struct ep_ctl_ctx *ctx) { struct epitems_head *head; head = container_of(file->f_ep, struct epitems_head, epitems); if (!head->next) { /* * The caller owns a reference to @file or holds the ep->mtx for the * epitem that led here. The latter blocks eventpoll_release_file() * before the file allocation can be freed and reused. A dying leaf * can be skipped since removing links cannot increase the reverse * path count. */ if (!file_ref_get(&file->f_ref)) return; head->file = file; head->next = ctx->tfile_check_list; ctx->tfile_check_list = head; } } static void unlist_file(struct epitems_head *head) { struct epitems_head *to_free = head; struct hlist_node *p = rcu_dereference(hlist_first_rcu(&head->epitems)); struct file *file = head->file; if (p) { struct epitem *epi= container_of(p, struct epitem, fllink); spin_lock(&epi->ffd.file->f_lock); if (!hlist_empty(&head->epitems)) to_free = NULL; head->next = NULL; head->file = NULL; spin_unlock(&epi->ffd.file->f_lock); } free_ephead(to_free); fput(file); } #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> static long long_zero; static long long_max = LONG_MAX; static const struct ctl_table epoll_table[] = { { .procname = "max_user_watches", .data = &max_user_watches, .maxlen = sizeof(max_user_watches), .mode = 0644, .proc_handler = proc_doulongvec_minmax, .extra1 = &long_zero, .extra2 = &long_max, }, }; static void __init epoll_sysctls_init(void) { register_sysctl("fs/epoll", epoll_table); } #else #define epoll_sysctls_init() do { } while (0) #endif /* CONFIG_SYSCTL */ static const struct file_operations eventpoll_fops; bool is_file_epoll(struct file *f) { return f->f_op == &eventpoll_fops; } /* Compare RB tree keys */ static inline int ep_cmp_ffd(struct epoll_key *p1, struct epoll_key *p2) { return (p1->file > p2->file ? +1: (p1->file < p2->file ? -1 : p1->fd - p2->fd)); } /* True iff @epi is on its owning ep's ready list. */ static inline bool ep_is_linked(struct epitem *epi) { return !list_empty(&epi->rdllink); } static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait); } /* Get the "struct epitem" from a wait queue pointer */ static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p) { return container_of(p, struct eppoll_entry, wait)->base; } /* * Ready-list / ovflist state (see "Ready-list state machine" in the * top-of-file banner for the full state machine). EP_UNACTIVE_PTR is * the sentinel; these wrappers name each transition and each test so * call sites do not need to know the sentinel's value. */ /* True iff @ep is between ep_enter_scan() and ep_exit_scan(). */ static inline bool ep_is_scanning(struct eventpoll *ep) { return READ_ONCE(ep->ovflist) != EP_UNACTIVE_PTR; } /* Called by ep_start_scan(): divert ep_poll_callback() to ovflist. */ static inline void ep_enter_scan(struct eventpoll *ep) { WRITE_ONCE(ep->ovflist, NULL); } /* Called by ep_done_scan(): redirect ep_poll_callback() back to rdllist. */ static inline void ep_exit_scan(struct eventpoll *ep) { WRITE_ONCE(ep->ovflist, EP_UNACTIVE_PTR); } /* True iff @epi is currently linked on its ep's ovflist. */ static inline bool epi_on_ovflist(const struct epitem *epi) { return epi->ovflist_next != EP_UNACTIVE_PTR; } /* Mark @epi as not on any ovflist (init and post-drain). */ static inline void epi_clear_ovflist(struct epitem *epi) { epi->ovflist_next = EP_UNACTIVE_PTR; } /* True iff @ep has ready events that epoll_wait() might harvest. */ static inline bool ep_events_available(struct eventpoll *ep) { unsigned int seq = read_seqcount_begin(&ep->seq); return !list_empty_careful(&ep->rdllist) || ep_is_scanning(ep) || read_seqcount_retry(&ep->seq, seq); } #ifdef CONFIG_NET_RX_BUSY_POLL /** * busy_loop_ep_timeout - check if busy poll has timed out. The timeout value * from the epoll instance ep is preferred, but if it is not set fallback to * the system-wide global via busy_loop_timeout. * * @start_time: The start time used to compute the remaining time until timeout. * @ep: Pointer to the eventpoll context. * * Return: true if the timeout has expired, false otherwise. */ static bool busy_loop_ep_timeout(unsigned long start_time, struct eventpoll *ep) { unsigned long bp_usec = READ_ONCE(ep->busy_poll_usecs); if (bp_usec) { unsigned long end_time = start_time + bp_usec; unsigned long now = busy_loop_current_time(); return time_after(now, end_time); } else { return busy_loop_timeout(start_time); } } static bool ep_busy_loop_on(struct eventpoll *ep) { return !!READ_ONCE(ep->busy_poll_usecs) || READ_ONCE(ep->prefer_busy_poll) || net_busy_loop_on(); } static bool ep_busy_loop_end(void *p, unsigned long start_time) { struct eventpoll *ep = p; return ep_events_available(ep) || busy_loop_ep_timeout(start_time, ep); } /* * Busy poll if globally on and supporting sockets found && no events, * busy loop will return if need_resched or ep_events_available. * * we must do our busy polling with irqs enabled */ static bool ep_busy_loop(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); u16 budget = READ_ONCE(ep->busy_poll_budget); bool prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (!budget) budget = BUSY_POLL_BUDGET; if (napi_id_valid(napi_id) && ep_busy_loop_on(ep)) { napi_busy_loop(napi_id, ep_busy_loop_end, ep, prefer_busy_poll, budget); if (ep_events_available(ep)) return true; /* * Busy poll timed out. Drop NAPI ID for now, we can add * it back in when we have moved a socket with a valid NAPI * ID onto the ready list. */ if (prefer_busy_poll) napi_resume_irqs(napi_id); ep->napi_id = 0; return false; } return false; } /* * Set epoll busy poll NAPI ID from sk. */ static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { struct eventpoll *ep = epi->ep; unsigned int napi_id; struct socket *sock; struct sock *sk; if (!ep_busy_loop_on(ep)) return; sock = sock_from_file(epi->ffd.file); if (!sock) return; sk = sock->sk; if (!sk) return; napi_id = READ_ONCE(sk->sk_napi_id); /* Non-NAPI IDs can be rejected * or * Nothing to do if we already have this ID */ if (!napi_id_valid(napi_id) || napi_id == ep->napi_id) return; /* record NAPI ID for use in next busy poll */ ep->napi_id = napi_id; } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { struct eventpoll *ep = file->private_data; void __user *uarg = (void __user *)arg; struct epoll_params epoll_params; switch (cmd) { case EPIOCSPARAMS: if (copy_from_user(&epoll_params, uarg, sizeof(epoll_params))) return -EFAULT; /* pad byte must be zero */ if (epoll_params.__pad) return -EINVAL; if (epoll_params.busy_poll_usecs > S32_MAX) return -EINVAL; if (epoll_params.prefer_busy_poll > 1) return -EINVAL; if (epoll_params.busy_poll_budget > NAPI_POLL_WEIGHT && !capable(CAP_NET_ADMIN)) return -EPERM; WRITE_ONCE(ep->busy_poll_usecs, epoll_params.busy_poll_usecs); WRITE_ONCE(ep->busy_poll_budget, epoll_params.busy_poll_budget); WRITE_ONCE(ep->prefer_busy_poll, epoll_params.prefer_busy_poll); return 0; case EPIOCGPARAMS: memset(&epoll_params, 0, sizeof(epoll_params)); epoll_params.busy_poll_usecs = READ_ONCE(ep->busy_poll_usecs); epoll_params.busy_poll_budget = READ_ONCE(ep->busy_poll_budget); epoll_params.prefer_busy_poll = READ_ONCE(ep->prefer_busy_poll); if (copy_to_user(uarg, &epoll_params, sizeof(epoll_params))) return -EFAULT; return 0; default: return -ENOIOCTLCMD; } } static void ep_suspend_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_suspend_irqs(napi_id); } static void ep_resume_napi_irqs(struct eventpoll *ep) { unsigned int napi_id = READ_ONCE(ep->napi_id); if (napi_id_valid(napi_id) && READ_ONCE(ep->prefer_busy_poll)) napi_resume_irqs(napi_id); } #else static inline bool ep_busy_loop(struct eventpoll *ep) { return false; } static inline void ep_set_busy_poll_napi_id(struct epitem *epi) { } static long ep_eventpoll_bp_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } static void ep_suspend_napi_irqs(struct eventpoll *ep) { } static void ep_resume_napi_irqs(struct eventpoll *ep) { } #endif /* CONFIG_NET_RX_BUSY_POLL */ /* * As described in commit 0ccf831cb lockdep: annotate epoll * the use of wait queues used by epoll is done in a very controlled * manner. Wake ups can nest inside each other, but are never done * with the same locking. For example: * * dfd = socket(...); * efd1 = epoll_create(); * efd2 = epoll_create(); * epoll_ctl(efd1, EPOLL_CTL_ADD, dfd, ...); * epoll_ctl(efd2, EPOLL_CTL_ADD, efd1, ...); * * When a packet arrives to the device underneath "dfd", the net code will * issue a wake_up() on its poll wake list. Epoll (efd1) has installed a * callback wakeup entry on that queue, and the wake_up() performed by the * "dfd" net code will end up in ep_poll_callback(). At this point epoll * (efd1) notices that it may have some event ready, so it needs to wake up * the waiters on its poll wait list (efd2). So it calls ep_poll_safewake() * that ends up in another wake_up(), after having checked about the * recursion constraints. That are, no more than EP_MAX_NESTS, to avoid * stack blasting. * * When CONFIG_DEBUG_LOCK_ALLOC is enabled, make sure lockdep can handle * this special case of epoll. */ #ifdef CONFIG_DEBUG_LOCK_ALLOC static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, unsigned pollflags) { struct eventpoll *ep_src; unsigned long flags; u8 nests = 0; /* * To set the subclass or nesting level for spin_lock_irqsave_nested() * it might be natural to create a per-cpu nest count. However, since * we can recurse on ep->poll_wait.lock, and a non-raw spinlock can * schedule() in the -rt kernel, the per-cpu variable are no longer * protected. Thus, we are introducing a per eventpoll nest field. * If we are not being call from ep_poll_callback(), epi is NULL and * we are at the first level of nesting, 0. Otherwise, we are being * called from ep_poll_callback() and if a previous wakeup source is * not an epoll file itself, we are at depth 1 since the wakeup source * is depth 0. If the wakeup source is a previous epoll file in the * wakeup chain then we use its nests value and record ours as * nests + 1. The previous epoll file nests value is stable since its * already holding its own poll_wait.lock. */ if (epi) { if ((is_file_epoll(epi->ffd.file))) { ep_src = epi->ffd.file->private_data; nests = ep_src->nests; } else { nests = 1; } } spin_lock_irqsave_nested(&ep->poll_wait.lock, flags, nests); ep->nests = nests + 1; wake_up_locked_poll(&ep->poll_wait, EPOLLIN | pollflags); ep->nests = 0; spin_unlock_irqrestore(&ep->poll_wait.lock, flags); } #else static void ep_poll_safewake(struct eventpoll *ep, struct epitem *epi, __poll_t pollflags) { wake_up_poll(&ep->poll_wait, EPOLLIN | pollflags); } #endif static void ep_remove_wait_queue(struct eppoll_entry *pwq) { wait_queue_head_t *whead; rcu_read_lock(); /* * POLLFREE handshake, acquire side; see "POLLFREE handshake" * at the top of this file. * * A NULL load is paired with the smp_store_release(&whead, NULL) * in ep_poll_callback()'s POLLFREE branch: the teardown is * complete and we must not touch whead again. On a non-NULL load * rcu_read_lock() keeps the waitqueue memory alive (POLLFREE * firers RCU-defer the free) and whead->lock inside * remove_wait_queue() serializes us against the store side. */ whead = smp_load_acquire(&pwq->whead); if (whead) remove_wait_queue(whead, &pwq->wait); rcu_read_unlock(); } /* * This function unregisters poll callbacks from the associated file * descriptor. Must be called with "mtx" held. */ static void ep_unregister_pollwait(struct eventpoll *ep, struct epitem *epi) { struct eppoll_entry **p = &epi->pwqlist; struct eppoll_entry *pwq; while ((pwq = *p) != NULL) { *p = pwq->next; ep_remove_wait_queue(pwq); kmem_cache_free(pwq_cache, pwq); } } /* call only when ep->mtx is held */ static inline struct wakeup_source *ep_wakeup_source(struct epitem *epi) { return rcu_dereference_check(epi->ws, lockdep_is_held(&epi->ep->mtx)); } /* call only when ep->mtx is held */ static inline void ep_pm_stay_awake(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); if (ws) __pm_stay_awake(ws); } static inline bool ep_has_wakeup_source(struct epitem *epi) { return rcu_access_pointer(epi->ws) ? true : false; } /* call when ep->mtx cannot be held (ep_poll_callback) */ static inline void ep_pm_stay_awake_rcu(struct epitem *epi) { struct wakeup_source *ws; rcu_read_lock(); ws = rcu_dereference(epi->ws); if (ws) __pm_stay_awake(ws); rcu_read_unlock(); } /* * ep->mutex needs to be held because we could be hit by * eventpoll_release_file() and epoll_ctl(). */ static void ep_start_scan(struct eventpoll *ep, struct list_head *scan_batch) { /* * Steal the ready list, and re-init the original one to the * empty list. Also, set ep->ovflist to NULL so that events * happening while looping w/out locks, are not lost. We cannot * have the poll callback to queue directly on ep->rdllist, * because we want the "sproc" callback to be able to do it * in a lockless way. */ lockdep_assert_irqs_enabled(); spin_lock_irq(&ep->lock); write_seqcount_begin(&ep->seq); list_splice_init(&ep->rdllist, scan_batch); ep_enter_scan(ep); write_seqcount_end(&ep->seq); spin_unlock_irq(&ep->lock); } static void ep_done_scan(struct eventpoll *ep, struct list_head *scan_batch) { struct epitem *epi, *nepi; spin_lock_irq(&ep->lock); /* * During the time we spent inside the "sproc" callback, some * other events might have been queued by the poll callback. * We re-insert them inside the main ready-list here. */ for (nepi = READ_ONCE(ep->ovflist); (epi = nepi) != NULL; ) { nepi = epi->ovflist_next; epi_clear_ovflist(epi); /* * Skip items that the caller already returned via @scan_batch * -- the list_splice() below takes care of those. */ if (!ep_is_linked(epi)) { /* * ovflist is LIFO; list_add() head-insert here * reverses the iteration order into FIFO. */ list_add(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } } write_seqcount_begin(&ep->seq); /* Back out of scan mode; callbacks target ep->rdllist again. */ ep_exit_scan(ep); /* * Quickly re-inject items left on "scan_batch". */ list_splice(scan_batch, &ep->rdllist); write_seqcount_end(&ep->seq); __pm_relax(ep->ws); if (!list_empty(&ep->rdllist)) { if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); } spin_unlock_irq(&ep->lock); } static void ep_get(struct eventpoll *ep) { refcount_inc(&ep->refcount); } /* * Drop a reference to @ep; returns true iff it was the last, in which * case the caller is responsible for ep_free(). */ static bool ep_put(struct eventpoll *ep) { if (!refcount_dec_and_test(&ep->refcount)) return false; WARN_ON_ONCE(!RB_EMPTY_ROOT(&ep->rbr.rb_root)); return true; } static void ep_free(struct eventpoll *ep) { ep_resume_napi_irqs(ep); mutex_destroy(&ep->mtx); free_uid(ep->user); wakeup_source_unregister(ep->ws); /* ep_get_upwards_depth_proc() may still hold epi->ep under RCU */ kfree_rcu(ep, rcu); } /* * Pin @epi->ffd.file for operations that require both safe dereference * and exclusion from __fput(). * * struct file uses SLAB_TYPESAFE_BY_RCU, so a freed slot can be * reassigned at any time. The bare load of epi->ffd.file is safe here * because the caller holds ep->mtx and eventpoll_release_file() blocks * on that mutex while tearing down the epi, so the backing file * allocation cannot be freed and reused under us. An rcu_read_lock() * is therefore unnecessary for the load. * * A successful file_ref_get() additionally blocks __fput() from * starting on this file: once the refcount has reached zero it cannot * come back. ep_remove() relies on that to touch file->f_lock and * file->f_ep without racing eventpoll_release_file() (see commit * a6dc643c6931). A NULL return means __fput() is already in flight; * the caller must bail without touching the file, and * eventpoll_release_file() will clean the epi up from its side. */ static struct file *epi_fget(const struct epitem *epi) { struct file *file; file = epi->ffd.file; if (!file_ref_get(&file->f_ref)) file = NULL; return file; } /* * Takes &file->f_lock; returns with it released. */ static void ep_remove_file(struct eventpoll *ep, struct epitem *epi, struct file *file) { struct epitems_head *to_free = NULL; struct hlist_head *head; lockdep_assert_held(&ep->mtx); spin_lock(&file->f_lock); head = file->f_ep; if (hlist_is_singular_node(&epi->fllink, head)) { /* * Last watcher: publish NULL so the eventpoll_release() * fastpath in include/linux/eventpoll.h can skip the slow * path on a future __fput(). Safe because every f_ep writer * either holds a pin on @file via epi_fget() or is __fput() * itself -- see the comment in eventpoll_release(). */ WRITE_ONCE(file->f_ep, NULL); if (!is_file_epoll(file)) { struct epitems_head *v; v = container_of(head, struct epitems_head, epitems); if (!smp_load_acquire(&v->next)) to_free = v; } } hlist_del_rcu(&epi->fllink); spin_unlock(&file->f_lock); free_ephead(to_free); } static void ep_remove_epi(struct eventpoll *ep, struct epitem *epi) { lockdep_assert_held(&ep->mtx); rb_erase_cached(&epi->rbn, &ep->rbr); spin_lock_irq(&ep->lock); if (ep_is_linked(epi)) list_del_init(&epi->rdllink); spin_unlock_irq(&ep->lock); wakeup_source_unregister(ep_wakeup_source(epi)); /* * At this point it is safe to free the eventpoll item. Use the union * field epi->rcu, since we are trying to minimize the size of * 'struct epitem'. The 'rbn' field is no longer in use. Protected by * ep->mtx. The rcu read side, reverse_path_check_proc(), does not make * use of the rbn field. */ kfree_rcu(epi, rcu); percpu_counter_dec(&ep->user->epoll_watches); } /* * ep_remove variant for callers owing an additional reference to the ep */ static void ep_remove(struct eventpoll *ep, struct epitem *epi) { struct file *file __free(fput) = NULL; lockdep_assert_irqs_enabled(); lockdep_assert_held(&ep->mtx); ep_unregister_pollwait(ep, epi); /* * If we manage to grab a reference it means we're not in * eventpoll_release_file() and aren't going to be: once @file's * refcount has reached zero, file_ref_get() cannot bring it back. */ file = epi_fget(epi); if (!file) return; ep_remove_file(ep, epi, file); ep_remove_epi(ep, epi); WARN_ON_ONCE(ep_put(ep)); } /* * Pass 1 of ep_clear_and_put(): drain every epi's pwqlist. * ep_unregister_pollwait() takes each watched wait-queue head's lock, * which synchronizes with any in-flight ep_poll_callback(); after * this returns no callback can still be about to dereference an epi * on this ep. Must strictly precede ep_drain_tree() -- fusing the * two walks would let a callback queued on epi_i still fire after * epi_{i+k} had already been freed. */ static void ep_drain_pollwaits(struct eventpoll *ep) { struct rb_node *rbp; struct epitem *epi; lockdep_assert_held(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); ep_unregister_pollwait(ep, epi); cond_resched(); } } /* * Pass 2 of ep_clear_and_put(): ep_remove() every epi. The per-epi * pwqlist is already empty (ep_drain_pollwaits ran), but the rest of * ep_remove() still runs: epi_fget() pin, f_ep clear under f_lock, * rbtree erase, rdllist unlink, kfree_rcu(epi). rb_next() is captured * before each erase so the iteration is stable. * * A concurrent eventpoll_release_file() (removal path C) on a watched * file serializes with us via ep->mtx; ep_remove() transparently * hands off any epi whose file is in __fput() by bailing when * epi_fget() returns NULL, and path C will clean that epi up. */ static void ep_drain_tree(struct eventpoll *ep) { struct rb_node *rbp, *next; struct epitem *epi; lockdep_assert_held(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = next) { next = rb_next(rbp); epi = rb_entry(rbp, struct epitem, rbn); ep_remove(ep, epi); cond_resched(); } } /* * Removal path B (see "Removal paths" in the top-of-file banner): * close of the epoll fd itself, reached via ep_eventpoll_release(). * * Two passes under ep->mtx: first ep_drain_pollwaits() quiesces * in-flight callbacks, then ep_drain_tree() frees the epis. The * ep->refcount is kept > 0 across the walk by the ep file's own * share, which we drop below; ep_free() runs iff we were the last * holder after the tree drained. */ static void ep_clear_and_put(struct eventpoll *ep) { /* Release any threads blocked in poll-on-ep. */ if (waitqueue_active(&ep->poll_wait)) ep_poll_safewake(ep, NULL, 0); mutex_lock(&ep->mtx); ep_drain_pollwaits(ep); ep_drain_tree(ep); mutex_unlock(&ep->mtx); if (ep_put(ep)) ep_free(ep); } static long ep_eventpoll_ioctl(struct file *file, unsigned int cmd, unsigned long arg) { int ret; if (!is_file_epoll(file)) return -EINVAL; switch (cmd) { case EPIOCSPARAMS: case EPIOCGPARAMS: ret = ep_eventpoll_bp_ioctl(file, cmd, arg); break; default: ret = -EINVAL; break; } return ret; } static int ep_eventpoll_release(struct inode *inode, struct file *file) { struct eventpoll *ep = file->private_data; if (ep) ep_clear_and_put(ep); return 0; } static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth); static __poll_t __ep_eventpoll_poll(struct file *file, poll_table *wait, int depth) { struct eventpoll *ep = file->private_data; LIST_HEAD(scan_batch); struct epitem *epi, *tmp; poll_table pt; __poll_t res = 0; init_poll_funcptr(&pt, NULL); /* Insert inside our poll wait queue */ poll_wait(file, &ep->poll_wait, wait); /* * Proceed to find out if wanted events are really available inside * the ready list. */ mutex_lock_nested(&ep->mtx, depth); ep_start_scan(ep, &scan_batch); list_for_each_entry_safe(epi, tmp, &scan_batch, rdllink) { if (ep_item_poll(epi, &pt, depth + 1)) { res = EPOLLIN | EPOLLRDNORM; break; } else { /* * Item has been dropped into the ready list by the poll * callback, but it's not actually ready, as far as * caller requested events goes. We can remove it here. */ __pm_relax(ep_wakeup_source(epi)); list_del_init(&epi->rdllink); } } ep_done_scan(ep, &scan_batch); mutex_unlock(&ep->mtx); return res; } /* * Differs from ep_eventpoll_poll() in that internal callers already have * the ep->mtx so we need to start from depth=1, such that mutex_lock_nested() * is correctly annotated. */ static __poll_t ep_item_poll(const struct epitem *epi, poll_table *pt, int depth) { struct file *file = epi_fget(epi); __poll_t res; /* * We could return EPOLLERR | EPOLLHUP or something, but let's * treat this more as "file doesn't exist, poll didn't happen". */ if (!file) return 0; pt->_key = epi->event.events; if (!is_file_epoll(file)) res = vfs_poll(file, pt); else res = __ep_eventpoll_poll(file, pt, depth); fput(file); return res & epi->event.events; } static __poll_t ep_eventpoll_poll(struct file *file, poll_table *wait) { return __ep_eventpoll_poll(file, wait, 0); } #ifdef CONFIG_PROC_FS static void ep_show_fdinfo(struct seq_file *m, struct file *f) { struct eventpoll *ep = f->private_data; struct rb_node *rbp; mutex_lock(&ep->mtx); for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { struct epitem *epi = rb_entry(rbp, struct epitem, rbn); struct inode *inode = file_inode(epi->ffd.file); seq_printf(m, "tfd: %8d events: %8x data: %16llx " " pos:%lli ino:%llx sdev:%x\n", epi->ffd.fd, epi->event.events, (long long)epi->event.data, (long long)epi->ffd.file->f_pos, inode->i_ino, inode->i_sb->s_dev); if (seq_has_overflowed(m)) break; } mutex_unlock(&ep->mtx); } #endif /* File callbacks that implement the eventpoll file behaviour */ static const struct file_operations eventpoll_fops = { #ifdef CONFIG_PROC_FS .show_fdinfo = ep_show_fdinfo, #endif .release = ep_eventpoll_release, .poll = ep_eventpoll_poll, .llseek = noop_llseek, .unlocked_ioctl = ep_eventpoll_ioctl, .compat_ioctl = compat_ptr_ioctl, }; /* * This is called from eventpoll_release() 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. */ void eventpoll_release_file(struct file *file) { struct eventpoll *ep; struct epitem *epi; /* * A concurrent ep_remove() cannot outrace us: it pins @file via * epi_fget(), which fails once __fput() has dropped the refcount * to zero -- the path we're on. So any racing ep_remove() bails * and leaves the epi for us to clean up here. */ again: spin_lock(&file->f_lock); if (file->f_ep && file->f_ep->first) { epi = hlist_entry(file->f_ep->first, struct epitem, fllink); spin_unlock(&file->f_lock); /* * ep access is safe as we still own a reference to the ep * struct */ ep = epi->ep; mutex_lock(&ep->mtx); ep_unregister_pollwait(ep, epi); ep_remove_file(ep, epi, file); ep_remove_epi(ep, epi); mutex_unlock(&ep->mtx); if (ep_put(ep)) ep_free(ep); goto again; } spin_unlock(&file->f_lock); } static int ep_alloc(struct eventpoll **pep) { struct eventpoll *ep; ep = kzalloc_obj(*ep); if (unlikely(!ep)) return -ENOMEM; mutex_init(&ep->mtx); spin_lock_init(&ep->lock); seqcount_spinlock_init(&ep->seq, &ep->lock); init_waitqueue_head(&ep->wq); init_waitqueue_head(&ep->poll_wait); INIT_LIST_HEAD(&ep->rdllist); ep->rbr = RB_ROOT_CACHED; ep->ovflist = EP_UNACTIVE_PTR; /* not scanning */ ep->user = get_current_user(); refcount_set(&ep->refcount, 1); *pep = ep; return 0; } /* * Search the file inside the eventpoll tree. The RB tree operations * are protected by the "mtx" mutex, and ep_find() must be called with * "mtx" held. */ static struct epitem *ep_find(struct eventpoll *ep, struct epoll_key *tf) { int kcmp; struct rb_node *rbp; struct epitem *epi, *epir = NULL; for (rbp = ep->rbr.rb_root.rb_node; rbp; ) { epi = rb_entry(rbp, struct epitem, rbn); kcmp = ep_cmp_ffd(tf, &epi->ffd); if (kcmp > 0) rbp = rbp->rb_right; else if (kcmp < 0) rbp = rbp->rb_left; else { epir = epi; break; } } return epir; } /* * This is the callback that is passed to the wait queue wakeup * mechanism. It is called by the stored file descriptors when they * have events to report. */ static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key) { int pwake = 0; struct epitem *epi = ep_item_from_wait(wait); struct eventpoll *ep = epi->ep; __poll_t pollflags = key_to_poll(key); unsigned long flags; int ewake = 0; spin_lock_irqsave(&ep->lock, flags); ep_set_busy_poll_napi_id(epi); /* * If the event mask does not contain any poll(2) event, we consider the * descriptor to be disabled. This condition is likely the effect of the * EPOLLONESHOT bit that disables the descriptor when an event is received, * until the next EPOLL_CTL_MOD will be issued. */ if (!(epi->event.events & ~EP_PRIVATE_BITS)) goto out_unlock; /* * Check the events coming with the callback. At this stage, not * every device reports the events in the "key" parameter of the * callback. We need to be able to handle both cases here, hence the * test for "key" != NULL before the event match test. */ if (pollflags && !(pollflags & epi->event.events)) goto out_unlock; /* * If we are transferring events to userspace, we can hold no locks * (because we're accessing user memory, and because of linux f_op->poll() * semantics). All the events that happen during that period of time are * chained in ep->ovflist and requeued later on. */ if (ep_is_scanning(ep)) { if (!epi_on_ovflist(epi)) { epi->ovflist_next = READ_ONCE(ep->ovflist); WRITE_ONCE(ep->ovflist, epi); ep_pm_stay_awake_rcu(epi); } } else if (!ep_is_linked(epi)) { /* In the usual case, add event to ready list. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake_rcu(epi); } /* * Wake up ( if active ) both the eventpoll wait list and the ->poll() * wait list. */ if (waitqueue_active(&ep->wq)) { if ((epi->event.events & EPOLLEXCLUSIVE) && !(pollflags & POLLFREE)) { switch (pollflags & EPOLLINOUT_BITS) { case EPOLLIN: if (epi->event.events & EPOLLIN) ewake = 1; break; case EPOLLOUT: if (epi->event.events & EPOLLOUT) ewake = 1; break; case 0: ewake = 1; break; } } if (sync) wake_up_sync(&ep->wq); else wake_up(&ep->wq); } if (waitqueue_active(&ep->poll_wait)) pwake++; out_unlock: spin_unlock_irqrestore(&ep->lock, flags); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, epi, pollflags & EPOLL_URING_WAKE); if (!(epi->event.events & EPOLLEXCLUSIVE)) ewake = 1; if (pollflags & POLLFREE) { /* * POLLFREE handshake, release side; see "POLLFREE handshake" * at the top of this file. * * Unlink our wait entry with list_del_init rather than * __remove_wait_queue: a concurrent ep_remove_wait_queue() * that already loaded a non-NULL whead may still call * remove_wait_queue() after us, and list_del_init() tolerates * the second delete. * * smp_store_release(&whead, NULL) publishes the teardown to * ep_remove_wait_queue()'s smp_load_acquire(). Before this * store, a racing ep_clear_and_put() / ep_remove() reaches * ep_remove_wait_queue() which sees whead != NULL and takes * whead->lock -- the same lock held by our caller, so it * serializes behind us. Once whead is zeroed, nothing else * protects ep / epi / wait. */ list_del_init(&wait->entry); smp_store_release(&ep_pwq_from_wait(wait)->whead, NULL); } return ewake; } /* * This is the callback that is used to add our wait queue to the * target file wakeup lists. */ static void ep_ptable_queue_proc(struct file *file, wait_queue_head_t *whead, poll_table *pt) { struct ep_pqueue *epq = container_of(pt, struct ep_pqueue, pt); struct epitem *epi = epq->epi; struct eppoll_entry *pwq; if (unlikely(!epi)) // an earlier allocation has failed return; pwq = kmem_cache_alloc(pwq_cache, GFP_KERNEL); if (unlikely(!pwq)) { epq->epi = NULL; return; } init_waitqueue_func_entry(&pwq->wait, ep_poll_callback); pwq->whead = whead; pwq->base = epi; if (epi->event.events & EPOLLEXCLUSIVE) add_wait_queue_exclusive(whead, &pwq->wait); else add_wait_queue(whead, &pwq->wait); pwq->next = epi->pwqlist; epi->pwqlist = pwq; } static void ep_rbtree_insert(struct eventpoll *ep, struct epitem *epi) { int kcmp; struct rb_node **p = &ep->rbr.rb_root.rb_node, *parent = NULL; struct epitem *epic; bool leftmost = true; while (*p) { parent = *p; epic = rb_entry(parent, struct epitem, rbn); kcmp = ep_cmp_ffd(&epi->ffd, &epic->ffd); if (kcmp > 0) { p = &parent->rb_right; leftmost = false; } else p = &parent->rb_left; } rb_link_node(&epi->rbn, parent, p); rb_insert_color_cached(&epi->rbn, &ep->rbr, leftmost); } /* * Upper bound on wakeup paths emanating from any one watched file, * indexed by path depth (1..PATH_ARR_SIZE). For example, we allow * 1000 paths of length 1 from each watched file. These caps limit * the wakeup amplification that can be built from epoll-watches- * epoll topologies without rejecting reasonable usage. * * Enforced at EPOLL_CTL_ADD; CTL_MOD and CTL_DEL cannot add paths. * The running tallies live in ctx->path_count[] and are protected by * epnested_mutex. */ static const int path_limits[PATH_ARR_SIZE] = { 1000, 500, 100, 50, 10 }; static int path_count_inc(struct ep_ctl_ctx *ctx, int nests) { /* Allow an arbitrary number of depth 1 paths */ if (nests == 0) return 0; if (++ctx->path_count[nests] > path_limits[nests]) return -1; return 0; } static void path_count_init(struct ep_ctl_ctx *ctx) { int i; for (i = 0; i < PATH_ARR_SIZE; i++) ctx->path_count[i] = 0; } static int reverse_path_check_proc(struct ep_ctl_ctx *ctx, struct hlist_head *refs, int depth) { int error = 0; struct epitem *epi; if (depth > EP_MAX_NESTS) /* too deep nesting */ return -1; /* CTL_DEL can remove links here, but that can't increase our count */ hlist_for_each_entry_rcu(epi, refs, fllink) { struct hlist_head *refs = &epi->ep->refs; if (hlist_empty(refs)) error = path_count_inc(ctx, depth); else error = reverse_path_check_proc(ctx, refs, depth + 1); if (error != 0) break; } return error; } /** * reverse_path_check - ctx->tfile_check_list is a list of epitems_head * anchoring files with newly proposed links; make * sure those links don't push any path-length bucket * over its limit in path_limits[]. * @ctx: Per-do_epoll_ctl() scratch for the loop / path checks. * * Return: %zero if the proposed links don't create too many paths, * %-1 otherwise. */ static int reverse_path_check(struct ep_ctl_ctx *ctx) { struct epitems_head *p; for (p = ctx->tfile_check_list; p != EP_UNACTIVE_PTR; p = p->next) { int error; path_count_init(ctx); rcu_read_lock(); error = reverse_path_check_proc(ctx, &p->epitems, 0); rcu_read_unlock(); if (error) return error; } return 0; } static int ep_create_wakeup_source(struct epitem *epi) { struct name_snapshot n; struct wakeup_source *ws; if (!epi->ep->ws) { epi->ep->ws = wakeup_source_register(NULL, "eventpoll"); if (!epi->ep->ws) return -ENOMEM; } take_dentry_name_snapshot(&n, epi->ffd.file->f_path.dentry); ws = wakeup_source_register(NULL, n.name.name); release_dentry_name_snapshot(&n); if (!ws) return -ENOMEM; rcu_assign_pointer(epi->ws, ws); return 0; } /* rare code path, only used when EPOLL_CTL_MOD removes a wakeup source */ static noinline void ep_destroy_wakeup_source(struct epitem *epi) { struct wakeup_source *ws = ep_wakeup_source(epi); RCU_INIT_POINTER(epi->ws, NULL); /* * wait for ep_pm_stay_awake_rcu to finish, synchronize_rcu is * used internally by wakeup_source_remove, too (called by * wakeup_source_unregister), so we cannot use call_rcu */ synchronize_rcu(); wakeup_source_unregister(ws); } static int ep_attach_file(struct file *file, struct epitem *epi) { struct epitems_head *to_free = NULL; struct hlist_head *head = NULL; struct eventpoll *ep = NULL; if (is_file_epoll(file)) ep = file->private_data; if (ep) { head = &ep->refs; } else if (!READ_ONCE(file->f_ep)) { allocate: to_free = kmem_cache_zalloc(ephead_cache, GFP_KERNEL); if (!to_free) return -ENOMEM; head = &to_free->epitems; } spin_lock(&file->f_lock); if (!file->f_ep) { if (unlikely(!head)) { spin_unlock(&file->f_lock); goto allocate; } /* See eventpoll_release() for details. */ WRITE_ONCE(file->f_ep, head); to_free = NULL; } hlist_add_head_rcu(&epi->fllink, file->f_ep); spin_unlock(&file->f_lock); free_ephead(to_free); return 0; } /* * Charge the user's epoll_watches quota, allocate a fresh epitem for * @tf, and initialize its fields. The returned item is not yet linked * into any data structure; the caller must install it via * ep_register_epitem() (which takes over on success) or kmem_cache_free() * it and decrement epoll_watches on its own. * * Returns ERR_PTR(-ENOSPC) if the quota is exceeded, ERR_PTR(-ENOMEM) * if the slab allocation fails. */ static struct epitem *ep_alloc_epitem(struct eventpoll *ep, const struct epoll_event *event, struct epoll_key *tf) { struct epitem *epi; if (unlikely(percpu_counter_compare(&ep->user->epoll_watches, max_user_watches) >= 0)) return ERR_PTR(-ENOSPC); percpu_counter_inc(&ep->user->epoll_watches); epi = kmem_cache_zalloc(epi_cache, GFP_KERNEL); if (unlikely(!epi)) { percpu_counter_dec(&ep->user->epoll_watches); return ERR_PTR(-ENOMEM); } INIT_LIST_HEAD(&epi->rdllink); epi->ep = ep; epi->ffd = *tf; epi->event = *event; epi_clear_ovflist(epi); return epi; } /* * Install @epi into its target file's f_ep hlist and into @ep's rbtree, * taking one additional reference on @ep for the lifetime of the item. * * If @tep is non-NULL, the target file is itself an eventpoll; we hold * tep->mtx at subclass 1 across the attach + rbtree insert to serialize * with the target side. RB tree ops are protected by @ep->mtx, which * the caller already holds. * * On failure the epi is freed and the epoll_watches counter decremented, * matching ep_alloc_epitem()'s allocation. After this returns * successfully, ep_insert()'s later error paths use ep_remove() for * unwind; that cannot drop @ep's refcount to zero because the ep file * itself still holds the original reference. */ static int ep_register_epitem(struct ep_ctl_ctx *ctx, struct eventpoll *ep, struct epitem *epi, struct eventpoll *tep, int full_check) { struct file *tfile = epi->ffd.file; int error; if (tep) mutex_lock_nested(&tep->mtx, 1); error = ep_attach_file(tfile, epi); if (unlikely(error)) { if (tep) mutex_unlock(&tep->mtx); kmem_cache_free(epi_cache, epi); percpu_counter_dec(&ep->user->epoll_watches); return error; } if (full_check && !tep) list_file(tfile, ctx); ep_rbtree_insert(ep, epi); if (tep) mutex_unlock(&tep->mtx); ep_get(ep); return 0; } /* * Must be called with "mtx" held. */ static int ep_insert(struct ep_ctl_ctx *ctx, struct eventpoll *ep, const struct epoll_event *event, struct epoll_key *tf, int full_check) { int error, pwake = 0; __poll_t revents; struct epitem *epi; struct ep_pqueue epq; struct eventpoll *tep = NULL; if (is_file_epoll(tf->file)) tep = tf->file->private_data; lockdep_assert_irqs_enabled(); epi = ep_alloc_epitem(ep, event, tf); if (IS_ERR(epi)) return PTR_ERR(epi); error = ep_register_epitem(ctx, ep, epi, tep, full_check); if (error) return error; /* Reject the insert if the new link would create too many back-paths. */ if (unlikely(full_check && reverse_path_check(ctx))) { ep_remove(ep, epi); return -EINVAL; } if (epi->event.events & EPOLLWAKEUP) { error = ep_create_wakeup_source(epi); if (error) { ep_remove(ep, epi); return error; } } /* Initialize the poll table using the queue callback */ epq.epi = epi; init_poll_funcptr(&epq.pt, ep_ptable_queue_proc); /* * Attach the item to the poll hooks and get current event bits. * We can safely use the file* here because its usage count has * been increased by the caller of this function. Note that after * this operation completes, the poll callback can start hitting * the new item. */ revents = ep_item_poll(epi, &epq.pt, 1); /* ep_ptable_queue_proc() signals allocation failure by clearing epq.epi. */ if (unlikely(!epq.epi)) { ep_remove(ep, epi); return -ENOMEM; } /* Drop the new item onto the ready list if it is already ready. */ spin_lock_irq(&ep->lock); ep_set_busy_poll_napi_id(epi); if (revents && !ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } spin_unlock_irq(&ep->lock); /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Modify the interest event mask by dropping an event if the new mask * has a match in the current file status. Must be called with "mtx" held. */ static int ep_modify(struct eventpoll *ep, struct epitem *epi, const struct epoll_event *event) { int pwake = 0; poll_table pt; lockdep_assert_irqs_enabled(); init_poll_funcptr(&pt, NULL); /* * Set the new event interest mask before calling f_op->poll(); * otherwise we might miss an event that happens between the * f_op->poll() call and the new event set registering. */ epi->event.events = event->events; /* need barrier below */ epi->event.data = event->data; /* protected by mtx */ if (epi->event.events & EPOLLWAKEUP) { if (!ep_has_wakeup_source(epi)) ep_create_wakeup_source(epi); } else if (ep_has_wakeup_source(epi)) { ep_destroy_wakeup_source(epi); } /* * The following barrier has two effects: * * 1) Flush epi changes above to other CPUs. This ensures * we do not miss events from ep_poll_callback if an * event occurs immediately after we call f_op->poll(). * We need this because we did not take ep->lock while * changing epi above (but ep_poll_callback does take * ep->lock). * * 2) We also need to ensure we do not miss _past_ events * when calling f_op->poll(). This barrier also * pairs with the barrier in wq_has_sleeper (see * comments for wq_has_sleeper). * * This barrier will now guarantee ep_poll_callback or f_op->poll * (or both) will notice the readiness of an item. */ smp_mb(); /* * Get current event bits. We can safely use the file* here because * its usage count has been increased by the caller of this function. * If the item is "hot" and it is not registered inside the ready * list, push it inside. */ if (ep_item_poll(epi, &pt, 1)) { spin_lock_irq(&ep->lock); if (!ep_is_linked(epi)) { list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); /* Notify waiting tasks that events are available */ if (waitqueue_active(&ep->wq)) wake_up(&ep->wq); if (waitqueue_active(&ep->poll_wait)) pwake++; } spin_unlock_irq(&ep->lock); } /* We have to call this outside the lock */ if (pwake) ep_poll_safewake(ep, NULL, 0); return 0; } /* * Attempt to deliver one event for @epi into @*uevents. * * Returns 1 if an event was delivered (with *uevents advanced to the * next slot), 0 if the re-poll reported no caller-requested events * (@epi drops out of the ready list; a future callback will re-add * it), or -EFAULT if copy_to_user() faulted (in which case @epi is * re-inserted at the head of @scan_batch so ep_done_scan() merges it * back to rdllist for the next attempt). * * PM bookkeeping and level-triggered re-queue are handled here. * Caller holds ep->mtx and the scan is active. */ static int ep_deliver_event(struct eventpoll *ep, struct epitem *epi, poll_table *pt, struct epoll_event __user **uevents, struct list_head *scan_batch) { struct epoll_event __user *next; struct wakeup_source *ws; __poll_t revents; /* * Activate ep->ws before deactivating epi->ws to prevent * triggering auto-suspend here (in case we reactivate epi->ws * below). Rearranging to delay the deactivation would let * epi->ws drift out of sync with ep_is_linked(). */ ws = ep_wakeup_source(epi); if (ws) { if (ws->active) __pm_stay_awake(ep->ws); __pm_relax(ws); } list_del_init(&epi->rdllink); /* * Re-poll under ep->mtx so userspace cannot change the item * out from under us. If no caller-requested events remain, * @epi stays off the ready list; the poll callback will * re-queue it when events next appear. */ revents = ep_item_poll(epi, pt, 1); if (!revents) return 0; next = epoll_put_uevent(revents, epi->event.data, *uevents); if (!next) { /* * copy_to_user() faulted: put the item back so * ep_done_scan() splices it onto rdllist for the next * attempt. */ list_add(&epi->rdllink, scan_batch); ep_pm_stay_awake(epi); return -EFAULT; } *uevents = next; if (epi->event.events & EPOLLONESHOT) { epi->event.events &= EP_PRIVATE_BITS; } else if (!(epi->event.events & EPOLLET)) { /* * Level-triggered: re-queue so the next epoll_wait() * rechecks availability. We are the sole writer to * rdllist here -- epoll_ctl() callers are locked out * by ep->mtx, and the poll callback queues to ovflist * during scans. */ list_add_tail(&epi->rdllink, &ep->rdllist); ep_pm_stay_awake(epi); } return 1; } static int ep_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { struct epitem *epi, *tmp; LIST_HEAD(scan_batch); poll_table pt; int res = 0; /* * Always short-circuit for fatal signals to allow threads to make a * timely exit without the chance of finding more events available and * fetching repeatedly. */ if (fatal_signal_pending(current)) return -EINTR; init_poll_funcptr(&pt, NULL); mutex_lock(&ep->mtx); ep_start_scan(ep, &scan_batch); /* * We can loop without lock because we are passed a task-private * scan_batch; items cannot vanish while we hold ep->mtx. */ list_for_each_entry_safe(epi, tmp, &scan_batch, rdllink) { int delivered; if (res >= maxevents) break; delivered = ep_deliver_event(ep, epi, &pt, &events, &scan_batch); if (delivered < 0) { if (!res) res = delivered; break; } res += delivered; } ep_done_scan(ep, &scan_batch); mutex_unlock(&ep->mtx); return res; } static struct timespec64 *ep_timeout_to_timespec(struct timespec64 *to, long ms) { struct timespec64 now; if (ms < 0) return NULL; if (!ms) { to->tv_sec = 0; to->tv_nsec = 0; return to; } to->tv_sec = ms / MSEC_PER_SEC; to->tv_nsec = NSEC_PER_MSEC * (ms % MSEC_PER_SEC); ktime_get_ts64(&now); *to = timespec64_add_safe(now, *to); return to; } /* * autoremove_wake_function, but remove even on failure to wake up, because we * know that default_wake_function/ttwu will only fail if the thread is already * woken, and in that case the ep_poll loop will remove the entry anyways, not * try to reuse it. */ static int ep_autoremove_wake_function(struct wait_queue_entry *wq_entry, unsigned int mode, int sync, void *key) { int ret = default_wake_function(wq_entry, mode, sync, key); /* * Pairs with list_empty_careful in ep_poll, and ensures future loop * iterations see the cause of this wakeup. */ list_del_init_careful(&wq_entry->entry); return ret; } static int ep_try_send_events(struct eventpoll *ep, struct epoll_event __user *events, int maxevents) { int res; /* * Try to transfer events to user space. In case we get 0 events and * there's still timeout left over, we go trying again in search of * more luck. */ res = ep_send_events(ep, events, maxevents); if (res > 0) ep_suspend_napi_irqs(ep); return res; } static int ep_schedule_timeout(ktime_t *to) { if (to) return ktime_after(*to, ktime_get()); else return 1; } /** * ep_poll - Retrieves ready events, and delivers them to the caller-supplied * event buffer. * * @ep: Pointer to the eventpoll context. * @events: Pointer to the userspace buffer where the ready events should be * stored. * @maxevents: Size (in terms of number of events) of the caller event buffer. * @timeout: Maximum timeout for the ready events fetch operation, in * timespec. If the timeout is zero, the function will not block, * while if the @timeout ptr is NULL, the function will block * until at least one event has been retrieved (or an error * occurred). * * Return: the number of ready events which have been fetched, or an * error code, in case of error. */ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout) { int res, timed_out = 0; bool eavail; u64 slack = 0; wait_queue_entry_t wait; ktime_t expires, *to = NULL; lockdep_assert_irqs_enabled(); if (timeout && (timeout->tv_sec | timeout->tv_nsec)) { slack = select_estimate_accuracy(timeout); to = &expires; *to = timespec64_to_ktime(*timeout); } else if (timeout) { /* * Avoid the unnecessary trip to the wait queue loop, if the * caller specified a non blocking operation. */ timed_out = 1; } /* * This call is racy: We may or may not see events that are being added * to the ready list under the lock (e.g., in IRQ callbacks). For cases * with a non-zero timeout, this thread will check the ready list under * lock and will add to the wait queue. For cases with a zero * timeout, the user by definition should not care and will have to * recheck again. */ eavail = ep_events_available(ep); while (1) { if (eavail) { res = ep_try_send_events(ep, events, maxevents); if (res) return res; } if (timed_out) return 0; eavail = ep_busy_loop(ep); if (eavail) continue; if (signal_pending(current)) return -EINTR; /* * Internally init_wait() uses autoremove_wake_function(), * thus wait entry is removed from the wait queue on each * wakeup. Why it is important? In case of several waiters * each new wakeup will hit the next waiter, giving it the * chance to harvest new event. Otherwise wakeup can be * lost. This is also good performance-wise, because on * normal wakeup path no need to call __remove_wait_queue() * explicitly, thus ep->lock is not taken, which halts the * event delivery. * * In fact, we now use an even more aggressive function that * unconditionally removes, because we don't reuse the wait * entry between loop iterations. This lets us also avoid the * performance issue if a process is killed, causing all of its * threads to wake up without being removed normally. */ init_wait(&wait); wait.func = ep_autoremove_wake_function; spin_lock_irq(&ep->lock); /* * Barrierless variant, waitqueue_active() is called under * the same lock on wakeup ep_poll_callback() side, so it * is safe to avoid an explicit barrier. */ __set_current_state(TASK_INTERRUPTIBLE); /* * Do the final check under the lock. ep_start/done_scan() * plays with two lists (->rdllist and ->ovflist) and there * is always a race when both lists are empty for short * period of time although events are pending, so lock is * important. */ eavail = ep_events_available(ep); if (!eavail) __add_wait_queue_exclusive(&ep->wq, &wait); spin_unlock_irq(&ep->lock); if (!eavail) timed_out = !ep_schedule_timeout(to) || !schedule_hrtimeout_range(to, slack, HRTIMER_MODE_ABS); __set_current_state(TASK_RUNNING); /* * We were woken up, thus go and try to harvest some events. * If timed out and still on the wait queue, recheck eavail * carefully under lock, below. */ eavail = true; if (!list_empty_careful(&wait.entry)) { spin_lock_irq(&ep->lock); /* * If the thread timed out and is not on the wait queue, * it means that the thread was woken up after its * timeout expired before it could reacquire the lock. * Thus, when wait.entry is empty, it needs to harvest * events. */ if (timed_out) eavail = list_empty(&wait.entry); __remove_wait_queue(&ep->wq, &wait); spin_unlock_irq(&ep->lock); } } } /** * ep_loop_check_proc - verify that adding an epoll file @ep inside another * epoll file does not create closed loops, and * determine the depth of the subtree starting at @ep * * @ctx: Per-do_epoll_ctl() scratch for the loop / path checks. * @ep: the &struct eventpoll to be currently checked. * @depth: Current depth of the path being checked. * * Return: depth of the subtree, or a value bigger than EP_MAX_NESTS if we found * a loop or went too deep. */ static int ep_loop_check_proc(struct ep_ctl_ctx *ctx, struct eventpoll *ep, int depth) { int result = 0; struct rb_node *rbp; struct epitem *epi; if (ep->gen == loop_check_gen) return ep->loop_check_depth; mutex_lock_nested(&ep->mtx, depth + 1); ep->gen = loop_check_gen; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (unlikely(is_file_epoll(epi->ffd.file))) { struct eventpoll *ep_tovisit; ep_tovisit = epi->ffd.file->private_data; if (ep_tovisit == ctx->inserting_into || depth > EP_MAX_NESTS) result = EP_MAX_NESTS+1; else result = max(result, ep_loop_check_proc(ctx, ep_tovisit, depth + 1) + 1); if (result > EP_MAX_NESTS) break; } else { /* * A non-epoll leaf. Queue it for the companion * reverse_path_check() that runs after this walk so * any new links we propose don't add too many wakeup * paths. */ list_file(epi->ffd.file, ctx); } } ep->loop_check_depth = result; mutex_unlock(&ep->mtx); return result; } /* ep_get_upwards_depth_proc - determine depth of @ep when traversed upwards */ static int ep_get_upwards_depth_proc(struct eventpoll *ep, int depth) { int result = 0; struct epitem *epi; if (ep->gen == loop_check_gen) return ep->loop_check_depth; hlist_for_each_entry_rcu(epi, &ep->refs, fllink) result = max(result, ep_get_upwards_depth_proc(epi->ep, depth + 1) + 1); ep->gen = loop_check_gen; ep->loop_check_depth = result; return result; } /** * ep_loop_check - Performs a check to verify that adding an epoll file (@to) * into another epoll file (represented by @ep) does not create * closed loops or too deep chains. * * @ctx: Per-CTL_ADD scratch context. * @ep: Pointer to the epoll we are inserting into. * @to: Pointer to the epoll to be inserted. * * Return: %zero if adding the epoll @to inside the epoll @from * does not violate the constraints, or %-1 otherwise. */ static int ep_loop_check(struct ep_ctl_ctx *ctx, struct eventpoll *ep, struct eventpoll *to) { int depth, upwards_depth; ctx->inserting_into = ep; /* * Check how deep down we can get from @to, and whether it is possible * to loop up to @ep. */ depth = ep_loop_check_proc(ctx, to, 0); if (depth > EP_MAX_NESTS) return -1; /* Check how far up we can go from @ep. */ rcu_read_lock(); upwards_depth = ep_get_upwards_depth_proc(ep, 0); rcu_read_unlock(); return (depth+1+upwards_depth > EP_MAX_NESTS) ? -1 : 0; } static void clear_tfile_check_list(struct ep_ctl_ctx *ctx) { rcu_read_lock(); while (ctx->tfile_check_list != EP_UNACTIVE_PTR) { struct epitems_head *head = ctx->tfile_check_list; ctx->tfile_check_list = head->next; unlist_file(head); } rcu_read_unlock(); } /* * Open an eventpoll file descriptor. */ static int do_epoll_create(int flags) { int error; struct eventpoll *ep; /* Check the EPOLL_* constant for consistency. */ BUILD_BUG_ON(EPOLL_CLOEXEC != O_CLOEXEC); if (flags & ~EPOLL_CLOEXEC) return -EINVAL; /* * Create the internal data structure ("struct eventpoll"). */ error = ep_alloc(&ep); if (error < 0) return error; /* * Creates all the items needed to setup an eventpoll file. That is, * a file structure and a free file descriptor. */ FD_PREPARE(fdf, O_RDWR | (flags & O_CLOEXEC), anon_inode_getfile("[eventpoll]", &eventpoll_fops, ep, O_RDWR | (flags & O_CLOEXEC))); if (fdf.err) { ep_clear_and_put(ep); return fdf.err; } ep->file = fd_prepare_file(fdf); return fd_publish(fdf); } SYSCALL_DEFINE1(epoll_create1, int, flags) { return do_epoll_create(flags); } SYSCALL_DEFINE1(epoll_create, int, size) { if (size <= 0) return -EINVAL; return do_epoll_create(0); } #ifdef CONFIG_PM_SLEEP static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { if ((epev->events & EPOLLWAKEUP) && !capable(CAP_BLOCK_SUSPEND)) epev->events &= ~EPOLLWAKEUP; } #else static inline void ep_take_care_of_epollwakeup(struct epoll_event *epev) { epev->events &= ~EPOLLWAKEUP; } #endif static inline int epoll_mutex_lock(struct mutex *mutex, bool nonblock) { if (!nonblock) { mutex_lock(mutex); return 0; } return mutex_trylock(mutex) ? 0 : -EAGAIN; } /* * Acquire the locks required for do_epoll_ctl() on @ep for @op. * * Always takes ep->mtx. For EPOLL_CTL_ADD, additionally runs the * loop / path check under epnested_mutex when the topology can * change: @ep is already watched (epfile->f_ep non-NULL), @ep was * recently loop-checked (ep->gen == loop_check_gen), or @tfile is * itself an eventpoll. * * Return value encodes both outcome and lock state: * * 0 success; ep->mtx held. * 1 success; ep->mtx held AND the full check ran under * epnested_mutex (which is also still held). The value * doubles as the @full_check argument to ep_insert(). * -errno failure; no locks held. * * The caller releases what was taken with ep_ctl_unlock(ep, ret). * * Holding epnested_mutex on add is what prevents two racing * EPOLL_CTL_ADDs on different eps from building a cycle without * either walker observing it. */ static int ep_ctl_lock(struct ep_ctl_ctx *ctx, struct eventpoll *ep, int op, struct file *epfile, struct file *tfile, bool nonblock) { struct eventpoll *tep; int error; error = epoll_mutex_lock(&ep->mtx, nonblock); if (error) return error; if (op != EPOLL_CTL_ADD) return 0; if (!READ_ONCE(epfile->f_ep) && ep->gen != loop_check_gen && !is_file_epoll(tfile)) return 0; /* Full check needed: drop ep->mtx so we can take epnested_mutex. */ mutex_unlock(&ep->mtx); error = epoll_mutex_lock(&epnested_mutex, nonblock); if (error) return error; loop_check_gen++; if (is_file_epoll(tfile)) { tep = tfile->private_data; if (ep_loop_check(ctx, ep, tep) != 0) { error = -ELOOP; goto err_unlock_nested; } } error = epoll_mutex_lock(&ep->mtx, nonblock); if (error) goto err_unlock_nested; return 1; err_unlock_nested: clear_tfile_check_list(ctx); loop_check_gen++; mutex_unlock(&epnested_mutex); return error; } static void ep_ctl_unlock(struct ep_ctl_ctx *ctx, struct eventpoll *ep, int full_check) { mutex_unlock(&ep->mtx); if (full_check) { clear_tfile_check_list(ctx); loop_check_gen++; mutex_unlock(&epnested_mutex); } } int do_epoll_ctl_file(struct file *f, int op, struct epoll_key *tf, struct epoll_event *epds, bool nonblock) { int error; int full_check; struct eventpoll *ep; struct epitem *epi; struct ep_ctl_ctx ctx = { .tfile_check_list = EP_UNACTIVE_PTR, }; /* The target file descriptor must support poll */ if (!file_can_poll(tf->file)) return -EPERM; /* Check if EPOLLWAKEUP is allowed */ if (ep_op_has_event(op)) ep_take_care_of_epollwakeup(epds); /* * The @f file must itself be an eventpoll, and we do not permit * adding an epoll file descriptor inside itself. */ if (f == tf->file || !is_file_epoll(f)) return -EINVAL; /* * epoll adds to the wakeup queue at EPOLL_CTL_ADD time only, * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation. * Also, nested exclusive wakeups are not supported. */ if (ep_op_has_event(op) && (epds->events & EPOLLEXCLUSIVE)) { if (op == EPOLL_CTL_MOD) return -EINVAL; if (op == EPOLL_CTL_ADD && (is_file_epoll(tf->file) || (epds->events & ~EPOLLEXCLUSIVE_OK_BITS))) return -EINVAL; } ep = f->private_data; full_check = ep_ctl_lock(&ctx, ep, op, f, tf->file, nonblock); if (full_check < 0) return full_check; /* * Look the target up in ep's RB tree. We hold ep->mtx, so the * item stays valid until we release. */ epi = ep_find(ep, tf); error = -EINVAL; switch (op) { case EPOLL_CTL_ADD: if (!epi) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_insert(&ctx, ep, epds, tf, full_check); } else error = -EEXIST; break; case EPOLL_CTL_DEL: if (epi) { /* * The eventpoll itself is still alive: the refcount * can't go to zero here. */ ep_remove(ep, epi); error = 0; } else { error = -ENOENT; } break; case EPOLL_CTL_MOD: if (epi) { if (!(epi->event.events & EPOLLEXCLUSIVE)) { epds->events |= EPOLLERR | EPOLLHUP; error = ep_modify(ep, epi, epds); } } else error = -ENOENT; break; } ep_ctl_unlock(&ctx, ep, full_check); return error; } int do_epoll_ctl(int epfd, int op, int fd, struct epoll_event *epds, bool nonblock) { struct epoll_key efd; CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; /* Get the "struct file *" for the target file */ CLASS(fd, tf)(fd); if (fd_empty(tf)) return -EBADF; efd.file = fd_file(tf); efd.fd = fd; return do_epoll_ctl_file(fd_file(f), op, &efd, epds, nonblock); } /* * The following function implements the controller interface for * the eventpoll file that enables the insertion/removal/change of * file descriptors inside the interest set. */ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd, struct epoll_event __user *, event) { struct epoll_event epds; if (ep_op_has_event(op) && copy_from_user(&epds, event, sizeof(struct epoll_event))) return -EFAULT; return do_epoll_ctl(epfd, op, fd, &epds, false); } static int ep_check_params(struct file *file, struct epoll_event __user *evs, int maxevents) { /* The maximum number of event must be greater than zero */ if (maxevents <= 0 || maxevents > EP_MAX_EVENTS) return -EINVAL; /* Verify that the area passed by the user is writeable */ if (!access_ok(evs, maxevents * sizeof(struct epoll_event))) return -EFAULT; /* * We have to check that the file structure underneath the fd * the user passed to us _is_ an eventpoll file. */ if (!is_file_epoll(file)) return -EINVAL; return 0; } int epoll_sendevents(struct file *file, struct epoll_event __user *events, int maxevents) { struct eventpoll *ep; int ret; ret = ep_check_params(file, events, maxevents); if (unlikely(ret)) return ret; ep = file->private_data; /* * Racy call, but that's ok - it should get retried based on * poll readiness anyway. */ if (ep_events_available(ep)) return ep_try_send_events(ep, events, maxevents); return 0; } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_wait(2). */ static int do_epoll_wait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to) { struct eventpoll *ep; int ret; /* Get the "struct file *" for the eventpoll file */ CLASS(fd, f)(epfd); if (fd_empty(f)) return -EBADF; ret = ep_check_params(fd_file(f), events, maxevents); if (unlikely(ret)) return ret; /* * At this point it is safe to assume that the "private_data" contains * our own data structure. */ ep = fd_file(f)->private_data; /* Time to fish for events ... */ return ep_poll(ep, events, maxevents, to); } SYSCALL_DEFINE4(epoll_wait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout) { struct timespec64 to; return do_epoll_wait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout)); } /* * Implement the event wait interface for the eventpoll file. It is the kernel * part of the user space epoll_pwait(2). */ static int do_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *to, const sigset_t __user *sigmask, size_t sigsetsize) { int error; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ error = set_user_sigmask(sigmask, sigsetsize); if (error) return error; error = do_epoll_wait(epfd, events, maxevents, to); restore_saved_sigmask_unless(error == -EINTR); return error; } SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 to; return do_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const sigset_t __user *, sigmask, size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #ifdef CONFIG_KCMP static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff) { struct rb_node *rbp; struct epitem *epi; for (rbp = rb_first_cached(&ep->rbr); rbp; rbp = rb_next(rbp)) { epi = rb_entry(rbp, struct epitem, rbn); if (epi->ffd.fd == tfd) { if (toff == 0) return epi; else toff--; } cond_resched(); } return NULL; } struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd, unsigned long toff) { struct file *file_raw; struct eventpoll *ep; struct epitem *epi; if (!is_file_epoll(file)) return ERR_PTR(-EINVAL); ep = file->private_data; mutex_lock(&ep->mtx); epi = ep_find_tfd(ep, tfd, toff); if (epi) file_raw = epi->ffd.file; else file_raw = ERR_PTR(-ENOENT); mutex_unlock(&ep->mtx); return file_raw; } #endif /* CONFIG_KCMP */ #ifdef CONFIG_COMPAT static int do_compat_epoll_pwait(int epfd, struct epoll_event __user *events, int maxevents, struct timespec64 *timeout, const compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { long err; /* * If the caller wants a certain signal mask to be set during the wait, * we apply it here. */ err = set_compat_user_sigmask(sigmask, sigsetsize); if (err) return err; err = do_epoll_wait(epfd, events, maxevents, timeout); restore_saved_sigmask_unless(err == -EINTR); return err; } COMPAT_SYSCALL_DEFINE6(epoll_pwait, int, epfd, struct epoll_event __user *, events, int, maxevents, int, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 to; return do_compat_epoll_pwait(epfd, events, maxevents, ep_timeout_to_timespec(&to, timeout), sigmask, sigsetsize); } COMPAT_SYSCALL_DEFINE6(epoll_pwait2, int, epfd, struct epoll_event __user *, events, int, maxevents, const struct __kernel_timespec __user *, timeout, const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) { struct timespec64 ts, *to = NULL; if (timeout) { if (get_timespec64(&ts, timeout)) return -EFAULT; to = &ts; if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } return do_compat_epoll_pwait(epfd, events, maxevents, to, sigmask, sigsetsize); } #endif static int __init eventpoll_init(void) { struct sysinfo si; si_meminfo(&si); /* * Allows top 4% of lomem to be allocated for epoll watches (per user). */ max_user_watches = (((si.totalram - si.totalhigh) / 25) << PAGE_SHIFT) / EP_ITEM_COST; BUG_ON(max_user_watches < 0); /* * We can have many thousands of epitems, so prevent this from * using an extra cache line on 64-bit (and smaller) CPUs */ BUILD_BUG_ON(sizeof(void *) <= 8 && sizeof(struct epitem) > 128); /* Allocates slab cache used to allocate "struct epitem" items */ epi_cache = kmem_cache_create("eventpoll_epi", sizeof(struct epitem), 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC|SLAB_ACCOUNT, NULL); /* Allocates slab cache used to allocate "struct eppoll_entry" */ pwq_cache = kmem_cache_create("eventpoll_pwq", sizeof(struct eppoll_entry), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); epoll_sysctls_init(); ephead_cache = kmem_cache_create("ep_head", sizeof(struct epitems_head), 0, SLAB_PANIC|SLAB_ACCOUNT, NULL); return 0; } fs_initcall(eventpoll_init); |
| 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-or-later */ /* SCTP kernel Implementation * (C) Copyright IBM Corp. 2001, 2004 * Copyright (C) 1999-2001 Cisco, Motorola * * This file is part of the SCTP kernel implementation * * These are the definitions needed for the command object. * * Please send any bug reports or fixes you make to the * email address(es): * lksctp developers <linux-sctp@vger.kernel.org> * * Written or modified by: * La Monte H.P. Yarroll <piggy@acm.org> * Karl Knutson <karl@athena.chicago.il.us> * Ardelle Fan <ardelle.fan@intel.com> * Sridhar Samudrala <sri@us.ibm.com> */ #ifndef __net_sctp_command_h__ #define __net_sctp_command_h__ #include <net/sctp/constants.h> #include <net/sctp/structs.h> enum sctp_verb { SCTP_CMD_NOP = 0, /* Do nothing. */ SCTP_CMD_NEW_ASOC, /* Register a new association. */ SCTP_CMD_DELETE_TCB, /* Delete the current association. */ SCTP_CMD_NEW_STATE, /* Enter a new state. */ SCTP_CMD_REPORT_TSN, /* Record the arrival of a TSN. */ SCTP_CMD_GEN_SACK, /* Send a Selective ACK (maybe). */ SCTP_CMD_PROCESS_SACK, /* Process an inbound SACK. */ SCTP_CMD_GEN_INIT_ACK, /* Generate an INIT ACK chunk. */ SCTP_CMD_PEER_INIT, /* Process a INIT from the peer. */ SCTP_CMD_GEN_COOKIE_ECHO, /* Generate a COOKIE ECHO chunk. */ SCTP_CMD_CHUNK_ULP, /* Send a chunk to the sockets layer. */ SCTP_CMD_EVENT_ULP, /* Send a notification to the sockets layer. */ SCTP_CMD_REPLY, /* Send a chunk to our peer. */ SCTP_CMD_SEND_PKT, /* Send a full packet to our peer. */ SCTP_CMD_RETRAN, /* Mark a transport for retransmission. */ SCTP_CMD_ECN_CE, /* Do delayed CE processing. */ SCTP_CMD_ECN_ECNE, /* Do delayed ECNE processing. */ SCTP_CMD_ECN_CWR, /* Do delayed CWR processing. */ SCTP_CMD_TIMER_START, /* Start a timer. */ SCTP_CMD_TIMER_START_ONCE, /* Start a timer once */ SCTP_CMD_TIMER_RESTART, /* Restart a timer. */ SCTP_CMD_TIMER_STOP, /* Stop a timer. */ SCTP_CMD_INIT_CHOOSE_TRANSPORT, /* Choose transport for an INIT. */ SCTP_CMD_INIT_COUNTER_RESET, /* Reset init counter. */ SCTP_CMD_INIT_COUNTER_INC, /* Increment init counter. */ SCTP_CMD_INIT_RESTART, /* High level, do init timer work. */ SCTP_CMD_COOKIEECHO_RESTART, /* High level, do cookie-echo timer work. */ SCTP_CMD_INIT_FAILED, /* High level, do init failure work. */ SCTP_CMD_REPORT_DUP, /* Report a duplicate TSN. */ SCTP_CMD_STRIKE, /* Mark a strike against a transport. */ SCTP_CMD_HB_TIMERS_START, /* Start the heartbeat timers. */ SCTP_CMD_HB_TIMER_UPDATE, /* Update a heartbeat timers. */ SCTP_CMD_HB_TIMERS_STOP, /* Stop the heartbeat timers. */ SCTP_CMD_PROBE_TIMER_UPDATE, /* Update a probe timer. */ SCTP_CMD_TRANSPORT_HB_SENT, /* Reset the status of a transport. */ SCTP_CMD_TRANSPORT_IDLE, /* Do manipulations on idle transport */ SCTP_CMD_TRANSPORT_ON, /* Mark the transport as active. */ SCTP_CMD_REPORT_ERROR, /* Pass this error back out of the sm. */ SCTP_CMD_REPORT_BAD_TAG, /* Verification tags didn't match. */ SCTP_CMD_PROCESS_CTSN, /* Sideeffect from shutdown. */ SCTP_CMD_ASSOC_FAILED, /* Handle association failure. */ SCTP_CMD_DISCARD_PACKET, /* Discard the whole packet. */ SCTP_CMD_GEN_SHUTDOWN, /* Generate a SHUTDOWN chunk. */ SCTP_CMD_PURGE_OUTQUEUE, /* Purge all data waiting to be sent. */ SCTP_CMD_SETUP_T2, /* Hi-level, setup T2-shutdown parms. */ SCTP_CMD_RTO_PENDING, /* Set transport's rto_pending. */ SCTP_CMD_PART_DELIVER, /* Partial data delivery considerations. */ SCTP_CMD_RENEGE, /* Renege data on an association. */ SCTP_CMD_SETUP_T4, /* ADDIP, setup T4 RTO timer parms. */ SCTP_CMD_PROCESS_OPERR, /* Process an ERROR chunk. */ SCTP_CMD_REPORT_FWDTSN, /* Report new cumulative TSN Ack. */ SCTP_CMD_PROCESS_FWDTSN, /* Skips were reported, so process further. */ SCTP_CMD_CLEAR_INIT_TAG, /* Clears association peer's inittag. */ SCTP_CMD_DEL_NON_PRIMARY, /* Removes non-primary peer transports. */ SCTP_CMD_T3_RTX_TIMERS_STOP, /* Stops T3-rtx pending timers */ SCTP_CMD_FORCE_PRIM_RETRAN, /* Forces retrans. over primary path. */ SCTP_CMD_SET_SK_ERR, /* Set sk_err */ SCTP_CMD_ASSOC_CHANGE, /* generate and send assoc_change event */ SCTP_CMD_ADAPTATION_IND, /* generate and send adaptation event */ SCTP_CMD_PEER_NO_AUTH, /* generate and send authentication event */ SCTP_CMD_ASSOC_SHKEY, /* generate the association shared keys */ SCTP_CMD_T1_RETRAN, /* Mark for retransmission after T1 timeout */ SCTP_CMD_UPDATE_INITTAG, /* Update peer inittag */ SCTP_CMD_SEND_MSG, /* Send the whole use message */ SCTP_CMD_PURGE_ASCONF_QUEUE, /* Purge all asconf queues.*/ SCTP_CMD_SET_ASOC, /* Restore association context */ SCTP_CMD_LAST }; /* How many commands can you put in an struct sctp_cmd_seq? * This is a rather arbitrary number, ideally derived from a careful * analysis of the state functions, but in reality just taken from * thin air in the hopes othat we don't trigger a kernel panic. */ #define SCTP_MAX_NUM_COMMANDS 20 union sctp_arg { void *zero_all; /* Set to NULL to clear the entire union */ __s32 i32; __u32 u32; __be32 be32; __u16 u16; __u8 u8; int error; __be16 err; enum sctp_state state; enum sctp_event_timeout to; struct sctp_chunk *chunk; struct sctp_association *asoc; struct sctp_transport *transport; struct sctp_bind_addr *bp; struct sctp_init_chunk *init; struct sctp_ulpevent *ulpevent; struct sctp_packet *packet; struct sctp_sackhdr *sackh; struct sctp_datamsg *msg; }; /* We are simulating ML type constructors here. * * SCTP_ARG_CONSTRUCTOR(NAME, TYPE, ELT) builds a function called * SCTP_NAME() which takes an argument of type TYPE and returns an * union sctp_arg. It does this by inserting the sole argument into * the ELT union element of a local union sctp_arg. * * E.g., SCTP_ARG_CONSTRUCTOR(I32, __s32, i32) builds SCTP_I32(arg), * which takes an __s32 and returns a union sctp_arg containing the * __s32. So, after foo = SCTP_I32(arg), foo.i32 == arg. */ #define SCTP_ARG_CONSTRUCTOR(name, type, elt) \ static inline union sctp_arg \ SCTP_## name (type arg) \ { union sctp_arg retval;\ retval.zero_all = NULL;\ retval.elt = arg;\ return retval;\ } SCTP_ARG_CONSTRUCTOR(I32, __s32, i32) SCTP_ARG_CONSTRUCTOR(U32, __u32, u32) SCTP_ARG_CONSTRUCTOR(BE32, __be32, be32) SCTP_ARG_CONSTRUCTOR(U16, __u16, u16) SCTP_ARG_CONSTRUCTOR(U8, __u8, u8) SCTP_ARG_CONSTRUCTOR(ERROR, int, error) SCTP_ARG_CONSTRUCTOR(PERR, __be16, err) /* protocol error */ SCTP_ARG_CONSTRUCTOR(STATE, enum sctp_state, state) SCTP_ARG_CONSTRUCTOR(TO, enum sctp_event_timeout, to) SCTP_ARG_CONSTRUCTOR(CHUNK, struct sctp_chunk *, chunk) SCTP_ARG_CONSTRUCTOR(ASOC, struct sctp_association *, asoc) SCTP_ARG_CONSTRUCTOR(TRANSPORT, struct sctp_transport *, transport) SCTP_ARG_CONSTRUCTOR(BA, struct sctp_bind_addr *, bp) SCTP_ARG_CONSTRUCTOR(PEER_INIT, struct sctp_init_chunk *, init) SCTP_ARG_CONSTRUCTOR(ULPEVENT, struct sctp_ulpevent *, ulpevent) SCTP_ARG_CONSTRUCTOR(PACKET, struct sctp_packet *, packet) SCTP_ARG_CONSTRUCTOR(SACKH, struct sctp_sackhdr *, sackh) SCTP_ARG_CONSTRUCTOR(DATAMSG, struct sctp_datamsg *, msg) static inline union sctp_arg SCTP_FORCE(void) { return SCTP_I32(1); } static inline union sctp_arg SCTP_NOFORCE(void) { return SCTP_I32(0); } static inline union sctp_arg SCTP_NULL(void) { union sctp_arg retval; retval.zero_all = NULL; return retval; } struct sctp_cmd { union sctp_arg obj; enum sctp_verb verb; }; struct sctp_cmd_seq { struct sctp_cmd cmds[SCTP_MAX_NUM_COMMANDS]; struct sctp_cmd *last_used_slot; struct sctp_cmd *next_cmd; }; /* Initialize a block of memory as a command sequence. * Return 0 if the initialization fails. */ static inline int sctp_init_cmd_seq(struct sctp_cmd_seq *seq) { /* cmds[] is filled backwards to simplify the overflow BUG() check */ seq->last_used_slot = seq->cmds + SCTP_MAX_NUM_COMMANDS; seq->next_cmd = seq->last_used_slot; return 1; /* We always succeed. */ } /* Add a command to an struct sctp_cmd_seq. * * Use the SCTP_* constructors defined by SCTP_ARG_CONSTRUCTOR() above * to wrap data which goes in the obj argument. */ static inline void sctp_add_cmd_sf(struct sctp_cmd_seq *seq, enum sctp_verb verb, union sctp_arg obj) { struct sctp_cmd *cmd = seq->last_used_slot - 1; BUG_ON(cmd < seq->cmds); cmd->verb = verb; cmd->obj = obj; seq->last_used_slot = cmd; } /* Return the next command structure in an sctp_cmd_seq. * Return NULL at the end of the sequence. */ static inline struct sctp_cmd *sctp_next_cmd(struct sctp_cmd_seq *seq) { if (seq->next_cmd <= seq->last_used_slot) return NULL; return --seq->next_cmd; } #endif /* __net_sctp_command_h__ */ |
| 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 | // SPDX-License-Identifier: GPL-2.0-only /* * async.c: Asynchronous function calls for boot performance * * (C) Copyright 2009 Intel Corporation * Author: Arjan van de Ven <arjan@linux.intel.com> */ /* Goals and Theory of Operation The primary goal of this feature is to reduce the kernel boot time, by doing various independent hardware delays and discovery operations decoupled and not strictly serialized. More specifically, the asynchronous function call concept allows certain operations (primarily during system boot) to happen asynchronously, out of order, while these operations still have their externally visible parts happen sequentially and in-order. (not unlike how out-of-order CPUs retire their instructions in order) Key to the asynchronous function call implementation is the concept of a "sequence cookie" (which, although it has an abstracted type, can be thought of as a monotonically incrementing number). The async core will assign each scheduled event such a sequence cookie and pass this to the called functions. The asynchronously called function should before doing a globally visible operation, such as registering device numbers, call the async_synchronize_cookie() function and pass in its own cookie. The async_synchronize_cookie() function will make sure that all asynchronous operations that were scheduled prior to the operation corresponding with the cookie have completed. Subsystem/driver initialization code that scheduled asynchronous probe functions, but which shares global resources with other drivers/subsystems that do not use the asynchronous call feature, need to do a full synchronization with the async_synchronize_full() function, before returning from their init function. This is to maintain strict ordering between the asynchronous and synchronous parts of the kernel. */ #include <linux/async.h> #include <linux/atomic.h> #include <linux/export.h> #include <linux/ktime.h> #include <linux/pid.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/wait.h> #include <linux/workqueue.h> #include "workqueue_internal.h" static async_cookie_t next_cookie = 1; #define MAX_WORK 32768 #define ASYNC_COOKIE_MAX ULLONG_MAX /* infinity cookie */ static LIST_HEAD(async_global_pending); /* pending from all registered doms */ static ASYNC_DOMAIN(async_dfl_domain); static DEFINE_SPINLOCK(async_lock); static struct workqueue_struct *async_wq; struct async_entry { struct list_head domain_list; struct list_head global_list; struct work_struct work; async_cookie_t cookie; async_func_t func; void *data; struct async_domain *domain; }; static DECLARE_WAIT_QUEUE_HEAD(async_done); static atomic_t entry_count; static long long microseconds_since(ktime_t start) { ktime_t now = ktime_get(); return ktime_to_ns(ktime_sub(now, start)) >> 10; } static async_cookie_t lowest_in_progress(struct async_domain *domain) { struct async_entry *first = NULL; async_cookie_t ret = ASYNC_COOKIE_MAX; unsigned long flags; spin_lock_irqsave(&async_lock, flags); if (domain) { if (!list_empty(&domain->pending)) first = list_first_entry(&domain->pending, struct async_entry, domain_list); } else { if (!list_empty(&async_global_pending)) first = list_first_entry(&async_global_pending, struct async_entry, global_list); } if (first) ret = first->cookie; spin_unlock_irqrestore(&async_lock, flags); return ret; } /* * pick the first pending entry and run it */ static void async_run_entry_fn(struct work_struct *work) { struct async_entry *entry = container_of(work, struct async_entry, work); unsigned long flags; ktime_t calltime; /* 1) run (and print duration) */ pr_debug("calling %lli_%pS @ %i\n", (long long)entry->cookie, entry->func, task_pid_nr(current)); calltime = ktime_get(); entry->func(entry->data, entry->cookie); pr_debug("initcall %lli_%pS returned after %lld usecs\n", (long long)entry->cookie, entry->func, microseconds_since(calltime)); /* 2) remove self from the pending queues */ spin_lock_irqsave(&async_lock, flags); list_del_init(&entry->domain_list); list_del_init(&entry->global_list); /* 3) free the entry */ kfree(entry); atomic_dec(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* 4) wake up any waiters */ wake_up(&async_done); } static async_cookie_t __async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain, struct async_entry *entry) { async_cookie_t newcookie; unsigned long flags; INIT_LIST_HEAD(&entry->domain_list); INIT_LIST_HEAD(&entry->global_list); INIT_WORK(&entry->work, async_run_entry_fn); entry->func = func; entry->data = data; entry->domain = domain; spin_lock_irqsave(&async_lock, flags); /* allocate cookie and queue */ newcookie = entry->cookie = next_cookie++; list_add_tail(&entry->domain_list, &domain->pending); if (domain->registered) list_add_tail(&entry->global_list, &async_global_pending); atomic_inc(&entry_count); spin_unlock_irqrestore(&async_lock, flags); /* schedule for execution */ queue_work_node(node, async_wq, &entry->work); return newcookie; } /** * async_schedule_node_domain - NUMA specific version of async_schedule_domain * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * @domain: the domain * * Returns an async_cookie_t that may be used for checkpointing later. * @domain may be used in the async_synchronize_*_domain() functions to * wait within a certain synchronization domain rather than globally. * * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node_domain(async_func_t func, void *data, int node, struct async_domain *domain) { struct async_entry *entry; unsigned long flags; async_cookie_t newcookie; /* allow irq-off callers */ entry = kzalloc_obj(struct async_entry, GFP_ATOMIC); /* * If we're out of memory or if there's too much work * pending already, we execute synchronously. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); spin_lock_irqsave(&async_lock, flags); newcookie = next_cookie++; spin_unlock_irqrestore(&async_lock, flags); /* low on memory.. run synchronously */ func(data, newcookie); return newcookie; } return __async_schedule_node_domain(func, data, node, domain, entry); } EXPORT_SYMBOL_GPL(async_schedule_node_domain); /** * async_schedule_node - NUMA specific version of async_schedule * @func: function to execute asynchronously * @data: data pointer to pass to the function * @node: NUMA node that we want to schedule this on or close to * * Returns an async_cookie_t that may be used for checkpointing later. * Note: This function may be called from atomic or non-atomic contexts. * * The node requested will be honored on a best effort basis. If the node * has no CPUs associated with it then the work is distributed among all * available CPUs. */ async_cookie_t async_schedule_node(async_func_t func, void *data, int node) { return async_schedule_node_domain(func, data, node, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_schedule_node); /** * async_schedule_dev_nocall - A simplified variant of async_schedule_dev() * @func: function to execute asynchronously * @dev: device argument to be passed to function * * @dev is used as both the argument for the function and to provide NUMA * context for where to run the function. * * If the asynchronous execution of @func is scheduled successfully, return * true. Otherwise, do nothing and return false, unlike async_schedule_dev() * that will run the function synchronously then. */ bool async_schedule_dev_nocall(async_func_t func, struct device *dev) { struct async_entry *entry; entry = kzalloc_obj(struct async_entry); /* Give up if there is no memory or too much work. */ if (!entry || atomic_read(&entry_count) > MAX_WORK) { kfree(entry); return false; } __async_schedule_node_domain(func, dev, dev_to_node(dev), &async_dfl_domain, entry); return true; } /** * async_synchronize_full - synchronize all asynchronous function calls * * This function waits until all asynchronous function calls have been done. */ void async_synchronize_full(void) { async_synchronize_full_domain(NULL); } EXPORT_SYMBOL_GPL(async_synchronize_full); /** * async_synchronize_full_domain - synchronize all asynchronous function within a certain domain * @domain: the domain to synchronize * * This function waits until all asynchronous function calls for the * synchronization domain specified by @domain have been done. */ void async_synchronize_full_domain(struct async_domain *domain) { async_synchronize_cookie_domain(ASYNC_COOKIE_MAX, domain); } EXPORT_SYMBOL_GPL(async_synchronize_full_domain); /** * async_synchronize_cookie_domain - synchronize asynchronous function calls within a certain domain with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * @domain: the domain to synchronize (%NULL for all registered domains) * * This function waits until all asynchronous function calls for the * synchronization domain specified by @domain submitted prior to @cookie * have been done. */ void async_synchronize_cookie_domain(async_cookie_t cookie, struct async_domain *domain) { ktime_t starttime; pr_debug("async_waiting @ %i\n", task_pid_nr(current)); starttime = ktime_get(); wait_event(async_done, lowest_in_progress(domain) >= cookie); pr_debug("async_continuing @ %i after %lli usec\n", task_pid_nr(current), microseconds_since(starttime)); } EXPORT_SYMBOL_GPL(async_synchronize_cookie_domain); /** * async_synchronize_cookie - synchronize asynchronous function calls with cookie checkpointing * @cookie: async_cookie_t to use as checkpoint * * This function waits until all asynchronous function calls prior to @cookie * have been done. */ void async_synchronize_cookie(async_cookie_t cookie) { async_synchronize_cookie_domain(cookie, &async_dfl_domain); } EXPORT_SYMBOL_GPL(async_synchronize_cookie); /** * current_is_async - is %current an async worker task? * * Returns %true if %current is an async worker task. */ bool current_is_async(void) { struct worker *worker = current_wq_worker(); return worker && worker->current_func == async_run_entry_fn; } EXPORT_SYMBOL_GPL(current_is_async); void __init async_init(void) { /* * Async can schedule a number of interdependent work items. However, * unbound workqueues can handle only upto min_active interdependent * work items. The default min_active of 8 isn't sufficient for async * and can lead to stalls. Let's use a dedicated workqueue with raised * min_active. */ async_wq = alloc_workqueue("async", WQ_UNBOUND, 0); BUG_ON(!async_wq); workqueue_set_min_active(async_wq, WQ_DFL_ACTIVE); } |
| 2 2 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008-2011, Intel Corporation. * * Description: Data Center Bridging netlink interface * Author: Lucy Liu <lucy.liu@intel.com> */ #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/slab.h> #include <net/netlink.h> #include <net/rtnetlink.h> #include <linux/dcbnl.h> #include <net/dcbevent.h> #include <linux/rtnetlink.h> #include <linux/init.h> #include <net/sock.h> /* Data Center Bridging (DCB) is a collection of Ethernet enhancements * intended to allow network traffic with differing requirements * (highly reliable, no drops vs. best effort vs. low latency) to operate * and co-exist on Ethernet. Current DCB features are: * * Enhanced Transmission Selection (aka Priority Grouping [PG]) - provides a * framework for assigning bandwidth guarantees to traffic classes. * * Priority-based Flow Control (PFC) - provides a flow control mechanism which * can work independently for each 802.1p priority. * * Congestion Notification - provides a mechanism for end-to-end congestion * control for protocols which do not have built-in congestion management. * * More information about the emerging standards for these Ethernet features * can be found at: http://www.ieee802.org/1/pages/dcbridges.html * * This file implements an rtnetlink interface to allow configuration of DCB * features for capable devices. */ /**************** DCB attribute policies *************************************/ /* DCB netlink attributes policy */ static const struct nla_policy dcbnl_rtnl_policy[DCB_ATTR_MAX + 1] = { [DCB_ATTR_IFNAME] = {.type = NLA_NUL_STRING, .len = IFNAMSIZ - 1}, [DCB_ATTR_STATE] = {.type = NLA_U8}, [DCB_ATTR_PFC_CFG] = {.type = NLA_NESTED}, [DCB_ATTR_PG_CFG] = {.type = NLA_NESTED}, [DCB_ATTR_SET_ALL] = {.type = NLA_U8}, [DCB_ATTR_PERM_HWADDR] = {.type = NLA_FLAG}, [DCB_ATTR_CAP] = {.type = NLA_NESTED}, [DCB_ATTR_PFC_STATE] = {.type = NLA_U8}, [DCB_ATTR_BCN] = {.type = NLA_NESTED}, [DCB_ATTR_APP] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE] = {.type = NLA_NESTED}, [DCB_ATTR_DCBX] = {.type = NLA_U8}, [DCB_ATTR_FEATCFG] = {.type = NLA_NESTED}, }; /* DCB priority flow control to User Priority nested attributes */ static const struct nla_policy dcbnl_pfc_up_nest[DCB_PFC_UP_ATTR_MAX + 1] = { [DCB_PFC_UP_ATTR_0] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_1] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_2] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_3] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_4] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_5] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_6] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_7] = {.type = NLA_U8}, [DCB_PFC_UP_ATTR_ALL] = {.type = NLA_FLAG}, }; /* DCB priority grouping nested attributes */ static const struct nla_policy dcbnl_pg_nest[DCB_PG_ATTR_MAX + 1] = { [DCB_PG_ATTR_TC_0] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_1] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_2] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_3] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_4] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_5] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_6] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_7] = {.type = NLA_NESTED}, [DCB_PG_ATTR_TC_ALL] = {.type = NLA_NESTED}, [DCB_PG_ATTR_BW_ID_0] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_1] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_2] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_3] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_4] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_5] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_6] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_7] = {.type = NLA_U8}, [DCB_PG_ATTR_BW_ID_ALL] = {.type = NLA_FLAG}, }; /* DCB traffic class nested attributes. */ static const struct nla_policy dcbnl_tc_param_nest[DCB_TC_ATTR_PARAM_MAX + 1] = { [DCB_TC_ATTR_PARAM_PGID] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_UP_MAPPING] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_STRICT_PRIO] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_BW_PCT] = {.type = NLA_U8}, [DCB_TC_ATTR_PARAM_ALL] = {.type = NLA_FLAG}, }; /* DCB capabilities nested attributes. */ static const struct nla_policy dcbnl_cap_nest[DCB_CAP_ATTR_MAX + 1] = { [DCB_CAP_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_CAP_ATTR_PG] = {.type = NLA_U8}, [DCB_CAP_ATTR_PFC] = {.type = NLA_U8}, [DCB_CAP_ATTR_UP2TC] = {.type = NLA_U8}, [DCB_CAP_ATTR_PG_TCS] = {.type = NLA_U8}, [DCB_CAP_ATTR_PFC_TCS] = {.type = NLA_U8}, [DCB_CAP_ATTR_GSP] = {.type = NLA_U8}, [DCB_CAP_ATTR_BCN] = {.type = NLA_U8}, [DCB_CAP_ATTR_DCBX] = {.type = NLA_U8}, }; /* DCB capabilities nested attributes. */ static const struct nla_policy dcbnl_numtcs_nest[DCB_NUMTCS_ATTR_MAX + 1] = { [DCB_NUMTCS_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_NUMTCS_ATTR_PG] = {.type = NLA_U8}, [DCB_NUMTCS_ATTR_PFC] = {.type = NLA_U8}, }; /* DCB BCN nested attributes. */ static const struct nla_policy dcbnl_bcn_nest[DCB_BCN_ATTR_MAX + 1] = { [DCB_BCN_ATTR_RP_0] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_1] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_2] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_3] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_4] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_5] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_6] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_7] = {.type = NLA_U8}, [DCB_BCN_ATTR_RP_ALL] = {.type = NLA_FLAG}, [DCB_BCN_ATTR_BCNA_0] = {.type = NLA_U32}, [DCB_BCN_ATTR_BCNA_1] = {.type = NLA_U32}, [DCB_BCN_ATTR_ALPHA] = {.type = NLA_U32}, [DCB_BCN_ATTR_BETA] = {.type = NLA_U32}, [DCB_BCN_ATTR_GD] = {.type = NLA_U32}, [DCB_BCN_ATTR_GI] = {.type = NLA_U32}, [DCB_BCN_ATTR_TMAX] = {.type = NLA_U32}, [DCB_BCN_ATTR_TD] = {.type = NLA_U32}, [DCB_BCN_ATTR_RMIN] = {.type = NLA_U32}, [DCB_BCN_ATTR_W] = {.type = NLA_U32}, [DCB_BCN_ATTR_RD] = {.type = NLA_U32}, [DCB_BCN_ATTR_RU] = {.type = NLA_U32}, [DCB_BCN_ATTR_WRTT] = {.type = NLA_U32}, [DCB_BCN_ATTR_RI] = {.type = NLA_U32}, [DCB_BCN_ATTR_C] = {.type = NLA_U32}, [DCB_BCN_ATTR_ALL] = {.type = NLA_FLAG}, }; /* DCB APP nested attributes. */ static const struct nla_policy dcbnl_app_nest[DCB_APP_ATTR_MAX + 1] = { [DCB_APP_ATTR_IDTYPE] = {.type = NLA_U8}, [DCB_APP_ATTR_ID] = {.type = NLA_U16}, [DCB_APP_ATTR_PRIORITY] = {.type = NLA_U8}, }; /* IEEE 802.1Qaz nested attributes. */ static const struct nla_policy dcbnl_ieee_policy[DCB_ATTR_IEEE_MAX + 1] = { [DCB_ATTR_IEEE_ETS] = {.len = sizeof(struct ieee_ets)}, [DCB_ATTR_IEEE_PFC] = {.len = sizeof(struct ieee_pfc)}, [DCB_ATTR_IEEE_APP_TABLE] = {.type = NLA_NESTED}, [DCB_ATTR_IEEE_MAXRATE] = {.len = sizeof(struct ieee_maxrate)}, [DCB_ATTR_IEEE_QCN] = {.len = sizeof(struct ieee_qcn)}, [DCB_ATTR_IEEE_QCN_STATS] = {.len = sizeof(struct ieee_qcn_stats)}, [DCB_ATTR_DCB_BUFFER] = {.len = sizeof(struct dcbnl_buffer)}, [DCB_ATTR_DCB_APP_TRUST_TABLE] = {.type = NLA_NESTED}, }; /* DCB number of traffic classes nested attributes. */ static const struct nla_policy dcbnl_featcfg_nest[DCB_FEATCFG_ATTR_MAX + 1] = { [DCB_FEATCFG_ATTR_ALL] = {.type = NLA_FLAG}, [DCB_FEATCFG_ATTR_PG] = {.type = NLA_U8}, [DCB_FEATCFG_ATTR_PFC] = {.type = NLA_U8}, [DCB_FEATCFG_ATTR_APP] = {.type = NLA_U8}, }; static LIST_HEAD(dcb_app_list); static LIST_HEAD(dcb_rewr_list); static DEFINE_SPINLOCK(dcb_lock); static enum ieee_attrs_app dcbnl_app_attr_type_get(u8 selector) { switch (selector) { case IEEE_8021QAZ_APP_SEL_ETHERTYPE: case IEEE_8021QAZ_APP_SEL_STREAM: case IEEE_8021QAZ_APP_SEL_DGRAM: case IEEE_8021QAZ_APP_SEL_ANY: case IEEE_8021QAZ_APP_SEL_DSCP: return DCB_ATTR_IEEE_APP; case DCB_APP_SEL_PCP: return DCB_ATTR_DCB_APP; default: return DCB_ATTR_IEEE_APP_UNSPEC; } } static bool dcbnl_app_attr_type_validate(enum ieee_attrs_app type) { switch (type) { case DCB_ATTR_IEEE_APP: case DCB_ATTR_DCB_APP: return true; default: return false; } } static bool dcbnl_app_selector_validate(enum ieee_attrs_app type, u8 selector) { return dcbnl_app_attr_type_get(selector) == type; } static struct sk_buff *dcbnl_newmsg(int type, u8 cmd, u32 port, u32 seq, u32 flags, struct nlmsghdr **nlhp) { struct sk_buff *skb; struct dcbmsg *dcb; struct nlmsghdr *nlh; skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return NULL; nlh = nlmsg_put(skb, port, seq, type, sizeof(*dcb), flags); BUG_ON(!nlh); dcb = nlmsg_data(nlh); dcb->dcb_family = AF_UNSPEC; dcb->cmd = cmd; dcb->dcb_pad = 0; if (nlhp) *nlhp = nlh; return skb; } static int dcbnl_getstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { /* if (!tb[DCB_ATTR_STATE] || !netdev->dcbnl_ops->getstate) */ if (!netdev->dcbnl_ops->getstate) return -EOPNOTSUPP; return nla_put_u8(skb, DCB_ATTR_STATE, netdev->dcbnl_ops->getstate(netdev)); } static int dcbnl_getpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1], *nest; u8 value; int ret; int i; int getall = 0; if (!tb[DCB_ATTR_PFC_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->getpfccfg) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX, tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_PFC_CFG); if (!nest) return -EMSGSIZE; if (data[DCB_PFC_UP_ATTR_ALL]) getall = 1; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { if (!getall && !data[i]) continue; netdev->dcbnl_ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); return ret; } } nla_nest_end(skb, nest); return 0; } static int dcbnl_getperm_hwaddr(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 perm_addr[MAX_ADDR_LEN]; if (!netdev->dcbnl_ops->getpermhwaddr) return -EOPNOTSUPP; memset(perm_addr, 0, sizeof(perm_addr)); netdev->dcbnl_ops->getpermhwaddr(netdev, perm_addr); return nla_put(skb, DCB_ATTR_PERM_HWADDR, sizeof(perm_addr), perm_addr); } static int dcbnl_getcap(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_CAP_ATTR_MAX + 1], *nest; u8 value; int ret; int i; int getall = 0; if (!tb[DCB_ATTR_CAP]) return -EINVAL; if (!netdev->dcbnl_ops->getcap) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_CAP_ATTR_MAX, tb[DCB_ATTR_CAP], dcbnl_cap_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_CAP); if (!nest) return -EMSGSIZE; if (data[DCB_CAP_ATTR_ALL]) getall = 1; for (i = DCB_CAP_ATTR_ALL+1; i <= DCB_CAP_ATTR_MAX; i++) { if (!getall && !data[i]) continue; if (!netdev->dcbnl_ops->getcap(netdev, i, &value)) { ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); return ret; } } } nla_nest_end(skb, nest); return 0; } static int dcbnl_getnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1], *nest; u8 value; int ret; int i; int getall = 0; if (!tb[DCB_ATTR_NUMTCS]) return -EINVAL; if (!netdev->dcbnl_ops->getnumtcs) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS], dcbnl_numtcs_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_NUMTCS); if (!nest) return -EMSGSIZE; if (data[DCB_NUMTCS_ATTR_ALL]) getall = 1; for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { if (!getall && !data[i]) continue; ret = netdev->dcbnl_ops->getnumtcs(netdev, i, &value); if (!ret) { ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); return ret; } } else return -EINVAL; } nla_nest_end(skb, nest); return 0; } static int dcbnl_setnumtcs(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_NUMTCS_ATTR_MAX + 1]; int ret; u8 value; int i; if (!tb[DCB_ATTR_NUMTCS]) return -EINVAL; if (!netdev->dcbnl_ops->setnumtcs) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_NUMTCS_ATTR_MAX, tb[DCB_ATTR_NUMTCS], dcbnl_numtcs_nest, NULL); if (ret) return ret; for (i = DCB_NUMTCS_ATTR_ALL+1; i <= DCB_NUMTCS_ATTR_MAX; i++) { if (data[i] == NULL) continue; value = nla_get_u8(data[i]); ret = netdev->dcbnl_ops->setnumtcs(netdev, i, value); if (ret) break; } return nla_put_u8(skb, DCB_ATTR_NUMTCS, !!ret); } static int dcbnl_getpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { if (!netdev->dcbnl_ops->getpfcstate) return -EOPNOTSUPP; return nla_put_u8(skb, DCB_ATTR_PFC_STATE, netdev->dcbnl_ops->getpfcstate(netdev)); } static int dcbnl_setpfcstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 value; if (!tb[DCB_ATTR_PFC_STATE]) return -EINVAL; if (!netdev->dcbnl_ops->setpfcstate) return -EOPNOTSUPP; value = nla_get_u8(tb[DCB_ATTR_PFC_STATE]); netdev->dcbnl_ops->setpfcstate(netdev, value); return nla_put_u8(skb, DCB_ATTR_PFC_STATE, 0); } static int dcbnl_getapp(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *app_nest; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; u16 id; u8 up, idtype; int ret; if (!tb[DCB_ATTR_APP]) return -EINVAL; ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], dcbnl_app_nest, NULL); if (ret) return ret; /* all must be non-null */ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || (!app_tb[DCB_APP_ATTR_ID])) return -EINVAL; /* either by eth type or by socket number */ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && (idtype != DCB_APP_IDTYPE_PORTNUM)) return -EINVAL; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); if (netdev->dcbnl_ops->getapp) { ret = netdev->dcbnl_ops->getapp(netdev, idtype, id); if (ret < 0) return ret; else up = ret; } else { struct dcb_app app = { .selector = idtype, .protocol = id, }; up = dcb_getapp(netdev, &app); } app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP); if (!app_nest) return -EMSGSIZE; ret = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, idtype); if (ret) goto out_cancel; ret = nla_put_u16(skb, DCB_APP_ATTR_ID, id); if (ret) goto out_cancel; ret = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, up); if (ret) goto out_cancel; nla_nest_end(skb, app_nest); return 0; out_cancel: nla_nest_cancel(skb, app_nest); return ret; } static int dcbnl_setapp(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { int ret; u16 id; u8 up, idtype; struct nlattr *app_tb[DCB_APP_ATTR_MAX + 1]; if (!tb[DCB_ATTR_APP]) return -EINVAL; ret = nla_parse_nested_deprecated(app_tb, DCB_APP_ATTR_MAX, tb[DCB_ATTR_APP], dcbnl_app_nest, NULL); if (ret) return ret; /* all must be non-null */ if ((!app_tb[DCB_APP_ATTR_IDTYPE]) || (!app_tb[DCB_APP_ATTR_ID]) || (!app_tb[DCB_APP_ATTR_PRIORITY])) return -EINVAL; /* either by eth type or by socket number */ idtype = nla_get_u8(app_tb[DCB_APP_ATTR_IDTYPE]); if ((idtype != DCB_APP_IDTYPE_ETHTYPE) && (idtype != DCB_APP_IDTYPE_PORTNUM)) return -EINVAL; id = nla_get_u16(app_tb[DCB_APP_ATTR_ID]); up = nla_get_u8(app_tb[DCB_APP_ATTR_PRIORITY]); if (netdev->dcbnl_ops->setapp) { ret = netdev->dcbnl_ops->setapp(netdev, idtype, id, up); if (ret < 0) return ret; } else { struct dcb_app app; app.selector = idtype; app.protocol = id; app.priority = up; ret = dcb_setapp(netdev, &app); } ret = nla_put_u8(skb, DCB_ATTR_APP, ret); dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SAPP, seq, 0); return ret; } static int __dcbnl_pg_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, struct nlattr **tb, struct sk_buff *skb, int dir) { struct nlattr *pg_nest, *param_nest, *data; struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; u8 prio, pgid, tc_pct, up_map; int ret; int getall = 0; int i; if (!tb[DCB_ATTR_PG_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->getpgtccfgtx || !netdev->dcbnl_ops->getpgtccfgrx || !netdev->dcbnl_ops->getpgbwgcfgtx || !netdev->dcbnl_ops->getpgbwgcfgrx) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest, NULL); if (ret) return ret; pg_nest = nla_nest_start_noflag(skb, DCB_ATTR_PG_CFG); if (!pg_nest) return -EMSGSIZE; if (pg_tb[DCB_PG_ATTR_TC_ALL]) getall = 1; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { if (!getall && !pg_tb[i]) continue; if (pg_tb[DCB_PG_ATTR_TC_ALL]) data = pg_tb[DCB_PG_ATTR_TC_ALL]; else data = pg_tb[i]; ret = nla_parse_nested_deprecated(param_tb, DCB_TC_ATTR_PARAM_MAX, data, dcbnl_tc_param_nest, NULL); if (ret) goto err_pg; param_nest = nla_nest_start_noflag(skb, i); if (!param_nest) goto err_pg; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; tc_pct = DCB_ATTR_VALUE_UNDEFINED; up_map = DCB_ATTR_VALUE_UNDEFINED; if (dir) { /* Rx */ netdev->dcbnl_ops->getpgtccfgrx(netdev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); } else { /* Tx */ netdev->dcbnl_ops->getpgtccfgtx(netdev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); } if (param_tb[DCB_TC_ATTR_PARAM_PGID] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio); if (ret) goto err_param; } if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT] || param_tb[DCB_TC_ATTR_PARAM_ALL]) { ret = nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct); if (ret) goto err_param; } nla_nest_end(skb, param_nest); } if (pg_tb[DCB_PG_ATTR_BW_ID_ALL]) getall = 1; else getall = 0; for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { if (!getall && !pg_tb[i]) continue; tc_pct = DCB_ATTR_VALUE_UNDEFINED; if (dir) { /* Rx */ netdev->dcbnl_ops->getpgbwgcfgrx(netdev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); } else { /* Tx */ netdev->dcbnl_ops->getpgbwgcfgtx(netdev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); } ret = nla_put_u8(skb, i, tc_pct); if (ret) goto err_pg; } nla_nest_end(skb, pg_nest); return 0; err_param: nla_nest_cancel(skb, param_nest); err_pg: nla_nest_cancel(skb, pg_nest); return -EMSGSIZE; } static int dcbnl_pgtx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 0); } static int dcbnl_pgrx_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_getcfg(netdev, nlh, tb, skb, 1); } static int dcbnl_setstate(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 value; if (!tb[DCB_ATTR_STATE]) return -EINVAL; if (!netdev->dcbnl_ops->setstate) return -EOPNOTSUPP; value = nla_get_u8(tb[DCB_ATTR_STATE]); return nla_put_u8(skb, DCB_ATTR_STATE, netdev->dcbnl_ops->setstate(netdev, value)); } static int dcbnl_setpfccfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_PFC_UP_ATTR_MAX + 1]; int i; int ret; u8 value; if (!tb[DCB_ATTR_PFC_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->setpfccfg) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_PFC_UP_ATTR_MAX, tb[DCB_ATTR_PFC_CFG], dcbnl_pfc_up_nest, NULL); if (ret) return ret; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { if (data[i] == NULL) continue; value = nla_get_u8(data[i]); netdev->dcbnl_ops->setpfccfg(netdev, data[i]->nla_type - DCB_PFC_UP_ATTR_0, value); } return nla_put_u8(skb, DCB_ATTR_PFC_CFG, 0); } static int dcbnl_setall(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { int ret; if (!tb[DCB_ATTR_SET_ALL]) return -EINVAL; if (!netdev->dcbnl_ops->setall) return -EOPNOTSUPP; ret = nla_put_u8(skb, DCB_ATTR_SET_ALL, netdev->dcbnl_ops->setall(netdev)); dcbnl_cee_notify(netdev, RTM_SETDCB, DCB_CMD_SET_ALL, seq, 0); return ret; } static int __dcbnl_pg_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb, int dir) { struct nlattr *pg_tb[DCB_PG_ATTR_MAX + 1]; struct nlattr *param_tb[DCB_TC_ATTR_PARAM_MAX + 1]; int ret; int i; u8 pgid; u8 up_map; u8 prio; u8 tc_pct; if (!tb[DCB_ATTR_PG_CFG]) return -EINVAL; if (!netdev->dcbnl_ops->setpgtccfgtx || !netdev->dcbnl_ops->setpgtccfgrx || !netdev->dcbnl_ops->setpgbwgcfgtx || !netdev->dcbnl_ops->setpgbwgcfgrx) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(pg_tb, DCB_PG_ATTR_MAX, tb[DCB_ATTR_PG_CFG], dcbnl_pg_nest, NULL); if (ret) return ret; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { if (!pg_tb[i]) continue; ret = nla_parse_nested_deprecated(param_tb, DCB_TC_ATTR_PARAM_MAX, pg_tb[i], dcbnl_tc_param_nest, NULL); if (ret) return ret; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; tc_pct = DCB_ATTR_VALUE_UNDEFINED; up_map = DCB_ATTR_VALUE_UNDEFINED; if (param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]) prio = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_STRICT_PRIO]); if (param_tb[DCB_TC_ATTR_PARAM_PGID]) pgid = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_PGID]); if (param_tb[DCB_TC_ATTR_PARAM_BW_PCT]) tc_pct = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_BW_PCT]); if (param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]) up_map = nla_get_u8(param_tb[DCB_TC_ATTR_PARAM_UP_MAPPING]); /* dir: Tx = 0, Rx = 1 */ if (dir) { /* Rx */ netdev->dcbnl_ops->setpgtccfgrx(netdev, i - DCB_PG_ATTR_TC_0, prio, pgid, tc_pct, up_map); } else { /* Tx */ netdev->dcbnl_ops->setpgtccfgtx(netdev, i - DCB_PG_ATTR_TC_0, prio, pgid, tc_pct, up_map); } } for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { if (!pg_tb[i]) continue; tc_pct = nla_get_u8(pg_tb[i]); /* dir: Tx = 0, Rx = 1 */ if (dir) { /* Rx */ netdev->dcbnl_ops->setpgbwgcfgrx(netdev, i - DCB_PG_ATTR_BW_ID_0, tc_pct); } else { /* Tx */ netdev->dcbnl_ops->setpgbwgcfgtx(netdev, i - DCB_PG_ATTR_BW_ID_0, tc_pct); } } return nla_put_u8(skb, DCB_ATTR_PG_CFG, 0); } static int dcbnl_pgtx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 0); } static int dcbnl_pgrx_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { return __dcbnl_pg_setcfg(netdev, nlh, seq, tb, skb, 1); } static int dcbnl_bcn_getcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *bcn_nest; struct nlattr *bcn_tb[DCB_BCN_ATTR_MAX + 1]; u8 value_byte; u32 value_integer; int ret; bool getall = false; int i; if (!tb[DCB_ATTR_BCN]) return -EINVAL; if (!netdev->dcbnl_ops->getbcnrp || !netdev->dcbnl_ops->getbcncfg) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(bcn_tb, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; bcn_nest = nla_nest_start_noflag(skb, DCB_ATTR_BCN); if (!bcn_nest) return -EMSGSIZE; if (bcn_tb[DCB_BCN_ATTR_ALL]) getall = true; for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { if (!getall && !bcn_tb[i]) continue; netdev->dcbnl_ops->getbcnrp(netdev, i - DCB_BCN_ATTR_RP_0, &value_byte); ret = nla_put_u8(skb, i, value_byte); if (ret) goto err_bcn; } for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { if (!getall && !bcn_tb[i]) continue; netdev->dcbnl_ops->getbcncfg(netdev, i, &value_integer); ret = nla_put_u32(skb, i, value_integer); if (ret) goto err_bcn; } nla_nest_end(skb, bcn_nest); return 0; err_bcn: nla_nest_cancel(skb, bcn_nest); return ret; } static int dcbnl_bcn_setcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_BCN_ATTR_MAX + 1]; int i; int ret; u8 value_byte; u32 value_int; if (!tb[DCB_ATTR_BCN]) return -EINVAL; if (!netdev->dcbnl_ops->setbcncfg || !netdev->dcbnl_ops->setbcnrp) return -EOPNOTSUPP; ret = nla_parse_nested_deprecated(data, DCB_BCN_ATTR_MAX, tb[DCB_ATTR_BCN], dcbnl_bcn_nest, NULL); if (ret) return ret; for (i = DCB_BCN_ATTR_RP_0; i <= DCB_BCN_ATTR_RP_7; i++) { if (data[i] == NULL) continue; value_byte = nla_get_u8(data[i]); netdev->dcbnl_ops->setbcnrp(netdev, data[i]->nla_type - DCB_BCN_ATTR_RP_0, value_byte); } for (i = DCB_BCN_ATTR_BCNA_0; i <= DCB_BCN_ATTR_RI; i++) { if (data[i] == NULL) continue; value_int = nla_get_u32(data[i]); netdev->dcbnl_ops->setbcncfg(netdev, i, value_int); } return nla_put_u8(skb, DCB_ATTR_BCN, 0); } static int dcbnl_build_peer_app(struct net_device *netdev, struct sk_buff* skb, int app_nested_type, int app_info_type, int app_entry_type) { struct dcb_peer_app_info info; struct dcb_app *table = NULL; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; u16 app_count; int err; /** * retrieve the peer app configuration form the driver. If the driver * handlers fail exit without doing anything */ err = ops->peer_getappinfo(netdev, &info, &app_count); if (!err && app_count) { table = kmalloc_objs(struct dcb_app, app_count); if (!table) return -ENOMEM; err = ops->peer_getapptable(netdev, table); } if (!err) { u16 i; struct nlattr *app; /** * build the message, from here on the only possible failure * is due to the skb size */ err = -EMSGSIZE; app = nla_nest_start_noflag(skb, app_nested_type); if (!app) goto nla_put_failure; if (app_info_type && nla_put(skb, app_info_type, sizeof(info), &info)) goto nla_put_failure; for (i = 0; i < app_count; i++) { if (nla_put(skb, app_entry_type, sizeof(struct dcb_app), &table[i])) goto nla_put_failure; } nla_nest_end(skb, app); } err = 0; nla_put_failure: kfree(table); return err; } static int dcbnl_getapptrust(struct net_device *netdev, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; enum ieee_attrs_app type; struct nlattr *apptrust; int nselectors, err, i; u8 *selectors; selectors = kzalloc(IEEE_8021QAZ_APP_SEL_MAX + 1, GFP_KERNEL); if (!selectors) return -ENOMEM; err = ops->dcbnl_getapptrust(netdev, selectors, &nselectors); if (err) { err = 0; goto out; } apptrust = nla_nest_start(skb, DCB_ATTR_DCB_APP_TRUST_TABLE); if (!apptrust) { err = -EMSGSIZE; goto out; } for (i = 0; i < nselectors; i++) { type = dcbnl_app_attr_type_get(selectors[i]); err = nla_put_u8(skb, type, selectors[i]); if (err) { nla_nest_cancel(skb, apptrust); goto out; } } nla_nest_end(skb, apptrust); out: kfree(selectors); return err; } /* Set or delete APP table or rewrite table entries. The APP struct is validated * and the appropriate callback function is called. */ static int dcbnl_app_table_setdel(struct nlattr *attr, struct net_device *netdev, int (*setdel)(struct net_device *dev, struct dcb_app *app)) { struct dcb_app *app_data; enum ieee_attrs_app type; struct nlattr *attr_itr; int rem, err; nla_for_each_nested(attr_itr, attr, rem) { type = nla_type(attr_itr); if (!dcbnl_app_attr_type_validate(type)) continue; if (nla_len(attr_itr) < sizeof(struct dcb_app)) return -ERANGE; app_data = nla_data(attr_itr); if (!dcbnl_app_selector_validate(type, app_data->selector)) return -EINVAL; err = setdel(netdev, app_data); if (err) return err; } return 0; } /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb GET commands. */ static int dcbnl_ieee_fill(struct sk_buff *skb, struct net_device *netdev) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee, *app, *rewr; struct dcb_app_type *itr; int dcbx; int err; if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) return -EMSGSIZE; ieee = nla_nest_start_noflag(skb, DCB_ATTR_IEEE); if (!ieee) return -EMSGSIZE; if (ops->ieee_getets) { struct ieee_ets ets; memset(&ets, 0, sizeof(ets)); err = ops->ieee_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_ETS, sizeof(ets), &ets)) return -EMSGSIZE; } if (ops->ieee_getmaxrate) { struct ieee_maxrate maxrate; memset(&maxrate, 0, sizeof(maxrate)); err = ops->ieee_getmaxrate(netdev, &maxrate); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_MAXRATE, sizeof(maxrate), &maxrate); if (err) return -EMSGSIZE; } } if (ops->ieee_getqcn) { struct ieee_qcn qcn; memset(&qcn, 0, sizeof(qcn)); err = ops->ieee_getqcn(netdev, &qcn); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_QCN, sizeof(qcn), &qcn); if (err) return -EMSGSIZE; } } if (ops->ieee_getqcnstats) { struct ieee_qcn_stats qcn_stats; memset(&qcn_stats, 0, sizeof(qcn_stats)); err = ops->ieee_getqcnstats(netdev, &qcn_stats); if (!err) { err = nla_put(skb, DCB_ATTR_IEEE_QCN_STATS, sizeof(qcn_stats), &qcn_stats); if (err) return -EMSGSIZE; } } if (ops->ieee_getpfc) { struct ieee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PFC, sizeof(pfc), &pfc)) return -EMSGSIZE; } if (ops->dcbnl_getbuffer) { struct dcbnl_buffer buffer; memset(&buffer, 0, sizeof(buffer)); err = ops->dcbnl_getbuffer(netdev, &buffer); if (!err && nla_put(skb, DCB_ATTR_DCB_BUFFER, sizeof(buffer), &buffer)) return -EMSGSIZE; } app = nla_nest_start_noflag(skb, DCB_ATTR_IEEE_APP_TABLE); if (!app) return -EMSGSIZE; spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { enum ieee_attrs_app type = dcbnl_app_attr_type_get(itr->app.selector); err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); return -EMSGSIZE; } } } if (netdev->dcbnl_ops->getdcbx) dcbx = netdev->dcbnl_ops->getdcbx(netdev); else dcbx = -EOPNOTSUPP; spin_unlock_bh(&dcb_lock); nla_nest_end(skb, app); rewr = nla_nest_start(skb, DCB_ATTR_DCB_REWR_TABLE); if (!rewr) return -EMSGSIZE; spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->ifindex == netdev->ifindex) { enum ieee_attrs_app type = dcbnl_app_attr_type_get(itr->app.selector); err = nla_put(skb, type, sizeof(itr->app), &itr->app); if (err) { spin_unlock_bh(&dcb_lock); nla_nest_cancel(skb, rewr); return -EMSGSIZE; } } } spin_unlock_bh(&dcb_lock); nla_nest_end(skb, rewr); if (ops->dcbnl_getapptrust) { err = dcbnl_getapptrust(netdev, skb); if (err) return err; } /* get peer info if available */ if (ops->ieee_peer_getets) { struct ieee_ets ets; memset(&ets, 0, sizeof(ets)); err = ops->ieee_peer_getets(netdev, &ets); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_ETS, sizeof(ets), &ets)) return -EMSGSIZE; } if (ops->ieee_peer_getpfc) { struct ieee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); err = ops->ieee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_IEEE_PEER_PFC, sizeof(pfc), &pfc)) return -EMSGSIZE; } if (ops->peer_getappinfo && ops->peer_getapptable) { err = dcbnl_build_peer_app(netdev, skb, DCB_ATTR_IEEE_PEER_APP, DCB_ATTR_IEEE_APP_UNSPEC, DCB_ATTR_IEEE_APP); if (err) return -EMSGSIZE; } nla_nest_end(skb, ieee); if (dcbx >= 0) { err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); if (err) return -EMSGSIZE; } return 0; } static int dcbnl_cee_pg_fill(struct sk_buff *skb, struct net_device *dev, int dir) { u8 pgid, up_map, prio, tc_pct; const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; int i = dir ? DCB_ATTR_CEE_TX_PG : DCB_ATTR_CEE_RX_PG; struct nlattr *pg = nla_nest_start_noflag(skb, i); if (!pg) return -EMSGSIZE; for (i = DCB_PG_ATTR_TC_0; i <= DCB_PG_ATTR_TC_7; i++) { struct nlattr *tc_nest = nla_nest_start_noflag(skb, i); if (!tc_nest) return -EMSGSIZE; pgid = DCB_ATTR_VALUE_UNDEFINED; prio = DCB_ATTR_VALUE_UNDEFINED; tc_pct = DCB_ATTR_VALUE_UNDEFINED; up_map = DCB_ATTR_VALUE_UNDEFINED; if (!dir) ops->getpgtccfgrx(dev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); else ops->getpgtccfgtx(dev, i - DCB_PG_ATTR_TC_0, &prio, &pgid, &tc_pct, &up_map); if (nla_put_u8(skb, DCB_TC_ATTR_PARAM_PGID, pgid) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_UP_MAPPING, up_map) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_STRICT_PRIO, prio) || nla_put_u8(skb, DCB_TC_ATTR_PARAM_BW_PCT, tc_pct)) return -EMSGSIZE; nla_nest_end(skb, tc_nest); } for (i = DCB_PG_ATTR_BW_ID_0; i <= DCB_PG_ATTR_BW_ID_7; i++) { tc_pct = DCB_ATTR_VALUE_UNDEFINED; if (!dir) ops->getpgbwgcfgrx(dev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); else ops->getpgbwgcfgtx(dev, i - DCB_PG_ATTR_BW_ID_0, &tc_pct); if (nla_put_u8(skb, i, tc_pct)) return -EMSGSIZE; } nla_nest_end(skb, pg); return 0; } static int dcbnl_cee_fill(struct sk_buff *skb, struct net_device *netdev) { struct nlattr *cee, *app; struct dcb_app_type *itr; const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; int dcbx, i, err = -EMSGSIZE; u8 value; if (nla_put_string(skb, DCB_ATTR_IFNAME, netdev->name)) goto nla_put_failure; cee = nla_nest_start_noflag(skb, DCB_ATTR_CEE); if (!cee) goto nla_put_failure; /* local pg */ if (ops->getpgtccfgtx && ops->getpgbwgcfgtx) { err = dcbnl_cee_pg_fill(skb, netdev, 1); if (err) goto nla_put_failure; } if (ops->getpgtccfgrx && ops->getpgbwgcfgrx) { err = dcbnl_cee_pg_fill(skb, netdev, 0); if (err) goto nla_put_failure; } /* local pfc */ if (ops->getpfccfg) { struct nlattr *pfc_nest = nla_nest_start_noflag(skb, DCB_ATTR_CEE_PFC); if (!pfc_nest) goto nla_put_failure; for (i = DCB_PFC_UP_ATTR_0; i <= DCB_PFC_UP_ATTR_7; i++) { ops->getpfccfg(netdev, i - DCB_PFC_UP_ATTR_0, &value); if (nla_put_u8(skb, i, value)) goto nla_put_failure; } nla_nest_end(skb, pfc_nest); } /* local app */ spin_lock_bh(&dcb_lock); app = nla_nest_start_noflag(skb, DCB_ATTR_CEE_APP_TABLE); if (!app) goto dcb_unlock; list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == netdev->ifindex) { struct nlattr *app_nest = nla_nest_start_noflag(skb, DCB_ATTR_APP); if (!app_nest) goto dcb_unlock; err = nla_put_u8(skb, DCB_APP_ATTR_IDTYPE, itr->app.selector); if (err) goto dcb_unlock; err = nla_put_u16(skb, DCB_APP_ATTR_ID, itr->app.protocol); if (err) goto dcb_unlock; err = nla_put_u8(skb, DCB_APP_ATTR_PRIORITY, itr->app.priority); if (err) goto dcb_unlock; nla_nest_end(skb, app_nest); } } nla_nest_end(skb, app); if (netdev->dcbnl_ops->getdcbx) dcbx = netdev->dcbnl_ops->getdcbx(netdev); else dcbx = -EOPNOTSUPP; spin_unlock_bh(&dcb_lock); /* features flags */ if (ops->getfeatcfg) { struct nlattr *feat = nla_nest_start_noflag(skb, DCB_ATTR_CEE_FEAT); if (!feat) goto nla_put_failure; for (i = DCB_FEATCFG_ATTR_ALL + 1; i <= DCB_FEATCFG_ATTR_MAX; i++) if (!ops->getfeatcfg(netdev, i, &value) && nla_put_u8(skb, i, value)) goto nla_put_failure; nla_nest_end(skb, feat); } /* peer info if available */ if (ops->cee_peer_getpg) { struct cee_pg pg; memset(&pg, 0, sizeof(pg)); err = ops->cee_peer_getpg(netdev, &pg); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PG, sizeof(pg), &pg)) goto nla_put_failure; } if (ops->cee_peer_getpfc) { struct cee_pfc pfc; memset(&pfc, 0, sizeof(pfc)); err = ops->cee_peer_getpfc(netdev, &pfc); if (!err && nla_put(skb, DCB_ATTR_CEE_PEER_PFC, sizeof(pfc), &pfc)) goto nla_put_failure; } if (ops->peer_getappinfo && ops->peer_getapptable) { err = dcbnl_build_peer_app(netdev, skb, DCB_ATTR_CEE_PEER_APP_TABLE, DCB_ATTR_CEE_PEER_APP_INFO, DCB_ATTR_CEE_PEER_APP); if (err) goto nla_put_failure; } nla_nest_end(skb, cee); /* DCBX state */ if (dcbx >= 0) { err = nla_put_u8(skb, DCB_ATTR_DCBX, dcbx); if (err) goto nla_put_failure; } return 0; dcb_unlock: spin_unlock_bh(&dcb_lock); nla_put_failure: err = -EMSGSIZE; return err; } static int dcbnl_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 portid, int dcbx_ver) { struct net *net = dev_net(dev); struct sk_buff *skb; struct nlmsghdr *nlh; const struct dcbnl_rtnl_ops *ops = dev->dcbnl_ops; int err; if (!ops) return -EOPNOTSUPP; skb = dcbnl_newmsg(event, cmd, portid, seq, 0, &nlh); if (!skb) return -ENOMEM; if (dcbx_ver == DCB_CAP_DCBX_VER_IEEE) err = dcbnl_ieee_fill(skb, dev); else err = dcbnl_cee_fill(skb, dev); if (err < 0) { /* Report error to broadcast listeners */ nlmsg_free(skb); rtnl_set_sk_err(net, RTNLGRP_DCB, err); } else { /* End nlmsg and notify broadcast listeners */ nlmsg_end(skb, nlh); rtnl_notify(skb, net, 0, RTNLGRP_DCB, NULL, GFP_KERNEL); } return err; } int dcbnl_ieee_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 portid) { return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_IEEE); } EXPORT_SYMBOL(dcbnl_ieee_notify); int dcbnl_cee_notify(struct net_device *dev, int event, int cmd, u32 seq, u32 portid) { return dcbnl_notify(dev, event, cmd, seq, portid, DCB_CAP_DCBX_VER_CEE); } EXPORT_SYMBOL(dcbnl_cee_notify); /* Handle IEEE 802.1Qaz/802.1Qau/802.1Qbb SET commands. * If any requested operation can not be completed * the entire msg is aborted and error value is returned. * No attempt is made to reconcile the case where only part of the * cmd can be completed. */ static int dcbnl_ieee_set(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; int prio; int err; if (!ops) return -EOPNOTSUPP; if (!tb[DCB_ATTR_IEEE]) return -EINVAL; err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE], dcbnl_ieee_policy, NULL); if (err) return err; if (ieee[DCB_ATTR_IEEE_ETS] && ops->ieee_setets) { struct ieee_ets *ets = nla_data(ieee[DCB_ATTR_IEEE_ETS]); err = ops->ieee_setets(netdev, ets); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_MAXRATE] && ops->ieee_setmaxrate) { struct ieee_maxrate *maxrate = nla_data(ieee[DCB_ATTR_IEEE_MAXRATE]); err = ops->ieee_setmaxrate(netdev, maxrate); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_QCN] && ops->ieee_setqcn) { struct ieee_qcn *qcn = nla_data(ieee[DCB_ATTR_IEEE_QCN]); err = ops->ieee_setqcn(netdev, qcn); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_PFC] && ops->ieee_setpfc) { struct ieee_pfc *pfc = nla_data(ieee[DCB_ATTR_IEEE_PFC]); err = ops->ieee_setpfc(netdev, pfc); if (err) goto err; } if (ieee[DCB_ATTR_DCB_BUFFER] && ops->dcbnl_setbuffer) { struct dcbnl_buffer *buffer = nla_data(ieee[DCB_ATTR_DCB_BUFFER]); for (prio = 0; prio < ARRAY_SIZE(buffer->prio2buffer); prio++) { if (buffer->prio2buffer[prio] >= DCBX_MAX_BUFFERS) { err = -EINVAL; goto err; } } err = ops->dcbnl_setbuffer(netdev, buffer); if (err) goto err; } if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], netdev, ops->dcbnl_setrewr ?: dcb_setrewr); if (err) goto err; } if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], netdev, ops->ieee_setapp ?: dcb_ieee_setapp); if (err) goto err; } if (ieee[DCB_ATTR_DCB_APP_TRUST_TABLE]) { u8 selectors[IEEE_8021QAZ_APP_SEL_MAX + 1] = {0}; struct nlattr *attr; int nselectors = 0; int rem; if (!ops->dcbnl_setapptrust) { err = -EOPNOTSUPP; goto err; } nla_for_each_nested(attr, ieee[DCB_ATTR_DCB_APP_TRUST_TABLE], rem) { enum ieee_attrs_app type = nla_type(attr); u8 selector; int i; if (!dcbnl_app_attr_type_validate(type) || nla_len(attr) != 1 || nselectors >= sizeof(selectors)) { err = -EINVAL; goto err; } selector = nla_get_u8(attr); if (!dcbnl_app_selector_validate(type, selector)) { err = -EINVAL; goto err; } /* Duplicate selector ? */ for (i = 0; i < nselectors; i++) { if (selectors[i] == selector) { err = -EINVAL; goto err; } } selectors[nselectors++] = selector; } err = ops->dcbnl_setapptrust(netdev, selectors, nselectors); if (err) goto err; } err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_SET, seq, 0); return err; } static int dcbnl_ieee_get(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; if (!ops) return -EOPNOTSUPP; return dcbnl_ieee_fill(skb, netdev); } static int dcbnl_ieee_del(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; struct nlattr *ieee[DCB_ATTR_IEEE_MAX + 1]; int err; if (!ops) return -EOPNOTSUPP; if (!tb[DCB_ATTR_IEEE]) return -EINVAL; err = nla_parse_nested_deprecated(ieee, DCB_ATTR_IEEE_MAX, tb[DCB_ATTR_IEEE], dcbnl_ieee_policy, NULL); if (err) return err; if (ieee[DCB_ATTR_IEEE_APP_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_IEEE_APP_TABLE], netdev, ops->ieee_delapp ?: dcb_ieee_delapp); if (err) goto err; } if (ieee[DCB_ATTR_DCB_REWR_TABLE]) { err = dcbnl_app_table_setdel(ieee[DCB_ATTR_DCB_REWR_TABLE], netdev, ops->dcbnl_delrewr ?: dcb_delrewr); if (err) goto err; } err: err = nla_put_u8(skb, DCB_ATTR_IEEE, err); dcbnl_ieee_notify(netdev, RTM_SETDCB, DCB_CMD_IEEE_DEL, seq, 0); return err; } /* DCBX configuration */ static int dcbnl_getdcbx(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { if (!netdev->dcbnl_ops->getdcbx) return -EOPNOTSUPP; return nla_put_u8(skb, DCB_ATTR_DCBX, netdev->dcbnl_ops->getdcbx(netdev)); } static int dcbnl_setdcbx(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { u8 value; if (!netdev->dcbnl_ops->setdcbx) return -EOPNOTSUPP; if (!tb[DCB_ATTR_DCBX]) return -EINVAL; value = nla_get_u8(tb[DCB_ATTR_DCBX]); return nla_put_u8(skb, DCB_ATTR_DCBX, netdev->dcbnl_ops->setdcbx(netdev, value)); } static int dcbnl_getfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1], *nest; u8 value; int ret, i; int getall = 0; if (!netdev->dcbnl_ops->getfeatcfg) return -EOPNOTSUPP; if (!tb[DCB_ATTR_FEATCFG]) return -EINVAL; ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL); if (ret) return ret; nest = nla_nest_start_noflag(skb, DCB_ATTR_FEATCFG); if (!nest) return -EMSGSIZE; if (data[DCB_FEATCFG_ATTR_ALL]) getall = 1; for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { if (!getall && !data[i]) continue; ret = netdev->dcbnl_ops->getfeatcfg(netdev, i, &value); if (!ret) ret = nla_put_u8(skb, i, value); if (ret) { nla_nest_cancel(skb, nest); goto nla_put_failure; } } nla_nest_end(skb, nest); nla_put_failure: return ret; } static int dcbnl_setfeatcfg(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { struct nlattr *data[DCB_FEATCFG_ATTR_MAX + 1]; int ret, i; u8 value; if (!netdev->dcbnl_ops->setfeatcfg) return -ENOTSUPP; if (!tb[DCB_ATTR_FEATCFG]) return -EINVAL; ret = nla_parse_nested_deprecated(data, DCB_FEATCFG_ATTR_MAX, tb[DCB_ATTR_FEATCFG], dcbnl_featcfg_nest, NULL); if (ret) goto err; for (i = DCB_FEATCFG_ATTR_ALL+1; i <= DCB_FEATCFG_ATTR_MAX; i++) { if (data[i] == NULL) continue; value = nla_get_u8(data[i]); ret = netdev->dcbnl_ops->setfeatcfg(netdev, i, value); if (ret) goto err; } err: ret = nla_put_u8(skb, DCB_ATTR_FEATCFG, ret); return ret; } /* Handle CEE DCBX GET commands. */ static int dcbnl_cee_get(struct net_device *netdev, struct nlmsghdr *nlh, u32 seq, struct nlattr **tb, struct sk_buff *skb) { const struct dcbnl_rtnl_ops *ops = netdev->dcbnl_ops; if (!ops) return -EOPNOTSUPP; return dcbnl_cee_fill(skb, netdev); } struct reply_func { /* reply netlink message type */ int type; /* function to fill message contents */ int (*cb)(struct net_device *, struct nlmsghdr *, u32, struct nlattr **, struct sk_buff *); }; static const struct reply_func reply_funcs[DCB_CMD_MAX+1] = { [DCB_CMD_GSTATE] = { RTM_GETDCB, dcbnl_getstate }, [DCB_CMD_SSTATE] = { RTM_SETDCB, dcbnl_setstate }, [DCB_CMD_PFC_GCFG] = { RTM_GETDCB, dcbnl_getpfccfg }, [DCB_CMD_PFC_SCFG] = { RTM_SETDCB, dcbnl_setpfccfg }, [DCB_CMD_GPERM_HWADDR] = { RTM_GETDCB, dcbnl_getperm_hwaddr }, [DCB_CMD_GCAP] = { RTM_GETDCB, dcbnl_getcap }, [DCB_CMD_GNUMTCS] = { RTM_GETDCB, dcbnl_getnumtcs }, [DCB_CMD_SNUMTCS] = { RTM_SETDCB, dcbnl_setnumtcs }, [DCB_CMD_PFC_GSTATE] = { RTM_GETDCB, dcbnl_getpfcstate }, [DCB_CMD_PFC_SSTATE] = { RTM_SETDCB, dcbnl_setpfcstate }, [DCB_CMD_GAPP] = { RTM_GETDCB, dcbnl_getapp }, [DCB_CMD_SAPP] = { RTM_SETDCB, dcbnl_setapp }, [DCB_CMD_PGTX_GCFG] = { RTM_GETDCB, dcbnl_pgtx_getcfg }, [DCB_CMD_PGTX_SCFG] = { RTM_SETDCB, dcbnl_pgtx_setcfg }, [DCB_CMD_PGRX_GCFG] = { RTM_GETDCB, dcbnl_pgrx_getcfg }, [DCB_CMD_PGRX_SCFG] = { RTM_SETDCB, dcbnl_pgrx_setcfg }, [DCB_CMD_SET_ALL] = { RTM_SETDCB, dcbnl_setall }, [DCB_CMD_BCN_GCFG] = { RTM_GETDCB, dcbnl_bcn_getcfg }, [DCB_CMD_BCN_SCFG] = { RTM_SETDCB, dcbnl_bcn_setcfg }, [DCB_CMD_IEEE_GET] = { RTM_GETDCB, dcbnl_ieee_get }, [DCB_CMD_IEEE_SET] = { RTM_SETDCB, dcbnl_ieee_set }, [DCB_CMD_IEEE_DEL] = { RTM_SETDCB, dcbnl_ieee_del }, [DCB_CMD_GDCBX] = { RTM_GETDCB, dcbnl_getdcbx }, [DCB_CMD_SDCBX] = { RTM_SETDCB, dcbnl_setdcbx }, [DCB_CMD_GFEATCFG] = { RTM_GETDCB, dcbnl_getfeatcfg }, [DCB_CMD_SFEATCFG] = { RTM_SETDCB, dcbnl_setfeatcfg }, [DCB_CMD_CEE_GET] = { RTM_GETDCB, dcbnl_cee_get }, }; static int dcb_doit(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); struct net_device *netdev; struct dcbmsg *dcb = nlmsg_data(nlh); struct nlattr *tb[DCB_ATTR_MAX + 1]; u32 portid = NETLINK_CB(skb).portid; int ret = -EINVAL; struct sk_buff *reply_skb; struct nlmsghdr *reply_nlh = NULL; const struct reply_func *fn; if ((nlh->nlmsg_type == RTM_SETDCB) && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; ret = nlmsg_parse_deprecated(nlh, sizeof(*dcb), tb, DCB_ATTR_MAX, dcbnl_rtnl_policy, extack); if (ret < 0) return ret; if (dcb->cmd > DCB_CMD_MAX) return -EINVAL; /* check if a reply function has been defined for the command */ fn = &reply_funcs[dcb->cmd]; if (!fn->cb) return -EOPNOTSUPP; if (fn->type == RTM_SETDCB && !netlink_capable(skb, CAP_NET_ADMIN)) return -EPERM; if (!tb[DCB_ATTR_IFNAME]) return -EINVAL; netdev = __dev_get_by_name(net, nla_data(tb[DCB_ATTR_IFNAME])); if (!netdev) return -ENODEV; if (!netdev->dcbnl_ops) return -EOPNOTSUPP; reply_skb = dcbnl_newmsg(fn->type, dcb->cmd, portid, nlh->nlmsg_seq, nlh->nlmsg_flags, &reply_nlh); if (!reply_skb) return -ENOMEM; ret = fn->cb(netdev, nlh, nlh->nlmsg_seq, tb, reply_skb); if (ret < 0) { nlmsg_free(reply_skb); goto out; } nlmsg_end(reply_skb, reply_nlh); ret = rtnl_unicast(reply_skb, net, portid); out: return ret; } static struct dcb_app_type *dcb_rewr_lookup(const struct dcb_app *app, int ifindex, int proto) { struct dcb_app_type *itr; list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->app.selector == app->selector && itr->app.priority == app->priority && itr->ifindex == ifindex && ((proto == -1) || itr->app.protocol == proto)) return itr; } return NULL; } static struct dcb_app_type *dcb_app_lookup(const struct dcb_app *app, int ifindex, int prio) { struct dcb_app_type *itr; list_for_each_entry(itr, &dcb_app_list, list) { if (itr->app.selector == app->selector && itr->app.protocol == app->protocol && itr->ifindex == ifindex && ((prio == -1) || itr->app.priority == prio)) return itr; } return NULL; } static int dcb_app_add(struct list_head *list, const struct dcb_app *app, int ifindex) { struct dcb_app_type *entry; entry = kmalloc_obj(*entry, GFP_ATOMIC); if (!entry) return -ENOMEM; memcpy(&entry->app, app, sizeof(*app)); entry->ifindex = ifindex; list_add(&entry->list, list); return 0; } /** * dcb_getapp - retrieve the DCBX application user priority * @dev: network interface * @app: application to get user priority of * * On success returns a non-zero 802.1p user priority bitmap * otherwise returns 0 as the invalid user priority bitmap to * indicate an error. */ u8 dcb_getapp(struct net_device *dev, struct dcb_app *app) { struct dcb_app_type *itr; u8 prio = 0; spin_lock_bh(&dcb_lock); itr = dcb_app_lookup(app, dev->ifindex, -1); if (itr) prio = itr->app.priority; spin_unlock_bh(&dcb_lock); return prio; } EXPORT_SYMBOL(dcb_getapp); /** * dcb_setapp - add CEE dcb application data to app list * @dev: network interface * @new: application data to add * * Priority 0 is an invalid priority in CEE spec. This routine * removes applications from the app list if the priority is * set to zero. Priority is expected to be 8-bit 802.1p user priority bitmap */ int dcb_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type *itr; struct dcb_app_type event; int err = 0; event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock_bh(&dcb_lock); /* Search for existing match and replace */ itr = dcb_app_lookup(new, dev->ifindex, -1); if (itr) { if (new->priority) itr->app.priority = new->priority; else { list_del(&itr->list); kfree(itr); } goto out; } /* App type does not exist add new application type */ if (new->priority) err = dcb_app_add(&dcb_app_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; } EXPORT_SYMBOL(dcb_setapp); /** * dcb_ieee_getapp_mask - retrieve the IEEE DCB application priority * @dev: network interface * @app: where to store the retrieve application data * * Helper routine which on success returns a non-zero 802.1Qaz user * priority bitmap otherwise returns 0 to indicate the dcb_app was * not found in APP list. */ u8 dcb_ieee_getapp_mask(struct net_device *dev, struct dcb_app *app) { struct dcb_app_type *itr; u8 prio = 0; spin_lock_bh(&dcb_lock); itr = dcb_app_lookup(app, dev->ifindex, -1); if (itr) prio |= 1 << itr->app.priority; spin_unlock_bh(&dcb_lock); return prio; } EXPORT_SYMBOL(dcb_ieee_getapp_mask); /* Get protocol value from rewrite entry. */ u16 dcb_getrewr(struct net_device *dev, struct dcb_app *app) { struct dcb_app_type *itr; u16 proto = 0; spin_lock_bh(&dcb_lock); itr = dcb_rewr_lookup(app, dev->ifindex, -1); if (itr) proto = itr->app.protocol; spin_unlock_bh(&dcb_lock); return proto; } EXPORT_SYMBOL(dcb_getrewr); /* Add rewrite entry to the rewrite list. */ int dcb_setrewr(struct net_device *dev, struct dcb_app *new) { int err; spin_lock_bh(&dcb_lock); /* Search for existing match and abort if found. */ if (dcb_rewr_lookup(new, dev->ifindex, new->protocol)) { err = -EEXIST; goto out; } err = dcb_app_add(&dcb_rewr_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); return err; } EXPORT_SYMBOL(dcb_setrewr); /* Delete rewrite entry from the rewrite list. */ int dcb_delrewr(struct net_device *dev, struct dcb_app *del) { struct dcb_app_type *itr; int err = -ENOENT; spin_lock_bh(&dcb_lock); /* Search for existing match and remove it. */ itr = dcb_rewr_lookup(del, dev->ifindex, del->protocol); if (itr) { list_del(&itr->list); kfree(itr); err = 0; } spin_unlock_bh(&dcb_lock); return err; } EXPORT_SYMBOL(dcb_delrewr); /** * dcb_ieee_setapp - add IEEE dcb application data to app list * @dev: network interface * @new: application data to add * * This adds Application data to the list. Multiple application * entries may exists for the same selector and protocol as long * as the priorities are different. Priority is expected to be a * 3-bit unsigned integer */ int dcb_ieee_setapp(struct net_device *dev, struct dcb_app *new) { struct dcb_app_type event; int err = 0; event.ifindex = dev->ifindex; memcpy(&event.app, new, sizeof(event.app)); if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock_bh(&dcb_lock); /* Search for existing match and abort if found */ if (dcb_app_lookup(new, dev->ifindex, new->priority)) { err = -EEXIST; goto out; } err = dcb_app_add(&dcb_app_list, new, dev->ifindex); out: spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; } EXPORT_SYMBOL(dcb_ieee_setapp); /** * dcb_ieee_delapp - delete IEEE dcb application data from list * @dev: network interface * @del: application data to delete * * This removes a matching APP data from the APP list */ int dcb_ieee_delapp(struct net_device *dev, struct dcb_app *del) { struct dcb_app_type *itr; struct dcb_app_type event; int err = -ENOENT; event.ifindex = dev->ifindex; memcpy(&event.app, del, sizeof(event.app)); if (dev->dcbnl_ops->getdcbx) event.dcbx = dev->dcbnl_ops->getdcbx(dev); spin_lock_bh(&dcb_lock); /* Search for existing match and remove it. */ if ((itr = dcb_app_lookup(del, dev->ifindex, del->priority))) { list_del(&itr->list); kfree(itr); err = 0; } spin_unlock_bh(&dcb_lock); if (!err) call_dcbevent_notifiers(DCB_APP_EVENT, &event); return err; } EXPORT_SYMBOL(dcb_ieee_delapp); /* dcb_getrewr_prio_pcp_mask_map - For a given device, find mapping from * priorities to the PCP and DEI values assigned to that priority. */ void dcb_getrewr_prio_pcp_mask_map(const struct net_device *dev, struct dcb_rewr_prio_pcp_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 prio; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->ifindex == ifindex && itr->app.selector == DCB_APP_SEL_PCP && itr->app.protocol < 16 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) { prio = itr->app.priority; p_map->map[prio] |= 1 << itr->app.protocol; } } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_getrewr_prio_pcp_mask_map); /* dcb_getrewr_prio_dscp_mask_map - For a given device, find mapping from * priorities to the DSCP values assigned to that priority. */ void dcb_getrewr_prio_dscp_mask_map(const struct net_device *dev, struct dcb_ieee_app_prio_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 prio; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_rewr_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && itr->app.protocol < 64 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) { prio = itr->app.priority; p_map->map[prio] |= 1ULL << itr->app.protocol; } } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_getrewr_prio_dscp_mask_map); /* * dcb_ieee_getapp_prio_dscp_mask_map - For a given device, find mapping from * priorities to the DSCP values assigned to that priority. Initialize p_map * such that each map element holds a bit mask of DSCP values configured for * that priority by APP entries. */ void dcb_ieee_getapp_prio_dscp_mask_map(const struct net_device *dev, struct dcb_ieee_app_prio_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 prio; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && itr->app.protocol < 64 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) { prio = itr->app.priority; p_map->map[prio] |= 1ULL << itr->app.protocol; } } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_ieee_getapp_prio_dscp_mask_map); /* * dcb_ieee_getapp_dscp_prio_mask_map - For a given device, find mapping from * DSCP values to the priorities assigned to that DSCP value. Initialize p_map * such that each map element holds a bit mask of priorities configured for a * given DSCP value by APP entries. */ void dcb_ieee_getapp_dscp_prio_mask_map(const struct net_device *dev, struct dcb_ieee_app_dscp_map *p_map) { int ifindex = dev->ifindex; struct dcb_app_type *itr; memset(p_map->map, 0, sizeof(p_map->map)); spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_DSCP && itr->app.protocol < 64 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) p_map->map[itr->app.protocol] |= 1 << itr->app.priority; } spin_unlock_bh(&dcb_lock); } EXPORT_SYMBOL(dcb_ieee_getapp_dscp_prio_mask_map); /* * Per 802.1Q-2014, the selector value of 1 is used for matching on Ethernet * type, with valid PID values >= 1536. A special meaning is then assigned to * protocol value of 0: "default priority. For use when priority is not * otherwise specified". * * dcb_ieee_getapp_default_prio_mask - For a given device, find all APP entries * of the form {$PRIO, ETHERTYPE, 0} and construct a bit mask of all default * priorities set by these entries. */ u8 dcb_ieee_getapp_default_prio_mask(const struct net_device *dev) { int ifindex = dev->ifindex; struct dcb_app_type *itr; u8 mask = 0; spin_lock_bh(&dcb_lock); list_for_each_entry(itr, &dcb_app_list, list) { if (itr->ifindex == ifindex && itr->app.selector == IEEE_8021QAZ_APP_SEL_ETHERTYPE && itr->app.protocol == 0 && itr->app.priority < IEEE_8021QAZ_MAX_TCS) mask |= 1 << itr->app.priority; } spin_unlock_bh(&dcb_lock); return mask; } EXPORT_SYMBOL(dcb_ieee_getapp_default_prio_mask); static void dcbnl_flush_dev(struct net_device *dev) { struct dcb_app_type *itr, *tmp; spin_lock_bh(&dcb_lock); list_for_each_entry_safe(itr, tmp, &dcb_app_list, list) { if (itr->ifindex == dev->ifindex) { list_del(&itr->list); kfree(itr); } } spin_unlock_bh(&dcb_lock); } static int dcbnl_netdevice_event(struct notifier_block *nb, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); switch (event) { case NETDEV_UNREGISTER: if (!dev->dcbnl_ops) return NOTIFY_DONE; dcbnl_flush_dev(dev); return NOTIFY_OK; default: return NOTIFY_DONE; } } static struct notifier_block dcbnl_nb __read_mostly = { .notifier_call = dcbnl_netdevice_event, }; static const struct rtnl_msg_handler dcbnl_rtnl_msg_handlers[] __initconst = { {.msgtype = RTM_GETDCB, .doit = dcb_doit}, {.msgtype = RTM_SETDCB, .doit = dcb_doit}, }; static int __init dcbnl_init(void) { int err; err = register_netdevice_notifier(&dcbnl_nb); if (err) return err; rtnl_register_many(dcbnl_rtnl_msg_handlers); return 0; } device_initcall(dcbnl_init); |
| 8 738 1 2 2 2 1 1 1 1 1 4 1 2 2 2 1 1 2 2 1 1 1 2 2 2 2 2 1 1 1 1 1 1 1 2 2 1 1 1 2 1 1 2 2 1 1 1 1 2 1 1 1 1 1 1 1 1 1 1 1 1 2 2 3 2 1 1 2 1 1 1 1 1 2 2 1 1 5 2 3 4 5 2 5 1 1 5 1 4 5 5 5 5 2 2 2 2 1 1 1 1 1 1 1 1 1 3 2 1 2 2 3 3 2 1 2 179 178 180 111 110 732 5 728 1 1 1 1 1 725 1 717 719 6 183 177 182 183 181 341 6 646 276 374 271 129 132 300 303 301 8 6 1 1 1 1 1 6 6 12 12 91 91 3 2 2 2 2 1 1 1 1 1 1 1 3 2 2 3 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 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Simple NUMA memory policy for the Linux kernel. * * Copyright 2003,2004 Andi Kleen, SuSE Labs. * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc. * * NUMA policy allows the user to give hints in which node(s) memory should * be allocated. * * Support six policies per VMA and per process: * * The VMA policy has priority over the process policy for a page fault. * * interleave Allocate memory interleaved over a set of nodes, * with normal fallback if it fails. * For VMA based allocations this interleaves based on the * offset into the backing object or offset into the mapping * for anonymous memory. For process policy an process counter * is used. * * weighted interleave * Allocate memory interleaved over a set of nodes based on * a set of weights (per-node), with normal fallback if it * fails. Otherwise operates the same as interleave. * Example: nodeset(0,1) & weights (2,1) - 2 pages allocated * on node 0 for every 1 page allocated on node 1. * * bind Only allocate memory on a specific set of nodes, * no fallback. * FIXME: memory is allocated starting with the first node * to the last. It would be better if bind would truly restrict * the allocation to memory nodes instead * * preferred Try a specific node first before normal fallback. * As a special case NUMA_NO_NODE here means do the allocation * on the local CPU. This is normally identical to default, * but useful to set in a VMA when you have a non default * process policy. * * preferred many Try a set of nodes first before normal fallback. This is * similar to preferred without the special case. * * default Allocate on the local node first, or when on a VMA * use the process policy. This is what Linux always did * in a NUMA aware kernel and still does by, ahem, default. * * The process policy is applied for most non interrupt memory allocations * in that process' context. Interrupts ignore the policies and always * try to allocate on the local CPU. The VMA policy is only applied for memory * allocations for a VMA in the VM. * * Currently there are a few corner cases in swapping where the policy * is not applied, but the majority should be handled. When process policy * is used it is not remembered over swap outs/swap ins. * * Only the highest zone in the zone hierarchy gets policied. Allocations * requesting a lower zone just use default policy. This implies that * on systems with highmem kernel lowmem allocation don't get policied. * Same with GFP_DMA allocations. * * For shmem/tmpfs shared memory the policy is shared between * all users and remembered even when nobody has memory mapped. */ /* Notebook: fix mmap readahead to honour policy and enable policy for any page cache object statistics for bigpages global policy for page cache? currently it uses process policy. Requires first item above. handle mremap for shared memory (currently ignored for the policy) grows down? make bind policy root only? It can trigger oom much faster and the kernel is not always grateful with that. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mempolicy.h> #include <linux/pagewalk.h> #include <linux/highmem.h> #include <linux/hugetlb.h> #include <linux/kernel.h> #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/sched/numa_balancing.h> #include <linux/sched/sysctl.h> #include <linux/sched/task.h> #include <linux/nodemask.h> #include <linux/cpuset.h> #include <linux/slab.h> #include <linux/string.h> #include <linux/export.h> #include <linux/nsproxy.h> #include <linux/interrupt.h> #include <linux/init.h> #include <linux/compat.h> #include <linux/ptrace.h> #include <linux/swap.h> #include <linux/seq_file.h> #include <linux/proc_fs.h> #include <linux/memory-tiers.h> #include <linux/migrate.h> #include <linux/ksm.h> #include <linux/rmap.h> #include <linux/security.h> #include <linux/syscalls.h> #include <linux/ctype.h> #include <linux/mm_inline.h> #include <linux/mmu_notifier.h> #include <linux/printk.h> #include <linux/leafops.h> #include <linux/gcd.h> #include <asm/tlbflush.h> #include <asm/tlb.h> #include <linux/uaccess.h> #include <linux/memory.h> #include "internal.h" /* Internal flags */ #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */ #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */ #define MPOL_MF_WRLOCK (MPOL_MF_INTERNAL << 2) /* Write-lock walked vmas */ static struct kmem_cache *policy_cache; static struct kmem_cache *sn_cache; /* Highest zone. An specific allocation for a zone below that is not policied. */ enum zone_type policy_zone = 0; /* * run-time system-wide default policy => local allocation */ static struct mempolicy default_policy = { .refcnt = ATOMIC_INIT(1), /* never free it */ .mode = MPOL_LOCAL, }; static struct mempolicy preferred_node_policy[MAX_NUMNODES]; /* * weightiness balances the tradeoff between small weights (cycles through nodes * faster, more fair/even distribution) and large weights (smaller errors * between actual bandwidth ratios and weight ratios). 32 is a number that has * been found to perform at a reasonable compromise between the two goals. */ static const int weightiness = 32; /* * A null weighted_interleave_state is interpreted as having .mode="auto", * and .iw_table is interpreted as an array of 1s with length nr_node_ids. */ struct weighted_interleave_state { bool mode_auto; u8 iw_table[]; }; static struct weighted_interleave_state __rcu *wi_state; static unsigned int *node_bw_table; /* * wi_state_lock protects both wi_state and node_bw_table. * node_bw_table is only used by writers to update wi_state. */ static DEFINE_MUTEX(wi_state_lock); static u8 get_il_weight(int node) { struct weighted_interleave_state *state; u8 weight = 1; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) weight = state->iw_table[node]; rcu_read_unlock(); return weight; } /* * Convert bandwidth values into weighted interleave weights. * Call with wi_state_lock. */ static void reduce_interleave_weights(unsigned int *bw, u8 *new_iw) { u64 sum_bw = 0; unsigned int cast_sum_bw, scaling_factor = 1, iw_gcd = 0; int nid; for_each_node_state(nid, N_MEMORY) sum_bw += bw[nid]; /* Scale bandwidths to whole numbers in the range [1, weightiness] */ for_each_node_state(nid, N_MEMORY) { /* * Try not to perform 64-bit division. * If sum_bw < scaling_factor, then sum_bw < U32_MAX. * If sum_bw > scaling_factor, then round the weight up to 1. */ scaling_factor = weightiness * bw[nid]; if (bw[nid] && sum_bw < scaling_factor) { cast_sum_bw = (unsigned int)sum_bw; new_iw[nid] = scaling_factor / cast_sum_bw; } else { new_iw[nid] = 1; } if (!iw_gcd) iw_gcd = new_iw[nid]; iw_gcd = gcd(iw_gcd, new_iw[nid]); } /* 1:2 is strictly better than 16:32. Reduce by the weights' GCD. */ for_each_node_state(nid, N_MEMORY) new_iw[nid] /= iw_gcd; } int mempolicy_set_node_perf(unsigned int node, struct access_coordinate *coords) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; unsigned int *old_bw, *new_bw; unsigned int bw_val; int i; bw_val = min(coords->read_bandwidth, coords->write_bandwidth); new_bw = kcalloc(nr_node_ids, sizeof(unsigned int), GFP_KERNEL); if (!new_bw) return -ENOMEM; new_wi_state = kmalloc_flex(*new_wi_state, iw_table, nr_node_ids); if (!new_wi_state) { kfree(new_bw); return -ENOMEM; } new_wi_state->mode_auto = true; for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; /* * Update bandwidth info, even in manual mode. That way, when switching * to auto mode in the future, iw_table can be overwritten using * accurate bw data. */ mutex_lock(&wi_state_lock); old_bw = node_bw_table; if (old_bw) memcpy(new_bw, old_bw, nr_node_ids * sizeof(*old_bw)); new_bw[node] = bw_val; node_bw_table = new_bw; old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state && !old_wi_state->mode_auto) { /* Manual mode; skip reducing weights and updating wi_state */ mutex_unlock(&wi_state_lock); kfree(new_wi_state); goto out; } /* NULL wi_state assumes auto=true; reduce weights and update wi_state*/ reduce_interleave_weights(new_bw, new_wi_state->iw_table); rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } out: kfree(old_bw); return 0; } /** * numa_nearest_node - Find nearest node by state * @node: Node id to start the search * @state: State to filter the search * * Lookup the closest node by distance if @nid is not in state. * * Return: this @node if it is in state, otherwise the closest node by distance */ int numa_nearest_node(int node, unsigned int state) { int min_dist = INT_MAX, dist, n, min_node; if (state >= NR_NODE_STATES) return -EINVAL; if (node == NUMA_NO_NODE || node_state(node, state)) return node; min_node = node; for_each_node_state(n, state) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(numa_nearest_node); /** * nearest_node_nodemask - Find the node in @mask at the nearest distance * from @node. * * @node: a valid node ID to start the search from. * @mask: a pointer to a nodemask representing the allowed nodes. * * This function iterates over all nodes in @mask and calculates the * distance from the starting @node, then it returns the node ID that is * the closest to @node, or MAX_NUMNODES if no node is found. * * Note that @node must be a valid node ID usable with node_distance(), * providing an invalid node ID (e.g., NUMA_NO_NODE) may result in crashes * or unexpected behavior. */ int nearest_node_nodemask(int node, nodemask_t *mask) { int dist, n, min_dist = INT_MAX, min_node = MAX_NUMNODES; for_each_node_mask(n, *mask) { dist = node_distance(node, n); if (dist < min_dist) { min_dist = dist; min_node = n; } } return min_node; } EXPORT_SYMBOL_GPL(nearest_node_nodemask); struct mempolicy *get_task_policy(struct task_struct *p) { struct mempolicy *pol = p->mempolicy; int node; if (pol) return pol; node = numa_node_id(); if (node != NUMA_NO_NODE) { pol = &preferred_node_policy[node]; /* preferred_node_policy is not initialised early in boot */ if (pol->mode) return pol; } return &default_policy; } EXPORT_SYMBOL_FOR_MODULES(get_task_policy, "kvm"); static const struct mempolicy_operations { int (*create)(struct mempolicy *pol, const nodemask_t *nodes); void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes); } mpol_ops[MPOL_MAX]; static inline int mpol_store_user_nodemask(const struct mempolicy *pol) { return pol->flags & MPOL_USER_NODEMASK_FLAGS; } static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig, const nodemask_t *rel) { nodemask_t tmp; nodes_fold(tmp, *orig, nodes_weight(*rel)); nodes_onto(*ret, tmp, *rel); } static int mpol_new_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; pol->nodes = *nodes; return 0; } static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes) { if (nodes_empty(*nodes)) return -EINVAL; nodes_clear(pol->nodes); node_set(first_node(*nodes), pol->nodes); return 0; } /* * mpol_set_nodemask is called after mpol_new() to set up the nodemask, if * any, for the new policy. mpol_new() has already validated the nodes * parameter with respect to the policy mode and flags. * * Must be called holding task's alloc_lock to protect task's mems_allowed * and mempolicy. May also be called holding the mmap_lock for write. */ static int mpol_set_nodemask(struct mempolicy *pol, const nodemask_t *nodes, struct nodemask_scratch *nsc) { int ret; /* * Default (pol==NULL) resp. local memory policies are not a * subject of any remapping. They also do not need any special * constructor. */ if (!pol || pol->mode == MPOL_LOCAL) return 0; /* Check N_MEMORY */ nodes_and(nsc->mask1, cpuset_current_mems_allowed, node_states[N_MEMORY]); VM_BUG_ON(!nodes); if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&nsc->mask2, nodes, &nsc->mask1); else nodes_and(nsc->mask2, *nodes, nsc->mask1); if (mpol_store_user_nodemask(pol)) pol->w.user_nodemask = *nodes; else pol->w.cpuset_mems_allowed = cpuset_current_mems_allowed; ret = mpol_ops[pol->mode].create(pol, &nsc->mask2); return ret; } /* * This function just creates a new policy, does some check and simple * initialization. You must invoke mpol_set_nodemask() to set nodes. */ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *policy; if (mode == MPOL_DEFAULT) { if (nodes && !nodes_empty(*nodes)) return ERR_PTR(-EINVAL); return NULL; } VM_BUG_ON(!nodes); /* * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation). * All other modes require a valid pointer to a non-empty nodemask. */ if (mode == MPOL_PREFERRED) { if (nodes_empty(*nodes)) { if (((flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES))) return ERR_PTR(-EINVAL); mode = MPOL_LOCAL; } } else if (mode == MPOL_LOCAL) { if (!nodes_empty(*nodes) || (flags & MPOL_F_STATIC_NODES) || (flags & MPOL_F_RELATIVE_NODES)) return ERR_PTR(-EINVAL); } else if (nodes_empty(*nodes)) return ERR_PTR(-EINVAL); policy = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!policy) return ERR_PTR(-ENOMEM); atomic_set(&policy->refcnt, 1); policy->mode = mode; policy->flags = flags; policy->home_node = NUMA_NO_NODE; return policy; } /* Slow path of a mpol destructor. */ void __mpol_put(struct mempolicy *pol) { if (!atomic_dec_and_test(&pol->refcnt)) return; /* * Required to allow mmap_lock_speculative*() access, see for example * futex_key_to_node_opt(). All accesses are serialized by mmap_lock, * however the speculative lock section unbound by the normal lock * boundaries, requiring RCU freeing. */ kfree_rcu(pol, rcu); } EXPORT_SYMBOL_FOR_MODULES(__mpol_put, "kvm"); static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes) { } static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) { nodemask_t tmp; if (pol->flags & MPOL_F_STATIC_NODES) nodes_and(tmp, pol->w.user_nodemask, *nodes); else if (pol->flags & MPOL_F_RELATIVE_NODES) mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes); else { nodes_remap(tmp, pol->nodes, pol->w.cpuset_mems_allowed, *nodes); pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) tmp = *nodes; pol->nodes = tmp; } static void mpol_rebind_preferred(struct mempolicy *pol, const nodemask_t *nodes) { pol->w.cpuset_mems_allowed = *nodes; } /* * mpol_rebind_policy - Migrate a policy to a different set of nodes * * Per-vma policies are protected by mmap_lock. Allocations using per-task * policies are protected by task->mems_allowed_seq to prevent a premature * OOM/allocation failure due to parallel nodemask modification. */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) return; mpol_ops[pol->mode].rebind(pol, newmask); } /* * Wrapper for mpol_rebind_policy() that just requires task * pointer, and updates task mempolicy. * * Called with task's alloc_lock held. */ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new) { mpol_rebind_policy(tsk->mempolicy, new); } /* * Rebind each vma in mm to new nodemask. * * Call holding a reference to mm. Takes mm->mmap_lock during call. */ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new) { struct vm_area_struct *vma; VMA_ITERATOR(vmi, mm, 0); mmap_write_lock(mm); for_each_vma(vmi, vma) { vma_start_write(vma); mpol_rebind_policy(vma->vm_policy, new); } mmap_write_unlock(mm); } static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { [MPOL_DEFAULT] = { .rebind = mpol_rebind_default, }, [MPOL_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_PREFERRED] = { .create = mpol_new_preferred, .rebind = mpol_rebind_preferred, }, [MPOL_BIND] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, [MPOL_LOCAL] = { .rebind = mpol_rebind_default, }, [MPOL_PREFERRED_MANY] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_preferred, }, [MPOL_WEIGHTED_INTERLEAVE] = { .create = mpol_new_nodemask, .rebind = mpol_rebind_nodemask, }, }; static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags); static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid); static bool strictly_unmovable(unsigned long flags) { /* * STRICT without MOVE flags lets do_mbind() fail immediately with -EIO * if any misplaced page is found. */ return (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) == MPOL_MF_STRICT; } struct migration_mpol { /* for alloc_migration_target_by_mpol() */ struct mempolicy *pol; pgoff_t ilx; }; struct queue_pages { struct list_head *pagelist; unsigned long flags; nodemask_t *nmask; unsigned long start; unsigned long end; struct vm_area_struct *first; struct folio *large; /* note last large folio encountered */ long nr_failed; /* could not be isolated at this time */ }; /* * Check if the folio's nid is in qp->nmask. * * If MPOL_MF_INVERT is set in qp->flags, check if the nid is * in the invert of qp->nmask. */ static inline bool queue_folio_required(struct folio *folio, struct queue_pages *qp) { int nid = folio_nid(folio); unsigned long flags = qp->flags; return node_isset(nid, *qp->nmask) == !(flags & MPOL_MF_INVERT); } static void queue_folios_pmd(pmd_t *pmd, struct mm_walk *walk) { struct folio *folio; struct queue_pages *qp = walk->private; if (unlikely(pmd_is_migration_entry(*pmd))) { qp->nr_failed++; return; } folio = pmd_folio(*pmd); if (is_huge_zero_folio(folio)) { walk->action = ACTION_CONTINUE; return; } if (!queue_folio_required(folio, qp)) return; if (!(qp->flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma) || !migrate_folio_add(folio, qp->pagelist, qp->flags)) qp->nr_failed++; } /* * Scan through folios, checking if they satisfy the required conditions, * moving them from LRU to local pagelist for migration if they do (or not). * * queue_folios_pte_range() has two possible return values: * 0 - continue walking to scan for more, even if an existing folio on the * wrong node could not be isolated and queued for migration. * -EIO - only MPOL_MF_STRICT was specified, without MPOL_MF_MOVE or ..._ALL, * and an existing folio was on a node that does not follow the policy. */ static int queue_folios_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *vma = walk->vma; struct folio *folio; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; pte_t *pte, *mapped_pte; pte_t ptent; spinlock_t *ptl; int max_nr, nr; ptl = pmd_trans_huge_lock(pmd, vma); if (ptl) { queue_folios_pmd(pmd, walk); spin_unlock(ptl); goto out; } mapped_pte = pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); if (!pte) { walk->action = ACTION_AGAIN; return 0; } for (; addr != end; pte += nr, addr += nr * PAGE_SIZE) { max_nr = (end - addr) >> PAGE_SHIFT; nr = 1; ptent = ptep_get(pte); if (pte_none(ptent)) continue; if (!pte_present(ptent)) { const softleaf_t entry = softleaf_from_pte(ptent); if (softleaf_is_migration(entry)) qp->nr_failed++; continue; } folio = vm_normal_folio(vma, addr, ptent); if (!folio || folio_is_zone_device(folio)) continue; if (folio_test_large(folio) && max_nr != 1) nr = folio_pte_batch(folio, pte, ptent, max_nr); /* * vm_normal_folio() filters out zero pages, but there might * still be reserved folios to skip, perhaps in a VDSO. */ if (folio_test_reserved(folio)) continue; if (!queue_folio_required(folio, qp)) continue; if (folio_test_large(folio)) { /* * A large folio can only be isolated from LRU once, * but may be mapped by many PTEs (and Copy-On-Write may * intersperse PTEs of other, order 0, folios). This is * a common case, so don't mistake it for failure (but * there can be other cases of multi-mapped pages which * this quick check does not help to filter out - and a * search of the pagelist might grow to be prohibitive). * * migrate_pages(&pagelist) returns nr_failed folios, so * check "large" now so that queue_pages_range() returns * a comparable nr_failed folios. This does imply that * if folio could not be isolated for some racy reason * at its first PTE, later PTEs will not give it another * chance of isolation; but keeps the accounting simple. */ if (folio == qp->large) continue; qp->large = folio; } if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(vma) || !migrate_folio_add(folio, qp->pagelist, flags)) { qp->nr_failed += nr; if (strictly_unmovable(flags)) break; } } pte_unmap_unlock(mapped_pte, ptl); cond_resched(); out: if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; return 0; } static int queue_folios_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; struct folio *folio; spinlock_t *ptl; pte_t ptep; ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); ptep = huge_ptep_get(walk->mm, addr, pte); if (!pte_present(ptep)) { if (!huge_pte_none(ptep)) { const softleaf_t entry = softleaf_from_pte(ptep); if (unlikely(softleaf_is_migration(entry))) qp->nr_failed++; } goto unlock; } folio = pfn_folio(pte_pfn(ptep)); if (!queue_folio_required(folio, qp)) goto unlock; if (!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) || !vma_migratable(walk->vma)) { qp->nr_failed++; goto unlock; } /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || (!folio_maybe_mapped_shared(folio) && !hugetlb_pmd_shared(pte))) if (!folio_isolate_hugetlb(folio, qp->pagelist)) qp->nr_failed++; unlock: spin_unlock(ptl); if (qp->nr_failed && strictly_unmovable(flags)) return -EIO; #endif return 0; } #ifdef CONFIG_NUMA_BALANCING /** * folio_can_map_prot_numa() - check whether the folio can map prot numa * @folio: The folio whose mapping considered for being made NUMA hintable * @vma: The VMA that the folio belongs to. * @is_private_single_threaded: Is this a single-threaded private VMA or not * * This function checks to see if the folio actually indicates that * we need to make the mapping one which causes a NUMA hinting fault, * as there are cases where it's simply unnecessary, and the folio's * access time is adjusted for memory tiering if prot numa needed. * * Return: True if the mapping of the folio needs to be changed, false otherwise. */ bool folio_can_map_prot_numa(struct folio *folio, struct vm_area_struct *vma, bool is_private_single_threaded) { int nid; if (!folio || folio_is_zone_device(folio) || folio_test_ksm(folio)) return false; /* Also skip shared copy-on-write folios */ if (is_cow_mapping(vma->vm_flags) && folio_maybe_mapped_shared(folio)) return false; /* Folios are pinned and can't be migrated */ if (folio_maybe_dma_pinned(folio)) return false; /* * While migration can move some dirty folios, * it cannot move them all from MIGRATE_ASYNC * context. */ if (folio_is_file_lru(folio) && folio_test_dirty(folio)) return false; /* * Don't mess with PTEs if folio is already on the node * a single-threaded process is running on. */ nid = folio_nid(folio); if (is_private_single_threaded && (nid == numa_node_id())) return false; /* * Skip scanning top tier node if normal numa * balancing is disabled */ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_NORMAL) && node_is_toptier(nid)) return false; if (folio_use_access_time(folio)) folio_xchg_access_time(folio, jiffies_to_msecs(jiffies)); return true; } /* * This is used to mark a range of virtual addresses to be inaccessible. * These are later cleared by a NUMA hinting fault. Depending on these * faults, pages may be migrated for better NUMA placement. * * This is assuming that NUMA faults are handled using PROT_NONE. If * an architecture makes a different choice, it will need further * changes to the core. */ unsigned long change_prot_numa(struct vm_area_struct *vma, unsigned long addr, unsigned long end) { struct mmu_gather tlb; long nr_updated; tlb_gather_mmu(&tlb, vma->vm_mm); nr_updated = change_protection(&tlb, vma, addr, end, MM_CP_PROT_NUMA); if (nr_updated > 0) { count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); count_memcg_events_mm(vma->vm_mm, NUMA_PTE_UPDATES, nr_updated); } tlb_finish_mmu(&tlb); return nr_updated; } #endif /* CONFIG_NUMA_BALANCING */ static int queue_pages_test_walk(unsigned long start, unsigned long end, struct mm_walk *walk) { struct vm_area_struct *next, *vma = walk->vma; struct queue_pages *qp = walk->private; unsigned long flags = qp->flags; /* range check first */ VM_BUG_ON_VMA(!range_in_vma(vma, start, end), vma); if (!qp->first) { qp->first = vma; if (!(flags & MPOL_MF_DISCONTIG_OK) && (qp->start < vma->vm_start)) /* hole at head side of range */ return -EFAULT; } next = find_vma(vma->vm_mm, vma->vm_end); if (!(flags & MPOL_MF_DISCONTIG_OK) && ((vma->vm_end < qp->end) && (!next || vma->vm_end < next->vm_start))) /* hole at middle or tail of range */ return -EFAULT; /* * Need check MPOL_MF_STRICT to return -EIO if possible * regardless of vma_migratable */ if (!vma_migratable(vma) && !(flags & MPOL_MF_STRICT)) return 1; /* * Check page nodes, and queue pages to move, in the current vma. * But if no moving, and no strict checking, the scan can be skipped. */ if (flags & (MPOL_MF_STRICT | MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } static const struct mm_walk_ops queue_pages_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_RDLOCK, }; static const struct mm_walk_ops queue_pages_lock_vma_walk_ops = { .hugetlb_entry = queue_folios_hugetlb, .pmd_entry = queue_folios_pte_range, .test_walk = queue_pages_test_walk, .walk_lock = PGWALK_WRLOCK, }; /* * Walk through page tables and collect pages to be migrated. * * If pages found in a given range are not on the required set of @nodes, * and migration is allowed, they are isolated and queued to @pagelist. * * queue_pages_range() may return: * 0 - all pages already on the right node, or successfully queued for moving * (or neither strict checking nor moving requested: only range checking). * >0 - this number of misplaced folios could not be queued for moving * (a hugetlbfs page or a transparent huge page being counted as 1). * -EIO - a misplaced page found, when MPOL_MF_STRICT specified without MOVEs. * -EFAULT - a hole in the memory range, when MPOL_MF_DISCONTIG_OK unspecified. */ static long queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, nodemask_t *nodes, unsigned long flags, struct list_head *pagelist) { int err; struct queue_pages qp = { .pagelist = pagelist, .flags = flags, .nmask = nodes, .start = start, .end = end, .first = NULL, }; const struct mm_walk_ops *ops = (flags & MPOL_MF_WRLOCK) ? &queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops; err = walk_page_range(mm, start, end, ops, &qp); if (!qp.first) /* whole range in hole */ err = -EFAULT; return err ? : qp.nr_failed; } /* * Apply policy to a single VMA * This must be called with the mmap_lock held for writing. */ static int vma_replace_policy(struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct mempolicy *old; struct mempolicy *new; vma_assert_write_locked(vma); new = mpol_dup(pol); if (IS_ERR(new)) return PTR_ERR(new); if (vma->vm_ops && vma->vm_ops->set_policy) { err = vma->vm_ops->set_policy(vma, new); if (err) goto err_out; } old = vma->vm_policy; WRITE_ONCE(vma->vm_policy, new); /* protected by mmap_lock */ mpol_put(old); return 0; err_out: mpol_put(new); return err; } /* Split or merge the VMA (if required) and apply the new policy */ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma, struct vm_area_struct **prev, unsigned long start, unsigned long end, struct mempolicy *new_pol) { unsigned long vmstart, vmend; vmend = min(end, vma->vm_end); if (start > vma->vm_start) { *prev = vma; vmstart = start; } else { vmstart = vma->vm_start; } if (mpol_equal(vma->vm_policy, new_pol)) { *prev = vma; return 0; } vma = vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol); if (IS_ERR(vma)) return PTR_ERR(vma); *prev = vma; return vma_replace_policy(vma, new_pol); } /* Set the process memory policy */ static long do_set_mempolicy(unsigned short mode, unsigned short flags, nodemask_t *nodes) { struct mempolicy *new, *old; NODEMASK_SCRATCH(scratch); int ret; if (!scratch) return -ENOMEM; new = mpol_new(mode, flags, nodes); if (IS_ERR(new)) { ret = PTR_ERR(new); goto out; } task_lock(current); ret = mpol_set_nodemask(new, nodes, scratch); if (ret) { task_unlock(current); mpol_put(new); goto out; } old = current->mempolicy; current->mempolicy = new; if (new && (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE)) { current->il_prev = MAX_NUMNODES-1; current->il_weight = 0; } task_unlock(current); mpol_put(old); ret = 0; out: NODEMASK_SCRATCH_FREE(scratch); return ret; } /* * Return nodemask for policy for get_mempolicy() query * * Called with task's alloc_lock held */ static void get_policy_nodemask(struct mempolicy *pol, nodemask_t *nodes) { nodes_clear(*nodes); if (pol == &default_policy) return; switch (pol->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: *nodes = pol->nodes; break; case MPOL_LOCAL: /* return empty node mask for local allocation */ break; default: BUG(); } } static int lookup_node(struct mm_struct *mm, unsigned long addr) { struct page *p = NULL; int ret; ret = get_user_pages_fast(addr & PAGE_MASK, 1, 0, &p); if (ret > 0) { ret = page_to_nid(p); put_page(p); } return ret; } /* Retrieve NUMA policy */ static long do_get_mempolicy(int *policy, nodemask_t *nmask, unsigned long addr, unsigned long flags) { int err; struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct mempolicy *pol = current->mempolicy, *pol_refcount = NULL; if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR|MPOL_F_MEMS_ALLOWED)) return -EINVAL; if (flags & MPOL_F_MEMS_ALLOWED) { if (flags & (MPOL_F_NODE|MPOL_F_ADDR)) return -EINVAL; *policy = 0; /* just so it's initialized */ task_lock(current); *nmask = cpuset_current_mems_allowed; task_unlock(current); return 0; } if (flags & MPOL_F_ADDR) { pgoff_t ilx; /* ignored here */ /* * Do NOT fall back to task policy if the * vma/shared policy at addr is NULL. We * want to return MPOL_DEFAULT in this case. */ mmap_read_lock(mm); vma = vma_lookup(mm, addr); if (!vma) { mmap_read_unlock(mm); return -EFAULT; } pol = __get_vma_policy(vma, addr, &ilx); } else if (addr) return -EINVAL; if (!pol) pol = &default_policy; /* indicates default behavior */ if (flags & MPOL_F_NODE) { if (flags & MPOL_F_ADDR) { /* * Take a refcount on the mpol, because we are about to * drop the mmap_lock, after which only "pol" remains * valid, "vma" is stale. */ pol_refcount = pol; vma = NULL; mpol_get(pol); mmap_read_unlock(mm); err = lookup_node(mm, addr); if (err < 0) goto out; *policy = err; } else if (pol == current->mempolicy && pol->mode == MPOL_INTERLEAVE) { *policy = next_node_in(current->il_prev, pol->nodes); } else if (pol == current->mempolicy && pol->mode == MPOL_WEIGHTED_INTERLEAVE) { if (current->il_weight) *policy = current->il_prev; else *policy = next_node_in(current->il_prev, pol->nodes); } else { err = -EINVAL; goto out; } } else { *policy = pol == &default_policy ? MPOL_DEFAULT : pol->mode; /* * Internal mempolicy flags must be masked off before exposing * the policy to userspace. */ *policy |= (pol->flags & MPOL_MODE_FLAGS); } err = 0; if (nmask) { if (mpol_store_user_nodemask(pol)) { *nmask = pol->w.user_nodemask; } else { task_lock(current); get_policy_nodemask(pol, nmask); task_unlock(current); } } out: mpol_cond_put(pol); if (vma) mmap_read_unlock(mm); if (pol_refcount) mpol_put(pol_refcount); return err; } #ifdef CONFIG_NUMA_MIGRATION static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { /* * Unless MPOL_MF_MOVE_ALL, we try to avoid migrating a shared folio. * Choosing not to migrate a shared folio is not counted as a failure. * * See folio_maybe_mapped_shared() on possible imprecision when we * cannot easily detect if a folio is shared. */ if ((flags & MPOL_MF_MOVE_ALL) || !folio_maybe_mapped_shared(folio)) { if (folio_isolate_lru(folio)) { list_add_tail(&folio->lru, foliolist); node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio), folio_nr_pages(folio)); } else { /* * Non-movable folio may reach here. And, there may be * temporary off LRU folios or non-LRU movable folios. * Treat them as unmovable folios since they can't be * isolated, so they can't be moved at the moment. */ return false; } } return true; } /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. */ static long migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) { nodemask_t nmask; struct vm_area_struct *vma; LIST_HEAD(pagelist); long nr_failed; long err = 0; struct migration_target_control mtc = { .nid = dest, .gfp_mask = GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, .reason = MR_SYSCALL, }; nodes_clear(nmask); node_set(source, nmask); VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))); mmap_read_lock(mm); vma = find_vma(mm, 0); if (unlikely(!vma)) { mmap_read_unlock(mm); return 0; } /* * This does not migrate the range, but isolates all pages that * need migration. Between passing in the full user address * space range and MPOL_MF_DISCONTIG_OK, this call cannot fail, * but passes back the count of pages which could not be isolated. */ nr_failed = queue_pages_range(mm, vma->vm_start, mm->task_size, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); mmap_read_unlock(mm); if (!list_empty(&pagelist)) { err = migrate_pages(&pagelist, alloc_migration_target, NULL, (unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL); if (err) putback_movable_pages(&pagelist); } if (err >= 0) err += nr_failed; return err; } /* * Move pages between the two nodesets so as to preserve the physical * layout as much as possible. * * Returns the number of page that could not be moved. */ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { long nr_failed = 0; long err = 0; nodemask_t tmp; lru_cache_disable(); /* * Find a 'source' bit set in 'tmp' whose corresponding 'dest' * bit in 'to' is not also set in 'tmp'. Clear the found 'source' * bit in 'tmp', and return that <source, dest> pair for migration. * The pair of nodemasks 'to' and 'from' define the map. * * If no pair of bits is found that way, fallback to picking some * pair of 'source' and 'dest' bits that are not the same. If the * 'source' and 'dest' bits are the same, this represents a node * that will be migrating to itself, so no pages need move. * * If no bits are left in 'tmp', or if all remaining bits left * in 'tmp' correspond to the same bit in 'to', return false * (nothing left to migrate). * * This lets us pick a pair of nodes to migrate between, such that * if possible the dest node is not already occupied by some other * source node, minimizing the risk of overloading the memory on a * node that would happen if we migrated incoming memory to a node * before migrating outgoing memory source that same node. * * A single scan of tmp is sufficient. As we go, we remember the * most recent <s, d> pair that moved (s != d). If we find a pair * that not only moved, but what's better, moved to an empty slot * (d is not set in tmp), then we break out then, with that pair. * Otherwise when we finish scanning from_tmp, we at least have the * most recent <s, d> pair that moved. If we get all the way through * the scan of tmp without finding any node that moved, much less * moved to an empty node, then there is nothing left worth migrating. */ tmp = *from; while (!nodes_empty(tmp)) { int s, d; int source = NUMA_NO_NODE; int dest = 0; for_each_node_mask(s, tmp) { /* * do_migrate_pages() tries to maintain the relative * node relationship of the pages established between * threads and memory areas. * * However if the number of source nodes is not equal to * the number of destination nodes we can not preserve * this node relative relationship. In that case, skip * copying memory from a node that is in the destination * mask. * * Example: [2,3,4] -> [3,4,5] moves everything. * [0-7] - > [3,4,5] moves only 0,1,2,6,7. */ if ((nodes_weight(*from) != nodes_weight(*to)) && (node_isset(s, *to))) continue; d = node_remap(s, *from, *to); if (s == d) continue; source = s; /* Node moved. Memorize */ dest = d; /* dest not in remaining from nodes? */ if (!node_isset(dest, tmp)) break; } if (source == NUMA_NO_NODE) break; node_clear(source, tmp); err = migrate_to_node(mm, source, dest, flags); if (err > 0) nr_failed += err; if (err < 0) break; } lru_cache_enable(); if (err < 0) return err; return (nr_failed < INT_MAX) ? nr_failed : INT_MAX; } /* * Allocate a new folio for page migration, according to NUMA mempolicy. */ static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { struct migration_mpol *mmpol = (struct migration_mpol *)private; struct mempolicy *pol = mmpol->pol; pgoff_t ilx = mmpol->ilx; unsigned int order; int nid = numa_node_id(); gfp_t gfp; order = folio_order(src); ilx += src->index >> order; if (folio_test_hugetlb(src)) { nodemask_t *nodemask; struct hstate *h; h = folio_hstate(src); gfp = htlb_alloc_mask(h); nodemask = policy_nodemask(gfp, pol, ilx, &nid); return alloc_hugetlb_folio_nodemask(h, nid, nodemask, gfp, htlb_allow_alloc_fallback(MR_MEMPOLICY_MBIND)); } if (folio_test_large(src)) gfp = GFP_TRANSHUGE; else gfp = GFP_HIGHUSER_MOVABLE | __GFP_RETRY_MAYFAIL | __GFP_COMP; return folio_alloc_mpol(gfp, order, pol, ilx, nid); } #else static bool migrate_folio_add(struct folio *folio, struct list_head *foliolist, unsigned long flags) { return false; } int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, const nodemask_t *to, int flags) { return -ENOSYS; } static struct folio *alloc_migration_target_by_mpol(struct folio *src, unsigned long private) { return NULL; } #endif static long do_mbind(unsigned long start, unsigned long len, unsigned short mode, unsigned short mode_flags, nodemask_t *nmask, unsigned long flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct vma_iterator vmi; struct migration_mpol mmpol; struct mempolicy *new; unsigned long end; long err; long nr_failed; LIST_HEAD(pagelist); if (flags & ~(unsigned long)MPOL_MF_VALID) return -EINVAL; if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) return -EPERM; if (start & ~PAGE_MASK) return -EINVAL; if (mode == MPOL_DEFAULT) flags &= ~MPOL_MF_STRICT; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; new = mpol_new(mode, mode_flags, nmask); if (IS_ERR(new)) return PTR_ERR(new); /* * If we are using the default policy then operation * on discontinuous address spaces is okay after all */ if (!new) flags |= MPOL_MF_DISCONTIG_OK; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_disable(); { NODEMASK_SCRATCH(scratch); if (scratch) { mmap_write_lock(mm); err = mpol_set_nodemask(new, nmask, scratch); if (err) mmap_write_unlock(mm); } else err = -ENOMEM; NODEMASK_SCRATCH_FREE(scratch); } if (err) goto mpol_out; /* * Lock the VMAs before scanning for pages to migrate, * to ensure we don't miss a concurrently inserted page. */ nr_failed = queue_pages_range(mm, start, end, nmask, flags | MPOL_MF_INVERT | MPOL_MF_WRLOCK, &pagelist); if (nr_failed < 0) { err = nr_failed; nr_failed = 0; } else { vma_iter_init(&vmi, mm, start); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { err = mbind_range(&vmi, vma, &prev, start, end, new); if (err) break; } } if (!err && !list_empty(&pagelist)) { /* Convert MPOL_DEFAULT's NULL to task or default policy */ if (!new) { new = get_task_policy(current); mpol_get(new); } mmpol.pol = new; mmpol.ilx = 0; /* * In the interleaved case, attempt to allocate on exactly the * targeted nodes, for the first VMA to be migrated; for later * VMAs, the nodes will still be interleaved from the targeted * nodemask, but one by one may be selected differently. */ if (new->mode == MPOL_INTERLEAVE || new->mode == MPOL_WEIGHTED_INTERLEAVE) { struct folio *folio; unsigned int order; unsigned long addr = -EFAULT; list_for_each_entry(folio, &pagelist, lru) { if (!folio_test_ksm(folio)) break; } if (!list_entry_is_head(folio, &pagelist, lru)) { vma_iter_init(&vmi, mm, start); for_each_vma_range(vmi, vma, end) { addr = page_address_in_vma(folio, folio_page(folio, 0), vma); if (addr != -EFAULT) break; } } if (addr != -EFAULT) { order = folio_order(folio); /* We already know the pol, but not the ilx */ mpol_cond_put(get_vma_policy(vma, addr, order, &mmpol.ilx)); /* Set base from which to increment by index */ mmpol.ilx -= folio->index >> order; } } } mmap_write_unlock(mm); if (!err && !list_empty(&pagelist)) { nr_failed |= migrate_pages(&pagelist, alloc_migration_target_by_mpol, NULL, (unsigned long)&mmpol, MIGRATE_SYNC, MR_MEMPOLICY_MBIND, NULL); } if (nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; if (!list_empty(&pagelist)) putback_movable_pages(&pagelist); mpol_out: mpol_put(new); if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) lru_cache_enable(); return err; } /* * User space interface with variable sized bitmaps for nodelists. */ static int get_bitmap(unsigned long *mask, const unsigned long __user *nmask, unsigned long maxnode) { unsigned long nlongs = BITS_TO_LONGS(maxnode); int ret; if (in_compat_syscall()) ret = compat_get_bitmap(mask, (const compat_ulong_t __user *)nmask, maxnode); else ret = copy_from_user(mask, nmask, nlongs * sizeof(unsigned long)); if (ret) return -EFAULT; if (maxnode % BITS_PER_LONG) mask[nlongs - 1] &= (1UL << (maxnode % BITS_PER_LONG)) - 1; return 0; } /* Copy a node mask from user space. */ static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask, unsigned long maxnode) { --maxnode; nodes_clear(*nodes); if (maxnode == 0 || !nmask) return 0; if (maxnode > PAGE_SIZE*BITS_PER_BYTE) return -EINVAL; /* * When the user specified more nodes than supported just check * if the non supported part is all zero, one word at a time, * starting at the end. */ while (maxnode > MAX_NUMNODES) { unsigned long bits = min_t(unsigned long, maxnode, BITS_PER_LONG); unsigned long t; if (get_bitmap(&t, &nmask[(maxnode - 1) / BITS_PER_LONG], bits)) return -EFAULT; if (maxnode - bits >= MAX_NUMNODES) { maxnode -= bits; } else { maxnode = MAX_NUMNODES; t &= ~((1UL << (MAX_NUMNODES % BITS_PER_LONG)) - 1); } if (t) return -EINVAL; } return get_bitmap(nodes_addr(*nodes), nmask, maxnode); } /* Copy a kernel node mask to user space */ static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode, nodemask_t *nodes) { unsigned long copy = ALIGN(maxnode-1, 64) / 8; unsigned int nbytes = BITS_TO_LONGS(nr_node_ids) * sizeof(long); bool compat = in_compat_syscall(); if (compat) nbytes = BITS_TO_COMPAT_LONGS(nr_node_ids) * sizeof(compat_long_t); if (copy > nbytes) { if (copy > PAGE_SIZE) return -EINVAL; if (clear_user((char __user *)mask + nbytes, copy - nbytes)) return -EFAULT; copy = nbytes; maxnode = nr_node_ids; } if (compat) return compat_put_bitmap((compat_ulong_t __user *)mask, nodes_addr(*nodes), maxnode); return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0; } /* Basic parameter sanity check used by both mbind() and set_mempolicy() */ static inline int sanitize_mpol_flags(int *mode, unsigned short *flags) { *flags = *mode & MPOL_MODE_FLAGS; *mode &= ~MPOL_MODE_FLAGS; if ((unsigned int)(*mode) >= MPOL_MAX) return -EINVAL; if ((*flags & MPOL_F_STATIC_NODES) && (*flags & MPOL_F_RELATIVE_NODES)) return -EINVAL; if (*flags & MPOL_F_NUMA_BALANCING) { if (*mode == MPOL_BIND || *mode == MPOL_PREFERRED_MANY) *flags |= (MPOL_F_MOF | MPOL_F_MORON); else return -EINVAL; } return 0; } static long kernel_mbind(unsigned long start, unsigned long len, unsigned long mode, const unsigned long __user *nmask, unsigned long maxnode, unsigned int flags) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; start = untagged_addr(start); err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_mbind(start, len, lmode, mode_flags, &nodes, flags); } SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len, unsigned long, home_node, unsigned long, flags) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma, *prev; struct mempolicy *new, *old; unsigned long end; int err = -ENOENT; VMA_ITERATOR(vmi, mm, start); start = untagged_addr(start); if (start & ~PAGE_MASK) return -EINVAL; /* * flags is used for future extension if any. */ if (flags != 0) return -EINVAL; /* * Check home_node is online to avoid accessing uninitialized * NODE_DATA. */ if (home_node >= MAX_NUMNODES || !node_online(home_node)) return -EINVAL; len = PAGE_ALIGN(len); end = start + len; if (end < start) return -EINVAL; if (end == start) return 0; mmap_write_lock(mm); prev = vma_prev(&vmi); for_each_vma_range(vmi, vma, end) { /* * If any vma in the range got policy other than MPOL_BIND * or MPOL_PREFERRED_MANY we return error. We don't reset * the home node for vmas we already updated before. */ old = vma_policy(vma); if (!old) { prev = vma; continue; } if (old->mode != MPOL_BIND && old->mode != MPOL_PREFERRED_MANY) { err = -EOPNOTSUPP; break; } new = mpol_dup(old); if (IS_ERR(new)) { err = PTR_ERR(new); break; } vma_start_write(vma); new->home_node = home_node; err = mbind_range(&vmi, vma, &prev, start, end, new); mpol_put(new); if (err) break; } mmap_write_unlock(mm); return err; } SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len, unsigned long, mode, const unsigned long __user *, nmask, unsigned long, maxnode, unsigned int, flags) { return kernel_mbind(start, len, mode, nmask, maxnode, flags); } /* Set the process memory policy */ static long kernel_set_mempolicy(int mode, const unsigned long __user *nmask, unsigned long maxnode) { unsigned short mode_flags; nodemask_t nodes; int lmode = mode; int err; err = sanitize_mpol_flags(&lmode, &mode_flags); if (err) return err; err = get_nodes(&nodes, nmask, maxnode); if (err) return err; return do_set_mempolicy(lmode, mode_flags, &nodes); } SYSCALL_DEFINE3(set_mempolicy, int, mode, const unsigned long __user *, nmask, unsigned long, maxnode) { return kernel_set_mempolicy(mode, nmask, maxnode); } static int kernel_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *old_nodes, const unsigned long __user *new_nodes) { struct mm_struct *mm = NULL; struct task_struct *task; nodemask_t task_nodes; int err; nodemask_t *old; nodemask_t *new; NODEMASK_SCRATCH(scratch); if (!scratch) return -ENOMEM; old = &scratch->mask1; new = &scratch->mask2; err = get_nodes(old, old_nodes, maxnode); if (err) goto out; err = get_nodes(new, new_nodes, maxnode); if (err) goto out; /* Find the mm_struct */ rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { rcu_read_unlock(); err = -ESRCH; goto out; } get_task_struct(task); err = -EINVAL; /* * Check if this process has the right to modify the specified process. * Use the regular "ptrace_may_access()" checks. */ if (!ptrace_may_access(task, PTRACE_MODE_READ_REALCREDS)) { rcu_read_unlock(); err = -EPERM; goto out_put; } rcu_read_unlock(); task_nodes = cpuset_mems_allowed(task); /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; goto out_put; } task_nodes = cpuset_mems_allowed(current); if (!nodes_and(*new, *new, task_nodes)) goto out_put; err = security_task_movememory(task); if (err) goto out_put; mm = get_task_mm(task); put_task_struct(task); if (!mm) { err = -EINVAL; goto out; } err = do_migrate_pages(mm, old, new, capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); mmput(mm); out: NODEMASK_SCRATCH_FREE(scratch); return err; out_put: put_task_struct(task); goto out; } SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, const unsigned long __user *, old_nodes, const unsigned long __user *, new_nodes) { return kernel_migrate_pages(pid, maxnode, old_nodes, new_nodes); } /* Retrieve NUMA policy */ static int kernel_get_mempolicy(int __user *policy, unsigned long __user *nmask, unsigned long maxnode, unsigned long addr, unsigned long flags) { int err; int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) return -EINVAL; addr = untagged_addr(addr); err = do_get_mempolicy(&pval, &nodes, addr, flags); if (err) return err; if (policy && put_user(pval, policy)) return -EFAULT; if (nmask) err = copy_nodes_to_user(nmask, maxnode, &nodes); return err; } SYSCALL_DEFINE5(get_mempolicy, int __user *, policy, unsigned long __user *, nmask, unsigned long, maxnode, unsigned long, addr, unsigned long, flags) { return kernel_get_mempolicy(policy, nmask, maxnode, addr, flags); } bool vma_migratable(struct vm_area_struct *vma) { if (vma->vm_flags & (VM_IO | VM_PFNMAP)) return false; /* * DAX device mappings require predictable access latency, so avoid * incurring periodic faults. */ if (vma_is_dax(vma)) return false; if (is_vm_hugetlb_page(vma) && !hugepage_migration_supported(hstate_vma(vma))) return false; /* * Migration allocates pages in the highest zone. If we cannot * do so then migration (at least from node to node) is not * possible. */ if (vma->vm_file && gfp_zone(mapping_gfp_mask(vma->vm_file->f_mapping)) < policy_zone) return false; return true; } struct mempolicy *__get_vma_policy(struct vm_area_struct *vma, unsigned long addr, pgoff_t *ilx) { *ilx = 0; return (vma->vm_ops && vma->vm_ops->get_policy) ? vma->vm_ops->get_policy(vma, addr, ilx) : vma->vm_policy; } /* * get_vma_policy(@vma, @addr, @order, @ilx) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup * @order: 0, or appropriate huge_page_order for interleaving * @ilx: interleave index (output), for use only when MPOL_INTERLEAVE or * MPOL_WEIGHTED_INTERLEAVE * * Returns effective policy for a VMA at specified address. * Falls back to current->mempolicy or system default policy, as necessary. * Shared policies [those marked as MPOL_F_SHARED] require an extra reference * count--added by the get_policy() vm_op, as appropriate--to protect against * freeing by another task. It is the caller's responsibility to free the * extra reference for shared policies. */ struct mempolicy *get_vma_policy(struct vm_area_struct *vma, unsigned long addr, int order, pgoff_t *ilx) { struct mempolicy *pol; pol = __get_vma_policy(vma, addr, ilx); if (!pol) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) { *ilx += vma->vm_pgoff >> order; *ilx += (addr - vma->vm_start) >> (PAGE_SHIFT + order); } return pol; } bool vma_policy_mof(struct vm_area_struct *vma) { struct mempolicy *pol; if (vma->vm_ops && vma->vm_ops->get_policy) { bool ret = false; pgoff_t ilx; /* ignored here */ pol = vma->vm_ops->get_policy(vma, vma->vm_start, &ilx); if (pol && (pol->flags & MPOL_F_MOF)) ret = true; mpol_cond_put(pol); return ret; } pol = vma->vm_policy; if (!pol) pol = get_task_policy(current); return pol->flags & MPOL_F_MOF; } bool apply_policy_zone(struct mempolicy *policy, enum zone_type zone) { enum zone_type dynamic_policy_zone = policy_zone; BUG_ON(dynamic_policy_zone == ZONE_MOVABLE); /* * if policy->nodes has movable memory only, * we apply policy when gfp_zone(gfp) = ZONE_MOVABLE only. * * policy->nodes is intersect with node_states[N_MEMORY]. * so if the following test fails, it implies * policy->nodes has movable memory only. */ if (!nodes_intersects(policy->nodes, node_states[N_HIGH_MEMORY])) dynamic_policy_zone = ZONE_MOVABLE; return zone >= dynamic_policy_zone; } static unsigned int weighted_interleave_nodes(struct mempolicy *policy) { unsigned int node; unsigned int cpuset_mems_cookie; retry: /* to prevent miscount use tsk->mems_allowed_seq to detect rebind */ cpuset_mems_cookie = read_mems_allowed_begin(); node = current->il_prev; if (!current->il_weight || !node_isset(node, policy->nodes)) { node = next_node_in(node, policy->nodes); if (read_mems_allowed_retry(cpuset_mems_cookie)) goto retry; if (node == MAX_NUMNODES) return node; current->il_prev = node; current->il_weight = get_il_weight(node); } current->il_weight--; return node; } /* Do dynamic interleaving for a process */ static unsigned int interleave_nodes(struct mempolicy *policy) { unsigned int nid; unsigned int cpuset_mems_cookie; /* to prevent miscount, use tsk->mems_allowed_seq to detect rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nid = next_node_in(current->il_prev, policy->nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); if (nid < MAX_NUMNODES) current->il_prev = nid; return nid; } /* * Depending on the memory policy provide a node from which to allocate the * next slab entry. */ unsigned int mempolicy_slab_node(void) { struct mempolicy *policy; int node = numa_mem_id(); if (!in_task()) return node; policy = current->mempolicy; if (!policy) return node; switch (policy->mode) { case MPOL_PREFERRED: return first_node(policy->nodes); case MPOL_INTERLEAVE: return interleave_nodes(policy); case MPOL_WEIGHTED_INTERLEAVE: return weighted_interleave_nodes(policy); case MPOL_BIND: case MPOL_PREFERRED_MANY: { struct zoneref *z; /* * Follow bind policy behavior and start allocation at the * first node. */ struct zonelist *zonelist; enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL); zonelist = &NODE_DATA(node)->node_zonelists[ZONELIST_FALLBACK]; z = first_zones_zonelist(zonelist, highest_zoneidx, &policy->nodes); return zonelist_zone(z) ? zonelist_node_idx(z) : node; } case MPOL_LOCAL: return node; default: BUG(); } } static unsigned int read_once_policy_nodemask(struct mempolicy *pol, nodemask_t *mask) { /* * barrier stabilizes the nodemask locally so that it can be iterated * over safely without concern for changes. Allocators validate node * selection does not violate mems_allowed, so this is safe. */ barrier(); memcpy(mask, &pol->nodes, sizeof(nodemask_t)); barrier(); return nodes_weight(*mask); } static unsigned int weighted_interleave_nid(struct mempolicy *pol, pgoff_t ilx) { struct weighted_interleave_state *state; nodemask_t nodemask; unsigned int target, nr_nodes; u8 *table = NULL; unsigned int weight_total = 0; u8 weight; int nid = 0; nr_nodes = read_once_policy_nodemask(pol, &nodemask); if (!nr_nodes) return numa_node_id(); rcu_read_lock(); state = rcu_dereference(wi_state); /* Uninitialized wi_state means we should assume all weights are 1 */ if (state) table = state->iw_table; /* calculate the total weight */ for_each_node_mask(nid, nodemask) weight_total += table ? table[nid] : 1; /* Calculate the node offset based on totals */ target = ilx % weight_total; nid = first_node(nodemask); while (target) { /* detect system default usage */ weight = table ? table[nid] : 1; if (target < weight) break; target -= weight; nid = next_node_in(nid, nodemask); } rcu_read_unlock(); return nid; } /* * Do static interleaving for interleave index @ilx. Returns the ilx'th * node in pol->nodes (starting from ilx=0), wrapping around if ilx * exceeds the number of present nodes. */ static unsigned int interleave_nid(struct mempolicy *pol, pgoff_t ilx) { nodemask_t nodemask; unsigned int target, nnodes; int i; int nid; nnodes = read_once_policy_nodemask(pol, &nodemask); if (!nnodes) return numa_node_id(); target = ilx % nnodes; nid = first_node(nodemask); for (i = 0; i < target; i++) nid = next_node(nid, nodemask); return nid; } /* * Return a nodemask representing a mempolicy for filtering nodes for * page allocation, together with preferred node id (or the input node id). */ static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *pol, pgoff_t ilx, int *nid) { nodemask_t *nodemask = NULL; switch (pol->mode) { case MPOL_PREFERRED: /* Override input node id */ *nid = first_node(pol->nodes); break; case MPOL_PREFERRED_MANY: nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; break; case MPOL_BIND: /* Restrict to nodemask (but not on lower zones) */ if (apply_policy_zone(pol, gfp_zone(gfp)) && cpuset_nodemask_valid_mems_allowed(&pol->nodes)) nodemask = &pol->nodes; if (pol->home_node != NUMA_NO_NODE) *nid = pol->home_node; /* * __GFP_THISNODE shouldn't even be used with the bind policy * because we might easily break the expectation to stay on the * requested node and not break the policy. */ WARN_ON_ONCE(gfp & __GFP_THISNODE); break; case MPOL_INTERLEAVE: /* Override input node id */ *nid = (ilx == NO_INTERLEAVE_INDEX) ? interleave_nodes(pol) : interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: *nid = (ilx == NO_INTERLEAVE_INDEX) ? weighted_interleave_nodes(pol) : weighted_interleave_nid(pol, ilx); break; } return nodemask; } #ifdef CONFIG_HUGETLBFS /* * huge_node(@vma, @addr, @gfp_flags, @mpol) * @vma: virtual memory area whose policy is sought * @addr: address in @vma for shared policy lookup and interleave policy * @gfp_flags: for requested zone * @mpol: pointer to mempolicy pointer for reference counted mempolicy * @nodemask: pointer to nodemask pointer for 'bind' and 'prefer-many' policy * * Returns a nid suitable for a huge page allocation and a pointer * to the struct mempolicy for conditional unref after allocation. * If the effective policy is 'bind' or 'prefer-many', returns a pointer * to the mempolicy's @nodemask for filtering the zonelist. */ int huge_node(struct vm_area_struct *vma, unsigned long addr, gfp_t gfp_flags, struct mempolicy **mpol, nodemask_t **nodemask) { pgoff_t ilx; int nid; nid = numa_node_id(); *mpol = get_vma_policy(vma, addr, hstate_vma(vma)->order, &ilx); *nodemask = policy_nodemask(gfp_flags, *mpol, ilx, &nid); return nid; } /* * init_nodemask_of_mempolicy * * If the current task's mempolicy is "default" [NULL], return 'false' * to indicate default policy. Otherwise, extract the policy nodemask * for 'bind' or 'interleave' policy into the argument nodemask, or * initialize the argument nodemask to contain the single node for * 'preferred' or 'local' policy and return 'true' to indicate presence * of non-default mempolicy. * * We don't bother with reference counting the mempolicy [mpol_get/put] * because the current task is examining it's own mempolicy and a task's * mempolicy is only ever changed by the task itself. * * N.B., it is the caller's responsibility to free a returned nodemask. */ bool init_nodemask_of_mempolicy(nodemask_t *mask) { struct mempolicy *mempolicy; if (!(mask && current->mempolicy)) return false; task_lock(current); mempolicy = current->mempolicy; switch (mempolicy->mode) { case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: *mask = mempolicy->nodes; break; case MPOL_LOCAL: init_nodemask_of_node(mask, numa_node_id()); break; default: BUG(); } task_unlock(current); return true; } #endif /* * mempolicy_in_oom_domain * * If tsk's mempolicy is "bind", check for intersection between mask and * the policy nodemask. Otherwise, return true for all other policies * including "interleave", as a tsk with "interleave" policy may have * memory allocated from all nodes in system. * * Takes task_lock(tsk) to prevent freeing of its mempolicy. */ bool mempolicy_in_oom_domain(struct task_struct *tsk, const nodemask_t *mask) { struct mempolicy *mempolicy; bool ret = true; if (!mask) return ret; task_lock(tsk); mempolicy = tsk->mempolicy; if (mempolicy && mempolicy->mode == MPOL_BIND) ret = nodes_intersects(mempolicy->nodes, *mask); task_unlock(tsk); return ret; } static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order, int nid, nodemask_t *nodemask) { struct page *page; gfp_t preferred_gfp; /* * This is a two pass approach. The first pass will only try the * preferred nodes but skip the direct reclaim and allow the * allocation to fail, while the second pass will try all the * nodes in system. */ preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); page = __alloc_frozen_pages_noprof(preferred_gfp, order, nid, nodemask); if (!page) page = __alloc_frozen_pages_noprof(gfp, order, nid, NULL); return page; } /** * alloc_pages_mpol - Allocate pages according to NUMA mempolicy. * @gfp: GFP flags. * @order: Order of the page allocation. * @pol: Pointer to the NUMA mempolicy. * @ilx: Index for interleave mempolicy (also distinguishes alloc_pages()). * @nid: Preferred node (usually numa_node_id() but @mpol may override it). * * Return: The page on success or NULL if allocation fails. */ static struct page *alloc_pages_mpol(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { nodemask_t *nodemask; struct page *page; nodemask = policy_nodemask(gfp, pol, ilx, &nid); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_preferred_many(gfp, order, nid, nodemask); if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && /* filter "hugepage" allocation, unless from alloc_pages() */ is_pmd_order(order) && ilx != NO_INTERLEAVE_INDEX) { /* * For hugepage allocation and non-interleave policy which * allows the current node (or other explicitly preferred * node) we only try to allocate from the current/preferred * node and don't fall back to other nodes, as the cost of * remote accesses would likely offset THP benefits. * * If the policy is interleave or does not allow the current * node in its nodemask, we allocate the standard way. */ if (pol->mode != MPOL_INTERLEAVE && pol->mode != MPOL_WEIGHTED_INTERLEAVE && (!nodemask || node_isset(nid, *nodemask))) { /* * First, try to allocate THP only on local node, but * don't reclaim unnecessarily, just compact. */ page = __alloc_frozen_pages_noprof( gfp | __GFP_THISNODE | __GFP_NORETRY, order, nid, NULL); if (page || !(gfp & __GFP_DIRECT_RECLAIM)) return page; /* * If hugepage allocations are configured to always * synchronous compact or the vma has been madvised * to prefer hugepage backing, retry allowing remote * memory with both reclaim and compact as well. */ } } page = __alloc_frozen_pages_noprof(gfp, order, nid, nodemask); if (unlikely(pol->mode == MPOL_INTERLEAVE || pol->mode == MPOL_WEIGHTED_INTERLEAVE) && page) { /* skip NUMA_INTERLEAVE_HIT update if numa stats is disabled */ if (static_branch_likely(&vm_numa_stat_key) && page_to_nid(page) == nid) { preempt_disable(); __count_numa_event(page_zone(page), NUMA_INTERLEAVE_HIT); preempt_enable(); } } return page; } struct folio *folio_alloc_mpol_noprof(gfp_t gfp, unsigned int order, struct mempolicy *pol, pgoff_t ilx, int nid) { struct page *page = alloc_pages_mpol(gfp | __GFP_COMP, order, pol, ilx, nid); if (!page) return NULL; set_page_refcounted(page); return page_rmappable_folio(page); } /** * vma_alloc_folio - Allocate a folio for a VMA. * @gfp: GFP flags. * @order: Order of the folio. * @vma: Pointer to VMA. * @addr: Virtual address of the allocation. Must be inside @vma. * * Allocate a folio for a specific address in @vma, using the appropriate * NUMA policy. The caller must hold the mmap_lock of the mm_struct of the * VMA to prevent it from going away. Should be used for all allocations * for folios that will be mapped into user space, excepting hugetlbfs, and * excepting where direct use of folio_alloc_mpol() is more appropriate. * * Return: The folio on success or NULL if allocation fails. */ struct folio *vma_alloc_folio_noprof(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct folio *folio; if (vma->vm_flags & VM_DROPPABLE) gfp |= __GFP_NOWARN; pol = get_vma_policy(vma, addr, order, &ilx); folio = folio_alloc_mpol_noprof(gfp, order, pol, ilx, numa_node_id()); mpol_cond_put(pol); return folio; } EXPORT_SYMBOL(vma_alloc_folio_noprof); struct page *alloc_frozen_pages_noprof(gfp_t gfp, unsigned order) { struct mempolicy *pol = &default_policy; /* * No reference counting needed for current->mempolicy * nor system default_policy */ if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); return alloc_pages_mpol(gfp, order, pol, NO_INTERLEAVE_INDEX, numa_node_id()); } /** * alloc_pages - Allocate pages. * @gfp: GFP flags. * @order: Power of two of number of pages to allocate. * * Allocate 1 << @order contiguous pages. The physical address of the * first page is naturally aligned (eg an order-3 allocation will be aligned * to a multiple of 8 * PAGE_SIZE bytes). The NUMA policy of the current * process is honoured when in process context. * * Context: Can be called from any context, providing the appropriate GFP * flags are used. * Return: The page on success or NULL if allocation fails. */ struct page *alloc_pages_noprof(gfp_t gfp, unsigned int order) { struct page *page = alloc_frozen_pages_noprof(gfp, order); if (page) set_page_refcounted(page); return page; } EXPORT_SYMBOL(alloc_pages_noprof); struct folio *folio_alloc_noprof(gfp_t gfp, unsigned int order) { return page_rmappable_folio(alloc_pages_noprof(gfp | __GFP_COMP, order)); } EXPORT_SYMBOL(folio_alloc_noprof); static unsigned long alloc_pages_bulk_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { int nodes; unsigned long nr_pages_per_node; int delta; int i; unsigned long nr_allocated; unsigned long total_allocated = 0; nodes = nodes_weight(pol->nodes); nr_pages_per_node = nr_pages / nodes; delta = nr_pages - nodes * nr_pages_per_node; for (i = 0; i < nodes; i++) { if (delta) { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node + 1, page_array); delta--; } else { nr_allocated = alloc_pages_bulk_noprof(gfp, interleave_nodes(pol), NULL, nr_pages_per_node, page_array); } page_array += nr_allocated; total_allocated += nr_allocated; } return total_allocated; } static unsigned long alloc_pages_bulk_weighted_interleave(gfp_t gfp, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { struct weighted_interleave_state *state; struct task_struct *me = current; unsigned int cpuset_mems_cookie; unsigned long total_allocated = 0; unsigned long nr_allocated = 0; unsigned long rounds; unsigned long node_pages, delta; u8 *weights, weight; unsigned int weight_total = 0; unsigned long rem_pages = nr_pages; nodemask_t nodes; int nnodes, node; int resume_node = MAX_NUMNODES - 1; u8 resume_weight = 0; int prev_node; int i; if (!nr_pages) return 0; /* read the nodes onto the stack, retry if done during rebind */ do { cpuset_mems_cookie = read_mems_allowed_begin(); nnodes = read_once_policy_nodemask(pol, &nodes); } while (read_mems_allowed_retry(cpuset_mems_cookie)); /* if the nodemask has become invalid, we cannot do anything */ if (!nnodes) return 0; /* Continue allocating from most recent node and adjust the nr_pages */ node = me->il_prev; weight = me->il_weight; if (weight && node_isset(node, nodes)) { node_pages = min(rem_pages, weight); nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; /* if that's all the pages, no need to interleave */ if (rem_pages <= weight) { me->il_weight -= rem_pages; return total_allocated; } /* Otherwise we adjust remaining pages, continue from there */ rem_pages -= weight; } /* clear active weight in case of an allocation failure */ me->il_weight = 0; prev_node = node; /* create a local copy of node weights to operate on outside rcu */ weights = kzalloc(nr_node_ids, GFP_KERNEL); if (!weights) return total_allocated; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) { memcpy(weights, state->iw_table, nr_node_ids * sizeof(u8)); rcu_read_unlock(); } else { rcu_read_unlock(); for (i = 0; i < nr_node_ids; i++) weights[i] = 1; } /* calculate total, detect system default usage */ for_each_node_mask(node, nodes) weight_total += weights[node]; /* * Calculate rounds/partial rounds to minimize __alloc_pages_bulk calls. * Track which node weighted interleave should resume from. * * if (rounds > 0) and (delta == 0), resume_node will always be * the node following prev_node and its weight. */ rounds = rem_pages / weight_total; delta = rem_pages % weight_total; resume_node = next_node_in(prev_node, nodes); resume_weight = weights[resume_node]; for (i = 0; i < nnodes; i++) { node = next_node_in(prev_node, nodes); weight = weights[node]; node_pages = weight * rounds; /* If a delta exists, add this node's portion of the delta */ if (delta > weight) { node_pages += weight; delta -= weight; } else if (delta) { /* when delta is depleted, resume from that node */ node_pages += delta; resume_node = node; resume_weight = weight - delta; delta = 0; } /* node_pages can be 0 if an allocation fails and rounds == 0 */ if (!node_pages) break; nr_allocated = __alloc_pages_bulk(gfp, node, NULL, node_pages, page_array); page_array += nr_allocated; total_allocated += nr_allocated; if (total_allocated == nr_pages) break; prev_node = node; } me->il_prev = resume_node; me->il_weight = resume_weight; kfree(weights); return total_allocated; } static unsigned long alloc_pages_bulk_preferred_many(gfp_t gfp, int nid, struct mempolicy *pol, unsigned long nr_pages, struct page **page_array) { gfp_t preferred_gfp; unsigned long nr_allocated = 0; preferred_gfp = gfp | __GFP_NOWARN; preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL); nr_allocated = alloc_pages_bulk_noprof(preferred_gfp, nid, &pol->nodes, nr_pages, page_array); if (nr_allocated < nr_pages) nr_allocated += alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL, nr_pages - nr_allocated, page_array + nr_allocated); return nr_allocated; } /* alloc pages bulk and mempolicy should be considered at the * same time in some situation such as vmalloc. * * It can accelerate memory allocation especially interleaving * allocate memory. */ unsigned long alloc_pages_bulk_mempolicy_noprof(gfp_t gfp, unsigned long nr_pages, struct page **page_array) { struct mempolicy *pol = &default_policy; nodemask_t *nodemask; int nid; if (!in_interrupt() && !(gfp & __GFP_THISNODE)) pol = get_task_policy(current); if (pol->mode == MPOL_INTERLEAVE) return alloc_pages_bulk_interleave(gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_WEIGHTED_INTERLEAVE) return alloc_pages_bulk_weighted_interleave( gfp, pol, nr_pages, page_array); if (pol->mode == MPOL_PREFERRED_MANY) return alloc_pages_bulk_preferred_many(gfp, numa_node_id(), pol, nr_pages, page_array); nid = numa_node_id(); nodemask = policy_nodemask(gfp, pol, NO_INTERLEAVE_INDEX, &nid); return alloc_pages_bulk_noprof(gfp, nid, nodemask, nr_pages, page_array); } int vma_dup_policy(struct vm_area_struct *src, struct vm_area_struct *dst) { struct mempolicy *pol = mpol_dup(src->vm_policy); if (IS_ERR(pol)) return PTR_ERR(pol); dst->vm_policy = pol; return 0; } /* * If mpol_dup() sees current->cpuset == cpuset_being_rebound, then it * rebinds the mempolicy its copying by calling mpol_rebind_policy() * with the mems_allowed returned by cpuset_mems_allowed(). This * keeps mempolicies cpuset relative after its cpuset moves. See * further kernel/cpuset.c update_nodemask(). * * current's mempolicy may be rebinded by the other task(the task that changes * cpuset's mems), so we needn't do rebind work for current task. */ /* Slow path of a mempolicy duplicate */ struct mempolicy *__mpol_dup(struct mempolicy *old) { struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!new) return ERR_PTR(-ENOMEM); /* task's mempolicy is protected by alloc_lock */ if (old == current->mempolicy) { task_lock(current); *new = *old; task_unlock(current); } else *new = *old; if (current_cpuset_is_being_rebound()) { nodemask_t mems = cpuset_mems_allowed(current); mpol_rebind_policy(new, &mems); } atomic_set(&new->refcnt, 1); return new; } /* Slow path of a mempolicy comparison */ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b) { if (!a || !b) return false; if (a->mode != b->mode) return false; if (a->flags != b->flags) return false; if (a->home_node != b->home_node) return false; if (mpol_store_user_nodemask(a)) if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask)) return false; switch (a->mode) { case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_WEIGHTED_INTERLEAVE: return nodes_equal(a->nodes, b->nodes); case MPOL_LOCAL: return true; default: BUG(); return false; } } /* * Shared memory backing store policy support. * * Remember policies even when nobody has shared memory mapped. * The policies are kept in Red-Black tree linked from the inode. * They are protected by the sp->lock rwlock, which should be held * for any accesses to the tree. */ /* * lookup first element intersecting start-end. Caller holds sp->lock for * reading or for writing */ static struct sp_node *sp_lookup(struct shared_policy *sp, pgoff_t start, pgoff_t end) { struct rb_node *n = sp->root.rb_node; while (n) { struct sp_node *p = rb_entry(n, struct sp_node, nd); if (start >= p->end) n = n->rb_right; else if (end <= p->start) n = n->rb_left; else break; } if (!n) return NULL; for (;;) { struct sp_node *w = NULL; struct rb_node *prev = rb_prev(n); if (!prev) break; w = rb_entry(prev, struct sp_node, nd); if (w->end <= start) break; n = prev; } return rb_entry(n, struct sp_node, nd); } /* * Insert a new shared policy into the list. Caller holds sp->lock for * writing. */ static void sp_insert(struct shared_policy *sp, struct sp_node *new) { struct rb_node **p = &sp->root.rb_node; struct rb_node *parent = NULL; struct sp_node *nd; while (*p) { parent = *p; nd = rb_entry(parent, struct sp_node, nd); if (new->start < nd->start) p = &(*p)->rb_left; else if (new->end > nd->end) p = &(*p)->rb_right; else BUG(); } rb_link_node(&new->nd, parent, p); rb_insert_color(&new->nd, &sp->root); } /* Find shared policy intersecting idx */ struct mempolicy *mpol_shared_policy_lookup(struct shared_policy *sp, pgoff_t idx) { struct mempolicy *pol = NULL; struct sp_node *sn; if (!sp->root.rb_node) return NULL; read_lock(&sp->lock); sn = sp_lookup(sp, idx, idx+1); if (sn) { mpol_get(sn->policy); pol = sn->policy; } read_unlock(&sp->lock); return pol; } EXPORT_SYMBOL_FOR_MODULES(mpol_shared_policy_lookup, "kvm"); static void sp_free(struct sp_node *n) { mpol_put(n->policy); kmem_cache_free(sn_cache, n); } /** * mpol_misplaced - check whether current folio node is valid in policy * * @folio: folio to be checked * @vmf: structure describing the fault * @addr: virtual address in @vma for shared policy lookup and interleave policy * * Lookup current policy node id for vma,addr and "compare to" folio's * node id. Policy determination "mimics" alloc_page_vma(). * Called from fault path where we know the vma and faulting address. * * Return: NUMA_NO_NODE if the page is in a node that is valid for this * policy, or a suitable node ID to allocate a replacement folio from. */ int mpol_misplaced(struct folio *folio, struct vm_fault *vmf, unsigned long addr) { struct mempolicy *pol; pgoff_t ilx; struct zoneref *z; int curnid = folio_nid(folio); struct vm_area_struct *vma = vmf->vma; int thiscpu = raw_smp_processor_id(); int thisnid = numa_node_id(); int polnid = NUMA_NO_NODE; int ret = NUMA_NO_NODE; /* * Make sure ptl is held so that we don't preempt and we * have a stable smp processor id */ lockdep_assert_held(vmf->ptl); pol = get_vma_policy(vma, addr, folio_order(folio), &ilx); if (!(pol->flags & MPOL_F_MOF)) goto out; switch (pol->mode) { case MPOL_INTERLEAVE: polnid = interleave_nid(pol, ilx); break; case MPOL_WEIGHTED_INTERLEAVE: polnid = weighted_interleave_nid(pol, ilx); break; case MPOL_PREFERRED: if (node_isset(curnid, pol->nodes)) goto out; polnid = first_node(pol->nodes); break; case MPOL_LOCAL: polnid = numa_node_id(); break; case MPOL_BIND: case MPOL_PREFERRED_MANY: /* * Even though MPOL_PREFERRED_MANY can allocate pages outside * policy nodemask we don't allow numa migration to nodes * outside policy nodemask for now. This is done so that if we * want demotion to slow memory to happen, before allocating * from some DRAM node say 'x', we will end up using a * MPOL_PREFERRED_MANY mask excluding node 'x'. In such scenario * we should not promote to node 'x' from slow memory node. */ if (pol->flags & MPOL_F_MORON) { /* * Optimize placement among multiple nodes * via NUMA balancing */ if (node_isset(thisnid, pol->nodes)) break; goto out; } /* * use current page if in policy nodemask, * else select nearest allowed node, if any. * If no allowed nodes, use current [!misplaced]. */ if (node_isset(curnid, pol->nodes)) goto out; z = first_zones_zonelist( node_zonelist(thisnid, GFP_HIGHUSER), gfp_zone(GFP_HIGHUSER), &pol->nodes); polnid = zonelist_node_idx(z); break; default: BUG(); } /* Migrate the folio towards the node whose CPU is referencing it */ if (pol->flags & MPOL_F_MORON) { polnid = thisnid; if (!should_numa_migrate_memory(current, folio, curnid, thiscpu)) goto out; } if (curnid != polnid) ret = polnid; out: mpol_cond_put(pol); return ret; } /* * Drop the (possibly final) reference to task->mempolicy. It needs to be * dropped after task->mempolicy is set to NULL so that any allocation done as * part of its kmem_cache_free(), such as by KASAN, doesn't reference a freed * policy. */ void mpol_put_task_policy(struct task_struct *task) { struct mempolicy *pol; task_lock(task); pol = task->mempolicy; task->mempolicy = NULL; task_unlock(task); mpol_put(pol); } static void sp_delete(struct shared_policy *sp, struct sp_node *n) { rb_erase(&n->nd, &sp->root); sp_free(n); } static void sp_node_init(struct sp_node *node, unsigned long start, unsigned long end, struct mempolicy *pol) { node->start = start; node->end = end; node->policy = pol; } static struct sp_node *sp_alloc(unsigned long start, unsigned long end, struct mempolicy *pol) { struct sp_node *n; struct mempolicy *newpol; n = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n) return NULL; newpol = mpol_dup(pol); if (IS_ERR(newpol)) { kmem_cache_free(sn_cache, n); return NULL; } newpol->flags |= MPOL_F_SHARED; sp_node_init(n, start, end, newpol); return n; } /* Replace a policy range. */ static int shared_policy_replace(struct shared_policy *sp, pgoff_t start, pgoff_t end, struct sp_node *new) { struct sp_node *n; struct sp_node *n_new = NULL; struct mempolicy *mpol_new = NULL; int ret = 0; restart: write_lock(&sp->lock); n = sp_lookup(sp, start, end); /* Take care of old policies in the same range. */ while (n && n->start < end) { struct rb_node *next = rb_next(&n->nd); if (n->start >= start) { if (n->end <= end) sp_delete(sp, n); else n->start = end; } else { /* Old policy spanning whole new range. */ if (n->end > end) { if (!n_new) goto alloc_new; *mpol_new = *n->policy; atomic_set(&mpol_new->refcnt, 1); sp_node_init(n_new, end, n->end, mpol_new); n->end = start; sp_insert(sp, n_new); n_new = NULL; mpol_new = NULL; break; } else n->end = start; } if (!next) break; n = rb_entry(next, struct sp_node, nd); } if (new) sp_insert(sp, new); write_unlock(&sp->lock); ret = 0; err_out: if (mpol_new) mpol_put(mpol_new); if (n_new) kmem_cache_free(sn_cache, n_new); return ret; alloc_new: write_unlock(&sp->lock); ret = -ENOMEM; n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL); if (!n_new) goto err_out; mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; atomic_set(&mpol_new->refcnt, 1); goto restart; } /** * mpol_shared_policy_init - initialize shared policy for inode * @sp: pointer to inode shared policy * @mpol: struct mempolicy to install * * Install non-NULL @mpol in inode's shared policy rb-tree. * On entry, the current task has a reference on a non-NULL @mpol. * This must be released on exit. * This is called at get_inode() calls and we can use GFP_KERNEL. */ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol) { int ret; sp->root = RB_ROOT; /* empty tree == default mempolicy */ rwlock_init(&sp->lock); if (mpol) { struct sp_node *sn; struct mempolicy *npol; NODEMASK_SCRATCH(scratch); if (!scratch) goto put_mpol; /* contextualize the tmpfs mount point mempolicy to this file */ npol = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask); if (IS_ERR(npol)) goto free_scratch; /* no valid nodemask intersection */ task_lock(current); ret = mpol_set_nodemask(npol, &mpol->w.user_nodemask, scratch); task_unlock(current); if (ret) goto put_npol; /* alloc node covering entire file; adds ref to file's npol */ sn = sp_alloc(0, MAX_LFS_FILESIZE >> PAGE_SHIFT, npol); if (sn) sp_insert(sp, sn); put_npol: mpol_put(npol); /* drop initial ref on file's npol */ free_scratch: NODEMASK_SCRATCH_FREE(scratch); put_mpol: mpol_put(mpol); /* drop our incoming ref on sb mpol */ } } EXPORT_SYMBOL_FOR_MODULES(mpol_shared_policy_init, "kvm"); int mpol_set_shared_policy(struct shared_policy *sp, struct vm_area_struct *vma, struct mempolicy *pol) { int err; struct sp_node *new = NULL; unsigned long sz = vma_pages(vma); if (pol) { new = sp_alloc(vma->vm_pgoff, vma->vm_pgoff + sz, pol); if (!new) return -ENOMEM; } err = shared_policy_replace(sp, vma->vm_pgoff, vma->vm_pgoff + sz, new); if (err && new) sp_free(new); return err; } EXPORT_SYMBOL_FOR_MODULES(mpol_set_shared_policy, "kvm"); /* Free a backing policy store on inode delete. */ void mpol_free_shared_policy(struct shared_policy *sp) { struct sp_node *n; struct rb_node *next; if (!sp->root.rb_node) return; write_lock(&sp->lock); next = rb_first(&sp->root); while (next) { n = rb_entry(next, struct sp_node, nd); next = rb_next(&n->nd); sp_delete(sp, n); } write_unlock(&sp->lock); } EXPORT_SYMBOL_FOR_MODULES(mpol_free_shared_policy, "kvm"); #ifdef CONFIG_NUMA_BALANCING static int __initdata numabalancing_override; static void __init check_numabalancing_enable(void) { bool numabalancing_default = false; if (IS_ENABLED(CONFIG_NUMA_BALANCING_DEFAULT_ENABLED)) numabalancing_default = true; /* Parsed by setup_numabalancing. override == 1 enables, -1 disables */ if (numabalancing_override) set_numabalancing_state(numabalancing_override == 1); if (num_online_nodes() > 1 && !numabalancing_override) { pr_info("%s automatic NUMA balancing. Configure with numa_balancing= or the kernel.numa_balancing sysctl\n", numabalancing_default ? "Enabling" : "Disabling"); set_numabalancing_state(numabalancing_default); } } static int __init setup_numabalancing(char *str) { int ret = 0; if (!str) goto out; if (!strcmp(str, "enable")) { numabalancing_override = 1; ret = 1; } else if (!strcmp(str, "disable")) { numabalancing_override = -1; ret = 1; } out: if (!ret) pr_warn("Unable to parse numa_balancing=\n"); return ret; } __setup("numa_balancing=", setup_numabalancing); #else static inline void __init check_numabalancing_enable(void) { } #endif /* CONFIG_NUMA_BALANCING */ void __init numa_policy_init(void) { nodemask_t interleave_nodes; unsigned long largest = 0; int nid, prefer = 0; policy_cache = kmem_cache_create("numa_policy", sizeof(struct mempolicy), 0, SLAB_PANIC, NULL); sn_cache = kmem_cache_create("shared_policy_node", sizeof(struct sp_node), 0, SLAB_PANIC, NULL); for_each_node(nid) { preferred_node_policy[nid] = (struct mempolicy) { .refcnt = ATOMIC_INIT(1), .mode = MPOL_PREFERRED, .flags = MPOL_F_MOF | MPOL_F_MORON, .nodes = nodemask_of_node(nid), }; } /* * Set interleaving policy for system init. Interleaving is only * enabled across suitably sized nodes (default is >= 16MB), or * fall back to the largest node if they're all smaller. */ nodes_clear(interleave_nodes); for_each_node_state(nid, N_MEMORY) { unsigned long total_pages = node_present_pages(nid); /* Preserve the largest node */ if (largest < total_pages) { largest = total_pages; prefer = nid; } /* Interleave this node? */ if ((total_pages << PAGE_SHIFT) >= (16 << 20)) node_set(nid, interleave_nodes); } /* All too small, use the largest */ if (unlikely(nodes_empty(interleave_nodes))) node_set(prefer, interleave_nodes); if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes)) pr_err("%s: interleaving failed\n", __func__); check_numabalancing_enable(); } /* Reset policy of current process to default */ void numa_default_policy(void) { do_set_mempolicy(MPOL_DEFAULT, 0, NULL); } /* * Parse and format mempolicy from/to strings */ static const char * const policy_modes[] = { [MPOL_DEFAULT] = "default", [MPOL_PREFERRED] = "prefer", [MPOL_BIND] = "bind", [MPOL_INTERLEAVE] = "interleave", [MPOL_WEIGHTED_INTERLEAVE] = "weighted interleave", [MPOL_LOCAL] = "local", [MPOL_PREFERRED_MANY] = "prefer (many)", }; #ifdef CONFIG_TMPFS /** * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option. * @str: string containing mempolicy to parse * @mpol: pointer to struct mempolicy pointer, returned on success. * * Format of input: * <mode>[=<flags>][:<nodelist>] * * Return: %0 on success, else %1 */ int mpol_parse_str(char *str, struct mempolicy **mpol) { struct mempolicy *new = NULL; unsigned short mode_flags; nodemask_t nodes; char *nodelist = strchr(str, ':'); char *flags = strchr(str, '='); int err = 1, mode; if (flags) *flags++ = '\0'; /* terminate mode string */ if (nodelist) { /* NUL-terminate mode or flags string */ *nodelist++ = '\0'; if (nodelist_parse(nodelist, nodes)) goto out; if (!nodes_subset(nodes, node_states[N_MEMORY])) goto out; } else nodes_clear(nodes); mode = match_string(policy_modes, MPOL_MAX, str); if (mode < 0) goto out; switch (mode) { case MPOL_PREFERRED: /* * Insist on a nodelist of one node only, although later * we use first_node(nodes) to grab a single node, so here * nodelist (or nodes) cannot be empty. */ if (nodelist) { char *rest = nodelist; while (isdigit(*rest)) rest++; if (*rest) goto out; if (nodes_empty(nodes)) goto out; } break; case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: /* * Default to online nodes with memory if no nodelist */ if (!nodelist) nodes = node_states[N_MEMORY]; break; case MPOL_LOCAL: /* * Don't allow a nodelist; mpol_new() checks flags */ if (nodelist) goto out; break; case MPOL_DEFAULT: /* * Insist on a empty nodelist */ if (!nodelist) err = 0; goto out; case MPOL_PREFERRED_MANY: case MPOL_BIND: /* * Insist on a nodelist */ if (!nodelist) goto out; } mode_flags = 0; if (flags) { /* * Currently, we only support two mutually exclusive * mode flags. */ if (!strcmp(flags, "static")) mode_flags |= MPOL_F_STATIC_NODES; else if (!strcmp(flags, "relative")) mode_flags |= MPOL_F_RELATIVE_NODES; else goto out; } new = mpol_new(mode, mode_flags, &nodes); if (IS_ERR(new)) goto out; /* * Save nodes for mpol_to_str() to show the tmpfs mount options * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo. */ if (mode != MPOL_PREFERRED) { new->nodes = nodes; } else if (nodelist) { nodes_clear(new->nodes); node_set(first_node(nodes), new->nodes); } else { new->mode = MPOL_LOCAL; } /* * Save nodes for contextualization: this will be used to "clone" * the mempolicy in a specific context [cpuset] at a later time. */ new->w.user_nodemask = nodes; err = 0; out: /* Restore string for error message */ if (nodelist) *--nodelist = ':'; if (flags) *--flags = '='; if (!err) *mpol = new; return err; } #endif /* CONFIG_TMPFS */ /** * mpol_to_str - format a mempolicy structure for printing * @buffer: to contain formatted mempolicy string * @maxlen: length of @buffer * @pol: pointer to mempolicy to be formatted * * Convert @pol into a string. If @buffer is too short, truncate the string. * Recommend a @maxlen of at least 51 for the longest mode, "weighted * interleave", plus the longest flag flags, "relative|balancing", and to * display at least a few node ids. */ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) { char *p = buffer; nodemask_t nodes = NODE_MASK_NONE; unsigned short mode = MPOL_DEFAULT; unsigned short flags = 0; if (pol && pol != &default_policy && !(pol >= &preferred_node_policy[0] && pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) { mode = pol->mode; flags = pol->flags; } switch (mode) { case MPOL_DEFAULT: case MPOL_LOCAL: break; case MPOL_PREFERRED: case MPOL_PREFERRED_MANY: case MPOL_BIND: case MPOL_INTERLEAVE: case MPOL_WEIGHTED_INTERLEAVE: nodes = pol->nodes; break; default: WARN_ON_ONCE(1); snprintf(p, maxlen, "unknown"); return; } p += snprintf(p, maxlen, "%s", policy_modes[mode]); if (flags & MPOL_MODE_FLAGS) { p += snprintf(p, buffer + maxlen - p, "="); /* * Static and relative are mutually exclusive. */ if (flags & MPOL_F_STATIC_NODES) p += snprintf(p, buffer + maxlen - p, "static"); else if (flags & MPOL_F_RELATIVE_NODES) p += snprintf(p, buffer + maxlen - p, "relative"); if (flags & MPOL_F_NUMA_BALANCING) { if (!is_power_of_2(flags & MPOL_MODE_FLAGS)) p += snprintf(p, buffer + maxlen - p, "|"); p += snprintf(p, buffer + maxlen - p, "balancing"); } } if (!nodes_empty(nodes)) p += scnprintf(p, buffer + maxlen - p, ":%*pbl", nodemask_pr_args(&nodes)); } #ifdef CONFIG_SYSFS struct iw_node_attr { struct kobj_attribute kobj_attr; int nid; }; struct sysfs_wi_group { struct kobject wi_kobj; struct mutex kobj_lock; struct iw_node_attr *nattrs[]; }; static struct sysfs_wi_group *wi_group; static ssize_t node_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct iw_node_attr *node_attr; u8 weight; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); weight = get_il_weight(node_attr->nid); return sysfs_emit(buf, "%d\n", weight); } static ssize_t node_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; struct iw_node_attr *node_attr; u8 weight = 0; int i; node_attr = container_of(attr, struct iw_node_attr, kobj_attr); if (count == 0 || sysfs_streq(buf, "") || kstrtou8(buf, 0, &weight) || weight == 0) return -EINVAL; new_wi_state = kzalloc_flex(*new_wi_state, iw_table, nr_node_ids); if (!new_wi_state) return -ENOMEM; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state) { memcpy(new_wi_state->iw_table, old_wi_state->iw_table, nr_node_ids * sizeof(u8)); } else { for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; } new_wi_state->iw_table[node_attr->nid] = weight; new_wi_state->mode_auto = false; rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } return count; } static ssize_t weighted_interleave_auto_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf) { struct weighted_interleave_state *state; bool wi_auto = true; rcu_read_lock(); state = rcu_dereference(wi_state); if (state) wi_auto = state->mode_auto; rcu_read_unlock(); return sysfs_emit(buf, "%s\n", str_true_false(wi_auto)); } static ssize_t weighted_interleave_auto_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count) { struct weighted_interleave_state *new_wi_state, *old_wi_state = NULL; unsigned int *bw; bool input; int i; if (kstrtobool(buf, &input)) return -EINVAL; new_wi_state = kzalloc_flex(*new_wi_state, iw_table, nr_node_ids); if (!new_wi_state) return -ENOMEM; for (i = 0; i < nr_node_ids; i++) new_wi_state->iw_table[i] = 1; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); if (old_wi_state && input == old_wi_state->mode_auto) { mutex_unlock(&wi_state_lock); kfree(new_wi_state); return count; } if (!input) { if (old_wi_state) memcpy(new_wi_state->iw_table, old_wi_state->iw_table, nr_node_ids * sizeof(u8)); goto update_wi_state; } bw = node_bw_table; if (!bw) { mutex_unlock(&wi_state_lock); kfree(new_wi_state); return -ENODEV; } new_wi_state->mode_auto = true; reduce_interleave_weights(bw, new_wi_state->iw_table); update_wi_state: rcu_assign_pointer(wi_state, new_wi_state); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } return count; } static void sysfs_wi_node_delete(int nid) { struct iw_node_attr *attr; if (nid < 0 || nid >= nr_node_ids) return; mutex_lock(&wi_group->kobj_lock); attr = wi_group->nattrs[nid]; if (!attr) { mutex_unlock(&wi_group->kobj_lock); return; } wi_group->nattrs[nid] = NULL; mutex_unlock(&wi_group->kobj_lock); sysfs_remove_file(&wi_group->wi_kobj, &attr->kobj_attr.attr); kfree(attr->kobj_attr.attr.name); kfree(attr); } static void sysfs_wi_node_delete_all(void) { int nid; for (nid = 0; nid < nr_node_ids; nid++) sysfs_wi_node_delete(nid); } static void wi_state_free(void) { struct weighted_interleave_state *old_wi_state; mutex_lock(&wi_state_lock); old_wi_state = rcu_dereference_protected(wi_state, lockdep_is_held(&wi_state_lock)); rcu_assign_pointer(wi_state, NULL); mutex_unlock(&wi_state_lock); if (old_wi_state) { synchronize_rcu(); kfree(old_wi_state); } } static struct kobj_attribute wi_auto_attr = { .attr = { .name = "auto", .mode = 0664 }, .show = weighted_interleave_auto_show, .store = weighted_interleave_auto_store, }; static void wi_cleanup(void) { sysfs_remove_file(&wi_group->wi_kobj, &wi_auto_attr.attr); sysfs_wi_node_delete_all(); wi_state_free(); } static void wi_kobj_release(struct kobject *wi_kobj) { kfree(wi_group); } static const struct kobj_type wi_ktype = { .sysfs_ops = &kobj_sysfs_ops, .release = wi_kobj_release, }; static int sysfs_wi_node_add(int nid) { int ret; char *name; struct iw_node_attr *new_attr; if (nid < 0 || nid >= nr_node_ids) { pr_err("invalid node id: %d\n", nid); return -EINVAL; } new_attr = kzalloc_obj(*new_attr); if (!new_attr) return -ENOMEM; name = kasprintf(GFP_KERNEL, "node%d", nid); if (!name) { kfree(new_attr); return -ENOMEM; } sysfs_attr_init(&new_attr->kobj_attr.attr); new_attr->kobj_attr.attr.name = name; new_attr->kobj_attr.attr.mode = 0644; new_attr->kobj_attr.show = node_show; new_attr->kobj_attr.store = node_store; new_attr->nid = nid; mutex_lock(&wi_group->kobj_lock); if (wi_group->nattrs[nid]) { mutex_unlock(&wi_group->kobj_lock); ret = -EEXIST; goto out; } ret = sysfs_create_file(&wi_group->wi_kobj, &new_attr->kobj_attr.attr); if (ret) { mutex_unlock(&wi_group->kobj_lock); goto out; } wi_group->nattrs[nid] = new_attr; mutex_unlock(&wi_group->kobj_lock); return 0; out: kfree(new_attr->kobj_attr.attr.name); kfree(new_attr); return ret; } static int wi_node_notifier(struct notifier_block *nb, unsigned long action, void *data) { int err; struct node_notify *nn = data; int nid = nn->nid; switch (action) { case NODE_ADDED_FIRST_MEMORY: err = sysfs_wi_node_add(nid); if (err) pr_err("failed to add sysfs for node%d during hotplug: %d\n", nid, err); break; case NODE_REMOVED_LAST_MEMORY: sysfs_wi_node_delete(nid); break; } return NOTIFY_OK; } static int __init add_weighted_interleave_group(struct kobject *mempolicy_kobj) { int nid, err; wi_group = kzalloc_flex(*wi_group, nattrs, nr_node_ids); if (!wi_group) return -ENOMEM; mutex_init(&wi_group->kobj_lock); err = kobject_init_and_add(&wi_group->wi_kobj, &wi_ktype, mempolicy_kobj, "weighted_interleave"); if (err) goto err_put_kobj; err = sysfs_create_file(&wi_group->wi_kobj, &wi_auto_attr.attr); if (err) goto err_put_kobj; for_each_online_node(nid) { if (!node_state(nid, N_MEMORY)) continue; err = sysfs_wi_node_add(nid); if (err) { pr_err("failed to add sysfs for node%d during init: %d\n", nid, err); goto err_cleanup_kobj; } } hotplug_node_notifier(wi_node_notifier, DEFAULT_CALLBACK_PRI); return 0; err_cleanup_kobj: wi_cleanup(); kobject_del(&wi_group->wi_kobj); err_put_kobj: kobject_put(&wi_group->wi_kobj); return err; } static int __init mempolicy_sysfs_init(void) { int err; static struct kobject *mempolicy_kobj; mempolicy_kobj = kobject_create_and_add("mempolicy", mm_kobj); if (!mempolicy_kobj) return -ENOMEM; err = add_weighted_interleave_group(mempolicy_kobj); if (err) goto err_kobj; return 0; err_kobj: kobject_del(mempolicy_kobj); kobject_put(mempolicy_kobj); return err; } late_initcall(mempolicy_sysfs_init); #endif /* CONFIG_SYSFS */ |
| 264 261 169 100 100 100 100 165 163 164 165 171 170 164 165 163 172 171 165 165 165 165 163 164 164 100 100 100 100 100 100 165 164 176 174 100 100 100 100 6 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 | // SPDX-License-Identifier: GPL-2.0 /* * bus.c - bus driver management * * Copyright (c) 2002-3 Patrick Mochel * Copyright (c) 2002-3 Open Source Development Labs * Copyright (c) 2007 Greg Kroah-Hartman <gregkh@suse.de> * Copyright (c) 2007 Novell Inc. * Copyright (c) 2023 Greg Kroah-Hartman <gregkh@linuxfoundation.org> */ #include <linux/async.h> #include <linux/device/bus.h> #include <linux/device.h> #include <linux/module.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/init.h> #include <linux/string.h> #include <linux/mutex.h> #include <linux/sysfs.h> #include "base.h" #include "power/power.h" /* /sys/devices/system */ static struct kset *system_kset; /* /sys/bus */ static struct kset *bus_kset; #define to_bus_attr(_attr) container_of(_attr, struct bus_attribute, attr) /* * sysfs bindings for drivers */ #define to_drv_attr(_attr) container_of(_attr, struct driver_attribute, attr) #define DRIVER_ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) \ struct driver_attribute driver_attr_##_name = \ __ATTR_IGNORE_LOCKDEP(_name, _mode, _show, _store) static int __must_check bus_rescan_devices_helper(struct device *dev, void *data); /** * bus_to_subsys - Turn a struct bus_type into a struct subsys_private * * @bus: pointer to the struct bus_type to look up * * The driver core internals needs to work on the subsys_private structure, not * the external struct bus_type pointer. This function walks the list of * registered busses in the system and finds the matching one and returns the * internal struct subsys_private that relates to that bus. * * Note, the reference count of the return value is INCREMENTED if it is not * NULL. A call to subsys_put() must be done when finished with the pointer in * order for it to be properly freed. */ struct subsys_private *bus_to_subsys(const struct bus_type *bus) { struct subsys_private *sp = NULL; struct kobject *kobj; if (!bus || !bus_kset) return NULL; spin_lock(&bus_kset->list_lock); if (list_empty(&bus_kset->list)) goto done; list_for_each_entry(kobj, &bus_kset->list, entry) { struct kset *kset = container_of(kobj, struct kset, kobj); sp = container_of_const(kset, struct subsys_private, subsys); if (sp->bus == bus) goto done; } sp = NULL; done: sp = subsys_get(sp); spin_unlock(&bus_kset->list_lock); return sp; } static const struct bus_type *bus_get(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); if (sp) return bus; return NULL; } static void bus_put(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); /* two puts are required as the call to bus_to_subsys incremented it again */ subsys_put(sp); subsys_put(sp); } static ssize_t drv_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct driver_attribute *drv_attr = to_drv_attr(attr); struct driver_private *drv_priv = to_driver(kobj); ssize_t ret = -EIO; if (drv_attr->show) ret = drv_attr->show(drv_priv->driver, buf); return ret; } static ssize_t drv_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct driver_attribute *drv_attr = to_drv_attr(attr); struct driver_private *drv_priv = to_driver(kobj); ssize_t ret = -EIO; if (drv_attr->store) ret = drv_attr->store(drv_priv->driver, buf, count); return ret; } static const struct sysfs_ops driver_sysfs_ops = { .show = drv_attr_show, .store = drv_attr_store, }; static void driver_release(struct kobject *kobj) { struct driver_private *drv_priv = to_driver(kobj); pr_debug("driver: '%s': %s\n", kobject_name(kobj), __func__); kfree(drv_priv); } static const struct kobj_type driver_ktype = { .sysfs_ops = &driver_sysfs_ops, .release = driver_release, }; /* * sysfs bindings for buses */ static ssize_t bus_attr_show(struct kobject *kobj, struct attribute *attr, char *buf) { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); /* return -EIO for reading a bus attribute without show() */ ssize_t ret = -EIO; if (bus_attr->show) ret = bus_attr->show(subsys_priv->bus, buf); return ret; } static ssize_t bus_attr_store(struct kobject *kobj, struct attribute *attr, const char *buf, size_t count) { struct bus_attribute *bus_attr = to_bus_attr(attr); struct subsys_private *subsys_priv = to_subsys_private(kobj); /* return -EIO for writing a bus attribute without store() */ ssize_t ret = -EIO; if (bus_attr->store) ret = bus_attr->store(subsys_priv->bus, buf, count); return ret; } static const struct sysfs_ops bus_sysfs_ops = { .show = bus_attr_show, .store = bus_attr_store, }; int bus_create_file(const struct bus_type *bus, struct bus_attribute *attr) { struct subsys_private *sp = bus_to_subsys(bus); int error; if (!sp) return -EINVAL; error = sysfs_create_file(&sp->subsys.kobj, &attr->attr); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(bus_create_file); void bus_remove_file(const struct bus_type *bus, struct bus_attribute *attr) { struct subsys_private *sp = bus_to_subsys(bus); if (!sp) return; sysfs_remove_file(&sp->subsys.kobj, &attr->attr); subsys_put(sp); } EXPORT_SYMBOL_GPL(bus_remove_file); static void bus_release(struct kobject *kobj) { struct subsys_private *priv = to_subsys_private(kobj); lockdep_unregister_key(&priv->lock_key); kfree(priv); } static const struct kobj_type bus_ktype = { .sysfs_ops = &bus_sysfs_ops, .release = bus_release, }; static int bus_uevent_filter(const struct kobject *kobj) { const struct kobj_type *ktype = get_ktype(kobj); if (ktype == &bus_ktype) return 1; return 0; } static const struct kset_uevent_ops bus_uevent_ops = { .filter = bus_uevent_filter, }; /* Manually detach a device from its associated driver. */ static ssize_t unbind_store(struct device_driver *drv, const char *buf, size_t count) { const struct bus_type *bus = bus_get(drv->bus); struct device *dev; int err = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); if (dev && dev->driver == drv) { device_driver_detach(dev); err = count; } put_device(dev); bus_put(bus); return err; } static DRIVER_ATTR_IGNORE_LOCKDEP(unbind, 0200, NULL, unbind_store); /* * Manually attach a device to a driver. * Note: the driver must want to bind to the device, * it is not possible to override the driver's id table. */ static ssize_t bind_store(struct device_driver *drv, const char *buf, size_t count) { const struct bus_type *bus = bus_get(drv->bus); struct device *dev; int err = -ENODEV; dev = bus_find_device_by_name(bus, NULL, buf); if (dev && driver_match_device(drv, dev)) { err = device_driver_attach(drv, dev); if (!err) { /* success */ err = count; } } put_device(dev); bus_put(bus); return err; } static DRIVER_ATTR_IGNORE_LOCKDEP(bind, 0200, NULL, bind_store); static ssize_t drivers_autoprobe_show(const struct bus_type *bus, char *buf) { struct subsys_private *sp = bus_to_subsys(bus); int ret; if (!sp) return -EINVAL; ret = sysfs_emit(buf, "%d\n", sp->drivers_autoprobe); subsys_put(sp); return ret; } static ssize_t drivers_autoprobe_store(const struct bus_type *bus, const char *buf, size_t count) { struct subsys_private *sp = bus_to_subsys(bus); if (!sp) return -EINVAL; if (buf[0] == '0') sp->drivers_autoprobe = 0; else sp->drivers_autoprobe = 1; subsys_put(sp); return count; } static ssize_t drivers_probe_store(const struct bus_type *bus, const char *buf, size_t count) { struct device *dev; int err = -EINVAL; dev = bus_find_device_by_name(bus, NULL, buf); if (!dev) return -ENODEV; if (bus_rescan_devices_helper(dev, NULL) == 0) err = count; put_device(dev); return err; } static struct device *next_device(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct device *dev = NULL; struct device_private *dev_prv; if (n) { dev_prv = to_device_private_bus(n); dev = dev_prv->device; } return dev; } static struct device *prev_device(struct klist_iter *i) { struct klist_node *n = klist_prev(i); struct device *dev = NULL; struct device_private *dev_prv; if (n) { dev_prv = to_device_private_bus(n); dev = dev_prv->device; } return dev; } /** * bus_for_each_dev - device iterator. * @bus: bus type. * @start: device to start iterating from. * @data: data for the callback. * @fn: function to be called for each device. * * Iterate over @bus's list of devices, and call @fn for each, * passing it @data. If @start is not NULL, we use that device to * begin iterating from. * * We check the return of @fn each time. If it returns anything * other than 0, we break out and return that value. * * NOTE: The device that returns a non-zero value is not retained * in any way, nor is its refcount incremented. If the caller needs * to retain this data, it should do so, and increment the reference * count in the supplied callback. */ int bus_for_each_dev(const struct bus_type *bus, struct device *start, void *data, device_iter_t fn) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; struct device *dev; int error = 0; if (!sp) return -EINVAL; klist_iter_init_node(&sp->klist_devices, &i, (start ? &start->p->knode_bus : NULL)); while (!error && (dev = next_device(&i))) error = fn(dev, data); klist_iter_exit(&i); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(bus_for_each_dev); /** * bus_find_device - device iterator for locating a particular device. * @bus: bus type * @start: Device to begin with * @data: Data to pass to match function * @match: Callback function to check device * * This is similar to the bus_for_each_dev() function above, but it * returns a reference to a device that is 'found' for later use, as * determined by the @match callback. * * The callback should return 0 if the device doesn't match and non-zero * if it does. If the callback returns non-zero, this function will * return to the caller and not iterate over any more devices. */ struct device *bus_find_device(const struct bus_type *bus, struct device *start, const void *data, device_match_t match) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; struct device *dev; if (!sp) return NULL; klist_iter_init_node(&sp->klist_devices, &i, (start ? &start->p->knode_bus : NULL)); while ((dev = next_device(&i))) { if (match(dev, data)) { get_device(dev); break; } } klist_iter_exit(&i); subsys_put(sp); return dev; } EXPORT_SYMBOL_GPL(bus_find_device); struct device *bus_find_device_reverse(const struct bus_type *bus, struct device *start, const void *data, device_match_t match) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; struct device *dev; if (!sp) return NULL; klist_iter_init_node(&sp->klist_devices, &i, (start ? &start->p->knode_bus : NULL)); while ((dev = prev_device(&i))) { if (match(dev, data)) { get_device(dev); break; } } klist_iter_exit(&i); subsys_put(sp); return dev; } EXPORT_SYMBOL_GPL(bus_find_device_reverse); static struct device_driver *next_driver(struct klist_iter *i) { struct klist_node *n = klist_next(i); struct driver_private *drv_priv; if (n) { drv_priv = container_of(n, struct driver_private, knode_bus); return drv_priv->driver; } return NULL; } /** * bus_for_each_drv - driver iterator * @bus: bus we're dealing with. * @start: driver to start iterating on. * @data: data to pass to the callback. * @fn: function to call for each driver. * * This is nearly identical to the device iterator above. * We iterate over each driver that belongs to @bus, and call * @fn for each. If @fn returns anything but 0, we break out * and return it. If @start is not NULL, we use it as the head * of the list. * * NOTE: we don't return the driver that returns a non-zero * value, nor do we leave the reference count incremented for that * driver. If the caller needs to know that info, it must set it * in the callback. It must also be sure to increment the refcount * so it doesn't disappear before returning to the caller. */ int bus_for_each_drv(const struct bus_type *bus, struct device_driver *start, void *data, int (*fn)(struct device_driver *, void *)) { struct subsys_private *sp = bus_to_subsys(bus); struct klist_iter i; struct device_driver *drv; int error = 0; if (!sp) return -EINVAL; klist_iter_init_node(&sp->klist_drivers, &i, start ? &start->p->knode_bus : NULL); while ((drv = next_driver(&i)) && !error) error = fn(drv, data); klist_iter_exit(&i); subsys_put(sp); return error; } EXPORT_SYMBOL_GPL(bus_for_each_drv); static ssize_t driver_override_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { int ret; ret = __device_set_driver_override(dev, buf, count); if (ret) return ret; return count; } static ssize_t driver_override_show(struct device *dev, struct device_attribute *attr, char *buf) { guard(spinlock)(&dev->driver_override.lock); return sysfs_emit(buf, "%s\n", dev->driver_override.name); } static DEVICE_ATTR_RW(driver_override); static struct attribute *driver_override_dev_attrs[] = { &dev_attr_driver_override.attr, NULL, }; static const struct attribute_group driver_override_dev_group = { .attrs = driver_override_dev_attrs, }; /** * bus_add_device - add device to bus * @dev: device being added * * - Add device's bus attributes. * - Create links to device's bus. * - Add the device to its bus's list of devices. */ int bus_add_device(struct device *dev) { struct subsys_private *sp; int error; if (!dev->bus) { /* * This is a normal operation for many devices that do not * have a bus assigned to them, just say that all went * well. */ return 0; } sp = bus_to_subsys(dev->bus); if (!sp) { pr_err("%s: cannot add device '%s' to unregistered bus '%s'\n", __func__, dev_name(dev), dev->bus->name); return -EINVAL; } /* * Reference in sp is now incremented and will be dropped when * the device is removed from the bus */ pr_debug("bus: '%s': add device %s\n", sp->bus->name, dev_name(dev)); error = device_add_groups(dev, sp->bus->dev_groups); if (error) goto out_put; if (dev->bus->driver_override) { error = device_add_group(dev, &driver_override_dev_group); if (error) goto out_groups; } error = sysfs_create_link(&sp->devices_kset->kobj, &dev->kobj, dev_name(dev)); if (error) goto out_override; error = sysfs_create_link(&dev->kobj, &sp->subsys.kobj, "subsystem"); if (error) goto out_subsys; klist_add_tail(&dev->p->knode_bus, &sp->klist_devices); return 0; out_subsys: sysfs_remove_link(&sp->devices_kset->kobj, dev_name(dev)); out_override: if (dev->bus->driver_override) device_remove_group(dev, &driver_override_dev_group); out_groups: device_remove_groups(dev, sp->bus->dev_groups); out_put: subsys_put(sp); return error; } /** * bus_probe_device - probe drivers for a new device * @dev: device to probe * * - Automatically probe for a driver if the bus allows it. */ void bus_probe_device(struct device *dev) { struct subsys_private *sp = bus_to_subsys(dev->bus); struct subsys_interface *sif; if (!sp) return; device_initial_probe(dev); mutex_lock(&sp->mutex); list_for_each_entry(sif, &sp->interfaces, node) if (sif->add_dev) sif->add_dev(dev, sif); mutex_unlock(&sp->mutex); subsys_put(sp); } /** * bus_remove_device - remove device from bus * @dev: device to be removed * * - Remove device from all interfaces. * - Remove symlink from bus' directory. * - Delete device from bus's list. * - Detach from its driver. * - Drop reference taken in bus_add_device(). */ void bus_remove_device(struct device *dev) { struct subsys_private *sp = bus_to_subsys(dev->bus); struct subsys_interface *sif; if (!sp) return; mutex_lock(&sp->mutex); list_for_each_entry(sif, &sp->interfaces, node) if (sif->remove_dev) sif->remove_dev(dev, sif); mutex_unlock(&sp->mutex); sysfs_remove_link(&dev->kobj, "subsystem"); sysfs_remove_link(&sp->devices_kset->kobj, dev_name(dev)); if (dev->bus->driver_override) device_remove_group(dev, &driver_override_dev_group); device_remove_groups(dev, dev->bus->dev_groups); if (klist_node_attached(&dev->p->knode_bus)) klist_del(&dev->p->knode_bus); pr_debug("bus: '%s': remove device %s\n", dev->bus->name, dev_name(dev)); device_release_driver(dev); /* * Decrement the reference count twice, once for the bus_to_subsys() * call in the start of this function, and the second one from the * reference increment in bus_add_device() */ subsys_put(sp); subsys_put(sp); } static int __must_check add_bind_files(struct device_driver *drv) { int ret; ret = driver_create_file(drv, &driver_attr_unbind); if (ret == 0) { ret = driver_create_file(drv, &driver_attr_bind); if (ret) driver_remove_file(drv, &driver_attr_unbind); } return ret; } static void remove_bind_files(struct device_driver *drv) { driver_remove_file(drv, &driver_attr_bind); driver_remove_file(drv, &driver_attr_unbind); } static BUS_ATTR_WO(drivers_probe); static BUS_ATTR_RW(drivers_autoprobe); static int add_probe_files(const struct bus_type *bus) { int retval; retval = bus_create_file(bus, &bus_attr_drivers_probe); if (retval) goto out; retval = bus_create_file(bus, &bus_attr_drivers_autoprobe); if (retval) bus_remove_file(bus, &bus_attr_drivers_probe); out: return retval; } static void remove_probe_files(const struct bus_type *bus) { bus_remove_file(bus, &bus_attr_drivers_autoprobe); bus_remove_file(bus, &bus_attr_drivers_probe); } static ssize_t uevent_store(struct device_driver *drv, const char *buf, size_t count) { int rc; rc = kobject_synth_uevent(&drv->p->kobj, buf, count); return rc ? rc : count; } static DRIVER_ATTR_WO(uevent); /** * bus_add_driver - Add a driver to the bus. * @drv: driver. */ int bus_add_driver(struct device_driver *drv) { struct subsys_private *sp = bus_to_subsys(drv->bus); struct driver_private *priv; int error = 0; if (!sp) return -EINVAL; /* * Reference in sp is now incremented and will be dropped when * the driver is removed from the bus */ pr_debug("bus: '%s': add driver %s\n", sp->bus->name, drv->name); priv = kzalloc_obj(*priv); if (!priv) { error = -ENOMEM; goto out_put_bus; } klist_init(&priv->klist_devices, NULL, NULL); priv->driver = drv; drv->p = priv; priv->kobj.kset = sp->drivers_kset; error = kobject_init_and_add(&priv->kobj, &driver_ktype, NULL, "%s", drv->name); if (error) goto out_unregister; klist_add_tail(&priv->knode_bus, &sp->klist_drivers); if (sp->drivers_autoprobe) { error = driver_attach(drv); if (error) goto out_del_list; } error = module_add_driver(drv->owner, drv); if (error) { printk(KERN_ERR "%s: failed to create module links for %s\n", __func__, drv->name); goto out_detach; } error = driver_create_file(drv, &driver_attr_uevent); if (error) { printk(KERN_ERR "%s: uevent attr (%s) failed\n", __func__, drv->name); } error = driver_add_groups(drv, sp->bus->drv_groups); if (error) { /* How the hell do we get out of this pickle? Give up */ printk(KERN_ERR "%s: driver_add_groups(%s) failed\n", __func__, drv->name); } if (!drv->suppress_bind_attrs) { error = add_bind_files(drv); if (error) { /* Ditto */ printk(KERN_ERR "%s: add_bind_files(%s) failed\n", __func__, drv->name); } } return 0; out_detach: driver_detach(drv); out_del_list: klist_del(&priv->knode_bus); out_unregister: kobject_put(&priv->kobj); /* drv->p is freed in driver_release() */ drv->p = NULL; out_put_bus: subsys_put(sp); return error; } /** * bus_remove_driver - delete driver from bus's knowledge. * @drv: driver. * * Detach the driver from the devices it controls, and remove * it from its bus's list of drivers. Finally, we drop the reference * to the bus we took in bus_add_driver(). */ void bus_remove_driver(struct device_driver *drv) { struct subsys_private *sp = bus_to_subsys(drv->bus); if (!sp) return; pr_debug("bus: '%s': remove driver %s\n", sp->bus->name, drv->name); if (!drv->suppress_bind_attrs) remove_bind_files(drv); driver_remove_groups(drv, sp->bus->drv_groups); driver_remove_file(drv, &driver_attr_uevent); klist_remove(&drv->p->knode_bus); driver_detach(drv); module_remove_driver(drv); kobject_put(&drv->p->kobj); /* * Decrement the reference count twice, once for the bus_to_subsys() * call in the start of this function, and the second one from the * reference increment in bus_add_driver() */ subsys_put(sp); subsys_put(sp); } /* Helper for bus_rescan_devices's iter */ static int __must_check bus_rescan_devices_helper(struct device *dev, void *data) { int ret = 0; if (!dev->driver) { if (dev->parent && dev->bus->need_parent_lock) device_lock(dev->parent); ret = device_attach(dev); if (dev->parent && dev->bus->need_parent_lock) device_unlock(dev->parent); } return ret < 0 ? ret : 0; } /** * bus_rescan_devices - rescan devices on the bus for possible drivers * @bus: the bus to scan. * * This function will look for devices on the bus with no driver * attached and rescan it against existing drivers to see if it matches * any by calling device_attach() for the unbound devices. */ int bus_rescan_devices(const struct bus_type *bus) { return bus_for_each_dev(bus, NULL, NULL, bus_rescan_devices_helper); } EXPORT_SYMBOL_GPL(bus_rescan_devices); /** * device_reprobe - remove driver for a device and probe for a new driver * @dev: the device to reprobe * * This function detaches the attached driver (if any) for the given * device and restarts the driver probing process. It is intended * to use if probing criteria changed during a devices lifetime and * driver attachment should change accordingly. */ int device_reprobe(struct device *dev) { if (dev->driver) device_driver_detach(dev); return bus_rescan_devices_helper(dev, NULL); } EXPORT_SYMBOL_GPL(device_reprobe); static void klist_devices_get(struct klist_node *n) { struct device_private *dev_prv = to_device_private_bus(n); struct device *dev = dev_prv->device; get_device(dev); } static void klist_devices_put(struct klist_node *n) { struct device_private *dev_prv = to_device_private_bus(n); struct device *dev = dev_prv->device; put_device(dev); } static ssize_t bus_uevent_store(const struct bus_type *bus, const char *buf, size_t count) { struct subsys_private *sp = bus_to_subsys(bus); int ret; if (!sp) return -EINVAL; ret = kobject_synth_uevent(&sp->subsys.kobj, buf, count); subsys_put(sp); if (ret) return ret; return count; } /* * "open code" the old BUS_ATTR() macro here. We want to use BUS_ATTR_WO() * here, but can not use it as earlier in the file we have * DEVICE_ATTR_WO(uevent), which would cause a clash with the with the store * function name. */ static struct bus_attribute bus_attr_uevent = __ATTR(uevent, 0200, NULL, bus_uevent_store); /** * bus_register - register a driver-core subsystem * @bus: bus to register * * Once we have that, we register the bus with the kobject * infrastructure, then register the children subsystems it has: * the devices and drivers that belong to the subsystem. */ int bus_register(const struct bus_type *bus) { int retval; struct subsys_private *priv; struct kobject *bus_kobj; struct lock_class_key *key; priv = kzalloc_obj(struct subsys_private); if (!priv) return -ENOMEM; priv->bus = bus; BLOCKING_INIT_NOTIFIER_HEAD(&priv->bus_notifier); bus_kobj = &priv->subsys.kobj; retval = kobject_set_name(bus_kobj, "%s", bus->name); if (retval) goto out; bus_kobj->kset = bus_kset; bus_kobj->ktype = &bus_ktype; priv->drivers_autoprobe = 1; retval = kset_register(&priv->subsys); if (retval) goto out; retval = bus_create_file(bus, &bus_attr_uevent); if (retval) goto bus_uevent_fail; priv->devices_kset = kset_create_and_add("devices", NULL, bus_kobj); if (!priv->devices_kset) { retval = -ENOMEM; goto bus_devices_fail; } priv->drivers_kset = kset_create_and_add("drivers", NULL, bus_kobj); if (!priv->drivers_kset) { retval = -ENOMEM; goto bus_drivers_fail; } INIT_LIST_HEAD(&priv->interfaces); key = &priv->lock_key; lockdep_register_key(key); __mutex_init(&priv->mutex, "subsys mutex", key); klist_init(&priv->klist_devices, klist_devices_get, klist_devices_put); klist_init(&priv->klist_drivers, NULL, NULL); retval = add_probe_files(bus); if (retval) goto bus_probe_files_fail; retval = sysfs_create_groups(bus_kobj, bus->bus_groups); if (retval) goto bus_groups_fail; pr_debug("bus: '%s': registered\n", bus->name); return 0; bus_groups_fail: remove_probe_files(bus); bus_probe_files_fail: kset_unregister(priv->drivers_kset); bus_drivers_fail: kset_unregister(priv->devices_kset); bus_devices_fail: bus_remove_file(bus, &bus_attr_uevent); bus_uevent_fail: kset_unregister(&priv->subsys); /* Above kset_unregister() will kfree @priv */ priv = NULL; out: kfree(priv); return retval; } EXPORT_SYMBOL_GPL(bus_register); /** * bus_unregister - remove a bus from the system * @bus: bus. * * Unregister the child subsystems and the bus itself. * Finally, we call bus_put() to release the refcount */ void bus_unregister(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct kobject *bus_kobj; if (!sp) return; pr_debug("bus: '%s': unregistering\n", bus->name); if (sp->dev_root) device_unregister(sp->dev_root); bus_kobj = &sp->subsys.kobj; sysfs_remove_groups(bus_kobj, bus->bus_groups); remove_probe_files(bus); bus_remove_file(bus, &bus_attr_uevent); kset_unregister(sp->drivers_kset); kset_unregister(sp->devices_kset); kset_unregister(&sp->subsys); subsys_put(sp); } EXPORT_SYMBOL_GPL(bus_unregister); int bus_register_notifier(const struct bus_type *bus, struct notifier_block *nb) { struct subsys_private *sp = bus_to_subsys(bus); int retval; if (!sp) return -EINVAL; retval = blocking_notifier_chain_register(&sp->bus_notifier, nb); subsys_put(sp); return retval; } EXPORT_SYMBOL_GPL(bus_register_notifier); int bus_unregister_notifier(const struct bus_type *bus, struct notifier_block *nb) { struct subsys_private *sp = bus_to_subsys(bus); int retval; if (!sp) return -EINVAL; retval = blocking_notifier_chain_unregister(&sp->bus_notifier, nb); subsys_put(sp); return retval; } EXPORT_SYMBOL_GPL(bus_unregister_notifier); void bus_notify(struct device *dev, enum bus_notifier_event value) { struct subsys_private *sp = bus_to_subsys(dev->bus); if (!sp) return; blocking_notifier_call_chain(&sp->bus_notifier, value, dev); subsys_put(sp); } struct kset *bus_get_kset(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct kset *kset; if (!sp) return NULL; kset = &sp->subsys; subsys_put(sp); return kset; } EXPORT_SYMBOL_GPL(bus_get_kset); /* * Yes, this forcibly breaks the klist abstraction temporarily. It * just wants to sort the klist, not change reference counts and * take/drop locks rapidly in the process. It does all this while * holding the lock for the list, so objects can't otherwise be * added/removed while we're swizzling. */ static void device_insertion_sort_klist(struct device *a, struct list_head *list, int (*compare)(const struct device *a, const struct device *b)) { struct klist_node *n; struct device_private *dev_prv; struct device *b; list_for_each_entry(n, list, n_node) { dev_prv = to_device_private_bus(n); b = dev_prv->device; if (compare(a, b) <= 0) { list_move_tail(&a->p->knode_bus.n_node, &b->p->knode_bus.n_node); return; } } list_move_tail(&a->p->knode_bus.n_node, list); } void bus_sort_breadthfirst(const struct bus_type *bus, int (*compare)(const struct device *a, const struct device *b)) { struct subsys_private *sp = bus_to_subsys(bus); LIST_HEAD(sorted_devices); struct klist_node *n, *tmp; struct device_private *dev_prv; struct device *dev; struct klist *device_klist; if (!sp) return; device_klist = &sp->klist_devices; spin_lock(&device_klist->k_lock); list_for_each_entry_safe(n, tmp, &device_klist->k_list, n_node) { dev_prv = to_device_private_bus(n); dev = dev_prv->device; device_insertion_sort_klist(dev, &sorted_devices, compare); } list_splice(&sorted_devices, &device_klist->k_list); spin_unlock(&device_klist->k_lock); subsys_put(sp); } EXPORT_SYMBOL_GPL(bus_sort_breadthfirst); struct subsys_dev_iter { struct klist_iter ki; const struct device_type *type; }; /** * subsys_dev_iter_init - initialize subsys device iterator * @iter: subsys iterator to initialize * @sp: the subsys private (i.e. bus) we wanna iterate over * @start: the device to start iterating from, if any * @type: device_type of the devices to iterate over, NULL for all * * Initialize subsys iterator @iter such that it iterates over devices * of @subsys. If @start is set, the list iteration will start there, * otherwise if it is NULL, the iteration starts at the beginning of * the list. */ static void subsys_dev_iter_init(struct subsys_dev_iter *iter, struct subsys_private *sp, struct device *start, const struct device_type *type) { struct klist_node *start_knode = NULL; if (start) start_knode = &start->p->knode_bus; klist_iter_init_node(&sp->klist_devices, &iter->ki, start_knode); iter->type = type; } /** * subsys_dev_iter_next - iterate to the next device * @iter: subsys iterator to proceed * * Proceed @iter to the next device and return it. Returns NULL if * iteration is complete. * * The returned device is referenced and won't be released till * iterator is proceed to the next device or exited. The caller is * free to do whatever it wants to do with the device including * calling back into subsys code. */ static struct device *subsys_dev_iter_next(struct subsys_dev_iter *iter) { struct klist_node *knode; struct device *dev; for (;;) { knode = klist_next(&iter->ki); if (!knode) return NULL; dev = to_device_private_bus(knode)->device; if (!iter->type || iter->type == dev->type) return dev; } } /** * subsys_dev_iter_exit - finish iteration * @iter: subsys iterator to finish * * Finish an iteration. Always call this function after iteration is * complete whether the iteration ran till the end or not. */ static void subsys_dev_iter_exit(struct subsys_dev_iter *iter) { klist_iter_exit(&iter->ki); } int subsys_interface_register(struct subsys_interface *sif) { struct subsys_private *sp; struct subsys_dev_iter iter; struct device *dev; if (!sif || !sif->subsys) return -ENODEV; sp = bus_to_subsys(sif->subsys); if (!sp) return -EINVAL; /* * Reference in sp is now incremented and will be dropped when * the interface is removed from the bus */ mutex_lock(&sp->mutex); list_add_tail(&sif->node, &sp->interfaces); if (sif->add_dev) { subsys_dev_iter_init(&iter, sp, NULL, NULL); while ((dev = subsys_dev_iter_next(&iter))) sif->add_dev(dev, sif); subsys_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); return 0; } EXPORT_SYMBOL_GPL(subsys_interface_register); void subsys_interface_unregister(struct subsys_interface *sif) { struct subsys_private *sp; struct subsys_dev_iter iter; struct device *dev; if (!sif || !sif->subsys) return; sp = bus_to_subsys(sif->subsys); if (!sp) return; mutex_lock(&sp->mutex); list_del_init(&sif->node); if (sif->remove_dev) { subsys_dev_iter_init(&iter, sp, NULL, NULL); while ((dev = subsys_dev_iter_next(&iter))) sif->remove_dev(dev, sif); subsys_dev_iter_exit(&iter); } mutex_unlock(&sp->mutex); /* * Decrement the reference count twice, once for the bus_to_subsys() * call in the start of this function, and the second one from the * reference increment in subsys_interface_register() */ subsys_put(sp); subsys_put(sp); } EXPORT_SYMBOL_GPL(subsys_interface_unregister); static void system_root_device_release(struct device *dev) { kfree(dev); } static int subsys_register(const struct bus_type *subsys, const struct attribute_group **groups, struct kobject *parent_of_root) { struct subsys_private *sp; struct device *dev; int err; err = bus_register(subsys); if (err < 0) return err; sp = bus_to_subsys(subsys); if (!sp) { err = -EINVAL; goto err_sp; } dev = kzalloc_obj(struct device); if (!dev) { err = -ENOMEM; goto err_dev; } err = dev_set_name(dev, "%s", subsys->name); if (err < 0) goto err_name; dev->kobj.parent = parent_of_root; dev->groups = groups; dev->release = system_root_device_release; err = device_register(dev); if (err < 0) goto err_dev_reg; sp->dev_root = dev; subsys_put(sp); return 0; err_dev_reg: put_device(dev); dev = NULL; err_name: kfree(dev); err_dev: subsys_put(sp); err_sp: bus_unregister(subsys); return err; } /** * subsys_system_register - register a subsystem at /sys/devices/system/ * @subsys: system subsystem * @groups: default attributes for the root device * * All 'system' subsystems have a /sys/devices/system/<name> root device * with the name of the subsystem. The root device can carry subsystem- * wide attributes. All registered devices are below this single root * device and are named after the subsystem with a simple enumeration * number appended. The registered devices are not explicitly named; * only 'id' in the device needs to be set. * * Do not use this interface for anything new, it exists for compatibility * with bad ideas only. New subsystems should use plain subsystems; and * add the subsystem-wide attributes should be added to the subsystem * directory itself and not some create fake root-device placed in * /sys/devices/system/<name>. */ int subsys_system_register(const struct bus_type *subsys, const struct attribute_group **groups) { return subsys_register(subsys, groups, &system_kset->kobj); } EXPORT_SYMBOL_GPL(subsys_system_register); /** * subsys_virtual_register - register a subsystem at /sys/devices/virtual/ * @subsys: virtual subsystem * @groups: default attributes for the root device * * All 'virtual' subsystems have a /sys/devices/system/<name> root device * with the name of the subsystem. The root device can carry subsystem-wide * attributes. All registered devices are below this single root device. * There's no restriction on device naming. This is for kernel software * constructs which need sysfs interface. */ int subsys_virtual_register(const struct bus_type *subsys, const struct attribute_group **groups) { struct kobject *virtual_dir; virtual_dir = virtual_device_parent(); if (!virtual_dir) return -ENOMEM; return subsys_register(subsys, groups, virtual_dir); } EXPORT_SYMBOL_GPL(subsys_virtual_register); /** * driver_find - locate driver on a bus by its name. * @name: name of the driver. * @bus: bus to scan for the driver. * * Call kset_find_obj() to iterate over list of drivers on * a bus to find driver by name. Return driver if found. * * This routine provides no locking to prevent the driver it returns * from being unregistered or unloaded while the caller is using it. * The caller is responsible for preventing this. */ struct device_driver *driver_find(const char *name, const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct kobject *k; struct driver_private *priv; if (!sp) return NULL; k = kset_find_obj(sp->drivers_kset, name); subsys_put(sp); if (!k) return NULL; priv = to_driver(k); /* Drop reference added by kset_find_obj() */ kobject_put(k); return priv->driver; } EXPORT_SYMBOL_GPL(driver_find); /* * Warning, the value could go to "removed" instantly after calling this function, so be very * careful when calling it... */ bool bus_is_registered(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); bool is_initialized = false; if (sp) { is_initialized = true; subsys_put(sp); } return is_initialized; } /** * bus_get_dev_root - return a pointer to the "device root" of a bus * @bus: bus to return the device root of. * * If a bus has a "device root" structure, return it, WITH THE REFERENCE * COUNT INCREMENTED. * * Note, when finished with the device, a call to put_device() is required. * * If the device root is not present (or bus is not a valid pointer), NULL * will be returned. */ struct device *bus_get_dev_root(const struct bus_type *bus) { struct subsys_private *sp = bus_to_subsys(bus); struct device *dev_root; if (!sp) return NULL; dev_root = get_device(sp->dev_root); subsys_put(sp); return dev_root; } EXPORT_SYMBOL_GPL(bus_get_dev_root); int __init buses_init(void) { bus_kset = kset_create_and_add("bus", &bus_uevent_ops, NULL); if (!bus_kset) return -ENOMEM; system_kset = kset_create_and_add("system", NULL, &devices_kset->kobj); if (!system_kset) { /* Do error handling here as devices_init() do */ kset_unregister(bus_kset); bus_kset = NULL; pr_err("%s: failed to create and add kset 'bus'\n", __func__); return -ENOMEM; } return 0; } |
| 170 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-only /* * Dynamic DMA mapping support. * * This implementation is a fallback for platforms that do not support * I/O TLBs (aka DMA address translation hardware). * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com> * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com> * Copyright (C) 2000, 2003 Hewlett-Packard Co * David Mosberger-Tang <davidm@hpl.hp.com> * * 03/05/07 davidm Switch from PCI-DMA to generic device DMA API. * 00/12/13 davidm Rename to swiotlb.c and add mark_clean() to avoid * unnecessary i-cache flushing. * 04/07/.. ak Better overflow handling. Assorted fixes. * 05/09/10 linville Add support for syncing ranges, support syncing for * DMA_BIDIRECTIONAL mappings, miscellaneous cleanup. * 08/12/11 beckyb Add highmem support */ #define pr_fmt(fmt) "software IO TLB: " fmt #include <linux/cache.h> #include <linux/cc_platform.h> #include <linux/ctype.h> #include <linux/debugfs.h> #include <linux/dma-direct.h> #include <linux/dma-map-ops.h> #include <linux/export.h> #include <linux/gfp.h> #include <linux/highmem.h> #include <linux/io.h> #include <linux/kmsan-checks.h> #include <linux/iommu-helper.h> #include <linux/init.h> #include <linux/memblock.h> #include <linux/mm.h> #include <linux/pfn.h> #include <linux/rculist.h> #include <linux/scatterlist.h> #include <linux/set_memory.h> #include <linux/spinlock.h> #include <linux/string.h> #include <linux/swiotlb.h> #include <linux/types.h> #ifdef CONFIG_DMA_RESTRICTED_POOL #include <linux/of.h> #include <linux/of_fdt.h> #include <linux/of_reserved_mem.h> #include <linux/slab.h> #endif #define CREATE_TRACE_POINTS #include <trace/events/swiotlb.h> #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT)) /* * Minimum IO TLB size to bother booting with. Systems with mainly * 64bit capable cards will only lightly use the swiotlb. If we can't * allocate a contiguous 1MB, we're probably in trouble anyway. */ #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT) /** * struct io_tlb_slot - IO TLB slot descriptor * @orig_addr: The original address corresponding to a mapped entry. * @alloc_size: Size of the allocated buffer. * @list: The free list describing the number of free entries available * from each index. * @pad_slots: Number of preceding padding slots. Valid only in the first * allocated non-padding slot. */ struct io_tlb_slot { phys_addr_t orig_addr; size_t alloc_size; unsigned short list; unsigned short pad_slots; }; static bool swiotlb_force_bounce; static bool swiotlb_force_disable; #ifdef CONFIG_SWIOTLB_DYNAMIC static void swiotlb_dyn_alloc(struct work_struct *work); static struct io_tlb_mem io_tlb_default_mem = { .lock = __SPIN_LOCK_UNLOCKED(io_tlb_default_mem.lock), .pools = LIST_HEAD_INIT(io_tlb_default_mem.pools), .dyn_alloc = __WORK_INITIALIZER(io_tlb_default_mem.dyn_alloc, swiotlb_dyn_alloc), }; #else /* !CONFIG_SWIOTLB_DYNAMIC */ static struct io_tlb_mem io_tlb_default_mem; #endif /* CONFIG_SWIOTLB_DYNAMIC */ static unsigned long default_nslabs = IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT; static unsigned long default_nareas; /** * struct io_tlb_area - IO TLB memory area descriptor * * This is a single area with a single lock. * * @used: The number of used IO TLB block. * @index: The slot index to start searching in this area for next round. * @lock: The lock to protect the above data structures in the map and * unmap calls. */ struct io_tlb_area { unsigned long used; unsigned int index; spinlock_t lock; }; /* * Round up number of slabs to the next power of 2. The last area is going * be smaller than the rest if default_nslabs is not power of two. * The number of slot in an area should be a multiple of IO_TLB_SEGSIZE, * otherwise a segment may span two or more areas. It conflicts with free * contiguous slots tracking: free slots are treated contiguous no matter * whether they cross an area boundary. * * Return true if default_nslabs is rounded up. */ static bool round_up_default_nslabs(void) { if (!default_nareas) return false; if (default_nslabs < IO_TLB_SEGSIZE * default_nareas) default_nslabs = IO_TLB_SEGSIZE * default_nareas; else if (is_power_of_2(default_nslabs)) return false; default_nslabs = roundup_pow_of_two(default_nslabs); return true; } /** * swiotlb_adjust_nareas() - adjust the number of areas and slots * @nareas: Desired number of areas. Zero is treated as 1. * * Adjust the default number of areas in a memory pool. * The default size of the memory pool may also change to meet minimum area * size requirements. */ static void swiotlb_adjust_nareas(unsigned int nareas) { if (!nareas) nareas = 1; else if (!is_power_of_2(nareas)) nareas = roundup_pow_of_two(nareas); default_nareas = nareas; pr_info("area num %d.\n", nareas); if (round_up_default_nslabs()) pr_info("SWIOTLB bounce buffer size roundup to %luMB", (default_nslabs << IO_TLB_SHIFT) >> 20); } /** * limit_nareas() - get the maximum number of areas for a given memory pool size * @nareas: Desired number of areas. * @nslots: Total number of slots in the memory pool. * * Limit the number of areas to the maximum possible number of areas in * a memory pool of the given size. * * Return: Maximum possible number of areas. */ static unsigned int limit_nareas(unsigned int nareas, unsigned long nslots) { if (nslots < nareas * IO_TLB_SEGSIZE) return nslots / IO_TLB_SEGSIZE; return nareas; } static int __init setup_io_tlb_npages(char *str) { if (isdigit(*str)) { /* avoid tail segment of size < IO_TLB_SEGSIZE */ default_nslabs = ALIGN(simple_strtoul(str, &str, 0), IO_TLB_SEGSIZE); } if (*str == ',') ++str; if (isdigit(*str)) swiotlb_adjust_nareas(simple_strtoul(str, &str, 0)); if (*str == ',') ++str; if (!strcmp(str, "force")) swiotlb_force_bounce = true; else if (!strcmp(str, "noforce")) swiotlb_force_disable = true; return 0; } early_param("swiotlb", setup_io_tlb_npages); unsigned long swiotlb_size_or_default(void) { return default_nslabs << IO_TLB_SHIFT; } void __init swiotlb_adjust_size(unsigned long size) { /* * If swiotlb parameter has not been specified, give a chance to * architectures such as those supporting memory encryption to * adjust/expand SWIOTLB size for their use. */ if (default_nslabs != IO_TLB_DEFAULT_SIZE >> IO_TLB_SHIFT) return; size = ALIGN(size, IO_TLB_SIZE); default_nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); if (round_up_default_nslabs()) size = default_nslabs << IO_TLB_SHIFT; pr_info("SWIOTLB bounce buffer size adjusted to %luMB", size >> 20); } void swiotlb_print_info(void) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; if (!mem->nslabs) { pr_warn("No low mem\n"); return; } pr_info("mapped [mem %pa-%pa] (%luMB)\n", &mem->start, &mem->end, (mem->nslabs << IO_TLB_SHIFT) >> 20); } static inline unsigned long io_tlb_offset(unsigned long val) { return val & (IO_TLB_SEGSIZE - 1); } static inline unsigned long nr_slots(u64 val) { return DIV_ROUND_UP(val, IO_TLB_SIZE); } /* * Early SWIOTLB allocation may be too early to allow an architecture to * perform the desired operations. This function allows the architecture to * call SWIOTLB when the operations are possible. It needs to be called * before the SWIOTLB memory is used. */ void __init swiotlb_update_mem_attributes(void) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long bytes; if (!mem->nslabs || mem->late_alloc) return; bytes = PAGE_ALIGN(mem->nslabs << IO_TLB_SHIFT); set_memory_decrypted((unsigned long)mem->vaddr, bytes >> PAGE_SHIFT); } static void swiotlb_init_io_tlb_pool(struct io_tlb_pool *mem, phys_addr_t start, unsigned long nslabs, bool late_alloc, unsigned int nareas) { void *vaddr = phys_to_virt(start); unsigned long bytes = nslabs << IO_TLB_SHIFT, i; mem->nslabs = nslabs; mem->start = start; mem->end = mem->start + bytes; mem->late_alloc = late_alloc; mem->nareas = nareas; mem->area_nslabs = nslabs / mem->nareas; for (i = 0; i < mem->nareas; i++) { spin_lock_init(&mem->areas[i].lock); mem->areas[i].index = 0; mem->areas[i].used = 0; } for (i = 0; i < mem->nslabs; i++) { mem->slots[i].list = min(IO_TLB_SEGSIZE - io_tlb_offset(i), mem->nslabs - i); mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; mem->slots[i].pad_slots = 0; } memset(vaddr, 0, bytes); mem->vaddr = vaddr; return; } /** * add_mem_pool() - add a memory pool to the allocator * @mem: Software IO TLB allocator. * @pool: Memory pool to be added. */ static void add_mem_pool(struct io_tlb_mem *mem, struct io_tlb_pool *pool) { #ifdef CONFIG_SWIOTLB_DYNAMIC spin_lock(&mem->lock); list_add_rcu(&pool->node, &mem->pools); mem->nslabs += pool->nslabs; spin_unlock(&mem->lock); #else mem->nslabs = pool->nslabs; #endif } static void __init *swiotlb_memblock_alloc(unsigned long nslabs, unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)) { size_t bytes = PAGE_ALIGN(nslabs << IO_TLB_SHIFT); void *tlb; /* * By default allocate the bounce buffer memory from low memory, but * allow to pick a location everywhere for hypervisors with guest * memory encryption. */ if (flags & SWIOTLB_ANY) tlb = memblock_alloc(bytes, PAGE_SIZE); else tlb = memblock_alloc_low(bytes, PAGE_SIZE); if (!tlb) { pr_warn("%s: Failed to allocate %zu bytes tlb structure\n", __func__, bytes); return NULL; } if (remap && remap(tlb, nslabs) < 0) { memblock_free(tlb, PAGE_ALIGN(bytes)); pr_warn("%s: Failed to remap %zu bytes\n", __func__, bytes); return NULL; } return tlb; } /* * Statically reserve bounce buffer space and initialize bounce buffer data * structures for the software IO TLB used to implement the DMA API. */ void __init swiotlb_init_remap(bool addressing_limit, unsigned int flags, int (*remap)(void *tlb, unsigned long nslabs)) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long nslabs; unsigned int nareas; size_t alloc_size; void *tlb; if (!addressing_limit && !swiotlb_force_bounce) return; if (swiotlb_force_disable) return; io_tlb_default_mem.force_bounce = swiotlb_force_bounce || (flags & SWIOTLB_FORCE); #ifdef CONFIG_SWIOTLB_DYNAMIC if (!remap) io_tlb_default_mem.can_grow = true; if (flags & SWIOTLB_ANY) io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); else io_tlb_default_mem.phys_limit = ARCH_LOW_ADDRESS_LIMIT; #endif if (!default_nareas) swiotlb_adjust_nareas(num_possible_cpus()); nslabs = default_nslabs; nareas = limit_nareas(default_nareas, nslabs); while ((tlb = swiotlb_memblock_alloc(nslabs, flags, remap)) == NULL) { if (nslabs <= IO_TLB_MIN_SLABS) return; nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); nareas = limit_nareas(nareas, nslabs); } if (default_nslabs != nslabs) { pr_info("SWIOTLB bounce buffer size adjusted %lu -> %lu slabs", default_nslabs, nslabs); default_nslabs = nslabs; } alloc_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), nslabs)); mem->slots = memblock_alloc(alloc_size, PAGE_SIZE); if (!mem->slots) { pr_warn("%s: Failed to allocate %zu bytes align=0x%lx\n", __func__, alloc_size, PAGE_SIZE); return; } mem->areas = memblock_alloc(array_size(sizeof(struct io_tlb_area), nareas), SMP_CACHE_BYTES); if (!mem->areas) { pr_warn("%s: Failed to allocate mem->areas.\n", __func__); return; } swiotlb_init_io_tlb_pool(mem, __pa(tlb), nslabs, false, nareas); add_mem_pool(&io_tlb_default_mem, mem); if (flags & SWIOTLB_VERBOSE) swiotlb_print_info(); } void __init swiotlb_init(bool addressing_limit, unsigned int flags) { swiotlb_init_remap(addressing_limit, flags, NULL); } /* * Systems with larger DMA zones (those that don't support ISA) can * initialize the swiotlb later using the slab allocator if needed. * This should be just like above, but with some error catching. */ int swiotlb_init_late(size_t size, gfp_t gfp_mask, int (*remap)(void *tlb, unsigned long nslabs)) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long nslabs = ALIGN(size >> IO_TLB_SHIFT, IO_TLB_SEGSIZE); unsigned int nareas; unsigned char *vstart = NULL; unsigned int order, area_order; bool retried = false; int rc = 0; if (io_tlb_default_mem.nslabs) return 0; if (swiotlb_force_disable) return 0; io_tlb_default_mem.force_bounce = swiotlb_force_bounce; #ifdef CONFIG_SWIOTLB_DYNAMIC if (!remap) io_tlb_default_mem.can_grow = true; if (IS_ENABLED(CONFIG_ZONE_DMA) && (gfp_mask & __GFP_DMA)) io_tlb_default_mem.phys_limit = zone_dma_limit; else if (IS_ENABLED(CONFIG_ZONE_DMA32) && (gfp_mask & __GFP_DMA32)) io_tlb_default_mem.phys_limit = max(DMA_BIT_MASK(32), zone_dma_limit); else io_tlb_default_mem.phys_limit = virt_to_phys(high_memory - 1); #endif if (!default_nareas) swiotlb_adjust_nareas(num_possible_cpus()); retry: order = get_order(nslabs << IO_TLB_SHIFT); nslabs = SLABS_PER_PAGE << order; while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) { vstart = (void *)__get_free_pages(gfp_mask | __GFP_NOWARN, order); if (vstart) break; order--; nslabs = SLABS_PER_PAGE << order; retried = true; } if (!vstart) return -ENOMEM; if (remap) rc = remap(vstart, nslabs); if (rc) { free_pages((unsigned long)vstart, order); nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); if (nslabs < IO_TLB_MIN_SLABS) return rc; retried = true; goto retry; } if (retried) { pr_warn("only able to allocate %ld MB\n", (PAGE_SIZE << order) >> 20); } nareas = limit_nareas(default_nareas, nslabs); area_order = get_order(array_size(sizeof(*mem->areas), nareas)); mem->areas = (struct io_tlb_area *) __get_free_pages(GFP_KERNEL | __GFP_ZERO, area_order); if (!mem->areas) goto error_area; mem->slots = (void *)__get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(array_size(sizeof(*mem->slots), nslabs))); if (!mem->slots) goto error_slots; set_memory_decrypted((unsigned long)vstart, (nslabs << IO_TLB_SHIFT) >> PAGE_SHIFT); swiotlb_init_io_tlb_pool(mem, virt_to_phys(vstart), nslabs, true, nareas); add_mem_pool(&io_tlb_default_mem, mem); swiotlb_print_info(); return 0; error_slots: free_pages((unsigned long)mem->areas, area_order); error_area: free_pages((unsigned long)vstart, order); return -ENOMEM; } void __init swiotlb_exit(void) { struct io_tlb_pool *mem = &io_tlb_default_mem.defpool; unsigned long tbl_vaddr; size_t tbl_size, slots_size; unsigned int area_order; if (swiotlb_force_bounce) return; if (!mem->nslabs) return; pr_info("tearing down default memory pool\n"); tbl_vaddr = (unsigned long)phys_to_virt(mem->start); tbl_size = PAGE_ALIGN(mem->end - mem->start); slots_size = PAGE_ALIGN(array_size(sizeof(*mem->slots), mem->nslabs)); set_memory_encrypted(tbl_vaddr, tbl_size >> PAGE_SHIFT); if (mem->late_alloc) { area_order = get_order(array_size(sizeof(*mem->areas), mem->nareas)); free_pages((unsigned long)mem->areas, area_order); free_pages(tbl_vaddr, get_order(tbl_size)); free_pages((unsigned long)mem->slots, get_order(slots_size)); } else { memblock_free(mem->areas, array_size(sizeof(*mem->areas), mem->nareas)); memblock_phys_free(mem->start, tbl_size); memblock_free(mem->slots, slots_size); } memset(mem, 0, sizeof(*mem)); } #ifdef CONFIG_SWIOTLB_DYNAMIC /** * alloc_dma_pages() - allocate pages to be used for DMA * @gfp: GFP flags for the allocation. * @bytes: Size of the buffer. * @phys_limit: Maximum allowed physical address of the buffer. * * Allocate pages from the buddy allocator. If successful, make the allocated * pages decrypted that they can be used for DMA. * * Return: Decrypted pages, %NULL on allocation failure, or ERR_PTR(-EAGAIN) * if the allocated physical address was above @phys_limit. */ static struct page *alloc_dma_pages(gfp_t gfp, size_t bytes, u64 phys_limit) { unsigned int order = get_order(bytes); struct page *page; phys_addr_t paddr; void *vaddr; page = alloc_pages(gfp, order); if (!page) return NULL; paddr = page_to_phys(page); if (paddr + bytes - 1 > phys_limit) { __free_pages(page, order); return ERR_PTR(-EAGAIN); } vaddr = phys_to_virt(paddr); if (set_memory_decrypted((unsigned long)vaddr, PFN_UP(bytes))) goto error; return page; error: /* Intentional leak if pages cannot be encrypted again. */ if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) __free_pages(page, order); return NULL; } /** * swiotlb_alloc_tlb() - allocate a dynamic IO TLB buffer * @dev: Device for which a memory pool is allocated. * @bytes: Size of the buffer. * @phys_limit: Maximum allowed physical address of the buffer. * @gfp: GFP flags for the allocation. * * Return: Allocated pages, or %NULL on allocation failure. */ static struct page *swiotlb_alloc_tlb(struct device *dev, size_t bytes, u64 phys_limit, gfp_t gfp) { struct page *page; /* * Allocate from the atomic pools if memory is encrypted and * the allocation is atomic, because decrypting may block. */ if (!gfpflags_allow_blocking(gfp) && dev && force_dma_unencrypted(dev)) { void *vaddr; if (!IS_ENABLED(CONFIG_DMA_COHERENT_POOL)) return NULL; return dma_alloc_from_pool(dev, bytes, &vaddr, gfp, dma_coherent_ok); } gfp &= ~GFP_ZONEMASK; if (phys_limit <= zone_dma_limit) gfp |= __GFP_DMA; else if (phys_limit <= DMA_BIT_MASK(32)) gfp |= __GFP_DMA32; while (IS_ERR(page = alloc_dma_pages(gfp, bytes, phys_limit))) { if (IS_ENABLED(CONFIG_ZONE_DMA32) && phys_limit < DMA_BIT_MASK(64) && !(gfp & (__GFP_DMA32 | __GFP_DMA))) gfp |= __GFP_DMA32; else if (IS_ENABLED(CONFIG_ZONE_DMA) && !(gfp & __GFP_DMA)) gfp = (gfp & ~__GFP_DMA32) | __GFP_DMA; else return NULL; } return page; } /** * swiotlb_free_tlb() - free a dynamically allocated IO TLB buffer * @vaddr: Virtual address of the buffer. * @bytes: Size of the buffer. */ static void swiotlb_free_tlb(void *vaddr, size_t bytes) { if (IS_ENABLED(CONFIG_DMA_COHERENT_POOL) && dma_free_from_pool(NULL, vaddr, bytes)) return; /* Intentional leak if pages cannot be encrypted again. */ if (!set_memory_encrypted((unsigned long)vaddr, PFN_UP(bytes))) __free_pages(virt_to_page(vaddr), get_order(bytes)); } /** * swiotlb_alloc_pool() - allocate a new IO TLB memory pool * @dev: Device for which a memory pool is allocated. * @minslabs: Minimum number of slabs. * @nslabs: Desired (maximum) number of slabs. * @nareas: Number of areas. * @phys_limit: Maximum DMA buffer physical address. * @gfp: GFP flags for the allocations. * * Allocate and initialize a new IO TLB memory pool. The actual number of * slabs may be reduced if allocation of @nslabs fails. If even * @minslabs cannot be allocated, this function fails. * * Return: New memory pool, or %NULL on allocation failure. */ static struct io_tlb_pool *swiotlb_alloc_pool(struct device *dev, unsigned long minslabs, unsigned long nslabs, unsigned int nareas, u64 phys_limit, gfp_t gfp) { struct io_tlb_pool *pool; unsigned int slot_order; struct page *tlb; size_t pool_size; size_t tlb_size; if (nslabs > SLABS_PER_PAGE << MAX_PAGE_ORDER) { nslabs = SLABS_PER_PAGE << MAX_PAGE_ORDER; nareas = limit_nareas(nareas, nslabs); } pool_size = sizeof(*pool) + array_size(sizeof(*pool->areas), nareas); pool = kzalloc(pool_size, gfp); if (!pool) goto error; pool->areas = (void *)pool + sizeof(*pool); tlb_size = nslabs << IO_TLB_SHIFT; while (!(tlb = swiotlb_alloc_tlb(dev, tlb_size, phys_limit, gfp))) { if (nslabs <= minslabs) goto error_tlb; nslabs = ALIGN(nslabs >> 1, IO_TLB_SEGSIZE); nareas = limit_nareas(nareas, nslabs); tlb_size = nslabs << IO_TLB_SHIFT; } slot_order = get_order(array_size(sizeof(*pool->slots), nslabs)); pool->slots = (struct io_tlb_slot *) __get_free_pages(gfp, slot_order); if (!pool->slots) goto error_slots; swiotlb_init_io_tlb_pool(pool, page_to_phys(tlb), nslabs, true, nareas); return pool; error_slots: swiotlb_free_tlb(page_address(tlb), tlb_size); error_tlb: kfree(pool); error: return NULL; } /** * swiotlb_dyn_alloc() - dynamic memory pool allocation worker * @work: Pointer to dyn_alloc in struct io_tlb_mem. */ static void swiotlb_dyn_alloc(struct work_struct *work) { struct io_tlb_mem *mem = container_of(work, struct io_tlb_mem, dyn_alloc); struct io_tlb_pool *pool; pool = swiotlb_alloc_pool(NULL, IO_TLB_MIN_SLABS, default_nslabs, default_nareas, mem->phys_limit, GFP_KERNEL); if (!pool) { pr_warn_ratelimited("Failed to allocate new pool"); return; } add_mem_pool(mem, pool); } /** * swiotlb_dyn_free() - RCU callback to free a memory pool * @rcu: RCU head in the corresponding struct io_tlb_pool. */ static void swiotlb_dyn_free(struct rcu_head *rcu) { struct io_tlb_pool *pool = container_of(rcu, struct io_tlb_pool, rcu); size_t slots_size = array_size(sizeof(*pool->slots), pool->nslabs); size_t tlb_size = pool->end - pool->start; free_pages((unsigned long)pool->slots, get_order(slots_size)); swiotlb_free_tlb(pool->vaddr, tlb_size); kfree(pool); } /** * __swiotlb_find_pool() - find the IO TLB pool for a physical address * @dev: Device which has mapped the DMA buffer. * @paddr: Physical address within the DMA buffer. * * Find the IO TLB memory pool descriptor which contains the given physical * address, if any. This function is for use only when the dev is known to * be using swiotlb. Use swiotlb_find_pool() for the more general case * when this condition is not met. * * Return: Memory pool which contains @paddr, or %NULL if none. */ struct io_tlb_pool *__swiotlb_find_pool(struct device *dev, phys_addr_t paddr) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; rcu_read_lock(); list_for_each_entry_rcu(pool, &mem->pools, node) { if (paddr >= pool->start && paddr < pool->end) goto out; } list_for_each_entry_rcu(pool, &dev->dma_io_tlb_pools, node) { if (paddr >= pool->start && paddr < pool->end) goto out; } pool = NULL; out: rcu_read_unlock(); return pool; } /** * swiotlb_del_pool() - remove an IO TLB pool from a device * @dev: Owning device. * @pool: Memory pool to be removed. */ static void swiotlb_del_pool(struct device *dev, struct io_tlb_pool *pool) { unsigned long flags; spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); list_del_rcu(&pool->node); spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); call_rcu(&pool->rcu, swiotlb_dyn_free); } #endif /* CONFIG_SWIOTLB_DYNAMIC */ /** * swiotlb_dev_init() - initialize swiotlb fields in &struct device * @dev: Device to be initialized. */ void swiotlb_dev_init(struct device *dev) { dev->dma_io_tlb_mem = &io_tlb_default_mem; #ifdef CONFIG_SWIOTLB_DYNAMIC INIT_LIST_HEAD(&dev->dma_io_tlb_pools); spin_lock_init(&dev->dma_io_tlb_lock); dev->dma_uses_io_tlb = false; #endif } /** * swiotlb_align_offset() - Get required offset into an IO TLB allocation. * @dev: Owning device. * @align_mask: Allocation alignment mask. * @addr: DMA address. * * Return the minimum offset from the start of an IO TLB allocation which is * required for a given buffer address and allocation alignment to keep the * device happy. * * First, the address bits covered by min_align_mask must be identical in the * original address and the bounce buffer address. High bits are preserved by * choosing a suitable IO TLB slot, but bits below IO_TLB_SHIFT require extra * padding bytes before the bounce buffer. * * Second, @align_mask specifies which bits of the first allocated slot must * be zero. This may require allocating additional padding slots, and then the * offset (in bytes) from the first such padding slot is returned. */ static unsigned int swiotlb_align_offset(struct device *dev, unsigned int align_mask, u64 addr) { return addr & dma_get_min_align_mask(dev) & (align_mask | (IO_TLB_SIZE - 1)); } /* * Bounce: copy the swiotlb buffer from or back to the original dma location */ static void swiotlb_bounce(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, struct io_tlb_pool *mem) { int index = (tlb_addr - mem->start) >> IO_TLB_SHIFT; phys_addr_t orig_addr = mem->slots[index].orig_addr; size_t alloc_size = mem->slots[index].alloc_size; unsigned long pfn = PFN_DOWN(orig_addr); unsigned char *vaddr = mem->vaddr + tlb_addr - mem->start; int tlb_offset; if (orig_addr == INVALID_PHYS_ADDR) return; if (dir == DMA_FROM_DEVICE && !dev_is_dma_coherent(dev)) arch_sync_dma_flush(); /* * It's valid for tlb_offset to be negative. This can happen when the * "offset" returned by swiotlb_align_offset() is non-zero, and the * tlb_addr is pointing within the first "offset" bytes of the second * or subsequent slots of the allocated swiotlb area. While it's not * valid for tlb_addr to be pointing within the first "offset" bytes * of the first slot, there's no way to check for such an error since * this function can't distinguish the first slot from the second and * subsequent slots. */ tlb_offset = (tlb_addr & (IO_TLB_SIZE - 1)) - swiotlb_align_offset(dev, 0, orig_addr); orig_addr += tlb_offset; alloc_size -= tlb_offset; if (size > alloc_size) { dev_WARN_ONCE(dev, 1, "Buffer overflow detected. Allocation size: %zu. Mapping size: %zu.\n", alloc_size, size); size = alloc_size; } if (PageHighMem(pfn_to_page(pfn))) { unsigned int offset = orig_addr & ~PAGE_MASK; struct page *page; unsigned int sz = 0; unsigned long flags; while (size) { sz = min_t(size_t, PAGE_SIZE - offset, size); local_irq_save(flags); page = pfn_to_page(pfn); if (dir == DMA_TO_DEVICE) { /* * Ideally, kmsan_check_highmem_page() * could be used here to detect infoleaks, * but callers may map uninitialized buffers * that will be written by the device, * causing false positives. */ memcpy_from_page(vaddr, page, offset, sz); } else { kmsan_unpoison_memory(vaddr, sz); memcpy_to_page(page, offset, vaddr, sz); } local_irq_restore(flags); size -= sz; pfn++; vaddr += sz; offset = 0; } } else if (dir == DMA_TO_DEVICE) { /* * Ideally, kmsan_check_memory() could be used here to detect * infoleaks (uninitialized data being sent to device), but * callers may map uninitialized buffers that will be written * by the device, causing false positives. */ memcpy(vaddr, phys_to_virt(orig_addr), size); } else { kmsan_unpoison_memory(vaddr, size); memcpy(phys_to_virt(orig_addr), vaddr, size); } } static inline phys_addr_t slot_addr(phys_addr_t start, phys_addr_t idx) { return start + (idx << IO_TLB_SHIFT); } /* * Carefully handle integer overflow which can occur when boundary_mask == ~0UL. */ static inline unsigned long get_max_slots(unsigned long boundary_mask) { return (boundary_mask >> IO_TLB_SHIFT) + 1; } static unsigned int wrap_area_index(struct io_tlb_pool *mem, unsigned int index) { if (index >= mem->area_nslabs) return 0; return index; } /* * Track the total used slots with a global atomic value in order to have * correct information to determine the high water mark. The mem_used() * function gives imprecise results because there's no locking across * multiple areas. */ #ifdef CONFIG_DEBUG_FS static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) { unsigned long old_hiwater, new_used; new_used = atomic_long_add_return(nslots, &mem->total_used); old_hiwater = atomic_long_read(&mem->used_hiwater); do { if (new_used <= old_hiwater) break; } while (!atomic_long_try_cmpxchg(&mem->used_hiwater, &old_hiwater, new_used)); } static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) { atomic_long_sub(nslots, &mem->total_used); } #else /* !CONFIG_DEBUG_FS */ static void inc_used_and_hiwater(struct io_tlb_mem *mem, unsigned int nslots) { } static void dec_used(struct io_tlb_mem *mem, unsigned int nslots) { } #endif /* CONFIG_DEBUG_FS */ #ifdef CONFIG_SWIOTLB_DYNAMIC #ifdef CONFIG_DEBUG_FS static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { atomic_long_add(nslots, &mem->transient_nslabs); } static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { atomic_long_sub(nslots, &mem->transient_nslabs); } #else /* !CONFIG_DEBUG_FS */ static void inc_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { } static void dec_transient_used(struct io_tlb_mem *mem, unsigned int nslots) { } #endif /* CONFIG_DEBUG_FS */ #endif /* CONFIG_SWIOTLB_DYNAMIC */ /** * swiotlb_search_pool_area() - search one memory area in one pool * @dev: Device which maps the buffer. * @pool: Memory pool to be searched. * @area_index: Index of the IO TLB memory area to be searched. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. * * Find a suitable sequence of IO TLB entries for the request and allocate * a buffer from the given IO TLB memory area. * This function takes care of locking. * * Return: Index of the first allocated slot, or -1 on error. */ static int swiotlb_search_pool_area(struct device *dev, struct io_tlb_pool *pool, int area_index, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask) { struct io_tlb_area *area = pool->areas + area_index; unsigned long boundary_mask = dma_get_seg_boundary(dev); dma_addr_t tbl_dma_addr = phys_to_dma_unencrypted(dev, pool->start) & boundary_mask; unsigned long max_slots = get_max_slots(boundary_mask); unsigned int iotlb_align_mask = dma_get_min_align_mask(dev); unsigned int nslots = nr_slots(alloc_size), stride; unsigned int offset = swiotlb_align_offset(dev, 0, orig_addr); unsigned int index, slots_checked, count = 0, i; unsigned long flags; unsigned int slot_base; unsigned int slot_index; BUG_ON(!nslots); BUG_ON(area_index >= pool->nareas); /* * Historically, swiotlb allocations >= PAGE_SIZE were guaranteed to be * page-aligned in the absence of any other alignment requirements. * 'alloc_align_mask' was later introduced to specify the alignment * explicitly, however this is passed as zero for streaming mappings * and so we preserve the old behaviour there in case any drivers are * relying on it. */ if (!alloc_align_mask && !iotlb_align_mask && alloc_size >= PAGE_SIZE) alloc_align_mask = PAGE_SIZE - 1; /* * Ensure that the allocation is at least slot-aligned and update * 'iotlb_align_mask' to ignore bits that will be preserved when * offsetting into the allocation. */ alloc_align_mask |= (IO_TLB_SIZE - 1); iotlb_align_mask &= ~alloc_align_mask; /* * For mappings with an alignment requirement don't bother looping to * unaligned slots once we found an aligned one. */ stride = get_max_slots(max(alloc_align_mask, iotlb_align_mask)); spin_lock_irqsave(&area->lock, flags); if (unlikely(nslots > pool->area_nslabs - area->used)) goto not_found; slot_base = area_index * pool->area_nslabs; index = area->index; for (slots_checked = 0; slots_checked < pool->area_nslabs; ) { phys_addr_t tlb_addr; slot_index = slot_base + index; tlb_addr = slot_addr(tbl_dma_addr, slot_index); if ((tlb_addr & alloc_align_mask) || (orig_addr && (tlb_addr & iotlb_align_mask) != (orig_addr & iotlb_align_mask))) { index = wrap_area_index(pool, index + 1); slots_checked++; continue; } if (!iommu_is_span_boundary(slot_index, nslots, nr_slots(tbl_dma_addr), max_slots)) { if (pool->slots[slot_index].list >= nslots) goto found; } index = wrap_area_index(pool, index + stride); slots_checked += stride; } not_found: spin_unlock_irqrestore(&area->lock, flags); return -1; found: /* * If we find a slot that indicates we have 'nslots' number of * contiguous buffers, we allocate the buffers from that slot onwards * and set the list of free entries to '0' indicating unavailable. */ for (i = slot_index; i < slot_index + nslots; i++) { pool->slots[i].list = 0; pool->slots[i].alloc_size = alloc_size - (offset + ((i - slot_index) << IO_TLB_SHIFT)); } for (i = slot_index - 1; io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && pool->slots[i].list; i--) pool->slots[i].list = ++count; /* * Update the indices to avoid searching in the next round. */ area->index = wrap_area_index(pool, index + nslots); area->used += nslots; spin_unlock_irqrestore(&area->lock, flags); inc_used_and_hiwater(dev->dma_io_tlb_mem, nslots); return slot_index; } #ifdef CONFIG_SWIOTLB_DYNAMIC /** * swiotlb_search_area() - search one memory area in all pools * @dev: Device which maps the buffer. * @start_cpu: Start CPU number. * @cpu_offset: Offset from @start_cpu. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. * @retpool: Used memory pool, updated on return. * * Search one memory area in all pools for a sequence of slots that match the * allocation constraints. * * Return: Index of the first allocated slot, or -1 on error. */ static int swiotlb_search_area(struct device *dev, int start_cpu, int cpu_offset, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; int area_index; int index = -1; rcu_read_lock(); list_for_each_entry_rcu(pool, &mem->pools, node) { if (cpu_offset >= pool->nareas) continue; area_index = (start_cpu + cpu_offset) & (pool->nareas - 1); index = swiotlb_search_pool_area(dev, pool, area_index, orig_addr, alloc_size, alloc_align_mask); if (index >= 0) { *retpool = pool; break; } } rcu_read_unlock(); return index; } /** * swiotlb_find_slots() - search for slots in the whole swiotlb * @dev: Device which maps the buffer. * @orig_addr: Original (non-bounced) IO buffer address. * @alloc_size: Total requested size of the bounce buffer, * including initial alignment padding. * @alloc_align_mask: Required alignment of the allocated buffer. * @retpool: Used memory pool, updated on return. * * Search through the whole software IO TLB to find a sequence of slots that * match the allocation constraints. * * Return: Index of the first allocated slot, or -1 on error. */ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; unsigned long nslabs; unsigned long flags; u64 phys_limit; int cpu, i; int index; if (alloc_size > IO_TLB_SEGSIZE * IO_TLB_SIZE) return -1; cpu = raw_smp_processor_id(); for (i = 0; i < default_nareas; ++i) { index = swiotlb_search_area(dev, cpu, i, orig_addr, alloc_size, alloc_align_mask, &pool); if (index >= 0) goto found; } if (!mem->can_grow) return -1; schedule_work(&mem->dyn_alloc); nslabs = nr_slots(alloc_size); phys_limit = min_not_zero(*dev->dma_mask, dev->bus_dma_limit); pool = swiotlb_alloc_pool(dev, nslabs, nslabs, 1, phys_limit, GFP_NOWAIT); if (!pool) return -1; index = swiotlb_search_pool_area(dev, pool, 0, orig_addr, alloc_size, alloc_align_mask); if (index < 0) { swiotlb_dyn_free(&pool->rcu); return -1; } pool->transient = true; spin_lock_irqsave(&dev->dma_io_tlb_lock, flags); list_add_rcu(&pool->node, &dev->dma_io_tlb_pools); spin_unlock_irqrestore(&dev->dma_io_tlb_lock, flags); inc_transient_used(mem, pool->nslabs); found: WRITE_ONCE(dev->dma_uses_io_tlb, true); /* * The general barrier orders reads and writes against a presumed store * of the SWIOTLB buffer address by a device driver (to a driver private * data structure). It serves two purposes. * * First, the store to dev->dma_uses_io_tlb must be ordered before the * presumed store. This guarantees that the returned buffer address * cannot be passed to another CPU before updating dev->dma_uses_io_tlb. * * Second, the load from mem->pools must be ordered before the same * presumed store. This guarantees that the returned buffer address * cannot be observed by another CPU before an update of the RCU list * that was made by swiotlb_dyn_alloc() on a third CPU (cf. multicopy * atomicity). * * See also the comment in swiotlb_find_pool(). */ smp_mb(); *retpool = pool; return index; } #else /* !CONFIG_SWIOTLB_DYNAMIC */ static int swiotlb_find_slots(struct device *dev, phys_addr_t orig_addr, size_t alloc_size, unsigned int alloc_align_mask, struct io_tlb_pool **retpool) { struct io_tlb_pool *pool; int start, i; int index; *retpool = pool = &dev->dma_io_tlb_mem->defpool; i = start = raw_smp_processor_id() & (pool->nareas - 1); do { index = swiotlb_search_pool_area(dev, pool, i, orig_addr, alloc_size, alloc_align_mask); if (index >= 0) return index; if (++i >= pool->nareas) i = 0; } while (i != start); return -1; } #endif /* CONFIG_SWIOTLB_DYNAMIC */ #ifdef CONFIG_DEBUG_FS /** * mem_used() - get number of used slots in an allocator * @mem: Software IO TLB allocator. * * The result is accurate in this version of the function, because an atomic * counter is available if CONFIG_DEBUG_FS is set. * * Return: Number of used slots. */ static unsigned long mem_used(struct io_tlb_mem *mem) { return atomic_long_read(&mem->total_used); } #else /* !CONFIG_DEBUG_FS */ /** * mem_pool_used() - get number of used slots in a memory pool * @pool: Software IO TLB memory pool. * * The result is not accurate, see mem_used(). * * Return: Approximate number of used slots. */ static unsigned long mem_pool_used(struct io_tlb_pool *pool) { int i; unsigned long used = 0; for (i = 0; i < pool->nareas; i++) used += pool->areas[i].used; return used; } /** * mem_used() - get number of used slots in an allocator * @mem: Software IO TLB allocator. * * The result is not accurate, because there is no locking of individual * areas. * * Return: Approximate number of used slots. */ static unsigned long mem_used(struct io_tlb_mem *mem) { #ifdef CONFIG_SWIOTLB_DYNAMIC struct io_tlb_pool *pool; unsigned long used = 0; rcu_read_lock(); list_for_each_entry_rcu(pool, &mem->pools, node) used += mem_pool_used(pool); rcu_read_unlock(); return used; #else return mem_pool_used(&mem->defpool); #endif } #endif /* CONFIG_DEBUG_FS */ /** * swiotlb_tbl_map_single() - bounce buffer map a single contiguous physical area * @dev: Device which maps the buffer. * @orig_addr: Original (non-bounced) physical IO buffer address * @mapping_size: Requested size of the actual bounce buffer, excluding * any pre- or post-padding for alignment * @alloc_align_mask: Required start and end alignment of the allocated buffer * @dir: DMA direction * @attrs: Optional DMA attributes for the map operation * * Find and allocate a suitable sequence of IO TLB slots for the request. * The allocated space starts at an alignment specified by alloc_align_mask, * and the size of the allocated space is rounded up so that the total amount * of allocated space is a multiple of (alloc_align_mask + 1). If * alloc_align_mask is zero, the allocated space may be at any alignment and * the size is not rounded up. * * The returned address is within the allocated space and matches the bits * of orig_addr that are specified in the DMA min_align_mask for the device. As * such, this returned address may be offset from the beginning of the allocated * space. The bounce buffer space starting at the returned address for * mapping_size bytes is initialized to the contents of the original IO buffer * area. Any pre-padding (due to an offset) and any post-padding (due to * rounding-up the size) is not initialized. */ phys_addr_t swiotlb_tbl_map_single(struct device *dev, phys_addr_t orig_addr, size_t mapping_size, unsigned int alloc_align_mask, enum dma_data_direction dir, unsigned long attrs) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; unsigned int offset; struct io_tlb_pool *pool; unsigned int i; size_t size; int index; phys_addr_t tlb_addr; unsigned short pad_slots; if (!mem || !mem->nslabs) { dev_warn_ratelimited(dev, "Can not allocate SWIOTLB buffer earlier and can't now provide you with the DMA bounce buffer"); return (phys_addr_t)DMA_MAPPING_ERROR; } if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) pr_warn_once("Memory encryption is active and system is using DMA bounce buffers\n"); /* * The default swiotlb memory pool is allocated with PAGE_SIZE * alignment. If a mapping is requested with larger alignment, * the mapping may be unable to use the initial slot(s) in all * sets of IO_TLB_SEGSIZE slots. In such case, a mapping request * of or near the maximum mapping size would always fail. */ dev_WARN_ONCE(dev, alloc_align_mask > ~PAGE_MASK, "Alloc alignment may prevent fulfilling requests with max mapping_size\n"); offset = swiotlb_align_offset(dev, alloc_align_mask, orig_addr); size = ALIGN(mapping_size + offset, alloc_align_mask + 1); index = swiotlb_find_slots(dev, orig_addr, size, alloc_align_mask, &pool); if (index == -1) { if (!(attrs & DMA_ATTR_NO_WARN)) dev_warn_ratelimited(dev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n", size, mem->nslabs, mem_used(mem)); return (phys_addr_t)DMA_MAPPING_ERROR; } /* * If dma_skip_sync was set, reset it on first SWIOTLB buffer * mapping to always sync SWIOTLB buffers. */ dma_reset_need_sync(dev); /* * Save away the mapping from the original address to the DMA address. * This is needed when we sync the memory. Then we sync the buffer if * needed. */ pad_slots = offset >> IO_TLB_SHIFT; offset &= (IO_TLB_SIZE - 1); index += pad_slots; pool->slots[index].pad_slots = pad_slots; for (i = 0; i < (nr_slots(size) - pad_slots); i++) pool->slots[index + i].orig_addr = slot_addr(orig_addr, i); tlb_addr = slot_addr(pool->start, index) + offset; /* * When the device is writing memory, i.e. dir == DMA_FROM_DEVICE, copy * the original buffer to the TLB buffer before initiating DMA in order * to preserve the original's data if the device does a partial write, * i.e. if the device doesn't overwrite the entire buffer. Preserving * the original data, even if it's garbage, is necessary to match * hardware behavior. Use of swiotlb is supposed to be transparent, * i.e. swiotlb must not corrupt memory by clobbering unwritten bytes. */ swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_TO_DEVICE, pool); return tlb_addr; } static void swiotlb_release_slots(struct device *dev, phys_addr_t tlb_addr, struct io_tlb_pool *mem) { unsigned long flags; unsigned int offset = swiotlb_align_offset(dev, 0, tlb_addr); int index, nslots, aindex; struct io_tlb_area *area; int count, i; index = (tlb_addr - offset - mem->start) >> IO_TLB_SHIFT; index -= mem->slots[index].pad_slots; nslots = nr_slots(mem->slots[index].alloc_size + offset); aindex = index / mem->area_nslabs; area = &mem->areas[aindex]; /* * Return the buffer to the free list by setting the corresponding * entries to indicate the number of contiguous entries available. * While returning the entries to the free list, we merge the entries * with slots below and above the pool being returned. */ BUG_ON(aindex >= mem->nareas); spin_lock_irqsave(&area->lock, flags); if (index + nslots < ALIGN(index + 1, IO_TLB_SEGSIZE)) count = mem->slots[index + nslots].list; else count = 0; /* * Step 1: return the slots to the free list, merging the slots with * superceeding slots */ for (i = index + nslots - 1; i >= index; i--) { mem->slots[i].list = ++count; mem->slots[i].orig_addr = INVALID_PHYS_ADDR; mem->slots[i].alloc_size = 0; mem->slots[i].pad_slots = 0; } /* * Step 2: merge the returned slots with the preceding slots, if * available (non zero) */ for (i = index - 1; io_tlb_offset(i) != IO_TLB_SEGSIZE - 1 && mem->slots[i].list; i--) mem->slots[i].list = ++count; area->used -= nslots; spin_unlock_irqrestore(&area->lock, flags); dec_used(dev->dma_io_tlb_mem, nslots); } #ifdef CONFIG_SWIOTLB_DYNAMIC /** * swiotlb_del_transient() - delete a transient memory pool * @dev: Device which mapped the buffer. * @tlb_addr: Physical address within a bounce buffer. * @pool: Pointer to the transient memory pool to be checked and deleted. * * Check whether the address belongs to a transient SWIOTLB memory pool. * If yes, then delete the pool. * * Return: %true if @tlb_addr belonged to a transient pool that was released. */ static bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr, struct io_tlb_pool *pool) { if (!pool->transient) return false; dec_used(dev->dma_io_tlb_mem, pool->nslabs); swiotlb_del_pool(dev, pool); dec_transient_used(dev->dma_io_tlb_mem, pool->nslabs); return true; } #else /* !CONFIG_SWIOTLB_DYNAMIC */ static inline bool swiotlb_del_transient(struct device *dev, phys_addr_t tlb_addr, struct io_tlb_pool *pool) { return false; } #endif /* CONFIG_SWIOTLB_DYNAMIC */ /* * tlb_addr is the physical address of the bounce buffer to unmap. */ void __swiotlb_tbl_unmap_single(struct device *dev, phys_addr_t tlb_addr, size_t mapping_size, enum dma_data_direction dir, unsigned long attrs, struct io_tlb_pool *pool) { /* * First, sync the memory before unmapping the entry */ if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) && (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)) swiotlb_bounce(dev, tlb_addr, mapping_size, DMA_FROM_DEVICE, pool); if (swiotlb_del_transient(dev, tlb_addr, pool)) return; swiotlb_release_slots(dev, tlb_addr, pool); } void __swiotlb_sync_single_for_device(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, struct io_tlb_pool *pool) { if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL) swiotlb_bounce(dev, tlb_addr, size, DMA_TO_DEVICE, pool); else BUG_ON(dir != DMA_FROM_DEVICE); } void __swiotlb_sync_single_for_cpu(struct device *dev, phys_addr_t tlb_addr, size_t size, enum dma_data_direction dir, struct io_tlb_pool *pool) { if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL) swiotlb_bounce(dev, tlb_addr, size, DMA_FROM_DEVICE, pool); else BUG_ON(dir != DMA_TO_DEVICE); } /* * Create a swiotlb mapping for the buffer at @paddr, and in case of DMAing * to the device copy the data into it as well. */ dma_addr_t swiotlb_map(struct device *dev, phys_addr_t paddr, size_t size, enum dma_data_direction dir, unsigned long attrs) { phys_addr_t swiotlb_addr; dma_addr_t dma_addr; trace_swiotlb_bounced(dev, phys_to_dma(dev, paddr), size); swiotlb_addr = swiotlb_tbl_map_single(dev, paddr, size, 0, dir, attrs); if (swiotlb_addr == (phys_addr_t)DMA_MAPPING_ERROR) return DMA_MAPPING_ERROR; /* Ensure that the address returned is DMA'ble */ dma_addr = phys_to_dma_unencrypted(dev, swiotlb_addr); if (unlikely(!dma_capable(dev, dma_addr, size, true))) { __swiotlb_tbl_unmap_single(dev, swiotlb_addr, size, dir, attrs | DMA_ATTR_SKIP_CPU_SYNC, swiotlb_find_pool(dev, swiotlb_addr)); dev_WARN_ONCE(dev, 1, "swiotlb addr %pad+%zu overflow (mask %llx, bus limit %llx).\n", &dma_addr, size, *dev->dma_mask, dev->bus_dma_limit); return DMA_MAPPING_ERROR; } if (!dev_is_dma_coherent(dev) && !(attrs & DMA_ATTR_SKIP_CPU_SYNC)) { arch_sync_dma_for_device(swiotlb_addr, size, dir); arch_sync_dma_flush(); } return dma_addr; } size_t swiotlb_max_mapping_size(struct device *dev) { int min_align_mask = dma_get_min_align_mask(dev); int min_align = 0; /* * swiotlb_find_slots() skips slots according to * min align mask. This affects max mapping size. * Take it into acount here. */ if (min_align_mask) min_align = roundup(min_align_mask, IO_TLB_SIZE); return ((size_t)IO_TLB_SIZE) * IO_TLB_SEGSIZE - min_align; } /** * is_swiotlb_allocated() - check if the default software IO TLB is initialized */ bool is_swiotlb_allocated(void) { return io_tlb_default_mem.nslabs; } bool is_swiotlb_active(struct device *dev) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; return mem && mem->nslabs; } /** * default_swiotlb_base() - get the base address of the default SWIOTLB * * Get the lowest physical address used by the default software IO TLB pool. */ phys_addr_t default_swiotlb_base(void) { #ifdef CONFIG_SWIOTLB_DYNAMIC io_tlb_default_mem.can_grow = false; #endif return io_tlb_default_mem.defpool.start; } /** * default_swiotlb_limit() - get the address limit of the default SWIOTLB * * Get the highest physical address used by the default software IO TLB pool. */ phys_addr_t default_swiotlb_limit(void) { #ifdef CONFIG_SWIOTLB_DYNAMIC return io_tlb_default_mem.phys_limit; #else return io_tlb_default_mem.defpool.end - 1; #endif } #ifdef CONFIG_DEBUG_FS #ifdef CONFIG_SWIOTLB_DYNAMIC static unsigned long mem_transient_used(struct io_tlb_mem *mem) { return atomic_long_read(&mem->transient_nslabs); } static int io_tlb_transient_used_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; *val = mem_transient_used(mem); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_transient_used, io_tlb_transient_used_get, NULL, "%llu\n"); #endif /* CONFIG_SWIOTLB_DYNAMIC */ static int io_tlb_used_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; *val = mem_used(mem); return 0; } static int io_tlb_hiwater_get(void *data, u64 *val) { struct io_tlb_mem *mem = data; *val = atomic_long_read(&mem->used_hiwater); return 0; } static int io_tlb_hiwater_set(void *data, u64 val) { struct io_tlb_mem *mem = data; /* Only allow setting to zero */ if (val != 0) return -EINVAL; atomic_long_set(&mem->used_hiwater, val); return 0; } DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_used, io_tlb_used_get, NULL, "%llu\n"); DEFINE_DEBUGFS_ATTRIBUTE(fops_io_tlb_hiwater, io_tlb_hiwater_get, io_tlb_hiwater_set, "%llu\n"); static void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { mem->debugfs = debugfs_create_dir(dirname, io_tlb_default_mem.debugfs); if (!mem->nslabs) return; debugfs_create_ulong("io_tlb_nslabs", 0400, mem->debugfs, &mem->nslabs); debugfs_create_file("io_tlb_used", 0400, mem->debugfs, mem, &fops_io_tlb_used); debugfs_create_file("io_tlb_used_hiwater", 0600, mem->debugfs, mem, &fops_io_tlb_hiwater); #ifdef CONFIG_SWIOTLB_DYNAMIC debugfs_create_file("io_tlb_transient_nslabs", 0400, mem->debugfs, mem, &fops_io_tlb_transient_used); #endif } static int __init swiotlb_create_default_debugfs(void) { swiotlb_create_debugfs_files(&io_tlb_default_mem, "swiotlb"); return 0; } late_initcall(swiotlb_create_default_debugfs); #else /* !CONFIG_DEBUG_FS */ static inline void swiotlb_create_debugfs_files(struct io_tlb_mem *mem, const char *dirname) { } #endif /* CONFIG_DEBUG_FS */ #ifdef CONFIG_DMA_RESTRICTED_POOL struct page *swiotlb_alloc(struct device *dev, size_t size) { struct io_tlb_mem *mem = dev->dma_io_tlb_mem; struct io_tlb_pool *pool; phys_addr_t tlb_addr; unsigned int align; int index; if (!mem) return NULL; align = (1 << (get_order(size) + PAGE_SHIFT)) - 1; index = swiotlb_find_slots(dev, 0, size, align, &pool); if (index == -1) return NULL; tlb_addr = slot_addr(pool->start, index); if (unlikely(!PAGE_ALIGNED(tlb_addr))) { dev_WARN_ONCE(dev, 1, "Cannot allocate pages from non page-aligned swiotlb addr 0x%pa.\n", &tlb_addr); swiotlb_release_slots(dev, tlb_addr, pool); return NULL; } return pfn_to_page(PFN_DOWN(tlb_addr)); } bool swiotlb_free(struct device *dev, struct page *page, size_t size) { phys_addr_t tlb_addr = page_to_phys(page); struct io_tlb_pool *pool; pool = swiotlb_find_pool(dev, tlb_addr); if (!pool) return false; swiotlb_release_slots(dev, tlb_addr, pool); return true; } static int rmem_swiotlb_device_init(struct reserved_mem *rmem, struct device *dev) { struct io_tlb_mem *mem = rmem->priv; unsigned long nslabs = rmem->size >> IO_TLB_SHIFT; /* Set Per-device io tlb area to one */ unsigned int nareas = 1; if (PageHighMem(pfn_to_page(PHYS_PFN(rmem->base)))) { dev_err(dev, "Restricted DMA pool must be accessible within the linear mapping."); return -EINVAL; } /* * Since multiple devices can share the same pool, the private data, * io_tlb_mem struct, will be initialized by the first device attached * to it. */ if (!mem) { struct io_tlb_pool *pool; mem = kzalloc_obj(*mem); if (!mem) return -ENOMEM; pool = &mem->defpool; pool->slots = kzalloc_objs(*pool->slots, nslabs); if (!pool->slots) { kfree(mem); return -ENOMEM; } pool->areas = kzalloc_objs(*pool->areas, nareas); if (!pool->areas) { kfree(pool->slots); kfree(mem); return -ENOMEM; } set_memory_decrypted((unsigned long)phys_to_virt(rmem->base), rmem->size >> PAGE_SHIFT); swiotlb_init_io_tlb_pool(pool, rmem->base, nslabs, false, nareas); mem->force_bounce = true; mem->for_alloc = true; #ifdef CONFIG_SWIOTLB_DYNAMIC spin_lock_init(&mem->lock); INIT_LIST_HEAD_RCU(&mem->pools); #endif add_mem_pool(mem, pool); rmem->priv = mem; swiotlb_create_debugfs_files(mem, rmem->name); } dev->dma_io_tlb_mem = mem; return 0; } static void rmem_swiotlb_device_release(struct reserved_mem *rmem, struct device *dev) { dev->dma_io_tlb_mem = &io_tlb_default_mem; } static int __init rmem_swiotlb_setup(unsigned long node, struct reserved_mem *rmem) { if (of_get_flat_dt_prop(node, "reusable", NULL) || of_get_flat_dt_prop(node, "linux,cma-default", NULL) || of_get_flat_dt_prop(node, "linux,dma-default", NULL) || of_get_flat_dt_prop(node, "no-map", NULL)) return -EINVAL; pr_info("Reserved memory: created restricted DMA pool at %pa, size %ld MiB\n", &rmem->base, (unsigned long)rmem->size / SZ_1M); return 0; } static const struct reserved_mem_ops rmem_swiotlb_ops = { .node_init = rmem_swiotlb_setup, .device_init = rmem_swiotlb_device_init, .device_release = rmem_swiotlb_device_release, }; RESERVEDMEM_OF_DECLARE(dma, "restricted-dma-pool", &rmem_swiotlb_ops); #endif /* CONFIG_DMA_RESTRICTED_POOL */ |
| 162 159 41 1 1 160 143 20 162 2 158 162 163 1 1 160 165 162 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 | // SPDX-License-Identifier: GPL-2.0 /* * security/tomoyo/mount.c * * Copyright (C) 2005-2011 NTT DATA CORPORATION */ #include <linux/slab.h> #include <uapi/linux/mount.h> #include "common.h" /* String table for special mount operations. */ static const char * const tomoyo_mounts[TOMOYO_MAX_SPECIAL_MOUNT] = { [TOMOYO_MOUNT_BIND] = "--bind", [TOMOYO_MOUNT_MOVE] = "--move", [TOMOYO_MOUNT_REMOUNT] = "--remount", [TOMOYO_MOUNT_MAKE_UNBINDABLE] = "--make-unbindable", [TOMOYO_MOUNT_MAKE_PRIVATE] = "--make-private", [TOMOYO_MOUNT_MAKE_SLAVE] = "--make-slave", [TOMOYO_MOUNT_MAKE_SHARED] = "--make-shared", }; /** * tomoyo_audit_mount_log - Audit mount log. * * @r: Pointer to "struct tomoyo_request_info". * * Returns 0 on success, negative value otherwise. */ static int tomoyo_audit_mount_log(struct tomoyo_request_info *r) __must_hold_shared(&tomoyo_ss) { return tomoyo_supervisor(r, "file mount %s %s %s 0x%lX\n", r->param.mount.dev->name, r->param.mount.dir->name, r->param.mount.type->name, r->param.mount.flags); } /** * tomoyo_check_mount_acl - Check permission for path path path number operation. * * @r: Pointer to "struct tomoyo_request_info". * @ptr: Pointer to "struct tomoyo_acl_info". * * Returns true if granted, false otherwise. */ static bool tomoyo_check_mount_acl(struct tomoyo_request_info *r, const struct tomoyo_acl_info *ptr) { const struct tomoyo_mount_acl *acl = container_of(ptr, typeof(*acl), head); return tomoyo_compare_number_union(r->param.mount.flags, &acl->flags) && tomoyo_compare_name_union(r->param.mount.type, &acl->fs_type) && tomoyo_compare_name_union(r->param.mount.dir, &acl->dir_name) && (!r->param.mount.need_dev || tomoyo_compare_name_union(r->param.mount.dev, &acl->dev_name)); } /** * tomoyo_mount_acl - Check permission for mount() operation. * * @r: Pointer to "struct tomoyo_request_info". * @dev_name: Name of device file. Maybe NULL. * @dir: Pointer to "struct path". * @type: Name of filesystem type. * @flags: Mount options. * * Returns 0 on success, negative value otherwise. * * Caller holds tomoyo_read_lock(). */ static int tomoyo_mount_acl(struct tomoyo_request_info *r, const char *dev_name, const struct path *dir, const char *type, unsigned long flags) __must_hold_shared(&tomoyo_ss) { struct tomoyo_obj_info obj = { }; struct path path; struct file_system_type *fstype = NULL; const char *requested_type = NULL; const char *requested_dir_name = NULL; const char *requested_dev_name = NULL; struct tomoyo_path_info rtype; struct tomoyo_path_info rdev; struct tomoyo_path_info rdir; int need_dev = 0; int error = -ENOMEM; r->obj = &obj; /* Get fstype. */ requested_type = tomoyo_encode(type); if (!requested_type) goto out; rtype.name = requested_type; tomoyo_fill_path_info(&rtype); /* Get mount point. */ obj.path2 = *dir; requested_dir_name = tomoyo_realpath_from_path(dir); if (!requested_dir_name) { error = -ENOMEM; goto out; } rdir.name = requested_dir_name; tomoyo_fill_path_info(&rdir); /* Compare fs name. */ if (type == tomoyo_mounts[TOMOYO_MOUNT_REMOUNT]) { /* dev_name is ignored. */ } else if (type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_UNBINDABLE] || type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_PRIVATE] || type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_SLAVE] || type == tomoyo_mounts[TOMOYO_MOUNT_MAKE_SHARED]) { /* dev_name is ignored. */ } else if (type == tomoyo_mounts[TOMOYO_MOUNT_BIND] || type == tomoyo_mounts[TOMOYO_MOUNT_MOVE]) { need_dev = -1; /* dev_name is a directory */ } else { fstype = get_fs_type(type); if (!fstype) { error = -ENODEV; goto out; } if (fstype->fs_flags & FS_REQUIRES_DEV) /* dev_name is a block device file. */ need_dev = 1; } if (need_dev) { /* Get mount point or device file. */ if (!dev_name || kern_path(dev_name, LOOKUP_FOLLOW, &path)) { error = -ENOENT; goto out; } obj.path1 = path; requested_dev_name = tomoyo_realpath_from_path(&path); if (!requested_dev_name) { error = -ENOENT; goto out; } } else { /* Map dev_name to "<NULL>" if no dev_name given. */ if (!dev_name) dev_name = "<NULL>"; requested_dev_name = tomoyo_encode(dev_name); if (!requested_dev_name) { error = -ENOMEM; goto out; } } rdev.name = requested_dev_name; tomoyo_fill_path_info(&rdev); r->param_type = TOMOYO_TYPE_MOUNT_ACL; r->param.mount.need_dev = need_dev; r->param.mount.dev = &rdev; r->param.mount.dir = &rdir; r->param.mount.type = &rtype; r->param.mount.flags = flags; do { tomoyo_check_acl(r, tomoyo_check_mount_acl); error = tomoyo_audit_mount_log(r); } while (error == TOMOYO_RETRY_REQUEST); out: kfree(requested_dev_name); kfree(requested_dir_name); if (fstype) put_filesystem(fstype); kfree(requested_type); /* Drop refcount obtained by kern_path(). */ if (obj.path1.dentry) path_put(&obj.path1); return error; } /** * tomoyo_mount_permission - Check permission for mount() operation. * * @dev_name: Name of device file. Maybe NULL. * @path: Pointer to "struct path". * @type: Name of filesystem type. Maybe NULL. * @flags: Mount options. * @data_page: Optional data. Maybe NULL. * * Returns 0 on success, negative value otherwise. */ int tomoyo_mount_permission(const char *dev_name, const struct path *path, const char *type, unsigned long flags, void *data_page) { struct tomoyo_request_info r; int error; int idx; if (tomoyo_init_request_info(&r, NULL, TOMOYO_MAC_FILE_MOUNT) == TOMOYO_CONFIG_DISABLED) return 0; if ((flags & MS_MGC_MSK) == MS_MGC_VAL) flags &= ~MS_MGC_MSK; if (flags & MS_REMOUNT) { type = tomoyo_mounts[TOMOYO_MOUNT_REMOUNT]; flags &= ~MS_REMOUNT; } else if (flags & MS_BIND) { type = tomoyo_mounts[TOMOYO_MOUNT_BIND]; flags &= ~MS_BIND; } else if (flags & MS_SHARED) { if (flags & (MS_PRIVATE | MS_SLAVE | MS_UNBINDABLE)) return -EINVAL; type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_SHARED]; flags &= ~MS_SHARED; } else if (flags & MS_PRIVATE) { if (flags & (MS_SHARED | MS_SLAVE | MS_UNBINDABLE)) return -EINVAL; type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_PRIVATE]; flags &= ~MS_PRIVATE; } else if (flags & MS_SLAVE) { if (flags & (MS_SHARED | MS_PRIVATE | MS_UNBINDABLE)) return -EINVAL; type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_SLAVE]; flags &= ~MS_SLAVE; } else if (flags & MS_UNBINDABLE) { if (flags & (MS_SHARED | MS_PRIVATE | MS_SLAVE)) return -EINVAL; type = tomoyo_mounts[TOMOYO_MOUNT_MAKE_UNBINDABLE]; flags &= ~MS_UNBINDABLE; } else if (flags & MS_MOVE) { type = tomoyo_mounts[TOMOYO_MOUNT_MOVE]; flags &= ~MS_MOVE; } if (!type) type = "<NULL>"; idx = tomoyo_read_lock(); error = tomoyo_mount_acl(&r, dev_name, path, type, flags); tomoyo_read_unlock(idx); return error; } |
| 168 165 1 167 166 167 167 165 164 167 1 1 2 2 5 4 1 165 32 164 142 11 132 139 142 85 85 131 130 127 10 1 11 130 145 5 142 74 131 164 121 83 131 165 165 132 77 131 80 163 167 164 167 164 165 165 19 161 32 38 23 165 165 165 165 165 164 13 9 161 161 165 161 163 165 47 164 22 161 79 19 10 3 6 6 6 1 1 160 160 161 163 161 2 1 1 163 164 79 85 163 164 164 165 165 165 159 100 61 161 161 159 160 165 164 164 159 161 161 165 17 16 2 1 14 1 1 12 1 11 1 1 1 4 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 | // SPDX-License-Identifier: GPL-2.0 /* * message.c - synchronous message handling * * Released under the GPLv2 only. */ #include <linux/acpi.h> #include <linux/pci.h> /* for scatterlist macros */ #include <linux/usb.h> #include <linux/module.h> #include <linux/of.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/timer.h> #include <linux/ctype.h> #include <linux/nls.h> #include <linux/device.h> #include <linux/scatterlist.h> #include <linux/usb/cdc.h> #include <linux/usb/quirks.h> #include <linux/usb/hcd.h> /* for usbcore internals */ #include <linux/usb/of.h> #include <asm/byteorder.h> #include "usb.h" static void cancel_async_set_config(struct usb_device *udev); struct api_context { struct completion done; int status; }; static void usb_api_blocking_completion(struct urb *urb) { struct api_context *ctx = urb->context; ctx->status = urb->status; complete(&ctx->done); } /* * Starts urb and waits for completion or timeout. * Whether or not the wait is killable depends on the flag passed in. * For example, compare usb_bulk_msg() and usb_bulk_msg_killable(). * * For non-killable waits, we enforce a maximum limit on the timeout value. */ static int usb_start_wait_urb(struct urb *urb, int timeout, int *actual_length, bool killable) { struct api_context ctx; unsigned long expire; int retval; long rc; init_completion(&ctx.done); urb->context = &ctx; urb->actual_length = 0; retval = usb_submit_urb(urb, GFP_NOIO); if (unlikely(retval)) goto out; if (!killable && (timeout <= 0 || timeout > USB_MAX_SYNCHRONOUS_TIMEOUT)) timeout = USB_MAX_SYNCHRONOUS_TIMEOUT; expire = (timeout > 0) ? msecs_to_jiffies(timeout) : MAX_SCHEDULE_TIMEOUT; if (killable) rc = wait_for_completion_killable_timeout(&ctx.done, expire); else rc = wait_for_completion_timeout(&ctx.done, expire); if (rc <= 0) { usb_kill_urb(urb); if (ctx.status != -ENOENT) retval = ctx.status; else if (rc == 0) retval = -ETIMEDOUT; else retval = rc; dev_dbg(&urb->dev->dev, "%s timed out or killed on ep%d%s len=%u/%u\n", current->comm, usb_endpoint_num(&urb->ep->desc), usb_urb_dir_in(urb) ? "in" : "out", urb->actual_length, urb->transfer_buffer_length); } else retval = ctx.status; out: if (actual_length) *actual_length = urb->actual_length; usb_free_urb(urb); return retval; } /*-------------------------------------------------------------------*/ /* returns status (negative) or length (positive) */ static int usb_internal_control_msg(struct usb_device *usb_dev, unsigned int pipe, struct usb_ctrlrequest *cmd, void *data, int len, int timeout) { struct urb *urb; int retv; int length; urb = usb_alloc_urb(0, GFP_NOIO); if (!urb) return -ENOMEM; usb_fill_control_urb(urb, usb_dev, pipe, (unsigned char *)cmd, data, len, usb_api_blocking_completion, NULL); retv = usb_start_wait_urb(urb, timeout, &length, false); if (retv < 0) return retv; else return length; } /** * usb_control_msg - Builds a control urb, sends it off and waits for completion * @dev: pointer to the usb device to send the message to * @pipe: endpoint "pipe" to send the message to * @request: USB message request value * @requesttype: USB message request type value * @value: USB message value * @index: USB message index value * @data: pointer to the data to send * @size: length in bytes of the data to send * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * * This function sends a simple control message to a specified endpoint and * waits for the message to complete, or timeout. * * Don't use this function from within an interrupt context. If you need * an asynchronous message, or need to send a message from within interrupt * context, use usb_submit_urb(). If a thread in your driver uses this call, * make sure your disconnect() method can wait for it to complete. Since you * don't have a handle on the URB used, you can't cancel the request. * * Return: If successful, the number of bytes transferred. Otherwise, a negative * error number. */ int usb_control_msg(struct usb_device *dev, unsigned int pipe, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *data, __u16 size, int timeout) { struct usb_ctrlrequest *dr; int ret; dr = kmalloc_obj(struct usb_ctrlrequest, GFP_NOIO); if (!dr) return -ENOMEM; dr->bRequestType = requesttype; dr->bRequest = request; dr->wValue = cpu_to_le16(value); dr->wIndex = cpu_to_le16(index); dr->wLength = cpu_to_le16(size); ret = usb_internal_control_msg(dev, pipe, dr, data, size, timeout); /* Linger a bit, prior to the next control message. */ if (dev->quirks & USB_QUIRK_DELAY_CTRL_MSG) msleep(200); kfree(dr); return ret; } EXPORT_SYMBOL_GPL(usb_control_msg); /** * usb_control_msg_send - Builds a control "send" message, sends it off and waits for completion * @dev: pointer to the usb device to send the message to * @endpoint: endpoint to send the message to * @request: USB message request value * @requesttype: USB message request type value * @value: USB message value * @index: USB message index value * @driver_data: pointer to the data to send * @size: length in bytes of the data to send * @timeout: time in msecs to wait for the message to complete before timing out * @memflags: the flags for memory allocation for buffers * * Context: !in_interrupt () * * This function sends a control message to a specified endpoint that is not * expected to fill in a response (i.e. a "send message") and waits for the * message to complete, or timeout. * * Do not use this function from within an interrupt context. If you need * an asynchronous message, or need to send a message from within interrupt * context, use usb_submit_urb(). If a thread in your driver uses this call, * make sure your disconnect() method can wait for it to complete. Since you * don't have a handle on the URB used, you can't cancel the request. * * The data pointer can be made to a reference on the stack, or anywhere else, * as it will not be modified at all. This does not have the restriction that * usb_control_msg() has where the data pointer must be to dynamically allocated * memory (i.e. memory that can be successfully DMAed to a device). * * Return: If successful, 0 is returned, Otherwise, a negative error number. */ int usb_control_msg_send(struct usb_device *dev, __u8 endpoint, __u8 request, __u8 requesttype, __u16 value, __u16 index, const void *driver_data, __u16 size, int timeout, gfp_t memflags) { unsigned int pipe = usb_sndctrlpipe(dev, endpoint); int ret; u8 *data = NULL; if (size) { data = kmemdup(driver_data, size, memflags); if (!data) return -ENOMEM; } ret = usb_control_msg(dev, pipe, request, requesttype, value, index, data, size, timeout); kfree(data); if (ret < 0) return ret; return 0; } EXPORT_SYMBOL_GPL(usb_control_msg_send); /** * usb_control_msg_recv - Builds a control "receive" message, sends it off and waits for completion * @dev: pointer to the usb device to send the message to * @endpoint: endpoint to send the message to * @request: USB message request value * @requesttype: USB message request type value * @value: USB message value * @index: USB message index value * @driver_data: pointer to the data to be filled in by the message * @size: length in bytes of the data to be received * @timeout: time in msecs to wait for the message to complete before timing out * @memflags: the flags for memory allocation for buffers * * Context: !in_interrupt () * * This function sends a control message to a specified endpoint that is * expected to fill in a response (i.e. a "receive message") and waits for the * message to complete, or timeout. * * Do not use this function from within an interrupt context. If you need * an asynchronous message, or need to send a message from within interrupt * context, use usb_submit_urb(). If a thread in your driver uses this call, * make sure your disconnect() method can wait for it to complete. Since you * don't have a handle on the URB used, you can't cancel the request. * * The data pointer can be made to a reference on the stack, or anywhere else * that can be successfully written to. This function does not have the * restriction that usb_control_msg() has where the data pointer must be to * dynamically allocated memory (i.e. memory that can be successfully DMAed to a * device). * * The "whole" message must be properly received from the device in order for * this function to be successful. If a device returns less than the expected * amount of data, then the function will fail. Do not use this for messages * where a variable amount of data might be returned. * * Return: If successful, 0 is returned, Otherwise, a negative error number. */ int usb_control_msg_recv(struct usb_device *dev, __u8 endpoint, __u8 request, __u8 requesttype, __u16 value, __u16 index, void *driver_data, __u16 size, int timeout, gfp_t memflags) { unsigned int pipe = usb_rcvctrlpipe(dev, endpoint); int ret; u8 *data; if (!size || !driver_data) return -EINVAL; data = kmalloc(size, memflags); if (!data) return -ENOMEM; ret = usb_control_msg(dev, pipe, request, requesttype, value, index, data, size, timeout); if (ret < 0) goto exit; if (ret == size) { memcpy(driver_data, data, size); ret = 0; } else { ret = -EREMOTEIO; } exit: kfree(data); return ret; } EXPORT_SYMBOL_GPL(usb_control_msg_recv); /** * usb_interrupt_msg - Builds an interrupt urb, sends it off and waits for completion * @usb_dev: pointer to the usb device to send the message to * @pipe: endpoint "pipe" to send the message to * @data: pointer to the data to send * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * * This function sends a simple interrupt message to a specified endpoint and * waits for the message to complete, or timeout. * * Don't use this function from within an interrupt context. If you need * an asynchronous message, or need to send a message from within interrupt * context, use usb_submit_urb() If a thread in your driver uses this call, * make sure your disconnect() method can wait for it to complete. Since you * don't have a handle on the URB used, you can't cancel the request. * * Return: * If successful, 0. Otherwise a negative error number. The number of actual * bytes transferred will be stored in the @actual_length parameter. */ int usb_interrupt_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout) { return usb_bulk_msg(usb_dev, pipe, data, len, actual_length, timeout); } EXPORT_SYMBOL_GPL(usb_interrupt_msg); /** * usb_bulk_msg - Builds a bulk urb, sends it off and waits for completion * @usb_dev: pointer to the usb device to send the message to * @pipe: endpoint "pipe" to send the message to * @data: pointer to the data to send * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes * @timeout: time in msecs to wait for the message to complete before timing out * * Context: task context, might sleep. * * This function sends a simple bulk message to a specified endpoint * and waits for the message to complete, or timeout. * * Don't use this function from within an interrupt context. If you need * an asynchronous message, or need to send a message from within interrupt * context, use usb_submit_urb() If a thread in your driver uses this call, * make sure your disconnect() method can wait for it to complete. Since you * don't have a handle on the URB used, you can't cancel the request. * * Because there is no usb_interrupt_msg() and no USBDEVFS_INTERRUPT ioctl, * users are forced to abuse this routine by using it to submit URBs for * interrupt endpoints. We will take the liberty of creating an interrupt URB * (with the default interval) if the target is an interrupt endpoint. * * Return: * If successful, 0. Otherwise a negative error number. The number of actual * bytes transferred will be stored in the @actual_length parameter. * */ int usb_bulk_msg(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout) { struct urb *urb; struct usb_host_endpoint *ep; ep = usb_pipe_endpoint(usb_dev, pipe); if (!ep || len < 0) return -EINVAL; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) return -ENOMEM; if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT) { pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30); usb_fill_int_urb(urb, usb_dev, pipe, data, len, usb_api_blocking_completion, NULL, ep->desc.bInterval); } else usb_fill_bulk_urb(urb, usb_dev, pipe, data, len, usb_api_blocking_completion, NULL); return usb_start_wait_urb(urb, timeout, actual_length, false); } EXPORT_SYMBOL_GPL(usb_bulk_msg); /** * usb_bulk_msg_killable - Builds a bulk urb, sends it off and waits for completion in a killable state * @usb_dev: pointer to the usb device to send the message to * @pipe: endpoint "pipe" to send the message to * @data: pointer to the data to send * @len: length in bytes of the data to send * @actual_length: pointer to a location to put the actual length transferred * in bytes * @timeout: time in msecs to wait for the message to complete before * timing out (if <= 0, the wait is as long as possible) * * Context: task context, might sleep. * * This function is just like usb_blk_msg(), except that it waits in a * killable state and there is no limit on the timeout length. * * Return: * If successful, 0. Otherwise a negative error number. The number of actual * bytes transferred will be stored in the @actual_length parameter. * */ int usb_bulk_msg_killable(struct usb_device *usb_dev, unsigned int pipe, void *data, int len, int *actual_length, int timeout) { struct urb *urb; struct usb_host_endpoint *ep; ep = usb_pipe_endpoint(usb_dev, pipe); if (!ep || len < 0) return -EINVAL; urb = usb_alloc_urb(0, GFP_KERNEL); if (!urb) return -ENOMEM; if ((ep->desc.bmAttributes & USB_ENDPOINT_XFERTYPE_MASK) == USB_ENDPOINT_XFER_INT) { pipe = (pipe & ~(3 << 30)) | (PIPE_INTERRUPT << 30); usb_fill_int_urb(urb, usb_dev, pipe, data, len, usb_api_blocking_completion, NULL, ep->desc.bInterval); } else usb_fill_bulk_urb(urb, usb_dev, pipe, data, len, usb_api_blocking_completion, NULL); return usb_start_wait_urb(urb, timeout, actual_length, true); } EXPORT_SYMBOL_GPL(usb_bulk_msg_killable); /*-------------------------------------------------------------------*/ static void sg_clean(struct usb_sg_request *io) { if (io->urbs) { while (io->entries--) usb_free_urb(io->urbs[io->entries]); kfree(io->urbs); io->urbs = NULL; } io->dev = NULL; } static void sg_complete(struct urb *urb) { unsigned long flags; struct usb_sg_request *io = urb->context; int status = urb->status; spin_lock_irqsave(&io->lock, flags); /* In 2.5 we require hcds' endpoint queues not to progress after fault * reports, until the completion callback (this!) returns. That lets * device driver code (like this routine) unlink queued urbs first, * if it needs to, since the HC won't work on them at all. So it's * not possible for page N+1 to overwrite page N, and so on. * * That's only for "hard" faults; "soft" faults (unlinks) sometimes * complete before the HCD can get requests away from hardware, * though never during cleanup after a hard fault. */ if (io->status && (io->status != -ECONNRESET || status != -ECONNRESET) && urb->actual_length) { dev_err(io->dev->bus->controller, "dev %s ep%d%s scatterlist error %d/%d\n", io->dev->devpath, usb_endpoint_num(&urb->ep->desc), usb_urb_dir_in(urb) ? "in" : "out", status, io->status); /* BUG (); */ } if (io->status == 0 && status && status != -ECONNRESET) { int i, found, retval; io->status = status; /* the previous urbs, and this one, completed already. * unlink pending urbs so they won't rx/tx bad data. * careful: unlink can sometimes be synchronous... */ spin_unlock_irqrestore(&io->lock, flags); for (i = 0, found = 0; i < io->entries; i++) { if (!io->urbs[i]) continue; if (found) { usb_block_urb(io->urbs[i]); retval = usb_unlink_urb(io->urbs[i]); if (retval != -EINPROGRESS && retval != -ENODEV && retval != -EBUSY && retval != -EIDRM) dev_err(&io->dev->dev, "%s, unlink --> %d\n", __func__, retval); } else if (urb == io->urbs[i]) found = 1; } spin_lock_irqsave(&io->lock, flags); } /* on the last completion, signal usb_sg_wait() */ io->bytes += urb->actual_length; io->count--; if (!io->count) complete(&io->complete); spin_unlock_irqrestore(&io->lock, flags); } /** * usb_sg_init - initializes scatterlist-based bulk/interrupt I/O request * @io: request block being initialized. until usb_sg_wait() returns, * treat this as a pointer to an opaque block of memory, * @dev: the usb device that will send or receive the data * @pipe: endpoint "pipe" used to transfer the data * @period: polling rate for interrupt endpoints, in frames or * (for high speed endpoints) microframes; ignored for bulk * @sg: scatterlist entries * @nents: how many entries in the scatterlist * @length: how many bytes to send from the scatterlist, or zero to * send every byte identified in the list. * @mem_flags: SLAB_* flags affecting memory allocations in this call * * This initializes a scatter/gather request, allocating resources such as * I/O mappings and urb memory (except maybe memory used by USB controller * drivers). * * The request must be issued using usb_sg_wait(), which waits for the I/O to * complete (or to be canceled) and then cleans up all resources allocated by * usb_sg_init(). * * The request may be canceled with usb_sg_cancel(), either before or after * usb_sg_wait() is called. * * Return: Zero for success, else a negative errno value. */ int usb_sg_init(struct usb_sg_request *io, struct usb_device *dev, unsigned pipe, unsigned period, struct scatterlist *sg, int nents, size_t length, gfp_t mem_flags) { int i; int urb_flags; int use_sg; if (!io || !dev || !sg || usb_pipecontrol(pipe) || usb_pipeisoc(pipe) || nents <= 0) return -EINVAL; spin_lock_init(&io->lock); io->dev = dev; io->pipe = pipe; if (dev->bus->sg_tablesize > 0) { use_sg = true; io->entries = 1; } else { use_sg = false; io->entries = nents; } /* initialize all the urbs we'll use */ io->urbs = kmalloc_objs(*io->urbs, io->entries, mem_flags); if (!io->urbs) goto nomem; urb_flags = URB_NO_INTERRUPT; if (usb_pipein(pipe)) urb_flags |= URB_SHORT_NOT_OK; for_each_sg(sg, sg, io->entries, i) { struct urb *urb; unsigned len; urb = usb_alloc_urb(0, mem_flags); if (!urb) { io->entries = i; goto nomem; } io->urbs[i] = urb; urb->dev = NULL; urb->pipe = pipe; urb->interval = period; urb->transfer_flags = urb_flags; urb->complete = sg_complete; urb->context = io; urb->sg = sg; if (use_sg) { /* There is no single transfer buffer */ urb->transfer_buffer = NULL; urb->num_sgs = nents; /* A length of zero means transfer the whole sg list */ len = length; if (len == 0) { struct scatterlist *sg2; int j; for_each_sg(sg, sg2, nents, j) len += sg2->length; } } else { /* * Some systems can't use DMA; they use PIO instead. * For their sakes, transfer_buffer is set whenever * possible. */ if (!PageHighMem(sg_page(sg))) urb->transfer_buffer = sg_virt(sg); else urb->transfer_buffer = NULL; len = sg->length; if (length) { len = min_t(size_t, len, length); length -= len; if (length == 0) io->entries = i + 1; } } urb->transfer_buffer_length = len; } io->urbs[--i]->transfer_flags &= ~URB_NO_INTERRUPT; /* transaction state */ io->count = io->entries; io->status = 0; io->bytes = 0; init_completion(&io->complete); return 0; nomem: sg_clean(io); return -ENOMEM; } EXPORT_SYMBOL_GPL(usb_sg_init); /** * usb_sg_wait - synchronously execute scatter/gather request * @io: request block handle, as initialized with usb_sg_init(). * some fields become accessible when this call returns. * * Context: task context, might sleep. * * This function blocks until the specified I/O operation completes. It * leverages the grouping of the related I/O requests to get good transfer * rates, by queueing the requests. At higher speeds, such queuing can * significantly improve USB throughput. * * There are three kinds of completion for this function. * * (1) success, where io->status is zero. The number of io->bytes * transferred is as requested. * (2) error, where io->status is a negative errno value. The number * of io->bytes transferred before the error is usually less * than requested, and can be nonzero. * (3) cancellation, a type of error with status -ECONNRESET that * is initiated by usb_sg_cancel(). * * When this function returns, all memory allocated through usb_sg_init() or * this call will have been freed. The request block parameter may still be * passed to usb_sg_cancel(), or it may be freed. It could also be * reinitialized and then reused. * * Data Transfer Rates: * * Bulk transfers are valid for full or high speed endpoints. * The best full speed data rate is 19 packets of 64 bytes each * per frame, or 1216 bytes per millisecond. * The best high speed data rate is 13 packets of 512 bytes each * per microframe, or 52 KBytes per millisecond. * * The reason to use interrupt transfers through this API would most likely * be to reserve high speed bandwidth, where up to 24 KBytes per millisecond * could be transferred. That capability is less useful for low or full * speed interrupt endpoints, which allow at most one packet per millisecond, * of at most 8 or 64 bytes (respectively). * * It is not necessary to call this function to reserve bandwidth for devices * under an xHCI host controller, as the bandwidth is reserved when the * configuration or interface alt setting is selected. */ void usb_sg_wait(struct usb_sg_request *io) { int i; int entries = io->entries; /* queue the urbs. */ spin_lock_irq(&io->lock); i = 0; while (i < entries && !io->status) { int retval; io->urbs[i]->dev = io->dev; spin_unlock_irq(&io->lock); retval = usb_submit_urb(io->urbs[i], GFP_NOIO); switch (retval) { /* maybe we retrying will recover */ case -ENXIO: /* hc didn't queue this one */ case -EAGAIN: case -ENOMEM: retval = 0; yield(); break; /* no error? continue immediately. * * NOTE: to work better with UHCI (4K I/O buffer may * need 3K of TDs) it may be good to limit how many * URBs are queued at once; N milliseconds? */ case 0: ++i; cpu_relax(); break; /* fail any uncompleted urbs */ default: io->urbs[i]->status = retval; dev_dbg(&io->dev->dev, "%s, submit --> %d\n", __func__, retval); usb_sg_cancel(io); } spin_lock_irq(&io->lock); if (retval && (io->status == 0 || io->status == -ECONNRESET)) io->status = retval; } io->count -= entries - i; if (io->count == 0) complete(&io->complete); spin_unlock_irq(&io->lock); /* OK, yes, this could be packaged as non-blocking. * So could the submit loop above ... but it's easier to * solve neither problem than to solve both! */ wait_for_completion(&io->complete); sg_clean(io); } EXPORT_SYMBOL_GPL(usb_sg_wait); /** * usb_sg_cancel - stop scatter/gather i/o issued by usb_sg_wait() * @io: request block, initialized with usb_sg_init() * * This stops a request after it has been started by usb_sg_wait(). * It can also prevents one initialized by usb_sg_init() from starting, * so that call just frees resources allocated to the request. */ void usb_sg_cancel(struct usb_sg_request *io) { unsigned long flags; int i, retval; spin_lock_irqsave(&io->lock, flags); if (io->status || io->count == 0) { spin_unlock_irqrestore(&io->lock, flags); return; } /* shut everything down */ io->status = -ECONNRESET; io->count++; /* Keep the request alive until we're done */ spin_unlock_irqrestore(&io->lock, flags); for (i = io->entries - 1; i >= 0; --i) { usb_block_urb(io->urbs[i]); retval = usb_unlink_urb(io->urbs[i]); if (retval != -EINPROGRESS && retval != -ENODEV && retval != -EBUSY && retval != -EIDRM) dev_warn(&io->dev->dev, "%s, unlink --> %d\n", __func__, retval); } spin_lock_irqsave(&io->lock, flags); io->count--; if (!io->count) complete(&io->complete); spin_unlock_irqrestore(&io->lock, flags); } EXPORT_SYMBOL_GPL(usb_sg_cancel); /*-------------------------------------------------------------------*/ /** * usb_get_descriptor - issues a generic GET_DESCRIPTOR request * @dev: the device whose descriptor is being retrieved * @type: the descriptor type (USB_DT_*) * @index: the number of the descriptor * @buf: where to put the descriptor * @size: how big is "buf"? * * Context: task context, might sleep. * * Gets a USB descriptor. Convenience functions exist to simplify * getting some types of descriptors. Use * usb_get_string() or usb_string() for USB_DT_STRING. * Device (USB_DT_DEVICE) and configuration descriptors (USB_DT_CONFIG) * are part of the device structure. * In addition to a number of USB-standard descriptors, some * devices also use class-specific or vendor-specific descriptors. * * This call is synchronous, and may not be used in an interrupt context. * * Return: The number of bytes received on success, or else the status code * returned by the underlying usb_control_msg() call. */ int usb_get_descriptor(struct usb_device *dev, unsigned char type, unsigned char index, void *buf, int size) { int i; int result; if (size <= 0) /* No point in asking for no data */ return -EINVAL; memset(buf, 0, size); /* Make sure we parse really received data */ for (i = 0; i < 3; ++i) { /* retry on length 0 or error; some devices are flakey */ result = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, (type << 8) + index, 0, buf, size, USB_CTRL_GET_TIMEOUT); if (result <= 0 && result != -ETIMEDOUT) continue; if (result > 1 && ((u8 *)buf)[1] != type) { result = -ENODATA; continue; } break; } return result; } EXPORT_SYMBOL_GPL(usb_get_descriptor); /** * usb_get_string - gets a string descriptor * @dev: the device whose string descriptor is being retrieved * @langid: code for language chosen (from string descriptor zero) * @index: the number of the descriptor * @buf: where to put the string * @size: how big is "buf"? * * Context: task context, might sleep. * * Retrieves a string, encoded using UTF-16LE (Unicode, 16 bits per character, * in little-endian byte order). * The usb_string() function will often be a convenient way to turn * these strings into kernel-printable form. * * Strings may be referenced in device, configuration, interface, or other * descriptors, and could also be used in vendor-specific ways. * * This call is synchronous, and may not be used in an interrupt context. * * Return: The number of bytes received on success, or else the status code * returned by the underlying usb_control_msg() call. */ static int usb_get_string(struct usb_device *dev, unsigned short langid, unsigned char index, void *buf, int size) { int i; int result; if (size <= 0) /* No point in asking for no data */ return -EINVAL; for (i = 0; i < 3; ++i) { /* retry on length 0 or stall; some devices are flakey */ result = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), USB_REQ_GET_DESCRIPTOR, USB_DIR_IN, (USB_DT_STRING << 8) + index, langid, buf, size, USB_CTRL_GET_TIMEOUT); if (result == 0 || result == -EPIPE) continue; if (result > 1 && ((u8 *) buf)[1] != USB_DT_STRING) { result = -ENODATA; continue; } break; } return result; } static void usb_try_string_workarounds(unsigned char *buf, int *length) { int newlength, oldlength = *length; for (newlength = 2; newlength + 1 < oldlength; newlength += 2) if (!isprint(buf[newlength]) || buf[newlength + 1]) break; if (newlength > 2) { buf[0] = newlength; *length = newlength; } } static int usb_string_sub(struct usb_device *dev, unsigned int langid, unsigned int index, unsigned char *buf) { int rc; /* Try to read the string descriptor by asking for the maximum * possible number of bytes */ if (dev->quirks & USB_QUIRK_STRING_FETCH_255) rc = -EIO; else rc = usb_get_string(dev, langid, index, buf, 255); /* If that failed try to read the descriptor length, then * ask for just that many bytes */ if (rc < 2) { rc = usb_get_string(dev, langid, index, buf, 2); if (rc == 2) rc = usb_get_string(dev, langid, index, buf, buf[0]); } if (rc >= 2) { if (!buf[0] && !buf[1]) usb_try_string_workarounds(buf, &rc); /* There might be extra junk at the end of the descriptor */ if (buf[0] < rc) rc = buf[0]; rc = rc - (rc & 1); /* force a multiple of two */ } if (rc < 2) rc = (rc < 0 ? rc : -EINVAL); return rc; } static int usb_get_langid(struct usb_device *dev, unsigned char *tbuf) { int err; if (dev->have_langid) return 0; if (dev->string_langid < 0) return -EPIPE; err = usb_string_sub(dev, 0, 0, tbuf); /* If the string was reported but is malformed, default to english * (0x0409) */ if (err == -ENODATA || (err > 0 && err < 4)) { dev->string_langid = 0x0409; dev->have_langid = 1; dev_err(&dev->dev, "language id specifier not provided by device, defaulting to English\n"); return 0; } /* In case of all other errors, we assume the device is not able to * deal with strings at all. Set string_langid to -1 in order to * prevent any string to be retrieved from the device */ if (err < 0) { dev_info(&dev->dev, "string descriptor 0 read error: %d\n", err); dev->string_langid = -1; return -EPIPE; } /* always use the first langid listed */ dev->string_langid = tbuf[2] | (tbuf[3] << 8); dev->have_langid = 1; dev_dbg(&dev->dev, "default language 0x%04x\n", dev->string_langid); return 0; } /** * usb_string - returns UTF-8 version of a string descriptor * @dev: the device whose string descriptor is being retrieved * @index: the number of the descriptor * @buf: where to put the string * @size: how big is "buf"? * * Context: task context, might sleep. * * This converts the UTF-16LE encoded strings returned by devices, from * usb_get_string_descriptor(), to null-terminated UTF-8 encoded ones * that are more usable in most kernel contexts. Note that this function * chooses strings in the first language supported by the device. * * This call is synchronous, and may not be used in an interrupt context. * * Return: length of the string (>= 0) or usb_control_msg status (< 0). */ int usb_string(struct usb_device *dev, int index, char *buf, size_t size) { unsigned char *tbuf; int err; if (dev->state == USB_STATE_SUSPENDED) return -EHOSTUNREACH; if (size <= 0 || !buf) return -EINVAL; buf[0] = 0; if (index <= 0 || index >= 256) return -EINVAL; tbuf = kmalloc(256, GFP_NOIO); if (!tbuf) return -ENOMEM; err = usb_get_langid(dev, tbuf); if (err < 0) goto errout; err = usb_string_sub(dev, dev->string_langid, index, tbuf); if (err < 0) goto errout; size--; /* leave room for trailing NULL char in output buffer */ err = utf16s_to_utf8s((wchar_t *) &tbuf[2], (err - 2) / 2, UTF16_LITTLE_ENDIAN, buf, size); buf[err] = 0; if (tbuf[1] != USB_DT_STRING) dev_dbg(&dev->dev, "wrong descriptor type %02x for string %d (\"%s\")\n", tbuf[1], index, buf); errout: kfree(tbuf); return err; } EXPORT_SYMBOL_GPL(usb_string); /* one 16-bit character, when UTF-8-encoded, has at most three bytes */ #define MAX_USB_STRING_SIZE (127 * 3 + 1) /** * usb_cache_string - read a string descriptor and cache it for later use * @udev: the device whose string descriptor is being read * @index: the descriptor index * * Return: A pointer to a kmalloc'ed buffer containing the descriptor string, * or %NULL if the index is 0 or the string could not be read. */ char *usb_cache_string(struct usb_device *udev, int index) { char *buf; char *smallbuf = NULL; int len; if (index <= 0) return NULL; buf = kmalloc(MAX_USB_STRING_SIZE, GFP_NOIO); if (!buf) return NULL; len = usb_string(udev, index, buf, MAX_USB_STRING_SIZE); if (len <= 0) { kfree(buf); return NULL; } smallbuf = krealloc(buf, len + 1, GFP_NOIO); if (unlikely(!smallbuf)) return buf; return smallbuf; } EXPORT_SYMBOL_GPL(usb_cache_string); /* * usb_get_device_descriptor - read the device descriptor * @udev: the device whose device descriptor should be read * * Context: task context, might sleep. * * Not exported, only for use by the core. If drivers really want to read * the device descriptor directly, they can call usb_get_descriptor() with * type = USB_DT_DEVICE and index = 0. * * Returns: a pointer to a dynamically allocated usb_device_descriptor * structure (which the caller must deallocate), or an ERR_PTR value. */ struct usb_device_descriptor *usb_get_device_descriptor(struct usb_device *udev) { struct usb_device_descriptor *desc; int ret; desc = kmalloc_obj(*desc, GFP_NOIO); if (!desc) return ERR_PTR(-ENOMEM); ret = usb_get_descriptor(udev, USB_DT_DEVICE, 0, desc, sizeof(*desc)); if (ret == sizeof(*desc)) return desc; if (ret >= 0) ret = -EMSGSIZE; kfree(desc); return ERR_PTR(ret); } /* * usb_set_isoch_delay - informs the device of the packet transmit delay * @dev: the device whose delay is to be informed * Context: task context, might sleep * * Since this is an optional request, we don't bother if it fails. */ int usb_set_isoch_delay(struct usb_device *dev) { /* skip hub devices */ if (dev->descriptor.bDeviceClass == USB_CLASS_HUB) return 0; /* skip non-SS/non-SSP devices */ if (dev->speed < USB_SPEED_SUPER) return 0; return usb_control_msg_send(dev, 0, USB_REQ_SET_ISOCH_DELAY, USB_DIR_OUT | USB_TYPE_STANDARD | USB_RECIP_DEVICE, dev->hub_delay, 0, NULL, 0, USB_CTRL_SET_TIMEOUT, GFP_NOIO); } /** * usb_get_status - issues a GET_STATUS call * @dev: the device whose status is being checked * @recip: USB_RECIP_*; for device, interface, or endpoint * @type: USB_STATUS_TYPE_*; for standard or PTM status types * @target: zero (for device), else interface or endpoint number * @data: pointer to two bytes of bitmap data * * Context: task context, might sleep. * * Returns device, interface, or endpoint status. Normally only of * interest to see if the device is self powered, or has enabled the * remote wakeup facility; or whether a bulk or interrupt endpoint * is halted ("stalled"). * * Bits in these status bitmaps are set using the SET_FEATURE request, * and cleared using the CLEAR_FEATURE request. The usb_clear_halt() * function should be used to clear halt ("stall") status. * * This call is synchronous, and may not be used in an interrupt context. * * Returns 0 and the status value in *@data (in host byte order) on success, * or else the status code from the underlying usb_control_msg() call. */ int usb_get_status(struct usb_device *dev, int recip, int type, int target, void *data) { int ret; void *status; int length; switch (type) { case USB_STATUS_TYPE_STANDARD: length = 2; break; case USB_STATUS_TYPE_PTM: if (recip != USB_RECIP_DEVICE) return -EINVAL; length = 4; break; default: return -EINVAL; } status = kmalloc(length, GFP_KERNEL); if (!status) return -ENOMEM; ret = usb_control_msg(dev, usb_rcvctrlpipe(dev, 0), USB_REQ_GET_STATUS, USB_DIR_IN | recip, USB_STATUS_TYPE_STANDARD, target, status, length, USB_CTRL_GET_TIMEOUT); switch (ret) { case 4: if (type != USB_STATUS_TYPE_PTM) { ret = -EIO; break; } *(u32 *) data = le32_to_cpu(*(__le32 *) status); ret = 0; break; case 2: if (type != USB_STATUS_TYPE_STANDARD) { ret = -EIO; break; } *(u16 *) data = le16_to_cpu(*(__le16 *) status); ret = 0; break; default: ret = -EIO; } kfree(status); return ret; } EXPORT_SYMBOL_GPL(usb_get_status); /** * usb_clear_halt - tells device to clear endpoint halt/stall condition * @dev: device whose endpoint is halted * @pipe: endpoint "pipe" being cleared * * Context: task context, might sleep. * * This is used to clear halt conditions for bulk and interrupt endpoints, * as reported by URB completion status. Endpoints that are halted are * sometimes referred to as being "stalled". Such endpoints are unable * to transmit or receive data until the halt status is cleared. Any URBs * queued for such an endpoint should normally be unlinked by the driver * before clearing the halt condition, as described in sections 5.7.5 * and 5.8.5 of the USB 2.0 spec. * * Note that control and isochronous endpoints don't halt, although control * endpoints report "protocol stall" (for unsupported requests) using the * same status code used to report a true stall. * * This call is synchronous, and may not be used in an interrupt context. * If a thread in your driver uses this call, make sure your disconnect() * method can wait for it to complete. * * Return: Zero on success, or else the status code returned by the * underlying usb_control_msg() call. */ int usb_clear_halt(struct usb_device *dev, int pipe) { int result; int endp = usb_pipeendpoint(pipe); if (usb_pipein(pipe)) endp |= USB_DIR_IN; /* we don't care if it wasn't halted first. in fact some devices * (like some ibmcam model 1 units) seem to expect hosts to make * this request for iso endpoints, which can't halt! */ result = usb_control_msg_send(dev, 0, USB_REQ_CLEAR_FEATURE, USB_RECIP_ENDPOINT, USB_ENDPOINT_HALT, endp, NULL, 0, USB_CTRL_SET_TIMEOUT, GFP_NOIO); /* don't un-halt or force to DATA0 except on success */ if (result) return result; /* NOTE: seems like Microsoft and Apple don't bother verifying * the clear "took", so some devices could lock up if you check... * such as the Hagiwara FlashGate DUAL. So we won't bother. * * NOTE: make sure the logic here doesn't diverge much from * the copy in usb-storage, for as long as we need two copies. */ usb_reset_endpoint(dev, endp); return 0; } EXPORT_SYMBOL_GPL(usb_clear_halt); static int create_intf_ep_devs(struct usb_interface *intf) { struct usb_device *udev = interface_to_usbdev(intf); struct usb_host_interface *alt = intf->cur_altsetting; int i; if (intf->ep_devs_created || intf->unregistering) return 0; for (i = 0; i < alt->desc.bNumEndpoints; ++i) (void) usb_create_ep_devs(&intf->dev, &alt->endpoint[i], udev); intf->ep_devs_created = 1; return 0; } static void remove_intf_ep_devs(struct usb_interface *intf) { struct usb_host_interface *alt = intf->cur_altsetting; int i; if (!intf->ep_devs_created) return; for (i = 0; i < alt->desc.bNumEndpoints; ++i) usb_remove_ep_devs(&alt->endpoint[i]); intf->ep_devs_created = 0; } /** * usb_disable_endpoint -- Disable an endpoint by address * @dev: the device whose endpoint is being disabled * @epaddr: the endpoint's address. Endpoint number for output, * endpoint number + USB_DIR_IN for input * @reset_hardware: flag to erase any endpoint state stored in the * controller hardware * * Disables the endpoint for URB submission and nukes all pending URBs. * If @reset_hardware is set then also deallocates hcd/hardware state * for the endpoint. */ void usb_disable_endpoint(struct usb_device *dev, unsigned int epaddr, bool reset_hardware) { unsigned int epnum = epaddr & USB_ENDPOINT_NUMBER_MASK; struct usb_host_endpoint *ep; if (!dev) return; if (usb_endpoint_out(epaddr)) { ep = dev->ep_out[epnum]; if (reset_hardware && epnum != 0) dev->ep_out[epnum] = NULL; } else { ep = dev->ep_in[epnum]; if (reset_hardware && epnum != 0) dev->ep_in[epnum] = NULL; } if (ep) { ep->enabled = 0; usb_hcd_flush_endpoint(dev, ep); if (reset_hardware) usb_hcd_disable_endpoint(dev, ep); } } /** * usb_reset_endpoint - Reset an endpoint's state. * @dev: the device whose endpoint is to be reset * @epaddr: the endpoint's address. Endpoint number for output, * endpoint number + USB_DIR_IN for input * * Resets any host-side endpoint state such as the toggle bit, * sequence number or current window. */ void usb_reset_endpoint(struct usb_device *dev, unsigned int epaddr) { unsigned int epnum = epaddr & USB_ENDPOINT_NUMBER_MASK; struct usb_host_endpoint *ep; if (usb_endpoint_out(epaddr)) ep = dev->ep_out[epnum]; else ep = dev->ep_in[epnum]; if (ep) usb_hcd_reset_endpoint(dev, ep); } EXPORT_SYMBOL_GPL(usb_reset_endpoint); /** * usb_disable_interface -- Disable all endpoints for an interface * @dev: the device whose interface is being disabled * @intf: pointer to the interface descriptor * @reset_hardware: flag to erase any endpoint state stored in the * controller hardware * * Disables all the endpoints for the interface's current altsetting. */ void usb_disable_interface(struct usb_device *dev, struct usb_interface *intf, bool reset_hardware) { struct usb_host_interface *alt = intf->cur_altsetting; int i; for (i = 0; i < alt->desc.bNumEndpoints; ++i) { usb_disable_endpoint(dev, alt->endpoint[i].desc.bEndpointAddress, reset_hardware); } } /* * usb_disable_device_endpoints -- Disable all endpoints for a device * @dev: the device whose endpoints are being disabled * @skip_ep0: 0 to disable endpoint 0, 1 to skip it. */ static void usb_disable_device_endpoints(struct usb_device *dev, int skip_ep0) { struct usb_hcd *hcd = bus_to_hcd(dev->bus); int i; if (hcd->driver->check_bandwidth) { /* First pass: Cancel URBs, leave endpoint pointers intact. */ for (i = skip_ep0; i < 16; ++i) { usb_disable_endpoint(dev, i, false); usb_disable_endpoint(dev, i + USB_DIR_IN, false); } /* Remove endpoints from the host controller internal state */ mutex_lock(hcd->bandwidth_mutex); usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL); mutex_unlock(hcd->bandwidth_mutex); } /* Second pass: remove endpoint pointers */ for (i = skip_ep0; i < 16; ++i) { usb_disable_endpoint(dev, i, true); usb_disable_endpoint(dev, i + USB_DIR_IN, true); } } /** * usb_disable_device - Disable all the endpoints for a USB device * @dev: the device whose endpoints are being disabled * @skip_ep0: 0 to disable endpoint 0, 1 to skip it. * * Disables all the device's endpoints, potentially including endpoint 0. * Deallocates hcd/hardware state for the endpoints (nuking all or most * pending urbs) and usbcore state for the interfaces, so that usbcore * must usb_set_configuration() before any interfaces could be used. */ void usb_disable_device(struct usb_device *dev, int skip_ep0) { int i; /* getting rid of interfaces will disconnect * any drivers bound to them (a key side effect) */ if (dev->actconfig) { /* * FIXME: In order to avoid self-deadlock involving the * bandwidth_mutex, we have to mark all the interfaces * before unregistering any of them. */ for (i = 0; i < dev->actconfig->desc.bNumInterfaces; i++) dev->actconfig->interface[i]->unregistering = 1; for (i = 0; i < dev->actconfig->desc.bNumInterfaces; i++) { struct usb_interface *interface; /* remove this interface if it has been registered */ interface = dev->actconfig->interface[i]; if (!device_is_registered(&interface->dev)) continue; dev_dbg(&dev->dev, "unregistering interface %s\n", dev_name(&interface->dev)); remove_intf_ep_devs(interface); device_del(&interface->dev); } /* Now that the interfaces are unbound, nobody should * try to access them. */ for (i = 0; i < dev->actconfig->desc.bNumInterfaces; i++) { put_device(&dev->actconfig->interface[i]->dev); dev->actconfig->interface[i] = NULL; } usb_disable_usb2_hardware_lpm(dev); usb_unlocked_disable_lpm(dev); usb_disable_ltm(dev); dev->actconfig = NULL; if (dev->state == USB_STATE_CONFIGURED) usb_set_device_state(dev, USB_STATE_ADDRESS); } dev_dbg(&dev->dev, "%s nuking %s URBs\n", __func__, skip_ep0 ? "non-ep0" : "all"); usb_disable_device_endpoints(dev, skip_ep0); } /** * usb_enable_endpoint - Enable an endpoint for USB communications * @dev: the device whose interface is being enabled * @ep: the endpoint * @reset_ep: flag to reset the endpoint state * * Resets the endpoint state if asked, and sets dev->ep_{in,out} pointers. * For control endpoints, both the input and output sides are handled. */ void usb_enable_endpoint(struct usb_device *dev, struct usb_host_endpoint *ep, bool reset_ep) { int epnum = usb_endpoint_num(&ep->desc); int is_out = usb_endpoint_dir_out(&ep->desc); int is_control = usb_endpoint_xfer_control(&ep->desc); if (reset_ep) usb_hcd_reset_endpoint(dev, ep); if (is_out || is_control) dev->ep_out[epnum] = ep; if (!is_out || is_control) dev->ep_in[epnum] = ep; ep->enabled = 1; } /** * usb_enable_interface - Enable all the endpoints for an interface * @dev: the device whose interface is being enabled * @intf: pointer to the interface descriptor * @reset_eps: flag to reset the endpoints' state * * Enables all the endpoints for the interface's current altsetting. */ void usb_enable_interface(struct usb_device *dev, struct usb_interface *intf, bool reset_eps) { struct usb_host_interface *alt = intf->cur_altsetting; int i; for (i = 0; i < alt->desc.bNumEndpoints; ++i) usb_enable_endpoint(dev, &alt->endpoint[i], reset_eps); } /** * usb_set_interface - Makes a particular alternate setting be current * @dev: the device whose interface is being updated * @interface: the interface being updated * @alternate: the setting being chosen. * * Context: task context, might sleep. * * This is used to enable data transfers on interfaces that may not * be enabled by default. Not all devices support such configurability. * Only the driver bound to an interface may change its setting. * * Within any given configuration, each interface may have several * alternative settings. These are often used to control levels of * bandwidth consumption. For example, the default setting for a high * speed interrupt endpoint may not send more than 64 bytes per microframe, * while interrupt transfers of up to 3KBytes per microframe are legal. * Also, isochronous endpoints may never be part of an * interface's default setting. To access such bandwidth, alternate * interface settings must be made current. * * Note that in the Linux USB subsystem, bandwidth associated with * an endpoint in a given alternate setting is not reserved until an URB * is submitted that needs that bandwidth. Some other operating systems * allocate bandwidth early, when a configuration is chosen. * * xHCI reserves bandwidth and configures the alternate setting in * usb_hcd_alloc_bandwidth(). If it fails the original interface altsetting * may be disabled. Drivers cannot rely on any particular alternate * setting being in effect after a failure. * * This call is synchronous, and may not be used in an interrupt context. * Also, drivers must not change altsettings while urbs are scheduled for * endpoints in that interface; all such urbs must first be completed * (perhaps forced by unlinking). If a thread in your driver uses this call, * make sure your disconnect() method can wait for it to complete. * * Return: Zero on success, or else the status code returned by the * underlying usb_control_msg() call. */ int usb_set_interface(struct usb_device *dev, int interface, int alternate) { struct usb_interface *iface; struct usb_host_interface *alt; struct usb_hcd *hcd = bus_to_hcd(dev->bus); int i, ret, manual = 0; unsigned int epaddr; unsigned int pipe; if (dev->state == USB_STATE_SUSPENDED) return -EHOSTUNREACH; iface = usb_ifnum_to_if(dev, interface); if (!iface) { dev_dbg(&dev->dev, "selecting invalid interface %d\n", interface); return -EINVAL; } if (iface->unregistering) return -ENODEV; alt = usb_altnum_to_altsetting(iface, alternate); if (!alt) { dev_warn(&dev->dev, "selecting invalid altsetting %d\n", alternate); return -EINVAL; } /* * usb3 hosts configure the interface in usb_hcd_alloc_bandwidth, * including freeing dropped endpoint ring buffers. * Make sure the interface endpoints are flushed before that */ usb_disable_interface(dev, iface, false); /* Make sure we have enough bandwidth for this alternate interface. * Remove the current alt setting and add the new alt setting. */ mutex_lock(hcd->bandwidth_mutex); /* Disable LPM, and re-enable it once the new alt setting is installed, * so that the xHCI driver can recalculate the U1/U2 timeouts. */ if (usb_disable_lpm(dev)) { dev_err(&iface->dev, "%s Failed to disable LPM\n", __func__); mutex_unlock(hcd->bandwidth_mutex); return -ENOMEM; } /* Changing alt-setting also frees any allocated streams */ for (i = 0; i < iface->cur_altsetting->desc.bNumEndpoints; i++) iface->cur_altsetting->endpoint[i].streams = 0; ret = usb_hcd_alloc_bandwidth(dev, NULL, iface->cur_altsetting, alt); if (ret < 0) { dev_info(&dev->dev, "Not enough bandwidth for altsetting %d\n", alternate); usb_enable_lpm(dev); mutex_unlock(hcd->bandwidth_mutex); return ret; } if (dev->quirks & USB_QUIRK_NO_SET_INTF) ret = -EPIPE; else ret = usb_control_msg_send(dev, 0, USB_REQ_SET_INTERFACE, USB_RECIP_INTERFACE, alternate, interface, NULL, 0, 5000, GFP_NOIO); /* 9.4.10 says devices don't need this and are free to STALL the * request if the interface only has one alternate setting. */ if (ret == -EPIPE && iface->num_altsetting == 1) { dev_dbg(&dev->dev, "manual set_interface for iface %d, alt %d\n", interface, alternate); manual = 1; } else if (ret) { /* Re-instate the old alt setting */ usb_hcd_alloc_bandwidth(dev, NULL, alt, iface->cur_altsetting); usb_enable_lpm(dev); mutex_unlock(hcd->bandwidth_mutex); return ret; } mutex_unlock(hcd->bandwidth_mutex); /* FIXME drivers shouldn't need to replicate/bugfix the logic here * when they implement async or easily-killable versions of this or * other "should-be-internal" functions (like clear_halt). * should hcd+usbcore postprocess control requests? */ /* prevent submissions using previous endpoint settings */ if (iface->cur_altsetting != alt) { remove_intf_ep_devs(iface); usb_remove_sysfs_intf_files(iface); } usb_disable_interface(dev, iface, true); iface->cur_altsetting = alt; /* Now that the interface is installed, re-enable LPM. */ usb_unlocked_enable_lpm(dev); /* If the interface only has one altsetting and the device didn't * accept the request, we attempt to carry out the equivalent action * by manually clearing the HALT feature for each endpoint in the * new altsetting. */ if (manual) { for (i = 0; i < alt->desc.bNumEndpoints; i++) { epaddr = alt->endpoint[i].desc.bEndpointAddress; pipe = __create_pipe(dev, USB_ENDPOINT_NUMBER_MASK & epaddr) | (usb_endpoint_out(epaddr) ? USB_DIR_OUT : USB_DIR_IN); usb_clear_halt(dev, pipe); } } /* 9.1.1.5: reset toggles for all endpoints in the new altsetting * * Note: * Despite EP0 is always present in all interfaces/AS, the list of * endpoints from the descriptor does not contain EP0. Due to its * omnipresence one might expect EP0 being considered "affected" by * any SetInterface request and hence assume toggles need to be reset. * However, EP0 toggles are re-synced for every individual transfer * during the SETUP stage - hence EP0 toggles are "don't care" here. * (Likewise, EP0 never "halts" on well designed devices.) */ usb_enable_interface(dev, iface, true); if (device_is_registered(&iface->dev)) { usb_create_sysfs_intf_files(iface); create_intf_ep_devs(iface); } return 0; } EXPORT_SYMBOL_GPL(usb_set_interface); /** * usb_reset_configuration - lightweight device reset * @dev: the device whose configuration is being reset * * This issues a standard SET_CONFIGURATION request to the device using * the current configuration. The effect is to reset most USB-related * state in the device, including interface altsettings (reset to zero), * endpoint halts (cleared), and endpoint state (only for bulk and interrupt * endpoints). Other usbcore state is unchanged, including bindings of * usb device drivers to interfaces. * * Because this affects multiple interfaces, avoid using this with composite * (multi-interface) devices. Instead, the driver for each interface may * use usb_set_interface() on the interfaces it claims. Be careful though; * some devices don't support the SET_INTERFACE request, and others won't * reset all the interface state (notably endpoint state). Resetting the whole * configuration would affect other drivers' interfaces. * * The caller must own the device lock. * * Return: Zero on success, else a negative error code. * * If this routine fails the device will probably be in an unusable state * with endpoints disabled, and interfaces only partially enabled. */ int usb_reset_configuration(struct usb_device *dev) { int i, retval; struct usb_host_config *config; struct usb_hcd *hcd = bus_to_hcd(dev->bus); if (dev->state == USB_STATE_SUSPENDED) return -EHOSTUNREACH; /* caller must have locked the device and must own * the usb bus readlock (so driver bindings are stable); * calls during probe() are fine */ usb_disable_device_endpoints(dev, 1); /* skip ep0*/ config = dev->actconfig; retval = 0; mutex_lock(hcd->bandwidth_mutex); /* Disable LPM, and re-enable it once the configuration is reset, so * that the xHCI driver can recalculate the U1/U2 timeouts. */ if (usb_disable_lpm(dev)) { dev_err(&dev->dev, "%s Failed to disable LPM\n", __func__); mutex_unlock(hcd->bandwidth_mutex); return -ENOMEM; } /* xHCI adds all endpoints in usb_hcd_alloc_bandwidth */ retval = usb_hcd_alloc_bandwidth(dev, config, NULL, NULL); if (retval < 0) { usb_enable_lpm(dev); mutex_unlock(hcd->bandwidth_mutex); return retval; } retval = usb_control_msg_send(dev, 0, USB_REQ_SET_CONFIGURATION, 0, config->desc.bConfigurationValue, 0, NULL, 0, USB_CTRL_SET_TIMEOUT, GFP_NOIO); if (retval) { usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL); usb_enable_lpm(dev); mutex_unlock(hcd->bandwidth_mutex); return retval; } mutex_unlock(hcd->bandwidth_mutex); /* re-init hc/hcd interface/endpoint state */ for (i = 0; i < config->desc.bNumInterfaces; i++) { struct usb_interface *intf = config->interface[i]; struct usb_host_interface *alt; alt = usb_altnum_to_altsetting(intf, 0); /* No altsetting 0? We'll assume the first altsetting. * We could use a GetInterface call, but if a device is * so non-compliant that it doesn't have altsetting 0 * then I wouldn't trust its reply anyway. */ if (!alt) alt = &intf->altsetting[0]; if (alt != intf->cur_altsetting) { remove_intf_ep_devs(intf); usb_remove_sysfs_intf_files(intf); } intf->cur_altsetting = alt; usb_enable_interface(dev, intf, true); if (device_is_registered(&intf->dev)) { usb_create_sysfs_intf_files(intf); create_intf_ep_devs(intf); } } /* Now that the interfaces are installed, re-enable LPM. */ usb_unlocked_enable_lpm(dev); return 0; } EXPORT_SYMBOL_GPL(usb_reset_configuration); static void usb_release_interface(struct device *dev) { struct usb_interface *intf = to_usb_interface(dev); struct usb_interface_cache *intfc = altsetting_to_usb_interface_cache(intf->altsetting); kref_put(&intfc->ref, usb_release_interface_cache); usb_put_dev(interface_to_usbdev(intf)); of_node_put(dev->of_node); kfree(intf); } /* * usb_deauthorize_interface - deauthorize an USB interface * * @intf: USB interface structure */ void usb_deauthorize_interface(struct usb_interface *intf) { struct device *dev = &intf->dev; device_lock(dev->parent); if (intf->authorized) { device_lock(dev); intf->authorized = 0; device_unlock(dev); usb_forced_unbind_intf(intf); } device_unlock(dev->parent); } /* * usb_authorize_interface - authorize an USB interface * * @intf: USB interface structure */ void usb_authorize_interface(struct usb_interface *intf) { struct device *dev = &intf->dev; if (!intf->authorized) { device_lock(dev); intf->authorized = 1; /* authorize interface */ device_unlock(dev); } } static int usb_if_uevent(const struct device *dev, struct kobj_uevent_env *env) { const struct usb_device *usb_dev; const struct usb_interface *intf; const struct usb_host_interface *alt; intf = to_usb_interface(dev); usb_dev = interface_to_usbdev(intf); alt = intf->cur_altsetting; if (add_uevent_var(env, "INTERFACE=%d/%d/%d", alt->desc.bInterfaceClass, alt->desc.bInterfaceSubClass, alt->desc.bInterfaceProtocol)) return -ENOMEM; if (add_uevent_var(env, "MODALIAS=usb:" "v%04Xp%04Xd%04Xdc%02Xdsc%02Xdp%02Xic%02Xisc%02Xip%02Xin%02X", le16_to_cpu(usb_dev->descriptor.idVendor), le16_to_cpu(usb_dev->descriptor.idProduct), le16_to_cpu(usb_dev->descriptor.bcdDevice), usb_dev->descriptor.bDeviceClass, usb_dev->descriptor.bDeviceSubClass, usb_dev->descriptor.bDeviceProtocol, alt->desc.bInterfaceClass, alt->desc.bInterfaceSubClass, alt->desc.bInterfaceProtocol, alt->desc.bInterfaceNumber)) return -ENOMEM; return 0; } const struct device_type usb_if_device_type = { .name = "usb_interface", .release = usb_release_interface, .uevent = usb_if_uevent, }; static struct usb_interface_assoc_descriptor *find_iad(struct usb_device *dev, struct usb_host_config *config, u8 inum) { struct usb_interface_assoc_descriptor *retval = NULL; struct usb_interface_assoc_descriptor *intf_assoc; int first_intf; int last_intf; int i; for (i = 0; (i < USB_MAXIADS && config->intf_assoc[i]); i++) { intf_assoc = config->intf_assoc[i]; if (intf_assoc->bInterfaceCount == 0) continue; first_intf = intf_assoc->bFirstInterface; last_intf = first_intf + (intf_assoc->bInterfaceCount - 1); if (inum >= first_intf && inum <= last_intf) { if (!retval) retval = intf_assoc; else dev_err(&dev->dev, "Interface #%d referenced" " by multiple IADs\n", inum); } } return retval; } /* * Internal function to queue a device reset * See usb_queue_reset_device() for more details */ static void __usb_queue_reset_device(struct work_struct *ws) { int rc; struct usb_interface *iface = container_of(ws, struct usb_interface, reset_ws); struct usb_device *udev = interface_to_usbdev(iface); rc = usb_lock_device_for_reset(udev, iface); if (rc >= 0) { usb_reset_device(udev); usb_unlock_device(udev); } usb_put_intf(iface); /* Undo _get_ in usb_queue_reset_device() */ } /* * Internal function to set the wireless_status sysfs attribute * See usb_set_wireless_status() for more details */ static void __usb_wireless_status_intf(struct work_struct *ws) { struct usb_interface *iface = container_of(ws, struct usb_interface, wireless_status_work); device_lock(iface->dev.parent); if (iface->sysfs_files_created) usb_update_wireless_status_attr(iface); device_unlock(iface->dev.parent); usb_put_intf(iface); /* Undo _get_ in usb_set_wireless_status() */ } /** * usb_set_wireless_status - sets the wireless_status struct member * @iface: the interface to modify * @status: the new wireless status * * Set the wireless_status struct member to the new value, and emit * sysfs changes as necessary. * * Returns: 0 on success, -EALREADY if already set. */ int usb_set_wireless_status(struct usb_interface *iface, enum usb_wireless_status status) { if (iface->wireless_status == status) return -EALREADY; usb_get_intf(iface); iface->wireless_status = status; schedule_work(&iface->wireless_status_work); return 0; } EXPORT_SYMBOL_GPL(usb_set_wireless_status); /* * usb_set_configuration - Makes a particular device setting be current * @dev: the device whose configuration is being updated * @configuration: the configuration being chosen. * * Context: task context, might sleep. Caller holds device lock. * * This is used to enable non-default device modes. Not all devices * use this kind of configurability; many devices only have one * configuration. * * @configuration is the value of the configuration to be installed. * According to the USB spec (e.g. section 9.1.1.5), configuration values * must be non-zero; a value of zero indicates that the device in * unconfigured. However some devices erroneously use 0 as one of their * configuration values. To help manage such devices, this routine will * accept @configuration = -1 as indicating the device should be put in * an unconfigured state. * * USB device configurations may affect Linux interoperability, * power consumption and the functionality available. For example, * the default configuration is limited to using 100mA of bus power, * so that when certain device functionality requires more power, * and the device is bus powered, that functionality should be in some * non-default device configuration. Other device modes may also be * reflected as configuration options, such as whether two ISDN * channels are available independently; and choosing between open * standard device protocols (like CDC) or proprietary ones. * * Note that a non-authorized device (dev->authorized == 0) will only * be put in unconfigured mode. * * Note that USB has an additional level of device configurability, * associated with interfaces. That configurability is accessed using * usb_set_interface(). * * This call is synchronous. The calling context must be able to sleep, * must own the device lock, and must not hold the driver model's USB * bus mutex; usb interface driver probe() methods cannot use this routine. * * Returns zero on success, or else the status code returned by the * underlying call that failed. On successful completion, each interface * in the original device configuration has been destroyed, and each one * in the new configuration has been probed by all relevant usb device * drivers currently known to the kernel. */ int usb_set_configuration(struct usb_device *dev, int configuration) { int i, ret; struct usb_host_config *cp = NULL; struct usb_interface **new_interfaces = NULL; struct usb_hcd *hcd = bus_to_hcd(dev->bus); int n, nintf; if (dev->authorized == 0 || configuration == -1) configuration = 0; else { for (i = 0; i < dev->descriptor.bNumConfigurations; i++) { if (dev->config[i].desc.bConfigurationValue == configuration) { cp = &dev->config[i]; break; } } } if ((!cp && configuration != 0)) return -EINVAL; /* The USB spec says configuration 0 means unconfigured. * But if a device includes a configuration numbered 0, * we will accept it as a correctly configured state. * Use -1 if you really want to unconfigure the device. */ if (cp && configuration == 0) dev_warn(&dev->dev, "config 0 descriptor??\n"); /* Allocate memory for new interfaces before doing anything else, * so that if we run out then nothing will have changed. */ n = nintf = 0; if (cp) { nintf = cp->desc.bNumInterfaces; new_interfaces = kmalloc_objs(*new_interfaces, nintf, GFP_NOIO); if (!new_interfaces) return -ENOMEM; for (; n < nintf; ++n) { new_interfaces[n] = kzalloc_obj(struct usb_interface, GFP_NOIO); if (!new_interfaces[n]) { ret = -ENOMEM; free_interfaces: while (--n >= 0) kfree(new_interfaces[n]); kfree(new_interfaces); return ret; } } i = dev->bus_mA - usb_get_max_power(dev, cp); if (i < 0) dev_warn(&dev->dev, "new config #%d exceeds power " "limit by %dmA\n", configuration, -i); } /* Wake up the device so we can send it the Set-Config request */ ret = usb_autoresume_device(dev); if (ret) goto free_interfaces; /* if it's already configured, clear out old state first. * getting rid of old interfaces means unbinding their drivers. */ if (dev->state != USB_STATE_ADDRESS) usb_disable_device(dev, 1); /* Skip ep0 */ /* Get rid of pending async Set-Config requests for this device */ cancel_async_set_config(dev); /* Make sure we have bandwidth (and available HCD resources) for this * configuration. Remove endpoints from the schedule if we're dropping * this configuration to set configuration 0. After this point, the * host controller will not allow submissions to dropped endpoints. If * this call fails, the device state is unchanged. */ mutex_lock(hcd->bandwidth_mutex); /* Disable LPM, and re-enable it once the new configuration is * installed, so that the xHCI driver can recalculate the U1/U2 * timeouts. */ if (dev->actconfig && usb_disable_lpm(dev)) { dev_err(&dev->dev, "%s Failed to disable LPM\n", __func__); mutex_unlock(hcd->bandwidth_mutex); ret = -ENOMEM; goto free_interfaces; } ret = usb_hcd_alloc_bandwidth(dev, cp, NULL, NULL); if (ret < 0) { if (dev->actconfig) usb_enable_lpm(dev); mutex_unlock(hcd->bandwidth_mutex); usb_autosuspend_device(dev); goto free_interfaces; } /* * Initialize the new interface structures and the * hc/hcd/usbcore interface/endpoint state. */ for (i = 0; i < nintf; ++i) { struct usb_interface_cache *intfc; struct usb_interface *intf; struct usb_host_interface *alt; u8 ifnum; cp->interface[i] = intf = new_interfaces[i]; intfc = cp->intf_cache[i]; intf->altsetting = intfc->altsetting; intf->num_altsetting = intfc->num_altsetting; intf->authorized = !!HCD_INTF_AUTHORIZED(hcd); kref_get(&intfc->ref); alt = usb_altnum_to_altsetting(intf, 0); /* No altsetting 0? We'll assume the first altsetting. * We could use a GetInterface call, but if a device is * so non-compliant that it doesn't have altsetting 0 * then I wouldn't trust its reply anyway. */ if (!alt) alt = &intf->altsetting[0]; ifnum = alt->desc.bInterfaceNumber; intf->intf_assoc = find_iad(dev, cp, ifnum); intf->cur_altsetting = alt; usb_enable_interface(dev, intf, true); intf->dev.parent = &dev->dev; if (usb_of_has_combined_node(dev)) { device_set_of_node_from_dev(&intf->dev, &dev->dev); } else { intf->dev.of_node = usb_of_get_interface_node(dev, configuration, ifnum); } ACPI_COMPANION_SET(&intf->dev, ACPI_COMPANION(&dev->dev)); intf->dev.driver = NULL; intf->dev.bus = &usb_bus_type; intf->dev.type = &usb_if_device_type; intf->dev.groups = usb_interface_groups; INIT_WORK(&intf->reset_ws, __usb_queue_reset_device); INIT_WORK(&intf->wireless_status_work, __usb_wireless_status_intf); intf->minor = -1; device_initialize(&intf->dev); pm_runtime_no_callbacks(&intf->dev); dev_set_name(&intf->dev, "%d-%s:%d.%d", dev->bus->busnum, dev->devpath, configuration, ifnum); usb_get_dev(dev); } kfree(new_interfaces); ret = usb_control_msg_send(dev, 0, USB_REQ_SET_CONFIGURATION, 0, configuration, 0, NULL, 0, USB_CTRL_SET_TIMEOUT, GFP_NOIO); if (ret && cp) { /* * All the old state is gone, so what else can we do? * The device is probably useless now anyway. */ usb_hcd_alloc_bandwidth(dev, NULL, NULL, NULL); for (i = 0; i < nintf; ++i) { usb_disable_interface(dev, cp->interface[i], true); put_device(&cp->interface[i]->dev); cp->interface[i] = NULL; } cp = NULL; } dev->actconfig = cp; mutex_unlock(hcd->bandwidth_mutex); if (!cp) { usb_set_device_state(dev, USB_STATE_ADDRESS); /* Leave LPM disabled while the device is unconfigured. */ usb_autosuspend_device(dev); return ret; } usb_set_device_state(dev, USB_STATE_CONFIGURED); if (cp->string == NULL && !(dev->quirks & USB_QUIRK_CONFIG_INTF_STRINGS)) cp->string = usb_cache_string(dev, cp->desc.iConfiguration); /* Now that the interfaces are installed, re-enable LPM. */ usb_unlocked_enable_lpm(dev); /* Enable LTM if it was turned off by usb_disable_device. */ usb_enable_ltm(dev); /* Now that all the interfaces are set up, register them * to trigger binding of drivers to interfaces. probe() * routines may install different altsettings and may * claim() any interfaces not yet bound. Many class drivers * need that: CDC, audio, video, etc. */ for (i = 0; i < nintf; ++i) { struct usb_interface *intf = cp->interface[i]; if (intf->dev.of_node && !of_device_is_available(intf->dev.of_node)) { dev_info(&dev->dev, "skipping disabled interface %d\n", intf->cur_altsetting->desc.bInterfaceNumber); continue; } dev_dbg(&dev->dev, "adding %s (config #%d, interface %d)\n", dev_name(&intf->dev), configuration, intf->cur_altsetting->desc.bInterfaceNumber); device_enable_async_suspend(&intf->dev); ret = device_add(&intf->dev); if (ret != 0) { dev_err(&dev->dev, "device_add(%s) --> %d\n", dev_name(&intf->dev), ret); continue; } create_intf_ep_devs(intf); } usb_autosuspend_device(dev); return 0; } EXPORT_SYMBOL_GPL(usb_set_configuration); static LIST_HEAD(set_config_list); static DEFINE_SPINLOCK(set_config_lock); struct set_config_request { struct usb_device *udev; int config; struct work_struct work; struct list_head node; }; /* Worker routine for usb_driver_set_configuration() */ static void driver_set_config_work(struct work_struct *work) { struct set_config_request *req = container_of(work, struct set_config_request, work); struct usb_device *udev = req->udev; usb_lock_device(udev); spin_lock(&set_config_lock); list_del(&req->node); spin_unlock(&set_config_lock); if (req->config >= -1) /* Is req still valid? */ usb_set_configuration(udev, req->config); usb_unlock_device(udev); usb_put_dev(udev); kfree(req); } /* Cancel pending Set-Config requests for a device whose configuration * was just changed */ static void cancel_async_set_config(struct usb_device *udev) { struct set_config_request *req; spin_lock(&set_config_lock); list_for_each_entry(req, &set_config_list, node) { if (req->udev == udev) req->config = -999; /* Mark as cancelled */ } spin_unlock(&set_config_lock); } /** * usb_driver_set_configuration - Provide a way for drivers to change device configurations * @udev: the device whose configuration is being updated * @config: the configuration being chosen. * Context: In process context, must be able to sleep * * Device interface drivers are not allowed to change device configurations. * This is because changing configurations will destroy the interface the * driver is bound to and create new ones; it would be like a floppy-disk * driver telling the computer to replace the floppy-disk drive with a * tape drive! * * Still, in certain specialized circumstances the need may arise. This * routine gets around the normal restrictions by using a work thread to * submit the change-config request. * * Return: 0 if the request was successfully queued, error code otherwise. * The caller has no way to know whether the queued request will eventually * succeed. */ int usb_driver_set_configuration(struct usb_device *udev, int config) { struct set_config_request *req; req = kmalloc_obj(*req); if (!req) return -ENOMEM; req->udev = udev; req->config = config; INIT_WORK(&req->work, driver_set_config_work); spin_lock(&set_config_lock); list_add(&req->node, &set_config_list); spin_unlock(&set_config_lock); usb_get_dev(udev); schedule_work(&req->work); return 0; } EXPORT_SYMBOL_GPL(usb_driver_set_configuration); /** * cdc_parse_cdc_header - parse the extra headers present in CDC devices * @hdr: the place to put the results of the parsing * @intf: the interface for which parsing is requested * @buffer: pointer to the extra headers to be parsed * @buflen: length of the extra headers * * This evaluates the extra headers present in CDC devices which * bind the interfaces for data and control and provide details * about the capabilities of the device. * * Return: number of descriptors parsed or -EINVAL * if the header is contradictory beyond salvage */ int cdc_parse_cdc_header(struct usb_cdc_parsed_header *hdr, struct usb_interface *intf, u8 *buffer, int buflen) { /* duplicates are ignored */ struct usb_cdc_union_desc *union_header = NULL; /* duplicates are not tolerated */ struct usb_cdc_header_desc *header = NULL; struct usb_cdc_ether_desc *ether = NULL; struct usb_cdc_mdlm_detail_desc *detail = NULL; struct usb_cdc_mdlm_desc *desc = NULL; unsigned int elength; int cnt = 0; memset(hdr, 0x00, sizeof(struct usb_cdc_parsed_header)); hdr->phonet_magic_present = false; while (buflen > 0) { elength = buffer[0]; if (!elength) { dev_err(&intf->dev, "skipping garbage byte\n"); elength = 1; goto next_desc; } if ((buflen < elength) || (elength < 3)) { dev_err(&intf->dev, "invalid descriptor buffer length\n"); break; } if (buffer[1] != USB_DT_CS_INTERFACE) { dev_err(&intf->dev, "skipping garbage\n"); goto next_desc; } switch (buffer[2]) { case USB_CDC_UNION_TYPE: /* we've found it */ if (elength < sizeof(struct usb_cdc_union_desc)) goto next_desc; if (union_header) { dev_err(&intf->dev, "More than one union descriptor, skipping ...\n"); goto next_desc; } union_header = (struct usb_cdc_union_desc *)buffer; break; case USB_CDC_COUNTRY_TYPE: if (elength < sizeof(struct usb_cdc_country_functional_desc)) goto next_desc; hdr->usb_cdc_country_functional_desc = (struct usb_cdc_country_functional_desc *)buffer; break; case USB_CDC_HEADER_TYPE: if (elength != sizeof(struct usb_cdc_header_desc)) goto next_desc; if (header) return -EINVAL; header = (struct usb_cdc_header_desc *)buffer; break; case USB_CDC_ACM_TYPE: if (elength < sizeof(struct usb_cdc_acm_descriptor)) goto next_desc; hdr->usb_cdc_acm_descriptor = (struct usb_cdc_acm_descriptor *)buffer; break; case USB_CDC_ETHERNET_TYPE: if (elength != sizeof(struct usb_cdc_ether_desc)) goto next_desc; if (ether) return -EINVAL; ether = (struct usb_cdc_ether_desc *)buffer; break; case USB_CDC_CALL_MANAGEMENT_TYPE: if (elength < sizeof(struct usb_cdc_call_mgmt_descriptor)) goto next_desc; hdr->usb_cdc_call_mgmt_descriptor = (struct usb_cdc_call_mgmt_descriptor *)buffer; break; case USB_CDC_DMM_TYPE: if (elength < sizeof(struct usb_cdc_dmm_desc)) goto next_desc; hdr->usb_cdc_dmm_desc = (struct usb_cdc_dmm_desc *)buffer; break; case USB_CDC_MDLM_TYPE: if (elength < sizeof(struct usb_cdc_mdlm_desc)) goto next_desc; if (desc) return -EINVAL; desc = (struct usb_cdc_mdlm_desc *)buffer; break; case USB_CDC_MDLM_DETAIL_TYPE: if (elength < sizeof(struct usb_cdc_mdlm_detail_desc)) goto next_desc; if (detail) return -EINVAL; detail = (struct usb_cdc_mdlm_detail_desc *)buffer; break; case USB_CDC_NCM_TYPE: if (elength < sizeof(struct usb_cdc_ncm_desc)) goto next_desc; hdr->usb_cdc_ncm_desc = (struct usb_cdc_ncm_desc *)buffer; break; case USB_CDC_MBIM_TYPE: if (elength < sizeof(struct usb_cdc_mbim_desc)) goto next_desc; hdr->usb_cdc_mbim_desc = (struct usb_cdc_mbim_desc *)buffer; break; case USB_CDC_MBIM_EXTENDED_TYPE: if (elength < sizeof(struct usb_cdc_mbim_extended_desc)) goto next_desc; hdr->usb_cdc_mbim_extended_desc = (struct usb_cdc_mbim_extended_desc *)buffer; break; case CDC_PHONET_MAGIC_NUMBER: hdr->phonet_magic_present = true; break; default: /* * there are LOTS more CDC descriptors that * could legitimately be found here. */ dev_dbg(&intf->dev, "Ignoring descriptor: type %02x, length %ud\n", buffer[2], elength); goto next_desc; } cnt++; next_desc: buflen -= elength; buffer += elength; } hdr->usb_cdc_union_desc = union_header; hdr->usb_cdc_header_desc = header; hdr->usb_cdc_mdlm_detail_desc = detail; hdr->usb_cdc_mdlm_desc = desc; hdr->usb_cdc_ether_desc = ether; return cnt; } EXPORT_SYMBOL(cdc_parse_cdc_header); |
| 3 3 3 3 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 | // SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2019 Facebook */ #include <linux/rculist.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/types.h> #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf.h> #include <linux/btf_ids.h> #include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> #include <linux/rcupdate_trace.h> DEFINE_BPF_STORAGE_CACHE(sk_cache); static struct bpf_local_storage_data * bpf_sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_map *smap; sk_storage = rcu_dereference_check(sk->sk_bpf_storage, bpf_rcu_lock_held()); if (!sk_storage) return NULL; smap = (struct bpf_local_storage_map *)map; return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int bpf_sk_storage_del(struct sock *sk, struct bpf_map *map) { struct bpf_local_storage_data *sdata; sdata = bpf_sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; return bpf_selem_unlink(SELEM(sdata)); } /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { struct bpf_local_storage *sk_storage; u32 uncharge; rcu_read_lock_dont_migrate(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) goto out; uncharge = bpf_local_storage_destroy(sk_storage); if (uncharge) atomic_sub(uncharge, &sk->sk_omem_alloc); out: rcu_read_unlock_migrate(); } static void bpf_sk_storage_map_free(struct bpf_map *map) { bpf_local_storage_map_free(map, &sk_cache); } static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) { return bpf_local_storage_map_alloc(attr, &sk_cache); } static int notsupp_get_next_key(struct bpf_map *map, void *key, void *next_key) { return -ENOTSUPP; } static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_sk_storage_lookup(sock->sk, map, true); sockfd_put(sock); return sdata ? sdata->data : NULL; } return ERR_PTR(err); } static long bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { sdata = bpf_local_storage_update( sock->sk, (struct bpf_local_storage_map *)map, value, map_flags, false); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } return err; } static long bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) { struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { err = bpf_sk_storage_del(sock->sk, map); sockfd_put(sock); return err; } return err; } static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, struct bpf_local_storage_map *smap, struct bpf_local_storage_elem *selem) { struct bpf_local_storage_elem *copy_selem; copy_selem = bpf_selem_alloc(smap, newsk, NULL, false); if (!copy_selem) return NULL; if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data, true); else copy_map_value(&smap->map, SDATA(copy_selem)->data, SDATA(selem)->data); return copy_selem; } int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { struct bpf_local_storage *new_sk_storage = NULL; struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; int ret = 0; rcu_read_lock_dont_migrate(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { struct bpf_local_storage_elem *copy_selem; struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); if (!smap || !(smap->map.map_flags & BPF_F_CLONE)) continue; /* Note that for lockless listeners adding new element * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ map = bpf_map_inc_not_zero(&smap->map); if (IS_ERR(map)) continue; copy_selem = bpf_sk_storage_clone_elem(newsk, smap, selem); if (!copy_selem) { ret = -ENOMEM; bpf_map_put(map); goto out; } if (new_sk_storage) { ret = bpf_selem_link_map(smap, new_sk_storage, copy_selem); if (ret) { bpf_selem_free(copy_selem, true); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); goto out; } bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { ret = bpf_local_storage_alloc(newsk, smap, copy_selem); if (ret) { bpf_selem_free(copy_selem, true); atomic_sub(smap->elem_size, &newsk->sk_omem_alloc); bpf_map_put(map); goto out; } new_sk_storage = rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } out: rcu_read_unlock_migrate(); /* In case of an error, don't free anything explicitly here, the * caller is responsible to call bpf_sk_storage_free. */ return ret; } BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { struct bpf_local_storage_data *sdata; WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = bpf_sk_storage_lookup(sk, map, true); if (sdata) return (unsigned long)sdata->data; if (flags == BPF_SK_STORAGE_GET_F_CREATE && /* Cannot add new elem to a going away sk. * Otherwise, the new elem may become a leak * (and also other memory issues during map * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { sdata = bpf_local_storage_update( sk, (struct bpf_local_storage_map *)map, value, BPF_NOEXIST, false); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ sock_put(sk); return IS_ERR(sdata) ? (unsigned long)NULL : (unsigned long)sdata->data; } return (unsigned long)NULL; } BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (!sk || !sk_fullsock(sk)) return -EINVAL; if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; err = bpf_sk_storage_del(sk, map); sock_put(sk); return err; } return -ENOENT; } static int bpf_sk_storage_charge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct sock *sk = (struct sock *)owner; int optmem_max; optmem_max = READ_ONCE(sock_net(sk)->core.sysctl_optmem_max); /* same check as in sock_kmalloc() */ if (size <= optmem_max && atomic_read(&sk->sk_omem_alloc) + size < optmem_max) { atomic_add(size, &sk->sk_omem_alloc); return 0; } return -ENOMEM; } static void bpf_sk_storage_uncharge(struct bpf_local_storage_map *smap, void *owner, u32 size) { struct sock *sk = owner; atomic_sub(size, &sk->sk_omem_alloc); } static struct bpf_local_storage __rcu ** bpf_sk_storage_ptr(void *owner) { struct sock *sk = owner; return &sk->sk_bpf_storage; } const struct bpf_map_ops sk_storage_map_ops = { .map_meta_equal = bpf_map_meta_equal, .map_alloc_check = bpf_local_storage_map_alloc_check, .map_alloc = bpf_sk_storage_map_alloc, .map_free = bpf_sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, .map_check_btf = bpf_local_storage_map_check_btf, .map_btf_id = &bpf_local_storage_map_btf_id[0], .map_local_storage_charge = bpf_sk_storage_charge, .map_local_storage_uncharge = bpf_sk_storage_uncharge, .map_owner_storage_ptr = bpf_sk_storage_ptr, .map_mem_usage = bpf_local_storage_map_mem_usage, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_get_cg_sock_proto = { .func = bpf_sk_storage_get, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_CTX, /* context is 'struct sock' */ .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; const struct bpf_func_proto bpf_sk_storage_delete_proto = { .func = bpf_sk_storage_delete, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog) { if (prog->aux->dst_prog) return false; /* Ensure the tracing program is not tracing * any bpf_sk_storage*() function and also * use the bpf_sk_storage_(get|delete) helper. */ switch (prog->expected_attach_type) { case BPF_TRACE_ITER: case BPF_TRACE_RAW_TP: /* bpf_sk_storage has no trace point */ return true; case BPF_TRACE_FENTRY: case BPF_TRACE_FEXIT: case BPF_TRACE_FSESSION: return !!strncmp(prog->aux->attach_func_name, "bpf_sk_storage", strlen("bpf_sk_storage")); default: return false; } return false; } BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return (unsigned long)NULL; return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags); } BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map, struct sock *, sk) { WARN_ON_ONCE(!bpf_rcu_lock_held()); if (in_hardirq() || in_nmi()) return -EPERM; return ____bpf_sk_storage_delete(map, sk); } const struct bpf_func_proto bpf_sk_storage_get_tracing_proto = { .func = bpf_sk_storage_get_tracing, .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, .allowed = bpf_sk_storage_tracing_allowed, }; const struct bpf_func_proto bpf_sk_storage_delete_tracing_proto = { .func = bpf_sk_storage_delete_tracing, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, .arg2_type = ARG_PTR_TO_BTF_ID_OR_NULL, .arg2_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_SOCK_COMMON], .allowed = bpf_sk_storage_tracing_allowed, }; struct bpf_sk_storage_diag { u32 nr_maps; struct bpf_map *maps[]; }; /* The reply will be like: * INET_DIAG_BPF_SK_STORAGES (nla_nest) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) * .... */ static int nla_value_size(u32 value_size) { /* SK_DIAG_BPF_STORAGE (nla_nest) * SK_DIAG_BPF_STORAGE_MAP_ID (nla_put_u32) * SK_DIAG_BPF_STORAGE_MAP_VALUE (nla_reserve_64bit) */ return nla_total_size(0) + nla_total_size(sizeof(u32)) + nla_total_size_64bit(value_size); } void bpf_sk_storage_diag_free(struct bpf_sk_storage_diag *diag) { u32 i; if (!diag) return; for (i = 0; i < diag->nr_maps; i++) bpf_map_put(diag->maps[i]); kfree(diag); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_free); static bool diag_check_dup(const struct bpf_sk_storage_diag *diag, const struct bpf_map *map) { u32 i; for (i = 0; i < diag->nr_maps; i++) { if (diag->maps[i] == map) return true; } return false; } struct bpf_sk_storage_diag * bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) { struct bpf_sk_storage_diag *diag; struct nlattr *nla; u32 nr_maps = 0; int rem, err; /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) return ERR_PTR(-EPERM); nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, nla_stgs, rem) { if (nla_len(nla) != sizeof(u32)) return ERR_PTR(-EINVAL); nr_maps++; } diag = kzalloc_flex(*diag, maps, nr_maps); if (!diag) return ERR_PTR(-ENOMEM); nla_for_each_nested_type(nla, SK_DIAG_BPF_STORAGE_REQ_MAP_FD, nla_stgs, rem) { int map_fd = nla_get_u32(nla); struct bpf_map *map = bpf_map_get(map_fd); if (IS_ERR(map)) { err = PTR_ERR(map); goto err_free; } if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) { bpf_map_put(map); err = -EINVAL; goto err_free; } if (diag_check_dup(diag, map)) { bpf_map_put(map); err = -EEXIST; goto err_free; } diag->maps[diag->nr_maps++] = map; } return diag; err_free: bpf_sk_storage_diag_free(diag); return ERR_PTR(err); } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); static int diag_get(struct bpf_local_storage_map *smap, struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; /* It cannot exceed max nlattr's payload */ BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) return -EMSGSIZE; if (nla_put_u32(skb, SK_DIAG_BPF_STORAGE_MAP_ID, smap->map.id)) goto errout; nla_value = nla_reserve_64bit(skb, SK_DIAG_BPF_STORAGE_MAP_VALUE, smap->map.value_size, SK_DIAG_BPF_STORAGE_PAD); if (!nla_value) goto errout; if (btf_record_has_field(smap->map.record, BPF_SPIN_LOCK)) copy_map_value_locked(&smap->map, nla_data(nla_value), sdata->data, true); else copy_map_value(&smap->map, nla_data(nla_value), sdata->data); check_and_init_map_value(&smap->map, nla_data(nla_value)); nla_nest_end(skb, nla_stg); return 0; errout: nla_nest_cancel(skb, nla_stg); return -EMSGSIZE; } static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { smap = rcu_dereference(SDATA(selem)->smap); if (!smap) continue; diag_size += nla_value_size(smap->map.value_size); if (nla_stgs && diag_get(smap, SDATA(selem), skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, struct sock *sk, struct sk_buff *skb, int stg_array_type, unsigned int *res_diag_size) { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); struct bpf_local_storage *sk_storage; struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; u32 i; *res_diag_size = 0; /* No map has been specified. Dump all. */ if (!diag->nr_maps) return bpf_sk_storage_diag_put_all(sk, skb, stg_array_type, res_diag_size); rcu_read_lock(); sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage || hlist_empty(&sk_storage->list)) { rcu_read_unlock(); return 0; } nla_stgs = nla_nest_start(skb, stg_array_type); if (!nla_stgs) /* Continue to learn diag_size */ err = -EMSGSIZE; saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { sdata = bpf_local_storage_lookup(sk_storage, (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) continue; diag_size += nla_value_size(diag->maps[i]->value_size); if (nla_stgs && diag_get((struct bpf_local_storage_map *)diag->maps[i], sdata, skb)) /* Continue to learn diag_size */ err = -EMSGSIZE; } rcu_read_unlock(); if (nla_stgs) { if (saved_len == skb->len) nla_nest_cancel(skb, nla_stgs); else nla_nest_end(skb, nla_stgs); } if (diag_size == nla_total_size(0)) { *res_diag_size = 0; return 0; } *res_diag_size = diag_size; return err; } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_put); struct bpf_iter_seq_sk_storage_map_info { struct bpf_map *map; unsigned int bucket_id; unsigned skip_elems; }; static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, struct bpf_local_storage_elem *prev_selem) __acquires(RCU) __releases(RCU) { struct bpf_local_storage *sk_storage; struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; struct bpf_local_storage_map_bucket *b; smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; /* try to find next selem in the same bucket */ selem = prev_selem; count = 0; while (selem) { selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; rcu_read_unlock(); skip_elems = 0; break; } sk_storage = rcu_dereference(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; } count++; } for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; rcu_read_lock(); count = 0; hlist_for_each_entry_rcu(selem, &b->list, map_node) { sk_storage = rcu_dereference(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; return selem; } count++; } rcu_read_unlock(); skip_elems = 0; } info->bucket_id = i; info->skip_elems = 0; return NULL; } static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) return NULL; if (*pos == 0) ++*pos; return selem; } static void *bpf_sk_storage_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; ++*pos; ++info->skip_elems; return bpf_sk_storage_map_seq_find_next(seq->private, v); } struct bpf_iter__bpf_sk_storage_map { __bpf_md_ptr(struct bpf_iter_meta *, meta); __bpf_md_ptr(struct bpf_map *, map); __bpf_md_ptr(struct sock *, sk); __bpf_md_ptr(void *, value); }; DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, struct bpf_map *map, struct sock *sk, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; meta.seq = seq; prog = bpf_iter_get_info(&meta, selem == NULL); if (prog) { ctx.meta = &meta; ctx.map = info->map; if (selem) { sk_storage = rcu_dereference(selem->local_storage); ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); } return ret; } static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) { return __bpf_sk_storage_map_seq_show(seq, v); } static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) __releases(RCU) { if (!v) (void)__bpf_sk_storage_map_seq_show(seq, v); else rcu_read_unlock(); } static int bpf_iter_init_sk_storage_map(void *priv_data, struct bpf_iter_aux_info *aux) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_inc_with_uref(aux->map); seq_info->map = aux->map; return 0; } static void bpf_iter_fini_sk_storage_map(void *priv_data) { struct bpf_iter_seq_sk_storage_map_info *seq_info = priv_data; bpf_map_put_with_uref(seq_info->map); } static int bpf_iter_attach_map(struct bpf_prog *prog, union bpf_iter_link_info *linfo, struct bpf_iter_aux_info *aux) { struct bpf_map *map; int err = -EINVAL; if (!linfo->map.map_fd) return -EBADF; map = bpf_map_get_with_uref(linfo->map.map_fd); if (IS_ERR(map)) return PTR_ERR(map); if (map->map_type != BPF_MAP_TYPE_SK_STORAGE) goto put_map; if (prog->aux->max_rdwr_access > map->value_size) { err = -EACCES; goto put_map; } aux->map = map; return 0; put_map: bpf_map_put_with_uref(map); return err; } static void bpf_iter_detach_map(struct bpf_iter_aux_info *aux) { bpf_map_put_with_uref(aux->map); } static const struct seq_operations bpf_sk_storage_map_seq_ops = { .start = bpf_sk_storage_map_seq_start, .next = bpf_sk_storage_map_seq_next, .stop = bpf_sk_storage_map_seq_stop, .show = bpf_sk_storage_map_seq_show, }; static const struct bpf_iter_seq_info iter_seq_info = { .seq_ops = &bpf_sk_storage_map_seq_ops, .init_seq_private = bpf_iter_init_sk_storage_map, .fini_seq_private = bpf_iter_fini_sk_storage_map, .seq_priv_size = sizeof(struct bpf_iter_seq_sk_storage_map_info), }; static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, .show_fdinfo = bpf_iter_map_show_fdinfo, .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), PTR_TO_BTF_ID_OR_NULL }, { offsetof(struct bpf_iter__bpf_sk_storage_map, value), PTR_TO_BUF | PTR_MAYBE_NULL }, }, .seq_info = &iter_seq_info, }; static int __init bpf_sk_storage_map_iter_init(void) { bpf_sk_storage_map_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_SOCK]; return bpf_iter_reg_target(&bpf_sk_storage_map_reg_info); } late_initcall(bpf_sk_storage_map_iter_init); |
| 2 2 2 2 2 2 2 2 316 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 | // SPDX-License-Identifier: GPL-2.0+ /* * Universal/legacy driver for 8250/16550-type serial ports * * Based on drivers/char/serial.c, by Linus Torvalds, Theodore Ts'o. * * Copyright (C) 2001 Russell King. * * Supports: * early_serial_setup() ports * userspace-configurable "phantom" ports * serial8250_register_8250_port() ports */ #include <linux/acpi.h> #include <linux/hashtable.h> #include <linux/module.h> #include <linux/moduleparam.h> #include <linux/ioport.h> #include <linux/init.h> #include <linux/console.h> #include <linux/sysrq.h> #include <linux/delay.h> #include <linux/platform_device.h> #include <linux/pm_runtime.h> #include <linux/tty.h> #include <linux/ratelimit.h> #include <linux/tty_flip.h> #include <linux/serial.h> #include <linux/serial_8250.h> #include <linux/nmi.h> #include <linux/mutex.h> #include <linux/slab.h> #include <linux/string_helpers.h> #include <linux/uaccess.h> #include <linux/io.h> #include <asm/irq.h> #include "8250.h" #define PASS_LIMIT 512 struct irq_info { struct hlist_node node; int irq; spinlock_t lock; /* Protects list not the hash */ struct list_head *head; }; #define IRQ_HASH_BITS 5 /* Can be adjusted later */ static DEFINE_HASHTABLE(irq_lists, IRQ_HASH_BITS); static DEFINE_MUTEX(hash_mutex); /* Used to walk the hash */ static bool skip_txen_test; module_param(skip_txen_test, bool, 0644); MODULE_PARM_DESC(skip_txen_test, "Skip checking for the TXEN bug at init time"); /* * This is the serial driver's interrupt routine. * * Arjan thinks the old way was overly complex, so it got simplified. * Alan disagrees, saying that need the complexity to handle the weird * nature of ISA shared interrupts. (This is a special exception.) * * In order to handle ISA shared interrupts properly, we need to check * that all ports have been serviced, and therefore the ISA interrupt * line has been de-asserted. * * This means we need to loop through all ports. checking that they * don't have an interrupt pending. */ static irqreturn_t serial8250_interrupt(int irq, void *dev_id) { struct irq_info *i = dev_id; struct list_head *l, *end = NULL; int pass_counter = 0, handled = 0; guard(spinlock)(&i->lock); l = i->head; do { struct uart_8250_port *up = list_entry(l, struct uart_8250_port, list); struct uart_port *port = &up->port; if (port->handle_irq(port)) { handled = 1; end = NULL; } else if (end == NULL) end = l; l = l->next; if (l == i->head && pass_counter++ > PASS_LIMIT) break; } while (l != end); return IRQ_RETVAL(handled); } /* * To support ISA shared interrupts, we need to have one interrupt * handler that ensures that the IRQ line has been deasserted * before returning. Failing to do this will result in the IRQ * line being stuck active, and, since ISA irqs are edge triggered, * no more IRQs will be seen. */ static void serial_do_unlink(struct irq_info *i, struct uart_8250_port *up) { spin_lock_irq(&i->lock); if (!list_empty(i->head)) { if (i->head == &up->list) i->head = i->head->next; list_del(&up->list); } else { BUG_ON(i->head != &up->list); i->head = NULL; } spin_unlock_irq(&i->lock); /* List empty so throw away the hash node */ if (i->head == NULL) { hlist_del(&i->node); kfree(i); } } /* * Either: * - find the corresponding info in the hashtable and return it, or * - allocate a new one, add it to the hashtable and return it. */ static struct irq_info *serial_get_or_create_irq_info(const struct uart_8250_port *up) { struct irq_info *i; guard(mutex)(&hash_mutex); hash_for_each_possible(irq_lists, i, node, up->port.irq) if (i->irq == up->port.irq) return i; i = kzalloc_obj(*i); if (i == NULL) return ERR_PTR(-ENOMEM); spin_lock_init(&i->lock); i->irq = up->port.irq; hash_add(irq_lists, &i->node, i->irq); return i; } static int serial_link_irq_chain(struct uart_8250_port *up) { struct irq_info *i; int ret; i = serial_get_or_create_irq_info(up); if (IS_ERR(i)) return PTR_ERR(i); scoped_guard(spinlock_irq, &i->lock) { if (i->head) { list_add(&up->list, i->head); return 0; } INIT_LIST_HEAD(&up->list); i->head = &up->list; } ret = request_irq(up->port.irq, serial8250_interrupt, up->port.irqflags, up->port.name, i); if (ret < 0) serial_do_unlink(i, up); return ret; } static void serial_unlink_irq_chain(struct uart_8250_port *up) { struct irq_info *i; guard(mutex)(&hash_mutex); hash_for_each_possible(irq_lists, i, node, up->port.irq) if (i->irq == up->port.irq) { if (WARN_ON(i->head == NULL)) return; if (list_empty(i->head)) free_irq(up->port.irq, i); serial_do_unlink(i, up); return; } WARN_ON(1); } /* * This function is used to handle ports that do not have an * interrupt. This doesn't work very well for 16450's, but gives * barely passable results for a 16550A. (Although at the expense * of much CPU overhead). */ static void serial8250_timeout(struct timer_list *t) { struct uart_8250_port *up = timer_container_of(up, t, timer); up->port.handle_irq(&up->port); mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port)); } static void serial8250_backup_timeout(struct timer_list *t) { struct uart_8250_port *up = timer_container_of(up, t, timer); unsigned int iir, ier = 0, lsr; unsigned long flags; uart_port_lock_irqsave(&up->port, &flags); /* * Must disable interrupts or else we risk racing with the interrupt * based handler. */ if (up->port.irq) { ier = serial_in(up, UART_IER); serial_out(up, UART_IER, 0); } iir = serial_in(up, UART_IIR); /* * This should be a safe test for anyone who doesn't trust the * IIR bits on their UART, but it's specifically designed for * the "Diva" UART used on the management processor on many HP * ia64 and parisc boxes. */ lsr = serial_lsr_in(up); if ((iir & UART_IIR_NO_INT) && (up->ier & UART_IER_THRI) && (!kfifo_is_empty(&up->port.state->port.xmit_fifo) || up->port.x_char) && (lsr & UART_LSR_THRE)) { iir &= ~(UART_IIR_ID | UART_IIR_NO_INT); iir |= UART_IIR_THRI; } if (!(iir & UART_IIR_NO_INT)) serial8250_tx_chars(up); if (up->port.irq) serial_out(up, UART_IER, ier); uart_port_unlock_irqrestore(&up->port, flags); /* Standard timer interval plus 0.2s to keep the port running */ mod_timer(&up->timer, jiffies + uart_poll_timeout(&up->port) + HZ / 5); } static void univ8250_setup_timer(struct uart_8250_port *up) { struct uart_port *port = &up->port; /* * The above check will only give an accurate result the first time * the port is opened so this value needs to be preserved. */ if (up->bugs & UART_BUG_THRE) { pr_debug("%s - using backup timer\n", port->name); up->timer.function = serial8250_backup_timeout; mod_timer(&up->timer, jiffies + uart_poll_timeout(port) + HZ / 5); } /* * If the "interrupt" for this port doesn't correspond with any * hardware interrupt, we use a timer-based system. The original * driver used to do this with IRQ0. */ if (!port->irq) mod_timer(&up->timer, jiffies + uart_poll_timeout(port)); } static int univ8250_setup_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; if (port->irq) return serial_link_irq_chain(up); return 0; } static void univ8250_release_irq(struct uart_8250_port *up) { struct uart_port *port = &up->port; timer_delete_sync(&up->timer); up->timer.function = serial8250_timeout; if (port->irq) serial_unlink_irq_chain(up); } const struct uart_ops *univ8250_port_base_ops; struct uart_ops univ8250_port_ops; static const struct uart_8250_ops univ8250_driver_ops = { .setup_irq = univ8250_setup_irq, .release_irq = univ8250_release_irq, .setup_timer = univ8250_setup_timer, }; static struct uart_8250_port serial8250_ports[UART_NR]; /** * serial8250_get_port - retrieve struct uart_8250_port * @line: serial line number * * This function retrieves struct uart_8250_port for the specific line. * This struct *must* *not* be used to perform a 8250 or serial core operation * which is not accessible otherwise. Its only purpose is to make the struct * accessible to the runtime-pm callbacks for context suspend/restore. * The lock assumption made here is none because runtime-pm suspend/resume * callbacks should not be invoked if there is any operation performed on the * port. */ struct uart_8250_port *serial8250_get_port(int line) { return &serial8250_ports[line]; } EXPORT_SYMBOL_GPL(serial8250_get_port); static inline void serial8250_apply_quirks(struct uart_8250_port *up) { up->port.quirks |= skip_txen_test ? UPQ_NO_TXEN_TEST : 0; } struct uart_8250_port *serial8250_setup_port(int index) { struct uart_8250_port *up; if (index >= UART_NR) return NULL; up = &serial8250_ports[index]; up->port.line = index; up->port.port_id = index; serial8250_init_port(up); if (!univ8250_port_base_ops) univ8250_port_base_ops = up->port.ops; up->port.ops = &univ8250_port_ops; timer_setup(&up->timer, serial8250_timeout, 0); up->ops = &univ8250_driver_ops; serial8250_set_defaults(up); return up; } void __init serial8250_register_ports(struct uart_driver *drv, struct device *dev) { int i; for (i = 0; i < nr_uarts; i++) { struct uart_8250_port *up = &serial8250_ports[i]; if (up->port.type == PORT_8250_CIR) continue; if (up->port.dev) continue; up->port.dev = dev; if (uart_console_registered(&up->port)) pm_runtime_get_sync(up->port.dev); serial8250_apply_quirks(up); uart_add_one_port(drv, &up->port); } } #ifdef CONFIG_SERIAL_8250_CONSOLE static void univ8250_console_write(struct console *co, const char *s, unsigned int count) { struct uart_8250_port *up = &serial8250_ports[co->index]; serial8250_console_write(up, s, count); } static int univ8250_console_setup(struct console *co, char *options) { struct uart_8250_port *up; struct uart_port *port; int retval, i; /* * Check whether an invalid uart number has been specified, and * if so, search for the first available port that does have * console support. */ if (co->index < 0 || co->index >= UART_NR) co->index = 0; /* * If the console is past the initial isa ports, init more ports up to * co->index as needed and increment nr_uarts accordingly. */ for (i = nr_uarts; i <= co->index; i++) { up = serial8250_setup_port(i); if (!up) return -ENODEV; nr_uarts++; } port = &serial8250_ports[co->index].port; /* link port to console */ uart_port_set_cons(port, co); retval = serial8250_console_setup(port, options, false); if (retval != 0) uart_port_set_cons(port, NULL); return retval; } static int univ8250_console_exit(struct console *co) { struct uart_port *port; port = &serial8250_ports[co->index].port; return serial8250_console_exit(port); } /** * univ8250_console_match - non-standard console matching * @co: registering console * @name: name from console command line * @idx: index from console command line * @options: ptr to option string from console command line * * Only attempts to match console command lines of the form: * console=uart[8250],io|mmio|mmio16|mmio32,<addr>[,<options>] * console=uart[8250],0x<addr>[,<options>] * This form is used to register an initial earlycon boot console and * replace it with the serial8250_console at 8250 driver init. * * Performs console setup for a match (as required by interface) * If no <options> are specified, then assume the h/w is already setup. * * Returns 0 if console matches; otherwise non-zero to use default matching */ static int univ8250_console_match(struct console *co, char *name, int idx, char *options) { char match[] = "uart"; /* 8250-specific earlycon name */ enum uart_iotype iotype; resource_size_t addr; int i; if (strncmp(name, match, 4) != 0) return -ENODEV; if (uart_parse_earlycon(options, &iotype, &addr, &options)) return -ENODEV; /* try to match the port specified on the command line */ for (i = 0; i < nr_uarts; i++) { struct uart_port *port = &serial8250_ports[i].port; if (port->iotype != iotype) continue; if ((iotype == UPIO_MEM || iotype == UPIO_MEM16 || iotype == UPIO_MEM32 || iotype == UPIO_MEM32BE) && (port->mapbase != addr)) continue; if (iotype == UPIO_PORT && port->iobase != addr) continue; co->index = i; uart_port_set_cons(port, co); return serial8250_console_setup(port, options, true); } return -ENODEV; } static struct console univ8250_console = { .name = "ttyS", .write = univ8250_console_write, .device = uart_console_device, .setup = univ8250_console_setup, .exit = univ8250_console_exit, .match = univ8250_console_match, .flags = CON_PRINTBUFFER | CON_ANYTIME, .index = -1, .data = &serial8250_reg, }; static int __init univ8250_console_init(void) { if (nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); register_console(&univ8250_console); return 0; } console_initcall(univ8250_console_init); #define SERIAL8250_CONSOLE (&univ8250_console) #else #define SERIAL8250_CONSOLE NULL #endif struct uart_driver serial8250_reg = { .owner = THIS_MODULE, .driver_name = "serial_8250", .dev_name = "ttyS", .major = TTY_MAJOR, .minor = 64, .cons = SERIAL8250_CONSOLE, }; /* * early_serial_setup - early registration for 8250 ports * * Setup an 8250 port structure prior to console initialisation. Use * after console initialisation will cause undefined behaviour. */ int __init early_serial_setup(struct uart_port *port) { struct uart_port *p; if (port->line >= ARRAY_SIZE(serial8250_ports) || nr_uarts == 0) return -ENODEV; serial8250_isa_init_ports(); p = &serial8250_ports[port->line].port; p->iobase = port->iobase; p->membase = port->membase; p->irq = port->irq; p->irqflags = port->irqflags; p->uartclk = port->uartclk; p->fifosize = port->fifosize; p->regshift = port->regshift; p->iotype = port->iotype; p->flags = port->flags; p->mapbase = port->mapbase; p->mapsize = port->mapsize; p->private_data = port->private_data; p->type = port->type; p->line = port->line; serial8250_set_defaults(up_to_u8250p(p)); if (port->serial_in) p->serial_in = port->serial_in; if (port->serial_out) p->serial_out = port->serial_out; if (port->handle_irq) p->handle_irq = port->handle_irq; return 0; } /** * serial8250_suspend_port - suspend one serial port * @line: serial line number * * Suspend one serial port. */ void serial8250_suspend_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; if (!console_suspend_enabled && uart_console(port) && port->type != PORT_8250) { unsigned char canary = 0xa5; serial_out(up, UART_SCR, canary); if (serial_in(up, UART_SCR) == canary) up->canary = canary; } uart_suspend_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_suspend_port); /** * serial8250_resume_port - resume one serial port * @line: serial line number * * Resume one serial port. */ void serial8250_resume_port(int line) { struct uart_8250_port *up = &serial8250_ports[line]; struct uart_port *port = &up->port; up->canary = 0; if (up->capabilities & UART_NATSEMI) { /* Ensure it's still in high speed mode */ serial_port_out(port, UART_LCR, 0xE0); ns16550a_goto_highspeed(up); serial_port_out(port, UART_LCR, 0); port->uartclk = 921600*16; } uart_resume_port(&serial8250_reg, port); } EXPORT_SYMBOL(serial8250_resume_port); /* * serial8250_register_8250_port and serial8250_unregister_port allows for * 16x50 serial ports to be configured at run-time, to support PCMCIA * modems and PCI multiport cards. */ static DEFINE_MUTEX(serial_mutex); static struct uart_8250_port *serial8250_find_match_or_unused(const struct uart_port *port) { int i; /* * First, find a port entry which matches. */ for (i = 0; i < nr_uarts; i++) if (uart_match_port(&serial8250_ports[i].port, port)) return &serial8250_ports[i]; /* try line number first if still available */ i = port->line; if (i < nr_uarts && serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * We didn't find a matching entry, so look for the first * free entry. We look for one which hasn't been previously * used (indicated by zero iobase). */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN && serial8250_ports[i].port.iobase == 0) return &serial8250_ports[i]; /* * That also failed. Last resort is to find any entry which * doesn't have a real port associated with it. */ for (i = 0; i < nr_uarts; i++) if (serial8250_ports[i].port.type == PORT_UNKNOWN) return &serial8250_ports[i]; return NULL; } static void serial_8250_overrun_backoff_work(struct work_struct *work) { struct uart_8250_port *up = container_of(to_delayed_work(work), struct uart_8250_port, overrun_backoff); guard(uart_port_lock_irqsave)(&up->port); up->ier |= UART_IER_RLSI | UART_IER_RDI; serial_out(up, UART_IER, up->ier); } /** * serial8250_register_8250_port - register a serial port * @up: serial port template * * Configure the serial port specified by the request. If the * port exists and is in use, it is hung up and unregistered * first. * * The port is then probed and if necessary the IRQ is autodetected * If this fails an error is returned. * * On success the port is ready to use and the line number is returned. */ int serial8250_register_8250_port(const struct uart_8250_port *up) { struct uart_8250_port *uart; bool cons_flow; int ret; if (up->port.uartclk == 0) return -EINVAL; guard(mutex)(&serial_mutex); uart = serial8250_find_match_or_unused(&up->port); if (!uart) { /* * If the port is past the initial isa ports, initialize a new * port and increment nr_uarts accordingly. */ uart = serial8250_setup_port(nr_uarts); if (!uart) return -ENOSPC; nr_uarts++; } /* Check if it is CIR already. We check this below again, see there why. */ if (uart->port.type == PORT_8250_CIR) return -ENODEV; /* Preserve specified console flow control. */ cons_flow = uart_cons_flow_enabled(&uart->port); if (uart->port.dev) uart_remove_one_port(&serial8250_reg, &uart->port); uart->port.ctrl_id = up->port.ctrl_id; uart->port.port_id = up->port.port_id; uart->port.iobase = up->port.iobase; uart->port.membase = up->port.membase; uart->port.irq = up->port.irq; uart->port.irqflags = up->port.irqflags; uart->port.uartclk = up->port.uartclk; uart->port.fifosize = up->port.fifosize; uart->port.regshift = up->port.regshift; uart->port.iotype = up->port.iotype; uart->port.flags = up->port.flags | UPF_BOOT_AUTOCONF; uart->bugs = up->bugs; uart->port.mapbase = up->port.mapbase; uart->port.mapsize = up->port.mapsize; uart->port.private_data = up->port.private_data; uart->tx_loadsz = up->tx_loadsz; uart->capabilities = up->capabilities; uart->port.throttle = up->port.throttle; uart->port.unthrottle = up->port.unthrottle; uart->port.rs485_config = up->port.rs485_config; uart->port.rs485_supported = up->port.rs485_supported; uart->port.rs485 = up->port.rs485; uart->rs485_start_tx = up->rs485_start_tx; uart->rs485_stop_tx = up->rs485_stop_tx; uart->lsr_save_mask = up->lsr_save_mask; uart->dma = up->dma; uart_set_cons_flow_enabled(&uart->port, uart_cons_flow_enabled(&up->port) | cons_flow); /* Take tx_loadsz from fifosize if it wasn't set separately */ if (uart->port.fifosize && !uart->tx_loadsz) uart->tx_loadsz = uart->port.fifosize; if (up->port.dev) { uart->port.dev = up->port.dev; ret = uart_get_rs485_mode(&uart->port); if (ret) goto err; } if (up->port.flags & UPF_FIXED_TYPE) uart->port.type = up->port.type; /* * Only call mctrl_gpio_init(), if the device has no ACPI * companion device */ if (uart->port.dev && !has_acpi_companion(uart->port.dev)) { struct mctrl_gpios *gpios = mctrl_gpio_init(&uart->port, 0); if (IS_ERR(gpios)) { ret = PTR_ERR(gpios); goto err; } else { uart->gpios = gpios; } } serial8250_set_defaults(uart); /* Possibly override default I/O functions. */ if (up->port.serial_in) uart->port.serial_in = up->port.serial_in; if (up->port.serial_out) uart->port.serial_out = up->port.serial_out; if (up->port.handle_irq) uart->port.handle_irq = up->port.handle_irq; /* Possibly override set_termios call */ if (up->port.set_termios) uart->port.set_termios = up->port.set_termios; if (up->port.set_ldisc) uart->port.set_ldisc = up->port.set_ldisc; if (up->port.get_mctrl) uart->port.get_mctrl = up->port.get_mctrl; if (up->port.set_mctrl) uart->port.set_mctrl = up->port.set_mctrl; if (up->port.get_divisor) uart->port.get_divisor = up->port.get_divisor; if (up->port.set_divisor) uart->port.set_divisor = up->port.set_divisor; if (up->port.startup) uart->port.startup = up->port.startup; if (up->port.shutdown) uart->port.shutdown = up->port.shutdown; if (up->port.pm) uart->port.pm = up->port.pm; if (up->port.handle_break) uart->port.handle_break = up->port.handle_break; if (up->dl_read) uart->dl_read = up->dl_read; if (up->dl_write) uart->dl_write = up->dl_write; /* Check the type (again)! It might have changed by the port.type assignment above. */ if (uart->port.type != PORT_8250_CIR) { if (uart_console_registered(&uart->port)) pm_runtime_get_sync(uart->port.dev); if (serial8250_isa_config != NULL) serial8250_isa_config(0, &uart->port, &uart->capabilities); serial8250_apply_quirks(uart); ret = uart_add_one_port(&serial8250_reg, &uart->port); if (ret) goto err; ret = uart->port.line; } else { dev_info(uart->port.dev, "skipping CIR port at 0x%lx / 0x%llx, IRQ %d\n", uart->port.iobase, (unsigned long long)uart->port.mapbase, uart->port.irq); ret = 0; } if (!uart->lsr_save_mask) uart->lsr_save_mask = LSR_SAVE_FLAGS; /* Use default LSR mask */ /* Initialise interrupt backoff work if required */ if (up->overrun_backoff_time_ms > 0) { uart->overrun_backoff_time_ms = up->overrun_backoff_time_ms; INIT_DELAYED_WORK(&uart->overrun_backoff, serial_8250_overrun_backoff_work); } else { uart->overrun_backoff_time_ms = 0; } return ret; err: uart->port.dev = NULL; return ret; } EXPORT_SYMBOL(serial8250_register_8250_port); /** * serial8250_unregister_port - remove a 16x50 serial port at runtime * @line: serial line number * * Remove one serial port. This may not be called from interrupt * context. We hand the port back to the our control. */ void serial8250_unregister_port(int line) { struct uart_8250_port *uart = &serial8250_ports[line]; guard(mutex)(&serial_mutex); if (uart->em485) { guard(uart_port_lock_irqsave)(&uart->port); serial8250_em485_destroy(uart); } uart_remove_one_port(&serial8250_reg, &uart->port); if (serial8250_isa_devs) { uart->port.flags &= ~UPF_BOOT_AUTOCONF; uart->port.type = PORT_UNKNOWN; uart->port.dev = &serial8250_isa_devs->dev; uart->port.port_id = line; uart->capabilities = 0; serial8250_init_port(uart); serial8250_apply_quirks(uart); uart_add_one_port(&serial8250_reg, &uart->port); } else { uart->port.dev = NULL; } } EXPORT_SYMBOL(serial8250_unregister_port); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("Generic 8250/16x50 serial driver"); |
| 23 142 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* fs/ internal definitions * * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ struct super_block; struct file_system_type; struct iomap; struct iomap_ops; struct linux_binprm; struct path; struct mount; struct shrink_control; struct fs_context; struct pipe_inode_info; struct iov_iter; struct mnt_idmap; struct ns_common; /* * block/bdev.c */ #ifdef CONFIG_BLOCK extern void __init bdev_cache_init(void); #else static inline void bdev_cache_init(void) { } #endif /* CONFIG_BLOCK */ /* * buffer.c */ int __block_write_begin_int(struct folio *folio, loff_t pos, unsigned len, get_block_t *get_block, const struct iomap *iomap); /* * char_dev.c */ extern void __init chrdev_init(void); /* * fs_context.c */ extern int parse_monolithic_mount_data(struct fs_context *, void *); extern void vfs_clean_context(struct fs_context *fc); extern int finish_clean_context(struct fs_context *fc); /* * namei.c */ extern int filename_lookup(int dfd, struct filename *name, unsigned flags, struct path *path, const struct path *root); int filename_rmdir(int dfd, struct filename *name); int filename_unlinkat(int dfd, struct filename *name); int may_linkat(struct mnt_idmap *idmap, const struct path *link); int filename_renameat2(int olddfd, struct filename *oldname, int newdfd, struct filename *newname, unsigned int flags); int filename_mkdirat(int dfd, struct filename *name, umode_t mode); int filename_mknodat(int dfd, struct filename *name, umode_t mode, unsigned int dev); int filename_symlinkat(struct filename *from, int newdfd, struct filename *to); int filename_linkat(int olddfd, struct filename *old, int newdfd, struct filename *new, int flags); int vfs_tmpfile(struct mnt_idmap *idmap, const struct path *parentpath, struct file *file, umode_t mode); struct dentry *d_hash_and_lookup(struct dentry *, struct qstr *); struct dentry *start_dirop(struct dentry *parent, struct qstr *name, unsigned int lookup_flags); int lookup_noperm_common(struct qstr *qname, struct dentry *base); void __init filename_init(void); /* * namespace.c */ extern struct vfsmount *lookup_mnt(const struct path *); extern int finish_automount(struct vfsmount *, const struct path *); extern int sb_prepare_remount_readonly(struct super_block *); extern void __init mnt_init(void); int mnt_get_write_access_file(struct file *file); void mnt_put_write_access_file(struct file *file); extern void dissolve_on_fput(struct vfsmount *); extern bool may_mount(void); int path_mount(const char *dev_name, const struct path *path, const char *type_page, unsigned long flags, void *data_page); int path_umount(const struct path *path, int flags); int path_pivot_root(struct path *new, struct path *old); int show_path(struct seq_file *m, struct dentry *root); /* * fs_struct.c */ extern void chroot_fs_refs(const struct path *, const struct path *); /* * file_table.c */ struct file *alloc_empty_file(int flags, const struct cred *cred); struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred); struct file *alloc_empty_backing_file(int flags, const struct cred *cred, const struct file *user_file); void backing_file_set_user_path(struct file *f, const struct path *path); static inline void file_put_write_access(struct file *file) { put_write_access(file->f_inode); mnt_put_write_access(file->f_path.mnt); if (unlikely(file->f_mode & FMODE_BACKING)) mnt_put_write_access(backing_file_user_path(file)->mnt); } static inline void put_file_access(struct file *file) { if ((file->f_mode & (FMODE_READ | FMODE_WRITE)) == FMODE_READ) { i_readcount_dec(file->f_inode); } else if (file->f_mode & FMODE_WRITER) { file_put_write_access(file); } } void fput_close_sync(struct file *); void fput_close(struct file *); /* * super.c */ extern int reconfigure_super(struct fs_context *); extern bool super_trylock_shared(struct super_block *sb); struct super_block *user_get_super(dev_t, bool excl); void put_super(struct super_block *sb); extern bool mount_capable(struct fs_context *); /* * Prepare superblock for changing its read-only state (i.e., either remount * read-write superblock read-only or vice versa). After this function returns * mnt_is_readonly() will return true for any mount of the superblock if its * caller is able to observe any changes done by the remount. This holds until * sb_end_ro_state_change() is called. */ static inline void sb_start_ro_state_change(struct super_block *sb) { WRITE_ONCE(sb->s_readonly_remount, 1); /* * For RO->RW transition, the barrier pairs with the barrier in * mnt_is_readonly() making sure if mnt_is_readonly() sees SB_RDONLY * cleared, it will see s_readonly_remount set. * For RW->RO transition, the barrier pairs with the barrier in * mnt_get_write_access() before the mnt_is_readonly() check. * The barrier makes sure if mnt_get_write_access() sees MNT_WRITE_HOLD * already cleared, it will see s_readonly_remount set. */ smp_wmb(); } /* * Ends section changing read-only state of the superblock. After this function * returns if mnt_is_readonly() returns false, the caller will be able to * observe all the changes remount did to the superblock. */ static inline void sb_end_ro_state_change(struct super_block *sb) { /* * This barrier provides release semantics that pairs with * the smp_rmb() acquire semantics in mnt_is_readonly(). * This barrier pair ensure that when mnt_is_readonly() sees * 0 for sb->s_readonly_remount, it will also see all the * preceding flag changes that were made during the RO state * change. */ smp_wmb(); WRITE_ONCE(sb->s_readonly_remount, 0); } /* * open.c */ struct open_flags { int open_flag; umode_t mode; int acc_mode; int intent; int lookup_flags; }; extern struct file *do_file_open(int dfd, struct filename *pathname, const struct open_flags *op); extern struct file *do_file_open_root(const struct path *, const char *, const struct open_flags *); extern struct open_how build_open_how(int flags, umode_t mode); extern int build_open_flags(const struct open_how *how, struct open_flags *op); struct file *file_close_fd_locked(struct files_struct *files, unsigned fd); int do_ftruncate(struct file *file, loff_t length, unsigned int flags); int chmod_common(const struct path *path, umode_t mode); int do_fchownat(int dfd, const char __user *filename, uid_t user, gid_t group, int flag); int chown_common(const struct path *path, uid_t user, gid_t group); extern int vfs_open(const struct path *, struct file *); /* * inode.c */ extern long prune_icache_sb(struct super_block *sb, struct shrink_control *sc); int dentry_needs_remove_privs(struct mnt_idmap *, struct dentry *dentry); bool in_group_or_capable(struct mnt_idmap *idmap, const struct inode *inode, vfsgid_t vfsgid); /* * fs-writeback.c */ long get_nr_dirty_inodes(void); bool sync_lazytime(struct inode *inode); /* * dcache.c */ extern int d_set_mounted(struct dentry *dentry); extern long prune_dcache_sb(struct super_block *sb, struct shrink_control *sc); extern struct dentry *d_alloc_cursor(struct dentry *); extern struct dentry * d_alloc_pseudo(struct super_block *, const struct qstr *); extern char *simple_dname(struct dentry *, char *, int); extern void dput_to_list(struct dentry *, struct list_head *); extern void shrink_dentry_list(struct list_head *); extern void shrink_dcache_for_umount(struct super_block *); extern struct dentry *__d_lookup(const struct dentry *, const struct qstr *); extern struct dentry *__d_lookup_rcu(const struct dentry *parent, const struct qstr *name, unsigned *seq); /* * pipe.c */ extern const struct file_operations pipefifo_fops; /* * fs_pin.c */ extern void group_pin_kill(struct hlist_head *p); extern void mnt_pin_kill(struct mount *m); /* * fs/nsfs.c */ extern const struct dentry_operations ns_dentry_operations; int open_namespace(struct ns_common *ns); struct file *open_namespace_file(struct ns_common *ns); /* * fs/stat.c: */ int do_statx(int dfd, struct filename *filename, unsigned int flags, unsigned int mask, struct statx __user *buffer); int do_statx_fd(int fd, unsigned int flags, unsigned int mask, struct statx __user *buffer); /* * fs/splice.c: */ ssize_t splice_file_to_pipe(struct file *in, struct pipe_inode_info *opipe, loff_t *offset, size_t len, unsigned int flags); /* * fs/xattr.c: */ struct xattr_name { char name[XATTR_NAME_MAX + 1]; }; struct kernel_xattr_ctx { /* Value of attribute */ union { const void __user *cvalue; void __user *value; }; void *kvalue; size_t size; /* Attribute name */ struct xattr_name *kname; unsigned int flags; }; ssize_t file_getxattr(struct file *file, struct kernel_xattr_ctx *ctx); ssize_t filename_getxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int file_setxattr(struct file *file, struct kernel_xattr_ctx *ctx); int filename_setxattr(int dfd, struct filename *filename, unsigned int lookup_flags, struct kernel_xattr_ctx *ctx); int setxattr_copy(const char __user *name, struct kernel_xattr_ctx *ctx); int import_xattr_name(struct xattr_name *kname, const char __user *name); int may_write_xattr(struct mnt_idmap *idmap, struct inode *inode); #ifdef CONFIG_FS_POSIX_ACL int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size); ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size); #else static inline int do_set_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, const void *kvalue, size_t size) { return -EOPNOTSUPP; } static inline ssize_t do_get_acl(struct mnt_idmap *idmap, struct dentry *dentry, const char *acl_name, void *kvalue, size_t size) { return -EOPNOTSUPP; } #endif ssize_t __kernel_write_iter(struct file *file, struct iov_iter *from, loff_t *pos); /* * fs/attr.c */ struct mnt_idmap *alloc_mnt_idmap(struct user_namespace *mnt_userns); struct mnt_idmap *mnt_idmap_get(struct mnt_idmap *idmap); void mnt_idmap_put(struct mnt_idmap *idmap); struct stashed_operations { struct dentry *(*stash_dentry)(struct dentry **stashed, struct dentry *dentry); void (*put_data)(void *data); int (*init_inode)(struct inode *inode, void *data); }; int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data, struct path *path); void stashed_dentry_prune(struct dentry *dentry); struct dentry *stash_dentry(struct dentry **stashed, struct dentry *dentry); struct dentry *stashed_dentry_get(struct dentry **stashed); /** * path_mounted - check whether path is mounted * @path: path to check * * Determine whether @path refers to the root of a mount. * * Return: true if @path is the root of a mount, false if not. */ static inline bool path_mounted(const struct path *path) { return path->mnt->mnt_root == path->dentry; } void file_f_owner_release(struct file *file); bool file_seek_cur_needs_f_lock(struct file *file); int statmount_mnt_idmap(struct mnt_idmap *idmap, struct seq_file *seq, bool uid_map); struct dentry *find_next_child(struct dentry *parent, struct dentry *prev); int anon_inode_getattr(struct mnt_idmap *idmap, const struct path *path, struct kstat *stat, u32 request_mask, unsigned int query_flags); int anon_inode_setattr(struct mnt_idmap *idmap, struct dentry *dentry, struct iattr *attr); void pidfs_get_root(struct path *path); void nsfs_get_root(struct path *path); |
| 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2009, Christoph Hellwig * All Rights Reserved. * * NOTE: none of these tracepoints shall be considered a stable kernel ABI * as they can change at any time. * * Current conventions for printing numbers measuring specific units: * * agno: allocation group number * * agino: per-AG inode number * ino: filesystem inode number * * agbno: per-AG block number in fs blocks * rgbno: per-rtgroup block number in fs blocks * startblock: physical block number for file mappings. This is either a * segmented fsblock for data device mappings, or a rfsblock * for realtime device mappings * fsbcount: number of blocks in an extent, in fs blocks * * gbno: generic allocation group block number. This is an agbno for * space in a per-AG or a rgbno for space in a realtime group. * * daddr: physical block number in 512b blocks * bbcount: number of blocks in a physical extent, in 512b blocks * * rtx: physical rt extent number for extent mappings * rtxcount: number of rt extents in an extent mapping * * owner: reverse-mapping owner, usually inodes * * fileoff: file offset, in fs blocks * pos: file offset, in bytes * bytecount: number of bytes * * dablk: directory or xattr block offset, in filesystem blocks * * disize: ondisk file size, in bytes * isize: incore file size, in bytes * * forkoff: inode fork offset, in bytes * * ireccount: number of inode records * * Numbers describing space allocations (blocks, extents, inodes) should be * formatted in hexadecimal. */ #undef TRACE_SYSTEM #define TRACE_SYSTEM xfs #if !defined(_TRACE_XFS_H) || defined(TRACE_HEADER_MULTI_READ) #define _TRACE_XFS_H #include <linux/tracepoint.h> struct xfs_agf; struct xfs_ail; struct xfs_alloc_arg; struct xfs_attr_list_context; struct xfs_buf_log_item; struct xfs_da_args; struct xfs_da_node_entry; struct xfs_dquot; struct xfs_log_item; struct xlog; struct xlog_ticket; struct xlog_recover; struct xlog_recover_item; struct xlog_rec_header; struct xlog_in_core; struct xfs_buf_log_format; struct xfs_inode_log_format; struct xfs_bmbt_irec; struct xfs_btree_cur; struct xfs_defer_op_type; struct xfs_refcount_irec; struct xfs_fsmap; struct xfs_fsmap_irec; struct xfs_group; struct xfs_rmap_irec; struct xfs_icreate_log; struct xfs_iunlink_item; struct xfs_owner_info; struct xfs_trans_res; struct xfs_inobt_rec_incore; union xfs_btree_ptr; struct xfs_dqtrx; struct xfs_icwalk; struct xfs_perag; struct xfbtree; struct xfs_btree_ops; struct xfs_bmap_intent; struct xfs_exchmaps_intent; struct xfs_exchmaps_req; struct xfs_exchrange; struct xfs_getparents; struct xfs_parent_irec; struct xfs_attrlist_cursor_kern; struct xfs_extent_free_item; struct xfs_rmap_intent; struct xfs_refcount_intent; struct xfs_metadir_update; struct xfs_rtgroup; struct xfs_open_zone; struct xfs_healthmon_event; struct xfs_healthmon; struct fserror_event; #define XFS_ATTR_FILTER_FLAGS \ { XFS_ATTR_ROOT, "ROOT" }, \ { XFS_ATTR_SECURE, "SECURE" }, \ { XFS_ATTR_INCOMPLETE, "INCOMPLETE" }, \ { XFS_ATTR_PARENT, "PARENT" } DECLARE_EVENT_CLASS(xfs_attr_list_class, TP_PROTO(struct xfs_attr_list_context *ctx), TP_ARGS(ctx), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(u32, hashval) __field(u32, blkno) __field(u32, offset) __field(void *, buffer) __field(int, bufsize) __field(int, count) __field(int, firstu) __field(int, dupcnt) __field(unsigned int, attr_filter) ), TP_fast_assign( __entry->dev = VFS_I(ctx->dp)->i_sb->s_dev; __entry->ino = I_INO(ctx->dp); __entry->hashval = ctx->cursor.hashval; __entry->blkno = ctx->cursor.blkno; __entry->offset = ctx->cursor.offset; __entry->buffer = ctx->buffer; __entry->bufsize = ctx->bufsize; __entry->count = ctx->count; __entry->firstu = ctx->firstu; __entry->attr_filter = ctx->attr_filter; ), TP_printk("dev %d:%d ino 0x%llx cursor h/b/o 0x%x/0x%x/%u dupcnt %u " "buffer %p size %u count %u firstu %u filter %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->hashval, __entry->blkno, __entry->offset, __entry->dupcnt, __entry->buffer, __entry->bufsize, __entry->count, __entry->firstu, __print_flags(__entry->attr_filter, "|", XFS_ATTR_FILTER_FLAGS) ) ) #define DEFINE_ATTR_LIST_EVENT(name) \ DEFINE_EVENT(xfs_attr_list_class, name, \ TP_PROTO(struct xfs_attr_list_context *ctx), \ TP_ARGS(ctx)) DEFINE_ATTR_LIST_EVENT(xfs_attr_list_sf); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_sf_all); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_leaf); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_leaf_end); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_full); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_add); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_wrong_blk); DEFINE_ATTR_LIST_EVENT(xfs_attr_list_notfound); DEFINE_ATTR_LIST_EVENT(xfs_attr_leaf_list); DEFINE_ATTR_LIST_EVENT(xfs_attr_node_list); TRACE_EVENT(xfs_calc_atomic_write_unit_max, TP_PROTO(struct xfs_mount *mp, enum xfs_group_type type, unsigned int max_write, unsigned int max_ioend, unsigned int max_gsize, unsigned int awu_max), TP_ARGS(mp, type, max_write, max_ioend, max_gsize, awu_max), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(unsigned int, max_write) __field(unsigned int, max_ioend) __field(unsigned int, max_gsize) __field(unsigned int, awu_max) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->type = type; __entry->max_write = max_write; __entry->max_ioend = max_ioend; __entry->max_gsize = max_gsize; __entry->awu_max = awu_max; ), TP_printk("dev %d:%d %s max_write %u max_ioend %u max_gsize %u awu_max %u", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->max_write, __entry->max_ioend, __entry->max_gsize, __entry->awu_max) ); TRACE_EVENT(xfs_calc_max_atomic_write_fsblocks, TP_PROTO(struct xfs_mount *mp, unsigned int per_intent, unsigned int step_size, unsigned int logres, unsigned int blockcount), TP_ARGS(mp, per_intent, step_size, logres, blockcount), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, per_intent) __field(unsigned int, step_size) __field(unsigned int, logres) __field(unsigned int, blockcount) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->per_intent = per_intent; __entry->step_size = step_size; __entry->logres = logres; __entry->blockcount = blockcount; ), TP_printk("dev %d:%d per_intent %u step_size %u logres %u blockcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->per_intent, __entry->step_size, __entry->logres, __entry->blockcount) ); TRACE_EVENT(xfs_calc_max_atomic_write_log_geometry, TP_PROTO(struct xfs_mount *mp, unsigned int per_intent, unsigned int step_size, unsigned int blockcount, unsigned int min_logblocks, unsigned int logres), TP_ARGS(mp, per_intent, step_size, blockcount, min_logblocks, logres), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, per_intent) __field(unsigned int, step_size) __field(unsigned int, blockcount) __field(unsigned int, min_logblocks) __field(unsigned int, cur_logblocks) __field(unsigned int, logres) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->per_intent = per_intent; __entry->step_size = step_size; __entry->blockcount = blockcount; __entry->min_logblocks = min_logblocks; __entry->cur_logblocks = mp->m_sb.sb_logblocks; __entry->logres = logres; ), TP_printk("dev %d:%d per_intent %u step_size %u blockcount %u min_logblocks %u logblocks %u logres %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->per_intent, __entry->step_size, __entry->blockcount, __entry->min_logblocks, __entry->cur_logblocks, __entry->logres) ); TRACE_EVENT(xlog_intent_recovery_failed, TP_PROTO(struct xfs_mount *mp, const struct xfs_defer_op_type *ops, int error), TP_ARGS(mp, ops, error), TP_STRUCT__entry( __field(dev_t, dev) __string(name, ops->name) __field(int, error) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __assign_str(name); __entry->error = error; ), TP_printk("dev %d:%d optype %s error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->error) ); DECLARE_EVENT_CLASS(xfs_perag_class, TP_PROTO(const struct xfs_perag *pag, unsigned long caller_ip), TP_ARGS(pag, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(int, refcount) __field(int, active_refcount) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->refcount = atomic_read(&pag->pag_group.xg_ref); __entry->active_refcount = atomic_read(&pag->pag_group.xg_active_ref); __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d agno 0x%x passive refs %d active refs %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->refcount, __entry->active_refcount, (char *)__entry->caller_ip) ); #define DEFINE_PERAG_REF_EVENT(name) \ DEFINE_EVENT(xfs_perag_class, name, \ TP_PROTO(const struct xfs_perag *pag, unsigned long caller_ip), \ TP_ARGS(pag, caller_ip)) DEFINE_PERAG_REF_EVENT(xfs_perag_set_inode_tag); DEFINE_PERAG_REF_EVENT(xfs_perag_clear_inode_tag); DEFINE_PERAG_REF_EVENT(xfs_reclaim_inodes_count); TRACE_DEFINE_ENUM(XG_TYPE_AG); TRACE_DEFINE_ENUM(XG_TYPE_RTG); DECLARE_EVENT_CLASS(xfs_group_class, TP_PROTO(struct xfs_group *xg, unsigned long caller_ip), TP_ARGS(xg, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(int, refcount) __field(int, active_refcount) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = xg->xg_mount->m_super->s_dev; __entry->type = xg->xg_type; __entry->agno = xg->xg_gno; __entry->refcount = atomic_read(&xg->xg_ref); __entry->active_refcount = atomic_read(&xg->xg_active_ref); __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d %sno 0x%x passive refs %d active refs %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->refcount, __entry->active_refcount, (char *)__entry->caller_ip) ); #define DEFINE_GROUP_REF_EVENT(name) \ DEFINE_EVENT(xfs_group_class, name, \ TP_PROTO(struct xfs_group *xg, unsigned long caller_ip), \ TP_ARGS(xg, caller_ip)) DEFINE_GROUP_REF_EVENT(xfs_group_get); DEFINE_GROUP_REF_EVENT(xfs_group_hold); DEFINE_GROUP_REF_EVENT(xfs_group_put); DEFINE_GROUP_REF_EVENT(xfs_group_grab); DEFINE_GROUP_REF_EVENT(xfs_group_grab_next_tag); DEFINE_GROUP_REF_EVENT(xfs_group_rele); #ifdef CONFIG_XFS_RT DECLARE_EVENT_CLASS(xfs_zone_class, TP_PROTO(struct xfs_rtgroup *rtg), TP_ARGS(rtg), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgno) __field(xfs_rgblock_t, used) __field(unsigned int, nr_open) ), TP_fast_assign( struct xfs_mount *mp = rtg_mount(rtg); __entry->dev = mp->m_super->s_dev; __entry->rgno = rtg_rgno(rtg); __entry->used = rtg_rmap(rtg)->i_used_blocks; __entry->nr_open = mp->m_zone_info->zi_nr_open_zones; ), TP_printk("dev %d:%d rgno 0x%x used 0x%x nr_open %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgno, __entry->used, __entry->nr_open) ); #define DEFINE_ZONE_EVENT(name) \ DEFINE_EVENT(xfs_zone_class, name, \ TP_PROTO(struct xfs_rtgroup *rtg), \ TP_ARGS(rtg)) DEFINE_ZONE_EVENT(xfs_zone_emptied); DEFINE_ZONE_EVENT(xfs_zone_full); DEFINE_ZONE_EVENT(xfs_zone_opened); DEFINE_ZONE_EVENT(xfs_zone_reset); DEFINE_ZONE_EVENT(xfs_zone_gc_target_opened); DEFINE_ZONE_EVENT(xfs_zone_gc_target_stolen); TRACE_EVENT(xfs_zone_free_blocks, TP_PROTO(struct xfs_rtgroup *rtg, xfs_rgblock_t rgbno, xfs_extlen_t len), TP_ARGS(rtg, rgbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgno) __field(xfs_rgblock_t, used) __field(xfs_rgblock_t, rgbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = rtg_mount(rtg)->m_super->s_dev; __entry->rgno = rtg_rgno(rtg); __entry->used = rtg_rmap(rtg)->i_used_blocks; __entry->rgbno = rgbno; __entry->len = len; ), TP_printk("dev %d:%d rgno 0x%x used 0x%x rgbno 0x%x len 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgno, __entry->used, __entry->rgbno, __entry->len) ); DECLARE_EVENT_CLASS(xfs_zone_alloc_class, TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno, xfs_extlen_t len), TP_ARGS(oz, rgbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgno) __field(xfs_rgblock_t, used) __field(xfs_rgblock_t, allocated) __field(xfs_rgblock_t, written) __field(xfs_rgblock_t, rgbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = rtg_mount(oz->oz_rtg)->m_super->s_dev; __entry->rgno = rtg_rgno(oz->oz_rtg); __entry->used = rtg_rmap(oz->oz_rtg)->i_used_blocks; __entry->allocated = oz->oz_allocated; __entry->written = oz->oz_written; __entry->rgbno = rgbno; __entry->len = len; ), TP_printk("dev %d:%d rgno 0x%x used 0x%x alloced 0x%x written 0x%x rgbno 0x%x len 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgno, __entry->used, __entry->allocated, __entry->written, __entry->rgbno, __entry->len) ); #define DEFINE_ZONE_ALLOC_EVENT(name) \ DEFINE_EVENT(xfs_zone_alloc_class, name, \ TP_PROTO(struct xfs_open_zone *oz, xfs_rgblock_t rgbno, \ xfs_extlen_t len), \ TP_ARGS(oz, rgbno, len)) DEFINE_ZONE_ALLOC_EVENT(xfs_zone_record_blocks); DEFINE_ZONE_ALLOC_EVENT(xfs_zone_skip_blocks); DEFINE_ZONE_ALLOC_EVENT(xfs_zone_alloc_blocks); DEFINE_ZONE_ALLOC_EVENT(xfs_zone_spurious_open); TRACE_EVENT(xfs_zone_gc_select_victim, TP_PROTO(struct xfs_rtgroup *rtg, unsigned int bucket), TP_ARGS(rtg, bucket), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgno) __field(xfs_rgblock_t, used) __field(unsigned int, bucket) ), TP_fast_assign( __entry->dev = rtg_mount(rtg)->m_super->s_dev; __entry->rgno = rtg_rgno(rtg); __entry->used = rtg_rmap(rtg)->i_used_blocks; __entry->bucket = bucket; ), TP_printk("dev %d:%d rgno 0x%x used 0x%x bucket %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgno, __entry->used, __entry->bucket) ); TRACE_EVENT(xfs_zones_mount, TP_PROTO(struct xfs_mount *mp), TP_ARGS(mp), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgcount) __field(uint32_t, blocks) __field(unsigned int, max_open_zones) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->rgcount = mp->m_sb.sb_rgcount; __entry->blocks = mp->m_groups[XG_TYPE_RTG].blocks; __entry->max_open_zones = mp->m_max_open_zones; ), TP_printk("dev %d:%d zoned %u blocks_per_zone %u, max_open %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgcount, __entry->blocks, __entry->max_open_zones) ); #endif /* CONFIG_XFS_RT */ TRACE_EVENT(xfs_inodegc_worker, TP_PROTO(struct xfs_mount *mp, unsigned int shrinker_hits), TP_ARGS(mp, shrinker_hits), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, shrinker_hits) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->shrinker_hits = shrinker_hits; ), TP_printk("dev %d:%d shrinker_hits %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->shrinker_hits) ); DECLARE_EVENT_CLASS(xfs_fs_class, TP_PROTO(struct xfs_mount *mp, void *caller_ip), TP_ARGS(mp, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, mflags) __field(unsigned long, opstate) __field(unsigned long, sbflags) __field(void *, caller_ip) ), TP_fast_assign( if (mp) { __entry->dev = mp->m_super->s_dev; __entry->mflags = mp->m_features; __entry->opstate = mp->m_opstate; __entry->sbflags = mp->m_super->s_flags; } __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d m_features 0x%llx opstate (%s) s_flags 0x%lx caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->mflags, __print_flags(__entry->opstate, "|", XFS_OPSTATE_STRINGS), __entry->sbflags, __entry->caller_ip) ); #define DEFINE_FS_EVENT(name) \ DEFINE_EVENT(xfs_fs_class, name, \ TP_PROTO(struct xfs_mount *mp, void *caller_ip), \ TP_ARGS(mp, caller_ip)) DEFINE_FS_EVENT(xfs_inodegc_flush); DEFINE_FS_EVENT(xfs_inodegc_push); DEFINE_FS_EVENT(xfs_inodegc_start); DEFINE_FS_EVENT(xfs_inodegc_stop); DEFINE_FS_EVENT(xfs_inodegc_queue); DEFINE_FS_EVENT(xfs_inodegc_throttle); DEFINE_FS_EVENT(xfs_fs_sync_fs); DEFINE_FS_EVENT(xfs_blockgc_start); DEFINE_FS_EVENT(xfs_blockgc_stop); DEFINE_FS_EVENT(xfs_blockgc_worker); DEFINE_FS_EVENT(xfs_blockgc_flush_all); TRACE_EVENT(xfs_inodegc_shrinker_scan, TP_PROTO(struct xfs_mount *mp, struct shrink_control *sc, void *caller_ip), TP_ARGS(mp, sc, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, nr_to_scan) __field(void *, caller_ip) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->nr_to_scan = sc->nr_to_scan; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d nr_to_scan %lu caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_to_scan, __entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_ag_class, TP_PROTO(const struct xfs_perag *pag), TP_ARGS(pag), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); ), TP_printk("dev %d:%d agno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno) ); #define DEFINE_AG_EVENT(name) \ DEFINE_EVENT(xfs_ag_class, name, \ TP_PROTO(const struct xfs_perag *pag), \ TP_ARGS(pag)) DEFINE_AG_EVENT(xfs_read_agf); DEFINE_AG_EVENT(xfs_alloc_read_agf); DEFINE_AG_EVENT(xfs_read_agi); DEFINE_AG_EVENT(xfs_ialloc_read_agi); TRACE_EVENT(xfs_attr_list_node_descend, TP_PROTO(struct xfs_attr_list_context *ctx, struct xfs_da_node_entry *btree), TP_ARGS(ctx, btree), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(u32, hashval) __field(u32, blkno) __field(u32, offset) __field(void *, buffer) __field(int, bufsize) __field(int, count) __field(int, firstu) __field(int, dupcnt) __field(unsigned int, attr_filter) __field(u32, bt_hashval) __field(u32, bt_before) ), TP_fast_assign( __entry->dev = VFS_I(ctx->dp)->i_sb->s_dev; __entry->ino = I_INO(ctx->dp); __entry->hashval = ctx->cursor.hashval; __entry->blkno = ctx->cursor.blkno; __entry->offset = ctx->cursor.offset; __entry->buffer = ctx->buffer; __entry->bufsize = ctx->bufsize; __entry->count = ctx->count; __entry->firstu = ctx->firstu; __entry->attr_filter = ctx->attr_filter; __entry->bt_hashval = be32_to_cpu(btree->hashval); __entry->bt_before = be32_to_cpu(btree->before); ), TP_printk("dev %d:%d ino 0x%llx cursor h/b/o 0x%x/0x%x/%u dupcnt %u " "buffer %p size %u count %u firstu %u filter %s " "node hashval %u, node before %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->hashval, __entry->blkno, __entry->offset, __entry->dupcnt, __entry->buffer, __entry->bufsize, __entry->count, __entry->firstu, __print_flags(__entry->attr_filter, "|", XFS_ATTR_FILTER_FLAGS), __entry->bt_hashval, __entry->bt_before) ); DECLARE_EVENT_CLASS(xfs_bmap_class, TP_PROTO(struct xfs_inode *ip, struct xfs_iext_cursor *cur, int state, unsigned long caller_ip), TP_ARGS(ip, cur, state, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(void *, leaf) __field(int, pos) __field(xfs_fileoff_t, startoff) __field(xfs_fsblock_t, startblock) __field(xfs_filblks_t, blockcount) __field(xfs_exntst_t, state) __field(int, bmap_state) __field(unsigned long, caller_ip) ), TP_fast_assign( struct xfs_ifork *ifp; struct xfs_bmbt_irec r; ifp = xfs_iext_state_to_fork(ip, state); xfs_iext_get_extent(ifp, cur, &r); __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->leaf = cur->leaf; __entry->pos = cur->pos; __entry->startoff = r.br_startoff; __entry->startblock = r.br_startblock; __entry->blockcount = r.br_blockcount; __entry->state = r.br_state; __entry->bmap_state = state; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ino 0x%llx state %s cur %p/%d " "fileoff 0x%llx startblock 0x%llx fsbcount 0x%llx flag %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS), __entry->leaf, __entry->pos, __entry->startoff, (int64_t)__entry->startblock, __entry->blockcount, __entry->state, (char *)__entry->caller_ip) ) #define DEFINE_BMAP_EVENT(name) \ DEFINE_EVENT(xfs_bmap_class, name, \ TP_PROTO(struct xfs_inode *ip, struct xfs_iext_cursor *cur, int state, \ unsigned long caller_ip), \ TP_ARGS(ip, cur, state, caller_ip)) DEFINE_BMAP_EVENT(xfs_iext_insert); DEFINE_BMAP_EVENT(xfs_iext_remove); DEFINE_BMAP_EVENT(xfs_bmap_pre_update); DEFINE_BMAP_EVENT(xfs_bmap_post_update); DEFINE_BMAP_EVENT(xfs_read_extent); DEFINE_BMAP_EVENT(xfs_write_extent); DECLARE_EVENT_CLASS(xfs_buf_class, TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip), TP_ARGS(bp, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_daddr_t, bno) __field(int, nblks) __field(int, hold) __field(int, pincount) __field(unsigned, lockval) __field(unsigned, flags) __field(unsigned long, caller_ip) __field(const void *, buf_ops) ), TP_fast_assign( __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; __entry->hold = bp->b_lockref.count; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; __entry->caller_ip = caller_ip; __entry->buf_ops = bp->b_ops; ), TP_printk("dev %d:%d daddr 0x%llx bbcount 0x%x hold %d pincount %d " "lock %d flags %s bufops %pS caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, __entry->nblks, __entry->hold, __entry->pincount, __entry->lockval, __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), __entry->buf_ops, (void *)__entry->caller_ip) ) #define DEFINE_BUF_EVENT(name) \ DEFINE_EVENT(xfs_buf_class, name, \ TP_PROTO(struct xfs_buf *bp, unsigned long caller_ip), \ TP_ARGS(bp, caller_ip)) DEFINE_BUF_EVENT(xfs_buf_init); DEFINE_BUF_EVENT(xfs_buf_free); DEFINE_BUF_EVENT(xfs_buf_hold); DEFINE_BUF_EVENT(xfs_buf_rele); DEFINE_BUF_EVENT(xfs_buf_iodone); DEFINE_BUF_EVENT(xfs_buf_submit); DEFINE_BUF_EVENT(xfs_buf_lock); DEFINE_BUF_EVENT(xfs_buf_lock_done); DEFINE_BUF_EVENT(xfs_buf_trylock_fail); DEFINE_BUF_EVENT(xfs_buf_trylock); DEFINE_BUF_EVENT(xfs_buf_unlock); DEFINE_BUF_EVENT(xfs_buf_iowait); DEFINE_BUF_EVENT(xfs_buf_iowait_done); DEFINE_BUF_EVENT(xfs_buf_delwri_queue); DEFINE_BUF_EVENT(xfs_buf_delwri_queued); DEFINE_BUF_EVENT(xfs_buf_delwri_split); DEFINE_BUF_EVENT(xfs_buf_get_uncached); DEFINE_BUF_EVENT(xfs_buf_item_relse); DEFINE_BUF_EVENT(xfs_buf_iodone_async); DEFINE_BUF_EVENT(xfs_buf_error_relse); DEFINE_BUF_EVENT(xfs_buf_drain_buftarg); DEFINE_BUF_EVENT(xfs_trans_read_buf_shut); DEFINE_BUF_EVENT(xfs_buf_backing_folio); DEFINE_BUF_EVENT(xfs_buf_backing_kmem); DEFINE_BUF_EVENT(xfs_buf_backing_vmalloc); DEFINE_BUF_EVENT(xfs_buf_backing_fallback); /* not really buffer traces, but the buf provides useful information */ DEFINE_BUF_EVENT(xfs_btree_corrupt); DEFINE_BUF_EVENT(xfs_reset_dqcounts); /* pass flags explicitly */ DECLARE_EVENT_CLASS(xfs_buf_flags_class, TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip), TP_ARGS(bp, flags, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_daddr_t, bno) __field(unsigned int, length) __field(int, hold) __field(int, pincount) __field(unsigned, lockval) __field(unsigned, flags) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; __entry->flags = flags; __entry->hold = bp->b_lockref.count; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d daddr 0x%llx bbcount 0x%x hold %d pincount %d " "lock %d flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, __entry->length, __entry->hold, __entry->pincount, __entry->lockval, __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), (void *)__entry->caller_ip) ) #define DEFINE_BUF_FLAGS_EVENT(name) \ DEFINE_EVENT(xfs_buf_flags_class, name, \ TP_PROTO(struct xfs_buf *bp, unsigned flags, unsigned long caller_ip), \ TP_ARGS(bp, flags, caller_ip)) DEFINE_BUF_FLAGS_EVENT(xfs_buf_find); DEFINE_BUF_FLAGS_EVENT(xfs_buf_get); DEFINE_BUF_FLAGS_EVENT(xfs_buf_read); DEFINE_BUF_FLAGS_EVENT(xfs_buf_readahead); TRACE_EVENT(xfs_buf_ioerror, TP_PROTO(struct xfs_buf *bp, int error, xfs_failaddr_t caller_ip), TP_ARGS(bp, error, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_daddr_t, bno) __field(unsigned int, length) __field(unsigned, flags) __field(int, hold) __field(int, pincount) __field(unsigned, lockval) __field(int, error) __field(xfs_failaddr_t, caller_ip) ), TP_fast_assign( __entry->dev = bp->b_target->bt_dev; __entry->bno = xfs_buf_daddr(bp); __entry->length = bp->b_length; __entry->hold = bp->b_lockref.count; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->error = error; __entry->flags = bp->b_flags; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d daddr 0x%llx bbcount 0x%x hold %d pincount %d " "lock %d error %d flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->bno, __entry->length, __entry->hold, __entry->pincount, __entry->lockval, __entry->error, __print_flags(__entry->flags, "|", XFS_BUF_FLAGS), (void *)__entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_buf_item_class, TP_PROTO(struct xfs_buf_log_item *bip), TP_ARGS(bip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_daddr_t, buf_bno) __field(unsigned int, buf_len) __field(int, buf_hold) __field(int, buf_pincount) __field(int, buf_lockval) __field(unsigned, buf_flags) __field(unsigned, bli_recur) __field(int, bli_refcount) __field(unsigned, bli_flags) __field(unsigned long, li_flags) ), TP_fast_assign( __entry->dev = bip->bli_buf->b_target->bt_dev; __entry->bli_flags = bip->bli_flags; __entry->bli_recur = bip->bli_recur; __entry->bli_refcount = atomic_read(&bip->bli_refcount); __entry->buf_bno = xfs_buf_daddr(bip->bli_buf); __entry->buf_len = bip->bli_buf->b_length; __entry->buf_flags = bip->bli_buf->b_flags; __entry->buf_hold = bip->bli_buf->b_lockref.count; __entry->buf_pincount = atomic_read(&bip->bli_buf->b_pin_count); __entry->buf_lockval = bip->bli_buf->b_sema.count; __entry->li_flags = bip->bli_item.li_flags; ), TP_printk("dev %d:%d daddr 0x%llx bbcount 0x%x hold %d pincount %d " "lock %d flags %s recur %d refcount %d bliflags %s " "liflags %s", MAJOR(__entry->dev), MINOR(__entry->dev), (unsigned long long)__entry->buf_bno, __entry->buf_len, __entry->buf_hold, __entry->buf_pincount, __entry->buf_lockval, __print_flags(__entry->buf_flags, "|", XFS_BUF_FLAGS), __entry->bli_recur, __entry->bli_refcount, __print_flags(__entry->bli_flags, "|", XFS_BLI_FLAGS), __print_flags(__entry->li_flags, "|", XFS_LI_FLAGS)) ) #define DEFINE_BUF_ITEM_EVENT(name) \ DEFINE_EVENT(xfs_buf_item_class, name, \ TP_PROTO(struct xfs_buf_log_item *bip), \ TP_ARGS(bip)) DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_size_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_format_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_ordered); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_pin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_unpin_stale); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_release); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_committed); DEFINE_BUF_ITEM_EVENT(xfs_buf_item_push); DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf); DEFINE_BUF_ITEM_EVENT(xfs_trans_get_buf_recur); DEFINE_BUF_ITEM_EVENT(xfs_trans_getsb); DEFINE_BUF_ITEM_EVENT(xfs_trans_getsb_recur); DEFINE_BUF_ITEM_EVENT(xfs_trans_read_buf); DEFINE_BUF_ITEM_EVENT(xfs_trans_read_buf_recur); DEFINE_BUF_ITEM_EVENT(xfs_trans_log_buf); DEFINE_BUF_ITEM_EVENT(xfs_trans_brelse); DEFINE_BUF_ITEM_EVENT(xfs_trans_bdetach); DEFINE_BUF_ITEM_EVENT(xfs_trans_bjoin); DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold); DEFINE_BUF_ITEM_EVENT(xfs_trans_bhold_release); DEFINE_BUF_ITEM_EVENT(xfs_trans_binval); DECLARE_EVENT_CLASS(xfs_filestream_class, TP_PROTO(const struct xfs_perag *pag, xfs_ino_t ino), TP_ARGS(pag, ino), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_agnumber_t, agno) __field(int, streams) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->ino = ino; __entry->agno = pag_agno(pag); __entry->streams = atomic_read(&pag->pagf_fstrms); ), TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->agno, __entry->streams) ) #define DEFINE_FILESTREAM_EVENT(name) \ DEFINE_EVENT(xfs_filestream_class, name, \ TP_PROTO(const struct xfs_perag *pag, xfs_ino_t ino), \ TP_ARGS(pag, ino)) DEFINE_FILESTREAM_EVENT(xfs_filestream_free); DEFINE_FILESTREAM_EVENT(xfs_filestream_lookup); DEFINE_FILESTREAM_EVENT(xfs_filestream_scan); TRACE_EVENT(xfs_filestream_pick, TP_PROTO(const struct xfs_perag *pag, xfs_ino_t ino), TP_ARGS(pag, ino), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_agnumber_t, agno) __field(int, streams) __field(xfs_extlen_t, free) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->ino = ino; __entry->agno = pag_agno(pag); __entry->streams = atomic_read(&pag->pagf_fstrms); __entry->free = pag->pagf_freeblks; ), TP_printk("dev %d:%d ino 0x%llx agno 0x%x streams %d free %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->agno, __entry->streams, __entry->free) ); DECLARE_EVENT_CLASS(xfs_lock_class, TP_PROTO(struct xfs_inode *ip, unsigned lock_flags, unsigned long caller_ip), TP_ARGS(ip, lock_flags, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(int, lock_flags) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->lock_flags = lock_flags; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ino 0x%llx flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->lock_flags, "|", XFS_LOCK_FLAGS), (void *)__entry->caller_ip) ) #define DEFINE_LOCK_EVENT(name) \ DEFINE_EVENT(xfs_lock_class, name, \ TP_PROTO(struct xfs_inode *ip, unsigned lock_flags, \ unsigned long caller_ip), \ TP_ARGS(ip, lock_flags, caller_ip)) DEFINE_LOCK_EVENT(xfs_ilock); DEFINE_LOCK_EVENT(xfs_ilock_nowait); DEFINE_LOCK_EVENT(xfs_ilock_demote); DEFINE_LOCK_EVENT(xfs_iunlock); DECLARE_EVENT_CLASS(xfs_inode_class, TP_PROTO(struct xfs_inode *ip), TP_ARGS(ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(unsigned long, iflags) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->iflags = ip->i_flags; ), TP_printk("dev %d:%d ino 0x%llx iflags 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->iflags) ) #define DEFINE_INODE_EVENT(name) \ DEFINE_EVENT(xfs_inode_class, name, \ TP_PROTO(struct xfs_inode *ip), \ TP_ARGS(ip)) DEFINE_INODE_EVENT(xfs_iget_skip); DEFINE_INODE_EVENT(xfs_iget_recycle); DEFINE_INODE_EVENT(xfs_iget_recycle_fail); DEFINE_INODE_EVENT(xfs_iget_hit); DEFINE_INODE_EVENT(xfs_iget_miss); DEFINE_INODE_EVENT(xfs_getattr); DEFINE_INODE_EVENT(xfs_setattr); DEFINE_INODE_EVENT(xfs_readlink); DEFINE_INODE_EVENT(xfs_inactive_symlink); DEFINE_INODE_EVENT(xfs_alloc_file_space); DEFINE_INODE_EVENT(xfs_free_file_space); DEFINE_INODE_EVENT(xfs_zero_file_space); DEFINE_INODE_EVENT(xfs_collapse_file_space); DEFINE_INODE_EVENT(xfs_insert_file_space); DEFINE_INODE_EVENT(xfs_readdir); #ifdef CONFIG_XFS_POSIX_ACL DEFINE_INODE_EVENT(xfs_get_acl); #endif DEFINE_INODE_EVENT(xfs_vm_bmap); DEFINE_INODE_EVENT(xfs_file_ioctl); #ifdef CONFIG_COMPAT DEFINE_INODE_EVENT(xfs_file_compat_ioctl); #endif DEFINE_INODE_EVENT(xfs_ioctl_setattr); DEFINE_INODE_EVENT(xfs_dir_fsync); DEFINE_INODE_EVENT(xfs_file_fsync); DEFINE_INODE_EVENT(xfs_destroy_inode); DEFINE_INODE_EVENT(xfs_update_time); DEFINE_INODE_EVENT(xfs_dquot_dqalloc); DEFINE_INODE_EVENT(xfs_dquot_dqdetach); DEFINE_INODE_EVENT(xfs_inode_set_eofblocks_tag); DEFINE_INODE_EVENT(xfs_inode_clear_eofblocks_tag); DEFINE_INODE_EVENT(xfs_inode_free_eofblocks_invalid); DEFINE_INODE_EVENT(xfs_inode_set_cowblocks_tag); DEFINE_INODE_EVENT(xfs_inode_clear_cowblocks_tag); DEFINE_INODE_EVENT(xfs_inode_free_cowblocks_invalid); DEFINE_INODE_EVENT(xfs_inode_set_reclaimable); DEFINE_INODE_EVENT(xfs_inode_reclaiming); DEFINE_INODE_EVENT(xfs_inode_set_need_inactive); DEFINE_INODE_EVENT(xfs_inode_inactivating); /* * ftrace's __print_symbolic requires that all enum values be wrapped in the * TRACE_DEFINE_ENUM macro so that the enum value can be encoded in the ftrace * ring buffer. Somehow this was only worth mentioning in the ftrace sample * code. */ TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_SHARED); TRACE_DEFINE_ENUM(XFS_REFC_DOMAIN_COW); DECLARE_EVENT_CLASS(xfs_fault_class, TP_PROTO(struct xfs_inode *ip, unsigned int order), TP_ARGS(ip, order), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(unsigned int, order) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->order = order; ), TP_printk("dev %d:%d ino 0x%llx order %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->order) ) #define DEFINE_FAULT_EVENT(name) \ DEFINE_EVENT(xfs_fault_class, name, \ TP_PROTO(struct xfs_inode *ip, unsigned int order), \ TP_ARGS(ip, order)) DEFINE_FAULT_EVENT(xfs_read_fault); DEFINE_FAULT_EVENT(xfs_write_fault); DECLARE_EVENT_CLASS(xfs_iref_class, TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), TP_ARGS(ip, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(int, count) __field(int, pincount) __field(unsigned long, iflags) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->count = icount_read_once(VFS_I(ip)); __entry->pincount = atomic_read(&ip->i_pincount); __entry->iflags = ip->i_flags; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ino 0x%llx count %d pincount %d iflags 0x%lx caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->count, __entry->pincount, __entry->iflags, (char *)__entry->caller_ip) ) TRACE_EVENT(xfs_iomap_prealloc_size, TP_PROTO(struct xfs_inode *ip, xfs_fsblock_t blocks, int shift, unsigned int writeio_blocks), TP_ARGS(ip, blocks, shift, writeio_blocks), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fsblock_t, blocks) __field(int, shift) __field(unsigned int, writeio_blocks) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->blocks = blocks; __entry->shift = shift; __entry->writeio_blocks = writeio_blocks; ), TP_printk("dev %d:%d ino 0x%llx prealloc blocks %llu shift %d " "m_allocsize_blocks %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->blocks, __entry->shift, __entry->writeio_blocks) ) TRACE_EVENT(xfs_irec_merge_pre, TP_PROTO(const struct xfs_perag *pag, const struct xfs_inobt_rec_incore *rec, const struct xfs_inobt_rec_incore *nrec), TP_ARGS(pag, rec, nrec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) __field(uint16_t, holemask) __field(xfs_agino_t, nagino) __field(uint16_t, nholemask) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->agino = rec->ir_startino; __entry->holemask = rec->ir_holemask; __entry->nagino = nrec->ir_startino; __entry->nholemask = nrec->ir_holemask; ), TP_printk("dev %d:%d agno 0x%x agino 0x%x holemask 0x%x new_agino 0x%x new_holemask 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agino, __entry->holemask, __entry->nagino, __entry->nholemask) ) TRACE_EVENT(xfs_irec_merge_post, TP_PROTO(const struct xfs_perag *pag, const struct xfs_inobt_rec_incore *nrec), TP_ARGS(pag, nrec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) __field(uint16_t, holemask) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->agino = nrec->ir_startino; __entry->holemask = nrec->ir_holemask; ), TP_printk("dev %d:%d agno 0x%x agino 0x%x holemask 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agino, __entry->holemask) ) #define DEFINE_IREF_EVENT(name) \ DEFINE_EVENT(xfs_iref_class, name, \ TP_PROTO(struct xfs_inode *ip, unsigned long caller_ip), \ TP_ARGS(ip, caller_ip)) DEFINE_IREF_EVENT(xfs_irele); DEFINE_IREF_EVENT(xfs_inode_pin); DEFINE_IREF_EVENT(xfs_inode_unpin); DEFINE_IREF_EVENT(xfs_inode_unpin_nowait); DEFINE_IREF_EVENT(xfs_inode_push_pinned); DEFINE_IREF_EVENT(xfs_inode_push_stale); DECLARE_EVENT_CLASS(xfs_namespace_class, TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name), TP_ARGS(dp, name), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, dp_ino) __field(int, namelen) __dynamic_array(char, name, name->len) ), TP_fast_assign( __entry->dev = VFS_I(dp)->i_sb->s_dev; __entry->dp_ino = I_INO(dp); __entry->namelen = name->len; memcpy(__get_str(name), name->name, name->len); ), TP_printk("dev %d:%d dp ino 0x%llx name %.*s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dp_ino, __entry->namelen, __get_str(name)) ) #define DEFINE_NAMESPACE_EVENT(name) \ DEFINE_EVENT(xfs_namespace_class, name, \ TP_PROTO(struct xfs_inode *dp, const struct xfs_name *name), \ TP_ARGS(dp, name)) DEFINE_NAMESPACE_EVENT(xfs_remove); DEFINE_NAMESPACE_EVENT(xfs_link); DEFINE_NAMESPACE_EVENT(xfs_lookup); DEFINE_NAMESPACE_EVENT(xfs_create); DEFINE_NAMESPACE_EVENT(xfs_symlink); TRACE_EVENT(xfs_rename, TP_PROTO(struct xfs_inode *src_dp, struct xfs_inode *target_dp, struct xfs_name *src_name, struct xfs_name *target_name), TP_ARGS(src_dp, target_dp, src_name, target_name), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, src_dp_ino) __field(xfs_ino_t, target_dp_ino) __field(int, src_namelen) __field(int, target_namelen) __dynamic_array(char, src_name, src_name->len) __dynamic_array(char, target_name, target_name->len) ), TP_fast_assign( __entry->dev = VFS_I(src_dp)->i_sb->s_dev; __entry->src_dp_ino = I_INO(src_dp); __entry->target_dp_ino = I_INO(target_dp); __entry->src_namelen = src_name->len; __entry->target_namelen = target_name->len; memcpy(__get_str(src_name), src_name->name, src_name->len); memcpy(__get_str(target_name), target_name->name, target_name->len); ), TP_printk("dev %d:%d src dp ino 0x%llx target dp ino 0x%llx" " src name %.*s target name %.*s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->src_dp_ino, __entry->target_dp_ino, __entry->src_namelen, __get_str(src_name), __entry->target_namelen, __get_str(target_name)) ) DECLARE_EVENT_CLASS(xfs_dquot_class, TP_PROTO(struct xfs_dquot *dqp), TP_ARGS(dqp), TP_STRUCT__entry( __field(dev_t, dev) __field(u32, id) __field(xfs_dqtype_t, type) __field(unsigned, flags) __field(unsigned, nrefs) __field(unsigned long long, res_bcount) __field(unsigned long long, res_rtbcount) __field(unsigned long long, res_icount) __field(unsigned long long, bcount) __field(unsigned long long, rtbcount) __field(unsigned long long, icount) __field(unsigned long long, blk_hardlimit) __field(unsigned long long, blk_softlimit) __field(unsigned long long, rtb_hardlimit) __field(unsigned long long, rtb_softlimit) __field(unsigned long long, ino_hardlimit) __field(unsigned long long, ino_softlimit) ), TP_fast_assign( __entry->dev = dqp->q_mount->m_super->s_dev; __entry->id = dqp->q_id; __entry->type = dqp->q_type; __entry->flags = dqp->q_flags; __entry->nrefs = data_race(dqp->q_lockref.count); __entry->res_bcount = dqp->q_blk.reserved; __entry->res_rtbcount = dqp->q_rtb.reserved; __entry->res_icount = dqp->q_ino.reserved; __entry->bcount = dqp->q_blk.count; __entry->rtbcount = dqp->q_rtb.count; __entry->icount = dqp->q_ino.count; __entry->blk_hardlimit = dqp->q_blk.hardlimit; __entry->blk_softlimit = dqp->q_blk.softlimit; __entry->rtb_hardlimit = dqp->q_rtb.hardlimit; __entry->rtb_softlimit = dqp->q_rtb.softlimit; __entry->ino_hardlimit = dqp->q_ino.hardlimit; __entry->ino_softlimit = dqp->q_ino.softlimit; ), TP_printk("dev %d:%d id 0x%x type %s flags %s nrefs %u " "res_bc 0x%llx res_rtbc 0x%llx res_ic 0x%llx " "bcnt 0x%llx bhardlimit 0x%llx bsoftlimit 0x%llx " "rtbcnt 0x%llx rtbhardlimit 0x%llx rtbsoftlimit 0x%llx " "icnt 0x%llx ihardlimit 0x%llx isoftlimit 0x%llx]", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->id, __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS), __print_flags(__entry->flags, "|", XFS_DQFLAG_STRINGS), __entry->nrefs, __entry->res_bcount, __entry->res_rtbcount, __entry->res_icount, __entry->bcount, __entry->blk_hardlimit, __entry->blk_softlimit, __entry->rtbcount, __entry->rtb_hardlimit, __entry->rtb_softlimit, __entry->icount, __entry->ino_hardlimit, __entry->ino_softlimit) ) #define DEFINE_DQUOT_EVENT(name) \ DEFINE_EVENT(xfs_dquot_class, name, \ TP_PROTO(struct xfs_dquot *dqp), \ TP_ARGS(dqp)) DEFINE_DQUOT_EVENT(xfs_dqadjust); DEFINE_DQUOT_EVENT(xfs_dqreclaim_want); DEFINE_DQUOT_EVENT(xfs_dqreclaim_busy); DEFINE_DQUOT_EVENT(xfs_dqreclaim_done); DEFINE_DQUOT_EVENT(xfs_dqattach_get); DEFINE_DQUOT_EVENT(xfs_dqalloc); DEFINE_DQUOT_EVENT(xfs_dqtobp_read); DEFINE_DQUOT_EVENT(xfs_dqread); DEFINE_DQUOT_EVENT(xfs_dqread_fail); DEFINE_DQUOT_EVENT(xfs_dqget_hit); DEFINE_DQUOT_EVENT(xfs_dqget_miss); DEFINE_DQUOT_EVENT(xfs_dqget_freeing); DEFINE_DQUOT_EVENT(xfs_dqget_dup); DEFINE_DQUOT_EVENT(xfs_dqrele); DEFINE_DQUOT_EVENT(xfs_dqrele_free); DEFINE_DQUOT_EVENT(xfs_dqflush); DEFINE_DQUOT_EVENT(xfs_dqflush_force); DEFINE_DQUOT_EVENT(xfs_dqflush_done); DEFINE_DQUOT_EVENT(xfs_trans_apply_dquot_deltas_before); DEFINE_DQUOT_EVENT(xfs_trans_apply_dquot_deltas_after); TRACE_EVENT(xfs_trans_mod_dquot, TP_PROTO(struct xfs_trans *tp, struct xfs_dquot *dqp, unsigned int field, int64_t delta), TP_ARGS(tp, dqp, field, delta), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_dqtype_t, type) __field(unsigned int, flags) __field(unsigned int, dqid) __field(unsigned int, field) __field(int64_t, delta) ), TP_fast_assign( __entry->dev = tp->t_mountp->m_super->s_dev; __entry->type = dqp->q_type; __entry->flags = dqp->q_flags; __entry->dqid = dqp->q_id; __entry->field = field; __entry->delta = delta; ), TP_printk("dev %d:%d dquot id 0x%x type %s flags %s field %s delta %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dqid, __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS), __print_flags(__entry->flags, "|", XFS_DQFLAG_STRINGS), __print_flags(__entry->field, "|", XFS_QMOPT_FLAGS), __entry->delta) ); DECLARE_EVENT_CLASS(xfs_dqtrx_class, TP_PROTO(struct xfs_dqtrx *qtrx), TP_ARGS(qtrx), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_dqtype_t, type) __field(unsigned int, flags) __field(u32, dqid) __field(uint64_t, blk_res) __field(int64_t, bcount_delta) __field(int64_t, delbcnt_delta) __field(uint64_t, rtblk_res) __field(uint64_t, rtblk_res_used) __field(int64_t, rtbcount_delta) __field(int64_t, delrtb_delta) __field(uint64_t, ino_res) __field(uint64_t, ino_res_used) __field(int64_t, icount_delta) ), TP_fast_assign( __entry->dev = qtrx->qt_dquot->q_mount->m_super->s_dev; __entry->type = qtrx->qt_dquot->q_type; __entry->flags = qtrx->qt_dquot->q_flags; __entry->dqid = qtrx->qt_dquot->q_id; __entry->blk_res = qtrx->qt_blk_res; __entry->bcount_delta = qtrx->qt_bcount_delta; __entry->delbcnt_delta = qtrx->qt_delbcnt_delta; __entry->rtblk_res = qtrx->qt_rtblk_res; __entry->rtblk_res_used = qtrx->qt_rtblk_res_used; __entry->rtbcount_delta = qtrx->qt_rtbcount_delta; __entry->delrtb_delta = qtrx->qt_delrtb_delta; __entry->ino_res = qtrx->qt_ino_res; __entry->ino_res_used = qtrx->qt_ino_res_used; __entry->icount_delta = qtrx->qt_icount_delta; ), TP_printk("dev %d:%d dquot id 0x%x type %s flags %s " "blk_res %llu bcount_delta %lld delbcnt_delta %lld " "rtblk_res %llu rtblk_res_used %llu rtbcount_delta %lld delrtb_delta %lld " "ino_res %llu ino_res_used %llu icount_delta %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dqid, __print_flags(__entry->type, "|", XFS_DQTYPE_STRINGS), __print_flags(__entry->flags, "|", XFS_DQFLAG_STRINGS), __entry->blk_res, __entry->bcount_delta, __entry->delbcnt_delta, __entry->rtblk_res, __entry->rtblk_res_used, __entry->rtbcount_delta, __entry->delrtb_delta, __entry->ino_res, __entry->ino_res_used, __entry->icount_delta) ) #define DEFINE_DQTRX_EVENT(name) \ DEFINE_EVENT(xfs_dqtrx_class, name, \ TP_PROTO(struct xfs_dqtrx *qtrx), \ TP_ARGS(qtrx)) DEFINE_DQTRX_EVENT(xfs_trans_apply_dquot_deltas); DEFINE_DQTRX_EVENT(xfs_trans_mod_dquot_before); DEFINE_DQTRX_EVENT(xfs_trans_mod_dquot_after); DECLARE_EVENT_CLASS(xfs_loggrant_class, TP_PROTO(struct xlog *log, struct xlog_ticket *tic), TP_ARGS(log, tic), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, tic) __field(char, ocnt) __field(char, cnt) __field(int, curr_res) __field(int, unit_res) __field(unsigned int, flags) __field(int, reserveq) __field(int, writeq) __field(uint64_t, grant_reserve_bytes) __field(uint64_t, grant_write_bytes) __field(uint64_t, tail_space) __field(int, curr_cycle) __field(int, curr_block) __field(xfs_lsn_t, tail_lsn) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->tic = (unsigned long)tic; __entry->ocnt = tic->t_ocnt; __entry->cnt = tic->t_cnt; __entry->curr_res = tic->t_curr_res; __entry->unit_res = tic->t_unit_res; __entry->flags = tic->t_flags; __entry->reserveq = list_empty(&log->l_reserve_head.waiters); __entry->writeq = list_empty(&log->l_write_head.waiters); __entry->tail_space = READ_ONCE(log->l_tail_space); __entry->grant_reserve_bytes = __entry->tail_space + atomic64_read(&log->l_reserve_head.grant); __entry->grant_write_bytes = __entry->tail_space + atomic64_read(&log->l_write_head.grant); __entry->curr_cycle = log->l_curr_cycle; __entry->curr_block = log->l_curr_block; __entry->tail_lsn = atomic64_read(&log->l_tail_lsn); ), TP_printk("dev %d:%d tic 0x%lx t_ocnt %u t_cnt %u t_curr_res %u " "t_unit_res %u t_flags %s reserveq %s writeq %s " "tail space %llu grant_reserve_bytes %llu " "grant_write_bytes %llu curr_cycle %d curr_block %d " "tail_cycle %d tail_block %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tic, __entry->ocnt, __entry->cnt, __entry->curr_res, __entry->unit_res, __print_flags(__entry->flags, "|", XLOG_TIC_FLAGS), __entry->reserveq ? "empty" : "active", __entry->writeq ? "empty" : "active", __entry->tail_space, __entry->grant_reserve_bytes, __entry->grant_write_bytes, __entry->curr_cycle, __entry->curr_block, CYCLE_LSN(__entry->tail_lsn), BLOCK_LSN(__entry->tail_lsn) ) ) #define DEFINE_LOGGRANT_EVENT(name) \ DEFINE_EVENT(xfs_loggrant_class, name, \ TP_PROTO(struct xlog *log, struct xlog_ticket *tic), \ TP_ARGS(log, tic)) DEFINE_LOGGRANT_EVENT(xfs_log_umount_write); DEFINE_LOGGRANT_EVENT(xfs_log_grant_sleep); DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake); DEFINE_LOGGRANT_EVENT(xfs_log_grant_wake_up); DEFINE_LOGGRANT_EVENT(xfs_log_reserve); DEFINE_LOGGRANT_EVENT(xfs_log_reserve_exit); DEFINE_LOGGRANT_EVENT(xfs_log_regrant); DEFINE_LOGGRANT_EVENT(xfs_log_regrant_exit); DEFINE_LOGGRANT_EVENT(xfs_log_ticket_regrant); DEFINE_LOGGRANT_EVENT(xfs_log_ticket_regrant_exit); DEFINE_LOGGRANT_EVENT(xfs_log_ticket_regrant_sub); DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant); DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant_sub); DEFINE_LOGGRANT_EVENT(xfs_log_ticket_ungrant_exit); DEFINE_LOGGRANT_EVENT(xfs_log_cil_wait); DECLARE_EVENT_CLASS(xfs_log_item_class, TP_PROTO(struct xfs_log_item *lip), TP_ARGS(lip), TP_STRUCT__entry( __field(dev_t, dev) __field(void *, lip) __field(uint, type) __field(unsigned long, flags) __field(xfs_lsn_t, lsn) ), TP_fast_assign( __entry->dev = lip->li_log->l_mp->m_super->s_dev; __entry->lip = lip; __entry->type = lip->li_type; __entry->flags = lip->li_flags; __entry->lsn = lip->li_lsn; ), TP_printk("dev %d:%d lip %p lsn %d/%d type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lip, CYCLE_LSN(__entry->lsn), BLOCK_LSN(__entry->lsn), __print_symbolic(__entry->type, XFS_LI_TYPE_DESC), __print_flags(__entry->flags, "|", XFS_LI_FLAGS)) ) TRACE_EVENT(xfs_log_force, TP_PROTO(struct xfs_mount *mp, xfs_lsn_t lsn, unsigned long caller_ip), TP_ARGS(mp, lsn, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_lsn_t, lsn) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->lsn = lsn; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d lsn 0x%llx caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lsn, (void *)__entry->caller_ip) ) #define DEFINE_LOG_ITEM_EVENT(name) \ DEFINE_EVENT(xfs_log_item_class, name, \ TP_PROTO(struct xfs_log_item *lip), \ TP_ARGS(lip)) DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_mark); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_skip); DEFINE_LOG_ITEM_EVENT(xfs_cil_whiteout_unpin); DEFINE_LOG_ITEM_EVENT(xlog_ail_insert_abort); DEFINE_LOG_ITEM_EVENT(xfs_trans_free_abort); DECLARE_EVENT_CLASS(xfs_ail_push_class, TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), TP_ARGS(ailp, type, flags, lsn), TP_STRUCT__entry( __field(dev_t, dev) __field(uint, type) __field(unsigned long, flags) __field(xfs_lsn_t, lsn) ), TP_fast_assign( __entry->dev = ailp->ail_log->l_mp->m_super->s_dev; __entry->type = type; __entry->flags = flags; __entry->lsn = lsn; ), TP_printk("dev %d:%d lsn %d/%d type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), CYCLE_LSN(__entry->lsn), BLOCK_LSN(__entry->lsn), __print_symbolic(__entry->type, XFS_LI_TYPE_DESC), __print_flags(__entry->flags, "|", XFS_LI_FLAGS)) ) #define DEFINE_AIL_PUSH_EVENT(name) \ DEFINE_EVENT(xfs_ail_push_class, name, \ TP_PROTO(struct xfs_ail *ailp, uint type, unsigned long flags, xfs_lsn_t lsn), \ TP_ARGS(ailp, type, flags, lsn)) DEFINE_AIL_PUSH_EVENT(xfs_ail_push); DEFINE_AIL_PUSH_EVENT(xfs_ail_pinned); DEFINE_AIL_PUSH_EVENT(xfs_ail_locked); DEFINE_AIL_PUSH_EVENT(xfs_ail_flushing); DECLARE_EVENT_CLASS(xfs_ail_class, TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn), TP_ARGS(lip, old_lsn, new_lsn), TP_STRUCT__entry( __field(dev_t, dev) __field(void *, lip) __field(uint, type) __field(unsigned long, flags) __field(xfs_lsn_t, old_lsn) __field(xfs_lsn_t, new_lsn) ), TP_fast_assign( __entry->dev = lip->li_log->l_mp->m_super->s_dev; __entry->lip = lip; __entry->type = lip->li_type; __entry->flags = lip->li_flags; __entry->old_lsn = old_lsn; __entry->new_lsn = new_lsn; ), TP_printk("dev %d:%d lip %p old lsn %d/%d new lsn %d/%d type %s flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lip, CYCLE_LSN(__entry->old_lsn), BLOCK_LSN(__entry->old_lsn), CYCLE_LSN(__entry->new_lsn), BLOCK_LSN(__entry->new_lsn), __print_symbolic(__entry->type, XFS_LI_TYPE_DESC), __print_flags(__entry->flags, "|", XFS_LI_FLAGS)) ) #define DEFINE_AIL_EVENT(name) \ DEFINE_EVENT(xfs_ail_class, name, \ TP_PROTO(struct xfs_log_item *lip, xfs_lsn_t old_lsn, xfs_lsn_t new_lsn), \ TP_ARGS(lip, old_lsn, new_lsn)) DEFINE_AIL_EVENT(xfs_ail_insert); DEFINE_AIL_EVENT(xfs_ail_move); DEFINE_AIL_EVENT(xfs_ail_delete); TRACE_EVENT(xfs_log_assign_tail_lsn, TP_PROTO(struct xlog *log, xfs_lsn_t new_lsn), TP_ARGS(log, new_lsn), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_lsn_t, new_lsn) __field(xfs_lsn_t, old_lsn) __field(xfs_lsn_t, head_lsn) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->new_lsn = new_lsn; __entry->old_lsn = atomic64_read(&log->l_tail_lsn); __entry->head_lsn = log->l_ailp->ail_head_lsn; ), TP_printk("dev %d:%d new tail lsn %d/%d, old lsn %d/%d, head lsn %d/%d", MAJOR(__entry->dev), MINOR(__entry->dev), CYCLE_LSN(__entry->new_lsn), BLOCK_LSN(__entry->new_lsn), CYCLE_LSN(__entry->old_lsn), BLOCK_LSN(__entry->old_lsn), CYCLE_LSN(__entry->head_lsn), BLOCK_LSN(__entry->head_lsn)) ) DECLARE_EVENT_CLASS(xfs_file_class, TP_PROTO(struct kiocb *iocb, struct iov_iter *iter), TP_ARGS(iocb, iter), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fsize_t, size) __field(loff_t, offset) __field(size_t, count) ), TP_fast_assign( __entry->dev = file_inode(iocb->ki_filp)->i_sb->s_dev; __entry->ino = file_inode(iocb->ki_filp)->i_ino; __entry->size = XFS_I(file_inode(iocb->ki_filp))->i_disk_size; __entry->offset = iocb->ki_pos; __entry->count = iov_iter_count(iter); ), TP_printk("dev %d:%d ino 0x%llx disize 0x%llx pos 0x%llx bytecount 0x%zx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->count) ) #define DEFINE_RW_EVENT(name) \ DEFINE_EVENT(xfs_file_class, name, \ TP_PROTO(struct kiocb *iocb, struct iov_iter *iter), \ TP_ARGS(iocb, iter)) DEFINE_RW_EVENT(xfs_file_buffered_read); DEFINE_RW_EVENT(xfs_file_direct_read); DEFINE_RW_EVENT(xfs_file_dax_read); DEFINE_RW_EVENT(xfs_file_buffered_write); DEFINE_RW_EVENT(xfs_file_direct_write); DEFINE_RW_EVENT(xfs_file_dax_write); DEFINE_RW_EVENT(xfs_reflink_bounce_dio_write); TRACE_EVENT(xfs_iomap_atomic_write_cow, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), TP_ARGS(ip, offset, count), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_off_t, offset) __field(ssize_t, count) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->offset = offset; __entry->count = count; ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx bytecount 0x%zx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->offset, __entry->count) ) DECLARE_EVENT_CLASS(xfs_imap_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, int whichfork, struct xfs_bmbt_irec *irec), TP_ARGS(ip, offset, count, whichfork, irec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(loff_t, size) __field(loff_t, offset) __field(size_t, count) __field(int, whichfork) __field(xfs_fileoff_t, startoff) __field(xfs_fsblock_t, startblock) __field(xfs_filblks_t, blockcount) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->size = ip->i_disk_size; __entry->offset = offset; __entry->count = count; __entry->whichfork = whichfork; __entry->startoff = irec ? irec->br_startoff : 0; __entry->startblock = irec ? irec->br_startblock : 0; __entry->blockcount = irec ? irec->br_blockcount : 0; ), TP_printk("dev %d:%d ino 0x%llx disize 0x%llx pos 0x%llx bytecount 0x%zx " "fork %s startoff 0x%llx startblock 0x%llx fsbcount 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->offset, __entry->count, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->startoff, (int64_t)__entry->startblock, __entry->blockcount) ) #define DEFINE_IMAP_EVENT(name) \ DEFINE_EVENT(xfs_imap_class, name, \ TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count, \ int whichfork, struct xfs_bmbt_irec *irec), \ TP_ARGS(ip, offset, count, whichfork, irec)) DEFINE_IMAP_EVENT(xfs_map_blocks_found); DEFINE_IMAP_EVENT(xfs_map_blocks_alloc); DEFINE_IMAP_EVENT(xfs_iomap_alloc); DEFINE_IMAP_EVENT(xfs_iomap_found); DECLARE_EVENT_CLASS(xfs_simple_io_class, TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), TP_ARGS(ip, offset, count), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(loff_t, isize) __field(loff_t, disize) __field(loff_t, offset) __field(size_t, count) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->isize = VFS_I(ip)->i_size; __entry->disize = ip->i_disk_size; __entry->offset = offset; __entry->count = count; ), TP_printk("dev %d:%d ino 0x%llx isize 0x%llx disize 0x%llx " "pos 0x%llx bytecount 0x%zx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->isize, __entry->disize, __entry->offset, __entry->count) ); #define DEFINE_SIMPLE_IO_EVENT(name) \ DEFINE_EVENT(xfs_simple_io_class, name, \ TP_PROTO(struct xfs_inode *ip, xfs_off_t offset, ssize_t count), \ TP_ARGS(ip, offset, count)) DEFINE_SIMPLE_IO_EVENT(xfs_delalloc_enospc); DEFINE_SIMPLE_IO_EVENT(xfs_unwritten_convert); DEFINE_SIMPLE_IO_EVENT(xfs_setfilesize); DEFINE_SIMPLE_IO_EVENT(xfs_zero_eof); DEFINE_SIMPLE_IO_EVENT(xfs_end_io_direct_write); DEFINE_SIMPLE_IO_EVENT(xfs_file_splice_read); DEFINE_SIMPLE_IO_EVENT(xfs_zoned_map_blocks); DECLARE_EVENT_CLASS(xfs_itrunc_class, TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), TP_ARGS(ip, new_size), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fsize_t, size) __field(xfs_fsize_t, new_size) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->size = ip->i_disk_size; __entry->new_size = new_size; ), TP_printk("dev %d:%d ino 0x%llx disize 0x%llx new_size 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->new_size) ) #define DEFINE_ITRUNC_EVENT(name) \ DEFINE_EVENT(xfs_itrunc_class, name, \ TP_PROTO(struct xfs_inode *ip, xfs_fsize_t new_size), \ TP_ARGS(ip, new_size)) DEFINE_ITRUNC_EVENT(xfs_itruncate_extents_start); DEFINE_ITRUNC_EVENT(xfs_itruncate_extents_end); TRACE_EVENT(xfs_bunmap, TP_PROTO(struct xfs_inode *ip, xfs_fileoff_t fileoff, xfs_filblks_t len, int flags, unsigned long caller_ip), TP_ARGS(ip, fileoff, len, flags, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fsize_t, size) __field(xfs_fileoff_t, fileoff) __field(xfs_filblks_t, len) __field(unsigned long, caller_ip) __field(int, flags) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->size = ip->i_disk_size; __entry->fileoff = fileoff; __entry->len = len; __entry->caller_ip = caller_ip; __entry->flags = flags; ), TP_printk("dev %d:%d ino 0x%llx disize 0x%llx fileoff 0x%llx fsbcount 0x%llx " "flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->fileoff, __entry->len, __print_flags(__entry->flags, "|", XFS_BMAPI_FLAGS), (void *)__entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_extent_busy_class, TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len), TP_ARGS(xg, agbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = xg->xg_mount->m_super->s_dev; __entry->type = xg->xg_type; __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; ), TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len) ); #define DEFINE_BUSY_EVENT(name) \ DEFINE_EVENT(xfs_extent_busy_class, name, \ TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len), \ TP_ARGS(xg, agbno, len)) DEFINE_BUSY_EVENT(xfs_extent_busy); DEFINE_BUSY_EVENT(xfs_extent_busy_force); DEFINE_BUSY_EVENT(xfs_extent_busy_reuse); DEFINE_BUSY_EVENT(xfs_extent_busy_clear); TRACE_EVENT(xfs_extent_busy_trim, TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len, xfs_agblock_t tbno, xfs_extlen_t tlen), TP_ARGS(xg, agbno, len, tbno, tlen), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) __field(xfs_agblock_t, tbno) __field(xfs_extlen_t, tlen) ), TP_fast_assign( __entry->dev = xg->xg_mount->m_super->s_dev; __entry->type = xg->xg_type; __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; __entry->tbno = tbno; __entry->tlen = tlen; ), TP_printk("dev %d:%d %sno 0x%x %sbno 0x%x fsbcount 0x%x found_agbno 0x%x found_fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agbno, __entry->len, __entry->tbno, __entry->tlen) ); #ifdef CONFIG_XFS_RT TRACE_EVENT(xfs_rtalloc_extent_busy, TP_PROTO(struct xfs_rtgroup *rtg, xfs_rtxnum_t start, xfs_rtxlen_t minlen, xfs_rtxlen_t maxlen, xfs_rtxlen_t len, xfs_rtxlen_t prod, xfs_rtxnum_t rtx, unsigned busy_gen), TP_ARGS(rtg, start, minlen, maxlen, len, prod, rtx, busy_gen), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgno) __field(xfs_rtxnum_t, start) __field(xfs_rtxlen_t, minlen) __field(xfs_rtxlen_t, maxlen) __field(xfs_rtxlen_t, mod) __field(xfs_rtxlen_t, prod) __field(xfs_rtxlen_t, len) __field(xfs_rtxnum_t, rtx) __field(unsigned, busy_gen) ), TP_fast_assign( __entry->dev = rtg_mount(rtg)->m_super->s_dev; __entry->rgno = rtg_rgno(rtg); __entry->start = start; __entry->minlen = minlen; __entry->maxlen = maxlen; __entry->prod = prod; __entry->len = len; __entry->rtx = rtx; __entry->busy_gen = busy_gen; ), TP_printk("dev %d:%d rgno 0x%x startrtx 0x%llx minlen %u maxlen %u " "prod %u len %u rtx 0%llx busy_gen 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgno, __entry->start, __entry->minlen, __entry->maxlen, __entry->prod, __entry->len, __entry->rtx, __entry->busy_gen) ) TRACE_EVENT(xfs_rtalloc_extent_busy_trim, TP_PROTO(struct xfs_rtgroup *rtg, xfs_rtxnum_t old_rtx, xfs_rtxlen_t old_len, xfs_rtxnum_t new_rtx, xfs_rtxlen_t new_len), TP_ARGS(rtg, old_rtx, old_len, new_rtx, new_len), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rgnumber_t, rgno) __field(xfs_rtxnum_t, old_rtx) __field(xfs_rtxnum_t, new_rtx) __field(xfs_rtxlen_t, old_len) __field(xfs_rtxlen_t, new_len) ), TP_fast_assign( __entry->dev = rtg_mount(rtg)->m_super->s_dev; __entry->rgno = rtg_rgno(rtg); __entry->old_rtx = old_rtx; __entry->old_len = old_len; __entry->new_rtx = new_rtx; __entry->new_len = new_len; ), TP_printk("dev %d:%d rgno 0x%x rtx 0x%llx rtxcount 0x%x -> rtx 0x%llx rtxcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rgno, __entry->old_rtx, __entry->old_len, __entry->new_rtx, __entry->new_len) ); #endif /* CONFIG_XFS_RT */ DECLARE_EVENT_CLASS(xfs_agf_class, TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, unsigned long caller_ip), TP_ARGS(mp, agf, flags, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(int, flags) __field(__u32, length) __field(__u32, bno_root) __field(__u32, cnt_root) __field(__u32, bno_level) __field(__u32, cnt_level) __field(__u32, flfirst) __field(__u32, fllast) __field(__u32, flcount) __field(__u32, freeblks) __field(__u32, longest) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->agno = be32_to_cpu(agf->agf_seqno), __entry->flags = flags; __entry->length = be32_to_cpu(agf->agf_length), __entry->bno_root = be32_to_cpu(agf->agf_bno_root), __entry->cnt_root = be32_to_cpu(agf->agf_cnt_root), __entry->bno_level = be32_to_cpu(agf->agf_bno_level), __entry->cnt_level = be32_to_cpu(agf->agf_cnt_level), __entry->flfirst = be32_to_cpu(agf->agf_flfirst), __entry->fllast = be32_to_cpu(agf->agf_fllast), __entry->flcount = be32_to_cpu(agf->agf_flcount), __entry->freeblks = be32_to_cpu(agf->agf_freeblks), __entry->longest = be32_to_cpu(agf->agf_longest); __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d agno 0x%x flags %s length %u roots b %u c %u " "levels b %u c %u flfirst %u fllast %u flcount %u " "freeblks %u longest %u caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __print_flags(__entry->flags, "|", XFS_AGF_FLAGS), __entry->length, __entry->bno_root, __entry->cnt_root, __entry->bno_level, __entry->cnt_level, __entry->flfirst, __entry->fllast, __entry->flcount, __entry->freeblks, __entry->longest, (void *)__entry->caller_ip) ); #define DEFINE_AGF_EVENT(name) \ DEFINE_EVENT(xfs_agf_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags, \ unsigned long caller_ip), \ TP_ARGS(mp, agf, flags, caller_ip)) DEFINE_AGF_EVENT(xfs_agf); DEFINE_AGF_EVENT(xfs_agfl_reset); TRACE_EVENT(xfs_free_extent, TP_PROTO(const struct xfs_perag *pag, xfs_agblock_t agbno, xfs_extlen_t len, enum xfs_ag_resv_type resv, int haveleft, int haveright), TP_ARGS(pag, agbno, len, resv, haveleft, haveright), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) __field(int, resv) __field(int, haveleft) __field(int, haveright) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->agbno = agbno; __entry->len = len; __entry->resv = resv; __entry->haveleft = haveleft; __entry->haveright = haveright; ), TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x resv %d %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agbno, __entry->len, __entry->resv, __entry->haveleft ? (__entry->haveright ? "both" : "left") : (__entry->haveright ? "right" : "none")) ); DECLARE_EVENT_CLASS(xfs_alloc_class, TP_PROTO(struct xfs_alloc_arg *args), TP_ARGS(args), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, minlen) __field(xfs_extlen_t, maxlen) __field(xfs_extlen_t, mod) __field(xfs_extlen_t, prod) __field(xfs_extlen_t, minleft) __field(xfs_extlen_t, total) __field(xfs_extlen_t, alignment) __field(xfs_extlen_t, minalignslop) __field(xfs_extlen_t, len) __field(char, wasdel) __field(char, wasfromfl) __field(int, resv) __field(int, datatype) __field(xfs_agnumber_t, highest_agno) ), TP_fast_assign( __entry->dev = args->mp->m_super->s_dev; __entry->agno = args->agno; __entry->agbno = args->agbno; __entry->minlen = args->minlen; __entry->maxlen = args->maxlen; __entry->mod = args->mod; __entry->prod = args->prod; __entry->minleft = args->minleft; __entry->total = args->total; __entry->alignment = args->alignment; __entry->minalignslop = args->minalignslop; __entry->len = args->len; __entry->wasdel = args->wasdel; __entry->wasfromfl = args->wasfromfl; __entry->resv = args->resv; __entry->datatype = args->datatype; __entry->highest_agno = args->tp->t_highest_agno; ), TP_printk("dev %d:%d agno 0x%x agbno 0x%x minlen %u maxlen %u mod %u " "prod %u minleft %u total %u alignment %u minalignslop %u " "len %u wasdel %d wasfromfl %d resv %d " "datatype 0x%x highest_agno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agbno, __entry->minlen, __entry->maxlen, __entry->mod, __entry->prod, __entry->minleft, __entry->total, __entry->alignment, __entry->minalignslop, __entry->len, __entry->wasdel, __entry->wasfromfl, __entry->resv, __entry->datatype, __entry->highest_agno) ) #define DEFINE_ALLOC_EVENT(name) \ DEFINE_EVENT(xfs_alloc_class, name, \ TP_PROTO(struct xfs_alloc_arg *args), \ TP_ARGS(args)) DEFINE_ALLOC_EVENT(xfs_alloc_exact_done); DEFINE_ALLOC_EVENT(xfs_alloc_exact_notfound); DEFINE_ALLOC_EVENT(xfs_alloc_exact_error); DEFINE_ALLOC_EVENT(xfs_alloc_near_first); DEFINE_ALLOC_EVENT(xfs_alloc_cur); DEFINE_ALLOC_EVENT(xfs_alloc_cur_right); DEFINE_ALLOC_EVENT(xfs_alloc_cur_left); DEFINE_ALLOC_EVENT(xfs_alloc_cur_lookup); DEFINE_ALLOC_EVENT(xfs_alloc_cur_lookup_done); DEFINE_ALLOC_EVENT(xfs_alloc_near_noentry); DEFINE_ALLOC_EVENT(xfs_alloc_near_busy); DEFINE_ALLOC_EVENT(xfs_alloc_size_neither); DEFINE_ALLOC_EVENT(xfs_alloc_size_noentry); DEFINE_ALLOC_EVENT(xfs_alloc_size_nominleft); DEFINE_ALLOC_EVENT(xfs_alloc_size_done); DEFINE_ALLOC_EVENT(xfs_alloc_size_error); DEFINE_ALLOC_EVENT(xfs_alloc_size_busy); DEFINE_ALLOC_EVENT(xfs_alloc_small_freelist); DEFINE_ALLOC_EVENT(xfs_alloc_small_notenough); DEFINE_ALLOC_EVENT(xfs_alloc_small_done); DEFINE_ALLOC_EVENT(xfs_alloc_small_error); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_badargs); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_skip_deadlock); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_nofix); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_noagbp); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_loopfailed); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_allfailed); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_this_ag); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_start_ag); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_first_ag); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_exact_bno); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_near_bno); DEFINE_ALLOC_EVENT(xfs_alloc_vextent_finish); TRACE_EVENT(xfs_alloc_cur_check, TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t bno, xfs_extlen_t len, xfs_extlen_t diff, bool new), TP_ARGS(cur, bno, len, diff, new), TP_STRUCT__entry( __field(dev_t, dev) __string(name, cur->bc_ops->name) __field(xfs_agblock_t, bno) __field(xfs_extlen_t, len) __field(xfs_extlen_t, diff) __field(bool, new) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __assign_str(name); __entry->bno = bno; __entry->len = len; __entry->diff = diff; __entry->new = new; ), TP_printk("dev %d:%d %sbt agbno 0x%x fsbcount 0x%x diff 0x%x new %d", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->bno, __entry->len, __entry->diff, __entry->new) ) DECLARE_EVENT_CLASS(xfs_da_class, TP_PROTO(struct xfs_da_args *args), TP_ARGS(args), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __dynamic_array(char, name, args->namelen) __field(int, namelen) __field(xfs_dahash_t, hashval) __field(xfs_ino_t, inumber) __field(uint32_t, op_flags) __field(xfs_ino_t, owner) ), TP_fast_assign( __entry->dev = VFS_I(args->dp)->i_sb->s_dev; __entry->ino = I_INO(args->dp); if (args->namelen) memcpy(__get_str(name), args->name, args->namelen); __entry->namelen = args->namelen; __entry->hashval = args->hashval; __entry->inumber = args->inumber; __entry->op_flags = args->op_flags; __entry->owner = args->owner; ), TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d hashval 0x%x " "inumber 0x%llx op_flags %s owner 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->namelen, __entry->namelen ? __get_str(name) : NULL, __entry->namelen, __entry->hashval, __entry->inumber, __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS), __entry->owner) ) #define DEFINE_DIR2_EVENT(name) \ DEFINE_EVENT(xfs_da_class, name, \ TP_PROTO(struct xfs_da_args *args), \ TP_ARGS(args)) DEFINE_DIR2_EVENT(xfs_dir2_sf_addname); DEFINE_DIR2_EVENT(xfs_dir2_sf_create); DEFINE_DIR2_EVENT(xfs_dir2_sf_lookup); DEFINE_DIR2_EVENT(xfs_dir2_sf_replace); DEFINE_DIR2_EVENT(xfs_dir2_sf_removename); DEFINE_DIR2_EVENT(xfs_dir2_sf_toino4); DEFINE_DIR2_EVENT(xfs_dir2_sf_toino8); DEFINE_DIR2_EVENT(xfs_dir2_sf_to_block); DEFINE_DIR2_EVENT(xfs_dir2_block_addname); DEFINE_DIR2_EVENT(xfs_dir2_block_lookup); DEFINE_DIR2_EVENT(xfs_dir2_block_replace); DEFINE_DIR2_EVENT(xfs_dir2_block_removename); DEFINE_DIR2_EVENT(xfs_dir2_block_to_sf); DEFINE_DIR2_EVENT(xfs_dir2_block_to_leaf); DEFINE_DIR2_EVENT(xfs_dir2_leaf_addname); DEFINE_DIR2_EVENT(xfs_dir2_leaf_lookup); DEFINE_DIR2_EVENT(xfs_dir2_leaf_replace); DEFINE_DIR2_EVENT(xfs_dir2_leaf_removename); DEFINE_DIR2_EVENT(xfs_dir2_leaf_to_block); DEFINE_DIR2_EVENT(xfs_dir2_leaf_to_node); DEFINE_DIR2_EVENT(xfs_dir2_node_addname); DEFINE_DIR2_EVENT(xfs_dir2_node_lookup); DEFINE_DIR2_EVENT(xfs_dir2_node_replace); DEFINE_DIR2_EVENT(xfs_dir2_node_removename); DEFINE_DIR2_EVENT(xfs_dir2_node_to_leaf); DECLARE_EVENT_CLASS(xfs_attr_class, TP_PROTO(struct xfs_da_args *args), TP_ARGS(args), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __dynamic_array(char, name, args->namelen) __field(int, namelen) __field(int, valuelen) __field(xfs_dahash_t, hashval) __field(unsigned int, attr_filter) __field(uint32_t, op_flags) ), TP_fast_assign( __entry->dev = VFS_I(args->dp)->i_sb->s_dev; __entry->ino = I_INO(args->dp); if (args->namelen) memcpy(__get_str(name), args->name, args->namelen); __entry->namelen = args->namelen; __entry->valuelen = args->valuelen; __entry->hashval = args->hashval; __entry->attr_filter = args->attr_filter; __entry->op_flags = args->op_flags; ), TP_printk("dev %d:%d ino 0x%llx name %.*s namelen %d valuelen %d " "hashval 0x%x filter %s op_flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->namelen, __entry->namelen ? __get_str(name) : NULL, __entry->namelen, __entry->valuelen, __entry->hashval, __print_flags(__entry->attr_filter, "|", XFS_ATTR_FILTER_FLAGS), __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS)) ) #define DEFINE_ATTR_EVENT(name) \ DEFINE_EVENT(xfs_attr_class, name, \ TP_PROTO(struct xfs_da_args *args), \ TP_ARGS(args)) DEFINE_ATTR_EVENT(xfs_attr_sf_add); DEFINE_ATTR_EVENT(xfs_attr_sf_addname); DEFINE_ATTR_EVENT(xfs_attr_sf_create); DEFINE_ATTR_EVENT(xfs_attr_sf_lookup); DEFINE_ATTR_EVENT(xfs_attr_sf_remove); DEFINE_ATTR_EVENT(xfs_attr_sf_replace); DEFINE_ATTR_EVENT(xfs_attr_sf_to_leaf); DEFINE_ATTR_EVENT(xfs_attr_leaf_add); DEFINE_ATTR_EVENT(xfs_attr_leaf_add_old); DEFINE_ATTR_EVENT(xfs_attr_leaf_add_new); DEFINE_ATTR_EVENT(xfs_attr_leaf_add_work); DEFINE_ATTR_EVENT(xfs_attr_leaf_create); DEFINE_ATTR_EVENT(xfs_attr_leaf_compact); DEFINE_ATTR_EVENT(xfs_attr_leaf_get); DEFINE_ATTR_EVENT(xfs_attr_leaf_lookup); DEFINE_ATTR_EVENT(xfs_attr_leaf_replace); DEFINE_ATTR_EVENT(xfs_attr_leaf_remove); DEFINE_ATTR_EVENT(xfs_attr_leaf_removename); DEFINE_ATTR_EVENT(xfs_attr_leaf_split); DEFINE_ATTR_EVENT(xfs_attr_leaf_split_before); DEFINE_ATTR_EVENT(xfs_attr_leaf_split_after); DEFINE_ATTR_EVENT(xfs_attr_leaf_clearflag); DEFINE_ATTR_EVENT(xfs_attr_leaf_setflag); DEFINE_ATTR_EVENT(xfs_attr_leaf_flipflags); DEFINE_ATTR_EVENT(xfs_attr_leaf_to_sf); DEFINE_ATTR_EVENT(xfs_attr_leaf_to_node); DEFINE_ATTR_EVENT(xfs_attr_leaf_rebalance); DEFINE_ATTR_EVENT(xfs_attr_leaf_unbalance); DEFINE_ATTR_EVENT(xfs_attr_leaf_toosmall); DEFINE_ATTR_EVENT(xfs_attr_node_addname); DEFINE_ATTR_EVENT(xfs_attr_node_get); DEFINE_ATTR_EVENT(xfs_attr_node_replace); DEFINE_ATTR_EVENT(xfs_attr_rmtval_get); #define DEFINE_DA_EVENT(name) \ DEFINE_EVENT(xfs_da_class, name, \ TP_PROTO(struct xfs_da_args *args), \ TP_ARGS(args)) DEFINE_DA_EVENT(xfs_da_split); DEFINE_DA_EVENT(xfs_da_join); DEFINE_DA_EVENT(xfs_da_link_before); DEFINE_DA_EVENT(xfs_da_link_after); DEFINE_DA_EVENT(xfs_da_unlink_back); DEFINE_DA_EVENT(xfs_da_unlink_forward); DEFINE_DA_EVENT(xfs_da_root_split); DEFINE_DA_EVENT(xfs_da_root_join); DEFINE_DA_EVENT(xfs_da_node_add); DEFINE_DA_EVENT(xfs_da_node_create); DEFINE_DA_EVENT(xfs_da_node_split); DEFINE_DA_EVENT(xfs_da_node_remove); DEFINE_DA_EVENT(xfs_da_node_rebalance); DEFINE_DA_EVENT(xfs_da_node_unbalance); DEFINE_DA_EVENT(xfs_da_node_toosmall); DEFINE_DA_EVENT(xfs_da_swap_lastblock); DEFINE_DA_EVENT(xfs_da_grow_inode); DEFINE_DA_EVENT(xfs_da_shrink_inode); DEFINE_DA_EVENT(xfs_da_fixhashpath); DEFINE_DA_EVENT(xfs_da_path_shift); DECLARE_EVENT_CLASS(xfs_dir2_space_class, TP_PROTO(struct xfs_da_args *args, int idx), TP_ARGS(args, idx), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(uint32_t, op_flags) __field(int, idx) ), TP_fast_assign( __entry->dev = VFS_I(args->dp)->i_sb->s_dev; __entry->ino = I_INO(args->dp); __entry->op_flags = args->op_flags; __entry->idx = idx; ), TP_printk("dev %d:%d ino 0x%llx op_flags %s index %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS), __entry->idx) ) #define DEFINE_DIR2_SPACE_EVENT(name) \ DEFINE_EVENT(xfs_dir2_space_class, name, \ TP_PROTO(struct xfs_da_args *args, int idx), \ TP_ARGS(args, idx)) DEFINE_DIR2_SPACE_EVENT(xfs_dir2_leafn_add); DEFINE_DIR2_SPACE_EVENT(xfs_dir2_leafn_remove); DEFINE_DIR2_SPACE_EVENT(xfs_dir2_grow_inode); DEFINE_DIR2_SPACE_EVENT(xfs_dir2_shrink_inode); TRACE_EVENT(xfs_dir2_leafn_moveents, TP_PROTO(struct xfs_da_args *args, int src_idx, int dst_idx, int count), TP_ARGS(args, src_idx, dst_idx, count), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(uint32_t, op_flags) __field(int, src_idx) __field(int, dst_idx) __field(int, count) ), TP_fast_assign( __entry->dev = VFS_I(args->dp)->i_sb->s_dev; __entry->ino = I_INO(args->dp); __entry->op_flags = args->op_flags; __entry->src_idx = src_idx; __entry->dst_idx = dst_idx; __entry->count = count; ), TP_printk("dev %d:%d ino 0x%llx op_flags %s " "src_idx %d dst_idx %d count %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_flags(__entry->op_flags, "|", XFS_DA_OP_FLAGS), __entry->src_idx, __entry->dst_idx, __entry->count) ); #define XFS_SWAPEXT_INODES \ { 0, "target" }, \ { 1, "temp" } TRACE_DEFINE_ENUM(XFS_DINODE_FMT_DEV); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_LOCAL); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_EXTENTS); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_BTREE); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_UUID); TRACE_DEFINE_ENUM(XFS_DINODE_FMT_META_BTREE); DECLARE_EVENT_CLASS(xfs_swap_extent_class, TP_PROTO(struct xfs_inode *ip, int which), TP_ARGS(ip, which), TP_STRUCT__entry( __field(dev_t, dev) __field(int, which) __field(xfs_ino_t, ino) __field(int, format) __field(xfs_extnum_t, nex) __field(int, broot_size) __field(int, fork_off) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->which = which; __entry->ino = I_INO(ip); __entry->format = ip->i_df.if_format; __entry->nex = ip->i_df.if_nextents; __entry->broot_size = ip->i_df.if_broot_bytes; __entry->fork_off = xfs_inode_fork_boff(ip); ), TP_printk("dev %d:%d ino 0x%llx (%s), %s format, num_extents %llu, " "broot size %d, forkoff 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_symbolic(__entry->which, XFS_SWAPEXT_INODES), __print_symbolic(__entry->format, XFS_INODE_FORMAT_STR), __entry->nex, __entry->broot_size, __entry->fork_off) ) #define DEFINE_SWAPEXT_EVENT(name) \ DEFINE_EVENT(xfs_swap_extent_class, name, \ TP_PROTO(struct xfs_inode *ip, int which), \ TP_ARGS(ip, which)) DEFINE_SWAPEXT_EVENT(xfs_swap_extent_before); DEFINE_SWAPEXT_EVENT(xfs_swap_extent_after); TRACE_EVENT(xfs_log_recover, TP_PROTO(struct xlog *log, xfs_daddr_t headblk, xfs_daddr_t tailblk), TP_ARGS(log, headblk, tailblk), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_daddr_t, headblk) __field(xfs_daddr_t, tailblk) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->headblk = headblk; __entry->tailblk = tailblk; ), TP_printk("dev %d:%d headblk 0x%llx tailblk 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->headblk, __entry->tailblk) ) TRACE_EVENT(xfs_log_recover_record, TP_PROTO(struct xlog *log, struct xlog_rec_header *rhead, int pass), TP_ARGS(log, rhead, pass), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_lsn_t, lsn) __field(int, len) __field(int, num_logops) __field(int, pass) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->lsn = be64_to_cpu(rhead->h_lsn); __entry->len = be32_to_cpu(rhead->h_len); __entry->num_logops = be32_to_cpu(rhead->h_num_logops); __entry->pass = pass; ), TP_printk("dev %d:%d lsn 0x%llx len 0x%x num_logops 0x%x pass %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lsn, __entry->len, __entry->num_logops, __entry->pass) ) DECLARE_EVENT_CLASS(xfs_log_recover_item_class, TP_PROTO(struct xlog *log, struct xlog_recover *trans, struct xlog_recover_item *item, int pass), TP_ARGS(log, trans, item, pass), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, item) __field(xlog_tid_t, tid) __field(xfs_lsn_t, lsn) __field(int, type) __field(int, pass) __field(int, count) __field(int, total) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->item = (unsigned long)item; __entry->tid = trans->r_log_tid; __entry->lsn = trans->r_lsn; __entry->type = ITEM_TYPE(item); __entry->pass = pass; __entry->count = item->ri_cnt; __entry->total = item->ri_total; ), TP_printk("dev %d:%d tid 0x%x lsn 0x%llx, pass %d, item %p, " "item type %s item region count/total %d/%d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->lsn, __entry->pass, (void *)__entry->item, __print_symbolic(__entry->type, XFS_LI_TYPE_DESC), __entry->count, __entry->total) ) #define DEFINE_LOG_RECOVER_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_item_class, name, \ TP_PROTO(struct xlog *log, struct xlog_recover *trans, \ struct xlog_recover_item *item, int pass), \ TP_ARGS(log, trans, item, pass)) DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_add); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_add_cont); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_head); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_reorder_tail); DEFINE_LOG_RECOVER_ITEM(xfs_log_recover_item_recover); DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class, TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), TP_ARGS(log, buf_f), TP_STRUCT__entry( __field(dev_t, dev) __field(int64_t, blkno) __field(unsigned short, len) __field(unsigned short, flags) __field(unsigned short, size) __field(unsigned int, map_size) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->blkno = buf_f->blf_blkno; __entry->len = buf_f->blf_len; __entry->flags = buf_f->blf_flags; __entry->size = buf_f->blf_size; __entry->map_size = buf_f->blf_map_size; ), TP_printk("dev %d:%d daddr 0x%llx, bbcount 0x%x, flags 0x%x, size %d, " "map_size %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->blkno, __entry->len, __entry->flags, __entry->size, __entry->map_size) ) #define DEFINE_LOG_RECOVER_BUF_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_buf_item_class, name, \ TP_PROTO(struct xlog *log, struct xfs_buf_log_format *buf_f), \ TP_ARGS(log, buf_f)) DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_not_cancel); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_cancel); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_cancel_add); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_cancel_ref_inc); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_recover); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_skip); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_inode_buf); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_reg_buf); DEFINE_LOG_RECOVER_BUF_ITEM(xfs_log_recover_buf_dquot_buf); DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class, TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), TP_ARGS(log, in_f), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(unsigned short, size) __field(int, fields) __field(unsigned short, asize) __field(unsigned short, dsize) __field(int64_t, blkno) __field(int, len) __field(int, boffset) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->ino = in_f->ilf_ino; __entry->size = in_f->ilf_size; __entry->fields = in_f->ilf_fields; __entry->asize = in_f->ilf_asize; __entry->dsize = in_f->ilf_dsize; __entry->blkno = in_f->ilf_blkno; __entry->len = in_f->ilf_len; __entry->boffset = in_f->ilf_boffset; ), TP_printk("dev %d:%d ino 0x%llx, size %u, fields 0x%x, asize %d, " "dsize %d, daddr 0x%llx, bbcount 0x%x, boffset %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->size, __entry->fields, __entry->asize, __entry->dsize, __entry->blkno, __entry->len, __entry->boffset) ) #define DEFINE_LOG_RECOVER_INO_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_ino_item_class, name, \ TP_PROTO(struct xlog *log, struct xfs_inode_log_format *in_f), \ TP_ARGS(log, in_f)) DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_recover); DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_cancel); DEFINE_LOG_RECOVER_INO_ITEM(xfs_log_recover_inode_skip); DECLARE_EVENT_CLASS(xfs_log_recover_icreate_item_class, TP_PROTO(struct xlog *log, struct xfs_icreate_log *in_f), TP_ARGS(log, in_f), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(unsigned int, count) __field(unsigned int, isize) __field(xfs_agblock_t, length) __field(unsigned int, gen) ), TP_fast_assign( __entry->dev = log->l_mp->m_super->s_dev; __entry->agno = be32_to_cpu(in_f->icl_ag); __entry->agbno = be32_to_cpu(in_f->icl_agbno); __entry->count = be32_to_cpu(in_f->icl_count); __entry->isize = be32_to_cpu(in_f->icl_isize); __entry->length = be32_to_cpu(in_f->icl_length); __entry->gen = be32_to_cpu(in_f->icl_gen); ), TP_printk("dev %d:%d agno 0x%x agbno 0x%x fsbcount 0x%x ireccount %u isize %u gen 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agbno, __entry->length, __entry->count, __entry->isize, __entry->gen) ) #define DEFINE_LOG_RECOVER_ICREATE_ITEM(name) \ DEFINE_EVENT(xfs_log_recover_icreate_item_class, name, \ TP_PROTO(struct xlog *log, struct xfs_icreate_log *in_f), \ TP_ARGS(log, in_f)) DEFINE_LOG_RECOVER_ICREATE_ITEM(xfs_log_recover_icreate_cancel); DEFINE_LOG_RECOVER_ICREATE_ITEM(xfs_log_recover_icreate_recover); DECLARE_EVENT_CLASS(xfs_discard_class, TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, xfs_extlen_t len), TP_ARGS(xg, agbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = xg->xg_mount->m_super->s_dev; __entry->type = xg->xg_type; __entry->agno = xg->xg_gno; __entry->agbno = agbno; __entry->len = len; ), TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->agbno, __entry->len) ) #define DEFINE_DISCARD_EVENT(name) \ DEFINE_EVENT(xfs_discard_class, name, \ TP_PROTO(const struct xfs_group *xg, xfs_agblock_t agbno, \ xfs_extlen_t len), \ TP_ARGS(xg, agbno, len)) DEFINE_DISCARD_EVENT(xfs_discard_extent); DEFINE_DISCARD_EVENT(xfs_discard_toosmall); DEFINE_DISCARD_EVENT(xfs_discard_exclude); DEFINE_DISCARD_EVENT(xfs_discard_busy); DECLARE_EVENT_CLASS(xfs_rtdiscard_class, TP_PROTO(struct xfs_mount *mp, xfs_rtblock_t rtbno, xfs_rtblock_t len), TP_ARGS(mp, rtbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_rtblock_t, rtbno) __field(xfs_rtblock_t, len) ), TP_fast_assign( __entry->dev = mp->m_rtdev_targp->bt_dev; __entry->rtbno = rtbno; __entry->len = len; ), TP_printk("dev %d:%d rtbno 0x%llx rtbcount 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->rtbno, __entry->len) ) #define DEFINE_RTDISCARD_EVENT(name) \ DEFINE_EVENT(xfs_rtdiscard_class, name, \ TP_PROTO(struct xfs_mount *mp, \ xfs_rtblock_t rtbno, xfs_rtblock_t len), \ TP_ARGS(mp, rtbno, len)) DEFINE_RTDISCARD_EVENT(xfs_discard_rtextent); DEFINE_RTDISCARD_EVENT(xfs_discard_rttoosmall); DECLARE_EVENT_CLASS(xfs_btree_cur_class, TP_PROTO(struct xfs_btree_cur *cur, int level, struct xfs_buf *bp), TP_ARGS(cur, level, bp), TP_STRUCT__entry( __field(dev_t, dev) __string(name, cur->bc_ops->name) __field(int, level) __field(int, nlevels) __field(int, ptr) __field(xfs_daddr_t, daddr) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __assign_str(name); __entry->level = level; __entry->nlevels = cur->bc_nlevels; __entry->ptr = cur->bc_levels[level].ptr; __entry->daddr = bp ? xfs_buf_daddr(bp) : -1; ), TP_printk("dev %d:%d %sbt level %d/%d ptr %d daddr 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->level, __entry->nlevels, __entry->ptr, (unsigned long long)__entry->daddr) ) #define DEFINE_BTREE_CUR_EVENT(name) \ DEFINE_EVENT(xfs_btree_cur_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, int level, struct xfs_buf *bp), \ TP_ARGS(cur, level, bp)) DEFINE_BTREE_CUR_EVENT(xfs_btree_updkeys); DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range); TRACE_EVENT(xfs_btree_alloc_block, TP_PROTO(struct xfs_btree_cur *cur, union xfs_btree_ptr *ptr, int stat, int error), TP_ARGS(cur, ptr, stat, error), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_ino_t, ino) __string(name, cur->bc_ops->name) __field(int, error) __field(xfs_agblock_t, agbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_INODE: __entry->agno = 0; __entry->ino = I_INO(cur->bc_ino.ip); break; case XFS_BTREE_TYPE_AG: __entry->agno = cur->bc_group->xg_gno; __entry->ino = 0; break; case XFS_BTREE_TYPE_MEM: __entry->agno = 0; __entry->ino = 0; break; } __assign_str(name); __entry->error = error; if (!error && stat) { if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { xfs_fsblock_t fsb = be64_to_cpu(ptr->l); __entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsb); __entry->agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsb); } else { __entry->agbno = be32_to_cpu(ptr->s); } } else { __entry->agbno = NULLAGBLOCK; } ), TP_printk("dev %d:%d %sbt agno 0x%x ino 0x%llx agbno 0x%x error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->agno, __entry->ino, __entry->agbno, __entry->error) ); TRACE_EVENT(xfs_btree_free_block, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_buf *bp), TP_ARGS(cur, bp), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_ino_t, ino) __string(name, cur->bc_ops->name) __field(xfs_agblock_t, agbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->agno = xfs_daddr_to_agno(cur->bc_mp, xfs_buf_daddr(bp)); if (cur->bc_ops->type == XFS_BTREE_TYPE_INODE) __entry->ino = I_INO(cur->bc_ino.ip); else __entry->ino = 0; __assign_str(name); __entry->agbno = xfs_daddr_to_agbno(cur->bc_mp, xfs_buf_daddr(bp)); ), TP_printk("dev %d:%d %sbt agno 0x%x ino 0x%llx agbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->agno, __entry->ino, __entry->agbno) ); /* deferred ops */ struct xfs_defer_pending; DECLARE_EVENT_CLASS(xfs_defer_class, TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), TP_ARGS(tp, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(struct xfs_trans *, tp) __field(char, committed) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = tp->t_mountp->m_super->s_dev; __entry->tp = tp; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d tp %p caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tp, (char *)__entry->caller_ip) ) #define DEFINE_DEFER_EVENT(name) \ DEFINE_EVENT(xfs_defer_class, name, \ TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \ TP_ARGS(tp, caller_ip)) DECLARE_EVENT_CLASS(xfs_defer_error_class, TP_PROTO(struct xfs_trans *tp, int error), TP_ARGS(tp, error), TP_STRUCT__entry( __field(dev_t, dev) __field(struct xfs_trans *, tp) __field(char, committed) __field(int, error) ), TP_fast_assign( __entry->dev = tp->t_mountp->m_super->s_dev; __entry->tp = tp; __entry->error = error; ), TP_printk("dev %d:%d tp %p err %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tp, __entry->error) ) #define DEFINE_DEFER_ERROR_EVENT(name) \ DEFINE_EVENT(xfs_defer_error_class, name, \ TP_PROTO(struct xfs_trans *tp, int error), \ TP_ARGS(tp, error)) DECLARE_EVENT_CLASS(xfs_defer_pending_class, TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp), TP_ARGS(mp, dfp), TP_STRUCT__entry( __field(dev_t, dev) __string(name, dfp->dfp_ops->name) __field(void *, intent) __field(unsigned int, flags) __field(char, committed) __field(int, nr) ), TP_fast_assign( __entry->dev = mp ? mp->m_super->s_dev : 0; __assign_str(name); __entry->intent = dfp->dfp_intent; __entry->flags = dfp->dfp_flags; __entry->committed = dfp->dfp_done != NULL; __entry->nr = dfp->dfp_count; ), TP_printk("dev %d:%d optype %s intent %p flags %s committed %d nr %d", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->intent, __print_flags(__entry->flags, "|", XFS_DEFER_PENDING_STRINGS), __entry->committed, __entry->nr) ) #define DEFINE_DEFER_PENDING_EVENT(name) \ DEFINE_EVENT(xfs_defer_pending_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp), \ TP_ARGS(mp, dfp)) DEFINE_DEFER_EVENT(xfs_defer_cancel); DEFINE_DEFER_EVENT(xfs_defer_trans_roll); DEFINE_DEFER_EVENT(xfs_defer_trans_abort); DEFINE_DEFER_EVENT(xfs_defer_finish); DEFINE_DEFER_EVENT(xfs_defer_finish_done); DEFINE_DEFER_ERROR_EVENT(xfs_defer_trans_roll_error); DEFINE_DEFER_ERROR_EVENT(xfs_defer_finish_error); DEFINE_DEFER_PENDING_EVENT(xfs_defer_create_intent); DEFINE_DEFER_PENDING_EVENT(xfs_defer_cancel_list); DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_finish); DEFINE_DEFER_PENDING_EVENT(xfs_defer_pending_abort); DEFINE_DEFER_PENDING_EVENT(xfs_defer_relog_intent); DEFINE_DEFER_PENDING_EVENT(xfs_defer_isolate_paused); DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_pause); DEFINE_DEFER_PENDING_EVENT(xfs_defer_item_unpause); DECLARE_EVENT_CLASS(xfs_free_extent_deferred_class, TP_PROTO(struct xfs_mount *mp, struct xfs_extent_free_item *free), TP_ARGS(mp, free), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_extlen_t, len) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->type = free->xefi_group->xg_type; __entry->agno = free->xefi_group->xg_gno; __entry->agbno = xfs_fsb_to_gbno(mp, free->xefi_startblock, free->xefi_group->xg_type); __entry->len = free->xefi_blockcount; __entry->flags = free->xefi_flags; ), TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->agbno, __entry->len, __entry->flags) ); #define DEFINE_FREE_EXTENT_DEFERRED_EVENT(name) \ DEFINE_EVENT(xfs_free_extent_deferred_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_extent_free_item *free), \ TP_ARGS(mp, free)) DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_agfl_free_deferred); DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_extent_free_defer); DEFINE_FREE_EXTENT_DEFERRED_EVENT(xfs_extent_free_deferred); DECLARE_EVENT_CLASS(xfs_defer_pending_item_class, TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp, void *item), TP_ARGS(mp, dfp, item), TP_STRUCT__entry( __field(dev_t, dev) __string(name, dfp->dfp_ops->name) __field(void *, intent) __field(void *, item) __field(char, committed) __field(unsigned int, flags) __field(int, nr) ), TP_fast_assign( __entry->dev = mp ? mp->m_super->s_dev : 0; __assign_str(name); __entry->intent = dfp->dfp_intent; __entry->item = item; __entry->committed = dfp->dfp_done != NULL; __entry->flags = dfp->dfp_flags; __entry->nr = dfp->dfp_count; ), TP_printk("dev %d:%d optype %s intent %p item %p flags %s committed %d nr %d", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->intent, __entry->item, __print_flags(__entry->flags, "|", XFS_DEFER_PENDING_STRINGS), __entry->committed, __entry->nr) ) #define DEFINE_DEFER_PENDING_ITEM_EVENT(name) \ DEFINE_EVENT(xfs_defer_pending_item_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_defer_pending *dfp, \ void *item), \ TP_ARGS(mp, dfp, item)) DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_add_item); DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_cancel_item); DEFINE_DEFER_PENDING_ITEM_EVENT(xfs_defer_finish_item); /* rmap tracepoints */ DECLARE_EVENT_CLASS(xfs_rmap_class, TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, const struct xfs_owner_info *oinfo), TP_ARGS(cur, gbno, len, unwritten, oinfo), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) __field(unsigned long, flags) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->gbno = gbno; __entry->len = len; __entry->owner = oinfo->oi_owner; __entry->offset = oinfo->oi_offset; __entry->flags = oinfo->oi_flags; if (unwritten) __entry->flags |= XFS_RMAP_UNWRITTEN; ), TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __entry->len, __entry->owner, __entry->offset, __entry->flags) ); #define DEFINE_RMAP_EVENT(name) \ DEFINE_EVENT(xfs_rmap_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ xfs_agblock_t gbno, xfs_extlen_t len, bool unwritten, \ const struct xfs_owner_info *oinfo), \ TP_ARGS(cur, gbno, len, unwritten, oinfo)) /* btree cursor error/%ip tracepoint class */ DECLARE_EVENT_CLASS(xfs_btree_error_class, TP_PROTO(struct xfs_btree_cur *cur, int error, unsigned long caller_ip), TP_ARGS(cur, error, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_ino_t, ino) __field(int, error) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; switch (cur->bc_ops->type) { case XFS_BTREE_TYPE_INODE: __entry->agno = 0; __entry->ino = I_INO(cur->bc_ino.ip); break; case XFS_BTREE_TYPE_AG: __entry->agno = cur->bc_group->xg_gno; __entry->ino = 0; break; case XFS_BTREE_TYPE_MEM: __entry->agno = 0; __entry->ino = 0; break; } __entry->error = error; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d agno 0x%x ino 0x%llx error %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->ino, __entry->error, (char *)__entry->caller_ip) ); #define DEFINE_BTREE_ERROR_EVENT(name) \ DEFINE_EVENT(xfs_btree_error_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, int error, \ unsigned long caller_ip), \ TP_ARGS(cur, error, caller_ip)) DEFINE_RMAP_EVENT(xfs_rmap_unmap); DEFINE_RMAP_EVENT(xfs_rmap_unmap_done); DEFINE_BTREE_ERROR_EVENT(xfs_rmap_unmap_error); DEFINE_RMAP_EVENT(xfs_rmap_map); DEFINE_RMAP_EVENT(xfs_rmap_map_done); DEFINE_BTREE_ERROR_EVENT(xfs_rmap_map_error); DEFINE_RMAP_EVENT(xfs_rmap_convert); DEFINE_RMAP_EVENT(xfs_rmap_convert_done); DEFINE_BTREE_ERROR_EVENT(xfs_rmap_convert_error); TRACE_EVENT(xfs_rmap_convert_state, TP_PROTO(struct xfs_btree_cur *cur, int state, unsigned long caller_ip), TP_ARGS(cur, state, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(int, state) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->state = state; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d %sno 0x%x state %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->state, (char *)__entry->caller_ip) ); DECLARE_EVENT_CLASS(xfs_rmapbt_class, TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_extlen_t len, uint64_t owner, uint64_t offset, unsigned int flags), TP_ARGS(cur, gbno, len, owner, offset, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) __field(uint64_t, owner) __field(uint64_t, offset) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->gbno = gbno; __entry->len = len; __entry->owner = owner; __entry->offset = offset; __entry->flags = flags; ), TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __entry->len, __entry->owner, __entry->offset, __entry->flags) ); #define DEFINE_RMAPBT_EVENT(name) \ DEFINE_EVENT(xfs_rmapbt_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, \ xfs_agblock_t gbno, xfs_extlen_t len, \ uint64_t owner, uint64_t offset, unsigned int flags), \ TP_ARGS(cur, gbno, len, owner, offset, flags)) TRACE_DEFINE_ENUM(XFS_RMAP_MAP); TRACE_DEFINE_ENUM(XFS_RMAP_MAP_SHARED); TRACE_DEFINE_ENUM(XFS_RMAP_UNMAP); TRACE_DEFINE_ENUM(XFS_RMAP_UNMAP_SHARED); TRACE_DEFINE_ENUM(XFS_RMAP_CONVERT); TRACE_DEFINE_ENUM(XFS_RMAP_CONVERT_SHARED); TRACE_DEFINE_ENUM(XFS_RMAP_ALLOC); TRACE_DEFINE_ENUM(XFS_RMAP_FREE); DECLARE_EVENT_CLASS(xfs_rmap_deferred_class, TP_PROTO(struct xfs_mount *mp, struct xfs_rmap_intent *ri), TP_ARGS(mp, ri), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, owner) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, gbno) __field(int, whichfork) __field(xfs_fileoff_t, l_loff) __field(xfs_filblks_t, l_len) __field(xfs_exntst_t, l_state) __field(int, op) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->type = ri->ri_group->xg_type; __entry->agno = ri->ri_group->xg_gno; __entry->gbno = xfs_fsb_to_gbno(mp, ri->ri_bmap.br_startblock, ri->ri_group->xg_type); __entry->owner = ri->ri_owner; __entry->whichfork = ri->ri_whichfork; __entry->l_loff = ri->ri_bmap.br_startoff; __entry->l_len = ri->ri_bmap.br_blockcount; __entry->l_state = ri->ri_bmap.br_state; __entry->op = ri->ri_type; ), TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x owner 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_RMAP_INTENT_STRINGS), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __entry->owner, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->l_loff, __entry->l_len, __entry->l_state) ); #define DEFINE_RMAP_DEFERRED_EVENT(name) \ DEFINE_EVENT(xfs_rmap_deferred_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_rmap_intent *ri), \ TP_ARGS(mp, ri)) DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_defer); DEFINE_RMAP_DEFERRED_EVENT(xfs_rmap_deferred); DEFINE_RMAPBT_EVENT(xfs_rmap_update); DEFINE_RMAPBT_EVENT(xfs_rmap_insert); DEFINE_RMAPBT_EVENT(xfs_rmap_delete); DEFINE_BTREE_ERROR_EVENT(xfs_rmap_insert_error); DEFINE_BTREE_ERROR_EVENT(xfs_rmap_delete_error); DEFINE_BTREE_ERROR_EVENT(xfs_rmap_update_error); DEFINE_RMAPBT_EVENT(xfs_rmap_find_left_neighbor_candidate); DEFINE_RMAPBT_EVENT(xfs_rmap_find_left_neighbor_query); DEFINE_RMAPBT_EVENT(xfs_rmap_lookup_le_range_candidate); DEFINE_RMAPBT_EVENT(xfs_rmap_lookup_le_range); DEFINE_RMAPBT_EVENT(xfs_rmap_lookup_le_range_result); DEFINE_RMAPBT_EVENT(xfs_rmap_find_right_neighbor_result); DEFINE_RMAPBT_EVENT(xfs_rmap_find_left_neighbor_result); /* deferred bmbt updates */ TRACE_DEFINE_ENUM(XFS_BMAP_MAP); TRACE_DEFINE_ENUM(XFS_BMAP_UNMAP); DECLARE_EVENT_CLASS(xfs_bmap_deferred_class, TP_PROTO(struct xfs_bmap_intent *bi), TP_ARGS(bi), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_ino_t, ino) __field(unsigned long long, gbno) __field(int, whichfork) __field(xfs_fileoff_t, l_loff) __field(xfs_filblks_t, l_len) __field(xfs_exntst_t, l_state) __field(int, op) ), TP_fast_assign( struct xfs_inode *ip = bi->bi_owner; struct xfs_mount *mp = ip->i_mount; __entry->dev = mp->m_super->s_dev; __entry->type = bi->bi_group->xg_type; __entry->agno = bi->bi_group->xg_gno; if (bi->bi_group->xg_type == XG_TYPE_RTG && !xfs_has_rtgroups(mp)) { /* * Legacy rt filesystems do not have allocation groups * ondisk. We emulate this incore with one gigantic * rtgroup whose size can exceed a 32-bit block number. * For this tracepoint, we report group 0 and a 64-bit * group block number. */ __entry->gbno = bi->bi_bmap.br_startblock; } else { __entry->gbno = xfs_fsb_to_gbno(mp, bi->bi_bmap.br_startblock, bi->bi_group->xg_type); } __entry->ino = I_INO(ip); __entry->whichfork = bi->bi_whichfork; __entry->l_loff = bi->bi_bmap.br_startoff; __entry->l_len = bi->bi_bmap.br_blockcount; __entry->l_state = bi->bi_bmap.br_state; __entry->op = bi->bi_type; ), TP_printk("dev %d:%d op %s ino 0x%llx %sno 0x%x gbno 0x%llx %s fileoff 0x%llx fsbcount 0x%llx state %d", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_BMAP_INTENT_STRINGS), __entry->ino, __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->l_loff, __entry->l_len, __entry->l_state) ); #define DEFINE_BMAP_DEFERRED_EVENT(name) \ DEFINE_EVENT(xfs_bmap_deferred_class, name, \ TP_PROTO(struct xfs_bmap_intent *bi), \ TP_ARGS(bi)) DEFINE_BMAP_DEFERRED_EVENT(xfs_bmap_defer); DEFINE_BMAP_DEFERRED_EVENT(xfs_bmap_deferred); /* per-AG reservation */ DECLARE_EVENT_CLASS(xfs_ag_resv_class, TP_PROTO(struct xfs_perag *pag, enum xfs_ag_resv_type resv, xfs_extlen_t len), TP_ARGS(pag, resv, len), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(int, resv) __field(xfs_extlen_t, freeblks) __field(xfs_extlen_t, flcount) __field(xfs_extlen_t, reserved) __field(xfs_extlen_t, asked) __field(xfs_extlen_t, len) ), TP_fast_assign( struct xfs_ag_resv *r = xfs_perag_resv(pag, resv); __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->resv = resv; __entry->freeblks = pag->pagf_freeblks; __entry->flcount = pag->pagf_flcount; __entry->reserved = r ? r->ar_reserved : 0; __entry->asked = r ? r->ar_asked : 0; __entry->len = len; ), TP_printk("dev %d:%d agno 0x%x resv %d freeblks %u flcount %u " "resv %u ask %u len %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->resv, __entry->freeblks, __entry->flcount, __entry->reserved, __entry->asked, __entry->len) ) #define DEFINE_AG_RESV_EVENT(name) \ DEFINE_EVENT(xfs_ag_resv_class, name, \ TP_PROTO(struct xfs_perag *pag, enum xfs_ag_resv_type type, \ xfs_extlen_t len), \ TP_ARGS(pag, type, len)) /* per-AG reservation tracepoints */ DEFINE_AG_RESV_EVENT(xfs_ag_resv_init); DEFINE_AG_RESV_EVENT(xfs_ag_resv_free); DEFINE_AG_RESV_EVENT(xfs_ag_resv_alloc_extent); DEFINE_AG_RESV_EVENT(xfs_ag_resv_free_extent); DEFINE_AG_RESV_EVENT(xfs_ag_resv_critical); DEFINE_AG_RESV_EVENT(xfs_ag_resv_needed); TRACE_EVENT(xfs_ag_resv_init_error, TP_PROTO(const struct xfs_perag *pag, int error, unsigned long caller_ip), TP_ARGS(pag, error, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(int, error) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->error = error; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d agno 0x%x error %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->error, (char *)__entry->caller_ip) ); /* refcount tracepoint classes */ DECLARE_EVENT_CLASS(xfs_refcount_class, TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_extlen_t len), TP_ARGS(cur, gbno, len), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->gbno = gbno; __entry->len = len; ), TP_printk("dev %d:%d %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, \ xfs_extlen_t len), \ TP_ARGS(cur, gbno, len)) TRACE_DEFINE_ENUM(XFS_LOOKUP_EQi); TRACE_DEFINE_ENUM(XFS_LOOKUP_LEi); TRACE_DEFINE_ENUM(XFS_LOOKUP_GEi); TRACE_EVENT(xfs_refcount_lookup, TP_PROTO(struct xfs_btree_cur *cur, xfs_agblock_t gbno, xfs_lookup_t dir), TP_ARGS(cur, gbno, dir), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, gbno) __field(xfs_lookup_t, dir) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->gbno = gbno; __entry->dir = dir; ), TP_printk("dev %d:%d %sno 0x%x gbno 0x%x cmp %s(%d)", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __print_symbolic(__entry->dir, XFS_AG_BTREE_CMP_FORMAT_STR), __entry->dir) ) /* single-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_extent_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec), TP_ARGS(cur, irec), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; ), TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount) ) #define DEFINE_REFCOUNT_EXTENT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_extent_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec), \ TP_ARGS(cur, irec)) /* single-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, xfs_agblock_t gbno), TP_ARGS(cur, irec, gbno), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, domain) __field(xfs_agblock_t, startblock) __field(xfs_extlen_t, blockcount) __field(xfs_nlink_t, refcount) __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->domain = irec->rc_domain; __entry->startblock = irec->rc_startblock; __entry->blockcount = irec->rc_blockcount; __entry->refcount = irec->rc_refcount; __entry->gbno = gbno; ), TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->domain, XFS_REFC_DOMAIN_STRINGS), __entry->startblock, __entry->blockcount, __entry->refcount, __entry->gbno) ) #define DEFINE_REFCOUNT_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *irec, \ xfs_agblock_t gbno), \ TP_ARGS(cur, irec, gbno)) /* double-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, struct xfs_refcount_irec *i2), TP_ARGS(cur, i1, i2), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; ), TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount) ) #define DEFINE_REFCOUNT_DOUBLE_EXTENT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_double_extent_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, \ struct xfs_refcount_irec *i2), \ TP_ARGS(cur, i1, i2)) /* double-rcext and an agbno tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, struct xfs_refcount_irec *i2, xfs_agblock_t gbno), TP_ARGS(cur, i1, i2, gbno), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) __field(xfs_agblock_t, gbno) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; __entry->gbno = gbno; ), TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " "dom %s gbno 0x%x fsbcount 0x%x refcount %u @ gbno 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, __entry->gbno) ) #define DEFINE_REFCOUNT_DOUBLE_EXTENT_AT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_double_extent_at_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, \ struct xfs_refcount_irec *i2, xfs_agblock_t gbno), \ TP_ARGS(cur, i1, i2, gbno)) /* triple-rcext tracepoint class */ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class, TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, struct xfs_refcount_irec *i2, struct xfs_refcount_irec *i3), TP_ARGS(cur, i1, i2, i3), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(enum xfs_refc_domain, i1_domain) __field(xfs_agblock_t, i1_startblock) __field(xfs_extlen_t, i1_blockcount) __field(xfs_nlink_t, i1_refcount) __field(enum xfs_refc_domain, i2_domain) __field(xfs_agblock_t, i2_startblock) __field(xfs_extlen_t, i2_blockcount) __field(xfs_nlink_t, i2_refcount) __field(enum xfs_refc_domain, i3_domain) __field(xfs_agblock_t, i3_startblock) __field(xfs_extlen_t, i3_blockcount) __field(xfs_nlink_t, i3_refcount) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __entry->type = cur->bc_group->xg_type; __entry->agno = cur->bc_group->xg_gno; __entry->i1_domain = i1->rc_domain; __entry->i1_startblock = i1->rc_startblock; __entry->i1_blockcount = i1->rc_blockcount; __entry->i1_refcount = i1->rc_refcount; __entry->i2_domain = i2->rc_domain; __entry->i2_startblock = i2->rc_startblock; __entry->i2_blockcount = i2->rc_blockcount; __entry->i2_refcount = i2->rc_refcount; __entry->i3_domain = i3->rc_domain; __entry->i3_startblock = i3->rc_startblock; __entry->i3_blockcount = i3->rc_blockcount; __entry->i3_refcount = i3->rc_refcount; ), TP_printk("dev %d:%d %sno 0x%x dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " "dom %s gbno 0x%x fsbcount 0x%x refcount %u -- " "dom %s gbno 0x%x fsbcount 0x%x refcount %u", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __print_symbolic(__entry->i1_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i1_startblock, __entry->i1_blockcount, __entry->i1_refcount, __print_symbolic(__entry->i2_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i2_startblock, __entry->i2_blockcount, __entry->i2_refcount, __print_symbolic(__entry->i3_domain, XFS_REFC_DOMAIN_STRINGS), __entry->i3_startblock, __entry->i3_blockcount, __entry->i3_refcount) ); #define DEFINE_REFCOUNT_TRIPLE_EXTENT_EVENT(name) \ DEFINE_EVENT(xfs_refcount_triple_extent_class, name, \ TP_PROTO(struct xfs_btree_cur *cur, struct xfs_refcount_irec *i1, \ struct xfs_refcount_irec *i2, struct xfs_refcount_irec *i3), \ TP_ARGS(cur, i1, i2, i3)) /* refcount btree tracepoints */ DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_get); DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_update); DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_insert); DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_delete); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_insert_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_delete_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_update_error); /* refcount adjustment tracepoints */ DEFINE_REFCOUNT_EVENT(xfs_refcount_increase); DEFINE_REFCOUNT_EVENT(xfs_refcount_decrease); DEFINE_REFCOUNT_EVENT(xfs_refcount_cow_increase); DEFINE_REFCOUNT_EVENT(xfs_refcount_cow_decrease); DEFINE_REFCOUNT_TRIPLE_EXTENT_EVENT(xfs_refcount_merge_center_extents); DEFINE_REFCOUNT_EXTENT_EVENT(xfs_refcount_modify_extent); DEFINE_REFCOUNT_EXTENT_AT_EVENT(xfs_refcount_split_extent); DEFINE_REFCOUNT_DOUBLE_EXTENT_EVENT(xfs_refcount_merge_left_extent); DEFINE_REFCOUNT_DOUBLE_EXTENT_EVENT(xfs_refcount_merge_right_extent); DEFINE_REFCOUNT_DOUBLE_EXTENT_AT_EVENT(xfs_refcount_find_left_extent); DEFINE_REFCOUNT_DOUBLE_EXTENT_AT_EVENT(xfs_refcount_find_right_extent); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_adjust_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_adjust_cow_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_merge_center_extents_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_modify_extent_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_split_extent_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_merge_left_extent_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_merge_right_extent_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_find_left_extent_error); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_find_right_extent_error); /* reflink helpers */ DEFINE_REFCOUNT_EVENT(xfs_refcount_find_shared); DEFINE_REFCOUNT_EVENT(xfs_refcount_find_shared_result); DEFINE_BTREE_ERROR_EVENT(xfs_refcount_find_shared_error); TRACE_DEFINE_ENUM(XFS_REFCOUNT_INCREASE); TRACE_DEFINE_ENUM(XFS_REFCOUNT_DECREASE); TRACE_DEFINE_ENUM(XFS_REFCOUNT_ALLOC_COW); TRACE_DEFINE_ENUM(XFS_REFCOUNT_FREE_COW); DECLARE_EVENT_CLASS(xfs_refcount_deferred_class, TP_PROTO(struct xfs_mount *mp, struct xfs_refcount_intent *refc), TP_ARGS(mp, refc), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(xfs_agnumber_t, agno) __field(int, op) __field(xfs_agblock_t, gbno) __field(xfs_extlen_t, len) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->type = refc->ri_group->xg_type; __entry->agno = refc->ri_group->xg_gno; __entry->op = refc->ri_type; __entry->gbno = xfs_fsb_to_gbno(mp, refc->ri_startblock, refc->ri_group->xg_type); __entry->len = refc->ri_blockcount; ), TP_printk("dev %d:%d op %s %sno 0x%x gbno 0x%x fsbcount 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->op, XFS_REFCOUNT_INTENT_STRINGS), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->agno, __entry->gbno, __entry->len) ); #define DEFINE_REFCOUNT_DEFERRED_EVENT(name) \ DEFINE_EVENT(xfs_refcount_deferred_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_refcount_intent *refc), \ TP_ARGS(mp, refc)) DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_defer); DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_deferred); DEFINE_REFCOUNT_DEFERRED_EVENT(xfs_refcount_finish_one_leftover); /* simple inode-based error/%ip tracepoint class */ DECLARE_EVENT_CLASS(xfs_inode_error_class, TP_PROTO(struct xfs_inode *ip, int error, unsigned long caller_ip), TP_ARGS(ip, error, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(int, error) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->error = error; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ino 0x%llx error %d caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->error, (char *)__entry->caller_ip) ); #define DEFINE_INODE_ERROR_EVENT(name) \ DEFINE_EVENT(xfs_inode_error_class, name, \ TP_PROTO(struct xfs_inode *ip, int error, \ unsigned long caller_ip), \ TP_ARGS(ip, error, caller_ip)) /* reflink tracepoint classes */ /* two-file io tracepoint class */ DECLARE_EVENT_CLASS(xfs_double_io_class, TP_PROTO(struct xfs_inode *src, xfs_off_t soffset, xfs_off_t len, struct xfs_inode *dest, xfs_off_t doffset), TP_ARGS(src, soffset, len, dest, doffset), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, src_ino) __field(loff_t, src_isize) __field(loff_t, src_disize) __field(loff_t, src_offset) __field(long long, len) __field(xfs_ino_t, dest_ino) __field(loff_t, dest_isize) __field(loff_t, dest_disize) __field(loff_t, dest_offset) ), TP_fast_assign( __entry->dev = VFS_I(src)->i_sb->s_dev; __entry->src_ino = I_INO(src); __entry->src_isize = VFS_I(src)->i_size; __entry->src_disize = src->i_disk_size; __entry->src_offset = soffset; __entry->len = len; __entry->dest_ino = I_INO(dest); __entry->dest_isize = VFS_I(dest)->i_size; __entry->dest_disize = dest->i_disk_size; __entry->dest_offset = doffset; ), TP_printk("dev %d:%d bytecount 0x%llx " "ino 0x%llx isize 0x%llx disize 0x%llx pos 0x%llx -> " "ino 0x%llx isize 0x%llx disize 0x%llx pos 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->len, __entry->src_ino, __entry->src_isize, __entry->src_disize, __entry->src_offset, __entry->dest_ino, __entry->dest_isize, __entry->dest_disize, __entry->dest_offset) ) #define DEFINE_DOUBLE_IO_EVENT(name) \ DEFINE_EVENT(xfs_double_io_class, name, \ TP_PROTO(struct xfs_inode *src, xfs_off_t soffset, xfs_off_t len, \ struct xfs_inode *dest, xfs_off_t doffset), \ TP_ARGS(src, soffset, len, dest, doffset)) /* inode/irec events */ DECLARE_EVENT_CLASS(xfs_inode_irec_class, TP_PROTO(struct xfs_inode *ip, struct xfs_bmbt_irec *irec), TP_ARGS(ip, irec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fileoff_t, lblk) __field(xfs_extlen_t, len) __field(xfs_fsblock_t, pblk) __field(int, state) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->lblk = irec->br_startoff; __entry->len = irec->br_blockcount; __entry->pblk = irec->br_startblock; __entry->state = irec->br_state; ), TP_printk("dev %d:%d ino 0x%llx fileoff 0x%llx fsbcount 0x%x startblock 0x%llx st %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->lblk, __entry->len, __entry->pblk, __entry->state) ); #define DEFINE_INODE_IREC_EVENT(name) \ DEFINE_EVENT(xfs_inode_irec_class, name, \ TP_PROTO(struct xfs_inode *ip, struct xfs_bmbt_irec *irec), \ TP_ARGS(ip, irec)) /* inode iomap invalidation events */ DECLARE_EVENT_CLASS(xfs_wb_invalid_class, TP_PROTO(struct xfs_inode *ip, const struct iomap *iomap, unsigned int wpcseq, int whichfork), TP_ARGS(ip, iomap, wpcseq, whichfork), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(u64, addr) __field(loff_t, pos) __field(u64, len) __field(u16, type) __field(u16, flags) __field(u32, wpcseq) __field(u32, forkseq) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->addr = iomap->addr; __entry->pos = iomap->offset; __entry->len = iomap->length; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->wpcseq = wpcseq; __entry->forkseq = READ_ONCE(xfs_ifork_ptr(ip, whichfork)->if_seq); ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx addr 0x%llx bytecount 0x%llx type 0x%x flags 0x%x wpcseq 0x%x forkseq 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->addr, __entry->len, __entry->type, __entry->flags, __entry->wpcseq, __entry->forkseq) ); #define DEFINE_WB_INVALID_EVENT(name) \ DEFINE_EVENT(xfs_wb_invalid_class, name, \ TP_PROTO(struct xfs_inode *ip, const struct iomap *iomap, unsigned int wpcseq, int whichfork), \ TP_ARGS(ip, iomap, wpcseq, whichfork)) DEFINE_WB_INVALID_EVENT(xfs_wb_cow_iomap_invalid); DEFINE_WB_INVALID_EVENT(xfs_wb_data_iomap_invalid); DECLARE_EVENT_CLASS(xfs_iomap_invalid_class, TP_PROTO(struct xfs_inode *ip, const struct iomap *iomap), TP_ARGS(ip, iomap), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(u64, addr) __field(loff_t, pos) __field(u64, len) __field(u64, validity_cookie) __field(u64, inodeseq) __field(u16, type) __field(u16, flags) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->ino = I_INO(ip); __entry->addr = iomap->addr; __entry->pos = iomap->offset; __entry->len = iomap->length; __entry->validity_cookie = iomap->validity_cookie; __entry->type = iomap->type; __entry->flags = iomap->flags; __entry->inodeseq = xfs_iomap_inode_sequence(ip, iomap->flags); ), TP_printk("dev %d:%d ino 0x%llx pos 0x%llx addr 0x%llx bytecount 0x%llx type 0x%x flags 0x%x validity_cookie 0x%llx inodeseq 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->pos, __entry->addr, __entry->len, __entry->type, __entry->flags, __entry->validity_cookie, __entry->inodeseq) ); #define DEFINE_IOMAP_INVALID_EVENT(name) \ DEFINE_EVENT(xfs_iomap_invalid_class, name, \ TP_PROTO(struct xfs_inode *ip, const struct iomap *iomap), \ TP_ARGS(ip, iomap)) DEFINE_IOMAP_INVALID_EVENT(xfs_iomap_invalid); /* refcount/reflink tracepoint definitions */ /* reflink tracepoints */ DEFINE_INODE_EVENT(xfs_reflink_set_inode_flag); DEFINE_INODE_EVENT(xfs_reflink_unset_inode_flag); DEFINE_ITRUNC_EVENT(xfs_reflink_update_inode_size); TRACE_EVENT(xfs_reflink_remap_blocks, TP_PROTO(struct xfs_inode *src, xfs_fileoff_t soffset, xfs_filblks_t len, struct xfs_inode *dest, xfs_fileoff_t doffset), TP_ARGS(src, soffset, len, dest, doffset), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, src_ino) __field(xfs_fileoff_t, src_lblk) __field(xfs_filblks_t, len) __field(xfs_ino_t, dest_ino) __field(xfs_fileoff_t, dest_lblk) ), TP_fast_assign( __entry->dev = VFS_I(src)->i_sb->s_dev; __entry->src_ino = I_INO(src); __entry->src_lblk = soffset; __entry->len = len; __entry->dest_ino = I_INO(dest); __entry->dest_lblk = doffset; ), TP_printk("dev %d:%d fsbcount 0x%llx " "ino 0x%llx fileoff 0x%llx -> ino 0x%llx fileoff 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->len, __entry->src_ino, __entry->src_lblk, __entry->dest_ino, __entry->dest_lblk) ); DEFINE_DOUBLE_IO_EVENT(xfs_reflink_remap_range); DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_set_inode_flag_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_update_inode_size_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_blocks_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_remap_extent_error); DEFINE_INODE_IREC_EVENT(xfs_reflink_remap_extent_src); DEFINE_INODE_IREC_EVENT(xfs_reflink_remap_extent_dest); /* unshare tracepoints */ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_unshare); DEFINE_INODE_ERROR_EVENT(xfs_reflink_unshare_error); /* copy on write */ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_around_shared); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found); DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range); DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_from); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_to); DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap_skip); DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error); DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error); DEFINE_INODE_IREC_EVENT(xfs_reflink_cancel_cow); /* rmap swapext tracepoints */ DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap); DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap_piece); DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_rmap_error); /* fsmap traces */ TRACE_EVENT(xfs_fsmap_mapping, TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno, const struct xfs_fsmap_irec *frec), TP_ARGS(mp, keydev, agno, frec), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(xfs_daddr_t, start_daddr) __field(xfs_daddr_t, len_daddr) __field(uint64_t, owner) __field(uint64_t, offset) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->keydev = new_decode_dev(keydev); __entry->agno = agno; __entry->agbno = frec->rec_key; __entry->start_daddr = frec->start_daddr; __entry->len_daddr = frec->len_daddr; __entry->owner = frec->owner; __entry->offset = frec->offset; __entry->flags = frec->rm_flags; ), TP_printk("dev %d:%d keydev %d:%d agno 0x%x gbno 0x%x start_daddr 0x%llx len_daddr 0x%llx owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, __entry->agbno, __entry->start_daddr, __entry->len_daddr, __entry->owner, __entry->offset, __entry->flags) ); DECLARE_EVENT_CLASS(xfs_fsmap_group_key_class, TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno, const struct xfs_rmap_irec *rmap), TP_ARGS(mp, keydev, agno, rmap), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(uint64_t, owner) __field(uint64_t, offset) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->keydev = new_decode_dev(keydev); __entry->agno = agno; __entry->agbno = rmap->rm_startblock; __entry->owner = rmap->rm_owner; __entry->offset = rmap->rm_offset; __entry->flags = rmap->rm_flags; ), TP_printk("dev %d:%d keydev %d:%d agno 0x%x startblock 0x%x owner 0x%llx fileoff 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->agno, __entry->agbno, __entry->owner, __entry->offset, __entry->flags) ) #define DEFINE_FSMAP_GROUP_KEY_EVENT(name) \ DEFINE_EVENT(xfs_fsmap_group_key_class, name, \ TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno, \ const struct xfs_rmap_irec *rmap), \ TP_ARGS(mp, keydev, agno, rmap)) DEFINE_FSMAP_GROUP_KEY_EVENT(xfs_fsmap_low_group_key); DEFINE_FSMAP_GROUP_KEY_EVENT(xfs_fsmap_high_group_key); DECLARE_EVENT_CLASS(xfs_fsmap_linear_key_class, TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_fsblock_t bno), TP_ARGS(mp, keydev, bno), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(xfs_fsblock_t, bno) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->keydev = new_decode_dev(keydev); __entry->bno = bno; ), TP_printk("dev %d:%d keydev %d:%d bno 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->bno) ) #define DEFINE_FSMAP_LINEAR_KEY_EVENT(name) \ DEFINE_EVENT(xfs_fsmap_linear_key_class, name, \ TP_PROTO(struct xfs_mount *mp, u32 keydev, uint64_t bno), \ TP_ARGS(mp, keydev, bno)) DEFINE_FSMAP_LINEAR_KEY_EVENT(xfs_fsmap_low_linear_key); DEFINE_FSMAP_LINEAR_KEY_EVENT(xfs_fsmap_high_linear_key); DECLARE_EVENT_CLASS(xfs_getfsmap_class, TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap), TP_ARGS(mp, fsmap), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, keydev) __field(xfs_daddr_t, block) __field(xfs_daddr_t, len) __field(uint64_t, owner) __field(uint64_t, offset) __field(uint64_t, flags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->keydev = new_decode_dev(fsmap->fmr_device); __entry->block = fsmap->fmr_physical; __entry->len = fsmap->fmr_length; __entry->owner = fsmap->fmr_owner; __entry->offset = fsmap->fmr_offset; __entry->flags = fsmap->fmr_flags; ), TP_printk("dev %d:%d keydev %d:%d daddr 0x%llx bbcount 0x%llx owner 0x%llx fileoff_daddr 0x%llx flags 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->keydev), MINOR(__entry->keydev), __entry->block, __entry->len, __entry->owner, __entry->offset, __entry->flags) ) #define DEFINE_GETFSMAP_EVENT(name) \ DEFINE_EVENT(xfs_getfsmap_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap), \ TP_ARGS(mp, fsmap)) DEFINE_GETFSMAP_EVENT(xfs_getfsmap_low_key); DEFINE_GETFSMAP_EVENT(xfs_getfsmap_high_key); DEFINE_GETFSMAP_EVENT(xfs_getfsmap_mapping); DECLARE_EVENT_CLASS(xfs_trans_resv_class, TP_PROTO(struct xfs_mount *mp, unsigned int type, struct xfs_trans_res *res), TP_ARGS(mp, type, res), TP_STRUCT__entry( __field(dev_t, dev) __field(int, type) __field(uint, logres) __field(int, logcount) __field(int, logflags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->type = type; __entry->logres = res->tr_logres; __entry->logcount = res->tr_logcount; __entry->logflags = res->tr_logflags; ), TP_printk("dev %d:%d type %d logres %u logcount %d flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->type, __entry->logres, __entry->logcount, __entry->logflags) ) #define DEFINE_TRANS_RESV_EVENT(name) \ DEFINE_EVENT(xfs_trans_resv_class, name, \ TP_PROTO(struct xfs_mount *mp, unsigned int type, \ struct xfs_trans_res *res), \ TP_ARGS(mp, type, res)) DEFINE_TRANS_RESV_EVENT(xfs_trans_resv_calc); DEFINE_TRANS_RESV_EVENT(xfs_trans_resv_calc_minlogsize); TRACE_EVENT(xfs_log_get_max_trans_res, TP_PROTO(struct xfs_mount *mp, const struct xfs_trans_res *res), TP_ARGS(mp, res), TP_STRUCT__entry( __field(dev_t, dev) __field(uint, logres) __field(int, logcount) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->logres = res->tr_logres; __entry->logcount = res->tr_logcount; ), TP_printk("dev %d:%d logres %u logcount %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->logres, __entry->logcount) ); DECLARE_EVENT_CLASS(xfs_trans_class, TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), TP_ARGS(tp, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(uint32_t, tid) __field(uint32_t, flags) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = tp->t_mountp->m_super->s_dev; __entry->tid = 0; if (tp->t_ticket) __entry->tid = tp->t_ticket->t_tid; __entry->flags = tp->t_flags; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d trans %x flags 0x%x caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->tid, __entry->flags, (char *)__entry->caller_ip) ) #define DEFINE_TRANS_EVENT(name) \ DEFINE_EVENT(xfs_trans_class, name, \ TP_PROTO(struct xfs_trans *tp, unsigned long caller_ip), \ TP_ARGS(tp, caller_ip)) DEFINE_TRANS_EVENT(xfs_trans_alloc); DEFINE_TRANS_EVENT(xfs_trans_cancel); DEFINE_TRANS_EVENT(xfs_trans_commit); DEFINE_TRANS_EVENT(xfs_trans_dup); DEFINE_TRANS_EVENT(xfs_trans_free); DEFINE_TRANS_EVENT(xfs_trans_roll); DEFINE_TRANS_EVENT(xfs_trans_add_item); DEFINE_TRANS_EVENT(xfs_trans_commit_items); DEFINE_TRANS_EVENT(xfs_trans_free_items); TRACE_EVENT(xfs_iunlink_update_bucket, TP_PROTO(const struct xfs_perag *pag, unsigned int bucket, xfs_agino_t old_ptr, xfs_agino_t new_ptr), TP_ARGS(pag, bucket, old_ptr, new_ptr), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(unsigned int, bucket) __field(xfs_agino_t, old_ptr) __field(xfs_agino_t, new_ptr) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->bucket = bucket; __entry->old_ptr = old_ptr; __entry->new_ptr = new_ptr; ), TP_printk("dev %d:%d agno 0x%x bucket %u old 0x%x new 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->bucket, __entry->old_ptr, __entry->new_ptr) ); TRACE_EVENT(xfs_iunlink_update_dinode, TP_PROTO(const struct xfs_iunlink_item *iup, xfs_agino_t old_ptr), TP_ARGS(iup, old_ptr), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) __field(xfs_agino_t, old_ptr) __field(xfs_agino_t, new_ptr) ), TP_fast_assign( __entry->dev = pag_mount(iup->pag)->m_super->s_dev; __entry->agno = pag_agno(iup->pag); __entry->agino = XFS_INODE_TO_AGINO(iup->ip); __entry->old_ptr = old_ptr; __entry->new_ptr = iup->next_agino; ), TP_printk("dev %d:%d agno 0x%x agino 0x%x old 0x%x new 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agino, __entry->old_ptr, __entry->new_ptr) ); TRACE_EVENT(xfs_iunlink_reload_next, TP_PROTO(struct xfs_inode *ip), TP_ARGS(ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) __field(xfs_agino_t, prev_agino) __field(xfs_agino_t, next_agino) ), TP_fast_assign( __entry->dev = ip->i_mount->m_super->s_dev; __entry->agno = XFS_INODE_TO_AGNO(ip); __entry->agino = XFS_INODE_TO_AGINO(ip); __entry->prev_agino = ip->i_prev_unlinked; __entry->next_agino = ip->i_next_unlinked; ), TP_printk("dev %d:%d agno 0x%x agino 0x%x prev_unlinked 0x%x next_unlinked 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agino, __entry->prev_agino, __entry->next_agino) ); TRACE_EVENT(xfs_inode_reload_unlinked_bucket, TP_PROTO(struct xfs_inode *ip), TP_ARGS(ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) ), TP_fast_assign( __entry->dev = ip->i_mount->m_super->s_dev; __entry->agno = XFS_INODE_TO_AGNO(ip); __entry->agino = XFS_INODE_TO_AGINO(ip); ), TP_printk("dev %d:%d agno 0x%x agino 0x%x bucket %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agino, __entry->agino % XFS_AGI_UNLINKED_BUCKETS) ); DECLARE_EVENT_CLASS(xfs_ag_inode_class, TP_PROTO(struct xfs_inode *ip), TP_ARGS(ip), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->agno = XFS_INODE_TO_AGNO(ip); __entry->agino = XFS_INODE_TO_AGINO(ip); ), TP_printk("dev %d:%d agno 0x%x agino 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->agino) ) #define DEFINE_AGINODE_EVENT(name) \ DEFINE_EVENT(xfs_ag_inode_class, name, \ TP_PROTO(struct xfs_inode *ip), \ TP_ARGS(ip)) DEFINE_AGINODE_EVENT(xfs_iunlink); DEFINE_AGINODE_EVENT(xfs_iunlink_remove); DECLARE_EVENT_CLASS(xfs_fs_corrupt_class, TP_PROTO(struct xfs_mount *mp, unsigned int flags), TP_ARGS(mp, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->flags = flags; ), TP_printk("dev %d:%d flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->flags) ); #define DEFINE_FS_CORRUPT_EVENT(name) \ DEFINE_EVENT(xfs_fs_corrupt_class, name, \ TP_PROTO(struct xfs_mount *mp, unsigned int flags), \ TP_ARGS(mp, flags)) DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_sick); DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_corrupt); DEFINE_FS_CORRUPT_EVENT(xfs_fs_mark_healthy); DEFINE_FS_CORRUPT_EVENT(xfs_fs_unfixed_corruption); DECLARE_EVENT_CLASS(xfs_group_corrupt_class, TP_PROTO(const struct xfs_group *xg, unsigned int flags), TP_ARGS(xg, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(uint32_t, index) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = xg->xg_mount->m_super->s_dev; __entry->type = xg->xg_type; __entry->index = xg->xg_gno; __entry->flags = flags; ), TP_printk("dev %d:%d %sno 0x%x flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->index, __entry->flags) ); #define DEFINE_GROUP_CORRUPT_EVENT(name) \ DEFINE_EVENT(xfs_group_corrupt_class, name, \ TP_PROTO(const struct xfs_group *xg, unsigned int flags), \ TP_ARGS(xg, flags)) DEFINE_GROUP_CORRUPT_EVENT(xfs_group_mark_sick); DEFINE_GROUP_CORRUPT_EVENT(xfs_group_mark_corrupt); DEFINE_GROUP_CORRUPT_EVENT(xfs_group_mark_healthy); DEFINE_GROUP_CORRUPT_EVENT(xfs_group_unfixed_corruption); DECLARE_EVENT_CLASS(xfs_inode_corrupt_class, TP_PROTO(struct xfs_inode *ip, unsigned int flags), TP_ARGS(ip, flags), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(unsigned int, flags) ), TP_fast_assign( __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->flags = flags; ), TP_printk("dev %d:%d ino 0x%llx flags 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->flags) ); #define DEFINE_INODE_CORRUPT_EVENT(name) \ DEFINE_EVENT(xfs_inode_corrupt_class, name, \ TP_PROTO(struct xfs_inode *ip, unsigned int flags), \ TP_ARGS(ip, flags)) DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_sick); DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_corrupt); DEFINE_INODE_CORRUPT_EVENT(xfs_inode_mark_healthy); DEFINE_INODE_CORRUPT_EVENT(xfs_inode_unfixed_corruption); TRACE_EVENT(xfs_iwalk_ag_rec, TP_PROTO(const struct xfs_perag *pag, \ struct xfs_inobt_rec_incore *irec), TP_ARGS(pag, irec), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, startino) __field(uint64_t, freemask) ), TP_fast_assign( __entry->dev = pag_mount(pag)->m_super->s_dev; __entry->agno = pag_agno(pag); __entry->startino = irec->ir_startino; __entry->freemask = irec->ir_free; ), TP_printk("dev %d:%d agno 0x%x startino 0x%x freemask 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->agno, __entry->startino, __entry->freemask) ) TRACE_EVENT(xfs_pwork_init, TP_PROTO(struct xfs_mount *mp, unsigned int nr_threads, pid_t pid), TP_ARGS(mp, nr_threads, pid), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, nr_threads) __field(pid_t, pid) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->nr_threads = nr_threads; __entry->pid = pid; ), TP_printk("dev %d:%d nr_threads %u pid %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->nr_threads, __entry->pid) ) TRACE_EVENT(xfs_check_new_dalign, TP_PROTO(struct xfs_mount *mp, int new_dalign, xfs_ino_t calc_rootino), TP_ARGS(mp, new_dalign, calc_rootino), TP_STRUCT__entry( __field(dev_t, dev) __field(int, new_dalign) __field(xfs_ino_t, sb_rootino) __field(xfs_ino_t, calc_rootino) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->new_dalign = new_dalign; __entry->sb_rootino = mp->m_sb.sb_rootino; __entry->calc_rootino = calc_rootino; ), TP_printk("dev %d:%d new_dalign %d sb_rootino 0x%llx calc_rootino 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->new_dalign, __entry->sb_rootino, __entry->calc_rootino) ) TRACE_EVENT(xfs_btree_commit_afakeroot, TP_PROTO(struct xfs_btree_cur *cur), TP_ARGS(cur), TP_STRUCT__entry( __field(dev_t, dev) __string(name, cur->bc_ops->name) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(unsigned int, levels) __field(unsigned int, blocks) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __assign_str(name); __entry->agno = cur->bc_group->xg_gno; __entry->agbno = cur->bc_ag.afake->af_root; __entry->levels = cur->bc_ag.afake->af_levels; __entry->blocks = cur->bc_ag.afake->af_blocks; ), TP_printk("dev %d:%d %sbt agno 0x%x levels %u blocks %u root %u", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->agno, __entry->levels, __entry->blocks, __entry->agbno) ) TRACE_EVENT(xfs_btree_commit_ifakeroot, TP_PROTO(struct xfs_btree_cur *cur), TP_ARGS(cur), TP_STRUCT__entry( __field(dev_t, dev) __string(name, cur->bc_ops->name) __field(xfs_agnumber_t, agno) __field(xfs_agino_t, agino) __field(unsigned int, levels) __field(unsigned int, blocks) __field(int, whichfork) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __assign_str(name); __entry->agno = XFS_INODE_TO_AGNO(cur->bc_ino.ip); __entry->agino = XFS_INODE_TO_AGINO(cur->bc_ino.ip); __entry->levels = cur->bc_ino.ifake->if_levels; __entry->blocks = cur->bc_ino.ifake->if_blocks; __entry->whichfork = cur->bc_ino.whichfork; ), TP_printk("dev %d:%d %sbt agno 0x%x agino 0x%x whichfork %s levels %u blocks %u", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->agno, __entry->agino, __print_symbolic(__entry->whichfork, XFS_WHICHFORK_STRINGS), __entry->levels, __entry->blocks) ) TRACE_EVENT(xfs_btree_bload_level_geometry, TP_PROTO(struct xfs_btree_cur *cur, unsigned int level, uint64_t nr_this_level, unsigned int nr_per_block, unsigned int desired_npb, uint64_t blocks, uint64_t blocks_with_extra), TP_ARGS(cur, level, nr_this_level, nr_per_block, desired_npb, blocks, blocks_with_extra), TP_STRUCT__entry( __field(dev_t, dev) __string(name, cur->bc_ops->name) __field(unsigned int, level) __field(unsigned int, nlevels) __field(uint64_t, nr_this_level) __field(unsigned int, nr_per_block) __field(unsigned int, desired_npb) __field(unsigned long long, blocks) __field(unsigned long long, blocks_with_extra) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __assign_str(name); __entry->level = level; __entry->nlevels = cur->bc_nlevels; __entry->nr_this_level = nr_this_level; __entry->nr_per_block = nr_per_block; __entry->desired_npb = desired_npb; __entry->blocks = blocks; __entry->blocks_with_extra = blocks_with_extra; ), TP_printk("dev %d:%d %sbt level %u/%u nr_this_level %llu nr_per_block %u desired_npb %u blocks %llu blocks_with_extra %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->level, __entry->nlevels, __entry->nr_this_level, __entry->nr_per_block, __entry->desired_npb, __entry->blocks, __entry->blocks_with_extra) ) TRACE_EVENT(xfs_btree_bload_block, TP_PROTO(struct xfs_btree_cur *cur, unsigned int level, uint64_t block_idx, uint64_t nr_blocks, union xfs_btree_ptr *ptr, unsigned int nr_records), TP_ARGS(cur, level, block_idx, nr_blocks, ptr, nr_records), TP_STRUCT__entry( __field(dev_t, dev) __string(name, cur->bc_ops->name) __field(unsigned int, level) __field(unsigned long long, block_idx) __field(unsigned long long, nr_blocks) __field(xfs_agnumber_t, agno) __field(xfs_agblock_t, agbno) __field(unsigned int, nr_records) ), TP_fast_assign( __entry->dev = cur->bc_mp->m_super->s_dev; __assign_str(name); __entry->level = level; __entry->block_idx = block_idx; __entry->nr_blocks = nr_blocks; if (cur->bc_ops->ptr_len == XFS_BTREE_LONG_PTR_LEN) { xfs_fsblock_t fsb = be64_to_cpu(ptr->l); __entry->agno = XFS_FSB_TO_AGNO(cur->bc_mp, fsb); __entry->agbno = XFS_FSB_TO_AGBNO(cur->bc_mp, fsb); } else { __entry->agno = cur->bc_group->xg_gno; __entry->agbno = be32_to_cpu(ptr->s); } __entry->nr_records = nr_records; ), TP_printk("dev %d:%d %sbt level %u block %llu/%llu agno 0x%x agbno 0x%x recs %u", MAJOR(__entry->dev), MINOR(__entry->dev), __get_str(name), __entry->level, __entry->block_idx, __entry->nr_blocks, __entry->agno, __entry->agbno, __entry->nr_records) ) DECLARE_EVENT_CLASS(xfs_timestamp_range_class, TP_PROTO(struct xfs_mount *mp, time64_t min, time64_t max), TP_ARGS(mp, min, max), TP_STRUCT__entry( __field(dev_t, dev) __field(long long, min) __field(long long, max) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->min = min; __entry->max = max; ), TP_printk("dev %d:%d min %lld max %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->min, __entry->max) ) #define DEFINE_TIMESTAMP_RANGE_EVENT(name) \ DEFINE_EVENT(xfs_timestamp_range_class, name, \ TP_PROTO(struct xfs_mount *mp, long long min, long long max), \ TP_ARGS(mp, min, max)) DEFINE_TIMESTAMP_RANGE_EVENT(xfs_inode_timestamp_range); DEFINE_TIMESTAMP_RANGE_EVENT(xfs_quota_expiry_range); DECLARE_EVENT_CLASS(xfs_icwalk_class, TP_PROTO(struct xfs_mount *mp, struct xfs_icwalk *icw, unsigned long caller_ip), TP_ARGS(mp, icw, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(__u32, flags) __field(uint32_t, uid) __field(uint32_t, gid) __field(prid_t, prid) __field(__u64, min_file_size) __field(long, scan_limit) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->flags = icw ? icw->icw_flags : 0; __entry->uid = icw ? from_kuid(mp->m_super->s_user_ns, icw->icw_uid) : 0; __entry->gid = icw ? from_kgid(mp->m_super->s_user_ns, icw->icw_gid) : 0; __entry->prid = icw ? icw->icw_prid : 0; __entry->min_file_size = icw ? icw->icw_min_file_size : 0; __entry->scan_limit = icw ? icw->icw_scan_limit : 0; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d flags 0x%x uid %u gid %u prid %u minsize %llu scan_limit %ld caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->flags, __entry->uid, __entry->gid, __entry->prid, __entry->min_file_size, __entry->scan_limit, (char *)__entry->caller_ip) ); #define DEFINE_ICWALK_EVENT(name) \ DEFINE_EVENT(xfs_icwalk_class, name, \ TP_PROTO(struct xfs_mount *mp, struct xfs_icwalk *icw, \ unsigned long caller_ip), \ TP_ARGS(mp, icw, caller_ip)) DEFINE_ICWALK_EVENT(xfs_ioc_free_eofblocks); DEFINE_ICWALK_EVENT(xfs_blockgc_free_space); TRACE_DEFINE_ENUM(XLOG_STATE_ACTIVE); TRACE_DEFINE_ENUM(XLOG_STATE_WANT_SYNC); TRACE_DEFINE_ENUM(XLOG_STATE_SYNCING); TRACE_DEFINE_ENUM(XLOG_STATE_DONE_SYNC); TRACE_DEFINE_ENUM(XLOG_STATE_CALLBACK); TRACE_DEFINE_ENUM(XLOG_STATE_DIRTY); DECLARE_EVENT_CLASS(xlog_iclog_class, TP_PROTO(struct xlog_in_core *iclog, unsigned long caller_ip), TP_ARGS(iclog, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(uint32_t, state) __field(int32_t, refcount) __field(uint32_t, offset) __field(uint32_t, flags) __field(unsigned long long, lsn) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = iclog->ic_log->l_mp->m_super->s_dev; __entry->state = iclog->ic_state; __entry->refcount = atomic_read(&iclog->ic_refcnt); __entry->offset = iclog->ic_offset; __entry->flags = iclog->ic_flags; __entry->lsn = be64_to_cpu(iclog->ic_header->h_lsn); __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d state %s refcnt %d offset %u lsn 0x%llx flags %s caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->state, XLOG_STATE_STRINGS), __entry->refcount, __entry->offset, __entry->lsn, __print_flags(__entry->flags, "|", XLOG_ICL_STRINGS), (char *)__entry->caller_ip) ); #define DEFINE_ICLOG_EVENT(name) \ DEFINE_EVENT(xlog_iclog_class, name, \ TP_PROTO(struct xlog_in_core *iclog, unsigned long caller_ip), \ TP_ARGS(iclog, caller_ip)) DEFINE_ICLOG_EVENT(xlog_iclog_activate); DEFINE_ICLOG_EVENT(xlog_iclog_clean); DEFINE_ICLOG_EVENT(xlog_iclog_callback); DEFINE_ICLOG_EVENT(xlog_iclog_callbacks_start); DEFINE_ICLOG_EVENT(xlog_iclog_callbacks_done); DEFINE_ICLOG_EVENT(xlog_iclog_force); DEFINE_ICLOG_EVENT(xlog_iclog_force_lsn); DEFINE_ICLOG_EVENT(xlog_iclog_get_space); DEFINE_ICLOG_EVENT(xlog_iclog_release); DEFINE_ICLOG_EVENT(xlog_iclog_switch); DEFINE_ICLOG_EVENT(xlog_iclog_sync); DEFINE_ICLOG_EVENT(xlog_iclog_syncing); DEFINE_ICLOG_EVENT(xlog_iclog_sync_done); DEFINE_ICLOG_EVENT(xlog_iclog_wait_on); DEFINE_ICLOG_EVENT(xlog_iclog_write); TRACE_DEFINE_ENUM(XFS_DAS_UNINIT); TRACE_DEFINE_ENUM(XFS_DAS_SF_ADD); TRACE_DEFINE_ENUM(XFS_DAS_SF_REMOVE); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_ADD); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_REMOVE); TRACE_DEFINE_ENUM(XFS_DAS_NODE_ADD); TRACE_DEFINE_ENUM(XFS_DAS_NODE_REMOVE); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_SET_RMT); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_ALLOC_RMT); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_REPLACE); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_REMOVE_OLD); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_REMOVE_RMT); TRACE_DEFINE_ENUM(XFS_DAS_LEAF_REMOVE_ATTR); TRACE_DEFINE_ENUM(XFS_DAS_NODE_SET_RMT); TRACE_DEFINE_ENUM(XFS_DAS_NODE_ALLOC_RMT); TRACE_DEFINE_ENUM(XFS_DAS_NODE_REPLACE); TRACE_DEFINE_ENUM(XFS_DAS_NODE_REMOVE_OLD); TRACE_DEFINE_ENUM(XFS_DAS_NODE_REMOVE_RMT); TRACE_DEFINE_ENUM(XFS_DAS_NODE_REMOVE_ATTR); TRACE_DEFINE_ENUM(XFS_DAS_DONE); DECLARE_EVENT_CLASS(xfs_das_state_class, TP_PROTO(int das, struct xfs_inode *ip), TP_ARGS(das, ip), TP_STRUCT__entry( __field(int, das) __field(xfs_ino_t, ino) ), TP_fast_assign( __entry->das = das; __entry->ino = I_INO(ip); ), TP_printk("state change %s ino 0x%llx", __print_symbolic(__entry->das, XFS_DAS_STRINGS), __entry->ino) ) #define DEFINE_DAS_STATE_EVENT(name) \ DEFINE_EVENT(xfs_das_state_class, name, \ TP_PROTO(int das, struct xfs_inode *ip), \ TP_ARGS(das, ip)) DEFINE_DAS_STATE_EVENT(xfs_attr_sf_addname_return); DEFINE_DAS_STATE_EVENT(xfs_attr_set_iter_return); DEFINE_DAS_STATE_EVENT(xfs_attr_leaf_addname_return); DEFINE_DAS_STATE_EVENT(xfs_attr_node_addname_return); DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_alloc); DEFINE_DAS_STATE_EVENT(xfs_attr_rmtval_remove_return); DEFINE_DAS_STATE_EVENT(xfs_attr_defer_add); TRACE_EVENT(xfs_force_shutdown, TP_PROTO(struct xfs_mount *mp, int ptag, int flags, const char *fname, int line_num), TP_ARGS(mp, ptag, flags, fname, line_num), TP_STRUCT__entry( __field(dev_t, dev) __field(int, ptag) __field(int, flags) __string(fname, fname) __field(int, line_num) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->ptag = ptag; __entry->flags = flags; __assign_str(fname); __entry->line_num = line_num; ), TP_printk("dev %d:%d tag %s flags %s file %s line_num %d", MAJOR(__entry->dev), MINOR(__entry->dev), __print_flags(__entry->ptag, "|", XFS_PTAG_STRINGS), __print_flags(__entry->flags, "|", XFS_SHUTDOWN_STRINGS), __get_str(fname), __entry->line_num) ); #ifdef CONFIG_XFS_DRAIN_INTENTS DECLARE_EVENT_CLASS(xfs_group_intents_class, TP_PROTO(const struct xfs_group *xg, void *caller_ip), TP_ARGS(xg, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_group_type, type) __field(uint32_t, index) __field(long, nr_intents) __field(void *, caller_ip) ), TP_fast_assign( __entry->dev = xg->xg_mount->m_super->s_dev; __entry->type = xg->xg_type; __entry->index = xg->xg_gno; __entry->nr_intents = atomic_read(&xg->xg_intents_drain.dr_count); __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d %sno 0x%x intents %ld caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XG_TYPE_STRINGS), __entry->index, __entry->nr_intents, __entry->caller_ip) ); #define DEFINE_GROUP_INTENTS_EVENT(name) \ DEFINE_EVENT(xfs_group_intents_class, name, \ TP_PROTO(const struct xfs_group *xg, void *caller_ip), \ TP_ARGS(xg, caller_ip)) DEFINE_GROUP_INTENTS_EVENT(xfs_group_intent_hold); DEFINE_GROUP_INTENTS_EVENT(xfs_group_intent_rele); DEFINE_GROUP_INTENTS_EVENT(xfs_group_wait_intents); #endif /* CONFIG_XFS_DRAIN_INTENTS */ #ifdef CONFIG_XFS_MEMORY_BUFS TRACE_EVENT(xmbuf_create, TP_PROTO(struct xfs_buftarg *btp), TP_ARGS(btp), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) ), TP_fast_assign( struct file *file = btp->bt_file; __entry->dev = btp->bt_mount->m_super->s_dev; __entry->ino = file_inode(file)->i_ino; ), TP_printk("dev %d:%d xmino 0x%lx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino) ); TRACE_EVENT(xmbuf_free, TP_PROTO(struct xfs_buftarg *btp), TP_ARGS(btp), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long, ino) __field(unsigned long long, bytes) __field(loff_t, size) ), TP_fast_assign( struct file *file = btp->bt_file; struct inode *inode = file_inode(file); __entry->dev = btp->bt_mount->m_super->s_dev; __entry->size = i_size_read(inode); __entry->bytes = (inode->i_blocks << SECTOR_SHIFT) + inode->i_bytes; __entry->ino = inode->i_ino; ), TP_printk("dev %d:%d xmino 0x%lx mem_bytes 0x%llx isize 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->bytes, __entry->size) ); #endif /* CONFIG_XFS_MEMORY_BUFS */ #ifdef CONFIG_XFS_BTREE_IN_MEM TRACE_EVENT(xfbtree_init, TP_PROTO(struct xfs_mount *mp, struct xfbtree *xfbt, const struct xfs_btree_ops *ops), TP_ARGS(mp, xfbt, ops), TP_STRUCT__entry( __field(const void *, btree_ops) __field(unsigned long, xfino) __field(unsigned int, leaf_mxr) __field(unsigned int, leaf_mnr) __field(unsigned int, node_mxr) __field(unsigned int, node_mnr) __field(unsigned long long, owner) ), TP_fast_assign( __entry->btree_ops = ops; __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; __entry->leaf_mxr = xfbt->maxrecs[0]; __entry->node_mxr = xfbt->maxrecs[1]; __entry->leaf_mnr = xfbt->minrecs[0]; __entry->node_mnr = xfbt->minrecs[1]; __entry->owner = xfbt->owner; ), TP_printk("xfino 0x%lx btree_ops %pS owner 0x%llx leaf_mxr %u leaf_mnr %u node_mxr %u node_mnr %u", __entry->xfino, __entry->btree_ops, __entry->owner, __entry->leaf_mxr, __entry->leaf_mnr, __entry->node_mxr, __entry->node_mnr) ); DECLARE_EVENT_CLASS(xfbtree_buf_class, TP_PROTO(struct xfbtree *xfbt, struct xfs_buf *bp), TP_ARGS(xfbt, bp), TP_STRUCT__entry( __field(unsigned long, xfino) __field(xfs_daddr_t, bno) __field(int, nblks) __field(int, hold) __field(int, pincount) __field(unsigned int, lockval) __field(unsigned int, flags) ), TP_fast_assign( __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; __entry->bno = xfs_buf_daddr(bp); __entry->nblks = bp->b_length; __entry->hold = bp->b_lockref.count; __entry->pincount = atomic_read(&bp->b_pin_count); __entry->lockval = bp->b_sema.count; __entry->flags = bp->b_flags; ), TP_printk("xfino 0x%lx daddr 0x%llx bbcount 0x%x hold %d pincount %d lock %d flags %s", __entry->xfino, (unsigned long long)__entry->bno, __entry->nblks, __entry->hold, __entry->pincount, __entry->lockval, __print_flags(__entry->flags, "|", XFS_BUF_FLAGS)) ) #define DEFINE_XFBTREE_BUF_EVENT(name) \ DEFINE_EVENT(xfbtree_buf_class, name, \ TP_PROTO(struct xfbtree *xfbt, struct xfs_buf *bp), \ TP_ARGS(xfbt, bp)) DEFINE_XFBTREE_BUF_EVENT(xfbtree_create_root_buf); DEFINE_XFBTREE_BUF_EVENT(xfbtree_trans_commit_buf); DEFINE_XFBTREE_BUF_EVENT(xfbtree_trans_cancel_buf); DECLARE_EVENT_CLASS(xfbtree_freesp_class, TP_PROTO(struct xfbtree *xfbt, struct xfs_btree_cur *cur, xfs_fileoff_t fileoff), TP_ARGS(xfbt, cur, fileoff), TP_STRUCT__entry( __field(unsigned long, xfino) __string(btname, cur->bc_ops->name) __field(int, nlevels) __field(xfs_fileoff_t, fileoff) ), TP_fast_assign( __entry->xfino = file_inode(xfbt->target->bt_file)->i_ino; __assign_str(btname); __entry->nlevels = cur->bc_nlevels; __entry->fileoff = fileoff; ), TP_printk("xfino 0x%lx %sbt nlevels %d fileoff 0x%llx", __entry->xfino, __get_str(btname), __entry->nlevels, (unsigned long long)__entry->fileoff) ) #define DEFINE_XFBTREE_FREESP_EVENT(name) \ DEFINE_EVENT(xfbtree_freesp_class, name, \ TP_PROTO(struct xfbtree *xfbt, struct xfs_btree_cur *cur, \ xfs_fileoff_t fileoff), \ TP_ARGS(xfbt, cur, fileoff)) DEFINE_XFBTREE_FREESP_EVENT(xfbtree_alloc_block); DEFINE_XFBTREE_FREESP_EVENT(xfbtree_free_block); #endif /* CONFIG_XFS_BTREE_IN_MEM */ /* exchmaps tracepoints */ #define XFS_EXCHMAPS_STRINGS \ { XFS_EXCHMAPS_ATTR_FORK, "ATTRFORK" }, \ { XFS_EXCHMAPS_SET_SIZES, "SETSIZES" }, \ { XFS_EXCHMAPS_INO1_WRITTEN, "INO1_WRITTEN" }, \ { XFS_EXCHMAPS_CLEAR_INO1_REFLINK, "CLEAR_INO1_REFLINK" }, \ { XFS_EXCHMAPS_CLEAR_INO2_REFLINK, "CLEAR_INO2_REFLINK" }, \ { __XFS_EXCHMAPS_INO2_SHORTFORM, "INO2_SF" } DEFINE_INODE_IREC_EVENT(xfs_exchmaps_mapping1_skip); DEFINE_INODE_IREC_EVENT(xfs_exchmaps_mapping1); DEFINE_INODE_IREC_EVENT(xfs_exchmaps_mapping2); DEFINE_ITRUNC_EVENT(xfs_exchmaps_update_inode_size); #define XFS_EXCHRANGE_INODES \ { 1, "file1" }, \ { 2, "file2" } DECLARE_EVENT_CLASS(xfs_exchrange_inode_class, TP_PROTO(struct xfs_inode *ip, int whichfile), TP_ARGS(ip, whichfile), TP_STRUCT__entry( __field(dev_t, dev) __field(int, whichfile) __field(xfs_ino_t, ino) __field(int, format) __field(xfs_extnum_t, nex) __field(int, broot_size) __field(int, fork_off) ), TP_fast_assign( __entry->dev = VFS_I(ip)->i_sb->s_dev; __entry->whichfile = whichfile; __entry->ino = I_INO(ip); __entry->format = ip->i_df.if_format; __entry->nex = ip->i_df.if_nextents; __entry->fork_off = xfs_inode_fork_boff(ip); ), TP_printk("dev %d:%d ino 0x%llx whichfile %s format %s num_extents %llu forkoff 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __print_symbolic(__entry->whichfile, XFS_EXCHRANGE_INODES), __print_symbolic(__entry->format, XFS_INODE_FORMAT_STR), __entry->nex, __entry->fork_off) ) #define DEFINE_EXCHRANGE_INODE_EVENT(name) \ DEFINE_EVENT(xfs_exchrange_inode_class, name, \ TP_PROTO(struct xfs_inode *ip, int whichfile), \ TP_ARGS(ip, whichfile)) DEFINE_EXCHRANGE_INODE_EVENT(xfs_exchrange_before); DEFINE_EXCHRANGE_INODE_EVENT(xfs_exchrange_after); DEFINE_INODE_ERROR_EVENT(xfs_exchrange_error); #define XFS_EXCHANGE_RANGE_FLAGS_STRS \ { XFS_EXCHANGE_RANGE_TO_EOF, "TO_EOF" }, \ { XFS_EXCHANGE_RANGE_DSYNC , "DSYNC" }, \ { XFS_EXCHANGE_RANGE_DRY_RUN, "DRY_RUN" }, \ { XFS_EXCHANGE_RANGE_FILE1_WRITTEN, "F1_WRITTEN" }, \ { __XFS_EXCHANGE_RANGE_UPD_CMTIME1, "CMTIME1" }, \ { __XFS_EXCHANGE_RANGE_UPD_CMTIME2, "CMTIME2" }, \ { __XFS_EXCHANGE_RANGE_CHECK_FRESH2, "FRESH2" } /* file exchange-range tracepoint class */ DECLARE_EVENT_CLASS(xfs_exchrange_class, TP_PROTO(const struct xfs_exchrange *fxr, struct xfs_inode *ip1, struct xfs_inode *ip2), TP_ARGS(fxr, ip1, ip2), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ip1_ino) __field(loff_t, ip1_isize) __field(loff_t, ip1_disize) __field(xfs_ino_t, ip2_ino) __field(loff_t, ip2_isize) __field(loff_t, ip2_disize) __field(loff_t, file1_offset) __field(loff_t, file2_offset) __field(unsigned long long, length) __field(unsigned long long, flags) ), TP_fast_assign( __entry->dev = VFS_I(ip1)->i_sb->s_dev; __entry->ip1_ino = I_INO(ip1); __entry->ip1_isize = VFS_I(ip1)->i_size; __entry->ip1_disize = ip1->i_disk_size; __entry->ip2_ino = I_INO(ip2); __entry->ip2_isize = VFS_I(ip2)->i_size; __entry->ip2_disize = ip2->i_disk_size; __entry->file1_offset = fxr->file1_offset; __entry->file2_offset = fxr->file2_offset; __entry->length = fxr->length; __entry->flags = fxr->flags; ), TP_printk("dev %d:%d flags %s bytecount 0x%llx " "ino1 0x%llx isize 0x%llx disize 0x%llx pos 0x%llx -> " "ino2 0x%llx isize 0x%llx disize 0x%llx pos 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __print_flags_u64(__entry->flags, "|", XFS_EXCHANGE_RANGE_FLAGS_STRS), __entry->length, __entry->ip1_ino, __entry->ip1_isize, __entry->ip1_disize, __entry->file1_offset, __entry->ip2_ino, __entry->ip2_isize, __entry->ip2_disize, __entry->file2_offset) ) #define DEFINE_EXCHRANGE_EVENT(name) \ DEFINE_EVENT(xfs_exchrange_class, name, \ TP_PROTO(const struct xfs_exchrange *fxr, struct xfs_inode *ip1, \ struct xfs_inode *ip2), \ TP_ARGS(fxr, ip1, ip2)) DEFINE_EXCHRANGE_EVENT(xfs_exchrange_prep); DEFINE_EXCHRANGE_EVENT(xfs_exchrange_flush); DEFINE_EXCHRANGE_EVENT(xfs_exchrange_mappings); TRACE_EVENT(xfs_exchrange_freshness, TP_PROTO(const struct xfs_exchrange *fxr, struct xfs_inode *ip2), TP_ARGS(fxr, ip2), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ip2_ino) __field(long long, ip2_mtime) __field(long long, ip2_ctime) __field(int, ip2_mtime_nsec) __field(int, ip2_ctime_nsec) __field(xfs_ino_t, file2_ino) __field(long long, file2_mtime) __field(long long, file2_ctime) __field(int, file2_mtime_nsec) __field(int, file2_ctime_nsec) ), TP_fast_assign( struct timespec64 ts64; struct inode *inode2 = VFS_I(ip2); __entry->dev = inode2->i_sb->s_dev; __entry->ip2_ino = I_INO(ip2); ts64 = inode_get_ctime(inode2); __entry->ip2_ctime = ts64.tv_sec; __entry->ip2_ctime_nsec = ts64.tv_nsec; ts64 = inode_get_mtime(inode2); __entry->ip2_mtime = ts64.tv_sec; __entry->ip2_mtime_nsec = ts64.tv_nsec; __entry->file2_ino = fxr->file2_ino; __entry->file2_mtime = fxr->file2_mtime.tv_sec; __entry->file2_ctime = fxr->file2_ctime.tv_sec; __entry->file2_mtime_nsec = fxr->file2_mtime.tv_nsec; __entry->file2_ctime_nsec = fxr->file2_ctime.tv_nsec; ), TP_printk("dev %d:%d " "ino 0x%llx mtime %lld:%d ctime %lld:%d -> " "file 0x%llx mtime %lld:%d ctime %lld:%d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ip2_ino, __entry->ip2_mtime, __entry->ip2_mtime_nsec, __entry->ip2_ctime, __entry->ip2_ctime_nsec, __entry->file2_ino, __entry->file2_mtime, __entry->file2_mtime_nsec, __entry->file2_ctime, __entry->file2_ctime_nsec) ); TRACE_EVENT(xfs_exchmaps_overhead, TP_PROTO(struct xfs_mount *mp, unsigned long long bmbt_blocks, unsigned long long rmapbt_blocks), TP_ARGS(mp, bmbt_blocks, rmapbt_blocks), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, bmbt_blocks) __field(unsigned long long, rmapbt_blocks) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->bmbt_blocks = bmbt_blocks; __entry->rmapbt_blocks = rmapbt_blocks; ), TP_printk("dev %d:%d bmbt_blocks 0x%llx rmapbt_blocks 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->bmbt_blocks, __entry->rmapbt_blocks) ); DECLARE_EVENT_CLASS(xfs_exchmaps_estimate_class, TP_PROTO(const struct xfs_exchmaps_req *req), TP_ARGS(req), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino1) __field(xfs_ino_t, ino2) __field(xfs_fileoff_t, startoff1) __field(xfs_fileoff_t, startoff2) __field(xfs_filblks_t, blockcount) __field(uint64_t, flags) __field(xfs_filblks_t, ip1_bcount) __field(xfs_filblks_t, ip2_bcount) __field(xfs_filblks_t, ip1_rtbcount) __field(xfs_filblks_t, ip2_rtbcount) __field(unsigned long long, resblks) __field(unsigned long long, nr_exchanges) ), TP_fast_assign( __entry->dev = req->ip1->i_mount->m_super->s_dev; __entry->ino1 = I_INO(req->ip1); __entry->ino2 = I_INO(req->ip2); __entry->startoff1 = req->startoff1; __entry->startoff2 = req->startoff2; __entry->blockcount = req->blockcount; __entry->flags = req->flags; __entry->ip1_bcount = req->ip1_bcount; __entry->ip2_bcount = req->ip2_bcount; __entry->ip1_rtbcount = req->ip1_rtbcount; __entry->ip2_rtbcount = req->ip2_rtbcount; __entry->resblks = req->resblks; __entry->nr_exchanges = req->nr_exchanges; ), TP_printk("dev %d:%d ino1 0x%llx fileoff1 0x%llx ino2 0x%llx fileoff2 0x%llx fsbcount 0x%llx flags (%s) bcount1 0x%llx rtbcount1 0x%llx bcount2 0x%llx rtbcount2 0x%llx resblks 0x%llx nr_exchanges %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino1, __entry->startoff1, __entry->ino2, __entry->startoff2, __entry->blockcount, __print_flags_u64(__entry->flags, "|", XFS_EXCHMAPS_STRINGS), __entry->ip1_bcount, __entry->ip1_rtbcount, __entry->ip2_bcount, __entry->ip2_rtbcount, __entry->resblks, __entry->nr_exchanges) ); #define DEFINE_EXCHMAPS_ESTIMATE_EVENT(name) \ DEFINE_EVENT(xfs_exchmaps_estimate_class, name, \ TP_PROTO(const struct xfs_exchmaps_req *req), \ TP_ARGS(req)) DEFINE_EXCHMAPS_ESTIMATE_EVENT(xfs_exchmaps_initial_estimate); DEFINE_EXCHMAPS_ESTIMATE_EVENT(xfs_exchmaps_final_estimate); DECLARE_EVENT_CLASS(xfs_exchmaps_intent_class, TP_PROTO(struct xfs_mount *mp, const struct xfs_exchmaps_intent *xmi), TP_ARGS(mp, xmi), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino1) __field(xfs_ino_t, ino2) __field(uint64_t, flags) __field(xfs_fileoff_t, startoff1) __field(xfs_fileoff_t, startoff2) __field(xfs_filblks_t, blockcount) __field(xfs_fsize_t, isize1) __field(xfs_fsize_t, isize2) __field(xfs_fsize_t, new_isize1) __field(xfs_fsize_t, new_isize2) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->ino1 = I_INO(xmi->xmi_ip1); __entry->ino2 = I_INO(xmi->xmi_ip2); __entry->flags = xmi->xmi_flags; __entry->startoff1 = xmi->xmi_startoff1; __entry->startoff2 = xmi->xmi_startoff2; __entry->blockcount = xmi->xmi_blockcount; __entry->isize1 = xmi->xmi_ip1->i_disk_size; __entry->isize2 = xmi->xmi_ip2->i_disk_size; __entry->new_isize1 = xmi->xmi_isize1; __entry->new_isize2 = xmi->xmi_isize2; ), TP_printk("dev %d:%d ino1 0x%llx fileoff1 0x%llx ino2 0x%llx fileoff2 0x%llx fsbcount 0x%llx flags (%s) isize1 0x%llx newisize1 0x%llx isize2 0x%llx newisize2 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino1, __entry->startoff1, __entry->ino2, __entry->startoff2, __entry->blockcount, __print_flags_u64(__entry->flags, "|", XFS_EXCHMAPS_STRINGS), __entry->isize1, __entry->new_isize1, __entry->isize2, __entry->new_isize2) ); #define DEFINE_EXCHMAPS_INTENT_EVENT(name) \ DEFINE_EVENT(xfs_exchmaps_intent_class, name, \ TP_PROTO(struct xfs_mount *mp, const struct xfs_exchmaps_intent *xmi), \ TP_ARGS(mp, xmi)) DEFINE_EXCHMAPS_INTENT_EVENT(xfs_exchmaps_defer); DEFINE_EXCHMAPS_INTENT_EVENT(xfs_exchmaps_recover); TRACE_EVENT(xfs_exchmaps_delta_nextents_step, TP_PROTO(struct xfs_mount *mp, const struct xfs_bmbt_irec *left, const struct xfs_bmbt_irec *curr, const struct xfs_bmbt_irec *new, const struct xfs_bmbt_irec *right, int delta, unsigned int state), TP_ARGS(mp, left, curr, new, right, delta, state), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_fileoff_t, loff) __field(xfs_fsblock_t, lstart) __field(xfs_filblks_t, lcount) __field(xfs_fileoff_t, coff) __field(xfs_fsblock_t, cstart) __field(xfs_filblks_t, ccount) __field(xfs_fileoff_t, noff) __field(xfs_fsblock_t, nstart) __field(xfs_filblks_t, ncount) __field(xfs_fileoff_t, roff) __field(xfs_fsblock_t, rstart) __field(xfs_filblks_t, rcount) __field(int, delta) __field(unsigned int, state) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->loff = left->br_startoff; __entry->lstart = left->br_startblock; __entry->lcount = left->br_blockcount; __entry->coff = curr->br_startoff; __entry->cstart = curr->br_startblock; __entry->ccount = curr->br_blockcount; __entry->noff = new->br_startoff; __entry->nstart = new->br_startblock; __entry->ncount = new->br_blockcount; __entry->roff = right->br_startoff; __entry->rstart = right->br_startblock; __entry->rcount = right->br_blockcount; __entry->delta = delta; __entry->state = state; ), TP_printk("dev %d:%d left 0x%llx:0x%llx:0x%llx; curr 0x%llx:0x%llx:0x%llx <- new 0x%llx:0x%llx:0x%llx; right 0x%llx:0x%llx:0x%llx delta %d state 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->loff, __entry->lstart, __entry->lcount, __entry->coff, __entry->cstart, __entry->ccount, __entry->noff, __entry->nstart, __entry->ncount, __entry->roff, __entry->rstart, __entry->rcount, __entry->delta, __entry->state) ); TRACE_EVENT(xfs_exchmaps_delta_nextents, TP_PROTO(const struct xfs_exchmaps_req *req, int64_t d_nexts1, int64_t d_nexts2), TP_ARGS(req, d_nexts1, d_nexts2), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino1) __field(xfs_ino_t, ino2) __field(xfs_extnum_t, nexts1) __field(xfs_extnum_t, nexts2) __field(int64_t, d_nexts1) __field(int64_t, d_nexts2) ), TP_fast_assign( int whichfork = xfs_exchmaps_reqfork(req); __entry->dev = req->ip1->i_mount->m_super->s_dev; __entry->ino1 = I_INO(req->ip1); __entry->ino2 = I_INO(req->ip2); __entry->nexts1 = xfs_ifork_ptr(req->ip1, whichfork)->if_nextents; __entry->nexts2 = xfs_ifork_ptr(req->ip2, whichfork)->if_nextents; __entry->d_nexts1 = d_nexts1; __entry->d_nexts2 = d_nexts2; ), TP_printk("dev %d:%d ino1 0x%llx nexts %llu ino2 0x%llx nexts %llu delta1 %lld delta2 %lld", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino1, __entry->nexts1, __entry->ino2, __entry->nexts2, __entry->d_nexts1, __entry->d_nexts2) ); DECLARE_EVENT_CLASS(xfs_getparents_rec_class, TP_PROTO(struct xfs_inode *ip, const struct xfs_getparents *ppi, const struct xfs_attr_list_context *context, const struct xfs_getparents_rec *pptr), TP_ARGS(ip, ppi, context, pptr), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(unsigned int, firstu) __field(unsigned short, reclen) __field(unsigned int, bufsize) __field(xfs_ino_t, parent_ino) __field(unsigned int, parent_gen) __string(name, pptr->gpr_name) ), TP_fast_assign( __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->firstu = context->firstu; __entry->reclen = pptr->gpr_reclen; __entry->bufsize = ppi->gp_bufsize; __entry->parent_ino = pptr->gpr_parent.ha_fid.fid_ino; __entry->parent_gen = pptr->gpr_parent.ha_fid.fid_gen; __assign_str(name); ), TP_printk("dev %d:%d ino 0x%llx firstu %u reclen %u bufsize %u parent_ino 0x%llx parent_gen 0x%x name '%s'", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->firstu, __entry->reclen, __entry->bufsize, __entry->parent_ino, __entry->parent_gen, __get_str(name)) ) #define DEFINE_XFS_GETPARENTS_REC_EVENT(name) \ DEFINE_EVENT(xfs_getparents_rec_class, name, \ TP_PROTO(struct xfs_inode *ip, const struct xfs_getparents *ppi, \ const struct xfs_attr_list_context *context, \ const struct xfs_getparents_rec *pptr), \ TP_ARGS(ip, ppi, context, pptr)) DEFINE_XFS_GETPARENTS_REC_EVENT(xfs_getparents_put_listent); DEFINE_XFS_GETPARENTS_REC_EVENT(xfs_getparents_expand_lastrec); DECLARE_EVENT_CLASS(xfs_getparents_class, TP_PROTO(struct xfs_inode *ip, const struct xfs_getparents *ppi, const struct xfs_attrlist_cursor_kern *cur), TP_ARGS(ip, ppi, cur), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(unsigned short, iflags) __field(unsigned short, oflags) __field(unsigned int, bufsize) __field(unsigned int, hashval) __field(unsigned int, blkno) __field(unsigned int, offset) __field(int, initted) ), TP_fast_assign( __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->iflags = ppi->gp_iflags; __entry->oflags = ppi->gp_oflags; __entry->bufsize = ppi->gp_bufsize; __entry->hashval = cur->hashval; __entry->blkno = cur->blkno; __entry->offset = cur->offset; __entry->initted = cur->initted; ), TP_printk("dev %d:%d ino 0x%llx iflags 0x%x oflags 0x%x bufsize %u cur_init? %d hashval 0x%x blkno %u offset %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->iflags, __entry->oflags, __entry->bufsize, __entry->initted, __entry->hashval, __entry->blkno, __entry->offset) ) #define DEFINE_XFS_GETPARENTS_EVENT(name) \ DEFINE_EVENT(xfs_getparents_class, name, \ TP_PROTO(struct xfs_inode *ip, const struct xfs_getparents *ppi, \ const struct xfs_attrlist_cursor_kern *cur), \ TP_ARGS(ip, ppi, cur)) DEFINE_XFS_GETPARENTS_EVENT(xfs_getparents_begin); DEFINE_XFS_GETPARENTS_EVENT(xfs_getparents_end); DECLARE_EVENT_CLASS(xfs_metadir_update_class, TP_PROTO(const struct xfs_metadir_update *upd), TP_ARGS(upd), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, dp_ino) __field(xfs_ino_t, ino) __string(fname, upd->path) ), TP_fast_assign( __entry->dev = upd->dp->i_mount->m_super->s_dev; __entry->dp_ino = I_INO(upd->dp); __entry->ino = upd->ip ? I_INO(upd->ip) : NULLFSINO; __assign_str(fname); ), TP_printk("dev %d:%d dp 0x%llx fname '%s' ino 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dp_ino, __get_str(fname), __entry->ino) ) #define DEFINE_METADIR_UPDATE_EVENT(name) \ DEFINE_EVENT(xfs_metadir_update_class, name, \ TP_PROTO(const struct xfs_metadir_update *upd), \ TP_ARGS(upd)) DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_start_create); DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_start_link); DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_commit); DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_cancel); DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_try_create); DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_create); DEFINE_METADIR_UPDATE_EVENT(xfs_metadir_link); DECLARE_EVENT_CLASS(xfs_metadir_update_error_class, TP_PROTO(const struct xfs_metadir_update *upd, int error), TP_ARGS(upd, error), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, dp_ino) __field(xfs_ino_t, ino) __field(int, error) __string(fname, upd->path) ), TP_fast_assign( __entry->dev = upd->dp->i_mount->m_super->s_dev; __entry->dp_ino = I_INO(upd->dp); __entry->ino = upd->ip ? I_INO(upd->ip) : NULLFSINO; __entry->error = error; __assign_str(fname); ), TP_printk("dev %d:%d dp 0x%llx fname '%s' ino 0x%llx error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dp_ino, __get_str(fname), __entry->ino, __entry->error) ) #define DEFINE_METADIR_UPDATE_ERROR_EVENT(name) \ DEFINE_EVENT(xfs_metadir_update_error_class, name, \ TP_PROTO(const struct xfs_metadir_update *upd, int error), \ TP_ARGS(upd, error)) DEFINE_METADIR_UPDATE_ERROR_EVENT(xfs_metadir_teardown); DECLARE_EVENT_CLASS(xfs_metadir_class, TP_PROTO(struct xfs_inode *dp, struct xfs_name *name, xfs_ino_t ino), TP_ARGS(dp, name, ino), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, dp_ino) __field(xfs_ino_t, ino) __field(int, ftype) __field(int, namelen) __dynamic_array(char, name, name->len) ), TP_fast_assign( __entry->dev = VFS_I(dp)->i_sb->s_dev; __entry->dp_ino = I_INO(dp); __entry->ino = ino, __entry->ftype = name->type; __entry->namelen = name->len; memcpy(__get_str(name), name->name, name->len); ), TP_printk("dev %d:%d dir 0x%llx type %s name '%.*s' ino 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->dp_ino, __print_symbolic(__entry->ftype, XFS_DIR3_FTYPE_STR), __entry->namelen, __get_str(name), __entry->ino) ) #define DEFINE_METADIR_EVENT(name) \ DEFINE_EVENT(xfs_metadir_class, name, \ TP_PROTO(struct xfs_inode *dp, struct xfs_name *name, \ xfs_ino_t ino), \ TP_ARGS(dp, name, ino)) DEFINE_METADIR_EVENT(xfs_metadir_lookup); /* metadata inode space reservations */ DECLARE_EVENT_CLASS(xfs_metafile_resv_class, TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len), TP_ARGS(mp, len), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, freeblks) __field(unsigned long long, reserved) __field(unsigned long long, asked) __field(unsigned long long, used) __field(unsigned long long, len) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->freeblks = xfs_sum_freecounter_raw(mp, XC_FREE_BLOCKS); __entry->reserved = mp->m_metafile_resv_avail; __entry->asked = mp->m_metafile_resv_target; __entry->used = mp->m_metafile_resv_used; __entry->len = len; ), TP_printk("dev %d:%d freeblks %llu resv %llu ask %llu used %llu len %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->freeblks, __entry->reserved, __entry->asked, __entry->used, __entry->len) ) #define DEFINE_METAFILE_RESV_EVENT(name) \ DEFINE_EVENT(xfs_metafile_resv_class, name, \ TP_PROTO(struct xfs_mount *mp, xfs_filblks_t len), \ TP_ARGS(mp, len)) DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init); DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free); DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_alloc_space); DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_free_space); DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_critical); DEFINE_METAFILE_RESV_EVENT(xfs_metafile_resv_init_error); #ifdef CONFIG_XFS_RT TRACE_EVENT(xfs_growfs_check_rtgeom, TP_PROTO(const struct xfs_mount *mp, unsigned int min_logfsbs), TP_ARGS(mp, min_logfsbs), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, logblocks) __field(unsigned int, min_logfsbs) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->logblocks = mp->m_sb.sb_logblocks; __entry->min_logfsbs = min_logfsbs; ), TP_printk("dev %d:%d logblocks %u min_logfsbs %u", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->logblocks, __entry->min_logfsbs) ); #endif /* CONFIG_XFS_RT */ TRACE_DEFINE_ENUM(XC_FREE_BLOCKS); TRACE_DEFINE_ENUM(XC_FREE_RTEXTENTS); TRACE_DEFINE_ENUM(XC_FREE_RTAVAILABLE); DECLARE_EVENT_CLASS(xfs_freeblocks_resv_class, TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr, uint64_t delta, unsigned long caller_ip), TP_ARGS(mp, ctr, delta, caller_ip), TP_STRUCT__entry( __field(dev_t, dev) __field(enum xfs_free_counter, ctr) __field(uint64_t, delta) __field(uint64_t, avail) __field(uint64_t, total) __field(unsigned long, caller_ip) ), TP_fast_assign( __entry->dev = mp->m_super->s_dev; __entry->ctr = ctr; __entry->delta = delta; __entry->avail = mp->m_free[ctr].res_avail; __entry->total = mp->m_free[ctr].res_total; __entry->caller_ip = caller_ip; ), TP_printk("dev %d:%d ctr %s delta %llu avail %llu total %llu caller %pS", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->ctr, XFS_FREECOUNTER_STR), __entry->delta, __entry->avail, __entry->total, (char *)__entry->caller_ip) ) #define DEFINE_FREEBLOCKS_RESV_EVENT(name) \ DEFINE_EVENT(xfs_freeblocks_resv_class, name, \ TP_PROTO(struct xfs_mount *mp, enum xfs_free_counter ctr, \ uint64_t delta, unsigned long caller_ip), \ TP_ARGS(mp, ctr, delta, caller_ip)) DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_reserved); DEFINE_FREEBLOCKS_RESV_EVENT(xfs_freecounter_enospc); TRACE_EVENT(xfs_healthmon_lost_event, TP_PROTO(const struct xfs_healthmon *hm), TP_ARGS(hm), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned long long, lost_prev) ), TP_fast_assign( __entry->dev = hm->dev; __entry->lost_prev = hm->lost_prev_event; ), TP_printk("dev %d:%d lost_prev %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->lost_prev) ); #define XFS_HEALTHMON_FLAGS_STRINGS \ { XFS_HEALTH_MONITOR_VERBOSE, "verbose" } #define XFS_HEALTHMON_FMT_STRINGS \ { XFS_HEALTH_MONITOR_FMT_V0, "v0" } TRACE_EVENT(xfs_healthmon_create, TP_PROTO(dev_t dev, u64 flags, u8 format), TP_ARGS(dev, flags, format), TP_STRUCT__entry( __field(dev_t, dev) __field(u64, flags) __field(u8, format) ), TP_fast_assign( __entry->dev = dev; __entry->flags = flags; __entry->format = format; ), TP_printk("dev %d:%d flags %s format %s", MAJOR(__entry->dev), MINOR(__entry->dev), __print_flags(__entry->flags, "|", XFS_HEALTHMON_FLAGS_STRINGS), __print_symbolic(__entry->format, XFS_HEALTHMON_FMT_STRINGS)) ); TRACE_EVENT(xfs_healthmon_copybuf, TP_PROTO(const struct xfs_healthmon *hm, const struct iov_iter *iov), TP_ARGS(hm, iov), TP_STRUCT__entry( __field(dev_t, dev) __field(size_t, bufsize) __field(size_t, inpos) __field(size_t, outpos) __field(size_t, to_copy) __field(size_t, iter_count) ), TP_fast_assign( __entry->dev = hm->dev; __entry->bufsize = hm->bufsize; __entry->inpos = hm->bufhead; __entry->outpos = hm->buftail; if (hm->bufhead > hm->buftail) __entry->to_copy = hm->bufhead - hm->buftail; else __entry->to_copy = 0; __entry->iter_count = iov_iter_count(iov); ), TP_printk("dev %d:%d bufsize %zu in_pos %zu out_pos %zu to_copy %zu iter_count %zu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->bufsize, __entry->inpos, __entry->outpos, __entry->to_copy, __entry->iter_count) ); DECLARE_EVENT_CLASS(xfs_healthmon_class, TP_PROTO(const struct xfs_healthmon *hm), TP_ARGS(hm), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, events) __field(unsigned long long, lost_prev) ), TP_fast_assign( __entry->dev = hm->dev; __entry->events = hm->events; __entry->lost_prev = hm->lost_prev_event; ), TP_printk("dev %d:%d events %u lost_prev? %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->events, __entry->lost_prev) ); #define DEFINE_HEALTHMON_EVENT(name) \ DEFINE_EVENT(xfs_healthmon_class, name, \ TP_PROTO(const struct xfs_healthmon *hm), \ TP_ARGS(hm)) DEFINE_HEALTHMON_EVENT(xfs_healthmon_read_start); DEFINE_HEALTHMON_EVENT(xfs_healthmon_read_finish); DEFINE_HEALTHMON_EVENT(xfs_healthmon_release); DEFINE_HEALTHMON_EVENT(xfs_healthmon_detach); DEFINE_HEALTHMON_EVENT(xfs_healthmon_report_unmount); #define XFS_HEALTHMON_TYPE_STRINGS \ { XFS_HEALTHMON_LOST, "lost" }, \ { XFS_HEALTHMON_UNMOUNT, "unmount" }, \ { XFS_HEALTHMON_SICK, "sick" }, \ { XFS_HEALTHMON_CORRUPT, "corrupt" }, \ { XFS_HEALTHMON_HEALTHY, "healthy" }, \ { XFS_HEALTHMON_SHUTDOWN, "shutdown" } #define XFS_HEALTHMON_DOMAIN_STRINGS \ { XFS_HEALTHMON_MOUNT, "mount" }, \ { XFS_HEALTHMON_FS, "fs" }, \ { XFS_HEALTHMON_AG, "ag" }, \ { XFS_HEALTHMON_INODE, "inode" }, \ { XFS_HEALTHMON_RTGROUP, "rtgroup" } TRACE_DEFINE_ENUM(XFS_HEALTHMON_LOST); TRACE_DEFINE_ENUM(XFS_HEALTHMON_SHUTDOWN); TRACE_DEFINE_ENUM(XFS_HEALTHMON_UNMOUNT); TRACE_DEFINE_ENUM(XFS_HEALTHMON_SICK); TRACE_DEFINE_ENUM(XFS_HEALTHMON_CORRUPT); TRACE_DEFINE_ENUM(XFS_HEALTHMON_HEALTHY); TRACE_DEFINE_ENUM(XFS_HEALTHMON_MOUNT); TRACE_DEFINE_ENUM(XFS_HEALTHMON_FS); TRACE_DEFINE_ENUM(XFS_HEALTHMON_AG); TRACE_DEFINE_ENUM(XFS_HEALTHMON_INODE); TRACE_DEFINE_ENUM(XFS_HEALTHMON_RTGROUP); DECLARE_EVENT_CLASS(xfs_healthmon_event_class, TP_PROTO(const struct xfs_healthmon *hm, const struct xfs_healthmon_event *event), TP_ARGS(hm, event), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, type) __field(unsigned int, domain) __field(unsigned int, mask) __field(unsigned long long, ino) __field(unsigned int, gen) __field(unsigned int, group) __field(unsigned long long, offset) __field(unsigned long long, length) __field(unsigned long long, lostcount) ), TP_fast_assign( __entry->dev = hm->dev; __entry->type = event->type; __entry->domain = event->domain; __entry->mask = 0; __entry->group = 0; __entry->ino = 0; __entry->gen = 0; __entry->offset = 0; __entry->length = 0; __entry->lostcount = 0; switch (__entry->domain) { case XFS_HEALTHMON_MOUNT: switch (__entry->type) { case XFS_HEALTHMON_SHUTDOWN: __entry->mask = event->flags; break; case XFS_HEALTHMON_LOST: __entry->lostcount = event->lostcount; break; } break; case XFS_HEALTHMON_FS: __entry->mask = event->fsmask; break; case XFS_HEALTHMON_AG: case XFS_HEALTHMON_RTGROUP: __entry->mask = event->grpmask; __entry->group = event->group; break; case XFS_HEALTHMON_INODE: __entry->mask = event->imask; __entry->ino = event->ino; __entry->gen = event->gen; break; case XFS_HEALTHMON_DATADEV: case XFS_HEALTHMON_LOGDEV: case XFS_HEALTHMON_RTDEV: __entry->offset = event->daddr; __entry->length = event->bbcount; break; case XFS_HEALTHMON_FILERANGE: __entry->ino = event->fino; __entry->gen = event->fgen; __entry->offset = event->fpos; __entry->length = event->flen; break; } ), TP_printk("dev %d:%d type %s domain %s mask 0x%x ino 0x%llx gen 0x%x offset 0x%llx len 0x%llx group 0x%x lost %llu", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XFS_HEALTHMON_TYPE_STRINGS), __print_symbolic(__entry->domain, XFS_HEALTHMON_DOMAIN_STRINGS), __entry->mask, __entry->ino, __entry->gen, __entry->offset, __entry->length, __entry->group, __entry->lostcount) ); #define DEFINE_HEALTHMONEVENT_EVENT(name) \ DEFINE_EVENT(xfs_healthmon_event_class, name, \ TP_PROTO(const struct xfs_healthmon *hm, \ const struct xfs_healthmon_event *event), \ TP_ARGS(hm, event)) DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_insert); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_push); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_pop); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_format); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_format_overflow); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_drop); DEFINE_HEALTHMONEVENT_EVENT(xfs_healthmon_merge); TRACE_EVENT(xfs_healthmon_report_fs, TP_PROTO(const struct xfs_healthmon *hm, unsigned int old_mask, unsigned int new_mask, const struct xfs_healthmon_event *event), TP_ARGS(hm, old_mask, new_mask, event), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, type) __field(unsigned int, domain) __field(unsigned int, old_mask) __field(unsigned int, new_mask) __field(unsigned int, fsmask) ), TP_fast_assign( __entry->dev = hm->dev; __entry->type = event->type; __entry->domain = event->domain; __entry->old_mask = old_mask; __entry->new_mask = new_mask; __entry->fsmask = event->fsmask; ), TP_printk("dev %d:%d type %s domain %s oldmask 0x%x newmask 0x%x fsmask 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XFS_HEALTHMON_TYPE_STRINGS), __print_symbolic(__entry->domain, XFS_HEALTHMON_DOMAIN_STRINGS), __entry->old_mask, __entry->new_mask, __entry->fsmask) ); TRACE_EVENT(xfs_healthmon_report_group, TP_PROTO(const struct xfs_healthmon *hm, unsigned int old_mask, unsigned int new_mask, const struct xfs_healthmon_event *event), TP_ARGS(hm, old_mask, new_mask, event), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, type) __field(unsigned int, domain) __field(unsigned int, old_mask) __field(unsigned int, new_mask) __field(unsigned int, grpmask) __field(unsigned int, group) ), TP_fast_assign( __entry->dev = hm->dev; __entry->type = event->type; __entry->domain = event->domain; __entry->old_mask = old_mask; __entry->new_mask = new_mask; __entry->grpmask = event->grpmask; __entry->group = event->group; ), TP_printk("dev %d:%d type %s domain %s oldmask 0x%x newmask 0x%x grpmask 0x%x group 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XFS_HEALTHMON_TYPE_STRINGS), __print_symbolic(__entry->domain, XFS_HEALTHMON_DOMAIN_STRINGS), __entry->old_mask, __entry->new_mask, __entry->grpmask, __entry->group) ); TRACE_EVENT(xfs_healthmon_report_inode, TP_PROTO(const struct xfs_healthmon *hm, unsigned int old_mask, unsigned int new_mask, const struct xfs_healthmon_event *event), TP_ARGS(hm, old_mask, new_mask, event), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, type) __field(unsigned int, domain) __field(unsigned int, old_mask) __field(unsigned int, new_mask) __field(unsigned int, imask) __field(unsigned long long, ino) __field(unsigned int, gen) ), TP_fast_assign( __entry->dev = hm->dev; __entry->type = event->type; __entry->domain = event->domain; __entry->old_mask = old_mask; __entry->new_mask = new_mask; __entry->imask = event->imask; __entry->ino = event->ino; __entry->gen = event->gen; ), TP_printk("dev %d:%d type %s domain %s oldmask 0x%x newmask 0x%x imask 0x%x ino 0x%llx gen 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->type, XFS_HEALTHMON_TYPE_STRINGS), __print_symbolic(__entry->domain, XFS_HEALTHMON_DOMAIN_STRINGS), __entry->old_mask, __entry->new_mask, __entry->imask, __entry->ino, __entry->gen) ); TRACE_EVENT(xfs_healthmon_report_shutdown, TP_PROTO(const struct xfs_healthmon *hm, uint32_t shutdown_flags), TP_ARGS(hm, shutdown_flags), TP_STRUCT__entry( __field(dev_t, dev) __field(uint32_t, shutdown_flags) ), TP_fast_assign( __entry->dev = hm->dev; __entry->shutdown_flags = shutdown_flags; ), TP_printk("dev %d:%d shutdown_flags %s", MAJOR(__entry->dev), MINOR(__entry->dev), __print_flags(__entry->shutdown_flags, "|", XFS_SHUTDOWN_STRINGS)) ); #define XFS_DEVICE_STRINGS \ { XFS_DEV_DATA, "datadev" }, \ { XFS_DEV_RT, "rtdev" }, \ { XFS_DEV_LOG, "logdev" } TRACE_DEFINE_ENUM(XFS_DEV_DATA); TRACE_DEFINE_ENUM(XFS_DEV_RT); TRACE_DEFINE_ENUM(XFS_DEV_LOG); TRACE_EVENT(xfs_healthmon_report_media, TP_PROTO(const struct xfs_healthmon *hm, enum xfs_device fdev, const struct xfs_healthmon_event *event), TP_ARGS(hm, fdev, event), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, error_dev) __field(uint64_t, daddr) __field(uint64_t, bbcount) ), TP_fast_assign( __entry->dev = hm->dev; __entry->error_dev = fdev; __entry->daddr = event->daddr; __entry->bbcount = event->bbcount; ), TP_printk("dev %d:%d %s daddr 0x%llx bbcount 0x%llx", MAJOR(__entry->dev), MINOR(__entry->dev), __print_symbolic(__entry->error_dev, XFS_DEVICE_STRINGS), __entry->daddr, __entry->bbcount) ); #define FS_ERROR_STRINGS \ { FSERR_BUFFERED_READ, "buffered_read" }, \ { FSERR_BUFFERED_WRITE, "buffered_write" }, \ { FSERR_DIRECTIO_READ, "directio_read" }, \ { FSERR_DIRECTIO_WRITE, "directio_write" }, \ { FSERR_DATA_LOST, "data_lost" }, \ { FSERR_METADATA, "metadata" } TRACE_DEFINE_ENUM(FSERR_BUFFERED_READ); TRACE_DEFINE_ENUM(FSERR_BUFFERED_WRITE); TRACE_DEFINE_ENUM(FSERR_DIRECTIO_READ); TRACE_DEFINE_ENUM(FSERR_DIRECTIO_WRITE); TRACE_DEFINE_ENUM(FSERR_DATA_LOST); TRACE_DEFINE_ENUM(FSERR_METADATA); TRACE_EVENT(xfs_healthmon_report_file_ioerror, TP_PROTO(const struct xfs_healthmon *hm, const struct fserror_event *p), TP_ARGS(hm, p), TP_STRUCT__entry( __field(dev_t, dev) __field(unsigned int, type) __field(unsigned long long, ino) __field(unsigned int, gen) __field(long long, pos) __field(unsigned long long, len) __field(int, error) ), TP_fast_assign( __entry->dev = hm->dev; __entry->type = p->type; __entry->ino = p->inode->i_ino; __entry->gen = p->inode->i_generation; __entry->pos = p->pos; __entry->len = p->len; __entry->error = p->error; ), TP_printk("dev %d:%d ino 0x%llx gen 0x%x op %s pos 0x%llx bytecount 0x%llx error %d", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->gen, __print_symbolic(__entry->type, FS_ERROR_STRINGS), __entry->pos, __entry->len, __entry->error) ); TRACE_EVENT(xfs_verify_media, TP_PROTO(const struct xfs_mount *mp, const struct xfs_verify_media *me, dev_t fdev, xfs_daddr_t daddr, uint64_t bbcount, const struct folio *folio), TP_ARGS(mp, me, fdev, daddr, bbcount, folio), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, fdev) __field(xfs_daddr_t, start_daddr) __field(xfs_daddr_t, end_daddr) __field(unsigned int, flags) __field(xfs_daddr_t, daddr) __field(uint64_t, bbcount) __field(unsigned int, bufsize) ), TP_fast_assign( __entry->dev = mp->m_ddev_targp->bt_dev; __entry->fdev = fdev; __entry->start_daddr = me->me_start_daddr; __entry->end_daddr = me->me_end_daddr; __entry->flags = me->me_flags; __entry->daddr = daddr; __entry->bbcount = bbcount; __entry->bufsize = folio_size(folio); ), TP_printk("dev %d:%d fdev %d:%d start_daddr 0x%llx end_daddr 0x%llx flags 0x%x daddr 0x%llx bbcount 0x%llx bufsize 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->fdev), MINOR(__entry->fdev), __entry->start_daddr, __entry->end_daddr, __entry->flags, __entry->daddr, __entry->bbcount, __entry->bufsize) ); TRACE_EVENT(xfs_verify_media_end, TP_PROTO(const struct xfs_mount *mp, const struct xfs_verify_media *me, dev_t fdev), TP_ARGS(mp, me, fdev), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, fdev) __field(xfs_daddr_t, start_daddr) __field(xfs_daddr_t, end_daddr) __field(int, ioerror) ), TP_fast_assign( __entry->dev = mp->m_ddev_targp->bt_dev; __entry->fdev = fdev; __entry->start_daddr = me->me_start_daddr; __entry->end_daddr = me->me_end_daddr; __entry->ioerror = me->me_ioerror; ), TP_printk("dev %d:%d fdev %d:%d start_daddr 0x%llx end_daddr 0x%llx ioerror %d", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->fdev), MINOR(__entry->fdev), __entry->start_daddr, __entry->end_daddr, __entry->ioerror) ); TRACE_EVENT(xfs_verify_media_error, TP_PROTO(const struct xfs_mount *mp, const struct xfs_verify_media *me, dev_t fdev, xfs_daddr_t daddr, uint64_t bbcount, blk_status_t status), TP_ARGS(mp, me, fdev, daddr, bbcount, status), TP_STRUCT__entry( __field(dev_t, dev) __field(dev_t, fdev) __field(xfs_daddr_t, start_daddr) __field(xfs_daddr_t, end_daddr) __field(unsigned int, flags) __field(xfs_daddr_t, daddr) __field(uint64_t, bbcount) __field(int, error) ), TP_fast_assign( __entry->dev = mp->m_ddev_targp->bt_dev; __entry->fdev = fdev; __entry->start_daddr = me->me_start_daddr; __entry->end_daddr = me->me_end_daddr; __entry->flags = me->me_flags; __entry->daddr = daddr; __entry->bbcount = bbcount; __entry->error = blk_status_to_errno(status); ), TP_printk("dev %d:%d fdev %d:%d start_daddr 0x%llx end_daddr 0x%llx flags 0x%x daddr 0x%llx bbcount 0x%llx error %d", MAJOR(__entry->dev), MINOR(__entry->dev), MAJOR(__entry->fdev), MINOR(__entry->fdev), __entry->start_daddr, __entry->end_daddr, __entry->flags, __entry->daddr, __entry->bbcount, __entry->error) ); TRACE_EVENT(xfs_bmap_replace_cow_mapping, TP_PROTO(struct xfs_inode *ip, const struct xfs_bmbt_irec *got, const struct xfs_bmbt_irec *rep), TP_ARGS(ip, got, rep), TP_STRUCT__entry( __field(dev_t, dev) __field(xfs_ino_t, ino) __field(xfs_fsblock_t, startblock) __field(xfs_fileoff_t, startoff) __field(xfs_filblks_t, blockcount) __field(xfs_exntst_t, state) __field(xfs_fileoff_t, new_startoff) __field(xfs_fsblock_t, new_startblock) __field(xfs_extlen_t, new_blockcount) __field(xfs_exntst_t, new_state) ), TP_fast_assign( __entry->dev = ip->i_mount->m_super->s_dev; __entry->ino = I_INO(ip); __entry->startoff = got->br_startoff; __entry->startblock = got->br_startblock; __entry->blockcount = got->br_blockcount; __entry->state = got->br_state; __entry->new_startoff = rep->br_startoff; __entry->new_startblock = rep->br_startblock; __entry->new_blockcount = rep->br_blockcount; __entry->new_state = rep->br_state; ), TP_printk("dev %d:%d ino 0x%llx startoff 0x%llx startblock 0x%llx fsbcount 0x%llx state 0x%x new_startoff 0x%llx new_startblock 0x%llx new_fsbcount 0x%x new_state 0x%x", MAJOR(__entry->dev), MINOR(__entry->dev), __entry->ino, __entry->startoff, __entry->startblock, __entry->blockcount, __entry->state, __entry->new_startoff, __entry->new_startblock, __entry->new_blockcount, __entry->new_state) ); #endif /* _TRACE_XFS_H */ #undef TRACE_INCLUDE_PATH #define TRACE_INCLUDE_PATH . #define TRACE_INCLUDE_FILE xfs_trace #include <trace/define_trace.h> |
| 16 17 4 4 17 17 17 17 18 1 16 1 2 4 17 17 5 4 17 17 17 1 17 17 17 16 17 17 16 2 2 2 2 2 2 2 2 1 32 14 25 1 1 1 8 24 8 16 17 15 2 16 14 1 1 1 1 1 1 15 16 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* Basic authentication token and access key management * * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved. * Written by David Howells (dhowells@redhat.com) */ #include <linux/export.h> #include <linux/init.h> #include <linux/poison.h> #include <linux/sched.h> #include <linux/slab.h> #include <linux/security.h> #include <linux/workqueue.h> #include <linux/random.h> #include <linux/err.h> #include "internal.h" struct kmem_cache *key_jar; struct rb_root key_serial_tree; /* tree of keys indexed by serial */ DEFINE_SPINLOCK(key_serial_lock); struct rb_root key_user_tree; /* tree of quota records indexed by UID */ DEFINE_SPINLOCK(key_user_lock); unsigned int key_quota_root_maxkeys = 1000000; /* root's key count quota */ unsigned int key_quota_root_maxbytes = 25000000; /* root's key space quota */ unsigned int key_quota_maxkeys = 200; /* general key count quota */ unsigned int key_quota_maxbytes = 20000; /* general key space quota */ static LIST_HEAD(key_types_list); static DECLARE_RWSEM(key_types_sem); /* We serialise key instantiation and link */ DEFINE_MUTEX(key_construction_mutex); #ifdef KEY_DEBUGGING void __key_check(const struct key *key) { printk("__key_check: key %p {%08x} should be {%08x}\n", key, key->magic, KEY_DEBUG_MAGIC); BUG(); } #endif /* * Get the key quota record for a user, allocating a new record if one doesn't * already exist. */ struct key_user *key_user_lookup(kuid_t uid) { struct key_user *candidate = NULL, *user; struct rb_node *parent, **p; try_again: parent = NULL; p = &key_user_tree.rb_node; spin_lock(&key_user_lock); /* search the tree for a user record with a matching UID */ while (*p) { parent = *p; user = rb_entry(parent, struct key_user, node); if (uid_lt(uid, user->uid)) p = &(*p)->rb_left; else if (uid_gt(uid, user->uid)) p = &(*p)->rb_right; else goto found; } /* if we get here, we failed to find a match in the tree */ if (!candidate) { /* allocate a candidate user record if we don't already have * one */ spin_unlock(&key_user_lock); user = NULL; candidate = kmalloc_obj(struct key_user); if (unlikely(!candidate)) goto out; /* the allocation may have scheduled, so we need to repeat the * search lest someone else added the record whilst we were * asleep */ goto try_again; } /* if we get here, then the user record still hadn't appeared on the * second pass - so we use the candidate record */ refcount_set(&candidate->usage, 1); atomic_set(&candidate->nkeys, 0); atomic_set(&candidate->nikeys, 0); candidate->uid = uid; candidate->qnkeys = 0; candidate->qnbytes = 0; spin_lock_init(&candidate->lock); mutex_init(&candidate->cons_lock); rb_link_node(&candidate->node, parent, p); rb_insert_color(&candidate->node, &key_user_tree); spin_unlock(&key_user_lock); user = candidate; goto out; /* okay - we found a user record for this UID */ found: refcount_inc(&user->usage); spin_unlock(&key_user_lock); kfree(candidate); out: return user; } /* * Dispose of a user structure */ void key_user_put(struct key_user *user) { if (refcount_dec_and_lock(&user->usage, &key_user_lock)) { rb_erase(&user->node, &key_user_tree); spin_unlock(&key_user_lock); kfree(user); } } /* * Allocate a serial number for a key. These are assigned randomly to avoid * security issues through covert channel problems. */ static inline void key_alloc_serial(struct key *key) { struct rb_node *parent, **p; struct key *xkey; /* propose a random serial number and look for a hole for it in the * serial number tree */ do { get_random_bytes(&key->serial, sizeof(key->serial)); key->serial >>= 1; /* negative numbers are not permitted */ } while (key->serial < 3); spin_lock(&key_serial_lock); attempt_insertion: parent = NULL; p = &key_serial_tree.rb_node; while (*p) { parent = *p; xkey = rb_entry(parent, struct key, serial_node); if (key->serial < xkey->serial) p = &(*p)->rb_left; else if (key->serial > xkey->serial) p = &(*p)->rb_right; else goto serial_exists; } /* we've found a suitable hole - arrange for this key to occupy it */ rb_link_node(&key->serial_node, parent, p); rb_insert_color(&key->serial_node, &key_serial_tree); spin_unlock(&key_serial_lock); return; /* we found a key with the proposed serial number - walk the tree from * that point looking for the next unused serial number */ serial_exists: for (;;) { key->serial++; if (key->serial < 3) { key->serial = 3; goto attempt_insertion; } parent = rb_next(parent); if (!parent) goto attempt_insertion; xkey = rb_entry(parent, struct key, serial_node); if (key->serial < xkey->serial) goto attempt_insertion; } } /** * key_alloc - Allocate a key of the specified type. * @type: The type of key to allocate. * @desc: The key description to allow the key to be searched out. * @uid: The owner of the new key. * @gid: The group ID for the new key's group permissions. * @cred: The credentials specifying UID namespace. * @perm: The permissions mask of the new key. * @flags: Flags specifying quota properties. * @restrict_link: Optional link restriction for new keyrings. * * Allocate a key of the specified type with the attributes given. The key is * returned in an uninstantiated state and the caller needs to instantiate the * key before returning. * * The restrict_link structure (if not NULL) will be freed when the * keyring is destroyed, so it must be dynamically allocated. * * The user's key count quota is updated to reflect the creation of the key and * the user's key data quota has the default for the key type reserved. The * instantiation function should amend this as necessary. If insufficient * quota is available, -EDQUOT will be returned. * * The LSM security modules can prevent a key being created, in which case * -EACCES will be returned. * * Returns a pointer to the new key if successful and an error code otherwise. * * Note that the caller needs to ensure the key type isn't uninstantiated. * Internally this can be done by locking key_types_sem. Externally, this can * be done by either never unregistering the key type, or making sure * key_alloc() calls don't race with module unloading. */ struct key *key_alloc(struct key_type *type, const char *desc, kuid_t uid, kgid_t gid, const struct cred *cred, key_perm_t perm, unsigned long flags, struct key_restriction *restrict_link) { struct key_user *user = NULL; struct key *key; size_t desclen, quotalen; int ret; unsigned long irqflags; key = ERR_PTR(-EINVAL); if (!desc || !*desc) goto error; if (type->vet_description) { ret = type->vet_description(desc); if (ret < 0) { key = ERR_PTR(ret); goto error; } } desclen = strlen(desc); quotalen = desclen + 1 + type->def_datalen; /* get hold of the key tracking for this user */ user = key_user_lookup(uid); if (!user) goto no_memory_1; /* check that the user's quota permits allocation of another key and * its description */ if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { unsigned maxkeys = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxkeys : key_quota_maxkeys; unsigned maxbytes = uid_eq(uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; spin_lock_irqsave(&user->lock, irqflags); if (!(flags & KEY_ALLOC_QUOTA_OVERRUN)) { if (user->qnkeys + 1 > maxkeys || user->qnbytes + quotalen > maxbytes || user->qnbytes + quotalen < user->qnbytes) goto no_quota; } user->qnkeys++; user->qnbytes += quotalen; spin_unlock_irqrestore(&user->lock, irqflags); } /* allocate and initialise the key and its description */ key = kmem_cache_zalloc(key_jar, GFP_KERNEL); if (!key) goto no_memory_2; key->index_key.desc_len = desclen; key->index_key.description = kmemdup(desc, desclen + 1, GFP_KERNEL); if (!key->index_key.description) goto no_memory_3; key->index_key.type = type; key_set_index_key(&key->index_key); refcount_set(&key->usage, 1); init_rwsem(&key->sem); lockdep_set_class(&key->sem, &type->lock_class); key->user = user; key->quotalen = quotalen; key->datalen = type->def_datalen; key->uid = uid; key->gid = gid; key->perm = perm; key->expiry = TIME64_MAX; key->restrict_link = restrict_link; key->last_used_at = ktime_get_real_seconds(); key->flags |= 1 << KEY_FLAG_USER_ALIVE; if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) key->flags |= 1 << KEY_FLAG_IN_QUOTA; if (flags & KEY_ALLOC_BUILT_IN) key->flags |= 1 << KEY_FLAG_BUILTIN; if (flags & KEY_ALLOC_UID_KEYRING) key->flags |= 1 << KEY_FLAG_UID_KEYRING; if (flags & KEY_ALLOC_SET_KEEP) key->flags |= 1 << KEY_FLAG_KEEP; #ifdef KEY_DEBUGGING key->magic = KEY_DEBUG_MAGIC; #endif /* let the security module know about the key */ ret = security_key_alloc(key, cred, flags); if (ret < 0) goto security_error; /* publish the key by giving it a serial number */ refcount_inc(&key->domain_tag->usage); atomic_inc(&user->nkeys); key_alloc_serial(key); error: return key; security_error: kfree(key->description); kmem_cache_free(key_jar, key); if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { spin_lock_irqsave(&user->lock, irqflags); user->qnkeys--; user->qnbytes -= quotalen; spin_unlock_irqrestore(&user->lock, irqflags); } key_user_put(user); key = ERR_PTR(ret); goto error; no_memory_3: kmem_cache_free(key_jar, key); no_memory_2: if (!(flags & KEY_ALLOC_NOT_IN_QUOTA)) { spin_lock_irqsave(&user->lock, irqflags); user->qnkeys--; user->qnbytes -= quotalen; spin_unlock_irqrestore(&user->lock, irqflags); } key_user_put(user); no_memory_1: key = ERR_PTR(-ENOMEM); goto error; no_quota: spin_unlock_irqrestore(&user->lock, irqflags); key_user_put(user); key = ERR_PTR(-EDQUOT); goto error; } EXPORT_SYMBOL(key_alloc); /** * key_payload_reserve - Adjust data quota reservation for the key's payload * @key: The key to make the reservation for. * @datalen: The amount of data payload the caller now wants. * * Adjust the amount of the owning user's key data quota that a key reserves. * If the amount is increased, then -EDQUOT may be returned if there isn't * enough free quota available. * * If successful, 0 is returned. */ int key_payload_reserve(struct key *key, size_t datalen) { int delta = (int)datalen - key->datalen; int ret = 0; key_check(key); /* contemplate the quota adjustment */ if (delta != 0 && test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { unsigned maxbytes = uid_eq(key->user->uid, GLOBAL_ROOT_UID) ? key_quota_root_maxbytes : key_quota_maxbytes; unsigned long flags; spin_lock_irqsave(&key->user->lock, flags); if (delta > 0 && (key->user->qnbytes + delta > maxbytes || key->user->qnbytes + delta < key->user->qnbytes)) { ret = -EDQUOT; } else { key->user->qnbytes += delta; key->quotalen += delta; } spin_unlock_irqrestore(&key->user->lock, flags); } /* change the recorded data length if that didn't generate an error */ if (ret == 0) key->datalen = datalen; return ret; } EXPORT_SYMBOL(key_payload_reserve); /* * Change the key state to being instantiated. */ static void mark_key_instantiated(struct key *key, int reject_error) { /* Commit the payload before setting the state; barrier versus * key_read_state(). */ smp_store_release(&key->state, (reject_error < 0) ? reject_error : KEY_IS_POSITIVE); } /* * Instantiate a key and link it into the target keyring atomically. Must be * called with the target keyring's semaphore writelocked. The target key's * semaphore need not be locked as instantiation is serialised by * key_construction_mutex. */ static int __key_instantiate_and_link(struct key *key, struct key_preparsed_payload *prep, struct key *keyring, struct key *authkey, struct assoc_array_edit **_edit) { int ret, awaken; key_check(key); key_check(keyring); awaken = 0; ret = -EBUSY; mutex_lock(&key_construction_mutex); /* can't instantiate twice */ if (key->state == KEY_IS_UNINSTANTIATED) { /* instantiate the key */ ret = key->type->instantiate(key, prep); if (ret == 0) { /* mark the key as being instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_INSTANTIATED, 0); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; /* and link it into the destination keyring */ if (keyring) { if (test_bit(KEY_FLAG_KEEP, &keyring->flags)) set_bit(KEY_FLAG_KEEP, &key->flags); __key_link(keyring, key, _edit); } /* disable the authorisation key */ if (authkey) key_invalidate(authkey); if (prep->expiry != TIME64_MAX) key_set_expiry(key, prep->expiry); } } mutex_unlock(&key_construction_mutex); /* wake up anyone waiting for a key to be constructed */ if (awaken) wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT); return ret; } /** * key_instantiate_and_link - Instantiate a key and link it into the keyring. * @key: The key to instantiate. * @data: The data to use to instantiate the keyring. * @datalen: The length of @data. * @keyring: Keyring to create a link in on success (or NULL). * @authkey: The authorisation token permitting instantiation. * * Instantiate a key that's in the uninstantiated state using the provided data * and, if successful, link it in to the destination keyring if one is * supplied. * * If successful, 0 is returned, the authorisation token is revoked and anyone * waiting for the key is woken up. If the key was already instantiated, * -EBUSY will be returned. */ int key_instantiate_and_link(struct key *key, const void *data, size_t datalen, struct key *keyring, struct key *authkey) { struct key_preparsed_payload prep; struct assoc_array_edit *edit = NULL; int ret; memset(&prep, 0, sizeof(prep)); prep.orig_description = key->description; prep.data = data; prep.datalen = datalen; prep.quotalen = key->type->def_datalen; prep.expiry = TIME64_MAX; if (key->type->preparse) { ret = key->type->preparse(&prep); if (ret < 0) goto error; } if (keyring) { ret = __key_link_lock(keyring, &key->index_key); if (ret < 0) goto error; ret = __key_link_begin(keyring, &key->index_key, &edit); if (ret < 0) goto error_link_end; if (keyring->restrict_link && keyring->restrict_link->check) { struct key_restriction *keyres = keyring->restrict_link; ret = keyres->check(keyring, key->type, &prep.payload, keyres->key); if (ret < 0) goto error_link_end; } } ret = __key_instantiate_and_link(key, &prep, keyring, authkey, &edit); error_link_end: if (keyring) __key_link_end(keyring, &key->index_key, edit); error: if (key->type->preparse) key->type->free_preparse(&prep); return ret; } EXPORT_SYMBOL(key_instantiate_and_link); /** * key_reject_and_link - Negatively instantiate a key and link it into the keyring. * @key: The key to instantiate. * @timeout: The timeout on the negative key. * @error: The error to return when the key is hit. * @keyring: Keyring to create a link in on success (or NULL). * @authkey: The authorisation token permitting instantiation. * * Negatively instantiate a key that's in the uninstantiated state and, if * successful, set its timeout and stored error and link it in to the * destination keyring if one is supplied. The key and any links to the key * will be automatically garbage collected after the timeout expires. * * Negative keys are used to rate limit repeated request_key() calls by causing * them to return the stored error code (typically ENOKEY) until the negative * key expires. * * If successful, 0 is returned, the authorisation token is revoked and anyone * waiting for the key is woken up. If the key was already instantiated, * -EBUSY will be returned. */ int key_reject_and_link(struct key *key, unsigned timeout, unsigned error, struct key *keyring, struct key *authkey) { struct assoc_array_edit *edit = NULL; int ret, awaken, link_ret = 0; key_check(key); key_check(keyring); awaken = 0; ret = -EBUSY; if (keyring) { if (keyring->restrict_link) return -EPERM; link_ret = __key_link_lock(keyring, &key->index_key); if (link_ret == 0) { link_ret = __key_link_begin(keyring, &key->index_key, &edit); if (link_ret < 0) __key_link_end(keyring, &key->index_key, edit); } } mutex_lock(&key_construction_mutex); /* can't instantiate twice */ if (key->state == KEY_IS_UNINSTANTIATED) { /* mark the key as being negatively instantiated */ atomic_inc(&key->user->nikeys); mark_key_instantiated(key, -error); notify_key(key, NOTIFY_KEY_INSTANTIATED, -error); key_set_expiry(key, ktime_get_real_seconds() + timeout); if (test_and_clear_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) awaken = 1; ret = 0; /* and link it into the destination keyring */ if (keyring && link_ret == 0) __key_link(keyring, key, &edit); /* disable the authorisation key */ if (authkey) key_invalidate(authkey); } mutex_unlock(&key_construction_mutex); if (keyring && link_ret == 0) __key_link_end(keyring, &key->index_key, edit); /* wake up anyone waiting for a key to be constructed */ if (awaken) wake_up_bit(&key->flags, KEY_FLAG_USER_CONSTRUCT); return ret == 0 ? link_ret : ret; } EXPORT_SYMBOL(key_reject_and_link); /** * key_put - Discard a reference to a key. * @key: The key to discard a reference from. * * Discard a reference to a key, and when all the references are gone, we * schedule the cleanup task to come and pull it out of the tree in process * context at some later time. */ void key_put(struct key *key) { if (key) { key_check(key); if (refcount_dec_and_test(&key->usage)) { unsigned long flags; /* deal with the user's key tracking and quota */ if (test_bit(KEY_FLAG_IN_QUOTA, &key->flags)) { spin_lock_irqsave(&key->user->lock, flags); key->user->qnkeys--; key->user->qnbytes -= key->quotalen; spin_unlock_irqrestore(&key->user->lock, flags); } /* Mark key as safe for GC after key->user done. */ clear_bit_unlock(KEY_FLAG_USER_ALIVE, &key->flags); schedule_work(&key_gc_work); } } } EXPORT_SYMBOL(key_put); /* * Find a key by its serial number. */ struct key *key_lookup(key_serial_t id) { struct rb_node *n; struct key *key; spin_lock(&key_serial_lock); /* search the tree for the specified key */ n = key_serial_tree.rb_node; while (n) { key = rb_entry(n, struct key, serial_node); if (id < key->serial) n = n->rb_left; else if (id > key->serial) n = n->rb_right; else goto found; } not_found: key = ERR_PTR(-ENOKEY); goto error; found: /* A key is allowed to be looked up only if someone still owns a * reference to it - otherwise it's awaiting the gc. */ if (!refcount_inc_not_zero(&key->usage)) goto not_found; error: spin_unlock(&key_serial_lock); return key; } EXPORT_SYMBOL(key_lookup); /* * Find and lock the specified key type against removal. * * We return with the sem read-locked if successful. If the type wasn't * available -ENOKEY is returned instead. */ struct key_type *key_type_lookup(const char *type) { struct key_type *ktype; down_read(&key_types_sem); /* look up the key type to see if it's one of the registered kernel * types */ list_for_each_entry(ktype, &key_types_list, link) { if (strcmp(ktype->name, type) == 0) goto found_kernel_type; } up_read(&key_types_sem); ktype = ERR_PTR(-ENOKEY); found_kernel_type: return ktype; } void key_set_timeout(struct key *key, unsigned timeout) { time64_t expiry = TIME64_MAX; /* make the changes with the locks held to prevent races */ down_write(&key->sem); if (timeout > 0) expiry = ktime_get_real_seconds() + timeout; key_set_expiry(key, expiry); up_write(&key->sem); } EXPORT_SYMBOL_GPL(key_set_timeout); /* * Unlock a key type locked by key_type_lookup(). */ void key_type_put(struct key_type *ktype) { up_read(&key_types_sem); } /* * Attempt to update an existing key. * * The key is given to us with an incremented refcount that we need to discard * if we get an error. */ static inline key_ref_t __key_update(key_ref_t key_ref, struct key_preparsed_payload *prep) { struct key *key = key_ref_to_ptr(key_ref); int ret; /* need write permission on the key to update it */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) goto error; ret = -EEXIST; if (!key->type->update) goto error; down_write(&key->sem); ret = key->type->update(key, prep); if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_UPDATED, 0); } up_write(&key->sem); if (ret < 0) goto error; out: return key_ref; error: key_put(key); key_ref = ERR_PTR(ret); goto out; } /* * Create or potentially update a key. The combined logic behind * key_create_or_update() and key_create() */ static key_ref_t __key_create_or_update(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags, bool allow_update) { struct keyring_index_key index_key = { .description = description, }; struct key_preparsed_payload prep; struct assoc_array_edit *edit = NULL; const struct cred *cred = current_cred(); struct key *keyring, *key = NULL; key_ref_t key_ref; int ret; struct key_restriction *restrict_link = NULL; /* look up the key type to see if it's one of the registered kernel * types */ index_key.type = key_type_lookup(type); if (IS_ERR(index_key.type)) { key_ref = ERR_PTR(-ENODEV); goto error; } key_ref = ERR_PTR(-EINVAL); if (!index_key.type->instantiate || (!index_key.description && !index_key.type->preparse)) goto error_put_type; keyring = key_ref_to_ptr(keyring_ref); key_check(keyring); if (!(flags & KEY_ALLOC_BYPASS_RESTRICTION)) restrict_link = keyring->restrict_link; key_ref = ERR_PTR(-ENOTDIR); if (keyring->type != &key_type_keyring) goto error_put_type; memset(&prep, 0, sizeof(prep)); prep.orig_description = description; prep.data = payload; prep.datalen = plen; prep.quotalen = index_key.type->def_datalen; prep.expiry = TIME64_MAX; if (index_key.type->preparse) { ret = index_key.type->preparse(&prep); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_free_prep; } if (!index_key.description) index_key.description = prep.description; key_ref = ERR_PTR(-EINVAL); if (!index_key.description) goto error_free_prep; } index_key.desc_len = strlen(index_key.description); key_set_index_key(&index_key); ret = __key_link_lock(keyring, &index_key); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_free_prep; } ret = __key_link_begin(keyring, &index_key, &edit); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } if (restrict_link && restrict_link->check) { ret = restrict_link->check(keyring, index_key.type, &prep.payload, restrict_link->key); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } } /* if we're going to allocate a new key, we're going to have * to modify the keyring */ ret = key_permission(keyring_ref, KEY_NEED_WRITE); if (ret < 0) { key_ref = ERR_PTR(ret); goto error_link_end; } /* if it's requested and possible to update this type of key, search * for an existing key of the same type and description in the * destination keyring and update that instead if possible */ if (allow_update) { if (index_key.type->update) { key_ref = find_key_to_update(keyring_ref, &index_key); if (key_ref) goto found_matching_key; } } else { key_ref = find_key_to_update(keyring_ref, &index_key); if (key_ref) { key_ref_put(key_ref); key_ref = ERR_PTR(-EEXIST); goto error_link_end; } } /* if the client doesn't provide, decide on the permissions we want */ if (perm == KEY_PERM_UNDEF) { perm = KEY_POS_VIEW | KEY_POS_SEARCH | KEY_POS_LINK | KEY_POS_SETATTR; perm |= KEY_USR_VIEW; if (index_key.type->read) perm |= KEY_POS_READ; if (index_key.type == &key_type_keyring || index_key.type->update) perm |= KEY_POS_WRITE; } /* allocate a new key */ key = key_alloc(index_key.type, index_key.description, cred->fsuid, cred->fsgid, cred, perm, flags, NULL); if (IS_ERR(key)) { key_ref = ERR_CAST(key); goto error_link_end; } /* instantiate it and link it into the target keyring */ ret = __key_instantiate_and_link(key, &prep, keyring, NULL, &edit); if (ret < 0) { key_put(key); key_ref = ERR_PTR(ret); goto error_link_end; } security_key_post_create_or_update(keyring, key, payload, plen, flags, true); key_ref = make_key_ref(key, is_key_possessed(keyring_ref)); error_link_end: __key_link_end(keyring, &index_key, edit); error_free_prep: if (index_key.type->preparse) index_key.type->free_preparse(&prep); error_put_type: key_type_put(index_key.type); error: return key_ref; found_matching_key: /* we found a matching key, so we're going to try to update it * - we can drop the locks first as we have the key pinned */ __key_link_end(keyring, &index_key, edit); key = key_ref_to_ptr(key_ref); if (test_bit(KEY_FLAG_USER_CONSTRUCT, &key->flags)) { ret = wait_for_key_construction(key, true); if (ret < 0) { key_ref_put(key_ref); key_ref = ERR_PTR(ret); goto error_free_prep; } } key_ref = __key_update(key_ref, &prep); if (!IS_ERR(key_ref)) security_key_post_create_or_update(keyring, key, payload, plen, flags, false); goto error_free_prep; } /** * key_create_or_update - Update or create and instantiate a key. * @keyring_ref: A pointer to the destination keyring with possession flag. * @type: The type of key. * @description: The searchable description for the key. * @payload: The data to use to instantiate or update the key. * @plen: The length of @payload. * @perm: The permissions mask for a new key. * @flags: The quota flags for a new key. * * Search the destination keyring for a key of the same description and if one * is found, update it, otherwise create and instantiate a new one and create a * link to it from that keyring. * * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be * concocted. * * Returns a pointer to the new key if successful, -ENODEV if the key type * wasn't available, -ENOTDIR if the keyring wasn't a keyring, -EACCES if the * caller isn't permitted to modify the keyring or the LSM did not permit * creation of the key. * * On success, the possession flag from the keyring ref will be tacked on to * the key ref before it is returned. */ key_ref_t key_create_or_update(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags) { return __key_create_or_update(keyring_ref, type, description, payload, plen, perm, flags, true); } EXPORT_SYMBOL(key_create_or_update); /** * key_create - Create and instantiate a key. * @keyring_ref: A pointer to the destination keyring with possession flag. * @type: The type of key. * @description: The searchable description for the key. * @payload: The data to use to instantiate or update the key. * @plen: The length of @payload. * @perm: The permissions mask for a new key. * @flags: The quota flags for a new key. * * Create and instantiate a new key and link to it from the destination keyring. * * If perm is KEY_PERM_UNDEF then an appropriate key permissions mask will be * concocted. * * Returns a pointer to the new key if successful, -EEXIST if a key with the * same description already exists, -ENODEV if the key type wasn't available, * -ENOTDIR if the keyring wasn't a keyring, -EACCES if the caller isn't * permitted to modify the keyring or the LSM did not permit creation of the * key. * * On success, the possession flag from the keyring ref will be tacked on to * the key ref before it is returned. */ key_ref_t key_create(key_ref_t keyring_ref, const char *type, const char *description, const void *payload, size_t plen, key_perm_t perm, unsigned long flags) { return __key_create_or_update(keyring_ref, type, description, payload, plen, perm, flags, false); } EXPORT_SYMBOL(key_create); /** * key_update - Update a key's contents. * @key_ref: The pointer (plus possession flag) to the key. * @payload: The data to be used to update the key. * @plen: The length of @payload. * * Attempt to update the contents of a key with the given payload data. The * caller must be granted Write permission on the key. Negative keys can be * instantiated by this method. * * Returns 0 on success, -EACCES if not permitted and -EOPNOTSUPP if the key * type does not support updating. The key type may return other errors. */ int key_update(key_ref_t key_ref, const void *payload, size_t plen) { struct key_preparsed_payload prep; struct key *key = key_ref_to_ptr(key_ref); int ret; key_check(key); /* the key must be writable */ ret = key_permission(key_ref, KEY_NEED_WRITE); if (ret < 0) return ret; /* attempt to update it if supported */ if (!key->type->update) return -EOPNOTSUPP; memset(&prep, 0, sizeof(prep)); prep.data = payload; prep.datalen = plen; prep.quotalen = key->type->def_datalen; prep.expiry = TIME64_MAX; if (key->type->preparse) { ret = key->type->preparse(&prep); if (ret < 0) goto error; } down_write(&key->sem); ret = key->type->update(key, &prep); if (ret == 0) { /* Updating a negative key positively instantiates it */ mark_key_instantiated(key, 0); notify_key(key, NOTIFY_KEY_UPDATED, 0); } up_write(&key->sem); error: if (key->type->preparse) key->type->free_preparse(&prep); return ret; } EXPORT_SYMBOL(key_update); /** * key_revoke - Revoke a key. * @key: The key to be revoked. * * Mark a key as being revoked and ask the type to free up its resources. The * revocation timeout is set and the key and all its links will be * automatically garbage collected after key_gc_delay amount of time if they * are not manually dealt with first. */ void key_revoke(struct key *key) { time64_t time; key_check(key); /* make sure no one's trying to change or use the key when we mark it * - we tell lockdep that we might nest because we might be revoking an * authorisation key whilst holding the sem on a key we've just * instantiated */ down_write_nested(&key->sem, 1); if (!test_and_set_bit(KEY_FLAG_REVOKED, &key->flags)) { notify_key(key, NOTIFY_KEY_REVOKED, 0); if (key->type->revoke) key->type->revoke(key); /* set the death time to no more than the expiry time */ time = ktime_get_real_seconds(); if (key->revoked_at == 0 || key->revoked_at > time) { key->revoked_at = time; key_schedule_gc(key->revoked_at + key_gc_delay); } } up_write(&key->sem); } EXPORT_SYMBOL(key_revoke); /** * key_invalidate - Invalidate a key. * @key: The key to be invalidated. * * Mark a key as being invalidated and have it cleaned up immediately. The key * is ignored by all searches and other operations from this point. */ void key_invalidate(struct key *key) { kenter("%d", key_serial(key)); key_check(key); if (!test_bit(KEY_FLAG_INVALIDATED, &key->flags)) { down_write_nested(&key->sem, 1); if (!test_and_set_bit(KEY_FLAG_INVALIDATED, &key->flags)) { notify_key(key, NOTIFY_KEY_INVALIDATED, 0); key_schedule_gc_links(); } up_write(&key->sem); } } EXPORT_SYMBOL(key_invalidate); /** * generic_key_instantiate - Simple instantiation of a key from preparsed data * @key: The key to be instantiated * @prep: The preparsed data to load. * * Instantiate a key from preparsed data. We assume we can just copy the data * in directly and clear the old pointers. * * This can be pointed to directly by the key type instantiate op pointer. */ int generic_key_instantiate(struct key *key, struct key_preparsed_payload *prep) { int ret; pr_devel("==>%s()\n", __func__); ret = key_payload_reserve(key, prep->quotalen); if (ret == 0) { rcu_assign_keypointer(key, prep->payload.data[0]); key->payload.data[1] = prep->payload.data[1]; key->payload.data[2] = prep->payload.data[2]; key->payload.data[3] = prep->payload.data[3]; prep->payload.data[0] = NULL; prep->payload.data[1] = NULL; prep->payload.data[2] = NULL; prep->payload.data[3] = NULL; } pr_devel("<==%s() = %d\n", __func__, ret); return ret; } EXPORT_SYMBOL(generic_key_instantiate); /** * register_key_type - Register a type of key. * @ktype: The new key type. * * Register a new key type. * * Returns 0 on success or -EEXIST if a type of this name already exists. */ int register_key_type(struct key_type *ktype) { struct key_type *p; int ret; memset(&ktype->lock_class, 0, sizeof(ktype->lock_class)); ret = -EEXIST; down_write(&key_types_sem); /* disallow key types with the same name */ list_for_each_entry(p, &key_types_list, link) { if (strcmp(p->name, ktype->name) == 0) goto out; } /* store the type */ list_add(&ktype->link, &key_types_list); pr_notice("Key type %s registered\n", ktype->name); ret = 0; out: up_write(&key_types_sem); return ret; } EXPORT_SYMBOL(register_key_type); /** * unregister_key_type - Unregister a type of key. * @ktype: The key type. * * Unregister a key type and mark all the extant keys of this type as dead. * Those keys of this type are then destroyed to get rid of their payloads and * they and their links will be garbage collected as soon as possible. */ void unregister_key_type(struct key_type *ktype) { down_write(&key_types_sem); list_del_init(&ktype->link); downgrade_write(&key_types_sem); key_gc_keytype(ktype); pr_notice("Key type %s unregistered\n", ktype->name); up_read(&key_types_sem); } EXPORT_SYMBOL(unregister_key_type); /* * Initialise the key management state. */ void __init key_init(void) { /* allocate a slab in which we can store keys */ key_jar = kmem_cache_create("key_jar", sizeof(struct key), 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_NO_MERGE, NULL); /* add the special key types */ list_add_tail(&key_type_keyring.link, &key_types_list); list_add_tail(&key_type_dead.link, &key_types_list); list_add_tail(&key_type_user.link, &key_types_list); list_add_tail(&key_type_logon.link, &key_types_list); /* record the root user tracking */ rb_link_node(&root_key_user.node, NULL, &key_user_tree.rb_node); rb_insert_color(&root_key_user.node, &key_user_tree); } |
| 4 4 4 4 1 1 4 4 4 4 4 4 1 1 2 1 4 1 4 1 1 1 1 1 4 4 4 1 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 4 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 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 | /* * Copyright (c) 2007-2011 Atheros Communications Inc. * Copyright (c) 2011-2012 Qualcomm Atheros, Inc. * * Permission to use, copy, modify, and/or distribute this software for any * purpose with or without fee is hereby granted, provided that the above * copyright notice and this permission notice appear in all copies. * * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR * ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN * ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF * OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE. */ #include <linux/module.h> #include <linux/usb.h> #include "debug.h" #include "core.h" /* constants */ #define TX_URB_COUNT 32 #define RX_URB_COUNT 32 #define ATH6KL_USB_RX_BUFFER_SIZE 4096 /* tx/rx pipes for usb */ enum ATH6KL_USB_PIPE_ID { ATH6KL_USB_PIPE_TX_CTRL = 0, ATH6KL_USB_PIPE_TX_DATA_LP, ATH6KL_USB_PIPE_TX_DATA_MP, ATH6KL_USB_PIPE_TX_DATA_HP, ATH6KL_USB_PIPE_RX_CTRL, ATH6KL_USB_PIPE_RX_DATA, ATH6KL_USB_PIPE_RX_DATA2, ATH6KL_USB_PIPE_RX_INT, ATH6KL_USB_PIPE_MAX }; #define ATH6KL_USB_PIPE_INVALID ATH6KL_USB_PIPE_MAX struct ath6kl_usb_pipe { struct list_head urb_list_head; struct usb_anchor urb_submitted; u32 urb_alloc; u32 urb_cnt; u32 urb_cnt_thresh; unsigned int usb_pipe_handle; u32 flags; u8 ep_address; u8 logical_pipe_num; struct ath6kl_usb *ar_usb; u16 max_packet_size; struct work_struct io_complete_work; struct sk_buff_head io_comp_queue; struct usb_endpoint_descriptor *ep_desc; }; #define ATH6KL_USB_PIPE_FLAG_TX (1 << 0) /* usb device object */ struct ath6kl_usb { /* protects pipe->urb_list_head and pipe->urb_cnt */ spinlock_t cs_lock; struct usb_device *udev; struct usb_interface *interface; struct ath6kl_usb_pipe pipes[ATH6KL_USB_PIPE_MAX]; u8 *diag_cmd_buffer; u8 *diag_resp_buffer; struct ath6kl *ar; struct workqueue_struct *wq; }; /* usb urb object */ struct ath6kl_urb_context { struct list_head link; struct ath6kl_usb_pipe *pipe; struct sk_buff *skb; struct ath6kl *ar; }; /* USB endpoint definitions */ #define ATH6KL_USB_EP_ADDR_APP_CTRL_IN 0x81 #define ATH6KL_USB_EP_ADDR_APP_DATA_IN 0x82 #define ATH6KL_USB_EP_ADDR_APP_DATA2_IN 0x83 #define ATH6KL_USB_EP_ADDR_APP_INT_IN 0x84 #define ATH6KL_USB_EP_ADDR_APP_CTRL_OUT 0x01 #define ATH6KL_USB_EP_ADDR_APP_DATA_LP_OUT 0x02 #define ATH6KL_USB_EP_ADDR_APP_DATA_MP_OUT 0x03 #define ATH6KL_USB_EP_ADDR_APP_DATA_HP_OUT 0x04 /* diagnostic command definitions */ #define ATH6KL_USB_CONTROL_REQ_SEND_BMI_CMD 1 #define ATH6KL_USB_CONTROL_REQ_RECV_BMI_RESP 2 #define ATH6KL_USB_CONTROL_REQ_DIAG_CMD 3 #define ATH6KL_USB_CONTROL_REQ_DIAG_RESP 4 #define ATH6KL_USB_CTRL_DIAG_CC_READ 0 #define ATH6KL_USB_CTRL_DIAG_CC_WRITE 1 struct ath6kl_usb_ctrl_diag_cmd_write { __le32 cmd; __le32 address; __le32 value; __le32 _pad[1]; } __packed; struct ath6kl_usb_ctrl_diag_cmd_read { __le32 cmd; __le32 address; } __packed; struct ath6kl_usb_ctrl_diag_resp_read { __le32 value; } __packed; /* function declarations */ static void ath6kl_usb_recv_complete(struct urb *urb); #define ATH6KL_USB_IS_BULK_EP(attr) (((attr) & 3) == 0x02) #define ATH6KL_USB_IS_INT_EP(attr) (((attr) & 3) == 0x03) #define ATH6KL_USB_IS_ISOC_EP(attr) (((attr) & 3) == 0x01) #define ATH6KL_USB_IS_DIR_IN(addr) ((addr) & 0x80) /* pipe/urb operations */ static struct ath6kl_urb_context * ath6kl_usb_alloc_urb_from_pipe(struct ath6kl_usb_pipe *pipe) { struct ath6kl_urb_context *urb_context = NULL; unsigned long flags; /* bail if this pipe is not initialized */ if (!pipe->ar_usb) return NULL; spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); if (!list_empty(&pipe->urb_list_head)) { urb_context = list_first_entry(&pipe->urb_list_head, struct ath6kl_urb_context, link); list_del(&urb_context->link); pipe->urb_cnt--; } spin_unlock_irqrestore(&pipe->ar_usb->cs_lock, flags); return urb_context; } static void ath6kl_usb_free_urb_to_pipe(struct ath6kl_usb_pipe *pipe, struct ath6kl_urb_context *urb_context) { unsigned long flags; /* bail if this pipe is not initialized */ if (!pipe->ar_usb) return; spin_lock_irqsave(&pipe->ar_usb->cs_lock, flags); pipe->urb_cnt++; list_add(&urb_context->link, &pipe->urb_list_head); spin_unlock_irqrestore(&pipe->ar_usb->cs_lock, flags); } static void ath6kl_usb_cleanup_recv_urb(struct ath6kl_urb_context *urb_context) { dev_kfree_skb(urb_context->skb); urb_context->skb = NULL; ath6kl_usb_free_urb_to_pipe(urb_context->pipe, urb_context); } static inline struct ath6kl_usb *ath6kl_usb_priv(struct ath6kl *ar) { return ar->hif_priv; } /* pipe resource allocation/cleanup */ static int ath6kl_usb_alloc_pipe_resources(struct ath6kl_usb_pipe *pipe, int urb_cnt) { struct ath6kl_urb_context *urb_context; int status = 0, i; INIT_LIST_HEAD(&pipe->urb_list_head); init_usb_anchor(&pipe->urb_submitted); for (i = 0; i < urb_cnt; i++) { urb_context = kzalloc_obj(struct ath6kl_urb_context); if (urb_context == NULL) { status = -ENOMEM; goto fail_alloc_pipe_resources; } urb_context->pipe = pipe; /* * we are only allocate the urb contexts here, the actual URB * is allocated from the kernel as needed to do a transaction */ pipe->urb_alloc++; ath6kl_usb_free_urb_to_pipe(pipe, urb_context); } ath6kl_dbg(ATH6KL_DBG_USB, "ath6kl usb: alloc resources lpipe:%d hpipe:0x%X urbs:%d\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->urb_alloc); fail_alloc_pipe_resources: return status; } static void ath6kl_usb_free_pipe_resources(struct ath6kl_usb_pipe *pipe) { struct ath6kl_urb_context *urb_context; if (pipe->ar_usb == NULL) { /* nothing allocated for this pipe */ return; } ath6kl_dbg(ATH6KL_DBG_USB, "ath6kl usb: free resources lpipe:%d" "hpipe:0x%X urbs:%d avail:%d\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->urb_alloc, pipe->urb_cnt); if (pipe->urb_alloc != pipe->urb_cnt) { ath6kl_dbg(ATH6KL_DBG_USB, "ath6kl usb: urb leak! lpipe:%d" "hpipe:0x%X urbs:%d avail:%d\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->urb_alloc, pipe->urb_cnt); } while (true) { urb_context = ath6kl_usb_alloc_urb_from_pipe(pipe); if (urb_context == NULL) break; kfree(urb_context); } } static void ath6kl_usb_cleanup_pipe_resources(struct ath6kl_usb *ar_usb) { int i; for (i = 0; i < ATH6KL_USB_PIPE_MAX; i++) ath6kl_usb_free_pipe_resources(&ar_usb->pipes[i]); } static u8 ath6kl_usb_get_logical_pipe_num(struct ath6kl_usb *ar_usb, u8 ep_address, int *urb_count) { u8 pipe_num = ATH6KL_USB_PIPE_INVALID; switch (ep_address) { case ATH6KL_USB_EP_ADDR_APP_CTRL_IN: pipe_num = ATH6KL_USB_PIPE_RX_CTRL; *urb_count = RX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_DATA_IN: pipe_num = ATH6KL_USB_PIPE_RX_DATA; *urb_count = RX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_INT_IN: pipe_num = ATH6KL_USB_PIPE_RX_INT; *urb_count = RX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_DATA2_IN: pipe_num = ATH6KL_USB_PIPE_RX_DATA2; *urb_count = RX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_CTRL_OUT: pipe_num = ATH6KL_USB_PIPE_TX_CTRL; *urb_count = TX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_DATA_LP_OUT: pipe_num = ATH6KL_USB_PIPE_TX_DATA_LP; *urb_count = TX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_DATA_MP_OUT: pipe_num = ATH6KL_USB_PIPE_TX_DATA_MP; *urb_count = TX_URB_COUNT; break; case ATH6KL_USB_EP_ADDR_APP_DATA_HP_OUT: pipe_num = ATH6KL_USB_PIPE_TX_DATA_HP; *urb_count = TX_URB_COUNT; break; default: /* note: there may be endpoints not currently used */ break; } return pipe_num; } static int ath6kl_usb_setup_pipe_resources(struct ath6kl_usb *ar_usb) { struct usb_interface *interface = ar_usb->interface; struct usb_host_interface *iface_desc = interface->cur_altsetting; struct usb_endpoint_descriptor *endpoint; struct ath6kl_usb_pipe *pipe; int i, urbcount, status = 0; u8 pipe_num; ath6kl_dbg(ATH6KL_DBG_USB, "setting up USB Pipes using interface\n"); /* walk descriptors and setup pipes */ for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { endpoint = &iface_desc->endpoint[i].desc; if (ATH6KL_USB_IS_BULK_EP(endpoint->bmAttributes)) { ath6kl_dbg(ATH6KL_DBG_USB, "%s Bulk Ep:0x%2.2X maxpktsz:%d\n", ATH6KL_USB_IS_DIR_IN (endpoint->bEndpointAddress) ? "RX" : "TX", endpoint->bEndpointAddress, le16_to_cpu(endpoint->wMaxPacketSize)); } else if (ATH6KL_USB_IS_INT_EP(endpoint->bmAttributes)) { ath6kl_dbg(ATH6KL_DBG_USB, "%s Int Ep:0x%2.2X maxpktsz:%d interval:%d\n", ATH6KL_USB_IS_DIR_IN (endpoint->bEndpointAddress) ? "RX" : "TX", endpoint->bEndpointAddress, le16_to_cpu(endpoint->wMaxPacketSize), endpoint->bInterval); } else if (ATH6KL_USB_IS_ISOC_EP(endpoint->bmAttributes)) { /* TODO for ISO */ ath6kl_dbg(ATH6KL_DBG_USB, "%s ISOC Ep:0x%2.2X maxpktsz:%d interval:%d\n", ATH6KL_USB_IS_DIR_IN (endpoint->bEndpointAddress) ? "RX" : "TX", endpoint->bEndpointAddress, le16_to_cpu(endpoint->wMaxPacketSize), endpoint->bInterval); } /* Ignore broken descriptors. */ if (usb_endpoint_maxp(endpoint) == 0) continue; urbcount = 0; pipe_num = ath6kl_usb_get_logical_pipe_num(ar_usb, endpoint->bEndpointAddress, &urbcount); if (pipe_num == ATH6KL_USB_PIPE_INVALID) continue; pipe = &ar_usb->pipes[pipe_num]; if (pipe->ar_usb != NULL) { /* hmmm..pipe was already setup */ continue; } pipe->ar_usb = ar_usb; pipe->logical_pipe_num = pipe_num; pipe->ep_address = endpoint->bEndpointAddress; pipe->max_packet_size = le16_to_cpu(endpoint->wMaxPacketSize); if (ATH6KL_USB_IS_BULK_EP(endpoint->bmAttributes)) { if (ATH6KL_USB_IS_DIR_IN(pipe->ep_address)) { pipe->usb_pipe_handle = usb_rcvbulkpipe(ar_usb->udev, pipe->ep_address); } else { pipe->usb_pipe_handle = usb_sndbulkpipe(ar_usb->udev, pipe->ep_address); } } else if (ATH6KL_USB_IS_INT_EP(endpoint->bmAttributes)) { if (ATH6KL_USB_IS_DIR_IN(pipe->ep_address)) { pipe->usb_pipe_handle = usb_rcvintpipe(ar_usb->udev, pipe->ep_address); } else { pipe->usb_pipe_handle = usb_sndintpipe(ar_usb->udev, pipe->ep_address); } } else if (ATH6KL_USB_IS_ISOC_EP(endpoint->bmAttributes)) { /* TODO for ISO */ if (ATH6KL_USB_IS_DIR_IN(pipe->ep_address)) { pipe->usb_pipe_handle = usb_rcvisocpipe(ar_usb->udev, pipe->ep_address); } else { pipe->usb_pipe_handle = usb_sndisocpipe(ar_usb->udev, pipe->ep_address); } } pipe->ep_desc = endpoint; if (!ATH6KL_USB_IS_DIR_IN(pipe->ep_address)) pipe->flags |= ATH6KL_USB_PIPE_FLAG_TX; status = ath6kl_usb_alloc_pipe_resources(pipe, urbcount); if (status != 0) break; } return status; } /* pipe operations */ static void ath6kl_usb_post_recv_transfers(struct ath6kl_usb_pipe *recv_pipe, int buffer_length) { struct ath6kl_urb_context *urb_context; struct urb *urb; int usb_status; while (true) { urb_context = ath6kl_usb_alloc_urb_from_pipe(recv_pipe); if (urb_context == NULL) break; urb_context->skb = dev_alloc_skb(buffer_length); if (urb_context->skb == NULL) goto err_cleanup_urb; urb = usb_alloc_urb(0, GFP_ATOMIC); if (urb == NULL) goto err_cleanup_urb; usb_fill_bulk_urb(urb, recv_pipe->ar_usb->udev, recv_pipe->usb_pipe_handle, urb_context->skb->data, buffer_length, ath6kl_usb_recv_complete, urb_context); ath6kl_dbg(ATH6KL_DBG_USB_BULK, "ath6kl usb: bulk recv submit:%d, 0x%X (ep:0x%2.2X), %d bytes buf:0x%p\n", recv_pipe->logical_pipe_num, recv_pipe->usb_pipe_handle, recv_pipe->ep_address, buffer_length, urb_context->skb); usb_anchor_urb(urb, &recv_pipe->urb_submitted); usb_status = usb_submit_urb(urb, GFP_ATOMIC); if (usb_status) { ath6kl_dbg(ATH6KL_DBG_USB_BULK, "ath6kl usb : usb bulk recv failed %d\n", usb_status); usb_unanchor_urb(urb); usb_free_urb(urb); goto err_cleanup_urb; } usb_free_urb(urb); } return; err_cleanup_urb: ath6kl_usb_cleanup_recv_urb(urb_context); return; } static void ath6kl_usb_flush_all(struct ath6kl_usb *ar_usb) { int i; for (i = 0; i < ATH6KL_USB_PIPE_MAX; i++) { if (ar_usb->pipes[i].ar_usb != NULL) usb_kill_anchored_urbs(&ar_usb->pipes[i].urb_submitted); } /* * Flushing any pending I/O may schedule work this call will block * until all scheduled work runs to completion. */ flush_workqueue(ar_usb->wq); } static void ath6kl_usb_start_recv_pipes(struct ath6kl_usb *ar_usb) { /* * note: control pipe is no longer used * ar_usb->pipes[ATH6KL_USB_PIPE_RX_CTRL].urb_cnt_thresh = * ar_usb->pipes[ATH6KL_USB_PIPE_RX_CTRL].urb_alloc/2; * ath6kl_usb_post_recv_transfers(&ar_usb-> * pipes[ATH6KL_USB_PIPE_RX_CTRL], * ATH6KL_USB_RX_BUFFER_SIZE); */ ar_usb->pipes[ATH6KL_USB_PIPE_RX_DATA].urb_cnt_thresh = 1; ath6kl_usb_post_recv_transfers(&ar_usb->pipes[ATH6KL_USB_PIPE_RX_DATA], ATH6KL_USB_RX_BUFFER_SIZE); } /* hif usb rx/tx completion functions */ static void ath6kl_usb_recv_complete(struct urb *urb) { struct ath6kl_urb_context *urb_context = urb->context; struct ath6kl_usb_pipe *pipe = urb_context->pipe; struct sk_buff *skb = NULL; int status = 0; ath6kl_dbg(ATH6KL_DBG_USB_BULK, "%s: recv pipe: %d, stat:%d, len:%d urb:0x%p\n", __func__, pipe->logical_pipe_num, urb->status, urb->actual_length, urb); if (urb->status != 0) { status = -EIO; switch (urb->status) { case -ECONNRESET: case -ENOENT: case -ESHUTDOWN: /* * no need to spew these errors when device * removed or urb killed due to driver shutdown */ status = -ECANCELED; break; default: ath6kl_dbg(ATH6KL_DBG_USB_BULK, "%s recv pipe: %d (ep:0x%2.2X), failed:%d\n", __func__, pipe->logical_pipe_num, pipe->ep_address, urb->status); break; } goto cleanup_recv_urb; } if (urb->actual_length == 0) goto cleanup_recv_urb; skb = urb_context->skb; /* we are going to pass it up */ urb_context->skb = NULL; skb_put(skb, urb->actual_length); /* note: queue implements a lock */ skb_queue_tail(&pipe->io_comp_queue, skb); queue_work(pipe->ar_usb->wq, &pipe->io_complete_work); cleanup_recv_urb: ath6kl_usb_cleanup_recv_urb(urb_context); if (status == 0 && pipe->urb_cnt >= pipe->urb_cnt_thresh) { /* our free urbs are piling up, post more transfers */ ath6kl_usb_post_recv_transfers(pipe, ATH6KL_USB_RX_BUFFER_SIZE); } } static void ath6kl_usb_usb_transmit_complete(struct urb *urb) { struct ath6kl_urb_context *urb_context = urb->context; struct ath6kl_usb_pipe *pipe = urb_context->pipe; struct sk_buff *skb; ath6kl_dbg(ATH6KL_DBG_USB_BULK, "%s: pipe: %d, stat:%d, len:%d\n", __func__, pipe->logical_pipe_num, urb->status, urb->actual_length); if (urb->status != 0) { ath6kl_dbg(ATH6KL_DBG_USB_BULK, "%s: pipe: %d, failed:%d\n", __func__, pipe->logical_pipe_num, urb->status); } skb = urb_context->skb; urb_context->skb = NULL; ath6kl_usb_free_urb_to_pipe(urb_context->pipe, urb_context); /* note: queue implements a lock */ skb_queue_tail(&pipe->io_comp_queue, skb); queue_work(pipe->ar_usb->wq, &pipe->io_complete_work); } static void ath6kl_usb_io_comp_work(struct work_struct *work) { struct ath6kl_usb_pipe *pipe = container_of(work, struct ath6kl_usb_pipe, io_complete_work); struct ath6kl_usb *ar_usb; struct sk_buff *skb; ar_usb = pipe->ar_usb; while ((skb = skb_dequeue(&pipe->io_comp_queue))) { if (pipe->flags & ATH6KL_USB_PIPE_FLAG_TX) { ath6kl_dbg(ATH6KL_DBG_USB_BULK, "ath6kl usb xmit callback buf:0x%p\n", skb); ath6kl_core_tx_complete(ar_usb->ar, skb); } else { ath6kl_dbg(ATH6KL_DBG_USB_BULK, "ath6kl usb recv callback buf:0x%p\n", skb); ath6kl_core_rx_complete(ar_usb->ar, skb, pipe->logical_pipe_num); } } } #define ATH6KL_USB_MAX_DIAG_CMD (sizeof(struct ath6kl_usb_ctrl_diag_cmd_write)) #define ATH6KL_USB_MAX_DIAG_RESP (sizeof(struct ath6kl_usb_ctrl_diag_resp_read)) static void ath6kl_usb_destroy(struct ath6kl_usb *ar_usb) { ath6kl_usb_flush_all(ar_usb); ath6kl_usb_cleanup_pipe_resources(ar_usb); usb_set_intfdata(ar_usb->interface, NULL); kfree(ar_usb->diag_cmd_buffer); kfree(ar_usb->diag_resp_buffer); destroy_workqueue(ar_usb->wq); kfree(ar_usb); } static struct ath6kl_usb *ath6kl_usb_create(struct usb_interface *interface) { struct usb_device *dev = interface_to_usbdev(interface); struct ath6kl_usb *ar_usb; struct ath6kl_usb_pipe *pipe; int status = 0; int i; /* ath6kl_usb_destroy() needs ar_usb != NULL && ar_usb->wq != NULL. */ ar_usb = kzalloc_obj(struct ath6kl_usb); if (ar_usb == NULL) return NULL; ar_usb->wq = alloc_workqueue("ath6kl_wq", WQ_PERCPU, 0); if (!ar_usb->wq) { kfree(ar_usb); return NULL; } usb_set_intfdata(interface, ar_usb); spin_lock_init(&(ar_usb->cs_lock)); ar_usb->udev = dev; ar_usb->interface = interface; for (i = 0; i < ATH6KL_USB_PIPE_MAX; i++) { pipe = &ar_usb->pipes[i]; INIT_WORK(&pipe->io_complete_work, ath6kl_usb_io_comp_work); skb_queue_head_init(&pipe->io_comp_queue); } ar_usb->diag_cmd_buffer = kzalloc(ATH6KL_USB_MAX_DIAG_CMD, GFP_KERNEL); if (ar_usb->diag_cmd_buffer == NULL) { status = -ENOMEM; goto fail_ath6kl_usb_create; } ar_usb->diag_resp_buffer = kzalloc(ATH6KL_USB_MAX_DIAG_RESP, GFP_KERNEL); if (ar_usb->diag_resp_buffer == NULL) { status = -ENOMEM; goto fail_ath6kl_usb_create; } status = ath6kl_usb_setup_pipe_resources(ar_usb); fail_ath6kl_usb_create: if (status != 0) { ath6kl_usb_destroy(ar_usb); ar_usb = NULL; } return ar_usb; } static void ath6kl_usb_device_detached(struct usb_interface *interface) { struct ath6kl_usb *ar_usb; ar_usb = usb_get_intfdata(interface); if (ar_usb == NULL) return; ath6kl_stop_txrx(ar_usb->ar); /* Delay to wait for the target to reboot */ mdelay(20); ath6kl_core_cleanup(ar_usb->ar); ath6kl_usb_destroy(ar_usb); } /* exported hif usb APIs for htc pipe */ static void hif_start(struct ath6kl *ar) { struct ath6kl_usb *device = ath6kl_usb_priv(ar); int i; ath6kl_usb_start_recv_pipes(device); /* set the TX resource avail threshold for each TX pipe */ for (i = ATH6KL_USB_PIPE_TX_CTRL; i <= ATH6KL_USB_PIPE_TX_DATA_HP; i++) { device->pipes[i].urb_cnt_thresh = device->pipes[i].urb_alloc / 2; } } static int ath6kl_usb_send(struct ath6kl *ar, u8 PipeID, struct sk_buff *hdr_skb, struct sk_buff *skb) { struct ath6kl_usb *device = ath6kl_usb_priv(ar); struct ath6kl_usb_pipe *pipe = &device->pipes[PipeID]; struct ath6kl_urb_context *urb_context; int usb_status, status = 0; struct urb *urb; u8 *data; u32 len; ath6kl_dbg(ATH6KL_DBG_USB_BULK, "+%s pipe : %d, buf:0x%p\n", __func__, PipeID, skb); urb_context = ath6kl_usb_alloc_urb_from_pipe(pipe); if (urb_context == NULL) { /* * TODO: it is possible to run out of urbs if * 2 endpoints map to the same pipe ID */ ath6kl_dbg(ATH6KL_DBG_USB_BULK, "%s pipe:%d no urbs left. URB Cnt : %d\n", __func__, PipeID, pipe->urb_cnt); status = -ENOMEM; goto fail_hif_send; } urb_context->skb = skb; data = skb->data; len = skb->len; urb = usb_alloc_urb(0, GFP_ATOMIC); if (urb == NULL) { status = -ENOMEM; ath6kl_usb_free_urb_to_pipe(urb_context->pipe, urb_context); goto fail_hif_send; } usb_fill_bulk_urb(urb, device->udev, pipe->usb_pipe_handle, data, len, ath6kl_usb_usb_transmit_complete, urb_context); if ((len % pipe->max_packet_size) == 0) { /* hit a max packet boundary on this pipe */ urb->transfer_flags |= URB_ZERO_PACKET; } ath6kl_dbg(ATH6KL_DBG_USB_BULK, "athusb bulk send submit:%d, 0x%X (ep:0x%2.2X), %d bytes\n", pipe->logical_pipe_num, pipe->usb_pipe_handle, pipe->ep_address, len); usb_anchor_urb(urb, &pipe->urb_submitted); usb_status = usb_submit_urb(urb, GFP_ATOMIC); if (usb_status) { ath6kl_dbg(ATH6KL_DBG_USB_BULK, "ath6kl usb : usb bulk transmit failed %d\n", usb_status); usb_unanchor_urb(urb); ath6kl_usb_free_urb_to_pipe(urb_context->pipe, urb_context); status = -EINVAL; } usb_free_urb(urb); fail_hif_send: return status; } static void hif_stop(struct ath6kl *ar) { struct ath6kl_usb *device = ath6kl_usb_priv(ar); ath6kl_usb_flush_all(device); } static void ath6kl_usb_get_default_pipe(struct ath6kl *ar, u8 *ul_pipe, u8 *dl_pipe) { *ul_pipe = ATH6KL_USB_PIPE_TX_CTRL; *dl_pipe = ATH6KL_USB_PIPE_RX_CTRL; } static int ath6kl_usb_map_service_pipe(struct ath6kl *ar, u16 svc_id, u8 *ul_pipe, u8 *dl_pipe) { int status = 0; switch (svc_id) { case HTC_CTRL_RSVD_SVC: case WMI_CONTROL_SVC: *ul_pipe = ATH6KL_USB_PIPE_TX_CTRL; /* due to large control packets, shift to data pipe */ *dl_pipe = ATH6KL_USB_PIPE_RX_DATA; break; case WMI_DATA_BE_SVC: case WMI_DATA_BK_SVC: *ul_pipe = ATH6KL_USB_PIPE_TX_DATA_LP; /* * Disable rxdata2 directly, it will be enabled * if FW enable rxdata2 */ *dl_pipe = ATH6KL_USB_PIPE_RX_DATA; break; case WMI_DATA_VI_SVC: if (test_bit(ATH6KL_FW_CAPABILITY_MAP_LP_ENDPOINT, ar->fw_capabilities)) *ul_pipe = ATH6KL_USB_PIPE_TX_DATA_LP; else *ul_pipe = ATH6KL_USB_PIPE_TX_DATA_MP; /* * Disable rxdata2 directly, it will be enabled * if FW enable rxdata2 */ *dl_pipe = ATH6KL_USB_PIPE_RX_DATA; break; case WMI_DATA_VO_SVC: if (test_bit(ATH6KL_FW_CAPABILITY_MAP_LP_ENDPOINT, ar->fw_capabilities)) *ul_pipe = ATH6KL_USB_PIPE_TX_DATA_LP; else *ul_pipe = ATH6KL_USB_PIPE_TX_DATA_MP; /* * Disable rxdata2 directly, it will be enabled * if FW enable rxdata2 */ *dl_pipe = ATH6KL_USB_PIPE_RX_DATA; break; default: status = -EPERM; break; } return status; } static u16 ath6kl_usb_get_free_queue_number(struct ath6kl *ar, u8 pipe_id) { struct ath6kl_usb *device = ath6kl_usb_priv(ar); return device->pipes[pipe_id].urb_cnt; } static void hif_detach_htc(struct ath6kl *ar) { struct ath6kl_usb *device = ath6kl_usb_priv(ar); ath6kl_usb_flush_all(device); } static int ath6kl_usb_submit_ctrl_out(struct ath6kl_usb *ar_usb, u8 req, u16 value, u16 index, void *data, u32 size) { u8 *buf = NULL; int ret; if (size > 0) { buf = kmemdup(data, size, GFP_KERNEL); if (buf == NULL) return -ENOMEM; } /* note: if successful returns number of bytes transferred */ ret = usb_control_msg(ar_usb->udev, usb_sndctrlpipe(ar_usb->udev, 0), req, USB_DIR_OUT | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, buf, size, 1000); if (ret < 0) { ath6kl_warn("Failed to submit usb control message: %d\n", ret); kfree(buf); return ret; } kfree(buf); return 0; } static int ath6kl_usb_submit_ctrl_in(struct ath6kl_usb *ar_usb, u8 req, u16 value, u16 index, void *data, u32 size) { u8 *buf = NULL; int ret; if (size > 0) { buf = kmalloc(size, GFP_KERNEL); if (buf == NULL) return -ENOMEM; } /* note: if successful returns number of bytes transferred */ ret = usb_control_msg(ar_usb->udev, usb_rcvctrlpipe(ar_usb->udev, 0), req, USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_DEVICE, value, index, buf, size, 2000); if (ret < 0) { ath6kl_warn("Failed to read usb control message: %d\n", ret); kfree(buf); return ret; } memcpy((u8 *) data, buf, size); kfree(buf); return 0; } static int ath6kl_usb_ctrl_msg_exchange(struct ath6kl_usb *ar_usb, u8 req_val, u8 *req_buf, u32 req_len, u8 resp_val, u8 *resp_buf, u32 *resp_len) { int ret; /* send command */ ret = ath6kl_usb_submit_ctrl_out(ar_usb, req_val, 0, 0, req_buf, req_len); if (ret != 0) return ret; if (resp_buf == NULL) { /* no expected response */ return ret; } /* get response */ ret = ath6kl_usb_submit_ctrl_in(ar_usb, resp_val, 0, 0, resp_buf, *resp_len); return ret; } static int ath6kl_usb_diag_read32(struct ath6kl *ar, u32 address, u32 *data) { struct ath6kl_usb *ar_usb = ar->hif_priv; struct ath6kl_usb_ctrl_diag_resp_read *resp; struct ath6kl_usb_ctrl_diag_cmd_read *cmd; u32 resp_len; int ret; cmd = (struct ath6kl_usb_ctrl_diag_cmd_read *) ar_usb->diag_cmd_buffer; memset(cmd, 0, sizeof(*cmd)); cmd->cmd = ATH6KL_USB_CTRL_DIAG_CC_READ; cmd->address = cpu_to_le32(address); resp_len = sizeof(*resp); ret = ath6kl_usb_ctrl_msg_exchange(ar_usb, ATH6KL_USB_CONTROL_REQ_DIAG_CMD, (u8 *) cmd, sizeof(struct ath6kl_usb_ctrl_diag_cmd_write), ATH6KL_USB_CONTROL_REQ_DIAG_RESP, ar_usb->diag_resp_buffer, &resp_len); if (ret) { ath6kl_warn("diag read32 failed: %d\n", ret); return ret; } resp = (struct ath6kl_usb_ctrl_diag_resp_read *) ar_usb->diag_resp_buffer; *data = le32_to_cpu(resp->value); return ret; } static int ath6kl_usb_diag_write32(struct ath6kl *ar, u32 address, __le32 data) { struct ath6kl_usb *ar_usb = ar->hif_priv; struct ath6kl_usb_ctrl_diag_cmd_write *cmd; int ret; cmd = (struct ath6kl_usb_ctrl_diag_cmd_write *) ar_usb->diag_cmd_buffer; memset(cmd, 0, sizeof(struct ath6kl_usb_ctrl_diag_cmd_write)); cmd->cmd = cpu_to_le32(ATH6KL_USB_CTRL_DIAG_CC_WRITE); cmd->address = cpu_to_le32(address); cmd->value = data; ret = ath6kl_usb_ctrl_msg_exchange(ar_usb, ATH6KL_USB_CONTROL_REQ_DIAG_CMD, (u8 *) cmd, sizeof(*cmd), 0, NULL, NULL); if (ret) { ath6kl_warn("diag_write32 failed: %d\n", ret); return ret; } return 0; } static int ath6kl_usb_bmi_read(struct ath6kl *ar, u8 *buf, u32 len) { struct ath6kl_usb *ar_usb = ar->hif_priv; int ret; /* get response */ ret = ath6kl_usb_submit_ctrl_in(ar_usb, ATH6KL_USB_CONTROL_REQ_RECV_BMI_RESP, 0, 0, buf, len); if (ret) { ath6kl_err("Unable to read the bmi data from the device: %d\n", ret); return ret; } return 0; } static int ath6kl_usb_bmi_write(struct ath6kl *ar, u8 *buf, u32 len) { struct ath6kl_usb *ar_usb = ar->hif_priv; int ret; /* send command */ ret = ath6kl_usb_submit_ctrl_out(ar_usb, ATH6KL_USB_CONTROL_REQ_SEND_BMI_CMD, 0, 0, buf, len); if (ret) { ath6kl_err("unable to send the bmi data to the device: %d\n", ret); return ret; } return 0; } static int ath6kl_usb_power_on(struct ath6kl *ar) { hif_start(ar); return 0; } static int ath6kl_usb_power_off(struct ath6kl *ar) { hif_detach_htc(ar); return 0; } static void ath6kl_usb_stop(struct ath6kl *ar) { hif_stop(ar); } static void ath6kl_usb_cleanup_scatter(struct ath6kl *ar) { /* * USB doesn't support it. Just return. */ return; } static int ath6kl_usb_suspend(struct ath6kl *ar, struct cfg80211_wowlan *wow) { /* * cfg80211 suspend/WOW currently not supported for USB. */ return 0; } static int ath6kl_usb_resume(struct ath6kl *ar) { /* * cfg80211 resume currently not supported for USB. */ return 0; } static const struct ath6kl_hif_ops ath6kl_usb_ops = { .diag_read32 = ath6kl_usb_diag_read32, .diag_write32 = ath6kl_usb_diag_write32, .bmi_read = ath6kl_usb_bmi_read, .bmi_write = ath6kl_usb_bmi_write, .power_on = ath6kl_usb_power_on, .power_off = ath6kl_usb_power_off, .stop = ath6kl_usb_stop, .pipe_send = ath6kl_usb_send, .pipe_get_default = ath6kl_usb_get_default_pipe, .pipe_map_service = ath6kl_usb_map_service_pipe, .pipe_get_free_queue_number = ath6kl_usb_get_free_queue_number, .cleanup_scatter = ath6kl_usb_cleanup_scatter, .suspend = ath6kl_usb_suspend, .resume = ath6kl_usb_resume, }; /* ath6kl usb driver registered functions */ static int ath6kl_usb_probe(struct usb_interface *interface, const struct usb_device_id *id) { struct usb_device *dev = interface_to_usbdev(interface); struct ath6kl *ar; struct ath6kl_usb *ar_usb = NULL; int vendor_id, product_id; int ret = 0; vendor_id = le16_to_cpu(dev->descriptor.idVendor); product_id = le16_to_cpu(dev->descriptor.idProduct); ath6kl_dbg(ATH6KL_DBG_USB, "vendor_id = %04x\n", vendor_id); ath6kl_dbg(ATH6KL_DBG_USB, "product_id = %04x\n", product_id); if (interface->cur_altsetting) ath6kl_dbg(ATH6KL_DBG_USB, "USB Interface %d\n", interface->cur_altsetting->desc.bInterfaceNumber); if (dev->speed == USB_SPEED_HIGH) ath6kl_dbg(ATH6KL_DBG_USB, "USB 2.0 Host\n"); else ath6kl_dbg(ATH6KL_DBG_USB, "USB 1.1 Host\n"); ar_usb = ath6kl_usb_create(interface); if (ar_usb == NULL) return -ENOMEM; ar = ath6kl_core_create(&ar_usb->udev->dev); if (ar == NULL) { ath6kl_err("Failed to alloc ath6kl core\n"); ret = -ENOMEM; goto err_usb_destroy; } ar->hif_priv = ar_usb; ar->hif_type = ATH6KL_HIF_TYPE_USB; ar->hif_ops = &ath6kl_usb_ops; ar->mbox_info.block_size = 16; ar->bmi.max_data_size = 252; ar_usb->ar = ar; ret = ath6kl_core_init(ar, ATH6KL_HTC_TYPE_PIPE); if (ret) { ath6kl_err("Failed to init ath6kl core: %d\n", ret); goto err_core_free; } return ret; err_core_free: ath6kl_core_destroy(ar); err_usb_destroy: ath6kl_usb_destroy(ar_usb); return ret; } static void ath6kl_usb_disconnect(struct usb_interface *interface) { ath6kl_usb_device_detached(interface); } #ifdef CONFIG_PM static int ath6kl_usb_pm_suspend(struct usb_interface *interface, pm_message_t message) { struct ath6kl_usb *device; device = usb_get_intfdata(interface); ath6kl_usb_flush_all(device); return 0; } static int ath6kl_usb_pm_resume(struct usb_interface *interface) { struct ath6kl_usb *device; device = usb_get_intfdata(interface); ath6kl_usb_post_recv_transfers(&device->pipes[ATH6KL_USB_PIPE_RX_DATA], ATH6KL_USB_RX_BUFFER_SIZE); ath6kl_usb_post_recv_transfers(&device->pipes[ATH6KL_USB_PIPE_RX_DATA2], ATH6KL_USB_RX_BUFFER_SIZE); return 0; } #else #define ath6kl_usb_pm_suspend NULL #define ath6kl_usb_pm_resume NULL #endif /* table of devices that work with this driver */ static const struct usb_device_id ath6kl_usb_ids[] = { {USB_DEVICE(0x0cf3, 0x9375)}, {USB_DEVICE(0x0cf3, 0x9374)}, {USB_DEVICE(0x04da, 0x390d)}, { /* Terminating entry */ }, }; MODULE_DEVICE_TABLE(usb, ath6kl_usb_ids); static struct usb_driver ath6kl_usb_driver = { .name = "ath6kl_usb", .probe = ath6kl_usb_probe, .suspend = ath6kl_usb_pm_suspend, .resume = ath6kl_usb_pm_resume, .disconnect = ath6kl_usb_disconnect, .id_table = ath6kl_usb_ids, .supports_autosuspend = true, .disable_hub_initiated_lpm = 1, }; module_usb_driver(ath6kl_usb_driver); MODULE_AUTHOR("Atheros Communications, Inc."); MODULE_DESCRIPTION("Driver support for Atheros AR600x USB devices"); MODULE_LICENSE("Dual BSD/GPL"); MODULE_FIRMWARE(AR6004_HW_1_0_FIRMWARE_FILE); MODULE_FIRMWARE(AR6004_HW_1_0_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_0_DEFAULT_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_1_FIRMWARE_FILE); MODULE_FIRMWARE(AR6004_HW_1_1_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_1_DEFAULT_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_2_FIRMWARE_FILE); MODULE_FIRMWARE(AR6004_HW_1_2_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_2_DEFAULT_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_3_FW_DIR "/" AR6004_HW_1_3_FIRMWARE_FILE); MODULE_FIRMWARE(AR6004_HW_1_3_BOARD_DATA_FILE); MODULE_FIRMWARE(AR6004_HW_1_3_DEFAULT_BOARD_DATA_FILE); |
| 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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PATH_H #define _LINUX_PATH_H struct dentry; struct vfsmount; struct path { struct vfsmount *mnt; struct dentry *dentry; } __randomize_layout; extern void path_get(const struct path *); extern void path_put(const struct path *); static inline int path_equal(const struct path *path1, const struct path *path2) { return path1->mnt == path2->mnt && path1->dentry == path2->dentry; } /* * Cleanup macro for use with __free(path_put). Avoids dereference and * copying @path unlike DEFINE_FREE(). path_put() will handle the empty * path correctly just ensure @path is initialized: * * struct path path __free(path_put) = {}; */ #define __free_path_put path_put #endif /* _LINUX_PATH_H */ |
| 14 135 192 113 105 117 9 26 5 115 25 11 128 92 13 13 13 13 6 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 1532 1533 1534 1535 1536 1537 1538 1539 1540 1541 1542 1543 1544 1545 1546 1547 1548 1549 1550 1551 1552 1553 1554 1555 1556 1557 1558 1559 1560 1561 1562 1563 1564 1565 1566 1567 1568 1569 1570 1571 1572 1573 1574 1575 1576 1577 1578 1579 1580 1581 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_PAGEMAP_H #define _LINUX_PAGEMAP_H /* * Copyright 1995 Linus Torvalds */ #include <linux/mm.h> #include <linux/fs.h> #include <linux/list.h> #include <linux/highmem.h> #include <linux/compiler.h> #include <linux/uaccess.h> #include <linux/gfp.h> #include <linux/bitops.h> #include <linux/hardirq.h> /* for in_interrupt() */ #include <linux/hugetlb_inline.h> struct folio_batch; unsigned long invalidate_mapping_pages(struct address_space *mapping, pgoff_t start, pgoff_t end); static inline void invalidate_remote_inode(struct inode *inode) { if (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) invalidate_mapping_pages(inode->i_mapping, 0, -1); } int invalidate_inode_pages2(struct address_space *mapping); int invalidate_inode_pages2_range(struct address_space *mapping, pgoff_t start, pgoff_t end); int kiocb_invalidate_pages(struct kiocb *iocb, size_t count); void kiocb_invalidate_post_direct_write(struct kiocb *iocb, size_t count); int filemap_invalidate_pages(struct address_space *mapping, loff_t pos, loff_t end, bool nowait); int write_inode_now(struct inode *, int sync); int filemap_fdatawrite(struct address_space *); int filemap_flush(struct address_space *); int filemap_flush_nr(struct address_space *mapping, long *nr_to_write); int filemap_fdatawait_keep_errors(struct address_space *mapping); int filemap_fdatawait_range(struct address_space *, loff_t lstart, loff_t lend); int filemap_fdatawait_range_keep_errors(struct address_space *mapping, loff_t start_byte, loff_t end_byte); int filemap_invalidate_inode(struct inode *inode, bool flush, loff_t start, loff_t end); static inline int filemap_fdatawait(struct address_space *mapping) { return filemap_fdatawait_range(mapping, 0, LLONG_MAX); } bool filemap_range_has_page(struct address_space *, loff_t lstart, loff_t lend); int filemap_write_and_wait_range(struct address_space *mapping, loff_t lstart, loff_t lend); int filemap_fdatawrite_range(struct address_space *mapping, loff_t start, loff_t end); int filemap_check_errors(struct address_space *mapping); void __filemap_set_wb_err(struct address_space *mapping, int err); int kiocb_write_and_wait(struct kiocb *iocb, size_t count); static inline int filemap_write_and_wait(struct address_space *mapping) { return filemap_write_and_wait_range(mapping, 0, LLONG_MAX); } /** * filemap_set_wb_err - set a writeback error on an address_space * @mapping: mapping in which to set writeback error * @err: error to be set in mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * filemap_set_wb_err to record the error in the mapping so that it will be * automatically reported whenever fsync is called on the file. */ static inline void filemap_set_wb_err(struct address_space *mapping, int err) { /* Fastpath for common case of no error */ if (unlikely(err)) __filemap_set_wb_err(mapping, err); } /** * filemap_check_wb_err - has an error occurred since the mark was sampled? * @mapping: mapping to check for writeback errors * @since: previously-sampled errseq_t * * Grab the errseq_t value from the mapping, and see if it has changed "since" * the given value was sampled. * * If it has then report the latest error set, otherwise return 0. */ static inline int filemap_check_wb_err(struct address_space *mapping, errseq_t since) { return errseq_check(&mapping->wb_err, since); } /** * filemap_sample_wb_err - sample the current errseq_t to test for later errors * @mapping: mapping to be sampled * * Writeback errors are always reported relative to a particular sample point * in the past. This function provides those sample points. */ static inline errseq_t filemap_sample_wb_err(struct address_space *mapping) { return errseq_sample(&mapping->wb_err); } /** * file_sample_sb_err - sample the current errseq_t to test for later errors * @file: file pointer to be sampled * * Grab the most current superblock-level errseq_t value for the given * struct file. */ static inline errseq_t file_sample_sb_err(struct file *file) { return errseq_sample(&file->f_path.dentry->d_sb->s_wb_err); } /* * Flush file data before changing attributes. Caller must hold any locks * required to prevent further writes to this file until we're done setting * flags. */ static inline int inode_drain_writes(struct inode *inode) { inode_dio_wait(inode); return filemap_write_and_wait(inode->i_mapping); } static inline bool mapping_empty(const struct address_space *mapping) { return xa_empty(&mapping->i_pages); } /* * mapping_shrinkable - test if page cache state allows inode reclaim * @mapping: the page cache mapping * * This checks the mapping's cache state for the pupose of inode * reclaim and LRU management. * * The caller is expected to hold the i_lock, but is not required to * hold the i_pages lock, which usually protects cache state. That's * because the i_lock and the list_lru lock that protect the inode and * its LRU state don't nest inside the irq-safe i_pages lock. * * Cache deletions are performed under the i_lock, which ensures that * when an inode goes empty, it will reliably get queued on the LRU. * * Cache additions do not acquire the i_lock and may race with this * check, in which case we'll report the inode as shrinkable when it * has cache pages. This is okay: the shrinker also checks the * refcount and the referenced bit, which will be elevated or set in * the process of adding new cache pages to an inode. */ static inline bool mapping_shrinkable(const struct address_space *mapping) { void *head; /* * On highmem systems, there could be lowmem pressure from the * inodes before there is highmem pressure from the page * cache. Make inodes shrinkable regardless of cache state. */ if (IS_ENABLED(CONFIG_HIGHMEM)) return true; /* Cache completely empty? Shrink away. */ head = rcu_access_pointer(mapping->i_pages.xa_head); if (!head) return true; /* * The xarray stores single offset-0 entries directly in the * head pointer, which allows non-resident page cache entries * to escape the shadow shrinker's list of xarray nodes. The * inode shrinker needs to pick them up under memory pressure. */ if (!xa_is_node(head) && xa_is_value(head)) return true; return false; } /* * Bits in mapping->flags. */ enum mapping_flags { AS_EIO = 0, /* IO error on async write */ AS_ENOSPC = 1, /* ENOSPC on async write */ AS_MM_ALL_LOCKS = 2, /* under mm_take_all_locks() */ AS_UNEVICTABLE = 3, /* e.g., ramdisk, SHM_LOCK */ AS_EXITING = 4, /* final truncate in progress */ /* writeback related tags are not used */ AS_NO_WRITEBACK_TAGS = 5, AS_RELEASE_ALWAYS = 6, /* Call ->release_folio(), even if no private data */ AS_STABLE_WRITES = 7, /* must wait for writeback before modifying folio contents */ AS_INACCESSIBLE = 8, /* Do not attempt direct R/W access to the mapping */ AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM = 9, AS_KERNEL_FILE = 10, /* mapping for a fake kernel file that shouldn't account usage to user cgroups */ /* Bits 16-25 are used for FOLIO_ORDER */ AS_FOLIO_ORDER_BITS = 5, AS_FOLIO_ORDER_MIN = 16, AS_FOLIO_ORDER_MAX = AS_FOLIO_ORDER_MIN + AS_FOLIO_ORDER_BITS, }; #define AS_FOLIO_ORDER_BITS_MASK ((1u << AS_FOLIO_ORDER_BITS) - 1) #define AS_FOLIO_ORDER_MIN_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MIN) #define AS_FOLIO_ORDER_MAX_MASK (AS_FOLIO_ORDER_BITS_MASK << AS_FOLIO_ORDER_MAX) #define AS_FOLIO_ORDER_MASK (AS_FOLIO_ORDER_MIN_MASK | AS_FOLIO_ORDER_MAX_MASK) /** * mapping_set_error - record a writeback error in the address_space * @mapping: the mapping in which an error should be set * @error: the error to set in the mapping * * When writeback fails in some way, we must record that error so that * userspace can be informed when fsync and the like are called. We endeavor * to report errors on any file that was open at the time of the error. Some * internal callers also need to know when writeback errors have occurred. * * When a writeback error occurs, most filesystems will want to call * mapping_set_error to record the error in the mapping so that it can be * reported when the application calls fsync(2). */ static inline void mapping_set_error(struct address_space *mapping, int error) { if (likely(!error)) return; /* Record in wb_err for checkers using errseq_t based tracking */ __filemap_set_wb_err(mapping, error); /* Record it in superblock */ if (mapping->host) errseq_set(&mapping->host->i_sb->s_wb_err, error); /* Record it in flags for now, for legacy callers */ if (error == -ENOSPC) set_bit(AS_ENOSPC, &mapping->flags); else set_bit(AS_EIO, &mapping->flags); } static inline void mapping_set_unevictable(struct address_space *mapping) { set_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_clear_unevictable(struct address_space *mapping) { clear_bit(AS_UNEVICTABLE, &mapping->flags); } static inline bool mapping_unevictable(const struct address_space *mapping) { return mapping && test_bit(AS_UNEVICTABLE, &mapping->flags); } static inline void mapping_set_exiting(struct address_space *mapping) { set_bit(AS_EXITING, &mapping->flags); } static inline int mapping_exiting(const struct address_space *mapping) { return test_bit(AS_EXITING, &mapping->flags); } static inline void mapping_set_no_writeback_tags(struct address_space *mapping) { set_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline int mapping_use_writeback_tags(const struct address_space *mapping) { return !test_bit(AS_NO_WRITEBACK_TAGS, &mapping->flags); } static inline bool mapping_release_always(const struct address_space *mapping) { return test_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_set_release_always(struct address_space *mapping) { set_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline void mapping_clear_release_always(struct address_space *mapping) { clear_bit(AS_RELEASE_ALWAYS, &mapping->flags); } static inline bool mapping_stable_writes(const struct address_space *mapping) { return test_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_stable_writes(struct address_space *mapping) { set_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_clear_stable_writes(struct address_space *mapping) { clear_bit(AS_STABLE_WRITES, &mapping->flags); } static inline void mapping_set_inaccessible(struct address_space *mapping) { /* * It's expected inaccessible mappings are also unevictable. Compaction * migrate scanner (isolate_migratepages_block()) relies on this to * reduce page locking. */ set_bit(AS_UNEVICTABLE, &mapping->flags); set_bit(AS_INACCESSIBLE, &mapping->flags); } static inline bool mapping_inaccessible(const struct address_space *mapping) { return test_bit(AS_INACCESSIBLE, &mapping->flags); } static inline void mapping_set_writeback_may_deadlock_on_reclaim(struct address_space *mapping) { set_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } static inline bool mapping_writeback_may_deadlock_on_reclaim(const struct address_space *mapping) { return test_bit(AS_WRITEBACK_MAY_DEADLOCK_ON_RECLAIM, &mapping->flags); } static inline gfp_t mapping_gfp_mask(const struct address_space *mapping) { return mapping->gfp_mask; } /* Restricts the given gfp_mask to what the mapping allows. */ static inline gfp_t mapping_gfp_constraint(const struct address_space *mapping, gfp_t gfp_mask) { return mapping_gfp_mask(mapping) & gfp_mask; } /* * This is non-atomic. Only to be used before the mapping is activated. * Probably needs a barrier... */ static inline void mapping_set_gfp_mask(struct address_space *m, gfp_t mask) { m->gfp_mask = mask; } /* * There are some parts of the kernel which assume that PMD entries * are exactly HPAGE_PMD_ORDER. Those should be fixed, but until then, * limit the maximum allocation order to PMD size. I'm not aware of any * assumptions about maximum order if THP are disabled, but 8 seems like * a good order (that's 1MB if you're using 4kB pages) */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE #define PREFERRED_MAX_PAGECACHE_ORDER HPAGE_PMD_ORDER #else #define PREFERRED_MAX_PAGECACHE_ORDER 8 #endif /* * xas_split_alloc() does not support arbitrary orders. This implies no * 512MB THP on ARM64 with 64KB base page size. */ #define MAX_XAS_ORDER (XA_CHUNK_SHIFT * 2 - 1) #define MAX_PAGECACHE_ORDER min(MAX_XAS_ORDER, PREFERRED_MAX_PAGECACHE_ORDER) /* * mapping_max_folio_size_supported() - Check the max folio size supported * * The filesystem should call this function at mount time if there is a * requirement on the folio mapping size in the page cache. */ static inline size_t mapping_max_folio_size_supported(void) { if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 1U << (PAGE_SHIFT + MAX_PAGECACHE_ORDER); return PAGE_SIZE; } /* * mapping_set_folio_order_range() - Set the orders supported by a file. * @mapping: The address space of the file. * @min: Minimum folio order (between 0-MAX_PAGECACHE_ORDER inclusive). * @max: Maximum folio order (between @min-MAX_PAGECACHE_ORDER inclusive). * * The filesystem should call this function in its inode constructor to * indicate which base size (min) and maximum size (max) of folio the VFS * can use to cache the contents of the file. This should only be used * if the filesystem needs special handling of folio sizes (ie there is * something the core cannot know). * Do not tune it based on, eg, i_size. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_folio_order_range(struct address_space *mapping, unsigned int min, unsigned int max) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return; if (min > MAX_PAGECACHE_ORDER) min = MAX_PAGECACHE_ORDER; if (max > MAX_PAGECACHE_ORDER) max = MAX_PAGECACHE_ORDER; if (max < min) max = min; mapping->flags = (mapping->flags & ~AS_FOLIO_ORDER_MASK) | (min << AS_FOLIO_ORDER_MIN) | (max << AS_FOLIO_ORDER_MAX); } static inline void mapping_set_folio_min_order(struct address_space *mapping, unsigned int min) { mapping_set_folio_order_range(mapping, min, MAX_PAGECACHE_ORDER); } /** * mapping_set_large_folios() - Indicate the file supports large folios. * @mapping: The address space of the file. * * The filesystem should call this function in its inode constructor to * indicate that the VFS can use large folios to cache the contents of * the file. * * Context: This should not be called while the inode is active as it * is non-atomic. */ static inline void mapping_set_large_folios(struct address_space *mapping) { mapping_set_folio_order_range(mapping, 0, MAX_PAGECACHE_ORDER); } static inline unsigned int mapping_max_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MAX_MASK) >> AS_FOLIO_ORDER_MAX; } static inline unsigned int mapping_min_folio_order(const struct address_space *mapping) { if (!IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE)) return 0; return (mapping->flags & AS_FOLIO_ORDER_MIN_MASK) >> AS_FOLIO_ORDER_MIN; } static inline unsigned long mapping_min_folio_nrpages(const struct address_space *mapping) { return 1UL << mapping_min_folio_order(mapping); } static inline unsigned long mapping_min_folio_nrbytes(const struct address_space *mapping) { return mapping_min_folio_nrpages(mapping) << PAGE_SHIFT; } /** * mapping_align_index() - Align index for this mapping. * @mapping: The address_space. * @index: The page index. * * The index of a folio must be naturally aligned. If you are adding a * new folio to the page cache and need to know what index to give it, * call this function. */ static inline pgoff_t mapping_align_index(const struct address_space *mapping, pgoff_t index) { return round_down(index, mapping_min_folio_nrpages(mapping)); } /* * Large folio support currently depends on THP. These dependencies are * being worked on but are not yet fixed. */ static inline bool mapping_large_folio_support(const struct address_space *mapping) { /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON, "Anonymous mapping always supports large folio"); return mapping_max_folio_order(mapping) > 0; } /** * mapping_pmd_folio_support() - Check if a mapping supports PMD-sized folio * @mapping: The address_space * * While some mappings support large folios, they might not support PMD-sized * folios. This function checks whether a mapping supports PMD-sized folios. * For example, khugepaged needs this information before attempting to * collapsing THPs. * * Return: True if PMD-sized folios are supported, otherwise false. */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE static inline bool mapping_pmd_folio_support(const struct address_space *mapping) { /* AS_FOLIO_ORDER is only reasonable for pagecache folios */ VM_WARN_ON_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON); return mapping_min_folio_order(mapping) <= PMD_ORDER && mapping_max_folio_order(mapping) >= PMD_ORDER; } #else static inline bool mapping_pmd_folio_support(const struct address_space *mapping) { return false; } #endif /* Return the maximum folio size for this pagecache mapping, in bytes. */ static inline size_t mapping_max_folio_size(const struct address_space *mapping) { return PAGE_SIZE << mapping_max_folio_order(mapping); } struct address_space *folio_mapping(const struct folio *folio); /** * folio_flush_mapping - Find the file mapping this folio belongs to. * @folio: The folio. * * For folios which are in the page cache, return the mapping that this * page belongs to. Anonymous folios return NULL, even if they're in * the swap cache. Other kinds of folio also return NULL. * * This is ONLY used by architecture cache flushing code. If you aren't * writing cache flushing code, you want either folio_mapping() or * folio_file_mapping(). */ static inline struct address_space *folio_flush_mapping(struct folio *folio) { if (unlikely(folio_test_swapcache(folio))) return NULL; return folio_mapping(folio); } /** * folio_inode - Get the host inode for this folio. * @folio: The folio. * * For folios which are in the page cache, return the inode that this folio * belongs to. * * Do not call this for folios which aren't in the page cache. */ static inline struct inode *folio_inode(struct folio *folio) { return folio->mapping->host; } /** * folio_attach_private - Attach private data to a folio. * @folio: Folio to attach data to. * @data: Data to attach to folio. * * Attaching private data to a folio increments the page's reference count. * The data must be detached before the folio will be freed. */ static inline void folio_attach_private(struct folio *folio, void *data) { folio_get(folio); folio->private = data; folio_set_private(folio); } /** * folio_change_private - Change private data on a folio. * @folio: Folio to change the data on. * @data: Data to set on the folio. * * Change the private data attached to a folio and return the old * data. The page must previously have had data attached and the data * must be detached before the folio will be freed. * * Return: Data that was previously attached to the folio. */ static inline void *folio_change_private(struct folio *folio, void *data) { void *old = folio_get_private(folio); folio->private = data; return old; } /** * folio_detach_private - Detach private data from a folio. * @folio: Folio to detach data from. * * Removes the data that was previously attached to the folio and decrements * the refcount on the page. * * Return: Data that was attached to the folio. */ static inline void *folio_detach_private(struct folio *folio) { void *data = folio_get_private(folio); if (!folio_test_private(folio)) return NULL; folio_clear_private(folio); folio->private = NULL; folio_put(folio); return data; } static inline void attach_page_private(struct page *page, void *data) { folio_attach_private(page_folio(page), data); } static inline void *detach_page_private(struct page *page) { return folio_detach_private(page_folio(page)); } #ifdef CONFIG_NUMA struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy); #else static inline struct folio *filemap_alloc_folio_noprof(gfp_t gfp, unsigned int order, struct mempolicy *policy) { return folio_alloc_noprof(gfp, order); } #endif #define filemap_alloc_folio(...) \ alloc_hooks(filemap_alloc_folio_noprof(__VA_ARGS__)) static inline struct page *__page_cache_alloc(gfp_t gfp) { return &filemap_alloc_folio(gfp, 0, NULL)->page; } static inline gfp_t readahead_gfp_mask(struct address_space *x) { return mapping_gfp_mask(x) | __GFP_NORETRY | __GFP_NOWARN; } typedef int filler_t(struct file *, struct folio *); pgoff_t page_cache_next_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); pgoff_t page_cache_prev_miss(struct address_space *mapping, pgoff_t index, unsigned long max_scan); /** * typedef fgf_t - Flags for getting folios from the page cache. * * Most users of the page cache will not need to use these flags; * there are convenience functions such as filemap_get_folio() and * filemap_lock_folio(). For users which need more control over exactly * what is done with the folios, these flags to __filemap_get_folio() * are available. * * * %FGP_ACCESSED - The folio will be marked accessed. * * %FGP_LOCK - The folio is returned locked. * * %FGP_CREAT - If no folio is present then a new folio is allocated, * added to the page cache and the VM's LRU list. The folio is * returned locked. * * %FGP_FOR_MMAP - The caller wants to do its own locking dance if the * folio is already in cache. If the folio was allocated, unlock it * before returning so the caller can do the same dance. * * %FGP_WRITE - The folio will be written to by the caller. * * %FGP_NOFS - __GFP_FS will get cleared in gfp. * * %FGP_NOWAIT - Don't block on the folio lock. * * %FGP_STABLE - Wait for the folio to be stable (finished writeback) * * %FGP_DONTCACHE - Uncached buffered IO * * %FGP_WRITEBEGIN - The flags to use in a filesystem write_begin() * implementation. */ typedef unsigned int __bitwise fgf_t; #define FGP_ACCESSED ((__force fgf_t)0x00000001) #define FGP_LOCK ((__force fgf_t)0x00000002) #define FGP_CREAT ((__force fgf_t)0x00000004) #define FGP_WRITE ((__force fgf_t)0x00000008) #define FGP_NOFS ((__force fgf_t)0x00000010) #define FGP_NOWAIT ((__force fgf_t)0x00000020) #define FGP_FOR_MMAP ((__force fgf_t)0x00000040) #define FGP_STABLE ((__force fgf_t)0x00000080) #define FGP_DONTCACHE ((__force fgf_t)0x00000100) #define FGF_GET_ORDER(fgf) (((__force unsigned)fgf) >> 26) /* top 6 bits */ #define FGP_WRITEBEGIN (FGP_LOCK | FGP_WRITE | FGP_CREAT | FGP_STABLE) static inline unsigned int filemap_get_order(size_t size) { unsigned int shift = ilog2(size); if (shift <= PAGE_SHIFT) return 0; return shift - PAGE_SHIFT; } /** * fgf_set_order - Encode a length in the fgf_t flags. * @size: The suggested size of the folio to create. * * The caller of __filemap_get_folio() can use this to suggest a preferred * size for the folio that is created. If there is already a folio at * the index, it will be returned, no matter what its size. If a folio * is freshly created, it may be of a different size than requested * due to alignment constraints, memory pressure, or the presence of * other folios at nearby indices. */ static inline fgf_t fgf_set_order(size_t size) { unsigned int order = filemap_get_order(size); if (!order) return 0; return (__force fgf_t)(order << 26); } void *filemap_get_entry(struct address_space *mapping, pgoff_t index); struct folio *__filemap_get_folio_mpol(struct address_space *mapping, pgoff_t index, fgf_t fgf_flags, gfp_t gfp, struct mempolicy *policy); struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index, fgf_t fgp_flags, gfp_t gfp); static inline struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index, fgf_t fgf_flags, gfp_t gfp) { return __filemap_get_folio_mpol(mapping, index, fgf_flags, gfp, NULL); } /** * write_begin_get_folio - Get folio for write_begin with flags. * @iocb: The kiocb passed from write_begin (may be NULL). * @mapping: The address space to search. * @index: The page cache index. * @len: Length of data being written. * * This is a helper for filesystem write_begin() implementations. * It wraps __filemap_get_folio(), setting appropriate flags in * the write begin context. * * Return: A folio or an ERR_PTR. */ static inline struct folio *write_begin_get_folio(const struct kiocb *iocb, struct address_space *mapping, pgoff_t index, size_t len) { fgf_t fgp_flags = FGP_WRITEBEGIN; fgp_flags |= fgf_set_order(len); if (iocb && iocb->ki_flags & IOCB_DONTCACHE) fgp_flags |= FGP_DONTCACHE; return __filemap_get_folio(mapping, index, fgp_flags, mapping_gfp_mask(mapping)); } /** * filemap_get_folio - Find and get a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned with an increased refcount. * * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_get_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, 0, 0); } /** * filemap_lock_folio - Find and lock a folio. * @mapping: The address_space to search. * @index: The page index. * * Looks up the page cache entry at @mapping & @index. If a folio is * present, it is returned locked with an increased refcount. * * Context: May sleep. * Return: A folio or ERR_PTR(-ENOENT) if there is no folio in the cache for * this index. Will not return a shadow, swap or DAX entry. */ static inline struct folio *filemap_lock_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK, 0); } /** * filemap_grab_folio - grab a folio from the page cache * @mapping: The address space to search * @index: The page index * * Looks up the page cache entry at @mapping & @index. If no folio is found, * a new folio is created. The folio is locked, marked as accessed, and * returned. * * Return: A found or created folio. ERR_PTR(-ENOMEM) if no folio is found * and failed to create a folio. */ static inline struct folio *filemap_grab_folio(struct address_space *mapping, pgoff_t index) { return __filemap_get_folio(mapping, index, FGP_LOCK | FGP_ACCESSED | FGP_CREAT, mapping_gfp_mask(mapping)); } /** * find_get_page - find and get a page reference * @mapping: the address_space to search * @offset: the page index * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned with an increased refcount. * * Otherwise, %NULL is returned. */ static inline struct page *find_get_page(struct address_space *mapping, pgoff_t offset) { return pagecache_get_page(mapping, offset, 0, 0); } static inline struct page *find_get_page_flags(struct address_space *mapping, pgoff_t offset, fgf_t fgp_flags) { return pagecache_get_page(mapping, offset, fgp_flags, 0); } /** * find_lock_page - locate, pin and lock a pagecache page * @mapping: the address_space to search * @index: the page index * * Looks up the page cache entry at @mapping & @index. If there is a * page cache page, it is returned locked and with an increased * refcount. * * Context: May sleep. * Return: A struct page or %NULL if there is no page in the cache for this * index. */ static inline struct page *find_lock_page(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK, 0); } /** * find_or_create_page - locate or add a pagecache page * @mapping: the page's address_space * @index: the page's index into the mapping * @gfp_mask: page allocation mode * * Looks up the page cache slot at @mapping & @offset. If there is a * page cache page, it is returned locked and with an increased * refcount. * * If the page is not present, a new page is allocated using @gfp_mask * and added to the page cache and the VM's LRU list. The page is * returned locked and with an increased refcount. * * On memory exhaustion, %NULL is returned. * * find_or_create_page() may sleep, even if @gfp_flags specifies an * atomic allocation! */ static inline struct page *find_or_create_page(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_ACCESSED|FGP_CREAT, gfp_mask); } /** * grab_cache_page_nowait - returns locked page at given index in given cache * @mapping: target address_space * @index: the page index * * Returns locked page at given index in given cache, creating it if * needed, but do not wait if the page is locked or to reclaim memory. * This is intended for speculative data generators, where the data can * be regenerated if the page couldn't be grabbed. This routine should * be safe to call while holding the lock for another page. * * Clear __GFP_FS when allocating the page to avoid recursion into the fs * and deadlock against the caller's locked page. */ static inline struct page *grab_cache_page_nowait(struct address_space *mapping, pgoff_t index) { return pagecache_get_page(mapping, index, FGP_LOCK|FGP_CREAT|FGP_NOFS|FGP_NOWAIT, mapping_gfp_mask(mapping)); } /** * folio_next_index - Get the index of the next folio. * @folio: The current folio. * * Return: The index of the folio which follows this folio in the file. */ static inline pgoff_t folio_next_index(const struct folio *folio) { return folio->index + folio_nr_pages(folio); } /** * folio_next_pos - Get the file position of the next folio. * @folio: The current folio. * * Return: The position of the folio which follows this folio in the file. */ static inline loff_t folio_next_pos(const struct folio *folio) { return (loff_t)folio_next_index(folio) << PAGE_SHIFT; } /** * folio_file_page - The page for a particular index. * @folio: The folio which contains this index. * @index: The index we want to look up. * * Sometimes after looking up a folio in the page cache, we need to * obtain the specific page for an index (eg a page fault). * * Return: The page containing the file data for this index. */ static inline struct page *folio_file_page(struct folio *folio, pgoff_t index) { return folio_page(folio, index & (folio_nr_pages(folio) - 1)); } /** * folio_contains - Does this folio contain this index? * @folio: The folio. * @index: The page index within the file. * * Context: The caller should have the folio locked and ensure * e.g., shmem did not move this folio to the swap cache. * Return: true or false. */ static inline bool folio_contains(const struct folio *folio, pgoff_t index) { VM_WARN_ON_ONCE_FOLIO(folio_test_swapcache(folio), folio); return index - folio->index < folio_nr_pages(folio); } unsigned filemap_get_folios(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_contig(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start, pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch); unsigned filemap_get_folios_dirty(struct address_space *mapping, pgoff_t *start, pgoff_t end, struct folio_batch *fbatch); struct folio *read_cache_folio(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index, gfp_t flags); struct page *read_cache_page(struct address_space *, pgoff_t index, filler_t *filler, struct file *file); extern struct page * read_cache_page_gfp(struct address_space *mapping, pgoff_t index, gfp_t gfp_mask); static inline struct page *read_mapping_page(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_page(mapping, index, NULL, file); } static inline struct folio *read_mapping_folio(struct address_space *mapping, pgoff_t index, struct file *file) { return read_cache_folio(mapping, index, NULL, file); } /** * page_pgoff - Calculate the logical page offset of this page. * @folio: The folio containing this page. * @page: The page which we need the offset of. * * For file pages, this is the offset from the beginning of the file * in units of PAGE_SIZE. For anonymous pages, this is the offset from * the beginning of the anon_vma in units of PAGE_SIZE. This will * return nonsense for KSM pages. * * Context: Caller must have a reference on the folio or otherwise * prevent it from being split or freed. * * Return: The offset in units of PAGE_SIZE. */ static inline pgoff_t page_pgoff(const struct folio *folio, const struct page *page) { return folio->index + folio_page_idx(folio, page); } /** * folio_pos - Returns the byte position of this folio in its file. * @folio: The folio. */ static inline loff_t folio_pos(const struct folio *folio) { return ((loff_t)folio->index) * PAGE_SIZE; } /* * Return byte-offset into filesystem object for page. */ static inline loff_t page_offset(struct page *page) { struct folio *folio = page_folio(page); return folio_pos(folio) + folio_page_idx(folio, page) * PAGE_SIZE; } /* * Get the offset in PAGE_SIZE (even for hugetlb folios). */ static inline pgoff_t folio_pgoff(const struct folio *folio) { return folio->index; } static inline pgoff_t linear_page_index(const struct vm_area_struct *vma, const unsigned long address) { pgoff_t pgoff; pgoff = (address - vma->vm_start) >> PAGE_SHIFT; pgoff += vma->vm_pgoff; return pgoff; } struct wait_page_key { struct folio *folio; int bit_nr; int page_match; }; struct wait_page_queue { struct folio *folio; int bit_nr; wait_queue_entry_t wait; }; static inline bool wake_page_match(struct wait_page_queue *wait_page, struct wait_page_key *key) { if (wait_page->folio != key->folio) return false; key->page_match = 1; if (wait_page->bit_nr != key->bit_nr) return false; return true; } void __folio_lock(struct folio *folio); int __folio_lock_killable(struct folio *folio); vm_fault_t __folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf); void unlock_page(struct page *page); void folio_unlock(struct folio *folio); /** * folio_trylock() - Attempt to lock a folio. * @folio: The folio to attempt to lock. * * Sometimes it is undesirable to wait for a folio to be unlocked (eg * when the locks are being taken in the wrong order, or if making * progress through a batch of folios is more important than processing * them in order). Usually folio_lock() is the correct function to call. * * Context: Any context. * Return: Whether the lock was successfully acquired. */ static inline bool folio_trylock(struct folio *folio) { return likely(!test_and_set_bit_lock(PG_locked, folio_flags(folio, 0))); } /* * Return true if the page was successfully locked */ static inline bool trylock_page(struct page *page) { return folio_trylock(page_folio(page)); } /** * folio_lock() - Lock this folio. * @folio: The folio to lock. * * The folio lock protects against many things, probably more than it * should. It is primarily held while a folio is being brought uptodate, * either from its backing file or from swap. It is also held while a * folio is being truncated from its address_space, so holding the lock * is sufficient to keep folio->mapping stable. * * The folio lock is also held while write() is modifying the page to * provide POSIX atomicity guarantees (as long as the write does not * cross a page boundary). Other modifications to the data in the folio * do not hold the folio lock and can race with writes, eg DMA and stores * to mapped pages. * * Context: May sleep. If you need to acquire the locks of two or * more folios, they must be in order of ascending index, if they are * in the same address_space. If they are in different address_spaces, * acquire the lock of the folio which belongs to the address_space which * has the lowest address in memory first. */ static inline void folio_lock(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) __folio_lock(folio); } /** * lock_page() - Lock the folio containing this page. * @page: The page to lock. * * See folio_lock() for a description of what the lock protects. * This is a legacy function and new code should probably use folio_lock() * instead. * * Context: May sleep. Pages in the same folio share a lock, so do not * attempt to lock two pages which share a folio. */ static inline void lock_page(struct page *page) { struct folio *folio; might_sleep(); folio = page_folio(page); if (!folio_trylock(folio)) __folio_lock(folio); } /** * folio_lock_killable() - Lock this folio, interruptible by a fatal signal. * @folio: The folio to lock. * * Attempts to lock the folio, like folio_lock(), except that the sleep * to acquire the lock is interruptible by a fatal signal. * * Context: May sleep; see folio_lock(). * Return: 0 if the lock was acquired; -EINTR if a fatal signal was received. */ static inline int folio_lock_killable(struct folio *folio) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_killable(folio); return 0; } /* * folio_lock_or_retry - Lock the folio, unless this would block and the * caller indicated that it can handle a retry. * * Return value and mmap_lock implications depend on flags; see * __folio_lock_or_retry(). */ static inline vm_fault_t folio_lock_or_retry(struct folio *folio, struct vm_fault *vmf) { might_sleep(); if (!folio_trylock(folio)) return __folio_lock_or_retry(folio, vmf); return 0; } /* * This is exported only for folio_wait_locked/folio_wait_writeback, etc., * and should not be used directly. */ void folio_wait_bit(struct folio *folio, int bit_nr); int folio_wait_bit_killable(struct folio *folio, int bit_nr); /* * Wait for a folio to be unlocked. * * This must be called with the caller "holding" the folio, * ie with increased folio reference count so that the folio won't * go away during the wait. */ static inline void folio_wait_locked(struct folio *folio) { if (folio_test_locked(folio)) folio_wait_bit(folio, PG_locked); } static inline int folio_wait_locked_killable(struct folio *folio) { if (!folio_test_locked(folio)) return 0; return folio_wait_bit_killable(folio, PG_locked); } void folio_end_read(struct folio *folio, bool success); void wait_on_page_writeback(struct page *page); void folio_wait_writeback(struct folio *folio); int folio_wait_writeback_killable(struct folio *folio); void end_page_writeback(struct page *page); void folio_end_writeback(struct folio *folio); void folio_end_writeback_no_dropbehind(struct folio *folio); void folio_end_dropbehind(struct folio *folio); void folio_wait_stable(struct folio *folio); void __folio_mark_dirty(struct folio *folio, struct address_space *, int warn); void folio_account_cleaned(struct folio *folio, struct bdi_writeback *wb); void __folio_cancel_dirty(struct folio *folio); static inline void folio_cancel_dirty(struct folio *folio) { /* Avoid atomic ops, locking, etc. when not actually needed. */ if (folio_test_dirty(folio)) __folio_cancel_dirty(folio); } bool folio_clear_dirty_for_io(struct folio *folio); bool clear_page_dirty_for_io(struct page *page); void folio_invalidate(struct folio *folio, size_t offset, size_t length); bool noop_dirty_folio(struct address_space *mapping, struct folio *folio); #ifdef CONFIG_MIGRATION int filemap_migrate_folio(struct address_space *mapping, struct folio *dst, struct folio *src, enum migrate_mode mode); #else #define filemap_migrate_folio NULL #endif void folio_end_private_2(struct folio *folio); void folio_wait_private_2(struct folio *folio); int folio_wait_private_2_killable(struct folio *folio); /* * Fault in userspace address range. */ size_t fault_in_writeable(char __user *uaddr, size_t size); size_t fault_in_subpage_writeable(char __user *uaddr, size_t size); size_t fault_in_safe_writeable(const char __user *uaddr, size_t size); size_t fault_in_readable(const char __user *uaddr, size_t size); int add_to_page_cache_lru(struct page *page, struct address_space *mapping, pgoff_t index, gfp_t gfp); int filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp); void filemap_remove_folio(struct folio *folio); void __filemap_remove_folio(struct folio *folio, void *shadow); void replace_page_cache_folio(struct folio *old, struct folio *new); void delete_from_page_cache_batch(struct address_space *mapping, struct folio_batch *fbatch); bool filemap_release_folio(struct folio *folio, gfp_t gfp); loff_t mapping_seek_hole_data(struct address_space *, loff_t start, loff_t end, int whence); /* Must be non-static for BPF error injection */ int __filemap_add_folio(struct address_space *mapping, struct folio *folio, pgoff_t index, gfp_t gfp, void **shadowp); bool filemap_range_has_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte); /** * filemap_range_needs_writeback - check if range potentially needs writeback * @mapping: address space within which to check * @start_byte: offset in bytes where the range starts * @end_byte: offset in bytes where the range ends (inclusive) * * Find at least one page in the range supplied, usually used to check if * direct writing in this range will trigger a writeback. Used by O_DIRECT * read/write with IOCB_NOWAIT, to see if the caller needs to do * filemap_write_and_wait_range() before proceeding. * * Return: %true if the caller should do filemap_write_and_wait_range() before * doing O_DIRECT to a page in this range, %false otherwise. */ static inline bool filemap_range_needs_writeback(struct address_space *mapping, loff_t start_byte, loff_t end_byte) { if (!mapping->nrpages) return false; if (!mapping_tagged(mapping, PAGECACHE_TAG_DIRTY) && !mapping_tagged(mapping, PAGECACHE_TAG_WRITEBACK)) return false; return filemap_range_has_writeback(mapping, start_byte, end_byte); } /** * struct readahead_control - Describes a readahead request. * * A readahead request is for consecutive pages. Filesystems which * implement the ->readahead method should call readahead_folio() or * __readahead_batch() in a loop and attempt to start reads into each * folio in the request. * * Most of the fields in this struct are private and should be accessed * by the functions below. * * @file: The file, used primarily by network filesystems for authentication. * May be NULL if invoked internally by the filesystem. * @mapping: Readahead this filesystem object. * @ra: File readahead state. May be NULL. */ struct readahead_control { struct file *file; struct address_space *mapping; struct file_ra_state *ra; /* private: use the readahead_* accessors instead */ pgoff_t _index; unsigned int _nr_pages; unsigned int _batch_count; bool dropbehind; bool _workingset; unsigned long _pflags; }; #define DEFINE_READAHEAD(ractl, f, r, m, i) \ struct readahead_control ractl = { \ .file = f, \ .mapping = m, \ .ra = r, \ ._index = i, \ } #define VM_READAHEAD_PAGES (SZ_128K / PAGE_SIZE) void page_cache_ra_unbounded(struct readahead_control *, unsigned long nr_to_read, unsigned long lookahead_count); void page_cache_sync_ra(struct readahead_control *, unsigned long req_count); void page_cache_async_ra(struct readahead_control *, struct folio *, unsigned long req_count); void readahead_expand(struct readahead_control *ractl, loff_t new_start, size_t new_len); /** * page_cache_sync_readahead - generic file readahead * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @index: Index of first page to be read. * @req_count: Total number of pages being read by the caller. * * page_cache_sync_readahead() should be called when a cache miss happened: * it will submit the read. The readahead logic may decide to piggyback more * pages onto the read request if access patterns suggest it will improve * performance. */ static inline void page_cache_sync_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, pgoff_t index, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, index); page_cache_sync_ra(&ractl, req_count); } /** * page_cache_async_readahead - file readahead for marked pages * @mapping: address_space which holds the pagecache and I/O vectors * @ra: file_ra_state which holds the readahead state * @file: Used by the filesystem for authentication. * @folio: The folio which triggered the readahead call. * @req_count: Total number of pages being read by the caller. * * page_cache_async_readahead() should be called when a page is used which * is marked as PageReadahead; this is a marker to suggest that the application * has used up enough of the readahead window that we should start pulling in * more pages. */ static inline void page_cache_async_readahead(struct address_space *mapping, struct file_ra_state *ra, struct file *file, struct folio *folio, unsigned long req_count) { DEFINE_READAHEAD(ractl, file, ra, mapping, folio->index); page_cache_async_ra(&ractl, folio, req_count); } static inline struct folio *__readahead_folio(struct readahead_control *ractl) { struct folio *folio; BUG_ON(ractl->_batch_count > ractl->_nr_pages); ractl->_nr_pages -= ractl->_batch_count; ractl->_index += ractl->_batch_count; if (!ractl->_nr_pages) { ractl->_batch_count = 0; return NULL; } folio = xa_load(&ractl->mapping->i_pages, ractl->_index); VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); ractl->_batch_count = folio_nr_pages(folio); return folio; } /** * readahead_folio - Get the next folio to read. * @ractl: The current readahead request. * * Context: The folio is locked. The caller should unlock the folio once * all I/O to that folio has completed. * Return: A pointer to the next folio, or %NULL if we are done. */ static inline struct folio *readahead_folio(struct readahead_control *ractl) { struct folio *folio = __readahead_folio(ractl); if (folio) folio_put(folio); return folio; } static inline unsigned int __readahead_batch(struct readahead_control *rac, struct page **array, unsigned int array_sz) { unsigned int i = 0; XA_STATE(xas, &rac->mapping->i_pages, 0); struct folio *folio; BUG_ON(rac->_batch_count > rac->_nr_pages); rac->_nr_pages -= rac->_batch_count; rac->_index += rac->_batch_count; rac->_batch_count = 0; xas_set(&xas, rac->_index); rcu_read_lock(); xas_for_each(&xas, folio, rac->_index + rac->_nr_pages - 1) { if (xas_retry(&xas, folio)) continue; VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio); array[i++] = folio_page(folio, 0); rac->_batch_count += folio_nr_pages(folio); if (i == array_sz) break; } rcu_read_unlock(); return i; } /** * readahead_pos - The byte offset into the file of this readahead request. * @rac: The readahead request. */ static inline loff_t readahead_pos(const struct readahead_control *rac) { return (loff_t)rac->_index * PAGE_SIZE; } /** * readahead_length - The number of bytes in this readahead request. * @rac: The readahead request. */ static inline size_t readahead_length(const struct readahead_control *rac) { return rac->_nr_pages * PAGE_SIZE; } /** * readahead_index - The index of the first page in this readahead request. * @rac: The readahead request. */ static inline pgoff_t readahead_index(const struct readahead_control *rac) { return rac->_index; } /** * readahead_count - The number of pages in this readahead request. * @rac: The readahead request. */ static inline unsigned int readahead_count(const struct readahead_control *rac) { return rac->_nr_pages; } /** * readahead_batch_length - The number of bytes in the current batch. * @rac: The readahead request. */ static inline size_t readahead_batch_length(const struct readahead_control *rac) { return rac->_batch_count * PAGE_SIZE; } static inline unsigned long dir_pages(const struct inode *inode) { return (unsigned long)(inode->i_size + PAGE_SIZE - 1) >> PAGE_SHIFT; } /** * folio_mkwrite_check_truncate - check if folio was truncated * @folio: the folio to check * @inode: the inode to check the folio against * * Return: the number of bytes in the folio up to EOF, * or -EFAULT if the folio was truncated. */ static inline ssize_t folio_mkwrite_check_truncate(const struct folio *folio, const struct inode *inode) { loff_t size = i_size_read(inode); pgoff_t index = size >> PAGE_SHIFT; size_t offset = offset_in_folio(folio, size); if (!folio->mapping) return -EFAULT; /* folio is wholly inside EOF */ if (folio_next_index(folio) - 1 < index) return folio_size(folio); /* folio is wholly past EOF */ if (folio->index > index || !offset) return -EFAULT; /* folio is partially inside EOF */ return offset; } /** * i_blocks_per_folio - How many blocks fit in this folio. * @inode: The inode which contains the blocks. * @folio: The folio. * * If the block size is larger than the size of this folio, return zero. * * Context: The caller should hold a refcount on the folio to prevent it * from being split. * Return: The number of filesystem blocks covered by this folio. */ static inline unsigned int i_blocks_per_folio(const struct inode *inode, const struct folio *folio) { return folio_size(folio) >> inode->i_blkbits; } #endif /* _LINUX_PAGEMAP_H */ |
| 137 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 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-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. * * Global definitions for the Ethernet IEEE 802.3 interface. * * Version: @(#)if_ether.h 1.0.1a 02/08/94 * * Author: Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Donald Becker, <becker@super.org> * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Steve Whitehouse, <gw7rrm@eeshack3.swan.ac.uk> */ #ifndef _LINUX_IF_ETHER_H #define _LINUX_IF_ETHER_H #include <linux/skbuff.h> #include <uapi/linux/if_ether.h> /* XX:XX:XX:XX:XX:XX */ #define MAC_ADDR_STR_LEN (3 * ETH_ALEN - 1) static inline struct ethhdr *eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_mac_header(skb); } /* Prefer this version in TX path, instead of * skb_reset_mac_header() + eth_hdr() */ static inline struct ethhdr *skb_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb->data; } static inline struct ethhdr *inner_eth_hdr(const struct sk_buff *skb) { return (struct ethhdr *)skb_inner_mac_header(skb); } int eth_header_parse(const struct sk_buff *skb, const struct net_device *dev, unsigned char *haddr); extern ssize_t sysfs_format_mac(char *buf, const unsigned char *addr, int len); #endif /* _LINUX_IF_ETHER_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 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _NETFILTER_NETDEV_H_ #define _NETFILTER_NETDEV_H_ #include <linux/netfilter.h> #include <linux/netdevice.h> #ifdef CONFIG_NETFILTER_INGRESS static inline bool nf_hook_ingress_active(const struct sk_buff *skb) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_INGRESS])) return false; #endif return rcu_access_pointer(skb->dev->nf_hooks_ingress); } /* caller must hold rcu_read_lock */ static inline int nf_hook_ingress(struct sk_buff *skb) { struct nf_hook_entries *e = rcu_dereference(skb->dev->nf_hooks_ingress); struct nf_hook_state state; int ret; /* Must recheck the ingress hook head, in the event it became NULL * after the check in nf_hook_ingress_active evaluated to true. */ if (unlikely(!e)) return 0; nf_hook_state_init(&state, NF_NETDEV_INGRESS, NFPROTO_NETDEV, skb->dev, NULL, NULL, dev_net(skb->dev), NULL); ret = nf_hook_slow(skb, &state, e, 0); if (ret == 0) return -1; return ret; } #else /* CONFIG_NETFILTER_INGRESS */ static inline int nf_hook_ingress_active(struct sk_buff *skb) { return 0; } static inline int nf_hook_ingress(struct sk_buff *skb) { return 0; } #endif /* CONFIG_NETFILTER_INGRESS */ #ifdef CONFIG_NETFILTER_EGRESS static inline bool nf_hook_egress_active(void) { #ifdef CONFIG_JUMP_LABEL if (!static_key_false(&nf_hooks_needed[NFPROTO_NETDEV][NF_NETDEV_EGRESS])) return false; #endif return true; } /** * nf_hook_egress - classify packets before transmission * @skb: packet to be classified * @rc: result code which shall be returned by __dev_queue_xmit() on failure * @dev: netdev whose egress hooks shall be applied to @skb * * Caller must hold rcu_read_lock. * * On ingress, packets are classified first by tc, then by netfilter. * On egress, the order is reversed for symmetry. Conceptually, tc and * netfilter can be thought of as layers, with netfilter layered above tc: * When tc redirects a packet to another interface, netfilter is not applied * because the packet is on the tc layer. * * The nf_skip_egress flag controls whether netfilter is applied on egress. * It is updated by __netif_receive_skb_core() and __dev_queue_xmit() when the * packet passes through tc and netfilter. Because __dev_queue_xmit() may be * called recursively by tunnel drivers such as vxlan, the flag is reverted to * false after sch_handle_egress(). This ensures that netfilter is applied * both on the overlay and underlying network. * * Returns: @skb on success or %NULL if the packet was consumed or filtered. */ static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { struct nf_hook_entries *e; struct nf_hook_state state; int ret; #ifdef CONFIG_NETFILTER_SKIP_EGRESS if (skb->nf_skip_egress) return skb; #endif e = rcu_dereference_check(dev->nf_hooks_egress, rcu_read_lock_bh_held()); if (!e) return skb; nf_hook_state_init(&state, NF_NETDEV_EGRESS, NFPROTO_NETDEV, NULL, dev, NULL, dev_net(dev), NULL); /* nf assumes rcu_read_lock, not just read_lock_bh */ rcu_read_lock(); ret = nf_hook_slow(skb, &state, e, 0); rcu_read_unlock(); if (ret == 1) { return skb; } else if (ret < 0) { *rc = NET_XMIT_DROP; return NULL; } else { /* ret == 0 */ *rc = NET_XMIT_SUCCESS; return NULL; } } #else /* CONFIG_NETFILTER_EGRESS */ static inline bool nf_hook_egress_active(void) { return false; } static inline struct sk_buff *nf_hook_egress(struct sk_buff *skb, int *rc, struct net_device *dev) { return skb; } #endif /* CONFIG_NETFILTER_EGRESS */ static inline void nf_skip_egress(struct sk_buff *skb, bool skip) { #ifdef CONFIG_NETFILTER_SKIP_EGRESS skb->nf_skip_egress = skip; #endif } static inline void nf_hook_netdev_init(struct net_device *dev) { #ifdef CONFIG_NETFILTER_INGRESS RCU_INIT_POINTER(dev->nf_hooks_ingress, NULL); #endif #ifdef CONFIG_NETFILTER_EGRESS RCU_INIT_POINTER(dev->nf_hooks_egress, NULL); #endif } #endif /* _NETFILTER_NETDEV_H_ */ |
| 103 107 4 4 4 3 4 113 129 135 370 364 152 4 4 3 4 4 3 4 3 4 1 1 372 365 372 371 375 367 148 5 143 48 49 357 357 1 104 101 105 3 3 3 14 350 368 364 9 13 350 214 362 1 1 148 148 152 148 | 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 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 1371 1372 1373 1374 1375 1376 1377 1378 1379 1380 1381 1382 1383 1384 1385 1386 1387 1388 1389 1390 1391 1392 1393 1394 1395 1396 1397 1398 1399 1400 1401 1402 1403 1404 1405 1406 1407 1408 1409 1410 1411 1412 1413 1414 1415 1416 1417 1418 1419 1420 1421 1422 1423 1424 1425 1426 1427 1428 1429 1430 1431 1432 1433 1434 1435 1436 1437 1438 1439 1440 1441 1442 1443 1444 1445 1446 1447 1448 1449 1450 1451 1452 1453 1454 1455 1456 1457 1458 1459 1460 1461 1462 1463 1464 1465 1466 1467 1468 1469 1470 1471 1472 1473 1474 1475 1476 1477 1478 1479 1480 1481 1482 1483 1484 1485 1486 1487 1488 1489 1490 1491 1492 1493 1494 1495 1496 1497 1498 1499 1500 1501 1502 1503 1504 1505 1506 1507 1508 1509 1510 1511 1512 1513 1514 1515 1516 1517 1518 1519 1520 1521 1522 1523 1524 1525 1526 1527 1528 1529 1530 1531 | // SPDX-License-Identifier: GPL-2.0 /* * linux/fs/file.c * * Copyright (C) 1998-1999, Stephen Tweedie and Bill Hawes * * Manage the dynamic fd arrays in the process files_struct. */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/fs.h> #include <linux/kernel.h> #include <linux/mm.h> #include <linux/sched/signal.h> #include <linux/slab.h> #include <linux/file.h> #include <linux/fdtable.h> #include <linux/bitops.h> #include <linux/spinlock.h> #include <linux/rcupdate.h> #include <linux/close_range.h> #include <linux/file_ref.h> #include <net/sock.h> #include <linux/init_task.h> #include "internal.h" static noinline bool __file_ref_put_badval(file_ref_t *ref, unsigned long cnt) { /* * If the reference count was already in the dead zone, then this * put() operation is imbalanced. Warn, put the reference count back to * DEAD and tell the caller to not deconstruct the object. */ if (WARN_ONCE(cnt >= FILE_REF_RELEASED, "imbalanced put on file reference count")) { atomic_long_set(&ref->refcnt, FILE_REF_DEAD); return false; } /* * This is a put() operation on a saturated refcount. Restore the * mean saturation value and tell the caller to not deconstruct the * object. */ if (cnt > FILE_REF_MAXREF) atomic_long_set(&ref->refcnt, FILE_REF_SATURATED); return false; } /** * __file_ref_put - Slowpath of file_ref_put() * @ref: Pointer to the reference count * @cnt: Current reference count * * Invoked when the reference count is outside of the valid zone. * * Return: * True if this was the last reference with no future references * possible. This signals the caller that it can safely schedule the * object, which is protected by the reference counter, for * deconstruction. * * False if there are still active references or the put() raced * with a concurrent get()/put() pair. Caller is not allowed to * deconstruct the protected object. */ bool __file_ref_put(file_ref_t *ref, unsigned long cnt) { /* Did this drop the last reference? */ if (likely(cnt == FILE_REF_NOREF)) { /* * Carefully try to set the reference count to FILE_REF_DEAD. * * This can fail if a concurrent get() operation has * elevated it again or the corresponding put() even marked * it dead already. Both are valid situations and do not * require a retry. If this fails the caller is not * allowed to deconstruct the object. */ if (!atomic_long_try_cmpxchg_release(&ref->refcnt, &cnt, FILE_REF_DEAD)) return false; /* * The caller can safely schedule the object for * deconstruction. Provide acquire ordering. */ smp_acquire__after_ctrl_dep(); return true; } return __file_ref_put_badval(ref, cnt); } EXPORT_SYMBOL_GPL(__file_ref_put); unsigned int sysctl_nr_open __read_mostly = 1024*1024; unsigned int sysctl_nr_open_min = BITS_PER_LONG; /* our min() is unusable in constant expressions ;-/ */ #define __const_min(x, y) ((x) < (y) ? (x) : (y)) unsigned int sysctl_nr_open_max = __const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG; static void __free_fdtable(struct fdtable *fdt) { kvfree(fdt->fd); kvfree(fdt->open_fds); kfree(fdt); } static void free_fdtable_rcu(struct rcu_head *rcu) { __free_fdtable(container_of(rcu, struct fdtable, rcu)); } #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr)) #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long)) #define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds /* * Copy 'count' fd bits from the old table to the new table and clear the extra * space if any. This does not copy the file pointers. Called with the files * spinlock held for write. */ static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt, unsigned int copy_words) { unsigned int nwords = fdt_words(nfdt); bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec, copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG); bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits, copy_words, nwords); } /* * Copy all file descriptors from the old table to the new, expanded table and * clear the extra space. Called with the files spinlock held for write. */ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt) { size_t cpy, set; BUG_ON(nfdt->max_fds < ofdt->max_fds); cpy = ofdt->max_fds * sizeof(struct file *); set = (nfdt->max_fds - ofdt->max_fds) * sizeof(struct file *); memcpy(nfdt->fd, ofdt->fd, cpy); memset((char *)nfdt->fd + cpy, 0, set); copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt)); } /* * Note how the fdtable bitmap allocations very much have to be a multiple of * BITS_PER_LONG. This is not only because we walk those things in chunks of * 'unsigned long' in some places, but simply because that is how the Linux * kernel bitmaps are defined to work: they are not "bits in an array of bytes", * they are very much "bits in an array of unsigned long". */ static struct fdtable *alloc_fdtable(unsigned int slots_wanted) { struct fdtable *fdt; unsigned int nr; void *data; /* * Figure out how many fds we actually want to support in this fdtable. * Allocation steps are keyed to the size of the fdarray, since it * grows far faster than any of the other dynamic data. We try to fit * the fdarray into comfortable page-tuned chunks: starting at 1024B * and growing in powers of two from there on. Since we called only * with slots_wanted > BITS_PER_LONG (embedded instance in files->fdtab * already gives BITS_PER_LONG slots), the above boils down to * 1. use the smallest power of two large enough to give us that many * slots. * 2. on 32bit skip 64 and 128 - the minimal capacity we want there is * 256 slots (i.e. 1Kb fd array). * 3. on 64bit don't skip anything, 1Kb fd array means 128 slots there * and we are never going to be asked for 64 or less. */ if (IS_ENABLED(CONFIG_32BIT) && slots_wanted < 256) nr = 256; else nr = roundup_pow_of_two(slots_wanted); /* * Note that this can drive nr *below* what we had passed if sysctl_nr_open * had been set lower between the check in expand_files() and here. * * We make sure that nr remains a multiple of BITS_PER_LONG - otherwise * bitmaps handling below becomes unpleasant, to put it mildly... */ if (unlikely(nr > sysctl_nr_open)) { nr = round_down(sysctl_nr_open, BITS_PER_LONG); if (nr < slots_wanted) return ERR_PTR(-EMFILE); } /* * Check if the allocation size would exceed INT_MAX. kvmalloc_array() * and kvmalloc() will warn if the allocation size is greater than * INT_MAX, as filp_cache objects are not __GFP_NOWARN. * * This can happen when sysctl_nr_open is set to a very high value and * a process tries to use a file descriptor near that limit. For example, * if sysctl_nr_open is set to 1073741816 (0x3ffffff8) - which is what * systemd typically sets it to - then trying to use a file descriptor * close to that value will require allocating a file descriptor table * that exceeds 8GB in size. */ if (unlikely(nr > INT_MAX / sizeof(struct file *))) return ERR_PTR(-EMFILE); fdt = kmalloc_obj(struct fdtable, GFP_KERNEL_ACCOUNT); if (!fdt) goto out; fdt->max_fds = nr; data = kvmalloc_objs(struct file *, nr, GFP_KERNEL_ACCOUNT); if (!data) goto out_fdt; fdt->fd = data; data = kvmalloc(max_t(size_t, 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES), GFP_KERNEL_ACCOUNT); if (!data) goto out_arr; fdt->open_fds = data; data += nr / BITS_PER_BYTE; fdt->close_on_exec = data; data += nr / BITS_PER_BYTE; fdt->full_fds_bits = data; return fdt; out_arr: kvfree(fdt->fd); out_fdt: kfree(fdt); out: return ERR_PTR(-ENOMEM); } /* * Expand the file descriptor table. * This function will allocate a new fdtable and both fd array and fdset, of * the given size. * Return <0 error code on error; 0 on successful completion. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_fdtable(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *new_fdt, *cur_fdt; spin_unlock(&files->file_lock); new_fdt = alloc_fdtable(nr + 1); /* make sure all fd_install() have seen resize_in_progress * or have finished their rcu_read_lock_sched() section. */ if (atomic_read(&files->count) > 1) synchronize_rcu(); spin_lock(&files->file_lock); if (IS_ERR(new_fdt)) return PTR_ERR(new_fdt); cur_fdt = files_fdtable(files); BUG_ON(nr < cur_fdt->max_fds); copy_fdtable(new_fdt, cur_fdt); rcu_assign_pointer(files->fdt, new_fdt); if (cur_fdt != &files->fdtab) call_rcu(&cur_fdt->rcu, free_fdtable_rcu); /* coupled with smp_rmb() in fd_install() */ smp_wmb(); return 0; } /* * Expand files. * This function will expand the file structures, if the requested size exceeds * the current capacity and there is room for expansion. * Return <0 error code on error; 0 on success. * The files->file_lock should be held on entry, and will be held on exit. */ static int expand_files(struct files_struct *files, unsigned int nr) __releases(files->file_lock) __acquires(files->file_lock) { struct fdtable *fdt; int error; repeat: fdt = files_fdtable(files); /* Do we need to expand? */ if (nr < fdt->max_fds) return 0; if (unlikely(files->resize_in_progress)) { spin_unlock(&files->file_lock); wait_event(files->resize_wait, !files->resize_in_progress); spin_lock(&files->file_lock); goto repeat; } /* Can we expand? */ if (unlikely(nr >= sysctl_nr_open)) return -EMFILE; /* All good, so we try */ files->resize_in_progress = true; error = expand_fdtable(files, nr); files->resize_in_progress = false; wake_up_all(&files->resize_wait); return error; } static inline void __set_close_on_exec(unsigned int fd, struct fdtable *fdt, bool set) { if (set) { __set_bit(fd, fdt->close_on_exec); } else { if (test_bit(fd, fdt->close_on_exec)) __clear_bit(fd, fdt->close_on_exec); } } static inline void __set_open_fd(unsigned int fd, struct fdtable *fdt, bool set) { __set_bit(fd, fdt->open_fds); __set_close_on_exec(fd, fdt, set); fd /= BITS_PER_LONG; if (!~fdt->open_fds[fd]) __set_bit(fd, fdt->full_fds_bits); } static inline void __clear_open_fd(unsigned int fd, struct fdtable *fdt) { __clear_bit(fd, fdt->open_fds); fd /= BITS_PER_LONG; if (test_bit(fd, fdt->full_fds_bits)) __clear_bit(fd, fdt->full_fds_bits); } static inline bool fd_is_open(unsigned int fd, const struct fdtable *fdt) { return test_bit(fd, fdt->open_fds); } /* * Note that a sane fdtable size always has to be a multiple of * BITS_PER_LONG, since we have bitmaps that are sized by this. * * punch_hole is optional - when close_range() is asked to unshare * and close, we don't need to copy descriptors in that range, so * a smaller cloned descriptor table might suffice if the last * currently opened descriptor falls into that range. */ static unsigned int sane_fdtable_size(struct fdtable *fdt, struct fd_range *punch_hole) { unsigned int last = find_last_bit(fdt->open_fds, fdt->max_fds); if (last == fdt->max_fds) return NR_OPEN_DEFAULT; if (punch_hole && punch_hole->to >= last && punch_hole->from <= last) { last = find_last_bit(fdt->open_fds, punch_hole->from); if (last == punch_hole->from) return NR_OPEN_DEFAULT; } return ALIGN(last + 1, BITS_PER_LONG); } /* * Allocate a new descriptor table and copy contents from the passed in * instance. Returns a pointer to cloned table on success, ERR_PTR() * on failure. For 'punch_hole' see sane_fdtable_size(). */ struct files_struct *dup_fd(struct files_struct *oldf, struct fd_range *punch_hole) { struct files_struct *newf; struct file **old_fds, **new_fds; unsigned int open_files, i; struct fdtable *old_fdt, *new_fdt; newf = kmem_cache_alloc(files_cachep, GFP_KERNEL); if (!newf) return ERR_PTR(-ENOMEM); atomic_set(&newf->count, 1); spin_lock_init(&newf->file_lock); newf->resize_in_progress = false; init_waitqueue_head(&newf->resize_wait); newf->next_fd = 0; new_fdt = &newf->fdtab; new_fdt->max_fds = NR_OPEN_DEFAULT; new_fdt->close_on_exec = newf->close_on_exec_init; new_fdt->open_fds = newf->open_fds_init; new_fdt->full_fds_bits = newf->full_fds_bits_init; new_fdt->fd = &newf->fd_array[0]; spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); /* * Check whether we need to allocate a larger fd array and fd set. */ while (unlikely(open_files > new_fdt->max_fds)) { spin_unlock(&oldf->file_lock); if (new_fdt != &newf->fdtab) __free_fdtable(new_fdt); new_fdt = alloc_fdtable(open_files); if (IS_ERR(new_fdt)) { kmem_cache_free(files_cachep, newf); return ERR_CAST(new_fdt); } /* * Reacquire the oldf lock and a pointer to its fd table * who knows it may have a new bigger fd table. We need * the latest pointer. */ spin_lock(&oldf->file_lock); old_fdt = files_fdtable(oldf); open_files = sane_fdtable_size(old_fdt, punch_hole); } copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG); old_fds = old_fdt->fd; new_fds = new_fdt->fd; /* * We may be racing against fd allocation from other threads using this * files_struct, despite holding ->file_lock. * * alloc_fd() might have already claimed a slot, while fd_install() * did not populate it yet. Note the latter operates locklessly, so * the file can show up as we are walking the array below. * * At the same time we know no files will disappear as all other * operations take the lock. * * Instead of trying to placate userspace racing with itself, we * ref the file if we see it and mark the fd slot as unused otherwise. */ for (i = open_files; i != 0; i--) { struct file *f = rcu_dereference_raw(*old_fds++); if (f) { get_file(f); } else { __clear_open_fd(open_files - i, new_fdt); } rcu_assign_pointer(*new_fds++, f); } spin_unlock(&oldf->file_lock); /* clear the remainder */ memset(new_fds, 0, (new_fdt->max_fds - open_files) * sizeof(struct file *)); rcu_assign_pointer(newf->fdt, new_fdt); return newf; } static struct fdtable *close_files(struct files_struct * files) { /* * It is safe to dereference the fd table without RCU or * ->file_lock because this is the last reference to the * files structure. */ struct fdtable *fdt = rcu_dereference_raw(files->fdt); unsigned int i, j = 0; for (;;) { unsigned long set; i = j * BITS_PER_LONG; if (i >= fdt->max_fds) break; set = fdt->open_fds[j++]; while (set) { if (set & 1) { struct file *file = fdt->fd[i]; if (file) { filp_close(file, files); cond_resched(); } } i++; set >>= 1; } } return fdt; } void put_files_struct(struct files_struct *files) { if (atomic_dec_and_test(&files->count)) { struct fdtable *fdt = close_files(files); /* free the arrays if they are not embedded */ if (fdt != &files->fdtab) __free_fdtable(fdt); kmem_cache_free(files_cachep, files); } } void exit_files(struct task_struct *tsk) { struct files_struct * files = tsk->files; if (files) { task_lock(tsk); tsk->files = NULL; task_unlock(tsk); put_files_struct(files); } } struct files_struct init_files = { .count = ATOMIC_INIT(1), .fdt = &init_files.fdtab, .fdtab = { .max_fds = NR_OPEN_DEFAULT, .fd = &init_files.fd_array[0], .close_on_exec = init_files.close_on_exec_init, .open_fds = init_files.open_fds_init, .full_fds_bits = init_files.full_fds_bits_init, }, .file_lock = __SPIN_LOCK_UNLOCKED(init_files.file_lock), .resize_wait = __WAIT_QUEUE_HEAD_INITIALIZER(init_files.resize_wait), }; static unsigned int find_next_fd(struct fdtable *fdt, unsigned int start) { unsigned int maxfd = fdt->max_fds; /* always multiple of BITS_PER_LONG */ unsigned int max_fds_words = maxfd / BITS_PER_LONG; unsigned int fds_word_idx = start / BITS_PER_LONG; unsigned int bit; /* * Try to avoid looking at the second level bitmap */ bit = find_next_zero_bit(&fdt->open_fds[fds_word_idx], BITS_PER_LONG, start & (BITS_PER_LONG - 1)); if (bit < BITS_PER_LONG) return bit + (fds_word_idx * BITS_PER_LONG); bit = BITS_PER_LONG * find_next_zero_bit(fdt->full_fds_bits, max_fds_words, fds_word_idx + 1); if (bit >= maxfd) return maxfd; return find_next_zero_bit(fdt->open_fds, maxfd, bit); } /* * allocate a file descriptor, mark it busy. */ static int alloc_fd(unsigned start, unsigned end, unsigned flags) { struct files_struct *files = current->files; unsigned int fd; int error; struct fdtable *fdt; spin_lock(&files->file_lock); repeat: fdt = files_fdtable(files); fd = start; if (fd < files->next_fd) fd = files->next_fd; if (likely(fd < fdt->max_fds)) fd = find_next_fd(fdt, fd); /* * N.B. For clone tasks sharing a files structure, this test * will limit the total number of files that can be opened. */ error = -EMFILE; if (unlikely(fd >= end)) goto out; if (unlikely(fd >= fdt->max_fds)) { error = expand_files(files, fd); if (error < 0) goto out; goto repeat; } if (start <= files->next_fd) files->next_fd = fd + 1; __set_open_fd(fd, fdt, flags & O_CLOEXEC); error = fd; VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); out: spin_unlock(&files->file_lock); return error; } int __get_unused_fd_flags(unsigned flags, unsigned long nofile) { return alloc_fd(0, nofile, flags); } int get_unused_fd_flags(unsigned flags) { return __get_unused_fd_flags(flags, rlimit(RLIMIT_NOFILE)); } EXPORT_SYMBOL(get_unused_fd_flags); static void __put_unused_fd(struct files_struct *files, unsigned int fd) { struct fdtable *fdt = files_fdtable(files); __clear_open_fd(fd, fdt); if (fd < files->next_fd) files->next_fd = fd; } void put_unused_fd(unsigned int fd) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); } EXPORT_SYMBOL(put_unused_fd); /* * Install a file pointer in the fd array while it is being resized. * * We need to make sure our update to the array does not get lost as the resizing * thread can be copying the content as we modify it. * * We have two ways to do it: * - go off CPU waiting for resize_in_progress to clear * - take the spin lock * * The latter is trivial to implement and saves us from having to might_sleep() * for debugging purposes. * * This is moved out of line from fd_install() to convince gcc to optimize that * routine better. */ static void noinline fd_install_slowpath(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; spin_lock(&files->file_lock); fdt = files_fdtable(files); VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); rcu_assign_pointer(fdt->fd[fd], file); spin_unlock(&files->file_lock); } /** * fd_install - install a file pointer in the fd array * @fd: file descriptor to install the file in * @file: the file to install * * This consumes the "file" refcount, so callers should treat it * as if they had called fput(file). */ void fd_install(unsigned int fd, struct file *file) { struct files_struct *files = current->files; struct fdtable *fdt; if (WARN_ON_ONCE(unlikely(file->f_mode & FMODE_BACKING))) return; rcu_read_lock_sched(); if (unlikely(files->resize_in_progress)) { rcu_read_unlock_sched(); fd_install_slowpath(fd, file); return; } /* coupled with smp_wmb() in expand_fdtable() */ smp_rmb(); fdt = rcu_dereference_sched(files->fdt); VFS_BUG_ON(rcu_access_pointer(fdt->fd[fd]) != NULL); rcu_assign_pointer(fdt->fd[fd], file); rcu_read_unlock_sched(); } EXPORT_SYMBOL(fd_install); /** * file_close_fd_locked - return file associated with fd * @files: file struct to retrieve file from * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Context: files_lock must be held. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd_locked(struct files_struct *files, unsigned fd) { struct fdtable *fdt = files_fdtable(files); struct file *file; lockdep_assert_held(&files->file_lock); if (fd >= fdt->max_fds) return NULL; fd = array_index_nospec(fd, fdt->max_fds); file = rcu_dereference_raw(fdt->fd[fd]); if (file) { rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); } return file; } int close_fd(unsigned fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); if (!file) return -EBADF; return filp_close(file, files); } EXPORT_SYMBOL(close_fd); /** * last_fd - return last valid index into fd table * @fdt: File descriptor table. * * Context: Either rcu read lock or files_lock must be held. * * Returns: Last valid index into fdtable. */ static inline unsigned last_fd(struct fdtable *fdt) { return fdt->max_fds - 1; } static inline void __range_cloexec(struct files_struct *cur_fds, unsigned int fd, unsigned int max_fd) { struct fdtable *fdt; /* make sure we're using the correct maximum value */ spin_lock(&cur_fds->file_lock); fdt = files_fdtable(cur_fds); max_fd = min(last_fd(fdt), max_fd); if (fd <= max_fd) bitmap_set(fdt->close_on_exec, fd, max_fd - fd + 1); spin_unlock(&cur_fds->file_lock); } static inline void __range_close(struct files_struct *files, unsigned int fd, unsigned int max_fd) { struct file *file; struct fdtable *fdt; unsigned n; spin_lock(&files->file_lock); fdt = files_fdtable(files); n = last_fd(fdt); max_fd = min(max_fd, n); for (fd = find_next_bit(fdt->open_fds, max_fd + 1, fd); fd <= max_fd; fd = find_next_bit(fdt->open_fds, max_fd + 1, fd + 1)) { file = file_close_fd_locked(files, fd); if (file) { spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); } else if (need_resched()) { spin_unlock(&files->file_lock); cond_resched(); spin_lock(&files->file_lock); fdt = files_fdtable(files); } } spin_unlock(&files->file_lock); } /** * sys_close_range() - Close all file descriptors in a given range. * * @fd: starting file descriptor to close * @max_fd: last file descriptor to close * @flags: CLOSE_RANGE flags. * * This closes a range of file descriptors. All file descriptors * from @fd up to and including @max_fd are closed. * Currently, errors to close a given file descriptor are ignored. */ SYSCALL_DEFINE3(close_range, unsigned int, fd, unsigned int, max_fd, unsigned int, flags) { struct task_struct *me = current; struct files_struct *cur_fds = me->files, *fds = NULL; if (flags & ~(CLOSE_RANGE_UNSHARE | CLOSE_RANGE_CLOEXEC)) return -EINVAL; if (fd > max_fd) return -EINVAL; if ((flags & CLOSE_RANGE_UNSHARE) && atomic_read(&cur_fds->count) > 1) { struct fd_range range = {fd, max_fd}, *punch_hole = ⦥ /* * If the caller requested all fds to be made cloexec we always * copy all of the file descriptors since they still want to * use them. */ if (flags & CLOSE_RANGE_CLOEXEC) punch_hole = NULL; fds = dup_fd(cur_fds, punch_hole); if (IS_ERR(fds)) return PTR_ERR(fds); /* * We used to share our file descriptor table, and have now * created a private one, make sure we're using it below. */ swap(cur_fds, fds); } if (flags & CLOSE_RANGE_CLOEXEC) __range_cloexec(cur_fds, fd, max_fd); else __range_close(cur_fds, fd, max_fd); if (fds) { /* * We're done closing the files we were supposed to. Time to install * the new file descriptor table and drop the old one. */ task_lock(me); me->files = cur_fds; task_unlock(me); put_files_struct(fds); } return 0; } /** * file_close_fd - return file associated with fd * @fd: file descriptor to retrieve file for * * Doesn't take a separate reference count. * * Returns: The file associated with @fd (NULL if @fd is not open) */ struct file *file_close_fd(unsigned int fd) { struct files_struct *files = current->files; struct file *file; spin_lock(&files->file_lock); file = file_close_fd_locked(files, fd); spin_unlock(&files->file_lock); return file; } void do_close_on_exec(struct files_struct *files) { unsigned i; struct fdtable *fdt; /* exec unshares first */ spin_lock(&files->file_lock); for (i = 0; ; i++) { unsigned long set; unsigned fd = i * BITS_PER_LONG; fdt = files_fdtable(files); if (fd >= fdt->max_fds) break; set = fdt->close_on_exec[i]; if (!set) continue; fdt->close_on_exec[i] = 0; for ( ; set ; fd++, set >>= 1) { struct file *file; if (!(set & 1)) continue; file = fdt->fd[fd]; if (!file) continue; rcu_assign_pointer(fdt->fd[fd], NULL); __put_unused_fd(files, fd); spin_unlock(&files->file_lock); filp_close(file, files); cond_resched(); spin_lock(&files->file_lock); } } spin_unlock(&files->file_lock); } static struct file *__get_file_rcu(struct file __rcu **f) { struct file __rcu *file; struct file __rcu *file_reloaded; struct file __rcu *file_reloaded_cmp; file = rcu_dereference_raw(*f); if (!file) return NULL; if (unlikely(!file_ref_get(&file->f_ref))) return ERR_PTR(-EAGAIN); file_reloaded = rcu_dereference_raw(*f); /* * Ensure that all accesses have a dependency on the load from * rcu_dereference_raw() above so we get correct ordering * between reuse/allocation and the pointer check below. */ file_reloaded_cmp = file_reloaded; OPTIMIZER_HIDE_VAR(file_reloaded_cmp); /* * file_ref_get() above provided a full memory barrier when we * acquired a reference. * * This is paired with the write barrier from assigning to the * __rcu protected file pointer so that if that pointer still * matches the current file, we know we have successfully * acquired a reference to the right file. * * If the pointers don't match the file has been reallocated by * SLAB_TYPESAFE_BY_RCU. */ if (file == file_reloaded_cmp) return file_reloaded; fput(file); return ERR_PTR(-EAGAIN); } /** * get_file_rcu - try go get a reference to a file under rcu * @f: the file to get a reference on * * This function tries to get a reference on @f carefully verifying that * @f hasn't been reused. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_rcu(struct file __rcu **f) { for (;;) { struct file __rcu *file; file = __get_file_rcu(f); if (!IS_ERR(file)) return file; } } EXPORT_SYMBOL_GPL(get_file_rcu); /** * get_file_active - try go get a reference to a file * @f: the file to get a reference on * * In contast to get_file_rcu() the pointer itself isn't part of the * reference counting. * * This function should rarely have to be used and only by users who * understand the implications of SLAB_TYPESAFE_BY_RCU. Try to avoid it. * * Return: Returns @f with the reference count increased or NULL. */ struct file *get_file_active(struct file **f) { struct file __rcu *file; rcu_read_lock(); file = __get_file_rcu(f); rcu_read_unlock(); if (IS_ERR(file)) file = NULL; return file; } EXPORT_SYMBOL_GPL(get_file_active); static inline struct file *__fget_files_rcu(struct files_struct *files, unsigned int fd, fmode_t mask) { for (;;) { struct file *file; struct fdtable *fdt = rcu_dereference_raw(files->fdt); struct file __rcu **fdentry; unsigned long nospec_mask; /* Mask is a 0 for invalid fd's, ~0 for valid ones */ nospec_mask = array_index_mask_nospec(fd, fdt->max_fds); /* * fdentry points to the 'fd' offset, or fdt->fd[0]. * Loading from fdt->fd[0] is always safe, because the * array always exists. */ fdentry = fdt->fd + (fd & nospec_mask); /* Do the load, then mask any invalid result */ file = rcu_dereference_raw(*fdentry); file = (void *)(nospec_mask & (unsigned long)file); if (unlikely(!file)) return NULL; /* * Ok, we have a file pointer that was valid at * some point, but it might have become stale since. * * We need to confirm it by incrementing the refcount * and then check the lookup again. * * file_ref_get() gives us a full memory barrier. We * only really need an 'acquire' one to protect the * loads below, but we don't have that. */ if (unlikely(!file_ref_get(&file->f_ref))) continue; /* * Such a race can take two forms: * * (a) the file ref already went down to zero and the * file hasn't been reused yet or the file count * isn't zero but the file has already been reused. * * (b) the file table entry has changed under us. * Note that we don't need to re-check the 'fdt->fd' * pointer having changed, because it always goes * hand-in-hand with 'fdt'. * * If so, we need to put our ref and try again. */ if (unlikely(file != rcu_dereference_raw(*fdentry)) || unlikely(rcu_dereference_raw(files->fdt) != fdt)) { fput(file); continue; } /* * This isn't the file we're looking for or we're not * allowed to get a reference to it. */ if (unlikely(file->f_mode & mask)) { fput(file); return NULL; } /* * Ok, we have a ref to the file, and checked that it * still exists. */ return file; } } static struct file *__fget_files(struct files_struct *files, unsigned int fd, fmode_t mask) { struct file *file; rcu_read_lock(); file = __fget_files_rcu(files, fd, mask); rcu_read_unlock(); return file; } static inline struct file *__fget(unsigned int fd, fmode_t mask) { return __fget_files(current->files, fd, mask); } struct file *fget(unsigned int fd) { return __fget(fd, FMODE_PATH); } EXPORT_SYMBOL(fget); struct file *fget_raw(unsigned int fd) { return __fget(fd, 0); } EXPORT_SYMBOL(fget_raw); struct file *fget_task(struct task_struct *task, unsigned int fd) { struct file *file = NULL; task_lock(task); if (task->files) file = __fget_files(task->files, fd, 0); task_unlock(task); return file; } struct file *fget_task_next(struct task_struct *task, unsigned int *ret_fd) { struct files_struct *files; unsigned int fd = *ret_fd; struct file *file = NULL; task_lock(task); files = task->files; if (files) { rcu_read_lock(); for (; fd < files_fdtable(files)->max_fds; fd++) { file = __fget_files_rcu(files, fd, 0); if (file) break; } rcu_read_unlock(); } task_unlock(task); *ret_fd = fd; return file; } EXPORT_SYMBOL(fget_task_next); /* * Lightweight file lookup - no refcnt increment if fd table isn't shared. * * You can use this instead of fget if you satisfy all of the following * conditions: * 1) You must call fput_light before exiting the syscall and returning control * to userspace (i.e. you cannot remember the returned struct file * after * returning to userspace). * 2) You must not call filp_close on the returned struct file * in between * calls to fget_light and fput_light. * 3) You must not clone the current task in between the calls to fget_light * and fput_light. * * The fput_needed flag returned by fget_light should be passed to the * corresponding fput_light. * * (As an exception to rule 2, you can call filp_close between fget_light and * fput_light provided that you capture a real refcount with get_file before * the call to filp_close, and ensure that this real refcount is fput *after* * the fput_light call.) * * See also the documentation in rust/kernel/file.rs. */ static inline struct fd __fget_light(unsigned int fd, fmode_t mask) { struct files_struct *files = current->files; struct file *file; /* * If another thread is concurrently calling close_fd() followed * by put_files_struct(), we must not observe the old table * entry combined with the new refcount - otherwise we could * return a file that is concurrently being freed. * * atomic_read_acquire() pairs with atomic_dec_and_test() in * put_files_struct(). */ if (likely(atomic_read_acquire(&files->count) == 1)) { file = files_lookup_fd_raw(files, fd); if (!file || unlikely(file->f_mode & mask)) return EMPTY_FD; return BORROWED_FD(file); } else { file = __fget_files(files, fd, mask); if (!file) return EMPTY_FD; return CLONED_FD(file); } } struct fd fdget(unsigned int fd) { return __fget_light(fd, FMODE_PATH); } EXPORT_SYMBOL(fdget); struct fd fdget_raw(unsigned int fd) { return __fget_light(fd, 0); } /* * Try to avoid f_pos locking. We only need it if the * file is marked for FMODE_ATOMIC_POS, and it can be * accessed multiple ways. * * Always do it for directories, because pidfd_getfd() * can make a file accessible even if it otherwise would * not be, and for directories this is a correctness * issue, not a "POSIX requirement". */ static inline bool file_needs_f_pos_lock(struct file *file) { if (!(file->f_mode & FMODE_ATOMIC_POS)) return false; if (__file_ref_read_raw(&file->f_ref) != FILE_REF_ONEREF) return true; if (file->f_op->iterate_shared) return true; return false; } bool file_seek_cur_needs_f_lock(struct file *file) { if (!(file->f_mode & FMODE_ATOMIC_POS) && !file->f_op->iterate_shared) return false; /* * Note that we are not guaranteed to be called after fdget_pos() on * this file obj, in which case the caller is expected to provide the * appropriate locking. */ return true; } struct fd fdget_pos(unsigned int fd) { struct fd f = fdget(fd); struct file *file = fd_file(f); if (likely(file) && file_needs_f_pos_lock(file)) { f.word |= FDPUT_POS_UNLOCK; mutex_lock(&file->f_pos_lock); } return f; } void __f_unlock_pos(struct file *f) { mutex_unlock(&f->f_pos_lock); } /* * We only lock f_pos if we have threads or if the file might be * shared with another process. In both cases we'll have an elevated * file count (done either by fdget() or by fork()). */ void set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; spin_lock(&files->file_lock); __set_close_on_exec(fd, files_fdtable(files), flag); spin_unlock(&files->file_lock); } bool get_close_on_exec(unsigned int fd) { bool res; rcu_read_lock(); res = close_on_exec(fd, current->files); rcu_read_unlock(); return res; } static int do_dup2(struct files_struct *files, struct file *file, unsigned fd, unsigned flags) __releases(&files->file_lock) { struct file *tofree; struct fdtable *fdt; /* * dup2() is expected to close the file installed in the target fd slot * (if any). However, userspace hand-picking a fd may be racing against * its own threads which happened to allocate it in open() et al but did * not populate it yet. * * Broadly speaking we may be racing against the following: * fd = get_unused_fd_flags(); // fd slot reserved, ->fd[fd] == NULL * file = hard_work_goes_here(); * fd_install(fd, file); // only now ->fd[fd] == file * * It is an invariant that a successfully allocated fd has a NULL entry * in the array until the matching fd_install(). * * If we fit the window, we have the fd to populate, yet no target file * to close. Trying to ignore it and install our new file would violate * the invariant and make fd_install() overwrite our file. * * Things can be done(tm) to handle this. However, the issue does not * concern legitimate programs and we only need to make sure the kernel * does not trip over it. * * The simplest way out is to return an error if we find ourselves here. * * POSIX is silent on the issue, we return -EBUSY. */ fdt = files_fdtable(files); fd = array_index_nospec(fd, fdt->max_fds); tofree = rcu_dereference_raw(fdt->fd[fd]); if (!tofree && fd_is_open(fd, fdt)) goto Ebusy; get_file(file); rcu_assign_pointer(fdt->fd[fd], file); __set_open_fd(fd, fdt, flags & O_CLOEXEC); spin_unlock(&files->file_lock); if (tofree) filp_close(tofree, files); return fd; Ebusy: spin_unlock(&files->file_lock); return -EBUSY; } int replace_fd(unsigned fd, struct file *file, unsigned flags) { int err; struct files_struct *files = current->files; if (!file) return close_fd(fd); if (fd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, fd); if (unlikely(err < 0)) goto out_unlock; err = do_dup2(files, file, fd, flags); if (err < 0) return err; return 0; out_unlock: spin_unlock(&files->file_lock); return err; } /** * receive_fd() - Install received file into file descriptor table * @file: struct file that was received from another process * @ufd: __user pointer to write new fd number to * @o_flags: the O_* flags to apply to the new fd entry * * Installs a received file into the file descriptor table, with appropriate * checks and count updates. Optionally writes the fd number to userspace, if * @ufd is non-NULL. * * This helper handles its own reference counting of the incoming * struct file. * * Returns newly install fd or -ve on error. */ int receive_fd(struct file *file, int __user *ufd, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; FD_PREPARE(fdf, o_flags, file); if (fdf.err) return fdf.err; get_file(file); if (ufd) { error = put_user(fd_prepare_fd(fdf), ufd); if (error) return error; } __receive_sock(fd_prepare_file(fdf)); return fd_publish(fdf); } EXPORT_SYMBOL_GPL(receive_fd); int receive_fd_replace(int new_fd, struct file *file, unsigned int o_flags) { int error; error = security_file_receive(file); if (error) return error; error = replace_fd(new_fd, file, o_flags); if (error) return error; __receive_sock(file); return new_fd; } static int ksys_dup3(unsigned int oldfd, unsigned int newfd, int flags) { int err = -EBADF; struct file *file; struct files_struct *files = current->files; if ((flags & ~O_CLOEXEC) != 0) return -EINVAL; if (unlikely(oldfd == newfd)) return -EINVAL; if (newfd >= rlimit(RLIMIT_NOFILE)) return -EBADF; spin_lock(&files->file_lock); err = expand_files(files, newfd); file = files_lookup_fd_locked(files, oldfd); if (unlikely(!file)) goto Ebadf; if (unlikely(err < 0)) { if (err == -EMFILE) goto Ebadf; goto out_unlock; } return do_dup2(files, file, newfd, flags); Ebadf: err = -EBADF; out_unlock: spin_unlock(&files->file_lock); return err; } SYSCALL_DEFINE3(dup3, unsigned int, oldfd, unsigned int, newfd, int, flags) { return ksys_dup3(oldfd, newfd, flags); } SYSCALL_DEFINE2(dup2, unsigned int, oldfd, unsigned int, newfd) { if (unlikely(newfd == oldfd)) { /* corner case */ struct files_struct *files = current->files; struct file *f; int retval = oldfd; rcu_read_lock(); f = __fget_files_rcu(files, oldfd, 0); if (!f) retval = -EBADF; rcu_read_unlock(); if (f) fput(f); return retval; } return ksys_dup3(oldfd, newfd, 0); } SYSCALL_DEFINE1(dup, unsigned int, fildes) { int ret = -EBADF; struct file *file = fget_raw(fildes); if (file) { ret = get_unused_fd_flags(0); if (ret >= 0) fd_install(ret, file); else fput(file); } return ret; } int f_dupfd(unsigned int from, struct file *file, unsigned flags) { unsigned long nofile = rlimit(RLIMIT_NOFILE); int err; if (from >= nofile) return -EINVAL; err = alloc_fd(from, nofile, flags); if (err >= 0) { get_file(file); fd_install(err, file); } return err; } int iterate_fd(struct files_struct *files, unsigned n, int (*f)(const void *, struct file *, unsigned), const void *p) { struct fdtable *fdt; int res = 0; if (!files) return 0; spin_lock(&files->file_lock); for (fdt = files_fdtable(files); n < fdt->max_fds; n++) { struct file *file; file = rcu_dereference_check_fdtable(files, fdt->fd[n]); if (!file) continue; res = f(p, file, n); if (res) break; } spin_unlock(&files->file_lock); return res; } EXPORT_SYMBOL(iterate_fd); |
| 6 6 6 6 2 2 2 1 2 2 9 9 9 10 9 1 9 9 10 6 6 2 6 6 6 5 6 5 6 6 1 1 2 2 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 2 2 2 2 2 2 2 1 1 1 2 2 2 1 2 2 2 2 2 2 2 1 1 2 1 1 2 2 2 2 2 2 2 2 2 2 2 1 1 2 1 16 2 1 1 1 6 6 6 1 6 1 1 6 6 5 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 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright (c) 2003-2006, Cluster File Systems, Inc, info@clusterfs.com * Written by Alex Tomas <alex@clusterfs.com> * * Architecture independence: * Copyright (c) 2005, Bull S.A. * Written by Pierre Peiffer <pierre.peiffer@bull.net> */ /* * Extents support for EXT4 * * TODO: * - ext4*_error() should be used in some situations * - analyze all BUG()/BUG_ON(), use -EIO where appropriate * - smart tree reduction */ #include <linux/fs.h> #include <linux/time.h> #include <linux/jbd2.h> #include <linux/highuid.h> #include <linux/pagemap.h> #include <linux/quotaops.h> #include <linux/string.h> #include <linux/slab.h> #include <linux/uaccess.h> #include <linux/fiemap.h> #include <linux/iomap.h> #include <linux/sched/mm.h> #include "ext4_jbd2.h" #include "ext4_extents.h" #include "xattr.h" #include <kunit/static_stub.h> #include <trace/events/ext4.h> /* * used by extent splitting. */ #define EXT4_EXT_MAY_ZEROOUT 0x1 /* safe to zeroout if split fails \ due to ENOSPC */ static struct ext4_ext_path *ext4_split_convert_extents( handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated); static __le32 ext4_extent_block_csum(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_inode_info *ei = EXT4_I(inode); __u32 csum; csum = ext4_chksum(ei->i_csum_seed, (__u8 *)eh, EXT4_EXTENT_TAIL_OFFSET(eh)); return cpu_to_le32(csum); } static int ext4_extent_block_csum_verify(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_feature_metadata_csum(inode->i_sb)) return 1; et = find_ext4_extent_tail(eh); if (et->et_checksum != ext4_extent_block_csum(inode, eh)) return 0; return 1; } static void ext4_extent_block_csum_set(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent_tail *et; if (!ext4_has_feature_metadata_csum(inode->i_sb)) return; et = find_ext4_extent_tail(eh); et->et_checksum = ext4_extent_block_csum(inode, eh); } static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t split, int flags); static int ext4_ext_trunc_restart_fn(struct inode *inode, int *dropped) { /* * Drop i_data_sem to avoid deadlock with ext4_map_blocks. At this * moment, get_block can be called only for blocks inside i_size since * page cache has been already dropped and writes are blocked by * i_rwsem. So we can safely drop the i_data_sem here. */ BUG_ON(EXT4_JOURNAL(inode) == NULL); ext4_discard_preallocations(inode); up_write(&EXT4_I(inode)->i_data_sem); *dropped = 1; return 0; } static inline void ext4_ext_path_brelse(struct ext4_ext_path *path) { brelse(path->p_bh); path->p_bh = NULL; } static void ext4_ext_drop_refs(struct ext4_ext_path *path) { int depth, i; if (IS_ERR_OR_NULL(path)) return; depth = path->p_depth; for (i = 0; i <= depth; i++, path++) ext4_ext_path_brelse(path); } void ext4_free_ext_path(struct ext4_ext_path *path) { if (IS_ERR_OR_NULL(path)) return; ext4_ext_drop_refs(path); kfree(path); } /* * Make sure 'handle' has at least 'check_cred' credits. If not, restart * transaction with 'restart_cred' credits. The function drops i_data_sem * when restarting transaction and gets it after transaction is restarted. * * The function returns 0 on success, 1 if transaction had to be restarted, * and < 0 in case of fatal error. */ int ext4_datasem_ensure_credits(handle_t *handle, struct inode *inode, int check_cred, int restart_cred, int revoke_cred) { int ret; int dropped = 0; ret = ext4_journal_ensure_credits_fn(handle, check_cred, restart_cred, revoke_cred, ext4_ext_trunc_restart_fn(inode, &dropped)); if (dropped) down_write(&EXT4_I(inode)->i_data_sem); return ret; } /* * could return: * - EROFS * - ENOMEM */ static int ext4_ext_get_access(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err = 0; if (path->p_bh) { /* path points to block */ BUFFER_TRACE(path->p_bh, "get_write_access"); err = ext4_journal_get_write_access(handle, inode->i_sb, path->p_bh, EXT4_JTR_NONE); /* * The extent buffer's verified bit will be set again in * __ext4_ext_dirty(). We could leave an inconsistent * buffer if the extents updating procudure break off du * to some error happens, force to check it again. */ if (!err) clear_buffer_verified(path->p_bh); } /* path points to leaf/index in inode body */ /* we use in-core data, no need to protect them */ return err; } /* * could return: * - EROFS * - ENOMEM * - EIO */ int __ext4_ext_dirty(const char *where, unsigned int line, handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { int err; KUNIT_STATIC_STUB_REDIRECT(__ext4_ext_dirty, where, line, handle, inode, path); WARN_ON(!rwsem_is_locked(&EXT4_I(inode)->i_data_sem)); if (path->p_bh) { ext4_extent_block_csum_set(inode, ext_block_hdr(path->p_bh)); /* path points to block */ err = __ext4_handle_dirty_metadata(where, line, handle, inode, path->p_bh); /* Extents updating done, re-set verified flag */ if (!err) set_buffer_verified(path->p_bh); } else { /* path points to leaf/index in inode body */ err = ext4_mark_inode_dirty(handle, inode); } return err; } #define ext4_ext_dirty(handle, inode, path) \ __ext4_ext_dirty(__func__, __LINE__, (handle), (inode), (path)) static ext4_fsblk_t ext4_ext_find_goal(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { if (path) { int depth = path->p_depth; struct ext4_extent *ex; /* * Try to predict block placement assuming that we are * filling in a file which will eventually be * non-sparse --- i.e., in the case of libbfd writing * an ELF object sections out-of-order but in a way * the eventually results in a contiguous object or * executable file, or some database extending a table * space file. However, this is actually somewhat * non-ideal if we are writing a sparse file such as * qemu or KVM writing a raw image file that is going * to stay fairly sparse, since it will end up * fragmenting the file system's free space. Maybe we * should have some hueristics or some way to allow * userspace to pass a hint to file system, * especially if the latter case turns out to be * common. */ ex = path[depth].p_ext; if (ex) { ext4_fsblk_t ext_pblk = ext4_ext_pblock(ex); ext4_lblk_t ext_block = le32_to_cpu(ex->ee_block); if (block > ext_block) return ext_pblk + (block - ext_block); else return ext_pblk - (ext_block - block); } /* it looks like index is empty; * try to find starting block from index itself */ if (path[depth].p_bh) return path[depth].p_bh->b_blocknr; } /* OK. use inode's group */ return ext4_inode_to_goal_block(inode); } /* * Allocation for a meta data block */ static ext4_fsblk_t ext4_ext_new_meta_block(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex, int *err, unsigned int flags) { ext4_fsblk_t goal, newblock; goal = ext4_ext_find_goal(inode, path, le32_to_cpu(ex->ee_block)); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, err); return newblock; } static inline int ext4_ext_space_block(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 6) size = 6; #endif return size; } static inline int ext4_ext_space_block_idx(struct inode *inode, int check) { int size; size = (inode->i_sb->s_blocksize - sizeof(struct ext4_extent_header)) / sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 5) size = 5; #endif return size; } static inline int ext4_ext_space_root(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent); #ifdef AGGRESSIVE_TEST if (!check && size > 3) size = 3; #endif return size; } static inline int ext4_ext_space_root_idx(struct inode *inode, int check) { int size; size = sizeof(EXT4_I(inode)->i_data); size -= sizeof(struct ext4_extent_header); size /= sizeof(struct ext4_extent_idx); #ifdef AGGRESSIVE_TEST if (!check && size > 4) size = 4; #endif return size; } static inline struct ext4_ext_path * ext4_force_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t lblk, int nofail) { int flags = EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_SPLIT_NOMERGE; if (nofail) flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL | EXT4_EX_NOFAIL; return ext4_split_extent_at(handle, inode, path, lblk, flags); } static int ext4_ext_max_entries(struct inode *inode, int depth) { int max; if (depth == ext_depth(inode)) { if (depth == 0) max = ext4_ext_space_root(inode, 1); else max = ext4_ext_space_root_idx(inode, 1); } else { if (depth == 0) max = ext4_ext_space_block(inode, 1); else max = ext4_ext_space_block_idx(inode, 1); } return max; } static int ext4_valid_extent(struct inode *inode, struct ext4_extent *ext) { ext4_fsblk_t block = ext4_ext_pblock(ext); int len = ext4_ext_get_actual_len(ext); ext4_lblk_t lblock = le32_to_cpu(ext->ee_block); /* * We allow neither: * - zero length * - overflow/wrap-around */ if (lblock + len <= lblock) return 0; return ext4_inode_block_valid(inode, block, len); } static int ext4_valid_extent_idx(struct inode *inode, struct ext4_extent_idx *ext_idx) { ext4_fsblk_t block = ext4_idx_pblock(ext_idx); return ext4_inode_block_valid(inode, block, 1); } static int ext4_valid_extent_entries(struct inode *inode, struct ext4_extent_header *eh, ext4_lblk_t lblk, ext4_fsblk_t *pblk, int depth) { unsigned short entries; ext4_lblk_t lblock = 0; ext4_lblk_t cur = 0; if (eh->eh_entries == 0) return 1; entries = le16_to_cpu(eh->eh_entries); if (depth == 0) { /* leaf entries */ struct ext4_extent *ext = EXT_FIRST_EXTENT(eh); /* * The logical block in the first entry should equal to * the number in the index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext->ee_block)) return 0; while (entries) { if (!ext4_valid_extent(inode, ext)) return 0; /* Check for overlapping extents */ lblock = le32_to_cpu(ext->ee_block); if (lblock < cur) { *pblk = ext4_ext_pblock(ext); return 0; } cur = lblock + ext4_ext_get_actual_len(ext); ext++; entries--; } } else { struct ext4_extent_idx *ext_idx = EXT_FIRST_INDEX(eh); /* * The logical block in the first entry should equal to * the number in the parent index block. */ if (depth != ext_depth(inode) && lblk != le32_to_cpu(ext_idx->ei_block)) return 0; while (entries) { if (!ext4_valid_extent_idx(inode, ext_idx)) return 0; /* Check for overlapping index extents */ lblock = le32_to_cpu(ext_idx->ei_block); if (lblock < cur) { *pblk = ext4_idx_pblock(ext_idx); return 0; } ext_idx++; entries--; cur = lblock + 1; } } return 1; } static int __ext4_ext_check(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_header *eh, int depth, ext4_fsblk_t pblk, ext4_lblk_t lblk) { const char *error_msg; int max = 0, err = -EFSCORRUPTED; if (unlikely(eh->eh_magic != EXT4_EXT_MAGIC)) { error_msg = "invalid magic"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_depth) != depth)) { error_msg = "unexpected eh_depth"; goto corrupted; } if (unlikely(eh->eh_max == 0)) { error_msg = "invalid eh_max"; goto corrupted; } max = ext4_ext_max_entries(inode, depth); if (unlikely(le16_to_cpu(eh->eh_max) > max)) { error_msg = "too large eh_max"; goto corrupted; } if (unlikely(le16_to_cpu(eh->eh_entries) > le16_to_cpu(eh->eh_max))) { error_msg = "invalid eh_entries"; goto corrupted; } if (unlikely((eh->eh_entries == 0) && (depth > 0))) { error_msg = "eh_entries is 0 but eh_depth is > 0"; goto corrupted; } if (!ext4_valid_extent_entries(inode, eh, lblk, &pblk, depth)) { error_msg = "invalid extent entries"; goto corrupted; } if (unlikely(depth > 32)) { error_msg = "too large eh_depth"; goto corrupted; } /* Verify checksum on non-root extent tree nodes */ if (ext_depth(inode) != depth && !ext4_extent_block_csum_verify(inode, eh)) { error_msg = "extent tree corrupted"; err = -EFSBADCRC; goto corrupted; } return 0; corrupted: ext4_error_inode_err(inode, function, line, 0, -err, "pblk %llu bad header/extent: %s - magic %x, " "entries %u, max %u(%u), depth %u(%u)", (unsigned long long) pblk, error_msg, le16_to_cpu(eh->eh_magic), le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max), max, le16_to_cpu(eh->eh_depth), depth); return err; } #define ext4_ext_check(inode, eh, depth, pblk) \ __ext4_ext_check(__func__, __LINE__, (inode), (eh), (depth), (pblk), 0) int ext4_ext_check_inode(struct inode *inode) { return ext4_ext_check(inode, ext_inode_hdr(inode), ext_depth(inode), 0); } static void ext4_cache_extents(struct inode *inode, struct ext4_extent_header *eh) { struct ext4_extent *ex = EXT_FIRST_EXTENT(eh); ext4_lblk_t prev = 0; int i; KUNIT_STATIC_STUB_REDIRECT(ext4_cache_extents, inode, eh); for (i = le16_to_cpu(eh->eh_entries); i > 0; i--, ex++) { unsigned int status = EXTENT_STATUS_WRITTEN; ext4_lblk_t lblk = le32_to_cpu(ex->ee_block); int len = ext4_ext_get_actual_len(ex); if (prev && (prev != lblk)) ext4_es_cache_extent(inode, prev, lblk - prev, ~0, EXTENT_STATUS_HOLE); if (ext4_ext_is_unwritten(ex)) status = EXTENT_STATUS_UNWRITTEN; ext4_es_cache_extent(inode, lblk, len, ext4_ext_pblock(ex), status); prev = lblk + len; } } static struct buffer_head * __read_extent_tree_block(const char *function, unsigned int line, struct inode *inode, struct ext4_extent_idx *idx, int depth, int flags) { struct buffer_head *bh; int err; gfp_t gfp_flags = __GFP_MOVABLE | GFP_NOFS; ext4_fsblk_t pblk; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; pblk = ext4_idx_pblock(idx); bh = sb_getblk_gfp(inode->i_sb, pblk, gfp_flags); if (unlikely(!bh)) return ERR_PTR(-ENOMEM); if (!bh_uptodate_or_lock(bh)) { trace_ext4_ext_load_extent(inode, pblk, _RET_IP_); err = ext4_read_bh(bh, 0, NULL, false); if (err < 0) goto errout; } if (buffer_verified(bh) && !(flags & EXT4_EX_FORCE_CACHE)) return bh; err = __ext4_ext_check(function, line, inode, ext_block_hdr(bh), depth, pblk, le32_to_cpu(idx->ei_block)); if (err) goto errout; set_buffer_verified(bh); /* * If this is a leaf block, cache all of its entries */ if (!(flags & EXT4_EX_NOCACHE) && depth == 0) { struct ext4_extent_header *eh = ext_block_hdr(bh); ext4_cache_extents(inode, eh); } return bh; errout: put_bh(bh); return ERR_PTR(err); } #define read_extent_tree_block(inode, idx, depth, flags) \ __read_extent_tree_block(__func__, __LINE__, (inode), (idx), \ (depth), (flags)) /* * This function is called to cache a file's extent information in the * extent status tree */ int ext4_ext_precache(struct inode *inode) { struct ext4_inode_info *ei = EXT4_I(inode); struct ext4_ext_path *path = NULL; struct buffer_head *bh; int i = 0, depth, ret = 0; if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return 0; /* not an extent-mapped inode */ ext4_check_map_extents_env(inode); down_read(&ei->i_data_sem); depth = ext_depth(inode); /* Don't cache anything if there are no external extent blocks */ if (!depth) { up_read(&ei->i_data_sem); return ret; } path = kzalloc_objs(struct ext4_ext_path, depth + 1, GFP_NOFS); if (path == NULL) { up_read(&ei->i_data_sem); return -ENOMEM; } path[0].p_hdr = ext_inode_hdr(inode); ret = ext4_ext_check(inode, path[0].p_hdr, depth, 0); if (ret) goto out; path[0].p_idx = EXT_FIRST_INDEX(path[0].p_hdr); while (i >= 0) { /* * If this is a leaf block or we've reached the end of * the index block, go up */ if ((i == depth) || path[i].p_idx > EXT_LAST_INDEX(path[i].p_hdr)) { ext4_ext_path_brelse(path + i); i--; continue; } bh = read_extent_tree_block(inode, path[i].p_idx++, depth - i - 1, EXT4_EX_FORCE_CACHE); if (IS_ERR(bh)) { ret = PTR_ERR(bh); break; } i++; path[i].p_bh = bh; path[i].p_hdr = ext_block_hdr(bh); path[i].p_idx = EXT_FIRST_INDEX(path[i].p_hdr); } ext4_set_inode_state(inode, EXT4_STATE_EXT_PRECACHED); out: up_read(&ei->i_data_sem); ext4_free_ext_path(path); return ret; } #ifdef EXT_DEBUG static void ext4_ext_show_path(struct inode *inode, struct ext4_ext_path *path) { int k, l = path->p_depth; ext_debug(inode, "path:"); for (k = 0; k <= l; k++, path++) { if (path->p_idx) { ext_debug(inode, " %d->%llu", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); } else if (path->p_ext) { ext_debug(inode, " %d:[%d]%d:%llu ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext), ext4_ext_pblock(path->p_ext)); } else ext_debug(inode, " []"); } ext_debug(inode, "\n"); } static void ext4_ext_show_leaf(struct inode *inode, struct ext4_ext_path *path) { int depth = ext_depth(inode); struct ext4_extent_header *eh; struct ext4_extent *ex; int i; if (IS_ERR_OR_NULL(path)) return; eh = path[depth].p_hdr; ex = EXT_FIRST_EXTENT(eh); ext_debug(inode, "Displaying leaf extents\n"); for (i = 0; i < le16_to_cpu(eh->eh_entries); i++, ex++) { ext_debug(inode, "%d:[%d]%d:%llu ", le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); } ext_debug(inode, "\n"); } static void ext4_ext_show_move(struct inode *inode, struct ext4_ext_path *path, ext4_fsblk_t newblock, int level) { int depth = ext_depth(inode); struct ext4_extent *ex; if (depth != level) { struct ext4_extent_idx *idx; idx = path[level].p_idx; while (idx <= EXT_MAX_INDEX(path[level].p_hdr)) { ext_debug(inode, "%d: move %d:%llu in new index %llu\n", level, le32_to_cpu(idx->ei_block), ext4_idx_pblock(idx), newblock); idx++; } return; } ex = path[depth].p_ext; while (ex <= EXT_MAX_EXTENT(path[depth].p_hdr)) { ext_debug(inode, "move %d:%llu:[%d]%d in new leaf %llu\n", le32_to_cpu(ex->ee_block), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), newblock); ex++; } } #else #define ext4_ext_show_path(inode, path) #define ext4_ext_show_leaf(inode, path) #define ext4_ext_show_move(inode, path, newblock, level) #endif /* * ext4_ext_binsearch_idx: * binary search for the closest index of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch_idx(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent_idx *r, *l, *m; ext_debug(inode, "binsearch for %u(idx): ", block); l = EXT_FIRST_INDEX(eh) + 1; r = EXT_LAST_INDEX(eh); while (l <= r) { m = l + (r - l) / 2; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ei_block), m, le32_to_cpu(m->ei_block), r, le32_to_cpu(r->ei_block)); if (block < le32_to_cpu(m->ei_block)) r = m - 1; else l = m + 1; } path->p_idx = l - 1; ext_debug(inode, " -> %u->%lld ", le32_to_cpu(path->p_idx->ei_block), ext4_idx_pblock(path->p_idx)); #ifdef CHECK_BINSEARCH { struct ext4_extent_idx *chix, *ix; int k; chix = ix = EXT_FIRST_INDEX(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ix++) { if (k != 0 && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)) { printk(KERN_DEBUG "k=%d, ix=0x%p, " "first=0x%p\n", k, ix, EXT_FIRST_INDEX(eh)); printk(KERN_DEBUG "%u <= %u\n", le32_to_cpu(ix->ei_block), le32_to_cpu(ix[-1].ei_block)); } BUG_ON(k && le32_to_cpu(ix->ei_block) <= le32_to_cpu(ix[-1].ei_block)); if (block < le32_to_cpu(ix->ei_block)) break; chix = ix; } BUG_ON(chix != path->p_idx); } #endif } /* * ext4_ext_binsearch: * binary search for closest extent of the given block * the header must be checked before calling this */ static void ext4_ext_binsearch(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t block) { struct ext4_extent_header *eh = path->p_hdr; struct ext4_extent *r, *l, *m; if (eh->eh_entries == 0) { /* * this leaf is empty: * we get such a leaf in split/add case */ return; } ext_debug(inode, "binsearch for %u: ", block); l = EXT_FIRST_EXTENT(eh) + 1; r = EXT_LAST_EXTENT(eh); while (l <= r) { m = l + (r - l) / 2; ext_debug(inode, "%p(%u):%p(%u):%p(%u) ", l, le32_to_cpu(l->ee_block), m, le32_to_cpu(m->ee_block), r, le32_to_cpu(r->ee_block)); if (block < le32_to_cpu(m->ee_block)) r = m - 1; else l = m + 1; } path->p_ext = l - 1; ext_debug(inode, " -> %d:%llu:[%d]%d ", le32_to_cpu(path->p_ext->ee_block), ext4_ext_pblock(path->p_ext), ext4_ext_is_unwritten(path->p_ext), ext4_ext_get_actual_len(path->p_ext)); #ifdef CHECK_BINSEARCH { struct ext4_extent *chex, *ex; int k; chex = ex = EXT_FIRST_EXTENT(eh); for (k = 0; k < le16_to_cpu(eh->eh_entries); k++, ex++) { BUG_ON(k && le32_to_cpu(ex->ee_block) <= le32_to_cpu(ex[-1].ee_block)); if (block < le32_to_cpu(ex->ee_block)) break; chex = ex; } BUG_ON(chex != path->p_ext); } #endif } void ext4_ext_tree_init(handle_t *handle, struct inode *inode) { struct ext4_extent_header *eh; eh = ext_inode_hdr(inode); eh->eh_depth = 0; eh->eh_entries = 0; eh->eh_magic = EXT4_EXT_MAGIC; eh->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); eh->eh_generation = 0; ext4_mark_inode_dirty(handle, inode); } struct ext4_ext_path * ext4_find_extent(struct inode *inode, ext4_lblk_t block, struct ext4_ext_path *path, int flags) { struct ext4_extent_header *eh; struct buffer_head *bh; short int depth, i, ppos = 0; int ret; gfp_t gfp_flags = GFP_NOFS; KUNIT_STATIC_STUB_REDIRECT(ext4_find_extent, inode, block, path, flags); if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; eh = ext_inode_hdr(inode); depth = ext_depth(inode); if (depth < 0 || depth > EXT4_MAX_EXTENT_DEPTH) { EXT4_ERROR_INODE(inode, "inode has invalid extent depth: %d", depth); ret = -EFSCORRUPTED; goto err; } if (path) { ext4_ext_drop_refs(path); if (depth > path[0].p_maxdepth) { kfree(path); path = NULL; } } if (!path) { /* account possible depth increase */ path = kzalloc_objs(struct ext4_ext_path, depth + 2, gfp_flags); if (unlikely(!path)) return ERR_PTR(-ENOMEM); path[0].p_maxdepth = depth + 1; } path[0].p_hdr = eh; path[0].p_bh = NULL; i = depth; if (!(flags & EXT4_EX_NOCACHE) && depth == 0) ext4_cache_extents(inode, eh); /* walk through the tree */ while (i) { ext_debug(inode, "depth %d: num %d, max %d\n", ppos, le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_ext_binsearch_idx(inode, path + ppos, block); path[ppos].p_block = ext4_idx_pblock(path[ppos].p_idx); path[ppos].p_depth = i; path[ppos].p_ext = NULL; bh = read_extent_tree_block(inode, path[ppos].p_idx, --i, flags); if (IS_ERR(bh)) { ret = PTR_ERR(bh); goto err; } eh = ext_block_hdr(bh); ppos++; path[ppos].p_bh = bh; path[ppos].p_hdr = eh; } path[ppos].p_depth = i; path[ppos].p_ext = NULL; path[ppos].p_idx = NULL; /* find extent */ ext4_ext_binsearch(inode, path + ppos, block); /* if not an empty leaf */ if (path[ppos].p_ext) path[ppos].p_block = ext4_ext_pblock(path[ppos].p_ext); ext4_ext_show_path(inode, path); return path; err: ext4_free_ext_path(path); return ERR_PTR(ret); } /* * ext4_ext_insert_index: * insert new index [@logical;@ptr] into the block at @curp; * check where to insert: before @curp or after @curp */ static int ext4_ext_insert_index(handle_t *handle, struct inode *inode, struct ext4_ext_path *curp, int logical, ext4_fsblk_t ptr) { struct ext4_extent_idx *ix; int len, err; err = ext4_ext_get_access(handle, inode, curp); if (err) return err; if (unlikely(logical == le32_to_cpu(curp->p_idx->ei_block))) { EXT4_ERROR_INODE(inode, "logical %d == ei_block %d!", logical, le32_to_cpu(curp->p_idx->ei_block)); return -EFSCORRUPTED; } if (unlikely(le16_to_cpu(curp->p_hdr->eh_entries) >= le16_to_cpu(curp->p_hdr->eh_max))) { EXT4_ERROR_INODE(inode, "eh_entries %d >= eh_max %d!", le16_to_cpu(curp->p_hdr->eh_entries), le16_to_cpu(curp->p_hdr->eh_max)); return -EFSCORRUPTED; } if (logical > le32_to_cpu(curp->p_idx->ei_block)) { /* insert after */ ext_debug(inode, "insert new index %d after: %llu\n", logical, ptr); ix = curp->p_idx + 1; } else { /* insert before */ ext_debug(inode, "insert new index %d before: %llu\n", logical, ptr); ix = curp->p_idx; } if (unlikely(ix > EXT_MAX_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_MAX_INDEX!"); return -EFSCORRUPTED; } len = EXT_LAST_INDEX(curp->p_hdr) - ix + 1; BUG_ON(len < 0); if (len > 0) { ext_debug(inode, "insert new index %d: " "move %d indices from 0x%p to 0x%p\n", logical, len, ix, ix + 1); memmove(ix + 1, ix, len * sizeof(struct ext4_extent_idx)); } ix->ei_block = cpu_to_le32(logical); ext4_idx_store_pblock(ix, ptr); le16_add_cpu(&curp->p_hdr->eh_entries, 1); if (unlikely(ix > EXT_LAST_INDEX(curp->p_hdr))) { EXT4_ERROR_INODE(inode, "ix > EXT_LAST_INDEX!"); return -EFSCORRUPTED; } err = ext4_ext_dirty(handle, inode, curp); ext4_std_error(inode->i_sb, err); return err; } /* * ext4_ext_split: * inserts new subtree into the path, using free index entry * at depth @at: * - allocates all needed blocks (new leaf and all intermediate index blocks) * - makes decision where to split * - moves remaining extents and index entries (right to the split point) * into the newly allocated blocks * - initializes subtree */ static int ext4_ext_split(handle_t *handle, struct inode *inode, unsigned int flags, struct ext4_ext_path *path, struct ext4_extent *newext, int at) { struct buffer_head *bh = NULL; int depth = ext_depth(inode); struct ext4_extent_header *neh; struct ext4_extent_idx *fidx; int i = at, k, m, a; ext4_fsblk_t newblock, oldblock; __le32 border; ext4_fsblk_t *ablocks = NULL; /* array of allocated blocks */ gfp_t gfp_flags = GFP_NOFS; int err = 0; size_t ext_size = 0; if (flags & EXT4_EX_NOFAIL) gfp_flags |= __GFP_NOFAIL; /* make decision: where to split? */ /* FIXME: now decision is simplest: at current extent */ /* if current leaf will be split, then we should use * border from split point */ if (unlikely(path[depth].p_ext > EXT_MAX_EXTENT(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "p_ext > EXT_MAX_EXTENT!"); return -EFSCORRUPTED; } if (path[depth].p_ext != EXT_MAX_EXTENT(path[depth].p_hdr)) { border = path[depth].p_ext[1].ee_block; ext_debug(inode, "leaf will be split." " next leaf starts at %d\n", le32_to_cpu(border)); } else { border = newext->ee_block; ext_debug(inode, "leaf will be added." " next leaf starts at %d\n", le32_to_cpu(border)); } /* * If error occurs, then we break processing * and mark filesystem read-only. index won't * be inserted and tree will be in consistent * state. Next mount will repair buffers too. */ /* * Get array to track all allocated blocks. * We need this to handle errors and free blocks * upon them. */ ablocks = kzalloc_objs(ext4_fsblk_t, depth, gfp_flags); if (!ablocks) return -ENOMEM; /* allocate all needed blocks */ ext_debug(inode, "allocate %d blocks for indexes/leaf\n", depth - at); for (a = 0; a < depth - at; a++) { newblock = ext4_ext_new_meta_block(handle, inode, path, newext, &err, flags); if (newblock == 0) goto cleanup; ablocks[a] = newblock; } /* initialize new leaf */ newblock = ablocks[--a]; if (unlikely(newblock == 0)) { EXT4_ERROR_INODE(inode, "newblock == 0!"); err = -EFSCORRUPTED; goto cleanup; } bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = 0; neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_depth = 0; neh->eh_generation = 0; /* move remainder of path[depth] to the new leaf */ if (unlikely(path[depth].p_hdr->eh_entries != path[depth].p_hdr->eh_max)) { EXT4_ERROR_INODE(inode, "eh_entries %d != eh_max %d!", path[depth].p_hdr->eh_entries, path[depth].p_hdr->eh_max); err = -EFSCORRUPTED; goto cleanup; } /* start copy from next extent */ m = EXT_MAX_EXTENT(path[depth].p_hdr) - path[depth].p_ext++; ext4_ext_show_move(inode, path, newblock, depth); if (m) { struct ext4_extent *ex; ex = EXT_FIRST_EXTENT(neh); memmove(ex, path[depth].p_ext, sizeof(struct ext4_extent) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old leaf */ if (m) { err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto cleanup; le16_add_cpu(&path[depth].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto cleanup; } /* create intermediate indexes */ k = depth - at - 1; if (unlikely(k < 0)) { EXT4_ERROR_INODE(inode, "k %d < 0!", k); err = -EFSCORRUPTED; goto cleanup; } if (k) ext_debug(inode, "create %d intermediate indices\n", k); /* insert new index into current index block */ /* current depth stored in i var */ i = depth - 1; while (k--) { oldblock = newblock; newblock = ablocks[--a]; bh = sb_getblk(inode->i_sb, newblock); if (unlikely(!bh)) { err = -ENOMEM; goto cleanup; } lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) goto cleanup; neh = ext_block_hdr(bh); neh->eh_entries = cpu_to_le16(1); neh->eh_magic = EXT4_EXT_MAGIC; neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); neh->eh_depth = cpu_to_le16(depth - i); neh->eh_generation = 0; fidx = EXT_FIRST_INDEX(neh); fidx->ei_block = border; ext4_idx_store_pblock(fidx, oldblock); ext_debug(inode, "int.index at %d (block %llu): %u -> %llu\n", i, newblock, le32_to_cpu(border), oldblock); /* move remainder of path[i] to the new index block */ if (unlikely(EXT_MAX_INDEX(path[i].p_hdr) != EXT_LAST_INDEX(path[i].p_hdr))) { EXT4_ERROR_INODE(inode, "EXT_MAX_INDEX != EXT_LAST_INDEX ee_block %d!", le32_to_cpu(path[i].p_ext->ee_block)); err = -EFSCORRUPTED; goto cleanup; } /* start copy indexes */ m = EXT_MAX_INDEX(path[i].p_hdr) - path[i].p_idx++; ext_debug(inode, "cur 0x%p, last 0x%p\n", path[i].p_idx, EXT_MAX_INDEX(path[i].p_hdr)); ext4_ext_show_move(inode, path, newblock, i); if (m) { memmove(++fidx, path[i].p_idx, sizeof(struct ext4_extent_idx) * m); le16_add_cpu(&neh->eh_entries, m); } /* zero out unused area in the extent block */ ext_size = sizeof(struct ext4_extent_header) + (sizeof(struct ext4_extent) * le16_to_cpu(neh->eh_entries)); memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto cleanup; brelse(bh); bh = NULL; /* correct old index */ if (m) { err = ext4_ext_get_access(handle, inode, path + i); if (err) goto cleanup; le16_add_cpu(&path[i].p_hdr->eh_entries, -m); err = ext4_ext_dirty(handle, inode, path + i); if (err) goto cleanup; } i--; } /* insert new index */ err = ext4_ext_insert_index(handle, inode, path + at, le32_to_cpu(border), newblock); cleanup: if (bh) { if (buffer_locked(bh)) unlock_buffer(bh); brelse(bh); } if (err) { /* free all allocated blocks in error case */ for (i = 0; i < depth; i++) { if (!ablocks[i]) continue; ext4_free_blocks(handle, inode, NULL, ablocks[i], 1, EXT4_FREE_BLOCKS_METADATA); } } kfree(ablocks); return err; } /* * ext4_ext_grow_indepth: * implements tree growing procedure: * - allocates new block * - moves top-level data (index block or leaf) into the new block * - initializes new top-level, creating index that points to the * just created block */ static int ext4_ext_grow_indepth(handle_t *handle, struct inode *inode, unsigned int flags) { struct ext4_extent_header *neh; struct buffer_head *bh; ext4_fsblk_t newblock, goal = 0; struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es; int err = 0; size_t ext_size = 0; /* Try to prepend new index to old one */ if (ext_depth(inode)) goal = ext4_idx_pblock(EXT_FIRST_INDEX(ext_inode_hdr(inode))); if (goal > le32_to_cpu(es->s_first_data_block)) { flags |= EXT4_MB_HINT_TRY_GOAL; goal--; } else goal = ext4_inode_to_goal_block(inode); newblock = ext4_new_meta_blocks(handle, inode, goal, flags, NULL, &err); if (newblock == 0) return err; bh = sb_getblk_gfp(inode->i_sb, newblock, __GFP_MOVABLE | GFP_NOFS); if (unlikely(!bh)) return -ENOMEM; lock_buffer(bh); err = ext4_journal_get_create_access(handle, inode->i_sb, bh, EXT4_JTR_NONE); if (err) { unlock_buffer(bh); goto out; } ext_size = sizeof(EXT4_I(inode)->i_data); /* move top-level index/leaf into new block */ memmove(bh->b_data, EXT4_I(inode)->i_data, ext_size); /* zero out unused area in the extent block */ memset(bh->b_data + ext_size, 0, inode->i_sb->s_blocksize - ext_size); /* set size of new block */ neh = ext_block_hdr(bh); /* old root could have indexes or leaves * so calculate e_max right way */ if (ext_depth(inode)) neh->eh_max = cpu_to_le16(ext4_ext_space_block_idx(inode, 0)); else neh->eh_max = cpu_to_le16(ext4_ext_space_block(inode, 0)); neh->eh_magic = EXT4_EXT_MAGIC; ext4_extent_block_csum_set(inode, neh); set_buffer_uptodate(bh); set_buffer_verified(bh); unlock_buffer(bh); err = ext4_handle_dirty_metadata(handle, inode, bh); if (err) goto out; /* Update top-level index: num,max,pointer */ neh = ext_inode_hdr(inode); neh->eh_entries = cpu_to_le16(1); ext4_idx_store_pblock(EXT_FIRST_INDEX(neh), newblock); if (neh->eh_depth == 0) { /* Root extent block becomes index block */ neh->eh_max = cpu_to_le16(ext4_ext_space_root_idx(inode, 0)); EXT_FIRST_INDEX(neh)->ei_block = EXT_FIRST_EXTENT(neh)->ee_block; } ext_debug(inode, "new root: num %d(%d), lblock %d, ptr %llu\n", le16_to_cpu(neh->eh_entries), le16_to_cpu(neh->eh_max), le32_to_cpu(EXT_FIRST_INDEX(neh)->ei_block), ext4_idx_pblock(EXT_FIRST_INDEX(neh))); le16_add_cpu(&neh->eh_depth, 1); err = ext4_mark_inode_dirty(handle, inode); out: brelse(bh); return err; } /* * ext4_ext_create_new_leaf: * finds empty index and adds new leaf. * if no free index is found, then it requests in-depth growing. */ static struct ext4_ext_path * ext4_ext_create_new_leaf(handle_t *handle, struct inode *inode, unsigned int mb_flags, unsigned int gb_flags, struct ext4_ext_path *path, struct ext4_extent *newext) { struct ext4_ext_path *curp; int depth, i, err = 0; ext4_lblk_t ee_block = le32_to_cpu(newext->ee_block); repeat: i = depth = ext_depth(inode); /* walk up to the tree and look for free index entry */ curp = path + depth; while (i > 0 && !EXT_HAS_FREE_INDEX(curp)) { i--; curp--; } /* we use already allocated block for index block, * so subsequent data blocks should be contiguous */ if (EXT_HAS_FREE_INDEX(curp)) { /* if we found index with free entry, then use that * entry: create all needed subtree and add new leaf */ err = ext4_ext_split(handle, inode, mb_flags, path, newext, i); if (err) goto errout; /* refill path */ path = ext4_find_extent(inode, ee_block, path, gb_flags); return path; } /* tree is full, time to grow in depth */ err = ext4_ext_grow_indepth(handle, inode, mb_flags); if (err) goto errout; /* refill path */ path = ext4_find_extent(inode, ee_block, path, gb_flags); if (IS_ERR(path)) return path; /* * only first (depth 0 -> 1) produces free space; * in all other cases we have to split the grown tree */ depth = ext_depth(inode); if (path[depth].p_hdr->eh_entries == path[depth].p_hdr->eh_max) { /* now we need to split */ goto repeat; } return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } /* * search the closest allocated block to the left for *logical * and returns it at @logical + it's physical address at @phys * if *logical is the smallest allocated block, the function * returns 0 at @phys * return value contains 0 (success) or error code */ static int ext4_ext_search_left(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys) { struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth, ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "EXT_FIRST_EXTENT != ex *logical %d ee_block %d!", *logical, le32_to_cpu(ex->ee_block)); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix (%d) != EXT_FIRST_INDEX (%d) (depth %d)!", ix != NULL ? le32_to_cpu(ix->ei_block) : 0, le32_to_cpu(EXT_FIRST_INDEX(path[depth].p_hdr)->ei_block), depth); return -EFSCORRUPTED; } } return 0; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } *logical = le32_to_cpu(ex->ee_block) + ee_len - 1; *phys = ext4_ext_pblock(ex) + ee_len - 1; return 0; } /* * Search the closest allocated block to the right for *logical * and returns it at @logical + it's physical address at @phys. * If not exists, return 0 and @phys is set to 0. We will return * 1 which means we found an allocated block and ret_ex is valid. * Or return a (< 0) error code. */ static int ext4_ext_search_right(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *logical, ext4_fsblk_t *phys, struct ext4_extent *ret_ex, int flags) { struct buffer_head *bh = NULL; struct ext4_extent_header *eh; struct ext4_extent_idx *ix; struct ext4_extent *ex; int depth; /* Note, NOT eh_depth; depth from top of tree */ int ee_len; if (unlikely(path == NULL)) { EXT4_ERROR_INODE(inode, "path == NULL *logical %d!", *logical); return -EFSCORRUPTED; } depth = path->p_depth; *phys = 0; if (depth == 0 && path->p_ext == NULL) return 0; /* usually extent in the path covers blocks smaller * then *logical, but it can be that extent is the * first one in the file */ ex = path[depth].p_ext; ee_len = ext4_ext_get_actual_len(ex); if (*logical < le32_to_cpu(ex->ee_block)) { if (unlikely(EXT_FIRST_EXTENT(path[depth].p_hdr) != ex)) { EXT4_ERROR_INODE(inode, "first_extent(path[%d].p_hdr) != ex", depth); return -EFSCORRUPTED; } while (--depth >= 0) { ix = path[depth].p_idx; if (unlikely(ix != EXT_FIRST_INDEX(path[depth].p_hdr))) { EXT4_ERROR_INODE(inode, "ix != EXT_FIRST_INDEX *logical %d!", *logical); return -EFSCORRUPTED; } } goto found_extent; } if (unlikely(*logical < (le32_to_cpu(ex->ee_block) + ee_len))) { EXT4_ERROR_INODE(inode, "logical %d < ee_block %d + ee_len %d!", *logical, le32_to_cpu(ex->ee_block), ee_len); return -EFSCORRUPTED; } if (ex != EXT_LAST_EXTENT(path[depth].p_hdr)) { /* next allocated block in this leaf */ ex++; goto found_extent; } /* go up and search for index to the right */ while (--depth >= 0) { ix = path[depth].p_idx; if (ix != EXT_LAST_INDEX(path[depth].p_hdr)) goto got_index; } /* we've gone up to the root and found no index to the right */ return 0; got_index: /* we've found index to the right, let's * follow it and find the closest allocated * block to the right */ ix++; while (++depth < path->p_depth) { /* subtract from p_depth to get proper eh_depth */ bh = read_extent_tree_block(inode, ix, path->p_depth - depth, flags); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ix = EXT_FIRST_INDEX(eh); put_bh(bh); } bh = read_extent_tree_block(inode, ix, path->p_depth - depth, flags); if (IS_ERR(bh)) return PTR_ERR(bh); eh = ext_block_hdr(bh); ex = EXT_FIRST_EXTENT(eh); found_extent: *logical = le32_to_cpu(ex->ee_block); *phys = ext4_ext_pblock(ex); if (ret_ex) *ret_ex = *ex; if (bh) put_bh(bh); return 1; } /* * ext4_ext_next_allocated_block: * returns allocated block in subsequent extent or EXT_MAX_BLOCKS. * NOTE: it considers block number from index entry as * allocated block. Thus, index entries have to be consistent * with leaves. */ ext4_lblk_t ext4_ext_next_allocated_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; if (depth == 0 && path->p_ext == NULL) return EXT_MAX_BLOCKS; while (depth >= 0) { struct ext4_ext_path *p = &path[depth]; if (depth == path->p_depth) { /* leaf */ if (p->p_ext && p->p_ext != EXT_LAST_EXTENT(p->p_hdr)) return le32_to_cpu(p->p_ext[1].ee_block); } else { /* index */ if (p->p_idx != EXT_LAST_INDEX(p->p_hdr)) return le32_to_cpu(p->p_idx[1].ei_block); } depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_next_leaf_block: * returns first allocated block from next leaf or EXT_MAX_BLOCKS */ static ext4_lblk_t ext4_ext_next_leaf_block(struct ext4_ext_path *path) { int depth; BUG_ON(path == NULL); depth = path->p_depth; /* zero-tree has no leaf blocks at all */ if (depth == 0) return EXT_MAX_BLOCKS; /* go to index block */ depth--; while (depth >= 0) { if (path[depth].p_idx != EXT_LAST_INDEX(path[depth].p_hdr)) return (ext4_lblk_t) le32_to_cpu(path[depth].p_idx[1].ei_block); depth--; } return EXT_MAX_BLOCKS; } /* * ext4_ext_correct_indexes: * if leaf gets modified and modified extent is first in the leaf, * then we have to correct all indexes above. * TODO: do we need to correct tree in all cases? */ static int ext4_ext_correct_indexes(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { struct ext4_extent_header *eh; int depth = ext_depth(inode); struct ext4_extent *ex; __le32 border; int k, err = 0; eh = path[depth].p_hdr; ex = path[depth].p_ext; if (unlikely(ex == NULL || eh == NULL)) { EXT4_ERROR_INODE(inode, "ex %p == NULL or eh %p == NULL", ex, eh); return -EFSCORRUPTED; } if (depth == 0) { /* there is no tree at all */ return 0; } if (ex != EXT_FIRST_EXTENT(eh)) { /* we correct tree if first leaf got modified only */ return 0; } /* * TODO: we need correction if border is smaller than current one */ k = depth - 1; border = path[depth].p_ext->ee_block; err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) { EXT4_ERROR_INODE(inode, "path[%d].p_idx %p > EXT_LAST_INDEX %p", k, path[k].p_idx, EXT_LAST_INDEX(path[k].p_hdr)); return -EFSCORRUPTED; } path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; while (k--) { /* change all left-side indexes */ if (path[k+1].p_idx != EXT_FIRST_INDEX(path[k+1].p_hdr)) break; err = ext4_ext_get_access(handle, inode, path + k); if (err) goto clean; if (unlikely(path[k].p_idx > EXT_LAST_INDEX(path[k].p_hdr))) { EXT4_ERROR_INODE(inode, "path[%d].p_idx %p > EXT_LAST_INDEX %p", k, path[k].p_idx, EXT_LAST_INDEX(path[k].p_hdr)); err = -EFSCORRUPTED; goto clean; } path[k].p_idx->ei_block = border; err = ext4_ext_dirty(handle, inode, path + k); if (err) goto clean; } return 0; clean: /* * The path[k].p_bh is either unmodified or with no verified bit * set (see ext4_ext_get_access()). So just clear the verified bit * of the successfully modified extents buffers, which will force * these extents to be checked to avoid using inconsistent data. */ while (++k < depth) clear_buffer_verified(path[k].p_bh); return err; } static int ext4_can_extents_be_merged(struct inode *inode, struct ext4_extent *ex1, struct ext4_extent *ex2) { unsigned short ext1_ee_len, ext2_ee_len; if (ext4_ext_is_unwritten(ex1) != ext4_ext_is_unwritten(ex2)) return 0; ext1_ee_len = ext4_ext_get_actual_len(ex1); ext2_ee_len = ext4_ext_get_actual_len(ex2); if (le32_to_cpu(ex1->ee_block) + ext1_ee_len != le32_to_cpu(ex2->ee_block)) return 0; if (ext1_ee_len + ext2_ee_len > EXT_INIT_MAX_LEN) return 0; if (ext4_ext_is_unwritten(ex1) && ext1_ee_len + ext2_ee_len > EXT_UNWRITTEN_MAX_LEN) return 0; #ifdef AGGRESSIVE_TEST if (ext1_ee_len >= 4) return 0; #endif if (ext4_ext_pblock(ex1) + ext1_ee_len == ext4_ext_pblock(ex2)) return 1; return 0; } /* * This function tries to merge the "ex" extent to the next extent in the tree. * It always tries to merge towards right. If you want to merge towards * left, pass "ex - 1" as argument instead of "ex". * Returns 0 if the extents (ex and ex+1) were _not_ merged and returns * 1 if they got merged. */ static int ext4_ext_try_to_merge_right(struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth, len; int merge_done = 0, unwritten; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; while (ex < EXT_LAST_EXTENT(eh)) { if (!ext4_can_extents_be_merged(inode, ex, ex + 1)) break; /* merge with next extent! */ unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(ex + 1)); if (unwritten) ext4_ext_mark_unwritten(ex); if (ex + 1 < EXT_LAST_EXTENT(eh)) { len = (EXT_LAST_EXTENT(eh) - ex - 1) * sizeof(struct ext4_extent); memmove(ex + 1, ex + 2, len); } le16_add_cpu(&eh->eh_entries, -1); merge_done = 1; WARN_ON(eh->eh_entries == 0); if (!eh->eh_entries) EXT4_ERROR_INODE(inode, "eh->eh_entries = 0!"); } return merge_done; } /* * This function does a very simple check to see if we can collapse * an extent tree with a single extent tree leaf block into the inode. */ static void ext4_ext_try_to_merge_up(handle_t *handle, struct inode *inode, struct ext4_ext_path *path) { size_t s; unsigned max_root = ext4_ext_space_root(inode, 0); ext4_fsblk_t blk; if ((path[0].p_depth != 1) || (le16_to_cpu(path[0].p_hdr->eh_entries) != 1) || (le16_to_cpu(path[1].p_hdr->eh_entries) > max_root)) return; /* * We need to modify the block allocation bitmap and the block * group descriptor to release the extent tree block. If we * can't get the journal credits, give up. */ if (ext4_journal_extend(handle, 2, ext4_free_metadata_revoke_credits(inode->i_sb, 1))) return; /* * Copy the extent data up to the inode */ blk = ext4_idx_pblock(path[0].p_idx); s = le16_to_cpu(path[1].p_hdr->eh_entries) * sizeof(struct ext4_extent_idx); s += sizeof(struct ext4_extent_header); path[1].p_maxdepth = path[0].p_maxdepth; memcpy(path[0].p_hdr, path[1].p_hdr, s); path[0].p_depth = 0; path[0].p_ext = EXT_FIRST_EXTENT(path[0].p_hdr) + (path[1].p_ext - EXT_FIRST_EXTENT(path[1].p_hdr)); path[0].p_hdr->eh_max = cpu_to_le16(max_root); ext4_ext_path_brelse(path + 1); ext4_free_blocks(handle, inode, NULL, blk, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); } /* * This function tries to merge the @ex extent to neighbours in the tree, then * tries to collapse the extent tree into the inode. */ static void ext4_ext_try_to_merge(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *ex) { struct ext4_extent_header *eh; unsigned int depth; int merge_done = 0; depth = ext_depth(inode); BUG_ON(path[depth].p_hdr == NULL); eh = path[depth].p_hdr; if (ex > EXT_FIRST_EXTENT(eh)) merge_done = ext4_ext_try_to_merge_right(inode, path, ex - 1); if (!merge_done) (void) ext4_ext_try_to_merge_right(inode, path, ex); ext4_ext_try_to_merge_up(handle, inode, path); } /* * check if a portion of the "newext" extent overlaps with an * existing extent. * * If there is an overlap discovered, it updates the length of the newext * such that there will be no overlap, and then returns 1. * If there is no overlap found, it returns 0. */ static unsigned int ext4_ext_check_overlap(struct ext4_sb_info *sbi, struct inode *inode, struct ext4_extent *newext, struct ext4_ext_path *path) { ext4_lblk_t b1, b2; unsigned int depth, len1; unsigned int ret = 0; b1 = le32_to_cpu(newext->ee_block); len1 = ext4_ext_get_actual_len(newext); depth = ext_depth(inode); if (!path[depth].p_ext) goto out; b2 = EXT4_LBLK_CMASK(sbi, le32_to_cpu(path[depth].p_ext->ee_block)); /* * get the next allocated block if the extent in the path * is before the requested block(s) */ if (b2 < b1) { b2 = ext4_ext_next_allocated_block(path); if (b2 == EXT_MAX_BLOCKS) goto out; b2 = EXT4_LBLK_CMASK(sbi, b2); } /* check for wrap through zero on extent logical start block*/ if (b1 + len1 < b1) { len1 = EXT_MAX_BLOCKS - b1; newext->ee_len = cpu_to_le16(len1); ret = 1; } /* check for overlap */ if (b1 + len1 > b2) { newext->ee_len = cpu_to_le16(b2 - b1); ret = 1; } out: return ret; } /* * ext4_ext_insert_extent: * tries to merge requested extent into the existing extent or * inserts requested extent as new one into the tree, * creating new leaf in the no-space case. */ struct ext4_ext_path * ext4_ext_insert_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_extent *newext, int gb_flags) { struct ext4_extent_header *eh; struct ext4_extent *ex, *fex; struct ext4_extent *nearex; /* nearest extent */ int depth, len, err = 0; ext4_lblk_t next; int mb_flags = 0, unwritten; KUNIT_STATIC_STUB_REDIRECT(ext4_ext_insert_extent, handle, inode, path, newext, gb_flags); if (gb_flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) mb_flags |= EXT4_MB_DELALLOC_RESERVED; if (unlikely(ext4_ext_get_actual_len(newext) == 0)) { EXT4_ERROR_INODE(inode, "ext4_ext_get_actual_len(newext) == 0"); err = -EFSCORRUPTED; goto errout; } depth = ext_depth(inode); ex = path[depth].p_ext; eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EFSCORRUPTED; goto errout; } /* try to insert block into found extent and return */ if (ex && !(gb_flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) { /* * Try to see whether we should rather test the extent on * right from ex, or from the left of ex. This is because * ext4_find_extent() can return either extent on the * left, or on the right from the searched position. This * will make merging more effective. */ if (ex < EXT_LAST_EXTENT(eh) && (le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex) < le32_to_cpu(newext->ee_block))) { ex += 1; goto prepend; } else if ((ex > EXT_FIRST_EXTENT(eh)) && (le32_to_cpu(newext->ee_block) + ext4_ext_get_actual_len(newext) < le32_to_cpu(ex->ee_block))) ex -= 1; /* Try to append newex to the ex */ if (ext4_can_extents_be_merged(inode, ex, newext)) { ext_debug(inode, "append [%d]%d block to %u:[%d]%d" "(from %llu)\n", ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; unwritten = ext4_ext_is_unwritten(ex); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); nearex = ex; goto merge; } prepend: /* Try to prepend newex to the ex */ if (ext4_can_extents_be_merged(inode, newext, ex)) { ext_debug(inode, "prepend %u[%d]%d block to %u:[%d]%d" "(from %llu)\n", le32_to_cpu(newext->ee_block), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), le32_to_cpu(ex->ee_block), ext4_ext_is_unwritten(ex), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex)); err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; unwritten = ext4_ext_is_unwritten(ex); ex->ee_block = newext->ee_block; ext4_ext_store_pblock(ex, ext4_ext_pblock(newext)); ex->ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex) + ext4_ext_get_actual_len(newext)); if (unwritten) ext4_ext_mark_unwritten(ex); nearex = ex; goto merge; } } depth = ext_depth(inode); eh = path[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) goto has_space; /* probably next leaf has space for us? */ fex = EXT_LAST_EXTENT(eh); next = EXT_MAX_BLOCKS; if (le32_to_cpu(newext->ee_block) > le32_to_cpu(fex->ee_block)) next = ext4_ext_next_leaf_block(path); if (next != EXT_MAX_BLOCKS) { struct ext4_ext_path *npath; ext_debug(inode, "next leaf block - %u\n", next); npath = ext4_find_extent(inode, next, NULL, gb_flags); if (IS_ERR(npath)) { err = PTR_ERR(npath); goto errout; } BUG_ON(npath->p_depth != path->p_depth); eh = npath[depth].p_hdr; if (le16_to_cpu(eh->eh_entries) < le16_to_cpu(eh->eh_max)) { ext_debug(inode, "next leaf isn't full(%d)\n", le16_to_cpu(eh->eh_entries)); ext4_free_ext_path(path); path = npath; goto has_space; } ext_debug(inode, "next leaf has no free space(%d,%d)\n", le16_to_cpu(eh->eh_entries), le16_to_cpu(eh->eh_max)); ext4_free_ext_path(npath); } /* * There is no free space in the found leaf. * We're gonna add a new leaf in the tree. */ if (gb_flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) mb_flags |= EXT4_MB_USE_RESERVED; path = ext4_ext_create_new_leaf(handle, inode, mb_flags, gb_flags, path, newext); if (IS_ERR(path)) return path; depth = ext_depth(inode); eh = path[depth].p_hdr; has_space: nearex = path[depth].p_ext; err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; if (!nearex) { /* there is no extent in this leaf, create first one */ ext_debug(inode, "first extent in the leaf: %u:%llu:[%d]%d\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext)); nearex = EXT_FIRST_EXTENT(eh); } else { if (le32_to_cpu(newext->ee_block) > le32_to_cpu(nearex->ee_block)) { /* Insert after */ ext_debug(inode, "insert %u:%llu:[%d]%d before: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); nearex++; } else { /* Insert before */ BUG_ON(newext->ee_block == nearex->ee_block); ext_debug(inode, "insert %u:%llu:[%d]%d after: " "nearest %p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), nearex); } len = EXT_LAST_EXTENT(eh) - nearex + 1; if (len > 0) { ext_debug(inode, "insert %u:%llu:[%d]%d: " "move %d extents from 0x%p to 0x%p\n", le32_to_cpu(newext->ee_block), ext4_ext_pblock(newext), ext4_ext_is_unwritten(newext), ext4_ext_get_actual_len(newext), len, nearex, nearex + 1); memmove(nearex + 1, nearex, len * sizeof(struct ext4_extent)); } } le16_add_cpu(&eh->eh_entries, 1); path[depth].p_ext = nearex; nearex->ee_block = newext->ee_block; ext4_ext_store_pblock(nearex, ext4_ext_pblock(newext)); nearex->ee_len = newext->ee_len; merge: /* try to merge extents */ if (!(gb_flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) ext4_ext_try_to_merge(handle, inode, path, nearex); /* time to correct all indexes above */ err = ext4_ext_correct_indexes(handle, inode, path); if (err) goto errout; err = ext4_ext_dirty(handle, inode, path + path->p_depth); if (err) goto errout; return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } static int ext4_fill_es_cache_info(struct inode *inode, ext4_lblk_t block, ext4_lblk_t num, struct fiemap_extent_info *fieinfo) { ext4_lblk_t next, end = block + num - 1; struct extent_status es; unsigned char blksize_bits = inode->i_sb->s_blocksize_bits; unsigned int flags; int err; while (block <= end) { next = 0; flags = 0; if (!ext4_es_lookup_extent(inode, block, &next, &es, NULL)) break; if (ext4_es_is_unwritten(&es)) flags |= FIEMAP_EXTENT_UNWRITTEN; if (ext4_es_is_delayed(&es)) flags |= (FIEMAP_EXTENT_DELALLOC | FIEMAP_EXTENT_UNKNOWN); if (ext4_es_is_hole(&es)) flags |= EXT4_FIEMAP_EXTENT_HOLE; if (next == 0) flags |= FIEMAP_EXTENT_LAST; if (flags & (FIEMAP_EXTENT_DELALLOC| EXT4_FIEMAP_EXTENT_HOLE)) es.es_pblk = 0; else es.es_pblk = ext4_es_pblock(&es); err = fiemap_fill_next_extent(fieinfo, (__u64)es.es_lblk << blksize_bits, (__u64)es.es_pblk << blksize_bits, (__u64)es.es_len << blksize_bits, flags); if (next == 0) break; block = next; if (err < 0) return err; if (err == 1) return 0; } return 0; } /* * ext4_ext_find_hole - find hole around given block according to the given path * @inode: inode we lookup in * @path: path in extent tree to @lblk * @lblk: pointer to logical block around which we want to determine hole * * Determine hole length (and start if easily possible) around given logical * block. We don't try too hard to find the beginning of the hole but @path * actually points to extent before @lblk, we provide it. * * The function returns the length of a hole starting at @lblk. We update @lblk * to the beginning of the hole if we managed to find it. */ static ext4_lblk_t ext4_ext_find_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t *lblk) { int depth = ext_depth(inode); struct ext4_extent *ex; ext4_lblk_t len; ex = path[depth].p_ext; if (ex == NULL) { /* there is no extent yet, so gap is [0;-] */ *lblk = 0; len = EXT_MAX_BLOCKS; } else if (*lblk < le32_to_cpu(ex->ee_block)) { len = le32_to_cpu(ex->ee_block) - *lblk; } else if (*lblk >= le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)) { ext4_lblk_t next; *lblk = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); next = ext4_ext_next_allocated_block(path); BUG_ON(next == *lblk); len = next - *lblk; } else { BUG(); } return len; } /* * ext4_ext_rm_idx: * removes index from the index block. */ static int ext4_ext_rm_idx(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, int depth) { int err; ext4_fsblk_t leaf; int k = depth - 1; /* free index block */ leaf = ext4_idx_pblock(path[k].p_idx); if (unlikely(path[k].p_hdr->eh_entries == 0)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr->eh_entries == 0", k); return -EFSCORRUPTED; } err = ext4_ext_get_access(handle, inode, path + k); if (err) return err; if (path[k].p_idx != EXT_LAST_INDEX(path[k].p_hdr)) { int len = EXT_LAST_INDEX(path[k].p_hdr) - path[k].p_idx; len *= sizeof(struct ext4_extent_idx); memmove(path[k].p_idx, path[k].p_idx + 1, len); } le16_add_cpu(&path[k].p_hdr->eh_entries, -1); err = ext4_ext_dirty(handle, inode, path + k); if (err) return err; ext_debug(inode, "index is empty, remove it, free block %llu\n", leaf); trace_ext4_ext_rm_idx(inode, leaf); ext4_free_blocks(handle, inode, NULL, leaf, 1, EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET); while (--k >= 0) { if (path[k + 1].p_idx != EXT_FIRST_INDEX(path[k + 1].p_hdr)) break; err = ext4_ext_get_access(handle, inode, path + k); if (err) goto clean; path[k].p_idx->ei_block = path[k + 1].p_idx->ei_block; err = ext4_ext_dirty(handle, inode, path + k); if (err) goto clean; } return 0; clean: /* * The path[k].p_bh is either unmodified or with no verified bit * set (see ext4_ext_get_access()). So just clear the verified bit * of the successfully modified extents buffers, which will force * these extents to be checked to avoid using inconsistent data. */ while (++k < depth) clear_buffer_verified(path[k].p_bh); return err; } /* * ext4_ext_calc_credits_for_single_extent: * This routine returns max. credits that needed to insert an extent * to the extent tree. * When pass the actual path, the caller should calculate credits * under i_data_sem. */ int ext4_ext_calc_credits_for_single_extent(struct inode *inode, int nrblocks, struct ext4_ext_path *path) { if (path) { int depth = ext_depth(inode); int ret = 0; /* probably there is space in leaf? */ if (le16_to_cpu(path[depth].p_hdr->eh_entries) < le16_to_cpu(path[depth].p_hdr->eh_max)) { /* * There are some space in the leaf tree, no * need to account for leaf block credit * * bitmaps and block group descriptor blocks * and other metadata blocks still need to be * accounted. */ /* 1 bitmap, 1 block group descriptor */ ret = 2 + EXT4_META_TRANS_BLOCKS(inode->i_sb); return ret; } } return ext4_chunk_trans_blocks(inode, nrblocks); } /* * How many index/leaf blocks need to change/allocate to add @extents extents? * * If we add a single extent, then in the worse case, each tree level * index/leaf need to be changed in case of the tree split. * * If more extents are inserted, they could cause the whole tree split more * than once, but this is really rare. */ int ext4_ext_index_trans_blocks(struct inode *inode, int extents) { int index; /* If we are converting the inline data, only one is needed here. */ if (ext4_has_inline_data(inode)) return 1; /* * Extent tree can change between the time we estimate credits and * the time we actually modify the tree. Assume the worst case. */ if (extents <= 1) index = (EXT4_MAX_EXTENT_DEPTH * 2) + extents; else index = (EXT4_MAX_EXTENT_DEPTH * 3) + DIV_ROUND_UP(extents, ext4_ext_space_block(inode, 0)); return index; } static inline int get_default_free_blocks_flags(struct inode *inode) { if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) || ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE)) return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET; else if (ext4_should_journal_data(inode)) return EXT4_FREE_BLOCKS_FORGET; return 0; } /* * ext4_rereserve_cluster - increment the reserved cluster count when * freeing a cluster with a pending reservation * * @inode - file containing the cluster * @lblk - logical block in cluster to be reserved * * Increments the reserved cluster count and adjusts quota in a bigalloc * file system when freeing a partial cluster containing at least one * delayed and unwritten block. A partial cluster meeting that * requirement will have a pending reservation. If so, the * RERESERVE_CLUSTER flag is used when calling ext4_free_blocks() to * defer reserved and allocated space accounting to a subsequent call * to this function. */ static void ext4_rereserve_cluster(struct inode *inode, ext4_lblk_t lblk) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_inode_info *ei = EXT4_I(inode); dquot_reclaim_block(inode, EXT4_C2B(sbi, 1)); spin_lock(&ei->i_block_reservation_lock); ei->i_reserved_data_blocks++; percpu_counter_add(&sbi->s_dirtyclusters_counter, 1); spin_unlock(&ei->i_block_reservation_lock); percpu_counter_add(&sbi->s_freeclusters_counter, 1); ext4_remove_pending(inode, lblk); } static int ext4_remove_blocks(handle_t *handle, struct inode *inode, struct ext4_extent *ex, struct partial_cluster *partial, ext4_lblk_t from, ext4_lblk_t to) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); unsigned short ee_len = ext4_ext_get_actual_len(ex); ext4_fsblk_t last_pblk, pblk; ext4_lblk_t num; int flags; /* only extent tail removal is allowed */ if (from < le32_to_cpu(ex->ee_block) || to != le32_to_cpu(ex->ee_block) + ee_len - 1) { ext4_error(sbi->s_sb, "strange request: removal(2) %u-%u from %u:%u", from, to, le32_to_cpu(ex->ee_block), ee_len); return 0; } #ifdef EXTENTS_STATS spin_lock(&sbi->s_ext_stats_lock); sbi->s_ext_blocks += ee_len; sbi->s_ext_extents++; if (ee_len < sbi->s_ext_min) sbi->s_ext_min = ee_len; if (ee_len > sbi->s_ext_max) sbi->s_ext_max = ee_len; if (ext_depth(inode) > sbi->s_depth_max) sbi->s_depth_max = ext_depth(inode); spin_unlock(&sbi->s_ext_stats_lock); #endif trace_ext4_remove_blocks(inode, ex, from, to, partial); /* * if we have a partial cluster, and it's different from the * cluster of the last block in the extent, we free it */ last_pblk = ext4_ext_pblock(ex) + ee_len - 1; if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, last_pblk)) { if (partial->state == tofree) { flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } num = le32_to_cpu(ex->ee_block) + ee_len - from; pblk = ext4_ext_pblock(ex) + ee_len - num; /* * We free the partial cluster at the end of the extent (if any), * unless the cluster is used by another extent (partial_cluster * state is nofree). If a partial cluster exists here, it must be * shared with the last block in the extent. */ flags = get_default_free_blocks_flags(inode); /* partial, left end cluster aligned, right end unaligned */ if ((EXT4_LBLK_COFF(sbi, to) != sbi->s_cluster_ratio - 1) && (EXT4_LBLK_CMASK(sbi, to) >= from) && (partial->state != nofree)) { if (ext4_is_pending(inode, to)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_PBLK_CMASK(sbi, last_pblk), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, to); partial->state = initial; flags = get_default_free_blocks_flags(inode); } flags |= EXT4_FREE_BLOCKS_NOFREE_LAST_CLUSTER; /* * For bigalloc file systems, we never free a partial cluster * at the beginning of the extent. Instead, we check to see if we * need to free it on a subsequent call to ext4_remove_blocks, * or at the end of ext4_ext_rm_leaf or ext4_ext_remove_space. */ flags |= EXT4_FREE_BLOCKS_NOFREE_FIRST_CLUSTER; ext4_free_blocks(handle, inode, NULL, pblk, num, flags); /* reset the partial cluster if we've freed past it */ if (partial->state != initial && partial->pclu != EXT4_B2C(sbi, pblk)) partial->state = initial; /* * If we've freed the entire extent but the beginning is not left * cluster aligned and is not marked as ineligible for freeing we * record the partial cluster at the beginning of the extent. It * wasn't freed by the preceding ext4_free_blocks() call, and we * need to look farther to the left to determine if it's to be freed * (not shared with another extent). Else, reset the partial * cluster - we're either done freeing or the beginning of the * extent is left cluster aligned. */ if (EXT4_LBLK_COFF(sbi, from) && num == ee_len) { if (partial->state == initial) { partial->pclu = EXT4_B2C(sbi, pblk); partial->lblk = from; partial->state = tofree; } } else { partial->state = initial; } return 0; } /* * ext4_ext_rm_leaf() Removes the extents associated with the * blocks appearing between "start" and "end". Both "start" * and "end" must appear in the same extent or EIO is returned. * * @handle: The journal handle * @inode: The files inode * @path: The path to the leaf * @partial_cluster: The cluster which we'll have to free if all extents * has been released from it. However, if this value is * negative, it's a cluster just to the right of the * punched region and it must not be freed. * @start: The first block to remove * @end: The last block to remove */ static int ext4_ext_rm_leaf(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct partial_cluster *partial, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int err = 0, correct_index = 0; int depth = ext_depth(inode), credits, revoke_credits; struct ext4_extent_header *eh; ext4_lblk_t a, b; unsigned num; ext4_lblk_t ex_ee_block; unsigned short ex_ee_len; unsigned unwritten = 0; struct ext4_extent *ex; ext4_fsblk_t pblk; /* the header must be checked already in ext4_ext_remove_space() */ ext_debug(inode, "truncate since %u in leaf to %u\n", start, end); if (!path[depth].p_hdr) path[depth].p_hdr = ext_block_hdr(path[depth].p_bh); eh = path[depth].p_hdr; if (unlikely(path[depth].p_hdr == NULL)) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); return -EFSCORRUPTED; } /* find where to start removing */ ex = path[depth].p_ext; if (!ex) ex = EXT_LAST_EXTENT(eh); ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_rm_leaf(inode, start, ex, partial); while (ex >= EXT_FIRST_EXTENT(eh) && ex_ee_block + ex_ee_len > start) { if (ext4_ext_is_unwritten(ex)) unwritten = 1; else unwritten = 0; ext_debug(inode, "remove ext %u:[%d]%d\n", ex_ee_block, unwritten, ex_ee_len); path[depth].p_ext = ex; a = max(ex_ee_block, start); b = min(ex_ee_block + ex_ee_len - 1, end); ext_debug(inode, " border %u:%u\n", a, b); /* If this extent is beyond the end of the hole, skip it */ if (end < ex_ee_block) { /* * We're going to skip this extent and move to another, * so note that its first cluster is in use to avoid * freeing it when removing blocks. Eventually, the * right edge of the truncated/punched region will * be just to the left. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex); partial->pclu = EXT4_B2C(sbi, pblk); partial->state = nofree; } ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); continue; } else if (b != ex_ee_block + ex_ee_len - 1) { EXT4_ERROR_INODE(inode, "can not handle truncate %u:%u " "on extent %u:%u", start, end, ex_ee_block, ex_ee_block + ex_ee_len - 1); err = -EFSCORRUPTED; goto out; } else if (a != ex_ee_block) { /* remove tail of the extent */ num = a - ex_ee_block; } else { /* remove whole extent: excellent! */ num = 0; } /* * 3 for leaf, sb, and inode plus 2 (bmap and group * descriptor) for each block group; assume two block * groups plus ex_ee_len/blocks_per_block_group for * the worst case */ credits = 7 + 2*(ex_ee_len/EXT4_BLOCKS_PER_GROUP(inode->i_sb)); if (ex == EXT_FIRST_EXTENT(eh)) { correct_index = 1; credits += (ext_depth(inode)) + 1; } credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(inode->i_sb); /* * We may end up freeing some index blocks and data from the * punched range. Note that partial clusters are accounted for * by ext4_free_data_revoke_credits(). */ revoke_credits = ext4_free_metadata_revoke_credits(inode->i_sb, ext_depth(inode)) + ext4_free_data_revoke_credits(inode, b - a + 1); err = ext4_datasem_ensure_credits(handle, inode, credits, credits, revoke_credits); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; err = ext4_remove_blocks(handle, inode, ex, partial, a, b); if (err) goto out; if (num == 0) /* this extent is removed; mark slot entirely unused */ ext4_ext_store_pblock(ex, 0); ex->ee_len = cpu_to_le16(num); /* * Do not mark unwritten if all the blocks in the * extent have been removed. */ if (unwritten && num) ext4_ext_mark_unwritten(ex); /* * If the extent was completely released, * we need to remove it from the leaf */ if (num == 0) { if (end != EXT_MAX_BLOCKS - 1) { /* * For hole punching, we need to scoot all the * extents up when an extent is removed so that * we dont have blank extents in the middle */ memmove(ex, ex+1, (EXT_LAST_EXTENT(eh) - ex) * sizeof(struct ext4_extent)); /* Now get rid of the one at the end */ memset(EXT_LAST_EXTENT(eh), 0, sizeof(struct ext4_extent)); } le16_add_cpu(&eh->eh_entries, -1); } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; ext_debug(inode, "new extent: %u:%u:%llu\n", ex_ee_block, num, ext4_ext_pblock(ex)); ex--; ex_ee_block = le32_to_cpu(ex->ee_block); ex_ee_len = ext4_ext_get_actual_len(ex); } if (correct_index && eh->eh_entries) err = ext4_ext_correct_indexes(handle, inode, path); /* * If there's a partial cluster and at least one extent remains in * the leaf, free the partial cluster if it isn't shared with the * current extent. If it is shared with the current extent * we reset the partial cluster because we've reached the start of the * truncated/punched region and we're done removing blocks. */ if (partial->state == tofree && ex >= EXT_FIRST_EXTENT(eh)) { pblk = ext4_ext_pblock(ex) + ex_ee_len - 1; if (partial->pclu != EXT4_B2C(sbi, pblk)) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial->lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial->pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial->lblk); } partial->state = initial; } /* if this leaf is free, then we should * remove it from index block above */ if (err == 0 && eh->eh_entries == 0 && path[depth].p_bh != NULL) err = ext4_ext_rm_idx(handle, inode, path, depth); out: return err; } /* * ext4_ext_more_to_rm: * returns 1 if current index has to be freed (even partial) */ static int ext4_ext_more_to_rm(struct ext4_ext_path *path) { BUG_ON(path->p_idx == NULL); if (path->p_idx < EXT_FIRST_INDEX(path->p_hdr)) return 0; /* * if truncate on deeper level happened, it wasn't partial, * so we have to consider current index for truncation */ if (le16_to_cpu(path->p_hdr->eh_entries) == path->p_block) return 0; return 1; } int ext4_ext_remove_space(struct inode *inode, ext4_lblk_t start, ext4_lblk_t end) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); int depth = ext_depth(inode); struct ext4_ext_path *path = NULL; struct partial_cluster partial; handle_t *handle; int i = 0, err = 0; int flags = EXT4_EX_NOCACHE | EXT4_EX_NOFAIL; partial.pclu = 0; partial.lblk = 0; partial.state = initial; ext_debug(inode, "truncate since %u to %u\n", start, end); /* probably first extent we're gonna free will be last in block */ handle = ext4_journal_start_with_revoke(inode, EXT4_HT_TRUNCATE, depth + 1, ext4_free_metadata_revoke_credits(inode->i_sb, depth)); if (IS_ERR(handle)) return PTR_ERR(handle); again: trace_ext4_ext_remove_space(inode, start, end, depth); /* * Check if we are removing extents inside the extent tree. If that * is the case, we are going to punch a hole inside the extent tree * so we have to check whether we need to split the extent covering * the last block to remove so we can easily remove the part of it * in ext4_ext_rm_leaf(). */ if (end < EXT_MAX_BLOCKS - 1) { struct ext4_extent *ex; ext4_lblk_t ee_block, ex_end, lblk; ext4_fsblk_t pblk; /* find extent for or closest extent to this block */ path = ext4_find_extent(inode, end, NULL, flags); if (IS_ERR(path)) { ext4_journal_stop(handle); return PTR_ERR(path); } depth = ext_depth(inode); /* Leaf not may not exist only if inode has no blocks at all */ ex = path[depth].p_ext; if (!ex) { if (depth) { EXT4_ERROR_INODE(inode, "path[%d].p_hdr == NULL", depth); err = -EFSCORRUPTED; } goto out; } ee_block = le32_to_cpu(ex->ee_block); ex_end = ee_block + ext4_ext_get_actual_len(ex) - 1; /* * See if the last block is inside the extent, if so split * the extent at 'end' block so we can easily remove the * tail of the first part of the split extent in * ext4_ext_rm_leaf(). */ if (end >= ee_block && end < ex_end) { /* * If we're going to split the extent, note that * the cluster containing the block after 'end' is * in use to avoid freeing it when removing blocks. */ if (sbi->s_cluster_ratio > 1) { pblk = ext4_ext_pblock(ex) + end - ee_block + 1; partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } /* * Split the extent in two so that 'end' is the last * block in the first new extent. Also we should not * fail removing space due to ENOSPC so try to use * reserved block if that happens. */ path = ext4_force_split_extent_at(handle, inode, path, end + 1, 1); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; } } else if (sbi->s_cluster_ratio > 1 && end >= ex_end && partial.state == initial) { /* * If we're punching, there's an extent to the right. * If the partial cluster hasn't been set, set it to * that extent's first cluster and its state to nofree * so it won't be freed should it contain blocks to be * removed. If it's already set (tofree/nofree), we're * retrying and keep the original partial cluster info * so a cluster marked tofree as a result of earlier * extent removal is not lost. */ lblk = ex_end + 1; err = ext4_ext_search_right(inode, path, &lblk, &pblk, NULL, flags); if (err < 0) goto out; if (pblk) { partial.pclu = EXT4_B2C(sbi, pblk); partial.state = nofree; } } } /* * We start scanning from right side, freeing all the blocks * after i_size and walking into the tree depth-wise. */ depth = ext_depth(inode); if (path) { int k = i = depth; while (--k > 0) path[k].p_block = le16_to_cpu(path[k].p_hdr->eh_entries)+1; } else { path = kzalloc_objs(struct ext4_ext_path, depth + 1, GFP_NOFS | __GFP_NOFAIL); path[0].p_maxdepth = path[0].p_depth = depth; path[0].p_hdr = ext_inode_hdr(inode); i = 0; if (ext4_ext_check(inode, path[0].p_hdr, depth, 0)) { err = -EFSCORRUPTED; goto out; } } err = 0; while (i >= 0 && err == 0) { if (i == depth) { /* this is leaf block */ err = ext4_ext_rm_leaf(handle, inode, path, &partial, start, end); /* root level has p_bh == NULL, brelse() eats this */ ext4_ext_path_brelse(path + i); i--; continue; } /* this is index block */ if (!path[i].p_hdr) { ext_debug(inode, "initialize header\n"); path[i].p_hdr = ext_block_hdr(path[i].p_bh); } if (!path[i].p_idx) { /* this level hasn't been touched yet */ path[i].p_idx = EXT_LAST_INDEX(path[i].p_hdr); path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries)+1; ext_debug(inode, "init index ptr: hdr 0x%p, num %d\n", path[i].p_hdr, le16_to_cpu(path[i].p_hdr->eh_entries)); } else { /* we were already here, see at next index */ path[i].p_idx--; } ext_debug(inode, "level %d - index, first 0x%p, cur 0x%p\n", i, EXT_FIRST_INDEX(path[i].p_hdr), path[i].p_idx); if (ext4_ext_more_to_rm(path + i)) { struct buffer_head *bh; /* go to the next level */ ext_debug(inode, "move to level %d (block %llu)\n", i + 1, ext4_idx_pblock(path[i].p_idx)); memset(path + i + 1, 0, sizeof(*path)); bh = read_extent_tree_block(inode, path[i].p_idx, depth - i - 1, flags); if (IS_ERR(bh)) { /* should we reset i_size? */ err = PTR_ERR(bh); break; } /* Yield here to deal with large extent trees. * Should be a no-op if we did IO above. */ cond_resched(); if (WARN_ON(i + 1 > depth)) { err = -EFSCORRUPTED; break; } path[i + 1].p_bh = bh; /* save actual number of indexes since this * number is changed at the next iteration */ path[i].p_block = le16_to_cpu(path[i].p_hdr->eh_entries); i++; } else { /* we finished processing this index, go up */ if (path[i].p_hdr->eh_entries == 0 && i > 0) { /* index is empty, remove it; * handle must be already prepared by the * truncatei_leaf() */ err = ext4_ext_rm_idx(handle, inode, path, i); } /* root level has p_bh == NULL, brelse() eats this */ ext4_ext_path_brelse(path + i); i--; ext_debug(inode, "return to level %d\n", i); } } trace_ext4_ext_remove_space_done(inode, start, end, depth, &partial, path->p_hdr->eh_entries); /* * if there's a partial cluster and we have removed the first extent * in the file, then we also free the partial cluster, if any */ if (partial.state == tofree && err == 0) { int flags = get_default_free_blocks_flags(inode); if (ext4_is_pending(inode, partial.lblk)) flags |= EXT4_FREE_BLOCKS_RERESERVE_CLUSTER; ext4_free_blocks(handle, inode, NULL, EXT4_C2B(sbi, partial.pclu), sbi->s_cluster_ratio, flags); if (flags & EXT4_FREE_BLOCKS_RERESERVE_CLUSTER) ext4_rereserve_cluster(inode, partial.lblk); partial.state = initial; } /* TODO: flexible tree reduction should be here */ if (path->p_hdr->eh_entries == 0) { /* * truncate to zero freed all the tree, * so we need to correct eh_depth */ err = ext4_ext_get_access(handle, inode, path); if (err == 0) { ext_inode_hdr(inode)->eh_depth = 0; ext_inode_hdr(inode)->eh_max = cpu_to_le16(ext4_ext_space_root(inode, 0)); err = ext4_ext_dirty(handle, inode, path); } } out: ext4_free_ext_path(path); path = NULL; if (err == -EAGAIN) goto again; ext4_journal_stop(handle); return err; } /* * called at mount time */ void ext4_ext_init(struct super_block *sb) { /* * possible initialization would be here */ if (ext4_has_feature_extents(sb)) { #if defined(AGGRESSIVE_TEST) || defined(CHECK_BINSEARCH) || defined(EXTENTS_STATS) printk(KERN_INFO "EXT4-fs: file extents enabled" #ifdef AGGRESSIVE_TEST ", aggressive tests" #endif #ifdef CHECK_BINSEARCH ", check binsearch" #endif #ifdef EXTENTS_STATS ", stats" #endif "\n"); #endif #ifdef EXTENTS_STATS spin_lock_init(&EXT4_SB(sb)->s_ext_stats_lock); EXT4_SB(sb)->s_ext_min = 1 << 30; EXT4_SB(sb)->s_ext_max = 0; #endif } } /* * called at umount time */ void ext4_ext_release(struct super_block *sb) { if (!ext4_has_feature_extents(sb)) return; #ifdef EXTENTS_STATS if (EXT4_SB(sb)->s_ext_blocks && EXT4_SB(sb)->s_ext_extents) { struct ext4_sb_info *sbi = EXT4_SB(sb); printk(KERN_ERR "EXT4-fs: %lu blocks in %lu extents (%lu ave)\n", sbi->s_ext_blocks, sbi->s_ext_extents, sbi->s_ext_blocks / sbi->s_ext_extents); printk(KERN_ERR "EXT4-fs: extents: %lu min, %lu max, max depth %lu\n", sbi->s_ext_min, sbi->s_ext_max, sbi->s_depth_max); } #endif } static void ext4_zeroout_es(struct inode *inode, struct ext4_extent *ex) { ext4_lblk_t ee_block; ext4_fsblk_t ee_pblock; unsigned int ee_len; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); if (ee_len == 0) return; ext4_es_insert_extent(inode, ee_block, ee_len, ee_pblock, EXTENT_STATUS_WRITTEN, false); } /* FIXME!! we need to try to merge to left or right after zero-out */ int ext4_ext_zeroout(struct inode *inode, struct ext4_extent *ex) { ext4_fsblk_t ee_pblock; unsigned int ee_len; KUNIT_STATIC_STUB_REDIRECT(ext4_ext_zeroout, inode, ex); ee_len = ext4_ext_get_actual_len(ex); ee_pblock = ext4_ext_pblock(ex); return ext4_issue_zeroout(inode, le32_to_cpu(ex->ee_block), ee_pblock, ee_len); } /* * ext4_split_extent_at() splits an extent at given block. * * @handle: the journal handle * @inode: the file inode * @path: the path to the extent * @split: the logical block where the extent is splitted. * @flags: flags used to insert new extent to extent tree. * * * Splits extent [a, b] into two extents [a, @split) and [@split, b], states * of which are same as the original extent. No conversion is performed. * * Return an extent path pointer on success, or an error pointer on failure. On * failure, the extent is restored to original state. */ static struct ext4_ext_path *ext4_split_extent_at(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t split, int flags) { ext4_fsblk_t newblock; ext4_lblk_t ee_block; struct ext4_extent *ex, newex, orig_ex; struct ext4_extent *ex2 = NULL; unsigned int ee_len, depth; int err = 0, insert_err = 0, is_unwrit = 0; /* Do not cache extents that are in the process of being modified. */ flags |= EXT4_EX_NOCACHE; ext_debug(inode, "logical block %llu\n", (unsigned long long)split); ext4_ext_show_leaf(inode, path); depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); newblock = split - ee_block + ext4_ext_pblock(ex); is_unwrit = ext4_ext_is_unwritten(ex); BUG_ON(split < ee_block || split >= (ee_block + ee_len)); /* * No split needed */ if (split == ee_block) goto out; err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; /* case a */ memcpy(&orig_ex, ex, sizeof(orig_ex)); ex->ee_len = cpu_to_le16(split - ee_block); if (is_unwrit) ext4_ext_mark_unwritten(ex); /* * path may lead to new leaf, not to original leaf any more * after ext4_ext_insert_extent() returns, */ err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto fix_extent_len; ex2 = &newex; ex2->ee_block = cpu_to_le32(split); ex2->ee_len = cpu_to_le16(ee_len - (split - ee_block)); ext4_ext_store_pblock(ex2, newblock); if (is_unwrit) ext4_ext_mark_unwritten(ex2); path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (!IS_ERR(path)) return path; insert_err = PTR_ERR(path); err = 0; if (insert_err != -ENOSPC && insert_err != -EDQUOT && insert_err != -ENOMEM) goto out_path; /* * Get a new path to try to zeroout or fix the extent length. * Using EXT4_EX_NOFAIL guarantees that ext4_find_extent() * will not return -ENOMEM, otherwise -ENOMEM will cause a * retry in do_writepages(), and a WARN_ON may be triggered * in ext4_da_update_reserve_space() due to an incorrect * ee_len causing the i_reserved_data_blocks exception. */ path = ext4_find_extent(inode, ee_block, NULL, flags | EXT4_EX_NOFAIL); if (IS_ERR(path)) { EXT4_ERROR_INODE(inode, "Failed split extent on %u, err %pe", split, path); goto out_path; } depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "bad extent address lblock: %lu, depth: %d pblock %llu", (unsigned long)ee_block, depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; fix_extent_len: ex->ee_len = orig_ex.ee_len; err = ext4_ext_dirty(handle, inode, path + path->p_depth); out: if (err || insert_err) { ext4_free_ext_path(path); path = err ? ERR_PTR(err) : ERR_PTR(insert_err); } out_path: if (IS_ERR(path)) /* Remove all remaining potentially stale extents. */ ext4_es_remove_extent(inode, ee_block, ee_len); ext4_ext_show_leaf(inode, path); return path; } static int ext4_split_extent_zeroout(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_map_blocks *map, int flags) { struct ext4_extent *ex; unsigned int ee_len, depth; ext4_lblk_t ee_block; uint64_t lblk, pblk, len; int is_unwrit; int err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); is_unwrit = ext4_ext_is_unwritten(ex); if (flags & EXT4_GET_BLOCKS_CONVERT) { /* * EXT4_GET_BLOCKS_CONVERT: Caller wants the range specified by * map to be initialized. Zeroout everything except the map * range. */ loff_t map_end = (loff_t) map->m_lblk + map->m_len; loff_t ex_end = (loff_t) ee_block + ee_len; if (!is_unwrit) /* Shouldn't happen. Just exit */ return -EINVAL; /* zeroout left */ if (map->m_lblk > ee_block) { lblk = ee_block; len = map->m_lblk - ee_block; pblk = ext4_ext_pblock(ex); err = ext4_issue_zeroout(inode, lblk, pblk, len); if (err) /* ZEROOUT failed, just return original error */ return err; } /* zeroout right */ if (map_end < ex_end) { lblk = map_end; len = ex_end - map_end; pblk = ext4_ext_pblock(ex) + (map_end - ee_block); err = ext4_issue_zeroout(inode, lblk, pblk, len); if (err) /* ZEROOUT failed, just return original error */ return err; } } else if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { /* * EXT4_GET_BLOCKS_CONVERT_UNWRITTEN: Caller wants the * range specified by map to be marked unwritten. * Zeroout the map range leaving rest as it is. */ if (is_unwrit) /* Shouldn't happen. Just exit */ return -EINVAL; lblk = map->m_lblk; len = map->m_len; pblk = ext4_ext_pblock(ex) + (map->m_lblk - ee_block); err = ext4_issue_zeroout(inode, lblk, pblk, len); if (err) /* ZEROOUT failed, just return original error */ return err; } else { /* * We no longer perform unwritten to unwritten splits in IO paths. * Hence this should not happen. */ WARN_ON_ONCE(true); return -EINVAL; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) return err; ext4_ext_mark_initialized(ex); err = ext4_ext_dirty(handle, inode, path + depth); if (err) return err; return 0; } /* * ext4_split_extent() splits an extent and mark extent which is covered * by @map as split_flags indicates * * It may result in splitting the extent into multiple extents (up to three) * There are three possibilities: * a> There is no split required * b> Splits in two extents: Split is happening at either end of the extent * c> Splits in three extents: Somone is splitting in middle of the extent * */ static struct ext4_ext_path *ext4_split_extent(handle_t *handle, struct inode *inode, struct ext4_ext_path *path, struct ext4_map_blocks *map, int split_flag, int flags, unsigned int *allocated, bool *did_zeroout) { ext4_lblk_t ee_block, orig_ee_block; struct ext4_extent *ex; unsigned int ee_len, orig_ee_len, depth; int unwritten, orig_unwritten; int orig_err = 0; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); orig_ee_block = ee_block; orig_ee_len = ee_len; orig_unwritten = unwritten; /* Do not cache extents that are in the process of being modified. */ flags |= EXT4_EX_NOCACHE; if (map->m_lblk + map->m_len < ee_block + ee_len) { path = ext4_split_extent_at(handle, inode, path, map->m_lblk + map->m_len, flags); if (IS_ERR(path)) goto try_zeroout; /* * Update path is required because previous ext4_split_extent_at * may result in split of original leaf or extent zeroout. */ path = ext4_find_extent(inode, map->m_lblk, path, flags); if (IS_ERR(path)) goto try_zeroout; depth = ext_depth(inode); ex = path[depth].p_ext; if (!ex) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) map->m_lblk); ext4_free_ext_path(path); return ERR_PTR(-EFSCORRUPTED); } /* extent would have changed so update original values */ orig_ee_block = le32_to_cpu(ex->ee_block); orig_ee_len = ext4_ext_get_actual_len(ex); orig_unwritten = ext4_ext_is_unwritten(ex); } if (map->m_lblk >= ee_block) { path = ext4_split_extent_at(handle, inode, path, map->m_lblk, flags); if (IS_ERR(path)) goto try_zeroout; } goto success; try_zeroout: /* * There was an error in splitting the extent. So instead, just zeroout * unwritten portions and convert it to initialized as a last resort. If * there is any failure here we just return the original error */ orig_err = PTR_ERR(path); if (orig_err != -ENOSPC && orig_err != -EDQUOT && orig_err != -ENOMEM) goto out_orig_err; /* we can't zeroout? just return the original err */ if (!(split_flag & EXT4_EXT_MAY_ZEROOUT)) goto out_orig_err; if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) { int max_zeroout_blks = EXT4_SB(inode->i_sb)->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); if (map->m_len > max_zeroout_blks) goto out_orig_err; } path = ext4_find_extent(inode, map->m_lblk, NULL, flags); if (IS_ERR(path)) goto out_orig_err; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); unwritten = ext4_ext_is_unwritten(ex); /* extent to zeroout should have been unchanged but its not */ if (WARN_ON(ee_block != orig_ee_block || ee_len != orig_ee_len || unwritten != orig_unwritten)) goto out_free_path; if (ext4_split_extent_zeroout(handle, inode, path, map, flags)) goto out_free_path; /* zeroout succeeded */ if (did_zeroout) *did_zeroout = true; success: if (allocated) { if (map->m_lblk + map->m_len > ee_block + ee_len) *allocated = ee_len - (map->m_lblk - ee_block); else *allocated = map->m_len; } ext4_ext_show_leaf(inode, path); return path; out_free_path: ext4_free_ext_path(path); out_orig_err: return ERR_PTR(orig_err); } /* * This function is called by ext4_ext_map_blocks() if someone tries to write * to an unwritten extent. It may result in splitting the unwritten * extent into multiple extents (up to three - one initialized and two * unwritten). * There are three possibilities: * a> There is no split required: Entire extent should be initialized * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * Pre-conditions: * - The extent pointed to by 'path' is unwritten. * - The extent pointed to by 'path' contains a superset * of the logical span [map->m_lblk, map->m_lblk + map->m_len). * * Post-conditions on success: * - the returned value is the number of blocks beyond map->l_lblk * that are allocated and initialized. * It is guaranteed to be >= map->m_len. */ static struct ext4_ext_path * ext4_ext_convert_to_initialized(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated) { struct ext4_sb_info *sbi; struct ext4_extent_header *eh; struct ext4_map_blocks split_map; struct ext4_extent zero_ex1, zero_ex2; struct ext4_extent *ex, *abut_ex; ext4_lblk_t ee_block, eof_block; unsigned int ee_len, depth, map_len = map->m_len; int err = 0; unsigned int max_zeroout = 0; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map_len); sbi = EXT4_SB(inode->i_sb); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map_len) eof_block = map->m_lblk + map_len; depth = ext_depth(inode); eh = path[depth].p_hdr; ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); zero_ex1.ee_len = 0; zero_ex2.ee_len = 0; trace_ext4_ext_convert_to_initialized_enter(inode, map, ex); /* Pre-conditions */ BUG_ON(!ext4_ext_is_unwritten(ex)); BUG_ON(!in_range(map->m_lblk, ee_block, ee_len)); /* * Attempt to transfer newly initialized blocks from the currently * unwritten extent to its neighbor. This is much cheaper * than an insertion followed by a merge as those involve costly * memmove() calls. Transferring to the left is the common case in * steady state for workloads doing fallocate(FALLOC_FL_KEEP_SIZE) * followed by append writes. * * Limitations of the current logic: * - L1: we do not deal with writes covering the whole extent. * This would require removing the extent if the transfer * is possible. * - L2: we only attempt to merge with an extent stored in the * same extent tree node. */ *allocated = 0; if ((map->m_lblk == ee_block) && /* See if we can merge left */ (map_len < ee_len) && /*L1*/ (ex > EXT_FIRST_EXTENT(eh))) { /*L2*/ ext4_lblk_t prev_lblk; ext4_fsblk_t prev_pblk, ee_pblk; unsigned int prev_len; abut_ex = ex - 1; prev_lblk = le32_to_cpu(abut_ex->ee_block); prev_len = ext4_ext_get_actual_len(abut_ex); prev_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((prev_lblk + prev_len) == ee_block) && /*C2*/ ((prev_pblk + prev_len) == ee_pblk) && /*C3*/ (prev_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of ex by 'map_len' blocks */ ex->ee_block = cpu_to_le32(ee_block + map_len); ext4_ext_store_pblock(ex, ee_pblk + map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(prev_len + map_len); /* Result: number of initialized blocks past m_lblk */ *allocated = map_len; } } else if (((map->m_lblk + map_len) == (ee_block + ee_len)) && (map_len < ee_len) && /*L1*/ ex < EXT_LAST_EXTENT(eh)) { /*L2*/ /* See if we can merge right */ ext4_lblk_t next_lblk; ext4_fsblk_t next_pblk, ee_pblk; unsigned int next_len; abut_ex = ex + 1; next_lblk = le32_to_cpu(abut_ex->ee_block); next_len = ext4_ext_get_actual_len(abut_ex); next_pblk = ext4_ext_pblock(abut_ex); ee_pblk = ext4_ext_pblock(ex); /* * A transfer of blocks from 'ex' to 'abut_ex' is allowed * upon those conditions: * - C1: abut_ex is initialized, * - C2: abut_ex is logically abutting ex, * - C3: abut_ex is physically abutting ex, * - C4: abut_ex can receive the additional blocks without * overflowing the (initialized) length limit. */ if ((!ext4_ext_is_unwritten(abut_ex)) && /*C1*/ ((map->m_lblk + map_len) == next_lblk) && /*C2*/ ((ee_pblk + ee_len) == next_pblk) && /*C3*/ (next_len < (EXT_INIT_MAX_LEN - map_len))) { /*C4*/ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto errout; trace_ext4_ext_convert_to_initialized_fastpath(inode, map, ex, abut_ex); /* Shift the start of abut_ex by 'map_len' blocks */ abut_ex->ee_block = cpu_to_le32(next_lblk - map_len); ext4_ext_store_pblock(abut_ex, next_pblk - map_len); ex->ee_len = cpu_to_le16(ee_len - map_len); ext4_ext_mark_unwritten(ex); /* Restore the flag */ /* Extend abut_ex by 'map_len' blocks */ abut_ex->ee_len = cpu_to_le16(next_len + map_len); /* Result: number of initialized blocks past m_lblk */ *allocated = map_len; } } if (*allocated) { /* Mark the block containing both extents as dirty */ err = ext4_ext_dirty(handle, inode, path + depth); /* Update path to point to the right extent */ path[depth].p_ext = abut_ex; if (err) goto errout; goto out; } else *allocated = ee_len - (map->m_lblk - ee_block); WARN_ON(map->m_lblk < ee_block); /* * It is safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ if (ee_block + ee_len <= eof_block) max_zeroout = sbi->s_extent_max_zeroout_kb >> (inode->i_sb->s_blocksize_bits - 10); /* * five cases: * 1. split the extent into three extents. * 2. split the extent into two extents, zeroout the head of the first * extent. * 3. split the extent into two extents, zeroout the tail of the second * extent. * 4. split the extent into two extents with out zeroout. * 5. no splitting needed, just possibly zeroout the head and / or the * tail of the extent. */ split_map.m_lblk = map->m_lblk; split_map.m_len = map->m_len; if (max_zeroout && (*allocated > split_map.m_len)) { if (*allocated <= max_zeroout) { /* case 3 or 5 */ zero_ex1.ee_block = cpu_to_le32(split_map.m_lblk + split_map.m_len); zero_ex1.ee_len = cpu_to_le16(*allocated - split_map.m_len); ext4_ext_store_pblock(&zero_ex1, ext4_ext_pblock(ex) + split_map.m_lblk + split_map.m_len - ee_block); err = ext4_ext_zeroout(inode, &zero_ex1); if (err) goto fallback; split_map.m_len = *allocated; } if (split_map.m_lblk - ee_block + split_map.m_len < max_zeroout) { /* case 2 or 5 */ if (split_map.m_lblk != ee_block) { zero_ex2.ee_block = ex->ee_block; zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk - ee_block); ext4_ext_store_pblock(&zero_ex2, ext4_ext_pblock(ex)); err = ext4_ext_zeroout(inode, &zero_ex2); if (err) goto fallback; } split_map.m_len += split_map.m_lblk - ee_block; split_map.m_lblk = ee_block; *allocated = map->m_len; } } fallback: path = ext4_split_convert_extents(handle, inode, &split_map, path, flags | EXT4_GET_BLOCKS_CONVERT, NULL); if (IS_ERR(path)) return path; out: /* If we have gotten a failure, don't zero out status tree */ ext4_zeroout_es(inode, &zero_ex1); ext4_zeroout_es(inode, &zero_ex2); return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } /* * This function is called by ext4_ext_map_blocks() from * ext4_get_blocks_dio_write() when DIO to write * to an unwritten extent. * * Writing to an unwritten extent may result in splitting the unwritten * extent into multiple initialized/unwritten extents (up to three) * There are three possibilities: * a> There is no split required: Entire extent should be unwritten * b> Splits in two extents: Write is happening at either end of the extent * c> Splits in three extents: Somone is writing in middle of the extent * * This works the same way in the case of initialized -> unwritten conversion. * * One of more index blocks maybe needed if the extent tree grow after * the unwritten extent split. To prevent ENOSPC occur at the IO * complete, we need to split the unwritten extent before DIO submit * the IO. The unwritten extent called at this time will be split * into three unwritten extent(at most). After IO complete, the part * being filled will be convert to initialized by the end_io callback function * via ext4_convert_unwritten_extents(). * * The size of unwritten extent to be written is passed to the caller via the * allocated pointer. Return an extent path pointer on success, or an error * pointer on failure. */ static struct ext4_ext_path *ext4_split_convert_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated) { ext4_lblk_t eof_block; ext4_lblk_t ee_block; struct ext4_extent *ex; unsigned int ee_len; int split_flag = 0, depth, err = 0; bool did_zeroout = false; ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)map->m_lblk, map->m_len); eof_block = (EXT4_I(inode)->i_disksize + inode->i_sb->s_blocksize - 1) >> inode->i_sb->s_blocksize_bits; if (eof_block < map->m_lblk + map->m_len) eof_block = map->m_lblk + map->m_len; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); /* No split needed */ if (ee_block == map->m_lblk && ee_len == map->m_len) goto convert; /* * It is only safe to convert extent to initialized via explicit * zeroout only if extent is fully inside i_size or new_size. */ split_flag |= ee_block + ee_len <= eof_block ? EXT4_EXT_MAY_ZEROOUT : 0; /* * pass SPLIT_NOMERGE explicitly so we don't end up merging extents we * just split. */ path = ext4_split_extent(handle, inode, path, map, split_flag, flags | EXT4_GET_BLOCKS_SPLIT_NOMERGE, allocated, &did_zeroout); if (IS_ERR(path)) return path; convert: path = ext4_find_extent(inode, map->m_lblk, path, flags); if (IS_ERR(path)) return path; depth = ext_depth(inode); ex = path[depth].p_ext; /* * Conversion is already handled in case of zeroout */ if (!did_zeroout) { err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto err; if (flags & EXT4_GET_BLOCKS_CONVERT) ext4_ext_mark_initialized(ex); else if (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN) ext4_ext_mark_unwritten(ex); if (!(flags & EXT4_GET_BLOCKS_SPLIT_NOMERGE)) /* * note: ext4_ext_correct_indexes() isn't needed here because * borders are not changed */ ext4_ext_try_to_merge(handle, inode, path, ex); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto err; } /* Lets update the extent status tree after conversion */ if (!(flags & EXT4_EX_NOCACHE)) ext4_es_insert_extent(inode, le32_to_cpu(ex->ee_block), ext4_ext_get_actual_len(ex), ext4_ext_pblock(ex), ext4_ext_is_unwritten(ex) ? EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN, false); err: if (err) { ext4_free_ext_path(path); return ERR_PTR(err); } return path; } static struct ext4_ext_path * ext4_convert_unwritten_extents_endio(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags) { struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); return ext4_split_convert_extents(handle, inode, map, path, flags, NULL); } static struct ext4_ext_path * convert_initialized_extent(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated) { struct ext4_extent *ex; ext4_lblk_t ee_block; unsigned int ee_len; int depth; /* * Make sure that the extent is no bigger than we support with * unwritten extent */ if (map->m_len > EXT_UNWRITTEN_MAX_LEN) map->m_len = EXT_UNWRITTEN_MAX_LEN / 2; depth = ext_depth(inode); ex = path[depth].p_ext; ee_block = le32_to_cpu(ex->ee_block); ee_len = ext4_ext_get_actual_len(ex); ext_debug(inode, "logical block %llu, max_blocks %u\n", (unsigned long long)ee_block, ee_len); path = ext4_split_convert_extents(handle, inode, map, path, flags, NULL); if (IS_ERR(path)) return path; ext4_ext_show_leaf(inode, path); ext4_update_inode_fsync_trans(handle, inode, 1); /* * The extent might be initialized in case of zeroout. */ path = ext4_find_extent(inode, map->m_lblk, path, flags); if (IS_ERR(path)) return path; depth = ext_depth(inode); ex = path[depth].p_ext; if (ext4_ext_is_unwritten(ex)) map->m_flags |= EXT4_MAP_UNWRITTEN; else map->m_flags |= EXT4_MAP_MAPPED; if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; return path; } static struct ext4_ext_path * ext4_ext_handle_unwritten_extents(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated, ext4_fsblk_t newblock) { int err = 0; ext_debug(inode, "logical block %llu, max_blocks %u, flags 0x%x, allocated %u\n", (unsigned long long)map->m_lblk, map->m_len, flags, *allocated); ext4_ext_show_leaf(inode, path); /* * When writing into unwritten space, we should not fail to * allocate metadata blocks for the new extent block if needed. */ flags |= EXT4_GET_BLOCKS_METADATA_NOFAIL; trace_ext4_ext_handle_unwritten_extents(inode, map, flags, *allocated, newblock); /* IO end_io complete, convert the filled extent to written */ if (flags & EXT4_GET_BLOCKS_CONVERT) { path = ext4_convert_unwritten_extents_endio(handle, inode, map, path, flags); if (IS_ERR(path)) return path; ext4_update_inode_fsync_trans(handle, inode, 1); goto map_out; } /* buffered IO cases */ /* * repeat fallocate creation request * we already have an unwritten extent */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { map->m_flags |= EXT4_MAP_UNWRITTEN; goto map_out; } /* buffered READ or buffered write_begin() lookup */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { /* * We have blocks reserved already. We * return allocated blocks so that delalloc * won't do block reservation for us. But * the buffer head will be unmapped so that * a read from the block returns 0s. */ map->m_flags |= EXT4_MAP_UNWRITTEN; goto out1; } /* * Default case when (flags & EXT4_GET_BLOCKS_CREATE) == 1. * For buffered writes, at writepage time, etc. Convert a * discovered unwritten extent to written. */ path = ext4_ext_convert_to_initialized(handle, inode, map, path, flags, allocated); if (IS_ERR(path)) return path; ext4_update_inode_fsync_trans(handle, inode, 1); /* * shouldn't get a 0 allocated when converting an unwritten extent * unless m_len is 0 (bug) or extent has been corrupted */ if (unlikely(*allocated == 0)) { EXT4_ERROR_INODE(inode, "unexpected allocated == 0, m_len = %u", map->m_len); err = -EFSCORRUPTED; goto errout; } map->m_flags |= EXT4_MAP_NEW; map_out: map->m_flags |= EXT4_MAP_MAPPED; out1: map->m_pblk = newblock; if (*allocated > map->m_len) *allocated = map->m_len; map->m_len = *allocated; ext4_ext_show_leaf(inode, path); return path; errout: ext4_free_ext_path(path); return ERR_PTR(err); } /* * get_implied_cluster_alloc - check to see if the requested * allocation (in the map structure) overlaps with a cluster already * allocated in an extent. * @sb The filesystem superblock structure * @map The requested lblk->pblk mapping * @ex The extent structure which might contain an implied * cluster allocation * * This function is called by ext4_ext_map_blocks() after we failed to * find blocks that were already in the inode's extent tree. Hence, * we know that the beginning of the requested region cannot overlap * the extent from the inode's extent tree. There are three cases we * want to catch. The first is this case: * * |--- cluster # N--| * |--- extent ---| |---- requested region ---| * |==========| * * The second case that we need to test for is this one: * * |--------- cluster # N ----------------| * |--- requested region --| |------- extent ----| * |=======================| * * The third case is when the requested region lies between two extents * within the same cluster: * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| * * In each of the above cases, we need to set the map->m_pblk and * map->m_len so it corresponds to the return the extent labelled as * "|====|" from cluster #N, since it is already in use for data in * cluster EXT4_B2C(sbi, map->m_lblk). We will then return 1 to * signal to ext4_ext_map_blocks() that map->m_pblk should be treated * as a new "allocated" block region. Otherwise, we will return 0 and * ext4_ext_map_blocks() will then allocate one or more new clusters * by calling ext4_mb_new_blocks(). */ static int get_implied_cluster_alloc(struct super_block *sb, struct ext4_map_blocks *map, struct ext4_extent *ex, struct ext4_ext_path *path) { struct ext4_sb_info *sbi = EXT4_SB(sb); ext4_lblk_t c_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ext4_lblk_t ex_cluster_start, ex_cluster_end; ext4_lblk_t rr_cluster_start; ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len = ext4_ext_get_actual_len(ex); /* The extent passed in that we are trying to match */ ex_cluster_start = EXT4_B2C(sbi, ee_block); ex_cluster_end = EXT4_B2C(sbi, ee_block + ee_len - 1); /* The requested region passed into ext4_map_blocks() */ rr_cluster_start = EXT4_B2C(sbi, map->m_lblk); if ((rr_cluster_start == ex_cluster_end) || (rr_cluster_start == ex_cluster_start)) { if (rr_cluster_start == ex_cluster_end) ee_start += ee_len - 1; map->m_pblk = EXT4_PBLK_CMASK(sbi, ee_start) + c_offset; map->m_len = min(map->m_len, (unsigned) sbi->s_cluster_ratio - c_offset); /* * Check for and handle this case: * * |--------- cluster # N-------------| * |------- extent ----| * |--- requested region ---| * |===========| */ if (map->m_lblk < ee_block) map->m_len = min(map->m_len, ee_block - map->m_lblk); /* * Check for the case where there is already another allocated * block to the right of 'ex' but before the end of the cluster. * * |------------- cluster # N-------------| * |----- ex -----| |---- ex_right ----| * |------ requested region ------| * |================| */ if (map->m_lblk > ee_block) { ext4_lblk_t next = ext4_ext_next_allocated_block(path); map->m_len = min(map->m_len, next - map->m_lblk); } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 1); return 1; } trace_ext4_get_implied_cluster_alloc_exit(sb, map, 0); return 0; } /* * Determine hole length around the given logical block, first try to * locate and expand the hole from the given @path, and then adjust it * if it's partially or completely converted to delayed extents, insert * it into the extent cache tree if it's indeed a hole, finally return * the length of the determined extent. */ static ext4_lblk_t ext4_ext_determine_insert_hole(struct inode *inode, struct ext4_ext_path *path, ext4_lblk_t lblk) { ext4_lblk_t hole_start, len; struct extent_status es; hole_start = lblk; len = ext4_ext_find_hole(inode, path, &hole_start); again: ext4_es_find_extent_range(inode, &ext4_es_is_delayed, hole_start, hole_start + len - 1, &es); if (!es.es_len) goto insert_hole; /* * There's a delalloc extent in the hole, handle it if the delalloc * extent is in front of, behind and straddle the queried range. */ if (lblk >= es.es_lblk + es.es_len) { /* * The delalloc extent is in front of the queried range, * find again from the queried start block. */ len -= lblk - hole_start; hole_start = lblk; goto again; } else if (in_range(lblk, es.es_lblk, es.es_len)) { /* * The delalloc extent containing lblk, it must have been * added after ext4_map_blocks() checked the extent status * tree so we are not holding i_rwsem and delalloc info is * only stabilized by i_data_sem we are going to release * soon. Don't modify the extent status tree and report * extent as a hole, just adjust the length to the delalloc * extent's after lblk. */ len = es.es_lblk + es.es_len - lblk; return len; } else { /* * The delalloc extent is partially or completely behind * the queried range, update hole length until the * beginning of the delalloc extent. */ len = min(es.es_lblk - hole_start, len); } insert_hole: /* Put just found gap into cache to speed up subsequent requests */ ext_debug(inode, " -> %u:%u\n", hole_start, len); ext4_es_cache_extent(inode, hole_start, len, ~0, EXTENT_STATUS_HOLE); /* Update hole_len to reflect hole size after lblk */ if (hole_start != lblk) len -= lblk - hole_start; return len; } /* * Block allocation/map/preallocation routine for extents based files * * * Need to be called with * down_read(&EXT4_I(inode)->i_data_sem) if not allocating file system block * (ie, flags is zero). Otherwise down_write(&EXT4_I(inode)->i_data_sem) * * return > 0, number of blocks already mapped/allocated * if flags doesn't contain EXT4_GET_BLOCKS_CREATE and these are pre-allocated blocks * buffer head is unmapped * otherwise blocks are mapped * * return = 0, if plain look up failed (blocks have not been allocated) * buffer head is unmapped * * return < 0, error case. */ int ext4_ext_map_blocks(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, int flags) { struct ext4_ext_path *path = NULL; struct ext4_extent newex, *ex, ex2; struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); ext4_fsblk_t newblock = 0, pblk; int err = 0, depth; unsigned int allocated = 0, offset = 0; unsigned int allocated_clusters = 0; struct ext4_allocation_request ar; ext4_lblk_t cluster_offset; ext_debug(inode, "blocks %u/%u requested\n", map->m_lblk, map->m_len); trace_ext4_ext_map_blocks_enter(inode, map->m_lblk, map->m_len, flags); /* find extent for this block */ path = ext4_find_extent(inode, map->m_lblk, NULL, flags); if (IS_ERR(path)) { err = PTR_ERR(path); goto out; } depth = ext_depth(inode); /* * consistent leaf must not be empty; * this situation is possible, though, _during_ tree modification; * this is why assert can't be put in ext4_find_extent() */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address " "lblock: %lu, depth: %d pblock %lld", (unsigned long) map->m_lblk, depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } ex = path[depth].p_ext; if (ex) { ext4_lblk_t ee_block = le32_to_cpu(ex->ee_block); ext4_fsblk_t ee_start = ext4_ext_pblock(ex); unsigned short ee_len; /* * unwritten extents are treated as holes, except that * we split out initialized portions during a write. */ ee_len = ext4_ext_get_actual_len(ex); trace_ext4_ext_show_extent(inode, ee_block, ee_start, ee_len); /* if found extent covers block, simply return it */ if (in_range(map->m_lblk, ee_block, ee_len)) { newblock = map->m_lblk - ee_block + ee_start; /* number of remaining blocks in the extent */ allocated = ee_len - (map->m_lblk - ee_block); ext_debug(inode, "%u fit into %u:%d -> %llu\n", map->m_lblk, ee_block, ee_len, newblock); /* * If the extent is initialized check whether the * caller wants to convert it to unwritten. */ if ((!ext4_ext_is_unwritten(ex)) && (flags & EXT4_GET_BLOCKS_CONVERT_UNWRITTEN)) { path = convert_initialized_extent(handle, inode, map, path, flags, &allocated); if (IS_ERR(path)) err = PTR_ERR(path); goto out; } else if (!ext4_ext_is_unwritten(ex)) { map->m_flags |= EXT4_MAP_MAPPED; map->m_pblk = newblock; if (allocated > map->m_len) allocated = map->m_len; map->m_len = allocated; ext4_ext_show_leaf(inode, path); goto out; } path = ext4_ext_handle_unwritten_extents( handle, inode, map, path, flags, &allocated, newblock); if (IS_ERR(path)) err = PTR_ERR(path); goto out; } } /* * requested block isn't allocated yet; * we couldn't try to create block if flags doesn't contain EXT4_GET_BLOCKS_CREATE */ if ((flags & EXT4_GET_BLOCKS_CREATE) == 0) { ext4_lblk_t len; len = ext4_ext_determine_insert_hole(inode, path, map->m_lblk); map->m_pblk = 0; map->m_len = min_t(unsigned int, map->m_len, len); goto out; } /* * Okay, we need to do block allocation. */ newex.ee_block = cpu_to_le32(map->m_lblk); cluster_offset = EXT4_LBLK_COFF(sbi, map->m_lblk); /* * If we are doing bigalloc, check to see if the extent returned * by ext4_find_extent() implies a cluster we can use. */ if (cluster_offset && ex && get_implied_cluster_alloc(inode->i_sb, map, ex, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; goto got_allocated_blocks; } /* find neighbour allocated blocks */ ar.lleft = map->m_lblk; err = ext4_ext_search_left(inode, path, &ar.lleft, &ar.pleft); if (err) goto out; ar.lright = map->m_lblk; err = ext4_ext_search_right(inode, path, &ar.lright, &ar.pright, &ex2, flags); if (err < 0) goto out; /* Check if the extent after searching to the right implies a * cluster we can use. */ if ((sbi->s_cluster_ratio > 1) && err && get_implied_cluster_alloc(inode->i_sb, map, &ex2, path)) { ar.len = allocated = map->m_len; newblock = map->m_pblk; err = 0; goto got_allocated_blocks; } /* * See if request is beyond maximum number of blocks we can have in * a single extent. For an initialized extent this limit is * EXT_INIT_MAX_LEN and for an unwritten extent this limit is * EXT_UNWRITTEN_MAX_LEN. */ if (map->m_len > EXT_INIT_MAX_LEN && !(flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_INIT_MAX_LEN; else if (map->m_len > EXT_UNWRITTEN_MAX_LEN && (flags & EXT4_GET_BLOCKS_UNWRIT_EXT)) map->m_len = EXT_UNWRITTEN_MAX_LEN; /* Check if we can really insert (m_lblk)::(m_lblk + m_len) extent */ newex.ee_len = cpu_to_le16(map->m_len); err = ext4_ext_check_overlap(sbi, inode, &newex, path); if (err) allocated = ext4_ext_get_actual_len(&newex); else allocated = map->m_len; /* allocate new block */ ar.inode = inode; ar.goal = ext4_ext_find_goal(inode, path, map->m_lblk); ar.logical = map->m_lblk; /* * We calculate the offset from the beginning of the cluster * for the logical block number, since when we allocate a * physical cluster, the physical block should start at the * same offset from the beginning of the cluster. This is * needed so that future calls to get_implied_cluster_alloc() * work correctly. */ offset = EXT4_LBLK_COFF(sbi, map->m_lblk); ar.len = EXT4_NUM_B2C(sbi, offset+allocated); ar.goal -= offset; ar.logical -= offset; if (S_ISREG(inode->i_mode)) ar.flags = EXT4_MB_HINT_DATA; else /* disable in-core preallocation for non-regular files */ ar.flags = 0; if (flags & EXT4_GET_BLOCKS_NO_NORMALIZE) ar.flags |= EXT4_MB_HINT_NOPREALLOC; if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) ar.flags |= EXT4_MB_DELALLOC_RESERVED; if (flags & EXT4_GET_BLOCKS_METADATA_NOFAIL) ar.flags |= EXT4_MB_USE_RESERVED; newblock = ext4_mb_new_blocks(handle, &ar, &err); if (!newblock) goto out; allocated_clusters = ar.len; ar.len = EXT4_C2B(sbi, ar.len) - offset; ext_debug(inode, "allocate new block: goal %llu, found %llu/%u, requested %u\n", ar.goal, newblock, ar.len, allocated); if (ar.len > allocated) ar.len = allocated; got_allocated_blocks: /* try to insert new extent into found leaf and return */ pblk = newblock + offset; ext4_ext_store_pblock(&newex, pblk); newex.ee_len = cpu_to_le16(ar.len); /* Mark unwritten */ if (flags & EXT4_GET_BLOCKS_UNWRIT_EXT) { ext4_ext_mark_unwritten(&newex); map->m_flags |= EXT4_MAP_UNWRITTEN; } path = ext4_ext_insert_extent(handle, inode, path, &newex, flags); if (IS_ERR(path)) { err = PTR_ERR(path); /* * Gracefully handle out of space conditions. If the filesystem * is inconsistent, we'll just leak allocated blocks to avoid * causing even more damage. */ if (allocated_clusters && (err == -EDQUOT || err == -ENOSPC)) { int fb_flags = 0; /* * free data blocks we just allocated. * not a good idea to call discard here directly, * but otherwise we'd need to call it every free(). */ ext4_discard_preallocations(inode); if (flags & EXT4_GET_BLOCKS_DELALLOC_RESERVE) fb_flags = EXT4_FREE_BLOCKS_NO_QUOT_UPDATE; ext4_free_blocks(handle, inode, NULL, newblock, EXT4_C2B(sbi, allocated_clusters), fb_flags); } goto out; } /* * Cache the extent and update transaction to commit on fdatasync only * when it is _not_ an unwritten extent. */ if ((flags & EXT4_GET_BLOCKS_UNWRIT_EXT) == 0) ext4_update_inode_fsync_trans(handle, inode, 1); else ext4_update_inode_fsync_trans(handle, inode, 0); map->m_flags |= (EXT4_MAP_NEW | EXT4_MAP_MAPPED); map->m_pblk = pblk; map->m_len = ar.len; allocated = map->m_len; ext4_ext_show_leaf(inode, path); out: /* * We never use EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF with CREATE flag. * So we know that the depth used here is correct, since there was no * block allocation done if EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF is set. * If tomorrow we start using this QUERY flag with CREATE, then we will * need to re-calculate the depth as it might have changed due to block * allocation. */ if (flags & EXT4_GET_BLOCKS_QUERY_LAST_IN_LEAF) { WARN_ON_ONCE(flags & EXT4_GET_BLOCKS_CREATE); if (!err && ex && (ex == EXT_LAST_EXTENT(path[depth].p_hdr))) map->m_flags |= EXT4_MAP_QUERY_LAST_IN_LEAF; } ext4_free_ext_path(path); trace_ext4_ext_map_blocks_exit(inode, flags, map, err ? err : allocated); return err ? err : allocated; } int ext4_ext_truncate(handle_t *handle, struct inode *inode) { struct super_block *sb = inode->i_sb; ext4_lblk_t last_block; int err = 0; /* * TODO: optimization is possible here. * Probably we need not scan at all, * because page truncation is enough. */ /* we have to know where to truncate from in crash case */ EXT4_I(inode)->i_disksize = inode->i_size; err = ext4_mark_inode_dirty(handle, inode); if (err) return err; last_block = (inode->i_size + sb->s_blocksize - 1) >> EXT4_BLOCK_SIZE_BITS(sb); ext4_es_remove_extent(inode, last_block, EXT_MAX_BLOCKS - last_block); retry_remove_space: err = ext4_ext_remove_space(inode, last_block, EXT_MAX_BLOCKS - 1); if (err == -ENOMEM) { memalloc_retry_wait(GFP_ATOMIC); goto retry_remove_space; } return err; } static int ext4_alloc_file_blocks(struct file *file, loff_t offset, loff_t len, loff_t new_size, int flags) { struct inode *inode = file_inode(file); handle_t *handle; int ret = 0, ret2 = 0, ret3 = 0; int retries = 0; int depth = 0; ext4_lblk_t len_lblk; struct ext4_map_blocks map; unsigned int credits; loff_t epos = 0, old_size = i_size_read(inode); unsigned int blkbits = inode->i_blkbits; bool alloc_zero = false; BUG_ON(!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)); map.m_lblk = offset >> blkbits; map.m_len = len_lblk = EXT4_MAX_BLOCKS(len, offset, blkbits); /* * Don't normalize the request if it can fit in one extent so * that it doesn't get unnecessarily split into multiple * extents. */ if (len_lblk <= EXT_UNWRITTEN_MAX_LEN) flags |= EXT4_GET_BLOCKS_NO_NORMALIZE; /* * Do the actual write zero during a running journal transaction * costs a lot. First allocate an unwritten extent and then * convert it to written after zeroing it out. */ if (flags & EXT4_GET_BLOCKS_ZERO) { flags &= ~EXT4_GET_BLOCKS_ZERO; flags |= EXT4_GET_BLOCKS_UNWRIT_EXT; alloc_zero = true; } /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, len_lblk); depth = ext_depth(inode); /* Zero to the end of the block containing i_size */ if (new_size > old_size) { ret = ext4_block_zero_eof(inode, old_size, LLONG_MAX); if (ret) return ret; } retry: while (len_lblk) { /* * Recalculate credits when extent tree depth changes. */ if (depth != ext_depth(inode)) { credits = ext4_chunk_trans_blocks(inode, len_lblk); depth = ext_depth(inode); } handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } ret = ext4_map_blocks(handle, inode, &map, flags); if (ret <= 0) { ext4_debug("inode #%llu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ext4_mark_inode_dirty(handle, inode); ext4_journal_stop(handle); break; } ext4_update_inode_fsync_trans(handle, inode, 1); ret = ext4_journal_stop(handle); if (unlikely(ret)) break; /* * allow a full retry cycle for any remaining allocations */ retries = 0; if (alloc_zero && (map.m_flags & (EXT4_MAP_MAPPED | EXT4_MAP_UNWRITTEN))) { ret = ext4_issue_zeroout(inode, map.m_lblk, map.m_pblk, map.m_len); if (likely(!ret)) ret = ext4_convert_unwritten_extents(NULL, inode, (loff_t)map.m_lblk << blkbits, (loff_t)map.m_len << blkbits); if (ret) break; } map.m_lblk += map.m_len; map.m_len = len_lblk = len_lblk - map.m_len; epos = EXT4_LBLK_TO_B(inode, map.m_lblk); } if (ret == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries)) goto retry; if (!epos || !new_size) return ret; /* * Allocate blocks, update the file size to match the size of the * already successfully allocated blocks. */ if (epos > new_size) epos = new_size; handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); if (IS_ERR(handle)) return ret ? ret : PTR_ERR(handle); ext4_update_inode_size(inode, epos); ret2 = ext4_mark_inode_dirty(handle, inode); ext4_update_inode_fsync_trans(handle, inode, 1); ret3 = ext4_journal_stop(handle); ret2 = ret3 ? ret3 : ret2; if (epos > old_size) pagecache_isize_extended(inode, old_size, epos); return ret ? ret : ret2; } static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len); static int ext4_insert_range(struct file *file, loff_t offset, loff_t len); static long ext4_zero_range(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); handle_t *handle = NULL; loff_t align_start, align_end, new_size = 0; loff_t end = offset + len; unsigned int blocksize = i_blocksize(inode); bool partial_zeroed = false; int ret, flags; trace_ext4_zero_range(inode, offset, len, mode); WARN_ON_ONCE(!inode_is_locked(inode)); /* Indirect files do not support unwritten extents */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) return -EOPNOTSUPP; if (!(mode & FALLOC_FL_KEEP_SIZE) && (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { new_size = end; ret = inode_newsize_ok(inode, new_size); if (ret) return ret; } flags = EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT; /* Preallocate the range including the unaligned edges */ if (!IS_ALIGNED(offset | end, blocksize)) { ret = ext4_alloc_file_blocks(file, offset, len, new_size, flags); if (ret) return ret; } ret = ext4_update_disksize_before_punch(inode, offset, len); if (ret) return ret; /* Now release the pages and zero block aligned part of pages */ ret = ext4_truncate_page_cache_block_range(inode, offset, end); if (ret) return ret; /* Zero range excluding the unaligned edges */ align_start = round_up(offset, blocksize); align_end = round_down(end, blocksize); if (align_end > align_start) { if (mode & FALLOC_FL_WRITE_ZEROES) flags = EXT4_GET_BLOCKS_CREATE_ZERO | EXT4_EX_NOCACHE; else flags |= (EXT4_GET_BLOCKS_CONVERT_UNWRITTEN | EXT4_EX_NOCACHE); ret = ext4_alloc_file_blocks(file, align_start, align_end - align_start, new_size, flags); if (ret) return ret; } /* Finish zeroing out if it doesn't contain partial block */ if (IS_ALIGNED(offset | end, blocksize)) return ret; /* Zero out partial block at the edges of the range */ ret = ext4_zero_partial_blocks(inode, offset, len, &partial_zeroed); if (ret) return ret; if (((file->f_flags & O_SYNC) || IS_SYNC(inode)) && partial_zeroed) { ret = filemap_write_and_wait_range(inode->i_mapping, offset, end - 1); if (ret) return ret; } handle = ext4_journal_start(inode, EXT4_HT_MISC, 1); if (IS_ERR(handle)) { ret = PTR_ERR(handle); ext4_std_error(inode->i_sb, ret); return ret; } if (new_size) ext4_update_inode_size(inode, new_size); ret = ext4_mark_inode_dirty(handle, inode); if (unlikely(ret)) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } static long ext4_do_fallocate(struct file *file, loff_t offset, loff_t len, int mode) { struct inode *inode = file_inode(file); loff_t end = offset + len; loff_t new_size = 0; int ret; trace_ext4_fallocate_enter(inode, offset, len, mode); WARN_ON_ONCE(!inode_is_locked(inode)); /* We only support preallocation for extent-based files only. */ if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) { ret = -EOPNOTSUPP; goto out; } if (!(mode & FALLOC_FL_KEEP_SIZE) && (end > inode->i_size || end > EXT4_I(inode)->i_disksize)) { new_size = end; ret = inode_newsize_ok(inode, new_size); if (ret) goto out; } ret = ext4_alloc_file_blocks(file, offset, len, new_size, EXT4_GET_BLOCKS_CREATE_UNWRIT_EXT); if (ret) goto out; if (((file->f_flags & O_SYNC) || IS_SYNC(inode)) && EXT4_SB(inode->i_sb)->s_journal) { ret = ext4_fc_commit(EXT4_SB(inode->i_sb)->s_journal, EXT4_I(inode)->i_sync_tid); } out: trace_ext4_fallocate_exit(inode, offset, EXT4_MAX_BLOCKS(len, offset, inode->i_blkbits), ret); return ret; } /* * preallocate space for a file. This implements ext4's fallocate file * operation, which gets called from sys_fallocate system call. * For block-mapped files, posix_fallocate should fall back to the method * of writing zeroes to the required new blocks (the same behavior which is * expected for file systems which do not support fallocate() system call). */ long ext4_fallocate(struct file *file, int mode, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct address_space *mapping = file->f_mapping; int ret; /* * Encrypted inodes can't handle collapse range or insert * range since we would need to re-encrypt blocks with a * different IV or XTS tweak (which are based on the logical * block number). */ if (IS_ENCRYPTED(inode) && (mode & (FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE))) return -EOPNOTSUPP; /* * Don't allow writing zeroes if the underlying device does not * enable the unmap write zeroes operation. */ if ((mode & FALLOC_FL_WRITE_ZEROES) && !bdev_write_zeroes_unmap_sectors(inode->i_sb->s_bdev)) return -EOPNOTSUPP; /* Return error if mode is not supported */ if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE | FALLOC_FL_ZERO_RANGE | FALLOC_FL_COLLAPSE_RANGE | FALLOC_FL_INSERT_RANGE | FALLOC_FL_WRITE_ZEROES)) return -EOPNOTSUPP; inode_lock(inode); ret = ext4_convert_inline_data(inode); if (ret) goto out_inode_lock; /* Wait all existing dio workers, newcomers will block on i_rwsem */ inode_dio_wait(inode); ret = file_modified(file); if (ret) goto out_inode_lock; if ((mode & FALLOC_FL_MODE_MASK) == FALLOC_FL_ALLOCATE_RANGE) { ret = ext4_do_fallocate(file, offset, len, mode); goto out_inode_lock; } /* * Follow-up operations will drop page cache, hold invalidate lock * to prevent page faults from reinstantiating pages we have * released from page cache. */ filemap_invalidate_lock(mapping); ret = ext4_break_layouts(inode); if (ret) goto out_invalidate_lock; switch (mode & FALLOC_FL_MODE_MASK) { case FALLOC_FL_PUNCH_HOLE: ret = ext4_punch_hole(file, offset, len); break; case FALLOC_FL_COLLAPSE_RANGE: ret = ext4_collapse_range(file, offset, len); break; case FALLOC_FL_INSERT_RANGE: ret = ext4_insert_range(file, offset, len); break; case FALLOC_FL_ZERO_RANGE: case FALLOC_FL_WRITE_ZEROES: ret = ext4_zero_range(file, offset, len, mode); break; default: ret = -EOPNOTSUPP; } out_invalidate_lock: filemap_invalidate_unlock(mapping); out_inode_lock: inode_unlock(inode); return ret; } /* * This function converts a range of blocks to written extents. The caller of * this function will pass the start offset and the size. all unwritten extents * within this range will be converted to written extents. * * This function is called from the direct IO end io call back function for * atomic writes, to convert the unwritten extents after IO is completed. * * Note that the requirement for atomic writes is that all conversion should * happen atomically in a single fs journal transaction. We mainly only allocate * unwritten extents either on a hole on a pre-exiting unwritten extent range in * ext4_map_blocks_atomic_write(). The only case where we can have multiple * unwritten extents in a range [offset, offset+len) is when there is a split * unwritten extent between two leaf nodes which was cached in extent status * cache during ext4_iomap_alloc() time. That will allow * ext4_map_blocks_atomic_write() to return the unwritten extent range w/o going * into the slow path. That means we might need a loop for conversion of this * unwritten extent split across leaf block within a single journal transaction. * Split extents across leaf nodes is a rare case, but let's still handle that * to meet the requirements of multi-fsblock atomic writes. * * Returns 0 on success. */ int ext4_convert_unwritten_extents_atomic(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; int flags = EXT4_GET_BLOCKS_IO_CONVERT_EXT | EXT4_EX_NOCACHE; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); if (!handle) { /* * TODO: An optimization can be added later by having an extent * status flag e.g. EXTENT_STATUS_SPLIT_LEAF. If we query that * it can tell if the extent in the cache is a split extent. * But for now let's assume pextents as 2 always. */ credits = ext4_meta_trans_blocks(inode, max_blocks, 2); } if (credits) { handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); return ret; } } while (ret >= 0 && ret < max_blocks) { map.m_lblk += ret; map.m_len = (max_blocks -= ret); ret = ext4_map_blocks(handle, inode, &map, flags); if (ret != max_blocks) ext4_msg(inode->i_sb, KERN_INFO, "inode #%llu: block %u: len %u: " "split block mapping found for atomic write, " "ret = %d", inode->i_ino, map.m_lblk, map.m_len, ret); if (ret <= 0) break; } ret2 = ext4_mark_inode_dirty(handle, inode); if (credits) { ret3 = ext4_journal_stop(handle); if (unlikely(ret3)) ret2 = ret3; } if (ret <= 0 || ret2) ext4_warning(inode->i_sb, "inode #%llu: block %u: len %u: " "returned %d or %d", inode->i_ino, map.m_lblk, map.m_len, ret, ret2); return ret > 0 ? ret2 : ret; } /* * This function convert a range of blocks to written extents * The caller of this function will pass the start offset and the size. * all unwritten extents within this range will be converted to * written extents. * * This function is called from the direct IO end io call back * function, to convert the fallocated extents after IO is completed. * Returns 0 on success. */ int ext4_convert_unwritten_extents(handle_t *handle, struct inode *inode, loff_t offset, ssize_t len) { unsigned int max_blocks; int ret = 0, ret2 = 0, ret3 = 0; struct ext4_map_blocks map; unsigned int blkbits = inode->i_blkbits; unsigned int credits = 0; map.m_lblk = offset >> blkbits; max_blocks = EXT4_MAX_BLOCKS(len, offset, blkbits); if (!handle) { /* * credits to insert 1 extent into extent tree */ credits = ext4_chunk_trans_blocks(inode, max_blocks); } while (ret >= 0 && ret < max_blocks) { map.m_lblk += ret; map.m_len = (max_blocks -= ret); if (credits) { handle = ext4_journal_start(inode, EXT4_HT_MAP_BLOCKS, credits); if (IS_ERR(handle)) { ret = PTR_ERR(handle); break; } } /* * Do not cache any unrelated extents, as it does not hold the * i_rwsem or invalidate_lock, which could corrupt the extent * status tree. */ ret = ext4_map_blocks(handle, inode, &map, EXT4_GET_BLOCKS_IO_CONVERT_EXT | EXT4_EX_NOCACHE); if (ret <= 0) ext4_warning(inode->i_sb, "inode #%llu: block %u: len %u: " "ext4_ext_map_blocks returned %d", inode->i_ino, map.m_lblk, map.m_len, ret); ret2 = ext4_mark_inode_dirty(handle, inode); if (credits) { ret3 = ext4_journal_stop(handle); if (unlikely(ret3)) ret2 = ret3; } if (ret <= 0 || ret2) break; } return ret > 0 ? ret2 : ret; } int ext4_convert_unwritten_io_end_vec(handle_t *handle, ext4_io_end_t *io_end) { int ret = 0, err = 0; struct ext4_io_end_vec *io_end_vec; /* * This is somewhat ugly but the idea is clear: When transaction is * reserved, everything goes into it. Otherwise we rather start several * smaller transactions for conversion of each extent separately. */ if (handle) { handle = ext4_journal_start_reserved(handle, EXT4_HT_EXT_CONVERT); if (IS_ERR(handle)) return PTR_ERR(handle); } list_for_each_entry(io_end_vec, &io_end->list_vec, list) { ret = ext4_convert_unwritten_extents(handle, io_end->inode, io_end_vec->offset, io_end_vec->size); if (ret) break; } if (handle) err = ext4_journal_stop(handle); return ret < 0 ? ret : err; } static int ext4_iomap_xattr_fiemap(struct inode *inode, struct iomap *iomap) { __u64 physical = 0; __u64 length = 0; int blockbits = inode->i_sb->s_blocksize_bits; int error = 0; u16 iomap_type; /* in-inode? */ if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) { struct ext4_iloc iloc; int offset; /* offset of xattr in inode */ error = ext4_get_inode_loc(inode, &iloc); if (error) return error; physical = (__u64)iloc.bh->b_blocknr << blockbits; offset = EXT4_GOOD_OLD_INODE_SIZE + EXT4_I(inode)->i_extra_isize; physical += offset; length = EXT4_SB(inode->i_sb)->s_inode_size - offset; brelse(iloc.bh); iomap_type = IOMAP_INLINE; } else if (EXT4_I(inode)->i_file_acl) { /* external block */ physical = (__u64)EXT4_I(inode)->i_file_acl << blockbits; length = inode->i_sb->s_blocksize; iomap_type = IOMAP_MAPPED; } else { /* no in-inode or external block for xattr, so return -ENOENT */ error = -ENOENT; goto out; } iomap->addr = physical; iomap->offset = 0; iomap->length = length; iomap->type = iomap_type; iomap->flags = 0; out: return error; } static int ext4_iomap_xattr_begin(struct inode *inode, loff_t offset, loff_t length, unsigned flags, struct iomap *iomap, struct iomap *srcmap) { int error; error = ext4_iomap_xattr_fiemap(inode, iomap); if (error == 0 && (offset >= iomap->length)) error = -ENOENT; return error; } static const struct iomap_ops ext4_iomap_xattr_ops = { .iomap_begin = ext4_iomap_xattr_begin, }; static int ext4_fiemap_check_ranges(struct inode *inode, u64 start, u64 *len) { u64 maxbytes = ext4_get_maxbytes(inode); 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; return 0; } int ext4_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo, u64 start, u64 len) { int error = 0; inode_lock_shared(inode); if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { error = ext4_ext_precache(inode); if (error) goto unlock; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } /* * For bitmap files the maximum size limit could be smaller than * s_maxbytes, so check len here manually instead of just relying on the * generic check. */ error = ext4_fiemap_check_ranges(inode, start, &len); if (error) goto unlock; if (fieinfo->fi_flags & FIEMAP_FLAG_XATTR) { fieinfo->fi_flags &= ~FIEMAP_FLAG_XATTR; error = iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_xattr_ops); } else { error = iomap_fiemap(inode, fieinfo, start, len, &ext4_iomap_report_ops); } unlock: inode_unlock_shared(inode); return error; } int ext4_get_es_cache(struct inode *inode, struct fiemap_extent_info *fieinfo, __u64 start, __u64 len) { ext4_lblk_t start_blk, len_blks; __u64 last_blk; int error = 0; if (ext4_has_inline_data(inode)) { int has_inline; down_read(&EXT4_I(inode)->xattr_sem); has_inline = ext4_has_inline_data(inode); up_read(&EXT4_I(inode)->xattr_sem); if (has_inline) return 0; } if (fieinfo->fi_flags & FIEMAP_FLAG_CACHE) { inode_lock_shared(inode); error = ext4_ext_precache(inode); inode_unlock_shared(inode); if (error) return error; fieinfo->fi_flags &= ~FIEMAP_FLAG_CACHE; } error = fiemap_prep(inode, fieinfo, start, &len, 0); if (error) return error; error = ext4_fiemap_check_ranges(inode, start, &len); if (error) return error; start_blk = start >> inode->i_sb->s_blocksize_bits; last_blk = (start + len - 1) >> inode->i_sb->s_blocksize_bits; if (last_blk >= EXT_MAX_BLOCKS) last_blk = EXT_MAX_BLOCKS-1; len_blks = ((ext4_lblk_t) last_blk) - start_blk + 1; /* * Walk the extent tree gathering extent information * and pushing extents back to the user. */ return ext4_fill_es_cache_info(inode, start_blk, len_blks, fieinfo); } /* * ext4_ext_shift_path_extents: * Shift the extents of a path structure lying between path[depth].p_ext * and EXT_LAST_EXTENT(path[depth].p_hdr), by @shift blocks. @SHIFT tells * if it is right shift or left shift operation. */ static int ext4_ext_shift_path_extents(struct ext4_ext_path *path, ext4_lblk_t shift, struct inode *inode, handle_t *handle, enum SHIFT_DIRECTION SHIFT) { int depth, err = 0; struct ext4_extent *ex_start, *ex_last; bool update = false; int credits, restart_credits; depth = path->p_depth; while (depth >= 0) { if (depth == path->p_depth) { ex_start = path[depth].p_ext; if (!ex_start) return -EFSCORRUPTED; ex_last = EXT_LAST_EXTENT(path[depth].p_hdr); /* leaf + sb + inode */ credits = 3; if (ex_start == EXT_FIRST_EXTENT(path[depth].p_hdr)) { update = true; /* extent tree + sb + inode */ credits = depth + 2; } restart_credits = ext4_chunk_trans_extent(inode, 0); err = ext4_datasem_ensure_credits(handle, inode, credits, restart_credits, 0); if (err) { if (err > 0) err = -EAGAIN; goto out; } err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; while (ex_start <= ex_last) { if (SHIFT == SHIFT_LEFT) { le32_add_cpu(&ex_start->ee_block, -shift); /* Try to merge to the left. */ if ((ex_start > EXT_FIRST_EXTENT(path[depth].p_hdr)) && ext4_ext_try_to_merge_right(inode, path, ex_start - 1)) ex_last--; else ex_start++; } else { le32_add_cpu(&ex_last->ee_block, shift); ext4_ext_try_to_merge_right(inode, path, ex_last); ex_last--; } } err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; if (--depth < 0 || !update) break; } /* Update index too */ err = ext4_ext_get_access(handle, inode, path + depth); if (err) goto out; if (SHIFT == SHIFT_LEFT) le32_add_cpu(&path[depth].p_idx->ei_block, -shift); else le32_add_cpu(&path[depth].p_idx->ei_block, shift); err = ext4_ext_dirty(handle, inode, path + depth); if (err) goto out; /* we are done if current index is not a starting index */ if (path[depth].p_idx != EXT_FIRST_INDEX(path[depth].p_hdr)) break; depth--; } out: return err; } /* * ext4_ext_shift_extents: * All the extents which lies in the range from @start to the last allocated * block for the @inode are shifted either towards left or right (depending * upon @SHIFT) by @shift blocks. * On success, 0 is returned, error otherwise. */ static int ext4_ext_shift_extents(struct inode *inode, handle_t *handle, ext4_lblk_t start, ext4_lblk_t shift, enum SHIFT_DIRECTION SHIFT) { struct ext4_ext_path *path; int ret = 0, depth; struct ext4_extent *extent; ext4_lblk_t stop, *iterator, ex_start, ex_end; ext4_lblk_t tmp = EXT_MAX_BLOCKS; /* Let path point to the last extent */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) goto out; stop = le32_to_cpu(extent->ee_block); /* * For left shifts, make sure the hole on the left is big enough to * accommodate the shift. For right shifts, make sure the last extent * won't be shifted beyond EXT_MAX_BLOCKS. */ if (SHIFT == SHIFT_LEFT) { path = ext4_find_extent(inode, start - 1, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (extent) { ex_start = le32_to_cpu(extent->ee_block); ex_end = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { ex_start = 0; ex_end = 0; } if ((start == ex_start && shift > ex_start) || (shift > start - ex_end)) { ret = -EINVAL; goto out; } } else { if (shift > EXT_MAX_BLOCKS - (stop + ext4_ext_get_actual_len(extent))) { ret = -EINVAL; goto out; } } /* * In case of left shift, iterator points to start and it is increased * till we reach stop. In case of right shift, iterator points to stop * and it is decreased till we reach start. */ again: ret = 0; if (SHIFT == SHIFT_LEFT) iterator = &start; else iterator = &stop; if (tmp != EXT_MAX_BLOCKS) *iterator = tmp; /* * Its safe to start updating extents. Start and stop are unsigned, so * in case of right shift if extent with 0 block is reached, iterator * becomes NULL to indicate the end of the loop. */ while (iterator && start <= stop) { path = ext4_find_extent(inode, *iterator, path, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); depth = path->p_depth; extent = path[depth].p_ext; if (!extent) { EXT4_ERROR_INODE(inode, "unexpected hole at %lu", (unsigned long) *iterator); ret = -EFSCORRUPTED; goto out; } if (SHIFT == SHIFT_LEFT && *iterator > le32_to_cpu(extent->ee_block)) { /* Hole, move to the next extent */ if (extent < EXT_LAST_EXTENT(path[depth].p_hdr)) { path[depth].p_ext++; } else { *iterator = ext4_ext_next_allocated_block(path); continue; } } tmp = *iterator; if (SHIFT == SHIFT_LEFT) { extent = EXT_LAST_EXTENT(path[depth].p_hdr); *iterator = le32_to_cpu(extent->ee_block) + ext4_ext_get_actual_len(extent); } else { extent = EXT_FIRST_EXTENT(path[depth].p_hdr); if (le32_to_cpu(extent->ee_block) > start) *iterator = le32_to_cpu(extent->ee_block) - 1; else if (le32_to_cpu(extent->ee_block) == start) iterator = NULL; else { extent = EXT_LAST_EXTENT(path[depth].p_hdr); while (le32_to_cpu(extent->ee_block) >= start) extent--; if (extent == EXT_LAST_EXTENT(path[depth].p_hdr)) break; extent++; iterator = NULL; } path[depth].p_ext = extent; } ret = ext4_ext_shift_path_extents(path, shift, inode, handle, SHIFT); /* iterator can be NULL which means we should break */ if (ret == -EAGAIN) goto again; if (ret) break; } out: ext4_free_ext_path(path); return ret; } /* * ext4_collapse_range: * This implements the fallocate's collapse range functionality for ext4 * Returns: 0 and non-zero on error. */ static int ext4_collapse_range(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; loff_t end = offset + len; ext4_lblk_t start_lblk, end_lblk; handle_t *handle; unsigned int credits; loff_t start, new_size; int ret; trace_ext4_collapse_range(inode, offset, len); WARN_ON_ONCE(!inode_is_locked(inode)); /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Collapse range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; /* * There is no need to overlap collapse range with EOF, in which case * it is effectively a truncate operation */ if (end >= inode->i_size) return -EINVAL; /* * Write tail of the last page before removed range and data that * will be shifted since they will get removed from the page cache * below. We are also protected from pages becoming dirty by * i_rwsem and invalidate_lock. * Need to round down offset to be aligned with page size boundary * for page size > block size. */ start = round_down(offset, PAGE_SIZE); ret = filemap_write_and_wait_range(mapping, start, offset); if (!ret) ret = filemap_write_and_wait_range(mapping, end, LLONG_MAX); if (ret) return ret; truncate_pagecache(inode, start); credits = ext4_chunk_trans_extent(inode, 0); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); start_lblk = offset >> inode->i_blkbits; end_lblk = (offset + len) >> inode->i_blkbits; ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk); ret = ext4_ext_remove_space(inode, start_lblk, end_lblk - 1); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_handle; } ext4_discard_preallocations(inode); ret = ext4_ext_shift_extents(inode, handle, end_lblk, end_lblk - start_lblk, SHIFT_LEFT); if (ret) { up_write(&EXT4_I(inode)->i_data_sem); goto out_handle; } new_size = inode->i_size - len; i_size_write(inode, new_size); EXT4_I(inode)->i_disksize = new_size; up_write(&EXT4_I(inode)->i_data_sem); ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } /* * ext4_insert_range: * This function implements the FALLOC_FL_INSERT_RANGE flag of fallocate. * The data blocks starting from @offset to the EOF are shifted by @len * towards right to create a hole in the @inode. Inode size is increased * by len bytes. * Returns 0 on success, error otherwise. */ static int ext4_insert_range(struct file *file, loff_t offset, loff_t len) { struct inode *inode = file_inode(file); struct super_block *sb = inode->i_sb; struct address_space *mapping = inode->i_mapping; handle_t *handle; struct ext4_ext_path *path; struct ext4_extent *extent; ext4_lblk_t start_lblk, len_lblk, ee_start_lblk = 0; unsigned int credits, ee_len; int ret, depth; loff_t start; trace_ext4_insert_range(inode, offset, len); WARN_ON_ONCE(!inode_is_locked(inode)); /* Currently just for extent based files */ if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS)) return -EOPNOTSUPP; /* Insert range works only on fs cluster size aligned regions. */ if (!IS_ALIGNED(offset | len, EXT4_CLUSTER_SIZE(sb))) return -EINVAL; /* Offset must be less than i_size */ if (offset >= inode->i_size) return -EINVAL; /* Check whether the maximum file size would be exceeded */ if (len > inode->i_sb->s_maxbytes - inode->i_size) return -EFBIG; /* * Write out all dirty pages. Need to round down to align start offset * to page size boundary for page size > block size. */ start = round_down(offset, PAGE_SIZE); ret = filemap_write_and_wait_range(mapping, start, LLONG_MAX); if (ret) return ret; truncate_pagecache(inode, start); credits = ext4_chunk_trans_extent(inode, 0); handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE, credits); if (IS_ERR(handle)) return PTR_ERR(handle); ext4_fc_mark_ineligible(sb, EXT4_FC_REASON_FALLOC_RANGE, handle); /* Expand file to avoid data loss if there is error while shifting */ inode->i_size += len; EXT4_I(inode)->i_disksize += len; ret = ext4_mark_inode_dirty(handle, inode); if (ret) goto out_handle; start_lblk = offset >> inode->i_blkbits; len_lblk = len >> inode->i_blkbits; ext4_check_map_extents_env(inode); down_write(&EXT4_I(inode)->i_data_sem); ext4_discard_preallocations(inode); path = ext4_find_extent(inode, start_lblk, NULL, 0); if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); ret = PTR_ERR(path); goto out_handle; } depth = ext_depth(inode); extent = path[depth].p_ext; if (extent) { ee_start_lblk = le32_to_cpu(extent->ee_block); ee_len = ext4_ext_get_actual_len(extent); /* * If start_lblk is not the starting block of extent, split * the extent @start_lblk */ if ((start_lblk > ee_start_lblk) && (start_lblk < (ee_start_lblk + ee_len))) { path = ext4_split_extent_at(handle, inode, path, start_lblk, EXT4_EX_NOCACHE | EXT4_GET_BLOCKS_SPLIT_NOMERGE | EXT4_GET_BLOCKS_METADATA_NOFAIL); } if (IS_ERR(path)) { up_write(&EXT4_I(inode)->i_data_sem); ret = PTR_ERR(path); goto out_handle; } } ext4_free_ext_path(path); ext4_es_remove_extent(inode, start_lblk, EXT_MAX_BLOCKS - start_lblk); /* * if start_lblk lies in a hole which is at start of file, use * ee_start_lblk to shift extents */ ret = ext4_ext_shift_extents(inode, handle, max(ee_start_lblk, start_lblk), len_lblk, SHIFT_RIGHT); up_write(&EXT4_I(inode)->i_data_sem); if (ret) goto out_handle; ext4_update_inode_fsync_trans(handle, inode, 1); if ((file->f_flags & O_SYNC) || IS_SYNC(inode)) ext4_handle_sync(handle); out_handle: ext4_journal_stop(handle); return ret; } /** * ext4_swap_extents() - Swap extents between two inodes * @handle: handle for this transaction * @inode1: First inode * @inode2: Second inode * @lblk1: Start block for first inode * @lblk2: Start block for second inode * @count: Number of blocks to swap * @unwritten: Mark second inode's extents as unwritten after swap * @erp: Pointer to save error value * * This helper routine does exactly what is promise "swap extents". All other * stuff such as page-cache locking consistency, bh mapping consistency or * extent's data copying must be performed by caller. * Locking: * i_rwsem is held for both inodes * i_data_sem is locked for write for both inodes * Assumptions: * All pages from requested range are locked for both inodes */ int ext4_swap_extents(handle_t *handle, struct inode *inode1, struct inode *inode2, ext4_lblk_t lblk1, ext4_lblk_t lblk2, ext4_lblk_t count, int unwritten, int *erp) { struct ext4_ext_path *path1 = NULL; struct ext4_ext_path *path2 = NULL; int replaced_count = 0; BUG_ON(!rwsem_is_locked(&EXT4_I(inode1)->i_data_sem)); BUG_ON(!rwsem_is_locked(&EXT4_I(inode2)->i_data_sem)); BUG_ON(!inode_is_locked(inode1)); BUG_ON(!inode_is_locked(inode2)); ext4_es_remove_extent(inode1, lblk1, count); ext4_es_remove_extent(inode2, lblk2, count); while (count) { struct ext4_extent *ex1, *ex2, tmp_ex; ext4_lblk_t e1_blk, e2_blk; int e1_len, e2_len, len; int split = 0; path1 = ext4_find_extent(inode1, lblk1, path1, EXT4_EX_NOCACHE); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); goto errout; } path2 = ext4_find_extent(inode2, lblk2, path2, EXT4_EX_NOCACHE); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); goto errout; } ex1 = path1[path1->p_depth].p_ext; ex2 = path2[path2->p_depth].p_ext; /* Do we have something to swap ? */ if (unlikely(!ex2 || !ex1)) goto errout; e1_blk = le32_to_cpu(ex1->ee_block); e2_blk = le32_to_cpu(ex2->ee_block); e1_len = ext4_ext_get_actual_len(ex1); e2_len = ext4_ext_get_actual_len(ex2); /* Hole handling */ if (!in_range(lblk1, e1_blk, e1_len) || !in_range(lblk2, e2_blk, e2_len)) { ext4_lblk_t next1, next2; /* if hole after extent, then go to next extent */ next1 = ext4_ext_next_allocated_block(path1); next2 = ext4_ext_next_allocated_block(path2); /* If hole before extent, then shift to that extent */ if (e1_blk > lblk1) next1 = e1_blk; if (e2_blk > lblk2) next2 = e2_blk; /* Do we have something to swap */ if (next1 == EXT_MAX_BLOCKS || next2 == EXT_MAX_BLOCKS) goto errout; /* Move to the rightest boundary */ len = next1 - lblk1; if (len < next2 - lblk2) len = next2 - lblk2; if (len > count) len = count; lblk1 += len; lblk2 += len; count -= len; continue; } /* Prepare left boundary */ if (e1_blk < lblk1) { split = 1; path1 = ext4_force_split_extent_at(handle, inode1, path1, lblk1, 0); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); goto errout; } } if (e2_blk < lblk2) { split = 1; path2 = ext4_force_split_extent_at(handle, inode2, path2, lblk2, 0); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); goto errout; } } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) continue; /* Prepare right boundary */ len = count; if (len > e1_blk + e1_len - lblk1) len = e1_blk + e1_len - lblk1; if (len > e2_blk + e2_len - lblk2) len = e2_blk + e2_len - lblk2; if (len != e1_len) { split = 1; path1 = ext4_force_split_extent_at(handle, inode1, path1, lblk1 + len, 0); if (IS_ERR(path1)) { *erp = PTR_ERR(path1); goto errout; } } if (len != e2_len) { split = 1; path2 = ext4_force_split_extent_at(handle, inode2, path2, lblk2 + len, 0); if (IS_ERR(path2)) { *erp = PTR_ERR(path2); goto errout; } } /* ext4_split_extent_at() may result in leaf extent split, * path must to be revalidated. */ if (split) continue; BUG_ON(e2_len != e1_len); *erp = ext4_ext_get_access(handle, inode1, path1 + path1->p_depth); if (unlikely(*erp)) goto errout; *erp = ext4_ext_get_access(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto errout; /* Both extents are fully inside boundaries. Swap it now */ tmp_ex = *ex1; ext4_ext_store_pblock(ex1, ext4_ext_pblock(ex2)); ext4_ext_store_pblock(ex2, ext4_ext_pblock(&tmp_ex)); ex1->ee_len = cpu_to_le16(e2_len); ex2->ee_len = cpu_to_le16(e1_len); if (unwritten) ext4_ext_mark_unwritten(ex2); if (ext4_ext_is_unwritten(&tmp_ex)) ext4_ext_mark_unwritten(ex1); ext4_ext_try_to_merge(handle, inode2, path2, ex2); ext4_ext_try_to_merge(handle, inode1, path1, ex1); *erp = ext4_ext_dirty(handle, inode2, path2 + path2->p_depth); if (unlikely(*erp)) goto errout; *erp = ext4_ext_dirty(handle, inode1, path1 + path1->p_depth); /* * Looks scarry ah..? second inode already points to new blocks, * and it was successfully dirtied. But luckily error may happen * only due to journal error, so full transaction will be * aborted anyway. */ if (unlikely(*erp)) goto errout; lblk1 += len; lblk2 += len; replaced_count += len; count -= len; } errout: ext4_free_ext_path(path1); ext4_free_ext_path(path2); return replaced_count; } /* * ext4_clu_mapped - determine whether any block in a logical cluster has * been mapped to a physical cluster * * @inode - file containing the logical cluster * @lclu - logical cluster of interest * * Returns 1 if any block in the logical cluster is mapped, signifying * that a physical cluster has been allocated for it. Otherwise, * returns 0. Can also return negative error codes. Derived from * ext4_ext_map_blocks(). */ int ext4_clu_mapped(struct inode *inode, ext4_lblk_t lclu) { struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb); struct ext4_ext_path *path; int depth, mapped = 0, err = 0; struct ext4_extent *extent; ext4_lblk_t first_lblk, first_lclu, last_lclu; /* * if data can be stored inline, the logical cluster isn't * mapped - no physical clusters have been allocated, and the * file has no extents */ if (ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA) || ext4_has_inline_data(inode)) return 0; /* search for the extent closest to the first block in the cluster */ path = ext4_find_extent(inode, EXT4_C2B(sbi, lclu), NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); depth = ext_depth(inode); /* * A consistent leaf must not be empty. This situation is possible, * though, _during_ tree modification, and it's why an assert can't * be put in ext4_find_extent(). */ if (unlikely(path[depth].p_ext == NULL && depth != 0)) { EXT4_ERROR_INODE(inode, "bad extent address - lblock: %lu, depth: %d, pblock: %lld", (unsigned long) EXT4_C2B(sbi, lclu), depth, path[depth].p_block); err = -EFSCORRUPTED; goto out; } extent = path[depth].p_ext; /* can't be mapped if the extent tree is empty */ if (extent == NULL) goto out; first_lblk = le32_to_cpu(extent->ee_block); first_lclu = EXT4_B2C(sbi, first_lblk); /* * Three possible outcomes at this point - found extent spanning * the target cluster, to the left of the target cluster, or to the * right of the target cluster. The first two cases are handled here. * The last case indicates the target cluster is not mapped. */ if (lclu >= first_lclu) { last_lclu = EXT4_B2C(sbi, first_lblk + ext4_ext_get_actual_len(extent) - 1); if (lclu <= last_lclu) { mapped = 1; } else { first_lblk = ext4_ext_next_allocated_block(path); first_lclu = EXT4_B2C(sbi, first_lblk); if (lclu == first_lclu) mapped = 1; } } out: ext4_free_ext_path(path); return err ? err : mapped; } /* * Updates physical block address and unwritten status of extent * starting at lblk start and of len. If such an extent doesn't exist, * this function splits the extent tree appropriately to create an * extent like this. This function is called in the fast commit * replay path. Returns 0 on success and error on failure. */ int ext4_ext_replay_update_ex(struct inode *inode, ext4_lblk_t start, int len, int unwritten, ext4_fsblk_t pblk) { struct ext4_ext_path *path; struct ext4_extent *ex; int ret; path = ext4_find_extent(inode, start, NULL, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) { ret = -EFSCORRUPTED; goto out; } if (le32_to_cpu(ex->ee_block) != start || ext4_ext_get_actual_len(ex) != len) { /* We need to split this extent to match our extent first */ down_write(&EXT4_I(inode)->i_data_sem); path = ext4_force_split_extent_at(NULL, inode, path, start, 1); up_write(&EXT4_I(inode)->i_data_sem); if (IS_ERR(path)) { ret = PTR_ERR(path); goto out; } path = ext4_find_extent(inode, start, path, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; WARN_ON(le32_to_cpu(ex->ee_block) != start); if (ext4_ext_get_actual_len(ex) != len) { down_write(&EXT4_I(inode)->i_data_sem); path = ext4_force_split_extent_at(NULL, inode, path, start + len, 1); up_write(&EXT4_I(inode)->i_data_sem); if (IS_ERR(path)) { ret = PTR_ERR(path); goto out; } path = ext4_find_extent(inode, start, path, 0); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; } } if (unwritten) ext4_ext_mark_unwritten(ex); else ext4_ext_mark_initialized(ex); ext4_ext_store_pblock(ex, pblk); down_write(&EXT4_I(inode)->i_data_sem); ret = ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); out: ext4_free_ext_path(path); ext4_mark_inode_dirty(NULL, inode); return ret; } /* Try to shrink the extent tree */ void ext4_ext_replay_shrink_inode(struct inode *inode, ext4_lblk_t end) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t old_cur, cur = 0; while (cur < end) { path = ext4_find_extent(inode, cur, NULL, 0); if (IS_ERR(path)) return; ex = path[path->p_depth].p_ext; if (!ex) { ext4_free_ext_path(path); ext4_mark_inode_dirty(NULL, inode); return; } old_cur = cur; cur = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); if (cur <= old_cur) cur = old_cur + 1; ext4_ext_try_to_merge(NULL, inode, path, ex); down_write(&EXT4_I(inode)->i_data_sem); ext4_ext_dirty(NULL, inode, &path[path->p_depth]); up_write(&EXT4_I(inode)->i_data_sem); ext4_mark_inode_dirty(NULL, inode); ext4_free_ext_path(path); } } /* Check if *cur is a hole and if it is, skip it */ static int skip_hole(struct inode *inode, ext4_lblk_t *cur) { int ret; struct ext4_map_blocks map; map.m_lblk = *cur; map.m_len = ((inode->i_size) >> inode->i_sb->s_blocksize_bits) - *cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) return ret; if (ret != 0) return 0; *cur = *cur + map.m_len; return 0; } /* Count number of blocks used by this inode and update i_blocks */ int ext4_ext_replay_set_iblocks(struct inode *inode) { struct ext4_ext_path *path = NULL, *path2 = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int numblks = 0, i, ret = 0; ext4_fsblk_t cmp1, cmp2; struct ext4_map_blocks map; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) goto out; end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); /* Count the number of data blocks */ cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) numblks += ret; cur = cur + map.m_len; } /* * Count the number of extent tree blocks. We do it by looking up * two successive extents and determining the difference between * their paths. When path is different for 2 successive extents * we compare the blocks in the path at each level and increment * iblocks by total number of differences found. */ cur = 0; ret = skip_hole(inode, &cur); if (ret < 0) goto out; path = ext4_find_extent(inode, cur, path, 0); if (IS_ERR(path)) goto out; numblks += path->p_depth; while (cur < end) { path = ext4_find_extent(inode, cur, path, 0); if (IS_ERR(path)) break; ex = path[path->p_depth].p_ext; if (!ex) goto cleanup; cur = max(cur + 1, le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex)); ret = skip_hole(inode, &cur); if (ret < 0) break; path2 = ext4_find_extent(inode, cur, path2, 0); if (IS_ERR(path2)) break; for (i = 0; i <= max(path->p_depth, path2->p_depth); i++) { cmp1 = cmp2 = 0; if (i <= path->p_depth) cmp1 = path[i].p_bh ? path[i].p_bh->b_blocknr : 0; if (i <= path2->p_depth) cmp2 = path2[i].p_bh ? path2[i].p_bh->b_blocknr : 0; if (cmp1 != cmp2 && cmp2 != 0) numblks++; } } out: inode->i_blocks = numblks << (inode->i_sb->s_blocksize_bits - 9); ext4_mark_inode_dirty(NULL, inode); cleanup: ext4_free_ext_path(path); ext4_free_ext_path(path2); return 0; } int ext4_ext_clear_bb(struct inode *inode) { struct ext4_ext_path *path = NULL; struct ext4_extent *ex; ext4_lblk_t cur = 0, end; int j, ret = 0; struct ext4_map_blocks map; if (ext4_test_inode_flag(inode, EXT4_INODE_INLINE_DATA)) return 0; /* Determin the size of the file first */ path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, EXT4_EX_NOCACHE); if (IS_ERR(path)) return PTR_ERR(path); ex = path[path->p_depth].p_ext; if (!ex) goto out; end = le32_to_cpu(ex->ee_block) + ext4_ext_get_actual_len(ex); cur = 0; while (cur < end) { map.m_lblk = cur; map.m_len = end - cur; ret = ext4_map_blocks(NULL, inode, &map, 0); if (ret < 0) break; if (ret > 0) { path = ext4_find_extent(inode, map.m_lblk, path, 0); if (!IS_ERR(path)) { for (j = 0; j < path->p_depth; j++) { ext4_mb_mark_bb(inode->i_sb, path[j].p_block, 1, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, 0, path[j].p_block, 1, 1); } } else { path = NULL; } ext4_mb_mark_bb(inode->i_sb, map.m_pblk, map.m_len, false); ext4_fc_record_regions(inode->i_sb, inode->i_ino, map.m_lblk, map.m_pblk, map.m_len, 1); } cur = cur + map.m_len; } out: ext4_free_ext_path(path); return 0; } #if IS_ENABLED(CONFIG_EXT4_KUNIT_TESTS) int ext4_ext_space_root_idx_test(struct inode *inode, int check) { return ext4_ext_space_root_idx(inode, check); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_space_root_idx_test); struct ext4_ext_path *ext4_split_convert_extents_test(handle_t *handle, struct inode *inode, struct ext4_map_blocks *map, struct ext4_ext_path *path, int flags, unsigned int *allocated) { return ext4_split_convert_extents(handle, inode, map, path, flags, allocated); } EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_split_convert_extents_test); EXPORT_SYMBOL_FOR_EXT4_TEST(__ext4_ext_dirty); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_zeroout); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_register_shrinker); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_unregister_shrinker); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_create_blocks); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_init_tree); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_lookup_extent); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_es_insert_extent); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_ext_insert_extent); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_find_extent); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_issue_zeroout); EXPORT_SYMBOL_FOR_EXT4_TEST(ext4_map_query_blocks); #endif |
| 5 283 1 291 285 281 282 282 1 285 283 284 283 288 284 15 282 1 1 282 1 281 282 1 283 4 4 4 4 4 4 4 3 4 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 | /* SPDX-License-Identifier: GPL-2.0 */ #include <linux/syscalls.h> #include <linux/export.h> #include <linux/uaccess.h> #include <linux/fs_struct.h> #include <linux/fs.h> #include <linux/slab.h> #include <linux/prefetch.h> #include "mount.h" #include "internal.h" struct prepend_buffer { char *buf; int len; }; #define DECLARE_BUFFER(__name, __buf, __len) \ struct prepend_buffer __name = {.buf = __buf + __len, .len = __len} static char *extract_string(struct prepend_buffer *p) { if (likely(p->len >= 0)) return p->buf; return ERR_PTR(-ENAMETOOLONG); } static bool prepend_char(struct prepend_buffer *p, unsigned char c) { if (likely(p->len > 0)) { p->len--; *--p->buf = c; return true; } p->len = -1; return false; } /* * The source of the prepend data can be an optimistic load * of a dentry name and length. And because we don't hold any * locks, the length and the pointer to the name may not be * in sync if a concurrent rename happens, and the kernel * copy might fault as a result. * * The end result will correct itself when we check the * rename sequence count, but we need to be able to handle * the fault gracefully. */ static bool prepend_copy(void *dst, const void *src, int len) { if (unlikely(copy_from_kernel_nofault(dst, src, len))) { memset(dst, 'x', len); return false; } return true; } static bool prepend(struct prepend_buffer *p, const char *str, int namelen) { // Already overflowed? if (p->len < 0) return false; // Will overflow? if (p->len < namelen) { // Fill as much as possible from the end of the name str += namelen - p->len; p->buf -= p->len; prepend_copy(p->buf, str, p->len); p->len = -1; return false; } // Fits fully p->len -= namelen; p->buf -= namelen; return prepend_copy(p->buf, str, namelen); } /** * prepend_name - prepend a pathname in front of current buffer pointer * @p: prepend buffer which contains buffer pointer and allocated length * @name: name string and length qstr structure * * With RCU path tracing, it may race with d_move(). Use READ_ONCE() to * make sure that either the old or the new name pointer and length are * fetched. However, there may be mismatch between length and pointer. * But since the length cannot be trusted, we need to copy the name very * carefully when doing the prepend_copy(). It also prepends "/" at * the beginning of the name. The sequence number check at the caller will * retry it again when a d_move() does happen. So any garbage in the buffer * due to mismatched pointer and length will be discarded. * * Load acquire is needed to make sure that we see the new name data even * if we might get the length wrong. */ static bool prepend_name(struct prepend_buffer *p, const struct qstr *name) { const char *dname = smp_load_acquire(&name->name); /* ^^^ */ u32 dlen = READ_ONCE(name->len); return prepend(p, dname, dlen) && prepend_char(p, '/'); } static int __prepend_path(const struct dentry *dentry, const struct mount *mnt, const struct path *root, struct prepend_buffer *p) { while (dentry != root->dentry || &mnt->mnt != root->mnt) { const struct dentry *parent = READ_ONCE(dentry->d_parent); if (dentry == mnt->mnt.mnt_root) { struct mount *m = READ_ONCE(mnt->mnt_parent); struct mnt_namespace *mnt_ns; if (likely(mnt != m)) { dentry = READ_ONCE(mnt->mnt_mountpoint); mnt = m; continue; } /* Global root */ mnt_ns = READ_ONCE(mnt->mnt_ns); /* open-coded is_mounted() to use local mnt_ns */ if (!IS_ERR_OR_NULL(mnt_ns) && !is_anon_ns(mnt_ns)) return 1; // absolute root else return 2; // detached or not attached yet } if (unlikely(dentry == parent)) /* Escaped? */ return 3; prefetch(parent); if (!prepend_name(p, &dentry->d_name)) break; dentry = parent; } return 0; } /** * prepend_path - Prepend path string to a buffer * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @p: prepend buffer which contains buffer pointer and allocated length * * The function will first try to write out the pathname without taking any * lock other than the RCU read lock to make sure that dentries won't go away. * It only checks the sequence number of the global rename_lock as any change * in the dentry's d_seq will be preceded by changes in the rename_lock * sequence number. If the sequence number had been changed, it will restart * the whole pathname back-tracing sequence again by taking the rename_lock. * In this case, there is no need to take the RCU read lock as the recursive * parent pointer references will keep the dentry chain alive as long as no * rename operation is performed. */ static int prepend_path(const struct path *path, const struct path *root, struct prepend_buffer *p) { unsigned seq, m_seq = 0; struct prepend_buffer b; int error; rcu_read_lock(); restart_mnt: read_seqbegin_or_lock(&mount_lock, &m_seq); seq = 0; rcu_read_lock(); restart: b = *p; read_seqbegin_or_lock(&rename_lock, &seq); error = __prepend_path(path->dentry, real_mount(path->mnt), root, &b); if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (!(m_seq & 1)) rcu_read_unlock(); if (need_seqretry(&mount_lock, m_seq)) { m_seq = 1; goto restart_mnt; } done_seqretry(&mount_lock, m_seq); if (unlikely(error == 3)) b = *p; if (b.len == p->len) prepend_char(&b, '/'); *p = b; return error; } /** * __d_path - return the path of a dentry * @path: the dentry/vfsmount to report * @root: root vfsmnt/dentry * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. * * Returns a pointer into the buffer or an error code if the * path was too long. * * "buflen" should be positive. * * If the path is not reachable from the supplied root, return %NULL. */ char *__d_path(const struct path *path, const struct path *root, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, root, &b) > 0)) return NULL; return extract_string(&b); } char *d_absolute_path(const struct path *path, char *buf, int buflen) { struct path root = {}; DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); if (unlikely(prepend_path(path, &root, &b) > 1)) return ERR_PTR(-EINVAL); return extract_string(&b); } static void get_fs_root_rcu(struct fs_struct *fs, struct path *root) { unsigned seq; do { seq = read_seqbegin(&fs->seq); *root = fs->root; } while (read_seqretry(&fs->seq, seq)); } /** * d_path - return the path of a dentry * @path: path to report * @buf: buffer to return value in * @buflen: buffer length * * Convert a dentry into an ASCII path name. If the entry has been deleted * the string " (deleted)" is appended. Note that this is ambiguous. * * Returns a pointer into the buffer or an error code if the path was * too long. Note: Callers should use the returned pointer, not the passed * in buffer, to use the name! The implementation often starts at an offset * into the buffer, and may leave 0 bytes at the start. * * "buflen" should be positive. */ char *d_path(const struct path *path, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); struct path root; /* * We have various synthetic filesystems that never get mounted. On * these filesystems dentries are never used for lookup purposes, and * thus don't need to be hashed. They also don't need a name until a * user wants to identify the object in /proc/pid/fd/. The little hack * below allows us to generate a name for these objects on demand: * * Some pseudo inodes are mountable. When they are mounted * path->dentry == path->mnt->mnt_root. In that case don't call d_dname * and instead have d_path return the mounted path. */ if (path->dentry->d_op && path->dentry->d_op->d_dname && (!IS_ROOT(path->dentry) || path->dentry != path->mnt->mnt_root)) return path->dentry->d_op->d_dname(path->dentry, buf, buflen); rcu_read_lock(); get_fs_root_rcu(current->fs, &root); if (unlikely(d_unlinked(path->dentry))) prepend(&b, " (deleted)", 11); else prepend_char(&b, 0); prepend_path(path, &root, &b); rcu_read_unlock(); return extract_string(&b); } EXPORT_SYMBOL(d_path); /* * Helper function for dentry_operations.d_dname() members */ char *dynamic_dname(char *buffer, int buflen, const char *fmt, ...) { va_list args; char *start; int sz; va_start(args, fmt); sz = vsnprintf(buffer, buflen, fmt, args) + 1; va_end(args); if (sz > NAME_MAX || sz > buflen) return ERR_PTR(-ENAMETOOLONG); /* Move the formatted d_name to the end of the buffer. */ start = buffer + (buflen - sz); return memmove(start, buffer, sz); } char *simple_dname(struct dentry *dentry, char *buffer, int buflen) { DECLARE_BUFFER(b, buffer, buflen); /* these dentries are never renamed, so d_lock is not needed */ prepend(&b, " (deleted)", 11); prepend(&b, dentry->d_name.name, dentry->d_name.len); prepend_char(&b, '/'); return extract_string(&b); } /* * Write full pathname from the root of the filesystem into the buffer. */ static char *__dentry_path(const struct dentry *d, struct prepend_buffer *p) { const struct dentry *dentry; struct prepend_buffer b; int seq = 0; rcu_read_lock(); restart: dentry = d; b = *p; read_seqbegin_or_lock(&rename_lock, &seq); while (!IS_ROOT(dentry)) { const struct dentry *parent = dentry->d_parent; prefetch(parent); if (!prepend_name(&b, &dentry->d_name)) break; dentry = parent; } if (!(seq & 1)) rcu_read_unlock(); if (need_seqretry(&rename_lock, seq)) { seq = 1; goto restart; } done_seqretry(&rename_lock, seq); if (b.len == p->len) prepend_char(&b, '/'); return extract_string(&b); } char *dentry_path_raw(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); prepend_char(&b, 0); return __dentry_path(dentry, &b); } EXPORT_SYMBOL(dentry_path_raw); char *dentry_path(const struct dentry *dentry, char *buf, int buflen) { DECLARE_BUFFER(b, buf, buflen); if (unlikely(d_unlinked(dentry))) prepend(&b, "//deleted", 10); else prepend_char(&b, 0); return __dentry_path(dentry, &b); } static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root, struct path *pwd) { unsigned seq; do { seq = read_seqbegin(&fs->seq); *root = fs->root; *pwd = fs->pwd; } while (read_seqretry(&fs->seq, seq)); } /* * NOTE! The user-level library version returns a * character pointer. The kernel system call just * returns the length of the buffer filled (which * includes the ending '\0' character), or a negative * error value. So libc would do something like * * char *getcwd(char * buf, size_t size) * { * int retval; * * retval = sys_getcwd(buf, size); * if (retval >= 0) * return buf; * errno = -retval; * return NULL; * } */ SYSCALL_DEFINE2(getcwd, char __user *, buf, unsigned long, size) { int error; struct path pwd, root; char *page = __getname(); if (!page) return -ENOMEM; rcu_read_lock(); get_fs_root_and_pwd_rcu(current->fs, &root, &pwd); if (unlikely(d_unlinked(pwd.dentry))) { rcu_read_unlock(); error = -ENOENT; } else { unsigned len; DECLARE_BUFFER(b, page, PATH_MAX); prepend_char(&b, 0); if (unlikely(prepend_path(&pwd, &root, &b) > 0)) prepend(&b, "(unreachable)", 13); rcu_read_unlock(); len = PATH_MAX - b.len; if (unlikely(len > PATH_MAX)) error = -ENAMETOOLONG; else if (unlikely(len > size)) error = -ERANGE; else if (copy_to_user(buf, b.buf, len)) error = -EFAULT; else error = len; } __putname(page); return error; } |
| 6 6 1 1 3 2 1 1 2 2 2 2 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 1094 1095 1096 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111 1112 1113 1114 1115 1116 1117 1118 1119 1120 1121 1122 1123 1124 1125 1126 1127 1128 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158 1159 1160 1161 1162 1163 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 1185 1186 1187 1188 1189 1190 1191 1192 1193 1194 1195 1196 1197 1198 1199 1200 1201 1202 1203 1204 1205 1206 1207 1208 1209 1210 1211 1212 1213 1214 1215 1216 1217 1218 1219 1220 1221 1222 1223 1224 1225 1226 1227 1228 1229 1230 1231 1232 1233 1234 1235 1236 1237 1238 1239 1240 1241 1242 1243 1244 1245 1246 1247 1248 1249 1250 1251 1252 1253 1254 1255 1256 1257 1258 1259 1260 1261 1262 1263 1264 1265 1266 1267 1268 1269 1270 1271 1272 1273 1274 1275 1276 1277 1278 1279 1280 1281 1282 1283 1284 1285 1286 1287 1288 1289 1290 1291 1292 1293 1294 1295 1296 1297 1298 1299 1300 1301 1302 1303 1304 1305 1306 1307 1308 1309 1310 1311 1312 1313 1314 1315 1316 1317 1318 1319 1320 1321 1322 1323 1324 1325 1326 1327 1328 1329 1330 1331 1332 1333 1334 1335 1336 1337 1338 1339 1340 1341 1342 1343 1344 1345 1346 1347 1348 1349 1350 1351 1352 1353 1354 1355 1356 1357 1358 1359 1360 1361 1362 1363 1364 1365 1366 1367 1368 1369 1370 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_HUGETLB_H #define _LINUX_HUGETLB_H #include <linux/mm.h> #include <linux/mm_types.h> #include <linux/mmdebug.h> #include <linux/fs.h> #include <linux/hugetlb_inline.h> #include <linux/cgroup.h> #include <linux/page_ref.h> #include <linux/list.h> #include <linux/kref.h> #include <linux/pgtable.h> #include <linux/gfp.h> #include <linux/userfaultfd_k.h> #include <linux/nodemask.h> struct mmu_gather; struct node; void free_huge_folio(struct folio *folio); #ifdef CONFIG_HUGETLB_PAGE #include <linux/pagemap.h> #include <linux/shm.h> #include <asm/tlbflush.h> /* * For HugeTLB page, there are more metadata to save in the struct page. But * the head struct page cannot meet our needs, so we have to abuse other tail * struct page to store the metadata. */ #define __NR_USED_SUBPAGE 3 struct hugepage_subpool { spinlock_t lock; long count; long max_hpages; /* Maximum huge pages or -1 if no maximum. */ long used_hpages; /* Used count against maximum, includes */ /* both allocated and reserved pages. */ struct hstate *hstate; long min_hpages; /* Minimum huge pages or -1 if no minimum. */ long rsv_hpages; /* Pages reserved against global pool to */ /* satisfy minimum size. */ }; struct resv_map { struct kref refs; spinlock_t lock; struct list_head regions; long adds_in_progress; struct list_head region_cache; long region_cache_count; struct rw_semaphore rw_sema; #ifdef CONFIG_CGROUP_HUGETLB /* * On private mappings, the counter to uncharge reservations is stored * here. If these fields are 0, then either the mapping is shared, or * cgroup accounting is disabled for this resv_map. */ struct page_counter *reservation_counter; unsigned long pages_per_hpage; struct cgroup_subsys_state *css; #endif }; /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. * * The region data structures are embedded into a resv_map and protected * by a resv_map's lock. The set of regions within the resv_map represent * reservations for huge pages, or huge pages that have already been * instantiated within the map. The from and to elements are huge page * indices into the associated mapping. from indicates the starting index * of the region. to represents the first index past the end of the region. * * For example, a file region structure with from == 0 and to == 4 represents * four huge pages in a mapping. It is important to note that the to element * represents the first element past the end of the region. This is used in * arithmetic as 4(to) - 0(from) = 4 huge pages in the region. * * Interval notation of the form [from, to) will be used to indicate that * the endpoint from is inclusive and to is exclusive. */ struct file_region { struct list_head link; long from; long to; #ifdef CONFIG_CGROUP_HUGETLB /* * On shared mappings, each reserved region appears as a struct * file_region in resv_map. These fields hold the info needed to * uncharge each reservation. */ struct page_counter *reservation_counter; struct cgroup_subsys_state *css; #endif }; struct hugetlb_vma_lock { struct kref refs; struct rw_semaphore rw_sema; struct vm_area_struct *vma; }; extern struct resv_map *resv_map_alloc(void); void resv_map_release(struct kref *ref); extern spinlock_t hugetlb_lock; extern int hugetlb_max_hstate __read_mostly; #define for_each_hstate(h) \ for ((h) = hstates; (h) < &hstates[hugetlb_max_hstate]; (h)++) struct hugepage_subpool *hugepage_new_subpool(struct hstate *h, long max_hpages, long min_hpages); void hugepage_put_subpool(struct hugepage_subpool *spool); void hugetlb_dup_vma_private(struct vm_area_struct *vma); void clear_vma_resv_huge_pages(struct vm_area_struct *vma); int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len); int copy_hugetlb_page_range(struct mm_struct *, struct mm_struct *, struct vm_area_struct *, struct vm_area_struct *); void unmap_hugepage_range(struct vm_area_struct *, unsigned long start, unsigned long end, struct folio *, zap_flags_t); void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *, zap_flags_t zap_flags); void hugetlb_report_meminfo(struct seq_file *); int hugetlb_report_node_meminfo(char *buf, int len, int nid); void hugetlb_show_meminfo_node(int nid); unsigned long hugetlb_total_pages(void); vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags); #ifdef CONFIG_USERFAULTFD int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop); #endif /* CONFIG_USERFAULTFD */ long hugetlb_reserve_pages(struct inode *inode, long from, long to, struct vm_area_struct *vma, vma_flags_t vma_flags); long hugetlb_unreserve_pages(struct inode *inode, long start, long end, long freed); bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list); int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison); void folio_putback_hugetlb(struct folio *folio); void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason); void hugetlb_fix_reserve_counts(struct inode *inode); extern struct mutex *hugetlb_fault_mutex_table; u32 hugetlb_fault_mutex_hash(struct address_space *mapping, pgoff_t idx); pte_t *huge_pmd_share(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, pud_t *pud); bool hugetlbfs_pagecache_present(struct hstate *h, struct vm_area_struct *vma, unsigned long address); struct address_space *hugetlb_folio_mapping_lock_write(struct folio *folio); extern int movable_gigantic_pages __read_mostly; extern int sysctl_hugetlb_shm_group __read_mostly; extern struct list_head huge_boot_pages[MAX_NUMNODES]; void hugetlb_bootmem_alloc(void); extern nodemask_t hugetlb_bootmem_nodes; void hugetlb_bootmem_set_nodes(void); /* arch callbacks */ #ifndef CONFIG_HIGHPTE /* * pte_offset_huge() and pte_alloc_huge() are helpers for those architectures * which may go down to the lowest PTE level in their huge_pte_offset() and * huge_pte_alloc(): to avoid reliance on pte_offset_map() without pte_unmap(). */ static inline pte_t *pte_offset_huge(pmd_t *pmd, unsigned long address) { return pte_offset_kernel(pmd, address); } static inline pte_t *pte_alloc_huge(struct mm_struct *mm, pmd_t *pmd, unsigned long address) { return pte_alloc(mm, pmd) ? NULL : pte_offset_huge(pmd, address); } #endif pte_t *huge_pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long addr, unsigned long sz); /* * huge_pte_offset(): Walk the hugetlb pgtable until the last level PTE. * Returns the pte_t* if found, or NULL if the address is not mapped. * * IMPORTANT: we should normally not directly call this function, instead * this is only a common interface to implement arch-specific * walker. Please use hugetlb_walk() instead, because that will attempt to * verify the locking for you. * * Since this function will walk all the pgtable pages (including not only * high-level pgtable page, but also PUD entry that can be unshared * concurrently for VM_SHARED), the caller of this function should be * responsible of its thread safety. One can follow this rule: * * (1) For private mappings: pmd unsharing is not possible, so holding the * mmap_lock for either read or write is sufficient. Most callers * already hold the mmap_lock, so normally, no special action is * required. * * (2) For shared mappings: pmd unsharing is possible (so the PUD-ranged * pgtable page can go away from under us! It can be done by a pmd * unshare with a follow up munmap() on the other process), then we * need either: * * (2.1) hugetlb vma lock read or write held, to make sure pmd unshare * won't happen upon the range (it also makes sure the pte_t we * read is the right and stable one), or, * * (2.2) hugetlb mapping i_mmap_rwsem lock held read or write, to make * sure even if unshare happened the racy unmap() will wait until * i_mmap_rwsem is released. * * Option (2.1) is the safest, which guarantees pte stability from pmd * sharing pov, until the vma lock released. Option (2.2) doesn't protect * a concurrent pmd unshare, but it makes sure the pgtable page is safe to * access. */ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz); unsigned long hugetlb_mask_last_page(struct hstate *h); int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep); void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma); void adjust_range_if_pmd_sharing_possible(struct vm_area_struct *vma, unsigned long *start, unsigned long *end); extern void __hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *begin, unsigned long *end); extern void __hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details); static inline void hugetlb_zap_begin(struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_begin(vma, start, end); } static inline void hugetlb_zap_end(struct vm_area_struct *vma, struct zap_details *details) { if (is_vm_hugetlb_page(vma)) __hugetlb_zap_end(vma, details); } void hugetlb_vma_lock_read(struct vm_area_struct *vma); void hugetlb_vma_unlock_read(struct vm_area_struct *vma); void hugetlb_vma_lock_write(struct vm_area_struct *vma); void hugetlb_vma_unlock_write(struct vm_area_struct *vma); int hugetlb_vma_trylock_write(struct vm_area_struct *vma); void hugetlb_vma_assert_locked(struct vm_area_struct *vma); void hugetlb_vma_lock_release(struct kref *kref); long hugetlb_change_protection(struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); void fixup_hugetlb_reservations(struct vm_area_struct *vma); void hugetlb_split(struct vm_area_struct *vma, unsigned long addr); unsigned int arch_hugetlb_cma_order(void); #else /* !CONFIG_HUGETLB_PAGE */ static inline void hugetlb_dup_vma_private(struct vm_area_struct *vma) { } static inline void clear_vma_resv_huge_pages(struct vm_area_struct *vma) { } static inline unsigned long hugetlb_total_pages(void) { return 0; } static inline struct address_space *hugetlb_folio_mapping_lock_write( struct folio *folio) { return NULL; } static inline int huge_pmd_unshare(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { return 0; } static inline void huge_pmd_unshare_flush(struct mmu_gather *tlb, struct vm_area_struct *vma) { } static inline void adjust_range_if_pmd_sharing_possible( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_begin( struct vm_area_struct *vma, unsigned long *start, unsigned long *end) { } static inline void hugetlb_zap_end( struct vm_area_struct *vma, struct zap_details *details) { } static inline int copy_hugetlb_page_range(struct mm_struct *dst, struct mm_struct *src, struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma) { BUG(); return 0; } static inline int move_hugetlb_page_tables(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long len) { BUG(); return 0; } static inline void hugetlb_report_meminfo(struct seq_file *m) { } static inline int hugetlb_report_node_meminfo(char *buf, int len, int nid) { return 0; } static inline void hugetlb_show_meminfo_node(int nid) { } static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_read(struct vm_area_struct *vma) { } static inline void hugetlb_vma_lock_write(struct vm_area_struct *vma) { } static inline void hugetlb_vma_unlock_write(struct vm_area_struct *vma) { } static inline int hugetlb_vma_trylock_write(struct vm_area_struct *vma) { return 1; } static inline void hugetlb_vma_assert_locked(struct vm_area_struct *vma) { } static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #ifdef CONFIG_USERFAULTFD static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte, struct vm_area_struct *dst_vma, unsigned long dst_addr, unsigned long src_addr, uffd_flags_t flags, struct folio **foliop) { BUG(); return 0; } #endif /* CONFIG_USERFAULTFD */ static inline pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr, unsigned long sz) { return NULL; } static inline bool folio_isolate_hugetlb(struct folio *folio, struct list_head *list) { return false; } static inline int get_hwpoison_hugetlb_folio(struct folio *folio, bool *hugetlb, bool unpoison) { return 0; } static inline void folio_putback_hugetlb(struct folio *folio) { } static inline void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int reason) { } static inline long hugetlb_change_protection( struct vm_area_struct *vma, unsigned long address, unsigned long end, pgprot_t newprot, unsigned long cp_flags) { return 0; } static inline void __unmap_hugepage_range(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start, unsigned long end, struct folio *folio, zap_flags_t zap_flags) { BUG(); } static inline vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, unsigned int flags) { BUG(); return 0; } static inline void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { } static inline void fixup_hugetlb_reservations(struct vm_area_struct *vma) { } static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {} #endif /* !CONFIG_HUGETLB_PAGE */ #ifndef pgd_write static inline int pgd_write(pgd_t pgd) { BUG(); return 0; } #endif #define HUGETLB_ANON_FILE "anon_hugepage" enum { /* * The file will be used as an shm file so shmfs accounting rules * apply */ HUGETLB_SHMFS_INODE = 1, /* * The file is being created on the internal vfs mount and shmfs * accounting rules do not apply */ HUGETLB_ANONHUGE_INODE = 2, }; #ifdef CONFIG_HUGETLBFS struct hugetlbfs_sb_info { long max_inodes; /* inodes allowed */ long free_inodes; /* inodes free */ spinlock_t stat_lock; struct hstate *hstate; struct hugepage_subpool *spool; kuid_t uid; kgid_t gid; umode_t mode; }; static inline struct hugetlbfs_sb_info *HUGETLBFS_SB(struct super_block *sb) { return sb->s_fs_info; } struct hugetlbfs_inode_info { struct inode vfs_inode; struct resv_map *resv_map; unsigned int seals; }; static inline struct hugetlbfs_inode_info *HUGETLBFS_I(struct inode *inode) { return container_of(inode, struct hugetlbfs_inode_info, vfs_inode); } extern const struct vm_operations_struct hugetlb_vm_ops; struct file *hugetlb_file_setup(const char *name, size_t size, vma_flags_t acct, int creat_flags, int page_size_log); static inline bool is_file_hugepages(const struct file *file) { return file->f_op->fop_flags & FOP_HUGE_PAGES; } static inline struct hstate *hstate_inode(struct inode *i) { return HUGETLBFS_SB(i->i_sb)->hstate; } #else /* !CONFIG_HUGETLBFS */ #define is_file_hugepages(file) false static inline struct file * hugetlb_file_setup(const char *name, size_t size, vma_flags_t acctflag, int creat_flags, int page_size_log) { return ERR_PTR(-ENOSYS); } static inline struct hstate *hstate_inode(struct inode *i) { return NULL; } #endif /* !CONFIG_HUGETLBFS */ unsigned long hugetlb_get_unmapped_area(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags); /* * huegtlb page specific state flags. These flags are located in page.private * of the hugetlb head page. Functions created via the below macros should be * used to manipulate these flags. * * HPG_restore_reserve - Set when a hugetlb page consumes a reservation at * allocation time. Cleared when page is fully instantiated. Free * routine checks flag to restore a reservation on error paths. * Synchronization: Examined or modified by code that knows it has * the only reference to page. i.e. After allocation but before use * or when the page is being freed. * HPG_migratable - Set after a newly allocated page is added to the page * cache and/or page tables. Indicates the page is a candidate for * migration. * Synchronization: Initially set after new page allocation with no * locking. When examined and modified during migration processing * (isolate, migrate, putback) the hugetlb_lock is held. * HPG_temporary - Set on a page that is temporarily allocated from the buddy * allocator. Typically used for migration target pages when no pages * are available in the pool. The hugetlb free page path will * immediately free pages with this flag set to the buddy allocator. * Synchronization: Can be set after huge page allocation from buddy when * code knows it has only reference. All other examinations and * modifications require hugetlb_lock. * HPG_freed - Set when page is on the free lists. * Synchronization: hugetlb_lock held for examination and modification. * HPG_vmemmap_optimized - Set when the vmemmap pages of the page are freed. * HPG_raw_hwp_unreliable - Set when the hugetlb page has a hwpoison sub-page * that is not tracked by raw_hwp_page list. */ enum hugetlb_page_flags { HPG_restore_reserve = 0, HPG_migratable, HPG_temporary, HPG_freed, HPG_vmemmap_optimized, HPG_raw_hwp_unreliable, HPG_cma, __NR_HPAGEFLAGS, }; /* * Macros to create test, set and clear function definitions for * hugetlb specific page flags. */ #ifdef CONFIG_HUGETLB_PAGE #define TESTHPAGEFLAG(uname, flname) \ static __always_inline \ bool folio_test_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ return test_bit(HPG_##flname, private); \ } #define SETHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_set_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ set_bit(HPG_##flname, private); \ } #define CLEARHPAGEFLAG(uname, flname) \ static __always_inline \ void folio_clear_hugetlb_##flname(struct folio *folio) \ { void *private = &folio->private; \ clear_bit(HPG_##flname, private); \ } #else #define TESTHPAGEFLAG(uname, flname) \ static inline bool \ folio_test_hugetlb_##flname(struct folio *folio) \ { return 0; } #define SETHPAGEFLAG(uname, flname) \ static inline void \ folio_set_hugetlb_##flname(struct folio *folio) \ { } #define CLEARHPAGEFLAG(uname, flname) \ static inline void \ folio_clear_hugetlb_##flname(struct folio *folio) \ { } #endif #define HPAGEFLAG(uname, flname) \ TESTHPAGEFLAG(uname, flname) \ SETHPAGEFLAG(uname, flname) \ CLEARHPAGEFLAG(uname, flname) \ /* * Create functions associated with hugetlb page flags */ HPAGEFLAG(RestoreReserve, restore_reserve) HPAGEFLAG(Migratable, migratable) HPAGEFLAG(Temporary, temporary) HPAGEFLAG(Freed, freed) HPAGEFLAG(VmemmapOptimized, vmemmap_optimized) HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable) HPAGEFLAG(Cma, cma) #ifdef CONFIG_HUGETLB_PAGE #define HSTATE_NAME_LEN 32 /* Defines one hugetlb page size */ struct hstate { struct mutex resize_lock; struct lock_class_key resize_key; int next_nid_to_alloc; int next_nid_to_free; unsigned int order; unsigned int demote_order; unsigned long mask; unsigned long max_huge_pages; unsigned long nr_huge_pages; unsigned long free_huge_pages; unsigned long resv_huge_pages; unsigned long surplus_huge_pages; unsigned long nr_overcommit_huge_pages; struct list_head hugepage_activelist; struct list_head hugepage_freelists[MAX_NUMNODES]; unsigned int max_huge_pages_node[MAX_NUMNODES]; unsigned int nr_huge_pages_node[MAX_NUMNODES]; unsigned int free_huge_pages_node[MAX_NUMNODES]; unsigned int surplus_huge_pages_node[MAX_NUMNODES]; char name[HSTATE_NAME_LEN]; }; struct cma; struct huge_bootmem_page { struct list_head list; struct hstate *hstate; unsigned long flags; struct cma *cma; }; #define HUGE_BOOTMEM_HVO 0x0001 #define HUGE_BOOTMEM_ZONES_VALID 0x0002 #define HUGE_BOOTMEM_CMA 0x0004 bool hugetlb_bootmem_page_zones_valid(int nid, struct huge_bootmem_page *m); int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list); int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn); void wait_for_freed_hugetlb_folios(void); struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner); struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback); struct folio *alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask); int hugetlb_add_to_page_cache(struct folio *folio, struct address_space *mapping, pgoff_t idx); void restore_reserve_on_error(struct hstate *h, struct vm_area_struct *vma, unsigned long address, struct folio *folio); /* arch callback */ int __init __alloc_bootmem_huge_page(struct hstate *h, int nid); int __init alloc_bootmem_huge_page(struct hstate *h, int nid); bool __init hugetlb_node_alloc_supported(void); void __init hugetlb_add_hstate(unsigned order); bool __init arch_hugetlb_valid_size(unsigned long size); struct hstate *size_to_hstate(unsigned long size); #ifndef HUGE_MAX_HSTATE #define HUGE_MAX_HSTATE 1 #endif extern struct hstate hstates[HUGE_MAX_HSTATE]; extern unsigned int default_hstate_idx; #define default_hstate (hstates[default_hstate_idx]) static inline struct hugepage_subpool *subpool_inode(struct inode *inode) { return HUGETLBFS_SB(inode->i_sb)->spool; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return folio->_hugetlb_subpool; } static inline void hugetlb_set_folio_subpool(struct folio *folio, struct hugepage_subpool *subpool) { folio->_hugetlb_subpool = subpool; } static inline struct hstate *hstate_file(struct file *f) { return hstate_inode(file_inode(f)); } static inline struct hstate *hstate_sizelog(int page_size_log) { if (!page_size_log) return &default_hstate; if (page_size_log < BITS_PER_LONG) return size_to_hstate(1UL << page_size_log); return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return hstate_file(vma->vm_file); } static inline unsigned long huge_page_size(const struct hstate *h) { return (unsigned long)PAGE_SIZE << h->order; } static inline unsigned long huge_page_mask(struct hstate *h) { return h->mask; } static inline unsigned int huge_page_order(struct hstate *h) { return h->order; } static inline unsigned huge_page_shift(struct hstate *h) { return h->order + PAGE_SHIFT; } /** * hugetlb_linear_page_index() - linear_page_index() but in hugetlb * page size granularity. * @vma: the hugetlb VMA * @address: the virtual address within the VMA * * Return: the page offset within the mapping in huge page units. */ static inline pgoff_t hugetlb_linear_page_index(struct vm_area_struct *vma, unsigned long address) { struct hstate *h = hstate_vma(vma); return ((address - vma->vm_start) >> huge_page_shift(h)) + (vma->vm_pgoff >> huge_page_order(h)); } static inline bool order_is_gigantic(unsigned int order) { return order > MAX_PAGE_ORDER; } static inline bool hstate_is_gigantic(struct hstate *h) { return order_is_gigantic(huge_page_order(h)); } static inline unsigned int pages_per_huge_page(const struct hstate *h) { return 1 << h->order; } static inline unsigned int blocks_per_huge_page(struct hstate *h) { return huge_page_size(h) / 512; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return filemap_lock_folio(mapping, idx << huge_page_order(h)); } #include <asm/hugetlb.h> #ifndef is_hugepage_only_range static inline int is_hugepage_only_range(struct mm_struct *mm, unsigned long addr, unsigned long len) { return 0; } #define is_hugepage_only_range is_hugepage_only_range #endif #ifndef arch_clear_hugetlb_flags static inline void arch_clear_hugetlb_flags(struct folio *folio) { } #define arch_clear_hugetlb_flags arch_clear_hugetlb_flags #endif #ifndef arch_make_huge_pte static inline pte_t arch_make_huge_pte(pte_t entry, unsigned int shift, vm_flags_t flags) { return pte_mkhuge(entry); } #endif #ifndef arch_has_huge_bootmem_alloc /* * Some architectures do their own bootmem allocation, so they can't use * early CMA allocation. */ static inline bool arch_has_huge_bootmem_alloc(void) { return false; } #endif static inline struct hstate *folio_hstate(struct folio *folio) { VM_BUG_ON_FOLIO(!folio_test_hugetlb(folio), folio); return size_to_hstate(folio_size(folio)); } static inline unsigned hstate_index_to_shift(unsigned index) { return hstates[index].order + PAGE_SHIFT; } static inline int hstate_index(struct hstate *h) { return h - hstates; } int dissolve_free_hugetlb_folio(struct folio *folio); int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn); #ifdef CONFIG_MEMORY_FAILURE extern void folio_clear_hugetlb_hwpoison(struct folio *folio); #else static inline void folio_clear_hugetlb_hwpoison(struct folio *folio) { } #endif #ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION #ifndef arch_hugetlb_migration_supported static inline bool arch_hugetlb_migration_supported(struct hstate *h) { if ((huge_page_shift(h) == PMD_SHIFT) || (huge_page_shift(h) == PUD_SHIFT) || (huge_page_shift(h) == PGDIR_SHIFT)) return true; else return false; } #endif #else static inline bool arch_hugetlb_migration_supported(struct hstate *h) { return false; } #endif static inline bool hugepage_migration_supported(struct hstate *h) { return arch_hugetlb_migration_supported(h); } /* * Movability check is different as compared to migration check. * It determines whether or not a huge page should be placed on * movable zone or not. Movability of any huge page should be * required only if huge page size is supported for migration. * There won't be any reason for the huge page to be movable if * it is not migratable to start with. Also the size of the huge * page should be large enough to be placed under a movable zone * and still feasible enough to be migratable. Just the presence * in movable zone does not make the migration feasible. * * So even though large huge page sizes like the gigantic ones * are migratable they should not be movable because its not * feasible to migrate them from movable zone. */ static inline bool hugepage_movable_supported(struct hstate *h) { if (!hugepage_migration_supported(h)) return false; if (hstate_is_gigantic(h) && !movable_gigantic_pages) return false; return true; } /* Movability of hugepages depends on migration support. */ static inline gfp_t htlb_alloc_mask(struct hstate *h) { gfp_t gfp = __GFP_COMP | __GFP_NOWARN; gfp |= hugepage_movable_supported(h) ? GFP_HIGHUSER_MOVABLE : GFP_HIGHUSER; return gfp; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { gfp_t modified_mask = htlb_alloc_mask(h); /* Some callers might want to enforce node */ modified_mask |= (gfp_mask & __GFP_THISNODE); modified_mask |= (gfp_mask & __GFP_NOWARN); return modified_mask; } static inline bool htlb_allow_alloc_fallback(int reason) { bool allowed_fallback = false; /* * Note: the memory offline, memory failure and migration syscalls will * be allowed to fallback to other nodes due to lack of a better chioce, * that might break the per-node hugetlb pool. While other cases will * set the __GFP_THISNODE to avoid breaking the per-node hugetlb pool. */ switch (reason) { case MR_MEMORY_HOTPLUG: case MR_MEMORY_FAILURE: case MR_SYSCALL: case MR_MEMPOLICY_MBIND: allowed_fallback = true; break; default: break; } return allowed_fallback; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { const unsigned long size = huge_page_size(h); VM_WARN_ON(size == PAGE_SIZE); /* * hugetlb must use the exact same PT locks as core-mm page table * walkers would. When modifying a PTE table, hugetlb must take the * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD * PT lock etc. * * The expectation is that any hugetlb folio smaller than a PMD is * always mapped into a single PTE table and that any hugetlb folio * smaller than a PUD (but at least as big as a PMD) is always mapped * into a single PMD table. * * If that does not hold for an architecture, then that architecture * must disable split PT locks such that all *_lockptr() functions * will give us the same result: the per-MM PT lock. * * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr() * and core-mm would use pmd_lockptr(). However, in such configurations * split PMD locks are disabled -- they don't make sense on a single * PGDIR page table -- and the end result is the same. */ if (size >= PUD_SIZE) return pud_lockptr(mm, (pud_t *) pte); else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE)) return pmd_lockptr(mm, (pmd_t *) pte); /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */ return ptep_lockptr(mm, pte); } #ifndef hugepages_supported /* * Some platform decide whether they support huge pages at boot * time. Some of them, such as powerpc, set HPAGE_SHIFT to 0 * when there is no such support */ #define hugepages_supported() (HPAGE_SHIFT != 0) #endif void hugetlb_report_usage(struct seq_file *m, struct mm_struct *mm); static inline void hugetlb_count_init(struct mm_struct *mm) { atomic_long_set(&mm->hugetlb_usage, 0); } static inline void hugetlb_count_add(long l, struct mm_struct *mm) { atomic_long_add(l, &mm->hugetlb_usage); } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { atomic_long_sub(l, &mm->hugetlb_usage); } #ifndef huge_ptep_modify_prot_start #define huge_ptep_modify_prot_start huge_ptep_modify_prot_start static inline pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { unsigned long psize = huge_page_size(hstate_vma(vma)); return huge_ptep_get_and_clear(vma->vm_mm, addr, ptep, psize); } #endif #ifndef huge_ptep_modify_prot_commit #define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit static inline 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); } #endif #ifdef CONFIG_NUMA void hugetlb_register_node(struct node *node); void hugetlb_unregister_node(struct node *node); #endif /* * Check if a given raw @page in a hugepage is HWPOISON. */ bool is_raw_hwpoison_page_in_hugepage(struct page *page); static inline unsigned long huge_page_mask_align(struct file *file) { return PAGE_MASK & ~huge_page_mask(hstate_file(file)); } #else /* CONFIG_HUGETLB_PAGE */ struct hstate {}; static inline unsigned long huge_page_mask_align(struct file *file) { return 0; } static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio) { return NULL; } static inline struct folio *filemap_lock_hugetlb_folio(struct hstate *h, struct address_space *mapping, pgoff_t idx) { return NULL; } static inline int isolate_or_dissolve_huge_folio(struct folio *folio, struct list_head *list) { return -ENOMEM; } static inline int replace_free_hugepage_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline void wait_for_freed_hugetlb_folios(void) { } static inline struct folio *alloc_hugetlb_folio(struct vm_area_struct *vma, unsigned long addr, bool cow_from_owner) { return NULL; } static inline struct folio * alloc_hugetlb_folio_reserve(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask) { return NULL; } static inline struct folio * alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid, nodemask_t *nmask, gfp_t gfp_mask, bool allow_alloc_fallback) { return NULL; } static inline int __alloc_bootmem_huge_page(struct hstate *h) { return 0; } static inline struct hstate *hstate_file(struct file *f) { return NULL; } static inline struct hstate *hstate_sizelog(int page_size_log) { return NULL; } static inline struct hstate *hstate_vma(struct vm_area_struct *vma) { return NULL; } static inline struct hstate *folio_hstate(struct folio *folio) { return NULL; } static inline struct hstate *size_to_hstate(unsigned long size) { return NULL; } static inline unsigned long huge_page_size(struct hstate *h) { return PAGE_SIZE; } static inline unsigned long huge_page_mask(struct hstate *h) { return PAGE_MASK; } static inline unsigned int huge_page_order(struct hstate *h) { return 0; } static inline unsigned int huge_page_shift(struct hstate *h) { return PAGE_SHIFT; } static inline bool hstate_is_gigantic(struct hstate *h) { return false; } static inline unsigned int pages_per_huge_page(struct hstate *h) { return 1; } static inline unsigned hstate_index_to_shift(unsigned index) { return 0; } static inline int hstate_index(struct hstate *h) { return 0; } static inline int dissolve_free_hugetlb_folio(struct folio *folio) { return 0; } static inline int dissolve_free_hugetlb_folios(unsigned long start_pfn, unsigned long end_pfn) { return 0; } static inline bool hugepage_migration_supported(struct hstate *h) { return false; } static inline bool hugepage_movable_supported(struct hstate *h) { return false; } static inline gfp_t htlb_alloc_mask(struct hstate *h) { return 0; } static inline gfp_t htlb_modify_alloc_mask(struct hstate *h, gfp_t gfp_mask) { return 0; } static inline bool htlb_allow_alloc_fallback(int reason) { return false; } static inline spinlock_t *huge_pte_lockptr(struct hstate *h, struct mm_struct *mm, pte_t *pte) { return &mm->page_table_lock; } static inline void hugetlb_count_init(struct mm_struct *mm) { } static inline void hugetlb_report_usage(struct seq_file *f, struct mm_struct *m) { } static inline void hugetlb_count_sub(long l, struct mm_struct *mm) { } static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { #ifdef CONFIG_MMU return ptep_get(ptep); #else return *ptep; #endif } static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr, pte_t *ptep, pte_t pte, unsigned long sz) { } static inline void hugetlb_register_node(struct node *node) { } static inline void hugetlb_unregister_node(struct node *node) { } static inline bool hugetlbfs_pagecache_present( struct hstate *h, struct vm_area_struct *vma, unsigned long address) { return false; } static inline void hugetlb_bootmem_alloc(void) { } #endif /* CONFIG_HUGETLB_PAGE */ static inline spinlock_t *huge_pte_lock(struct hstate *h, struct mm_struct *mm, pte_t *pte) { spinlock_t *ptl; ptl = huge_pte_lockptr(h, mm, pte); spin_lock(ptl); return ptl; } #if defined(CONFIG_HUGETLB_PAGE) && defined(CONFIG_CMA) extern void __init hugetlb_cma_reserve(void); #else static inline __init void hugetlb_cma_reserve(void) { } #endif #ifdef CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING static inline bool hugetlb_pmd_shared(pte_t *pte) { return ptdesc_pmd_is_shared(virt_to_ptdesc(pte)); } #else static inline bool hugetlb_pmd_shared(pte_t *pte) { return false; } #endif bool want_pmd_share(struct vm_area_struct *vma, unsigned long addr); #ifndef __HAVE_ARCH_FLUSH_HUGETLB_TLB_RANGE /* * ARCHes with special requirements for evicting HUGETLB backing TLB entries can * implement this. */ #define flush_hugetlb_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) #endif static inline bool __vma_shareable_lock(struct vm_area_struct *vma) { return (vma->vm_flags & VM_MAYSHARE) && vma->vm_private_data; } bool __vma_private_lock(struct vm_area_struct *vma); /* * Safe version of huge_pte_offset() to check the locks. See comments * above huge_pte_offset(). */ static inline pte_t * hugetlb_walk(struct vm_area_struct *vma, unsigned long addr, unsigned long sz) { #if defined(CONFIG_HUGETLB_PMD_PAGE_TABLE_SHARING) && defined(CONFIG_LOCKDEP) struct hugetlb_vma_lock *vma_lock = vma->vm_private_data; /* * If pmd sharing possible, locking needed to safely walk the * hugetlb pgtables. More information can be found at the comment * above huge_pte_offset() in the same file. * * NOTE: lockdep_is_held() is only defined with CONFIG_LOCKDEP. */ if (__vma_shareable_lock(vma)) WARN_ON_ONCE(!lockdep_is_held(&vma_lock->rw_sema) && !lockdep_is_held( &vma->vm_file->f_mapping->i_mmap_rwsem)); #endif return huge_pte_offset(vma->vm_mm, addr, sz); } #endif /* _LINUX_HUGETLB_H */ |
| 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 | // SPDX-License-Identifier: GPL-2.0 /* * Copyright 2019 ARM Ltd. * * Generic implementation of update_vsyscall and update_vsyscall_tz. * * Based on the x86 specific implementation. */ #include <linux/hrtimer.h> #include <linux/timekeeper_internal.h> #include <vdso/datapage.h> #include <vdso/helpers.h> #include <vdso/vsyscall.h> #include "timekeeping_internal.h" static inline void fill_clock_configuration(struct vdso_clock *vc, const struct tk_read_base *base) { vc->cycle_last = base->cycle_last; #ifdef CONFIG_GENERIC_VDSO_OVERFLOW_PROTECT vc->max_cycles = base->clock->max_cycles; #endif vc->mask = base->mask; vc->mult = base->mult; vc->shift = base->shift; } static inline void update_vdso_time_data(struct vdso_time_data *vdata, struct timekeeper *tk) { struct vdso_clock *vc = vdata->clock_data; struct vdso_timestamp *vdso_ts; u64 nsec, sec; fill_clock_configuration(&vc[CS_HRES_COARSE], &tk->tkr_mono); fill_clock_configuration(&vc[CS_RAW], &tk->tkr_raw); /* CLOCK_MONOTONIC */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsec = tk->tkr_mono.xtime_nsec; nsec += ((u64)tk->wall_to_monotonic.tv_nsec << tk->tkr_mono.shift); while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift); vdso_ts->sec++; } vdso_ts->nsec = nsec; /* Copy MONOTONIC time for BOOTTIME */ sec = vdso_ts->sec; /* Add the boot offset */ sec += tk->monotonic_to_boot.tv_sec; nsec += (u64)tk->monotonic_to_boot.tv_nsec << tk->tkr_mono.shift; /* CLOCK_BOOTTIME */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_BOOTTIME]; vdso_ts->sec = sec; while (nsec >= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift)) { nsec -= (((u64)NSEC_PER_SEC) << tk->tkr_mono.shift); vdso_ts->sec++; } vdso_ts->nsec = nsec; /* CLOCK_MONOTONIC_RAW */ vdso_ts = &vc[CS_RAW].basetime[CLOCK_MONOTONIC_RAW]; vdso_ts->sec = tk->raw_sec; vdso_ts->nsec = tk->tkr_raw.xtime_nsec; /* CLOCK_TAI */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_TAI]; vdso_ts->sec = tk->xtime_sec + (s64)tk->tai_offset; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; } void update_vsyscall(struct timekeeper *tk) { struct vdso_time_data *vdata = vdso_k_time_data; struct vdso_clock *vc = vdata->clock_data; struct vdso_timestamp *vdso_ts; s32 clock_mode; u64 nsec; /* copy vsyscall data */ vdso_write_begin(vdata); clock_mode = tk->tkr_mono.clock->vdso_clock_mode; vc[CS_HRES_COARSE].clock_mode = clock_mode; vc[CS_RAW].clock_mode = clock_mode; /* CLOCK_REALTIME also required for time() */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME]; vdso_ts->sec = tk->xtime_sec; vdso_ts->nsec = tk->tkr_mono.xtime_nsec; /* CLOCK_REALTIME_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_REALTIME_COARSE]; vdso_ts->sec = tk->xtime_sec; vdso_ts->nsec = tk->coarse_nsec; /* CLOCK_MONOTONIC_COARSE */ vdso_ts = &vc[CS_HRES_COARSE].basetime[CLOCK_MONOTONIC_COARSE]; vdso_ts->sec = tk->xtime_sec + tk->wall_to_monotonic.tv_sec; nsec = tk->coarse_nsec; nsec = nsec + tk->wall_to_monotonic.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &vdso_ts->nsec); /* * Read without the seqlock held by clock_getres(). */ WRITE_ONCE(vdata->hrtimer_res, hrtimer_resolution); /* * If the current clocksource is not VDSO capable, then spare the * update of the high resolution parts. */ if (clock_mode != VDSO_CLOCKMODE_NONE) update_vdso_time_data(vdata, tk); __arch_update_vdso_clock(&vc[CS_HRES_COARSE]); __arch_update_vdso_clock(&vc[CS_RAW]); vdso_write_end(vdata); __arch_sync_vdso_time_data(vdata); } void update_vsyscall_tz(void) { struct vdso_time_data *vdata = vdso_k_time_data; vdata->tz_minuteswest = sys_tz.tz_minuteswest; vdata->tz_dsttime = sys_tz.tz_dsttime; __arch_sync_vdso_time_data(vdata); } #ifdef CONFIG_POSIX_AUX_CLOCKS void vdso_time_update_aux(struct timekeeper *tk) { struct vdso_time_data *vdata = vdso_k_time_data; struct vdso_timestamp *vdso_ts; struct vdso_clock *vc; s32 clock_mode; u64 nsec; vc = &vdata->aux_clock_data[tk->id - TIMEKEEPER_AUX_FIRST]; vdso_ts = &vc->basetime[VDSO_BASE_AUX]; clock_mode = tk->tkr_mono.clock->vdso_clock_mode; if (!tk->clock_valid) clock_mode = VDSO_CLOCKMODE_NONE; /* copy vsyscall data */ vdso_write_begin_clock(vc); vc->clock_mode = clock_mode; if (clock_mode != VDSO_CLOCKMODE_NONE) { fill_clock_configuration(vc, &tk->tkr_mono); vdso_ts->sec = tk->xtime_sec + tk->monotonic_to_aux.tv_sec; nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift; nsec += tk->monotonic_to_aux.tv_nsec; vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec); nsec = nsec << tk->tkr_mono.shift; vdso_ts->nsec = nsec; } __arch_update_vdso_clock(vc); vdso_write_end_clock(vc); __arch_sync_vdso_time_data(vdata); } #endif /** * vdso_update_begin - Start of a VDSO update section * * Allows architecture code to safely update the architecture specific VDSO * data. Disables interrupts, acquires timekeeper lock to serialize against * concurrent updates from timekeeping and invalidates the VDSO data * sequence counter to prevent concurrent readers from accessing * inconsistent data. * * Returns: Saved interrupt flags which need to be handed in to * vdso_update_end(). */ unsigned long vdso_update_begin(void) { struct vdso_time_data *vdata = vdso_k_time_data; unsigned long flags = timekeeper_lock_irqsave(); vdso_write_begin(vdata); return flags; } /** * vdso_update_end - End of a VDSO update section * @flags: Interrupt flags as returned from vdso_update_begin() * * Pairs with vdso_update_begin(). Marks vdso data consistent, invokes data * synchronization if the architecture requires it, drops timekeeper lock * and restores interrupt flags. */ void vdso_update_end(unsigned long flags) { struct vdso_time_data *vdata = vdso_k_time_data; vdso_write_end(vdata); __arch_sync_vdso_time_data(vdata); timekeeper_unlock_irqrestore(flags); } |
| 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 | // SPDX-License-Identifier: GPL-2.0+ /* Keyspan USB to Serial Converter driver (C) Copyright (C) 2000-2001 Hugh Blemings <hugh@blemings.org> (C) Copyright (C) 2002 Greg Kroah-Hartman <greg@kroah.com> See http://blemings.org/hugh/keyspan.html for more information. Code in this driver inspired by and in a number of places taken from Brian Warner's original Keyspan-PDA driver. This driver has been put together with the support of Innosys, Inc. and Keyspan, Inc the manufacturers of the Keyspan USB-serial products. Thanks Guys :) Thanks to Paulus for miscellaneous tidy ups, some largish chunks of much nicer and/or completely new code and (perhaps most uniquely) having the patience to sit down and explain why and where he'd changed stuff. Tip 'o the hat to IBM (and previously Linuxcare :) for supporting staff in their work on open source projects. */ #include <linux/kernel.h> #include <linux/jiffies.h> #include <linux/errno.h> #include <linux/slab.h> #include <linux/tty.h> #include <linux/tty_flip.h> #include <linux/module.h> #include <linux/spinlock.h> #include <linux/usb.h> #include <linux/usb/serial.h> #include <linux/usb/ezusb.h> #define DRIVER_AUTHOR "Hugh Blemings <hugh@misc.nu" #define DRIVER_DESC "Keyspan USB to Serial Converter Driver" static void keyspan_send_setup(struct usb_serial_port *port, int reset_port); static int keyspan_usa19_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum); static int keyspan_usa19w_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum); static int keyspan_usa28_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum); static int keyspan_usa19hs_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum); static int keyspan_usa28_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port); static int keyspan_usa26_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port); static int keyspan_usa49_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port); static int keyspan_usa90_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port); static int keyspan_usa67_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port); /* Values used for baud rate calculation - device specific */ #define KEYSPAN_INVALID_BAUD_RATE (-1) #define KEYSPAN_BAUD_RATE_OK (0) #define KEYSPAN_USA18X_BAUDCLK (12000000L) /* a guess */ #define KEYSPAN_USA19_BAUDCLK (12000000L) #define KEYSPAN_USA19W_BAUDCLK (24000000L) #define KEYSPAN_USA19HS_BAUDCLK (14769231L) #define KEYSPAN_USA28_BAUDCLK (1843200L) #define KEYSPAN_USA28X_BAUDCLK (12000000L) #define KEYSPAN_USA49W_BAUDCLK (48000000L) /* Some constants used to characterise each device. */ #define KEYSPAN_MAX_NUM_PORTS (4) #define KEYSPAN_MAX_FLIPS (2) /* * Device info for the Keyspan serial converter, used by the overall * usb-serial probe function. */ #define KEYSPAN_VENDOR_ID (0x06cd) /* Product IDs for the products supported, pre-renumeration */ #define keyspan_usa18x_pre_product_id 0x0105 #define keyspan_usa19_pre_product_id 0x0103 #define keyspan_usa19qi_pre_product_id 0x010b #define keyspan_mpr_pre_product_id 0x011b #define keyspan_usa19qw_pre_product_id 0x0118 #define keyspan_usa19w_pre_product_id 0x0106 #define keyspan_usa28_pre_product_id 0x0101 #define keyspan_usa28x_pre_product_id 0x0102 #define keyspan_usa28xa_pre_product_id 0x0114 #define keyspan_usa28xb_pre_product_id 0x0113 #define keyspan_usa49w_pre_product_id 0x0109 #define keyspan_usa49wlc_pre_product_id 0x011a /* * Product IDs post-renumeration. Note that the 28x and 28xb have the same * id's post-renumeration but behave identically so it's not an issue. As * such, the 28xb is not listed in any of the device tables. */ #define keyspan_usa18x_product_id 0x0112 #define keyspan_usa19_product_id 0x0107 #define keyspan_usa19qi_product_id 0x010c #define keyspan_usa19hs_product_id 0x0121 #define keyspan_mpr_product_id 0x011c #define keyspan_usa19qw_product_id 0x0119 #define keyspan_usa19w_product_id 0x0108 #define keyspan_usa28_product_id 0x010f #define keyspan_usa28x_product_id 0x0110 #define keyspan_usa28xa_product_id 0x0115 #define keyspan_usa28xb_product_id 0x0110 #define keyspan_usa28xg_product_id 0x0135 #define keyspan_usa49w_product_id 0x010a #define keyspan_usa49wlc_product_id 0x012a #define keyspan_usa49wg_product_id 0x0131 struct keyspan_device_details { /* product ID value */ int product_id; enum {msg_usa26, msg_usa28, msg_usa49, msg_usa90, msg_usa67} msg_format; /* Number of physical ports */ int num_ports; /* 1 if endpoint flipping used on input, 0 if not */ int indat_endp_flip; /* 1 if endpoint flipping used on output, 0 if not */ int outdat_endp_flip; /* * Table mapping input data endpoint IDs to physical port * number and flip if used */ int indat_endpoints[KEYSPAN_MAX_NUM_PORTS]; /* Same for output endpoints */ int outdat_endpoints[KEYSPAN_MAX_NUM_PORTS]; /* Input acknowledge endpoints */ int inack_endpoints[KEYSPAN_MAX_NUM_PORTS]; /* Output control endpoints */ int outcont_endpoints[KEYSPAN_MAX_NUM_PORTS]; /* Endpoint used for input status */ int instat_endpoint; /* Endpoint used for input data 49WG only */ int indat_endpoint; /* Endpoint used for global control functions */ int glocont_endpoint; int (*calculate_baud_rate)(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum); u32 baudclk; }; /* * Now for each device type we setup the device detail structure with the * appropriate information (provided in Keyspan's documentation) */ static const struct keyspan_device_details usa18x_device_details = { .product_id = keyspan_usa18x_product_id, .msg_format = msg_usa26, .num_ports = 1, .indat_endp_flip = 0, .outdat_endp_flip = 1, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {0x85}, .outcont_endpoints = {0x05}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA18X_BAUDCLK, }; static const struct keyspan_device_details usa19_device_details = { .product_id = keyspan_usa19_product_id, .msg_format = msg_usa28, .num_ports = 1, .indat_endp_flip = 1, .outdat_endp_flip = 1, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {0x83}, .outcont_endpoints = {0x03}, .instat_endpoint = 0x84, .indat_endpoint = -1, .glocont_endpoint = -1, .calculate_baud_rate = keyspan_usa19_calc_baud, .baudclk = KEYSPAN_USA19_BAUDCLK, }; static const struct keyspan_device_details usa19qi_device_details = { .product_id = keyspan_usa19qi_product_id, .msg_format = msg_usa28, .num_ports = 1, .indat_endp_flip = 1, .outdat_endp_flip = 1, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {0x83}, .outcont_endpoints = {0x03}, .instat_endpoint = 0x84, .indat_endpoint = -1, .glocont_endpoint = -1, .calculate_baud_rate = keyspan_usa28_calc_baud, .baudclk = KEYSPAN_USA19_BAUDCLK, }; static const struct keyspan_device_details mpr_device_details = { .product_id = keyspan_mpr_product_id, .msg_format = msg_usa28, .num_ports = 1, .indat_endp_flip = 1, .outdat_endp_flip = 1, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {0x83}, .outcont_endpoints = {0x03}, .instat_endpoint = 0x84, .indat_endpoint = -1, .glocont_endpoint = -1, .calculate_baud_rate = keyspan_usa28_calc_baud, .baudclk = KEYSPAN_USA19_BAUDCLK, }; static const struct keyspan_device_details usa19qw_device_details = { .product_id = keyspan_usa19qw_product_id, .msg_format = msg_usa26, .num_ports = 1, .indat_endp_flip = 0, .outdat_endp_flip = 1, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {0x85}, .outcont_endpoints = {0x05}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA19W_BAUDCLK, }; static const struct keyspan_device_details usa19w_device_details = { .product_id = keyspan_usa19w_product_id, .msg_format = msg_usa26, .num_ports = 1, .indat_endp_flip = 0, .outdat_endp_flip = 1, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {0x85}, .outcont_endpoints = {0x05}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA19W_BAUDCLK, }; static const struct keyspan_device_details usa19hs_device_details = { .product_id = keyspan_usa19hs_product_id, .msg_format = msg_usa90, .num_ports = 1, .indat_endp_flip = 0, .outdat_endp_flip = 0, .indat_endpoints = {0x81}, .outdat_endpoints = {0x01}, .inack_endpoints = {-1}, .outcont_endpoints = {0x02}, .instat_endpoint = 0x82, .indat_endpoint = -1, .glocont_endpoint = -1, .calculate_baud_rate = keyspan_usa19hs_calc_baud, .baudclk = KEYSPAN_USA19HS_BAUDCLK, }; static const struct keyspan_device_details usa28_device_details = { .product_id = keyspan_usa28_product_id, .msg_format = msg_usa28, .num_ports = 2, .indat_endp_flip = 1, .outdat_endp_flip = 1, .indat_endpoints = {0x81, 0x83}, .outdat_endpoints = {0x01, 0x03}, .inack_endpoints = {0x85, 0x86}, .outcont_endpoints = {0x05, 0x06}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa28_calc_baud, .baudclk = KEYSPAN_USA28_BAUDCLK, }; static const struct keyspan_device_details usa28x_device_details = { .product_id = keyspan_usa28x_product_id, .msg_format = msg_usa26, .num_ports = 2, .indat_endp_flip = 0, .outdat_endp_flip = 1, .indat_endpoints = {0x81, 0x83}, .outdat_endpoints = {0x01, 0x03}, .inack_endpoints = {0x85, 0x86}, .outcont_endpoints = {0x05, 0x06}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA28X_BAUDCLK, }; static const struct keyspan_device_details usa28xa_device_details = { .product_id = keyspan_usa28xa_product_id, .msg_format = msg_usa26, .num_ports = 2, .indat_endp_flip = 0, .outdat_endp_flip = 1, .indat_endpoints = {0x81, 0x83}, .outdat_endpoints = {0x01, 0x03}, .inack_endpoints = {0x85, 0x86}, .outcont_endpoints = {0x05, 0x06}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA28X_BAUDCLK, }; static const struct keyspan_device_details usa28xg_device_details = { .product_id = keyspan_usa28xg_product_id, .msg_format = msg_usa67, .num_ports = 2, .indat_endp_flip = 0, .outdat_endp_flip = 0, .indat_endpoints = {0x84, 0x88}, .outdat_endpoints = {0x02, 0x06}, .inack_endpoints = {-1, -1}, .outcont_endpoints = {-1, -1}, .instat_endpoint = 0x81, .indat_endpoint = -1, .glocont_endpoint = 0x01, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA28X_BAUDCLK, }; /* * We don't need a separate entry for the usa28xb as it appears as a 28x * anyway. */ static const struct keyspan_device_details usa49w_device_details = { .product_id = keyspan_usa49w_product_id, .msg_format = msg_usa49, .num_ports = 4, .indat_endp_flip = 0, .outdat_endp_flip = 0, .indat_endpoints = {0x81, 0x82, 0x83, 0x84}, .outdat_endpoints = {0x01, 0x02, 0x03, 0x04}, .inack_endpoints = {-1, -1, -1, -1}, .outcont_endpoints = {-1, -1, -1, -1}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA49W_BAUDCLK, }; static const struct keyspan_device_details usa49wlc_device_details = { .product_id = keyspan_usa49wlc_product_id, .msg_format = msg_usa49, .num_ports = 4, .indat_endp_flip = 0, .outdat_endp_flip = 0, .indat_endpoints = {0x81, 0x82, 0x83, 0x84}, .outdat_endpoints = {0x01, 0x02, 0x03, 0x04}, .inack_endpoints = {-1, -1, -1, -1}, .outcont_endpoints = {-1, -1, -1, -1}, .instat_endpoint = 0x87, .indat_endpoint = -1, .glocont_endpoint = 0x07, .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA19W_BAUDCLK, }; static const struct keyspan_device_details usa49wg_device_details = { .product_id = keyspan_usa49wg_product_id, .msg_format = msg_usa49, .num_ports = 4, .indat_endp_flip = 0, .outdat_endp_flip = 0, .indat_endpoints = {-1, -1, -1, -1}, /* single 'global' data in EP */ .outdat_endpoints = {0x01, 0x02, 0x04, 0x06}, .inack_endpoints = {-1, -1, -1, -1}, .outcont_endpoints = {-1, -1, -1, -1}, .instat_endpoint = 0x81, .indat_endpoint = 0x88, .glocont_endpoint = 0x00, /* uses control EP */ .calculate_baud_rate = keyspan_usa19w_calc_baud, .baudclk = KEYSPAN_USA19W_BAUDCLK, }; static const struct keyspan_device_details *keyspan_devices[] = { &usa18x_device_details, &usa19_device_details, &usa19qi_device_details, &mpr_device_details, &usa19qw_device_details, &usa19w_device_details, &usa19hs_device_details, &usa28_device_details, &usa28x_device_details, &usa28xa_device_details, &usa28xg_device_details, /* 28xb not required as it renumerates as a 28x */ &usa49w_device_details, &usa49wlc_device_details, &usa49wg_device_details, NULL, }; static const struct usb_device_id keyspan_ids_combined[] = { { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa18x_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19w_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qi_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qw_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_mpr_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28x_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xa_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xb_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49w_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49wlc_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa18x_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19w_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qi_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qw_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19hs_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_mpr_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28x_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xa_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xg_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49w_product_id)}, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49wlc_product_id)}, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49wg_product_id)}, { } /* Terminating entry */ }; MODULE_DEVICE_TABLE(usb, keyspan_ids_combined); /* usb_device_id table for the pre-firmware download keyspan devices */ static const struct usb_device_id keyspan_pre_ids[] = { { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa18x_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qi_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qw_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19w_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_mpr_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28x_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xa_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xb_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49w_pre_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49wlc_pre_product_id) }, { } /* Terminating entry */ }; static const struct usb_device_id keyspan_1port_ids[] = { { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa18x_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qi_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19qw_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19w_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa19hs_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_mpr_product_id) }, { } /* Terminating entry */ }; static const struct usb_device_id keyspan_2port_ids[] = { { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28x_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xa_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa28xg_product_id) }, { } /* Terminating entry */ }; static const struct usb_device_id keyspan_4port_ids[] = { { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49w_product_id) }, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49wlc_product_id)}, { USB_DEVICE(KEYSPAN_VENDOR_ID, keyspan_usa49wg_product_id)}, { } /* Terminating entry */ }; #define INSTAT_BUFLEN 32 #define GLOCONT_BUFLEN 64 #define INDAT49W_BUFLEN 512 #define IN_BUFLEN 64 #define OUT_BUFLEN 64 #define INACK_BUFLEN 1 #define OUTCONT_BUFLEN 64 /* Per device and per port private data */ struct keyspan_serial_private { const struct keyspan_device_details *device_details; struct urb *instat_urb; char *instat_buf; /* added to support 49wg, where data from all 4 ports comes in on 1 EP and high-speed supported */ struct urb *indat_urb; char *indat_buf; /* XXX this one probably will need a lock */ struct urb *glocont_urb; char *glocont_buf; char *ctrl_buf; /* for EP0 control message */ }; struct keyspan_port_private { /* Keep track of which input & output endpoints to use */ int in_flip; int out_flip; /* Keep duplicate of device details in each port structure as well - simplifies some of the callback functions etc. */ const struct keyspan_device_details *device_details; /* Input endpoints and buffer for this port */ struct urb *in_urbs[2]; char *in_buffer[2]; /* Output endpoints and buffer for this port */ struct urb *out_urbs[2]; char *out_buffer[2]; /* Input ack endpoint */ struct urb *inack_urb; char *inack_buffer; /* Output control endpoint */ struct urb *outcont_urb; char *outcont_buffer; /* Settings for the port */ int baud; int old_baud; unsigned int cflag; unsigned int old_cflag; enum {flow_none, flow_cts, flow_xon} flow_control; int rts_state; /* Handshaking pins (outputs) */ int dtr_state; int cts_state; /* Handshaking pins (inputs) */ int dsr_state; int dcd_state; int ri_state; int break_on; unsigned long tx_start_time[2]; int resend_cont; /* need to resend control packet */ }; /* Include Keyspan message headers. All current Keyspan Adapters make use of one of five message formats which are referred to as USA-26, USA-28, USA-49, USA-90, USA-67 by Keyspan and within this driver. */ #include "keyspan_usa26msg.h" #include "keyspan_usa28msg.h" #include "keyspan_usa49msg.h" #include "keyspan_usa90msg.h" #include "keyspan_usa67msg.h" static int keyspan_break_ctl(struct tty_struct *tty, int break_state) { struct usb_serial_port *port = tty->driver_data; struct keyspan_port_private *p_priv; p_priv = usb_get_serial_port_data(port); if (break_state == -1) p_priv->break_on = 1; else p_priv->break_on = 0; /* FIXME: return errors */ keyspan_send_setup(port, 0); return 0; } static void keyspan_set_termios(struct tty_struct *tty, struct usb_serial_port *port, const struct ktermios *old_termios) { int baud_rate, device_port; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; unsigned int cflag; p_priv = usb_get_serial_port_data(port); d_details = p_priv->device_details; cflag = tty->termios.c_cflag; device_port = port->port_number; /* Baud rate calculation takes baud rate as an integer so other rates can be generated if desired. */ baud_rate = tty_get_baud_rate(tty); /* If no match or invalid, don't change */ if (d_details->calculate_baud_rate(port, baud_rate, d_details->baudclk, NULL, NULL, NULL, device_port) == KEYSPAN_BAUD_RATE_OK) { /* FIXME - more to do here to ensure rate changes cleanly */ /* FIXME - calculate exact rate from divisor ? */ p_priv->baud = baud_rate; } else baud_rate = tty_termios_baud_rate(old_termios); tty_encode_baud_rate(tty, baud_rate, baud_rate); /* set CTS/RTS handshake etc. */ p_priv->cflag = cflag; p_priv->flow_control = (cflag & CRTSCTS) ? flow_cts : flow_none; /* Mark/Space not supported */ tty->termios.c_cflag &= ~CMSPAR; keyspan_send_setup(port, 0); } static int keyspan_tiocmget(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct keyspan_port_private *p_priv = usb_get_serial_port_data(port); unsigned int value; value = ((p_priv->rts_state) ? TIOCM_RTS : 0) | ((p_priv->dtr_state) ? TIOCM_DTR : 0) | ((p_priv->cts_state) ? TIOCM_CTS : 0) | ((p_priv->dsr_state) ? TIOCM_DSR : 0) | ((p_priv->dcd_state) ? TIOCM_CAR : 0) | ((p_priv->ri_state) ? TIOCM_RNG : 0); return value; } static int keyspan_tiocmset(struct tty_struct *tty, unsigned int set, unsigned int clear) { struct usb_serial_port *port = tty->driver_data; struct keyspan_port_private *p_priv = usb_get_serial_port_data(port); if (set & TIOCM_RTS) p_priv->rts_state = 1; if (set & TIOCM_DTR) p_priv->dtr_state = 1; if (clear & TIOCM_RTS) p_priv->rts_state = 0; if (clear & TIOCM_DTR) p_priv->dtr_state = 0; keyspan_send_setup(port, 0); return 0; } /* Write function is similar for the four protocols used with only a minor change for usa90 (usa19hs) required */ static int keyspan_write(struct tty_struct *tty, struct usb_serial_port *port, const unsigned char *buf, int count) { struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; int flip; int left, todo; struct urb *this_urb; int err, maxDataLen, dataOffset; p_priv = usb_get_serial_port_data(port); d_details = p_priv->device_details; if (d_details->msg_format == msg_usa90) { maxDataLen = 64; dataOffset = 0; } else { maxDataLen = 63; dataOffset = 1; } dev_dbg(&port->dev, "%s - %d chars, flip=%d\n", __func__, count, p_priv->out_flip); for (left = count; left > 0; left -= todo) { todo = left; if (todo > maxDataLen) todo = maxDataLen; flip = p_priv->out_flip; /* Check we have a valid urb/endpoint before we use it... */ this_urb = p_priv->out_urbs[flip]; if (this_urb == NULL) { /* no bulk out, so return 0 bytes written */ dev_dbg(&port->dev, "%s - no output urb :(\n", __func__); return count; } dev_dbg(&port->dev, "%s - endpoint %x flip %d\n", __func__, usb_pipeendpoint(this_urb->pipe), flip); if (this_urb->status == -EINPROGRESS) { if (time_before(jiffies, p_priv->tx_start_time[flip] + 10 * HZ)) break; usb_unlink_urb(this_urb); break; } /* First byte in buffer is "last flag" (except for usa19hx) - unused so for now so set to zero */ ((char *)this_urb->transfer_buffer)[0] = 0; memcpy(this_urb->transfer_buffer + dataOffset, buf, todo); buf += todo; /* send the data out the bulk port */ this_urb->transfer_buffer_length = todo + dataOffset; err = usb_submit_urb(this_urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "usb_submit_urb(write bulk) failed (%d)\n", err); p_priv->tx_start_time[flip] = jiffies; /* Flip for next time if usa26 or usa28 interface (not used on usa49) */ p_priv->out_flip = (flip + 1) & d_details->outdat_endp_flip; } return count - left; } static void usa26_indat_callback(struct urb *urb) { int i, err; int endpoint; struct usb_serial_port *port; unsigned char *data = urb->transfer_buffer; int status = urb->status; endpoint = usb_pipeendpoint(urb->pipe); if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status %d on endpoint %x\n", __func__, status, endpoint); return; } port = urb->context; if (urb->actual_length) { /* 0x80 bit is error flag */ if ((data[0] & 0x80) == 0) { /* no errors on individual bytes, only possible overrun err */ if (data[0] & RXERROR_OVERRUN) { tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } for (i = 1; i < urb->actual_length ; ++i) tty_insert_flip_char(&port->port, data[i], TTY_NORMAL); } else { /* some bytes had errors, every byte has status */ dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__); for (i = 0; i + 1 < urb->actual_length; i += 2) { int stat = data[i]; int flag = TTY_NORMAL; if (stat & RXERROR_OVERRUN) { tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } /* XXX should handle break (0x10) */ if (stat & RXERROR_PARITY) flag = TTY_PARITY; else if (stat & RXERROR_FRAMING) flag = TTY_FRAME; tty_insert_flip_char(&port->port, data[i+1], flag); } } tty_flip_buffer_push(&port->port); } /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); } /* Outdat handling is common for all devices */ static void usa2x_outdat_callback(struct urb *urb) { struct usb_serial_port *port; struct keyspan_port_private *p_priv; port = urb->context; p_priv = usb_get_serial_port_data(port); dev_dbg(&port->dev, "%s - urb %d\n", __func__, urb == p_priv->out_urbs[1]); usb_serial_port_softint(port); } static void usa26_inack_callback(struct urb *urb) { } static void usa26_outcont_callback(struct urb *urb) { struct usb_serial_port *port; struct keyspan_port_private *p_priv; port = urb->context; p_priv = usb_get_serial_port_data(port); if (p_priv->resend_cont) { dev_dbg(&port->dev, "%s - sending setup\n", __func__); keyspan_usa26_send_setup(port->serial, port, p_priv->resend_cont - 1); } } static void usa26_instat_callback(struct urb *urb) { unsigned char *data = urb->transfer_buffer; struct keyspan_usa26_portStatusMessage *msg; struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int old_dcd_state, err; int status = urb->status; serial = urb->context; if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status: %d\n", __func__, status); return; } if (urb->actual_length != 9) { dev_dbg(&urb->dev->dev, "%s - %d byte report??\n", __func__, urb->actual_length); goto exit; } msg = (struct keyspan_usa26_portStatusMessage *)data; /* Check port number from message and retrieve private data */ if (msg->port >= serial->num_ports) { dev_dbg(&urb->dev->dev, "%s - Unexpected port number %d\n", __func__, msg->port); goto exit; } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); if (!p_priv) goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; p_priv->cts_state = ((msg->hskia_cts) ? 1 : 0); p_priv->dsr_state = ((msg->dsr) ? 1 : 0); p_priv->dcd_state = ((msg->gpia_dcd) ? 1 : 0); p_priv->ri_state = ((msg->ri) ? 1 : 0); if (old_dcd_state != p_priv->dcd_state) tty_port_tty_hangup(&port->port, true); resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); exit: ; } static void usa26_glocont_callback(struct urb *urb) { } static void usa28_indat_callback(struct urb *urb) { int err; struct usb_serial_port *port; unsigned char *data; struct keyspan_port_private *p_priv; int status = urb->status; port = urb->context; p_priv = usb_get_serial_port_data(port); if (urb != p_priv->in_urbs[p_priv->in_flip]) return; do { if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status %d on endpoint %x\n", __func__, status, usb_pipeendpoint(urb->pipe)); return; } port = urb->context; p_priv = usb_get_serial_port_data(port); data = urb->transfer_buffer; if (urb->actual_length) { tty_insert_flip_string(&port->port, data, urb->actual_length); tty_flip_buffer_push(&port->port); } /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); p_priv->in_flip ^= 1; urb = p_priv->in_urbs[p_priv->in_flip]; } while (urb->status != -EINPROGRESS); } static void usa28_inack_callback(struct urb *urb) { } static void usa28_outcont_callback(struct urb *urb) { struct usb_serial_port *port; struct keyspan_port_private *p_priv; port = urb->context; p_priv = usb_get_serial_port_data(port); if (p_priv->resend_cont) { dev_dbg(&port->dev, "%s - sending setup\n", __func__); keyspan_usa28_send_setup(port->serial, port, p_priv->resend_cont - 1); } } static void usa28_instat_callback(struct urb *urb) { int err; unsigned char *data = urb->transfer_buffer; struct keyspan_usa28_portStatusMessage *msg; struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int old_dcd_state; int status = urb->status; serial = urb->context; if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status: %d\n", __func__, status); return; } if (urb->actual_length != sizeof(struct keyspan_usa28_portStatusMessage)) { dev_dbg(&urb->dev->dev, "%s - bad length %d\n", __func__, urb->actual_length); goto exit; } msg = (struct keyspan_usa28_portStatusMessage *)data; /* Check port number from message and retrieve private data */ if (msg->port >= serial->num_ports) { dev_dbg(&urb->dev->dev, "%s - Unexpected port number %d\n", __func__, msg->port); goto exit; } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); if (!p_priv) goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; p_priv->cts_state = ((msg->cts) ? 1 : 0); p_priv->dsr_state = ((msg->dsr) ? 1 : 0); p_priv->dcd_state = ((msg->dcd) ? 1 : 0); p_priv->ri_state = ((msg->ri) ? 1 : 0); if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); exit: ; } static void usa28_glocont_callback(struct urb *urb) { } static void usa49_glocont_callback(struct urb *urb) { struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int i; serial = urb->context; for (i = 0; i < serial->num_ports; ++i) { port = serial->port[i]; p_priv = usb_get_serial_port_data(port); if (!p_priv) continue; if (p_priv->resend_cont) { dev_dbg(&port->dev, "%s - sending setup\n", __func__); keyspan_usa49_send_setup(serial, port, p_priv->resend_cont - 1); break; } } } /* This is actually called glostat in the Keyspan doco */ static void usa49_instat_callback(struct urb *urb) { int err; unsigned char *data = urb->transfer_buffer; struct keyspan_usa49_portStatusMessage *msg; struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int old_dcd_state; int status = urb->status; serial = urb->context; if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status: %d\n", __func__, status); return; } if (urb->actual_length != sizeof(struct keyspan_usa49_portStatusMessage)) { dev_dbg(&urb->dev->dev, "%s - bad length %d\n", __func__, urb->actual_length); goto exit; } msg = (struct keyspan_usa49_portStatusMessage *)data; /* Check port number from message and retrieve private data */ if (msg->portNumber >= serial->num_ports) { dev_dbg(&urb->dev->dev, "%s - Unexpected port number %d\n", __func__, msg->portNumber); goto exit; } port = serial->port[msg->portNumber]; p_priv = usb_get_serial_port_data(port); if (!p_priv) goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; p_priv->cts_state = ((msg->cts) ? 1 : 0); p_priv->dsr_state = ((msg->dsr) ? 1 : 0); p_priv->dcd_state = ((msg->dcd) ? 1 : 0); p_priv->ri_state = ((msg->ri) ? 1 : 0); if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); exit: ; } static void usa49_inack_callback(struct urb *urb) { } static void usa49_indat_callback(struct urb *urb) { int i, err; int endpoint; struct usb_serial_port *port; unsigned char *data = urb->transfer_buffer; int status = urb->status; endpoint = usb_pipeendpoint(urb->pipe); if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status %d on endpoint %x\n", __func__, status, endpoint); return; } port = urb->context; if (urb->actual_length) { /* 0x80 bit is error flag */ if ((data[0] & 0x80) == 0) { /* no error on any byte */ tty_insert_flip_string(&port->port, data + 1, urb->actual_length - 1); } else { /* some bytes had errors, every byte has status */ for (i = 0; i + 1 < urb->actual_length; i += 2) { int stat = data[i]; int flag = TTY_NORMAL; if (stat & RXERROR_OVERRUN) { tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } /* XXX should handle break (0x10) */ if (stat & RXERROR_PARITY) flag = TTY_PARITY; else if (stat & RXERROR_FRAMING) flag = TTY_FRAME; tty_insert_flip_char(&port->port, data[i+1], flag); } } tty_flip_buffer_push(&port->port); } /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); } static void usa49wg_indat_callback(struct urb *urb) { int i, len, x, err; struct usb_serial *serial; struct usb_serial_port *port; unsigned char *data = urb->transfer_buffer; int status = urb->status; serial = urb->context; if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status: %d\n", __func__, status); return; } /* inbound data is in the form P#, len, status, data */ i = 0; len = 0; while (i < urb->actual_length) { if (urb->actual_length - i < 3) { dev_warn_ratelimited(&urb->dev->dev, "malformed indat packet\n"); break; } /* Check port number from message */ if (data[i] >= serial->num_ports) { dev_dbg(&urb->dev->dev, "%s - Unexpected port number %d\n", __func__, data[i]); return; } port = serial->port[data[i++]]; len = data[i++]; /* 0x80 bit is error flag */ if ((data[i] & 0x80) == 0) { /* no error on any byte */ i++; for (x = 1; x < len && i < urb->actual_length; ++x) tty_insert_flip_char(&port->port, data[i++], 0); } else { /* * some bytes had errors, every byte has status */ for (x = 0; x + 1 < len && i + 1 < urb->actual_length; x += 2) { int stat = data[i]; int flag = TTY_NORMAL; if (stat & RXERROR_OVERRUN) { tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } /* XXX should handle break (0x10) */ if (stat & RXERROR_PARITY) flag = TTY_PARITY; else if (stat & RXERROR_FRAMING) flag = TTY_FRAME; tty_insert_flip_char(&port->port, data[i+1], flag); i += 2; } } tty_flip_buffer_push(&port->port); } /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&urb->dev->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); } /* not used, usa-49 doesn't have per-port control endpoints */ static void usa49_outcont_callback(struct urb *urb) { } static void usa90_indat_callback(struct urb *urb) { int i, err; int endpoint; struct usb_serial_port *port; struct keyspan_port_private *p_priv; unsigned char *data = urb->transfer_buffer; int status = urb->status; endpoint = usb_pipeendpoint(urb->pipe); if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status %d on endpoint %x\n", __func__, status, endpoint); return; } port = urb->context; p_priv = usb_get_serial_port_data(port); if (urb->actual_length) { /* if current mode is DMA, looks like usa28 format otherwise looks like usa26 data format */ if (p_priv->baud > 57600) tty_insert_flip_string(&port->port, data, urb->actual_length); else { /* 0x80 bit is error flag */ if ((data[0] & 0x80) == 0) { /* no errors on individual bytes, only possible overrun err*/ if (data[0] & RXERROR_OVERRUN) { tty_insert_flip_char(&port->port, 0, TTY_OVERRUN); } for (i = 1; i < urb->actual_length ; ++i) tty_insert_flip_char(&port->port, data[i], TTY_NORMAL); } else { /* some bytes had errors, every byte has status */ dev_dbg(&port->dev, "%s - RX error!!!!\n", __func__); for (i = 0; i + 1 < urb->actual_length; i += 2) { int stat = data[i]; int flag = TTY_NORMAL; if (stat & RXERROR_OVERRUN) { tty_insert_flip_char( &port->port, 0, TTY_OVERRUN); } /* XXX should handle break (0x10) */ if (stat & RXERROR_PARITY) flag = TTY_PARITY; else if (stat & RXERROR_FRAMING) flag = TTY_FRAME; tty_insert_flip_char(&port->port, data[i+1], flag); } } } tty_flip_buffer_push(&port->port); } /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); } static void usa90_instat_callback(struct urb *urb) { unsigned char *data = urb->transfer_buffer; struct keyspan_usa90_portStatusMessage *msg; struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int old_dcd_state, err; int status = urb->status; serial = urb->context; if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status: %d\n", __func__, status); return; } if (urb->actual_length < 14) { dev_dbg(&urb->dev->dev, "%s - %d byte report??\n", __func__, urb->actual_length); goto exit; } msg = (struct keyspan_usa90_portStatusMessage *)data; /* Now do something useful with the data */ port = serial->port[0]; p_priv = usb_get_serial_port_data(port); if (!p_priv) goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; p_priv->cts_state = ((msg->cts) ? 1 : 0); p_priv->dsr_state = ((msg->dsr) ? 1 : 0); p_priv->dcd_state = ((msg->dcd) ? 1 : 0); p_priv->ri_state = ((msg->ri) ? 1 : 0); if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); exit: ; } static void usa90_outcont_callback(struct urb *urb) { struct usb_serial_port *port; struct keyspan_port_private *p_priv; port = urb->context; p_priv = usb_get_serial_port_data(port); if (p_priv->resend_cont) { dev_dbg(&urb->dev->dev, "%s - sending setup\n", __func__); keyspan_usa90_send_setup(port->serial, port, p_priv->resend_cont - 1); } } /* Status messages from the 28xg */ static void usa67_instat_callback(struct urb *urb) { int err; unsigned char *data = urb->transfer_buffer; struct keyspan_usa67_portStatusMessage *msg; struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int old_dcd_state; int status = urb->status; serial = urb->context; if (status) { dev_dbg(&urb->dev->dev, "%s - nonzero status: %d\n", __func__, status); return; } if (urb->actual_length != sizeof(struct keyspan_usa67_portStatusMessage)) { dev_dbg(&urb->dev->dev, "%s - bad length %d\n", __func__, urb->actual_length); return; } /* Now do something useful with the data */ msg = (struct keyspan_usa67_portStatusMessage *)data; /* Check port number from message and retrieve private data */ if (msg->port >= serial->num_ports) { dev_dbg(&urb->dev->dev, "%s - Unexpected port number %d\n", __func__, msg->port); return; } port = serial->port[msg->port]; p_priv = usb_get_serial_port_data(port); if (!p_priv) goto resubmit; /* Update handshaking pin state information */ old_dcd_state = p_priv->dcd_state; p_priv->cts_state = ((msg->hskia_cts) ? 1 : 0); p_priv->dcd_state = ((msg->gpia_dcd) ? 1 : 0); if (old_dcd_state != p_priv->dcd_state && old_dcd_state) tty_port_tty_hangup(&port->port, true); resubmit: /* Resubmit urb so we continue receiving */ err = usb_submit_urb(urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - resubmit read urb failed. (%d)\n", __func__, err); } static void usa67_glocont_callback(struct urb *urb) { struct usb_serial *serial; struct usb_serial_port *port; struct keyspan_port_private *p_priv; int i; serial = urb->context; for (i = 0; i < serial->num_ports; ++i) { port = serial->port[i]; p_priv = usb_get_serial_port_data(port); if (!p_priv) continue; if (p_priv->resend_cont) { dev_dbg(&port->dev, "%s - sending setup\n", __func__); keyspan_usa67_send_setup(serial, port, p_priv->resend_cont - 1); break; } } } static unsigned int keyspan_write_room(struct tty_struct *tty) { struct usb_serial_port *port = tty->driver_data; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; int flip; unsigned int data_len; struct urb *this_urb; p_priv = usb_get_serial_port_data(port); d_details = p_priv->device_details; /* FIXME: locking */ if (d_details->msg_format == msg_usa90) data_len = 64; else data_len = 63; flip = p_priv->out_flip; /* Check both endpoints to see if any are available. */ this_urb = p_priv->out_urbs[flip]; if (this_urb != NULL) { if (this_urb->status != -EINPROGRESS) return data_len; flip = (flip + 1) & d_details->outdat_endp_flip; this_urb = p_priv->out_urbs[flip]; if (this_urb != NULL) { if (this_urb->status != -EINPROGRESS) return data_len; } } return 0; } static int keyspan_open(struct tty_struct *tty, struct usb_serial_port *port) { struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; int i, err; int baud_rate, device_port; struct urb *urb; unsigned int cflag = 0; p_priv = usb_get_serial_port_data(port); d_details = p_priv->device_details; /* Set some sane defaults */ p_priv->rts_state = 1; p_priv->dtr_state = 1; p_priv->baud = 9600; /* force baud and lcr to be set on open */ p_priv->old_baud = 0; p_priv->old_cflag = 0; p_priv->out_flip = 0; p_priv->in_flip = 0; /* Reset low level data toggle and start reading from endpoints */ for (i = 0; i < 2; i++) { urb = p_priv->in_urbs[i]; if (urb == NULL) continue; /* make sure endpoint data toggle is synchronized with the device */ usb_clear_halt(urb->dev, urb->pipe); err = usb_submit_urb(urb, GFP_KERNEL); if (err != 0) dev_dbg(&port->dev, "%s - submit urb %d failed (%d)\n", __func__, i, err); } /* Reset low level data toggle on out endpoints */ for (i = 0; i < 2; i++) { urb = p_priv->out_urbs[i]; if (urb == NULL) continue; /* usb_settoggle(urb->dev, usb_pipeendpoint(urb->pipe), usb_pipeout(urb->pipe), 0); */ } /* get the terminal config for the setup message now so we don't * need to send 2 of them */ device_port = port->port_number; if (tty) { cflag = tty->termios.c_cflag; /* Baud rate calculation takes baud rate as an integer so other rates can be generated if desired. */ baud_rate = tty_get_baud_rate(tty); /* If no match or invalid, leave as default */ if (baud_rate >= 0 && d_details->calculate_baud_rate(port, baud_rate, d_details->baudclk, NULL, NULL, NULL, device_port) == KEYSPAN_BAUD_RATE_OK) { p_priv->baud = baud_rate; } } /* set CTS/RTS handshake etc. */ p_priv->cflag = cflag; p_priv->flow_control = (cflag & CRTSCTS) ? flow_cts : flow_none; keyspan_send_setup(port, 1); /* mdelay(100); */ /* keyspan_set_termios(port, NULL); */ return 0; } static void keyspan_dtr_rts(struct usb_serial_port *port, int on) { struct keyspan_port_private *p_priv = usb_get_serial_port_data(port); p_priv->rts_state = on; p_priv->dtr_state = on; keyspan_send_setup(port, 0); } static void keyspan_close(struct usb_serial_port *port) { int i; struct keyspan_port_private *p_priv; p_priv = usb_get_serial_port_data(port); p_priv->rts_state = 0; p_priv->dtr_state = 0; keyspan_send_setup(port, 2); /* pilot-xfer seems to work best with this delay */ mdelay(100); p_priv->out_flip = 0; p_priv->in_flip = 0; usb_kill_urb(p_priv->inack_urb); for (i = 0; i < 2; i++) { usb_kill_urb(p_priv->in_urbs[i]); usb_kill_urb(p_priv->out_urbs[i]); } } /* download the firmware to a pre-renumeration device */ static int keyspan_fake_startup(struct usb_serial *serial) { char *fw_name; dev_dbg(&serial->dev->dev, "Keyspan startup version %04x product %04x\n", le16_to_cpu(serial->dev->descriptor.bcdDevice), le16_to_cpu(serial->dev->descriptor.idProduct)); if ((le16_to_cpu(serial->dev->descriptor.bcdDevice) & 0x8000) != 0x8000) { dev_dbg(&serial->dev->dev, "Firmware already loaded. Quitting.\n"); return 1; } /* Select firmware image on the basis of idProduct */ switch (le16_to_cpu(serial->dev->descriptor.idProduct)) { case keyspan_usa28_pre_product_id: fw_name = "keyspan/usa28.fw"; break; case keyspan_usa28x_pre_product_id: fw_name = "keyspan/usa28x.fw"; break; case keyspan_usa28xa_pre_product_id: fw_name = "keyspan/usa28xa.fw"; break; case keyspan_usa28xb_pre_product_id: fw_name = "keyspan/usa28xb.fw"; break; case keyspan_usa19_pre_product_id: fw_name = "keyspan/usa19.fw"; break; case keyspan_usa19qi_pre_product_id: fw_name = "keyspan/usa19qi.fw"; break; case keyspan_mpr_pre_product_id: fw_name = "keyspan/mpr.fw"; break; case keyspan_usa19qw_pre_product_id: fw_name = "keyspan/usa19qw.fw"; break; case keyspan_usa18x_pre_product_id: fw_name = "keyspan/usa18x.fw"; break; case keyspan_usa19w_pre_product_id: fw_name = "keyspan/usa19w.fw"; break; case keyspan_usa49w_pre_product_id: fw_name = "keyspan/usa49w.fw"; break; case keyspan_usa49wlc_pre_product_id: fw_name = "keyspan/usa49wlc.fw"; break; default: dev_err(&serial->dev->dev, "Unknown product ID (%04x)\n", le16_to_cpu(serial->dev->descriptor.idProduct)); return 1; } dev_dbg(&serial->dev->dev, "Uploading Keyspan %s firmware.\n", fw_name); if (ezusb_fx1_ihex_firmware_download(serial->dev, fw_name) < 0) { dev_err(&serial->dev->dev, "failed to load firmware \"%s\"\n", fw_name); return -ENOENT; } /* after downloading firmware Renumeration will occur in a moment and the new device will bind to the real driver */ /* we don't want this device to have a driver assigned to it. */ return 1; } /* Helper functions used by keyspan_setup_urbs */ static struct usb_endpoint_descriptor const *find_ep(struct usb_serial const *serial, int endpoint) { struct usb_host_interface *iface_desc; struct usb_endpoint_descriptor *ep; int i; iface_desc = serial->interface->cur_altsetting; for (i = 0; i < iface_desc->desc.bNumEndpoints; ++i) { ep = &iface_desc->endpoint[i].desc; if (ep->bEndpointAddress == endpoint) return ep; } dev_warn(&serial->interface->dev, "found no endpoint descriptor for endpoint %x\n", endpoint); return NULL; } static struct urb *keyspan_setup_urb(struct usb_serial *serial, int endpoint, int dir, void *ctx, char *buf, int len, void (*callback)(struct urb *)) { struct urb *urb; struct usb_endpoint_descriptor const *ep_desc; char const *ep_type_name; if (endpoint == -1) return NULL; /* endpoint not needed */ dev_dbg(&serial->interface->dev, "%s - alloc for endpoint %x\n", __func__, endpoint); urb = usb_alloc_urb(0, GFP_KERNEL); /* No ISO */ if (!urb) return NULL; if (endpoint == 0) { /* control EP filled in when used */ return urb; } ep_desc = find_ep(serial, endpoint); if (!ep_desc) { usb_free_urb(urb); return NULL; } if (usb_endpoint_xfer_int(ep_desc)) { ep_type_name = "INT"; usb_fill_int_urb(urb, serial->dev, usb_sndintpipe(serial->dev, endpoint) | dir, buf, len, callback, ctx, ep_desc->bInterval); } else if (usb_endpoint_xfer_bulk(ep_desc)) { ep_type_name = "BULK"; usb_fill_bulk_urb(urb, serial->dev, usb_sndbulkpipe(serial->dev, endpoint) | dir, buf, len, callback, ctx); } else { dev_warn(&serial->interface->dev, "unsupported endpoint type %x\n", usb_endpoint_type(ep_desc)); usb_free_urb(urb); return NULL; } dev_dbg(&serial->interface->dev, "%s - using urb %p for %s endpoint %x\n", __func__, urb, ep_type_name, endpoint); return urb; } static struct callbacks { void (*instat_callback)(struct urb *); void (*glocont_callback)(struct urb *); void (*indat_callback)(struct urb *); void (*outdat_callback)(struct urb *); void (*inack_callback)(struct urb *); void (*outcont_callback)(struct urb *); } keyspan_callbacks[] = { { /* msg_usa26 callbacks */ .instat_callback = usa26_instat_callback, .glocont_callback = usa26_glocont_callback, .indat_callback = usa26_indat_callback, .outdat_callback = usa2x_outdat_callback, .inack_callback = usa26_inack_callback, .outcont_callback = usa26_outcont_callback, }, { /* msg_usa28 callbacks */ .instat_callback = usa28_instat_callback, .glocont_callback = usa28_glocont_callback, .indat_callback = usa28_indat_callback, .outdat_callback = usa2x_outdat_callback, .inack_callback = usa28_inack_callback, .outcont_callback = usa28_outcont_callback, }, { /* msg_usa49 callbacks */ .instat_callback = usa49_instat_callback, .glocont_callback = usa49_glocont_callback, .indat_callback = usa49_indat_callback, .outdat_callback = usa2x_outdat_callback, .inack_callback = usa49_inack_callback, .outcont_callback = usa49_outcont_callback, }, { /* msg_usa90 callbacks */ .instat_callback = usa90_instat_callback, .glocont_callback = usa28_glocont_callback, .indat_callback = usa90_indat_callback, .outdat_callback = usa2x_outdat_callback, .inack_callback = usa28_inack_callback, .outcont_callback = usa90_outcont_callback, }, { /* msg_usa67 callbacks */ .instat_callback = usa67_instat_callback, .glocont_callback = usa67_glocont_callback, .indat_callback = usa26_indat_callback, .outdat_callback = usa2x_outdat_callback, .inack_callback = usa26_inack_callback, .outcont_callback = usa26_outcont_callback, } }; /* Generic setup urbs function that uses data in device_details */ static void keyspan_setup_urbs(struct usb_serial *serial) { struct keyspan_serial_private *s_priv; const struct keyspan_device_details *d_details; struct callbacks *cback; s_priv = usb_get_serial_data(serial); d_details = s_priv->device_details; /* Setup values for the various callback routines */ cback = &keyspan_callbacks[d_details->msg_format]; /* Allocate and set up urbs for each one that is in use, starting with instat endpoints */ s_priv->instat_urb = keyspan_setup_urb (serial, d_details->instat_endpoint, USB_DIR_IN, serial, s_priv->instat_buf, INSTAT_BUFLEN, cback->instat_callback); s_priv->indat_urb = keyspan_setup_urb (serial, d_details->indat_endpoint, USB_DIR_IN, serial, s_priv->indat_buf, INDAT49W_BUFLEN, usa49wg_indat_callback); s_priv->glocont_urb = keyspan_setup_urb (serial, d_details->glocont_endpoint, USB_DIR_OUT, serial, s_priv->glocont_buf, GLOCONT_BUFLEN, cback->glocont_callback); } /* usa19 function doesn't require prescaler */ static int keyspan_usa19_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum) { u32 b16, /* baud rate times 16 (actual rate used internally) */ div, /* divisor */ cnt; /* inverse of divisor (programmed into 8051) */ dev_dbg(&port->dev, "%s - %d.\n", __func__, baud_rate); /* prevent divide by zero... */ b16 = baud_rate * 16L; if (b16 == 0) return KEYSPAN_INVALID_BAUD_RATE; /* Any "standard" rate over 57k6 is marginal on the USA-19 as we run out of divisor resolution. */ if (baud_rate > 57600) return KEYSPAN_INVALID_BAUD_RATE; /* calculate the divisor and the counter (its inverse) */ div = baudclk / b16; if (div == 0) return KEYSPAN_INVALID_BAUD_RATE; else cnt = 0 - div; if (div > 0xffff) return KEYSPAN_INVALID_BAUD_RATE; /* return the counter values if non-null */ if (rate_low) *rate_low = (u8) (cnt & 0xff); if (rate_hi) *rate_hi = (u8) ((cnt >> 8) & 0xff); if (rate_low && rate_hi) dev_dbg(&port->dev, "%s - %d %02x %02x.\n", __func__, baud_rate, *rate_hi, *rate_low); return KEYSPAN_BAUD_RATE_OK; } /* usa19hs function doesn't require prescaler */ static int keyspan_usa19hs_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum) { u32 b16, /* baud rate times 16 (actual rate used internally) */ div; /* divisor */ dev_dbg(&port->dev, "%s - %d.\n", __func__, baud_rate); /* prevent divide by zero... */ b16 = baud_rate * 16L; if (b16 == 0) return KEYSPAN_INVALID_BAUD_RATE; /* calculate the divisor */ div = baudclk / b16; if (div == 0) return KEYSPAN_INVALID_BAUD_RATE; if (div > 0xffff) return KEYSPAN_INVALID_BAUD_RATE; /* return the counter values if non-null */ if (rate_low) *rate_low = (u8) (div & 0xff); if (rate_hi) *rate_hi = (u8) ((div >> 8) & 0xff); if (rate_low && rate_hi) dev_dbg(&port->dev, "%s - %d %02x %02x.\n", __func__, baud_rate, *rate_hi, *rate_low); return KEYSPAN_BAUD_RATE_OK; } static int keyspan_usa19w_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum) { u32 b16, /* baud rate times 16 (actual rate used internally) */ clk, /* clock with 13/8 prescaler */ div, /* divisor using 13/8 prescaler */ res, /* resulting baud rate using 13/8 prescaler */ diff, /* error using 13/8 prescaler */ smallest_diff; u8 best_prescaler; int i; dev_dbg(&port->dev, "%s - %d.\n", __func__, baud_rate); /* prevent divide by zero */ b16 = baud_rate * 16L; if (b16 == 0) return KEYSPAN_INVALID_BAUD_RATE; /* Calculate prescaler by trying them all and looking for best fit */ /* start with largest possible difference */ smallest_diff = 0xffffffff; /* 0 is an invalid prescaler, used as a flag */ best_prescaler = 0; for (i = 8; i <= 0xff; ++i) { clk = (baudclk * 8) / (u32) i; div = clk / b16; if (div == 0) continue; res = clk / div; diff = (res > b16) ? (res-b16) : (b16-res); if (diff < smallest_diff) { best_prescaler = i; smallest_diff = diff; } } if (best_prescaler == 0) return KEYSPAN_INVALID_BAUD_RATE; clk = (baudclk * 8) / (u32) best_prescaler; div = clk / b16; /* return the divisor and prescaler if non-null */ if (rate_low) *rate_low = (u8) (div & 0xff); if (rate_hi) *rate_hi = (u8) ((div >> 8) & 0xff); if (prescaler) { *prescaler = best_prescaler; /* dev_dbg(&port->dev, "%s - %d %d\n", __func__, *prescaler, div); */ } return KEYSPAN_BAUD_RATE_OK; } /* USA-28 supports different maximum baud rates on each port */ static int keyspan_usa28_calc_baud(struct usb_serial_port *port, u32 baud_rate, u32 baudclk, u8 *rate_hi, u8 *rate_low, u8 *prescaler, int portnum) { u32 b16, /* baud rate times 16 (actual rate used internally) */ div, /* divisor */ cnt; /* inverse of divisor (programmed into 8051) */ dev_dbg(&port->dev, "%s - %d.\n", __func__, baud_rate); /* prevent divide by zero */ b16 = baud_rate * 16L; if (b16 == 0) return KEYSPAN_INVALID_BAUD_RATE; /* calculate the divisor and the counter (its inverse) */ div = KEYSPAN_USA28_BAUDCLK / b16; if (div == 0) return KEYSPAN_INVALID_BAUD_RATE; else cnt = 0 - div; /* check for out of range, based on portnum, and return result */ if (portnum == 0) { if (div > 0xffff) return KEYSPAN_INVALID_BAUD_RATE; } else { if (portnum == 1) { if (div > 0xff) return KEYSPAN_INVALID_BAUD_RATE; } else return KEYSPAN_INVALID_BAUD_RATE; } /* return the counter values if not NULL (port 1 will ignore retHi) */ if (rate_low) *rate_low = (u8) (cnt & 0xff); if (rate_hi) *rate_hi = (u8) ((cnt >> 8) & 0xff); dev_dbg(&port->dev, "%s - %d OK.\n", __func__, baud_rate); return KEYSPAN_BAUD_RATE_OK; } static int keyspan_usa26_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port) { struct keyspan_usa26_portControlMessage msg; struct keyspan_serial_private *s_priv; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; struct urb *this_urb; int device_port, err; dev_dbg(&port->dev, "%s reset=%d\n", __func__, reset_port); s_priv = usb_get_serial_data(serial); p_priv = usb_get_serial_port_data(port); d_details = s_priv->device_details; device_port = port->port_number; this_urb = p_priv->outcont_urb; /* Make sure we have an urb then send the message */ if (this_urb == NULL) { dev_dbg(&port->dev, "%s - oops no urb.\n", __func__); return -1; } dev_dbg(&port->dev, "%s - endpoint %x\n", __func__, usb_pipeendpoint(this_urb->pipe)); /* Save reset port val for resend. Don't overwrite resend for open/close condition. */ if ((reset_port + 1) > p_priv->resend_cont) p_priv->resend_cont = reset_port + 1; if (this_urb->status == -EINPROGRESS) { /* dev_dbg(&port->dev, "%s - already writing\n", __func__); */ mdelay(5); return -1; } memset(&msg, 0, sizeof(struct keyspan_usa26_portControlMessage)); /* Only set baud rate if it's changed */ if (p_priv->old_baud != p_priv->baud) { p_priv->old_baud = p_priv->baud; msg.setClocking = 0xff; if (d_details->calculate_baud_rate(port, p_priv->baud, d_details->baudclk, &msg.baudHi, &msg.baudLo, &msg.prescaler, device_port) == KEYSPAN_INVALID_BAUD_RATE) { dev_dbg(&port->dev, "%s - Invalid baud rate %d requested, using 9600.\n", __func__, p_priv->baud); msg.baudLo = 0; msg.baudHi = 125; /* Values for 9600 baud */ msg.prescaler = 10; } msg.setPrescaler = 0xff; } msg.lcr = (p_priv->cflag & CSTOPB) ? STOPBITS_678_2 : STOPBITS_5678_1; switch (p_priv->cflag & CSIZE) { case CS5: msg.lcr |= USA_DATABITS_5; break; case CS6: msg.lcr |= USA_DATABITS_6; break; case CS7: msg.lcr |= USA_DATABITS_7; break; case CS8: msg.lcr |= USA_DATABITS_8; break; } if (p_priv->cflag & PARENB) { /* note USA_PARITY_NONE == 0 */ msg.lcr |= (p_priv->cflag & PARODD) ? USA_PARITY_ODD : USA_PARITY_EVEN; } msg.setLcr = 0xff; msg.ctsFlowControl = (p_priv->flow_control == flow_cts); msg.xonFlowControl = 0; msg.setFlowControl = 0xff; msg.forwardingLength = 16; msg.xonChar = 17; msg.xoffChar = 19; /* Opening port */ if (reset_port == 1) { msg._txOn = 1; msg._txOff = 0; msg.txFlush = 0; msg.txBreak = 0; msg.rxOn = 1; msg.rxOff = 0; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0xff; } /* Closing port */ else if (reset_port == 2) { msg._txOn = 0; msg._txOff = 1; msg.txFlush = 0; msg.txBreak = 0; msg.rxOn = 0; msg.rxOff = 1; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0; } /* Sending intermediate configs */ else { msg._txOn = (!p_priv->break_on); msg._txOff = 0; msg.txFlush = 0; msg.txBreak = (p_priv->break_on); msg.rxOn = 0; msg.rxOff = 0; msg.rxFlush = 0; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0x0; } /* Do handshaking outputs */ msg.setTxTriState_setRts = 0xff; msg.txTriState_rts = p_priv->rts_state; msg.setHskoa_setDtr = 0xff; msg.hskoa_dtr = p_priv->dtr_state; p_priv->resend_cont = 0; memcpy(this_urb->transfer_buffer, &msg, sizeof(msg)); /* send the data out the device on control endpoint */ this_urb->transfer_buffer_length = sizeof(msg); err = usb_submit_urb(this_urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - usb_submit_urb(setup) failed (%d)\n", __func__, err); return 0; } static int keyspan_usa28_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port) { struct keyspan_usa28_portControlMessage msg; struct keyspan_serial_private *s_priv; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; struct urb *this_urb; int device_port, err; s_priv = usb_get_serial_data(serial); p_priv = usb_get_serial_port_data(port); d_details = s_priv->device_details; device_port = port->port_number; /* only do something if we have a bulk out endpoint */ this_urb = p_priv->outcont_urb; if (this_urb == NULL) { dev_dbg(&port->dev, "%s - oops no urb.\n", __func__); return -1; } /* Save reset port val for resend. Don't overwrite resend for open/close condition. */ if ((reset_port + 1) > p_priv->resend_cont) p_priv->resend_cont = reset_port + 1; if (this_urb->status == -EINPROGRESS) { dev_dbg(&port->dev, "%s already writing\n", __func__); mdelay(5); return -1; } memset(&msg, 0, sizeof(struct keyspan_usa28_portControlMessage)); msg.setBaudRate = 1; if (d_details->calculate_baud_rate(port, p_priv->baud, d_details->baudclk, &msg.baudHi, &msg.baudLo, NULL, device_port) == KEYSPAN_INVALID_BAUD_RATE) { dev_dbg(&port->dev, "%s - Invalid baud rate requested %d.\n", __func__, p_priv->baud); msg.baudLo = 0xff; msg.baudHi = 0xb2; /* Values for 9600 baud */ } /* If parity is enabled, we must calculate it ourselves. */ msg.parity = 0; /* XXX for now */ msg.ctsFlowControl = (p_priv->flow_control == flow_cts); msg.xonFlowControl = 0; /* Do handshaking outputs, DTR is inverted relative to RTS */ msg.rts = p_priv->rts_state; msg.dtr = p_priv->dtr_state; msg.forwardingLength = 16; msg.forwardMs = 10; msg.breakThreshold = 45; msg.xonChar = 17; msg.xoffChar = 19; /*msg.returnStatus = 1; msg.resetDataToggle = 0xff;*/ /* Opening port */ if (reset_port == 1) { msg._txOn = 1; msg._txOff = 0; msg.txFlush = 0; msg.txForceXoff = 0; msg.txBreak = 0; msg.rxOn = 1; msg.rxOff = 0; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0xff; } /* Closing port */ else if (reset_port == 2) { msg._txOn = 0; msg._txOff = 1; msg.txFlush = 0; msg.txForceXoff = 0; msg.txBreak = 0; msg.rxOn = 0; msg.rxOff = 1; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0; } /* Sending intermediate configs */ else { msg._txOn = (!p_priv->break_on); msg._txOff = 0; msg.txFlush = 0; msg.txForceXoff = 0; msg.txBreak = (p_priv->break_on); msg.rxOn = 0; msg.rxOff = 0; msg.rxFlush = 0; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0x0; } p_priv->resend_cont = 0; memcpy(this_urb->transfer_buffer, &msg, sizeof(msg)); /* send the data out the device on control endpoint */ this_urb->transfer_buffer_length = sizeof(msg); err = usb_submit_urb(this_urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - usb_submit_urb(setup) failed\n", __func__); return 0; } static int keyspan_usa49_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port) { struct keyspan_usa49_portControlMessage msg; struct usb_ctrlrequest *dr = NULL; struct keyspan_serial_private *s_priv; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; struct urb *this_urb; int err, device_port; s_priv = usb_get_serial_data(serial); p_priv = usb_get_serial_port_data(port); d_details = s_priv->device_details; this_urb = s_priv->glocont_urb; /* Work out which port within the device is being setup */ device_port = port->port_number; /* Make sure we have an urb then send the message */ if (this_urb == NULL) { dev_dbg(&port->dev, "%s - oops no urb for port.\n", __func__); return -1; } dev_dbg(&port->dev, "%s - endpoint %x (%d)\n", __func__, usb_pipeendpoint(this_urb->pipe), device_port); /* Save reset port val for resend. Don't overwrite resend for open/close condition. */ if ((reset_port + 1) > p_priv->resend_cont) p_priv->resend_cont = reset_port + 1; if (this_urb->status == -EINPROGRESS) { /* dev_dbg(&port->dev, "%s - already writing\n", __func__); */ mdelay(5); return -1; } memset(&msg, 0, sizeof(struct keyspan_usa49_portControlMessage)); msg.portNumber = device_port; /* Only set baud rate if it's changed */ if (p_priv->old_baud != p_priv->baud) { p_priv->old_baud = p_priv->baud; msg.setClocking = 0xff; if (d_details->calculate_baud_rate(port, p_priv->baud, d_details->baudclk, &msg.baudHi, &msg.baudLo, &msg.prescaler, device_port) == KEYSPAN_INVALID_BAUD_RATE) { dev_dbg(&port->dev, "%s - Invalid baud rate %d requested, using 9600.\n", __func__, p_priv->baud); msg.baudLo = 0; msg.baudHi = 125; /* Values for 9600 baud */ msg.prescaler = 10; } /* msg.setPrescaler = 0xff; */ } msg.lcr = (p_priv->cflag & CSTOPB) ? STOPBITS_678_2 : STOPBITS_5678_1; switch (p_priv->cflag & CSIZE) { case CS5: msg.lcr |= USA_DATABITS_5; break; case CS6: msg.lcr |= USA_DATABITS_6; break; case CS7: msg.lcr |= USA_DATABITS_7; break; case CS8: msg.lcr |= USA_DATABITS_8; break; } if (p_priv->cflag & PARENB) { /* note USA_PARITY_NONE == 0 */ msg.lcr |= (p_priv->cflag & PARODD) ? USA_PARITY_ODD : USA_PARITY_EVEN; } msg.setLcr = 0xff; msg.ctsFlowControl = (p_priv->flow_control == flow_cts); msg.xonFlowControl = 0; msg.setFlowControl = 0xff; msg.forwardingLength = 16; msg.xonChar = 17; msg.xoffChar = 19; /* Opening port */ if (reset_port == 1) { msg._txOn = 1; msg._txOff = 0; msg.txFlush = 0; msg.txBreak = 0; msg.rxOn = 1; msg.rxOff = 0; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0xff; msg.enablePort = 1; msg.disablePort = 0; } /* Closing port */ else if (reset_port == 2) { msg._txOn = 0; msg._txOff = 1; msg.txFlush = 0; msg.txBreak = 0; msg.rxOn = 0; msg.rxOff = 1; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0; msg.enablePort = 0; msg.disablePort = 1; } /* Sending intermediate configs */ else { msg._txOn = (!p_priv->break_on); msg._txOff = 0; msg.txFlush = 0; msg.txBreak = (p_priv->break_on); msg.rxOn = 0; msg.rxOff = 0; msg.rxFlush = 0; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0x0; msg.enablePort = 0; msg.disablePort = 0; } /* Do handshaking outputs */ msg.setRts = 0xff; msg.rts = p_priv->rts_state; msg.setDtr = 0xff; msg.dtr = p_priv->dtr_state; p_priv->resend_cont = 0; /* if the device is a 49wg, we send control message on usb control EP 0 */ if (d_details->product_id == keyspan_usa49wg_product_id) { dr = (void *)(s_priv->ctrl_buf); dr->bRequestType = USB_TYPE_VENDOR | USB_DIR_OUT; dr->bRequest = 0xB0; /* 49wg control message */ dr->wValue = 0; dr->wIndex = 0; dr->wLength = cpu_to_le16(sizeof(msg)); memcpy(s_priv->glocont_buf, &msg, sizeof(msg)); usb_fill_control_urb(this_urb, serial->dev, usb_sndctrlpipe(serial->dev, 0), (unsigned char *)dr, s_priv->glocont_buf, sizeof(msg), usa49_glocont_callback, serial); } else { memcpy(this_urb->transfer_buffer, &msg, sizeof(msg)); /* send the data out the device on control endpoint */ this_urb->transfer_buffer_length = sizeof(msg); } err = usb_submit_urb(this_urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - usb_submit_urb(setup) failed (%d)\n", __func__, err); return 0; } static int keyspan_usa90_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port) { struct keyspan_usa90_portControlMessage msg; struct keyspan_serial_private *s_priv; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; struct urb *this_urb; int err; u8 prescaler; s_priv = usb_get_serial_data(serial); p_priv = usb_get_serial_port_data(port); d_details = s_priv->device_details; /* only do something if we have a bulk out endpoint */ this_urb = p_priv->outcont_urb; if (this_urb == NULL) { dev_dbg(&port->dev, "%s - oops no urb.\n", __func__); return -1; } /* Save reset port val for resend. Don't overwrite resend for open/close condition. */ if ((reset_port + 1) > p_priv->resend_cont) p_priv->resend_cont = reset_port + 1; if (this_urb->status == -EINPROGRESS) { dev_dbg(&port->dev, "%s already writing\n", __func__); mdelay(5); return -1; } memset(&msg, 0, sizeof(struct keyspan_usa90_portControlMessage)); /* Only set baud rate if it's changed */ if (p_priv->old_baud != p_priv->baud) { p_priv->old_baud = p_priv->baud; msg.setClocking = 0x01; if (d_details->calculate_baud_rate(port, p_priv->baud, d_details->baudclk, &msg.baudHi, &msg.baudLo, &prescaler, 0) == KEYSPAN_INVALID_BAUD_RATE) { dev_dbg(&port->dev, "%s - Invalid baud rate %d requested, using 9600.\n", __func__, p_priv->baud); p_priv->baud = 9600; d_details->calculate_baud_rate(port, p_priv->baud, d_details->baudclk, &msg.baudHi, &msg.baudLo, &prescaler, 0); } msg.setRxMode = 1; msg.setTxMode = 1; } /* modes must always be correctly specified */ if (p_priv->baud > 57600) { msg.rxMode = RXMODE_DMA; msg.txMode = TXMODE_DMA; } else { msg.rxMode = RXMODE_BYHAND; msg.txMode = TXMODE_BYHAND; } msg.lcr = (p_priv->cflag & CSTOPB) ? STOPBITS_678_2 : STOPBITS_5678_1; switch (p_priv->cflag & CSIZE) { case CS5: msg.lcr |= USA_DATABITS_5; break; case CS6: msg.lcr |= USA_DATABITS_6; break; case CS7: msg.lcr |= USA_DATABITS_7; break; case CS8: msg.lcr |= USA_DATABITS_8; break; } if (p_priv->cflag & PARENB) { /* note USA_PARITY_NONE == 0 */ msg.lcr |= (p_priv->cflag & PARODD) ? USA_PARITY_ODD : USA_PARITY_EVEN; } if (p_priv->old_cflag != p_priv->cflag) { p_priv->old_cflag = p_priv->cflag; msg.setLcr = 0x01; } if (p_priv->flow_control == flow_cts) msg.txFlowControl = TXFLOW_CTS; msg.setTxFlowControl = 0x01; msg.setRxFlowControl = 0x01; msg.rxForwardingLength = 16; msg.rxForwardingTimeout = 16; msg.txAckSetting = 0; msg.xonChar = 17; msg.xoffChar = 19; /* Opening port */ if (reset_port == 1) { msg.portEnabled = 1; msg.rxFlush = 1; msg.txBreak = (p_priv->break_on); } /* Closing port */ else if (reset_port == 2) msg.portEnabled = 0; /* Sending intermediate configs */ else { msg.portEnabled = 1; msg.txBreak = (p_priv->break_on); } /* Do handshaking outputs */ msg.setRts = 0x01; msg.rts = p_priv->rts_state; msg.setDtr = 0x01; msg.dtr = p_priv->dtr_state; p_priv->resend_cont = 0; memcpy(this_urb->transfer_buffer, &msg, sizeof(msg)); /* send the data out the device on control endpoint */ this_urb->transfer_buffer_length = sizeof(msg); err = usb_submit_urb(this_urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - usb_submit_urb(setup) failed (%d)\n", __func__, err); return 0; } static int keyspan_usa67_send_setup(struct usb_serial *serial, struct usb_serial_port *port, int reset_port) { struct keyspan_usa67_portControlMessage msg; struct keyspan_serial_private *s_priv; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; struct urb *this_urb; int err, device_port; s_priv = usb_get_serial_data(serial); p_priv = usb_get_serial_port_data(port); d_details = s_priv->device_details; this_urb = s_priv->glocont_urb; /* Work out which port within the device is being setup */ device_port = port->port_number; /* Make sure we have an urb then send the message */ if (this_urb == NULL) { dev_dbg(&port->dev, "%s - oops no urb for port.\n", __func__); return -1; } /* Save reset port val for resend. Don't overwrite resend for open/close condition. */ if ((reset_port + 1) > p_priv->resend_cont) p_priv->resend_cont = reset_port + 1; if (this_urb->status == -EINPROGRESS) { /* dev_dbg(&port->dev, "%s - already writing\n", __func__); */ mdelay(5); return -1; } memset(&msg, 0, sizeof(struct keyspan_usa67_portControlMessage)); msg.port = device_port; /* Only set baud rate if it's changed */ if (p_priv->old_baud != p_priv->baud) { p_priv->old_baud = p_priv->baud; msg.setClocking = 0xff; if (d_details->calculate_baud_rate(port, p_priv->baud, d_details->baudclk, &msg.baudHi, &msg.baudLo, &msg.prescaler, device_port) == KEYSPAN_INVALID_BAUD_RATE) { dev_dbg(&port->dev, "%s - Invalid baud rate %d requested, using 9600.\n", __func__, p_priv->baud); msg.baudLo = 0; msg.baudHi = 125; /* Values for 9600 baud */ msg.prescaler = 10; } msg.setPrescaler = 0xff; } msg.lcr = (p_priv->cflag & CSTOPB) ? STOPBITS_678_2 : STOPBITS_5678_1; switch (p_priv->cflag & CSIZE) { case CS5: msg.lcr |= USA_DATABITS_5; break; case CS6: msg.lcr |= USA_DATABITS_6; break; case CS7: msg.lcr |= USA_DATABITS_7; break; case CS8: msg.lcr |= USA_DATABITS_8; break; } if (p_priv->cflag & PARENB) { /* note USA_PARITY_NONE == 0 */ msg.lcr |= (p_priv->cflag & PARODD) ? USA_PARITY_ODD : USA_PARITY_EVEN; } msg.setLcr = 0xff; msg.ctsFlowControl = (p_priv->flow_control == flow_cts); msg.xonFlowControl = 0; msg.setFlowControl = 0xff; msg.forwardingLength = 16; msg.xonChar = 17; msg.xoffChar = 19; if (reset_port == 1) { /* Opening port */ msg._txOn = 1; msg._txOff = 0; msg.txFlush = 0; msg.txBreak = 0; msg.rxOn = 1; msg.rxOff = 0; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0xff; } else if (reset_port == 2) { /* Closing port */ msg._txOn = 0; msg._txOff = 1; msg.txFlush = 0; msg.txBreak = 0; msg.rxOn = 0; msg.rxOff = 1; msg.rxFlush = 1; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0; } else { /* Sending intermediate configs */ msg._txOn = (!p_priv->break_on); msg._txOff = 0; msg.txFlush = 0; msg.txBreak = (p_priv->break_on); msg.rxOn = 0; msg.rxOff = 0; msg.rxFlush = 0; msg.rxForward = 0; msg.returnStatus = 0; msg.resetDataToggle = 0x0; } /* Do handshaking outputs */ msg.setTxTriState_setRts = 0xff; msg.txTriState_rts = p_priv->rts_state; msg.setHskoa_setDtr = 0xff; msg.hskoa_dtr = p_priv->dtr_state; p_priv->resend_cont = 0; memcpy(this_urb->transfer_buffer, &msg, sizeof(msg)); /* send the data out the device on control endpoint */ this_urb->transfer_buffer_length = sizeof(msg); err = usb_submit_urb(this_urb, GFP_ATOMIC); if (err != 0) dev_dbg(&port->dev, "%s - usb_submit_urb(setup) failed (%d)\n", __func__, err); return 0; } static void keyspan_send_setup(struct usb_serial_port *port, int reset_port) { struct usb_serial *serial = port->serial; struct keyspan_serial_private *s_priv; const struct keyspan_device_details *d_details; s_priv = usb_get_serial_data(serial); d_details = s_priv->device_details; switch (d_details->msg_format) { case msg_usa26: keyspan_usa26_send_setup(serial, port, reset_port); break; case msg_usa28: keyspan_usa28_send_setup(serial, port, reset_port); break; case msg_usa49: keyspan_usa49_send_setup(serial, port, reset_port); break; case msg_usa90: keyspan_usa90_send_setup(serial, port, reset_port); break; case msg_usa67: keyspan_usa67_send_setup(serial, port, reset_port); break; } } /* Gets called by the "real" driver (ie once firmware is loaded and renumeration has taken place. */ static int keyspan_startup(struct usb_serial *serial) { int i, err; struct keyspan_serial_private *s_priv; const struct keyspan_device_details *d_details; for (i = 0; (d_details = keyspan_devices[i]) != NULL; ++i) if (d_details->product_id == le16_to_cpu(serial->dev->descriptor.idProduct)) break; if (d_details == NULL) { dev_err(&serial->dev->dev, "%s - unknown product id %x\n", __func__, le16_to_cpu(serial->dev->descriptor.idProduct)); return -ENODEV; } /* Setup private data for serial driver */ s_priv = kzalloc_obj(struct keyspan_serial_private); if (!s_priv) return -ENOMEM; s_priv->instat_buf = kzalloc(INSTAT_BUFLEN, GFP_KERNEL); if (!s_priv->instat_buf) goto err_instat_buf; s_priv->indat_buf = kzalloc(INDAT49W_BUFLEN, GFP_KERNEL); if (!s_priv->indat_buf) goto err_indat_buf; s_priv->glocont_buf = kzalloc(GLOCONT_BUFLEN, GFP_KERNEL); if (!s_priv->glocont_buf) goto err_glocont_buf; s_priv->ctrl_buf = kzalloc(sizeof(struct usb_ctrlrequest), GFP_KERNEL); if (!s_priv->ctrl_buf) goto err_ctrl_buf; s_priv->device_details = d_details; usb_set_serial_data(serial, s_priv); keyspan_setup_urbs(serial); if (s_priv->instat_urb != NULL) { err = usb_submit_urb(s_priv->instat_urb, GFP_KERNEL); if (err != 0) dev_dbg(&serial->dev->dev, "%s - submit instat urb failed %d\n", __func__, err); } if (s_priv->indat_urb != NULL) { err = usb_submit_urb(s_priv->indat_urb, GFP_KERNEL); if (err != 0) dev_dbg(&serial->dev->dev, "%s - submit indat urb failed %d\n", __func__, err); } return 0; err_ctrl_buf: kfree(s_priv->glocont_buf); err_glocont_buf: kfree(s_priv->indat_buf); err_indat_buf: kfree(s_priv->instat_buf); err_instat_buf: kfree(s_priv); return -ENOMEM; } static void keyspan_disconnect(struct usb_serial *serial) { struct keyspan_serial_private *s_priv; s_priv = usb_get_serial_data(serial); usb_kill_urb(s_priv->instat_urb); usb_kill_urb(s_priv->glocont_urb); usb_kill_urb(s_priv->indat_urb); } static void keyspan_release(struct usb_serial *serial) { struct keyspan_serial_private *s_priv; s_priv = usb_get_serial_data(serial); /* Make sure to unlink the URBs submitted in attach. */ usb_kill_urb(s_priv->instat_urb); usb_kill_urb(s_priv->indat_urb); usb_free_urb(s_priv->instat_urb); usb_free_urb(s_priv->indat_urb); usb_free_urb(s_priv->glocont_urb); kfree(s_priv->ctrl_buf); kfree(s_priv->glocont_buf); kfree(s_priv->indat_buf); kfree(s_priv->instat_buf); kfree(s_priv); } static int keyspan_port_probe(struct usb_serial_port *port) { struct usb_serial *serial = port->serial; struct keyspan_serial_private *s_priv; struct keyspan_port_private *p_priv; const struct keyspan_device_details *d_details; struct callbacks *cback; int endp; int port_num; int i; s_priv = usb_get_serial_data(serial); d_details = s_priv->device_details; p_priv = kzalloc_obj(*p_priv); if (!p_priv) return -ENOMEM; for (i = 0; i < ARRAY_SIZE(p_priv->in_buffer); ++i) { p_priv->in_buffer[i] = kzalloc(IN_BUFLEN, GFP_KERNEL); if (!p_priv->in_buffer[i]) goto err_free_in_buffer; } for (i = 0; i < ARRAY_SIZE(p_priv->out_buffer); ++i) { p_priv->out_buffer[i] = kzalloc(OUT_BUFLEN, GFP_KERNEL); if (!p_priv->out_buffer[i]) goto err_free_out_buffer; } p_priv->inack_buffer = kzalloc(INACK_BUFLEN, GFP_KERNEL); if (!p_priv->inack_buffer) goto err_free_out_buffer; p_priv->outcont_buffer = kzalloc(OUTCONT_BUFLEN, GFP_KERNEL); if (!p_priv->outcont_buffer) goto err_free_inack_buffer; p_priv->device_details = d_details; /* Setup values for the various callback routines */ cback = &keyspan_callbacks[d_details->msg_format]; port_num = port->port_number; /* Do indat endpoints first, once for each flip */ endp = d_details->indat_endpoints[port_num]; for (i = 0; i <= d_details->indat_endp_flip; ++i, ++endp) { p_priv->in_urbs[i] = keyspan_setup_urb(serial, endp, USB_DIR_IN, port, p_priv->in_buffer[i], IN_BUFLEN, cback->indat_callback); } /* outdat endpoints also have flip */ endp = d_details->outdat_endpoints[port_num]; for (i = 0; i <= d_details->outdat_endp_flip; ++i, ++endp) { p_priv->out_urbs[i] = keyspan_setup_urb(serial, endp, USB_DIR_OUT, port, p_priv->out_buffer[i], OUT_BUFLEN, cback->outdat_callback); } /* inack endpoint */ p_priv->inack_urb = keyspan_setup_urb(serial, d_details->inack_endpoints[port_num], USB_DIR_IN, port, p_priv->inack_buffer, INACK_BUFLEN, cback->inack_callback); /* outcont endpoint */ p_priv->outcont_urb = keyspan_setup_urb(serial, d_details->outcont_endpoints[port_num], USB_DIR_OUT, port, p_priv->outcont_buffer, OUTCONT_BUFLEN, cback->outcont_callback); usb_set_serial_port_data(port, p_priv); return 0; err_free_inack_buffer: kfree(p_priv->inack_buffer); err_free_out_buffer: for (i = 0; i < ARRAY_SIZE(p_priv->out_buffer); ++i) kfree(p_priv->out_buffer[i]); err_free_in_buffer: for (i = 0; i < ARRAY_SIZE(p_priv->in_buffer); ++i) kfree(p_priv->in_buffer[i]); kfree(p_priv); return -ENOMEM; } static void keyspan_port_remove(struct usb_serial_port *port) { struct keyspan_port_private *p_priv; int i; p_priv = usb_get_serial_port_data(port); usb_kill_urb(p_priv->inack_urb); usb_kill_urb(p_priv->outcont_urb); for (i = 0; i < 2; i++) { usb_kill_urb(p_priv->in_urbs[i]); usb_kill_urb(p_priv->out_urbs[i]); } usb_free_urb(p_priv->inack_urb); usb_free_urb(p_priv->outcont_urb); for (i = 0; i < 2; i++) { usb_free_urb(p_priv->in_urbs[i]); usb_free_urb(p_priv->out_urbs[i]); } kfree(p_priv->outcont_buffer); kfree(p_priv->inack_buffer); for (i = 0; i < ARRAY_SIZE(p_priv->out_buffer); ++i) kfree(p_priv->out_buffer[i]); for (i = 0; i < ARRAY_SIZE(p_priv->in_buffer); ++i) kfree(p_priv->in_buffer[i]); kfree(p_priv); } /* Structs for the devices, pre and post renumeration. */ static struct usb_serial_driver keyspan_pre_device = { .driver = { .name = "keyspan_no_firm", }, .description = "Keyspan - (without firmware)", .id_table = keyspan_pre_ids, .num_ports = 1, .attach = keyspan_fake_startup, }; static struct usb_serial_driver keyspan_1port_device = { .driver = { .name = "keyspan_1", }, .description = "Keyspan 1 port adapter", .id_table = keyspan_1port_ids, .num_ports = 1, .open = keyspan_open, .close = keyspan_close, .dtr_rts = keyspan_dtr_rts, .write = keyspan_write, .write_room = keyspan_write_room, .set_termios = keyspan_set_termios, .break_ctl = keyspan_break_ctl, .tiocmget = keyspan_tiocmget, .tiocmset = keyspan_tiocmset, .attach = keyspan_startup, .disconnect = keyspan_disconnect, .release = keyspan_release, .port_probe = keyspan_port_probe, .port_remove = keyspan_port_remove, }; static struct usb_serial_driver keyspan_2port_device = { .driver = { .name = "keyspan_2", }, .description = "Keyspan 2 port adapter", .id_table = keyspan_2port_ids, .num_ports = 2, .open = keyspan_open, .close = keyspan_close, .dtr_rts = keyspan_dtr_rts, .write = keyspan_write, .write_room = keyspan_write_room, .set_termios = keyspan_set_termios, .break_ctl = keyspan_break_ctl, .tiocmget = keyspan_tiocmget, .tiocmset = keyspan_tiocmset, .attach = keyspan_startup, .disconnect = keyspan_disconnect, .release = keyspan_release, .port_probe = keyspan_port_probe, .port_remove = keyspan_port_remove, }; static struct usb_serial_driver keyspan_4port_device = { .driver = { .name = "keyspan_4", }, .description = "Keyspan 4 port adapter", .id_table = keyspan_4port_ids, .num_ports = 4, .open = keyspan_open, .close = keyspan_close, .dtr_rts = keyspan_dtr_rts, .write = keyspan_write, .write_room = keyspan_write_room, .set_termios = keyspan_set_termios, .break_ctl = keyspan_break_ctl, .tiocmget = keyspan_tiocmget, .tiocmset = keyspan_tiocmset, .attach = keyspan_startup, .disconnect = keyspan_disconnect, .release = keyspan_release, .port_probe = keyspan_port_probe, .port_remove = keyspan_port_remove, }; static struct usb_serial_driver * const serial_drivers[] = { &keyspan_pre_device, &keyspan_1port_device, &keyspan_2port_device, &keyspan_4port_device, NULL }; module_usb_serial_driver(serial_drivers, keyspan_ids_combined); MODULE_AUTHOR(DRIVER_AUTHOR); MODULE_DESCRIPTION(DRIVER_DESC); MODULE_LICENSE("GPL"); MODULE_FIRMWARE("keyspan/usa28.fw"); MODULE_FIRMWARE("keyspan/usa28x.fw"); MODULE_FIRMWARE("keyspan/usa28xa.fw"); MODULE_FIRMWARE("keyspan/usa28xb.fw"); MODULE_FIRMWARE("keyspan/usa19.fw"); MODULE_FIRMWARE("keyspan/usa19qi.fw"); MODULE_FIRMWARE("keyspan/mpr.fw"); MODULE_FIRMWARE("keyspan/usa19qw.fw"); MODULE_FIRMWARE("keyspan/usa18x.fw"); MODULE_FIRMWARE("keyspan/usa19w.fw"); MODULE_FIRMWARE("keyspan/usa49w.fw"); MODULE_FIRMWARE("keyspan/usa49wlc.fw"); |
| 1 1 1 1 1 1 1 1 1 4 4 1 1 1 1 1 4 4 2 2 2 4 4 4 3 1 1 3 1 4 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 | // SPDX-License-Identifier: GPL-2.0-or-later /* * IPv6 tunneling device * Linux INET6 implementation * * Authors: * Ville Nuorvala <vnuorval@tcs.hut.fi> * Yasuyuki Kozakai <kozakai@linux-ipv6.org> * * Based on: * linux/net/ipv6/sit.c and linux/net/ipv4/ipip.c * * RFC 2473 */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/module.h> #include <linux/capability.h> #include <linux/errno.h> #include <linux/types.h> #include <linux/sockios.h> #include <linux/icmp.h> #include <linux/if.h> #include <linux/in.h> #include <linux/ip.h> #include <linux/net.h> #include <linux/in6.h> #include <linux/netdevice.h> #include <linux/if_arp.h> #include <linux/icmpv6.h> #include <linux/init.h> #include <linux/route.h> #include <linux/rtnetlink.h> #include <linux/netfilter_ipv6.h> #include <linux/slab.h> #include <linux/hash.h> #include <linux/etherdevice.h> #include <linux/uaccess.h> #include <linux/atomic.h> #include <net/icmp.h> #include <net/ip.h> #include <net/ip_tunnels.h> #include <net/ipv6.h> #include <net/ip6_route.h> #include <net/addrconf.h> #include <net/ip6_tunnel.h> #include <net/xfrm.h> #include <net/dsfield.h> #include <net/inet_ecn.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/netdev_lock.h> #include <net/dst_metadata.h> #include <net/inet_dscp.h> MODULE_AUTHOR("Ville Nuorvala"); MODULE_DESCRIPTION("IPv6 tunneling device"); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("ip6tnl"); MODULE_ALIAS_NETDEV("ip6tnl0"); #define IP6_TUNNEL_MAX_DEST_TLVS 8 #define IP6_TUNNEL_HASH_SIZE_SHIFT 5 #define IP6_TUNNEL_HASH_SIZE (1 << IP6_TUNNEL_HASH_SIZE_SHIFT) static bool log_ecn_error = true; module_param(log_ecn_error, bool, 0644); MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); static u32 HASH(const struct in6_addr *addr1, const struct in6_addr *addr2) { u32 hash = ipv6_addr_hash(addr1) ^ ipv6_addr_hash(addr2); return hash_32(hash, IP6_TUNNEL_HASH_SIZE_SHIFT); } static int ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); static struct rtnl_link_ops ip6_link_ops __read_mostly; static unsigned int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; /* lists for storing tunnels in use */ struct ip6_tnl __rcu *tnls_r_l[IP6_TUNNEL_HASH_SIZE]; struct ip6_tnl __rcu *tnls_wc[1]; struct ip6_tnl __rcu **tnls[2]; struct ip6_tnl __rcu *collect_md_tun; }; static inline int ip6_tnl_mpls_supported(void) { return IS_ENABLED(CONFIG_MPLS); } /** * ip6_tnl_lookup - fetch tunnel matching the end-point addresses * @net: network namespace * @link: ifindex of underlying interface * @remote: the address of the tunnel exit-point * @local: the address of the tunnel entry-point * * Return: * tunnel matching given end-points if found, * else fallback tunnel if its device is up, * else %NULL **/ static struct ip6_tnl * ip6_tnl_lookup(struct net *net, int link, const struct in6_addr *remote, const struct in6_addr *local) { unsigned int hash = HASH(remote, local); struct ip6_tnl *t, *cand = NULL; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct in6_addr any; for_each_ip_tunnel_rcu(t, ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_equal(remote, &t->parms.raddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else cand = t; } memset(&any, 0, sizeof(any)); hash = HASH(&any, local); for_each_ip_tunnel_rcu(t, ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || !ipv6_addr_any(&t->parms.raddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else if (!cand) cand = t; } hash = HASH(remote, &any); for_each_ip_tunnel_rcu(t, ip6n->tnls_r_l[hash]) { if (!ipv6_addr_equal(remote, &t->parms.raddr) || !ipv6_addr_any(&t->parms.laddr) || !(t->dev->flags & IFF_UP)) continue; if (link == t->parms.link) return t; else if (!cand) cand = t; } if (cand) return cand; t = rcu_dereference(ip6n->collect_md_tun); if (t && t->dev->flags & IFF_UP) return t; t = rcu_dereference(ip6n->tnls_wc[0]); if (t && (t->dev->flags & IFF_UP)) return t; return NULL; } /** * ip6_tnl_bucket - get head of list matching given tunnel parameters * @ip6n: the private data for ip6_vti in the netns * @p: parameters containing tunnel end-points * * Description: * ip6_tnl_bucket() returns the head of the list matching the * &struct in6_addr entries laddr and raddr in @p. * * Return: head of IPv6 tunnel list **/ static struct ip6_tnl __rcu ** ip6_tnl_bucket(struct ip6_tnl_net *ip6n, const struct __ip6_tnl_parm *p) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; unsigned int h = 0; int prio = 0; if (!ipv6_addr_any(remote) || !ipv6_addr_any(local)) { prio = 1; h = HASH(remote, local); } return &ip6n->tnls[prio][h]; } /** * ip6_tnl_link - add tunnel to hash table * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be added **/ static void ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp = ip6_tnl_bucket(ip6n, &t->parms); if (t->parms.collect_md) rcu_assign_pointer(ip6n->collect_md_tun, t); rcu_assign_pointer(t->next , rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); } /** * ip6_tnl_unlink - remove tunnel from hash table * @ip6n: the private data for ip6_vti in the netns * @t: tunnel to be removed **/ static void ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl __rcu **tp; struct ip6_tnl *iter; if (t->parms.collect_md) rcu_assign_pointer(ip6n->collect_md_tun, NULL); for (tp = ip6_tnl_bucket(ip6n, &t->parms); (iter = rtnl_dereference(*tp)) != NULL; tp = &iter->next) { if (t == iter) { rcu_assign_pointer(*tp, t->next); break; } } } static void ip6_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); } static int ip6_tnl_create2(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct ip6_tnl_net *ip6n = net_generic(t->net, ip6_tnl_net_id); int err; dev->rtnl_link_ops = &ip6_link_ops; err = register_netdevice(dev); if (err < 0) goto out; strcpy(t->parms.name, dev->name); ip6_tnl_link(ip6n, t); return 0; out: return err; } /** * ip6_tnl_create - create a new tunnel * @net: network namespace * @p: tunnel parameters * * Description: * Create tunnel matching given parameters. * * Return: * created tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_create(struct net *net, struct __ip6_tnl_parm *p) { struct net_device *dev; struct ip6_tnl *t; char name[IFNAMSIZ]; int err = -E2BIG; if (p->name[0]) { if (!dev_valid_name(p->name)) goto failed; strscpy(name, p->name, IFNAMSIZ); } else { sprintf(name, "ip6tnl%%d"); } err = -ENOMEM; dev = alloc_netdev(sizeof(*t), name, NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!dev) goto failed; dev_net_set(dev, net); t = netdev_priv(dev); t->parms = *p; t->net = dev_net(dev); err = ip6_tnl_create2(dev); if (err < 0) goto failed_free; return t; failed_free: free_netdev(dev); failed: return ERR_PTR(err); } /** * ip6_tnl_locate - find or create tunnel matching given parameters * @net: network namespace * @p: tunnel parameters * @create: != 0 if allowed to create new tunnel if no match found * * Description: * ip6_tnl_locate() first tries to locate an existing tunnel * based on @parms. If this is unsuccessful, but @create is set a new * tunnel device is created and registered for use. * * Return: * matching tunnel or error pointer **/ static struct ip6_tnl *ip6_tnl_locate(struct net *net, struct __ip6_tnl_parm *p, int create) { const struct in6_addr *remote = &p->raddr; const struct in6_addr *local = &p->laddr; struct ip6_tnl __rcu **tp; struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); for (tp = ip6_tnl_bucket(ip6n, p); (t = rtnl_dereference(*tp)) != NULL; tp = &t->next) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && p->link == t->parms.link) { if (create) return ERR_PTR(-EEXIST); return t; } } if (!create) return ERR_PTR(-ENODEV); return ip6_tnl_create(net, p); } /** * ip6_tnl_dev_uninit - tunnel device uninitializer * @dev: the device to be destroyed * * Description: * ip6_tnl_dev_uninit() removes tunnel from its list **/ static void ip6_tnl_dev_uninit(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) RCU_INIT_POINTER(ip6n->tnls_wc[0], NULL); else ip6_tnl_unlink(ip6n, t); dst_cache_reset(&t->dst_cache); netdev_put(dev, &t->dev_tracker); } /** * ip6_tnl_parse_tlv_enc_lim - handle encapsulation limit option * @skb: received socket buffer * @raw: the ICMPv6 error message data * * Return: * 0 if none was found, * else index to encapsulation limit **/ __u16 ip6_tnl_parse_tlv_enc_lim(struct sk_buff *skb, __u8 *raw) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)raw; unsigned int nhoff = raw - skb->data; unsigned int off = nhoff + sizeof(*ipv6h); u8 nexthdr = ipv6h->nexthdr; int exthdr_cnt = 0; while (ipv6_ext_hdr(nexthdr) && nexthdr != NEXTHDR_NONE) { struct ipv6_opt_hdr *hdr; u16 optlen; if (unlikely(exthdr_cnt++ >= IP6_MAX_EXT_HDRS_CNT)) break; if (!pskb_may_pull(skb, off + sizeof(*hdr))) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { optlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { optlen = ipv6_authlen(hdr); } else { optlen = ipv6_optlen(hdr); } if (!pskb_may_pull(skb, off + optlen)) break; hdr = (struct ipv6_opt_hdr *)(skb->data + off); if (nexthdr == NEXTHDR_FRAGMENT) { struct frag_hdr *frag_hdr = (struct frag_hdr *)hdr; if (frag_hdr->frag_off) break; } if (nexthdr == NEXTHDR_DEST) { int tlv_cnt = 0; u16 i = 2; while (1) { struct ipv6_tlv_tnl_enc_lim *tel; if (unlikely(tlv_cnt++ >= IP6_TUNNEL_MAX_DEST_TLVS)) break; /* No more room for encapsulation limit */ if (i + sizeof(*tel) > optlen) break; tel = (struct ipv6_tlv_tnl_enc_lim *)(skb->data + off + i); /* return index of option if found and valid */ if (tel->type == IPV6_TLV_TNL_ENCAP_LIMIT && tel->length == 1) return i + off - nhoff; /* else jump to next option */ if (tel->type) i += tel->length + 2; else i++; } } nexthdr = hdr->nexthdr; off += optlen; } return 0; } EXPORT_SYMBOL(ip6_tnl_parse_tlv_enc_lim); /* ip6_tnl_err() should handle errors in the tunnel according to the * specifications in RFC 2473. */ static int ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, u8 *type, u8 *code, int *msg, __u32 *info, int offset) { const struct ipv6hdr *ipv6h = (const struct ipv6hdr *)skb->data; struct net *net = dev_net(skb->dev); u8 rel_type = ICMPV6_DEST_UNREACH; u8 rel_code = ICMPV6_ADDR_UNREACH; __u32 rel_info = 0; struct ip6_tnl *t; int err = -ENOENT; int rel_msg = 0; u8 tproto; __u16 len; /* If the packet doesn't contain the original IPv6 header we are in trouble since we might need the source address for further processing of the error. */ rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->daddr, &ipv6h->saddr); if (!t) goto out; tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto out; err = 0; switch (*type) { case ICMPV6_DEST_UNREACH: net_dbg_ratelimited("%s: Path to destination invalid or inactive!\n", t->parms.name); rel_msg = 1; break; case ICMPV6_TIME_EXCEED: if ((*code) == ICMPV6_EXC_HOPLIMIT) { net_dbg_ratelimited("%s: Too small hop limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } break; case ICMPV6_PARAMPROB: { struct ipv6_tlv_tnl_enc_lim *tel; __u32 teli; teli = 0; if ((*code) == ICMPV6_HDR_FIELD) teli = ip6_tnl_parse_tlv_enc_lim(skb, skb->data); if (teli && teli == *info - 2) { tel = (struct ipv6_tlv_tnl_enc_lim *) &skb->data[teli]; if (tel->encap_limit == 0) { net_dbg_ratelimited("%s: Too small encapsulation limit or routing loop in tunnel!\n", t->parms.name); rel_msg = 1; } } else { net_dbg_ratelimited("%s: Recipient unable to parse tunneled packet!\n", t->parms.name); } break; } case ICMPV6_PKT_TOOBIG: { __u32 mtu; ip6_update_pmtu(skb, net, htonl(*info), 0, 0, sock_net_uid(net, NULL)); mtu = *info - offset; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; len = sizeof(*ipv6h) + ntohs(ipv6h->payload_len); if (len > mtu) { rel_type = ICMPV6_PKT_TOOBIG; rel_code = 0; rel_info = mtu; rel_msg = 1; } break; } case NDISC_REDIRECT: ip6_redirect(skb, net, skb->dev->ifindex, 0, sock_net_uid(net, NULL)); break; } *type = rel_type; *code = rel_code; *info = rel_info; *msg = rel_msg; out: rcu_read_unlock(); return err; } static int ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); const struct iphdr *eiph; struct sk_buff *skb2; int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; struct rtable *rt; struct flowi4 fl4; err = ip6_tnl_err(skb, IPPROTO_IPIP, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg == 0) return 0; switch (rel_type) { case ICMPV6_DEST_UNREACH: if (rel_code != ICMPV6_ADDR_UNREACH) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_HOST_UNREACH; break; case ICMPV6_PKT_TOOBIG: if (rel_code != 0) return 0; rel_type = ICMP_DEST_UNREACH; rel_code = ICMP_FRAG_NEEDED; break; default: return 0; } if (!pskb_may_pull(skb, offset + sizeof(struct iphdr))) return 0; skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; /* Remove debris left by IPv6 stack. */ memset(IPCB(skb2), 0, sizeof(*IPCB(skb2))); skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); eiph = ip_hdr(skb2); if (eiph->version != 4 || eiph->ihl < 5) goto out; /* Try to guess incoming interface */ rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->saddr, 0, 0, 0, IPPROTO_IPIP, eiph->tos & INET_DSCP_MASK, 0); if (IS_ERR(rt)) goto out; skb2->dev = rt->dst.dev; ip_rt_put(rt); /* route "incoming" packet */ if (rt->rt_flags & RTCF_LOCAL) { rt = ip_route_output_ports(dev_net(skb->dev), &fl4, NULL, eiph->daddr, eiph->saddr, 0, 0, IPPROTO_IPIP, eiph->tos & INET_DSCP_MASK, 0); if (IS_ERR(rt) || rt->dst.dev->type != ARPHRD_TUNNEL6) { if (!IS_ERR(rt)) ip_rt_put(rt); goto out; } skb_dst_set(skb2, &rt->dst); } else { if (ip_route_input(skb2, eiph->daddr, eiph->saddr, ip4h_dscp(eiph), skb2->dev) || skb_dst_dev(skb2)->type != ARPHRD_TUNNEL6) goto out; } /* change mtu on this route */ if (rel_type == ICMP_DEST_UNREACH && rel_code == ICMP_FRAG_NEEDED) { if (rel_info > dst4_mtu(skb_dst(skb2))) goto out; skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); out: kfree_skb(skb2); return 0; } static int ip6ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; err = ip6_tnl_err(skb, IPPROTO_IPV6, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); if (err < 0) return err; if (rel_msg && pskb_may_pull(skb, offset + sizeof(struct ipv6hdr))) { struct rt6_info *rt; struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) return 0; /* Remove debris left by outer IPv6 stack. */ memset(IP6CB(skb2), 0, sizeof(*IP6CB(skb2))); skb_dst_drop(skb2); skb_pull(skb2, offset); skb_reset_network_header(skb2); /* Try to guess incoming interface */ rt = rt6_lookup(dev_net(skb->dev), &ipv6_hdr(skb2)->saddr, NULL, 0, skb2, 0); if (rt && rt->dst.dev) skb2->dev = rt->dst.dev; icmpv6_send(skb2, rel_type, rel_code, rel_info); ip6_rt_put(rt); kfree_skb(skb2); } return 0; } static int mplsip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, u8 type, u8 code, int offset, __be32 info) { __u32 rel_info = ntohl(info); int err, rel_msg = 0; u8 rel_type = type; u8 rel_code = code; err = ip6_tnl_err(skb, IPPROTO_MPLS, opt, &rel_type, &rel_code, &rel_msg, &rel_info, offset); return err; } static int ip4ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { __u8 dsfield = ipv6_get_dsfield(ipv6h) & ~INET_ECN_MASK; if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, dsfield); return IP6_ECN_decapsulate(ipv6h, skb); } static int ip6ip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { if (t->parms.flags & IP6_TNL_F_RCV_DSCP_COPY) ipv6_copy_dscp(ipv6_get_dsfield(ipv6h), ipv6_hdr(skb)); return IP6_ECN_decapsulate(ipv6h, skb); } static inline int mplsip6_dscp_ecn_decapsulate(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb) { /* ECN is not supported in AF_MPLS */ return 0; } __u32 ip6_tnl_get_cap(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ltype = ipv6_addr_type(laddr); int rtype = ipv6_addr_type(raddr); __u32 flags = 0; if (ltype == IPV6_ADDR_ANY || rtype == IPV6_ADDR_ANY) { flags = IP6_TNL_F_CAP_PER_PACKET; } else if (ltype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && rtype & (IPV6_ADDR_UNICAST|IPV6_ADDR_MULTICAST) && !((ltype|rtype) & IPV6_ADDR_LOOPBACK) && (!((ltype|rtype) & IPV6_ADDR_LINKLOCAL) || p->link)) { if (ltype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_XMIT; if (rtype&IPV6_ADDR_UNICAST) flags |= IP6_TNL_F_CAP_RCV; } return flags; } EXPORT_SYMBOL(ip6_tnl_get_cap); /* called with rcu_read_lock() */ int ip6_tnl_rcv_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if ((p->flags & IP6_TNL_F_CAP_RCV) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_RCV))) { struct net_device *ldev = NULL; if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(laddr) || likely(ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) && ((p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) || likely(!ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE)))) ret = 1; } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_rcv_ctl); static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb), bool log_ecn_err) { const struct ipv6hdr *ipv6h; int nh, err; if (test_bit(IP_TUNNEL_CSUM_BIT, tunnel->parms.i_flags) != test_bit(IP_TUNNEL_CSUM_BIT, tpi->flags)) { DEV_STATS_INC(tunnel->dev, rx_crc_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } if (test_bit(IP_TUNNEL_SEQ_BIT, tunnel->parms.i_flags)) { if (!test_bit(IP_TUNNEL_SEQ_BIT, tpi->flags) || (tunnel->i_seqno && (s32)(ntohl(tpi->seq) - tunnel->i_seqno) < 0)) { DEV_STATS_INC(tunnel->dev, rx_fifo_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } tunnel->i_seqno = ntohl(tpi->seq) + 1; } skb->protocol = tpi->proto; /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; skb_reset_mac_header(skb); } /* Save offset of outer header relative to skb->head, * because we are going to reset the network header to the inner header * and might change skb->head. */ nh = skb_network_header(skb) - skb->head; skb_reset_network_header(skb); if (skb_vlan_inet_prepare(skb, true)) { DEV_STATS_INC(tunnel->dev, rx_length_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } /* Get the outer header. */ ipv6h = (struct ipv6hdr *)(skb->head + nh); memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); err = dscp_ecn_decapsulate(tunnel, ipv6h, skb); if (unlikely(err)) { if (log_ecn_err) net_info_ratelimited("non-ECT from %pI6 with DS=%#x\n", &ipv6h->saddr, ipv6_get_dsfield(ipv6h)); if (err > 1) { DEV_STATS_INC(tunnel->dev, rx_frame_errors); DEV_STATS_INC(tunnel->dev, rx_errors); goto drop; } } dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); if (tun_dst) skb_dst_set(skb, (struct dst_entry *)tun_dst); gro_cells_receive(&tunnel->gro_cells, skb); return 0; drop: if (tun_dst) dst_release((struct dst_entry *)tun_dst); kfree_skb(skb); return 0; } int ip6_tnl_rcv(struct ip6_tnl *t, struct sk_buff *skb, const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, bool log_ecn_err) { int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb); dscp_ecn_decapsulate = ip6ip6_dscp_ecn_decapsulate; if (tpi->proto == htons(ETH_P_IP)) dscp_ecn_decapsulate = ip4ip6_dscp_ecn_decapsulate; return __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_err); } EXPORT_SYMBOL(ip6_tnl_rcv); static const struct tnl_ptk_info tpi_v6 = { /* no tunnel info required for ipxip6. */ .proto = htons(ETH_P_IPV6), }; static const struct tnl_ptk_info tpi_v4 = { /* no tunnel info required for ipxip6. */ .proto = htons(ETH_P_IP), }; static const struct tnl_ptk_info tpi_mpls = { /* no tunnel info required for mplsip6. */ .proto = htons(ETH_P_MPLS_UC), }; static int ipxip6_rcv(struct sk_buff *skb, u8 ipproto, const struct tnl_ptk_info *tpi, int (*dscp_ecn_decapsulate)(const struct ip6_tnl *t, const struct ipv6hdr *ipv6h, struct sk_buff *skb)) { struct ip6_tnl *t; const struct ipv6hdr *ipv6h = ipv6_hdr(skb); struct metadata_dst *tun_dst = NULL; int ret = -1; rcu_read_lock(); t = ip6_tnl_lookup(dev_net(skb->dev), skb->dev->ifindex, &ipv6h->saddr, &ipv6h->daddr); if (t) { u8 tproto = READ_ONCE(t->parms.proto); if (tproto != ipproto && tproto != 0) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; ipv6h = ipv6_hdr(skb); if (!ip6_tnl_rcv_ctl(t, &ipv6h->daddr, &ipv6h->saddr)) goto drop; if (iptunnel_pull_header(skb, 0, tpi->proto, false)) goto drop; if (t->parms.collect_md) { IP_TUNNEL_DECLARE_FLAGS(flags) = { }; tun_dst = ipv6_tun_rx_dst(skb, flags, 0, 0); if (!tun_dst) goto drop; } ret = __ip6_tnl_rcv(t, skb, tpi, tun_dst, dscp_ecn_decapsulate, log_ecn_error); } rcu_read_unlock(); return ret; drop: rcu_read_unlock(); kfree_skb(skb); return 0; } static int ip4ip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_IPIP, &tpi_v4, ip4ip6_dscp_ecn_decapsulate); } static int ip6ip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_IPV6, &tpi_v6, ip6ip6_dscp_ecn_decapsulate); } static int mplsip6_rcv(struct sk_buff *skb) { return ipxip6_rcv(skb, IPPROTO_MPLS, &tpi_mpls, mplsip6_dscp_ecn_decapsulate); } struct ipv6_tel_txoption { struct ipv6_txoptions ops; __u8 dst_opt[8]; }; static void init_tel_txopt(struct ipv6_tel_txoption *opt, __u8 encap_limit) { memset(opt, 0, sizeof(struct ipv6_tel_txoption)); opt->dst_opt[2] = IPV6_TLV_TNL_ENCAP_LIMIT; opt->dst_opt[3] = 1; opt->dst_opt[4] = encap_limit; opt->dst_opt[5] = IPV6_TLV_PADN; opt->dst_opt[6] = 1; opt->ops.dst1opt = (struct ipv6_opt_hdr *) opt->dst_opt; opt->ops.opt_nflen = 8; } /** * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * * Description: * Avoid trivial tunneling loop by checking that tunnel exit-point * doesn't match source of incoming packet. * * Return: * 1 if conflict, * 0 else **/ static inline bool ip6_tnl_addr_conflict(const struct ip6_tnl *t, const struct ipv6hdr *hdr) { return ipv6_addr_equal(&t->parms.raddr, &hdr->saddr); } int ip6_tnl_xmit_ctl(struct ip6_tnl *t, const struct in6_addr *laddr, const struct in6_addr *raddr) { struct __ip6_tnl_parm *p = &t->parms; int ret = 0; struct net *net = t->net; if (t->parms.collect_md) return 1; if ((p->flags & IP6_TNL_F_CAP_XMIT) || ((p->flags & IP6_TNL_F_CAP_PER_PACKET) && (ip6_tnl_get_cap(t, laddr, raddr) & IP6_TNL_F_CAP_XMIT))) { struct net_device *ldev = NULL; rcu_read_lock(); if (p->link) ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr_and_flags(net, laddr, ldev, false, 0, IFA_F_TENTATIVE))) pr_warn_ratelimited("%s xmit: Local address not yet configured!\n", p->name); else if (!(p->flags & IP6_TNL_F_ALLOW_LOCAL_REMOTE) && !ipv6_addr_is_multicast(raddr) && unlikely(ipv6_chk_addr_and_flags(net, raddr, ldev, true, 0, IFA_F_TENTATIVE))) pr_warn_ratelimited("%s xmit: Routing loop! Remote address found on this node!\n", p->name); else ret = 1; rcu_read_unlock(); } return ret; } EXPORT_SYMBOL_GPL(ip6_tnl_xmit_ctl); /** * ip6_tnl_xmit - encapsulate packet and send * @skb: the outgoing socket buffer * @dev: the outgoing tunnel device * @dsfield: dscp code for outer header * @fl6: flow of tunneled packet * @encap_limit: encapsulation limit * @pmtu: Path MTU is stored if packet is too big * @proto: next header value * * Description: * Build new header and do some sanity checks on the packet before sending * it. * * Return: * 0 on success * -1 fail * %-EMSGSIZE message too big. return mtu in this case. **/ int ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, __u8 dsfield, struct flowi6 *fl6, int encap_limit, __u32 *pmtu, __u8 proto) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ipv6hdr *ipv6h; struct ipv6_tel_txoption opt; struct dst_entry *dst = NULL, *ndst = NULL; struct net_device *tdev; int err_count, mtu; unsigned int eth_hlen = t->dev->type == ARPHRD_ETHER ? ETH_HLEN : 0; unsigned int psh_hlen = sizeof(struct ipv6hdr) + t->encap_hlen; unsigned int max_headroom = psh_hlen; __be16 payload_protocol; bool use_cache = false; u8 hop_limit; int err = -1; payload_protocol = skb_protocol(skb, true); if (t->parms.collect_md) { hop_limit = skb_tunnel_info(skb)->key.ttl; goto route_lookup; } else { hop_limit = t->parms.hop_limit; } /* NBMA tunnel */ if (ipv6_addr_any(&t->parms.raddr)) { if (payload_protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; struct neighbour *neigh; int addr_type; if (!skb_dst(skb)) goto tx_err_link_failure; neigh = dst_neigh_lookup(skb_dst(skb), &ipv6_hdr(skb)->daddr); if (!neigh) goto tx_err_link_failure; addr6 = (struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) addr6 = &ipv6_hdr(skb)->daddr; memcpy(&fl6->daddr, addr6, sizeof(fl6->daddr)); neigh_release(neigh); } else if (payload_protocol == htons(ETH_P_IP)) { const struct rtable *rt = skb_rtable(skb); if (!rt) goto tx_err_link_failure; if (rt->rt_gw_family == AF_INET6) memcpy(&fl6->daddr, &rt->rt_gw6, sizeof(fl6->daddr)); } } else if (t->parms.proto != 0 && !(t->parms.flags & (IP6_TNL_F_USE_ORIG_TCLASS | IP6_TNL_F_USE_ORIG_FWMARK))) { /* enable the cache only if neither the outer protocol nor the * routing decision depends on the current inner header value */ use_cache = true; } if (use_cache) dst = dst_cache_get(&t->dst_cache); if (!ip6_tnl_xmit_ctl(t, &fl6->saddr, &fl6->daddr)) goto tx_err_link_failure; if (!dst) { route_lookup: /* add dsfield to flowlabel for route lookup */ fl6->flowlabel = ip6_make_flowinfo(dsfield, fl6->flowlabel); dst = ip6_route_output(net, NULL, fl6); if (dst->error) goto tx_err_link_failure; dst = xfrm_lookup(net, dst, flowi6_to_flowi(fl6), NULL, 0); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; goto tx_err_link_failure; } if (t->parms.collect_md && ipv6_addr_any(&fl6->saddr) && ipv6_dev_get_saddr(net, ip6_dst_idev(dst)->dev, &fl6->daddr, 0, &fl6->saddr)) goto tx_err_link_failure; ndst = dst; } tdev = dst_dev(dst); if (tdev == dev) { DEV_STATS_INC(dev, collisions); net_warn_ratelimited("%s: Local routing loop detected!\n", t->parms.name); goto tx_err_dst_release; } mtu = dst6_mtu(dst) - eth_hlen - psh_hlen - t->tun_hlen; if (encap_limit >= 0) { max_headroom += 8; mtu -= 8; } mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; goto tx_err_dst_release; } err_count = READ_ONCE(t->err_count); if (err_count > 0) { if (time_before(jiffies, READ_ONCE(t->err_time) + IP6TUNNEL_ERR_TIMEO)) { WRITE_ONCE(t->err_count, err_count - 1); dst_link_failure(skb); } else { WRITE_ONCE(t->err_count, 0); } } skb_scrub_packet(skb, !net_eq(t->net, dev_net(dev))); /* * Okay, now see if we can stuff it in the buffer as-is. */ max_headroom += LL_RESERVED_SPACE(tdev); if (skb_headroom(skb) < max_headroom || skb_shared(skb) || (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb; new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) goto tx_err_dst_release; if (skb->sk) skb_set_owner_w(new_skb, skb->sk); consume_skb(skb); skb = new_skb; } if (t->parms.collect_md) { if (t->encap.type != TUNNEL_ENCAP_NONE) goto tx_err_dst_release; } else { if (use_cache && ndst) dst_cache_set_ip6(&t->dst_cache, ndst, &fl6->saddr); } skb_dst_set(skb, dst); if (hop_limit == 0) { if (payload_protocol == htons(ETH_P_IP)) hop_limit = ip_hdr(skb)->ttl; else if (payload_protocol == htons(ETH_P_IPV6)) hop_limit = ipv6_hdr(skb)->hop_limit; else hop_limit = ip6_dst_hoplimit(dst); } /* Calculate max headroom for all the headers and adjust * needed_headroom if necessary. */ max_headroom = LL_RESERVED_SPACE(tdev) + sizeof(struct ipv6hdr) + dst->header_len + t->hlen; ip_tunnel_adj_headroom(dev, max_headroom); err = ip6_tnl_encap(skb, t, &proto, fl6); if (err) return err; if (encap_limit >= 0) { init_tel_txopt(&opt, encap_limit); proto = ipv6_push_frag_opts(skb, &opt.ops, proto); } skb_push(skb, sizeof(struct ipv6hdr)); skb_reset_network_header(skb); ipv6h = ipv6_hdr(skb); ip6_flow_hdr(ipv6h, dsfield, ip6_make_flowlabel(net, skb, fl6->flowlabel, true, fl6)); ipv6h->hop_limit = hop_limit; ipv6h->nexthdr = proto; ipv6h->saddr = fl6->saddr; ipv6h->daddr = fl6->daddr; ip6tunnel_xmit(NULL, skb, dev, 0); return 0; tx_err_link_failure: DEV_STATS_INC(dev, tx_carrier_errors); dst_link_failure(skb); tx_err_dst_release: dst_release(dst); return err; } EXPORT_SYMBOL(ip6_tnl_xmit); static inline int ipxip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev, u8 protocol) { struct ip6_tnl *t = netdev_priv(dev); struct ipv6hdr *ipv6h; const struct iphdr *iph; int encap_limit = -1; __u16 offset; struct flowi6 fl6; __u8 dsfield, orig_dsfield; __u32 mtu; u8 tproto; int err; tproto = READ_ONCE(t->parms.proto); if (tproto != protocol && tproto != 0) return -1; if (t->parms.collect_md) { struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || ip_tunnel_info_af(tun_info) != AF_INET6)) return -1; key = &tun_info->key; memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_proto = protocol; fl6.saddr = key->u.ipv6.src; fl6.daddr = key->u.ipv6.dst; fl6.flowlabel = key->label; dsfield = key->tos; switch (protocol) { case IPPROTO_IPIP: iph = ip_hdr(skb); orig_dsfield = ipv4_get_dsfield(iph); break; case IPPROTO_IPV6: ipv6h = ipv6_hdr(skb); orig_dsfield = ipv6_get_dsfield(ipv6h); break; default: orig_dsfield = dsfield; break; } } else { if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; if (protocol == IPPROTO_IPV6) { offset = ip6_tnl_parse_tlv_enc_lim(skb, skb_network_header(skb)); /* ip6_tnl_parse_tlv_enc_lim() might have * reallocated skb->head */ if (offset > 0) { struct ipv6_tlv_tnl_enc_lim *tel; tel = (void *)&skb_network_header(skb)[offset]; if (tel->encap_limit == 0) { icmpv6_ndo_send(skb, ICMPV6_PARAMPROB, ICMPV6_HDR_FIELD, offset + 2); return -1; } encap_limit = tel->encap_limit - 1; } } memcpy(&fl6, &t->fl.u.ip6, sizeof(fl6)); fl6.flowi6_proto = protocol; if (t->parms.flags & IP6_TNL_F_USE_ORIG_FWMARK) fl6.flowi6_mark = skb->mark; else fl6.flowi6_mark = t->parms.fwmark; switch (protocol) { case IPPROTO_IPIP: iph = ip_hdr(skb); orig_dsfield = ipv4_get_dsfield(iph); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) dsfield = orig_dsfield; else dsfield = ip6_tclass(t->parms.flowinfo); break; case IPPROTO_IPV6: ipv6h = ipv6_hdr(skb); orig_dsfield = ipv6_get_dsfield(ipv6h); if (t->parms.flags & IP6_TNL_F_USE_ORIG_TCLASS) dsfield = orig_dsfield; else dsfield = ip6_tclass(t->parms.flowinfo); if (t->parms.flags & IP6_TNL_F_USE_ORIG_FLOWLABEL) fl6.flowlabel |= ip6_flowlabel(ipv6h); break; default: orig_dsfield = dsfield = ip6_tclass(t->parms.flowinfo); break; } } fl6.flowi6_uid = sock_net_uid(dev_net(dev), NULL); dsfield = INET_ECN_encapsulate(dsfield, orig_dsfield); if (iptunnel_handle_offloads(skb, SKB_GSO_IPXIP6)) return -1; skb_set_inner_ipproto(skb, protocol); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, protocol); if (err != 0) { /* XXX: send ICMP error even if DF is not set. */ if (err == -EMSGSIZE) switch (protocol) { case IPPROTO_IPIP: icmp_ndo_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); break; case IPPROTO_IPV6: icmpv6_ndo_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); break; default: break; } return -1; } return 0; } static netdev_tx_t ip6_tnl_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); u8 ipproto; int ret; if (!pskb_inet_may_pull(skb)) goto tx_err; switch (skb->protocol) { case htons(ETH_P_IP): ipproto = IPPROTO_IPIP; break; case htons(ETH_P_IPV6): if (ip6_tnl_addr_conflict(t, ipv6_hdr(skb))) goto tx_err; ipproto = IPPROTO_IPV6; break; case htons(ETH_P_MPLS_UC): ipproto = IPPROTO_MPLS; break; default: goto tx_err; } ret = ipxip6_tnl_xmit(skb, dev, ipproto); if (ret < 0) goto tx_err; return NETDEV_TX_OK; tx_err: DEV_STATS_INC(dev, tx_errors); DEV_STATS_INC(dev, tx_dropped); kfree_skb(skb); return NETDEV_TX_OK; } static void ip6_tnl_link_config(struct ip6_tnl *t) { struct net_device *dev = t->dev; struct net_device *tdev = NULL; struct __ip6_tnl_parm *p = &t->parms; struct flowi6 *fl6 = &t->fl.u.ip6; int t_hlen; int mtu; __dev_addr_set(dev, &p->laddr, sizeof(struct in6_addr)); memcpy(dev->broadcast, &p->raddr, sizeof(struct in6_addr)); /* Set up flowi template */ fl6->saddr = p->laddr; fl6->daddr = p->raddr; fl6->flowi6_oif = p->link; fl6->flowlabel = 0; if (!(p->flags&IP6_TNL_F_USE_ORIG_TCLASS)) fl6->flowlabel |= IPV6_TCLASS_MASK & p->flowinfo; if (!(p->flags&IP6_TNL_F_USE_ORIG_FLOWLABEL)) fl6->flowlabel |= IPV6_FLOWLABEL_MASK & p->flowinfo; p->flags &= ~(IP6_TNL_F_CAP_XMIT|IP6_TNL_F_CAP_RCV|IP6_TNL_F_CAP_PER_PACKET); p->flags |= ip6_tnl_get_cap(t, &p->laddr, &p->raddr); if (p->flags&IP6_TNL_F_CAP_XMIT && p->flags&IP6_TNL_F_CAP_RCV) dev->flags |= IFF_POINTOPOINT; else dev->flags &= ~IFF_POINTOPOINT; t->tun_hlen = 0; t->hlen = t->encap_hlen + t->tun_hlen; t_hlen = t->hlen + sizeof(struct ipv6hdr); if (p->flags & IP6_TNL_F_CAP_XMIT) { int strict = (ipv6_addr_type(&p->raddr) & (IPV6_ADDR_MULTICAST|IPV6_ADDR_LINKLOCAL)); struct rt6_info *rt = rt6_lookup(t->net, &p->raddr, &p->laddr, p->link, NULL, strict); if (rt) { tdev = rt->dst.dev; ip6_rt_put(rt); } if (!tdev && p->link) tdev = __dev_get_by_index(t->net, p->link); if (tdev) { dev->needed_headroom = tdev->hard_header_len + tdev->needed_headroom + t_hlen; mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU); mtu = mtu - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) mtu -= 8; if (mtu < IPV6_MIN_MTU) mtu = IPV6_MIN_MTU; WRITE_ONCE(dev->mtu, mtu); } } } /** * ip6_tnl_change - update the tunnel parameters * @t: tunnel to be changed * @p: tunnel configuration parameters * * Description: * ip6_tnl_change() updates the tunnel parameters **/ static void ip6_tnl_change(struct ip6_tnl *t, const struct __ip6_tnl_parm *p) { t->parms.laddr = p->laddr; t->parms.raddr = p->raddr; t->parms.flags = p->flags; t->parms.hop_limit = p->hop_limit; t->parms.encap_limit = p->encap_limit; t->parms.flowinfo = p->flowinfo; t->parms.link = p->link; t->parms.proto = p->proto; t->parms.fwmark = p->fwmark; dst_cache_reset(&t->dst_cache); ip6_tnl_link_config(t); } static void ip6_tnl_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p) { struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); ip6_tnl_unlink(ip6n, t); synchronize_net(); ip6_tnl_change(t, p); ip6_tnl_link(ip6n, t); netdev_state_change(t->dev); } static int ip6_tnl0_update(struct ip6_tnl *t, struct __ip6_tnl_parm *p, bool strict) { /* For the default ip6tnl0 device, allow changing only the protocol * (the IP6_TNL_F_CAP_PER_PACKET flag is set on ip6tnl0, and all other * parameters are 0). */ if (strict && (!ipv6_addr_any(&p->laddr) || !ipv6_addr_any(&p->raddr) || p->flags != t->parms.flags || p->hop_limit || p->encap_limit || p->flowinfo || p->link || p->fwmark || p->collect_md)) return -EINVAL; t->parms.proto = p->proto; netdev_state_change(t->dev); return 0; } static void ip6_tnl_parm_from_user(struct __ip6_tnl_parm *p, const struct ip6_tnl_parm *u) { p->laddr = u->laddr; p->raddr = u->raddr; p->flags = u->flags; p->hop_limit = u->hop_limit; p->encap_limit = u->encap_limit; p->flowinfo = u->flowinfo; p->link = u->link; p->proto = u->proto; memcpy(p->name, u->name, sizeof(u->name)); } static void ip6_tnl_parm_to_user(struct ip6_tnl_parm *u, const struct __ip6_tnl_parm *p) { u->laddr = p->laddr; u->raddr = p->raddr; u->flags = p->flags; u->hop_limit = p->hop_limit; u->encap_limit = p->encap_limit; u->flowinfo = p->flowinfo; u->link = p->link; u->proto = p->proto; memcpy(u->name, p->name, sizeof(u->name)); } /** * ip6_tnl_siocdevprivate - configure ipv6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: unused * @data: parameters passed from userspace * @cmd: command to be performed * * Description: * ip6_tnl_ioctl() is used for managing IPv6 tunnels * from userspace. * * The possible commands are the following: * %SIOCGETTUNNEL: get tunnel parameters for device * %SIOCADDTUNNEL: add tunnel matching given tunnel parameters * %SIOCCHGTUNNEL: change tunnel parameters to those given * %SIOCDELTUNNEL: delete tunnel * * The fallback device "ip6tnl0", created during module * initialization, can be used for creating other tunnel devices. * * Return: * 0 on success, * %-EFAULT if unable to copy data to or from userspace, * %-EPERM if current process hasn't %CAP_NET_ADMIN set * %-EINVAL if passed tunnel parameters are invalid, * %-EEXIST if changing a tunnel's parameters would cause a conflict * %-ENODEV if attempting to change or delete a nonexisting device **/ static int ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr, void __user *data, int cmd) { int err = 0; struct ip6_tnl_parm p; struct __ip6_tnl_parm p1; struct ip6_tnl *t = netdev_priv(dev); struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); memset(&p1, 0, sizeof(p1)); switch (cmd) { case SIOCGETTUNNEL: if (dev == ip6n->fb_tnl_dev) { if (copy_from_user(&p, data, sizeof(p))) { err = -EFAULT; break; } ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) t = netdev_priv(dev); } else { memset(&p, 0, sizeof(p)); } ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; break; case SIOCADDTUNNEL: case SIOCCHGTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -EINVAL; if (p.proto != IPPROTO_IPV6 && p.proto != IPPROTO_IPIP && p.proto != 0) break; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, cmd == SIOCADDTUNNEL); if (cmd == SIOCCHGTUNNEL) { if (!IS_ERR(t)) { if (t->dev != dev) { err = -EEXIST; break; } } else t = netdev_priv(dev); if (dev == ip6n->fb_tnl_dev) ip6_tnl0_update(t, &p1, false); else ip6_tnl_update(t, &p1); } if (!IS_ERR(t)) { err = 0; ip6_tnl_parm_to_user(&p, &t->parms); if (copy_to_user(data, &p, sizeof(p))) err = -EFAULT; } else { err = PTR_ERR(t); } break; case SIOCDELTUNNEL: err = -EPERM; if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) break; if (dev == ip6n->fb_tnl_dev) { err = -EFAULT; if (copy_from_user(&p, data, sizeof(p))) break; err = -ENOENT; ip6_tnl_parm_from_user(&p1, &p); t = ip6_tnl_locate(net, &p1, 0); if (IS_ERR(t)) break; err = -EPERM; if (t->dev == ip6n->fb_tnl_dev) break; dev = t->dev; } err = 0; unregister_netdevice(dev); break; default: err = -EINVAL; } return err; } /** * ip6_tnl_change_mtu - change mtu manually for tunnel device * @dev: virtual device associated with tunnel * @new_mtu: the new mtu * * Return: * 0 on success, * %-EINVAL if mtu too small **/ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu) { struct ip6_tnl *tnl = netdev_priv(dev); int t_hlen; t_hlen = tnl->hlen + sizeof(struct ipv6hdr); if (tnl->parms.proto == IPPROTO_IPV6) { if (new_mtu < IPV6_MIN_MTU) return -EINVAL; } else { if (new_mtu < ETH_MIN_MTU) return -EINVAL; } if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) { if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } else { if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen) return -EINVAL; } WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(ip6_tnl_change_mtu); int ip6_tnl_get_iflink(const struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); return READ_ONCE(t->parms.link); } EXPORT_SYMBOL(ip6_tnl_get_iflink); int ip6_tnl_encap_add_ops(const struct ip6_tnl_encap_ops *ops, unsigned int num) { if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; return !cmpxchg((const struct ip6_tnl_encap_ops **) &ip6tun_encaps[num], NULL, ops) ? 0 : -1; } EXPORT_SYMBOL(ip6_tnl_encap_add_ops); int ip6_tnl_encap_del_ops(const struct ip6_tnl_encap_ops *ops, unsigned int num) { int ret; if (num >= MAX_IPTUN_ENCAP_OPS) return -ERANGE; ret = (cmpxchg((const struct ip6_tnl_encap_ops **) &ip6tun_encaps[num], ops, NULL) == ops) ? 0 : -1; synchronize_net(); return ret; } EXPORT_SYMBOL(ip6_tnl_encap_del_ops); int ip6_tnl_encap_setup(struct ip6_tnl *t, struct ip_tunnel_encap *ipencap) { int hlen; memset(&t->encap, 0, sizeof(t->encap)); hlen = ip6_encap_hlen(ipencap); if (hlen < 0) return hlen; t->encap.type = ipencap->type; t->encap.sport = ipencap->sport; t->encap.dport = ipencap->dport; t->encap.flags = ipencap->flags; t->encap_hlen = hlen; t->hlen = t->encap_hlen + t->tun_hlen; return 0; } EXPORT_SYMBOL_GPL(ip6_tnl_encap_setup); static int ip6_tnl_fill_forward_path(struct net_device_path_ctx *ctx, struct net_device_path *path) { struct ip6_tnl *t = netdev_priv(ctx->dev); struct flowi6 fl6 = { .daddr = t->parms.raddr, }; struct dst_entry *dst; int err; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) { /* encaplimit option is currently not supported is * sw-acceleration path. */ return -EOPNOTSUPP; } dst = ip6_route_output(dev_net(ctx->dev), NULL, &fl6); if (!dst->error) { path->type = DEV_PATH_TUN; path->tun.src_v6 = t->parms.laddr; path->tun.dst_v6 = t->parms.raddr; path->tun.l3_proto = IPPROTO_IPV6; path->dev = ctx->dev; ctx->dev = dst->dev; } err = dst->error; dst_release(dst); return err; } static const struct net_device_ops ip6_tnl_netdev_ops = { .ndo_init = ip6_tnl_dev_init, .ndo_uninit = ip6_tnl_dev_uninit, .ndo_start_xmit = ip6_tnl_start_xmit, .ndo_siocdevprivate = ip6_tnl_siocdevprivate, .ndo_change_mtu = ip6_tnl_change_mtu, .ndo_get_stats64 = dev_get_tstats64, .ndo_get_iflink = ip6_tnl_get_iflink, .ndo_fill_forward_path = ip6_tnl_fill_forward_path, }; #define IPXIPX_FEATURES (NETIF_F_SG | \ NETIF_F_FRAGLIST | \ NETIF_F_HIGHDMA | \ NETIF_F_GSO_SOFTWARE | \ NETIF_F_HW_CSUM) /** * ip6_tnl_dev_setup - setup virtual tunnel device * @dev: virtual device associated with tunnel * * Description: * Initialize function pointers and device parameters **/ static void ip6_tnl_dev_setup(struct net_device *dev) { dev->netdev_ops = &ip6_tnl_netdev_ops; dev->header_ops = &ip_tunnel_header_ops; dev->needs_free_netdev = true; dev->priv_destructor = ip6_dev_free; dev->type = ARPHRD_TUNNEL6; dev->flags |= IFF_NOARP; dev->addr_len = sizeof(struct in6_addr); dev->lltx = true; dev->pcpu_stat_type = NETDEV_PCPU_STAT_TSTATS; netif_keep_dst(dev); dev->features |= IPXIPX_FEATURES; dev->hw_features |= IPXIPX_FEATURES; /* This perm addr will be used as interface identifier by IPv6 */ dev->addr_assign_type = NET_ADDR_RANDOM; eth_random_addr(dev->perm_addr); } /** * ip6_tnl_dev_init_gen - general initializer for all tunnel devices * @dev: virtual device associated with tunnel **/ static inline int ip6_tnl_dev_init_gen(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int ret; int t_hlen; t->dev = dev; ret = dst_cache_init(&t->dst_cache, GFP_KERNEL); if (ret) return ret; ret = gro_cells_init(&t->gro_cells, dev); if (ret) goto destroy_dst; t->tun_hlen = 0; t->hlen = t->encap_hlen + t->tun_hlen; t_hlen = t->hlen + sizeof(struct ipv6hdr); dev->type = ARPHRD_TUNNEL6; dev->mtu = ETH_DATA_LEN - t_hlen; if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) dev->mtu -= 8; dev->min_mtu = ETH_MIN_MTU; dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen; netdev_hold(dev, &t->dev_tracker, GFP_KERNEL); netdev_lockdep_set_classes(dev); return 0; destroy_dst: dst_cache_destroy(&t->dst_cache); return ret; } /** * ip6_tnl_dev_init - initializer for all non fallback tunnel devices * @dev: virtual device associated with tunnel **/ static int ip6_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); int err = ip6_tnl_dev_init_gen(dev); if (err) return err; ip6_tnl_link_config(t); if (t->parms.collect_md) netif_keep_dst(dev); return 0; } /** * ip6_fb_tnl_dev_init - initializer for fallback tunnel device * @dev: fallback device * * Return: 0 **/ static int __net_init ip6_fb_tnl_dev_init(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); t->net = net; t->parms.proto = IPPROTO_IPV6; rcu_assign_pointer(ip6n->tnls_wc[0], t); return 0; } static int ip6_tnl_validate(struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { u8 proto; if (!data || !data[IFLA_IPTUN_PROTO]) return 0; proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (proto != IPPROTO_IPV6 && proto != IPPROTO_IPIP && proto != 0) return -EINVAL; return 0; } static void ip6_tnl_netlink_parms(struct nlattr *data[], struct __ip6_tnl_parm *parms) { memset(parms, 0, sizeof(*parms)); if (!data) return; if (data[IFLA_IPTUN_LINK]) parms->link = nla_get_u32(data[IFLA_IPTUN_LINK]); if (data[IFLA_IPTUN_LOCAL]) parms->laddr = nla_get_in6_addr(data[IFLA_IPTUN_LOCAL]); if (data[IFLA_IPTUN_REMOTE]) parms->raddr = nla_get_in6_addr(data[IFLA_IPTUN_REMOTE]); if (data[IFLA_IPTUN_TTL]) parms->hop_limit = nla_get_u8(data[IFLA_IPTUN_TTL]); if (data[IFLA_IPTUN_ENCAP_LIMIT]) parms->encap_limit = nla_get_u8(data[IFLA_IPTUN_ENCAP_LIMIT]); if (data[IFLA_IPTUN_FLOWINFO]) parms->flowinfo = nla_get_be32(data[IFLA_IPTUN_FLOWINFO]); if (data[IFLA_IPTUN_FLAGS]) parms->flags = nla_get_u32(data[IFLA_IPTUN_FLAGS]); if (data[IFLA_IPTUN_PROTO]) parms->proto = nla_get_u8(data[IFLA_IPTUN_PROTO]); if (data[IFLA_IPTUN_COLLECT_METADATA]) parms->collect_md = true; if (data[IFLA_IPTUN_FWMARK]) parms->fwmark = nla_get_u32(data[IFLA_IPTUN_FWMARK]); } static int ip6_tnl_newlink(struct net_device *dev, struct rtnl_newlink_params *params, struct netlink_ext_ack *extack) { struct nlattr **data = params->data; struct nlattr **tb = params->tb; struct ip_tunnel_encap ipencap; struct ip6_tnl_net *ip6n; struct ip6_tnl *nt, *t; struct net *net; int err; net = params->link_net ? : dev_net(dev); ip6n = net_generic(net, ip6_tnl_net_id); nt = netdev_priv(dev); nt->net = net; if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { err = ip6_tnl_encap_setup(nt, &ipencap); if (err < 0) return err; } ip6_tnl_netlink_parms(data, &nt->parms); if (nt->parms.collect_md) { if (rtnl_dereference(ip6n->collect_md_tun)) return -EEXIST; } else { t = ip6_tnl_locate(net, &nt->parms, 0); if (!IS_ERR(t)) return -EEXIST; } err = ip6_tnl_create2(dev); if (!err && tb[IFLA_MTU]) ip6_tnl_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); return err; } static int ip6_tnl_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip6_tnl *t = netdev_priv(dev); struct __ip6_tnl_parm p; struct net *net = t->net; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip_tunnel_encap ipencap; if (!rtnl_dev_link_net_capable(dev, net)) return -EPERM; if (dev == ip6n->fb_tnl_dev) { if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { /* iproute2 always sets TUNNEL_ENCAP_FLAG_CSUM6, so * let's ignore this flag. */ ipencap.flags &= ~TUNNEL_ENCAP_FLAG_CSUM6; if (memchr_inv(&ipencap, 0, sizeof(ipencap))) { NL_SET_ERR_MSG(extack, "Only protocol can be changed for fallback tunnel, not encap params"); return -EINVAL; } } ip6_tnl_netlink_parms(data, &p); if (ip6_tnl0_update(t, &p, true) < 0) { NL_SET_ERR_MSG(extack, "Only protocol can be changed for fallback tunnel"); return -EINVAL; } return 0; } if (ip_tunnel_netlink_encap_parms(data, &ipencap)) { int err = ip6_tnl_encap_setup(t, &ipencap); if (err < 0) return err; } ip6_tnl_netlink_parms(data, &p); if (p.collect_md) return -EINVAL; t = ip6_tnl_locate(net, &p, 0); if (!IS_ERR(t)) { if (t->dev != dev) return -EEXIST; } else t = netdev_priv(dev); ip6_tnl_update(t, &p); return 0; } static void ip6_tnl_dellink(struct net_device *dev, struct list_head *head) { struct net *net = dev_net(dev); struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev != ip6n->fb_tnl_dev) unregister_netdevice_queue(dev, head); } static size_t ip6_tnl_get_size(const struct net_device *dev) { return /* IFLA_IPTUN_LINK */ nla_total_size(4) + /* IFLA_IPTUN_LOCAL */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_REMOTE */ nla_total_size(sizeof(struct in6_addr)) + /* IFLA_IPTUN_TTL */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_LIMIT */ nla_total_size(1) + /* IFLA_IPTUN_FLOWINFO */ nla_total_size(4) + /* IFLA_IPTUN_FLAGS */ nla_total_size(4) + /* IFLA_IPTUN_PROTO */ nla_total_size(1) + /* IFLA_IPTUN_ENCAP_TYPE */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_FLAGS */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_SPORT */ nla_total_size(2) + /* IFLA_IPTUN_ENCAP_DPORT */ nla_total_size(2) + /* IFLA_IPTUN_COLLECT_METADATA */ nla_total_size(0) + /* IFLA_IPTUN_FWMARK */ nla_total_size(4) + 0; } static int ip6_tnl_fill_info(struct sk_buff *skb, const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); struct __ip6_tnl_parm *parm = &tunnel->parms; if (nla_put_u32(skb, IFLA_IPTUN_LINK, parm->link) || nla_put_in6_addr(skb, IFLA_IPTUN_LOCAL, &parm->laddr) || nla_put_in6_addr(skb, IFLA_IPTUN_REMOTE, &parm->raddr) || nla_put_u8(skb, IFLA_IPTUN_TTL, parm->hop_limit) || nla_put_u8(skb, IFLA_IPTUN_ENCAP_LIMIT, parm->encap_limit) || nla_put_be32(skb, IFLA_IPTUN_FLOWINFO, parm->flowinfo) || nla_put_u32(skb, IFLA_IPTUN_FLAGS, parm->flags) || nla_put_u8(skb, IFLA_IPTUN_PROTO, parm->proto) || nla_put_u32(skb, IFLA_IPTUN_FWMARK, parm->fwmark)) goto nla_put_failure; if (nla_put_u16(skb, IFLA_IPTUN_ENCAP_TYPE, tunnel->encap.type) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_SPORT, tunnel->encap.sport) || nla_put_be16(skb, IFLA_IPTUN_ENCAP_DPORT, tunnel->encap.dport) || nla_put_u16(skb, IFLA_IPTUN_ENCAP_FLAGS, tunnel->encap.flags)) goto nla_put_failure; if (parm->collect_md) if (nla_put_flag(skb, IFLA_IPTUN_COLLECT_METADATA)) goto nla_put_failure; return 0; nla_put_failure: return -EMSGSIZE; } struct net *ip6_tnl_get_link_net(const struct net_device *dev) { struct ip6_tnl *tunnel = netdev_priv(dev); return READ_ONCE(tunnel->net); } EXPORT_SYMBOL(ip6_tnl_get_link_net); static const struct nla_policy ip6_tnl_policy[IFLA_IPTUN_MAX + 1] = { [IFLA_IPTUN_LINK] = { .type = NLA_U32 }, [IFLA_IPTUN_LOCAL] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_REMOTE] = { .len = sizeof(struct in6_addr) }, [IFLA_IPTUN_TTL] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_LIMIT] = { .type = NLA_U8 }, [IFLA_IPTUN_FLOWINFO] = { .type = NLA_U32 }, [IFLA_IPTUN_FLAGS] = { .type = NLA_U32 }, [IFLA_IPTUN_PROTO] = { .type = NLA_U8 }, [IFLA_IPTUN_ENCAP_TYPE] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_ENCAP_DPORT] = { .type = NLA_U16 }, [IFLA_IPTUN_COLLECT_METADATA] = { .type = NLA_FLAG }, [IFLA_IPTUN_FWMARK] = { .type = NLA_U32 }, }; static struct rtnl_link_ops ip6_link_ops __read_mostly = { .kind = "ip6tnl", .maxtype = IFLA_IPTUN_MAX, .policy = ip6_tnl_policy, .priv_size = sizeof(struct ip6_tnl), .setup = ip6_tnl_dev_setup, .validate = ip6_tnl_validate, .newlink = ip6_tnl_newlink, .changelink = ip6_tnl_changelink, .dellink = ip6_tnl_dellink, .get_size = ip6_tnl_get_size, .fill_info = ip6_tnl_fill_info, .get_link_net = ip6_tnl_get_link_net, }; static struct xfrm6_tunnel ip4ip6_handler __read_mostly = { .handler = ip4ip6_rcv, .err_handler = ip4ip6_err, .priority = 1, }; static struct xfrm6_tunnel ip6ip6_handler __read_mostly = { .handler = ip6ip6_rcv, .err_handler = ip6ip6_err, .priority = 1, }; static struct xfrm6_tunnel mplsip6_handler __read_mostly = { .handler = mplsip6_rcv, .err_handler = mplsip6_err, .priority = 1, }; static void __net_exit ip6_tnl_exit_rtnl_net(struct net *net, struct list_head *list) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct net_device *dev, *aux; int h; struct ip6_tnl *t; for_each_netdev_safe(net, dev, aux) if (dev->rtnl_link_ops == &ip6_link_ops) unregister_netdevice_queue(dev, list); for (h = 0; h < IP6_TUNNEL_HASH_SIZE; h++) { t = rtnl_net_dereference(net, ip6n->tnls_r_l[h]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, list); t = rtnl_net_dereference(net, t->next); } } t = rtnl_net_dereference(net, ip6n->tnls_wc[0]); while (t) { /* If dev is in the same netns, it has already * been added to the list by the previous loop. */ if (!net_eq(dev_net(t->dev), net)) unregister_netdevice_queue(t->dev, list); t = rtnl_net_dereference(net, t->next); } } static int __net_init ip6_tnl_init_net(struct net *net) { struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); struct ip6_tnl *t = NULL; int err; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; if (!net_has_fallback_tunnels(net)) return 0; err = -ENOMEM; ip6n->fb_tnl_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6tnl0", NET_NAME_UNKNOWN, ip6_tnl_dev_setup); if (!ip6n->fb_tnl_dev) goto err_alloc_dev; dev_net_set(ip6n->fb_tnl_dev, net); ip6n->fb_tnl_dev->rtnl_link_ops = &ip6_link_ops; /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. */ ip6n->fb_tnl_dev->netns_immutable = true; err = ip6_fb_tnl_dev_init(ip6n->fb_tnl_dev); if (err < 0) goto err_register; err = register_netdev(ip6n->fb_tnl_dev); if (err < 0) goto err_register; t = netdev_priv(ip6n->fb_tnl_dev); strcpy(t->parms.name, ip6n->fb_tnl_dev->name); return 0; err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: return err; } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit_rtnl = ip6_tnl_exit_rtnl_net, .id = &ip6_tnl_net_id, .size = sizeof(struct ip6_tnl_net), }; /** * ip6_tunnel_init - register protocol and reserve needed resources * * Return: 0 on success **/ static int __init ip6_tunnel_init(void) { int err; if (!ipv6_mod_enabled()) return -EOPNOTSUPP; err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto out_pernet; err = xfrm6_tunnel_register(&ip4ip6_handler, AF_INET); if (err < 0) { pr_err("%s: can't register ip4ip6\n", __func__); goto out_ip4ip6; } err = xfrm6_tunnel_register(&ip6ip6_handler, AF_INET6); if (err < 0) { pr_err("%s: can't register ip6ip6\n", __func__); goto out_ip6ip6; } if (ip6_tnl_mpls_supported()) { err = xfrm6_tunnel_register(&mplsip6_handler, AF_MPLS); if (err < 0) { pr_err("%s: can't register mplsip6\n", __func__); goto out_mplsip6; } } err = rtnl_link_register(&ip6_link_ops); if (err < 0) goto rtnl_link_failed; return 0; rtnl_link_failed: if (ip6_tnl_mpls_supported()) xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS); out_mplsip6: xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6); out_ip6ip6: xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET); out_ip4ip6: unregister_pernet_device(&ip6_tnl_net_ops); out_pernet: return err; } /** * ip6_tunnel_cleanup - free resources and unregister protocol **/ static void __exit ip6_tunnel_cleanup(void) { rtnl_link_unregister(&ip6_link_ops); if (xfrm6_tunnel_deregister(&ip4ip6_handler, AF_INET)) pr_info("%s: can't deregister ip4ip6\n", __func__); if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) pr_info("%s: can't deregister ip6ip6\n", __func__); if (ip6_tnl_mpls_supported() && xfrm6_tunnel_deregister(&mplsip6_handler, AF_MPLS)) pr_info("%s: can't deregister mplsip6\n", __func__); unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); module_exit(ip6_tunnel_cleanup); |
| 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | /* SPDX-License-Identifier: GPL-2.0-or-later */ /* * i2c.h - definitions for the Linux i2c bus interface * Copyright (C) 1995-2000 Simon G. Vogl * Copyright (C) 2013-2019 Wolfram Sang <wsa@kernel.org> * * With some changes from Kyösti Mälkki <kmalkki@cc.hut.fi> and * Frodo Looijaard <frodol@dds.nl> */ #ifndef _LINUX_I2C_H #define _LINUX_I2C_H #include <linux/acpi.h> /* for acpi_handle */ #include <linux/bits.h> #include <linux/device-id/i2c.h> #include <linux/device.h> /* for struct device */ #include <linux/sched.h> /* for completion */ #include <linux/mutex.h> #include <linux/regulator/consumer.h> #include <linux/rtmutex.h> #include <linux/irqdomain.h> /* for Host Notify IRQ */ #include <linux/of.h> /* for struct device_node */ #include <linux/swab.h> /* for swab16 */ #include <uapi/linux/i2c.h> extern const struct bus_type i2c_bus_type; extern const struct device_type i2c_adapter_type; extern const struct device_type i2c_client_type; /* --- General options ------------------------------------------------ */ struct i2c_msg; struct i2c_adapter; struct i2c_client; struct i2c_driver; struct i2c_device_identity; union i2c_smbus_data; struct i2c_board_info; enum i2c_slave_event; typedef int (*i2c_slave_cb_t)(struct i2c_client *client, enum i2c_slave_event event, u8 *val); /* I2C Frequency Modes */ #define I2C_MAX_STANDARD_MODE_FREQ 100000 #define I2C_MAX_FAST_MODE_FREQ 400000 #define I2C_MAX_FAST_MODE_PLUS_FREQ 1000000 #define I2C_MAX_TURBO_MODE_FREQ 1400000 #define I2C_MAX_HIGH_SPEED_MODE_FREQ 3400000 #define I2C_MAX_ULTRA_FAST_MODE_FREQ 5000000 struct module; struct property_entry; #if IS_ENABLED(CONFIG_I2C) /* Return the Frequency mode string based on the bus frequency */ const char *i2c_freq_mode_string(u32 bus_freq_hz); /* * The master routines are the ones normally used to transmit data to devices * on a bus (or read from them). Apart from two basic transfer functions to * transmit one message at a time, a more complex version can be used to * transmit an arbitrary number of messages without interruption. * @count must be less than 64k since msg.len is u16. */ int i2c_transfer_buffer_flags(const struct i2c_client *client, char *buf, int count, u16 flags); /** * i2c_master_recv - issue a single I2C message in master receive mode * @client: Handle to slave device * @buf: Where to store data read from slave * @count: How many bytes to read, must be less than 64k since msg.len is u16 * * Returns negative errno, or else the number of bytes read. */ static inline int i2c_master_recv(const struct i2c_client *client, char *buf, int count) { return i2c_transfer_buffer_flags(client, buf, count, I2C_M_RD); }; /** * i2c_master_recv_dmasafe - issue a single I2C message in master receive mode * using a DMA safe buffer * @client: Handle to slave device * @buf: Where to store data read from slave, must be safe to use with DMA * @count: How many bytes to read, must be less than 64k since msg.len is u16 * * Returns negative errno, or else the number of bytes read. */ static inline int i2c_master_recv_dmasafe(const struct i2c_client *client, char *buf, int count) { return i2c_transfer_buffer_flags(client, buf, count, I2C_M_RD | I2C_M_DMA_SAFE); }; /** * i2c_master_send - issue a single I2C message in master transmit mode * @client: Handle to slave device * @buf: Data that will be written to the slave * @count: How many bytes to write, must be less than 64k since msg.len is u16 * * Returns negative errno, or else the number of bytes written. */ static inline int i2c_master_send(const struct i2c_client *client, const char *buf, int count) { return i2c_transfer_buffer_flags(client, (char *)buf, count, 0); }; /** * i2c_master_send_dmasafe - issue a single I2C message in master transmit mode * using a DMA safe buffer * @client: Handle to slave device * @buf: Data that will be written to the slave, must be safe to use with DMA * @count: How many bytes to write, must be less than 64k since msg.len is u16 * * Returns negative errno, or else the number of bytes written. */ static inline int i2c_master_send_dmasafe(const struct i2c_client *client, const char *buf, int count) { return i2c_transfer_buffer_flags(client, (char *)buf, count, I2C_M_DMA_SAFE); }; /* Transfer num messages. */ int i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); /* Unlocked flavor */ int __i2c_transfer(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); /* This is the very generalized SMBus access routine. You probably do not want to use this, though; one of the functions below may be much easier, and probably just as fast. Note that we use i2c_adapter here, because you do not need a specific smbus adapter to call this function. */ s32 i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, char read_write, u8 command, int protocol, union i2c_smbus_data *data); /* Unlocked flavor */ s32 __i2c_smbus_xfer(struct i2c_adapter *adapter, u16 addr, unsigned short flags, char read_write, u8 command, int protocol, union i2c_smbus_data *data); /* Now follow the 'nice' access routines. These also document the calling conventions of i2c_smbus_xfer. */ u8 i2c_smbus_pec(u8 crc, u8 *p, size_t count); s32 i2c_smbus_read_byte(const struct i2c_client *client); s32 i2c_smbus_write_byte(const struct i2c_client *client, u8 value); s32 i2c_smbus_read_byte_data(const struct i2c_client *client, u8 command); s32 i2c_smbus_write_byte_data(const struct i2c_client *client, u8 command, u8 value); s32 i2c_smbus_read_word_data(const struct i2c_client *client, u8 command); s32 i2c_smbus_write_word_data(const struct i2c_client *client, u8 command, u16 value); static inline s32 i2c_smbus_read_word_swapped(const struct i2c_client *client, u8 command) { s32 value = i2c_smbus_read_word_data(client, command); return (value < 0) ? value : swab16(value); } static inline s32 i2c_smbus_write_word_swapped(const struct i2c_client *client, u8 command, u16 value) { return i2c_smbus_write_word_data(client, command, swab16(value)); } /* Returns the number of read bytes */ s32 i2c_smbus_read_block_data(const struct i2c_client *client, u8 command, u8 *values); s32 i2c_smbus_write_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values); /* Returns the number of read bytes */ s32 i2c_smbus_read_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, u8 *values); s32 i2c_smbus_write_i2c_block_data(const struct i2c_client *client, u8 command, u8 length, const u8 *values); s32 i2c_smbus_read_i2c_block_data_or_emulated(const struct i2c_client *client, u8 command, u8 length, u8 *values); int i2c_get_device_id(const struct i2c_client *client, struct i2c_device_identity *id); const struct i2c_device_id *i2c_client_get_device_id(const struct i2c_client *client); #endif /* I2C */ /** * struct i2c_device_identity - i2c client device identification * @manufacturer_id: 0 - 4095, database maintained by NXP * @part_id: 0 - 511, according to manufacturer * @die_revision: 0 - 7, according to manufacturer */ struct i2c_device_identity { u16 manufacturer_id; #define I2C_DEVICE_ID_NXP_SEMICONDUCTORS 0 #define I2C_DEVICE_ID_NXP_SEMICONDUCTORS_1 1 #define I2C_DEVICE_ID_NXP_SEMICONDUCTORS_2 2 #define I2C_DEVICE_ID_NXP_SEMICONDUCTORS_3 3 #define I2C_DEVICE_ID_RAMTRON_INTERNATIONAL 4 #define I2C_DEVICE_ID_ANALOG_DEVICES 5 #define I2C_DEVICE_ID_STMICROELECTRONICS 6 #define I2C_DEVICE_ID_ON_SEMICONDUCTOR 7 #define I2C_DEVICE_ID_SPRINTEK_CORPORATION 8 #define I2C_DEVICE_ID_ESPROS_PHOTONICS_AG 9 #define I2C_DEVICE_ID_FUJITSU_SEMICONDUCTOR 10 #define I2C_DEVICE_ID_FLIR 11 #define I2C_DEVICE_ID_O2MICRO 12 #define I2C_DEVICE_ID_ATMEL 13 #define I2C_DEVICE_ID_NONE 0xffff u16 part_id; u8 die_revision; }; enum i2c_alert_protocol { I2C_PROTOCOL_SMBUS_ALERT, I2C_PROTOCOL_SMBUS_HOST_NOTIFY, }; /** * enum i2c_driver_flags - Flags for an I2C device driver * * @I2C_DRV_ACPI_WAIVE_D0_PROBE: Don't put the device in D0 state for probe */ enum i2c_driver_flags { I2C_DRV_ACPI_WAIVE_D0_PROBE = BIT(0), }; /** * struct i2c_driver - represent an I2C device driver * @class: What kind of i2c device we instantiate (for detect) * @probe: Callback for device binding * @remove: Callback for device unbinding * @shutdown: Callback for device shutdown * @alert: Alert callback, for example for the SMBus alert protocol * @command: Callback for bus-wide signaling (optional) * @driver: Device driver model driver * @id_table: List of I2C devices supported by this driver * @detect: Callback for device detection * @address_list: The I2C addresses to probe (for detect) * @clients: List of detected clients we created (for i2c-core use only) * @flags: A bitmask of flags defined in &enum i2c_driver_flags * * The driver.owner field should be set to the module owner of this driver. * The driver.name field should be set to the name of this driver. * * For automatic device detection, both @detect and @address_list must * be defined. @class should also be set, otherwise only devices forced * with module parameters will be created. The detect function must * fill at least the name field of the i2c_board_info structure it is * handed upon successful detection, and possibly also the flags field. * * If @detect is missing, the driver will still work fine for enumerated * devices. Detected devices simply won't be supported. This is expected * for the many I2C/SMBus devices which can't be detected reliably, and * the ones which can always be enumerated in practice. * * The i2c_client structure which is handed to the @detect callback is * not a real i2c_client. It is initialized just enough so that you can * call i2c_smbus_read_byte_data and friends on it. Don't do anything * else with it. In particular, calling dev_dbg and friends on it is * not allowed. */ struct i2c_driver { unsigned int class; /* Standard driver model interfaces */ int (*probe)(struct i2c_client *client); void (*remove)(struct i2c_client *client); /* driver model interfaces that don't relate to enumeration */ void (*shutdown)(struct i2c_client *client); /* Alert callback, for example for the SMBus alert protocol. * The format and meaning of the data value depends on the protocol. * For the SMBus alert protocol, there is a single bit of data passed * as the alert response's low bit ("event flag"). * For the SMBus Host Notify protocol, the data corresponds to the * 16-bit payload data reported by the slave device acting as master. */ void (*alert)(struct i2c_client *client, enum i2c_alert_protocol protocol, unsigned int data); /* a ioctl like command that can be used to perform specific functions * with the device. */ int (*command)(struct i2c_client *client, unsigned int cmd, void *arg); struct device_driver driver; const struct i2c_device_id *id_table; /* Device detection callback for automatic device creation */ int (*detect)(struct i2c_client *client, struct i2c_board_info *info); const unsigned short *address_list; struct list_head clients; u32 flags; }; #define to_i2c_driver(d) container_of_const(d, struct i2c_driver, driver) /** * struct i2c_client - represent an I2C slave device * @flags: see I2C_CLIENT_* for possible flags * @addr: Address used on the I2C bus connected to the parent adapter. * @name: Indicates the type of the device, usually a chip name that's * generic enough to hide second-sourcing and compatible revisions. * @adapter: manages the bus segment hosting this I2C device * @dev: Driver model device node for the slave. * @init_irq: IRQ that was set at initialization * @irq: indicates the IRQ generated by this device (if any) * @detected: member of an i2c_driver.clients list or i2c-core's * userspace_devices list * @slave_cb: Callback when I2C slave mode of an adapter is used. The adapter * calls it to pass on slave events to the slave driver. * @devres_group_id: id of the devres group that will be created for resources * acquired when probing this device. * @debugfs: pointer to the debugfs subdirectory which the I2C core created * for this client. * * An i2c_client identifies a single device (i.e. chip) connected to an * i2c bus. The behaviour exposed to Linux is defined by the driver * managing the device. */ struct i2c_client { unsigned short flags; /* div., see below */ #define I2C_CLIENT_PEC 0x04 /* Use Packet Error Checking */ #define I2C_CLIENT_TEN 0x10 /* we have a ten bit chip address */ /* Must equal I2C_M_TEN below */ #define I2C_CLIENT_SLAVE 0x20 /* we are the slave */ #define I2C_CLIENT_HOST_NOTIFY 0x40 /* We want to use I2C host notify */ #define I2C_CLIENT_WAKE 0x80 /* for board_info; true iff can wake */ #define I2C_CLIENT_SCCB 0x9000 /* Use Omnivision SCCB protocol */ /* Must match I2C_M_STOP|IGNORE_NAK */ unsigned short addr; /* chip address - NOTE: 7bit */ /* addresses are stored in the */ /* _LOWER_ 7 bits */ char name[I2C_NAME_SIZE]; struct i2c_adapter *adapter; /* the adapter we sit on */ struct device dev; /* the device structure */ int init_irq; /* irq set at initialization */ int irq; /* irq issued by device */ struct list_head detected; #if IS_ENABLED(CONFIG_I2C_SLAVE) i2c_slave_cb_t slave_cb; /* callback for slave mode */ #endif void *devres_group_id; /* ID of probe devres group */ struct dentry *debugfs; /* per-client debugfs dir */ }; #define to_i2c_client(d) container_of(d, struct i2c_client, dev) struct i2c_adapter *i2c_verify_adapter(struct device *dev); const struct i2c_device_id *i2c_match_id(const struct i2c_device_id *id, const struct i2c_client *client); const void *i2c_get_match_data(const struct i2c_client *client); static inline struct i2c_client *kobj_to_i2c_client(struct kobject *kobj) { struct device * const dev = kobj_to_dev(kobj); return to_i2c_client(dev); } static inline void *i2c_get_clientdata(const struct i2c_client *client) { return dev_get_drvdata(&client->dev); } static inline void i2c_set_clientdata(struct i2c_client *client, void *data) { dev_set_drvdata(&client->dev, data); } /* I2C slave support */ enum i2c_slave_event { I2C_SLAVE_READ_REQUESTED, I2C_SLAVE_WRITE_REQUESTED, I2C_SLAVE_READ_PROCESSED, I2C_SLAVE_WRITE_RECEIVED, I2C_SLAVE_STOP, }; int i2c_slave_register(struct i2c_client *client, i2c_slave_cb_t slave_cb); int i2c_slave_unregister(struct i2c_client *client); int i2c_slave_event(struct i2c_client *client, enum i2c_slave_event event, u8 *val); #if IS_ENABLED(CONFIG_I2C_SLAVE) bool i2c_detect_slave_mode(struct device *dev); #else static inline bool i2c_detect_slave_mode(struct device *dev) { return false; } #endif /** * struct i2c_board_info - template for device creation * @type: chip type, to initialize i2c_client.name * @flags: to initialize i2c_client.flags * @addr: stored in i2c_client.addr * @dev_name: Overrides the default <busnr>-<addr> dev_name if set * @platform_data: stored in i2c_client.dev.platform_data * @fwnode: device node supplied by the platform firmware * @swnode: software node for the device * @resources: resources associated with the device * @num_resources: number of resources in the @resources array * @irq: stored in i2c_client.irq * * I2C doesn't actually support hardware probing, although controllers and * devices may be able to use I2C_SMBUS_QUICK to tell whether or not there's * a device at a given address. Drivers commonly need more information than * that, such as chip type, configuration, associated IRQ, and so on. * * i2c_board_info is used to build tables of information listing I2C devices * that are present. This information is used to grow the driver model tree. * For mainboards this is done statically using i2c_register_board_info(); * bus numbers identify adapters that aren't yet available. For add-on boards, * i2c_new_client_device() does this dynamically with the adapter already known. */ struct i2c_board_info { char type[I2C_NAME_SIZE]; unsigned short flags; unsigned short addr; const char *dev_name; void *platform_data; struct fwnode_handle *fwnode; const struct software_node *swnode; const struct resource *resources; unsigned int num_resources; int irq; }; /** * I2C_BOARD_INFO - macro used to list an i2c device and its address * @dev_type: identifies the device type * @dev_addr: the device's address on the bus. * * This macro initializes essential fields of a struct i2c_board_info, * declaring what has been provided on a particular board. Optional * fields (such as associated irq, or device-specific platform_data) * are provided using conventional syntax. */ #define I2C_BOARD_INFO(dev_type, dev_addr) \ .type = dev_type, .addr = (dev_addr) #if IS_ENABLED(CONFIG_I2C) /* * Add-on boards should register/unregister their devices; e.g. a board * with integrated I2C, a config eeprom, sensors, and a codec that's * used in conjunction with the primary hardware. */ struct i2c_client * i2c_new_client_device(struct i2c_adapter *adap, struct i2c_board_info const *info); /* If you don't know the exact address of an I2C device, use this variant * instead, which can probe for device presence in a list of possible * addresses. The "probe" callback function is optional. If it is provided, * it must return 1 on successful probe, 0 otherwise. If it is not provided, * a default probing method is used. */ struct i2c_client * i2c_new_scanned_device(struct i2c_adapter *adap, struct i2c_board_info *info, unsigned short const *addr_list, int (*probe)(struct i2c_adapter *adap, unsigned short addr)); /* Common custom probe functions */ int i2c_probe_func_quick_read(struct i2c_adapter *adap, unsigned short addr); struct i2c_client * i2c_new_dummy_device(struct i2c_adapter *adapter, u16 address); struct i2c_client * devm_i2c_new_dummy_device(struct device *dev, struct i2c_adapter *adap, u16 address); struct i2c_client * i2c_new_ancillary_device(struct i2c_client *client, const char *name, u16 default_addr); void i2c_unregister_device(struct i2c_client *client); struct i2c_client *i2c_verify_client(struct device *dev); #else static inline struct i2c_client *i2c_verify_client(struct device *dev) { return NULL; } #endif /* I2C */ /* Mainboard arch_initcall() code should register all its I2C devices. * This is done at arch_initcall time, before declaring any i2c adapters. * Modules for add-on boards must use other calls. */ #ifdef CONFIG_I2C_BOARDINFO int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned n); #else static inline int i2c_register_board_info(int busnum, struct i2c_board_info const *info, unsigned n) { return 0; } #endif /* I2C_BOARDINFO */ /** * struct i2c_algorithm - represent I2C transfer methods * @xfer: Transfer a given number of messages defined by the msgs array via * the specified adapter. * @xfer_atomic: Same as @xfer. Yet, only using atomic context so e.g. PMICs * can be accessed very late before shutdown. Optional. * @smbus_xfer: Issue SMBus transactions to the given I2C adapter. If this * is not present, then the bus layer will try and convert the SMBus calls * into I2C transfers instead. * @smbus_xfer_atomic: Same as @smbus_xfer. Yet, only using atomic context * so e.g. PMICs can be accessed very late before shutdown. Optional. * @functionality: Return the flags that this algorithm/adapter pair supports * from the ``I2C_FUNC_*`` flags. * @reg_target: Register given client to local target mode of this adapter * @unreg_target: Unregister given client from local target mode of this adapter * * @master_xfer: deprecated, use @xfer * @master_xfer_atomic: deprecated, use @xfer_atomic * @reg_slave: deprecated, use @reg_target * @unreg_slave: deprecated, use @unreg_target * * i2c_algorithm is the interface to a class of hardware solutions which can * be addressed using the same bus algorithms - i.e. bit-banging or the PCF8584 * to name two of the most common. * * The return codes from the ``xfer{_atomic}`` fields should indicate the * type of error code that occurred during the transfer, as documented in the * Kernel Documentation file Documentation/i2c/fault-codes.rst. Otherwise, the * number of messages executed should be returned. */ struct i2c_algorithm { /* * If an adapter algorithm can't do I2C-level access, set xfer * to NULL. If an adapter algorithm can do SMBus access, set * smbus_xfer. If set to NULL, the SMBus protocol is simulated * using common I2C messages. */ union { int (*xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); int (*master_xfer)(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); }; union { int (*xfer_atomic)(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); int (*master_xfer_atomic)(struct i2c_adapter *adap, struct i2c_msg *msgs, int num); }; int (*smbus_xfer)(struct i2c_adapter *adap, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data); int (*smbus_xfer_atomic)(struct i2c_adapter *adap, u16 addr, unsigned short flags, char read_write, u8 command, int size, union i2c_smbus_data *data); /* To determine what the adapter supports */ u32 (*functionality)(struct i2c_adapter *adap); #if IS_ENABLED(CONFIG_I2C_SLAVE) union { int (*reg_target)(struct i2c_client *client); int (*reg_slave)(struct i2c_client *client); }; union { int (*unreg_target)(struct i2c_client *client); int (*unreg_slave)(struct i2c_client *client); }; #endif }; /** * struct i2c_lock_operations - represent I2C locking operations * @lock_bus: Get exclusive access to an I2C bus segment * @trylock_bus: Try to get exclusive access to an I2C bus segment * @unlock_bus: Release exclusive access to an I2C bus segment * * The main operations are wrapped by i2c_lock_bus and i2c_unlock_bus. */ struct i2c_lock_operations { void (*lock_bus)(struct i2c_adapter *adapter, unsigned int flags); int (*trylock_bus)(struct i2c_adapter *adapter, unsigned int flags); void (*unlock_bus)(struct i2c_adapter *adapter, unsigned int flags); }; /** * struct i2c_timings - I2C timing information * @bus_freq_hz: the bus frequency in Hz * @scl_rise_ns: time SCL signal takes to rise in ns; t(r) in the I2C specification * @scl_fall_ns: time SCL signal takes to fall in ns; t(f) in the I2C specification * @scl_int_delay_ns: time IP core additionally needs to setup SCL in ns * @sda_fall_ns: time SDA signal takes to fall in ns; t(f) in the I2C specification * @sda_hold_ns: time IP core additionally needs to hold SDA in ns * @digital_filter_width_ns: width in ns of spikes on i2c lines that the IP core * digital filter can filter out * @analog_filter_cutoff_freq_hz: threshold frequency for the low pass IP core * analog filter */ struct i2c_timings { u32 bus_freq_hz; u32 scl_rise_ns; u32 scl_fall_ns; u32 scl_int_delay_ns; u32 sda_fall_ns; u32 sda_hold_ns; u32 digital_filter_width_ns; u32 analog_filter_cutoff_freq_hz; }; /** * struct i2c_bus_recovery_info - I2C bus recovery information * @recover_bus: Recover routine. Either pass driver's recover_bus() routine, or * i2c_generic_scl_recovery(). * @get_scl: This gets current value of SCL line. Mandatory for generic SCL * recovery. Populated internally for generic GPIO recovery. * @set_scl: This sets/clears the SCL line. Mandatory for generic SCL recovery. * Populated internally for generic GPIO recovery. * @get_sda: This gets current value of SDA line. This or set_sda() is mandatory * for generic SCL recovery. Populated internally, if sda_gpio is a valid * GPIO, for generic GPIO recovery. * @set_sda: This sets/clears the SDA line. This or get_sda() is mandatory for * generic SCL recovery. Populated internally, if sda_gpio is a valid GPIO, * for generic GPIO recovery. * @get_bus_free: Returns the bus free state as seen from the IP core in case it * has a more complex internal logic than just reading SDA. Optional. * @prepare_recovery: This will be called before starting recovery. Platform may * configure padmux here for SDA/SCL line or something else they want. * @unprepare_recovery: This will be called after completing recovery. Platform * may configure padmux here for SDA/SCL line or something else they want. * @scl_gpiod: gpiod of the SCL line. Only required for GPIO recovery. * @sda_gpiod: gpiod of the SDA line. Only required for GPIO recovery. * @pinctrl: pinctrl used by GPIO recovery to change the state of the I2C pins. * Optional. * @pins_default: default pinctrl state of SCL/SDA lines, when they are assigned * to the I2C bus. Optional. Populated internally for GPIO recovery, if * state with the name PINCTRL_STATE_DEFAULT is found and pinctrl is valid. * @pins_gpio: recovery pinctrl state of SCL/SDA lines, when they are used as * GPIOs. Optional. Populated internally for GPIO recovery, if this state * is called "gpio" or "recovery" and pinctrl is valid. */ struct i2c_bus_recovery_info { int (*recover_bus)(struct i2c_adapter *adap); int (*get_scl)(struct i2c_adapter *adap); void (*set_scl)(struct i2c_adapter *adap, int val); int (*get_sda)(struct i2c_adapter *adap); void (*set_sda)(struct i2c_adapter *adap, int val); int (*get_bus_free)(struct i2c_adapter *adap); void (*prepare_recovery)(struct i2c_adapter *adap); void (*unprepare_recovery)(struct i2c_adapter *adap); /* gpio recovery */ struct gpio_desc *scl_gpiod; struct gpio_desc *sda_gpiod; struct pinctrl *pinctrl; struct pinctrl_state *pins_default; struct pinctrl_state *pins_gpio; }; int i2c_recover_bus(struct i2c_adapter *adap); /* Generic recovery routines */ int i2c_generic_scl_recovery(struct i2c_adapter *adap); /** * struct i2c_adapter_quirks - describe flaws of an i2c adapter * @flags: see I2C_AQ_* for possible flags and read below * @max_num_msgs: maximum number of messages per transfer * @max_write_len: maximum length of a write message * @max_read_len: maximum length of a read message * @max_comb_1st_msg_len: maximum length of the first msg in a combined message * @max_comb_2nd_msg_len: maximum length of the second msg in a combined message * * Note about combined messages: Some I2C controllers can only send one message * per transfer, plus something called combined message or write-then-read. * This is (usually) a small write message followed by a read message and * barely enough to access register based devices like EEPROMs. There is a flag * to support this mode. It implies max_num_msg = 2 and does the length checks * with max_comb_*_len because combined message mode usually has its own * limitations. Because of HW implementations, some controllers can actually do * write-then-anything or other variants. To support that, write-then-read has * been broken out into smaller bits like write-first and read-second which can * be combined as needed. */ struct i2c_adapter_quirks { u64 flags; int max_num_msgs; u16 max_write_len; u16 max_read_len; u16 max_comb_1st_msg_len; u16 max_comb_2nd_msg_len; }; /* enforce max_num_msgs = 2 and use max_comb_*_len for length checks */ #define I2C_AQ_COMB BIT(0) /* first combined message must be write */ #define I2C_AQ_COMB_WRITE_FIRST BIT(1) /* second combined message must be read */ #define I2C_AQ_COMB_READ_SECOND BIT(2) /* both combined messages must have the same target address */ #define I2C_AQ_COMB_SAME_ADDR BIT(3) /* convenience macro for typical write-then read case */ #define I2C_AQ_COMB_WRITE_THEN_READ (I2C_AQ_COMB | I2C_AQ_COMB_WRITE_FIRST | \ I2C_AQ_COMB_READ_SECOND | I2C_AQ_COMB_SAME_ADDR) /* clock stretching is not supported */ #define I2C_AQ_NO_CLK_STRETCH BIT(4) /* message cannot have length of 0 */ #define I2C_AQ_NO_ZERO_LEN_READ BIT(5) #define I2C_AQ_NO_ZERO_LEN_WRITE BIT(6) #define I2C_AQ_NO_ZERO_LEN (I2C_AQ_NO_ZERO_LEN_READ | I2C_AQ_NO_ZERO_LEN_WRITE) /* adapter cannot do repeated START */ #define I2C_AQ_NO_REP_START BIT(7) /* * i2c_adapter is the structure used to identify a physical i2c bus along * with the access algorithms necessary to access it. */ struct i2c_adapter { struct module *owner; unsigned int class; /* classes to allow probing for */ const struct i2c_algorithm *algo; /* the algorithm to access the bus */ void *algo_data; /* data fields that are valid for all devices */ const struct i2c_lock_operations *lock_ops; struct rt_mutex bus_lock; struct rt_mutex mux_lock; int timeout; /* in jiffies */ int retries; struct device dev; /* the adapter device */ unsigned long locked_flags; /* owned by the I2C core */ #define I2C_ALF_IS_SUSPENDED 0 #define I2C_ALF_SUSPEND_REPORTED 1 int nr; char name[48]; struct completion dev_released; struct mutex userspace_clients_lock; struct list_head userspace_clients; struct i2c_bus_recovery_info *bus_recovery_info; const struct i2c_adapter_quirks *quirks; struct irq_domain *host_notify_domain; struct regulator *bus_regulator; struct dentry *debugfs; /* 7bit address space */ DECLARE_BITMAP(addrs_in_instantiation, 1 << 7); }; #define to_i2c_adapter(d) container_of(d, struct i2c_adapter, dev) static inline void *i2c_get_adapdata(const struct i2c_adapter *adap) { return dev_get_drvdata(&adap->dev); } static inline void i2c_set_adapdata(struct i2c_adapter *adap, void *data) { dev_set_drvdata(&adap->dev, data); } static inline struct i2c_adapter * i2c_parent_is_i2c_adapter(const struct i2c_adapter *adapter) { #if IS_ENABLED(CONFIG_I2C_MUX) struct device *parent = adapter->dev.parent; if (parent != NULL && parent->type == &i2c_adapter_type) return to_i2c_adapter(parent); else #endif return NULL; } int i2c_for_each_dev(void *data, int (*fn)(struct device *dev, void *data)); /* Adapter locking functions, exported for shared pin cases */ #define I2C_LOCK_ROOT_ADAPTER BIT(0) #define I2C_LOCK_SEGMENT BIT(1) /** * i2c_lock_bus - Get exclusive access to an I2C bus segment * @adapter: Target I2C bus segment * @flags: I2C_LOCK_ROOT_ADAPTER locks the root i2c adapter, I2C_LOCK_SEGMENT * locks only this branch in the adapter tree */ static inline void i2c_lock_bus(struct i2c_adapter *adapter, unsigned int flags) { adapter->lock_ops->lock_bus(adapter, flags); } /** * i2c_trylock_bus - Try to get exclusive access to an I2C bus segment * @adapter: Target I2C bus segment * @flags: I2C_LOCK_ROOT_ADAPTER tries to locks the root i2c adapter, * I2C_LOCK_SEGMENT tries to lock only this branch in the adapter tree * * Return: true if the I2C bus segment is locked, false otherwise */ static inline int i2c_trylock_bus(struct i2c_adapter *adapter, unsigned int flags) { return adapter->lock_ops->trylock_bus(adapter, flags); } /** * i2c_unlock_bus - Release exclusive access to an I2C bus segment * @adapter: Target I2C bus segment * @flags: I2C_LOCK_ROOT_ADAPTER unlocks the root i2c adapter, I2C_LOCK_SEGMENT * unlocks only this branch in the adapter tree */ static inline void i2c_unlock_bus(struct i2c_adapter *adapter, unsigned int flags) { adapter->lock_ops->unlock_bus(adapter, flags); } /** * i2c_mark_adapter_suspended - Report suspended state of the adapter to the core * @adap: Adapter to mark as suspended * * When using this helper to mark an adapter as suspended, the core will reject * further transfers to this adapter. The usage of this helper is optional but * recommended for devices having distinct handlers for system suspend and * runtime suspend. More complex devices are free to implement custom solutions * to reject transfers when suspended. */ static inline void i2c_mark_adapter_suspended(struct i2c_adapter *adap) { i2c_lock_bus(adap, I2C_LOCK_ROOT_ADAPTER); set_bit(I2C_ALF_IS_SUSPENDED, &adap->locked_flags); i2c_unlock_bus(adap, I2C_LOCK_ROOT_ADAPTER); } /** * i2c_mark_adapter_resumed - Report resumed state of the adapter to the core * @adap: Adapter to mark as resumed * * When using this helper to mark an adapter as resumed, the core will allow * further transfers to this adapter. See also further notes to * @i2c_mark_adapter_suspended(). */ static inline void i2c_mark_adapter_resumed(struct i2c_adapter *adap) { i2c_lock_bus(adap, I2C_LOCK_ROOT_ADAPTER); clear_bit(I2C_ALF_IS_SUSPENDED, &adap->locked_flags); i2c_unlock_bus(adap, I2C_LOCK_ROOT_ADAPTER); } /* i2c adapter classes (bitmask) */ #define I2C_CLASS_HWMON (1<<0) /* lm_sensors, ... */ /* Warn users that the adapter doesn't support classes anymore */ #define I2C_CLASS_DEPRECATED (1<<8) /* Internal numbers to terminate lists */ #define I2C_CLIENT_END 0xfffeU /* Construct an I2C_CLIENT_END-terminated array of i2c addresses */ #define I2C_ADDRS(addr, addrs...) \ ((const unsigned short []){ addr, ## addrs, I2C_CLIENT_END }) /* ----- functions exported by i2c.o */ /* administration... */ #if IS_ENABLED(CONFIG_I2C) int i2c_add_adapter(struct i2c_adapter *adap); int devm_i2c_add_adapter(struct device *dev, struct i2c_adapter *adapter); void i2c_del_adapter(struct i2c_adapter *adap); int i2c_add_numbered_adapter(struct i2c_adapter *adap); int i2c_register_driver(struct module *owner, struct i2c_driver *driver); void i2c_del_driver(struct i2c_driver *driver); /* use a define to avoid include chaining to get THIS_MODULE */ #define i2c_add_driver(driver) \ i2c_register_driver(THIS_MODULE, driver) static inline bool i2c_client_has_driver(struct i2c_client *client) { return !IS_ERR_OR_NULL(client) && client->dev.driver; } /* call the i2c_client->command() of all attached clients with * the given arguments */ void i2c_clients_command(struct i2c_adapter *adap, unsigned int cmd, void *arg); struct i2c_adapter *i2c_get_adapter(int nr); void i2c_put_adapter(struct i2c_adapter *adap); unsigned int i2c_adapter_depth(struct i2c_adapter *adapter); void i2c_parse_fw_timings(struct device *dev, struct i2c_timings *t, bool use_defaults); /* Return the functionality mask */ static inline u32 i2c_get_functionality(struct i2c_adapter *adap) { return adap->algo->functionality(adap); } /* Return 1 if adapter supports everything we need, 0 if not. */ static inline int i2c_check_functionality(struct i2c_adapter *adap, u32 func) { return (func & i2c_get_functionality(adap)) == func; } /** * i2c_check_quirks() - Function for checking the quirk flags in an i2c adapter * @adap: i2c adapter * @quirks: quirk flags * * Return: true if the adapter has all the specified quirk flags, false if not */ static inline bool i2c_check_quirks(struct i2c_adapter *adap, u64 quirks) { if (!adap->quirks) return false; return (adap->quirks->flags & quirks) == quirks; } /* Return the adapter number for a specific adapter */ static inline int i2c_adapter_id(struct i2c_adapter *adap) { return adap->nr; } static inline u8 i2c_8bit_addr_from_msg(const struct i2c_msg *msg) { return (msg->addr << 1) | (msg->flags & I2C_M_RD); } /* * 10-bit address * addr_1: 5'b11110 | addr[9:8] | (R/nW) * addr_2: addr[7:0] */ static inline u8 i2c_10bit_addr_hi_from_msg(const struct i2c_msg *msg) { return 0xf0 | ((msg->addr & GENMASK(9, 8)) >> 7) | (msg->flags & I2C_M_RD); } static inline u8 i2c_10bit_addr_lo_from_msg(const struct i2c_msg *msg) { return msg->addr & GENMASK(7, 0); } u8 *i2c_get_dma_safe_msg_buf(struct i2c_msg *msg, unsigned int threshold); void i2c_put_dma_safe_msg_buf(u8 *buf, struct i2c_msg *msg, bool xferred); int i2c_handle_smbus_host_notify(struct i2c_adapter *adap, unsigned short addr); /** * module_i2c_driver() - Helper macro for registering a modular I2C driver * @__i2c_driver: i2c_driver struct * * Helper macro for I2C drivers which do not do anything special in module * init/exit. This eliminates a lot of boilerplate. Each module may only * use this macro once, and calling it replaces module_init() and module_exit() */ #define module_i2c_driver(__i2c_driver) \ module_driver(__i2c_driver, i2c_add_driver, \ i2c_del_driver) /** * builtin_i2c_driver() - Helper macro for registering a builtin I2C driver * @__i2c_driver: i2c_driver struct * * Helper macro for I2C drivers which do not do anything special in their * init. This eliminates a lot of boilerplate. Each driver may only * use this macro once, and calling it replaces device_initcall(). */ #define builtin_i2c_driver(__i2c_driver) \ builtin_driver(__i2c_driver, i2c_add_driver) /* must call put_device() when done with returned i2c_client device */ struct i2c_client *i2c_find_device_by_fwnode(struct fwnode_handle *fwnode); /* must call put_device() when done with returned i2c_adapter device */ struct i2c_adapter *i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode); /* must call i2c_put_adapter() when done with returned i2c_adapter device */ struct i2c_adapter *i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode); #else /* I2C */ static inline struct i2c_client * i2c_find_device_by_fwnode(struct fwnode_handle *fwnode) { return NULL; } static inline struct i2c_adapter * i2c_find_adapter_by_fwnode(struct fwnode_handle *fwnode) { return NULL; } static inline struct i2c_adapter * i2c_get_adapter_by_fwnode(struct fwnode_handle *fwnode) { return NULL; } #endif /* !I2C */ #if IS_ENABLED(CONFIG_OF) /* must call put_device() when done with returned i2c_client device */ static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) { return i2c_find_device_by_fwnode(of_fwnode_handle(node)); } /* must call put_device() when done with returned i2c_adapter device */ static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) { return i2c_find_adapter_by_fwnode(of_fwnode_handle(node)); } /* must call i2c_put_adapter() when done with returned i2c_adapter device */ static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node) { return i2c_get_adapter_by_fwnode(of_fwnode_handle(node)); } int of_i2c_get_board_info(struct device *dev, struct device_node *node, struct i2c_board_info *info); #else static inline struct i2c_client *of_find_i2c_device_by_node(struct device_node *node) { return NULL; } static inline struct i2c_adapter *of_find_i2c_adapter_by_node(struct device_node *node) { return NULL; } static inline struct i2c_adapter *of_get_i2c_adapter_by_node(struct device_node *node) { return NULL; } static inline int of_i2c_get_board_info(struct device *dev, struct device_node *node, struct i2c_board_info *info) { return -ENOTSUPP; } #endif /* CONFIG_OF */ struct acpi_resource; struct acpi_resource_i2c_serialbus; #if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C) bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c); int i2c_acpi_client_count(struct acpi_device *adev); u32 i2c_acpi_find_bus_speed(struct device *dev); struct i2c_client *i2c_acpi_new_device_by_fwnode(struct fwnode_handle *fwnode, int index, struct i2c_board_info *info); struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle); bool i2c_acpi_waive_d0_probe(struct device *dev); #else static inline bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares, struct acpi_resource_i2c_serialbus **i2c) { return false; } static inline int i2c_acpi_client_count(struct acpi_device *adev) { return 0; } static inline u32 i2c_acpi_find_bus_speed(struct device *dev) { return 0; } static inline struct i2c_client *i2c_acpi_new_device_by_fwnode( struct fwnode_handle *fwnode, int index, struct i2c_board_info *info) { return ERR_PTR(-ENODEV); } static inline struct i2c_adapter *i2c_acpi_find_adapter_by_handle(acpi_handle handle) { return NULL; } static inline bool i2c_acpi_waive_d0_probe(struct device *dev) { return false; } #endif /* CONFIG_ACPI */ static inline struct i2c_client *i2c_acpi_new_device(struct device *dev, int index, struct i2c_board_info *info) { return i2c_acpi_new_device_by_fwnode(dev_fwnode(dev), index, info); } #endif /* _LINUX_I2C_H */ |
| 92 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 | /* SPDX-License-Identifier: GPL-2.0 */ #ifndef _LINUX_VMALLOC_H #define _LINUX_VMALLOC_H #include <linux/alloc_tag.h> #include <linux/sched.h> #include <linux/spinlock.h> #include <linux/init.h> #include <linux/list.h> #include <linux/llist.h> #include <asm/page.h> /* pgprot_t */ #include <linux/rbtree.h> #include <linux/overflow.h> #include <asm/vmalloc.h> struct vm_area_struct; /* vma defining user mapping in mm_types.h */ struct notifier_block; /* in notifier.h */ struct iov_iter; /* in uio.h */ /* bits in flags of vmalloc's vm_struct below */ #define VM_IOREMAP 0x00000001 /* ioremap() and friends */ #define VM_ALLOC 0x00000002 /* vmalloc() */ #define VM_MAP 0x00000004 /* vmap()ed pages */ #define VM_USERMAP 0x00000008 /* suitable for remap_vmalloc_range */ #define VM_DMA_COHERENT 0x00000010 /* dma_alloc_coherent */ #define VM_UNINITIALIZED 0x00000020 /* vm_struct is not fully initialized */ #define VM_NO_GUARD 0x00000040 /* ***DANGEROUS*** don't add guard page */ #define VM_KASAN 0x00000080 /* has allocated kasan shadow memory */ #define VM_FLUSH_RESET_PERMS 0x00000100 /* reset direct map and flush TLB on unmap, can't be freed in atomic context */ #define VM_MAP_PUT_PAGES 0x00000200 /* put pages and free array in vfree */ #define VM_ALLOW_HUGE_VMAP 0x00000400 /* Allow for huge pages on archs with HAVE_ARCH_HUGE_VMALLOC */ #if (defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)) && \ !defined(CONFIG_KASAN_VMALLOC) #define VM_DEFER_KMEMLEAK 0x00000800 /* defer kmemleak object creation */ #else #define VM_DEFER_KMEMLEAK 0 #endif #define VM_SPARSE 0x00001000 /* sparse vm_area. not all pages are present. */ /* bits [20..32] reserved for arch specific ioremap internals */ /* * Maximum alignment for ioremap() regions. * Can be overridden by arch-specific value. */ #ifndef IOREMAP_MAX_ORDER #define IOREMAP_MAX_ORDER (7 + PAGE_SHIFT) /* 128 pages */ #endif struct vm_struct { union { struct vm_struct *next; /* Early registration of vm_areas. */ struct llist_node llnode; /* Asynchronous freeing on error paths. */ }; void *addr; unsigned long size; unsigned long flags; struct page **pages; #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC unsigned int page_order; #endif unsigned int nr_pages; phys_addr_t phys_addr; const void *caller; unsigned long requested_size; }; struct vmap_area { unsigned long va_start; unsigned long va_end; struct rb_node rb_node; /* address sorted rbtree */ struct list_head list; /* address sorted list */ /* * The following two variables can be packed, because * a vmap_area object can be either: * 1) in "free" tree (root is free_vmap_area_root) * 2) or "busy" tree (root is vmap_area_root) */ union { unsigned long subtree_max_size; /* in "free" tree */ struct vm_struct *vm; /* in "busy" tree */ }; unsigned long flags; /* mark type of vm_map_ram area */ }; /* archs that select HAVE_ARCH_HUGE_VMAP should override one or more of these */ #ifndef arch_vmap_p4d_supported static inline bool arch_vmap_p4d_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pud_supported static inline bool arch_vmap_pud_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pmd_supported static inline bool arch_vmap_pmd_supported(pgprot_t prot) { return false; } #endif #ifndef arch_vmap_pte_range_map_size static inline unsigned long arch_vmap_pte_range_map_size(unsigned long addr, unsigned long end, u64 pfn, unsigned int max_page_shift) { return PAGE_SIZE; } #endif #ifndef arch_vmap_pte_range_unmap_size static inline unsigned long arch_vmap_pte_range_unmap_size(unsigned long addr, pte_t *ptep) { return PAGE_SIZE; } #endif #ifndef arch_vmap_pte_supported_shift static inline int arch_vmap_pte_supported_shift(unsigned long size) { return PAGE_SHIFT; } #endif #ifndef arch_vmap_pgprot_tagged static inline pgprot_t arch_vmap_pgprot_tagged(pgprot_t prot) { return prot; } #endif /* * Highlevel APIs for driver use */ extern void vm_unmap_ram(const void *mem, unsigned int count); extern void *vm_map_ram(struct page **pages, unsigned int count, int node); extern void vm_unmap_aliases(void); extern void *vmalloc_noprof(unsigned long size) __alloc_size(1); #define vmalloc(...) alloc_hooks(vmalloc_noprof(__VA_ARGS__)) extern void *vzalloc_noprof(unsigned long size) __alloc_size(1); #define vzalloc(...) alloc_hooks(vzalloc_noprof(__VA_ARGS__)) extern void *vmalloc_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_user(...) alloc_hooks(vmalloc_user_noprof(__VA_ARGS__)) extern void *vmalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vmalloc_node(...) alloc_hooks(vmalloc_node_noprof(__VA_ARGS__)) extern void *vzalloc_node_noprof(unsigned long size, int node) __alloc_size(1); #define vzalloc_node(...) alloc_hooks(vzalloc_node_noprof(__VA_ARGS__)) extern void *vmalloc_32_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32(...) alloc_hooks(vmalloc_32_noprof(__VA_ARGS__)) extern void *vmalloc_32_user_noprof(unsigned long size) __alloc_size(1); #define vmalloc_32_user(...) alloc_hooks(vmalloc_32_user_noprof(__VA_ARGS__)) extern void *__vmalloc_noprof(unsigned long size, gfp_t gfp_mask) __alloc_size(1); #define __vmalloc(...) alloc_hooks(__vmalloc_noprof(__VA_ARGS__)) extern void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, pgprot_t prot, unsigned long vm_flags, int node, const void *caller) __alloc_size(1); #define __vmalloc_node_range(...) alloc_hooks(__vmalloc_node_range_noprof(__VA_ARGS__)) void *__vmalloc_node_noprof(unsigned long size, unsigned long align, gfp_t gfp_mask, int node, const void *caller) __alloc_size(1); #define __vmalloc_node(...) alloc_hooks(__vmalloc_node_noprof(__VA_ARGS__)) void *vmalloc_huge_node_noprof(unsigned long size, gfp_t gfp_mask, int node) __alloc_size(1); #define vmalloc_huge_node(...) alloc_hooks(vmalloc_huge_node_noprof(__VA_ARGS__)) static inline void *vmalloc_huge(unsigned long size, gfp_t gfp_mask) { return vmalloc_huge_node(size, gfp_mask, NUMA_NO_NODE); } extern void *__vmalloc_array_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vmalloc_array(...) alloc_hooks(__vmalloc_array_noprof(__VA_ARGS__)) extern void *vmalloc_array_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vmalloc_array(...) alloc_hooks(vmalloc_array_noprof(__VA_ARGS__)) extern void *__vcalloc_noprof(size_t n, size_t size, gfp_t flags) __alloc_size(1, 2); #define __vcalloc(...) alloc_hooks(__vcalloc_noprof(__VA_ARGS__)) extern void *vcalloc_noprof(size_t n, size_t size) __alloc_size(1, 2); #define vcalloc(...) alloc_hooks(vcalloc_noprof(__VA_ARGS__)) void *__must_check vrealloc_node_align_noprof(const void *p, size_t size, unsigned long align, gfp_t flags, int nid) __realloc_size(2); #define vrealloc_node_noprof(_p, _s, _f, _nid) \ vrealloc_node_align_noprof(_p, _s, 1, _f, _nid) #define vrealloc_noprof(_p, _s, _f) \ vrealloc_node_align_noprof(_p, _s, 1, _f, NUMA_NO_NODE) #define vrealloc_node_align(...) alloc_hooks(vrealloc_node_align_noprof(__VA_ARGS__)) #define vrealloc_node(...) alloc_hooks(vrealloc_node_noprof(__VA_ARGS__)) #define vrealloc(...) alloc_hooks(vrealloc_noprof(__VA_ARGS__)) extern void vfree(const void *addr); extern void vfree_atomic(const void *addr); extern void *vmap(struct page **pages, unsigned int count, unsigned long flags, pgprot_t prot); void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot); extern void vunmap(const void *addr); extern int remap_vmalloc_range_partial(struct vm_area_struct *vma, unsigned long uaddr, void *kaddr, unsigned long pgoff, unsigned long size); extern int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff); int vmap_pages_range(unsigned long addr, unsigned long end, pgprot_t prot, struct page **pages, unsigned int page_shift); /* * Lowlevel-APIs (not for driver use!) */ static inline size_t get_vm_area_size(const struct vm_struct *area) { if (!(area->flags & VM_NO_GUARD)) /* return actual size without guard page */ return area->size - PAGE_SIZE; else return area->size; } extern struct vm_struct *get_vm_area(unsigned long size, unsigned long flags); extern struct vm_struct *get_vm_area_caller(unsigned long size, unsigned long flags, const void *caller); extern struct vm_struct *__get_vm_area_caller(unsigned long size, unsigned long flags, unsigned long start, unsigned long end, const void *caller); void free_vm_area(struct vm_struct *area); extern struct vm_struct *remove_vm_area(const void *addr); extern struct vm_struct *find_vm_area(const void *addr); struct vmap_area *find_vmap_area(unsigned long addr); static inline bool is_vm_area_hugepages(const void *addr) { /* * This may not 100% tell if the area is mapped with > PAGE_SIZE * page table entries, if for some reason the architecture indicates * larger sizes are available but decides not to use them, nothing * prevents that. This only indicates the size of the physical page * allocated in the vmalloc layer. */ #ifdef CONFIG_HAVE_ARCH_HUGE_VMALLOC struct vm_struct *area = find_vm_area(addr); return area && area->page_order > 0; #else return false; #endif } /* for /proc/kcore */ long vread_iter(struct iov_iter *iter, const char *addr, size_t count); /* * Internals. Don't use.. */ __init void vm_area_add_early(struct vm_struct *vm); __init void vm_area_register_early(struct vm_struct *vm, size_t align); int register_vmap_purge_notifier(struct notifier_block *nb); int unregister_vmap_purge_notifier(struct notifier_block *nb); #ifdef CONFIG_MMU #define VMALLOC_TOTAL (VMALLOC_END - VMALLOC_START) int vm_area_map_pages(struct vm_struct *area, unsigned long start, unsigned long end, struct page **pages); void vm_area_unmap_pages(struct vm_struct *area, unsigned long start, unsigned long end); void vunmap_range(unsigned long addr, unsigned long end); static inline void set_vm_flush_reset_perms(void *addr) { struct vm_struct *vm = find_vm_area(addr); if (vm) vm->flags |= VM_FLUSH_RESET_PERMS; } #else /* !CONFIG_MMU */ #define VMALLOC_TOTAL 0UL static inline void set_vm_flush_reset_perms(void *addr) {} #endif /* CONFIG_MMU */ #if defined(CONFIG_MMU) && defined(CONFIG_SMP) struct vm_struct **pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align); void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms); # else static inline struct vm_struct ** pcpu_get_vm_areas(const unsigned long *offsets, const size_t *sizes, int nr_vms, size_t align) { return NULL; } static inline void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) {} #endif #if defined(CONFIG_MMU) && defined(CONFIG_PRINTK) bool vmalloc_dump_obj(void *object); #else static inline bool vmalloc_dump_obj(void *object) { return false; } #endif unsigned int memalloc_apply_gfp_scope(gfp_t gfp_mask); void memalloc_restore_scope(unsigned int flags); #endif /* _LINUX_VMALLOC_H */ |
| 1 1 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 | // SPDX-License-Identifier: GPL-2.0-only /* * Copyright (c) 2008, Intel Corporation. * * Author: Alexander Duyck <alexander.h.duyck@intel.com> */ #include <linux/module.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/rtnetlink.h> #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/ip.h> #include <net/ipv6.h> #include <net/dsfield.h> #include <net/pkt_cls.h> #include <net/tc_wrapper.h> #include <linux/tc_act/tc_skbedit.h> #include <net/tc_act/tc_skbedit.h> static struct tc_action_ops act_skbedit_ops; static u16 tcf_skbedit_hash(struct tcf_skbedit_params *params, struct sk_buff *skb) { u16 queue_mapping = params->queue_mapping; if (params->flags & SKBEDIT_F_TXQ_SKBHASH) { u32 hash = skb_get_hash(skb); queue_mapping += hash % params->mapping_mod; } return netdev_cap_txqueue(skb->dev, queue_mapping); } TC_INDIRECT_SCOPE int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_skbedit_params *params; tcf_lastuse_update(&d->tcf_tm); bstats_update(this_cpu_ptr(d->common.cpu_bstats), skb); params = rcu_dereference_bh(d->params); if (params->flags & SKBEDIT_F_PRIORITY) skb->priority = params->priority; if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) goto err; skb->priority = ipv4_get_dsfield(ip_hdr(skb)) >> 2; break; case htons(ETH_P_IPV6): wlen += sizeof(struct ipv6hdr); if (!pskb_may_pull(skb, wlen)) goto err; skb->priority = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; break; } } if (params->flags & SKBEDIT_F_QUEUE_MAPPING && skb->dev->real_num_tx_queues > params->queue_mapping) { #ifdef CONFIG_NET_EGRESS netdev_xmit_skip_txqueue(true); #endif skb_set_queue_mapping(skb, tcf_skbedit_hash(params, skb)); } if (params->flags & SKBEDIT_F_MARK) { skb->mark &= ~params->mask; skb->mark |= params->mark & params->mask; } if (params->flags & SKBEDIT_F_PTYPE) skb->pkt_type = params->ptype; return params->action; err: qstats_cpu_drop_inc(d->common.cpu_qstats); return TC_ACT_SHOT; } static void tcf_skbedit_stats_update(struct tc_action *a, u64 bytes, u64 packets, u64 drops, u64 lastuse, bool hw) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_t *tm = &d->tcf_tm; tcf_action_update_stats(a, bytes, packets, drops, hw); tm->lastuse = max_t(u64, tm->lastuse, lastuse); } static const struct nla_policy skbedit_policy[TCA_SKBEDIT_MAX + 1] = { [TCA_SKBEDIT_PARMS] = { .len = sizeof(struct tc_skbedit) }, [TCA_SKBEDIT_PRIORITY] = { .len = sizeof(u32) }, [TCA_SKBEDIT_QUEUE_MAPPING] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MARK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_PTYPE] = { .len = sizeof(u16) }, [TCA_SKBEDIT_MASK] = { .len = sizeof(u32) }, [TCA_SKBEDIT_FLAGS] = { .len = sizeof(u64) }, [TCA_SKBEDIT_QUEUE_MAPPING_MAX] = { .len = sizeof(u16) }, }; static int tcf_skbedit_init(struct net *net, struct nlattr *nla, struct nlattr *est, struct tc_action **a, struct tcf_proto *tp, u32 act_flags, struct netlink_ext_ack *extack) { struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id); bool bind = act_flags & TCA_ACT_FLAGS_BIND; struct tcf_skbedit_params *params_new; struct nlattr *tb[TCA_SKBEDIT_MAX + 1]; struct tcf_chain *goto_ch = NULL; struct tc_skbedit *parm; struct tcf_skbedit *d; u32 flags = 0, *priority = NULL, *mark = NULL, *mask = NULL; u16 *queue_mapping = NULL, *ptype = NULL; u32 mapping_mod = 1; bool exists = false; int ret = 0, err; u32 index; if (nla == NULL) return -EINVAL; err = nla_parse_nested_deprecated(tb, TCA_SKBEDIT_MAX, nla, skbedit_policy, NULL); if (err < 0) return err; if (tb[TCA_SKBEDIT_PARMS] == NULL) return -EINVAL; if (tb[TCA_SKBEDIT_PRIORITY] != NULL) { flags |= SKBEDIT_F_PRIORITY; priority = nla_data(tb[TCA_SKBEDIT_PRIORITY]); } if (tb[TCA_SKBEDIT_QUEUE_MAPPING] != NULL) { if (is_tcf_skbedit_ingress(act_flags) && !(act_flags & TCA_ACT_FLAGS_SKIP_SW)) { NL_SET_ERR_MSG_MOD(extack, "\"queue_mapping\" option on receive side is hardware only, use skip_sw"); return -EOPNOTSUPP; } flags |= SKBEDIT_F_QUEUE_MAPPING; queue_mapping = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING]); } if (tb[TCA_SKBEDIT_PTYPE] != NULL) { ptype = nla_data(tb[TCA_SKBEDIT_PTYPE]); if (!skb_pkt_type_ok(*ptype)) return -EINVAL; flags |= SKBEDIT_F_PTYPE; } if (tb[TCA_SKBEDIT_MARK] != NULL) { flags |= SKBEDIT_F_MARK; mark = nla_data(tb[TCA_SKBEDIT_MARK]); } if (tb[TCA_SKBEDIT_MASK] != NULL) { flags |= SKBEDIT_F_MASK; mask = nla_data(tb[TCA_SKBEDIT_MASK]); } if (tb[TCA_SKBEDIT_FLAGS] != NULL) { u64 *pure_flags = nla_data(tb[TCA_SKBEDIT_FLAGS]); if (*pure_flags & SKBEDIT_F_TXQ_SKBHASH) { u16 *queue_mapping_max; if (!tb[TCA_SKBEDIT_QUEUE_MAPPING] || !tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]) { NL_SET_ERR_MSG_MOD(extack, "Missing required range of queue_mapping."); return -EINVAL; } queue_mapping_max = nla_data(tb[TCA_SKBEDIT_QUEUE_MAPPING_MAX]); if (*queue_mapping_max < *queue_mapping) { NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid, max < min."); return -EINVAL; } mapping_mod = *queue_mapping_max - *queue_mapping + 1; if (mapping_mod > U16_MAX) { NL_SET_ERR_MSG_MOD(extack, "The range of queue_mapping is invalid."); return -EINVAL; } flags |= SKBEDIT_F_TXQ_SKBHASH; } if (*pure_flags & SKBEDIT_F_INHERITDSFIELD) flags |= SKBEDIT_F_INHERITDSFIELD; } parm = nla_data(tb[TCA_SKBEDIT_PARMS]); index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (err < 0) return err; exists = err; if (exists && bind) return ACT_P_BOUND; if (!flags) { if (exists) tcf_idr_release(*a, bind); else tcf_idr_cleanup(tn, index); return -EINVAL; } if (!exists) { ret = tcf_idr_create(tn, index, est, a, &act_skbedit_ops, bind, true, act_flags); if (ret) { tcf_idr_cleanup(tn, index); return ret; } d = to_skbedit(*a); ret = ACT_P_CREATED; } else { d = to_skbedit(*a); if (!(act_flags & TCA_ACT_FLAGS_REPLACE)) { tcf_idr_release(*a, bind); return -EEXIST; } } err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; params_new = kzalloc_obj(*params_new); if (unlikely(!params_new)) { err = -ENOMEM; goto put_chain; } params_new->flags = flags; if (flags & SKBEDIT_F_PRIORITY) params_new->priority = *priority; if (flags & SKBEDIT_F_QUEUE_MAPPING) { params_new->queue_mapping = *queue_mapping; params_new->mapping_mod = mapping_mod; } if (flags & SKBEDIT_F_MARK) params_new->mark = *mark; if (flags & SKBEDIT_F_PTYPE) params_new->ptype = *ptype; /* default behaviour is to use all the bits */ params_new->mask = 0xffffffff; if (flags & SKBEDIT_F_MASK) params_new->mask = *mask; params_new->action = parm->action; spin_lock_bh(&d->tcf_lock); goto_ch = tcf_action_set_ctrlact(*a, parm->action, goto_ch); params_new = rcu_replace_pointer(d->params, params_new, lockdep_is_held(&d->tcf_lock)); spin_unlock_bh(&d->tcf_lock); if (params_new) kfree_rcu(params_new, rcu); if (goto_ch) tcf_chain_put_by_act(goto_ch); return ret; put_chain: if (goto_ch) tcf_chain_put_by_act(goto_ch); release_idr: tcf_idr_release(*a, bind); return err; } static int tcf_skbedit_dump(struct sk_buff *skb, struct tc_action *a, int bind, int ref) { const struct tcf_skbedit *d = to_skbedit(a); unsigned char *b = skb_tail_pointer(skb); const struct tcf_skbedit_params *params; struct tc_skbedit opt = { .index = d->tcf_index, .refcnt = refcount_read(&d->tcf_refcnt) - ref, .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, }; u64 pure_flags = 0; struct tcf_t t; rcu_read_lock(); params = rcu_dereference(d->params); opt.action = params->action; if (nla_put(skb, TCA_SKBEDIT_PARMS, sizeof(opt), &opt)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_PRIORITY) && nla_put_u32(skb, TCA_SKBEDIT_PRIORITY, params->priority)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_QUEUE_MAPPING) && nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING, params->queue_mapping)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_MARK) && nla_put_u32(skb, TCA_SKBEDIT_MARK, params->mark)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_PTYPE) && nla_put_u16(skb, TCA_SKBEDIT_PTYPE, params->ptype)) goto nla_put_failure; if ((params->flags & SKBEDIT_F_MASK) && nla_put_u32(skb, TCA_SKBEDIT_MASK, params->mask)) goto nla_put_failure; if (params->flags & SKBEDIT_F_INHERITDSFIELD) pure_flags |= SKBEDIT_F_INHERITDSFIELD; if (params->flags & SKBEDIT_F_TXQ_SKBHASH) { if (nla_put_u16(skb, TCA_SKBEDIT_QUEUE_MAPPING_MAX, params->queue_mapping + params->mapping_mod - 1)) goto nla_put_failure; pure_flags |= SKBEDIT_F_TXQ_SKBHASH; } if (pure_flags != 0 && nla_put(skb, TCA_SKBEDIT_FLAGS, sizeof(pure_flags), &pure_flags)) goto nla_put_failure; tcf_tm_dump(&t, &d->tcf_tm); if (nla_put_64bit(skb, TCA_SKBEDIT_TM, sizeof(t), &t, TCA_SKBEDIT_PAD)) goto nla_put_failure; rcu_read_unlock(); return skb->len; nla_put_failure: rcu_read_unlock(); nlmsg_trim(skb, b); return -1; } static void tcf_skbedit_cleanup(struct tc_action *a) { struct tcf_skbedit *d = to_skbedit(a); struct tcf_skbedit_params *params; params = rcu_dereference_protected(d->params, 1); if (params) kfree_rcu(params, rcu); } static size_t tcf_skbedit_get_fill_size(const struct tc_action *act) { return nla_total_size(sizeof(struct tc_skbedit)) + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_PRIORITY */ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING */ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_QUEUE_MAPPING_MAX */ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MARK */ + nla_total_size(sizeof(u16)) /* TCA_SKBEDIT_PTYPE */ + nla_total_size(sizeof(u32)) /* TCA_SKBEDIT_MASK */ + nla_total_size_64bit(sizeof(u64)); /* TCA_SKBEDIT_FLAGS */ } static int tcf_skbedit_offload_act_setup(struct tc_action *act, void *entry_data, u32 *index_inc, bool bind, struct netlink_ext_ack *extack) { if (bind) { struct flow_action_entry *entry = entry_data; if (is_tcf_skbedit_mark(act)) { entry->id = FLOW_ACTION_MARK; entry->mark = tcf_skbedit_mark(act); } else if (is_tcf_skbedit_ptype(act)) { entry->id = FLOW_ACTION_PTYPE; entry->ptype = tcf_skbedit_ptype(act); } else if (is_tcf_skbedit_priority(act)) { entry->id = FLOW_ACTION_PRIORITY; entry->priority = tcf_skbedit_priority(act); } else if (is_tcf_skbedit_tx_queue_mapping(act)) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"queue_mapping\" option is used on transmit side"); return -EOPNOTSUPP; } else if (is_tcf_skbedit_rx_queue_mapping(act)) { entry->id = FLOW_ACTION_RX_QUEUE_MAPPING; entry->rx_queue = tcf_skbedit_rx_queue_mapping(act); } else if (is_tcf_skbedit_inheritdsfield(act)) { NL_SET_ERR_MSG_MOD(extack, "Offload not supported when \"inheritdsfield\" option is used"); return -EOPNOTSUPP; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported skbedit option offload"); return -EOPNOTSUPP; } *index_inc = 1; } else { struct flow_offload_action *fl_action = entry_data; if (is_tcf_skbedit_mark(act)) fl_action->id = FLOW_ACTION_MARK; else if (is_tcf_skbedit_ptype(act)) fl_action->id = FLOW_ACTION_PTYPE; else if (is_tcf_skbedit_priority(act)) fl_action->id = FLOW_ACTION_PRIORITY; else if (is_tcf_skbedit_rx_queue_mapping(act)) fl_action->id = FLOW_ACTION_RX_QUEUE_MAPPING; else return -EOPNOTSUPP; } return 0; } static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", .id = TCA_ID_SKBEDIT, .owner = THIS_MODULE, .act = tcf_skbedit_act, .stats_update = tcf_skbedit_stats_update, .dump = tcf_skbedit_dump, .init = tcf_skbedit_init, .cleanup = tcf_skbedit_cleanup, .get_fill_size = tcf_skbedit_get_fill_size, .offload_act_setup = tcf_skbedit_offload_act_setup, .size = sizeof(struct tcf_skbedit), }; MODULE_ALIAS_NET_ACT("skbedit"); static __net_init int skbedit_init_net(struct net *net) { struct tc_action_net *tn = net_generic(net, act_skbedit_ops.net_id); return tc_action_net_init(net, tn, &act_skbedit_ops); } static void __net_exit skbedit_exit_net(struct list_head *net_list) { tc_action_net_exit(net_list, act_skbedit_ops.net_id); } static struct pernet_operations skbedit_net_ops = { .init = skbedit_init_net, .exit_batch = skbedit_exit_net, .id = &act_skbedit_ops.net_id, .size = sizeof(struct tc_action_net), }; MODULE_AUTHOR("Alexander Duyck, <alexander.h.duyck@intel.com>"); MODULE_DESCRIPTION("SKB Editing"); MODULE_LICENSE("GPL"); static int __init skbedit_init_module(void) { return tcf_register_action(&act_skbedit_ops, &skbedit_net_ops); } static void __exit skbedit_cleanup_module(void) { tcf_unregister_action(&act_skbedit_ops, &skbedit_net_ops); } module_init(skbedit_init_module); module_exit(skbedit_cleanup_module); |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/types.h> #include <linux/sched.h> #include <linux/module.h> #include <linux/sunrpc/types.h> #include <linux/sunrpc/xdr.h> #include <linux/sunrpc/svcsock.h> #include <linux/sunrpc/svcauth.h> #include <linux/sunrpc/gss_api.h> #include <linux/sunrpc/addr.h> #include <linux/err.h> #include <linux/seq_file.h> #include <linux/hash.h> #include <linux/string.h> #include <linux/slab.h> #include <net/sock.h> #include <net/ipv6.h> #include <linux/kernel.h> #include <linux/user_namespace.h> #include <net/genetlink.h> #include <uapi/linux/sunrpc_netlink.h> #include <trace/events/sunrpc.h> #define RPCDBG_FACILITY RPCDBG_AUTH #include "netns.h" #include "netlink.h" /* * AUTHUNIX and AUTHNULL credentials are both handled here. * AUTHNULL is treated just like AUTHUNIX except that the uid/gid * are always nobody (-2). i.e. we do the same IP address checks for * AUTHNULL as for AUTHUNIX, and that is done here. */ struct unix_domain { struct auth_domain h; /* other stuff later */ }; extern struct auth_ops svcauth_null; extern struct auth_ops svcauth_unix; extern struct auth_ops svcauth_tls; static void svcauth_unix_domain_release_rcu(struct rcu_head *head) { struct auth_domain *dom = container_of(head, struct auth_domain, rcu_head); struct unix_domain *ud = container_of(dom, struct unix_domain, h); kfree(dom->name); kfree(ud); } static void svcauth_unix_domain_release(struct auth_domain *dom) { call_rcu(&dom->rcu_head, svcauth_unix_domain_release_rcu); } struct auth_domain *unix_domain_find(char *name) { struct auth_domain *rv; struct unix_domain *new = NULL; rv = auth_domain_find(name); while(1) { if (rv) { if (new && rv != &new->h) svcauth_unix_domain_release(&new->h); if (rv->flavour != &svcauth_unix) { auth_domain_put(rv); return NULL; } return rv; } new = kmalloc_obj(*new); if (new == NULL) return NULL; kref_init(&new->h.ref); new->h.name = kstrdup(name, GFP_KERNEL); if (new->h.name == NULL) { kfree(new); return NULL; } new->h.flavour = &svcauth_unix; rv = auth_domain_lookup(name, &new->h); } } EXPORT_SYMBOL_GPL(unix_domain_find); /************************************************** * cache for IP address to unix_domain * as needed by AUTH_UNIX */ #define IP_HASHBITS 8 #define IP_HASHMAX (1<<IP_HASHBITS) struct ip_map { struct cache_head h; char m_class[8]; /* e.g. "nfsd" */ struct in6_addr m_addr; struct unix_domain *m_client; struct rcu_head m_rcu; }; static void ip_map_put(struct kref *kref) { struct cache_head *item = container_of(kref, struct cache_head, ref); struct ip_map *im = container_of(item, struct ip_map,h); if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) auth_domain_put(&im->m_client->h); kfree_rcu(im, m_rcu); } static inline int hash_ip6(const struct in6_addr *ip) { return hash_32(ipv6_addr_hash(ip), IP_HASHBITS); } static int ip_map_match(struct cache_head *corig, struct cache_head *cnew) { struct ip_map *orig = container_of(corig, struct ip_map, h); struct ip_map *new = container_of(cnew, struct ip_map, h); return strcmp(orig->m_class, new->m_class) == 0 && ipv6_addr_equal(&orig->m_addr, &new->m_addr); } static void ip_map_init(struct cache_head *cnew, struct cache_head *citem) { struct ip_map *new = container_of(cnew, struct ip_map, h); struct ip_map *item = container_of(citem, struct ip_map, h); strcpy(new->m_class, item->m_class); new->m_addr = item->m_addr; } static void update(struct cache_head *cnew, struct cache_head *citem) { struct ip_map *new = container_of(cnew, struct ip_map, h); struct ip_map *item = container_of(citem, struct ip_map, h); kref_get(&item->m_client->h.ref); new->m_client = item->m_client; } static struct cache_head *ip_map_alloc(void) { struct ip_map *i = kmalloc_obj(*i); if (i) return &i->h; else return NULL; } static int ip_map_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_upcall(cd, h); } static void ip_map_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { char text_addr[40]; struct ip_map *im = container_of(h, struct ip_map, h); if (ipv6_addr_v4mapped(&(im->m_addr))) { snprintf(text_addr, 20, "%pI4", &im->m_addr.s6_addr32[3]); } else { snprintf(text_addr, 40, "%pI6", &im->m_addr); } qword_add(bpp, blen, im->m_class); qword_add(bpp, blen, text_addr); (*bpp)[-1] = '\n'; } static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct in6_addr *addr); static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, struct unix_domain *udom, time64_t expiry); static int ip_map_parse(struct cache_detail *cd, char *mesg, int mlen) { /* class ipaddress [domainname] */ /* should be safe just to use the start of the input buffer * for scratch: */ char *buf = mesg; int len; char class[8]; union { struct sockaddr sa; struct sockaddr_in s4; struct sockaddr_in6 s6; } address; struct sockaddr_in6 sin6; int err; struct ip_map *ipmp; struct auth_domain *dom; time64_t expiry; if (mesg[mlen-1] != '\n') return -EINVAL; mesg[mlen-1] = 0; /* class */ len = qword_get(&mesg, class, sizeof(class)); if (len <= 0) return -EINVAL; /* ip address */ len = qword_get(&mesg, buf, mlen); if (len <= 0) return -EINVAL; if (rpc_pton(cd->net, buf, len, &address.sa, sizeof(address)) == 0) return -EINVAL; switch (address.sa.sa_family) { case AF_INET: /* Form a mapped IPv4 address in sin6 */ sin6.sin6_family = AF_INET6; ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr, &sin6.sin6_addr); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: memcpy(&sin6, &address.s6, sizeof(sin6)); break; #endif default: return -EINVAL; } err = get_expiry(&mesg, &expiry); if (err) return err; /* domainname, or empty for NEGATIVE */ len = qword_get(&mesg, buf, mlen); if (len < 0) return -EINVAL; if (len) { dom = unix_domain_find(buf); if (dom == NULL) return -ENOENT; } else dom = NULL; /* IPv6 scope IDs are ignored for now */ ipmp = __ip_map_lookup(cd, class, &sin6.sin6_addr); if (ipmp) { err = __ip_map_update(cd, ipmp, container_of(dom, struct unix_domain, h), expiry); } else err = -ENOMEM; if (dom) auth_domain_put(dom); cache_flush(); return err; } static int ip_map_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct ip_map *im; struct in6_addr addr; char *dom = "-no-domain-"; if (h == NULL) { seq_puts(m, "#class IP domain\n"); return 0; } im = container_of(h, struct ip_map, h); /* class addr domain */ addr = im->m_addr; if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) dom = im->m_client->h.name; if (ipv6_addr_v4mapped(&addr)) { seq_printf(m, "%s %pI4 %s\n", im->m_class, &addr.s6_addr32[3], dom); } else { seq_printf(m, "%s %pI6 %s\n", im->m_class, &addr, dom); } return 0; } static struct ip_map *__ip_map_lookup(struct cache_detail *cd, char *class, struct in6_addr *addr) { struct ip_map ip; struct cache_head *ch; strcpy(ip.m_class, class); ip.m_addr = *addr; ch = sunrpc_cache_lookup_rcu(cd, &ip.h, hash_str(class, IP_HASHBITS) ^ hash_ip6(addr)); if (ch) return container_of(ch, struct ip_map, h); else return NULL; } static int __ip_map_update(struct cache_detail *cd, struct ip_map *ipm, struct unix_domain *udom, time64_t expiry) { struct ip_map ip; struct cache_head *ch; ip.m_client = udom; ip.h.flags = 0; if (!udom) set_bit(CACHE_NEGATIVE, &ip.h.flags); ip.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ip.h, &ipm->h, hash_str(ipm->m_class, IP_HASHBITS) ^ hash_ip6(&ipm->m_addr)); if (!ch) return -ENOMEM; cache_put(ch, cd); return 0; } void svcauth_unix_purge(struct net *net) { struct sunrpc_net *sn; sn = net_generic(net, sunrpc_net_id); cache_purge(sn->ip_map_cache); } EXPORT_SYMBOL_GPL(svcauth_unix_purge); static inline struct ip_map * ip_map_cached_get(struct svc_xprt *xprt) { struct ip_map *ipm = NULL; struct sunrpc_net *sn; if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) { spin_lock(&xprt->xpt_lock); ipm = xprt->xpt_auth_cache; if (ipm != NULL) { sn = net_generic(xprt->xpt_net, sunrpc_net_id); if (cache_is_expired(sn->ip_map_cache, &ipm->h)) { /* * The entry has been invalidated since it was * remembered, e.g. by a second mount from the * same IP address. */ xprt->xpt_auth_cache = NULL; spin_unlock(&xprt->xpt_lock); cache_put(&ipm->h, sn->ip_map_cache); return NULL; } cache_get(&ipm->h); } spin_unlock(&xprt->xpt_lock); } return ipm; } static inline void ip_map_cached_put(struct svc_xprt *xprt, struct ip_map *ipm) { if (test_bit(XPT_CACHE_AUTH, &xprt->xpt_flags)) { spin_lock(&xprt->xpt_lock); if (xprt->xpt_auth_cache == NULL) { /* newly cached, keep the reference */ xprt->xpt_auth_cache = ipm; ipm = NULL; } spin_unlock(&xprt->xpt_lock); } if (ipm) { struct sunrpc_net *sn; sn = net_generic(xprt->xpt_net, sunrpc_net_id); cache_put(&ipm->h, sn->ip_map_cache); } } void svcauth_unix_info_release(struct svc_xprt *xpt) { struct ip_map *ipm; ipm = xpt->xpt_auth_cache; if (ipm != NULL) { struct sunrpc_net *sn; sn = net_generic(xpt->xpt_net, sunrpc_net_id); cache_put(&ipm->h, sn->ip_map_cache); } } /**************************************************************************** * auth.unix.gid cache * simple cache to map a UID to a list of GIDs * because AUTH_UNIX aka AUTH_SYS has a max of UNX_NGROUPS */ #define GID_HASHBITS 8 #define GID_HASHMAX (1<<GID_HASHBITS) struct unix_gid { struct cache_head h; kuid_t uid; struct group_info *gi; struct rcu_head rcu; }; static int unix_gid_hash(kuid_t uid) { return hash_long(from_kuid(&init_user_ns, uid), GID_HASHBITS); } static void unix_gid_free(struct rcu_head *rcu) { struct unix_gid *ug = container_of(rcu, struct unix_gid, rcu); struct cache_head *item = &ug->h; if (test_bit(CACHE_VALID, &item->flags) && !test_bit(CACHE_NEGATIVE, &item->flags)) put_group_info(ug->gi); kfree(ug); } static void unix_gid_put(struct kref *kref) { struct cache_head *item = container_of(kref, struct cache_head, ref); struct unix_gid *ug = container_of(item, struct unix_gid, h); call_rcu(&ug->rcu, unix_gid_free); } static int unix_gid_match(struct cache_head *corig, struct cache_head *cnew) { struct unix_gid *orig = container_of(corig, struct unix_gid, h); struct unix_gid *new = container_of(cnew, struct unix_gid, h); return uid_eq(orig->uid, new->uid); } static void unix_gid_init(struct cache_head *cnew, struct cache_head *citem) { struct unix_gid *new = container_of(cnew, struct unix_gid, h); struct unix_gid *item = container_of(citem, struct unix_gid, h); new->uid = item->uid; } static void unix_gid_update(struct cache_head *cnew, struct cache_head *citem) { struct unix_gid *new = container_of(cnew, struct unix_gid, h); struct unix_gid *item = container_of(citem, struct unix_gid, h); get_group_info(item->gi); new->gi = item->gi; } static struct cache_head *unix_gid_alloc(void) { struct unix_gid *g = kmalloc_obj(*g); if (g) return &g->h; else return NULL; } static int unix_gid_upcall(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_upcall_warn(cd, h); } static void unix_gid_request(struct cache_detail *cd, struct cache_head *h, char **bpp, int *blen) { char tuid[20]; struct unix_gid *ug = container_of(h, struct unix_gid, h); snprintf(tuid, 20, "%u", from_kuid(&init_user_ns, ug->uid)); qword_add(bpp, blen, tuid); (*bpp)[-1] = '\n'; } static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid); static int unix_gid_parse(struct cache_detail *cd, char *mesg, int mlen) { /* uid expiry Ngid gid0 gid1 ... gidN-1 */ int id; kuid_t uid; int gids; int rv; int i; int err; time64_t expiry; struct unix_gid ug, *ugp; if (mesg[mlen - 1] != '\n') return -EINVAL; mesg[mlen-1] = 0; rv = get_int(&mesg, &id); if (rv) return -EINVAL; uid = make_kuid(current_user_ns(), id); ug.uid = uid; err = get_expiry(&mesg, &expiry); if (err) return err; rv = get_int(&mesg, &gids); if (rv || gids < 0 || gids > 8192) return -EINVAL; ug.gi = groups_alloc(gids); if (!ug.gi) return -ENOMEM; for (i = 0 ; i < gids ; i++) { int gid; kgid_t kgid; rv = get_int(&mesg, &gid); err = -EINVAL; if (rv) goto out; kgid = make_kgid(current_user_ns(), gid); if (!gid_valid(kgid)) goto out; ug.gi->gid[i] = kgid; } groups_sort(ug.gi); ugp = unix_gid_lookup(cd, uid); if (ugp) { struct cache_head *ch; ug.h.flags = 0; ug.h.expiry_time = expiry; ch = sunrpc_cache_update(cd, &ug.h, &ugp->h, unix_gid_hash(uid)); if (!ch) err = -ENOMEM; else { err = 0; cache_put(ch, cd); } } else err = -ENOMEM; out: if (ug.gi) put_group_info(ug.gi); return err; } static int unix_gid_show(struct seq_file *m, struct cache_detail *cd, struct cache_head *h) { struct user_namespace *user_ns = m->file->f_cred->user_ns; struct unix_gid *ug; int i; int glen; if (h == NULL) { seq_puts(m, "#uid cnt: gids...\n"); return 0; } ug = container_of(h, struct unix_gid, h); if (test_bit(CACHE_VALID, &h->flags) && !test_bit(CACHE_NEGATIVE, &h->flags)) glen = ug->gi->ngroups; else glen = 0; seq_printf(m, "%u %d:", from_kuid_munged(user_ns, ug->uid), glen); for (i = 0; i < glen; i++) seq_printf(m, " %d", from_kgid_munged(user_ns, ug->gi->gid[i])); seq_printf(m, "\n"); return 0; } static int unix_gid_notify(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_notify(cd, h, SUNRPC_CACHE_TYPE_UNIX_GID); } /** * sunrpc_nl_unix_gid_get_reqs_dumpit - dump pending unix_gid requests * @skb: reply buffer * @cb: netlink metadata and command arguments * * Walk the unix_gid cache's pending request list and create a netlink * message with a nested entry for each cache_request, containing the * seqno and uid. * * Uses cb->args[0] as a seqno cursor for dump continuation across * multiple netlink messages. * * Returns the size of the reply or a negative errno. */ int sunrpc_nl_unix_gid_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct sunrpc_net *sn; struct cache_detail *cd; struct cache_head **items; u64 *seqnos; int cnt, i, emitted; void *hdr; int ret; sn = net_generic(sock_net(skb->sk), sunrpc_net_id); cd = sn->unix_gid_cache; if (!cd) return -ENODEV; cnt = sunrpc_cache_requests_count(cd); if (!cnt) return 0; items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; goto out_alloc; } cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt, cb->args[0]); if (!cnt) { ret = 0; goto out_alloc; } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &sunrpc_nl_family, NLM_F_MULTI, SUNRPC_CMD_UNIX_GID_GET_REQS); if (!hdr) { ret = -ENOBUFS; goto out_put; } emitted = 0; for (i = 0; i < cnt; i++) { struct unix_gid *ug; struct nlattr *nest; ug = container_of(items[i], struct unix_gid, h); nest = nla_nest_start(skb, SUNRPC_A_UNIX_GID_REQS_REQUESTS); if (!nest) break; if (nla_put_u64_64bit(skb, SUNRPC_A_UNIX_GID_SEQNO, seqnos[i], 0) || nla_put_u32(skb, SUNRPC_A_UNIX_GID_UID, from_kuid(&init_user_ns, ug->uid))) { nla_nest_cancel(skb, nest); break; } nla_nest_end(skb, nest); cb->args[0] = seqnos[i]; emitted++; } if (!emitted) { genlmsg_cancel(skb, hdr); ret = -EMSGSIZE; goto out_put; } genlmsg_end(skb, hdr); ret = skb->len; out_put: for (i = 0; i < cnt; i++) cache_put(items[i], cd); out_alloc: kfree(seqnos); kfree(items); return ret; } /** * sunrpc_nl_parse_one_unix_gid - parse one unix_gid entry from netlink * @cd: cache_detail for the unix_gid cache * @attr: nested attribute containing unix_gid fields * * Parses one unix_gid entry from a netlink message and updates the * cache. Mirrors the logic in unix_gid_parse(). * * Returns 0 on success or a negative errno. */ static int sunrpc_nl_parse_one_unix_gid(struct cache_detail *cd, struct nlattr *attr) { struct nlattr *tb[SUNRPC_A_UNIX_GID_EXPIRY + 1]; struct unix_gid ug, *ugp; struct timespec64 boot; struct nlattr *gid_attr; int err, rem, gids = 0; kuid_t uid; err = nla_parse_nested(tb, SUNRPC_A_UNIX_GID_EXPIRY, attr, sunrpc_unix_gid_nl_policy, NULL); if (err) return err; /* uid (required) */ if (!tb[SUNRPC_A_UNIX_GID_UID]) return -EINVAL; uid = make_kuid(current_user_ns(), nla_get_u32(tb[SUNRPC_A_UNIX_GID_UID])); ug.uid = uid; /* expiry (required, wallclock seconds) */ if (!tb[SUNRPC_A_UNIX_GID_EXPIRY]) return -EINVAL; getboottime64(&boot); ug.h.flags = 0; ug.h.expiry_time = nla_get_u64(tb[SUNRPC_A_UNIX_GID_EXPIRY]) - boot.tv_sec; if (tb[SUNRPC_A_UNIX_GID_NEGATIVE]) { ug.gi = groups_alloc(0); if (!ug.gi) return -ENOMEM; } else { /* Count gids */ nla_for_each_nested_type(gid_attr, SUNRPC_A_UNIX_GID_GIDS, attr, rem) gids++; if (gids > 8192) return -EINVAL; ug.gi = groups_alloc(gids); if (!ug.gi) return -ENOMEM; gids = 0; nla_for_each_nested_type(gid_attr, SUNRPC_A_UNIX_GID_GIDS, attr, rem) { kgid_t kgid; kgid = make_kgid(current_user_ns(), nla_get_u32(gid_attr)); if (!gid_valid(kgid)) { err = -EINVAL; goto out; } ug.gi->gid[gids++] = kgid; } groups_sort(ug.gi); } ugp = unix_gid_lookup(cd, uid); if (ugp) { struct cache_head *ch; ch = sunrpc_cache_update(cd, &ug.h, &ugp->h, unix_gid_hash(uid)); if (!ch) { err = -ENOMEM; } else { err = 0; cache_put(ch, cd); } } else { err = -ENOMEM; } out: if (ug.gi) put_group_info(ug.gi); return err; } /** * sunrpc_nl_unix_gid_set_reqs_doit - respond to unix_gid requests * @skb: reply buffer * @info: netlink metadata and command arguments * * Parse one or more unix_gid cache responses from userspace and * update the unix_gid cache accordingly. * * Returns 0 on success or a negative errno. */ int sunrpc_nl_unix_gid_set_reqs_doit(struct sk_buff *skb, struct genl_info *info) { struct sunrpc_net *sn; struct cache_detail *cd; const struct nlattr *attr; int rem, ret = 0; sn = net_generic(genl_info_net(info), sunrpc_net_id); cd = sn->unix_gid_cache; if (!cd) return -ENODEV; nlmsg_for_each_attr_type(attr, SUNRPC_A_UNIX_GID_REQS_REQUESTS, info->nlhdr, GENL_HDRLEN, rem) { ret = sunrpc_nl_parse_one_unix_gid(cd, (struct nlattr *)attr); if (ret) break; } return ret; } /** * sunrpc_nl_cache_flush_doit - flush sunrpc caches via netlink * @skb: reply buffer * @info: netlink metadata and command arguments * * Flush the ip_map and/or unix_gid caches. If SUNRPC_A_CACHE_FLUSH_MASK * is provided, only flush the caches indicated by the bitmask (bit 1 = * ip_map, bit 2 = unix_gid). If omitted, flush both. * * Return 0 on success or a negative errno. */ int sunrpc_nl_cache_flush_doit(struct sk_buff *skb, struct genl_info *info) { struct sunrpc_net *sn; u32 mask = ~0U; sn = net_generic(genl_info_net(info), sunrpc_net_id); if (info->attrs[SUNRPC_A_CACHE_FLUSH_MASK]) mask = nla_get_u32(info->attrs[SUNRPC_A_CACHE_FLUSH_MASK]); if ((mask & SUNRPC_CACHE_TYPE_IP_MAP) && sn->ip_map_cache) cache_purge(sn->ip_map_cache); if ((mask & SUNRPC_CACHE_TYPE_UNIX_GID) && sn->unix_gid_cache) cache_purge(sn->unix_gid_cache); return 0; } static const struct cache_detail unix_gid_cache_template = { .owner = THIS_MODULE, .hash_size = GID_HASHMAX, .name = "auth.unix.gid", .cache_put = unix_gid_put, .cache_upcall = unix_gid_upcall, .cache_notify = unix_gid_notify, .cache_request = unix_gid_request, .cache_parse = unix_gid_parse, .cache_show = unix_gid_show, .match = unix_gid_match, .init = unix_gid_init, .update = unix_gid_update, .alloc = unix_gid_alloc, }; int unix_gid_cache_create(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&unix_gid_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->unix_gid_cache = cd; return 0; } void unix_gid_cache_destroy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->unix_gid_cache; sn->unix_gid_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } static struct unix_gid *unix_gid_lookup(struct cache_detail *cd, kuid_t uid) { struct unix_gid ug; struct cache_head *ch; ug.uid = uid; ch = sunrpc_cache_lookup_rcu(cd, &ug.h, unix_gid_hash(uid)); if (ch) return container_of(ch, struct unix_gid, h); else return NULL; } static struct group_info *unix_gid_find(kuid_t uid, struct svc_rqst *rqstp) { struct unix_gid *ug; struct group_info *gi; int ret; struct sunrpc_net *sn = net_generic(rqstp->rq_xprt->xpt_net, sunrpc_net_id); ug = unix_gid_lookup(sn->unix_gid_cache, uid); if (!ug) return ERR_PTR(-EAGAIN); ret = cache_check(sn->unix_gid_cache, &ug->h, &rqstp->rq_chandle); switch (ret) { case -ENOENT: return ERR_PTR(-ENOENT); case -ETIMEDOUT: return ERR_PTR(-ESHUTDOWN); case 0: gi = get_group_info(ug->gi); cache_put(&ug->h, sn->unix_gid_cache); return gi; default: return ERR_PTR(-EAGAIN); } } enum svc_auth_status svcauth_unix_set_client(struct svc_rqst *rqstp) { struct sockaddr_in *sin; struct sockaddr_in6 *sin6, sin6_storage; struct ip_map *ipm; struct group_info *gi; struct svc_cred *cred = &rqstp->rq_cred; struct svc_xprt *xprt = rqstp->rq_xprt; struct net *net = xprt->xpt_net; struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); switch (rqstp->rq_addr.ss_family) { case AF_INET: sin = svc_addr_in(rqstp); sin6 = &sin6_storage; ipv6_addr_set_v4mapped(sin->sin_addr.s_addr, &sin6->sin6_addr); break; case AF_INET6: sin6 = svc_addr_in6(rqstp); break; default: BUG(); } rqstp->rq_client = NULL; if (rqstp->rq_proc == 0) goto out; rqstp->rq_auth_stat = rpc_autherr_badcred; ipm = ip_map_cached_get(xprt); if (ipm == NULL) ipm = __ip_map_lookup(sn->ip_map_cache, rqstp->rq_server->sv_programs->pg_class, &sin6->sin6_addr); if (ipm == NULL) return SVC_DENIED; switch (cache_check(sn->ip_map_cache, &ipm->h, &rqstp->rq_chandle)) { default: BUG(); case -ETIMEDOUT: return SVC_CLOSE; case -EAGAIN: return SVC_DROP; case -ENOENT: return SVC_DENIED; case 0: rqstp->rq_client = &ipm->m_client->h; kref_get(&rqstp->rq_client->ref); ip_map_cached_put(xprt, ipm); break; } gi = unix_gid_find(cred->cr_uid, rqstp); switch (PTR_ERR(gi)) { case -EAGAIN: return SVC_DROP; case -ESHUTDOWN: return SVC_CLOSE; case -ENOENT: break; default: put_group_info(cred->cr_group_info); cred->cr_group_info = gi; } out: rqstp->rq_auth_stat = rpc_auth_ok; return SVC_OK; } EXPORT_SYMBOL_GPL(svcauth_unix_set_client); /** * svcauth_null_accept - Decode and validate incoming RPC_AUTH_NULL credential * @rqstp: RPC transaction * * Return values: * %SVC_OK: Both credential and verifier are valid * %SVC_DENIED: Credential or verifier is not valid * %SVC_GARBAGE: Failed to decode credential or verifier * %SVC_CLOSE: Temporary failure * * rqstp->rq_auth_stat is set as mandated by RFC 5531. */ static enum svc_auth_status svcauth_null_accept(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct svc_cred *cred = &rqstp->rq_cred; u32 flavor, len; void *body; /* Length of Call's credential body field: */ if (xdr_stream_decode_u32(xdr, &len) < 0) return SVC_GARBAGE; if (len != 0) { rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, &body, &len) < 0) return SVC_GARBAGE; if (flavor != RPC_AUTH_NULL || len != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } /* Signal that mapping to nobody uid/gid is required */ cred->cr_uid = INVALID_UID; cred->cr_gid = INVALID_GID; cred->cr_group_info = groups_alloc(0); if (cred->cr_group_info == NULL) return SVC_CLOSE; /* kmalloc failure - client must retry */ if (xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; if (!svcxdr_set_accept_stat(rqstp)) return SVC_CLOSE; rqstp->rq_cred.cr_flavor = RPC_AUTH_NULL; return SVC_OK; } static int svcauth_null_release(struct svc_rqst *rqstp) { if (rqstp->rq_client) auth_domain_put(rqstp->rq_client); rqstp->rq_client = NULL; if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; return 0; /* don't drop */ } struct auth_ops svcauth_null = { .name = "null", .owner = THIS_MODULE, .flavour = RPC_AUTH_NULL, .accept = svcauth_null_accept, .release = svcauth_null_release, .set_client = svcauth_unix_set_client, }; /** * svcauth_tls_accept - Decode and validate incoming RPC_AUTH_TLS credential * @rqstp: RPC transaction * * Return values: * %SVC_OK: Both credential and verifier are valid * %SVC_DENIED: Credential or verifier is not valid * %SVC_GARBAGE: Failed to decode credential or verifier * %SVC_CLOSE: Temporary failure * * rqstp->rq_auth_stat is set as mandated by RFC 5531. */ static enum svc_auth_status svcauth_tls_accept(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct svc_cred *cred = &rqstp->rq_cred; struct svc_xprt *xprt = rqstp->rq_xprt; u32 flavor, len; void *body; __be32 *p; /* Length of Call's credential body field: */ if (xdr_stream_decode_u32(xdr, &len) < 0) return SVC_GARBAGE; if (len != 0) { rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, &body, &len) < 0) return SVC_GARBAGE; if (flavor != RPC_AUTH_NULL || len != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } /* AUTH_TLS is not valid on non-NULL procedures */ if (rqstp->rq_proc != 0) { rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } /* Signal that mapping to nobody uid/gid is required */ cred->cr_uid = INVALID_UID; cred->cr_gid = INVALID_GID; cred->cr_group_info = groups_alloc(0); if (cred->cr_group_info == NULL) return SVC_CLOSE; if (xprt->xpt_ops->xpo_handshake) { p = xdr_reserve_space(&rqstp->rq_res_stream, XDR_UNIT * 2 + 8); if (!p) return SVC_CLOSE; trace_svc_tls_start(xprt); *p++ = rpc_auth_null; *p++ = cpu_to_be32(8); memcpy(p, "STARTTLS", 8); set_bit(XPT_HANDSHAKE, &xprt->xpt_flags); svc_xprt_enqueue(xprt); } else { trace_svc_tls_unavailable(xprt); if (xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; } if (!svcxdr_set_accept_stat(rqstp)) return SVC_CLOSE; rqstp->rq_cred.cr_flavor = RPC_AUTH_TLS; return SVC_OK; } struct auth_ops svcauth_tls = { .name = "tls", .owner = THIS_MODULE, .flavour = RPC_AUTH_TLS, .accept = svcauth_tls_accept, .release = svcauth_null_release, .set_client = svcauth_unix_set_client, }; /** * svcauth_unix_accept - Decode and validate incoming RPC_AUTH_SYS credential * @rqstp: RPC transaction * * Return values: * %SVC_OK: Both credential and verifier are valid * %SVC_DENIED: Credential or verifier is not valid * %SVC_GARBAGE: Failed to decode credential or verifier * %SVC_CLOSE: Temporary failure * * rqstp->rq_auth_stat is set as mandated by RFC 5531. */ static enum svc_auth_status svcauth_unix_accept(struct svc_rqst *rqstp) { struct xdr_stream *xdr = &rqstp->rq_arg_stream; struct svc_cred *cred = &rqstp->rq_cred; struct user_namespace *userns; u32 flavor, len, i; void *body; __be32 *p; /* * This implementation ignores the length of the Call's * credential body field and the timestamp and machinename * fields. */ p = xdr_inline_decode(xdr, XDR_UNIT * 3); if (!p) return SVC_GARBAGE; len = be32_to_cpup(p + 2); if (len > RPC_MAX_MACHINENAME) return SVC_GARBAGE; if (!xdr_inline_decode(xdr, len)) return SVC_GARBAGE; /* * Note: we skip uid_valid()/gid_valid() checks here for * backwards compatibility with clients that use -1 id's. * Instead, -1 uid or gid is later mapped to the * (export-specific) anonymous id by nfsd_setuser. * Supplementary gid's will be left alone. */ userns = (rqstp->rq_xprt && rqstp->rq_xprt->xpt_cred) ? rqstp->rq_xprt->xpt_cred->user_ns : &init_user_ns; if (xdr_stream_decode_u32(xdr, &i) < 0) return SVC_GARBAGE; cred->cr_uid = make_kuid(userns, i); if (xdr_stream_decode_u32(xdr, &i) < 0) return SVC_GARBAGE; cred->cr_gid = make_kgid(userns, i); if (xdr_stream_decode_u32(xdr, &len) < 0) return SVC_GARBAGE; if (len > UNX_NGROUPS) goto badcred; p = xdr_inline_decode(xdr, XDR_UNIT * len); if (!p) return SVC_GARBAGE; cred->cr_group_info = groups_alloc(len); if (cred->cr_group_info == NULL) return SVC_CLOSE; for (i = 0; i < len; i++) { kgid_t kgid = make_kgid(userns, be32_to_cpup(p++)); cred->cr_group_info->gid[i] = kgid; } groups_sort(cred->cr_group_info); /* Call's verf field: */ if (xdr_stream_decode_opaque_auth(xdr, &flavor, &body, &len) < 0) return SVC_GARBAGE; if (flavor != RPC_AUTH_NULL || len != 0) { rqstp->rq_auth_stat = rpc_autherr_badverf; return SVC_DENIED; } if (xdr_stream_encode_opaque_auth(&rqstp->rq_res_stream, RPC_AUTH_NULL, NULL, 0) < 0) return SVC_CLOSE; if (!svcxdr_set_accept_stat(rqstp)) return SVC_CLOSE; rqstp->rq_cred.cr_flavor = RPC_AUTH_UNIX; return SVC_OK; badcred: rqstp->rq_auth_stat = rpc_autherr_badcred; return SVC_DENIED; } static int svcauth_unix_release(struct svc_rqst *rqstp) { /* Verifier (such as it is) is already in place. */ if (rqstp->rq_client) auth_domain_put(rqstp->rq_client); rqstp->rq_client = NULL; if (rqstp->rq_cred.cr_group_info) put_group_info(rqstp->rq_cred.cr_group_info); rqstp->rq_cred.cr_group_info = NULL; return 0; } struct auth_ops svcauth_unix = { .name = "unix", .owner = THIS_MODULE, .flavour = RPC_AUTH_UNIX, .accept = svcauth_unix_accept, .release = svcauth_unix_release, .domain_release = svcauth_unix_domain_release, .set_client = svcauth_unix_set_client, }; static int ip_map_notify(struct cache_detail *cd, struct cache_head *h) { return sunrpc_cache_notify(cd, h, SUNRPC_CACHE_TYPE_IP_MAP); } /** * sunrpc_nl_ip_map_get_reqs_dumpit - dump pending ip_map requests * @skb: reply buffer * @cb: netlink metadata and command arguments * * Walk the ip_map cache's pending request list and create a netlink * message with a nested entry for each cache_request, containing the * seqno, class and addr. * * Uses cb->args[0] as a seqno cursor for dump continuation across * multiple netlink messages. * * Returns the size of the reply or a negative errno. */ int sunrpc_nl_ip_map_get_reqs_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { struct sunrpc_net *sn; struct cache_detail *cd; struct cache_head **items; u64 *seqnos; int cnt, i, emitted; void *hdr; int ret; sn = net_generic(sock_net(skb->sk), sunrpc_net_id); cd = sn->ip_map_cache; if (!cd) return -ENODEV; cnt = sunrpc_cache_requests_count(cd); if (!cnt) return 0; items = kcalloc(cnt, sizeof(*items), GFP_KERNEL); seqnos = kcalloc(cnt, sizeof(*seqnos), GFP_KERNEL); if (!items || !seqnos) { ret = -ENOMEM; goto out_alloc; } cnt = sunrpc_cache_requests_snapshot(cd, items, seqnos, cnt, cb->args[0]); if (!cnt) { ret = 0; goto out_alloc; } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &sunrpc_nl_family, NLM_F_MULTI, SUNRPC_CMD_IP_MAP_GET_REQS); if (!hdr) { ret = -ENOBUFS; goto out_put; } emitted = 0; for (i = 0; i < cnt; i++) { struct ip_map *im; struct nlattr *nest; char text_addr[40]; im = container_of(items[i], struct ip_map, h); if (ipv6_addr_v4mapped(&im->m_addr)) snprintf(text_addr, 20, "%pI4", &im->m_addr.s6_addr32[3]); else snprintf(text_addr, 40, "%pI6", &im->m_addr); nest = nla_nest_start(skb, SUNRPC_A_IP_MAP_REQS_REQUESTS); if (!nest) break; if (nla_put_u64_64bit(skb, SUNRPC_A_IP_MAP_SEQNO, seqnos[i], 0) || nla_put_string(skb, SUNRPC_A_IP_MAP_CLASS, im->m_class) || nla_put_string(skb, SUNRPC_A_IP_MAP_ADDR, text_addr)) { nla_nest_cancel(skb, nest); break; } nla_nest_end(skb, nest); cb->args[0] = seqnos[i]; emitted++; } if (!emitted) { genlmsg_cancel(skb, hdr); ret = -EMSGSIZE; goto out_put; } genlmsg_end(skb, hdr); ret = skb->len; out_put: for (i = 0; i < cnt; i++) cache_put(items[i], cd); out_alloc: kfree(seqnos); kfree(items); return ret; } /** * sunrpc_nl_parse_one_ip_map - parse one ip_map entry from netlink * @cd: cache_detail for the ip_map cache * @attr: nested attribute containing ip_map fields * * Parses one ip_map entry from a netlink message and updates the * cache. Mirrors the logic in ip_map_parse(). * * Returns 0 on success or a negative errno. */ static int sunrpc_nl_parse_one_ip_map(struct cache_detail *cd, struct nlattr *attr) { struct nlattr *tb[SUNRPC_A_IP_MAP_EXPIRY + 1]; union { struct sockaddr sa; struct sockaddr_in s4; struct sockaddr_in6 s6; } address; struct sockaddr_in6 sin6; struct ip_map *ipmp; struct auth_domain *dom = NULL; struct unix_domain *udom = NULL; struct timespec64 boot; time64_t expiry; char class[8]; int err; int len; err = nla_parse_nested(tb, SUNRPC_A_IP_MAP_EXPIRY, attr, sunrpc_ip_map_nl_policy, NULL); if (err) return err; /* class (required) */ if (!tb[SUNRPC_A_IP_MAP_CLASS]) return -EINVAL; len = nla_len(tb[SUNRPC_A_IP_MAP_CLASS]); if (len <= 0 || len > sizeof(class)) return -EINVAL; nla_strscpy(class, tb[SUNRPC_A_IP_MAP_CLASS], sizeof(class)); /* addr (required) */ if (!tb[SUNRPC_A_IP_MAP_ADDR]) return -EINVAL; if (rpc_pton(cd->net, nla_data(tb[SUNRPC_A_IP_MAP_ADDR]), nla_len(tb[SUNRPC_A_IP_MAP_ADDR]) - 1, &address.sa, sizeof(address)) == 0) return -EINVAL; switch (address.sa.sa_family) { case AF_INET: sin6.sin6_family = AF_INET6; ipv6_addr_set_v4mapped(address.s4.sin_addr.s_addr, &sin6.sin6_addr); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: memcpy(&sin6, &address.s6, sizeof(sin6)); break; #endif default: return -EINVAL; } /* expiry (required, wallclock seconds) */ if (!tb[SUNRPC_A_IP_MAP_EXPIRY]) return -EINVAL; getboottime64(&boot); expiry = nla_get_u64(tb[SUNRPC_A_IP_MAP_EXPIRY]) - boot.tv_sec; /* domain name or negative */ if (tb[SUNRPC_A_IP_MAP_NEGATIVE]) { udom = NULL; } else if (tb[SUNRPC_A_IP_MAP_DOMAIN]) { dom = unix_domain_find(nla_data(tb[SUNRPC_A_IP_MAP_DOMAIN])); if (!dom) return -ENOENT; udom = container_of(dom, struct unix_domain, h); } else { return -EINVAL; } ipmp = __ip_map_lookup(cd, class, &sin6.sin6_addr); if (ipmp) err = __ip_map_update(cd, ipmp, udom, expiry); else err = -ENOMEM; if (dom) auth_domain_put(dom); cache_flush(); return err; } /** * sunrpc_nl_ip_map_set_reqs_doit - respond to ip_map requests * @skb: reply buffer * @info: netlink metadata and command arguments * * Parse one or more ip_map cache responses from userspace and * update the ip_map cache accordingly. * * Returns 0 on success or a negative errno. */ int sunrpc_nl_ip_map_set_reqs_doit(struct sk_buff *skb, struct genl_info *info) { struct sunrpc_net *sn; struct cache_detail *cd; const struct nlattr *attr; int rem, ret = 0; sn = net_generic(genl_info_net(info), sunrpc_net_id); cd = sn->ip_map_cache; if (!cd) return -ENODEV; nlmsg_for_each_attr_type(attr, SUNRPC_A_IP_MAP_REQS_REQUESTS, info->nlhdr, GENL_HDRLEN, rem) { ret = sunrpc_nl_parse_one_ip_map(cd, (struct nlattr *)attr); if (ret) break; } return ret; } static const struct cache_detail ip_map_cache_template = { .owner = THIS_MODULE, .hash_size = IP_HASHMAX, .name = "auth.unix.ip", .cache_put = ip_map_put, .cache_upcall = ip_map_upcall, .cache_notify = ip_map_notify, .cache_request = ip_map_request, .cache_parse = ip_map_parse, .cache_show = ip_map_show, .match = ip_map_match, .init = ip_map_init, .update = update, .alloc = ip_map_alloc, }; int ip_map_cache_create(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd; int err; cd = cache_create_net(&ip_map_cache_template, net); if (IS_ERR(cd)) return PTR_ERR(cd); err = cache_register_net(cd, net); if (err) { cache_destroy_net(cd, net); return err; } sn->ip_map_cache = cd; return 0; } void ip_map_cache_destroy(struct net *net) { struct sunrpc_net *sn = net_generic(net, sunrpc_net_id); struct cache_detail *cd = sn->ip_map_cache; sn->ip_map_cache = NULL; cache_purge(cd); cache_unregister_net(cd, net); cache_destroy_net(cd, net); } |
| 1 11 12 12 14 14 13 14 1 12 2 13 13 13 1 14 14 1 13 2 1 1 14 12 12 12 12 14 14 2 12 12 12 12 12 12 14 14 12 2 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 | // SPDX-License-Identifier: GPL-2.0 /* * * Copyright (C) 2019-2021 Paragon Software GmbH, All rights reserved. * */ #include <linux/blkdev.h> #include <linux/fs.h> #include <linux/random.h> #include <linux/slab.h> #include "debug.h" #include "ntfs.h" #include "ntfs_fs.h" /* * LOG FILE structs */ // clang-format off #define MaxLogFileSize 0x100000000ull #define DefaultLogPageSize 4096 #define MinLogRecordPages 0x30 struct RESTART_HDR { struct NTFS_RECORD_HEADER rhdr; // 'RSTR' __le32 sys_page_size; // 0x10: Page size of the system which initialized the log. __le32 page_size; // 0x14: Log page size used for this log file. __le16 ra_off; // 0x18: __le16 minor_ver; // 0x1A: __le16 major_ver; // 0x1C: __le16 fixups[]; }; #define LFS_NO_CLIENT 0xffff #define LFS_NO_CLIENT_LE cpu_to_le16(0xffff) struct CLIENT_REC { __le64 oldest_lsn; __le64 restart_lsn; // 0x08: __le16 prev_client; // 0x10: __le16 next_client; // 0x12: __le16 seq_num; // 0x14: u8 align[6]; // 0x16: __le32 name_bytes; // 0x1C: In bytes. __le16 name[64]; // 0x20: Name of client. }; static_assert(sizeof(struct CLIENT_REC) == 0xa0); /* Two copies of these will exist at the beginning of the log file */ struct RESTART_AREA { __le64 current_lsn; // 0x00: Current logical end of log file. __le16 log_clients; // 0x08: Maximum number of clients. __le16 client_idx[2]; // 0x0A: Free/use index into the client record arrays. __le16 flags; // 0x0E: See RESTART_SINGLE_PAGE_IO. __le32 seq_num_bits; // 0x10: The number of bits in sequence number. __le16 ra_len; // 0x14: __le16 client_off; // 0x16: __le64 l_size; // 0x18: Usable log file size. __le32 last_lsn_data_len; // 0x20: __le16 rec_hdr_len; // 0x24: Log page data offset. __le16 data_off; // 0x26: Log page data length. __le32 open_log_count; // 0x28: __le32 align[5]; // 0x2C: struct CLIENT_REC clients[]; // 0x40: }; struct LOG_REC_HDR { __le16 redo_op; // 0x00: NTFS_LOG_OPERATION __le16 undo_op; // 0x02: NTFS_LOG_OPERATION __le16 redo_off; // 0x04: Offset to Redo record. __le16 redo_len; // 0x06: Redo length. __le16 undo_off; // 0x08: Offset to Undo record. __le16 undo_len; // 0x0A: Undo length. __le16 target_attr; // 0x0C: __le16 lcns_follow; // 0x0E: __le16 record_off; // 0x10: __le16 attr_off; // 0x12: __le16 cluster_off; // 0x14: __le16 reserved; // 0x16: __le64 target_vcn; // 0x18: __le64 page_lcns[]; // 0x20: }; static_assert(sizeof(struct LOG_REC_HDR) == 0x20); #define RESTART_ENTRY_ALLOCATED 0xFFFFFFFF #define RESTART_ENTRY_ALLOCATED_LE cpu_to_le32(0xFFFFFFFF) struct RESTART_TABLE { __le16 size; // 0x00: In bytes __le16 used; // 0x02: Entries __le16 total; // 0x04: Entries __le16 res[3]; // 0x06: __le32 free_goal; // 0x0C: __le32 first_free; // 0x10: __le32 last_free; // 0x14: }; static_assert(sizeof(struct RESTART_TABLE) == 0x18); struct ATTR_NAME_ENTRY { __le16 off; // Offset in the Open attribute Table. __le16 name_bytes; __le16 name[]; }; struct OPEN_ATTR_ENRTY { __le32 next; // 0x00: RESTART_ENTRY_ALLOCATED if allocated __le32 bytes_per_index; // 0x04: enum ATTR_TYPE type; // 0x08: u8 is_dirty_pages; // 0x0C: u8 is_attr_name; // 0x0B: Faked field to manage 'ptr' u8 name_len; // 0x0C: Faked field to manage 'ptr' u8 res; struct MFT_REF ref; // 0x10: File Reference of file containing attribute __le64 open_record_lsn; // 0x18: void *ptr; // 0x20: }; /* 32 bit version of 'struct OPEN_ATTR_ENRTY' */ struct OPEN_ATTR_ENRTY_32 { __le32 next; // 0x00: RESTART_ENTRY_ALLOCATED if allocated __le32 ptr; // 0x04: struct MFT_REF ref; // 0x08: __le64 open_record_lsn; // 0x10: u8 is_dirty_pages; // 0x18: u8 is_attr_name; // 0x19: u8 res1[2]; enum ATTR_TYPE type; // 0x1C: u8 name_len; // 0x20: In wchar u8 res2[3]; __le32 AttributeName; // 0x24: __le32 bytes_per_index; // 0x28: }; #define SIZEOF_OPENATTRIBUTEENTRY0 0x2c // static_assert( 0x2C == sizeof(struct OPEN_ATTR_ENRTY_32) ); static_assert(sizeof(struct OPEN_ATTR_ENRTY) < SIZEOF_OPENATTRIBUTEENTRY0); /* * One entry exists in the Dirty Pages Table for each page which is dirty at * the time the Restart Area is written. */ struct DIR_PAGE_ENTRY { __le32 next; // 0x00: RESTART_ENTRY_ALLOCATED if allocated __le32 target_attr; // 0x04: Index into the Open attribute Table __le32 transfer_len; // 0x08: __le32 lcns_follow; // 0x0C: __le64 vcn; // 0x10: Vcn of dirty page __le64 oldest_lsn; // 0x18: __le64 page_lcns[]; // 0x20: }; static_assert(sizeof(struct DIR_PAGE_ENTRY) == 0x20); /* 32 bit version of 'struct DIR_PAGE_ENTRY' */ struct DIR_PAGE_ENTRY_32 { __le32 next; // 0x00: RESTART_ENTRY_ALLOCATED if allocated __le32 target_attr; // 0x04: Index into the Open attribute Table __le32 transfer_len; // 0x08: __le32 lcns_follow; // 0x0C: __le32 reserved; // 0x10: __le32 vcn_low; // 0x14: Vcn of dirty page __le32 vcn_hi; // 0x18: Vcn of dirty page __le32 oldest_lsn_low; // 0x1C: __le32 oldest_lsn_hi; // 0x1C: __le32 page_lcns_low; // 0x24: __le32 page_lcns_hi; // 0x24: }; static_assert(offsetof(struct DIR_PAGE_ENTRY_32, vcn_low) == 0x14); static_assert(sizeof(struct DIR_PAGE_ENTRY_32) == 0x2c); enum transact_state { TransactionUninitialized = 0, TransactionActive, TransactionPrepared, TransactionCommitted }; struct TRANSACTION_ENTRY { __le32 next; // 0x00: RESTART_ENTRY_ALLOCATED if allocated u8 transact_state; // 0x04: u8 reserved[3]; // 0x05: __le64 first_lsn; // 0x08: __le64 prev_lsn; // 0x10: __le64 undo_next_lsn; // 0x18: __le32 undo_records; // 0x20: Number of undo log records pending abort __le32 undo_len; // 0x24: Total undo size }; static_assert(sizeof(struct TRANSACTION_ENTRY) == 0x28); struct NTFS_RESTART { __le32 major_ver; // 0x00: __le32 minor_ver; // 0x04: __le64 check_point_start; // 0x08: __le64 open_attr_table_lsn; // 0x10: __le64 attr_names_lsn; // 0x18: __le64 dirty_pages_table_lsn; // 0x20: __le64 transact_table_lsn; // 0x28: __le32 open_attr_len; // 0x30: In bytes __le32 attr_names_len; // 0x34: In bytes __le32 dirty_pages_len; // 0x38: In bytes __le32 transact_table_len; // 0x3C: In bytes }; static_assert(sizeof(struct NTFS_RESTART) == 0x40); struct NEW_ATTRIBUTE_SIZES { __le64 alloc_size; __le64 valid_size; __le64 data_size; __le64 total_size; }; struct BITMAP_RANGE { __le32 bitmap_off; __le32 bits; }; struct LCN_RANGE { __le64 lcn; __le64 len; }; /* The following type defines the different log record types. */ #define LfsClientRecord cpu_to_le32(1) #define LfsClientRestart cpu_to_le32(2) /* This is used to uniquely identify a client for a particular log file. */ struct CLIENT_ID { __le16 seq_num; __le16 client_idx; }; /* This is the header that begins every Log Record in the log file. */ struct LFS_RECORD_HDR { __le64 this_lsn; // 0x00: __le64 client_prev_lsn; // 0x08: __le64 client_undo_next_lsn; // 0x10: __le32 client_data_len; // 0x18: struct CLIENT_ID client; // 0x1C: Owner of this log record. __le32 record_type; // 0x20: LfsClientRecord or LfsClientRestart. __le32 transact_id; // 0x24: __le16 flags; // 0x28: LOG_RECORD_MULTI_PAGE u8 align[6]; // 0x2A: }; #define LOG_RECORD_MULTI_PAGE cpu_to_le16(1) static_assert(sizeof(struct LFS_RECORD_HDR) == 0x30); struct LFS_RECORD { __le16 next_record_off; // 0x00: Offset of the free space in the page, u8 align[6]; // 0x02: __le64 last_end_lsn; // 0x08: lsn for the last log record which ends on the page, }; static_assert(sizeof(struct LFS_RECORD) == 0x10); struct RECORD_PAGE_HDR { struct NTFS_RECORD_HEADER rhdr; // 'RCRD' __le32 rflags; // 0x10: See LOG_PAGE_LOG_RECORD_END __le16 page_count; // 0x14: __le16 page_pos; // 0x16: struct LFS_RECORD record_hdr; // 0x18: __le16 fixups[10]; // 0x28: __le32 file_off; // 0x3c: Used when major version >= 2 }; // clang-format on // Page contains the end of a log record. #define LOG_PAGE_LOG_RECORD_END cpu_to_le32(0x00000001) static inline bool is_log_record_end(const struct RECORD_PAGE_HDR *hdr) { return hdr->rflags & LOG_PAGE_LOG_RECORD_END; } static_assert(offsetof(struct RECORD_PAGE_HDR, file_off) == 0x3c); /* * END of NTFS LOG structures */ /* Define some tuning parameters to keep the restart tables a reasonable size. */ #define INITIAL_NUMBER_TRANSACTIONS 5 enum NTFS_LOG_OPERATION { Noop = 0x00, CompensationLogRecord = 0x01, InitializeFileRecordSegment = 0x02, DeallocateFileRecordSegment = 0x03, WriteEndOfFileRecordSegment = 0x04, CreateAttribute = 0x05, DeleteAttribute = 0x06, UpdateResidentValue = 0x07, UpdateNonresidentValue = 0x08, UpdateMappingPairs = 0x09, DeleteDirtyClusters = 0x0A, SetNewAttributeSizes = 0x0B, AddIndexEntryRoot = 0x0C, DeleteIndexEntryRoot = 0x0D, AddIndexEntryAllocation = 0x0E, DeleteIndexEntryAllocation = 0x0F, WriteEndOfIndexBuffer = 0x10, SetIndexEntryVcnRoot = 0x11, SetIndexEntryVcnAllocation = 0x12, UpdateFileNameRoot = 0x13, UpdateFileNameAllocation = 0x14, SetBitsInNonresidentBitMap = 0x15, ClearBitsInNonresidentBitMap = 0x16, HotFix = 0x17, EndTopLevelAction = 0x18, PrepareTransaction = 0x19, CommitTransaction = 0x1A, ForgetTransaction = 0x1B, OpenNonresidentAttribute = 0x1C, OpenAttributeTableDump = 0x1D, AttributeNamesDump = 0x1E, DirtyPageTableDump = 0x1F, TransactionTableDump = 0x20, UpdateRecordDataRoot = 0x21, UpdateRecordDataAllocation = 0x22, UpdateRelativeDataInIndex = 0x23, // NtOfsRestartUpdateRelativeDataInIndex UpdateRelativeDataInIndex2 = 0x24, ZeroEndOfFileRecord = 0x25, }; /* * Array for log records which require a target attribute. * A true indicates that the corresponding restart operation * requires a target attribute. */ static const u8 AttributeRequired[] = { 0xFC, 0xFB, 0xFF, 0x10, 0x06, }; static inline bool is_target_required(u16 op) { bool ret = op <= UpdateRecordDataAllocation && (AttributeRequired[op >> 3] >> (op & 7) & 1); return ret; } static inline bool can_skip_action(enum NTFS_LOG_OPERATION op) { switch (op) { case Noop: case DeleteDirtyClusters: case HotFix: case EndTopLevelAction: case PrepareTransaction: case CommitTransaction: case ForgetTransaction: case CompensationLogRecord: case OpenNonresidentAttribute: case OpenAttributeTableDump: case AttributeNamesDump: case DirtyPageTableDump: case TransactionTableDump: return true; default: return false; } } enum { lcb_ctx_undo_next, lcb_ctx_prev, lcb_ctx_next }; /* Bytes per restart table. */ static inline u32 bytes_per_rt(const struct RESTART_TABLE *rt) { return le16_to_cpu(rt->used) * le16_to_cpu(rt->size) + sizeof(struct RESTART_TABLE); } /* Log record length. */ static inline u32 lrh_length(const struct LOG_REC_HDR *lr) { u16 t16 = le16_to_cpu(lr->lcns_follow); return struct_size(lr, page_lcns, max_t(u16, 1, t16)); } struct lcb { struct LFS_RECORD_HDR *lrh; // Log record header of the current lsn. struct LOG_REC_HDR *log_rec; u32 ctx_mode; // lcb_ctx_undo_next/lcb_ctx_prev/lcb_ctx_next struct CLIENT_ID client; bool alloc; // If true the we should deallocate 'log_rec'. }; static void lcb_put(struct lcb *lcb) { if (lcb->alloc) kfree(lcb->log_rec); kfree(lcb->lrh); kfree(lcb); } /* Find the oldest lsn from active clients. */ static inline void oldest_client_lsn(const struct CLIENT_REC *ca, __le16 next_client, u64 *oldest_lsn) { while (next_client != LFS_NO_CLIENT_LE) { const struct CLIENT_REC *cr = ca + le16_to_cpu(next_client); u64 lsn = le64_to_cpu(cr->oldest_lsn); /* Ignore this block if it's oldest lsn is 0. */ if (lsn && lsn < *oldest_lsn) *oldest_lsn = lsn; next_client = cr->next_client; } } static inline bool is_rst_page_hdr_valid(u32 file_off, const struct RESTART_HDR *rhdr) { u32 sys_page = le32_to_cpu(rhdr->sys_page_size); u32 page_size = le32_to_cpu(rhdr->page_size); u32 end_usa; u16 ro; if (sys_page < SECTOR_SIZE || page_size < SECTOR_SIZE || sys_page & (sys_page - 1) || page_size & (page_size - 1)) { return false; } /* Check that if the file offset isn't 0, it is the system page size. */ if (file_off && file_off != sys_page) return false; /* Check support version 1.1+. */ if (le16_to_cpu(rhdr->major_ver) <= 1 && !rhdr->minor_ver) return false; if (le16_to_cpu(rhdr->major_ver) > 2) return false; ro = le16_to_cpu(rhdr->ra_off); if (!IS_ALIGNED(ro, 8) || ro > sys_page) return false; end_usa = ((sys_page >> SECTOR_SHIFT) + 1) * sizeof(short); end_usa += le16_to_cpu(rhdr->rhdr.fix_off); if (ro < end_usa) return false; return true; } static inline bool is_rst_area_valid(const struct RESTART_HDR *rhdr) { const struct RESTART_AREA *ra; u16 cl, fl, ul; u32 off, l_size, seq_bits; u16 ro = le16_to_cpu(rhdr->ra_off); u32 sys_page = le32_to_cpu(rhdr->sys_page_size); if (ro + offsetof(struct RESTART_AREA, l_size) > SECTOR_SIZE - sizeof(short)) return false; ra = Add2Ptr(rhdr, ro); cl = le16_to_cpu(ra->log_clients); if (cl > 1) return false; off = le16_to_cpu(ra->client_off); if (!IS_ALIGNED(off, 8) || ro + off > SECTOR_SIZE - sizeof(short)) return false; off += cl * sizeof(struct CLIENT_REC); if (off > sys_page) return false; /* * Check the restart length field and whether the entire * restart area is contained that length. */ if (le16_to_cpu(rhdr->ra_off) + le16_to_cpu(ra->ra_len) > sys_page || off > le16_to_cpu(ra->ra_len)) { return false; } /* * As a final check make sure that the use list and the free list * are either empty or point to a valid client. */ fl = le16_to_cpu(ra->client_idx[0]); ul = le16_to_cpu(ra->client_idx[1]); if ((fl != LFS_NO_CLIENT && fl >= cl) || (ul != LFS_NO_CLIENT && ul >= cl)) return false; /* Make sure the sequence number bits match the log file size. */ l_size = le64_to_cpu(ra->l_size); seq_bits = sizeof(u64) * 8 + 3; while (l_size) { l_size >>= 1; seq_bits -= 1; } if (seq_bits != le32_to_cpu(ra->seq_num_bits)) return false; /* The log page data offset and record header length must be quad-aligned. */ if (!IS_ALIGNED(le16_to_cpu(ra->data_off), 8) || !IS_ALIGNED(le16_to_cpu(ra->rec_hdr_len), 8)) return false; return true; } static inline bool is_client_area_valid(const struct RESTART_HDR *rhdr, bool usa_error) { u16 ro = le16_to_cpu(rhdr->ra_off); const struct RESTART_AREA *ra = Add2Ptr(rhdr, ro); u16 ra_len = le16_to_cpu(ra->ra_len); const struct CLIENT_REC *ca; u32 i; if (usa_error && ra_len + ro > SECTOR_SIZE - sizeof(short)) return false; /* Find the start of the client array. */ ca = Add2Ptr(ra, le16_to_cpu(ra->client_off)); /* * Start with the free list. * Check that all the clients are valid and that there isn't a cycle. * Do the in-use list on the second pass. */ for (i = 0; i < 2; i++) { u16 client_idx = le16_to_cpu(ra->client_idx[i]); bool first_client = true; u16 clients = le16_to_cpu(ra->log_clients); while (client_idx != LFS_NO_CLIENT) { const struct CLIENT_REC *cr; if (!clients || client_idx >= le16_to_cpu(ra->log_clients)) return false; clients -= 1; cr = ca + client_idx; client_idx = le16_to_cpu(cr->next_client); if (first_client) { first_client = false; if (cr->prev_client != LFS_NO_CLIENT_LE) return false; } } } return true; } /* * remove_client * * Remove a client record from a client record list an restart area. */ static inline void remove_client(struct CLIENT_REC *ca, const struct CLIENT_REC *cr, __le16 *head) { if (cr->prev_client == LFS_NO_CLIENT_LE) *head = cr->next_client; else ca[le16_to_cpu(cr->prev_client)].next_client = cr->next_client; if (cr->next_client != LFS_NO_CLIENT_LE) ca[le16_to_cpu(cr->next_client)].prev_client = cr->prev_client; } /* * add_client - Add a client record to the start of a list. */ static inline void add_client(struct CLIENT_REC *ca, u16 index, __le16 *head) { struct CLIENT_REC *cr = ca + index; cr->prev_client = LFS_NO_CLIENT_LE; cr->next_client = *head; if (*head != LFS_NO_CLIENT_LE) ca[le16_to_cpu(*head)].prev_client = cpu_to_le16(index); *head = cpu_to_le16(index); } /* * Enumerate restart table. * * @t - table to enumerate. * @c - current enumerated element. * * enumeration starts with @c == NULL * returns next element or NULL */ static inline void *enum_rstbl(struct RESTART_TABLE *t, void *c) { __le32 *e; u32 bprt; u16 rsize; if (!t) return NULL; rsize = le16_to_cpu(t->size); if (!c) { /* start enumeration. */ if (!t->total) return NULL; e = Add2Ptr(t, sizeof(struct RESTART_TABLE)); } else { e = Add2Ptr(c, rsize); } /* Loop until we hit the first one allocated, or the end of the list. */ for (bprt = bytes_per_rt(t); PtrOffset(t, e) < bprt; e = Add2Ptr(e, rsize)) { if (*e == RESTART_ENTRY_ALLOCATED_LE) return e; } return NULL; } /* * find_dp - Search for a @vcn in Dirty Page Table. */ static inline struct DIR_PAGE_ENTRY *find_dp(struct RESTART_TABLE *dptbl, u32 target_attr, u64 vcn) { __le32 ta = cpu_to_le32(target_attr); struct DIR_PAGE_ENTRY *dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { u64 dp_vcn = le64_to_cpu(dp->vcn); if (dp->target_attr == ta && vcn >= dp_vcn && vcn < dp_vcn + le32_to_cpu(dp->lcns_follow)) { return dp; } } return NULL; } static inline u32 norm_file_page(u32 page_size, u32 *l_size, bool use_default) { if (use_default) page_size = DefaultLogPageSize; /* Round the file size down to a system page boundary. */ *l_size &= ~(page_size - 1); /* File should contain at least 2 restart pages and MinLogRecordPages pages. */ if (*l_size < (MinLogRecordPages + 2) * page_size) return 0; return page_size; } static bool check_log_rec(const struct LOG_REC_HDR *lr, u32 bytes, u32 tr, u32 bytes_per_attr_entry) { u16 t16; if (bytes < sizeof(struct LOG_REC_HDR)) return false; if (!tr) return false; if ((tr - sizeof(struct RESTART_TABLE)) % sizeof(struct TRANSACTION_ENTRY)) return false; if (le16_to_cpu(lr->redo_off) & 7) return false; if (le16_to_cpu(lr->undo_off) & 7) return false; if (lr->target_attr) goto check_lcns; if (is_target_required(le16_to_cpu(lr->redo_op))) return false; if (is_target_required(le16_to_cpu(lr->undo_op))) return false; check_lcns: if (!lr->lcns_follow) goto check_length; t16 = le16_to_cpu(lr->target_attr); if ((t16 - sizeof(struct RESTART_TABLE)) % bytes_per_attr_entry) return false; check_length: if (bytes < lrh_length(lr)) return false; return true; } static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes) { u32 ts; u32 i, off; u16 rsize = le16_to_cpu(rt->size); u16 ne = le16_to_cpu(rt->used); u32 ff = le32_to_cpu(rt->first_free); u32 lf = le32_to_cpu(rt->last_free); ts = rsize * ne + sizeof(struct RESTART_TABLE); if (!rsize || rsize > bytes || rsize + sizeof(struct RESTART_TABLE) > bytes || bytes < ts || le16_to_cpu(rt->total) > ne || ff > ts - sizeof(__le32) || lf > ts - sizeof(__le32) || (ff && ff < sizeof(struct RESTART_TABLE)) || (lf && lf < sizeof(struct RESTART_TABLE))) { return false; } /* * Verify each entry is either allocated or points * to a valid offset the table. */ for (i = 0; i < ne; i++) { off = le32_to_cpu(*(__le32 *)Add2Ptr( rt, i * rsize + sizeof(struct RESTART_TABLE))); if (off != RESTART_ENTRY_ALLOCATED && off && (off < sizeof(struct RESTART_TABLE) || ((off - sizeof(struct RESTART_TABLE)) % rsize))) { return false; } } /* * Walk through the list headed by the first entry to make * sure none of the entries are currently being used. * * Bound traversal by ne (rt->used) to defeat a crafted on-disk * cycle in the free chain. Each entry in a legitimate free * list is unique, so a chain that visits more than ne slots * is malformed. Without this guard, an attacker-controlled * RESTART_TABLE with a self-loop or A->B->A cycle whose * offsets satisfy the existing alignment + in-bounds guards * spins forever at mount time. */ for (off = ff, i = 0; off; i++) { if (i > ne) return false; if (off == RESTART_ENTRY_ALLOCATED) return false; off = le32_to_cpu(*(__le32 *)Add2Ptr(rt, off)); if (off > ts - sizeof(__le32)) return false; } return true; } /* * free_rsttbl_idx - Free a previously allocated index a Restart Table. */ static inline void free_rsttbl_idx(struct RESTART_TABLE *rt, u32 off) { __le32 *e; u32 lf = le32_to_cpu(rt->last_free); __le32 off_le = cpu_to_le32(off); e = Add2Ptr(rt, off); if (off < le32_to_cpu(rt->free_goal)) { *e = rt->first_free; rt->first_free = off_le; if (!lf) rt->last_free = off_le; } else { if (lf) *(__le32 *)Add2Ptr(rt, lf) = off_le; else rt->first_free = off_le; rt->last_free = off_le; *e = 0; } le16_sub_cpu(&rt->total, 1); } static inline struct RESTART_TABLE *init_rsttbl(u16 esize, u16 used) { __le32 *e, *last_free; u32 off; u32 bytes = esize * used + sizeof(struct RESTART_TABLE); u32 lf = sizeof(struct RESTART_TABLE) + (used - 1) * esize; struct RESTART_TABLE *t = kzalloc(bytes, GFP_NOFS); if (!t) return NULL; t->size = cpu_to_le16(esize); t->used = cpu_to_le16(used); t->free_goal = cpu_to_le32(~0u); t->first_free = cpu_to_le32(sizeof(struct RESTART_TABLE)); t->last_free = cpu_to_le32(lf); e = (__le32 *)(t + 1); last_free = Add2Ptr(t, lf); for (off = sizeof(struct RESTART_TABLE) + esize; e < last_free; e = Add2Ptr(e, esize), off += esize) { *e = cpu_to_le32(off); } return t; } static inline struct RESTART_TABLE *extend_rsttbl(struct RESTART_TABLE *tbl, u32 add, u32 free_goal) { u16 esize = le16_to_cpu(tbl->size); __le32 osize = cpu_to_le32(bytes_per_rt(tbl)); u32 used = le16_to_cpu(tbl->used); struct RESTART_TABLE *rt; rt = init_rsttbl(esize, used + add); if (!rt) return NULL; memcpy(rt + 1, tbl + 1, esize * used); rt->free_goal = free_goal == ~0u ? cpu_to_le32(~0u) : cpu_to_le32(sizeof(struct RESTART_TABLE) + free_goal * esize); if (tbl->first_free) { rt->first_free = tbl->first_free; *(__le32 *)Add2Ptr(rt, le32_to_cpu(tbl->last_free)) = osize; } else { rt->first_free = osize; } rt->total = tbl->total; kfree(tbl); return rt; } /* * alloc_rsttbl_idx * * Allocate an index from within a previously initialized Restart Table. */ static inline void *alloc_rsttbl_idx(struct RESTART_TABLE **tbl) { u32 off; __le32 *e; struct RESTART_TABLE *t = *tbl; if (!t->first_free) { *tbl = t = extend_rsttbl(t, 16, ~0u); if (!t) return NULL; } off = le32_to_cpu(t->first_free); /* Dequeue this entry and zero it. */ e = Add2Ptr(t, off); t->first_free = *e; memset(e, 0, le16_to_cpu(t->size)); *e = RESTART_ENTRY_ALLOCATED_LE; /* If list is going empty, then we fix the last_free as well. */ if (!t->first_free) t->last_free = 0; le16_add_cpu(&t->total, 1); return Add2Ptr(t, off); } /* * alloc_rsttbl_from_idx * * Allocate a specific index from within a previously initialized Restart Table. */ static inline void *alloc_rsttbl_from_idx(struct RESTART_TABLE **tbl, u32 vbo) { u32 off; __le32 *e; struct RESTART_TABLE *rt = *tbl; u32 bytes = bytes_per_rt(rt); u16 esize = le16_to_cpu(rt->size); /* If the entry is not the table, we will have to extend the table. */ if (vbo >= bytes) { /* * Extend the size by computing the number of entries between * the existing size and the desired index and adding 1 to that. */ u32 bytes2idx = vbo - bytes; /* * There should always be an integral number of entries * being added. Now extend the table. */ *tbl = rt = extend_rsttbl(rt, bytes2idx / esize + 1, bytes); if (!rt) return NULL; } /* See if the entry is already allocated, and just return if it is. */ e = Add2Ptr(rt, vbo); if (*e == RESTART_ENTRY_ALLOCATED_LE) return e; /* * Walk through the table, looking for the entry we're * interested and the previous entry. */ off = le32_to_cpu(rt->first_free); e = Add2Ptr(rt, off); if (off == vbo) { /* this is a match */ rt->first_free = *e; goto skip_looking; } /* * Need to walk through the list looking for the predecessor * of our entry. */ for (;;) { /* Remember the entry just found */ u32 last_off = off; __le32 *last_e = e; /* Should never run of entries. */ /* Lookup up the next entry the list. */ off = le32_to_cpu(*last_e); e = Add2Ptr(rt, off); /* If this is our match we are done. */ if (off == vbo) { *last_e = *e; /* * If this was the last entry, we update that * table as well. */ if (le32_to_cpu(rt->last_free) == off) rt->last_free = cpu_to_le32(last_off); break; } } skip_looking: /* If the list is now empty, we fix the last_free as well. */ if (!rt->first_free) rt->last_free = 0; /* Zero this entry. */ memset(e, 0, esize); *e = RESTART_ENTRY_ALLOCATED_LE; le16_add_cpu(&rt->total, 1); return e; } struct restart_info { u64 last_lsn; struct RESTART_HDR *r_page; u32 vbo; bool chkdsk_was_run; bool valid_page; bool initialized; bool restart; }; #define RESTART_SINGLE_PAGE_IO cpu_to_le16(0x0001) #define NTFSLOG_WRAPPED 0x00000001 #define NTFSLOG_MULTIPLE_PAGE_IO 0x00000002 #define NTFSLOG_NO_LAST_LSN 0x00000004 #define NTFSLOG_REUSE_TAIL 0x00000010 #define NTFSLOG_NO_OLDEST_LSN 0x00000020 /* Helper struct to work with NTFS $LogFile. */ struct ntfs_log { struct ntfs_inode *ni; u32 l_size; u32 orig_file_size; u32 sys_page_size; u32 sys_page_mask; u32 page_size; u32 page_mask; // page_size - 1 u8 page_bits; struct RECORD_PAGE_HDR *one_page_buf; struct RESTART_TABLE *open_attr_tbl; u32 transaction_id; u32 clst_per_page; u32 first_page; u32 next_page; u32 ra_off; u32 data_off; u32 restart_size; u32 data_size; u16 record_header_len; u64 seq_num; u32 seq_num_bits; u32 file_data_bits; u32 seq_num_mask; /* (1 << file_data_bits) - 1 */ struct RESTART_AREA *ra; /* In-memory image of the next restart area. */ u32 ra_size; /* The usable size of the restart area. */ /* * If true, then the in-memory restart area is to be written * to the first position on the disk. */ bool init_ra; bool set_dirty; /* True if we need to set dirty flag. */ u64 oldest_lsn; u32 oldest_lsn_off; u64 last_lsn; u32 total_avail; u32 total_avail_pages; u32 total_undo_commit; u32 max_current_avail; u32 current_avail; u32 reserved; short major_ver; short minor_ver; u32 l_flags; /* See NTFSLOG_XXX */ u32 current_openlog_count; /* On-disk value for open_log_count. */ struct CLIENT_ID client_id; u32 client_undo_commit; struct restart_info rst_info, rst_info2; struct file_ra_state read_ahead; }; static inline u32 lsn_to_vbo(struct ntfs_log *log, const u64 lsn) { u32 vbo = (lsn << log->seq_num_bits) >> (log->seq_num_bits - 3); return vbo; } /* Compute the offset in the log file of the next log page. */ static inline u32 next_page_off(struct ntfs_log *log, u32 off) { off = (off & ~log->sys_page_mask) + log->page_size; return off >= log->l_size ? log->first_page : off; } static inline u32 lsn_to_page_off(struct ntfs_log *log, u64 lsn) { return (((u32)lsn) << 3) & log->page_mask; } static inline u64 vbo_to_lsn(struct ntfs_log *log, u32 off, u64 Seq) { return (off >> 3) + (Seq << log->file_data_bits); } static inline bool is_lsn_in_file(struct ntfs_log *log, u64 lsn) { return lsn >= log->oldest_lsn && lsn <= le64_to_cpu(log->ra->current_lsn); } static inline u32 hdr_file_off(struct ntfs_log *log, struct RECORD_PAGE_HDR *hdr) { if (log->major_ver < 2) return le64_to_cpu(hdr->rhdr.lsn); return le32_to_cpu(hdr->file_off); } static inline u64 base_lsn(struct ntfs_log *log, const struct RECORD_PAGE_HDR *hdr, u64 lsn) { u64 h_lsn = le64_to_cpu(hdr->rhdr.lsn); u64 ret = (((h_lsn >> log->file_data_bits) + (lsn < (lsn_to_vbo(log, h_lsn) & ~log->page_mask) ? 1 : 0)) << log->file_data_bits) + ((((is_log_record_end(hdr) && h_lsn <= le64_to_cpu(hdr->record_hdr.last_end_lsn)) ? le16_to_cpu(hdr->record_hdr.next_record_off) : log->page_size) + lsn) >> 3); return ret; } static inline bool verify_client_lsn(struct ntfs_log *log, const struct CLIENT_REC *client, u64 lsn) { return lsn >= le64_to_cpu(client->oldest_lsn) && lsn <= le64_to_cpu(log->ra->current_lsn) && lsn; } static int read_log_page(struct ntfs_log *log, u32 vbo, struct RECORD_PAGE_HDR **buffer, bool *usa_error) { int err = 0; u32 page_idx = vbo >> log->page_bits; u32 page_off = vbo & log->page_mask; u32 bytes = log->page_size - page_off; void *to_free = NULL; u32 page_vbo = page_idx << log->page_bits; struct RECORD_PAGE_HDR *page_buf; struct ntfs_inode *ni = log->ni; bool bBAAD; if (vbo >= log->l_size) return -EINVAL; if (!*buffer) { to_free = kmalloc(log->page_size, GFP_NOFS); if (!to_free) return -ENOMEM; *buffer = to_free; } page_buf = page_off ? log->one_page_buf : *buffer; err = ntfs_read_run_nb_ra(ni->mi.sbi, &ni->file.run, page_vbo, page_buf, log->page_size, NULL, &log->read_ahead); if (err) goto out; if (page_buf->rhdr.sign != NTFS_FFFF_SIGNATURE) ntfs_fix_post_read(&page_buf->rhdr, log->page_size, false); if (page_buf != *buffer) memcpy(*buffer, Add2Ptr(page_buf, page_off), bytes); bBAAD = page_buf->rhdr.sign == NTFS_BAAD_SIGNATURE; if (usa_error) *usa_error = bBAAD; /* Check that the update sequence array for this page is valid */ /* If we don't allow errors, raise an error status */ else if (bBAAD) err = -EINVAL; out: if (err && to_free) { kfree(to_free); *buffer = NULL; } return err; } /* * log_read_rst * * It walks through 512 blocks of the file looking for a valid * restart page header. It will stop the first time we find a * valid page header. */ static int log_read_rst(struct ntfs_log *log, bool first, struct restart_info *info) { u32 skip; u64 vbo; struct RESTART_HDR *r_page = NULL; /* Determine which restart area we are looking for. */ if (first) { vbo = 0; skip = 512; } else { vbo = 512; skip = 0; } /* Loop continuously until we succeed. */ for (; vbo < log->l_size; vbo = 2 * vbo + skip, skip = 0) { bool usa_error; bool brst, bchk; struct RESTART_AREA *ra; /* Read a page header at the current offset. */ if (read_log_page(log, vbo, (struct RECORD_PAGE_HDR **)&r_page, &usa_error)) { /* Ignore any errors. */ continue; } /* Exit if the signature is a log record page. */ if (r_page->rhdr.sign == NTFS_RCRD_SIGNATURE) { info->initialized = true; break; } brst = r_page->rhdr.sign == NTFS_RSTR_SIGNATURE; bchk = r_page->rhdr.sign == NTFS_CHKD_SIGNATURE; if (!bchk && !brst) { if (r_page->rhdr.sign != NTFS_FFFF_SIGNATURE) { /* * Remember if the signature does not * indicate uninitialized file. */ info->initialized = true; } continue; } ra = NULL; info->valid_page = false; info->initialized = true; info->vbo = vbo; /* Let's check the restart area if this is a valid page. */ if (!is_rst_page_hdr_valid(vbo, r_page)) goto check_result; ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off)); if (!is_rst_area_valid(r_page)) goto check_result; /* * We have a valid restart page header and restart area. * If chkdsk was run or we have no clients then we have * no more checking to do. */ if (bchk || ra->client_idx[1] == LFS_NO_CLIENT_LE) { info->valid_page = true; goto check_result; } if (is_client_area_valid(r_page, usa_error)) { info->valid_page = true; ra = Add2Ptr(r_page, le16_to_cpu(r_page->ra_off)); } check_result: /* * If chkdsk was run then update the caller's * values and return. */ if (r_page->rhdr.sign == NTFS_CHKD_SIGNATURE) { info->chkdsk_was_run = true; info->last_lsn = le64_to_cpu(r_page->rhdr.lsn); info->restart = true; info->r_page = r_page; return 0; } /* * If we have a valid page then copy the values * we need from it. */ if (info->valid_page) { info->last_lsn = le64_to_cpu(ra->current_lsn); info->restart = true; info->r_page = r_page; return 0; } } kfree(r_page); return 0; } /* * Ilog_init_pg_hdr - Init @log from restart page header. */ static void log_init_pg_hdr(struct ntfs_log *log, u16 major_ver, u16 minor_ver) { log->sys_page_size = log->page_size; log->sys_page_mask = log->page_mask; log->clst_per_page = log->page_size >> log->ni->mi.sbi->cluster_bits; if (!log->clst_per_page) log->clst_per_page = 1; log->first_page = major_ver >= 2 ? 0x22 * log->page_size : 4 * log->page_size; log->major_ver = major_ver; log->minor_ver = minor_ver; } /* * log_create - Init @log in cases when we don't have a restart area to use. */ static void log_create(struct ntfs_log *log, const u64 last_lsn, u32 open_log_count, bool wrapped, bool use_multi_page) { /* All file offsets must be quadword aligned. */ log->file_data_bits = blksize_bits(log->l_size) - 3; log->seq_num_mask = (8 << log->file_data_bits) - 1; log->seq_num_bits = sizeof(u64) * 8 - log->file_data_bits; log->seq_num = (last_lsn >> log->file_data_bits) + 2; log->next_page = log->first_page; log->oldest_lsn = log->seq_num << log->file_data_bits; log->oldest_lsn_off = 0; log->last_lsn = log->oldest_lsn; log->l_flags |= NTFSLOG_NO_LAST_LSN | NTFSLOG_NO_OLDEST_LSN; /* Set the correct flags for the I/O and indicate if we have wrapped. */ if (wrapped) log->l_flags |= NTFSLOG_WRAPPED; if (use_multi_page) log->l_flags |= NTFSLOG_MULTIPLE_PAGE_IO; /* Compute the log page values. */ log->data_off = ALIGN( offsetof(struct RECORD_PAGE_HDR, fixups) + sizeof(short) * ((log->page_size >> SECTOR_SHIFT) + 1), 8); log->data_size = log->page_size - log->data_off; log->record_header_len = sizeof(struct LFS_RECORD_HDR); /* Remember the different page sizes for reservation. */ log->reserved = log->data_size - log->record_header_len; /* Compute the restart page values. */ log->ra_off = ALIGN( offsetof(struct RESTART_HDR, fixups) + sizeof(short) * ((log->sys_page_size >> SECTOR_SHIFT) + 1), 8); log->restart_size = log->sys_page_size - log->ra_off; log->ra_size = struct_size(log->ra, clients, 1); log->current_openlog_count = open_log_count; /* * The total available log file space is the number of * log file pages times the space available on each page. */ log->total_avail_pages = log->l_size - log->first_page; log->total_avail = log->total_avail_pages >> log->page_bits; /* * We assume that we can't use the end of the page less than * the file record size. * Then we won't need to reserve more than the caller asks for. */ log->max_current_avail = log->total_avail * log->reserved; log->total_avail = log->total_avail * log->data_size; log->current_avail = log->max_current_avail; } /* * log_create_ra - Fill a restart area from the values stored in @log. */ static struct RESTART_AREA *log_create_ra(struct ntfs_log *log) { struct CLIENT_REC *cr; struct RESTART_AREA *ra = kzalloc(log->restart_size, GFP_NOFS); if (!ra) return NULL; ra->current_lsn = cpu_to_le64(log->last_lsn); ra->log_clients = cpu_to_le16(1); ra->client_idx[1] = LFS_NO_CLIENT_LE; if (log->l_flags & NTFSLOG_MULTIPLE_PAGE_IO) ra->flags = RESTART_SINGLE_PAGE_IO; ra->seq_num_bits = cpu_to_le32(log->seq_num_bits); ra->ra_len = cpu_to_le16(log->ra_size); ra->client_off = cpu_to_le16(offsetof(struct RESTART_AREA, clients)); ra->l_size = cpu_to_le64(log->l_size); ra->rec_hdr_len = cpu_to_le16(log->record_header_len); ra->data_off = cpu_to_le16(log->data_off); ra->open_log_count = cpu_to_le32(log->current_openlog_count + 1); cr = ra->clients; cr->prev_client = LFS_NO_CLIENT_LE; cr->next_client = LFS_NO_CLIENT_LE; return ra; } static u32 final_log_off(struct ntfs_log *log, u64 lsn, u32 data_len) { u32 base_vbo = lsn << 3; u32 final_log_off = (base_vbo & log->seq_num_mask) & ~log->page_mask; u32 page_off = base_vbo & log->page_mask; u32 tail = log->page_size - page_off; page_off -= 1; /* Add the length of the header. */ data_len += log->record_header_len; /* * If this lsn is contained this log page we are done. * Otherwise we need to walk through several log pages. */ if (data_len > tail) { data_len -= tail; tail = log->data_size; page_off = log->data_off - 1; for (;;) { final_log_off = next_page_off(log, final_log_off); /* * We are done if the remaining bytes * fit on this page. */ if (data_len <= tail) break; data_len -= tail; } } /* * We add the remaining bytes to our starting position on this page * and then add that value to the file offset of this log page. */ return final_log_off + data_len + page_off; } static int next_log_lsn(struct ntfs_log *log, const struct LFS_RECORD_HDR *rh, u64 *lsn) { int err; u64 this_lsn = le64_to_cpu(rh->this_lsn); u32 vbo = lsn_to_vbo(log, this_lsn); u32 end = final_log_off(log, this_lsn, le32_to_cpu(rh->client_data_len)); u32 hdr_off = end & ~log->sys_page_mask; u64 seq = this_lsn >> log->file_data_bits; struct RECORD_PAGE_HDR *page = NULL; /* Remember if we wrapped. */ if (end <= vbo) seq += 1; /* Log page header for this page. */ err = read_log_page(log, hdr_off, &page, NULL); if (err) return err; /* * If the lsn we were given was not the last lsn on this page, * then the starting offset for the next lsn is on a quad word * boundary following the last file offset for the current lsn. * Otherwise the file offset is the start of the data on the next page. */ if (this_lsn == le64_to_cpu(page->rhdr.lsn)) { /* If we wrapped, we need to increment the sequence number. */ hdr_off = next_page_off(log, hdr_off); if (hdr_off == log->first_page) seq += 1; vbo = hdr_off + log->data_off; } else { vbo = ALIGN(end, 8); } /* Compute the lsn based on the file offset and the sequence count. */ *lsn = vbo_to_lsn(log, vbo, seq); /* * If this lsn is within the legal range for the file, we return true. * Otherwise false indicates that there are no more lsn's. */ if (!is_lsn_in_file(log, *lsn)) *lsn = 0; kfree(page); return 0; } /* * current_log_avail - Calculate the number of bytes available for log records. */ static u32 current_log_avail(struct ntfs_log *log) { u32 oldest_off, next_free_off, free_bytes; if (log->l_flags & NTFSLOG_NO_LAST_LSN) { /* The entire file is available. */ return log->max_current_avail; } /* * If there is a last lsn the restart area then we know that we will * have to compute the free range. * If there is no oldest lsn then start at the first page of the file. */ oldest_off = (log->l_flags & NTFSLOG_NO_OLDEST_LSN) ? log->first_page : (log->oldest_lsn_off & ~log->sys_page_mask); /* * We will use the next log page offset to compute the next free page. * If we are going to reuse this page go to the next page. * If we are at the first page then use the end of the file. */ next_free_off = (log->l_flags & NTFSLOG_REUSE_TAIL) ? log->next_page + log->page_size : log->next_page == log->first_page ? log->l_size : log->next_page; /* If the two offsets are the same then there is no available space. */ if (oldest_off == next_free_off) return 0; /* * If the free offset follows the oldest offset then subtract * this range from the total available pages. */ free_bytes = oldest_off < next_free_off ? log->total_avail_pages - (next_free_off - oldest_off) : oldest_off - next_free_off; free_bytes >>= log->page_bits; return free_bytes * log->reserved; } static bool check_subseq_log_page(struct ntfs_log *log, const struct RECORD_PAGE_HDR *rp, u32 vbo, u64 seq) { u64 lsn_seq; const struct NTFS_RECORD_HEADER *rhdr = &rp->rhdr; u64 lsn = le64_to_cpu(rhdr->lsn); if (rhdr->sign == NTFS_FFFF_SIGNATURE || !rhdr->sign) return false; /* * If the last lsn on the page occurs was written after the page * that caused the original error then we have a fatal error. */ lsn_seq = lsn >> log->file_data_bits; /* * If the sequence number for the lsn the page is equal or greater * than lsn we expect, then this is a subsequent write. */ return lsn_seq >= seq || (lsn_seq == seq - 1 && log->first_page == vbo && vbo != (lsn_to_vbo(log, lsn) & ~log->page_mask)); } /* * last_log_lsn * * Walks through the log pages for a file, searching for the * last log page written to the file. */ static int last_log_lsn(struct ntfs_log *log) { int err; bool usa_error = false; bool replace_page = false; bool reuse_page = log->l_flags & NTFSLOG_REUSE_TAIL; bool wrapped_file, wrapped; u32 page_cnt = 1, page_pos = 1; u32 page_off = 0, page_off1 = 0, saved_off = 0; u32 final_off, second_off, final_off_prev = 0, second_off_prev = 0; u32 first_file_off = 0, second_file_off = 0; u32 part_io_count = 0; u32 tails = 0; u32 this_off, curpage_off, nextpage_off, remain_pages; u64 expected_seq, seq_base = 0, lsn_base = 0; u64 best_lsn, best_lsn1, best_lsn2; u64 lsn_cur, lsn1, lsn2; u64 last_ok_lsn = reuse_page ? log->last_lsn : 0; u16 cur_pos, best_page_pos; struct RECORD_PAGE_HDR *page = NULL; struct RECORD_PAGE_HDR *tst_page = NULL; struct RECORD_PAGE_HDR *first_tail = NULL; struct RECORD_PAGE_HDR *second_tail = NULL; struct RECORD_PAGE_HDR *tail_page = NULL; struct RECORD_PAGE_HDR *second_tail_prev = NULL; struct RECORD_PAGE_HDR *first_tail_prev = NULL; struct RECORD_PAGE_HDR *page_bufs = NULL; struct RECORD_PAGE_HDR *best_page; if (log->major_ver >= 2) { final_off = 0x02 * log->page_size; second_off = 0x12 * log->page_size; // 0x10 == 0x12 - 0x2 page_bufs = kmalloc(log->page_size * 0x10, GFP_NOFS); if (!page_bufs) return -ENOMEM; } else { second_off = log->first_page - log->page_size; final_off = second_off - log->page_size; } next_tail: /* Read second tail page (at pos 3/0x12000). */ if (read_log_page(log, second_off, &second_tail, &usa_error) || usa_error || second_tail->rhdr.sign != NTFS_RCRD_SIGNATURE) { kfree(second_tail); second_tail = NULL; second_file_off = 0; lsn2 = 0; } else { second_file_off = hdr_file_off(log, second_tail); lsn2 = le64_to_cpu(second_tail->record_hdr.last_end_lsn); } /* Read first tail page (at pos 2/0x2000). */ if (read_log_page(log, final_off, &first_tail, &usa_error) || usa_error || first_tail->rhdr.sign != NTFS_RCRD_SIGNATURE) { kfree(first_tail); first_tail = NULL; first_file_off = 0; lsn1 = 0; } else { first_file_off = hdr_file_off(log, first_tail); lsn1 = le64_to_cpu(first_tail->record_hdr.last_end_lsn); } if (log->major_ver < 2) { int best_page; first_tail_prev = first_tail; final_off_prev = first_file_off; second_tail_prev = second_tail; second_off_prev = second_file_off; tails = 1; if (!first_tail && !second_tail) goto tail_read; if (first_tail && second_tail) best_page = lsn1 < lsn2 ? 1 : 0; else if (first_tail) best_page = 0; else best_page = 1; page_off = best_page ? second_file_off : first_file_off; seq_base = (best_page ? lsn2 : lsn1) >> log->file_data_bits; goto tail_read; } best_lsn1 = first_tail ? base_lsn(log, first_tail, first_file_off) : 0; best_lsn2 = second_tail ? base_lsn(log, second_tail, second_file_off) : 0; if (first_tail && second_tail) { if (best_lsn1 > best_lsn2) { best_lsn = best_lsn1; best_page = first_tail; this_off = first_file_off; } else { best_lsn = best_lsn2; best_page = second_tail; this_off = second_file_off; } } else if (first_tail) { best_lsn = best_lsn1; best_page = first_tail; this_off = first_file_off; } else if (second_tail) { best_lsn = best_lsn2; best_page = second_tail; this_off = second_file_off; } else { goto tail_read; } best_page_pos = le16_to_cpu(best_page->page_pos); if (!tails) { if (best_page_pos == page_pos) { seq_base = best_lsn >> log->file_data_bits; saved_off = page_off = le32_to_cpu(best_page->file_off); lsn_base = best_lsn; memmove(page_bufs, best_page, log->page_size); page_cnt = le16_to_cpu(best_page->page_count); if (page_cnt > 1) page_pos += 1; tails = 1; } } else if (seq_base == (best_lsn >> log->file_data_bits) && saved_off + log->page_size == this_off && lsn_base < best_lsn && (page_pos != page_cnt || best_page_pos == page_pos || best_page_pos == 1) && (page_pos >= page_cnt || best_page_pos == page_pos)) { u16 bppc = le16_to_cpu(best_page->page_count); saved_off += log->page_size; lsn_base = best_lsn; memmove(Add2Ptr(page_bufs, tails * log->page_size), best_page, log->page_size); tails += 1; if (best_page_pos != bppc) { page_cnt = bppc; page_pos = best_page_pos; if (page_cnt > 1) page_pos += 1; } else { page_pos = page_cnt = 1; } } else { kfree(first_tail); kfree(second_tail); goto tail_read; } kfree(first_tail_prev); first_tail_prev = first_tail; final_off_prev = first_file_off; first_tail = NULL; kfree(second_tail_prev); second_tail_prev = second_tail; second_off_prev = second_file_off; second_tail = NULL; final_off += log->page_size; second_off += log->page_size; if (tails < 0x10) goto next_tail; tail_read: first_tail = first_tail_prev; final_off = final_off_prev; second_tail = second_tail_prev; second_off = second_off_prev; page_cnt = page_pos = 1; curpage_off = seq_base == log->seq_num ? min(log->next_page, page_off) : log->next_page; wrapped_file = curpage_off == log->first_page && !(log->l_flags & (NTFSLOG_NO_LAST_LSN | NTFSLOG_REUSE_TAIL)); expected_seq = wrapped_file ? (log->seq_num + 1) : log->seq_num; nextpage_off = curpage_off; next_page: tail_page = NULL; /* Read the next log page. */ err = read_log_page(log, curpage_off, &page, &usa_error); /* Compute the next log page offset the file. */ nextpage_off = next_page_off(log, curpage_off); wrapped = nextpage_off == log->first_page; if (tails > 1) { struct RECORD_PAGE_HDR *cur_page = Add2Ptr(page_bufs, curpage_off - page_off); if (curpage_off == saved_off) { tail_page = cur_page; goto use_tail_page; } if (page_off > curpage_off || curpage_off >= saved_off) goto use_tail_page; if (page_off1) goto use_cur_page; if (!err && !usa_error && page->rhdr.sign == NTFS_RCRD_SIGNATURE && cur_page->rhdr.lsn == page->rhdr.lsn && cur_page->record_hdr.next_record_off == page->record_hdr.next_record_off && ((page_pos == page_cnt && le16_to_cpu(page->page_pos) == 1) || (page_pos != page_cnt && le16_to_cpu(page->page_pos) == page_pos + 1 && le16_to_cpu(page->page_count) == page_cnt))) { cur_page = NULL; goto use_tail_page; } page_off1 = page_off; use_cur_page: lsn_cur = le64_to_cpu(cur_page->rhdr.lsn); if (last_ok_lsn != le64_to_cpu(cur_page->record_hdr.last_end_lsn) && ((lsn_cur >> log->file_data_bits) + ((curpage_off < (lsn_to_vbo(log, lsn_cur) & ~log->page_mask)) ? 1 : 0)) != expected_seq) { goto check_tail; } if (!is_log_record_end(cur_page)) { tail_page = NULL; last_ok_lsn = lsn_cur; goto next_page_1; } log->seq_num = expected_seq; log->l_flags &= ~NTFSLOG_NO_LAST_LSN; log->last_lsn = le64_to_cpu(cur_page->record_hdr.last_end_lsn); log->ra->current_lsn = cur_page->record_hdr.last_end_lsn; if (log->record_header_len <= log->page_size - le16_to_cpu(cur_page->record_hdr.next_record_off)) { log->l_flags |= NTFSLOG_REUSE_TAIL; log->next_page = curpage_off; } else { log->l_flags &= ~NTFSLOG_REUSE_TAIL; log->next_page = nextpage_off; } if (wrapped_file) log->l_flags |= NTFSLOG_WRAPPED; last_ok_lsn = le64_to_cpu(cur_page->record_hdr.last_end_lsn); goto next_page_1; } /* * If we are at the expected first page of a transfer check to see * if either tail copy is at this offset. * If this page is the last page of a transfer, check if we wrote * a subsequent tail copy. */ if (page_cnt == page_pos || page_cnt == page_pos + 1) { /* * Check if the offset matches either the first or second * tail copy. It is possible it will match both. */ if (curpage_off == final_off) tail_page = first_tail; /* * If we already matched on the first page then * check the ending lsn's. */ if (curpage_off == second_off) { if (!tail_page || (second_tail && le64_to_cpu(second_tail->record_hdr.last_end_lsn) > le64_to_cpu(first_tail->record_hdr .last_end_lsn))) { tail_page = second_tail; } } } use_tail_page: if (tail_page) { /* We have a candidate for a tail copy. */ lsn_cur = le64_to_cpu(tail_page->record_hdr.last_end_lsn); if (last_ok_lsn < lsn_cur) { /* * If the sequence number is not expected, * then don't use the tail copy. */ if (expected_seq != (lsn_cur >> log->file_data_bits)) tail_page = NULL; } else if (last_ok_lsn > lsn_cur) { /* * If the last lsn is greater than the one on * this page then forget this tail. */ tail_page = NULL; } } /* *If we have an error on the current page, * we will break of this loop. */ if (err || usa_error) goto check_tail; /* * Done if the last lsn on this page doesn't match the previous known * last lsn or the sequence number is not expected. */ lsn_cur = le64_to_cpu(page->rhdr.lsn); if (last_ok_lsn != lsn_cur && expected_seq != (lsn_cur >> log->file_data_bits)) { goto check_tail; } /* * Check that the page position and page count values are correct. * If this is the first page of a transfer the position must be 1 * and the count will be unknown. */ if (page_cnt == page_pos) { if (page->page_pos != cpu_to_le16(1) && (!reuse_page || page->page_pos != page->page_count)) { /* * If the current page is the first page we are * looking at and we are reusing this page then * it can be either the first or last page of a * transfer. Otherwise it can only be the first. */ goto check_tail; } } else if (le16_to_cpu(page->page_count) != page_cnt || le16_to_cpu(page->page_pos) != page_pos + 1) { /* * The page position better be 1 more than the last page * position and the page count better match. */ goto check_tail; } /* * We have a valid page the file and may have a valid page * the tail copy area. * If the tail page was written after the page the file then * break of the loop. */ if (tail_page && le64_to_cpu(tail_page->record_hdr.last_end_lsn) > lsn_cur) { /* Remember if we will replace the page. */ replace_page = true; goto check_tail; } tail_page = NULL; if (is_log_record_end(page)) { /* * Since we have read this page we know the sequence number * is the same as our expected value. */ log->seq_num = expected_seq; log->last_lsn = le64_to_cpu(page->record_hdr.last_end_lsn); log->ra->current_lsn = page->record_hdr.last_end_lsn; log->l_flags &= ~NTFSLOG_NO_LAST_LSN; /* * If there is room on this page for another header then * remember we want to reuse the page. */ if (log->record_header_len <= log->page_size - le16_to_cpu(page->record_hdr.next_record_off)) { log->l_flags |= NTFSLOG_REUSE_TAIL; log->next_page = curpage_off; } else { log->l_flags &= ~NTFSLOG_REUSE_TAIL; log->next_page = nextpage_off; } /* Remember if we wrapped the log file. */ if (wrapped_file) log->l_flags |= NTFSLOG_WRAPPED; } /* * Remember the last page count and position. * Also remember the last known lsn. */ page_cnt = le16_to_cpu(page->page_count); page_pos = le16_to_cpu(page->page_pos); last_ok_lsn = le64_to_cpu(page->rhdr.lsn); next_page_1: if (wrapped) { expected_seq += 1; wrapped_file = 1; } curpage_off = nextpage_off; kfree(page); page = NULL; reuse_page = 0; goto next_page; check_tail: if (tail_page) { log->seq_num = expected_seq; log->last_lsn = le64_to_cpu(tail_page->record_hdr.last_end_lsn); log->ra->current_lsn = tail_page->record_hdr.last_end_lsn; log->l_flags &= ~NTFSLOG_NO_LAST_LSN; if (log->page_size - le16_to_cpu( tail_page->record_hdr.next_record_off) >= log->record_header_len) { log->l_flags |= NTFSLOG_REUSE_TAIL; log->next_page = curpage_off; } else { log->l_flags &= ~NTFSLOG_REUSE_TAIL; log->next_page = nextpage_off; } if (wrapped) log->l_flags |= NTFSLOG_WRAPPED; } /* Remember that the partial IO will start at the next page. */ second_off = nextpage_off; /* * If the next page is the first page of the file then update * the sequence number for log records which begon the next page. */ if (wrapped) expected_seq += 1; /* * If we have a tail copy or are performing single page I/O we can * immediately look at the next page. */ if (replace_page || (log->ra->flags & RESTART_SINGLE_PAGE_IO)) { page_cnt = 2; page_pos = 1; goto check_valid; } if (page_pos != page_cnt) goto check_valid; /* * If the next page causes us to wrap to the beginning of the log * file then we know which page to check next. */ if (wrapped) { page_cnt = 2; page_pos = 1; goto check_valid; } cur_pos = 2; next_test_page: kfree(tst_page); tst_page = NULL; /* Walk through the file, reading log pages. */ err = read_log_page(log, nextpage_off, &tst_page, &usa_error); /* * If we get a USA error then assume that we correctly found * the end of the original transfer. */ if (usa_error) goto file_is_valid; /* * If we were able to read the page, we examine it to see if it * is the same or different Io block. */ if (err) goto next_test_page_1; if (le16_to_cpu(tst_page->page_pos) == cur_pos && check_subseq_log_page(log, tst_page, nextpage_off, expected_seq)) { page_cnt = le16_to_cpu(tst_page->page_count) + 1; page_pos = le16_to_cpu(tst_page->page_pos); goto check_valid; } else { goto file_is_valid; } next_test_page_1: nextpage_off = next_page_off(log, curpage_off); wrapped = nextpage_off == log->first_page; if (wrapped) { expected_seq += 1; page_cnt = 2; page_pos = 1; } cur_pos += 1; part_io_count += 1; if (!wrapped) goto next_test_page; check_valid: /* Skip over the remaining pages this transfer. */ remain_pages = page_cnt - page_pos - 1; part_io_count += remain_pages; while (remain_pages--) { nextpage_off = next_page_off(log, curpage_off); wrapped = nextpage_off == log->first_page; if (wrapped) expected_seq += 1; } /* Call our routine to check this log page. */ kfree(tst_page); tst_page = NULL; err = read_log_page(log, nextpage_off, &tst_page, &usa_error); if (!err && !usa_error && check_subseq_log_page(log, tst_page, nextpage_off, expected_seq)) { err = -EINVAL; goto out; } file_is_valid: /* We have a valid file. */ if (page_off1 || tail_page) { struct RECORD_PAGE_HDR *tmp_page; if (sb_rdonly(log->ni->mi.sbi->sb)) { err = -EROFS; goto out; } if (page_off1) { tmp_page = Add2Ptr(page_bufs, page_off1 - page_off); tails -= (page_off1 - page_off) / log->page_size; if (!tail_page) tails -= 1; } else { tmp_page = tail_page; tails = 1; } while (tails--) { u64 off = hdr_file_off(log, tmp_page); if (!page) { page = kmalloc(log->page_size, GFP_NOFS); if (!page) { err = -ENOMEM; goto out; } } /* * Correct page and copy the data from this page * into it and flush it to disk. */ memcpy(page, tmp_page, log->page_size); /* Fill last flushed lsn value flush the page. */ if (log->major_ver < 2) page->rhdr.lsn = page->record_hdr.last_end_lsn; else page->file_off = 0; page->page_pos = page->page_count = cpu_to_le16(1); ntfs_fix_pre_write(&page->rhdr, log->page_size); err = ntfs_sb_write_run(log->ni->mi.sbi, &log->ni->file.run, off, page, log->page_size, 0); if (err) goto out; if (part_io_count && second_off == off) { second_off += log->page_size; part_io_count -= 1; } tmp_page = Add2Ptr(tmp_page, log->page_size); } } if (part_io_count) { if (sb_rdonly(log->ni->mi.sbi->sb)) { err = -EROFS; goto out; } } out: kfree(second_tail); kfree(first_tail); kfree(page); kfree(tst_page); kfree(page_bufs); return err; } /* * read_log_rec_buf - Copy a log record from the file to a buffer. * * The log record may span several log pages and may even wrap the file. */ static int read_log_rec_buf(struct ntfs_log *log, const struct LFS_RECORD_HDR *rh, void *buffer) { int err; struct RECORD_PAGE_HDR *ph = NULL; u64 lsn = le64_to_cpu(rh->this_lsn); u32 vbo = lsn_to_vbo(log, lsn) & ~log->page_mask; u32 off = lsn_to_page_off(log, lsn) + log->record_header_len; u32 data_len = le32_to_cpu(rh->client_data_len); /* * While there are more bytes to transfer, * we continue to attempt to perform the read. */ for (;;) { bool usa_error; u32 tail = log->page_size - off; if (tail >= data_len) tail = data_len; data_len -= tail; err = read_log_page(log, vbo, &ph, &usa_error); if (err) goto out; /* * The last lsn on this page better be greater or equal * to the lsn we are copying. */ if (lsn > le64_to_cpu(ph->rhdr.lsn)) { err = -EINVAL; goto out; } memcpy(buffer, Add2Ptr(ph, off), tail); /* If there are no more bytes to transfer, we exit the loop. */ if (!data_len) { if (!is_log_record_end(ph) || lsn > le64_to_cpu(ph->record_hdr.last_end_lsn)) { err = -EINVAL; goto out; } break; } if (ph->rhdr.lsn == ph->record_hdr.last_end_lsn || lsn > le64_to_cpu(ph->rhdr.lsn)) { err = -EINVAL; goto out; } vbo = next_page_off(log, vbo); off = log->data_off; /* * Adjust our pointer the user's buffer to transfer * the next block to. */ buffer = Add2Ptr(buffer, tail); } out: kfree(ph); return err; } static int read_rst_area(struct ntfs_log *log, struct NTFS_RESTART **rst_, u64 *lsn) { int err; struct LFS_RECORD_HDR *rh = NULL; const struct CLIENT_REC *cr = Add2Ptr(log->ra, le16_to_cpu(log->ra->client_off)); u64 lsnr, lsnc = le64_to_cpu(cr->restart_lsn); u32 len; struct NTFS_RESTART *rst; *lsn = 0; *rst_ = NULL; /* If the client doesn't have a restart area, go ahead and exit now. */ if (!lsnc) return 0; err = read_log_page(log, lsn_to_vbo(log, lsnc), (struct RECORD_PAGE_HDR **)&rh, NULL); if (err) return err; rst = NULL; lsnr = le64_to_cpu(rh->this_lsn); if (lsnc != lsnr) { /* If the lsn values don't match, then the disk is corrupt. */ err = -EINVAL; goto out; } *lsn = lsnr; len = le32_to_cpu(rh->client_data_len); if (!len) { err = 0; goto out; } if (len < sizeof(struct NTFS_RESTART)) { err = -EINVAL; goto out; } rst = kmalloc(len, GFP_NOFS); if (!rst) { err = -ENOMEM; goto out; } /* Copy the data into the 'rst' buffer. */ err = read_log_rec_buf(log, rh, rst); if (err) goto out; *rst_ = rst; rst = NULL; out: kfree(rh); kfree(rst); return err; } static int find_log_rec(struct ntfs_log *log, u64 lsn, struct lcb *lcb) { int err; struct LFS_RECORD_HDR *rh = lcb->lrh; u32 rec_len, len; /* Read the record header for this lsn. */ if (!rh) { err = read_log_page(log, lsn_to_vbo(log, lsn), (struct RECORD_PAGE_HDR **)&rh, NULL); lcb->lrh = rh; if (err) return err; } /* * If the lsn the log record doesn't match the desired * lsn then the disk is corrupt. */ if (lsn != le64_to_cpu(rh->this_lsn)) return -EINVAL; len = le32_to_cpu(rh->client_data_len); /* * Check that the length field isn't greater than the total * available space the log file. */ rec_len = len + log->record_header_len; if (rec_len >= log->total_avail) return -EINVAL; /* * If the entire log record is on this log page, * put a pointer to the log record the context block. */ if (rh->flags & LOG_RECORD_MULTI_PAGE) { void *lr = kmalloc(len, GFP_NOFS); if (!lr) return -ENOMEM; lcb->log_rec = lr; lcb->alloc = true; /* Copy the data into the buffer returned. */ err = read_log_rec_buf(log, rh, lr); if (err) return err; } else { /* If beyond the end of the current page -> an error. */ u32 page_off = lsn_to_page_off(log, lsn); if (page_off + len + log->record_header_len > log->page_size) return -EINVAL; lcb->log_rec = Add2Ptr(rh, sizeof(struct LFS_RECORD_HDR)); lcb->alloc = false; } return 0; } /* * read_log_rec_lcb - Init the query operation. */ static int read_log_rec_lcb(struct ntfs_log *log, u64 lsn, u32 ctx_mode, struct lcb **lcb_) { int err; const struct CLIENT_REC *cr; struct lcb *lcb; switch (ctx_mode) { case lcb_ctx_undo_next: case lcb_ctx_prev: case lcb_ctx_next: break; default: return -EINVAL; } /* Check that the given lsn is the legal range for this client. */ cr = Add2Ptr(log->ra, le16_to_cpu(log->ra->client_off)); if (!verify_client_lsn(log, cr, lsn)) return -EINVAL; lcb = kzalloc_obj(struct lcb, GFP_NOFS); if (!lcb) return -ENOMEM; lcb->client = log->client_id; lcb->ctx_mode = ctx_mode; /* Find the log record indicated by the given lsn. */ err = find_log_rec(log, lsn, lcb); if (err) goto out; *lcb_ = lcb; return 0; out: lcb_put(lcb); *lcb_ = NULL; return err; } /* * find_client_next_lsn * * Attempt to find the next lsn to return to a client based on the context mode. */ static int find_client_next_lsn(struct ntfs_log *log, struct lcb *lcb, u64 *lsn) { int err; u64 next_lsn; struct LFS_RECORD_HDR *hdr; hdr = lcb->lrh; *lsn = 0; if (lcb_ctx_next != lcb->ctx_mode) goto check_undo_next; /* Loop as long as another lsn can be found. */ for (;;) { u64 current_lsn; err = next_log_lsn(log, hdr, ¤t_lsn); if (err) goto out; if (!current_lsn) break; if (hdr != lcb->lrh) kfree(hdr); hdr = NULL; err = read_log_page(log, lsn_to_vbo(log, current_lsn), (struct RECORD_PAGE_HDR **)&hdr, NULL); if (err) goto out; if (memcmp(&hdr->client, &lcb->client, sizeof(struct CLIENT_ID))) { /*err = -EINVAL; */ } else if (LfsClientRecord == hdr->record_type) { kfree(lcb->lrh); lcb->lrh = hdr; *lsn = current_lsn; return 0; } } out: if (hdr != lcb->lrh) kfree(hdr); return err; check_undo_next: if (lcb_ctx_undo_next == lcb->ctx_mode) next_lsn = le64_to_cpu(hdr->client_undo_next_lsn); else if (lcb_ctx_prev == lcb->ctx_mode) next_lsn = le64_to_cpu(hdr->client_prev_lsn); else return 0; if (!next_lsn) return 0; if (!verify_client_lsn( log, Add2Ptr(log->ra, le16_to_cpu(log->ra->client_off)), next_lsn)) return 0; hdr = NULL; err = read_log_page(log, lsn_to_vbo(log, next_lsn), (struct RECORD_PAGE_HDR **)&hdr, NULL); if (err) return err; kfree(lcb->lrh); lcb->lrh = hdr; *lsn = next_lsn; return 0; } static int read_next_log_rec(struct ntfs_log *log, struct lcb *lcb, u64 *lsn) { int err; err = find_client_next_lsn(log, lcb, lsn); if (err) return err; if (!*lsn) return 0; if (lcb->alloc) kfree(lcb->log_rec); lcb->log_rec = NULL; lcb->alloc = false; kfree(lcb->lrh); lcb->lrh = NULL; return find_log_rec(log, *lsn, lcb); } bool check_index_header(const struct INDEX_HDR *hdr, size_t bytes) { const bool has_subnode = hdr_has_subnode(hdr); __le16 mask; u32 min_de, de_off, used, total; const struct NTFS_DE *e; if (has_subnode) { min_de = sizeof(struct NTFS_DE) + sizeof(u64); mask = NTFS_IE_HAS_SUBNODES; } else { min_de = sizeof(struct NTFS_DE); mask = 0; } de_off = le32_to_cpu(hdr->de_off); used = le32_to_cpu(hdr->used); total = le32_to_cpu(hdr->total); if (de_off > bytes - min_de || used > bytes || total > bytes || de_off + min_de > used || used > total) { return false; } e = (const struct NTFS_DE *)((const u8 *)hdr + de_off); for (;;) { u16 esize = le16_to_cpu(e->size); u16 key_size = le16_to_cpu(e->key_size); u16 data_size; if (!IS_ALIGNED(esize, 8) || esize < min_de || (e->flags & NTFS_IE_HAS_SUBNODES) != mask) { return false; } if (size_add(de_off, esize) > used) return false; if (de_is_last(e)) { if (key_size) return false; break; } data_size = esize - min_de; if (key_size > data_size) return false; de_off += esize; e = (const struct NTFS_DE *)((const u8 *)hdr + de_off); } return true; } static inline bool check_index_buffer(const struct INDEX_BUFFER *ib, u32 bytes) { u16 fo; const struct NTFS_RECORD_HEADER *r = &ib->rhdr; if (r->sign != NTFS_INDX_SIGNATURE) return false; fo = (SECTOR_SIZE - ((bytes >> SECTOR_SHIFT) + 1) * sizeof(short)); if (le16_to_cpu(r->fix_off) > fo) return false; if ((le16_to_cpu(r->fix_num) - 1) * SECTOR_SIZE != bytes) return false; return check_index_header(&ib->ihdr, bytes - offsetof(struct INDEX_BUFFER, ihdr)); } static inline bool check_index_root(const struct ATTRIB *attr, struct ntfs_sb_info *sbi) { bool ret; const struct INDEX_ROOT *root = resident_data(attr); u8 index_bits = le32_to_cpu(root->index_block_size) >= sbi->cluster_size ? sbi->cluster_bits : SECTOR_SHIFT; u8 block_clst = root->index_block_clst; if (le32_to_cpu(attr->res.data_size) < sizeof(struct INDEX_ROOT) || (root->type != ATTR_NAME && root->type != ATTR_ZERO) || (root->type == ATTR_NAME && root->rule != NTFS_COLLATION_TYPE_FILENAME) || (le32_to_cpu(root->index_block_size) != (block_clst << index_bits)) || (block_clst != 1 && block_clst != 2 && block_clst != 4 && block_clst != 8 && block_clst != 0x10 && block_clst != 0x20 && block_clst != 0x40 && block_clst != 0x80)) { return false; } ret = check_index_header(&root->ihdr, le32_to_cpu(attr->res.data_size) - offsetof(struct INDEX_ROOT, ihdr)); return ret; } static inline bool check_attr(const struct MFT_REC *rec, const struct ATTRIB *attr, struct ntfs_sb_info *sbi) { u32 asize = le32_to_cpu(attr->size); u32 rsize = 0; u64 dsize, svcn, evcn; u16 run_off; /* Check the fixed part of the attribute record header. */ if (asize >= sbi->record_size || asize + PtrOffset(rec, attr) >= sbi->record_size || (attr->name_len && le16_to_cpu(attr->name_off) + attr->name_len * sizeof(short) > asize)) { return false; } /* Check the attribute fields. */ switch (attr->non_res) { case 0: rsize = le32_to_cpu(attr->res.data_size); if (rsize >= asize || le16_to_cpu(attr->res.data_off) + rsize > asize) { return false; } break; case 1: dsize = le64_to_cpu(attr->nres.data_size); svcn = le64_to_cpu(attr->nres.svcn); evcn = le64_to_cpu(attr->nres.evcn); run_off = le16_to_cpu(attr->nres.run_off); if (svcn > evcn + 1 || run_off >= asize || le64_to_cpu(attr->nres.valid_size) > dsize || dsize > le64_to_cpu(attr->nres.alloc_size)) { return false; } if (run_off > asize) return false; if (run_unpack(NULL, sbi, 0, svcn, evcn, svcn, Add2Ptr(attr, run_off), asize - run_off) < 0) { return false; } return true; default: return false; } switch (attr->type) { case ATTR_NAME: if (fname_full_size(Add2Ptr( attr, le16_to_cpu(attr->res.data_off))) > asize) { return false; } break; case ATTR_ROOT: return check_index_root(attr, sbi); case ATTR_STD: if (rsize < sizeof(struct ATTR_STD_INFO5) && rsize != sizeof(struct ATTR_STD_INFO)) { return false; } break; case ATTR_LIST: case ATTR_ID: case ATTR_SECURE: case ATTR_LABEL: case ATTR_VOL_INFO: case ATTR_DATA: case ATTR_ALLOC: case ATTR_BITMAP: case ATTR_REPARSE: case ATTR_EA_INFO: case ATTR_EA: case ATTR_PROPERTYSET: case ATTR_LOGGED_UTILITY_STREAM: break; default: return false; } return true; } static inline bool check_file_record(const struct MFT_REC *rec, const struct MFT_REC *rec2, struct ntfs_sb_info *sbi) { const struct ATTRIB *attr; u16 fo = le16_to_cpu(rec->rhdr.fix_off); u16 fn = le16_to_cpu(rec->rhdr.fix_num); u16 ao = le16_to_cpu(rec->attr_off); u32 rs = sbi->record_size; u32 used = le32_to_cpu(rec->used); /* Check the file record header for consistency. */ if (rec->rhdr.sign != NTFS_FILE_SIGNATURE || fo > (SECTOR_SIZE - ((rs >> SECTOR_SHIFT) + 1) * sizeof(short)) || (fn - 1) * SECTOR_SIZE != rs || ao < MFTRECORD_FIXUP_OFFSET_1 || ao > sbi->record_size - SIZEOF_RESIDENT || !is_rec_inuse(rec) || le32_to_cpu(rec->total) != rs || used > rs || used < ao) { return false; } /* Loop to check all of the attributes. */ for (attr = Add2Ptr(rec, ao); attr->type != ATTR_END; attr = Add2Ptr(attr, le32_to_cpu(attr->size))) { if (check_attr(rec, attr, sbi)) continue; return false; } /* * The do_action() handlers compute memmove lengths as * "rec->used - <offset of validated attr>", which underflows when * rec->used is smaller than the attribute walk reached. At this * point attr is the ATTR_END marker; rec->used must cover it. */ if (used < PtrOffset(rec, attr) + sizeof(attr->type)) return false; return true; } static inline int check_lsn(const struct NTFS_RECORD_HEADER *hdr, const u64 *rlsn) { u64 lsn; if (!rlsn) return true; lsn = le64_to_cpu(hdr->lsn); if (hdr->sign == NTFS_HOLE_SIGNATURE) return false; if (*rlsn > lsn) return true; return false; } static inline bool check_if_attr(const struct MFT_REC *rec, const struct LOG_REC_HDR *lrh) { u16 ro = le16_to_cpu(lrh->record_off); u16 o = le16_to_cpu(rec->attr_off); const struct ATTRIB *attr = Add2Ptr(rec, o); while (o < ro) { u32 asize; if (attr->type == ATTR_END) break; asize = le32_to_cpu(attr->size); if (!asize) break; o += asize; attr = Add2Ptr(attr, asize); } return o == ro; } static inline bool check_if_index_root(const struct MFT_REC *rec, const struct LOG_REC_HDR *lrh) { u16 ro = le16_to_cpu(lrh->record_off); u16 o = le16_to_cpu(rec->attr_off); const struct ATTRIB *attr = Add2Ptr(rec, o); while (o < ro) { u32 asize; if (attr->type == ATTR_END) break; asize = le32_to_cpu(attr->size); if (!asize) break; o += asize; attr = Add2Ptr(attr, asize); } return o == ro && attr->type == ATTR_ROOT; } static inline bool check_if_root_index(const struct ATTRIB *attr, const struct INDEX_HDR *hdr, const struct LOG_REC_HDR *lrh) { u16 ao = le16_to_cpu(lrh->attr_off); u32 de_off = le32_to_cpu(hdr->de_off); u32 o = PtrOffset(attr, hdr) + de_off; const struct NTFS_DE *e = Add2Ptr(hdr, de_off); u32 asize = le32_to_cpu(attr->size); while (o < ao) { u16 esize; if (o >= asize) break; esize = le16_to_cpu(e->size); if (!esize) break; o += esize; e = Add2Ptr(e, esize); } return o == ao; } static inline bool check_if_alloc_index(const struct INDEX_HDR *hdr, u32 attr_off) { u32 de_off = le32_to_cpu(hdr->de_off); u32 o = offsetof(struct INDEX_BUFFER, ihdr) + de_off; const struct NTFS_DE *e = Add2Ptr(hdr, de_off); u32 used = le32_to_cpu(hdr->used); while (o < attr_off) { u16 esize; if (de_off >= used) break; esize = le16_to_cpu(e->size); if (!esize) break; o += esize; de_off += esize; e = Add2Ptr(e, esize); } return o == attr_off; } static inline void change_attr_size(struct MFT_REC *rec, struct ATTRIB *attr, u32 nsize) { u32 asize = le32_to_cpu(attr->size); int dsize = nsize - asize; u8 *next = Add2Ptr(attr, asize); u32 used = le32_to_cpu(rec->used); memmove(Add2Ptr(attr, nsize), next, used - PtrOffset(rec, next)); rec->used = cpu_to_le32(used + dsize); attr->size = cpu_to_le32(nsize); } struct OpenAttr { struct ATTRIB *attr; struct runs_tree *run1; struct runs_tree run0; struct ntfs_inode *ni; // CLST rno; }; /* * cmp_type_and_name * * Return: 0 if 'attr' has the same type and name. */ static inline int cmp_type_and_name(const struct ATTRIB *a1, const struct ATTRIB *a2) { return a1->type != a2->type || a1->name_len != a2->name_len || (a1->name_len && memcmp(attr_name(a1), attr_name(a2), a1->name_len * sizeof(short))); } static struct OpenAttr *find_loaded_attr(struct ntfs_log *log, const struct ATTRIB *attr, CLST rno) { struct OPEN_ATTR_ENRTY *oe = NULL; while ((oe = enum_rstbl(log->open_attr_tbl, oe))) { struct OpenAttr *op_attr; if (ino_get(&oe->ref) != rno) continue; op_attr = (struct OpenAttr *)oe->ptr; if (!cmp_type_and_name(op_attr->attr, attr)) return op_attr; } return NULL; } static struct ATTRIB *attr_create_nonres_log(struct ntfs_sb_info *sbi, enum ATTR_TYPE type, u64 size, const u16 *name, size_t name_len, __le16 flags) { struct ATTRIB *attr; u32 name_size = ALIGN(name_len * sizeof(short), 8); bool is_ext = flags & (ATTR_FLAG_COMPRESSED | ATTR_FLAG_SPARSED); u32 asize = name_size + (is_ext ? SIZEOF_NONRESIDENT_EX : SIZEOF_NONRESIDENT); attr = kzalloc(asize, GFP_NOFS); if (!attr) return NULL; attr->type = type; attr->size = cpu_to_le32(asize); attr->flags = flags; attr->non_res = 1; attr->name_len = name_len; attr->nres.evcn = cpu_to_le64((u64)bytes_to_cluster(sbi, size) - 1); attr->nres.alloc_size = cpu_to_le64(ntfs_up_cluster(sbi, size)); attr->nres.data_size = cpu_to_le64(size); attr->nres.valid_size = attr->nres.data_size; if (is_ext) { attr->name_off = SIZEOF_NONRESIDENT_EX_LE; if (is_attr_compressed(attr)) attr->nres.c_unit = NTFS_LZNT_CUNIT; attr->nres.run_off = cpu_to_le16(SIZEOF_NONRESIDENT_EX + name_size); memcpy(Add2Ptr(attr, SIZEOF_NONRESIDENT_EX), name, name_len * sizeof(short)); } else { attr->name_off = SIZEOF_NONRESIDENT_LE; attr->nres.run_off = cpu_to_le16(SIZEOF_NONRESIDENT + name_size); memcpy(Add2Ptr(attr, SIZEOF_NONRESIDENT), name, name_len * sizeof(short)); } return attr; } /* * update_oa_attr - Synchronize OpenAttr's attribute pointer with modified attribute * @oa2: OpenAttr structure in memory that needs to be updated * @attr: Modified attribute from MFT record to duplicate * * Returns true on success, false on allocation failure. */ static bool update_oa_attr(struct OpenAttr *oa2, struct ATTRIB *attr) { void *p2; p2 = kmemdup(attr, le32_to_cpu(attr->size), GFP_NOFS); if (p2) { kfree(oa2->attr); oa2->attr = p2; return true; } return false; } /* * do_action - Common routine for the Redo and Undo Passes. * @rlsn: If it is NULL then undo. */ static int do_action(struct ntfs_log *log, struct OPEN_ATTR_ENRTY *oe, const struct LOG_REC_HDR *lrh, u32 op, void *data, u32 dlen, u32 rec_len, const u64 *rlsn) { int err = 0; struct ntfs_sb_info *sbi = log->ni->mi.sbi; struct inode *inode = NULL, *inode_parent; struct mft_inode *mi = NULL, *mi2_child = NULL; CLST rno = 0, rno_base = 0; struct INDEX_BUFFER *ib = NULL; struct MFT_REC *rec = NULL; struct ATTRIB *attr = NULL, *attr2; struct INDEX_HDR *hdr; struct INDEX_ROOT *root; struct NTFS_DE *e, *e1, *e2; struct NEW_ATTRIBUTE_SIZES *new_sz; struct ATTR_FILE_NAME *fname; struct OpenAttr *oa, *oa2; u32 nsize, t32, asize, used, esize, off, bits; u16 id, id2; u32 record_size = sbi->record_size; u64 t64; u16 roff = le16_to_cpu(lrh->record_off); u16 aoff = le16_to_cpu(lrh->attr_off); u64 lco = 0; u64 cbo = (u64)le16_to_cpu(lrh->cluster_off) << SECTOR_SHIFT; u64 tvo = le64_to_cpu(lrh->target_vcn) << sbi->cluster_bits; u64 vbo = cbo + tvo; void *buffer_le = NULL; u32 bytes = 0; bool a_dirty = false; u16 data_off; oa = oe->ptr; /* Big switch to prepare. */ switch (op) { /* ============================================================ * Process MFT records, as described by the current log record. * ============================================================ */ case InitializeFileRecordSegment: case DeallocateFileRecordSegment: case WriteEndOfFileRecordSegment: case CreateAttribute: case DeleteAttribute: case UpdateResidentValue: case UpdateMappingPairs: case SetNewAttributeSizes: case AddIndexEntryRoot: case DeleteIndexEntryRoot: case SetIndexEntryVcnRoot: case UpdateFileNameRoot: case UpdateRecordDataRoot: case ZeroEndOfFileRecord: rno = vbo >> sbi->record_bits; inode = ilookup(sbi->sb, rno); if (inode) { mi = &ntfs_i(inode)->mi; } else { /* Read from disk. */ err = mi_get(sbi, rno, &mi); if (err && op == InitializeFileRecordSegment) { mi = kzalloc_obj(struct mft_inode, GFP_NOFS); if (!mi) return -ENOMEM; err = mi_format_new(mi, sbi, rno, 0, false); } if (err) return err; } rec = mi->mrec; if (op == DeallocateFileRecordSegment) goto skip_load_parent; if (rec->rhdr.sign == NTFS_BAAD_SIGNATURE) goto dirty_vol; if (!check_lsn(&rec->rhdr, rlsn)) goto out; if (!check_file_record(rec, NULL, sbi)) goto dirty_vol; attr = Add2Ptr(rec, roff); if (is_rec_base(rec) || InitializeFileRecordSegment == op) { rno_base = rno; goto skip_load_parent; } rno_base = ino_get(&rec->parent_ref); inode_parent = ntfs_iget5(sbi->sb, &rec->parent_ref, NULL); if (IS_ERR(inode_parent)) goto skip_load_parent; if (is_bad_inode(inode_parent)) { iput(inode_parent); goto skip_load_parent; } if (ni_load_mi_ex(ntfs_i(inode_parent), rno, &mi2_child)) { iput(inode_parent); } else { if (mi2_child->mrec != mi->mrec) memcpy(mi2_child->mrec, mi->mrec, sbi->record_size); if (inode) iput(inode); else mi_put(mi); inode = inode_parent; mi = mi2_child; rec = mi2_child->mrec; attr = Add2Ptr(rec, roff); } skip_load_parent: inode_parent = NULL; break; /* * Process attributes, as described by the current log record. */ case UpdateNonresidentValue: case AddIndexEntryAllocation: case DeleteIndexEntryAllocation: case WriteEndOfIndexBuffer: case SetIndexEntryVcnAllocation: case UpdateFileNameAllocation: case SetBitsInNonresidentBitMap: case ClearBitsInNonresidentBitMap: case UpdateRecordDataAllocation: attr = oa->attr; bytes = UpdateNonresidentValue == op ? dlen : 0; lco = (u64)le16_to_cpu(lrh->lcns_follow) << sbi->cluster_bits; if (attr->type == ATTR_ALLOC) { t32 = le32_to_cpu(oe->bytes_per_index); if (bytes < t32) bytes = t32; } if (!bytes) bytes = lco - cbo; bytes += roff; if (attr->type == ATTR_ALLOC) bytes = (bytes + 511) & ~511; // align buffer_le = kmalloc(bytes, GFP_NOFS); if (!buffer_le) return -ENOMEM; err = ntfs_read_run_nb(sbi, oa->run1, vbo, buffer_le, bytes, NULL); if (err) goto out; if (attr->type == ATTR_ALLOC && *(int *)buffer_le) ntfs_fix_post_read(buffer_le, bytes, false); break; default: WARN_ON(1); } /* Big switch to do operation. */ switch (op) { case InitializeFileRecordSegment: if (roff + dlen > record_size) goto dirty_vol; memcpy(Add2Ptr(rec, roff), data, dlen); mi->dirty = true; break; case DeallocateFileRecordSegment: clear_rec_inuse(rec); le16_add_cpu(&rec->seq, 1); mi->dirty = true; break; case WriteEndOfFileRecordSegment: attr2 = (struct ATTRIB *)data; if (!check_if_attr(rec, lrh) || roff + dlen > record_size) goto dirty_vol; memmove(attr, attr2, dlen); rec->used = cpu_to_le32(ALIGN(roff + dlen, 8)); mi->dirty = true; break; case CreateAttribute: attr2 = (struct ATTRIB *)data; asize = le32_to_cpu(attr2->size); used = le32_to_cpu(rec->used); if (!check_if_attr(rec, lrh) || dlen < SIZEOF_RESIDENT || !IS_ALIGNED(asize, 8) || Add2Ptr(attr2, asize) > Add2Ptr(lrh, rec_len) || dlen > record_size - used) { goto dirty_vol; } memmove(Add2Ptr(attr, asize), attr, used - roff); memcpy(attr, attr2, asize); rec->used = cpu_to_le32(used + asize); id = le16_to_cpu(rec->next_attr_id); id2 = le16_to_cpu(attr2->id); if (id <= id2) rec->next_attr_id = cpu_to_le16(id2 + 1); if (is_attr_indexed(attr)) le16_add_cpu(&rec->hard_links, 1); oa2 = find_loaded_attr(log, attr, rno_base); if (oa2) update_oa_attr(oa2, attr); mi->dirty = true; break; case DeleteAttribute: asize = le32_to_cpu(attr->size); used = le32_to_cpu(rec->used); if (!check_if_attr(rec, lrh)) goto dirty_vol; rec->used = cpu_to_le32(used - asize); if (is_attr_indexed(attr)) le16_add_cpu(&rec->hard_links, -1); memmove(attr, Add2Ptr(attr, asize), used - asize - roff); mi->dirty = true; break; case UpdateResidentValue: nsize = aoff + dlen; if (!check_if_attr(rec, lrh)) goto dirty_vol; asize = le32_to_cpu(attr->size); used = le32_to_cpu(rec->used); if (lrh->redo_len == lrh->undo_len) { if (nsize > asize) goto dirty_vol; goto move_data; } if (nsize > asize && nsize - asize > record_size - used) goto dirty_vol; nsize = ALIGN(nsize, 8); data_off = le16_to_cpu(attr->res.data_off); /* * aoff comes from the on-disk lrh->attr_off. Forbid * writes that begin below the resident attribute's * data_off (which would overwrite the resident header), * and forbid aoff + dlen < data_off, which would make * the data_size assignment below underflow to ~4 GiB. */ if (aoff < data_off || aoff + dlen < data_off || aoff + dlen > asize) goto dirty_vol; if (nsize < asize) { memmove(Add2Ptr(attr, aoff), data, dlen); data = NULL; // To skip below memmove(). } memmove(Add2Ptr(attr, nsize), Add2Ptr(attr, asize), used - le16_to_cpu(lrh->record_off) - asize); rec->used = cpu_to_le32(used + nsize - asize); attr->size = cpu_to_le32(nsize); attr->res.data_size = cpu_to_le32(aoff + dlen - data_off); move_data: if (data) memmove(Add2Ptr(attr, aoff), data, dlen); oa2 = find_loaded_attr(log, attr, rno_base); if (oa2 && update_oa_attr(oa2, attr)) oa2->run1 = &oa2->run0; mi->dirty = true; break; case UpdateMappingPairs: nsize = aoff + dlen; asize = le32_to_cpu(attr->size); used = le32_to_cpu(rec->used); if (!check_if_attr(rec, lrh) || !attr->non_res || aoff < le16_to_cpu(attr->nres.run_off) || aoff > asize || (nsize > asize && nsize - asize > record_size - used)) { goto dirty_vol; } nsize = ALIGN(nsize, 8); memmove(Add2Ptr(attr, nsize), Add2Ptr(attr, asize), used - le16_to_cpu(lrh->record_off) - asize); rec->used = cpu_to_le32(used + nsize - asize); attr->size = cpu_to_le32(nsize); memmove(Add2Ptr(attr, aoff), data, dlen); if (run_get_highest_vcn(le64_to_cpu(attr->nres.svcn), attr_run(attr), le32_to_cpu(attr->size) - le16_to_cpu(attr->nres.run_off), &t64)) { goto dirty_vol; } attr->nres.evcn = cpu_to_le64(t64); oa2 = find_loaded_attr(log, attr, rno_base); if (oa2 && oa2->attr->non_res) oa2->attr->nres.evcn = attr->nres.evcn; mi->dirty = true; break; case SetNewAttributeSizes: new_sz = data; if (!check_if_attr(rec, lrh) || !attr->non_res) goto dirty_vol; attr->nres.alloc_size = new_sz->alloc_size; attr->nres.data_size = new_sz->data_size; attr->nres.valid_size = new_sz->valid_size; if (dlen >= sizeof(struct NEW_ATTRIBUTE_SIZES)) attr->nres.total_size = new_sz->total_size; oa2 = find_loaded_attr(log, attr, rno_base); if (oa2) update_oa_attr(oa2, attr); mi->dirty = true; break; case AddIndexEntryRoot: e = (struct NTFS_DE *)data; esize = le16_to_cpu(e->size); root = resident_data(attr); hdr = &root->ihdr; used = le32_to_cpu(hdr->used); if (!check_if_index_root(rec, lrh) || !check_if_root_index(attr, hdr, lrh) || Add2Ptr(data, esize) > Add2Ptr(lrh, rec_len) || esize > le32_to_cpu(rec->total) - le32_to_cpu(rec->used)) { goto dirty_vol; } e1 = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); change_attr_size(rec, attr, le32_to_cpu(attr->size) + esize); memmove(Add2Ptr(e1, esize), e1, PtrOffset(e1, Add2Ptr(hdr, used))); memmove(e1, e, esize); le32_add_cpu(&attr->res.data_size, esize); hdr->used = cpu_to_le32(used + esize); le32_add_cpu(&hdr->total, esize); mi->dirty = true; break; case DeleteIndexEntryRoot: root = resident_data(attr); hdr = &root->ihdr; used = le32_to_cpu(hdr->used); if (!check_if_index_root(rec, lrh) || !check_if_root_index(attr, hdr, lrh)) { goto dirty_vol; } e1 = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); esize = le16_to_cpu(e1->size); if (PtrOffset(e1, Add2Ptr(hdr, used)) < esize) goto dirty_vol; e2 = Add2Ptr(e1, esize); memmove(e1, e2, PtrOffset(e2, Add2Ptr(hdr, used))); le32_sub_cpu(&attr->res.data_size, esize); hdr->used = cpu_to_le32(used - esize); le32_sub_cpu(&hdr->total, esize); change_attr_size(rec, attr, le32_to_cpu(attr->size) - esize); mi->dirty = true; break; case SetIndexEntryVcnRoot: root = resident_data(attr); hdr = &root->ihdr; if (!check_if_index_root(rec, lrh) || !check_if_root_index(attr, hdr, lrh)) { goto dirty_vol; } e = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); de_set_vbn_le(e, *(__le64 *)data); mi->dirty = true; break; case UpdateFileNameRoot: root = resident_data(attr); hdr = &root->ihdr; if (!check_if_index_root(rec, lrh) || !check_if_root_index(attr, hdr, lrh)) { goto dirty_vol; } e = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); fname = (struct ATTR_FILE_NAME *)(e + 1); memmove(&fname->dup, data, sizeof(fname->dup)); // mi->dirty = true; break; case UpdateRecordDataRoot: root = resident_data(attr); hdr = &root->ihdr; if (!check_if_index_root(rec, lrh) || !check_if_root_index(attr, hdr, lrh)) { goto dirty_vol; } e = Add2Ptr(attr, le16_to_cpu(lrh->attr_off)); /* * e->view.data_off and dlen come from the on-disk * INDEX_ROOT entry / LRH. The neighbouring read sites * (e.g. fs/ntfs3/index.c) check that * view.data_off + view.data_size <= e->size; mirror that * bound here so the memmove cannot reach past the entry. */ if (le16_to_cpu(e->view.data_off) > le16_to_cpu(e->size) || le16_to_cpu(e->view.data_off) + dlen > le16_to_cpu(e->size)) goto dirty_vol; memmove(Add2Ptr(e, le16_to_cpu(e->view.data_off)), data, dlen); mi->dirty = true; break; case ZeroEndOfFileRecord: if (roff + dlen > record_size) goto dirty_vol; memset(attr, 0, dlen); mi->dirty = true; break; case UpdateNonresidentValue: if (lco < cbo + roff + dlen) goto dirty_vol; memcpy(Add2Ptr(buffer_le, roff), data, dlen); a_dirty = true; if (attr->type == ATTR_ALLOC) ntfs_fix_pre_write(buffer_le, bytes); break; case AddIndexEntryAllocation: ib = Add2Ptr(buffer_le, roff); hdr = &ib->ihdr; e = data; esize = le16_to_cpu(e->size); e1 = Add2Ptr(ib, aoff); if (is_baad(&ib->rhdr)) goto dirty_vol; if (!check_lsn(&ib->rhdr, rlsn)) goto out; used = le32_to_cpu(hdr->used); if (!check_index_buffer(ib, bytes) || !check_if_alloc_index(hdr, aoff) || Add2Ptr(e, esize) > Add2Ptr(lrh, rec_len) || used + esize > le32_to_cpu(hdr->total)) { goto dirty_vol; } memmove(Add2Ptr(e1, esize), e1, PtrOffset(e1, Add2Ptr(hdr, used))); memcpy(e1, e, esize); hdr->used = cpu_to_le32(used + esize); a_dirty = true; ntfs_fix_pre_write(&ib->rhdr, bytes); break; case DeleteIndexEntryAllocation: ib = Add2Ptr(buffer_le, roff); hdr = &ib->ihdr; e = Add2Ptr(ib, aoff); esize = le16_to_cpu(e->size); if (is_baad(&ib->rhdr)) goto dirty_vol; if (!check_lsn(&ib->rhdr, rlsn)) goto out; if (!check_index_buffer(ib, bytes) || !check_if_alloc_index(hdr, aoff)) { goto dirty_vol; } e1 = Add2Ptr(e, esize); used = le32_to_cpu(hdr->used); /* * Reject crafted entries whose e->size makes e + esize * point past the INDEX_HDR's used boundary. Without this, * PtrOffset(e1, hdr + used) underflows to a quasi-infinite * size_t when fed to the memmove() below. * * Also reject esize == 0: memmove(e, e, ...) is a no-op and * leaves hdr->used unchanged, masking the crafted entry. */ if (!esize || Add2Ptr(e, esize) > Add2Ptr(hdr, used) || PtrOffset(e1, Add2Ptr(hdr, used)) < esize) goto dirty_vol; nsize = esize; memmove(e, e1, PtrOffset(e1, Add2Ptr(hdr, used))); hdr->used = cpu_to_le32(used - nsize); a_dirty = true; ntfs_fix_pre_write(&ib->rhdr, bytes); break; case WriteEndOfIndexBuffer: ib = Add2Ptr(buffer_le, roff); hdr = &ib->ihdr; e = Add2Ptr(ib, aoff); if (is_baad(&ib->rhdr)) goto dirty_vol; if (!check_lsn(&ib->rhdr, rlsn)) goto out; if (!check_index_buffer(ib, bytes) || !check_if_alloc_index(hdr, aoff) || aoff + dlen > offsetof(struct INDEX_BUFFER, ihdr) + le32_to_cpu(hdr->total)) { goto dirty_vol; } hdr->used = cpu_to_le32(dlen + PtrOffset(hdr, e)); memmove(e, data, dlen); a_dirty = true; ntfs_fix_pre_write(&ib->rhdr, bytes); break; case SetIndexEntryVcnAllocation: ib = Add2Ptr(buffer_le, roff); hdr = &ib->ihdr; e = Add2Ptr(ib, aoff); if (is_baad(&ib->rhdr)) goto dirty_vol; if (!check_lsn(&ib->rhdr, rlsn)) goto out; if (!check_index_buffer(ib, bytes) || !check_if_alloc_index(hdr, aoff)) { goto dirty_vol; } de_set_vbn_le(e, *(__le64 *)data); a_dirty = true; ntfs_fix_pre_write(&ib->rhdr, bytes); break; case UpdateFileNameAllocation: ib = Add2Ptr(buffer_le, roff); hdr = &ib->ihdr; e = Add2Ptr(ib, aoff); if (is_baad(&ib->rhdr)) goto dirty_vol; if (!check_lsn(&ib->rhdr, rlsn)) goto out; if (!check_index_buffer(ib, bytes) || !check_if_alloc_index(hdr, aoff)) { goto dirty_vol; } fname = (struct ATTR_FILE_NAME *)(e + 1); memmove(&fname->dup, data, sizeof(fname->dup)); a_dirty = true; ntfs_fix_pre_write(&ib->rhdr, bytes); break; case SetBitsInNonresidentBitMap: off = le32_to_cpu(((struct BITMAP_RANGE *)data)->bitmap_off); bits = le32_to_cpu(((struct BITMAP_RANGE *)data)->bits); if (cbo + (off + 7) / 8 > lco || cbo + ((off + bits + 7) / 8) > lco) { goto dirty_vol; } ntfs_bitmap_set_le(Add2Ptr(buffer_le, roff), off, bits); a_dirty = true; break; case ClearBitsInNonresidentBitMap: off = le32_to_cpu(((struct BITMAP_RANGE *)data)->bitmap_off); bits = le32_to_cpu(((struct BITMAP_RANGE *)data)->bits); if (cbo + (off + 7) / 8 > lco || cbo + ((off + bits + 7) / 8) > lco) { goto dirty_vol; } ntfs_bitmap_clear_le(Add2Ptr(buffer_le, roff), off, bits); a_dirty = true; break; case UpdateRecordDataAllocation: ib = Add2Ptr(buffer_le, roff); hdr = &ib->ihdr; e = Add2Ptr(ib, aoff); if (is_baad(&ib->rhdr)) goto dirty_vol; if (!check_lsn(&ib->rhdr, rlsn)) goto out; if (!check_index_buffer(ib, bytes) || !check_if_alloc_index(hdr, aoff)) { goto dirty_vol; } /* See UpdateRecordDataRoot for the rationale. */ if (le16_to_cpu(e->view.data_off) > le16_to_cpu(e->size) || le16_to_cpu(e->view.data_off) + dlen > le16_to_cpu(e->size)) goto dirty_vol; memmove(Add2Ptr(e, le16_to_cpu(e->view.data_off)), data, dlen); a_dirty = true; ntfs_fix_pre_write(&ib->rhdr, bytes); break; default: WARN_ON(1); } if (rlsn) { __le64 t64 = cpu_to_le64(*rlsn); if (rec) rec->rhdr.lsn = t64; if (ib) ib->rhdr.lsn = t64; } if (mi && mi->dirty) { err = mi_write(mi, 0); if (err) goto out; } if (a_dirty) { attr = oa->attr; err = ntfs_sb_write_run(sbi, oa->run1, vbo, buffer_le, bytes, 0); if (err) goto out; } out: if (inode) iput(inode); else if (mi != mi2_child) mi_put(mi); kfree(buffer_le); return err; dirty_vol: log->set_dirty = true; goto out; } /* * log_replay - Replays log and empties it. * * This function is called during mount operation. * It replays log and empties it. * Initialized is set false if logfile contains '-1'. */ int log_replay(struct ntfs_inode *ni, bool *initialized) { int err; struct ntfs_sb_info *sbi = ni->mi.sbi; struct ntfs_log *log; u64 rec_lsn, checkpt_lsn = 0, rlsn = 0; struct ATTR_NAME_ENTRY *attr_names = NULL; u32 attr_names_bytes = 0; u32 oatbl_bytes = 0; struct RESTART_TABLE *dptbl = NULL; struct RESTART_TABLE *trtbl = NULL; const struct RESTART_TABLE *rt; struct RESTART_TABLE *oatbl = NULL; struct inode *inode; struct OpenAttr *oa; struct ntfs_inode *ni_oe; struct ATTRIB *attr = NULL; u64 size, vcn, undo_next_lsn; CLST rno, lcn, lcn0, len0, clen; void *data; struct NTFS_RESTART *rst = NULL; struct lcb *lcb = NULL; struct OPEN_ATTR_ENRTY *oe; struct ATTR_NAME_ENTRY *ane; struct TRANSACTION_ENTRY *tr; struct DIR_PAGE_ENTRY *dp; u32 i, bytes_per_attr_entry; u32 vbo, tail, off, dlen; u32 saved_len, rec_len, transact_id; bool use_second_page; struct RESTART_AREA *ra2, *ra = NULL; struct CLIENT_REC *ca, *cr; __le16 client; struct RESTART_HDR *rh; const struct LFS_RECORD_HDR *frh; const struct LOG_REC_HDR *lrh; bool is_mapped; bool is_ro = sb_rdonly(sbi->sb); u64 t64; u16 t16; u32 t32; log = kzalloc_obj(struct ntfs_log, GFP_NOFS); if (!log) return -ENOMEM; log->ni = ni; log->l_size = log->orig_file_size = ni->vfs_inode.i_size; /* Get the size of page. NOTE: To replay we can use default page. */ log->page_size = norm_file_page(PAGE_SIZE, &log->l_size, true); if (!log->page_size) { err = -EINVAL; goto out; } log->one_page_buf = kmalloc(log->page_size, GFP_NOFS); if (!log->one_page_buf) { err = -ENOMEM; goto out; } log->page_mask = log->page_size - 1; log->page_bits = blksize_bits(log->page_size); /* Look for a restart area on the disk. */ err = log_read_rst(log, true, &log->rst_info); if (err) goto out; /* remember 'initialized' */ *initialized = log->rst_info.initialized; if (!log->rst_info.restart) { if (log->rst_info.initialized) { /* No restart area but the file is not initialized. */ err = -EINVAL; goto out; } log_init_pg_hdr(log, 1, 1); log_create(log, 0, get_random_u32(), false, false); ra = log_create_ra(log); if (!ra) { err = -ENOMEM; goto out; } log->ra = ra; log->init_ra = true; goto process_log; } /* * If the restart offset above wasn't zero then we won't * look for a second restart. */ if (log->rst_info.vbo) goto check_restart_area; err = log_read_rst(log, false, &log->rst_info2); if (err) goto out; /* Determine which restart area to use. */ if (!log->rst_info2.restart || log->rst_info2.last_lsn <= log->rst_info.last_lsn) goto use_first_page; use_second_page = true; if (log->rst_info.chkdsk_was_run && log->page_size != log->rst_info.vbo) { struct RECORD_PAGE_HDR *sp = NULL; bool usa_error; if (!read_log_page(log, log->page_size, &sp, &usa_error) && sp->rhdr.sign == NTFS_CHKD_SIGNATURE) { use_second_page = false; } kfree(sp); } if (use_second_page) { kfree(log->rst_info.r_page); memcpy(&log->rst_info, &log->rst_info2, sizeof(struct restart_info)); log->rst_info2.r_page = NULL; } use_first_page: kfree(log->rst_info2.r_page); check_restart_area: /* * If the restart area is at offset 0, we want * to write the second restart area first. */ log->init_ra = !!log->rst_info.vbo; /* If we have a valid page then grab a pointer to the restart area. */ ra2 = log->rst_info.valid_page ? Add2Ptr(log->rst_info.r_page, le16_to_cpu(log->rst_info.r_page->ra_off)) : NULL; if (log->rst_info.chkdsk_was_run || (ra2 && ra2->client_idx[1] == LFS_NO_CLIENT_LE)) { bool wrapped = false; bool use_multi_page = false; u32 open_log_count; /* Do some checks based on whether we have a valid log page. */ open_log_count = log->rst_info.valid_page ? le32_to_cpu(ra2->open_log_count) : get_random_u32(); log_init_pg_hdr(log, 1, 1); log_create(log, log->rst_info.last_lsn, open_log_count, wrapped, use_multi_page); ra = log_create_ra(log); if (!ra) { err = -ENOMEM; goto out; } log->ra = ra; /* Put the restart areas and initialize * the log file as required. */ goto process_log; } if (!ra2) { err = -EINVAL; goto out; } /* * If the log page or the system page sizes have changed, we can't * use the log file. We must use the system page size instead of the * default size if there is not a clean shutdown. */ t32 = le32_to_cpu(log->rst_info.r_page->sys_page_size); if (log->page_size != t32) { u32 old_page_size = log->page_size; log->l_size = log->orig_file_size; log->page_size = norm_file_page(t32, &log->l_size, t32 == DefaultLogPageSize); /* * If the adopted on-disk page size is larger than the size used * to allocate one_page_buf above, grow the scratch buffer so a * later read_log_page() cannot overflow it. */ if (log->page_size > old_page_size) { void *buf; buf = krealloc(log->one_page_buf, log->page_size, GFP_NOFS); if (!buf) { err = -ENOMEM; goto out; } log->one_page_buf = buf; } } if (log->page_size != t32 || log->page_size != le32_to_cpu(log->rst_info.r_page->page_size)) { err = -EINVAL; goto out; } log->page_mask = log->page_size - 1; log->page_bits = blksize_bits(log->page_size); /* If the file size has shrunk then we won't mount it. */ if (log->l_size < le64_to_cpu(ra2->l_size)) { err = -EINVAL; goto out; } log_init_pg_hdr(log, le16_to_cpu(log->rst_info.r_page->major_ver), le16_to_cpu(log->rst_info.r_page->minor_ver)); log->l_size = le64_to_cpu(ra2->l_size); log->seq_num_bits = le32_to_cpu(ra2->seq_num_bits); log->file_data_bits = sizeof(u64) * 8 - log->seq_num_bits; log->seq_num_mask = (8 << log->file_data_bits) - 1; log->last_lsn = le64_to_cpu(ra2->current_lsn); log->seq_num = log->last_lsn >> log->file_data_bits; log->ra_off = le16_to_cpu(log->rst_info.r_page->ra_off); log->restart_size = log->sys_page_size - log->ra_off; log->record_header_len = le16_to_cpu(ra2->rec_hdr_len); log->ra_size = le16_to_cpu(ra2->ra_len); log->data_off = le16_to_cpu(ra2->data_off); log->data_size = log->page_size - log->data_off; log->reserved = log->data_size - log->record_header_len; vbo = lsn_to_vbo(log, log->last_lsn); if (vbo < log->first_page) { /* This is a pseudo lsn. */ log->l_flags |= NTFSLOG_NO_LAST_LSN; log->next_page = log->first_page; goto find_oldest; } /* Find the end of this log record. */ off = final_log_off(log, log->last_lsn, le32_to_cpu(ra2->last_lsn_data_len)); /* If we wrapped the file then increment the sequence number. */ if (off <= vbo) { log->seq_num += 1; log->l_flags |= NTFSLOG_WRAPPED; } /* Now compute the next log page to use. */ vbo &= ~log->sys_page_mask; tail = log->page_size - (off & log->page_mask) - 1; /* *If we can fit another log record on the page, * move back a page the log file. */ if (tail >= log->record_header_len) { log->l_flags |= NTFSLOG_REUSE_TAIL; log->next_page = vbo; } else { log->next_page = next_page_off(log, vbo); } find_oldest: /* * Find the oldest client lsn. Use the last * flushed lsn as a starting point. */ log->oldest_lsn = log->last_lsn; oldest_client_lsn(Add2Ptr(ra2, le16_to_cpu(ra2->client_off)), ra2->client_idx[1], &log->oldest_lsn); log->oldest_lsn_off = lsn_to_vbo(log, log->oldest_lsn); if (log->oldest_lsn_off < log->first_page) log->l_flags |= NTFSLOG_NO_OLDEST_LSN; if (!(ra2->flags & RESTART_SINGLE_PAGE_IO)) log->l_flags |= NTFSLOG_WRAPPED | NTFSLOG_MULTIPLE_PAGE_IO; log->current_openlog_count = le32_to_cpu(ra2->open_log_count); log->total_avail_pages = log->l_size - log->first_page; log->total_avail = log->total_avail_pages >> log->page_bits; log->max_current_avail = log->total_avail * log->reserved; log->total_avail = log->total_avail * log->data_size; log->current_avail = current_log_avail(log); ra = kzalloc(log->restart_size, GFP_NOFS); if (!ra) { err = -ENOMEM; goto out; } log->ra = ra; t16 = le16_to_cpu(ra2->client_off); if (t16 == offsetof(struct RESTART_AREA, clients)) { memcpy(ra, ra2, log->ra_size); } else { memcpy(ra, ra2, offsetof(struct RESTART_AREA, clients)); memcpy(ra->clients, Add2Ptr(ra2, t16), le16_to_cpu(ra2->ra_len) - t16); log->current_openlog_count = get_random_u32(); ra->open_log_count = cpu_to_le32(log->current_openlog_count); log->ra_size = offsetof(struct RESTART_AREA, clients) + sizeof(struct CLIENT_REC); ra->client_off = cpu_to_le16(offsetof(struct RESTART_AREA, clients)); ra->ra_len = cpu_to_le16(log->ra_size); } le32_add_cpu(&ra->open_log_count, 1); /* Now we need to walk through looking for the last lsn. */ err = last_log_lsn(log); if (err) goto out; log->current_avail = current_log_avail(log); /* Remember which restart area to write first. */ log->init_ra = log->rst_info.vbo; process_log: /* 1.0, 1.1, 2.0 log->major_ver/minor_ver - short values. */ switch ((log->major_ver << 16) + log->minor_ver) { case 0x10000: case 0x10001: case 0x20000: break; default: ntfs_warn(sbi->sb, "\x24LogFile version %d.%d is not supported", log->major_ver, log->minor_ver); err = -EOPNOTSUPP; log->set_dirty = true; goto out; } /* One client "NTFS" per logfile. */ ca = Add2Ptr(ra, le16_to_cpu(ra->client_off)); for (client = ra->client_idx[1];; client = cr->next_client) { if (client == LFS_NO_CLIENT_LE) { /* Insert "NTFS" client LogFile. */ client = ra->client_idx[0]; if (client == LFS_NO_CLIENT_LE) { err = -EINVAL; goto out; } t16 = le16_to_cpu(client); cr = ca + t16; remove_client(ca, cr, &ra->client_idx[0]); cr->restart_lsn = 0; cr->oldest_lsn = cpu_to_le64(log->oldest_lsn); cr->name_bytes = cpu_to_le32(8); cr->name[0] = cpu_to_le16('N'); cr->name[1] = cpu_to_le16('T'); cr->name[2] = cpu_to_le16('F'); cr->name[3] = cpu_to_le16('S'); add_client(ca, t16, &ra->client_idx[1]); break; } cr = ca + le16_to_cpu(client); if (cpu_to_le32(8) == cr->name_bytes && cpu_to_le16('N') == cr->name[0] && cpu_to_le16('T') == cr->name[1] && cpu_to_le16('F') == cr->name[2] && cpu_to_le16('S') == cr->name[3]) break; } /* Update the client handle with the client block information. */ log->client_id.seq_num = cr->seq_num; log->client_id.client_idx = client; err = read_rst_area(log, &rst, &checkpt_lsn); if (err) goto out; if (!rst) goto out; bytes_per_attr_entry = !rst->major_ver ? 0x2C : 0x28; if (rst->check_point_start) checkpt_lsn = le64_to_cpu(rst->check_point_start); /* Allocate and Read the Transaction Table. */ if (!rst->transact_table_len) goto check_dirty_page_table; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->transact_table_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); if (err) goto out; lrh = lcb->log_rec; frh = lcb->lrh; rec_len = le32_to_cpu(frh->client_data_len); if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), bytes_per_attr_entry)) { err = -EINVAL; goto out; } t16 = le16_to_cpu(lrh->redo_off); rt = Add2Ptr(lrh, t16); t32 = rec_len - t16; /* Now check that this is a valid restart table. */ if (!check_rstbl(rt, t32)) { err = -EINVAL; goto out; } trtbl = kmemdup(rt, t32, GFP_NOFS); if (!trtbl) { err = -ENOMEM; goto out; } lcb_put(lcb); lcb = NULL; check_dirty_page_table: /* The next record back should be the Dirty Pages Table. */ if (!rst->dirty_pages_len) goto check_attribute_names; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->dirty_pages_table_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); if (err) goto out; lrh = lcb->log_rec; frh = lcb->lrh; rec_len = le32_to_cpu(frh->client_data_len); if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), bytes_per_attr_entry)) { err = -EINVAL; goto out; } t16 = le16_to_cpu(lrh->redo_off); rt = Add2Ptr(lrh, t16); t32 = rec_len - t16; /* Now check that this is a valid restart table. */ if (!check_rstbl(rt, t32)) { err = -EINVAL; goto out; } dptbl = kmemdup(rt, t32, GFP_NOFS); if (!dptbl) { err = -ENOMEM; goto out; } /* Convert Ra version '0' into version '1'. */ if (rst->major_ver) goto end_conv_1; /* reduce tab pressure. */ t16 = le16_to_cpu(dptbl->size); if (t16 < sizeof(struct DIR_PAGE_ENTRY)) { log->set_dirty = true; goto out; } t32 = (t16 - sizeof(struct DIR_PAGE_ENTRY)) / sizeof(u64); dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { struct DIR_PAGE_ENTRY_32 *dp0 = (struct DIR_PAGE_ENTRY_32 *)dp; u32 lcns = le32_to_cpu(dp->lcns_follow); if (lcns > t32) { log->set_dirty = true; goto out; } memmove(&dp->vcn, &dp0->vcn_low, 2 * sizeof(u64) + lcns * sizeof(u64)); } end_conv_1: lcb_put(lcb); lcb = NULL; /* * Go through the table and remove the duplicates, * remembering the oldest lsn values. */ if (sbi->cluster_size <= log->page_size) goto trace_dp_table; /* reduce tab pressure. */ dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { struct DIR_PAGE_ENTRY *next = dp; while ((next = enum_rstbl(dptbl, next))) { if (next->target_attr == dp->target_attr && next->vcn == dp->vcn) { if (le64_to_cpu(next->oldest_lsn) < le64_to_cpu(dp->oldest_lsn)) { dp->oldest_lsn = next->oldest_lsn; } free_rsttbl_idx(dptbl, PtrOffset(dptbl, next)); } } } trace_dp_table: check_attribute_names: /* The next record should be the Attribute Names. */ if (!rst->attr_names_len) goto check_attr_table; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->attr_names_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); if (err) goto out; lrh = lcb->log_rec; frh = lcb->lrh; rec_len = le32_to_cpu(frh->client_data_len); if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), bytes_per_attr_entry)) { err = -EINVAL; goto out; } t32 = lrh_length(lrh); attr_names_bytes = rec_len - t32; attr_names = kmemdup(Add2Ptr(lrh, t32), attr_names_bytes, GFP_NOFS); if (!attr_names) { err = -ENOMEM; goto out; } lcb_put(lcb); lcb = NULL; check_attr_table: /* The next record should be the attribute Table. */ if (!rst->open_attr_len) goto check_attribute_names2; /* reduce tab pressure. */ t64 = le64_to_cpu(rst->open_attr_table_lsn); err = read_log_rec_lcb(log, t64, lcb_ctx_prev, &lcb); if (err) goto out; lrh = lcb->log_rec; frh = lcb->lrh; rec_len = le32_to_cpu(frh->client_data_len); if (!check_log_rec(lrh, rec_len, le32_to_cpu(frh->transact_id), bytes_per_attr_entry)) { err = -EINVAL; goto out; } t16 = le16_to_cpu(lrh->redo_off); rt = Add2Ptr(lrh, t16); oatbl_bytes = rec_len - t16; if (!check_rstbl(rt, oatbl_bytes)) { err = -EINVAL; goto out; } oatbl = kmemdup(rt, oatbl_bytes, GFP_NOFS); if (!oatbl) { err = -ENOMEM; goto out; } log->open_attr_tbl = oatbl; /* Clear all of the Attr pointers. */ oe = NULL; while ((oe = enum_rstbl(oatbl, oe))) { if (!rst->major_ver) { struct OPEN_ATTR_ENRTY_32 oe0; /* Really 'oe' points to OPEN_ATTR_ENRTY_32. */ memcpy(&oe0, oe, SIZEOF_OPENATTRIBUTEENTRY0); oe->bytes_per_index = oe0.bytes_per_index; oe->type = oe0.type; oe->is_dirty_pages = oe0.is_dirty_pages; oe->name_len = 0; oe->ref = oe0.ref; oe->open_record_lsn = oe0.open_record_lsn; } oe->is_attr_name = 0; oe->ptr = NULL; } lcb_put(lcb); lcb = NULL; check_attribute_names2: if (attr_names && oatbl) { off = 0; for (;;) { /* Check we can use attribute name entry 'ane'. */ static_assert(sizeof(*ane) == 4); if (off + sizeof(*ane) > attr_names_bytes) { /* just ignore the rest. */ break; } ane = Add2Ptr(attr_names, off); t16 = le16_to_cpu(ane->off); if (!t16) { /* this is the only valid exit. */ break; } /* Check we can use open attribute entry 'oe'. */ if (t16 + sizeof(*oe) > oatbl_bytes) { /* just ignore the rest. */ break; } /* TODO: Clear table on exit! */ oe = Add2Ptr(oatbl, t16); t16 = le16_to_cpu(ane->name_bytes); off += t16 + sizeof(*ane); if (off > attr_names_bytes) { /* just ignore the rest. */ break; } oe->name_len = t16 / sizeof(short); oe->ptr = ane->name; oe->is_attr_name = 2; } } /* * If the checkpt_lsn is zero, then this is a freshly * formatted disk and we have no work to do. */ if (!checkpt_lsn) { err = 0; goto out; } if (!oatbl) { oatbl = init_rsttbl(bytes_per_attr_entry, 8); if (!oatbl) { err = -ENOMEM; goto out; } } log->open_attr_tbl = oatbl; /* Start the analysis pass from the Checkpoint lsn. */ rec_lsn = checkpt_lsn; /* Read the first lsn. */ err = read_log_rec_lcb(log, checkpt_lsn, lcb_ctx_next, &lcb); if (err) goto out; /* Loop to read all subsequent records to the end of the log file. */ next_log_record_analyze: err = read_next_log_rec(log, lcb, &rec_lsn); if (err) goto out; if (!rec_lsn) goto end_log_records_enumerate; frh = lcb->lrh; transact_id = le32_to_cpu(frh->transact_id); rec_len = le32_to_cpu(frh->client_data_len); lrh = lcb->log_rec; if (!check_log_rec(lrh, rec_len, transact_id, bytes_per_attr_entry)) { err = -EINVAL; goto out; } /* * The first lsn after the previous lsn remembered * the checkpoint is the first candidate for the rlsn. */ if (!rlsn) rlsn = rec_lsn; if (LfsClientRecord != frh->record_type) goto next_log_record_analyze; /* * Now update the Transaction Table for this transaction. If there * is no entry present or it is unallocated we allocate the entry. */ if (!trtbl) { trtbl = init_rsttbl(sizeof(struct TRANSACTION_ENTRY), INITIAL_NUMBER_TRANSACTIONS); if (!trtbl) { err = -ENOMEM; goto out; } } tr = Add2Ptr(trtbl, transact_id); if (transact_id >= bytes_per_rt(trtbl) || tr->next != RESTART_ENTRY_ALLOCATED_LE) { tr = alloc_rsttbl_from_idx(&trtbl, transact_id); if (!tr) { err = -ENOMEM; goto out; } tr->transact_state = TransactionActive; tr->first_lsn = cpu_to_le64(rec_lsn); } tr->prev_lsn = tr->undo_next_lsn = cpu_to_le64(rec_lsn); /* * If this is a compensation log record, then change * the undo_next_lsn to be the undo_next_lsn of this record. */ if (lrh->undo_op == cpu_to_le16(CompensationLogRecord)) tr->undo_next_lsn = frh->client_undo_next_lsn; /* Dispatch to handle log record depending on type. */ switch (le16_to_cpu(lrh->redo_op)) { case InitializeFileRecordSegment: case DeallocateFileRecordSegment: case WriteEndOfFileRecordSegment: case CreateAttribute: case DeleteAttribute: case UpdateResidentValue: case UpdateNonresidentValue: case UpdateMappingPairs: case SetNewAttributeSizes: case AddIndexEntryRoot: case DeleteIndexEntryRoot: case AddIndexEntryAllocation: case DeleteIndexEntryAllocation: case WriteEndOfIndexBuffer: case SetIndexEntryVcnRoot: case SetIndexEntryVcnAllocation: case UpdateFileNameRoot: case UpdateFileNameAllocation: case SetBitsInNonresidentBitMap: case ClearBitsInNonresidentBitMap: case UpdateRecordDataRoot: case UpdateRecordDataAllocation: case ZeroEndOfFileRecord: t16 = le16_to_cpu(lrh->target_attr); t64 = le64_to_cpu(lrh->target_vcn); dp = find_dp(dptbl, t16, t64); if (dp) goto copy_lcns; /* * Calculate the number of clusters per page the system * which wrote the checkpoint, possibly creating the table. */ if (dptbl) { t32 = (le16_to_cpu(dptbl->size) - sizeof(struct DIR_PAGE_ENTRY)) / sizeof(u64); } else { t32 = log->clst_per_page; kfree(dptbl); dptbl = init_rsttbl(struct_size(dp, page_lcns, t32), 32); if (!dptbl) { err = -ENOMEM; goto out; } } dp = alloc_rsttbl_idx(&dptbl); if (!dp) { err = -ENOMEM; goto out; } dp->target_attr = cpu_to_le32(t16); dp->transfer_len = cpu_to_le32(t32 << sbi->cluster_bits); dp->lcns_follow = cpu_to_le32(t32); dp->vcn = cpu_to_le64(t64 & ~((u64)t32 - 1)); dp->oldest_lsn = cpu_to_le64(rec_lsn); copy_lcns: /* * Copy the Lcns from the log record into the Dirty Page Entry. * TODO: For different page size support, must somehow make * whole routine a loop, case Lcns do not fit below. */ t16 = le16_to_cpu(lrh->lcns_follow); t32 = le32_to_cpu(dp->lcns_follow); if (le64_to_cpu(lrh->target_vcn) < le64_to_cpu(dp->vcn)) { err = -EINVAL; goto out; } /* * find_dp() only validates that target_vcn is the first * cluster covered by dp. The walk through lrh->lcns_follow * further entries must stay within the allocated * dp->page_lcns[] array, which is sized by dp->lcns_follow. */ if (le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn) + t16 > le32_to_cpu(dp->lcns_follow)) { err = -EINVAL; log->set_dirty = true; goto out; } for (i = 0; i < t16; i++) { size_t j = (size_t)(le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn)); if (j >= t32 || i >= t32 - j) { err = -EINVAL; goto out; } dp->page_lcns[j + i] = lrh->page_lcns[i]; } goto next_log_record_analyze; case DeleteDirtyClusters: { u32 range_count = le16_to_cpu(lrh->redo_len) / sizeof(struct LCN_RANGE); const struct LCN_RANGE *r = Add2Ptr(lrh, le16_to_cpu(lrh->redo_off)); /* Loop through all of the Lcn ranges this log record. */ for (i = 0; i < range_count; i++, r++) { u64 lcn0 = le64_to_cpu(r->lcn); u64 lcn_e = lcn0 + le64_to_cpu(r->len) - 1; dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { u32 j; t32 = le32_to_cpu(dp->lcns_follow); for (j = 0; j < t32; j++) { t64 = le64_to_cpu(dp->page_lcns[j]); if (t64 >= lcn0 && t64 <= lcn_e) dp->page_lcns[j] = 0; } } } goto next_log_record_analyze; } case OpenNonresidentAttribute: t16 = le16_to_cpu(lrh->target_attr); if (t16 >= bytes_per_rt(oatbl)) { /* * Compute how big the table needs to be. * Add 10 extra entries for some cushion. */ u32 new_e = t16 / le16_to_cpu(oatbl->size); new_e += 10 - le16_to_cpu(oatbl->used); oatbl = extend_rsttbl(oatbl, new_e, ~0u); log->open_attr_tbl = oatbl; if (!oatbl) { err = -ENOMEM; goto out; } } /* Point to the entry being opened. */ oe = alloc_rsttbl_from_idx(&oatbl, t16); log->open_attr_tbl = oatbl; if (!oe) { err = -ENOMEM; goto out; } /* Initialize this entry from the log record. */ t16 = le16_to_cpu(lrh->redo_off); if (!rst->major_ver) { /* Convert version '0' into version '1'. */ struct OPEN_ATTR_ENRTY_32 *oe0 = Add2Ptr(lrh, t16); oe->bytes_per_index = oe0->bytes_per_index; oe->type = oe0->type; oe->is_dirty_pages = oe0->is_dirty_pages; oe->name_len = 0; //oe0.name_len; oe->ref = oe0->ref; oe->open_record_lsn = oe0->open_record_lsn; } else { memcpy(oe, Add2Ptr(lrh, t16), bytes_per_attr_entry); } t16 = le16_to_cpu(lrh->undo_len); if (t16) { oe->ptr = kmalloc(t16, GFP_NOFS); if (!oe->ptr) { err = -ENOMEM; goto out; } oe->name_len = t16 / sizeof(short); memcpy(oe->ptr, Add2Ptr(lrh, le16_to_cpu(lrh->undo_off)), t16); oe->is_attr_name = 1; } else { oe->ptr = NULL; oe->is_attr_name = 0; } goto next_log_record_analyze; case HotFix: t16 = le16_to_cpu(lrh->target_attr); t64 = le64_to_cpu(lrh->target_vcn); dp = find_dp(dptbl, t16, t64); if (dp) { size_t j = le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn); if (dp->page_lcns[j]) dp->page_lcns[j] = lrh->page_lcns[0]; } goto next_log_record_analyze; case EndTopLevelAction: tr = Add2Ptr(trtbl, transact_id); tr->prev_lsn = cpu_to_le64(rec_lsn); tr->undo_next_lsn = frh->client_undo_next_lsn; goto next_log_record_analyze; case PrepareTransaction: tr = Add2Ptr(trtbl, transact_id); tr->transact_state = TransactionPrepared; goto next_log_record_analyze; case CommitTransaction: tr = Add2Ptr(trtbl, transact_id); tr->transact_state = TransactionCommitted; goto next_log_record_analyze; case ForgetTransaction: free_rsttbl_idx(trtbl, transact_id); goto next_log_record_analyze; case Noop: case OpenAttributeTableDump: case AttributeNamesDump: case DirtyPageTableDump: case TransactionTableDump: /* The following cases require no action the Analysis Pass. */ goto next_log_record_analyze; default: /* * All codes will be explicitly handled. * If we see a code we do not expect, then we are trouble. */ goto next_log_record_analyze; } end_log_records_enumerate: lcb_put(lcb); lcb = NULL; /* * Scan the Dirty Page Table and Transaction Table for * the lowest lsn, and return it as the Redo lsn. */ dp = NULL; while ((dp = enum_rstbl(dptbl, dp))) { t64 = le64_to_cpu(dp->oldest_lsn); if (t64 && t64 < rlsn) rlsn = t64; } tr = NULL; while ((tr = enum_rstbl(trtbl, tr))) { t64 = le64_to_cpu(tr->first_lsn); if (t64 && t64 < rlsn) rlsn = t64; } /* * Only proceed if the Dirty Page Table or Transaction * table are not empty. */ if ((!dptbl || !dptbl->total) && (!trtbl || !trtbl->total)) goto end_replay; sbi->flags |= NTFS_FLAGS_NEED_REPLAY; if (is_ro) goto out; /* Reopen all of the attributes with dirty pages. */ oe = NULL; next_open_attribute: oe = enum_rstbl(oatbl, oe); if (!oe) { err = 0; dp = NULL; goto next_dirty_page; } oa = kzalloc_obj(struct OpenAttr, GFP_NOFS); if (!oa) { err = -ENOMEM; goto out; } inode = ntfs_iget5(sbi->sb, &oe->ref, NULL); if (IS_ERR(inode)) goto fake_attr; if (is_bad_inode(inode)) { iput(inode); fake_attr: if (oa->ni) { iput(&oa->ni->vfs_inode); oa->ni = NULL; } attr = attr_create_nonres_log(sbi, oe->type, 0, oe->ptr, oe->name_len, 0); if (!attr) { kfree(oa); err = -ENOMEM; goto out; } oa->attr = attr; oa->run1 = &oa->run0; goto final_oe; } ni_oe = ntfs_i(inode); oa->ni = ni_oe; attr = ni_find_attr(ni_oe, NULL, NULL, oe->type, oe->ptr, oe->name_len, NULL, NULL); if (!attr) goto fake_attr; t32 = le32_to_cpu(attr->size); oa->attr = kmemdup(attr, t32, GFP_NOFS); if (!oa->attr) goto fake_attr; if (!S_ISDIR(inode->i_mode)) { if (attr->type == ATTR_DATA && !attr->name_len) { oa->run1 = &ni_oe->file.run; goto final_oe; } } else { if (attr->type == ATTR_ALLOC && attr->name_len == ARRAY_SIZE(I30_NAME) && !memcmp(attr_name(attr), I30_NAME, sizeof(I30_NAME))) { oa->run1 = &ni_oe->dir.alloc_run; goto final_oe; } } if (attr->non_res) { u16 roff = le16_to_cpu(attr->nres.run_off); CLST svcn = le64_to_cpu(attr->nres.svcn); if (roff > t32) { kfree(oa->attr); oa->attr = NULL; goto fake_attr; } err = run_unpack(&oa->run0, sbi, inode->i_ino, svcn, le64_to_cpu(attr->nres.evcn), svcn, Add2Ptr(attr, roff), t32 - roff); if (err < 0) { kfree(oa->attr); oa->attr = NULL; goto fake_attr; } err = 0; } oa->run1 = &oa->run0; attr = oa->attr; final_oe: if (oe->is_attr_name == 1) kfree(oe->ptr); oe->is_attr_name = 0; oe->ptr = oa; oe->name_len = attr->name_len; goto next_open_attribute; /* * Now loop through the dirty page table to extract all of the Vcn/Lcn. * Mapping that we have, and insert it into the appropriate run. */ next_dirty_page: dp = enum_rstbl(dptbl, dp); if (!dp) goto do_redo_1; oe = Add2Ptr(oatbl, le32_to_cpu(dp->target_attr)); if (oe->next != RESTART_ENTRY_ALLOCATED_LE) goto next_dirty_page; oa = oe->ptr; if (!oa) goto next_dirty_page; i = -1; next_dirty_page_vcn: i += 1; if (i >= le32_to_cpu(dp->lcns_follow)) goto next_dirty_page; vcn = le64_to_cpu(dp->vcn) + i; size = (vcn + 1) << sbi->cluster_bits; if (!dp->page_lcns[i]) goto next_dirty_page_vcn; rno = ino_get(&oe->ref); if (rno <= MFT_REC_MIRR && size < (MFT_REC_VOL + 1) * sbi->record_size && oe->type == ATTR_DATA) { goto next_dirty_page_vcn; } lcn = le64_to_cpu(dp->page_lcns[i]); if ((!run_lookup_entry(oa->run1, vcn, &lcn0, &len0, NULL) || lcn0 != lcn) && !run_add_entry(oa->run1, vcn, lcn, 1, false)) { err = -ENOMEM; goto out; } attr = oa->attr; if (size > le64_to_cpu(attr->nres.alloc_size)) { attr->nres.valid_size = attr->nres.data_size = attr->nres.alloc_size = cpu_to_le64(size); } goto next_dirty_page_vcn; do_redo_1: /* * Perform the Redo Pass, to restore all of the dirty pages to the same * contents that they had immediately before the crash. If the dirty * page table is empty, then we can skip the entire Redo Pass. */ if (!dptbl || !dptbl->total) goto do_undo_action; rec_lsn = rlsn; /* * Read the record at the Redo lsn, before falling * into common code to handle each record. */ err = read_log_rec_lcb(log, rlsn, lcb_ctx_next, &lcb); if (err) goto out; /* * Now loop to read all of our log records forwards, until * we hit the end of the file, cleaning up at the end. */ do_action_next: frh = lcb->lrh; if (LfsClientRecord != frh->record_type) goto read_next_log_do_action; transact_id = le32_to_cpu(frh->transact_id); rec_len = le32_to_cpu(frh->client_data_len); lrh = lcb->log_rec; if (!check_log_rec(lrh, rec_len, transact_id, bytes_per_attr_entry)) { err = -EINVAL; goto out; } /* Ignore log records that do not update pages. */ if (lrh->lcns_follow) goto find_dirty_page; goto read_next_log_do_action; find_dirty_page: t16 = le16_to_cpu(lrh->target_attr); t64 = le64_to_cpu(lrh->target_vcn); dp = find_dp(dptbl, t16, t64); if (!dp) goto read_next_log_do_action; if (rec_lsn < le64_to_cpu(dp->oldest_lsn)) goto read_next_log_do_action; t16 = le16_to_cpu(lrh->target_attr); if (t16 >= bytes_per_rt(oatbl)) { err = -EINVAL; goto out; } oe = Add2Ptr(oatbl, t16); if (oe->next != RESTART_ENTRY_ALLOCATED_LE) { err = -EINVAL; goto out; } oa = oe->ptr; if (!oa) { err = -EINVAL; goto out; } attr = oa->attr; vcn = le64_to_cpu(lrh->target_vcn); if (!run_lookup_entry(oa->run1, vcn, &lcn, NULL, NULL) || lcn == SPARSE_LCN) { goto read_next_log_do_action; } /* Point to the Redo data and get its length. */ data = Add2Ptr(lrh, le16_to_cpu(lrh->redo_off)); dlen = le16_to_cpu(lrh->redo_len); /* Shorten length by any Lcns which were deleted. */ saved_len = dlen; for (i = le16_to_cpu(lrh->lcns_follow); i; i--) { size_t j; u32 alen, voff; voff = le16_to_cpu(lrh->record_off) + le16_to_cpu(lrh->attr_off); voff += le16_to_cpu(lrh->cluster_off) << SECTOR_SHIFT; /* If the Vcn question is allocated, we can just get out. */ j = le64_to_cpu(lrh->target_vcn) - le64_to_cpu(dp->vcn); if (dp->page_lcns[j + i - 1]) break; if (!saved_len) saved_len = 1; /* * Calculate the allocated space left relative to the * log record Vcn, after removing this unallocated Vcn. */ alen = (i - 1) << sbi->cluster_bits; /* * If the update described this log record goes beyond * the allocated space, then we will have to reduce the length. */ if (voff >= alen) dlen = 0; else if (voff + dlen > alen) dlen = alen - voff; } /* * If the resulting dlen from above is now zero, * we can skip this log record. */ if (!dlen && saved_len) goto read_next_log_do_action; t16 = le16_to_cpu(lrh->redo_op); if (can_skip_action(t16)) goto read_next_log_do_action; /* Apply the Redo operation a common routine. */ err = do_action(log, oe, lrh, t16, data, dlen, rec_len, &rec_lsn); if (err) goto out; /* Keep reading and looping back until end of file. */ read_next_log_do_action: err = read_next_log_rec(log, lcb, &rec_lsn); if (!err && rec_lsn) goto do_action_next; lcb_put(lcb); lcb = NULL; do_undo_action: /* Scan Transaction Table. */ tr = NULL; transaction_table_next: tr = enum_rstbl(trtbl, tr); if (!tr) goto undo_action_done; if (TransactionActive != tr->transact_state || !tr->undo_next_lsn) { free_rsttbl_idx(trtbl, PtrOffset(trtbl, tr)); goto transaction_table_next; } log->transaction_id = PtrOffset(trtbl, tr); undo_next_lsn = le64_to_cpu(tr->undo_next_lsn); /* * We only have to do anything if the transaction has * something its undo_next_lsn field. */ if (!undo_next_lsn) goto commit_undo; /* Read the first record to be undone by this transaction. */ err = read_log_rec_lcb(log, undo_next_lsn, lcb_ctx_undo_next, &lcb); if (err) goto out; /* * Now loop to read all of our log records forwards, * until we hit the end of the file, cleaning up at the end. */ undo_action_next: lrh = lcb->log_rec; frh = lcb->lrh; transact_id = le32_to_cpu(frh->transact_id); rec_len = le32_to_cpu(frh->client_data_len); if (!check_log_rec(lrh, rec_len, transact_id, bytes_per_attr_entry)) { err = -EINVAL; goto out; } if (lrh->undo_op == cpu_to_le16(Noop)) goto read_next_log_undo_action; oe = Add2Ptr(oatbl, le16_to_cpu(lrh->target_attr)); oa = oe->ptr; t16 = le16_to_cpu(lrh->lcns_follow); if (!t16) goto add_allocated_vcns; is_mapped = run_lookup_entry(oa->run1, le64_to_cpu(lrh->target_vcn), &lcn, &clen, NULL); /* * If the mapping isn't already the table or the mapping * corresponds to a hole the mapping, we need to make sure * there is no partial page already memory. */ if (is_mapped && lcn != SPARSE_LCN && clen >= t16) goto add_allocated_vcns; vcn = le64_to_cpu(lrh->target_vcn); vcn &= ~(u64)(log->clst_per_page - 1); add_allocated_vcns: for (i = 0, vcn = le64_to_cpu(lrh->target_vcn), size = (vcn + 1) << sbi->cluster_bits; i < t16; i++, vcn += 1, size += sbi->cluster_size) { attr = oa->attr; if (!attr->non_res) { if (size > le32_to_cpu(attr->res.data_size)) attr->res.data_size = cpu_to_le32(size); } else { if (size > le64_to_cpu(attr->nres.data_size)) attr->nres.valid_size = attr->nres.data_size = attr->nres.alloc_size = cpu_to_le64(size); } } t16 = le16_to_cpu(lrh->undo_op); if (can_skip_action(t16)) goto read_next_log_undo_action; /* Point to the Redo data and get its length. */ data = Add2Ptr(lrh, le16_to_cpu(lrh->undo_off)); dlen = le16_to_cpu(lrh->undo_len); /* It is time to apply the undo action. */ err = do_action(log, oe, lrh, t16, data, dlen, rec_len, NULL); read_next_log_undo_action: /* * Keep reading and looping back until we have read the * last record for this transaction. */ err = read_next_log_rec(log, lcb, &rec_lsn); if (err) goto out; if (rec_lsn) goto undo_action_next; lcb_put(lcb); lcb = NULL; commit_undo: free_rsttbl_idx(trtbl, log->transaction_id); log->transaction_id = 0; goto transaction_table_next; undo_action_done: ntfs_update_mftmirr(sbi); sbi->flags &= ~NTFS_FLAGS_NEED_REPLAY; end_replay: err = 0; if (is_ro) goto out; rh = kzalloc(log->page_size, GFP_NOFS); if (!rh) { err = -ENOMEM; goto out; } rh->rhdr.sign = NTFS_RSTR_SIGNATURE; rh->rhdr.fix_off = cpu_to_le16(offsetof(struct RESTART_HDR, fixups)); t16 = (log->page_size >> SECTOR_SHIFT) + 1; rh->rhdr.fix_num = cpu_to_le16(t16); rh->sys_page_size = cpu_to_le32(log->page_size); rh->page_size = cpu_to_le32(log->page_size); t16 = ALIGN(offsetof(struct RESTART_HDR, fixups) + sizeof(short) * t16, 8); rh->ra_off = cpu_to_le16(t16); rh->minor_ver = cpu_to_le16(1); // 0x1A: rh->major_ver = cpu_to_le16(1); // 0x1C: ra2 = Add2Ptr(rh, t16); memcpy(ra2, ra, sizeof(struct RESTART_AREA)); ra2->client_idx[0] = 0; ra2->client_idx[1] = LFS_NO_CLIENT_LE; ra2->flags = cpu_to_le16(2); le32_add_cpu(&ra2->open_log_count, 1); ntfs_fix_pre_write(&rh->rhdr, log->page_size); err = ntfs_sb_write_run(sbi, &ni->file.run, 0, rh, log->page_size, 0); if (!err) err = ntfs_sb_write_run(sbi, &log->ni->file.run, log->page_size, rh, log->page_size, 0); kfree(rh); if (err) goto out; out: kfree(rst); if (lcb) lcb_put(lcb); /* * Scan the Open Attribute Table to close all of * the open attributes. */ oe = NULL; while ((oe = enum_rstbl(oatbl, oe))) { rno = ino_get(&oe->ref); if (oe->is_attr_name == 1) { kfree(oe->ptr); oe->ptr = NULL; continue; } if (oe->is_attr_name) continue; oa = oe->ptr; if (!oa) continue; run_close(&oa->run0); kfree(oa->attr); if (oa->ni) iput(&oa->ni->vfs_inode); kfree(oa); } kfree(trtbl); kfree(oatbl); kfree(dptbl); kfree(attr_names); kfree(log->rst_info.r_page); kfree(ra); kfree(log->one_page_buf); if (err) sbi->flags |= NTFS_FLAGS_NEED_REPLAY; if (err == -EROFS) err = 0; else if (log->set_dirty) ntfs_set_state(sbi, NTFS_DIRTY_ERROR); kfree(log); return err; } |
| 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 | // SPDX-License-Identifier: GPL-2.0-only #include <linux/module.h> #include <linux/errno.h> #include <linux/socket.h> #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> #include <linux/in6.h> #include <net/udp.h> #include <net/udp_tunnel.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/ip6_tunnel.h> #include <net/ip6_checksum.h> int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) { struct sockaddr_in6 udp6_addr = {}; int err; struct socket *sock = NULL; err = sock_create_kern(net, AF_INET6, SOCK_DGRAM, 0, &sock); if (err < 0) goto error; if (cfg->ipv6_v6only) { err = ip6_sock_set_v6only(sock->sk); if (err < 0) goto error; } if (cfg->bind_ifindex) { err = sock_bindtoindex(sock->sk, cfg->bind_ifindex, true); if (err < 0) goto error; } udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->local_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->local_udp_port; err = kernel_bind(sock, (struct sockaddr_unsized *)&udp6_addr, sizeof(udp6_addr)); if (err < 0) goto error; if (cfg->peer_udp_port) { memset(&udp6_addr, 0, sizeof(udp6_addr)); udp6_addr.sin6_family = AF_INET6; memcpy(&udp6_addr.sin6_addr, &cfg->peer_ip6, sizeof(udp6_addr.sin6_addr)); udp6_addr.sin6_port = cfg->peer_udp_port; err = kernel_connect(sock, (struct sockaddr_unsized *)&udp6_addr, sizeof(udp6_addr), 0); } if (err < 0) goto error; udp_set_no_check6_tx(sock->sk, !cfg->use_udp6_tx_checksums); udp_set_no_check6_rx(sock->sk, !cfg->use_udp6_rx_checksums); *sockp = sock; return 0; error: if (sock) { kernel_sock_shutdown(sock, SHUT_RDWR); sock_release(sock); } *sockp = NULL; return err; } EXPORT_SYMBOL_GPL(udp_sock_create6); void udp_tunnel6_xmit_skb(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct in6_addr *saddr, const struct in6_addr *daddr, __u8 prio, __u8 ttl, __be32 label, __be16 src_port, __be16 dst_port, bool nocheck, u16 ip6cb_flags) { struct udphdr *uh; struct ipv6hdr *ip6h; __skb_push(skb, sizeof(*uh)); skb_reset_transport_header(skb); uh = udp_hdr(skb); uh->dest = dst_port; uh->source = src_port; uh->len = htons(skb->len); skb_dst_set(skb, dst); udp6_set_csum(nocheck, skb, saddr, daddr, skb->len); __skb_push(skb, sizeof(*ip6h)); skb_reset_network_header(skb); ip6h = ipv6_hdr(skb); ip6_flow_hdr(ip6h, prio, label); ip6h->payload_len = htons(skb->len); ip6h->nexthdr = IPPROTO_UDP; ip6h->hop_limit = ttl; ip6h->daddr = *daddr; ip6h->saddr = *saddr; ip6tunnel_xmit(sk, skb, dev, ip6cb_flags); } EXPORT_SYMBOL_GPL(udp_tunnel6_xmit_skb); /** * udp_tunnel6_dst_lookup - perform route lookup on UDP tunnel * @skb: Packet for which lookup is done * @dev: Tunnel device * @net: Network namespace of tunnel device * @sk: Socket which provides route info * @oif: Index of the output interface * @saddr: Memory to store the src ip address * @key: Tunnel information * @sport: UDP source port * @dport: UDP destination port * @dsfield: The traffic class field * @dst_cache: The dst cache to use for lookup * This function performs a route lookup on a UDP tunnel * * It returns a valid dst pointer and stores src address to be used in * tunnel in param saddr on success, else a pointer encoded error code. */ struct dst_entry *udp_tunnel6_dst_lookup(struct sk_buff *skb, struct net_device *dev, struct net *net, struct sock *sk, int oif, struct in6_addr *saddr, const struct ip_tunnel_key *key, __be16 sport, __be16 dport, u8 dsfield, struct dst_cache *dst_cache) { struct dst_entry *dst = NULL; struct flowi6 fl6; #ifdef CONFIG_DST_CACHE if (dst_cache) { dst = dst_cache_get_ip6(dst_cache, saddr); if (dst) return dst; } #endif memset(&fl6, 0, sizeof(fl6)); fl6.flowi6_mark = skb->mark; fl6.flowi6_proto = IPPROTO_UDP; fl6.flowi6_oif = oif; fl6.daddr = key->u.ipv6.dst; fl6.saddr = key->u.ipv6.src; fl6.fl6_sport = sport; fl6.fl6_dport = dport; fl6.flowlabel = ip6_make_flowinfo(dsfield, key->label); dst = ip6_dst_lookup_flow(net, sk, &fl6, NULL); if (IS_ERR(dst)) { netdev_dbg(dev, "no route to %pI6\n", &fl6.daddr); return ERR_PTR(-ENETUNREACH); } if (dst_dev(dst) == dev) { /* is this necessary? */ netdev_dbg(dev, "circular route to %pI6\n", &fl6.daddr); dst_release(dst); return ERR_PTR(-ELOOP); } #ifdef CONFIG_DST_CACHE if (dst_cache) dst_cache_set_ip6(dst_cache, dst, &fl6.saddr); #endif *saddr = fl6.saddr; return dst; } EXPORT_SYMBOL_GPL(udp_tunnel6_dst_lookup); MODULE_DESCRIPTION("IPv6 Foo over UDP tunnel driver"); MODULE_LICENSE("GPL"); |
| 9 9 9 2 8 1 8 9 10 10 1 9 10 8 8 3 7 2 1 1 1 9 9 9 9 9 9 9 8 9 9 9 2 4 3 2 2 7 2 1 10 1 7 2 9 9 8 9 7 2 9 1 12 11 1 12 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 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 | // SPDX-License-Identifier: GPL-2.0 /* * linux/kernel/seccomp.c * * Copyright 2004-2005 Andrea Arcangeli <andrea@cpushare.com> * * Copyright (C) 2012 Google, Inc. * Will Drewry <wad@chromium.org> * * This defines a simple but solid secure-computing facility. * * Mode 1 uses a fixed list of allowed system calls. * Mode 2 allows user-defined system call filters in the form * of Berkeley Packet Filters/Linux Socket Filters. */ #define pr_fmt(fmt) "seccomp: " fmt #include <linux/refcount.h> #include <linux/audit.h> #include <linux/compat.h> #include <linux/coredump.h> #include <linux/kmemleak.h> #include <linux/nospec.h> #include <linux/prctl.h> #include <linux/sched.h> #include <linux/sched/task_stack.h> #include <linux/seccomp.h> #include <linux/slab.h> #include <linux/syscalls.h> #include <linux/sysctl.h> #include <asm/syscall.h> /* Not exposed in headers: strictly internal use only. */ #define SECCOMP_MODE_DEAD (SECCOMP_MODE_FILTER + 1) #ifdef CONFIG_SECCOMP_FILTER #include <linux/file.h> #include <linux/filter.h> #include <linux/pid.h> #include <linux/ptrace.h> #include <linux/capability.h> #include <linux/uaccess.h> #include <linux/anon_inodes.h> #include <linux/lockdep.h> /* * When SECCOMP_IOCTL_NOTIF_ID_VALID was first introduced, it had the * wrong direction flag in the ioctl number. This is the broken one, * which the kernel needs to keep supporting until all userspaces stop * using the wrong command number. */ #define SECCOMP_IOCTL_NOTIF_ID_VALID_WRONG_DIR SECCOMP_IOR(2, __u64) enum notify_state { SECCOMP_NOTIFY_INIT, SECCOMP_NOTIFY_SENT, SECCOMP_NOTIFY_REPLIED, }; struct seccomp_knotif { /* The struct pid of the task whose filter triggered the notification */ struct task_struct *task; /* The "cookie" for this request; this is unique for this filter. */ u64 id; /* * The seccomp data. This pointer is valid the entire time this * notification is active, since it comes from __seccomp_filter which * eclipses the entire lifecycle here. */ const struct seccomp_data *data; /* * Notification states. When SECCOMP_RET_USER_NOTIF is returned, a * struct seccomp_knotif is created and starts out in INIT. Once the * handler reads the notification off of an FD, it transitions to SENT. * If a signal is received the state transitions back to INIT and * another message is sent. When the userspace handler replies, state * transitions to REPLIED. */ enum notify_state state; /* The return values, only valid when in SECCOMP_NOTIFY_REPLIED */ int error; long val; u32 flags; /* * Signals when this has changed states, such as the listener * dying, a new seccomp addfd message, or changing to REPLIED */ struct completion ready; struct list_head list; /* outstanding addfd requests */ struct list_head addfd; }; /** * struct seccomp_kaddfd - container for seccomp_addfd ioctl messages * * @file: A reference to the file to install in the other task * @fd: The fd number to install it at. If the fd number is -1, it means the * installing process should allocate the fd as normal. * @flags: The flags for the new file descriptor. At the moment, only O_CLOEXEC * is allowed. * @ioctl_flags: The flags used for the seccomp_addfd ioctl. * @setfd: whether or not SECCOMP_ADDFD_FLAG_SETFD was set during notify_addfd * @ret: The return value of the installing process. It is set to the fd num * upon success (>= 0). * @completion: Indicates that the installing process has completed fd * installation, or gone away (either due to successful * reply, or signal) * @list: list_head for chaining seccomp_kaddfd together. * */ struct seccomp_kaddfd { struct file *file; int fd; unsigned int flags; __u32 ioctl_flags; union { bool setfd; /* To only be set on reply */ int ret; }; struct completion completion; struct list_head list; }; /** * struct notification - container for seccomp userspace notifications. Since * most seccomp filters will not have notification listeners attached and this * structure is fairly large, we store the notification-specific stuff in a * separate structure. * * @requests: A semaphore that users of this notification can wait on for * changes. Actual reads and writes are still controlled with * filter->notify_lock. * @flags: A set of SECCOMP_USER_NOTIF_FD_* flags. * @next_id: The id of the next request. * @notifications: A list of struct seccomp_knotif elements. */ struct notification { atomic_t requests; u32 flags; u64 next_id; struct list_head notifications; }; #ifdef SECCOMP_ARCH_NATIVE /** * struct action_cache - per-filter cache of seccomp actions per * arch/syscall pair * * @allow_native: A bitmap where each bit represents whether the * filter will always allow the syscall, for the * native architecture. * @allow_compat: A bitmap where each bit represents whether the * filter will always allow the syscall, for the * compat architecture. */ struct action_cache { DECLARE_BITMAP(allow_native, SECCOMP_ARCH_NATIVE_NR); #ifdef SECCOMP_ARCH_COMPAT DECLARE_BITMAP(allow_compat, SECCOMP_ARCH_COMPAT_NR); #endif }; #else struct action_cache { }; static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter, const struct seccomp_data *sd) { return false; } static inline void seccomp_cache_prepare(struct seccomp_filter *sfilter) { } #endif /* SECCOMP_ARCH_NATIVE */ /** * struct seccomp_filter - container for seccomp BPF programs * * @refs: Reference count to manage the object lifetime. * A filter's reference count is incremented for each directly * attached task, once for the dependent filter, and if * requested for the user notifier. When @refs reaches zero, * the filter can be freed. * @users: A filter's @users count is incremented for each directly * attached task (filter installation, fork(), thread_sync), * and once for the dependent filter (tracked in filter->prev). * When it reaches zero it indicates that no direct or indirect * users of that filter exist. No new tasks can get associated with * this filter after reaching 0. The @users count is always smaller * or equal to @refs. Hence, reaching 0 for @users does not mean * the filter can be freed. * @cache: cache of arch/syscall mappings to actions * @log: true if all actions except for SECCOMP_RET_ALLOW should be logged * @wait_killable_recv: Put notifying process in killable state once the * notification is received by the userspace listener. * @prev: points to a previously installed, or inherited, filter * @prog: the BPF program to evaluate * @notif: the struct that holds all notification related information * @notify_lock: A lock for all notification-related accesses. * @wqh: A wait queue for poll if a notifier is in use. * * seccomp_filter objects are organized in a tree linked via the @prev * pointer. For any task, it appears to be a singly-linked list starting * with current->seccomp.filter, the most recently attached or inherited filter. * However, multiple filters may share a @prev node, by way of fork(), which * results in a unidirectional tree existing in memory. This is similar to * how namespaces work. * * seccomp_filter objects should never be modified after being attached * to a task_struct (other than @refs). */ struct seccomp_filter { refcount_t refs; refcount_t users; bool log; bool wait_killable_recv; struct action_cache cache; struct seccomp_filter *prev; struct bpf_prog *prog; struct notification *notif; struct mutex notify_lock; wait_queue_head_t wqh; }; /* Limit any path through the tree to 256KB worth of instructions. */ #define MAX_INSNS_PER_PATH ((1 << 18) / sizeof(struct sock_filter)) /* * Endianness is explicitly ignored and left for BPF program authors to manage * as per the specific architecture. */ static void populate_seccomp_data(struct seccomp_data *sd) { /* * Instead of using current_pt_reg(), we're already doing the work * to safely fetch "current", so just use "task" everywhere below. */ struct task_struct *task = current; struct pt_regs *regs = task_pt_regs(task); unsigned long args[6]; sd->nr = syscall_get_nr(task, regs); sd->arch = syscall_get_arch(task); syscall_get_arguments(task, regs, args); sd->args[0] = args[0]; sd->args[1] = args[1]; sd->args[2] = args[2]; sd->args[3] = args[3]; sd->args[4] = args[4]; sd->args[5] = args[5]; sd->instruction_pointer = KSTK_EIP(task); } /** * seccomp_check_filter - verify seccomp filter code * @filter: filter to verify * @flen: length of filter * * Takes a previously checked filter (by bpf_check_classic) and * redirects all filter code that loads struct sk_buff data * and related data through seccomp_bpf_load. It also * enforces length and alignment checking of those loads. * * Returns 0 if the rule set is legal or -EINVAL if not. */ static int seccomp_check_filter(struct sock_filter *filter, unsigned int flen) { int pc; for (pc = 0; pc < flen; pc++) { struct sock_filter *ftest = &filter[pc]; u16 code = ftest->code; u32 k = ftest->k; switch (code) { case BPF_LD | BPF_W | BPF_ABS: ftest->code = BPF_LDX | BPF_W | BPF_ABS; /* 32-bit aligned and not out of bounds. */ if (k >= sizeof(struct seccomp_data) || k & 3) return -EINVAL; continue; case BPF_LD | BPF_W | BPF_LEN: ftest->code = BPF_LD | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; case BPF_LDX | BPF_W | BPF_LEN: ftest->code = BPF_LDX | BPF_IMM; ftest->k = sizeof(struct seccomp_data); continue; /* Explicitly include allowed calls. */ case BPF_RET | BPF_K: case BPF_RET | BPF_A: case BPF_ALU | BPF_ADD | BPF_K: case BPF_ALU | BPF_ADD | BPF_X: case BPF_ALU | BPF_SUB | BPF_K: case BPF_ALU | BPF_SUB | BPF_X: case BPF_ALU | BPF_MUL | BPF_K: case BPF_ALU | BPF_MUL | BPF_X: case BPF_ALU | BPF_DIV | BPF_K: case BPF_ALU | BPF_DIV | BPF_X: case BPF_ALU | BPF_AND | BPF_K: case BPF_ALU | BPF_AND | BPF_X: case BPF_ALU | BPF_OR | BPF_K: case BPF_ALU | BPF_OR | BPF_X: case BPF_ALU | BPF_XOR | BPF_K: case BPF_ALU | BPF_XOR | BPF_X: case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_LSH | BPF_X: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_X: case BPF_ALU | BPF_NEG: case BPF_LD | BPF_IMM: case BPF_LDX | BPF_IMM: case BPF_MISC | BPF_TAX: case BPF_MISC | BPF_TXA: case BPF_LD | BPF_MEM: case BPF_LDX | BPF_MEM: case BPF_ST: case BPF_STX: case BPF_JMP | BPF_JA: case BPF_JMP | BPF_JEQ | BPF_K: case BPF_JMP | BPF_JEQ | BPF_X: case BPF_JMP | BPF_JGE | BPF_K: case BPF_JMP | BPF_JGE | BPF_X: case BPF_JMP | BPF_JGT | BPF_K: case BPF_JMP | BPF_JGT | BPF_X: case BPF_JMP | BPF_JSET | BPF_K: case BPF_JMP | BPF_JSET | BPF_X: continue; default: return -EINVAL; } } return 0; } #ifdef SECCOMP_ARCH_NATIVE static inline bool seccomp_cache_check_allow_bitmap(const void *bitmap, size_t bitmap_size, int syscall_nr) { if (unlikely(syscall_nr < 0 || syscall_nr >= bitmap_size)) return false; syscall_nr = array_index_nospec(syscall_nr, bitmap_size); return test_bit(syscall_nr, bitmap); } /** * seccomp_cache_check_allow - lookup seccomp cache * @sfilter: The seccomp filter * @sd: The seccomp data to lookup the cache with * * Returns true if the seccomp_data is cached and allowed. */ static inline bool seccomp_cache_check_allow(const struct seccomp_filter *sfilter, const struct seccomp_data *sd) { int syscall_nr = sd->nr; const struct action_cache *cache = &sfilter->cache; #ifndef SECCOMP_ARCH_COMPAT /* A native-only architecture doesn't need to check sd->arch. */ return seccomp_cache_check_allow_bitmap(cache->allow_native, SECCOMP_ARCH_NATIVE_NR, syscall_nr); #else if (likely(sd->arch == SECCOMP_ARCH_NATIVE)) return seccomp_cache_check_allow_bitmap(cache->allow_native, SECCOMP_ARCH_NATIVE_NR, syscall_nr); if (likely(sd->arch == SECCOMP_ARCH_COMPAT)) return seccomp_cache_check_allow_bitmap(cache->allow_compat, SECCOMP_ARCH_COMPAT_NR, syscall_nr); #endif /* SECCOMP_ARCH_COMPAT */ WARN_ON_ONCE(true); return false; } #endif /* SECCOMP_ARCH_NATIVE */ #define ACTION_ONLY(ret) ((s32)((ret) & (SECCOMP_RET_ACTION_FULL))) /** * seccomp_run_filters - evaluates all seccomp filters against @sd * @sd: optional seccomp data to be passed to filters * @match: stores struct seccomp_filter that resulted in the return value, * unless filter returned SECCOMP_RET_ALLOW, in which case it will * be unchanged. * * Returns valid seccomp BPF response codes. */ static u32 seccomp_run_filters(const struct seccomp_data *sd, struct seccomp_filter **match) { u32 ret = SECCOMP_RET_ALLOW; /* Make sure cross-thread synced filter points somewhere sane. */ struct seccomp_filter *f = READ_ONCE(current->seccomp.filter); /* Ensure unexpected behavior doesn't result in failing open. */ if (WARN_ON(f == NULL)) return SECCOMP_RET_KILL_PROCESS; if (seccomp_cache_check_allow(f, sd)) return SECCOMP_RET_ALLOW; /* * All filters in the list are evaluated and the lowest BPF return * value always takes priority (ignoring the DATA). */ for (; f; f = f->prev) { u32 cur_ret = bpf_prog_run_pin_on_cpu(f->prog, sd); if (ACTION_ONLY(cur_ret) < ACTION_ONLY(ret)) { ret = cur_ret; *match = f; } } return ret; } #endif /* CONFIG_SECCOMP_FILTER */ static inline bool seccomp_may_assign_mode(unsigned long seccomp_mode) { assert_spin_locked(¤t->sighand->siglock); if (current->seccomp.mode && current->seccomp.mode != seccomp_mode) return false; return true; } void __weak arch_seccomp_spec_mitigate(struct task_struct *task) { } static inline void seccomp_assign_mode(struct task_struct *task, unsigned long seccomp_mode, unsigned long flags) { assert_spin_locked(&task->sighand->siglock); task->seccomp.mode = seccomp_mode; /* * Make sure SYSCALL_WORK_SECCOMP cannot be set before the mode (and * filter) is set. */ smp_mb__before_atomic(); /* Assume default seccomp processes want spec flaw mitigation. */ if ((flags & SECCOMP_FILTER_FLAG_SPEC_ALLOW) == 0) arch_seccomp_spec_mitigate(task); set_task_syscall_work(task, SECCOMP); } #ifdef CONFIG_SECCOMP_FILTER /* Returns 1 if the parent is an ancestor of the child. */ static int is_ancestor(struct seccomp_filter *parent, struct seccomp_filter *child) { /* NULL is the root ancestor. */ if (parent == NULL) return 1; for (; child; child = child->prev) if (child == parent) return 1; return 0; } /** * seccomp_can_sync_threads: checks if all threads can be synchronized * * Expects sighand and cred_guard_mutex locks to be held. * * Returns 0 on success, -ve on error, or the pid of a thread which was * either not in the correct seccomp mode or did not have an ancestral * seccomp filter. */ static inline pid_t seccomp_can_sync_threads(void) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* Validate all threads being eligible for synchronization. */ caller = current; for_each_thread(caller, thread) { pid_t failed; /* Skip current, since it is initiating the sync. */ if (thread == caller) continue; /* Skip exited threads. */ if (thread->flags & PF_EXITING) continue; if (thread->seccomp.mode == SECCOMP_MODE_DISABLED || (thread->seccomp.mode == SECCOMP_MODE_FILTER && is_ancestor(thread->seccomp.filter, caller->seccomp.filter))) continue; /* Return the first thread that cannot be synchronized. */ failed = task_pid_vnr(thread); /* If the pid cannot be resolved, then return -ESRCH */ if (WARN_ON(failed == 0)) failed = -ESRCH; return failed; } return 0; } static inline void seccomp_filter_free(struct seccomp_filter *filter) { if (filter) { bpf_prog_destroy(filter->prog); kfree(filter); } } static void __seccomp_filter_orphan(struct seccomp_filter *orig) { while (orig && refcount_dec_and_test(&orig->users)) { if (waitqueue_active(&orig->wqh)) wake_up_poll(&orig->wqh, EPOLLHUP); orig = orig->prev; } } static void __put_seccomp_filter(struct seccomp_filter *orig) { /* Clean up single-reference branches iteratively. */ while (orig && refcount_dec_and_test(&orig->refs)) { struct seccomp_filter *freeme = orig; orig = orig->prev; seccomp_filter_free(freeme); } } static void __seccomp_filter_release(struct seccomp_filter *orig) { /* Notify about any unused filters in the task's former filter tree. */ __seccomp_filter_orphan(orig); /* Finally drop all references to the task's former tree. */ __put_seccomp_filter(orig); } /** * seccomp_filter_release - Detach the task from its filter tree, * drop its reference count, and notify * about unused filters * * @tsk: task the filter should be released from. * * This function should only be called when the task is exiting as * it detaches it from its filter tree. PF_EXITING has to be set * for the task. */ void seccomp_filter_release(struct task_struct *tsk) { struct seccomp_filter *orig; if (WARN_ON((tsk->flags & PF_EXITING) == 0)) return; if (READ_ONCE(tsk->seccomp.filter) == NULL) return; spin_lock_irq(&tsk->sighand->siglock); orig = tsk->seccomp.filter; /* Detach task from its filter tree. */ tsk->seccomp.filter = NULL; spin_unlock_irq(&tsk->sighand->siglock); __seccomp_filter_release(orig); } /** * seccomp_sync_threads: sets all threads to use current's filter * * @flags: SECCOMP_FILTER_FLAG_* flags to set during sync. * * Expects sighand and cred_guard_mutex locks to be held, and for * seccomp_can_sync_threads() to have returned success already * without dropping the locks. * */ static inline void seccomp_sync_threads(unsigned long flags) { struct task_struct *thread, *caller; BUG_ON(!mutex_is_locked(¤t->signal->cred_guard_mutex)); assert_spin_locked(¤t->sighand->siglock); /* * Don't touch any of the threads if the process is being killed. * This allows for a lockless check in seccomp_filter_release. */ if (current->signal->flags & SIGNAL_GROUP_EXIT) return; /* Synchronize all threads. */ caller = current; for_each_thread(caller, thread) { /* Skip current, since it needs no changes. */ if (thread == caller) continue; /* * Skip exited threads. seccomp_filter_release could have * been already called for this task. */ if (thread->flags & PF_EXITING) continue; /* Get a task reference for the new leaf node. */ get_seccomp_filter(caller); /* * Drop the task reference to the shared ancestor since * current's path will hold a reference. (This also * allows a put before the assignment.) */ __seccomp_filter_release(thread->seccomp.filter); /* Make our new filter tree visible. */ smp_store_release(&thread->seccomp.filter, caller->seccomp.filter); atomic_set(&thread->seccomp.filter_count, atomic_read(&caller->seccomp.filter_count)); /* * Don't let an unprivileged task work around * the no_new_privs restriction by creating * a thread that sets it up, enters seccomp, * then dies. */ if (task_no_new_privs(caller)) task_set_no_new_privs(thread); /* * Opt the other thread into seccomp if needed. * As threads are considered to be trust-realm * equivalent (see ptrace_may_access), it is safe to * allow one thread to transition the other. */ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED) seccomp_assign_mode(thread, SECCOMP_MODE_FILTER, flags); } } /** * seccomp_prepare_filter: Prepares a seccomp filter for use. * @fprog: BPF program to install * * Returns filter on success or an ERR_PTR on failure. */ static struct seccomp_filter *seccomp_prepare_filter(struct sock_fprog *fprog) { struct seccomp_filter *sfilter; int ret; const bool save_orig = #if defined(CONFIG_CHECKPOINT_RESTORE) || defined(SECCOMP_ARCH_NATIVE) true; #else false; #endif if (fprog->len == 0 || fprog->len > BPF_MAXINSNS) return ERR_PTR(-EINVAL); BUG_ON(INT_MAX / fprog->len < sizeof(struct sock_filter)); /* * Installing a seccomp filter requires that the task has * CAP_SYS_ADMIN in its namespace or be running with no_new_privs. * This avoids scenarios where unprivileged tasks can affect the * behavior of privileged children. */ if (!task_no_new_privs(current) && !ns_capable_noaudit(current_user_ns(), CAP_SYS_ADMIN)) return ERR_PTR(-EACCES); /* Allocate a new seccomp_filter */ sfilter = kzalloc_obj(*sfilter, GFP_KERNEL | __GFP_NOWARN); if (!sfilter) return ERR_PTR(-ENOMEM); mutex_init(&sfilter->notify_lock); ret = bpf_prog_create_from_user(&sfilter->prog, fprog, seccomp_check_filter, save_orig); if (ret < 0) { kfree(sfilter); return ERR_PTR(ret); } refcount_set(&sfilter->refs, 1); refcount_set(&sfilter->users, 1); init_waitqueue_head(&sfilter->wqh); return sfilter; } /** * seccomp_prepare_user_filter - prepares a user-supplied sock_fprog * @user_filter: pointer to the user data containing a sock_fprog. * * Returns 0 on success and non-zero otherwise. */ static struct seccomp_filter * seccomp_prepare_user_filter(const char __user *user_filter) { struct sock_fprog fprog; struct seccomp_filter *filter = ERR_PTR(-EFAULT); #ifdef CONFIG_COMPAT if (in_compat_syscall()) { struct compat_sock_fprog fprog32; if (copy_from_user(&fprog32, user_filter, sizeof(fprog32))) goto out; fprog.len = fprog32.len; fprog.filter = compat_ptr(fprog32.filter); } else /* falls through to the if below. */ #endif if (copy_from_user(&fprog, user_filter, sizeof(fprog))) goto out; filter = seccomp_prepare_filter(&fprog); out: return filter; } #ifdef SECCOMP_ARCH_NATIVE static bool seccomp_uprobe_exception(struct seccomp_data *sd) { #if defined __NR_uretprobe || defined __NR_uprobe #ifdef SECCOMP_ARCH_COMPAT if (sd->arch == SECCOMP_ARCH_NATIVE) #endif { #ifdef __NR_uretprobe if (sd->nr == __NR_uretprobe) return true; #endif #ifdef __NR_uprobe if (sd->nr == __NR_uprobe) return true; #endif } #endif return false; } /** * seccomp_is_const_allow - check if filter is constant allow with given data * @fprog: The BPF programs * @sd: The seccomp data to check against, only syscall number and arch * number are considered constant. */ static bool seccomp_is_const_allow(struct sock_fprog_kern *fprog, struct seccomp_data *sd) { unsigned int reg_value = 0; unsig |